From ed0850e2db467362066a3d94e3ececd17c1756cd Mon Sep 17 00:00:00 2001 From: Michael Steed Date: Tue, 11 Aug 2015 23:37:22 -0600 Subject: [PATCH] Add missing pcre2 files + .gitignore --- Makefile.in | 7 +- pcre2-10.20/.gitignore | 15 + pcre2-10.20/configure | 18234 ++++++++++++++++ pcre2-10.20/doc/html/NON-AUTOTOOLS-BUILD.txt | 391 + pcre2-10.20/doc/html/README.txt | 835 + pcre2-10.20/doc/html/index.html | 264 + pcre2-10.20/doc/html/pcre2-config.html | 102 + pcre2-10.20/doc/html/pcre2.html | 196 + .../doc/html/pcre2_callout_enumerate.html | 62 + pcre2-10.20/doc/html/pcre2_code_free.html | 39 + pcre2-10.20/doc/html/pcre2_compile.html | 91 + .../doc/html/pcre2_compile_context_copy.html | 41 + .../html/pcre2_compile_context_create.html | 42 + .../doc/html/pcre2_compile_context_free.html | 40 + pcre2-10.20/doc/html/pcre2_config.html | 83 + pcre2-10.20/doc/html/pcre2_dfa_match.html | 79 + .../doc/html/pcre2_general_context_copy.html | 42 + .../html/pcre2_general_context_create.html | 44 + .../doc/html/pcre2_general_context_free.html | 39 + .../doc/html/pcre2_get_error_message.html | 48 + pcre2-10.20/doc/html/pcre2_get_mark.html | 43 + .../doc/html/pcre2_get_ovector_count.html | 39 + .../doc/html/pcre2_get_ovector_pointer.html | 40 + pcre2-10.20/doc/html/pcre2_get_startchar.html | 44 + pcre2-10.20/doc/html/pcre2_jit_compile.html | 56 + .../html/pcre2_jit_free_unused_memory.html | 43 + pcre2-10.20/doc/html/pcre2_jit_match.html | 58 + .../doc/html/pcre2_jit_stack_assign.html | 70 + .../doc/html/pcre2_jit_stack_create.html | 50 + .../doc/html/pcre2_jit_stack_free.html | 42 + pcre2-10.20/doc/html/pcre2_maketables.html | 48 + pcre2-10.20/doc/html/pcre2_match.html | 76 + .../doc/html/pcre2_match_context_copy.html | 41 + .../doc/html/pcre2_match_context_create.html | 42 + .../doc/html/pcre2_match_context_free.html | 40 + .../doc/html/pcre2_match_data_create.html | 49 + .../pcre2_match_data_create_from_pattern.html | 50 + .../doc/html/pcre2_match_data_free.html | 40 + pcre2-10.20/doc/html/pcre2_pattern_info.html | 106 + .../doc/html/pcre2_serialize_decode.html | 62 + .../doc/html/pcre2_serialize_encode.html | 61 + .../doc/html/pcre2_serialize_free.html | 40 + .../pcre2_serialize_get_number_of_codes.html | 49 + pcre2-10.20/doc/html/pcre2_set_bsr.html | 42 + pcre2-10.20/doc/html/pcre2_set_callout.html | 43 + .../doc/html/pcre2_set_character_tables.html | 42 + .../pcre2_set_compile_recursion_guard.html | 46 + .../doc/html/pcre2_set_match_limit.html | 40 + pcre2-10.20/doc/html/pcre2_set_newline.html | 50 + .../doc/html/pcre2_set_parens_nest_limit.html | 40 + .../doc/html/pcre2_set_recursion_limit.html | 40 + ...pcre2_set_recursion_memory_management.html | 47 + pcre2-10.20/doc/html/pcre2_substitute.html | 85 + .../doc/html/pcre2_substring_copy_byname.html | 58 + .../html/pcre2_substring_copy_bynumber.html | 57 + .../doc/html/pcre2_substring_free.html | 41 + .../doc/html/pcre2_substring_get_byname.html | 60 + .../html/pcre2_substring_get_bynumber.html | 58 + .../html/pcre2_substring_length_byname.html | 46 + .../html/pcre2_substring_length_bynumber.html | 48 + .../doc/html/pcre2_substring_list_free.html | 40 + .../doc/html/pcre2_substring_list_get.html | 56 + .../html/pcre2_substring_nametable_scan.html | 53 + .../pcre2_substring_number_from_name.html | 50 + pcre2-10.20/doc/html/pcre2api.html | 2892 +++ pcre2-10.20/doc/html/pcre2build.html | 504 + pcre2-10.20/doc/html/pcre2callout.html | 408 + pcre2-10.20/doc/html/pcre2compat.html | 223 + pcre2-10.20/doc/html/pcre2demo.html | 443 + pcre2-10.20/doc/html/pcre2grep.html | 783 + pcre2-10.20/doc/html/pcre2jit.html | 428 + pcre2-10.20/doc/html/pcre2limits.html | 94 + pcre2-10.20/doc/html/pcre2matching.html | 241 + pcre2-10.20/doc/html/pcre2partial.html | 465 + pcre2-10.20/doc/html/pcre2pattern.html | 3332 +++ pcre2-10.20/doc/html/pcre2perform.html | 201 + pcre2-10.20/doc/html/pcre2posix.html | 292 + pcre2-10.20/doc/html/pcre2sample.html | 106 + pcre2-10.20/doc/html/pcre2serialize.html | 184 + pcre2-10.20/doc/html/pcre2stack.html | 207 + pcre2-10.20/doc/html/pcre2syntax.html | 591 + pcre2-10.20/doc/html/pcre2test.html | 1478 ++ pcre2-10.20/doc/html/pcre2unicode.html | 273 + pcre2-10.20/doc/index.html.src | 264 + pcre2-10.20/doc/pcre2-config.1 | 86 + pcre2-10.20/doc/pcre2-config.txt | 81 + pcre2-10.20/doc/pcre2.3 | 192 + pcre2-10.20/doc/pcre2.txt | 5199 +++++ pcre2-10.20/doc/pcre2_callout_enumerate.3 | 50 + pcre2-10.20/doc/pcre2_code_free.3 | 27 + pcre2-10.20/doc/pcre2_compile.3 | 78 + pcre2-10.20/doc/pcre2_compile_context_copy.3 | 29 + .../doc/pcre2_compile_context_create.3 | 30 + pcre2-10.20/doc/pcre2_compile_context_free.3 | 28 + pcre2-10.20/doc/pcre2_config.3 | 69 + pcre2-10.20/doc/pcre2_dfa_match.3 | 72 + pcre2-10.20/doc/pcre2_general_context_copy.3 | 30 + .../doc/pcre2_general_context_create.3 | 32 + pcre2-10.20/doc/pcre2_general_context_free.3 | 27 + pcre2-10.20/doc/pcre2_get_error_message.3 | 36 + pcre2-10.20/doc/pcre2_get_mark.3 | 31 + pcre2-10.20/doc/pcre2_get_ovector_count.3 | 27 + pcre2-10.20/doc/pcre2_get_ovector_pointer.3 | 28 + pcre2-10.20/doc/pcre2_get_startchar.3 | 32 + pcre2-10.20/doc/pcre2_jit_compile.3 | 45 + .../doc/pcre2_jit_free_unused_memory.3 | 31 + pcre2-10.20/doc/pcre2_jit_match.3 | 48 + pcre2-10.20/doc/pcre2_jit_stack_assign.3 | 55 + pcre2-10.20/doc/pcre2_jit_stack_create.3 | 40 + pcre2-10.20/doc/pcre2_jit_stack_free.3 | 31 + pcre2-10.20/doc/pcre2_maketables.3 | 36 + pcre2-10.20/doc/pcre2_match.3 | 67 + pcre2-10.20/doc/pcre2_match_context_copy.3 | 29 + pcre2-10.20/doc/pcre2_match_context_create.3 | 30 + pcre2-10.20/doc/pcre2_match_context_free.3 | 28 + pcre2-10.20/doc/pcre2_match_data_create.3 | 36 + .../pcre2_match_data_create_from_pattern.3 | 37 + pcre2-10.20/doc/pcre2_match_data_free.3 | 28 + pcre2-10.20/doc/pcre2_pattern_info.3 | 93 + pcre2-10.20/doc/pcre2_serialize_decode.3 | 50 + pcre2-10.20/doc/pcre2_serialize_encode.3 | 49 + pcre2-10.20/doc/pcre2_serialize_free.3 | 28 + .../doc/pcre2_serialize_get_number_of_codes.3 | 37 + pcre2-10.20/doc/pcre2_set_bsr.3 | 30 + pcre2-10.20/doc/pcre2_set_callout.3 | 31 + pcre2-10.20/doc/pcre2_set_character_tables.3 | 30 + .../doc/pcre2_set_compile_recursion_guard.3 | 34 + pcre2-10.20/doc/pcre2_set_match_limit.3 | 28 + pcre2-10.20/doc/pcre2_set_newline.3 | 38 + pcre2-10.20/doc/pcre2_set_parens_nest_limit.3 | 28 + pcre2-10.20/doc/pcre2_set_recursion_limit.3 | 28 + .../pcre2_set_recursion_memory_management.3 | 35 + pcre2-10.20/doc/pcre2_substitute.3 | 73 + pcre2-10.20/doc/pcre2_substring_copy_byname.3 | 46 + .../doc/pcre2_substring_copy_bynumber.3 | 44 + pcre2-10.20/doc/pcre2_substring_free.3 | 28 + pcre2-10.20/doc/pcre2_substring_get_byname.3 | 48 + .../doc/pcre2_substring_get_bynumber.3 | 45 + .../doc/pcre2_substring_length_byname.3 | 34 + .../doc/pcre2_substring_length_bynumber.3 | 36 + pcre2-10.20/doc/pcre2_substring_list_free.3 | 27 + pcre2-10.20/doc/pcre2_substring_list_get.3 | 44 + .../doc/pcre2_substring_nametable_scan.3 | 41 + .../doc/pcre2_substring_number_from_name.3 | 38 + pcre2-10.20/doc/pcre2api.3 | 2944 +++ pcre2-10.20/doc/pcre2build.3 | 515 + pcre2-10.20/doc/pcre2callout.3 | 387 + pcre2-10.20/doc/pcre2compat.3 | 190 + pcre2-10.20/doc/pcre2demo.3 | 441 + pcre2-10.20/doc/pcre2grep.1 | 705 + pcre2-10.20/doc/pcre2grep.txt | 769 + pcre2-10.20/doc/pcre2jit.3 | 404 + pcre2-10.20/doc/pcre2limits.3 | 74 + pcre2-10.20/doc/pcre2matching.3 | 213 + pcre2-10.20/doc/pcre2partial.3 | 434 + pcre2-10.20/doc/pcre2pattern.3 | 3366 +++ pcre2-10.20/doc/pcre2perform.3 | 182 + pcre2-10.20/doc/pcre2posix.3 | 268 + pcre2-10.20/doc/pcre2sample.3 | 94 + pcre2-10.20/doc/pcre2serialize.3 | 170 + pcre2-10.20/doc/pcre2stack.3 | 202 + pcre2-10.20/doc/pcre2syntax.3 | 575 + pcre2-10.20/doc/pcre2test.1 | 1456 ++ pcre2-10.20/doc/pcre2test.txt | 1334 ++ pcre2-10.20/doc/pcre2unicode.3 | 257 + pcre2-10.20/src/config.h.in | 294 + 166 files changed, 59374 insertions(+), 2 deletions(-) create mode 100644 pcre2-10.20/.gitignore create mode 100755 pcre2-10.20/configure create mode 100644 pcre2-10.20/doc/html/NON-AUTOTOOLS-BUILD.txt create mode 100644 pcre2-10.20/doc/html/README.txt create mode 100644 pcre2-10.20/doc/html/index.html create mode 100644 pcre2-10.20/doc/html/pcre2-config.html create mode 100644 pcre2-10.20/doc/html/pcre2.html create mode 100644 pcre2-10.20/doc/html/pcre2_callout_enumerate.html create mode 100644 pcre2-10.20/doc/html/pcre2_code_free.html create mode 100644 pcre2-10.20/doc/html/pcre2_compile.html create mode 100644 pcre2-10.20/doc/html/pcre2_compile_context_copy.html create mode 100644 pcre2-10.20/doc/html/pcre2_compile_context_create.html create mode 100644 pcre2-10.20/doc/html/pcre2_compile_context_free.html create mode 100644 pcre2-10.20/doc/html/pcre2_config.html create mode 100644 pcre2-10.20/doc/html/pcre2_dfa_match.html create mode 100644 pcre2-10.20/doc/html/pcre2_general_context_copy.html create mode 100644 pcre2-10.20/doc/html/pcre2_general_context_create.html create mode 100644 pcre2-10.20/doc/html/pcre2_general_context_free.html create mode 100644 pcre2-10.20/doc/html/pcre2_get_error_message.html create mode 100644 pcre2-10.20/doc/html/pcre2_get_mark.html create mode 100644 pcre2-10.20/doc/html/pcre2_get_ovector_count.html create mode 100644 pcre2-10.20/doc/html/pcre2_get_ovector_pointer.html create mode 100644 pcre2-10.20/doc/html/pcre2_get_startchar.html create mode 100644 pcre2-10.20/doc/html/pcre2_jit_compile.html create mode 100644 pcre2-10.20/doc/html/pcre2_jit_free_unused_memory.html create mode 100644 pcre2-10.20/doc/html/pcre2_jit_match.html create mode 100644 pcre2-10.20/doc/html/pcre2_jit_stack_assign.html create mode 100644 pcre2-10.20/doc/html/pcre2_jit_stack_create.html create mode 100644 pcre2-10.20/doc/html/pcre2_jit_stack_free.html create mode 100644 pcre2-10.20/doc/html/pcre2_maketables.html create mode 100644 pcre2-10.20/doc/html/pcre2_match.html create mode 100644 pcre2-10.20/doc/html/pcre2_match_context_copy.html create mode 100644 pcre2-10.20/doc/html/pcre2_match_context_create.html create mode 100644 pcre2-10.20/doc/html/pcre2_match_context_free.html create mode 100644 pcre2-10.20/doc/html/pcre2_match_data_create.html create mode 100644 pcre2-10.20/doc/html/pcre2_match_data_create_from_pattern.html create mode 100644 pcre2-10.20/doc/html/pcre2_match_data_free.html create mode 100644 pcre2-10.20/doc/html/pcre2_pattern_info.html create mode 100644 pcre2-10.20/doc/html/pcre2_serialize_decode.html create mode 100644 pcre2-10.20/doc/html/pcre2_serialize_encode.html create mode 100644 pcre2-10.20/doc/html/pcre2_serialize_free.html create mode 100644 pcre2-10.20/doc/html/pcre2_serialize_get_number_of_codes.html create mode 100644 pcre2-10.20/doc/html/pcre2_set_bsr.html create mode 100644 pcre2-10.20/doc/html/pcre2_set_callout.html create mode 100644 pcre2-10.20/doc/html/pcre2_set_character_tables.html create mode 100644 pcre2-10.20/doc/html/pcre2_set_compile_recursion_guard.html create mode 100644 pcre2-10.20/doc/html/pcre2_set_match_limit.html create mode 100644 pcre2-10.20/doc/html/pcre2_set_newline.html create mode 100644 pcre2-10.20/doc/html/pcre2_set_parens_nest_limit.html create mode 100644 pcre2-10.20/doc/html/pcre2_set_recursion_limit.html create mode 100644 pcre2-10.20/doc/html/pcre2_set_recursion_memory_management.html create mode 100644 pcre2-10.20/doc/html/pcre2_substitute.html create mode 100644 pcre2-10.20/doc/html/pcre2_substring_copy_byname.html create mode 100644 pcre2-10.20/doc/html/pcre2_substring_copy_bynumber.html create mode 100644 pcre2-10.20/doc/html/pcre2_substring_free.html create mode 100644 pcre2-10.20/doc/html/pcre2_substring_get_byname.html create mode 100644 pcre2-10.20/doc/html/pcre2_substring_get_bynumber.html create mode 100644 pcre2-10.20/doc/html/pcre2_substring_length_byname.html create mode 100644 pcre2-10.20/doc/html/pcre2_substring_length_bynumber.html create mode 100644 pcre2-10.20/doc/html/pcre2_substring_list_free.html create mode 100644 pcre2-10.20/doc/html/pcre2_substring_list_get.html create mode 100644 pcre2-10.20/doc/html/pcre2_substring_nametable_scan.html create mode 100644 pcre2-10.20/doc/html/pcre2_substring_number_from_name.html create mode 100644 pcre2-10.20/doc/html/pcre2api.html create mode 100644 pcre2-10.20/doc/html/pcre2build.html create mode 100644 pcre2-10.20/doc/html/pcre2callout.html create mode 100644 pcre2-10.20/doc/html/pcre2compat.html create mode 100644 pcre2-10.20/doc/html/pcre2demo.html create mode 100644 pcre2-10.20/doc/html/pcre2grep.html create mode 100644 pcre2-10.20/doc/html/pcre2jit.html create mode 100644 pcre2-10.20/doc/html/pcre2limits.html create mode 100644 pcre2-10.20/doc/html/pcre2matching.html create mode 100644 pcre2-10.20/doc/html/pcre2partial.html create mode 100644 pcre2-10.20/doc/html/pcre2pattern.html create mode 100644 pcre2-10.20/doc/html/pcre2perform.html create mode 100644 pcre2-10.20/doc/html/pcre2posix.html create mode 100644 pcre2-10.20/doc/html/pcre2sample.html create mode 100644 pcre2-10.20/doc/html/pcre2serialize.html create mode 100644 pcre2-10.20/doc/html/pcre2stack.html create mode 100644 pcre2-10.20/doc/html/pcre2syntax.html create mode 100644 pcre2-10.20/doc/html/pcre2test.html create mode 100644 pcre2-10.20/doc/html/pcre2unicode.html create mode 100644 pcre2-10.20/doc/index.html.src create mode 100644 pcre2-10.20/doc/pcre2-config.1 create mode 100644 pcre2-10.20/doc/pcre2-config.txt create mode 100644 pcre2-10.20/doc/pcre2.3 create mode 100644 pcre2-10.20/doc/pcre2.txt create mode 100644 pcre2-10.20/doc/pcre2_callout_enumerate.3 create mode 100644 pcre2-10.20/doc/pcre2_code_free.3 create mode 100644 pcre2-10.20/doc/pcre2_compile.3 create mode 100644 pcre2-10.20/doc/pcre2_compile_context_copy.3 create mode 100644 pcre2-10.20/doc/pcre2_compile_context_create.3 create mode 100644 pcre2-10.20/doc/pcre2_compile_context_free.3 create mode 100644 pcre2-10.20/doc/pcre2_config.3 create mode 100644 pcre2-10.20/doc/pcre2_dfa_match.3 create mode 100644 pcre2-10.20/doc/pcre2_general_context_copy.3 create mode 100644 pcre2-10.20/doc/pcre2_general_context_create.3 create mode 100644 pcre2-10.20/doc/pcre2_general_context_free.3 create mode 100644 pcre2-10.20/doc/pcre2_get_error_message.3 create mode 100644 pcre2-10.20/doc/pcre2_get_mark.3 create mode 100644 pcre2-10.20/doc/pcre2_get_ovector_count.3 create mode 100644 pcre2-10.20/doc/pcre2_get_ovector_pointer.3 create mode 100644 pcre2-10.20/doc/pcre2_get_startchar.3 create mode 100644 pcre2-10.20/doc/pcre2_jit_compile.3 create mode 100644 pcre2-10.20/doc/pcre2_jit_free_unused_memory.3 create mode 100644 pcre2-10.20/doc/pcre2_jit_match.3 create mode 100644 pcre2-10.20/doc/pcre2_jit_stack_assign.3 create mode 100644 pcre2-10.20/doc/pcre2_jit_stack_create.3 create mode 100644 pcre2-10.20/doc/pcre2_jit_stack_free.3 create mode 100644 pcre2-10.20/doc/pcre2_maketables.3 create mode 100644 pcre2-10.20/doc/pcre2_match.3 create mode 100644 pcre2-10.20/doc/pcre2_match_context_copy.3 create mode 100644 pcre2-10.20/doc/pcre2_match_context_create.3 create mode 100644 pcre2-10.20/doc/pcre2_match_context_free.3 create mode 100644 pcre2-10.20/doc/pcre2_match_data_create.3 create mode 100644 pcre2-10.20/doc/pcre2_match_data_create_from_pattern.3 create mode 100644 pcre2-10.20/doc/pcre2_match_data_free.3 create mode 100644 pcre2-10.20/doc/pcre2_pattern_info.3 create mode 100644 pcre2-10.20/doc/pcre2_serialize_decode.3 create mode 100644 pcre2-10.20/doc/pcre2_serialize_encode.3 create mode 100644 pcre2-10.20/doc/pcre2_serialize_free.3 create mode 100644 pcre2-10.20/doc/pcre2_serialize_get_number_of_codes.3 create mode 100644 pcre2-10.20/doc/pcre2_set_bsr.3 create mode 100644 pcre2-10.20/doc/pcre2_set_callout.3 create mode 100644 pcre2-10.20/doc/pcre2_set_character_tables.3 create mode 100644 pcre2-10.20/doc/pcre2_set_compile_recursion_guard.3 create mode 100644 pcre2-10.20/doc/pcre2_set_match_limit.3 create mode 100644 pcre2-10.20/doc/pcre2_set_newline.3 create mode 100644 pcre2-10.20/doc/pcre2_set_parens_nest_limit.3 create mode 100644 pcre2-10.20/doc/pcre2_set_recursion_limit.3 create mode 100644 pcre2-10.20/doc/pcre2_set_recursion_memory_management.3 create mode 100644 pcre2-10.20/doc/pcre2_substitute.3 create mode 100644 pcre2-10.20/doc/pcre2_substring_copy_byname.3 create mode 100644 pcre2-10.20/doc/pcre2_substring_copy_bynumber.3 create mode 100644 pcre2-10.20/doc/pcre2_substring_free.3 create mode 100644 pcre2-10.20/doc/pcre2_substring_get_byname.3 create mode 100644 pcre2-10.20/doc/pcre2_substring_get_bynumber.3 create mode 100644 pcre2-10.20/doc/pcre2_substring_length_byname.3 create mode 100644 pcre2-10.20/doc/pcre2_substring_length_bynumber.3 create mode 100644 pcre2-10.20/doc/pcre2_substring_list_free.3 create mode 100644 pcre2-10.20/doc/pcre2_substring_list_get.3 create mode 100644 pcre2-10.20/doc/pcre2_substring_nametable_scan.3 create mode 100644 pcre2-10.20/doc/pcre2_substring_number_from_name.3 create mode 100644 pcre2-10.20/doc/pcre2api.3 create mode 100644 pcre2-10.20/doc/pcre2build.3 create mode 100644 pcre2-10.20/doc/pcre2callout.3 create mode 100644 pcre2-10.20/doc/pcre2compat.3 create mode 100644 pcre2-10.20/doc/pcre2demo.3 create mode 100644 pcre2-10.20/doc/pcre2grep.1 create mode 100644 pcre2-10.20/doc/pcre2grep.txt create mode 100644 pcre2-10.20/doc/pcre2jit.3 create mode 100644 pcre2-10.20/doc/pcre2limits.3 create mode 100644 pcre2-10.20/doc/pcre2matching.3 create mode 100644 pcre2-10.20/doc/pcre2partial.3 create mode 100644 pcre2-10.20/doc/pcre2pattern.3 create mode 100644 pcre2-10.20/doc/pcre2perform.3 create mode 100644 pcre2-10.20/doc/pcre2posix.3 create mode 100644 pcre2-10.20/doc/pcre2sample.3 create mode 100644 pcre2-10.20/doc/pcre2serialize.3 create mode 100644 pcre2-10.20/doc/pcre2stack.3 create mode 100644 pcre2-10.20/doc/pcre2syntax.3 create mode 100644 pcre2-10.20/doc/pcre2test.1 create mode 100644 pcre2-10.20/doc/pcre2test.txt create mode 100644 pcre2-10.20/doc/pcre2unicode.3 create mode 100644 pcre2-10.20/src/config.h.in diff --git a/Makefile.in b/Makefile.in index 748dfa85b..e79e9d298 100644 --- a/Makefile.in +++ b/Makefile.in @@ -58,6 +58,7 @@ PCRE2_DIR = pcre2-10.20 PCRE2_CXXFLAGS = -I$(PCRE2_DIR)/src PCRE2_LIBDIR = $(PCRE2_DIR)/.libs PCRE2_LIB = $(PCRE2_LIBDIR)/libpcre2-$(PCRE2_WIDTH).a +PCRE2_H = $(PCRE2_DIR)/src/pcre2.h PCRE2_CONFIG = --disable-pcre2-8 --enable-pcre2-$(PCRE2_WIDTH) --disable-shared # @@ -487,6 +488,8 @@ messages.pot: src/*.cpp src/*.h share/completions/*.fish share/functions/*.fish builtin.o: $(BUILTIN_FILES) +src/builtin_string.cpp: $(PCRE2_H) + # # Generate the internal help functions by making doxygen create @@ -794,8 +797,8 @@ obj: fish: $(FISH_OBJS) obj/fish.o $(PCRE2_LIB) $(CXX) $(CXXFLAGS) $(LDFLAGS_FISH) $(FISH_OBJS) obj/fish.o $(LIBS) -o $@ -$(PCRE2_LIB): - (cd $(PCRE2_DIR); ./configure $(PCRE2_CONFIG); make) +$(PCRE2_H) $(PCRE2_LIB): + (cd $(PCRE2_DIR) && ./configure $(PCRE2_CONFIG) && make) # # Build the fish_tests program. diff --git a/pcre2-10.20/.gitignore b/pcre2-10.20/.gitignore new file mode 100644 index 000000000..0b7a536be --- /dev/null +++ b/pcre2-10.20/.gitignore @@ -0,0 +1,15 @@ +!config.h.in +!configure +!doc/ +.deps +.dirstamp +.libs/ +*.la +*.lo +*.pc +libtool +pcre2_chartables.c +pcre2-config +pcre2test +pcre2.h +stamp-h1 diff --git a/pcre2-10.20/configure b/pcre2-10.20/configure new file mode 100755 index 000000000..15777d450 --- /dev/null +++ b/pcre2-10.20/configure @@ -0,0 +1,18234 @@ +#! /bin/sh +# Guess values for system-dependent variables and create Makefiles. +# Generated by GNU Autoconf 2.69 for PCRE2 10.20. +# +# +# Copyright (C) 1992-1996, 1998-2012 Free Software Foundation, Inc. +# +# +# This configure script is free software; the Free Software Foundation +# gives unlimited permission to copy, distribute and modify it. +## -------------------- ## +## M4sh Initialization. ## +## -------------------- ## + +# Be more Bourne compatible +DUALCASE=1; export DUALCASE # for MKS sh +if test -n "${ZSH_VERSION+set}" && (emulate sh) >/dev/null 2>&1; then : + emulate sh + NULLCMD=: + # Pre-4.2 versions of Zsh do word splitting on ${1+"$@"}, which + # is contrary to our usage. Disable this feature. + alias -g '${1+"$@"}'='"$@"' + setopt NO_GLOB_SUBST +else + case `(set -o) 2>/dev/null` in #( + *posix*) : + set -o posix ;; #( + *) : + ;; +esac +fi + + +as_nl=' +' +export as_nl +# Printing a long string crashes Solaris 7 /usr/bin/printf. +as_echo='\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\' +as_echo=$as_echo$as_echo$as_echo$as_echo$as_echo +as_echo=$as_echo$as_echo$as_echo$as_echo$as_echo$as_echo +# Prefer a ksh shell builtin over an external printf program on Solaris, +# but without wasting forks for bash or zsh. +if test -z "$BASH_VERSION$ZSH_VERSION" \ + && (test "X`print -r -- $as_echo`" = "X$as_echo") 2>/dev/null; then + as_echo='print -r --' + as_echo_n='print -rn --' +elif (test "X`printf %s $as_echo`" = "X$as_echo") 2>/dev/null; then + as_echo='printf %s\n' + as_echo_n='printf %s' +else + if test "X`(/usr/ucb/echo -n -n $as_echo) 2>/dev/null`" = "X-n $as_echo"; then + as_echo_body='eval /usr/ucb/echo -n "$1$as_nl"' + as_echo_n='/usr/ucb/echo -n' + else + as_echo_body='eval expr "X$1" : "X\\(.*\\)"' + as_echo_n_body='eval + arg=$1; + case $arg in #( + *"$as_nl"*) + expr "X$arg" : "X\\(.*\\)$as_nl"; + arg=`expr "X$arg" : ".*$as_nl\\(.*\\)"`;; + esac; + expr "X$arg" : "X\\(.*\\)" | tr -d "$as_nl" + ' + export as_echo_n_body + as_echo_n='sh -c $as_echo_n_body as_echo' + fi + export as_echo_body + as_echo='sh -c $as_echo_body as_echo' +fi + +# The user is always right. +if test "${PATH_SEPARATOR+set}" != set; then + PATH_SEPARATOR=: + (PATH='/bin;/bin'; FPATH=$PATH; sh -c :) >/dev/null 2>&1 && { + (PATH='/bin:/bin'; FPATH=$PATH; sh -c :) >/dev/null 2>&1 || + PATH_SEPARATOR=';' + } +fi + + +# IFS +# We need space, tab and new line, in precisely that order. Quoting is +# there to prevent editors from complaining about space-tab. +# (If _AS_PATH_WALK were called with IFS unset, it would disable word +# splitting by setting IFS to empty value.) +IFS=" "" $as_nl" + +# Find who we are. Look in the path if we contain no directory separator. +as_myself= +case $0 in #(( + *[\\/]* ) as_myself=$0 ;; + *) as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + test -r "$as_dir/$0" && as_myself=$as_dir/$0 && break + done +IFS=$as_save_IFS + + ;; +esac +# We did not find ourselves, most probably we were run as `sh COMMAND' +# in which case we are not to be found in the path. +if test "x$as_myself" = x; then + as_myself=$0 +fi +if test ! -f "$as_myself"; then + $as_echo "$as_myself: error: cannot find myself; rerun with an absolute file name" >&2 + exit 1 +fi + +# Unset variables that we do not need and which cause bugs (e.g. in +# pre-3.0 UWIN ksh). But do not cause bugs in bash 2.01; the "|| exit 1" +# suppresses any "Segmentation fault" message there. '((' could +# trigger a bug in pdksh 5.2.14. +for as_var in BASH_ENV ENV MAIL MAILPATH +do eval test x\${$as_var+set} = xset \ + && ( (unset $as_var) || exit 1) >/dev/null 2>&1 && unset $as_var || : +done +PS1='$ ' +PS2='> ' +PS4='+ ' + +# NLS nuisances. +LC_ALL=C +export LC_ALL +LANGUAGE=C +export LANGUAGE + +# CDPATH. +(unset CDPATH) >/dev/null 2>&1 && unset CDPATH + +# Use a proper internal environment variable to ensure we don't fall + # into an infinite loop, continuously re-executing ourselves. + if test x"${_as_can_reexec}" != xno && test "x$CONFIG_SHELL" != x; then + _as_can_reexec=no; export _as_can_reexec; + # We cannot yet assume a decent shell, so we have to provide a +# neutralization value for shells without unset; and this also +# works around shells that cannot unset nonexistent variables. +# Preserve -v and -x to the replacement shell. +BASH_ENV=/dev/null +ENV=/dev/null +(unset BASH_ENV) >/dev/null 2>&1 && unset BASH_ENV ENV +case $- in # (((( + *v*x* | *x*v* ) as_opts=-vx ;; + *v* ) as_opts=-v ;; + *x* ) as_opts=-x ;; + * ) as_opts= ;; +esac +exec $CONFIG_SHELL $as_opts "$as_myself" ${1+"$@"} +# Admittedly, this is quite paranoid, since all the known shells bail +# out after a failed `exec'. +$as_echo "$0: could not re-execute with $CONFIG_SHELL" >&2 +as_fn_exit 255 + fi + # We don't want this to propagate to other subprocesses. + { _as_can_reexec=; unset _as_can_reexec;} +if test "x$CONFIG_SHELL" = x; then + as_bourne_compatible="if test -n \"\${ZSH_VERSION+set}\" && (emulate sh) >/dev/null 2>&1; then : + emulate sh + NULLCMD=: + # Pre-4.2 versions of Zsh do word splitting on \${1+\"\$@\"}, which + # is contrary to our usage. Disable this feature. + alias -g '\${1+\"\$@\"}'='\"\$@\"' + setopt NO_GLOB_SUBST +else + case \`(set -o) 2>/dev/null\` in #( + *posix*) : + set -o posix ;; #( + *) : + ;; +esac +fi +" + as_required="as_fn_return () { (exit \$1); } +as_fn_success () { as_fn_return 0; } +as_fn_failure () { as_fn_return 1; } +as_fn_ret_success () { return 0; } +as_fn_ret_failure () { return 1; } + +exitcode=0 +as_fn_success || { exitcode=1; echo as_fn_success failed.; } +as_fn_failure && { exitcode=1; echo as_fn_failure succeeded.; } +as_fn_ret_success || { exitcode=1; echo as_fn_ret_success failed.; } +as_fn_ret_failure && { exitcode=1; echo as_fn_ret_failure succeeded.; } +if ( set x; as_fn_ret_success y && test x = \"\$1\" ); then : + +else + exitcode=1; echo positional parameters were not saved. +fi +test x\$exitcode = x0 || exit 1 +test -x / || exit 1" + as_suggested=" as_lineno_1=";as_suggested=$as_suggested$LINENO;as_suggested=$as_suggested" as_lineno_1a=\$LINENO + as_lineno_2=";as_suggested=$as_suggested$LINENO;as_suggested=$as_suggested" as_lineno_2a=\$LINENO + eval 'test \"x\$as_lineno_1'\$as_run'\" != \"x\$as_lineno_2'\$as_run'\" && + test \"x\`expr \$as_lineno_1'\$as_run' + 1\`\" = \"x\$as_lineno_2'\$as_run'\"' || exit 1 +test \$(( 1 + 1 )) = 2 || exit 1 + + test -n \"\${ZSH_VERSION+set}\${BASH_VERSION+set}\" || ( + ECHO='\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\' + ECHO=\$ECHO\$ECHO\$ECHO\$ECHO\$ECHO + ECHO=\$ECHO\$ECHO\$ECHO\$ECHO\$ECHO\$ECHO + PATH=/empty FPATH=/empty; export PATH FPATH + test \"X\`printf %s \$ECHO\`\" = \"X\$ECHO\" \\ + || test \"X\`print -r -- \$ECHO\`\" = \"X\$ECHO\" ) || exit 1" + if (eval "$as_required") 2>/dev/null; then : + as_have_required=yes +else + as_have_required=no +fi + if test x$as_have_required = xyes && (eval "$as_suggested") 2>/dev/null; then : + +else + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +as_found=false +for as_dir in /bin$PATH_SEPARATOR/usr/bin$PATH_SEPARATOR$PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + as_found=: + case $as_dir in #( + /*) + for as_base in sh bash ksh sh5; do + # Try only shells that exist, to save several forks. + as_shell=$as_dir/$as_base + if { test -f "$as_shell" || test -f "$as_shell.exe"; } && + { $as_echo "$as_bourne_compatible""$as_required" | as_run=a "$as_shell"; } 2>/dev/null; then : + CONFIG_SHELL=$as_shell as_have_required=yes + if { $as_echo "$as_bourne_compatible""$as_suggested" | as_run=a "$as_shell"; } 2>/dev/null; then : + break 2 +fi +fi + done;; + esac + as_found=false +done +$as_found || { if { test -f "$SHELL" || test -f "$SHELL.exe"; } && + { $as_echo "$as_bourne_compatible""$as_required" | as_run=a "$SHELL"; } 2>/dev/null; then : + CONFIG_SHELL=$SHELL as_have_required=yes +fi; } +IFS=$as_save_IFS + + + if test "x$CONFIG_SHELL" != x; then : + export CONFIG_SHELL + # We cannot yet assume a decent shell, so we have to provide a +# neutralization value for shells without unset; and this also +# works around shells that cannot unset nonexistent variables. +# Preserve -v and -x to the replacement shell. +BASH_ENV=/dev/null +ENV=/dev/null +(unset BASH_ENV) >/dev/null 2>&1 && unset BASH_ENV ENV +case $- in # (((( + *v*x* | *x*v* ) as_opts=-vx ;; + *v* ) as_opts=-v ;; + *x* ) as_opts=-x ;; + * ) as_opts= ;; +esac +exec $CONFIG_SHELL $as_opts "$as_myself" ${1+"$@"} +# Admittedly, this is quite paranoid, since all the known shells bail +# out after a failed `exec'. +$as_echo "$0: could not re-execute with $CONFIG_SHELL" >&2 +exit 255 +fi + + if test x$as_have_required = xno; then : + $as_echo "$0: This script requires a shell more modern than all" + $as_echo "$0: the shells that I found on your system." + if test x${ZSH_VERSION+set} = xset ; then + $as_echo "$0: In particular, zsh $ZSH_VERSION has bugs and should" + $as_echo "$0: be upgraded to zsh 4.3.4 or later." + else + $as_echo "$0: Please tell bug-autoconf@gnu.org about your system, +$0: including any error possibly output before this +$0: message. Then install a modern shell, or manually run +$0: the script under such a shell if you do have one." + fi + exit 1 +fi +fi +fi +SHELL=${CONFIG_SHELL-/bin/sh} +export SHELL +# Unset more variables known to interfere with behavior of common tools. +CLICOLOR_FORCE= GREP_OPTIONS= +unset CLICOLOR_FORCE GREP_OPTIONS + +## --------------------- ## +## M4sh Shell Functions. ## +## --------------------- ## +# as_fn_unset VAR +# --------------- +# Portably unset VAR. +as_fn_unset () +{ + { eval $1=; unset $1;} +} +as_unset=as_fn_unset + +# as_fn_set_status STATUS +# ----------------------- +# Set $? to STATUS, without forking. +as_fn_set_status () +{ + return $1 +} # as_fn_set_status + +# as_fn_exit STATUS +# ----------------- +# Exit the shell with STATUS, even in a "trap 0" or "set -e" context. +as_fn_exit () +{ + set +e + as_fn_set_status $1 + exit $1 +} # as_fn_exit + +# as_fn_mkdir_p +# ------------- +# Create "$as_dir" as a directory, including parents if necessary. +as_fn_mkdir_p () +{ + + case $as_dir in #( + -*) as_dir=./$as_dir;; + esac + test -d "$as_dir" || eval $as_mkdir_p || { + as_dirs= + while :; do + case $as_dir in #( + *\'*) as_qdir=`$as_echo "$as_dir" | sed "s/'/'\\\\\\\\''/g"`;; #'( + *) as_qdir=$as_dir;; + esac + as_dirs="'$as_qdir' $as_dirs" + as_dir=`$as_dirname -- "$as_dir" || +$as_expr X"$as_dir" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X"$as_dir" : 'X\(//\)[^/]' \| \ + X"$as_dir" : 'X\(//\)$' \| \ + X"$as_dir" : 'X\(/\)' \| . 2>/dev/null || +$as_echo X"$as_dir" | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ + s//\1/ + q + } + /^X\(\/\/\)[^/].*/{ + s//\1/ + q + } + /^X\(\/\/\)$/{ + s//\1/ + q + } + /^X\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'` + test -d "$as_dir" && break + done + test -z "$as_dirs" || eval "mkdir $as_dirs" + } || test -d "$as_dir" || as_fn_error $? "cannot create directory $as_dir" + + +} # as_fn_mkdir_p + +# as_fn_executable_p FILE +# ----------------------- +# Test if FILE is an executable regular file. +as_fn_executable_p () +{ + test -f "$1" && test -x "$1" +} # as_fn_executable_p +# as_fn_append VAR VALUE +# ---------------------- +# Append the text in VALUE to the end of the definition contained in VAR. Take +# advantage of any shell optimizations that allow amortized linear growth over +# repeated appends, instead of the typical quadratic growth present in naive +# implementations. +if (eval "as_var=1; as_var+=2; test x\$as_var = x12") 2>/dev/null; then : + eval 'as_fn_append () + { + eval $1+=\$2 + }' +else + as_fn_append () + { + eval $1=\$$1\$2 + } +fi # as_fn_append + +# as_fn_arith ARG... +# ------------------ +# Perform arithmetic evaluation on the ARGs, and store the result in the +# global $as_val. Take advantage of shells that can avoid forks. The arguments +# must be portable across $(()) and expr. +if (eval "test \$(( 1 + 1 )) = 2") 2>/dev/null; then : + eval 'as_fn_arith () + { + as_val=$(( $* )) + }' +else + as_fn_arith () + { + as_val=`expr "$@" || test $? -eq 1` + } +fi # as_fn_arith + + +# as_fn_error STATUS ERROR [LINENO LOG_FD] +# ---------------------------------------- +# Output "`basename $0`: error: ERROR" to stderr. If LINENO and LOG_FD are +# provided, also output the error to LOG_FD, referencing LINENO. Then exit the +# script with STATUS, using 1 if that was 0. +as_fn_error () +{ + as_status=$1; test $as_status -eq 0 && as_status=1 + if test "$4"; then + as_lineno=${as_lineno-"$3"} as_lineno_stack=as_lineno_stack=$as_lineno_stack + $as_echo "$as_me:${as_lineno-$LINENO}: error: $2" >&$4 + fi + $as_echo "$as_me: error: $2" >&2 + as_fn_exit $as_status +} # as_fn_error + +if expr a : '\(a\)' >/dev/null 2>&1 && + test "X`expr 00001 : '.*\(...\)'`" = X001; then + as_expr=expr +else + as_expr=false +fi + +if (basename -- /) >/dev/null 2>&1 && test "X`basename -- / 2>&1`" = "X/"; then + as_basename=basename +else + as_basename=false +fi + +if (as_dir=`dirname -- /` && test "X$as_dir" = X/) >/dev/null 2>&1; then + as_dirname=dirname +else + as_dirname=false +fi + +as_me=`$as_basename -- "$0" || +$as_expr X/"$0" : '.*/\([^/][^/]*\)/*$' \| \ + X"$0" : 'X\(//\)$' \| \ + X"$0" : 'X\(/\)' \| . 2>/dev/null || +$as_echo X/"$0" | + sed '/^.*\/\([^/][^/]*\)\/*$/{ + s//\1/ + q + } + /^X\/\(\/\/\)$/{ + s//\1/ + q + } + /^X\/\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'` + +# Avoid depending upon Character Ranges. +as_cr_letters='abcdefghijklmnopqrstuvwxyz' +as_cr_LETTERS='ABCDEFGHIJKLMNOPQRSTUVWXYZ' +as_cr_Letters=$as_cr_letters$as_cr_LETTERS +as_cr_digits='0123456789' +as_cr_alnum=$as_cr_Letters$as_cr_digits + + + as_lineno_1=$LINENO as_lineno_1a=$LINENO + as_lineno_2=$LINENO as_lineno_2a=$LINENO + eval 'test "x$as_lineno_1'$as_run'" != "x$as_lineno_2'$as_run'" && + test "x`expr $as_lineno_1'$as_run' + 1`" = "x$as_lineno_2'$as_run'"' || { + # Blame Lee E. McMahon (1931-1989) for sed's syntax. :-) + sed -n ' + p + /[$]LINENO/= + ' <$as_myself | + sed ' + s/[$]LINENO.*/&-/ + t lineno + b + :lineno + N + :loop + s/[$]LINENO\([^'$as_cr_alnum'_].*\n\)\(.*\)/\2\1\2/ + t loop + s/-\n.*// + ' >$as_me.lineno && + chmod +x "$as_me.lineno" || + { $as_echo "$as_me: error: cannot create $as_me.lineno; rerun with a POSIX shell" >&2; as_fn_exit 1; } + + # If we had to re-execute with $CONFIG_SHELL, we're ensured to have + # already done that, so ensure we don't try to do so again and fall + # in an infinite loop. This has already happened in practice. + _as_can_reexec=no; export _as_can_reexec + # Don't try to exec as it changes $[0], causing all sort of problems + # (the dirname of $[0] is not the place where we might find the + # original and so on. Autoconf is especially sensitive to this). + . "./$as_me.lineno" + # Exit status is that of the last command. + exit +} + +ECHO_C= ECHO_N= ECHO_T= +case `echo -n x` in #((((( +-n*) + case `echo 'xy\c'` in + *c*) ECHO_T=' ';; # ECHO_T is single tab character. + xy) ECHO_C='\c';; + *) echo `echo ksh88 bug on AIX 6.1` > /dev/null + ECHO_T=' ';; + esac;; +*) + ECHO_N='-n';; +esac + +rm -f conf$$ conf$$.exe conf$$.file +if test -d conf$$.dir; then + rm -f conf$$.dir/conf$$.file +else + rm -f conf$$.dir + mkdir conf$$.dir 2>/dev/null +fi +if (echo >conf$$.file) 2>/dev/null; then + if ln -s conf$$.file conf$$ 2>/dev/null; then + as_ln_s='ln -s' + # ... but there are two gotchas: + # 1) On MSYS, both `ln -s file dir' and `ln file dir' fail. + # 2) DJGPP < 2.04 has no symlinks; `ln -s' creates a wrapper executable. + # In both cases, we have to default to `cp -pR'. + ln -s conf$$.file conf$$.dir 2>/dev/null && test ! -f conf$$.exe || + as_ln_s='cp -pR' + elif ln conf$$.file conf$$ 2>/dev/null; then + as_ln_s=ln + else + as_ln_s='cp -pR' + fi +else + as_ln_s='cp -pR' +fi +rm -f conf$$ conf$$.exe conf$$.dir/conf$$.file conf$$.file +rmdir conf$$.dir 2>/dev/null + +if mkdir -p . 2>/dev/null; then + as_mkdir_p='mkdir -p "$as_dir"' +else + test -d ./-p && rmdir ./-p + as_mkdir_p=false +fi + +as_test_x='test -x' +as_executable_p=as_fn_executable_p + +# Sed expression to map a string onto a valid CPP name. +as_tr_cpp="eval sed 'y%*$as_cr_letters%P$as_cr_LETTERS%;s%[^_$as_cr_alnum]%_%g'" + +# Sed expression to map a string onto a valid variable name. +as_tr_sh="eval sed 'y%*+%pp%;s%[^_$as_cr_alnum]%_%g'" + +SHELL=${CONFIG_SHELL-/bin/sh} + + +test -n "$DJDIR" || exec 7<&0 &1 + +# Name of the host. +# hostname on some systems (SVR3.2, old GNU/Linux) returns a bogus exit status, +# so uname gets run too. +ac_hostname=`(hostname || uname -n) 2>/dev/null | sed 1q` + +# +# Initializations. +# +ac_default_prefix=/usr/local +ac_clean_files= +ac_config_libobj_dir=. +LIBOBJS= +cross_compiling=no +subdirs= +MFLAGS= +MAKEFLAGS= + +# Identity of this package. +PACKAGE_NAME='PCRE2' +PACKAGE_TARNAME='pcre2' +PACKAGE_VERSION='10.20' +PACKAGE_STRING='PCRE2 10.20' +PACKAGE_BUGREPORT='' +PACKAGE_URL='' + +ac_unique_file="src/pcre2.h.in" +# Factoring default headers for most tests. +ac_includes_default="\ +#include +#ifdef HAVE_SYS_TYPES_H +# include +#endif +#ifdef HAVE_SYS_STAT_H +# include +#endif +#ifdef STDC_HEADERS +# include +# include +#else +# ifdef HAVE_STDLIB_H +# include +# endif +#endif +#ifdef HAVE_STRING_H +# if !defined STDC_HEADERS && defined HAVE_MEMORY_H +# include +# endif +# include +#endif +#ifdef HAVE_STRINGS_H +# include +#endif +#ifdef HAVE_INTTYPES_H +# include +#endif +#ifdef HAVE_STDINT_H +# include +#endif +#ifdef HAVE_UNISTD_H +# include +#endif" + +ac_subst_vars='am__EXEEXT_FALSE +am__EXEEXT_TRUE +LTLIBOBJS +LIBOBJS +WITH_GCOV_FALSE +WITH_GCOV_TRUE +GCOV_LIBS +GCOV_CXXFLAGS +GCOV_CFLAGS +GENHTML +LCOV +SHTOOL +VALGRIND_LIBS +VALGRIND_CFLAGS +PKG_CONFIG_LIBDIR +PKG_CONFIG_PATH +PKG_CONFIG +LIBBZ2 +LIBZ +DISTCHECK_CONFIGURE_FLAGS +EXTRA_LIBPCRE2_POSIX_LDFLAGS +EXTRA_LIBPCRE2_32_LDFLAGS +EXTRA_LIBPCRE2_16_LDFLAGS +EXTRA_LIBPCRE2_8_LDFLAGS +PTHREAD_CFLAGS +PTHREAD_LIBS +PTHREAD_CC +ax_pthread_config +PCRE2_STATIC_CFLAG +LIBREADLINE +WITH_VALGRIND_FALSE +WITH_VALGRIND_TRUE +WITH_UNICODE_FALSE +WITH_UNICODE_TRUE +WITH_JIT_FALSE +WITH_JIT_TRUE +WITH_REBUILD_CHARTABLES_FALSE +WITH_REBUILD_CHARTABLES_TRUE +WITH_DEBUG_FALSE +WITH_DEBUG_TRUE +WITH_PCRE2_32_FALSE +WITH_PCRE2_32_TRUE +WITH_PCRE2_16_FALSE +WITH_PCRE2_16_TRUE +WITH_PCRE2_8_FALSE +WITH_PCRE2_8_TRUE +enable_pcre2_32 +enable_pcre2_16 +enable_pcre2_8 +PCRE2_DATE +PCRE2_PRERELEASE +PCRE2_MINOR +PCRE2_MAJOR +HAVE_VISIBILITY +VISIBILITY_CXXFLAGS +VISIBILITY_CFLAGS +LT_SYS_LIBRARY_PATH +OTOOL64 +OTOOL +LIPO +NMEDIT +DSYMUTIL +MANIFEST_TOOL +RANLIB +LN_S +NM +ac_ct_DUMPBIN +DUMPBIN +LD +FGREP +SED +LIBTOOL +OBJDUMP +DLLTOOL +AS +host_os +host_vendor +host_cpu +host +build_os +build_vendor +build_cpu +build +EGREP +GREP +CPP +am__fastdepCC_FALSE +am__fastdepCC_TRUE +CCDEPMODE +am__nodep +AMDEPBACKSLASH +AMDEP_FALSE +AMDEP_TRUE +am__quote +am__include +DEPDIR +OBJEXT +EXEEXT +ac_ct_CC +CPPFLAGS +LDFLAGS +CFLAGS +CC +ac_ct_AR +AR +AM_BACKSLASH +AM_DEFAULT_VERBOSITY +AM_DEFAULT_V +AM_V +am__untar +am__tar +AMTAR +am__leading_dot +SET_MAKE +AWK +mkdir_p +MKDIR_P +INSTALL_STRIP_PROGRAM +STRIP +install_sh +MAKEINFO +AUTOHEADER +AUTOMAKE +AUTOCONF +ACLOCAL +VERSION +PACKAGE +CYGPATH_W +am__isrc +INSTALL_DATA +INSTALL_SCRIPT +INSTALL_PROGRAM +target_alias +host_alias +build_alias +LIBS +ECHO_T +ECHO_N +ECHO_C +DEFS +mandir +localedir +libdir +psdir +pdfdir +dvidir +htmldir +infodir +docdir +oldincludedir +includedir +localstatedir +sharedstatedir +sysconfdir +datadir +datarootdir +libexecdir +sbindir +bindir +program_transform_name +prefix +exec_prefix +PACKAGE_URL +PACKAGE_BUGREPORT +PACKAGE_STRING +PACKAGE_VERSION +PACKAGE_TARNAME +PACKAGE_NAME +PATH_SEPARATOR +SHELL' +ac_subst_files='' +ac_user_opts=' +enable_option_checking +enable_silent_rules +enable_dependency_tracking +enable_shared +enable_static +with_pic +enable_fast_install +with_aix_soname +with_gnu_ld +with_sysroot +enable_libtool_lock +enable_pcre8 +enable_pcre16 +enable_pcre32 +enable_pcre2_8 +enable_pcre2_16 +enable_pcre2_32 +enable_debug +enable_jit +enable_pcre2grep_jit +enable_rebuild_chartables +enable_unicode +enable_newline_is_cr +enable_newline_is_lf +enable_newline_is_crlf +enable_newline_is_anycrlf +enable_newline_is_any +enable_bsr_anycrlf +enable_ebcdic +enable_ebcdic_nl25 +enable_stack_for_recursion +enable_pcre2grep_libz +enable_pcre2grep_libbz2 +with_pcre2grep_bufsize +enable_pcre2test_libedit +enable_pcre2test_libreadline +with_link_size +with_parens_nest_limit +with_match_limit +with_match_limit_recursion +enable_valgrind +enable_coverage +' + ac_precious_vars='build_alias +host_alias +target_alias +CC +CFLAGS +LDFLAGS +LIBS +CPPFLAGS +CPP +LT_SYS_LIBRARY_PATH +PKG_CONFIG +PKG_CONFIG_PATH +PKG_CONFIG_LIBDIR +VALGRIND_CFLAGS +VALGRIND_LIBS +LCOV +GENHTML' + + +# Initialize some variables set by options. +ac_init_help= +ac_init_version=false +ac_unrecognized_opts= +ac_unrecognized_sep= +# The variables have the same names as the options, with +# dashes changed to underlines. +cache_file=/dev/null +exec_prefix=NONE +no_create= +no_recursion= +prefix=NONE +program_prefix=NONE +program_suffix=NONE +program_transform_name=s,x,x, +silent= +site= +srcdir= +verbose= +x_includes=NONE +x_libraries=NONE + +# Installation directory options. +# These are left unexpanded so users can "make install exec_prefix=/foo" +# and all the variables that are supposed to be based on exec_prefix +# by default will actually change. +# Use braces instead of parens because sh, perl, etc. also accept them. +# (The list follows the same order as the GNU Coding Standards.) +bindir='${exec_prefix}/bin' +sbindir='${exec_prefix}/sbin' +libexecdir='${exec_prefix}/libexec' +datarootdir='${prefix}/share' +datadir='${datarootdir}' +sysconfdir='${prefix}/etc' +sharedstatedir='${prefix}/com' +localstatedir='${prefix}/var' +includedir='${prefix}/include' +oldincludedir='/usr/include' +docdir='${datarootdir}/doc/${PACKAGE_TARNAME}' +infodir='${datarootdir}/info' +htmldir='${docdir}' +dvidir='${docdir}' +pdfdir='${docdir}' +psdir='${docdir}' +libdir='${exec_prefix}/lib' +localedir='${datarootdir}/locale' +mandir='${datarootdir}/man' + +ac_prev= +ac_dashdash= +for ac_option +do + # If the previous option needs an argument, assign it. + if test -n "$ac_prev"; then + eval $ac_prev=\$ac_option + ac_prev= + continue + fi + + case $ac_option in + *=?*) ac_optarg=`expr "X$ac_option" : '[^=]*=\(.*\)'` ;; + *=) ac_optarg= ;; + *) ac_optarg=yes ;; + esac + + # Accept the important Cygnus configure options, so we can diagnose typos. + + case $ac_dashdash$ac_option in + --) + ac_dashdash=yes ;; + + -bindir | --bindir | --bindi | --bind | --bin | --bi) + ac_prev=bindir ;; + -bindir=* | --bindir=* | --bindi=* | --bind=* | --bin=* | --bi=*) + bindir=$ac_optarg ;; + + -build | --build | --buil | --bui | --bu) + ac_prev=build_alias ;; + -build=* | --build=* | --buil=* | --bui=* | --bu=*) + build_alias=$ac_optarg ;; + + -cache-file | --cache-file | --cache-fil | --cache-fi \ + | --cache-f | --cache- | --cache | --cach | --cac | --ca | --c) + ac_prev=cache_file ;; + -cache-file=* | --cache-file=* | --cache-fil=* | --cache-fi=* \ + | --cache-f=* | --cache-=* | --cache=* | --cach=* | --cac=* | --ca=* | --c=*) + cache_file=$ac_optarg ;; + + --config-cache | -C) + cache_file=config.cache ;; + + -datadir | --datadir | --datadi | --datad) + ac_prev=datadir ;; + -datadir=* | --datadir=* | --datadi=* | --datad=*) + datadir=$ac_optarg ;; + + -datarootdir | --datarootdir | --datarootdi | --datarootd | --dataroot \ + | --dataroo | --dataro | --datar) + ac_prev=datarootdir ;; + -datarootdir=* | --datarootdir=* | --datarootdi=* | --datarootd=* \ + | --dataroot=* | --dataroo=* | --dataro=* | --datar=*) + datarootdir=$ac_optarg ;; + + -disable-* | --disable-*) + ac_useropt=`expr "x$ac_option" : 'x-*disable-\(.*\)'` + # Reject names that are not valid shell variable names. + expr "x$ac_useropt" : ".*[^-+._$as_cr_alnum]" >/dev/null && + as_fn_error $? "invalid feature name: $ac_useropt" + ac_useropt_orig=$ac_useropt + ac_useropt=`$as_echo "$ac_useropt" | sed 's/[-+.]/_/g'` + case $ac_user_opts in + *" +"enable_$ac_useropt" +"*) ;; + *) ac_unrecognized_opts="$ac_unrecognized_opts$ac_unrecognized_sep--disable-$ac_useropt_orig" + ac_unrecognized_sep=', ';; + esac + eval enable_$ac_useropt=no ;; + + -docdir | --docdir | --docdi | --doc | --do) + ac_prev=docdir ;; + -docdir=* | --docdir=* | --docdi=* | --doc=* | --do=*) + docdir=$ac_optarg ;; + + -dvidir | --dvidir | --dvidi | --dvid | --dvi | --dv) + ac_prev=dvidir ;; + -dvidir=* | --dvidir=* | --dvidi=* | --dvid=* | --dvi=* | --dv=*) + dvidir=$ac_optarg ;; + + -enable-* | --enable-*) + ac_useropt=`expr "x$ac_option" : 'x-*enable-\([^=]*\)'` + # Reject names that are not valid shell variable names. + expr "x$ac_useropt" : ".*[^-+._$as_cr_alnum]" >/dev/null && + as_fn_error $? "invalid feature name: $ac_useropt" + ac_useropt_orig=$ac_useropt + ac_useropt=`$as_echo "$ac_useropt" | sed 's/[-+.]/_/g'` + case $ac_user_opts in + *" +"enable_$ac_useropt" +"*) ;; + *) ac_unrecognized_opts="$ac_unrecognized_opts$ac_unrecognized_sep--enable-$ac_useropt_orig" + ac_unrecognized_sep=', ';; + esac + eval enable_$ac_useropt=\$ac_optarg ;; + + -exec-prefix | --exec_prefix | --exec-prefix | --exec-prefi \ + | --exec-pref | --exec-pre | --exec-pr | --exec-p | --exec- \ + | --exec | --exe | --ex) + ac_prev=exec_prefix ;; + -exec-prefix=* | --exec_prefix=* | --exec-prefix=* | --exec-prefi=* \ + | --exec-pref=* | --exec-pre=* | --exec-pr=* | --exec-p=* | --exec-=* \ + | --exec=* | --exe=* | --ex=*) + exec_prefix=$ac_optarg ;; + + -gas | --gas | --ga | --g) + # Obsolete; use --with-gas. + with_gas=yes ;; + + -help | --help | --hel | --he | -h) + ac_init_help=long ;; + -help=r* | --help=r* | --hel=r* | --he=r* | -hr*) + ac_init_help=recursive ;; + -help=s* | --help=s* | --hel=s* | --he=s* | -hs*) + ac_init_help=short ;; + + -host | --host | --hos | --ho) + ac_prev=host_alias ;; + -host=* | --host=* | --hos=* | --ho=*) + host_alias=$ac_optarg ;; + + -htmldir | --htmldir | --htmldi | --htmld | --html | --htm | --ht) + ac_prev=htmldir ;; + -htmldir=* | --htmldir=* | --htmldi=* | --htmld=* | --html=* | --htm=* \ + | --ht=*) + htmldir=$ac_optarg ;; + + -includedir | --includedir | --includedi | --included | --include \ + | --includ | --inclu | --incl | --inc) + ac_prev=includedir ;; + -includedir=* | --includedir=* | --includedi=* | --included=* | --include=* \ + | --includ=* | --inclu=* | --incl=* | --inc=*) + includedir=$ac_optarg ;; + + -infodir | --infodir | --infodi | --infod | --info | --inf) + ac_prev=infodir ;; + -infodir=* | --infodir=* | --infodi=* | --infod=* | --info=* | --inf=*) + infodir=$ac_optarg ;; + + -libdir | --libdir | --libdi | --libd) + ac_prev=libdir ;; + -libdir=* | --libdir=* | --libdi=* | --libd=*) + libdir=$ac_optarg ;; + + -libexecdir | --libexecdir | --libexecdi | --libexecd | --libexec \ + | --libexe | --libex | --libe) + ac_prev=libexecdir ;; + -libexecdir=* | --libexecdir=* | --libexecdi=* | --libexecd=* | --libexec=* \ + | --libexe=* | --libex=* | --libe=*) + libexecdir=$ac_optarg ;; + + -localedir | --localedir | --localedi | --localed | --locale) + ac_prev=localedir ;; + -localedir=* | --localedir=* | --localedi=* | --localed=* | --locale=*) + localedir=$ac_optarg ;; + + -localstatedir | --localstatedir | --localstatedi | --localstated \ + | --localstate | --localstat | --localsta | --localst | --locals) + ac_prev=localstatedir ;; + -localstatedir=* | --localstatedir=* | --localstatedi=* | --localstated=* \ + | --localstate=* | --localstat=* | --localsta=* | --localst=* | --locals=*) + localstatedir=$ac_optarg ;; + + -mandir | --mandir | --mandi | --mand | --man | --ma | --m) + ac_prev=mandir ;; + -mandir=* | --mandir=* | --mandi=* | --mand=* | --man=* | --ma=* | --m=*) + mandir=$ac_optarg ;; + + -nfp | --nfp | --nf) + # Obsolete; use --without-fp. + with_fp=no ;; + + -no-create | --no-create | --no-creat | --no-crea | --no-cre \ + | --no-cr | --no-c | -n) + no_create=yes ;; + + -no-recursion | --no-recursion | --no-recursio | --no-recursi \ + | --no-recurs | --no-recur | --no-recu | --no-rec | --no-re | --no-r) + no_recursion=yes ;; + + -oldincludedir | --oldincludedir | --oldincludedi | --oldincluded \ + | --oldinclude | --oldinclud | --oldinclu | --oldincl | --oldinc \ + | --oldin | --oldi | --old | --ol | --o) + ac_prev=oldincludedir ;; + -oldincludedir=* | --oldincludedir=* | --oldincludedi=* | --oldincluded=* \ + | --oldinclude=* | --oldinclud=* | --oldinclu=* | --oldincl=* | --oldinc=* \ + | --oldin=* | --oldi=* | --old=* | --ol=* | --o=*) + oldincludedir=$ac_optarg ;; + + -prefix | --prefix | --prefi | --pref | --pre | --pr | --p) + ac_prev=prefix ;; + -prefix=* | --prefix=* | --prefi=* | --pref=* | --pre=* | --pr=* | --p=*) + prefix=$ac_optarg ;; + + -program-prefix | --program-prefix | --program-prefi | --program-pref \ + | --program-pre | --program-pr | --program-p) + ac_prev=program_prefix ;; + -program-prefix=* | --program-prefix=* | --program-prefi=* \ + | --program-pref=* | --program-pre=* | --program-pr=* | --program-p=*) + program_prefix=$ac_optarg ;; + + -program-suffix | --program-suffix | --program-suffi | --program-suff \ + | --program-suf | --program-su | --program-s) + ac_prev=program_suffix ;; + -program-suffix=* | --program-suffix=* | --program-suffi=* \ + | --program-suff=* | --program-suf=* | --program-su=* | --program-s=*) + program_suffix=$ac_optarg ;; + + -program-transform-name | --program-transform-name \ + | --program-transform-nam | --program-transform-na \ + | --program-transform-n | --program-transform- \ + | --program-transform | --program-transfor \ + | --program-transfo | --program-transf \ + | --program-trans | --program-tran \ + | --progr-tra | --program-tr | --program-t) + ac_prev=program_transform_name ;; + -program-transform-name=* | --program-transform-name=* \ + | --program-transform-nam=* | --program-transform-na=* \ + | --program-transform-n=* | --program-transform-=* \ + | --program-transform=* | --program-transfor=* \ + | --program-transfo=* | --program-transf=* \ + | --program-trans=* | --program-tran=* \ + | --progr-tra=* | --program-tr=* | --program-t=*) + program_transform_name=$ac_optarg ;; + + -pdfdir | --pdfdir | --pdfdi | --pdfd | --pdf | --pd) + ac_prev=pdfdir ;; + -pdfdir=* | --pdfdir=* | --pdfdi=* | --pdfd=* | --pdf=* | --pd=*) + pdfdir=$ac_optarg ;; + + -psdir | --psdir | --psdi | --psd | --ps) + ac_prev=psdir ;; + -psdir=* | --psdir=* | --psdi=* | --psd=* | --ps=*) + psdir=$ac_optarg ;; + + -q | -quiet | --quiet | --quie | --qui | --qu | --q \ + | -silent | --silent | --silen | --sile | --sil) + silent=yes ;; + + -sbindir | --sbindir | --sbindi | --sbind | --sbin | --sbi | --sb) + ac_prev=sbindir ;; + -sbindir=* | --sbindir=* | --sbindi=* | --sbind=* | --sbin=* \ + | --sbi=* | --sb=*) + sbindir=$ac_optarg ;; + + -sharedstatedir | --sharedstatedir | --sharedstatedi \ + | --sharedstated | --sharedstate | --sharedstat | --sharedsta \ + | --sharedst | --shareds | --shared | --share | --shar \ + | --sha | --sh) + ac_prev=sharedstatedir ;; + -sharedstatedir=* | --sharedstatedir=* | --sharedstatedi=* \ + | --sharedstated=* | --sharedstate=* | --sharedstat=* | --sharedsta=* \ + | --sharedst=* | --shareds=* | --shared=* | --share=* | --shar=* \ + | --sha=* | --sh=*) + sharedstatedir=$ac_optarg ;; + + -site | --site | --sit) + ac_prev=site ;; + -site=* | --site=* | --sit=*) + site=$ac_optarg ;; + + -srcdir | --srcdir | --srcdi | --srcd | --src | --sr) + ac_prev=srcdir ;; + -srcdir=* | --srcdir=* | --srcdi=* | --srcd=* | --src=* | --sr=*) + srcdir=$ac_optarg ;; + + -sysconfdir | --sysconfdir | --sysconfdi | --sysconfd | --sysconf \ + | --syscon | --sysco | --sysc | --sys | --sy) + ac_prev=sysconfdir ;; + -sysconfdir=* | --sysconfdir=* | --sysconfdi=* | --sysconfd=* | --sysconf=* \ + | --syscon=* | --sysco=* | --sysc=* | --sys=* | --sy=*) + sysconfdir=$ac_optarg ;; + + -target | --target | --targe | --targ | --tar | --ta | --t) + ac_prev=target_alias ;; + -target=* | --target=* | --targe=* | --targ=* | --tar=* | --ta=* | --t=*) + target_alias=$ac_optarg ;; + + -v | -verbose | --verbose | --verbos | --verbo | --verb) + verbose=yes ;; + + -version | --version | --versio | --versi | --vers | -V) + ac_init_version=: ;; + + -with-* | --with-*) + ac_useropt=`expr "x$ac_option" : 'x-*with-\([^=]*\)'` + # Reject names that are not valid shell variable names. + expr "x$ac_useropt" : ".*[^-+._$as_cr_alnum]" >/dev/null && + as_fn_error $? "invalid package name: $ac_useropt" + ac_useropt_orig=$ac_useropt + ac_useropt=`$as_echo "$ac_useropt" | sed 's/[-+.]/_/g'` + case $ac_user_opts in + *" +"with_$ac_useropt" +"*) ;; + *) ac_unrecognized_opts="$ac_unrecognized_opts$ac_unrecognized_sep--with-$ac_useropt_orig" + ac_unrecognized_sep=', ';; + esac + eval with_$ac_useropt=\$ac_optarg ;; + + -without-* | --without-*) + ac_useropt=`expr "x$ac_option" : 'x-*without-\(.*\)'` + # Reject names that are not valid shell variable names. + expr "x$ac_useropt" : ".*[^-+._$as_cr_alnum]" >/dev/null && + as_fn_error $? "invalid package name: $ac_useropt" + ac_useropt_orig=$ac_useropt + ac_useropt=`$as_echo "$ac_useropt" | sed 's/[-+.]/_/g'` + case $ac_user_opts in + *" +"with_$ac_useropt" +"*) ;; + *) ac_unrecognized_opts="$ac_unrecognized_opts$ac_unrecognized_sep--without-$ac_useropt_orig" + ac_unrecognized_sep=', ';; + esac + eval with_$ac_useropt=no ;; + + --x) + # Obsolete; use --with-x. + with_x=yes ;; + + -x-includes | --x-includes | --x-include | --x-includ | --x-inclu \ + | --x-incl | --x-inc | --x-in | --x-i) + ac_prev=x_includes ;; + -x-includes=* | --x-includes=* | --x-include=* | --x-includ=* | --x-inclu=* \ + | --x-incl=* | --x-inc=* | --x-in=* | --x-i=*) + x_includes=$ac_optarg ;; + + -x-libraries | --x-libraries | --x-librarie | --x-librari \ + | --x-librar | --x-libra | --x-libr | --x-lib | --x-li | --x-l) + ac_prev=x_libraries ;; + -x-libraries=* | --x-libraries=* | --x-librarie=* | --x-librari=* \ + | --x-librar=* | --x-libra=* | --x-libr=* | --x-lib=* | --x-li=* | --x-l=*) + x_libraries=$ac_optarg ;; + + -*) as_fn_error $? "unrecognized option: \`$ac_option' +Try \`$0 --help' for more information" + ;; + + *=*) + ac_envvar=`expr "x$ac_option" : 'x\([^=]*\)='` + # Reject names that are not valid shell variable names. + case $ac_envvar in #( + '' | [0-9]* | *[!_$as_cr_alnum]* ) + as_fn_error $? "invalid variable name: \`$ac_envvar'" ;; + esac + eval $ac_envvar=\$ac_optarg + export $ac_envvar ;; + + *) + # FIXME: should be removed in autoconf 3.0. + $as_echo "$as_me: WARNING: you should use --build, --host, --target" >&2 + expr "x$ac_option" : ".*[^-._$as_cr_alnum]" >/dev/null && + $as_echo "$as_me: WARNING: invalid host type: $ac_option" >&2 + : "${build_alias=$ac_option} ${host_alias=$ac_option} ${target_alias=$ac_option}" + ;; + + esac +done + +if test -n "$ac_prev"; then + ac_option=--`echo $ac_prev | sed 's/_/-/g'` + as_fn_error $? "missing argument to $ac_option" +fi + +if test -n "$ac_unrecognized_opts"; then + case $enable_option_checking in + no) ;; + fatal) as_fn_error $? "unrecognized options: $ac_unrecognized_opts" ;; + *) $as_echo "$as_me: WARNING: unrecognized options: $ac_unrecognized_opts" >&2 ;; + esac +fi + +# Check all directory arguments for consistency. +for ac_var in exec_prefix prefix bindir sbindir libexecdir datarootdir \ + datadir sysconfdir sharedstatedir localstatedir includedir \ + oldincludedir docdir infodir htmldir dvidir pdfdir psdir \ + libdir localedir mandir +do + eval ac_val=\$$ac_var + # Remove trailing slashes. + case $ac_val in + */ ) + ac_val=`expr "X$ac_val" : 'X\(.*[^/]\)' \| "X$ac_val" : 'X\(.*\)'` + eval $ac_var=\$ac_val;; + esac + # Be sure to have absolute directory names. + case $ac_val in + [\\/$]* | ?:[\\/]* ) continue;; + NONE | '' ) case $ac_var in *prefix ) continue;; esac;; + esac + as_fn_error $? "expected an absolute directory name for --$ac_var: $ac_val" +done + +# There might be people who depend on the old broken behavior: `$host' +# used to hold the argument of --host etc. +# FIXME: To remove some day. +build=$build_alias +host=$host_alias +target=$target_alias + +# FIXME: To remove some day. +if test "x$host_alias" != x; then + if test "x$build_alias" = x; then + cross_compiling=maybe + elif test "x$build_alias" != "x$host_alias"; then + cross_compiling=yes + fi +fi + +ac_tool_prefix= +test -n "$host_alias" && ac_tool_prefix=$host_alias- + +test "$silent" = yes && exec 6>/dev/null + + +ac_pwd=`pwd` && test -n "$ac_pwd" && +ac_ls_di=`ls -di .` && +ac_pwd_ls_di=`cd "$ac_pwd" && ls -di .` || + as_fn_error $? "working directory cannot be determined" +test "X$ac_ls_di" = "X$ac_pwd_ls_di" || + as_fn_error $? "pwd does not report name of working directory" + + +# Find the source files, if location was not specified. +if test -z "$srcdir"; then + ac_srcdir_defaulted=yes + # Try the directory containing this script, then the parent directory. + ac_confdir=`$as_dirname -- "$as_myself" || +$as_expr X"$as_myself" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X"$as_myself" : 'X\(//\)[^/]' \| \ + X"$as_myself" : 'X\(//\)$' \| \ + X"$as_myself" : 'X\(/\)' \| . 2>/dev/null || +$as_echo X"$as_myself" | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ + s//\1/ + q + } + /^X\(\/\/\)[^/].*/{ + s//\1/ + q + } + /^X\(\/\/\)$/{ + s//\1/ + q + } + /^X\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'` + srcdir=$ac_confdir + if test ! -r "$srcdir/$ac_unique_file"; then + srcdir=.. + fi +else + ac_srcdir_defaulted=no +fi +if test ! -r "$srcdir/$ac_unique_file"; then + test "$ac_srcdir_defaulted" = yes && srcdir="$ac_confdir or .." + as_fn_error $? "cannot find sources ($ac_unique_file) in $srcdir" +fi +ac_msg="sources are in $srcdir, but \`cd $srcdir' does not work" +ac_abs_confdir=`( + cd "$srcdir" && test -r "./$ac_unique_file" || as_fn_error $? "$ac_msg" + pwd)` +# When building in place, set srcdir=. +if test "$ac_abs_confdir" = "$ac_pwd"; then + srcdir=. +fi +# Remove unnecessary trailing slashes from srcdir. +# Double slashes in file names in object file debugging info +# mess up M-x gdb in Emacs. +case $srcdir in +*/) srcdir=`expr "X$srcdir" : 'X\(.*[^/]\)' \| "X$srcdir" : 'X\(.*\)'`;; +esac +for ac_var in $ac_precious_vars; do + eval ac_env_${ac_var}_set=\${${ac_var}+set} + eval ac_env_${ac_var}_value=\$${ac_var} + eval ac_cv_env_${ac_var}_set=\${${ac_var}+set} + eval ac_cv_env_${ac_var}_value=\$${ac_var} +done + +# +# Report the --help message. +# +if test "$ac_init_help" = "long"; then + # Omit some internal or obsolete options to make the list less imposing. + # This message is too long to be a string in the A/UX 3.1 sh. + cat <<_ACEOF +\`configure' configures PCRE2 10.20 to adapt to many kinds of systems. + +Usage: $0 [OPTION]... [VAR=VALUE]... + +To assign environment variables (e.g., CC, CFLAGS...), specify them as +VAR=VALUE. See below for descriptions of some of the useful variables. + +Defaults for the options are specified in brackets. + +Configuration: + -h, --help display this help and exit + --help=short display options specific to this package + --help=recursive display the short help of all the included packages + -V, --version display version information and exit + -q, --quiet, --silent do not print \`checking ...' messages + --cache-file=FILE cache test results in FILE [disabled] + -C, --config-cache alias for \`--cache-file=config.cache' + -n, --no-create do not create output files + --srcdir=DIR find the sources in DIR [configure dir or \`..'] + +Installation directories: + --prefix=PREFIX install architecture-independent files in PREFIX + [$ac_default_prefix] + --exec-prefix=EPREFIX install architecture-dependent files in EPREFIX + [PREFIX] + +By default, \`make install' will install all the files in +\`$ac_default_prefix/bin', \`$ac_default_prefix/lib' etc. You can specify +an installation prefix other than \`$ac_default_prefix' using \`--prefix', +for instance \`--prefix=\$HOME'. + +For better control, use the options below. + +Fine tuning of the installation directories: + --bindir=DIR user executables [EPREFIX/bin] + --sbindir=DIR system admin executables [EPREFIX/sbin] + --libexecdir=DIR program executables [EPREFIX/libexec] + --sysconfdir=DIR read-only single-machine data [PREFIX/etc] + --sharedstatedir=DIR modifiable architecture-independent data [PREFIX/com] + --localstatedir=DIR modifiable single-machine data [PREFIX/var] + --libdir=DIR object code libraries [EPREFIX/lib] + --includedir=DIR C header files [PREFIX/include] + --oldincludedir=DIR C header files for non-gcc [/usr/include] + --datarootdir=DIR read-only arch.-independent data root [PREFIX/share] + --datadir=DIR read-only architecture-independent data [DATAROOTDIR] + --infodir=DIR info documentation [DATAROOTDIR/info] + --localedir=DIR locale-dependent data [DATAROOTDIR/locale] + --mandir=DIR man documentation [DATAROOTDIR/man] + --docdir=DIR documentation root [DATAROOTDIR/doc/pcre2] + --htmldir=DIR html documentation [DOCDIR] + --dvidir=DIR dvi documentation [DOCDIR] + --pdfdir=DIR pdf documentation [DOCDIR] + --psdir=DIR ps documentation [DOCDIR] +_ACEOF + + cat <<\_ACEOF + +Program names: + --program-prefix=PREFIX prepend PREFIX to installed program names + --program-suffix=SUFFIX append SUFFIX to installed program names + --program-transform-name=PROGRAM run sed PROGRAM on installed program names + +System types: + --build=BUILD configure for building on BUILD [guessed] + --host=HOST cross-compile to build programs to run on HOST [BUILD] +_ACEOF +fi + +if test -n "$ac_init_help"; then + case $ac_init_help in + short | recursive ) echo "Configuration of PCRE2 10.20:";; + esac + cat <<\_ACEOF + +Optional Features: + --disable-option-checking ignore unrecognized --enable/--with options + --disable-FEATURE do not include FEATURE (same as --enable-FEATURE=no) + --enable-FEATURE[=ARG] include FEATURE [ARG=yes] + --enable-silent-rules less verbose build output (undo: "make V=1") + --disable-silent-rules verbose build output (undo: "make V=0") + --enable-dependency-tracking + do not reject slow dependency extractors + --disable-dependency-tracking + speeds up one-time build + --enable-shared[=PKGS] build shared libraries [default=yes] + --enable-static[=PKGS] build static libraries [default=yes] + --enable-fast-install[=PKGS] + optimize for fast installation [default=yes] + --disable-libtool-lock avoid locking (might break parallel builds) + + --disable-pcre2-8 disable 8 bit character support + --enable-pcre2-16 enable 16 bit character support + --enable-pcre2-32 enable 32 bit character support + --enable-debug enable debugging code + --enable-jit enable Just-In-Time compiling support + --disable-pcre2grep-jit disable JIT support in pcre2grep + --enable-rebuild-chartables + rebuild character tables in current locale + --disable-unicode disable Unicode support + --enable-newline-is-cr use CR as newline character + --enable-newline-is-lf use LF as newline character (default) + --enable-newline-is-crlf + use CRLF as newline sequence + --enable-newline-is-anycrlf + use CR, LF, or CRLF as newline sequence + --enable-newline-is-any use any valid Unicode newline sequence + --enable-bsr-anycrlf \R matches only CR, LF, CRLF by default + --enable-ebcdic assume EBCDIC coding rather than ASCII; incompatible + with --enable-utf; use only in (uncommon) EBCDIC + environments; it implies --enable-rebuild-chartables + --enable-ebcdic-nl25 set EBCDIC code for NL to 0x25 instead of 0x15; it + implies --enable-ebcdic + --disable-stack-for-recursion + don't use stack recursion when matching + --enable-pcre2grep-libz link pcre2grep with libz to handle .gz files + --enable-pcre2grep-libbz2 + link pcre2grep with libbz2 to handle .bz2 files + --enable-pcre2test-libedit + link pcre2test with libedit + --enable-pcre2test-libreadline + link pcre2test with libreadline + --enable-valgrind valgrind support + --enable-coverage enable code coverage reports using gcov + +Optional Packages: + --with-PACKAGE[=ARG] use PACKAGE [ARG=yes] + --without-PACKAGE do not use PACKAGE (same as --with-PACKAGE=no) + --with-pic[=PKGS] try to use only PIC/non-PIC objects [default=use + both] + --with-aix-soname=aix|svr4|both + shared library versioning (aka "SONAME") variant to + provide on AIX, [default=aix]. + --with-gnu-ld assume the C compiler uses GNU ld [default=no] + --with-sysroot[=DIR] Search for dependent libraries within DIR (or the + compiler's sysroot if not specified). + --with-pcre2grep-bufsize=N + pcre2grep buffer size (default=20480, minimum=8192) + --with-link-size=N internal link size (2, 3, or 4 allowed; default=2) + --with-parens-nest-limit=N + nested parentheses limit (default=250) + --with-match-limit=N default limit on internal looping (default=10000000) + --with-match-limit-recursion=N + default limit on internal recursion + (default=MATCH_LIMIT) + +Some influential environment variables: + CC C compiler command + CFLAGS C compiler flags + LDFLAGS linker flags, e.g. -L if you have libraries in a + nonstandard directory + LIBS libraries to pass to the linker, e.g. -l + CPPFLAGS (Objective) C/C++ preprocessor flags, e.g. -I if + you have headers in a nonstandard directory + CPP C preprocessor + LT_SYS_LIBRARY_PATH + User-defined run-time library search path. + PKG_CONFIG path to pkg-config utility + PKG_CONFIG_PATH + directories to add to pkg-config's search path + PKG_CONFIG_LIBDIR + path overriding pkg-config's built-in search path + VALGRIND_CFLAGS + C compiler flags for VALGRIND, overriding pkg-config + VALGRIND_LIBS + linker flags for VALGRIND, overriding pkg-config + LCOV the ltp lcov program + GENHTML the ltp genhtml program + +Use these variables to override the choices made by `configure' or to help +it to find libraries and programs with nonstandard names/locations. + +Report bugs to the package provider. +_ACEOF +ac_status=$? +fi + +if test "$ac_init_help" = "recursive"; then + # If there are subdirs, report their specific --help. + for ac_dir in : $ac_subdirs_all; do test "x$ac_dir" = x: && continue + test -d "$ac_dir" || + { cd "$srcdir" && ac_pwd=`pwd` && srcdir=. && test -d "$ac_dir"; } || + continue + ac_builddir=. + +case "$ac_dir" in +.) ac_dir_suffix= ac_top_builddir_sub=. ac_top_build_prefix= ;; +*) + ac_dir_suffix=/`$as_echo "$ac_dir" | sed 's|^\.[\\/]||'` + # A ".." for each directory in $ac_dir_suffix. + ac_top_builddir_sub=`$as_echo "$ac_dir_suffix" | sed 's|/[^\\/]*|/..|g;s|/||'` + case $ac_top_builddir_sub in + "") ac_top_builddir_sub=. ac_top_build_prefix= ;; + *) ac_top_build_prefix=$ac_top_builddir_sub/ ;; + esac ;; +esac +ac_abs_top_builddir=$ac_pwd +ac_abs_builddir=$ac_pwd$ac_dir_suffix +# for backward compatibility: +ac_top_builddir=$ac_top_build_prefix + +case $srcdir in + .) # We are building in place. + ac_srcdir=. + ac_top_srcdir=$ac_top_builddir_sub + ac_abs_top_srcdir=$ac_pwd ;; + [\\/]* | ?:[\\/]* ) # Absolute name. + ac_srcdir=$srcdir$ac_dir_suffix; + ac_top_srcdir=$srcdir + ac_abs_top_srcdir=$srcdir ;; + *) # Relative name. + ac_srcdir=$ac_top_build_prefix$srcdir$ac_dir_suffix + ac_top_srcdir=$ac_top_build_prefix$srcdir + ac_abs_top_srcdir=$ac_pwd/$srcdir ;; +esac +ac_abs_srcdir=$ac_abs_top_srcdir$ac_dir_suffix + + cd "$ac_dir" || { ac_status=$?; continue; } + # Check for guested configure. + if test -f "$ac_srcdir/configure.gnu"; then + echo && + $SHELL "$ac_srcdir/configure.gnu" --help=recursive + elif test -f "$ac_srcdir/configure"; then + echo && + $SHELL "$ac_srcdir/configure" --help=recursive + else + $as_echo "$as_me: WARNING: no configuration information is in $ac_dir" >&2 + fi || ac_status=$? + cd "$ac_pwd" || { ac_status=$?; break; } + done +fi + +test -n "$ac_init_help" && exit $ac_status +if $ac_init_version; then + cat <<\_ACEOF +PCRE2 configure 10.20 +generated by GNU Autoconf 2.69 + +Copyright (C) 2012 Free Software Foundation, Inc. +This configure script is free software; the Free Software Foundation +gives unlimited permission to copy, distribute and modify it. +_ACEOF + exit +fi + +## ------------------------ ## +## Autoconf initialization. ## +## ------------------------ ## + +# ac_fn_c_try_compile LINENO +# -------------------------- +# Try to compile conftest.$ac_ext, and return whether this succeeded. +ac_fn_c_try_compile () +{ + as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack + rm -f conftest.$ac_objext + if { { ac_try="$ac_compile" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\"" +$as_echo "$ac_try_echo"; } >&5 + (eval "$ac_compile") 2>conftest.err + ac_status=$? + if test -s conftest.err; then + grep -v '^ *+' conftest.err >conftest.er1 + cat conftest.er1 >&5 + mv -f conftest.er1 conftest.err + fi + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } && { + test -z "$ac_c_werror_flag" || + test ! -s conftest.err + } && test -s conftest.$ac_objext; then : + ac_retval=0 +else + $as_echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + ac_retval=1 +fi + eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno + as_fn_set_status $ac_retval + +} # ac_fn_c_try_compile + +# ac_fn_c_try_cpp LINENO +# ---------------------- +# Try to preprocess conftest.$ac_ext, and return whether this succeeded. +ac_fn_c_try_cpp () +{ + as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack + if { { ac_try="$ac_cpp conftest.$ac_ext" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\"" +$as_echo "$ac_try_echo"; } >&5 + (eval "$ac_cpp conftest.$ac_ext") 2>conftest.err + ac_status=$? + if test -s conftest.err; then + grep -v '^ *+' conftest.err >conftest.er1 + cat conftest.er1 >&5 + mv -f conftest.er1 conftest.err + fi + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } > conftest.i && { + test -z "$ac_c_preproc_warn_flag$ac_c_werror_flag" || + test ! -s conftest.err + }; then : + ac_retval=0 +else + $as_echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + ac_retval=1 +fi + eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno + as_fn_set_status $ac_retval + +} # ac_fn_c_try_cpp + +# ac_fn_c_try_run LINENO +# ---------------------- +# Try to link conftest.$ac_ext, and return whether this succeeded. Assumes +# that executables *can* be run. +ac_fn_c_try_run () +{ + as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack + if { { ac_try="$ac_link" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\"" +$as_echo "$ac_try_echo"; } >&5 + (eval "$ac_link") 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } && { ac_try='./conftest$ac_exeext' + { { case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\"" +$as_echo "$ac_try_echo"; } >&5 + (eval "$ac_try") 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; }; }; then : + ac_retval=0 +else + $as_echo "$as_me: program exited with status $ac_status" >&5 + $as_echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + ac_retval=$ac_status +fi + rm -rf conftest.dSYM conftest_ipa8_conftest.oo + eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno + as_fn_set_status $ac_retval + +} # ac_fn_c_try_run + +# ac_fn_c_check_header_compile LINENO HEADER VAR INCLUDES +# ------------------------------------------------------- +# Tests whether HEADER exists and can be compiled using the include files in +# INCLUDES, setting the cache variable VAR accordingly. +ac_fn_c_check_header_compile () +{ + as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for $2" >&5 +$as_echo_n "checking for $2... " >&6; } +if eval \${$3+:} false; then : + $as_echo_n "(cached) " >&6 +else + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +$4 +#include <$2> +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + eval "$3=yes" +else + eval "$3=no" +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext +fi +eval ac_res=\$$3 + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_res" >&5 +$as_echo "$ac_res" >&6; } + eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno + +} # ac_fn_c_check_header_compile + +# ac_fn_c_find_intX_t LINENO BITS VAR +# ----------------------------------- +# Finds a signed integer type with width BITS, setting cache variable VAR +# accordingly. +ac_fn_c_find_intX_t () +{ + as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for int$2_t" >&5 +$as_echo_n "checking for int$2_t... " >&6; } +if eval \${$3+:} false; then : + $as_echo_n "(cached) " >&6 +else + eval "$3=no" + # Order is important - never check a type that is potentially smaller + # than half of the expected target width. + for ac_type in int$2_t 'int' 'long int' \ + 'long long int' 'short int' 'signed char'; do + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +$ac_includes_default + enum { N = $2 / 2 - 1 }; +int +main () +{ +static int test_array [1 - 2 * !(0 < ($ac_type) ((((($ac_type) 1 << N) << N) - 1) * 2 + 1))]; +test_array [0] = 0; +return test_array [0]; + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +$ac_includes_default + enum { N = $2 / 2 - 1 }; +int +main () +{ +static int test_array [1 - 2 * !(($ac_type) ((((($ac_type) 1 << N) << N) - 1) * 2 + 1) + < ($ac_type) ((((($ac_type) 1 << N) << N) - 1) * 2 + 2))]; +test_array [0] = 0; +return test_array [0]; + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + +else + case $ac_type in #( + int$2_t) : + eval "$3=yes" ;; #( + *) : + eval "$3=\$ac_type" ;; +esac +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext + if eval test \"x\$"$3"\" = x"no"; then : + +else + break +fi + done +fi +eval ac_res=\$$3 + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_res" >&5 +$as_echo "$ac_res" >&6; } + eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno + +} # ac_fn_c_find_intX_t + +# ac_fn_c_try_link LINENO +# ----------------------- +# Try to link conftest.$ac_ext, and return whether this succeeded. +ac_fn_c_try_link () +{ + as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack + rm -f conftest.$ac_objext conftest$ac_exeext + if { { ac_try="$ac_link" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\"" +$as_echo "$ac_try_echo"; } >&5 + (eval "$ac_link") 2>conftest.err + ac_status=$? + if test -s conftest.err; then + grep -v '^ *+' conftest.err >conftest.er1 + cat conftest.er1 >&5 + mv -f conftest.er1 conftest.err + fi + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } && { + test -z "$ac_c_werror_flag" || + test ! -s conftest.err + } && test -s conftest$ac_exeext && { + test "$cross_compiling" = yes || + test -x conftest$ac_exeext + }; then : + ac_retval=0 +else + $as_echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + ac_retval=1 +fi + # Delete the IPA/IPO (Inter Procedural Analysis/Optimization) information + # created by the PGI compiler (conftest_ipa8_conftest.oo), as it would + # interfere with the next link command; also delete a directory that is + # left behind by Apple's compiler. We do this before executing the actions. + rm -rf conftest.dSYM conftest_ipa8_conftest.oo + eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno + as_fn_set_status $ac_retval + +} # ac_fn_c_try_link + +# ac_fn_c_check_func LINENO FUNC VAR +# ---------------------------------- +# Tests whether FUNC exists, setting the cache variable VAR accordingly +ac_fn_c_check_func () +{ + as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for $2" >&5 +$as_echo_n "checking for $2... " >&6; } +if eval \${$3+:} false; then : + $as_echo_n "(cached) " >&6 +else + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +/* Define $2 to an innocuous variant, in case declares $2. + For example, HP-UX 11i declares gettimeofday. */ +#define $2 innocuous_$2 + +/* System header to define __stub macros and hopefully few prototypes, + which can conflict with char $2 (); below. + Prefer to if __STDC__ is defined, since + exists even on freestanding compilers. */ + +#ifdef __STDC__ +# include +#else +# include +#endif + +#undef $2 + +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char $2 (); +/* The GNU C library defines this for functions which it implements + to always fail with ENOSYS. Some functions are actually named + something starting with __ and the normal name is an alias. */ +#if defined __stub_$2 || defined __stub___$2 +choke me +#endif + +int +main () +{ +return $2 (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + eval "$3=yes" +else + eval "$3=no" +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +fi +eval ac_res=\$$3 + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_res" >&5 +$as_echo "$ac_res" >&6; } + eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno + +} # ac_fn_c_check_func + +# ac_fn_c_check_header_mongrel LINENO HEADER VAR INCLUDES +# ------------------------------------------------------- +# Tests whether HEADER exists, giving a warning if it cannot be compiled using +# the include files in INCLUDES and setting the cache variable VAR +# accordingly. +ac_fn_c_check_header_mongrel () +{ + as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack + if eval \${$3+:} false; then : + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for $2" >&5 +$as_echo_n "checking for $2... " >&6; } +if eval \${$3+:} false; then : + $as_echo_n "(cached) " >&6 +fi +eval ac_res=\$$3 + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_res" >&5 +$as_echo "$ac_res" >&6; } +else + # Is the header compilable? +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking $2 usability" >&5 +$as_echo_n "checking $2 usability... " >&6; } +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +$4 +#include <$2> +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + ac_header_compiler=yes +else + ac_header_compiler=no +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_header_compiler" >&5 +$as_echo "$ac_header_compiler" >&6; } + +# Is the header present? +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking $2 presence" >&5 +$as_echo_n "checking $2 presence... " >&6; } +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#include <$2> +_ACEOF +if ac_fn_c_try_cpp "$LINENO"; then : + ac_header_preproc=yes +else + ac_header_preproc=no +fi +rm -f conftest.err conftest.i conftest.$ac_ext +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_header_preproc" >&5 +$as_echo "$ac_header_preproc" >&6; } + +# So? What about this header? +case $ac_header_compiler:$ac_header_preproc:$ac_c_preproc_warn_flag in #(( + yes:no: ) + { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: accepted by the compiler, rejected by the preprocessor!" >&5 +$as_echo "$as_me: WARNING: $2: accepted by the compiler, rejected by the preprocessor!" >&2;} + { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: proceeding with the compiler's result" >&5 +$as_echo "$as_me: WARNING: $2: proceeding with the compiler's result" >&2;} + ;; + no:yes:* ) + { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: present but cannot be compiled" >&5 +$as_echo "$as_me: WARNING: $2: present but cannot be compiled" >&2;} + { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: check for missing prerequisite headers?" >&5 +$as_echo "$as_me: WARNING: $2: check for missing prerequisite headers?" >&2;} + { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: see the Autoconf documentation" >&5 +$as_echo "$as_me: WARNING: $2: see the Autoconf documentation" >&2;} + { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: section \"Present But Cannot Be Compiled\"" >&5 +$as_echo "$as_me: WARNING: $2: section \"Present But Cannot Be Compiled\"" >&2;} + { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: proceeding with the compiler's result" >&5 +$as_echo "$as_me: WARNING: $2: proceeding with the compiler's result" >&2;} + ;; +esac + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for $2" >&5 +$as_echo_n "checking for $2... " >&6; } +if eval \${$3+:} false; then : + $as_echo_n "(cached) " >&6 +else + eval "$3=\$ac_header_compiler" +fi +eval ac_res=\$$3 + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_res" >&5 +$as_echo "$ac_res" >&6; } +fi + eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno + +} # ac_fn_c_check_header_mongrel + +# ac_fn_c_check_type LINENO TYPE VAR INCLUDES +# ------------------------------------------- +# Tests whether TYPE exists after having included INCLUDES, setting cache +# variable VAR accordingly. +ac_fn_c_check_type () +{ + as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for $2" >&5 +$as_echo_n "checking for $2... " >&6; } +if eval \${$3+:} false; then : + $as_echo_n "(cached) " >&6 +else + eval "$3=no" + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +$4 +int +main () +{ +if (sizeof ($2)) + return 0; + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +$4 +int +main () +{ +if (sizeof (($2))) + return 0; + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + +else + eval "$3=yes" +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext +fi +eval ac_res=\$$3 + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_res" >&5 +$as_echo "$ac_res" >&6; } + eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno + +} # ac_fn_c_check_type +cat >config.log <<_ACEOF +This file contains any messages produced by compilers while +running configure, to aid debugging if configure makes a mistake. + +It was created by PCRE2 $as_me 10.20, which was +generated by GNU Autoconf 2.69. Invocation command line was + + $ $0 $@ + +_ACEOF +exec 5>>config.log +{ +cat <<_ASUNAME +## --------- ## +## Platform. ## +## --------- ## + +hostname = `(hostname || uname -n) 2>/dev/null | sed 1q` +uname -m = `(uname -m) 2>/dev/null || echo unknown` +uname -r = `(uname -r) 2>/dev/null || echo unknown` +uname -s = `(uname -s) 2>/dev/null || echo unknown` +uname -v = `(uname -v) 2>/dev/null || echo unknown` + +/usr/bin/uname -p = `(/usr/bin/uname -p) 2>/dev/null || echo unknown` +/bin/uname -X = `(/bin/uname -X) 2>/dev/null || echo unknown` + +/bin/arch = `(/bin/arch) 2>/dev/null || echo unknown` +/usr/bin/arch -k = `(/usr/bin/arch -k) 2>/dev/null || echo unknown` +/usr/convex/getsysinfo = `(/usr/convex/getsysinfo) 2>/dev/null || echo unknown` +/usr/bin/hostinfo = `(/usr/bin/hostinfo) 2>/dev/null || echo unknown` +/bin/machine = `(/bin/machine) 2>/dev/null || echo unknown` +/usr/bin/oslevel = `(/usr/bin/oslevel) 2>/dev/null || echo unknown` +/bin/universe = `(/bin/universe) 2>/dev/null || echo unknown` + +_ASUNAME + +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + $as_echo "PATH: $as_dir" + done +IFS=$as_save_IFS + +} >&5 + +cat >&5 <<_ACEOF + + +## ----------- ## +## Core tests. ## +## ----------- ## + +_ACEOF + + +# Keep a trace of the command line. +# Strip out --no-create and --no-recursion so they do not pile up. +# Strip out --silent because we don't want to record it for future runs. +# Also quote any args containing shell meta-characters. +# Make two passes to allow for proper duplicate-argument suppression. +ac_configure_args= +ac_configure_args0= +ac_configure_args1= +ac_must_keep_next=false +for ac_pass in 1 2 +do + for ac_arg + do + case $ac_arg in + -no-create | --no-c* | -n | -no-recursion | --no-r*) continue ;; + -q | -quiet | --quiet | --quie | --qui | --qu | --q \ + | -silent | --silent | --silen | --sile | --sil) + continue ;; + *\'*) + ac_arg=`$as_echo "$ac_arg" | sed "s/'/'\\\\\\\\''/g"` ;; + esac + case $ac_pass in + 1) as_fn_append ac_configure_args0 " '$ac_arg'" ;; + 2) + as_fn_append ac_configure_args1 " '$ac_arg'" + if test $ac_must_keep_next = true; then + ac_must_keep_next=false # Got value, back to normal. + else + case $ac_arg in + *=* | --config-cache | -C | -disable-* | --disable-* \ + | -enable-* | --enable-* | -gas | --g* | -nfp | --nf* \ + | -q | -quiet | --q* | -silent | --sil* | -v | -verb* \ + | -with-* | --with-* | -without-* | --without-* | --x) + case "$ac_configure_args0 " in + "$ac_configure_args1"*" '$ac_arg' "* ) continue ;; + esac + ;; + -* ) ac_must_keep_next=true ;; + esac + fi + as_fn_append ac_configure_args " '$ac_arg'" + ;; + esac + done +done +{ ac_configure_args0=; unset ac_configure_args0;} +{ ac_configure_args1=; unset ac_configure_args1;} + +# When interrupted or exit'd, cleanup temporary files, and complete +# config.log. We remove comments because anyway the quotes in there +# would cause problems or look ugly. +# WARNING: Use '\'' to represent an apostrophe within the trap. +# WARNING: Do not start the trap code with a newline, due to a FreeBSD 4.0 bug. +trap 'exit_status=$? + # Save into config.log some information that might help in debugging. + { + echo + + $as_echo "## ---------------- ## +## Cache variables. ## +## ---------------- ##" + echo + # The following way of writing the cache mishandles newlines in values, +( + for ac_var in `(set) 2>&1 | sed -n '\''s/^\([a-zA-Z_][a-zA-Z0-9_]*\)=.*/\1/p'\''`; do + eval ac_val=\$$ac_var + case $ac_val in #( + *${as_nl}*) + case $ac_var in #( + *_cv_*) { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: cache variable $ac_var contains a newline" >&5 +$as_echo "$as_me: WARNING: cache variable $ac_var contains a newline" >&2;} ;; + esac + case $ac_var in #( + _ | IFS | as_nl) ;; #( + BASH_ARGV | BASH_SOURCE) eval $ac_var= ;; #( + *) { eval $ac_var=; unset $ac_var;} ;; + esac ;; + esac + done + (set) 2>&1 | + case $as_nl`(ac_space='\'' '\''; set) 2>&1` in #( + *${as_nl}ac_space=\ *) + sed -n \ + "s/'\''/'\''\\\\'\'''\''/g; + s/^\\([_$as_cr_alnum]*_cv_[_$as_cr_alnum]*\\)=\\(.*\\)/\\1='\''\\2'\''/p" + ;; #( + *) + sed -n "/^[_$as_cr_alnum]*_cv_[_$as_cr_alnum]*=/p" + ;; + esac | + sort +) + echo + + $as_echo "## ----------------- ## +## Output variables. ## +## ----------------- ##" + echo + for ac_var in $ac_subst_vars + do + eval ac_val=\$$ac_var + case $ac_val in + *\'\''*) ac_val=`$as_echo "$ac_val" | sed "s/'\''/'\''\\\\\\\\'\'''\''/g"`;; + esac + $as_echo "$ac_var='\''$ac_val'\''" + done | sort + echo + + if test -n "$ac_subst_files"; then + $as_echo "## ------------------- ## +## File substitutions. ## +## ------------------- ##" + echo + for ac_var in $ac_subst_files + do + eval ac_val=\$$ac_var + case $ac_val in + *\'\''*) ac_val=`$as_echo "$ac_val" | sed "s/'\''/'\''\\\\\\\\'\'''\''/g"`;; + esac + $as_echo "$ac_var='\''$ac_val'\''" + done | sort + echo + fi + + if test -s confdefs.h; then + $as_echo "## ----------- ## +## confdefs.h. ## +## ----------- ##" + echo + cat confdefs.h + echo + fi + test "$ac_signal" != 0 && + $as_echo "$as_me: caught signal $ac_signal" + $as_echo "$as_me: exit $exit_status" + } >&5 + rm -f core *.core core.conftest.* && + rm -f -r conftest* confdefs* conf$$* $ac_clean_files && + exit $exit_status +' 0 +for ac_signal in 1 2 13 15; do + trap 'ac_signal='$ac_signal'; as_fn_exit 1' $ac_signal +done +ac_signal=0 + +# confdefs.h avoids OS command line length limits that DEFS can exceed. +rm -f -r conftest* confdefs.h + +$as_echo "/* confdefs.h */" > confdefs.h + +# Predefined preprocessor variables. + +cat >>confdefs.h <<_ACEOF +#define PACKAGE_NAME "$PACKAGE_NAME" +_ACEOF + +cat >>confdefs.h <<_ACEOF +#define PACKAGE_TARNAME "$PACKAGE_TARNAME" +_ACEOF + +cat >>confdefs.h <<_ACEOF +#define PACKAGE_VERSION "$PACKAGE_VERSION" +_ACEOF + +cat >>confdefs.h <<_ACEOF +#define PACKAGE_STRING "$PACKAGE_STRING" +_ACEOF + +cat >>confdefs.h <<_ACEOF +#define PACKAGE_BUGREPORT "$PACKAGE_BUGREPORT" +_ACEOF + +cat >>confdefs.h <<_ACEOF +#define PACKAGE_URL "$PACKAGE_URL" +_ACEOF + + +# Let the site file select an alternate cache file if it wants to. +# Prefer an explicitly selected file to automatically selected ones. +ac_site_file1=NONE +ac_site_file2=NONE +if test -n "$CONFIG_SITE"; then + # We do not want a PATH search for config.site. + case $CONFIG_SITE in #(( + -*) ac_site_file1=./$CONFIG_SITE;; + */*) ac_site_file1=$CONFIG_SITE;; + *) ac_site_file1=./$CONFIG_SITE;; + esac +elif test "x$prefix" != xNONE; then + ac_site_file1=$prefix/share/config.site + ac_site_file2=$prefix/etc/config.site +else + ac_site_file1=$ac_default_prefix/share/config.site + ac_site_file2=$ac_default_prefix/etc/config.site +fi +for ac_site_file in "$ac_site_file1" "$ac_site_file2" +do + test "x$ac_site_file" = xNONE && continue + if test /dev/null != "$ac_site_file" && test -r "$ac_site_file"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: loading site script $ac_site_file" >&5 +$as_echo "$as_me: loading site script $ac_site_file" >&6;} + sed 's/^/| /' "$ac_site_file" >&5 + . "$ac_site_file" \ + || { { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5 +$as_echo "$as_me: error: in \`$ac_pwd':" >&2;} +as_fn_error $? "failed to load site script $ac_site_file +See \`config.log' for more details" "$LINENO" 5; } + fi +done + +if test -r "$cache_file"; then + # Some versions of bash will fail to source /dev/null (special files + # actually), so we avoid doing that. DJGPP emulates it as a regular file. + if test /dev/null != "$cache_file" && test -f "$cache_file"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: loading cache $cache_file" >&5 +$as_echo "$as_me: loading cache $cache_file" >&6;} + case $cache_file in + [\\/]* | ?:[\\/]* ) . "$cache_file";; + *) . "./$cache_file";; + esac + fi +else + { $as_echo "$as_me:${as_lineno-$LINENO}: creating cache $cache_file" >&5 +$as_echo "$as_me: creating cache $cache_file" >&6;} + >$cache_file +fi + +# Check that the precious variables saved in the cache have kept the same +# value. +ac_cache_corrupted=false +for ac_var in $ac_precious_vars; do + eval ac_old_set=\$ac_cv_env_${ac_var}_set + eval ac_new_set=\$ac_env_${ac_var}_set + eval ac_old_val=\$ac_cv_env_${ac_var}_value + eval ac_new_val=\$ac_env_${ac_var}_value + case $ac_old_set,$ac_new_set in + set,) + { $as_echo "$as_me:${as_lineno-$LINENO}: error: \`$ac_var' was set to \`$ac_old_val' in the previous run" >&5 +$as_echo "$as_me: error: \`$ac_var' was set to \`$ac_old_val' in the previous run" >&2;} + ac_cache_corrupted=: ;; + ,set) + { $as_echo "$as_me:${as_lineno-$LINENO}: error: \`$ac_var' was not set in the previous run" >&5 +$as_echo "$as_me: error: \`$ac_var' was not set in the previous run" >&2;} + ac_cache_corrupted=: ;; + ,);; + *) + if test "x$ac_old_val" != "x$ac_new_val"; then + # differences in whitespace do not lead to failure. + ac_old_val_w=`echo x $ac_old_val` + ac_new_val_w=`echo x $ac_new_val` + if test "$ac_old_val_w" != "$ac_new_val_w"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: error: \`$ac_var' has changed since the previous run:" >&5 +$as_echo "$as_me: error: \`$ac_var' has changed since the previous run:" >&2;} + ac_cache_corrupted=: + else + { $as_echo "$as_me:${as_lineno-$LINENO}: warning: ignoring whitespace changes in \`$ac_var' since the previous run:" >&5 +$as_echo "$as_me: warning: ignoring whitespace changes in \`$ac_var' since the previous run:" >&2;} + eval $ac_var=\$ac_old_val + fi + { $as_echo "$as_me:${as_lineno-$LINENO}: former value: \`$ac_old_val'" >&5 +$as_echo "$as_me: former value: \`$ac_old_val'" >&2;} + { $as_echo "$as_me:${as_lineno-$LINENO}: current value: \`$ac_new_val'" >&5 +$as_echo "$as_me: current value: \`$ac_new_val'" >&2;} + fi;; + esac + # Pass precious variables to config.status. + if test "$ac_new_set" = set; then + case $ac_new_val in + *\'*) ac_arg=$ac_var=`$as_echo "$ac_new_val" | sed "s/'/'\\\\\\\\''/g"` ;; + *) ac_arg=$ac_var=$ac_new_val ;; + esac + case " $ac_configure_args " in + *" '$ac_arg' "*) ;; # Avoid dups. Use of quotes ensures accuracy. + *) as_fn_append ac_configure_args " '$ac_arg'" ;; + esac + fi +done +if $ac_cache_corrupted; then + { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5 +$as_echo "$as_me: error: in \`$ac_pwd':" >&2;} + { $as_echo "$as_me:${as_lineno-$LINENO}: error: changes in the environment can compromise the build" >&5 +$as_echo "$as_me: error: changes in the environment can compromise the build" >&2;} + as_fn_error $? "run \`make distclean' and/or \`rm $cache_file' and start over" "$LINENO" 5 +fi +## -------------------- ## +## Main body of script. ## +## -------------------- ## + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + + + +am__api_version='1.15' + +ac_aux_dir= +for ac_dir in "$srcdir" "$srcdir/.." "$srcdir/../.."; do + if test -f "$ac_dir/install-sh"; then + ac_aux_dir=$ac_dir + ac_install_sh="$ac_aux_dir/install-sh -c" + break + elif test -f "$ac_dir/install.sh"; then + ac_aux_dir=$ac_dir + ac_install_sh="$ac_aux_dir/install.sh -c" + break + elif test -f "$ac_dir/shtool"; then + ac_aux_dir=$ac_dir + ac_install_sh="$ac_aux_dir/shtool install -c" + break + fi +done +if test -z "$ac_aux_dir"; then + as_fn_error $? "cannot find install-sh, install.sh, or shtool in \"$srcdir\" \"$srcdir/..\" \"$srcdir/../..\"" "$LINENO" 5 +fi + +# These three variables are undocumented and unsupported, +# and are intended to be withdrawn in a future Autoconf release. +# They can cause serious problems if a builder's source tree is in a directory +# whose full name contains unusual characters. +ac_config_guess="$SHELL $ac_aux_dir/config.guess" # Please don't use this var. +ac_config_sub="$SHELL $ac_aux_dir/config.sub" # Please don't use this var. +ac_configure="$SHELL $ac_aux_dir/configure" # Please don't use this var. + + +# Find a good install program. We prefer a C program (faster), +# so one script is as good as another. But avoid the broken or +# incompatible versions: +# SysV /etc/install, /usr/sbin/install +# SunOS /usr/etc/install +# IRIX /sbin/install +# AIX /bin/install +# AmigaOS /C/install, which installs bootblocks on floppy discs +# AIX 4 /usr/bin/installbsd, which doesn't work without a -g flag +# AFS /usr/afsws/bin/install, which mishandles nonexistent args +# SVR4 /usr/ucb/install, which tries to use the nonexistent group "staff" +# OS/2's system install, which has a completely different semantic +# ./install, which can be erroneously created by make from ./install.sh. +# Reject install programs that cannot install multiple files. +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for a BSD-compatible install" >&5 +$as_echo_n "checking for a BSD-compatible install... " >&6; } +if test -z "$INSTALL"; then +if ${ac_cv_path_install+:} false; then : + $as_echo_n "(cached) " >&6 +else + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + # Account for people who put trailing slashes in PATH elements. +case $as_dir/ in #(( + ./ | .// | /[cC]/* | \ + /etc/* | /usr/sbin/* | /usr/etc/* | /sbin/* | /usr/afsws/bin/* | \ + ?:[\\/]os2[\\/]install[\\/]* | ?:[\\/]OS2[\\/]INSTALL[\\/]* | \ + /usr/ucb/* ) ;; + *) + # OSF1 and SCO ODT 3.0 have their own names for install. + # Don't use installbsd from OSF since it installs stuff as root + # by default. + for ac_prog in ginstall scoinst install; do + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_prog$ac_exec_ext"; then + if test $ac_prog = install && + grep dspmsg "$as_dir/$ac_prog$ac_exec_ext" >/dev/null 2>&1; then + # AIX install. It has an incompatible calling convention. + : + elif test $ac_prog = install && + grep pwplus "$as_dir/$ac_prog$ac_exec_ext" >/dev/null 2>&1; then + # program-specific install script used by HP pwplus--don't use. + : + else + rm -rf conftest.one conftest.two conftest.dir + echo one > conftest.one + echo two > conftest.two + mkdir conftest.dir + if "$as_dir/$ac_prog$ac_exec_ext" -c conftest.one conftest.two "`pwd`/conftest.dir" && + test -s conftest.one && test -s conftest.two && + test -s conftest.dir/conftest.one && + test -s conftest.dir/conftest.two + then + ac_cv_path_install="$as_dir/$ac_prog$ac_exec_ext -c" + break 3 + fi + fi + fi + done + done + ;; +esac + + done +IFS=$as_save_IFS + +rm -rf conftest.one conftest.two conftest.dir + +fi + if test "${ac_cv_path_install+set}" = set; then + INSTALL=$ac_cv_path_install + else + # As a last resort, use the slow shell script. Don't cache a + # value for INSTALL within a source directory, because that will + # break other packages using the cache if that directory is + # removed, or if the value is a relative name. + INSTALL=$ac_install_sh + fi +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $INSTALL" >&5 +$as_echo "$INSTALL" >&6; } + +# Use test -z because SunOS4 sh mishandles braces in ${var-val}. +# It thinks the first close brace ends the variable substitution. +test -z "$INSTALL_PROGRAM" && INSTALL_PROGRAM='${INSTALL}' + +test -z "$INSTALL_SCRIPT" && INSTALL_SCRIPT='${INSTALL}' + +test -z "$INSTALL_DATA" && INSTALL_DATA='${INSTALL} -m 644' + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether build environment is sane" >&5 +$as_echo_n "checking whether build environment is sane... " >&6; } +# Reject unsafe characters in $srcdir or the absolute working directory +# name. Accept space and tab only in the latter. +am_lf=' +' +case `pwd` in + *[\\\"\#\$\&\'\`$am_lf]*) + as_fn_error $? "unsafe absolute working directory name" "$LINENO" 5;; +esac +case $srcdir in + *[\\\"\#\$\&\'\`$am_lf\ \ ]*) + as_fn_error $? "unsafe srcdir value: '$srcdir'" "$LINENO" 5;; +esac + +# Do 'set' in a subshell so we don't clobber the current shell's +# arguments. Must try -L first in case configure is actually a +# symlink; some systems play weird games with the mod time of symlinks +# (eg FreeBSD returns the mod time of the symlink's containing +# directory). +if ( + am_has_slept=no + for am_try in 1 2; do + echo "timestamp, slept: $am_has_slept" > conftest.file + set X `ls -Lt "$srcdir/configure" conftest.file 2> /dev/null` + if test "$*" = "X"; then + # -L didn't work. + set X `ls -t "$srcdir/configure" conftest.file` + fi + if test "$*" != "X $srcdir/configure conftest.file" \ + && test "$*" != "X conftest.file $srcdir/configure"; then + + # If neither matched, then we have a broken ls. This can happen + # if, for instance, CONFIG_SHELL is bash and it inherits a + # broken ls alias from the environment. This has actually + # happened. Such a system could not be considered "sane". + as_fn_error $? "ls -t appears to fail. Make sure there is not a broken + alias in your environment" "$LINENO" 5 + fi + if test "$2" = conftest.file || test $am_try -eq 2; then + break + fi + # Just in case. + sleep 1 + am_has_slept=yes + done + test "$2" = conftest.file + ) +then + # Ok. + : +else + as_fn_error $? "newly created file is older than distributed files! +Check your system clock" "$LINENO" 5 +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5 +$as_echo "yes" >&6; } +# If we didn't sleep, we still need to ensure time stamps of config.status and +# generated files are strictly newer. +am_sleep_pid= +if grep 'slept: no' conftest.file >/dev/null 2>&1; then + ( sleep 1 ) & + am_sleep_pid=$! +fi + +rm -f conftest.file + +test "$program_prefix" != NONE && + program_transform_name="s&^&$program_prefix&;$program_transform_name" +# Use a double $ so make ignores it. +test "$program_suffix" != NONE && + program_transform_name="s&\$&$program_suffix&;$program_transform_name" +# Double any \ or $. +# By default was `s,x,x', remove it if useless. +ac_script='s/[\\$]/&&/g;s/;s,x,x,$//' +program_transform_name=`$as_echo "$program_transform_name" | sed "$ac_script"` + +# Expand $ac_aux_dir to an absolute path. +am_aux_dir=`cd "$ac_aux_dir" && pwd` + +if test x"${MISSING+set}" != xset; then + case $am_aux_dir in + *\ * | *\ *) + MISSING="\${SHELL} \"$am_aux_dir/missing\"" ;; + *) + MISSING="\${SHELL} $am_aux_dir/missing" ;; + esac +fi +# Use eval to expand $SHELL +if eval "$MISSING --is-lightweight"; then + am_missing_run="$MISSING " +else + am_missing_run= + { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: 'missing' script is too old or missing" >&5 +$as_echo "$as_me: WARNING: 'missing' script is too old or missing" >&2;} +fi + +if test x"${install_sh+set}" != xset; then + case $am_aux_dir in + *\ * | *\ *) + install_sh="\${SHELL} '$am_aux_dir/install-sh'" ;; + *) + install_sh="\${SHELL} $am_aux_dir/install-sh" + esac +fi + +# Installed binaries are usually stripped using 'strip' when the user +# run "make install-strip". However 'strip' might not be the right +# tool to use in cross-compilation environments, therefore Automake +# will honor the 'STRIP' environment variable to overrule this program. +if test "$cross_compiling" != no; then + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}strip", so it can be a program name with args. +set dummy ${ac_tool_prefix}strip; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_STRIP+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$STRIP"; then + ac_cv_prog_STRIP="$STRIP" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_STRIP="${ac_tool_prefix}strip" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +STRIP=$ac_cv_prog_STRIP +if test -n "$STRIP"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $STRIP" >&5 +$as_echo "$STRIP" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_prog_STRIP"; then + ac_ct_STRIP=$STRIP + # Extract the first word of "strip", so it can be a program name with args. +set dummy strip; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_STRIP+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_STRIP"; then + ac_cv_prog_ac_ct_STRIP="$ac_ct_STRIP" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_STRIP="strip" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_STRIP=$ac_cv_prog_ac_ct_STRIP +if test -n "$ac_ct_STRIP"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_STRIP" >&5 +$as_echo "$ac_ct_STRIP" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_ct_STRIP" = x; then + STRIP=":" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + STRIP=$ac_ct_STRIP + fi +else + STRIP="$ac_cv_prog_STRIP" +fi + +fi +INSTALL_STRIP_PROGRAM="\$(install_sh) -c -s" + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for a thread-safe mkdir -p" >&5 +$as_echo_n "checking for a thread-safe mkdir -p... " >&6; } +if test -z "$MKDIR_P"; then + if ${ac_cv_path_mkdir+:} false; then : + $as_echo_n "(cached) " >&6 +else + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH$PATH_SEPARATOR/opt/sfw/bin +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_prog in mkdir gmkdir; do + for ac_exec_ext in '' $ac_executable_extensions; do + as_fn_executable_p "$as_dir/$ac_prog$ac_exec_ext" || continue + case `"$as_dir/$ac_prog$ac_exec_ext" --version 2>&1` in #( + 'mkdir (GNU coreutils) '* | \ + 'mkdir (coreutils) '* | \ + 'mkdir (fileutils) '4.1*) + ac_cv_path_mkdir=$as_dir/$ac_prog$ac_exec_ext + break 3;; + esac + done + done + done +IFS=$as_save_IFS + +fi + + test -d ./--version && rmdir ./--version + if test "${ac_cv_path_mkdir+set}" = set; then + MKDIR_P="$ac_cv_path_mkdir -p" + else + # As a last resort, use the slow shell script. Don't cache a + # value for MKDIR_P within a source directory, because that will + # break other packages using the cache if that directory is + # removed, or if the value is a relative name. + MKDIR_P="$ac_install_sh -d" + fi +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $MKDIR_P" >&5 +$as_echo "$MKDIR_P" >&6; } + +for ac_prog in gawk mawk nawk awk +do + # Extract the first word of "$ac_prog", so it can be a program name with args. +set dummy $ac_prog; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_AWK+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$AWK"; then + ac_cv_prog_AWK="$AWK" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_AWK="$ac_prog" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +AWK=$ac_cv_prog_AWK +if test -n "$AWK"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $AWK" >&5 +$as_echo "$AWK" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + test -n "$AWK" && break +done + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether ${MAKE-make} sets \$(MAKE)" >&5 +$as_echo_n "checking whether ${MAKE-make} sets \$(MAKE)... " >&6; } +set x ${MAKE-make} +ac_make=`$as_echo "$2" | sed 's/+/p/g; s/[^a-zA-Z0-9_]/_/g'` +if eval \${ac_cv_prog_make_${ac_make}_set+:} false; then : + $as_echo_n "(cached) " >&6 +else + cat >conftest.make <<\_ACEOF +SHELL = /bin/sh +all: + @echo '@@@%%%=$(MAKE)=@@@%%%' +_ACEOF +# GNU make sometimes prints "make[1]: Entering ...", which would confuse us. +case `${MAKE-make} -f conftest.make 2>/dev/null` in + *@@@%%%=?*=@@@%%%*) + eval ac_cv_prog_make_${ac_make}_set=yes;; + *) + eval ac_cv_prog_make_${ac_make}_set=no;; +esac +rm -f conftest.make +fi +if eval test \$ac_cv_prog_make_${ac_make}_set = yes; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5 +$as_echo "yes" >&6; } + SET_MAKE= +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } + SET_MAKE="MAKE=${MAKE-make}" +fi + +rm -rf .tst 2>/dev/null +mkdir .tst 2>/dev/null +if test -d .tst; then + am__leading_dot=. +else + am__leading_dot=_ +fi +rmdir .tst 2>/dev/null + +# Check whether --enable-silent-rules was given. +if test "${enable_silent_rules+set}" = set; then : + enableval=$enable_silent_rules; +fi + +case $enable_silent_rules in # ((( + yes) AM_DEFAULT_VERBOSITY=0;; + no) AM_DEFAULT_VERBOSITY=1;; + *) AM_DEFAULT_VERBOSITY=1;; +esac +am_make=${MAKE-make} +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether $am_make supports nested variables" >&5 +$as_echo_n "checking whether $am_make supports nested variables... " >&6; } +if ${am_cv_make_support_nested_variables+:} false; then : + $as_echo_n "(cached) " >&6 +else + if $as_echo 'TRUE=$(BAR$(V)) +BAR0=false +BAR1=true +V=1 +am__doit: + @$(TRUE) +.PHONY: am__doit' | $am_make -f - >/dev/null 2>&1; then + am_cv_make_support_nested_variables=yes +else + am_cv_make_support_nested_variables=no +fi +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $am_cv_make_support_nested_variables" >&5 +$as_echo "$am_cv_make_support_nested_variables" >&6; } +if test $am_cv_make_support_nested_variables = yes; then + AM_V='$(V)' + AM_DEFAULT_V='$(AM_DEFAULT_VERBOSITY)' +else + AM_V=$AM_DEFAULT_VERBOSITY + AM_DEFAULT_V=$AM_DEFAULT_VERBOSITY +fi +AM_BACKSLASH='\' + +if test "`cd $srcdir && pwd`" != "`pwd`"; then + # Use -I$(srcdir) only when $(srcdir) != ., so that make's output + # is not polluted with repeated "-I." + am__isrc=' -I$(srcdir)' + # test to see if srcdir already configured + if test -f $srcdir/config.status; then + as_fn_error $? "source directory already configured; run \"make distclean\" there first" "$LINENO" 5 + fi +fi + +# test whether we have cygpath +if test -z "$CYGPATH_W"; then + if (cygpath --version) >/dev/null 2>/dev/null; then + CYGPATH_W='cygpath -w' + else + CYGPATH_W=echo + fi +fi + + +# Define the identity of the package. + PACKAGE='pcre2' + VERSION='10.20' + + +cat >>confdefs.h <<_ACEOF +#define PACKAGE "$PACKAGE" +_ACEOF + + +cat >>confdefs.h <<_ACEOF +#define VERSION "$VERSION" +_ACEOF + +# Some tools Automake needs. + +ACLOCAL=${ACLOCAL-"${am_missing_run}aclocal-${am__api_version}"} + + +AUTOCONF=${AUTOCONF-"${am_missing_run}autoconf"} + + +AUTOMAKE=${AUTOMAKE-"${am_missing_run}automake-${am__api_version}"} + + +AUTOHEADER=${AUTOHEADER-"${am_missing_run}autoheader"} + + +MAKEINFO=${MAKEINFO-"${am_missing_run}makeinfo"} + +# For better backward compatibility. To be removed once Automake 1.9.x +# dies out for good. For more background, see: +# +# +mkdir_p='$(MKDIR_P)' + +# We need awk for the "check" target (and possibly the TAP driver). The +# system "awk" is bad on some platforms. +# Always define AMTAR for backward compatibility. Yes, it's still used +# in the wild :-( We should find a proper way to deprecate it ... +AMTAR='$${TAR-tar}' + + +# We'll loop over all known methods to create a tar archive until one works. +_am_tools='gnutar pax cpio none' + +am__tar='$${TAR-tar} chof - "$$tardir"' am__untar='$${TAR-tar} xf -' + + + + + + +# POSIX will say in a future version that running "rm -f" with no argument +# is OK; and we want to be able to make that assumption in our Makefile +# recipes. So use an aggressive probe to check that the usage we want is +# actually supported "in the wild" to an acceptable degree. +# See automake bug#10828. +# To make any issue more visible, cause the running configure to be aborted +# by default if the 'rm' program in use doesn't match our expectations; the +# user can still override this though. +if rm -f && rm -fr && rm -rf; then : OK; else + cat >&2 <<'END' +Oops! + +Your 'rm' program seems unable to run without file operands specified +on the command line, even when the '-f' option is present. This is contrary +to the behaviour of most rm programs out there, and not conforming with +the upcoming POSIX standard: + +Please tell bug-automake@gnu.org about your system, including the value +of your $PATH and any error possibly output before this message. This +can help us improve future automake versions. + +END + if test x"$ACCEPT_INFERIOR_RM_PROGRAM" = x"yes"; then + echo 'Configuration will proceed anyway, since you have set the' >&2 + echo 'ACCEPT_INFERIOR_RM_PROGRAM variable to "yes"' >&2 + echo >&2 + else + cat >&2 <<'END' +Aborting the configuration process, to ensure you take notice of the issue. + +You can download and install GNU coreutils to get an 'rm' implementation +that behaves properly: . + +If you want to complete the configuration process using your problematic +'rm' anyway, export the environment variable ACCEPT_INFERIOR_RM_PROGRAM +to "yes", and re-run configure. + +END + as_fn_error $? "Your 'rm' program is bad, sorry." "$LINENO" 5 + fi +fi + +# Check whether --enable-silent-rules was given. +if test "${enable_silent_rules+set}" = set; then : + enableval=$enable_silent_rules; +fi + +case $enable_silent_rules in # ((( + yes) AM_DEFAULT_VERBOSITY=0;; + no) AM_DEFAULT_VERBOSITY=1;; + *) AM_DEFAULT_VERBOSITY=0;; +esac +am_make=${MAKE-make} +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether $am_make supports nested variables" >&5 +$as_echo_n "checking whether $am_make supports nested variables... " >&6; } +if ${am_cv_make_support_nested_variables+:} false; then : + $as_echo_n "(cached) " >&6 +else + if $as_echo 'TRUE=$(BAR$(V)) +BAR0=false +BAR1=true +V=1 +am__doit: + @$(TRUE) +.PHONY: am__doit' | $am_make -f - >/dev/null 2>&1; then + am_cv_make_support_nested_variables=yes +else + am_cv_make_support_nested_variables=no +fi +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $am_cv_make_support_nested_variables" >&5 +$as_echo "$am_cv_make_support_nested_variables" >&6; } +if test $am_cv_make_support_nested_variables = yes; then + AM_V='$(V)' + AM_DEFAULT_V='$(AM_DEFAULT_VERBOSITY)' +else + AM_V=$AM_DEFAULT_VERBOSITY + AM_DEFAULT_V=$AM_DEFAULT_VERBOSITY +fi +AM_BACKSLASH='\' + +ac_config_headers="$ac_config_headers src/config.h" + + +# This is a new thing required to stop a warning from automake 1.12 +DEPDIR="${am__leading_dot}deps" + +ac_config_commands="$ac_config_commands depfiles" + + +am_make=${MAKE-make} +cat > confinc << 'END' +am__doit: + @echo this is the am__doit target +.PHONY: am__doit +END +# If we don't find an include directive, just comment out the code. +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for style of include used by $am_make" >&5 +$as_echo_n "checking for style of include used by $am_make... " >&6; } +am__include="#" +am__quote= +_am_result=none +# First try GNU make style include. +echo "include confinc" > confmf +# Ignore all kinds of additional output from 'make'. +case `$am_make -s -f confmf 2> /dev/null` in #( +*the\ am__doit\ target*) + am__include=include + am__quote= + _am_result=GNU + ;; +esac +# Now try BSD make style include. +if test "$am__include" = "#"; then + echo '.include "confinc"' > confmf + case `$am_make -s -f confmf 2> /dev/null` in #( + *the\ am__doit\ target*) + am__include=.include + am__quote="\"" + _am_result=BSD + ;; + esac +fi + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $_am_result" >&5 +$as_echo "$_am_result" >&6; } +rm -f confinc confmf + +# Check whether --enable-dependency-tracking was given. +if test "${enable_dependency_tracking+set}" = set; then : + enableval=$enable_dependency_tracking; +fi + +if test "x$enable_dependency_tracking" != xno; then + am_depcomp="$ac_aux_dir/depcomp" + AMDEPBACKSLASH='\' + am__nodep='_no' +fi + if test "x$enable_dependency_tracking" != xno; then + AMDEP_TRUE= + AMDEP_FALSE='#' +else + AMDEP_TRUE='#' + AMDEP_FALSE= +fi + + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu +if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}gcc", so it can be a program name with args. +set dummy ${ac_tool_prefix}gcc; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_CC+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$CC"; then + ac_cv_prog_CC="$CC" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_CC="${ac_tool_prefix}gcc" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +CC=$ac_cv_prog_CC +if test -n "$CC"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $CC" >&5 +$as_echo "$CC" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_prog_CC"; then + ac_ct_CC=$CC + # Extract the first word of "gcc", so it can be a program name with args. +set dummy gcc; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_CC+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_CC"; then + ac_cv_prog_ac_ct_CC="$ac_ct_CC" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_CC="gcc" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_CC=$ac_cv_prog_ac_ct_CC +if test -n "$ac_ct_CC"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_CC" >&5 +$as_echo "$ac_ct_CC" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_ct_CC" = x; then + CC="" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + CC=$ac_ct_CC + fi +else + CC="$ac_cv_prog_CC" +fi + +if test -z "$CC"; then + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}cc", so it can be a program name with args. +set dummy ${ac_tool_prefix}cc; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_CC+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$CC"; then + ac_cv_prog_CC="$CC" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_CC="${ac_tool_prefix}cc" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +CC=$ac_cv_prog_CC +if test -n "$CC"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $CC" >&5 +$as_echo "$CC" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + fi +fi +if test -z "$CC"; then + # Extract the first word of "cc", so it can be a program name with args. +set dummy cc; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_CC+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$CC"; then + ac_cv_prog_CC="$CC" # Let the user override the test. +else + ac_prog_rejected=no +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + if test "$as_dir/$ac_word$ac_exec_ext" = "/usr/ucb/cc"; then + ac_prog_rejected=yes + continue + fi + ac_cv_prog_CC="cc" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +if test $ac_prog_rejected = yes; then + # We found a bogon in the path, so make sure we never use it. + set dummy $ac_cv_prog_CC + shift + if test $# != 0; then + # We chose a different compiler from the bogus one. + # However, it has the same basename, so the bogon will be chosen + # first if we set CC to just the basename; use the full file name. + shift + ac_cv_prog_CC="$as_dir/$ac_word${1+' '}$@" + fi +fi +fi +fi +CC=$ac_cv_prog_CC +if test -n "$CC"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $CC" >&5 +$as_echo "$CC" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$CC"; then + if test -n "$ac_tool_prefix"; then + for ac_prog in cl.exe + do + # Extract the first word of "$ac_tool_prefix$ac_prog", so it can be a program name with args. +set dummy $ac_tool_prefix$ac_prog; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_CC+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$CC"; then + ac_cv_prog_CC="$CC" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_CC="$ac_tool_prefix$ac_prog" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +CC=$ac_cv_prog_CC +if test -n "$CC"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $CC" >&5 +$as_echo "$CC" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + test -n "$CC" && break + done +fi +if test -z "$CC"; then + ac_ct_CC=$CC + for ac_prog in cl.exe +do + # Extract the first word of "$ac_prog", so it can be a program name with args. +set dummy $ac_prog; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_CC+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_CC"; then + ac_cv_prog_ac_ct_CC="$ac_ct_CC" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_CC="$ac_prog" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_CC=$ac_cv_prog_ac_ct_CC +if test -n "$ac_ct_CC"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_CC" >&5 +$as_echo "$ac_ct_CC" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + test -n "$ac_ct_CC" && break +done + + if test "x$ac_ct_CC" = x; then + CC="" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + CC=$ac_ct_CC + fi +fi + +fi + + +test -z "$CC" && { { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5 +$as_echo "$as_me: error: in \`$ac_pwd':" >&2;} +as_fn_error $? "no acceptable C compiler found in \$PATH +See \`config.log' for more details" "$LINENO" 5; } + +# Provide some information about the compiler. +$as_echo "$as_me:${as_lineno-$LINENO}: checking for C compiler version" >&5 +set X $ac_compile +ac_compiler=$2 +for ac_option in --version -v -V -qversion; do + { { ac_try="$ac_compiler $ac_option >&5" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\"" +$as_echo "$ac_try_echo"; } >&5 + (eval "$ac_compiler $ac_option >&5") 2>conftest.err + ac_status=$? + if test -s conftest.err; then + sed '10a\ +... rest of stderr output deleted ... + 10q' conftest.err >conftest.er1 + cat conftest.er1 >&5 + fi + rm -f conftest.er1 conftest.err + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } +done + +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +ac_clean_files_save=$ac_clean_files +ac_clean_files="$ac_clean_files a.out a.out.dSYM a.exe b.out" +# Try to create an executable without -o first, disregard a.out. +# It will help us diagnose broken compilers, and finding out an intuition +# of exeext. +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether the C compiler works" >&5 +$as_echo_n "checking whether the C compiler works... " >&6; } +ac_link_default=`$as_echo "$ac_link" | sed 's/ -o *conftest[^ ]*//'` + +# The possible output files: +ac_files="a.out conftest.exe conftest a.exe a_out.exe b.out conftest.*" + +ac_rmfiles= +for ac_file in $ac_files +do + case $ac_file in + *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg | *.map | *.inf | *.dSYM | *.o | *.obj ) ;; + * ) ac_rmfiles="$ac_rmfiles $ac_file";; + esac +done +rm -f $ac_rmfiles + +if { { ac_try="$ac_link_default" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\"" +$as_echo "$ac_try_echo"; } >&5 + (eval "$ac_link_default") 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; }; then : + # Autoconf-2.13 could set the ac_cv_exeext variable to `no'. +# So ignore a value of `no', otherwise this would lead to `EXEEXT = no' +# in a Makefile. We should not override ac_cv_exeext if it was cached, +# so that the user can short-circuit this test for compilers unknown to +# Autoconf. +for ac_file in $ac_files '' +do + test -f "$ac_file" || continue + case $ac_file in + *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg | *.map | *.inf | *.dSYM | *.o | *.obj ) + ;; + [ab].out ) + # We found the default executable, but exeext='' is most + # certainly right. + break;; + *.* ) + if test "${ac_cv_exeext+set}" = set && test "$ac_cv_exeext" != no; + then :; else + ac_cv_exeext=`expr "$ac_file" : '[^.]*\(\..*\)'` + fi + # We set ac_cv_exeext here because the later test for it is not + # safe: cross compilers may not add the suffix if given an `-o' + # argument, so we may need to know it at that point already. + # Even if this section looks crufty: it has the advantage of + # actually working. + break;; + * ) + break;; + esac +done +test "$ac_cv_exeext" = no && ac_cv_exeext= + +else + ac_file='' +fi +if test -z "$ac_file"; then : + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +$as_echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +{ { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5 +$as_echo "$as_me: error: in \`$ac_pwd':" >&2;} +as_fn_error 77 "C compiler cannot create executables +See \`config.log' for more details" "$LINENO" 5; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5 +$as_echo "yes" >&6; } +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for C compiler default output file name" >&5 +$as_echo_n "checking for C compiler default output file name... " >&6; } +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_file" >&5 +$as_echo "$ac_file" >&6; } +ac_exeext=$ac_cv_exeext + +rm -f -r a.out a.out.dSYM a.exe conftest$ac_cv_exeext b.out +ac_clean_files=$ac_clean_files_save +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for suffix of executables" >&5 +$as_echo_n "checking for suffix of executables... " >&6; } +if { { ac_try="$ac_link" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\"" +$as_echo "$ac_try_echo"; } >&5 + (eval "$ac_link") 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; }; then : + # If both `conftest.exe' and `conftest' are `present' (well, observable) +# catch `conftest.exe'. For instance with Cygwin, `ls conftest' will +# work properly (i.e., refer to `conftest.exe'), while it won't with +# `rm'. +for ac_file in conftest.exe conftest conftest.*; do + test -f "$ac_file" || continue + case $ac_file in + *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg | *.map | *.inf | *.dSYM | *.o | *.obj ) ;; + *.* ) ac_cv_exeext=`expr "$ac_file" : '[^.]*\(\..*\)'` + break;; + * ) break;; + esac +done +else + { { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5 +$as_echo "$as_me: error: in \`$ac_pwd':" >&2;} +as_fn_error $? "cannot compute suffix of executables: cannot compile and link +See \`config.log' for more details" "$LINENO" 5; } +fi +rm -f conftest conftest$ac_cv_exeext +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_exeext" >&5 +$as_echo "$ac_cv_exeext" >&6; } + +rm -f conftest.$ac_ext +EXEEXT=$ac_cv_exeext +ac_exeext=$EXEEXT +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#include +int +main () +{ +FILE *f = fopen ("conftest.out", "w"); + return ferror (f) || fclose (f) != 0; + + ; + return 0; +} +_ACEOF +ac_clean_files="$ac_clean_files conftest.out" +# Check that the compiler produces executables we can run. If not, either +# the compiler is broken, or we cross compile. +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether we are cross compiling" >&5 +$as_echo_n "checking whether we are cross compiling... " >&6; } +if test "$cross_compiling" != yes; then + { { ac_try="$ac_link" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\"" +$as_echo "$ac_try_echo"; } >&5 + (eval "$ac_link") 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } + if { ac_try='./conftest$ac_cv_exeext' + { { case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\"" +$as_echo "$ac_try_echo"; } >&5 + (eval "$ac_try") 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; }; }; then + cross_compiling=no + else + if test "$cross_compiling" = maybe; then + cross_compiling=yes + else + { { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5 +$as_echo "$as_me: error: in \`$ac_pwd':" >&2;} +as_fn_error $? "cannot run C compiled programs. +If you meant to cross compile, use \`--host'. +See \`config.log' for more details" "$LINENO" 5; } + fi + fi +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $cross_compiling" >&5 +$as_echo "$cross_compiling" >&6; } + +rm -f conftest.$ac_ext conftest$ac_cv_exeext conftest.out +ac_clean_files=$ac_clean_files_save +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for suffix of object files" >&5 +$as_echo_n "checking for suffix of object files... " >&6; } +if ${ac_cv_objext+:} false; then : + $as_echo_n "(cached) " >&6 +else + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +rm -f conftest.o conftest.obj +if { { ac_try="$ac_compile" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\"" +$as_echo "$ac_try_echo"; } >&5 + (eval "$ac_compile") 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; }; then : + for ac_file in conftest.o conftest.obj conftest.*; do + test -f "$ac_file" || continue; + case $ac_file in + *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg | *.map | *.inf | *.dSYM ) ;; + *) ac_cv_objext=`expr "$ac_file" : '.*\.\(.*\)'` + break;; + esac +done +else + $as_echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +{ { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5 +$as_echo "$as_me: error: in \`$ac_pwd':" >&2;} +as_fn_error $? "cannot compute suffix of object files: cannot compile +See \`config.log' for more details" "$LINENO" 5; } +fi +rm -f conftest.$ac_cv_objext conftest.$ac_ext +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_objext" >&5 +$as_echo "$ac_cv_objext" >&6; } +OBJEXT=$ac_cv_objext +ac_objext=$OBJEXT +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether we are using the GNU C compiler" >&5 +$as_echo_n "checking whether we are using the GNU C compiler... " >&6; } +if ${ac_cv_c_compiler_gnu+:} false; then : + $as_echo_n "(cached) " >&6 +else + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ +#ifndef __GNUC__ + choke me +#endif + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + ac_compiler_gnu=yes +else + ac_compiler_gnu=no +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext +ac_cv_c_compiler_gnu=$ac_compiler_gnu + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_c_compiler_gnu" >&5 +$as_echo "$ac_cv_c_compiler_gnu" >&6; } +if test $ac_compiler_gnu = yes; then + GCC=yes +else + GCC= +fi +ac_test_CFLAGS=${CFLAGS+set} +ac_save_CFLAGS=$CFLAGS +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether $CC accepts -g" >&5 +$as_echo_n "checking whether $CC accepts -g... " >&6; } +if ${ac_cv_prog_cc_g+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_save_c_werror_flag=$ac_c_werror_flag + ac_c_werror_flag=yes + ac_cv_prog_cc_g=no + CFLAGS="-g" + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + ac_cv_prog_cc_g=yes +else + CFLAGS="" + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + +else + ac_c_werror_flag=$ac_save_c_werror_flag + CFLAGS="-g" + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + ac_cv_prog_cc_g=yes +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext + ac_c_werror_flag=$ac_save_c_werror_flag +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_prog_cc_g" >&5 +$as_echo "$ac_cv_prog_cc_g" >&6; } +if test "$ac_test_CFLAGS" = set; then + CFLAGS=$ac_save_CFLAGS +elif test $ac_cv_prog_cc_g = yes; then + if test "$GCC" = yes; then + CFLAGS="-g -O2" + else + CFLAGS="-g" + fi +else + if test "$GCC" = yes; then + CFLAGS="-O2" + else + CFLAGS= + fi +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $CC option to accept ISO C89" >&5 +$as_echo_n "checking for $CC option to accept ISO C89... " >&6; } +if ${ac_cv_prog_cc_c89+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_cv_prog_cc_c89=no +ac_save_CC=$CC +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#include +#include +struct stat; +/* Most of the following tests are stolen from RCS 5.7's src/conf.sh. */ +struct buf { int x; }; +FILE * (*rcsopen) (struct buf *, struct stat *, int); +static char *e (p, i) + char **p; + int i; +{ + return p[i]; +} +static char *f (char * (*g) (char **, int), char **p, ...) +{ + char *s; + va_list v; + va_start (v,p); + s = g (p, va_arg (v,int)); + va_end (v); + return s; +} + +/* OSF 4.0 Compaq cc is some sort of almost-ANSI by default. It has + function prototypes and stuff, but not '\xHH' hex character constants. + These don't provoke an error unfortunately, instead are silently treated + as 'x'. The following induces an error, until -std is added to get + proper ANSI mode. Curiously '\x00'!='x' always comes out true, for an + array size at least. It's necessary to write '\x00'==0 to get something + that's true only with -std. */ +int osf4_cc_array ['\x00' == 0 ? 1 : -1]; + +/* IBM C 6 for AIX is almost-ANSI by default, but it replaces macro parameters + inside strings and character constants. */ +#define FOO(x) 'x' +int xlc6_cc_array[FOO(a) == 'x' ? 1 : -1]; + +int test (int i, double x); +struct s1 {int (*f) (int a);}; +struct s2 {int (*f) (double a);}; +int pairnames (int, char **, FILE *(*)(struct buf *, struct stat *, int), int, int); +int argc; +char **argv; +int +main () +{ +return f (e, argv, 0) != argv[0] || f (e, argv, 1) != argv[1]; + ; + return 0; +} +_ACEOF +for ac_arg in '' -qlanglvl=extc89 -qlanglvl=ansi -std \ + -Ae "-Aa -D_HPUX_SOURCE" "-Xc -D__EXTENSIONS__" +do + CC="$ac_save_CC $ac_arg" + if ac_fn_c_try_compile "$LINENO"; then : + ac_cv_prog_cc_c89=$ac_arg +fi +rm -f core conftest.err conftest.$ac_objext + test "x$ac_cv_prog_cc_c89" != "xno" && break +done +rm -f conftest.$ac_ext +CC=$ac_save_CC + +fi +# AC_CACHE_VAL +case "x$ac_cv_prog_cc_c89" in + x) + { $as_echo "$as_me:${as_lineno-$LINENO}: result: none needed" >&5 +$as_echo "none needed" >&6; } ;; + xno) + { $as_echo "$as_me:${as_lineno-$LINENO}: result: unsupported" >&5 +$as_echo "unsupported" >&6; } ;; + *) + CC="$CC $ac_cv_prog_cc_c89" + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_prog_cc_c89" >&5 +$as_echo "$ac_cv_prog_cc_c89" >&6; } ;; +esac +if test "x$ac_cv_prog_cc_c89" != xno; then : + +fi + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether $CC understands -c and -o together" >&5 +$as_echo_n "checking whether $CC understands -c and -o together... " >&6; } +if ${am_cv_prog_cc_c_o+:} false; then : + $as_echo_n "(cached) " >&6 +else + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF + # Make sure it works both with $CC and with simple cc. + # Following AC_PROG_CC_C_O, we do the test twice because some + # compilers refuse to overwrite an existing .o file with -o, + # though they will create one. + am_cv_prog_cc_c_o=yes + for am_i in 1 2; do + if { echo "$as_me:$LINENO: $CC -c conftest.$ac_ext -o conftest2.$ac_objext" >&5 + ($CC -c conftest.$ac_ext -o conftest2.$ac_objext) >&5 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } \ + && test -f conftest2.$ac_objext; then + : OK + else + am_cv_prog_cc_c_o=no + break + fi + done + rm -f core conftest* + unset am_i +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $am_cv_prog_cc_c_o" >&5 +$as_echo "$am_cv_prog_cc_c_o" >&6; } +if test "$am_cv_prog_cc_c_o" != yes; then + # Losing compiler, so override with the script. + # FIXME: It is wrong to rewrite CC. + # But if we don't then we get into trouble of one sort or another. + # A longer-term fix would be to have automake use am__CC in this case, + # and then we could set am__CC="\$(top_srcdir)/compile \$(CC)" + CC="$am_aux_dir/compile $CC" +fi +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + + +depcc="$CC" am_compiler_list= + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking dependency style of $depcc" >&5 +$as_echo_n "checking dependency style of $depcc... " >&6; } +if ${am_cv_CC_dependencies_compiler_type+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -z "$AMDEP_TRUE" && test -f "$am_depcomp"; then + # We make a subdir and do the tests there. Otherwise we can end up + # making bogus files that we don't know about and never remove. For + # instance it was reported that on HP-UX the gcc test will end up + # making a dummy file named 'D' -- because '-MD' means "put the output + # in D". + rm -rf conftest.dir + mkdir conftest.dir + # Copy depcomp to subdir because otherwise we won't find it if we're + # using a relative directory. + cp "$am_depcomp" conftest.dir + cd conftest.dir + # We will build objects and dependencies in a subdirectory because + # it helps to detect inapplicable dependency modes. For instance + # both Tru64's cc and ICC support -MD to output dependencies as a + # side effect of compilation, but ICC will put the dependencies in + # the current directory while Tru64 will put them in the object + # directory. + mkdir sub + + am_cv_CC_dependencies_compiler_type=none + if test "$am_compiler_list" = ""; then + am_compiler_list=`sed -n 's/^#*\([a-zA-Z0-9]*\))$/\1/p' < ./depcomp` + fi + am__universal=false + case " $depcc " in #( + *\ -arch\ *\ -arch\ *) am__universal=true ;; + esac + + for depmode in $am_compiler_list; do + # Setup a source with many dependencies, because some compilers + # like to wrap large dependency lists on column 80 (with \), and + # we should not choose a depcomp mode which is confused by this. + # + # We need to recreate these files for each test, as the compiler may + # overwrite some of them when testing with obscure command lines. + # This happens at least with the AIX C compiler. + : > sub/conftest.c + for i in 1 2 3 4 5 6; do + echo '#include "conftst'$i'.h"' >> sub/conftest.c + # Using ": > sub/conftst$i.h" creates only sub/conftst1.h with + # Solaris 10 /bin/sh. + echo '/* dummy */' > sub/conftst$i.h + done + echo "${am__include} ${am__quote}sub/conftest.Po${am__quote}" > confmf + + # We check with '-c' and '-o' for the sake of the "dashmstdout" + # mode. It turns out that the SunPro C++ compiler does not properly + # handle '-M -o', and we need to detect this. Also, some Intel + # versions had trouble with output in subdirs. + am__obj=sub/conftest.${OBJEXT-o} + am__minus_obj="-o $am__obj" + case $depmode in + gcc) + # This depmode causes a compiler race in universal mode. + test "$am__universal" = false || continue + ;; + nosideeffect) + # After this tag, mechanisms are not by side-effect, so they'll + # only be used when explicitly requested. + if test "x$enable_dependency_tracking" = xyes; then + continue + else + break + fi + ;; + msvc7 | msvc7msys | msvisualcpp | msvcmsys) + # This compiler won't grok '-c -o', but also, the minuso test has + # not run yet. These depmodes are late enough in the game, and + # so weak that their functioning should not be impacted. + am__obj=conftest.${OBJEXT-o} + am__minus_obj= + ;; + none) break ;; + esac + if depmode=$depmode \ + source=sub/conftest.c object=$am__obj \ + depfile=sub/conftest.Po tmpdepfile=sub/conftest.TPo \ + $SHELL ./depcomp $depcc -c $am__minus_obj sub/conftest.c \ + >/dev/null 2>conftest.err && + grep sub/conftst1.h sub/conftest.Po > /dev/null 2>&1 && + grep sub/conftst6.h sub/conftest.Po > /dev/null 2>&1 && + grep $am__obj sub/conftest.Po > /dev/null 2>&1 && + ${MAKE-make} -s -f confmf > /dev/null 2>&1; then + # icc doesn't choke on unknown options, it will just issue warnings + # or remarks (even with -Werror). So we grep stderr for any message + # that says an option was ignored or not supported. + # When given -MP, icc 7.0 and 7.1 complain thusly: + # icc: Command line warning: ignoring option '-M'; no argument required + # The diagnosis changed in icc 8.0: + # icc: Command line remark: option '-MP' not supported + if (grep 'ignoring option' conftest.err || + grep 'not supported' conftest.err) >/dev/null 2>&1; then :; else + am_cv_CC_dependencies_compiler_type=$depmode + break + fi + fi + done + + cd .. + rm -rf conftest.dir +else + am_cv_CC_dependencies_compiler_type=none +fi + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $am_cv_CC_dependencies_compiler_type" >&5 +$as_echo "$am_cv_CC_dependencies_compiler_type" >&6; } +CCDEPMODE=depmode=$am_cv_CC_dependencies_compiler_type + + if + test "x$enable_dependency_tracking" != xno \ + && test "$am_cv_CC_dependencies_compiler_type" = gcc3; then + am__fastdepCC_TRUE= + am__fastdepCC_FALSE='#' +else + am__fastdepCC_TRUE='#' + am__fastdepCC_FALSE= +fi + + + +if test -n "$ac_tool_prefix"; then + for ac_prog in ar lib "link -lib" + do + # Extract the first word of "$ac_tool_prefix$ac_prog", so it can be a program name with args. +set dummy $ac_tool_prefix$ac_prog; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_AR+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$AR"; then + ac_cv_prog_AR="$AR" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_AR="$ac_tool_prefix$ac_prog" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +AR=$ac_cv_prog_AR +if test -n "$AR"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $AR" >&5 +$as_echo "$AR" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + test -n "$AR" && break + done +fi +if test -z "$AR"; then + ac_ct_AR=$AR + for ac_prog in ar lib "link -lib" +do + # Extract the first word of "$ac_prog", so it can be a program name with args. +set dummy $ac_prog; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_AR+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_AR"; then + ac_cv_prog_ac_ct_AR="$ac_ct_AR" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_AR="$ac_prog" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_AR=$ac_cv_prog_ac_ct_AR +if test -n "$ac_ct_AR"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_AR" >&5 +$as_echo "$ac_ct_AR" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + test -n "$ac_ct_AR" && break +done + + if test "x$ac_ct_AR" = x; then + AR="false" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + AR=$ac_ct_AR + fi +fi + +: ${AR=ar} + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking the archiver ($AR) interface" >&5 +$as_echo_n "checking the archiver ($AR) interface... " >&6; } +if ${am_cv_ar_interface+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + + am_cv_ar_interface=ar + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +int some_variable = 0; +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + am_ar_try='$AR cru libconftest.a conftest.$ac_objext >&5' + { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$am_ar_try\""; } >&5 + (eval $am_ar_try) 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } + if test "$ac_status" -eq 0; then + am_cv_ar_interface=ar + else + am_ar_try='$AR -NOLOGO -OUT:conftest.lib conftest.$ac_objext >&5' + { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$am_ar_try\""; } >&5 + (eval $am_ar_try) 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } + if test "$ac_status" -eq 0; then + am_cv_ar_interface=lib + else + am_cv_ar_interface=unknown + fi + fi + rm -f conftest.lib libconftest.a + +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext + ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $am_cv_ar_interface" >&5 +$as_echo "$am_cv_ar_interface" >&6; } + +case $am_cv_ar_interface in +ar) + ;; +lib) + # Microsoft lib, so override with the ar-lib wrapper script. + # FIXME: It is wrong to rewrite AR. + # But if we don't then we get into trouble of one sort or another. + # A longer-term fix would be to have automake use am__AR in this case, + # and then we could set am__AR="$am_aux_dir/ar-lib \$(AR)" or something + # similar. + AR="$am_aux_dir/ar-lib $AR" + ;; +unknown) + as_fn_error $? "could not determine $AR interface" "$LINENO" 5 + ;; +esac + + +# This was added at the suggestion of libtoolize (03-Jan-10) + + +# The default CFLAGS in Autoconf are "-g -O2" for gcc and just "-g" for any +# other compiler. There doesn't seem to be a standard way of getting rid of the +# -g (which I don't think is needed for a production library). This fudge seems +# to achieve the necessary. First, we remember the externally set values of +# CFLAGS. Then call the AC_PROG_CC macro to find the compiler - if CFLAGS is +# not set, it will be set to Autoconf's defaults. Afterwards, if the original +# values were not set, remove the -g from the Autoconf defaults. + +remember_set_CFLAGS="$CFLAGS" + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu +if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}gcc", so it can be a program name with args. +set dummy ${ac_tool_prefix}gcc; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_CC+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$CC"; then + ac_cv_prog_CC="$CC" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_CC="${ac_tool_prefix}gcc" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +CC=$ac_cv_prog_CC +if test -n "$CC"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $CC" >&5 +$as_echo "$CC" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_prog_CC"; then + ac_ct_CC=$CC + # Extract the first word of "gcc", so it can be a program name with args. +set dummy gcc; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_CC+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_CC"; then + ac_cv_prog_ac_ct_CC="$ac_ct_CC" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_CC="gcc" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_CC=$ac_cv_prog_ac_ct_CC +if test -n "$ac_ct_CC"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_CC" >&5 +$as_echo "$ac_ct_CC" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_ct_CC" = x; then + CC="" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + CC=$ac_ct_CC + fi +else + CC="$ac_cv_prog_CC" +fi + +if test -z "$CC"; then + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}cc", so it can be a program name with args. +set dummy ${ac_tool_prefix}cc; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_CC+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$CC"; then + ac_cv_prog_CC="$CC" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_CC="${ac_tool_prefix}cc" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +CC=$ac_cv_prog_CC +if test -n "$CC"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $CC" >&5 +$as_echo "$CC" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + fi +fi +if test -z "$CC"; then + # Extract the first word of "cc", so it can be a program name with args. +set dummy cc; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_CC+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$CC"; then + ac_cv_prog_CC="$CC" # Let the user override the test. +else + ac_prog_rejected=no +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + if test "$as_dir/$ac_word$ac_exec_ext" = "/usr/ucb/cc"; then + ac_prog_rejected=yes + continue + fi + ac_cv_prog_CC="cc" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +if test $ac_prog_rejected = yes; then + # We found a bogon in the path, so make sure we never use it. + set dummy $ac_cv_prog_CC + shift + if test $# != 0; then + # We chose a different compiler from the bogus one. + # However, it has the same basename, so the bogon will be chosen + # first if we set CC to just the basename; use the full file name. + shift + ac_cv_prog_CC="$as_dir/$ac_word${1+' '}$@" + fi +fi +fi +fi +CC=$ac_cv_prog_CC +if test -n "$CC"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $CC" >&5 +$as_echo "$CC" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$CC"; then + if test -n "$ac_tool_prefix"; then + for ac_prog in cl.exe + do + # Extract the first word of "$ac_tool_prefix$ac_prog", so it can be a program name with args. +set dummy $ac_tool_prefix$ac_prog; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_CC+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$CC"; then + ac_cv_prog_CC="$CC" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_CC="$ac_tool_prefix$ac_prog" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +CC=$ac_cv_prog_CC +if test -n "$CC"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $CC" >&5 +$as_echo "$CC" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + test -n "$CC" && break + done +fi +if test -z "$CC"; then + ac_ct_CC=$CC + for ac_prog in cl.exe +do + # Extract the first word of "$ac_prog", so it can be a program name with args. +set dummy $ac_prog; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_CC+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_CC"; then + ac_cv_prog_ac_ct_CC="$ac_ct_CC" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_CC="$ac_prog" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_CC=$ac_cv_prog_ac_ct_CC +if test -n "$ac_ct_CC"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_CC" >&5 +$as_echo "$ac_ct_CC" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + test -n "$ac_ct_CC" && break +done + + if test "x$ac_ct_CC" = x; then + CC="" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + CC=$ac_ct_CC + fi +fi + +fi + + +test -z "$CC" && { { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5 +$as_echo "$as_me: error: in \`$ac_pwd':" >&2;} +as_fn_error $? "no acceptable C compiler found in \$PATH +See \`config.log' for more details" "$LINENO" 5; } + +# Provide some information about the compiler. +$as_echo "$as_me:${as_lineno-$LINENO}: checking for C compiler version" >&5 +set X $ac_compile +ac_compiler=$2 +for ac_option in --version -v -V -qversion; do + { { ac_try="$ac_compiler $ac_option >&5" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\"" +$as_echo "$ac_try_echo"; } >&5 + (eval "$ac_compiler $ac_option >&5") 2>conftest.err + ac_status=$? + if test -s conftest.err; then + sed '10a\ +... rest of stderr output deleted ... + 10q' conftest.err >conftest.er1 + cat conftest.er1 >&5 + fi + rm -f conftest.er1 conftest.err + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } +done + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether we are using the GNU C compiler" >&5 +$as_echo_n "checking whether we are using the GNU C compiler... " >&6; } +if ${ac_cv_c_compiler_gnu+:} false; then : + $as_echo_n "(cached) " >&6 +else + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ +#ifndef __GNUC__ + choke me +#endif + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + ac_compiler_gnu=yes +else + ac_compiler_gnu=no +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext +ac_cv_c_compiler_gnu=$ac_compiler_gnu + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_c_compiler_gnu" >&5 +$as_echo "$ac_cv_c_compiler_gnu" >&6; } +if test $ac_compiler_gnu = yes; then + GCC=yes +else + GCC= +fi +ac_test_CFLAGS=${CFLAGS+set} +ac_save_CFLAGS=$CFLAGS +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether $CC accepts -g" >&5 +$as_echo_n "checking whether $CC accepts -g... " >&6; } +if ${ac_cv_prog_cc_g+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_save_c_werror_flag=$ac_c_werror_flag + ac_c_werror_flag=yes + ac_cv_prog_cc_g=no + CFLAGS="-g" + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + ac_cv_prog_cc_g=yes +else + CFLAGS="" + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + +else + ac_c_werror_flag=$ac_save_c_werror_flag + CFLAGS="-g" + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + ac_cv_prog_cc_g=yes +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext + ac_c_werror_flag=$ac_save_c_werror_flag +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_prog_cc_g" >&5 +$as_echo "$ac_cv_prog_cc_g" >&6; } +if test "$ac_test_CFLAGS" = set; then + CFLAGS=$ac_save_CFLAGS +elif test $ac_cv_prog_cc_g = yes; then + if test "$GCC" = yes; then + CFLAGS="-g -O2" + else + CFLAGS="-g" + fi +else + if test "$GCC" = yes; then + CFLAGS="-O2" + else + CFLAGS= + fi +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $CC option to accept ISO C89" >&5 +$as_echo_n "checking for $CC option to accept ISO C89... " >&6; } +if ${ac_cv_prog_cc_c89+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_cv_prog_cc_c89=no +ac_save_CC=$CC +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#include +#include +struct stat; +/* Most of the following tests are stolen from RCS 5.7's src/conf.sh. */ +struct buf { int x; }; +FILE * (*rcsopen) (struct buf *, struct stat *, int); +static char *e (p, i) + char **p; + int i; +{ + return p[i]; +} +static char *f (char * (*g) (char **, int), char **p, ...) +{ + char *s; + va_list v; + va_start (v,p); + s = g (p, va_arg (v,int)); + va_end (v); + return s; +} + +/* OSF 4.0 Compaq cc is some sort of almost-ANSI by default. It has + function prototypes and stuff, but not '\xHH' hex character constants. + These don't provoke an error unfortunately, instead are silently treated + as 'x'. The following induces an error, until -std is added to get + proper ANSI mode. Curiously '\x00'!='x' always comes out true, for an + array size at least. It's necessary to write '\x00'==0 to get something + that's true only with -std. */ +int osf4_cc_array ['\x00' == 0 ? 1 : -1]; + +/* IBM C 6 for AIX is almost-ANSI by default, but it replaces macro parameters + inside strings and character constants. */ +#define FOO(x) 'x' +int xlc6_cc_array[FOO(a) == 'x' ? 1 : -1]; + +int test (int i, double x); +struct s1 {int (*f) (int a);}; +struct s2 {int (*f) (double a);}; +int pairnames (int, char **, FILE *(*)(struct buf *, struct stat *, int), int, int); +int argc; +char **argv; +int +main () +{ +return f (e, argv, 0) != argv[0] || f (e, argv, 1) != argv[1]; + ; + return 0; +} +_ACEOF +for ac_arg in '' -qlanglvl=extc89 -qlanglvl=ansi -std \ + -Ae "-Aa -D_HPUX_SOURCE" "-Xc -D__EXTENSIONS__" +do + CC="$ac_save_CC $ac_arg" + if ac_fn_c_try_compile "$LINENO"; then : + ac_cv_prog_cc_c89=$ac_arg +fi +rm -f core conftest.err conftest.$ac_objext + test "x$ac_cv_prog_cc_c89" != "xno" && break +done +rm -f conftest.$ac_ext +CC=$ac_save_CC + +fi +# AC_CACHE_VAL +case "x$ac_cv_prog_cc_c89" in + x) + { $as_echo "$as_me:${as_lineno-$LINENO}: result: none needed" >&5 +$as_echo "none needed" >&6; } ;; + xno) + { $as_echo "$as_me:${as_lineno-$LINENO}: result: unsupported" >&5 +$as_echo "unsupported" >&6; } ;; + *) + CC="$CC $ac_cv_prog_cc_c89" + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_prog_cc_c89" >&5 +$as_echo "$ac_cv_prog_cc_c89" >&6; } ;; +esac +if test "x$ac_cv_prog_cc_c89" != xno; then : + +fi + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether $CC understands -c and -o together" >&5 +$as_echo_n "checking whether $CC understands -c and -o together... " >&6; } +if ${am_cv_prog_cc_c_o+:} false; then : + $as_echo_n "(cached) " >&6 +else + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF + # Make sure it works both with $CC and with simple cc. + # Following AC_PROG_CC_C_O, we do the test twice because some + # compilers refuse to overwrite an existing .o file with -o, + # though they will create one. + am_cv_prog_cc_c_o=yes + for am_i in 1 2; do + if { echo "$as_me:$LINENO: $CC -c conftest.$ac_ext -o conftest2.$ac_objext" >&5 + ($CC -c conftest.$ac_ext -o conftest2.$ac_objext) >&5 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } \ + && test -f conftest2.$ac_objext; then + : OK + else + am_cv_prog_cc_c_o=no + break + fi + done + rm -f core conftest* + unset am_i +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $am_cv_prog_cc_c_o" >&5 +$as_echo "$am_cv_prog_cc_c_o" >&6; } +if test "$am_cv_prog_cc_c_o" != yes; then + # Losing compiler, so override with the script. + # FIXME: It is wrong to rewrite CC. + # But if we don't then we get into trouble of one sort or another. + # A longer-term fix would be to have automake use am__CC in this case, + # and then we could set am__CC="\$(top_srcdir)/compile \$(CC)" + CC="$am_aux_dir/compile $CC" +fi +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + + +depcc="$CC" am_compiler_list= + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking dependency style of $depcc" >&5 +$as_echo_n "checking dependency style of $depcc... " >&6; } +if ${am_cv_CC_dependencies_compiler_type+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -z "$AMDEP_TRUE" && test -f "$am_depcomp"; then + # We make a subdir and do the tests there. Otherwise we can end up + # making bogus files that we don't know about and never remove. For + # instance it was reported that on HP-UX the gcc test will end up + # making a dummy file named 'D' -- because '-MD' means "put the output + # in D". + rm -rf conftest.dir + mkdir conftest.dir + # Copy depcomp to subdir because otherwise we won't find it if we're + # using a relative directory. + cp "$am_depcomp" conftest.dir + cd conftest.dir + # We will build objects and dependencies in a subdirectory because + # it helps to detect inapplicable dependency modes. For instance + # both Tru64's cc and ICC support -MD to output dependencies as a + # side effect of compilation, but ICC will put the dependencies in + # the current directory while Tru64 will put them in the object + # directory. + mkdir sub + + am_cv_CC_dependencies_compiler_type=none + if test "$am_compiler_list" = ""; then + am_compiler_list=`sed -n 's/^#*\([a-zA-Z0-9]*\))$/\1/p' < ./depcomp` + fi + am__universal=false + case " $depcc " in #( + *\ -arch\ *\ -arch\ *) am__universal=true ;; + esac + + for depmode in $am_compiler_list; do + # Setup a source with many dependencies, because some compilers + # like to wrap large dependency lists on column 80 (with \), and + # we should not choose a depcomp mode which is confused by this. + # + # We need to recreate these files for each test, as the compiler may + # overwrite some of them when testing with obscure command lines. + # This happens at least with the AIX C compiler. + : > sub/conftest.c + for i in 1 2 3 4 5 6; do + echo '#include "conftst'$i'.h"' >> sub/conftest.c + # Using ": > sub/conftst$i.h" creates only sub/conftst1.h with + # Solaris 10 /bin/sh. + echo '/* dummy */' > sub/conftst$i.h + done + echo "${am__include} ${am__quote}sub/conftest.Po${am__quote}" > confmf + + # We check with '-c' and '-o' for the sake of the "dashmstdout" + # mode. It turns out that the SunPro C++ compiler does not properly + # handle '-M -o', and we need to detect this. Also, some Intel + # versions had trouble with output in subdirs. + am__obj=sub/conftest.${OBJEXT-o} + am__minus_obj="-o $am__obj" + case $depmode in + gcc) + # This depmode causes a compiler race in universal mode. + test "$am__universal" = false || continue + ;; + nosideeffect) + # After this tag, mechanisms are not by side-effect, so they'll + # only be used when explicitly requested. + if test "x$enable_dependency_tracking" = xyes; then + continue + else + break + fi + ;; + msvc7 | msvc7msys | msvisualcpp | msvcmsys) + # This compiler won't grok '-c -o', but also, the minuso test has + # not run yet. These depmodes are late enough in the game, and + # so weak that their functioning should not be impacted. + am__obj=conftest.${OBJEXT-o} + am__minus_obj= + ;; + none) break ;; + esac + if depmode=$depmode \ + source=sub/conftest.c object=$am__obj \ + depfile=sub/conftest.Po tmpdepfile=sub/conftest.TPo \ + $SHELL ./depcomp $depcc -c $am__minus_obj sub/conftest.c \ + >/dev/null 2>conftest.err && + grep sub/conftst1.h sub/conftest.Po > /dev/null 2>&1 && + grep sub/conftst6.h sub/conftest.Po > /dev/null 2>&1 && + grep $am__obj sub/conftest.Po > /dev/null 2>&1 && + ${MAKE-make} -s -f confmf > /dev/null 2>&1; then + # icc doesn't choke on unknown options, it will just issue warnings + # or remarks (even with -Werror). So we grep stderr for any message + # that says an option was ignored or not supported. + # When given -MP, icc 7.0 and 7.1 complain thusly: + # icc: Command line warning: ignoring option '-M'; no argument required + # The diagnosis changed in icc 8.0: + # icc: Command line remark: option '-MP' not supported + if (grep 'ignoring option' conftest.err || + grep 'not supported' conftest.err) >/dev/null 2>&1; then :; else + am_cv_CC_dependencies_compiler_type=$depmode + break + fi + fi + done + + cd .. + rm -rf conftest.dir +else + am_cv_CC_dependencies_compiler_type=none +fi + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $am_cv_CC_dependencies_compiler_type" >&5 +$as_echo "$am_cv_CC_dependencies_compiler_type" >&6; } +CCDEPMODE=depmode=$am_cv_CC_dependencies_compiler_type + + if + test "x$enable_dependency_tracking" != xno \ + && test "$am_cv_CC_dependencies_compiler_type" = gcc3; then + am__fastdepCC_TRUE= + am__fastdepCC_FALSE='#' +else + am__fastdepCC_TRUE='#' + am__fastdepCC_FALSE= +fi + + + + +if test "x$remember_set_CFLAGS" = "x" +then + if test "$CFLAGS" = "-g -O2" + then + CFLAGS="-O2" + elif test "$CFLAGS" = "-g" + then + CFLAGS="" + fi +fi + +# Check for a 64-bit integer type +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking how to run the C preprocessor" >&5 +$as_echo_n "checking how to run the C preprocessor... " >&6; } +# On Suns, sometimes $CPP names a directory. +if test -n "$CPP" && test -d "$CPP"; then + CPP= +fi +if test -z "$CPP"; then + if ${ac_cv_prog_CPP+:} false; then : + $as_echo_n "(cached) " >&6 +else + # Double quotes because CPP needs to be expanded + for CPP in "$CC -E" "$CC -E -traditional-cpp" "/lib/cpp" + do + ac_preproc_ok=false +for ac_c_preproc_warn_flag in '' yes +do + # Use a header file that comes with gcc, so configuring glibc + # with a fresh cross-compiler works. + # Prefer to if __STDC__ is defined, since + # exists even on freestanding compilers. + # On the NeXT, cc -E runs the code through the compiler's parser, + # not just through cpp. "Syntax error" is here to catch this case. + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#ifdef __STDC__ +# include +#else +# include +#endif + Syntax error +_ACEOF +if ac_fn_c_try_cpp "$LINENO"; then : + +else + # Broken: fails on valid input. +continue +fi +rm -f conftest.err conftest.i conftest.$ac_ext + + # OK, works on sane cases. Now check whether nonexistent headers + # can be detected and how. + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#include +_ACEOF +if ac_fn_c_try_cpp "$LINENO"; then : + # Broken: success on invalid input. +continue +else + # Passes both tests. +ac_preproc_ok=: +break +fi +rm -f conftest.err conftest.i conftest.$ac_ext + +done +# Because of `break', _AC_PREPROC_IFELSE's cleaning code was skipped. +rm -f conftest.i conftest.err conftest.$ac_ext +if $ac_preproc_ok; then : + break +fi + + done + ac_cv_prog_CPP=$CPP + +fi + CPP=$ac_cv_prog_CPP +else + ac_cv_prog_CPP=$CPP +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $CPP" >&5 +$as_echo "$CPP" >&6; } +ac_preproc_ok=false +for ac_c_preproc_warn_flag in '' yes +do + # Use a header file that comes with gcc, so configuring glibc + # with a fresh cross-compiler works. + # Prefer to if __STDC__ is defined, since + # exists even on freestanding compilers. + # On the NeXT, cc -E runs the code through the compiler's parser, + # not just through cpp. "Syntax error" is here to catch this case. + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#ifdef __STDC__ +# include +#else +# include +#endif + Syntax error +_ACEOF +if ac_fn_c_try_cpp "$LINENO"; then : + +else + # Broken: fails on valid input. +continue +fi +rm -f conftest.err conftest.i conftest.$ac_ext + + # OK, works on sane cases. Now check whether nonexistent headers + # can be detected and how. + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#include +_ACEOF +if ac_fn_c_try_cpp "$LINENO"; then : + # Broken: success on invalid input. +continue +else + # Passes both tests. +ac_preproc_ok=: +break +fi +rm -f conftest.err conftest.i conftest.$ac_ext + +done +# Because of `break', _AC_PREPROC_IFELSE's cleaning code was skipped. +rm -f conftest.i conftest.err conftest.$ac_ext +if $ac_preproc_ok; then : + +else + { { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5 +$as_echo "$as_me: error: in \`$ac_pwd':" >&2;} +as_fn_error $? "C preprocessor \"$CPP\" fails sanity check +See \`config.log' for more details" "$LINENO" 5; } +fi + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for grep that handles long lines and -e" >&5 +$as_echo_n "checking for grep that handles long lines and -e... " >&6; } +if ${ac_cv_path_GREP+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -z "$GREP"; then + ac_path_GREP_found=false + # Loop through the user's path and test for each of PROGNAME-LIST + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH$PATH_SEPARATOR/usr/xpg4/bin +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_prog in grep ggrep; do + for ac_exec_ext in '' $ac_executable_extensions; do + ac_path_GREP="$as_dir/$ac_prog$ac_exec_ext" + as_fn_executable_p "$ac_path_GREP" || continue +# Check for GNU ac_path_GREP and select it if it is found. + # Check for GNU $ac_path_GREP +case `"$ac_path_GREP" --version 2>&1` in +*GNU*) + ac_cv_path_GREP="$ac_path_GREP" ac_path_GREP_found=:;; +*) + ac_count=0 + $as_echo_n 0123456789 >"conftest.in" + while : + do + cat "conftest.in" "conftest.in" >"conftest.tmp" + mv "conftest.tmp" "conftest.in" + cp "conftest.in" "conftest.nl" + $as_echo 'GREP' >> "conftest.nl" + "$ac_path_GREP" -e 'GREP$' -e '-(cannot match)-' < "conftest.nl" >"conftest.out" 2>/dev/null || break + diff "conftest.out" "conftest.nl" >/dev/null 2>&1 || break + as_fn_arith $ac_count + 1 && ac_count=$as_val + if test $ac_count -gt ${ac_path_GREP_max-0}; then + # Best one so far, save it but keep looking for a better one + ac_cv_path_GREP="$ac_path_GREP" + ac_path_GREP_max=$ac_count + fi + # 10*(2^10) chars as input seems more than enough + test $ac_count -gt 10 && break + done + rm -f conftest.in conftest.tmp conftest.nl conftest.out;; +esac + + $ac_path_GREP_found && break 3 + done + done + done +IFS=$as_save_IFS + if test -z "$ac_cv_path_GREP"; then + as_fn_error $? "no acceptable grep could be found in $PATH$PATH_SEPARATOR/usr/xpg4/bin" "$LINENO" 5 + fi +else + ac_cv_path_GREP=$GREP +fi + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_path_GREP" >&5 +$as_echo "$ac_cv_path_GREP" >&6; } + GREP="$ac_cv_path_GREP" + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for egrep" >&5 +$as_echo_n "checking for egrep... " >&6; } +if ${ac_cv_path_EGREP+:} false; then : + $as_echo_n "(cached) " >&6 +else + if echo a | $GREP -E '(a|b)' >/dev/null 2>&1 + then ac_cv_path_EGREP="$GREP -E" + else + if test -z "$EGREP"; then + ac_path_EGREP_found=false + # Loop through the user's path and test for each of PROGNAME-LIST + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH$PATH_SEPARATOR/usr/xpg4/bin +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_prog in egrep; do + for ac_exec_ext in '' $ac_executable_extensions; do + ac_path_EGREP="$as_dir/$ac_prog$ac_exec_ext" + as_fn_executable_p "$ac_path_EGREP" || continue +# Check for GNU ac_path_EGREP and select it if it is found. + # Check for GNU $ac_path_EGREP +case `"$ac_path_EGREP" --version 2>&1` in +*GNU*) + ac_cv_path_EGREP="$ac_path_EGREP" ac_path_EGREP_found=:;; +*) + ac_count=0 + $as_echo_n 0123456789 >"conftest.in" + while : + do + cat "conftest.in" "conftest.in" >"conftest.tmp" + mv "conftest.tmp" "conftest.in" + cp "conftest.in" "conftest.nl" + $as_echo 'EGREP' >> "conftest.nl" + "$ac_path_EGREP" 'EGREP$' < "conftest.nl" >"conftest.out" 2>/dev/null || break + diff "conftest.out" "conftest.nl" >/dev/null 2>&1 || break + as_fn_arith $ac_count + 1 && ac_count=$as_val + if test $ac_count -gt ${ac_path_EGREP_max-0}; then + # Best one so far, save it but keep looking for a better one + ac_cv_path_EGREP="$ac_path_EGREP" + ac_path_EGREP_max=$ac_count + fi + # 10*(2^10) chars as input seems more than enough + test $ac_count -gt 10 && break + done + rm -f conftest.in conftest.tmp conftest.nl conftest.out;; +esac + + $ac_path_EGREP_found && break 3 + done + done + done +IFS=$as_save_IFS + if test -z "$ac_cv_path_EGREP"; then + as_fn_error $? "no acceptable egrep could be found in $PATH$PATH_SEPARATOR/usr/xpg4/bin" "$LINENO" 5 + fi +else + ac_cv_path_EGREP=$EGREP +fi + + fi +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_path_EGREP" >&5 +$as_echo "$ac_cv_path_EGREP" >&6; } + EGREP="$ac_cv_path_EGREP" + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for ANSI C header files" >&5 +$as_echo_n "checking for ANSI C header files... " >&6; } +if ${ac_cv_header_stdc+:} false; then : + $as_echo_n "(cached) " >&6 +else + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#include +#include +#include +#include + +int +main () +{ + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + ac_cv_header_stdc=yes +else + ac_cv_header_stdc=no +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext + +if test $ac_cv_header_stdc = yes; then + # SunOS 4.x string.h does not declare mem*, contrary to ANSI. + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#include + +_ACEOF +if (eval "$ac_cpp conftest.$ac_ext") 2>&5 | + $EGREP "memchr" >/dev/null 2>&1; then : + +else + ac_cv_header_stdc=no +fi +rm -f conftest* + +fi + +if test $ac_cv_header_stdc = yes; then + # ISC 2.0.2 stdlib.h does not declare free, contrary to ANSI. + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#include + +_ACEOF +if (eval "$ac_cpp conftest.$ac_ext") 2>&5 | + $EGREP "free" >/dev/null 2>&1; then : + +else + ac_cv_header_stdc=no +fi +rm -f conftest* + +fi + +if test $ac_cv_header_stdc = yes; then + # /bin/cc in Irix-4.0.5 gets non-ANSI ctype macros unless using -ansi. + if test "$cross_compiling" = yes; then : + : +else + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#include +#include +#if ((' ' & 0x0FF) == 0x020) +# define ISLOWER(c) ('a' <= (c) && (c) <= 'z') +# define TOUPPER(c) (ISLOWER(c) ? 'A' + ((c) - 'a') : (c)) +#else +# define ISLOWER(c) \ + (('a' <= (c) && (c) <= 'i') \ + || ('j' <= (c) && (c) <= 'r') \ + || ('s' <= (c) && (c) <= 'z')) +# define TOUPPER(c) (ISLOWER(c) ? ((c) | 0x40) : (c)) +#endif + +#define XOR(e, f) (((e) && !(f)) || (!(e) && (f))) +int +main () +{ + int i; + for (i = 0; i < 256; i++) + if (XOR (islower (i), ISLOWER (i)) + || toupper (i) != TOUPPER (i)) + return 2; + return 0; +} +_ACEOF +if ac_fn_c_try_run "$LINENO"; then : + +else + ac_cv_header_stdc=no +fi +rm -f core *.core core.conftest.* gmon.out bb.out conftest$ac_exeext \ + conftest.$ac_objext conftest.beam conftest.$ac_ext +fi + +fi +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_header_stdc" >&5 +$as_echo "$ac_cv_header_stdc" >&6; } +if test $ac_cv_header_stdc = yes; then + +$as_echo "#define STDC_HEADERS 1" >>confdefs.h + +fi + +# On IRIX 5.3, sys/types and inttypes.h are conflicting. +for ac_header in sys/types.h sys/stat.h stdlib.h string.h memory.h strings.h \ + inttypes.h stdint.h unistd.h +do : + as_ac_Header=`$as_echo "ac_cv_header_$ac_header" | $as_tr_sh` +ac_fn_c_check_header_compile "$LINENO" "$ac_header" "$as_ac_Header" "$ac_includes_default +" +if eval test \"x\$"$as_ac_Header"\" = x"yes"; then : + cat >>confdefs.h <<_ACEOF +#define `$as_echo "HAVE_$ac_header" | $as_tr_cpp` 1 +_ACEOF + +fi + +done + + +ac_fn_c_find_intX_t "$LINENO" "64" "ac_cv_c_int64_t" +case $ac_cv_c_int64_t in #( + no|yes) ;; #( + *) + +cat >>confdefs.h <<_ACEOF +#define int64_t $ac_cv_c_int64_t +_ACEOF +;; +esac + + + +# Make sure we can run config.sub. +$SHELL "$ac_aux_dir/config.sub" sun4 >/dev/null 2>&1 || + as_fn_error $? "cannot run $SHELL $ac_aux_dir/config.sub" "$LINENO" 5 + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking build system type" >&5 +$as_echo_n "checking build system type... " >&6; } +if ${ac_cv_build+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_build_alias=$build_alias +test "x$ac_build_alias" = x && + ac_build_alias=`$SHELL "$ac_aux_dir/config.guess"` +test "x$ac_build_alias" = x && + as_fn_error $? "cannot guess build type; you must specify one" "$LINENO" 5 +ac_cv_build=`$SHELL "$ac_aux_dir/config.sub" $ac_build_alias` || + as_fn_error $? "$SHELL $ac_aux_dir/config.sub $ac_build_alias failed" "$LINENO" 5 + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_build" >&5 +$as_echo "$ac_cv_build" >&6; } +case $ac_cv_build in +*-*-*) ;; +*) as_fn_error $? "invalid value of canonical build" "$LINENO" 5;; +esac +build=$ac_cv_build +ac_save_IFS=$IFS; IFS='-' +set x $ac_cv_build +shift +build_cpu=$1 +build_vendor=$2 +shift; shift +# Remember, the first character of IFS is used to create $*, +# except with old shells: +build_os=$* +IFS=$ac_save_IFS +case $build_os in *\ *) build_os=`echo "$build_os" | sed 's/ /-/g'`;; esac + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking host system type" >&5 +$as_echo_n "checking host system type... " >&6; } +if ${ac_cv_host+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test "x$host_alias" = x; then + ac_cv_host=$ac_cv_build +else + ac_cv_host=`$SHELL "$ac_aux_dir/config.sub" $host_alias` || + as_fn_error $? "$SHELL $ac_aux_dir/config.sub $host_alias failed" "$LINENO" 5 +fi + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_host" >&5 +$as_echo "$ac_cv_host" >&6; } +case $ac_cv_host in +*-*-*) ;; +*) as_fn_error $? "invalid value of canonical host" "$LINENO" 5;; +esac +host=$ac_cv_host +ac_save_IFS=$IFS; IFS='-' +set x $ac_cv_host +shift +host_cpu=$1 +host_vendor=$2 +shift; shift +# Remember, the first character of IFS is used to create $*, +# except with old shells: +host_os=$* +IFS=$ac_save_IFS +case $host_os in *\ *) host_os=`echo "$host_os" | sed 's/ /-/g'`;; esac + + +enable_win32_dll=yes + +case $host in +*-*-cygwin* | *-*-mingw* | *-*-pw32* | *-*-cegcc*) + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}as", so it can be a program name with args. +set dummy ${ac_tool_prefix}as; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_AS+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$AS"; then + ac_cv_prog_AS="$AS" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_AS="${ac_tool_prefix}as" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +AS=$ac_cv_prog_AS +if test -n "$AS"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $AS" >&5 +$as_echo "$AS" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_prog_AS"; then + ac_ct_AS=$AS + # Extract the first word of "as", so it can be a program name with args. +set dummy as; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_AS+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_AS"; then + ac_cv_prog_ac_ct_AS="$ac_ct_AS" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_AS="as" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_AS=$ac_cv_prog_ac_ct_AS +if test -n "$ac_ct_AS"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_AS" >&5 +$as_echo "$ac_ct_AS" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_ct_AS" = x; then + AS="false" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + AS=$ac_ct_AS + fi +else + AS="$ac_cv_prog_AS" +fi + + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}dlltool", so it can be a program name with args. +set dummy ${ac_tool_prefix}dlltool; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_DLLTOOL+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$DLLTOOL"; then + ac_cv_prog_DLLTOOL="$DLLTOOL" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_DLLTOOL="${ac_tool_prefix}dlltool" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +DLLTOOL=$ac_cv_prog_DLLTOOL +if test -n "$DLLTOOL"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $DLLTOOL" >&5 +$as_echo "$DLLTOOL" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_prog_DLLTOOL"; then + ac_ct_DLLTOOL=$DLLTOOL + # Extract the first word of "dlltool", so it can be a program name with args. +set dummy dlltool; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_DLLTOOL+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_DLLTOOL"; then + ac_cv_prog_ac_ct_DLLTOOL="$ac_ct_DLLTOOL" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_DLLTOOL="dlltool" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_DLLTOOL=$ac_cv_prog_ac_ct_DLLTOOL +if test -n "$ac_ct_DLLTOOL"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_DLLTOOL" >&5 +$as_echo "$ac_ct_DLLTOOL" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_ct_DLLTOOL" = x; then + DLLTOOL="false" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + DLLTOOL=$ac_ct_DLLTOOL + fi +else + DLLTOOL="$ac_cv_prog_DLLTOOL" +fi + + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}objdump", so it can be a program name with args. +set dummy ${ac_tool_prefix}objdump; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_OBJDUMP+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$OBJDUMP"; then + ac_cv_prog_OBJDUMP="$OBJDUMP" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_OBJDUMP="${ac_tool_prefix}objdump" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +OBJDUMP=$ac_cv_prog_OBJDUMP +if test -n "$OBJDUMP"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $OBJDUMP" >&5 +$as_echo "$OBJDUMP" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_prog_OBJDUMP"; then + ac_ct_OBJDUMP=$OBJDUMP + # Extract the first word of "objdump", so it can be a program name with args. +set dummy objdump; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_OBJDUMP+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_OBJDUMP"; then + ac_cv_prog_ac_ct_OBJDUMP="$ac_ct_OBJDUMP" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_OBJDUMP="objdump" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_OBJDUMP=$ac_cv_prog_ac_ct_OBJDUMP +if test -n "$ac_ct_OBJDUMP"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_OBJDUMP" >&5 +$as_echo "$ac_ct_OBJDUMP" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_ct_OBJDUMP" = x; then + OBJDUMP="false" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + OBJDUMP=$ac_ct_OBJDUMP + fi +else + OBJDUMP="$ac_cv_prog_OBJDUMP" +fi + + ;; +esac + +test -z "$AS" && AS=as + + + + + +test -z "$DLLTOOL" && DLLTOOL=dlltool + + + + + +test -z "$OBJDUMP" && OBJDUMP=objdump + + + + + + + +case `pwd` in + *\ * | *\ *) + { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: Libtool does not cope well with whitespace in \`pwd\`" >&5 +$as_echo "$as_me: WARNING: Libtool does not cope well with whitespace in \`pwd\`" >&2;} ;; +esac + + + +macro_version='2.4.6' +macro_revision='2.4.6' + + + + + + + + + + + + + +ltmain=$ac_aux_dir/ltmain.sh + +# Backslashify metacharacters that are still active within +# double-quoted strings. +sed_quote_subst='s/\(["`$\\]\)/\\\1/g' + +# Same as above, but do not quote variable references. +double_quote_subst='s/\(["`\\]\)/\\\1/g' + +# Sed substitution to delay expansion of an escaped shell variable in a +# double_quote_subst'ed string. +delay_variable_subst='s/\\\\\\\\\\\$/\\\\\\$/g' + +# Sed substitution to delay expansion of an escaped single quote. +delay_single_quote_subst='s/'\''/'\'\\\\\\\'\''/g' + +# Sed substitution to avoid accidental globbing in evaled expressions +no_glob_subst='s/\*/\\\*/g' + +ECHO='\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\' +ECHO=$ECHO$ECHO$ECHO$ECHO$ECHO +ECHO=$ECHO$ECHO$ECHO$ECHO$ECHO$ECHO + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking how to print strings" >&5 +$as_echo_n "checking how to print strings... " >&6; } +# Test print first, because it will be a builtin if present. +if test "X`( print -r -- -n ) 2>/dev/null`" = X-n && \ + test "X`print -r -- $ECHO 2>/dev/null`" = "X$ECHO"; then + ECHO='print -r --' +elif test "X`printf %s $ECHO 2>/dev/null`" = "X$ECHO"; then + ECHO='printf %s\n' +else + # Use this function as a fallback that always works. + func_fallback_echo () + { + eval 'cat <<_LTECHO_EOF +$1 +_LTECHO_EOF' + } + ECHO='func_fallback_echo' +fi + +# func_echo_all arg... +# Invoke $ECHO with all args, space-separated. +func_echo_all () +{ + $ECHO "" +} + +case $ECHO in + printf*) { $as_echo "$as_me:${as_lineno-$LINENO}: result: printf" >&5 +$as_echo "printf" >&6; } ;; + print*) { $as_echo "$as_me:${as_lineno-$LINENO}: result: print -r" >&5 +$as_echo "print -r" >&6; } ;; + *) { $as_echo "$as_me:${as_lineno-$LINENO}: result: cat" >&5 +$as_echo "cat" >&6; } ;; +esac + + + + + + + + + + + + + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for a sed that does not truncate output" >&5 +$as_echo_n "checking for a sed that does not truncate output... " >&6; } +if ${ac_cv_path_SED+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_script=s/aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb/ + for ac_i in 1 2 3 4 5 6 7; do + ac_script="$ac_script$as_nl$ac_script" + done + echo "$ac_script" 2>/dev/null | sed 99q >conftest.sed + { ac_script=; unset ac_script;} + if test -z "$SED"; then + ac_path_SED_found=false + # Loop through the user's path and test for each of PROGNAME-LIST + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_prog in sed gsed; do + for ac_exec_ext in '' $ac_executable_extensions; do + ac_path_SED="$as_dir/$ac_prog$ac_exec_ext" + as_fn_executable_p "$ac_path_SED" || continue +# Check for GNU ac_path_SED and select it if it is found. + # Check for GNU $ac_path_SED +case `"$ac_path_SED" --version 2>&1` in +*GNU*) + ac_cv_path_SED="$ac_path_SED" ac_path_SED_found=:;; +*) + ac_count=0 + $as_echo_n 0123456789 >"conftest.in" + while : + do + cat "conftest.in" "conftest.in" >"conftest.tmp" + mv "conftest.tmp" "conftest.in" + cp "conftest.in" "conftest.nl" + $as_echo '' >> "conftest.nl" + "$ac_path_SED" -f conftest.sed < "conftest.nl" >"conftest.out" 2>/dev/null || break + diff "conftest.out" "conftest.nl" >/dev/null 2>&1 || break + as_fn_arith $ac_count + 1 && ac_count=$as_val + if test $ac_count -gt ${ac_path_SED_max-0}; then + # Best one so far, save it but keep looking for a better one + ac_cv_path_SED="$ac_path_SED" + ac_path_SED_max=$ac_count + fi + # 10*(2^10) chars as input seems more than enough + test $ac_count -gt 10 && break + done + rm -f conftest.in conftest.tmp conftest.nl conftest.out;; +esac + + $ac_path_SED_found && break 3 + done + done + done +IFS=$as_save_IFS + if test -z "$ac_cv_path_SED"; then + as_fn_error $? "no acceptable sed could be found in \$PATH" "$LINENO" 5 + fi +else + ac_cv_path_SED=$SED +fi + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_path_SED" >&5 +$as_echo "$ac_cv_path_SED" >&6; } + SED="$ac_cv_path_SED" + rm -f conftest.sed + +test -z "$SED" && SED=sed +Xsed="$SED -e 1s/^X//" + + + + + + + + + + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for fgrep" >&5 +$as_echo_n "checking for fgrep... " >&6; } +if ${ac_cv_path_FGREP+:} false; then : + $as_echo_n "(cached) " >&6 +else + if echo 'ab*c' | $GREP -F 'ab*c' >/dev/null 2>&1 + then ac_cv_path_FGREP="$GREP -F" + else + if test -z "$FGREP"; then + ac_path_FGREP_found=false + # Loop through the user's path and test for each of PROGNAME-LIST + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH$PATH_SEPARATOR/usr/xpg4/bin +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_prog in fgrep; do + for ac_exec_ext in '' $ac_executable_extensions; do + ac_path_FGREP="$as_dir/$ac_prog$ac_exec_ext" + as_fn_executable_p "$ac_path_FGREP" || continue +# Check for GNU ac_path_FGREP and select it if it is found. + # Check for GNU $ac_path_FGREP +case `"$ac_path_FGREP" --version 2>&1` in +*GNU*) + ac_cv_path_FGREP="$ac_path_FGREP" ac_path_FGREP_found=:;; +*) + ac_count=0 + $as_echo_n 0123456789 >"conftest.in" + while : + do + cat "conftest.in" "conftest.in" >"conftest.tmp" + mv "conftest.tmp" "conftest.in" + cp "conftest.in" "conftest.nl" + $as_echo 'FGREP' >> "conftest.nl" + "$ac_path_FGREP" FGREP < "conftest.nl" >"conftest.out" 2>/dev/null || break + diff "conftest.out" "conftest.nl" >/dev/null 2>&1 || break + as_fn_arith $ac_count + 1 && ac_count=$as_val + if test $ac_count -gt ${ac_path_FGREP_max-0}; then + # Best one so far, save it but keep looking for a better one + ac_cv_path_FGREP="$ac_path_FGREP" + ac_path_FGREP_max=$ac_count + fi + # 10*(2^10) chars as input seems more than enough + test $ac_count -gt 10 && break + done + rm -f conftest.in conftest.tmp conftest.nl conftest.out;; +esac + + $ac_path_FGREP_found && break 3 + done + done + done +IFS=$as_save_IFS + if test -z "$ac_cv_path_FGREP"; then + as_fn_error $? "no acceptable fgrep could be found in $PATH$PATH_SEPARATOR/usr/xpg4/bin" "$LINENO" 5 + fi +else + ac_cv_path_FGREP=$FGREP +fi + + fi +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_path_FGREP" >&5 +$as_echo "$ac_cv_path_FGREP" >&6; } + FGREP="$ac_cv_path_FGREP" + + +test -z "$GREP" && GREP=grep + + + + + + + + + + + + + + + + + + + +# Check whether --with-gnu-ld was given. +if test "${with_gnu_ld+set}" = set; then : + withval=$with_gnu_ld; test no = "$withval" || with_gnu_ld=yes +else + with_gnu_ld=no +fi + +ac_prog=ld +if test yes = "$GCC"; then + # Check if gcc -print-prog-name=ld gives a path. + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for ld used by $CC" >&5 +$as_echo_n "checking for ld used by $CC... " >&6; } + case $host in + *-*-mingw*) + # gcc leaves a trailing carriage return, which upsets mingw + ac_prog=`($CC -print-prog-name=ld) 2>&5 | tr -d '\015'` ;; + *) + ac_prog=`($CC -print-prog-name=ld) 2>&5` ;; + esac + case $ac_prog in + # Accept absolute paths. + [\\/]* | ?:[\\/]*) + re_direlt='/[^/][^/]*/\.\./' + # Canonicalize the pathname of ld + ac_prog=`$ECHO "$ac_prog"| $SED 's%\\\\%/%g'` + while $ECHO "$ac_prog" | $GREP "$re_direlt" > /dev/null 2>&1; do + ac_prog=`$ECHO $ac_prog| $SED "s%$re_direlt%/%"` + done + test -z "$LD" && LD=$ac_prog + ;; + "") + # If it fails, then pretend we aren't using GCC. + ac_prog=ld + ;; + *) + # If it is relative, then search for the first ld in PATH. + with_gnu_ld=unknown + ;; + esac +elif test yes = "$with_gnu_ld"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for GNU ld" >&5 +$as_echo_n "checking for GNU ld... " >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for non-GNU ld" >&5 +$as_echo_n "checking for non-GNU ld... " >&6; } +fi +if ${lt_cv_path_LD+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -z "$LD"; then + lt_save_ifs=$IFS; IFS=$PATH_SEPARATOR + for ac_dir in $PATH; do + IFS=$lt_save_ifs + test -z "$ac_dir" && ac_dir=. + if test -f "$ac_dir/$ac_prog" || test -f "$ac_dir/$ac_prog$ac_exeext"; then + lt_cv_path_LD=$ac_dir/$ac_prog + # Check to see if the program is GNU ld. I'd rather use --version, + # but apparently some variants of GNU ld only accept -v. + # Break only if it was the GNU/non-GNU ld that we prefer. + case `"$lt_cv_path_LD" -v 2>&1 &5 +$as_echo "$LD" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi +test -z "$LD" && as_fn_error $? "no acceptable ld found in \$PATH" "$LINENO" 5 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking if the linker ($LD) is GNU ld" >&5 +$as_echo_n "checking if the linker ($LD) is GNU ld... " >&6; } +if ${lt_cv_prog_gnu_ld+:} false; then : + $as_echo_n "(cached) " >&6 +else + # I'd rather use --version here, but apparently some GNU lds only accept -v. +case `$LD -v 2>&1 &5 +$as_echo "$lt_cv_prog_gnu_ld" >&6; } +with_gnu_ld=$lt_cv_prog_gnu_ld + + + + + + + + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for BSD- or MS-compatible name lister (nm)" >&5 +$as_echo_n "checking for BSD- or MS-compatible name lister (nm)... " >&6; } +if ${lt_cv_path_NM+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$NM"; then + # Let the user override the test. + lt_cv_path_NM=$NM +else + lt_nm_to_check=${ac_tool_prefix}nm + if test -n "$ac_tool_prefix" && test "$build" = "$host"; then + lt_nm_to_check="$lt_nm_to_check nm" + fi + for lt_tmp_nm in $lt_nm_to_check; do + lt_save_ifs=$IFS; IFS=$PATH_SEPARATOR + for ac_dir in $PATH /usr/ccs/bin/elf /usr/ccs/bin /usr/ucb /bin; do + IFS=$lt_save_ifs + test -z "$ac_dir" && ac_dir=. + tmp_nm=$ac_dir/$lt_tmp_nm + if test -f "$tmp_nm" || test -f "$tmp_nm$ac_exeext"; then + # Check to see if the nm accepts a BSD-compat flag. + # Adding the 'sed 1q' prevents false positives on HP-UX, which says: + # nm: unknown option "B" ignored + # Tru64's nm complains that /dev/null is an invalid object file + # MSYS converts /dev/null to NUL, MinGW nm treats NUL as empty + case $build_os in + mingw*) lt_bad_file=conftest.nm/nofile ;; + *) lt_bad_file=/dev/null ;; + esac + case `"$tmp_nm" -B $lt_bad_file 2>&1 | sed '1q'` in + *$lt_bad_file* | *'Invalid file or object type'*) + lt_cv_path_NM="$tmp_nm -B" + break 2 + ;; + *) + case `"$tmp_nm" -p /dev/null 2>&1 | sed '1q'` in + */dev/null*) + lt_cv_path_NM="$tmp_nm -p" + break 2 + ;; + *) + lt_cv_path_NM=${lt_cv_path_NM="$tmp_nm"} # keep the first match, but + continue # so that we can try to find one that supports BSD flags + ;; + esac + ;; + esac + fi + done + IFS=$lt_save_ifs + done + : ${lt_cv_path_NM=no} +fi +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_path_NM" >&5 +$as_echo "$lt_cv_path_NM" >&6; } +if test no != "$lt_cv_path_NM"; then + NM=$lt_cv_path_NM +else + # Didn't find any BSD compatible name lister, look for dumpbin. + if test -n "$DUMPBIN"; then : + # Let the user override the test. + else + if test -n "$ac_tool_prefix"; then + for ac_prog in dumpbin "link -dump" + do + # Extract the first word of "$ac_tool_prefix$ac_prog", so it can be a program name with args. +set dummy $ac_tool_prefix$ac_prog; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_DUMPBIN+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$DUMPBIN"; then + ac_cv_prog_DUMPBIN="$DUMPBIN" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_DUMPBIN="$ac_tool_prefix$ac_prog" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +DUMPBIN=$ac_cv_prog_DUMPBIN +if test -n "$DUMPBIN"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $DUMPBIN" >&5 +$as_echo "$DUMPBIN" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + test -n "$DUMPBIN" && break + done +fi +if test -z "$DUMPBIN"; then + ac_ct_DUMPBIN=$DUMPBIN + for ac_prog in dumpbin "link -dump" +do + # Extract the first word of "$ac_prog", so it can be a program name with args. +set dummy $ac_prog; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_DUMPBIN+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_DUMPBIN"; then + ac_cv_prog_ac_ct_DUMPBIN="$ac_ct_DUMPBIN" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_DUMPBIN="$ac_prog" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_DUMPBIN=$ac_cv_prog_ac_ct_DUMPBIN +if test -n "$ac_ct_DUMPBIN"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_DUMPBIN" >&5 +$as_echo "$ac_ct_DUMPBIN" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + test -n "$ac_ct_DUMPBIN" && break +done + + if test "x$ac_ct_DUMPBIN" = x; then + DUMPBIN=":" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + DUMPBIN=$ac_ct_DUMPBIN + fi +fi + + case `$DUMPBIN -symbols -headers /dev/null 2>&1 | sed '1q'` in + *COFF*) + DUMPBIN="$DUMPBIN -symbols -headers" + ;; + *) + DUMPBIN=: + ;; + esac + fi + + if test : != "$DUMPBIN"; then + NM=$DUMPBIN + fi +fi +test -z "$NM" && NM=nm + + + + + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking the name lister ($NM) interface" >&5 +$as_echo_n "checking the name lister ($NM) interface... " >&6; } +if ${lt_cv_nm_interface+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_nm_interface="BSD nm" + echo "int some_variable = 0;" > conftest.$ac_ext + (eval echo "\"\$as_me:$LINENO: $ac_compile\"" >&5) + (eval "$ac_compile" 2>conftest.err) + cat conftest.err >&5 + (eval echo "\"\$as_me:$LINENO: $NM \\\"conftest.$ac_objext\\\"\"" >&5) + (eval "$NM \"conftest.$ac_objext\"" 2>conftest.err > conftest.out) + cat conftest.err >&5 + (eval echo "\"\$as_me:$LINENO: output\"" >&5) + cat conftest.out >&5 + if $GREP 'External.*some_variable' conftest.out > /dev/null; then + lt_cv_nm_interface="MS dumpbin" + fi + rm -f conftest* +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_nm_interface" >&5 +$as_echo "$lt_cv_nm_interface" >&6; } + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether ln -s works" >&5 +$as_echo_n "checking whether ln -s works... " >&6; } +LN_S=$as_ln_s +if test "$LN_S" = "ln -s"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5 +$as_echo "yes" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no, using $LN_S" >&5 +$as_echo "no, using $LN_S" >&6; } +fi + +# find the maximum length of command line arguments +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking the maximum length of command line arguments" >&5 +$as_echo_n "checking the maximum length of command line arguments... " >&6; } +if ${lt_cv_sys_max_cmd_len+:} false; then : + $as_echo_n "(cached) " >&6 +else + i=0 + teststring=ABCD + + case $build_os in + msdosdjgpp*) + # On DJGPP, this test can blow up pretty badly due to problems in libc + # (any single argument exceeding 2000 bytes causes a buffer overrun + # during glob expansion). Even if it were fixed, the result of this + # check would be larger than it should be. + lt_cv_sys_max_cmd_len=12288; # 12K is about right + ;; + + gnu*) + # Under GNU Hurd, this test is not required because there is + # no limit to the length of command line arguments. + # Libtool will interpret -1 as no limit whatsoever + lt_cv_sys_max_cmd_len=-1; + ;; + + cygwin* | mingw* | cegcc*) + # On Win9x/ME, this test blows up -- it succeeds, but takes + # about 5 minutes as the teststring grows exponentially. + # Worse, since 9x/ME are not pre-emptively multitasking, + # you end up with a "frozen" computer, even though with patience + # the test eventually succeeds (with a max line length of 256k). + # Instead, let's just punt: use the minimum linelength reported by + # all of the supported platforms: 8192 (on NT/2K/XP). + lt_cv_sys_max_cmd_len=8192; + ;; + + mint*) + # On MiNT this can take a long time and run out of memory. + lt_cv_sys_max_cmd_len=8192; + ;; + + amigaos*) + # On AmigaOS with pdksh, this test takes hours, literally. + # So we just punt and use a minimum line length of 8192. + lt_cv_sys_max_cmd_len=8192; + ;; + + bitrig* | darwin* | dragonfly* | freebsd* | netbsd* | openbsd*) + # This has been around since 386BSD, at least. Likely further. + if test -x /sbin/sysctl; then + lt_cv_sys_max_cmd_len=`/sbin/sysctl -n kern.argmax` + elif test -x /usr/sbin/sysctl; then + lt_cv_sys_max_cmd_len=`/usr/sbin/sysctl -n kern.argmax` + else + lt_cv_sys_max_cmd_len=65536 # usable default for all BSDs + fi + # And add a safety zone + lt_cv_sys_max_cmd_len=`expr $lt_cv_sys_max_cmd_len \/ 4` + lt_cv_sys_max_cmd_len=`expr $lt_cv_sys_max_cmd_len \* 3` + ;; + + interix*) + # We know the value 262144 and hardcode it with a safety zone (like BSD) + lt_cv_sys_max_cmd_len=196608 + ;; + + os2*) + # The test takes a long time on OS/2. + lt_cv_sys_max_cmd_len=8192 + ;; + + osf*) + # Dr. Hans Ekkehard Plesser reports seeing a kernel panic running configure + # due to this test when exec_disable_arg_limit is 1 on Tru64. It is not + # nice to cause kernel panics so lets avoid the loop below. + # First set a reasonable default. + lt_cv_sys_max_cmd_len=16384 + # + if test -x /sbin/sysconfig; then + case `/sbin/sysconfig -q proc exec_disable_arg_limit` in + *1*) lt_cv_sys_max_cmd_len=-1 ;; + esac + fi + ;; + sco3.2v5*) + lt_cv_sys_max_cmd_len=102400 + ;; + sysv5* | sco5v6* | sysv4.2uw2*) + kargmax=`grep ARG_MAX /etc/conf/cf.d/stune 2>/dev/null` + if test -n "$kargmax"; then + lt_cv_sys_max_cmd_len=`echo $kargmax | sed 's/.*[ ]//'` + else + lt_cv_sys_max_cmd_len=32768 + fi + ;; + *) + lt_cv_sys_max_cmd_len=`(getconf ARG_MAX) 2> /dev/null` + if test -n "$lt_cv_sys_max_cmd_len" && \ + test undefined != "$lt_cv_sys_max_cmd_len"; then + lt_cv_sys_max_cmd_len=`expr $lt_cv_sys_max_cmd_len \/ 4` + lt_cv_sys_max_cmd_len=`expr $lt_cv_sys_max_cmd_len \* 3` + else + # Make teststring a little bigger before we do anything with it. + # a 1K string should be a reasonable start. + for i in 1 2 3 4 5 6 7 8; do + teststring=$teststring$teststring + done + SHELL=${SHELL-${CONFIG_SHELL-/bin/sh}} + # If test is not a shell built-in, we'll probably end up computing a + # maximum length that is only half of the actual maximum length, but + # we can't tell. + while { test X`env echo "$teststring$teststring" 2>/dev/null` \ + = "X$teststring$teststring"; } >/dev/null 2>&1 && + test 17 != "$i" # 1/2 MB should be enough + do + i=`expr $i + 1` + teststring=$teststring$teststring + done + # Only check the string length outside the loop. + lt_cv_sys_max_cmd_len=`expr "X$teststring" : ".*" 2>&1` + teststring= + # Add a significant safety factor because C++ compilers can tack on + # massive amounts of additional arguments before passing them to the + # linker. It appears as though 1/2 is a usable value. + lt_cv_sys_max_cmd_len=`expr $lt_cv_sys_max_cmd_len \/ 2` + fi + ;; + esac + +fi + +if test -n "$lt_cv_sys_max_cmd_len"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_sys_max_cmd_len" >&5 +$as_echo "$lt_cv_sys_max_cmd_len" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: none" >&5 +$as_echo "none" >&6; } +fi +max_cmd_len=$lt_cv_sys_max_cmd_len + + + + + + +: ${CP="cp -f"} +: ${MV="mv -f"} +: ${RM="rm -f"} + +if ( (MAIL=60; unset MAIL) || exit) >/dev/null 2>&1; then + lt_unset=unset +else + lt_unset=false +fi + + + + + +# test EBCDIC or ASCII +case `echo X|tr X '\101'` in + A) # ASCII based system + # \n is not interpreted correctly by Solaris 8 /usr/ucb/tr + lt_SP2NL='tr \040 \012' + lt_NL2SP='tr \015\012 \040\040' + ;; + *) # EBCDIC based system + lt_SP2NL='tr \100 \n' + lt_NL2SP='tr \r\n \100\100' + ;; +esac + + + + + + + + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking how to convert $build file names to $host format" >&5 +$as_echo_n "checking how to convert $build file names to $host format... " >&6; } +if ${lt_cv_to_host_file_cmd+:} false; then : + $as_echo_n "(cached) " >&6 +else + case $host in + *-*-mingw* ) + case $build in + *-*-mingw* ) # actually msys + lt_cv_to_host_file_cmd=func_convert_file_msys_to_w32 + ;; + *-*-cygwin* ) + lt_cv_to_host_file_cmd=func_convert_file_cygwin_to_w32 + ;; + * ) # otherwise, assume *nix + lt_cv_to_host_file_cmd=func_convert_file_nix_to_w32 + ;; + esac + ;; + *-*-cygwin* ) + case $build in + *-*-mingw* ) # actually msys + lt_cv_to_host_file_cmd=func_convert_file_msys_to_cygwin + ;; + *-*-cygwin* ) + lt_cv_to_host_file_cmd=func_convert_file_noop + ;; + * ) # otherwise, assume *nix + lt_cv_to_host_file_cmd=func_convert_file_nix_to_cygwin + ;; + esac + ;; + * ) # unhandled hosts (and "normal" native builds) + lt_cv_to_host_file_cmd=func_convert_file_noop + ;; +esac + +fi + +to_host_file_cmd=$lt_cv_to_host_file_cmd +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_to_host_file_cmd" >&5 +$as_echo "$lt_cv_to_host_file_cmd" >&6; } + + + + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking how to convert $build file names to toolchain format" >&5 +$as_echo_n "checking how to convert $build file names to toolchain format... " >&6; } +if ${lt_cv_to_tool_file_cmd+:} false; then : + $as_echo_n "(cached) " >&6 +else + #assume ordinary cross tools, or native build. +lt_cv_to_tool_file_cmd=func_convert_file_noop +case $host in + *-*-mingw* ) + case $build in + *-*-mingw* ) # actually msys + lt_cv_to_tool_file_cmd=func_convert_file_msys_to_w32 + ;; + esac + ;; +esac + +fi + +to_tool_file_cmd=$lt_cv_to_tool_file_cmd +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_to_tool_file_cmd" >&5 +$as_echo "$lt_cv_to_tool_file_cmd" >&6; } + + + + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $LD option to reload object files" >&5 +$as_echo_n "checking for $LD option to reload object files... " >&6; } +if ${lt_cv_ld_reload_flag+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_ld_reload_flag='-r' +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_ld_reload_flag" >&5 +$as_echo "$lt_cv_ld_reload_flag" >&6; } +reload_flag=$lt_cv_ld_reload_flag +case $reload_flag in +"" | " "*) ;; +*) reload_flag=" $reload_flag" ;; +esac +reload_cmds='$LD$reload_flag -o $output$reload_objs' +case $host_os in + cygwin* | mingw* | pw32* | cegcc*) + if test yes != "$GCC"; then + reload_cmds=false + fi + ;; + darwin*) + if test yes = "$GCC"; then + reload_cmds='$LTCC $LTCFLAGS -nostdlib $wl-r -o $output$reload_objs' + else + reload_cmds='$LD$reload_flag -o $output$reload_objs' + fi + ;; +esac + + + + + + + + + +if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}objdump", so it can be a program name with args. +set dummy ${ac_tool_prefix}objdump; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_OBJDUMP+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$OBJDUMP"; then + ac_cv_prog_OBJDUMP="$OBJDUMP" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_OBJDUMP="${ac_tool_prefix}objdump" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +OBJDUMP=$ac_cv_prog_OBJDUMP +if test -n "$OBJDUMP"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $OBJDUMP" >&5 +$as_echo "$OBJDUMP" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_prog_OBJDUMP"; then + ac_ct_OBJDUMP=$OBJDUMP + # Extract the first word of "objdump", so it can be a program name with args. +set dummy objdump; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_OBJDUMP+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_OBJDUMP"; then + ac_cv_prog_ac_ct_OBJDUMP="$ac_ct_OBJDUMP" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_OBJDUMP="objdump" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_OBJDUMP=$ac_cv_prog_ac_ct_OBJDUMP +if test -n "$ac_ct_OBJDUMP"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_OBJDUMP" >&5 +$as_echo "$ac_ct_OBJDUMP" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_ct_OBJDUMP" = x; then + OBJDUMP="false" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + OBJDUMP=$ac_ct_OBJDUMP + fi +else + OBJDUMP="$ac_cv_prog_OBJDUMP" +fi + +test -z "$OBJDUMP" && OBJDUMP=objdump + + + + + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking how to recognize dependent libraries" >&5 +$as_echo_n "checking how to recognize dependent libraries... " >&6; } +if ${lt_cv_deplibs_check_method+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_file_magic_cmd='$MAGIC_CMD' +lt_cv_file_magic_test_file= +lt_cv_deplibs_check_method='unknown' +# Need to set the preceding variable on all platforms that support +# interlibrary dependencies. +# 'none' -- dependencies not supported. +# 'unknown' -- same as none, but documents that we really don't know. +# 'pass_all' -- all dependencies passed with no checks. +# 'test_compile' -- check by making test program. +# 'file_magic [[regex]]' -- check by looking for files in library path +# that responds to the $file_magic_cmd with a given extended regex. +# If you have 'file' or equivalent on your system and you're not sure +# whether 'pass_all' will *always* work, you probably want this one. + +case $host_os in +aix[4-9]*) + lt_cv_deplibs_check_method=pass_all + ;; + +beos*) + lt_cv_deplibs_check_method=pass_all + ;; + +bsdi[45]*) + lt_cv_deplibs_check_method='file_magic ELF [0-9][0-9]*-bit [ML]SB (shared object|dynamic lib)' + lt_cv_file_magic_cmd='/usr/bin/file -L' + lt_cv_file_magic_test_file=/shlib/libc.so + ;; + +cygwin*) + # func_win32_libid is a shell function defined in ltmain.sh + lt_cv_deplibs_check_method='file_magic ^x86 archive import|^x86 DLL' + lt_cv_file_magic_cmd='func_win32_libid' + ;; + +mingw* | pw32*) + # Base MSYS/MinGW do not provide the 'file' command needed by + # func_win32_libid shell function, so use a weaker test based on 'objdump', + # unless we find 'file', for example because we are cross-compiling. + if ( file / ) >/dev/null 2>&1; then + lt_cv_deplibs_check_method='file_magic ^x86 archive import|^x86 DLL' + lt_cv_file_magic_cmd='func_win32_libid' + else + # Keep this pattern in sync with the one in func_win32_libid. + lt_cv_deplibs_check_method='file_magic file format (pei*-i386(.*architecture: i386)?|pe-arm-wince|pe-x86-64)' + lt_cv_file_magic_cmd='$OBJDUMP -f' + fi + ;; + +cegcc*) + # use the weaker test based on 'objdump'. See mingw*. + lt_cv_deplibs_check_method='file_magic file format pe-arm-.*little(.*architecture: arm)?' + lt_cv_file_magic_cmd='$OBJDUMP -f' + ;; + +darwin* | rhapsody*) + lt_cv_deplibs_check_method=pass_all + ;; + +freebsd* | dragonfly*) + if echo __ELF__ | $CC -E - | $GREP __ELF__ > /dev/null; then + case $host_cpu in + i*86 ) + # Not sure whether the presence of OpenBSD here was a mistake. + # Let's accept both of them until this is cleared up. + lt_cv_deplibs_check_method='file_magic (FreeBSD|OpenBSD|DragonFly)/i[3-9]86 (compact )?demand paged shared library' + lt_cv_file_magic_cmd=/usr/bin/file + lt_cv_file_magic_test_file=`echo /usr/lib/libc.so.*` + ;; + esac + else + lt_cv_deplibs_check_method=pass_all + fi + ;; + +haiku*) + lt_cv_deplibs_check_method=pass_all + ;; + +hpux10.20* | hpux11*) + lt_cv_file_magic_cmd=/usr/bin/file + case $host_cpu in + ia64*) + lt_cv_deplibs_check_method='file_magic (s[0-9][0-9][0-9]|ELF-[0-9][0-9]) shared object file - IA64' + lt_cv_file_magic_test_file=/usr/lib/hpux32/libc.so + ;; + hppa*64*) + lt_cv_deplibs_check_method='file_magic (s[0-9][0-9][0-9]|ELF[ -][0-9][0-9])(-bit)?( [LM]SB)? shared object( file)?[, -]* PA-RISC [0-9]\.[0-9]' + lt_cv_file_magic_test_file=/usr/lib/pa20_64/libc.sl + ;; + *) + lt_cv_deplibs_check_method='file_magic (s[0-9][0-9][0-9]|PA-RISC[0-9]\.[0-9]) shared library' + lt_cv_file_magic_test_file=/usr/lib/libc.sl + ;; + esac + ;; + +interix[3-9]*) + # PIC code is broken on Interix 3.x, that's why |\.a not |_pic\.a here + lt_cv_deplibs_check_method='match_pattern /lib[^/]+(\.so|\.a)$' + ;; + +irix5* | irix6* | nonstopux*) + case $LD in + *-32|*"-32 ") libmagic=32-bit;; + *-n32|*"-n32 ") libmagic=N32;; + *-64|*"-64 ") libmagic=64-bit;; + *) libmagic=never-match;; + esac + lt_cv_deplibs_check_method=pass_all + ;; + +# This must be glibc/ELF. +linux* | k*bsd*-gnu | kopensolaris*-gnu | gnu*) + lt_cv_deplibs_check_method=pass_all + ;; + +netbsd*) + if echo __ELF__ | $CC -E - | $GREP __ELF__ > /dev/null; then + lt_cv_deplibs_check_method='match_pattern /lib[^/]+(\.so\.[0-9]+\.[0-9]+|_pic\.a)$' + else + lt_cv_deplibs_check_method='match_pattern /lib[^/]+(\.so|_pic\.a)$' + fi + ;; + +newos6*) + lt_cv_deplibs_check_method='file_magic ELF [0-9][0-9]*-bit [ML]SB (executable|dynamic lib)' + lt_cv_file_magic_cmd=/usr/bin/file + lt_cv_file_magic_test_file=/usr/lib/libnls.so + ;; + +*nto* | *qnx*) + lt_cv_deplibs_check_method=pass_all + ;; + +openbsd* | bitrig*) + if test -z "`echo __ELF__ | $CC -E - | $GREP __ELF__`"; then + lt_cv_deplibs_check_method='match_pattern /lib[^/]+(\.so\.[0-9]+\.[0-9]+|\.so|_pic\.a)$' + else + lt_cv_deplibs_check_method='match_pattern /lib[^/]+(\.so\.[0-9]+\.[0-9]+|_pic\.a)$' + fi + ;; + +osf3* | osf4* | osf5*) + lt_cv_deplibs_check_method=pass_all + ;; + +rdos*) + lt_cv_deplibs_check_method=pass_all + ;; + +solaris*) + lt_cv_deplibs_check_method=pass_all + ;; + +sysv5* | sco3.2v5* | sco5v6* | unixware* | OpenUNIX* | sysv4*uw2*) + lt_cv_deplibs_check_method=pass_all + ;; + +sysv4 | sysv4.3*) + case $host_vendor in + motorola) + lt_cv_deplibs_check_method='file_magic ELF [0-9][0-9]*-bit [ML]SB (shared object|dynamic lib) M[0-9][0-9]* Version [0-9]' + lt_cv_file_magic_test_file=`echo /usr/lib/libc.so*` + ;; + ncr) + lt_cv_deplibs_check_method=pass_all + ;; + sequent) + lt_cv_file_magic_cmd='/bin/file' + lt_cv_deplibs_check_method='file_magic ELF [0-9][0-9]*-bit [LM]SB (shared object|dynamic lib )' + ;; + sni) + lt_cv_file_magic_cmd='/bin/file' + lt_cv_deplibs_check_method="file_magic ELF [0-9][0-9]*-bit [LM]SB dynamic lib" + lt_cv_file_magic_test_file=/lib/libc.so + ;; + siemens) + lt_cv_deplibs_check_method=pass_all + ;; + pc) + lt_cv_deplibs_check_method=pass_all + ;; + esac + ;; + +tpf*) + lt_cv_deplibs_check_method=pass_all + ;; +os2*) + lt_cv_deplibs_check_method=pass_all + ;; +esac + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_deplibs_check_method" >&5 +$as_echo "$lt_cv_deplibs_check_method" >&6; } + +file_magic_glob= +want_nocaseglob=no +if test "$build" = "$host"; then + case $host_os in + mingw* | pw32*) + if ( shopt | grep nocaseglob ) >/dev/null 2>&1; then + want_nocaseglob=yes + else + file_magic_glob=`echo aAbBcCdDeEfFgGhHiIjJkKlLmMnNoOpPqQrRsStTuUvVwWxXyYzZ | $SED -e "s/\(..\)/s\/[\1]\/[\1]\/g;/g"` + fi + ;; + esac +fi + +file_magic_cmd=$lt_cv_file_magic_cmd +deplibs_check_method=$lt_cv_deplibs_check_method +test -z "$deplibs_check_method" && deplibs_check_method=unknown + + + + + + + + + + + + + + + + + + + + + + +if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}dlltool", so it can be a program name with args. +set dummy ${ac_tool_prefix}dlltool; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_DLLTOOL+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$DLLTOOL"; then + ac_cv_prog_DLLTOOL="$DLLTOOL" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_DLLTOOL="${ac_tool_prefix}dlltool" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +DLLTOOL=$ac_cv_prog_DLLTOOL +if test -n "$DLLTOOL"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $DLLTOOL" >&5 +$as_echo "$DLLTOOL" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_prog_DLLTOOL"; then + ac_ct_DLLTOOL=$DLLTOOL + # Extract the first word of "dlltool", so it can be a program name with args. +set dummy dlltool; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_DLLTOOL+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_DLLTOOL"; then + ac_cv_prog_ac_ct_DLLTOOL="$ac_ct_DLLTOOL" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_DLLTOOL="dlltool" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_DLLTOOL=$ac_cv_prog_ac_ct_DLLTOOL +if test -n "$ac_ct_DLLTOOL"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_DLLTOOL" >&5 +$as_echo "$ac_ct_DLLTOOL" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_ct_DLLTOOL" = x; then + DLLTOOL="false" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + DLLTOOL=$ac_ct_DLLTOOL + fi +else + DLLTOOL="$ac_cv_prog_DLLTOOL" +fi + +test -z "$DLLTOOL" && DLLTOOL=dlltool + + + + + + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking how to associate runtime and link libraries" >&5 +$as_echo_n "checking how to associate runtime and link libraries... " >&6; } +if ${lt_cv_sharedlib_from_linklib_cmd+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_sharedlib_from_linklib_cmd='unknown' + +case $host_os in +cygwin* | mingw* | pw32* | cegcc*) + # two different shell functions defined in ltmain.sh; + # decide which one to use based on capabilities of $DLLTOOL + case `$DLLTOOL --help 2>&1` in + *--identify-strict*) + lt_cv_sharedlib_from_linklib_cmd=func_cygming_dll_for_implib + ;; + *) + lt_cv_sharedlib_from_linklib_cmd=func_cygming_dll_for_implib_fallback + ;; + esac + ;; +*) + # fallback: assume linklib IS sharedlib + lt_cv_sharedlib_from_linklib_cmd=$ECHO + ;; +esac + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_sharedlib_from_linklib_cmd" >&5 +$as_echo "$lt_cv_sharedlib_from_linklib_cmd" >&6; } +sharedlib_from_linklib_cmd=$lt_cv_sharedlib_from_linklib_cmd +test -z "$sharedlib_from_linklib_cmd" && sharedlib_from_linklib_cmd=$ECHO + + + + + + + +if test -n "$ac_tool_prefix"; then + for ac_prog in ar + do + # Extract the first word of "$ac_tool_prefix$ac_prog", so it can be a program name with args. +set dummy $ac_tool_prefix$ac_prog; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_AR+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$AR"; then + ac_cv_prog_AR="$AR" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_AR="$ac_tool_prefix$ac_prog" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +AR=$ac_cv_prog_AR +if test -n "$AR"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $AR" >&5 +$as_echo "$AR" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + test -n "$AR" && break + done +fi +if test -z "$AR"; then + ac_ct_AR=$AR + for ac_prog in ar +do + # Extract the first word of "$ac_prog", so it can be a program name with args. +set dummy $ac_prog; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_AR+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_AR"; then + ac_cv_prog_ac_ct_AR="$ac_ct_AR" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_AR="$ac_prog" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_AR=$ac_cv_prog_ac_ct_AR +if test -n "$ac_ct_AR"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_AR" >&5 +$as_echo "$ac_ct_AR" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + test -n "$ac_ct_AR" && break +done + + if test "x$ac_ct_AR" = x; then + AR="false" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + AR=$ac_ct_AR + fi +fi + +: ${AR=ar} +: ${AR_FLAGS=cru} + + + + + + + + + + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for archiver @FILE support" >&5 +$as_echo_n "checking for archiver @FILE support... " >&6; } +if ${lt_cv_ar_at_file+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_ar_at_file=no + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + echo conftest.$ac_objext > conftest.lst + lt_ar_try='$AR $AR_FLAGS libconftest.a @conftest.lst >&5' + { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$lt_ar_try\""; } >&5 + (eval $lt_ar_try) 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } + if test 0 -eq "$ac_status"; then + # Ensure the archiver fails upon bogus file names. + rm -f conftest.$ac_objext libconftest.a + { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$lt_ar_try\""; } >&5 + (eval $lt_ar_try) 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } + if test 0 -ne "$ac_status"; then + lt_cv_ar_at_file=@ + fi + fi + rm -f conftest.* libconftest.a + +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_ar_at_file" >&5 +$as_echo "$lt_cv_ar_at_file" >&6; } + +if test no = "$lt_cv_ar_at_file"; then + archiver_list_spec= +else + archiver_list_spec=$lt_cv_ar_at_file +fi + + + + + + + +if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}strip", so it can be a program name with args. +set dummy ${ac_tool_prefix}strip; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_STRIP+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$STRIP"; then + ac_cv_prog_STRIP="$STRIP" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_STRIP="${ac_tool_prefix}strip" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +STRIP=$ac_cv_prog_STRIP +if test -n "$STRIP"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $STRIP" >&5 +$as_echo "$STRIP" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_prog_STRIP"; then + ac_ct_STRIP=$STRIP + # Extract the first word of "strip", so it can be a program name with args. +set dummy strip; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_STRIP+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_STRIP"; then + ac_cv_prog_ac_ct_STRIP="$ac_ct_STRIP" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_STRIP="strip" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_STRIP=$ac_cv_prog_ac_ct_STRIP +if test -n "$ac_ct_STRIP"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_STRIP" >&5 +$as_echo "$ac_ct_STRIP" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_ct_STRIP" = x; then + STRIP=":" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + STRIP=$ac_ct_STRIP + fi +else + STRIP="$ac_cv_prog_STRIP" +fi + +test -z "$STRIP" && STRIP=: + + + + + + +if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}ranlib", so it can be a program name with args. +set dummy ${ac_tool_prefix}ranlib; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_RANLIB+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$RANLIB"; then + ac_cv_prog_RANLIB="$RANLIB" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_RANLIB="${ac_tool_prefix}ranlib" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +RANLIB=$ac_cv_prog_RANLIB +if test -n "$RANLIB"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $RANLIB" >&5 +$as_echo "$RANLIB" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_prog_RANLIB"; then + ac_ct_RANLIB=$RANLIB + # Extract the first word of "ranlib", so it can be a program name with args. +set dummy ranlib; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_RANLIB+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_RANLIB"; then + ac_cv_prog_ac_ct_RANLIB="$ac_ct_RANLIB" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_RANLIB="ranlib" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_RANLIB=$ac_cv_prog_ac_ct_RANLIB +if test -n "$ac_ct_RANLIB"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_RANLIB" >&5 +$as_echo "$ac_ct_RANLIB" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_ct_RANLIB" = x; then + RANLIB=":" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + RANLIB=$ac_ct_RANLIB + fi +else + RANLIB="$ac_cv_prog_RANLIB" +fi + +test -z "$RANLIB" && RANLIB=: + + + + + + +# Determine commands to create old-style static archives. +old_archive_cmds='$AR $AR_FLAGS $oldlib$oldobjs' +old_postinstall_cmds='chmod 644 $oldlib' +old_postuninstall_cmds= + +if test -n "$RANLIB"; then + case $host_os in + bitrig* | openbsd*) + old_postinstall_cmds="$old_postinstall_cmds~\$RANLIB -t \$tool_oldlib" + ;; + *) + old_postinstall_cmds="$old_postinstall_cmds~\$RANLIB \$tool_oldlib" + ;; + esac + old_archive_cmds="$old_archive_cmds~\$RANLIB \$tool_oldlib" +fi + +case $host_os in + darwin*) + lock_old_archive_extraction=yes ;; + *) + lock_old_archive_extraction=no ;; +esac + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +# If no C compiler was specified, use CC. +LTCC=${LTCC-"$CC"} + +# If no C compiler flags were specified, use CFLAGS. +LTCFLAGS=${LTCFLAGS-"$CFLAGS"} + +# Allow CC to be a program name with arguments. +compiler=$CC + + +# Check for command to grab the raw symbol name followed by C symbol from nm. +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking command to parse $NM output from $compiler object" >&5 +$as_echo_n "checking command to parse $NM output from $compiler object... " >&6; } +if ${lt_cv_sys_global_symbol_pipe+:} false; then : + $as_echo_n "(cached) " >&6 +else + +# These are sane defaults that work on at least a few old systems. +# [They come from Ultrix. What could be older than Ultrix?!! ;)] + +# Character class describing NM global symbol codes. +symcode='[BCDEGRST]' + +# Regexp to match symbols that can be accessed directly from C. +sympat='\([_A-Za-z][_A-Za-z0-9]*\)' + +# Define system-specific variables. +case $host_os in +aix*) + symcode='[BCDT]' + ;; +cygwin* | mingw* | pw32* | cegcc*) + symcode='[ABCDGISTW]' + ;; +hpux*) + if test ia64 = "$host_cpu"; then + symcode='[ABCDEGRST]' + fi + ;; +irix* | nonstopux*) + symcode='[BCDEGRST]' + ;; +osf*) + symcode='[BCDEGQRST]' + ;; +solaris*) + symcode='[BDRT]' + ;; +sco3.2v5*) + symcode='[DT]' + ;; +sysv4.2uw2*) + symcode='[DT]' + ;; +sysv5* | sco5v6* | unixware* | OpenUNIX*) + symcode='[ABDT]' + ;; +sysv4) + symcode='[DFNSTU]' + ;; +esac + +# If we're using GNU nm, then use its standard symbol codes. +case `$NM -V 2>&1` in +*GNU* | *'with BFD'*) + symcode='[ABCDGIRSTW]' ;; +esac + +if test "$lt_cv_nm_interface" = "MS dumpbin"; then + # Gets list of data symbols to import. + lt_cv_sys_global_symbol_to_import="sed -n -e 's/^I .* \(.*\)$/\1/p'" + # Adjust the below global symbol transforms to fixup imported variables. + lt_cdecl_hook=" -e 's/^I .* \(.*\)$/extern __declspec(dllimport) char \1;/p'" + lt_c_name_hook=" -e 's/^I .* \(.*\)$/ {\"\1\", (void *) 0},/p'" + lt_c_name_lib_hook="\ + -e 's/^I .* \(lib.*\)$/ {\"\1\", (void *) 0},/p'\ + -e 's/^I .* \(.*\)$/ {\"lib\1\", (void *) 0},/p'" +else + # Disable hooks by default. + lt_cv_sys_global_symbol_to_import= + lt_cdecl_hook= + lt_c_name_hook= + lt_c_name_lib_hook= +fi + +# Transform an extracted symbol line into a proper C declaration. +# Some systems (esp. on ia64) link data and code symbols differently, +# so use this general approach. +lt_cv_sys_global_symbol_to_cdecl="sed -n"\ +$lt_cdecl_hook\ +" -e 's/^T .* \(.*\)$/extern int \1();/p'"\ +" -e 's/^$symcode$symcode* .* \(.*\)$/extern char \1;/p'" + +# Transform an extracted symbol line into symbol name and symbol address +lt_cv_sys_global_symbol_to_c_name_address="sed -n"\ +$lt_c_name_hook\ +" -e 's/^: \(.*\) .*$/ {\"\1\", (void *) 0},/p'"\ +" -e 's/^$symcode$symcode* .* \(.*\)$/ {\"\1\", (void *) \&\1},/p'" + +# Transform an extracted symbol line into symbol name with lib prefix and +# symbol address. +lt_cv_sys_global_symbol_to_c_name_address_lib_prefix="sed -n"\ +$lt_c_name_lib_hook\ +" -e 's/^: \(.*\) .*$/ {\"\1\", (void *) 0},/p'"\ +" -e 's/^$symcode$symcode* .* \(lib.*\)$/ {\"\1\", (void *) \&\1},/p'"\ +" -e 's/^$symcode$symcode* .* \(.*\)$/ {\"lib\1\", (void *) \&\1},/p'" + +# Handle CRLF in mingw tool chain +opt_cr= +case $build_os in +mingw*) + opt_cr=`$ECHO 'x\{0,1\}' | tr x '\015'` # option cr in regexp + ;; +esac + +# Try without a prefix underscore, then with it. +for ac_symprfx in "" "_"; do + + # Transform symcode, sympat, and symprfx into a raw symbol and a C symbol. + symxfrm="\\1 $ac_symprfx\\2 \\2" + + # Write the raw and C identifiers. + if test "$lt_cv_nm_interface" = "MS dumpbin"; then + # Fake it for dumpbin and say T for any non-static function, + # D for any global variable and I for any imported variable. + # Also find C++ and __fastcall symbols from MSVC++, + # which start with @ or ?. + lt_cv_sys_global_symbol_pipe="$AWK '"\ +" {last_section=section; section=\$ 3};"\ +" /^COFF SYMBOL TABLE/{for(i in hide) delete hide[i]};"\ +" /Section length .*#relocs.*(pick any)/{hide[last_section]=1};"\ +" /^ *Symbol name *: /{split(\$ 0,sn,\":\"); si=substr(sn[2],2)};"\ +" /^ *Type *: code/{print \"T\",si,substr(si,length(prfx))};"\ +" /^ *Type *: data/{print \"I\",si,substr(si,length(prfx))};"\ +" \$ 0!~/External *\|/{next};"\ +" / 0+ UNDEF /{next}; / UNDEF \([^|]\)*()/{next};"\ +" {if(hide[section]) next};"\ +" {f=\"D\"}; \$ 0~/\(\).*\|/{f=\"T\"};"\ +" {split(\$ 0,a,/\||\r/); split(a[2],s)};"\ +" s[1]~/^[@?]/{print f,s[1],s[1]; next};"\ +" s[1]~prfx {split(s[1],t,\"@\"); print f,t[1],substr(t[1],length(prfx))}"\ +" ' prfx=^$ac_symprfx" + else + lt_cv_sys_global_symbol_pipe="sed -n -e 's/^.*[ ]\($symcode$symcode*\)[ ][ ]*$ac_symprfx$sympat$opt_cr$/$symxfrm/p'" + fi + lt_cv_sys_global_symbol_pipe="$lt_cv_sys_global_symbol_pipe | sed '/ __gnu_lto/d'" + + # Check to see that the pipe works correctly. + pipe_works=no + + rm -f conftest* + cat > conftest.$ac_ext <<_LT_EOF +#ifdef __cplusplus +extern "C" { +#endif +char nm_test_var; +void nm_test_func(void); +void nm_test_func(void){} +#ifdef __cplusplus +} +#endif +int main(){nm_test_var='a';nm_test_func();return(0);} +_LT_EOF + + if { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$ac_compile\""; } >&5 + (eval $ac_compile) 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; }; then + # Now try to grab the symbols. + nlist=conftest.nm + if { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$NM conftest.$ac_objext \| "$lt_cv_sys_global_symbol_pipe" \> $nlist\""; } >&5 + (eval $NM conftest.$ac_objext \| "$lt_cv_sys_global_symbol_pipe" \> $nlist) 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } && test -s "$nlist"; then + # Try sorting and uniquifying the output. + if sort "$nlist" | uniq > "$nlist"T; then + mv -f "$nlist"T "$nlist" + else + rm -f "$nlist"T + fi + + # Make sure that we snagged all the symbols we need. + if $GREP ' nm_test_var$' "$nlist" >/dev/null; then + if $GREP ' nm_test_func$' "$nlist" >/dev/null; then + cat <<_LT_EOF > conftest.$ac_ext +/* Keep this code in sync between libtool.m4, ltmain, lt_system.h, and tests. */ +#if defined _WIN32 || defined __CYGWIN__ || defined _WIN32_WCE +/* DATA imports from DLLs on WIN32 can't be const, because runtime + relocations are performed -- see ld's documentation on pseudo-relocs. */ +# define LT_DLSYM_CONST +#elif defined __osf__ +/* This system does not cope well with relocations in const data. */ +# define LT_DLSYM_CONST +#else +# define LT_DLSYM_CONST const +#endif + +#ifdef __cplusplus +extern "C" { +#endif + +_LT_EOF + # Now generate the symbol file. + eval "$lt_cv_sys_global_symbol_to_cdecl"' < "$nlist" | $GREP -v main >> conftest.$ac_ext' + + cat <<_LT_EOF >> conftest.$ac_ext + +/* The mapping between symbol names and symbols. */ +LT_DLSYM_CONST struct { + const char *name; + void *address; +} +lt__PROGRAM__LTX_preloaded_symbols[] = +{ + { "@PROGRAM@", (void *) 0 }, +_LT_EOF + $SED "s/^$symcode$symcode* .* \(.*\)$/ {\"\1\", (void *) \&\1},/" < "$nlist" | $GREP -v main >> conftest.$ac_ext + cat <<\_LT_EOF >> conftest.$ac_ext + {0, (void *) 0} +}; + +/* This works around a problem in FreeBSD linker */ +#ifdef FREEBSD_WORKAROUND +static const void *lt_preloaded_setup() { + return lt__PROGRAM__LTX_preloaded_symbols; +} +#endif + +#ifdef __cplusplus +} +#endif +_LT_EOF + # Now try linking the two files. + mv conftest.$ac_objext conftstm.$ac_objext + lt_globsym_save_LIBS=$LIBS + lt_globsym_save_CFLAGS=$CFLAGS + LIBS=conftstm.$ac_objext + CFLAGS="$CFLAGS$lt_prog_compiler_no_builtin_flag" + if { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$ac_link\""; } >&5 + (eval $ac_link) 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } && test -s conftest$ac_exeext; then + pipe_works=yes + fi + LIBS=$lt_globsym_save_LIBS + CFLAGS=$lt_globsym_save_CFLAGS + else + echo "cannot find nm_test_func in $nlist" >&5 + fi + else + echo "cannot find nm_test_var in $nlist" >&5 + fi + else + echo "cannot run $lt_cv_sys_global_symbol_pipe" >&5 + fi + else + echo "$progname: failed program was:" >&5 + cat conftest.$ac_ext >&5 + fi + rm -rf conftest* conftst* + + # Do not use the global_symbol_pipe unless it works. + if test yes = "$pipe_works"; then + break + else + lt_cv_sys_global_symbol_pipe= + fi +done + +fi + +if test -z "$lt_cv_sys_global_symbol_pipe"; then + lt_cv_sys_global_symbol_to_cdecl= +fi +if test -z "$lt_cv_sys_global_symbol_pipe$lt_cv_sys_global_symbol_to_cdecl"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: failed" >&5 +$as_echo "failed" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: ok" >&5 +$as_echo "ok" >&6; } +fi + +# Response file support. +if test "$lt_cv_nm_interface" = "MS dumpbin"; then + nm_file_list_spec='@' +elif $NM --help 2>/dev/null | grep '[@]FILE' >/dev/null; then + nm_file_list_spec='@' +fi + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for sysroot" >&5 +$as_echo_n "checking for sysroot... " >&6; } + +# Check whether --with-sysroot was given. +if test "${with_sysroot+set}" = set; then : + withval=$with_sysroot; +else + with_sysroot=no +fi + + +lt_sysroot= +case $with_sysroot in #( + yes) + if test yes = "$GCC"; then + lt_sysroot=`$CC --print-sysroot 2>/dev/null` + fi + ;; #( + /*) + lt_sysroot=`echo "$with_sysroot" | sed -e "$sed_quote_subst"` + ;; #( + no|'') + ;; #( + *) + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $with_sysroot" >&5 +$as_echo "$with_sysroot" >&6; } + as_fn_error $? "The sysroot must be an absolute path." "$LINENO" 5 + ;; +esac + + { $as_echo "$as_me:${as_lineno-$LINENO}: result: ${lt_sysroot:-no}" >&5 +$as_echo "${lt_sysroot:-no}" >&6; } + + + + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for a working dd" >&5 +$as_echo_n "checking for a working dd... " >&6; } +if ${ac_cv_path_lt_DD+:} false; then : + $as_echo_n "(cached) " >&6 +else + printf 0123456789abcdef0123456789abcdef >conftest.i +cat conftest.i conftest.i >conftest2.i +: ${lt_DD:=$DD} +if test -z "$lt_DD"; then + ac_path_lt_DD_found=false + # Loop through the user's path and test for each of PROGNAME-LIST + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_prog in dd; do + for ac_exec_ext in '' $ac_executable_extensions; do + ac_path_lt_DD="$as_dir/$ac_prog$ac_exec_ext" + as_fn_executable_p "$ac_path_lt_DD" || continue +if "$ac_path_lt_DD" bs=32 count=1 conftest.out 2>/dev/null; then + cmp -s conftest.i conftest.out \ + && ac_cv_path_lt_DD="$ac_path_lt_DD" ac_path_lt_DD_found=: +fi + $ac_path_lt_DD_found && break 3 + done + done + done +IFS=$as_save_IFS + if test -z "$ac_cv_path_lt_DD"; then + : + fi +else + ac_cv_path_lt_DD=$lt_DD +fi + +rm -f conftest.i conftest2.i conftest.out +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_path_lt_DD" >&5 +$as_echo "$ac_cv_path_lt_DD" >&6; } + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking how to truncate binary pipes" >&5 +$as_echo_n "checking how to truncate binary pipes... " >&6; } +if ${lt_cv_truncate_bin+:} false; then : + $as_echo_n "(cached) " >&6 +else + printf 0123456789abcdef0123456789abcdef >conftest.i +cat conftest.i conftest.i >conftest2.i +lt_cv_truncate_bin= +if "$ac_cv_path_lt_DD" bs=32 count=1 conftest.out 2>/dev/null; then + cmp -s conftest.i conftest.out \ + && lt_cv_truncate_bin="$ac_cv_path_lt_DD bs=4096 count=1" +fi +rm -f conftest.i conftest2.i conftest.out +test -z "$lt_cv_truncate_bin" && lt_cv_truncate_bin="$SED -e 4q" +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_truncate_bin" >&5 +$as_echo "$lt_cv_truncate_bin" >&6; } + + + + + + + +# Calculate cc_basename. Skip known compiler wrappers and cross-prefix. +func_cc_basename () +{ + for cc_temp in $*""; do + case $cc_temp in + compile | *[\\/]compile | ccache | *[\\/]ccache ) ;; + distcc | *[\\/]distcc | purify | *[\\/]purify ) ;; + \-*) ;; + *) break;; + esac + done + func_cc_basename_result=`$ECHO "$cc_temp" | $SED "s%.*/%%; s%^$host_alias-%%"` +} + +# Check whether --enable-libtool-lock was given. +if test "${enable_libtool_lock+set}" = set; then : + enableval=$enable_libtool_lock; +fi + +test no = "$enable_libtool_lock" || enable_libtool_lock=yes + +# Some flags need to be propagated to the compiler or linker for good +# libtool support. +case $host in +ia64-*-hpux*) + # Find out what ABI is being produced by ac_compile, and set mode + # options accordingly. + echo 'int i;' > conftest.$ac_ext + if { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$ac_compile\""; } >&5 + (eval $ac_compile) 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; }; then + case `/usr/bin/file conftest.$ac_objext` in + *ELF-32*) + HPUX_IA64_MODE=32 + ;; + *ELF-64*) + HPUX_IA64_MODE=64 + ;; + esac + fi + rm -rf conftest* + ;; +*-*-irix6*) + # Find out what ABI is being produced by ac_compile, and set linker + # options accordingly. + echo '#line '$LINENO' "configure"' > conftest.$ac_ext + if { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$ac_compile\""; } >&5 + (eval $ac_compile) 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; }; then + if test yes = "$lt_cv_prog_gnu_ld"; then + case `/usr/bin/file conftest.$ac_objext` in + *32-bit*) + LD="${LD-ld} -melf32bsmip" + ;; + *N32*) + LD="${LD-ld} -melf32bmipn32" + ;; + *64-bit*) + LD="${LD-ld} -melf64bmip" + ;; + esac + else + case `/usr/bin/file conftest.$ac_objext` in + *32-bit*) + LD="${LD-ld} -32" + ;; + *N32*) + LD="${LD-ld} -n32" + ;; + *64-bit*) + LD="${LD-ld} -64" + ;; + esac + fi + fi + rm -rf conftest* + ;; + +mips64*-*linux*) + # Find out what ABI is being produced by ac_compile, and set linker + # options accordingly. + echo '#line '$LINENO' "configure"' > conftest.$ac_ext + if { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$ac_compile\""; } >&5 + (eval $ac_compile) 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; }; then + emul=elf + case `/usr/bin/file conftest.$ac_objext` in + *32-bit*) + emul="${emul}32" + ;; + *64-bit*) + emul="${emul}64" + ;; + esac + case `/usr/bin/file conftest.$ac_objext` in + *MSB*) + emul="${emul}btsmip" + ;; + *LSB*) + emul="${emul}ltsmip" + ;; + esac + case `/usr/bin/file conftest.$ac_objext` in + *N32*) + emul="${emul}n32" + ;; + esac + LD="${LD-ld} -m $emul" + fi + rm -rf conftest* + ;; + +x86_64-*kfreebsd*-gnu|x86_64-*linux*|powerpc*-*linux*| \ +s390*-*linux*|s390*-*tpf*|sparc*-*linux*) + # Find out what ABI is being produced by ac_compile, and set linker + # options accordingly. Note that the listed cases only cover the + # situations where additional linker options are needed (such as when + # doing 32-bit compilation for a host where ld defaults to 64-bit, or + # vice versa); the common cases where no linker options are needed do + # not appear in the list. + echo 'int i;' > conftest.$ac_ext + if { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$ac_compile\""; } >&5 + (eval $ac_compile) 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; }; then + case `/usr/bin/file conftest.o` in + *32-bit*) + case $host in + x86_64-*kfreebsd*-gnu) + LD="${LD-ld} -m elf_i386_fbsd" + ;; + x86_64-*linux*) + case `/usr/bin/file conftest.o` in + *x86-64*) + LD="${LD-ld} -m elf32_x86_64" + ;; + *) + LD="${LD-ld} -m elf_i386" + ;; + esac + ;; + powerpc64le-*linux*) + LD="${LD-ld} -m elf32lppclinux" + ;; + powerpc64-*linux*) + LD="${LD-ld} -m elf32ppclinux" + ;; + s390x-*linux*) + LD="${LD-ld} -m elf_s390" + ;; + sparc64-*linux*) + LD="${LD-ld} -m elf32_sparc" + ;; + esac + ;; + *64-bit*) + case $host in + x86_64-*kfreebsd*-gnu) + LD="${LD-ld} -m elf_x86_64_fbsd" + ;; + x86_64-*linux*) + LD="${LD-ld} -m elf_x86_64" + ;; + powerpcle-*linux*) + LD="${LD-ld} -m elf64lppc" + ;; + powerpc-*linux*) + LD="${LD-ld} -m elf64ppc" + ;; + s390*-*linux*|s390*-*tpf*) + LD="${LD-ld} -m elf64_s390" + ;; + sparc*-*linux*) + LD="${LD-ld} -m elf64_sparc" + ;; + esac + ;; + esac + fi + rm -rf conftest* + ;; + +*-*-sco3.2v5*) + # On SCO OpenServer 5, we need -belf to get full-featured binaries. + SAVE_CFLAGS=$CFLAGS + CFLAGS="$CFLAGS -belf" + { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether the C compiler needs -belf" >&5 +$as_echo_n "checking whether the C compiler needs -belf... " >&6; } +if ${lt_cv_cc_needs_belf+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + lt_cv_cc_needs_belf=yes +else + lt_cv_cc_needs_belf=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext + ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_cc_needs_belf" >&5 +$as_echo "$lt_cv_cc_needs_belf" >&6; } + if test yes != "$lt_cv_cc_needs_belf"; then + # this is probably gcc 2.8.0, egcs 1.0 or newer; no need for -belf + CFLAGS=$SAVE_CFLAGS + fi + ;; +*-*solaris*) + # Find out what ABI is being produced by ac_compile, and set linker + # options accordingly. + echo 'int i;' > conftest.$ac_ext + if { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$ac_compile\""; } >&5 + (eval $ac_compile) 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; }; then + case `/usr/bin/file conftest.o` in + *64-bit*) + case $lt_cv_prog_gnu_ld in + yes*) + case $host in + i?86-*-solaris*|x86_64-*-solaris*) + LD="${LD-ld} -m elf_x86_64" + ;; + sparc*-*-solaris*) + LD="${LD-ld} -m elf64_sparc" + ;; + esac + # GNU ld 2.21 introduced _sol2 emulations. Use them if available. + if ${LD-ld} -V | grep _sol2 >/dev/null 2>&1; then + LD=${LD-ld}_sol2 + fi + ;; + *) + if ${LD-ld} -64 -r -o conftest2.o conftest.o >/dev/null 2>&1; then + LD="${LD-ld} -64" + fi + ;; + esac + ;; + esac + fi + rm -rf conftest* + ;; +esac + +need_locks=$enable_libtool_lock + +if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}mt", so it can be a program name with args. +set dummy ${ac_tool_prefix}mt; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_MANIFEST_TOOL+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$MANIFEST_TOOL"; then + ac_cv_prog_MANIFEST_TOOL="$MANIFEST_TOOL" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_MANIFEST_TOOL="${ac_tool_prefix}mt" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +MANIFEST_TOOL=$ac_cv_prog_MANIFEST_TOOL +if test -n "$MANIFEST_TOOL"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $MANIFEST_TOOL" >&5 +$as_echo "$MANIFEST_TOOL" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_prog_MANIFEST_TOOL"; then + ac_ct_MANIFEST_TOOL=$MANIFEST_TOOL + # Extract the first word of "mt", so it can be a program name with args. +set dummy mt; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_MANIFEST_TOOL+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_MANIFEST_TOOL"; then + ac_cv_prog_ac_ct_MANIFEST_TOOL="$ac_ct_MANIFEST_TOOL" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_MANIFEST_TOOL="mt" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_MANIFEST_TOOL=$ac_cv_prog_ac_ct_MANIFEST_TOOL +if test -n "$ac_ct_MANIFEST_TOOL"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_MANIFEST_TOOL" >&5 +$as_echo "$ac_ct_MANIFEST_TOOL" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_ct_MANIFEST_TOOL" = x; then + MANIFEST_TOOL=":" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + MANIFEST_TOOL=$ac_ct_MANIFEST_TOOL + fi +else + MANIFEST_TOOL="$ac_cv_prog_MANIFEST_TOOL" +fi + +test -z "$MANIFEST_TOOL" && MANIFEST_TOOL=mt +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking if $MANIFEST_TOOL is a manifest tool" >&5 +$as_echo_n "checking if $MANIFEST_TOOL is a manifest tool... " >&6; } +if ${lt_cv_path_mainfest_tool+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_path_mainfest_tool=no + echo "$as_me:$LINENO: $MANIFEST_TOOL '-?'" >&5 + $MANIFEST_TOOL '-?' 2>conftest.err > conftest.out + cat conftest.err >&5 + if $GREP 'Manifest Tool' conftest.out > /dev/null; then + lt_cv_path_mainfest_tool=yes + fi + rm -f conftest* +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_path_mainfest_tool" >&5 +$as_echo "$lt_cv_path_mainfest_tool" >&6; } +if test yes != "$lt_cv_path_mainfest_tool"; then + MANIFEST_TOOL=: +fi + + + + + + + case $host_os in + rhapsody* | darwin*) + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}dsymutil", so it can be a program name with args. +set dummy ${ac_tool_prefix}dsymutil; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_DSYMUTIL+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$DSYMUTIL"; then + ac_cv_prog_DSYMUTIL="$DSYMUTIL" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_DSYMUTIL="${ac_tool_prefix}dsymutil" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +DSYMUTIL=$ac_cv_prog_DSYMUTIL +if test -n "$DSYMUTIL"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $DSYMUTIL" >&5 +$as_echo "$DSYMUTIL" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_prog_DSYMUTIL"; then + ac_ct_DSYMUTIL=$DSYMUTIL + # Extract the first word of "dsymutil", so it can be a program name with args. +set dummy dsymutil; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_DSYMUTIL+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_DSYMUTIL"; then + ac_cv_prog_ac_ct_DSYMUTIL="$ac_ct_DSYMUTIL" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_DSYMUTIL="dsymutil" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_DSYMUTIL=$ac_cv_prog_ac_ct_DSYMUTIL +if test -n "$ac_ct_DSYMUTIL"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_DSYMUTIL" >&5 +$as_echo "$ac_ct_DSYMUTIL" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_ct_DSYMUTIL" = x; then + DSYMUTIL=":" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + DSYMUTIL=$ac_ct_DSYMUTIL + fi +else + DSYMUTIL="$ac_cv_prog_DSYMUTIL" +fi + + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}nmedit", so it can be a program name with args. +set dummy ${ac_tool_prefix}nmedit; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_NMEDIT+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$NMEDIT"; then + ac_cv_prog_NMEDIT="$NMEDIT" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_NMEDIT="${ac_tool_prefix}nmedit" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +NMEDIT=$ac_cv_prog_NMEDIT +if test -n "$NMEDIT"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $NMEDIT" >&5 +$as_echo "$NMEDIT" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_prog_NMEDIT"; then + ac_ct_NMEDIT=$NMEDIT + # Extract the first word of "nmedit", so it can be a program name with args. +set dummy nmedit; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_NMEDIT+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_NMEDIT"; then + ac_cv_prog_ac_ct_NMEDIT="$ac_ct_NMEDIT" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_NMEDIT="nmedit" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_NMEDIT=$ac_cv_prog_ac_ct_NMEDIT +if test -n "$ac_ct_NMEDIT"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_NMEDIT" >&5 +$as_echo "$ac_ct_NMEDIT" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_ct_NMEDIT" = x; then + NMEDIT=":" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + NMEDIT=$ac_ct_NMEDIT + fi +else + NMEDIT="$ac_cv_prog_NMEDIT" +fi + + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}lipo", so it can be a program name with args. +set dummy ${ac_tool_prefix}lipo; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_LIPO+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$LIPO"; then + ac_cv_prog_LIPO="$LIPO" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_LIPO="${ac_tool_prefix}lipo" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +LIPO=$ac_cv_prog_LIPO +if test -n "$LIPO"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $LIPO" >&5 +$as_echo "$LIPO" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_prog_LIPO"; then + ac_ct_LIPO=$LIPO + # Extract the first word of "lipo", so it can be a program name with args. +set dummy lipo; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_LIPO+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_LIPO"; then + ac_cv_prog_ac_ct_LIPO="$ac_ct_LIPO" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_LIPO="lipo" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_LIPO=$ac_cv_prog_ac_ct_LIPO +if test -n "$ac_ct_LIPO"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_LIPO" >&5 +$as_echo "$ac_ct_LIPO" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_ct_LIPO" = x; then + LIPO=":" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + LIPO=$ac_ct_LIPO + fi +else + LIPO="$ac_cv_prog_LIPO" +fi + + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}otool", so it can be a program name with args. +set dummy ${ac_tool_prefix}otool; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_OTOOL+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$OTOOL"; then + ac_cv_prog_OTOOL="$OTOOL" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_OTOOL="${ac_tool_prefix}otool" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +OTOOL=$ac_cv_prog_OTOOL +if test -n "$OTOOL"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $OTOOL" >&5 +$as_echo "$OTOOL" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_prog_OTOOL"; then + ac_ct_OTOOL=$OTOOL + # Extract the first word of "otool", so it can be a program name with args. +set dummy otool; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_OTOOL+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_OTOOL"; then + ac_cv_prog_ac_ct_OTOOL="$ac_ct_OTOOL" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_OTOOL="otool" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_OTOOL=$ac_cv_prog_ac_ct_OTOOL +if test -n "$ac_ct_OTOOL"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_OTOOL" >&5 +$as_echo "$ac_ct_OTOOL" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_ct_OTOOL" = x; then + OTOOL=":" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + OTOOL=$ac_ct_OTOOL + fi +else + OTOOL="$ac_cv_prog_OTOOL" +fi + + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}otool64", so it can be a program name with args. +set dummy ${ac_tool_prefix}otool64; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_OTOOL64+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$OTOOL64"; then + ac_cv_prog_OTOOL64="$OTOOL64" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_OTOOL64="${ac_tool_prefix}otool64" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +OTOOL64=$ac_cv_prog_OTOOL64 +if test -n "$OTOOL64"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $OTOOL64" >&5 +$as_echo "$OTOOL64" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_prog_OTOOL64"; then + ac_ct_OTOOL64=$OTOOL64 + # Extract the first word of "otool64", so it can be a program name with args. +set dummy otool64; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ac_ct_OTOOL64+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ac_ct_OTOOL64"; then + ac_cv_prog_ac_ct_OTOOL64="$ac_ct_OTOOL64" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_OTOOL64="otool64" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +ac_ct_OTOOL64=$ac_cv_prog_ac_ct_OTOOL64 +if test -n "$ac_ct_OTOOL64"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_ct_OTOOL64" >&5 +$as_echo "$ac_ct_OTOOL64" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_ct_OTOOL64" = x; then + OTOOL64=":" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + OTOOL64=$ac_ct_OTOOL64 + fi +else + OTOOL64="$ac_cv_prog_OTOOL64" +fi + + + + + + + + + + + + + + + + + + + + + + + + + + + + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for -single_module linker flag" >&5 +$as_echo_n "checking for -single_module linker flag... " >&6; } +if ${lt_cv_apple_cc_single_mod+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_apple_cc_single_mod=no + if test -z "$LT_MULTI_MODULE"; then + # By default we will add the -single_module flag. You can override + # by either setting the environment variable LT_MULTI_MODULE + # non-empty at configure time, or by adding -multi_module to the + # link flags. + rm -rf libconftest.dylib* + echo "int foo(void){return 1;}" > conftest.c + echo "$LTCC $LTCFLAGS $LDFLAGS -o libconftest.dylib \ +-dynamiclib -Wl,-single_module conftest.c" >&5 + $LTCC $LTCFLAGS $LDFLAGS -o libconftest.dylib \ + -dynamiclib -Wl,-single_module conftest.c 2>conftest.err + _lt_result=$? + # If there is a non-empty error log, and "single_module" + # appears in it, assume the flag caused a linker warning + if test -s conftest.err && $GREP single_module conftest.err; then + cat conftest.err >&5 + # Otherwise, if the output was created with a 0 exit code from + # the compiler, it worked. + elif test -f libconftest.dylib && test 0 = "$_lt_result"; then + lt_cv_apple_cc_single_mod=yes + else + cat conftest.err >&5 + fi + rm -rf libconftest.dylib* + rm -f conftest.* + fi +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_apple_cc_single_mod" >&5 +$as_echo "$lt_cv_apple_cc_single_mod" >&6; } + + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for -exported_symbols_list linker flag" >&5 +$as_echo_n "checking for -exported_symbols_list linker flag... " >&6; } +if ${lt_cv_ld_exported_symbols_list+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_ld_exported_symbols_list=no + save_LDFLAGS=$LDFLAGS + echo "_main" > conftest.sym + LDFLAGS="$LDFLAGS -Wl,-exported_symbols_list,conftest.sym" + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + lt_cv_ld_exported_symbols_list=yes +else + lt_cv_ld_exported_symbols_list=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext + LDFLAGS=$save_LDFLAGS + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_ld_exported_symbols_list" >&5 +$as_echo "$lt_cv_ld_exported_symbols_list" >&6; } + + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for -force_load linker flag" >&5 +$as_echo_n "checking for -force_load linker flag... " >&6; } +if ${lt_cv_ld_force_load+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_ld_force_load=no + cat > conftest.c << _LT_EOF +int forced_loaded() { return 2;} +_LT_EOF + echo "$LTCC $LTCFLAGS -c -o conftest.o conftest.c" >&5 + $LTCC $LTCFLAGS -c -o conftest.o conftest.c 2>&5 + echo "$AR cru libconftest.a conftest.o" >&5 + $AR cru libconftest.a conftest.o 2>&5 + echo "$RANLIB libconftest.a" >&5 + $RANLIB libconftest.a 2>&5 + cat > conftest.c << _LT_EOF +int main() { return 0;} +_LT_EOF + echo "$LTCC $LTCFLAGS $LDFLAGS -o conftest conftest.c -Wl,-force_load,./libconftest.a" >&5 + $LTCC $LTCFLAGS $LDFLAGS -o conftest conftest.c -Wl,-force_load,./libconftest.a 2>conftest.err + _lt_result=$? + if test -s conftest.err && $GREP force_load conftest.err; then + cat conftest.err >&5 + elif test -f conftest && test 0 = "$_lt_result" && $GREP forced_load conftest >/dev/null 2>&1; then + lt_cv_ld_force_load=yes + else + cat conftest.err >&5 + fi + rm -f conftest.err libconftest.a conftest conftest.c + rm -rf conftest.dSYM + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_ld_force_load" >&5 +$as_echo "$lt_cv_ld_force_load" >&6; } + case $host_os in + rhapsody* | darwin1.[012]) + _lt_dar_allow_undefined='$wl-undefined ${wl}suppress' ;; + darwin1.*) + _lt_dar_allow_undefined='$wl-flat_namespace $wl-undefined ${wl}suppress' ;; + darwin*) # darwin 5.x on + # if running on 10.5 or later, the deployment target defaults + # to the OS version, if on x86, and 10.4, the deployment + # target defaults to 10.4. Don't you love it? + case ${MACOSX_DEPLOYMENT_TARGET-10.0},$host in + 10.0,*86*-darwin8*|10.0,*-darwin[91]*) + _lt_dar_allow_undefined='$wl-undefined ${wl}dynamic_lookup' ;; + 10.[012][,.]*) + _lt_dar_allow_undefined='$wl-flat_namespace $wl-undefined ${wl}suppress' ;; + 10.*) + _lt_dar_allow_undefined='$wl-undefined ${wl}dynamic_lookup' ;; + esac + ;; + esac + if test yes = "$lt_cv_apple_cc_single_mod"; then + _lt_dar_single_mod='$single_module' + fi + if test yes = "$lt_cv_ld_exported_symbols_list"; then + _lt_dar_export_syms=' $wl-exported_symbols_list,$output_objdir/$libname-symbols.expsym' + else + _lt_dar_export_syms='~$NMEDIT -s $output_objdir/$libname-symbols.expsym $lib' + fi + if test : != "$DSYMUTIL" && test no = "$lt_cv_ld_force_load"; then + _lt_dsymutil='~$DSYMUTIL $lib || :' + else + _lt_dsymutil= + fi + ;; + esac + +# func_munge_path_list VARIABLE PATH +# ----------------------------------- +# VARIABLE is name of variable containing _space_ separated list of +# directories to be munged by the contents of PATH, which is string +# having a format: +# "DIR[:DIR]:" +# string "DIR[ DIR]" will be prepended to VARIABLE +# ":DIR[:DIR]" +# string "DIR[ DIR]" will be appended to VARIABLE +# "DIRP[:DIRP]::[DIRA:]DIRA" +# string "DIRP[ DIRP]" will be prepended to VARIABLE and string +# "DIRA[ DIRA]" will be appended to VARIABLE +# "DIR[:DIR]" +# VARIABLE will be replaced by "DIR[ DIR]" +func_munge_path_list () +{ + case x$2 in + x) + ;; + *:) + eval $1=\"`$ECHO $2 | $SED 's/:/ /g'` \$$1\" + ;; + x:*) + eval $1=\"\$$1 `$ECHO $2 | $SED 's/:/ /g'`\" + ;; + *::*) + eval $1=\"\$$1\ `$ECHO $2 | $SED -e 's/.*:://' -e 's/:/ /g'`\" + eval $1=\"`$ECHO $2 | $SED -e 's/::.*//' -e 's/:/ /g'`\ \$$1\" + ;; + *) + eval $1=\"`$ECHO $2 | $SED 's/:/ /g'`\" + ;; + esac +} + +for ac_header in dlfcn.h +do : + ac_fn_c_check_header_compile "$LINENO" "dlfcn.h" "ac_cv_header_dlfcn_h" "$ac_includes_default +" +if test "x$ac_cv_header_dlfcn_h" = xyes; then : + cat >>confdefs.h <<_ACEOF +#define HAVE_DLFCN_H 1 +_ACEOF + +fi + +done + + + + + +# Set options + + + + enable_dlopen=no + + + + # Check whether --enable-shared was given. +if test "${enable_shared+set}" = set; then : + enableval=$enable_shared; p=${PACKAGE-default} + case $enableval in + yes) enable_shared=yes ;; + no) enable_shared=no ;; + *) + enable_shared=no + # Look at the argument we got. We use all the common list separators. + lt_save_ifs=$IFS; IFS=$IFS$PATH_SEPARATOR, + for pkg in $enableval; do + IFS=$lt_save_ifs + if test "X$pkg" = "X$p"; then + enable_shared=yes + fi + done + IFS=$lt_save_ifs + ;; + esac +else + enable_shared=yes +fi + + + + + + + + + + # Check whether --enable-static was given. +if test "${enable_static+set}" = set; then : + enableval=$enable_static; p=${PACKAGE-default} + case $enableval in + yes) enable_static=yes ;; + no) enable_static=no ;; + *) + enable_static=no + # Look at the argument we got. We use all the common list separators. + lt_save_ifs=$IFS; IFS=$IFS$PATH_SEPARATOR, + for pkg in $enableval; do + IFS=$lt_save_ifs + if test "X$pkg" = "X$p"; then + enable_static=yes + fi + done + IFS=$lt_save_ifs + ;; + esac +else + enable_static=yes +fi + + + + + + + + + + +# Check whether --with-pic was given. +if test "${with_pic+set}" = set; then : + withval=$with_pic; lt_p=${PACKAGE-default} + case $withval in + yes|no) pic_mode=$withval ;; + *) + pic_mode=default + # Look at the argument we got. We use all the common list separators. + lt_save_ifs=$IFS; IFS=$IFS$PATH_SEPARATOR, + for lt_pkg in $withval; do + IFS=$lt_save_ifs + if test "X$lt_pkg" = "X$lt_p"; then + pic_mode=yes + fi + done + IFS=$lt_save_ifs + ;; + esac +else + pic_mode=default +fi + + + + + + + + + # Check whether --enable-fast-install was given. +if test "${enable_fast_install+set}" = set; then : + enableval=$enable_fast_install; p=${PACKAGE-default} + case $enableval in + yes) enable_fast_install=yes ;; + no) enable_fast_install=no ;; + *) + enable_fast_install=no + # Look at the argument we got. We use all the common list separators. + lt_save_ifs=$IFS; IFS=$IFS$PATH_SEPARATOR, + for pkg in $enableval; do + IFS=$lt_save_ifs + if test "X$pkg" = "X$p"; then + enable_fast_install=yes + fi + done + IFS=$lt_save_ifs + ;; + esac +else + enable_fast_install=yes +fi + + + + + + + + + shared_archive_member_spec= +case $host,$enable_shared in +power*-*-aix[5-9]*,yes) + { $as_echo "$as_me:${as_lineno-$LINENO}: checking which variant of shared library versioning to provide" >&5 +$as_echo_n "checking which variant of shared library versioning to provide... " >&6; } + +# Check whether --with-aix-soname was given. +if test "${with_aix_soname+set}" = set; then : + withval=$with_aix_soname; case $withval in + aix|svr4|both) + ;; + *) + as_fn_error $? "Unknown argument to --with-aix-soname" "$LINENO" 5 + ;; + esac + lt_cv_with_aix_soname=$with_aix_soname +else + if ${lt_cv_with_aix_soname+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_with_aix_soname=aix +fi + + with_aix_soname=$lt_cv_with_aix_soname +fi + + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $with_aix_soname" >&5 +$as_echo "$with_aix_soname" >&6; } + if test aix != "$with_aix_soname"; then + # For the AIX way of multilib, we name the shared archive member + # based on the bitwidth used, traditionally 'shr.o' or 'shr_64.o', + # and 'shr.imp' or 'shr_64.imp', respectively, for the Import File. + # Even when GNU compilers ignore OBJECT_MODE but need '-maix64' flag, + # the AIX toolchain works better with OBJECT_MODE set (default 32). + if test 64 = "${OBJECT_MODE-32}"; then + shared_archive_member_spec=shr_64 + else + shared_archive_member_spec=shr + fi + fi + ;; +*) + with_aix_soname=aix + ;; +esac + + + + + + + + + + +# This can be used to rebuild libtool when needed +LIBTOOL_DEPS=$ltmain + +# Always use our own libtool. +LIBTOOL='$(SHELL) $(top_builddir)/libtool' + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +test -z "$LN_S" && LN_S="ln -s" + + + + + + + + + + + + + + +if test -n "${ZSH_VERSION+set}"; then + setopt NO_GLOB_SUBST +fi + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for objdir" >&5 +$as_echo_n "checking for objdir... " >&6; } +if ${lt_cv_objdir+:} false; then : + $as_echo_n "(cached) " >&6 +else + rm -f .libs 2>/dev/null +mkdir .libs 2>/dev/null +if test -d .libs; then + lt_cv_objdir=.libs +else + # MS-DOS does not allow filenames that begin with a dot. + lt_cv_objdir=_libs +fi +rmdir .libs 2>/dev/null +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_objdir" >&5 +$as_echo "$lt_cv_objdir" >&6; } +objdir=$lt_cv_objdir + + + + + +cat >>confdefs.h <<_ACEOF +#define LT_OBJDIR "$lt_cv_objdir/" +_ACEOF + + + + +case $host_os in +aix3*) + # AIX sometimes has problems with the GCC collect2 program. For some + # reason, if we set the COLLECT_NAMES environment variable, the problems + # vanish in a puff of smoke. + if test set != "${COLLECT_NAMES+set}"; then + COLLECT_NAMES= + export COLLECT_NAMES + fi + ;; +esac + +# Global variables: +ofile=libtool +can_build_shared=yes + +# All known linkers require a '.a' archive for static linking (except MSVC, +# which needs '.lib'). +libext=a + +with_gnu_ld=$lt_cv_prog_gnu_ld + +old_CC=$CC +old_CFLAGS=$CFLAGS + +# Set sane defaults for various variables +test -z "$CC" && CC=cc +test -z "$LTCC" && LTCC=$CC +test -z "$LTCFLAGS" && LTCFLAGS=$CFLAGS +test -z "$LD" && LD=ld +test -z "$ac_objext" && ac_objext=o + +func_cc_basename $compiler +cc_basename=$func_cc_basename_result + + +# Only perform the check for file, if the check method requires it +test -z "$MAGIC_CMD" && MAGIC_CMD=file +case $deplibs_check_method in +file_magic*) + if test "$file_magic_cmd" = '$MAGIC_CMD'; then + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for ${ac_tool_prefix}file" >&5 +$as_echo_n "checking for ${ac_tool_prefix}file... " >&6; } +if ${lt_cv_path_MAGIC_CMD+:} false; then : + $as_echo_n "(cached) " >&6 +else + case $MAGIC_CMD in +[\\/*] | ?:[\\/]*) + lt_cv_path_MAGIC_CMD=$MAGIC_CMD # Let the user override the test with a path. + ;; +*) + lt_save_MAGIC_CMD=$MAGIC_CMD + lt_save_ifs=$IFS; IFS=$PATH_SEPARATOR + ac_dummy="/usr/bin$PATH_SEPARATOR$PATH" + for ac_dir in $ac_dummy; do + IFS=$lt_save_ifs + test -z "$ac_dir" && ac_dir=. + if test -f "$ac_dir/${ac_tool_prefix}file"; then + lt_cv_path_MAGIC_CMD=$ac_dir/"${ac_tool_prefix}file" + if test -n "$file_magic_test_file"; then + case $deplibs_check_method in + "file_magic "*) + file_magic_regex=`expr "$deplibs_check_method" : "file_magic \(.*\)"` + MAGIC_CMD=$lt_cv_path_MAGIC_CMD + if eval $file_magic_cmd \$file_magic_test_file 2> /dev/null | + $EGREP "$file_magic_regex" > /dev/null; then + : + else + cat <<_LT_EOF 1>&2 + +*** Warning: the command libtool uses to detect shared libraries, +*** $file_magic_cmd, produces output that libtool cannot recognize. +*** The result is that libtool may fail to recognize shared libraries +*** as such. This will affect the creation of libtool libraries that +*** depend on shared libraries, but programs linked with such libtool +*** libraries will work regardless of this problem. Nevertheless, you +*** may want to report the problem to your system manager and/or to +*** bug-libtool@gnu.org + +_LT_EOF + fi ;; + esac + fi + break + fi + done + IFS=$lt_save_ifs + MAGIC_CMD=$lt_save_MAGIC_CMD + ;; +esac +fi + +MAGIC_CMD=$lt_cv_path_MAGIC_CMD +if test -n "$MAGIC_CMD"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $MAGIC_CMD" >&5 +$as_echo "$MAGIC_CMD" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + + + +if test -z "$lt_cv_path_MAGIC_CMD"; then + if test -n "$ac_tool_prefix"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for file" >&5 +$as_echo_n "checking for file... " >&6; } +if ${lt_cv_path_MAGIC_CMD+:} false; then : + $as_echo_n "(cached) " >&6 +else + case $MAGIC_CMD in +[\\/*] | ?:[\\/]*) + lt_cv_path_MAGIC_CMD=$MAGIC_CMD # Let the user override the test with a path. + ;; +*) + lt_save_MAGIC_CMD=$MAGIC_CMD + lt_save_ifs=$IFS; IFS=$PATH_SEPARATOR + ac_dummy="/usr/bin$PATH_SEPARATOR$PATH" + for ac_dir in $ac_dummy; do + IFS=$lt_save_ifs + test -z "$ac_dir" && ac_dir=. + if test -f "$ac_dir/file"; then + lt_cv_path_MAGIC_CMD=$ac_dir/"file" + if test -n "$file_magic_test_file"; then + case $deplibs_check_method in + "file_magic "*) + file_magic_regex=`expr "$deplibs_check_method" : "file_magic \(.*\)"` + MAGIC_CMD=$lt_cv_path_MAGIC_CMD + if eval $file_magic_cmd \$file_magic_test_file 2> /dev/null | + $EGREP "$file_magic_regex" > /dev/null; then + : + else + cat <<_LT_EOF 1>&2 + +*** Warning: the command libtool uses to detect shared libraries, +*** $file_magic_cmd, produces output that libtool cannot recognize. +*** The result is that libtool may fail to recognize shared libraries +*** as such. This will affect the creation of libtool libraries that +*** depend on shared libraries, but programs linked with such libtool +*** libraries will work regardless of this problem. Nevertheless, you +*** may want to report the problem to your system manager and/or to +*** bug-libtool@gnu.org + +_LT_EOF + fi ;; + esac + fi + break + fi + done + IFS=$lt_save_ifs + MAGIC_CMD=$lt_save_MAGIC_CMD + ;; +esac +fi + +MAGIC_CMD=$lt_cv_path_MAGIC_CMD +if test -n "$MAGIC_CMD"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $MAGIC_CMD" >&5 +$as_echo "$MAGIC_CMD" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + else + MAGIC_CMD=: + fi +fi + + fi + ;; +esac + +# Use C for the default configuration in the libtool script + +lt_save_CC=$CC +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + + +# Source file extension for C test sources. +ac_ext=c + +# Object file extension for compiled C test sources. +objext=o +objext=$objext + +# Code to be used in simple compile tests +lt_simple_compile_test_code="int some_variable = 0;" + +# Code to be used in simple link tests +lt_simple_link_test_code='int main(){return(0);}' + + + + + + + +# If no C compiler was specified, use CC. +LTCC=${LTCC-"$CC"} + +# If no C compiler flags were specified, use CFLAGS. +LTCFLAGS=${LTCFLAGS-"$CFLAGS"} + +# Allow CC to be a program name with arguments. +compiler=$CC + +# Save the default compiler, since it gets overwritten when the other +# tags are being tested, and _LT_TAGVAR(compiler, []) is a NOP. +compiler_DEFAULT=$CC + +# save warnings/boilerplate of simple test code +ac_outfile=conftest.$ac_objext +echo "$lt_simple_compile_test_code" >conftest.$ac_ext +eval "$ac_compile" 2>&1 >/dev/null | $SED '/^$/d; /^ *+/d' >conftest.err +_lt_compiler_boilerplate=`cat conftest.err` +$RM conftest* + +ac_outfile=conftest.$ac_objext +echo "$lt_simple_link_test_code" >conftest.$ac_ext +eval "$ac_link" 2>&1 >/dev/null | $SED '/^$/d; /^ *+/d' >conftest.err +_lt_linker_boilerplate=`cat conftest.err` +$RM -r conftest* + + +## CAVEAT EMPTOR: +## There is no encapsulation within the following macros, do not change +## the running order or otherwise move them around unless you know exactly +## what you are doing... +if test -n "$compiler"; then + +lt_prog_compiler_no_builtin_flag= + +if test yes = "$GCC"; then + case $cc_basename in + nvcc*) + lt_prog_compiler_no_builtin_flag=' -Xcompiler -fno-builtin' ;; + *) + lt_prog_compiler_no_builtin_flag=' -fno-builtin' ;; + esac + + { $as_echo "$as_me:${as_lineno-$LINENO}: checking if $compiler supports -fno-rtti -fno-exceptions" >&5 +$as_echo_n "checking if $compiler supports -fno-rtti -fno-exceptions... " >&6; } +if ${lt_cv_prog_compiler_rtti_exceptions+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_prog_compiler_rtti_exceptions=no + ac_outfile=conftest.$ac_objext + echo "$lt_simple_compile_test_code" > conftest.$ac_ext + lt_compiler_flag="-fno-rtti -fno-exceptions" ## exclude from sc_useless_quotes_in_assignment + # Insert the option either (1) after the last *FLAGS variable, or + # (2) before a word containing "conftest.", or (3) at the end. + # Note that $ac_compile itself does not contain backslashes and begins + # with a dollar sign (not a hyphen), so the echo should work correctly. + # The option is referenced via a variable to avoid confusing sed. + lt_compile=`echo "$ac_compile" | $SED \ + -e 's:.*FLAGS}\{0,1\} :&$lt_compiler_flag :; t' \ + -e 's: [^ ]*conftest\.: $lt_compiler_flag&:; t' \ + -e 's:$: $lt_compiler_flag:'` + (eval echo "\"\$as_me:$LINENO: $lt_compile\"" >&5) + (eval "$lt_compile" 2>conftest.err) + ac_status=$? + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + if (exit $ac_status) && test -s "$ac_outfile"; then + # The compiler can only warn and ignore the option if not recognized + # So say no if there are warnings other than the usual output. + $ECHO "$_lt_compiler_boilerplate" | $SED '/^$/d' >conftest.exp + $SED '/^$/d; /^ *+/d' conftest.err >conftest.er2 + if test ! -s conftest.er2 || diff conftest.exp conftest.er2 >/dev/null; then + lt_cv_prog_compiler_rtti_exceptions=yes + fi + fi + $RM conftest* + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_prog_compiler_rtti_exceptions" >&5 +$as_echo "$lt_cv_prog_compiler_rtti_exceptions" >&6; } + +if test yes = "$lt_cv_prog_compiler_rtti_exceptions"; then + lt_prog_compiler_no_builtin_flag="$lt_prog_compiler_no_builtin_flag -fno-rtti -fno-exceptions" +else + : +fi + +fi + + + + + + + lt_prog_compiler_wl= +lt_prog_compiler_pic= +lt_prog_compiler_static= + + + if test yes = "$GCC"; then + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_static='-static' + + case $host_os in + aix*) + # All AIX code is PIC. + if test ia64 = "$host_cpu"; then + # AIX 5 now supports IA64 processor + lt_prog_compiler_static='-Bstatic' + fi + lt_prog_compiler_pic='-fPIC' + ;; + + amigaos*) + case $host_cpu in + powerpc) + # see comment about AmigaOS4 .so support + lt_prog_compiler_pic='-fPIC' + ;; + m68k) + # FIXME: we need at least 68020 code to build shared libraries, but + # adding the '-m68020' flag to GCC prevents building anything better, + # like '-m68040'. + lt_prog_compiler_pic='-m68020 -resident32 -malways-restore-a4' + ;; + esac + ;; + + beos* | irix5* | irix6* | nonstopux* | osf3* | osf4* | osf5*) + # PIC is the default for these OSes. + ;; + + mingw* | cygwin* | pw32* | os2* | cegcc*) + # This hack is so that the source file can tell whether it is being + # built for inclusion in a dll (and should export symbols for example). + # Although the cygwin gcc ignores -fPIC, still need this for old-style + # (--disable-auto-import) libraries + lt_prog_compiler_pic='-DDLL_EXPORT' + case $host_os in + os2*) + lt_prog_compiler_static='$wl-static' + ;; + esac + ;; + + darwin* | rhapsody*) + # PIC is the default on this platform + # Common symbols not allowed in MH_DYLIB files + lt_prog_compiler_pic='-fno-common' + ;; + + haiku*) + # PIC is the default for Haiku. + # The "-static" flag exists, but is broken. + lt_prog_compiler_static= + ;; + + hpux*) + # PIC is the default for 64-bit PA HP-UX, but not for 32-bit + # PA HP-UX. On IA64 HP-UX, PIC is the default but the pic flag + # sets the default TLS model and affects inlining. + case $host_cpu in + hppa*64*) + # +Z the default + ;; + *) + lt_prog_compiler_pic='-fPIC' + ;; + esac + ;; + + interix[3-9]*) + # Interix 3.x gcc -fpic/-fPIC options generate broken code. + # Instead, we relocate shared libraries at runtime. + ;; + + msdosdjgpp*) + # Just because we use GCC doesn't mean we suddenly get shared libraries + # on systems that don't support them. + lt_prog_compiler_can_build_shared=no + enable_shared=no + ;; + + *nto* | *qnx*) + # QNX uses GNU C++, but need to define -shared option too, otherwise + # it will coredump. + lt_prog_compiler_pic='-fPIC -shared' + ;; + + sysv4*MP*) + if test -d /usr/nec; then + lt_prog_compiler_pic=-Kconform_pic + fi + ;; + + *) + lt_prog_compiler_pic='-fPIC' + ;; + esac + + case $cc_basename in + nvcc*) # Cuda Compiler Driver 2.2 + lt_prog_compiler_wl='-Xlinker ' + if test -n "$lt_prog_compiler_pic"; then + lt_prog_compiler_pic="-Xcompiler $lt_prog_compiler_pic" + fi + ;; + esac + else + # PORTME Check for flag to pass linker flags through the system compiler. + case $host_os in + aix*) + lt_prog_compiler_wl='-Wl,' + if test ia64 = "$host_cpu"; then + # AIX 5 now supports IA64 processor + lt_prog_compiler_static='-Bstatic' + else + lt_prog_compiler_static='-bnso -bI:/lib/syscalls.exp' + fi + ;; + + darwin* | rhapsody*) + # PIC is the default on this platform + # Common symbols not allowed in MH_DYLIB files + lt_prog_compiler_pic='-fno-common' + case $cc_basename in + nagfor*) + # NAG Fortran compiler + lt_prog_compiler_wl='-Wl,-Wl,,' + lt_prog_compiler_pic='-PIC' + lt_prog_compiler_static='-Bstatic' + ;; + esac + ;; + + mingw* | cygwin* | pw32* | os2* | cegcc*) + # This hack is so that the source file can tell whether it is being + # built for inclusion in a dll (and should export symbols for example). + lt_prog_compiler_pic='-DDLL_EXPORT' + case $host_os in + os2*) + lt_prog_compiler_static='$wl-static' + ;; + esac + ;; + + hpux9* | hpux10* | hpux11*) + lt_prog_compiler_wl='-Wl,' + # PIC is the default for IA64 HP-UX and 64-bit HP-UX, but + # not for PA HP-UX. + case $host_cpu in + hppa*64*|ia64*) + # +Z the default + ;; + *) + lt_prog_compiler_pic='+Z' + ;; + esac + # Is there a better lt_prog_compiler_static that works with the bundled CC? + lt_prog_compiler_static='$wl-a ${wl}archive' + ;; + + irix5* | irix6* | nonstopux*) + lt_prog_compiler_wl='-Wl,' + # PIC (with -KPIC) is the default. + lt_prog_compiler_static='-non_shared' + ;; + + linux* | k*bsd*-gnu | kopensolaris*-gnu | gnu*) + case $cc_basename in + # old Intel for x86_64, which still supported -KPIC. + ecc*) + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_pic='-KPIC' + lt_prog_compiler_static='-static' + ;; + # icc used to be incompatible with GCC. + # ICC 10 doesn't accept -KPIC any more. + icc* | ifort*) + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_pic='-fPIC' + lt_prog_compiler_static='-static' + ;; + # Lahey Fortran 8.1. + lf95*) + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_pic='--shared' + lt_prog_compiler_static='--static' + ;; + nagfor*) + # NAG Fortran compiler + lt_prog_compiler_wl='-Wl,-Wl,,' + lt_prog_compiler_pic='-PIC' + lt_prog_compiler_static='-Bstatic' + ;; + tcc*) + # Fabrice Bellard et al's Tiny C Compiler + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_pic='-fPIC' + lt_prog_compiler_static='-static' + ;; + pgcc* | pgf77* | pgf90* | pgf95* | pgfortran*) + # Portland Group compilers (*not* the Pentium gcc compiler, + # which looks to be a dead project) + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_pic='-fpic' + lt_prog_compiler_static='-Bstatic' + ;; + ccc*) + lt_prog_compiler_wl='-Wl,' + # All Alpha code is PIC. + lt_prog_compiler_static='-non_shared' + ;; + xl* | bgxl* | bgf* | mpixl*) + # IBM XL C 8.0/Fortran 10.1, 11.1 on PPC and BlueGene + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_pic='-qpic' + lt_prog_compiler_static='-qstaticlink' + ;; + *) + case `$CC -V 2>&1 | sed 5q` in + *Sun\ Ceres\ Fortran* | *Sun*Fortran*\ [1-7].* | *Sun*Fortran*\ 8.[0-3]*) + # Sun Fortran 8.3 passes all unrecognized flags to the linker + lt_prog_compiler_pic='-KPIC' + lt_prog_compiler_static='-Bstatic' + lt_prog_compiler_wl='' + ;; + *Sun\ F* | *Sun*Fortran*) + lt_prog_compiler_pic='-KPIC' + lt_prog_compiler_static='-Bstatic' + lt_prog_compiler_wl='-Qoption ld ' + ;; + *Sun\ C*) + # Sun C 5.9 + lt_prog_compiler_pic='-KPIC' + lt_prog_compiler_static='-Bstatic' + lt_prog_compiler_wl='-Wl,' + ;; + *Intel*\ [CF]*Compiler*) + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_pic='-fPIC' + lt_prog_compiler_static='-static' + ;; + *Portland\ Group*) + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_pic='-fpic' + lt_prog_compiler_static='-Bstatic' + ;; + esac + ;; + esac + ;; + + newsos6) + lt_prog_compiler_pic='-KPIC' + lt_prog_compiler_static='-Bstatic' + ;; + + *nto* | *qnx*) + # QNX uses GNU C++, but need to define -shared option too, otherwise + # it will coredump. + lt_prog_compiler_pic='-fPIC -shared' + ;; + + osf3* | osf4* | osf5*) + lt_prog_compiler_wl='-Wl,' + # All OSF/1 code is PIC. + lt_prog_compiler_static='-non_shared' + ;; + + rdos*) + lt_prog_compiler_static='-non_shared' + ;; + + solaris*) + lt_prog_compiler_pic='-KPIC' + lt_prog_compiler_static='-Bstatic' + case $cc_basename in + f77* | f90* | f95* | sunf77* | sunf90* | sunf95*) + lt_prog_compiler_wl='-Qoption ld ';; + *) + lt_prog_compiler_wl='-Wl,';; + esac + ;; + + sunos4*) + lt_prog_compiler_wl='-Qoption ld ' + lt_prog_compiler_pic='-PIC' + lt_prog_compiler_static='-Bstatic' + ;; + + sysv4 | sysv4.2uw2* | sysv4.3*) + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_pic='-KPIC' + lt_prog_compiler_static='-Bstatic' + ;; + + sysv4*MP*) + if test -d /usr/nec; then + lt_prog_compiler_pic='-Kconform_pic' + lt_prog_compiler_static='-Bstatic' + fi + ;; + + sysv5* | unixware* | sco3.2v5* | sco5v6* | OpenUNIX*) + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_pic='-KPIC' + lt_prog_compiler_static='-Bstatic' + ;; + + unicos*) + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_can_build_shared=no + ;; + + uts4*) + lt_prog_compiler_pic='-pic' + lt_prog_compiler_static='-Bstatic' + ;; + + *) + lt_prog_compiler_can_build_shared=no + ;; + esac + fi + +case $host_os in + # For platforms that do not support PIC, -DPIC is meaningless: + *djgpp*) + lt_prog_compiler_pic= + ;; + *) + lt_prog_compiler_pic="$lt_prog_compiler_pic -DPIC" + ;; +esac + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $compiler option to produce PIC" >&5 +$as_echo_n "checking for $compiler option to produce PIC... " >&6; } +if ${lt_cv_prog_compiler_pic+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_prog_compiler_pic=$lt_prog_compiler_pic +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_prog_compiler_pic" >&5 +$as_echo "$lt_cv_prog_compiler_pic" >&6; } +lt_prog_compiler_pic=$lt_cv_prog_compiler_pic + +# +# Check to make sure the PIC flag actually works. +# +if test -n "$lt_prog_compiler_pic"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: checking if $compiler PIC flag $lt_prog_compiler_pic works" >&5 +$as_echo_n "checking if $compiler PIC flag $lt_prog_compiler_pic works... " >&6; } +if ${lt_cv_prog_compiler_pic_works+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_prog_compiler_pic_works=no + ac_outfile=conftest.$ac_objext + echo "$lt_simple_compile_test_code" > conftest.$ac_ext + lt_compiler_flag="$lt_prog_compiler_pic -DPIC" ## exclude from sc_useless_quotes_in_assignment + # Insert the option either (1) after the last *FLAGS variable, or + # (2) before a word containing "conftest.", or (3) at the end. + # Note that $ac_compile itself does not contain backslashes and begins + # with a dollar sign (not a hyphen), so the echo should work correctly. + # The option is referenced via a variable to avoid confusing sed. + lt_compile=`echo "$ac_compile" | $SED \ + -e 's:.*FLAGS}\{0,1\} :&$lt_compiler_flag :; t' \ + -e 's: [^ ]*conftest\.: $lt_compiler_flag&:; t' \ + -e 's:$: $lt_compiler_flag:'` + (eval echo "\"\$as_me:$LINENO: $lt_compile\"" >&5) + (eval "$lt_compile" 2>conftest.err) + ac_status=$? + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + if (exit $ac_status) && test -s "$ac_outfile"; then + # The compiler can only warn and ignore the option if not recognized + # So say no if there are warnings other than the usual output. + $ECHO "$_lt_compiler_boilerplate" | $SED '/^$/d' >conftest.exp + $SED '/^$/d; /^ *+/d' conftest.err >conftest.er2 + if test ! -s conftest.er2 || diff conftest.exp conftest.er2 >/dev/null; then + lt_cv_prog_compiler_pic_works=yes + fi + fi + $RM conftest* + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_prog_compiler_pic_works" >&5 +$as_echo "$lt_cv_prog_compiler_pic_works" >&6; } + +if test yes = "$lt_cv_prog_compiler_pic_works"; then + case $lt_prog_compiler_pic in + "" | " "*) ;; + *) lt_prog_compiler_pic=" $lt_prog_compiler_pic" ;; + esac +else + lt_prog_compiler_pic= + lt_prog_compiler_can_build_shared=no +fi + +fi + + + + + + + + + + + +# +# Check to make sure the static flag actually works. +# +wl=$lt_prog_compiler_wl eval lt_tmp_static_flag=\"$lt_prog_compiler_static\" +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking if $compiler static flag $lt_tmp_static_flag works" >&5 +$as_echo_n "checking if $compiler static flag $lt_tmp_static_flag works... " >&6; } +if ${lt_cv_prog_compiler_static_works+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_prog_compiler_static_works=no + save_LDFLAGS=$LDFLAGS + LDFLAGS="$LDFLAGS $lt_tmp_static_flag" + echo "$lt_simple_link_test_code" > conftest.$ac_ext + if (eval $ac_link 2>conftest.err) && test -s conftest$ac_exeext; then + # The linker can only warn and ignore the option if not recognized + # So say no if there are warnings + if test -s conftest.err; then + # Append any errors to the config.log. + cat conftest.err 1>&5 + $ECHO "$_lt_linker_boilerplate" | $SED '/^$/d' > conftest.exp + $SED '/^$/d; /^ *+/d' conftest.err >conftest.er2 + if diff conftest.exp conftest.er2 >/dev/null; then + lt_cv_prog_compiler_static_works=yes + fi + else + lt_cv_prog_compiler_static_works=yes + fi + fi + $RM -r conftest* + LDFLAGS=$save_LDFLAGS + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_prog_compiler_static_works" >&5 +$as_echo "$lt_cv_prog_compiler_static_works" >&6; } + +if test yes = "$lt_cv_prog_compiler_static_works"; then + : +else + lt_prog_compiler_static= +fi + + + + + + + + { $as_echo "$as_me:${as_lineno-$LINENO}: checking if $compiler supports -c -o file.$ac_objext" >&5 +$as_echo_n "checking if $compiler supports -c -o file.$ac_objext... " >&6; } +if ${lt_cv_prog_compiler_c_o+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_prog_compiler_c_o=no + $RM -r conftest 2>/dev/null + mkdir conftest + cd conftest + mkdir out + echo "$lt_simple_compile_test_code" > conftest.$ac_ext + + lt_compiler_flag="-o out/conftest2.$ac_objext" + # Insert the option either (1) after the last *FLAGS variable, or + # (2) before a word containing "conftest.", or (3) at the end. + # Note that $ac_compile itself does not contain backslashes and begins + # with a dollar sign (not a hyphen), so the echo should work correctly. + lt_compile=`echo "$ac_compile" | $SED \ + -e 's:.*FLAGS}\{0,1\} :&$lt_compiler_flag :; t' \ + -e 's: [^ ]*conftest\.: $lt_compiler_flag&:; t' \ + -e 's:$: $lt_compiler_flag:'` + (eval echo "\"\$as_me:$LINENO: $lt_compile\"" >&5) + (eval "$lt_compile" 2>out/conftest.err) + ac_status=$? + cat out/conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + if (exit $ac_status) && test -s out/conftest2.$ac_objext + then + # The compiler can only warn and ignore the option if not recognized + # So say no if there are warnings + $ECHO "$_lt_compiler_boilerplate" | $SED '/^$/d' > out/conftest.exp + $SED '/^$/d; /^ *+/d' out/conftest.err >out/conftest.er2 + if test ! -s out/conftest.er2 || diff out/conftest.exp out/conftest.er2 >/dev/null; then + lt_cv_prog_compiler_c_o=yes + fi + fi + chmod u+w . 2>&5 + $RM conftest* + # SGI C++ compiler will create directory out/ii_files/ for + # template instantiation + test -d out/ii_files && $RM out/ii_files/* && rmdir out/ii_files + $RM out/* && rmdir out + cd .. + $RM -r conftest + $RM conftest* + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_prog_compiler_c_o" >&5 +$as_echo "$lt_cv_prog_compiler_c_o" >&6; } + + + + + + + { $as_echo "$as_me:${as_lineno-$LINENO}: checking if $compiler supports -c -o file.$ac_objext" >&5 +$as_echo_n "checking if $compiler supports -c -o file.$ac_objext... " >&6; } +if ${lt_cv_prog_compiler_c_o+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_prog_compiler_c_o=no + $RM -r conftest 2>/dev/null + mkdir conftest + cd conftest + mkdir out + echo "$lt_simple_compile_test_code" > conftest.$ac_ext + + lt_compiler_flag="-o out/conftest2.$ac_objext" + # Insert the option either (1) after the last *FLAGS variable, or + # (2) before a word containing "conftest.", or (3) at the end. + # Note that $ac_compile itself does not contain backslashes and begins + # with a dollar sign (not a hyphen), so the echo should work correctly. + lt_compile=`echo "$ac_compile" | $SED \ + -e 's:.*FLAGS}\{0,1\} :&$lt_compiler_flag :; t' \ + -e 's: [^ ]*conftest\.: $lt_compiler_flag&:; t' \ + -e 's:$: $lt_compiler_flag:'` + (eval echo "\"\$as_me:$LINENO: $lt_compile\"" >&5) + (eval "$lt_compile" 2>out/conftest.err) + ac_status=$? + cat out/conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + if (exit $ac_status) && test -s out/conftest2.$ac_objext + then + # The compiler can only warn and ignore the option if not recognized + # So say no if there are warnings + $ECHO "$_lt_compiler_boilerplate" | $SED '/^$/d' > out/conftest.exp + $SED '/^$/d; /^ *+/d' out/conftest.err >out/conftest.er2 + if test ! -s out/conftest.er2 || diff out/conftest.exp out/conftest.er2 >/dev/null; then + lt_cv_prog_compiler_c_o=yes + fi + fi + chmod u+w . 2>&5 + $RM conftest* + # SGI C++ compiler will create directory out/ii_files/ for + # template instantiation + test -d out/ii_files && $RM out/ii_files/* && rmdir out/ii_files + $RM out/* && rmdir out + cd .. + $RM -r conftest + $RM conftest* + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_prog_compiler_c_o" >&5 +$as_echo "$lt_cv_prog_compiler_c_o" >&6; } + + + + +hard_links=nottested +if test no = "$lt_cv_prog_compiler_c_o" && test no != "$need_locks"; then + # do not overwrite the value of need_locks provided by the user + { $as_echo "$as_me:${as_lineno-$LINENO}: checking if we can lock with hard links" >&5 +$as_echo_n "checking if we can lock with hard links... " >&6; } + hard_links=yes + $RM conftest* + ln conftest.a conftest.b 2>/dev/null && hard_links=no + touch conftest.a + ln conftest.a conftest.b 2>&5 || hard_links=no + ln conftest.a conftest.b 2>/dev/null && hard_links=no + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $hard_links" >&5 +$as_echo "$hard_links" >&6; } + if test no = "$hard_links"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: '$CC' does not support '-c -o', so 'make -j' may be unsafe" >&5 +$as_echo "$as_me: WARNING: '$CC' does not support '-c -o', so 'make -j' may be unsafe" >&2;} + need_locks=warn + fi +else + need_locks=no +fi + + + + + + + { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether the $compiler linker ($LD) supports shared libraries" >&5 +$as_echo_n "checking whether the $compiler linker ($LD) supports shared libraries... " >&6; } + + runpath_var= + allow_undefined_flag= + always_export_symbols=no + archive_cmds= + archive_expsym_cmds= + compiler_needs_object=no + enable_shared_with_static_runtimes=no + export_dynamic_flag_spec= + export_symbols_cmds='$NM $libobjs $convenience | $global_symbol_pipe | $SED '\''s/.* //'\'' | sort | uniq > $export_symbols' + hardcode_automatic=no + hardcode_direct=no + hardcode_direct_absolute=no + hardcode_libdir_flag_spec= + hardcode_libdir_separator= + hardcode_minus_L=no + hardcode_shlibpath_var=unsupported + inherit_rpath=no + link_all_deplibs=unknown + module_cmds= + module_expsym_cmds= + old_archive_from_new_cmds= + old_archive_from_expsyms_cmds= + thread_safe_flag_spec= + whole_archive_flag_spec= + # include_expsyms should be a list of space-separated symbols to be *always* + # included in the symbol list + include_expsyms= + # exclude_expsyms can be an extended regexp of symbols to exclude + # it will be wrapped by ' (' and ')$', so one must not match beginning or + # end of line. Example: 'a|bc|.*d.*' will exclude the symbols 'a' and 'bc', + # as well as any symbol that contains 'd'. + exclude_expsyms='_GLOBAL_OFFSET_TABLE_|_GLOBAL__F[ID]_.*' + # Although _GLOBAL_OFFSET_TABLE_ is a valid symbol C name, most a.out + # platforms (ab)use it in PIC code, but their linkers get confused if + # the symbol is explicitly referenced. Since portable code cannot + # rely on this symbol name, it's probably fine to never include it in + # preloaded symbol tables. + # Exclude shared library initialization/finalization symbols. + extract_expsyms_cmds= + + case $host_os in + cygwin* | mingw* | pw32* | cegcc*) + # FIXME: the MSVC++ port hasn't been tested in a loooong time + # When not using gcc, we currently assume that we are using + # Microsoft Visual C++. + if test yes != "$GCC"; then + with_gnu_ld=no + fi + ;; + interix*) + # we just hope/assume this is gcc and not c89 (= MSVC++) + with_gnu_ld=yes + ;; + openbsd* | bitrig*) + with_gnu_ld=no + ;; + esac + + ld_shlibs=yes + + # On some targets, GNU ld is compatible enough with the native linker + # that we're better off using the native interface for both. + lt_use_gnu_ld_interface=no + if test yes = "$with_gnu_ld"; then + case $host_os in + aix*) + # The AIX port of GNU ld has always aspired to compatibility + # with the native linker. However, as the warning in the GNU ld + # block says, versions before 2.19.5* couldn't really create working + # shared libraries, regardless of the interface used. + case `$LD -v 2>&1` in + *\ \(GNU\ Binutils\)\ 2.19.5*) ;; + *\ \(GNU\ Binutils\)\ 2.[2-9]*) ;; + *\ \(GNU\ Binutils\)\ [3-9]*) ;; + *) + lt_use_gnu_ld_interface=yes + ;; + esac + ;; + *) + lt_use_gnu_ld_interface=yes + ;; + esac + fi + + if test yes = "$lt_use_gnu_ld_interface"; then + # If archive_cmds runs LD, not CC, wlarc should be empty + wlarc='$wl' + + # Set some defaults for GNU ld with shared library support. These + # are reset later if shared libraries are not supported. Putting them + # here allows them to be overridden if necessary. + runpath_var=LD_RUN_PATH + hardcode_libdir_flag_spec='$wl-rpath $wl$libdir' + export_dynamic_flag_spec='$wl--export-dynamic' + # ancient GNU ld didn't support --whole-archive et. al. + if $LD --help 2>&1 | $GREP 'no-whole-archive' > /dev/null; then + whole_archive_flag_spec=$wlarc'--whole-archive$convenience '$wlarc'--no-whole-archive' + else + whole_archive_flag_spec= + fi + supports_anon_versioning=no + case `$LD -v | $SED -e 's/(^)\+)\s\+//' 2>&1` in + *GNU\ gold*) supports_anon_versioning=yes ;; + *\ [01].* | *\ 2.[0-9].* | *\ 2.10.*) ;; # catch versions < 2.11 + *\ 2.11.93.0.2\ *) supports_anon_versioning=yes ;; # RH7.3 ... + *\ 2.11.92.0.12\ *) supports_anon_versioning=yes ;; # Mandrake 8.2 ... + *\ 2.11.*) ;; # other 2.11 versions + *) supports_anon_versioning=yes ;; + esac + + # See if GNU ld supports shared libraries. + case $host_os in + aix[3-9]*) + # On AIX/PPC, the GNU linker is very broken + if test ia64 != "$host_cpu"; then + ld_shlibs=no + cat <<_LT_EOF 1>&2 + +*** Warning: the GNU linker, at least up to release 2.19, is reported +*** to be unable to reliably create shared libraries on AIX. +*** Therefore, libtool is disabling shared libraries support. If you +*** really care for shared libraries, you may want to install binutils +*** 2.20 or above, or modify your PATH so that a non-GNU linker is found. +*** You will then need to restart the configuration process. + +_LT_EOF + fi + ;; + + amigaos*) + case $host_cpu in + powerpc) + # see comment about AmigaOS4 .so support + archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags $wl-soname $wl$soname -o $lib' + archive_expsym_cmds='' + ;; + m68k) + archive_cmds='$RM $output_objdir/a2ixlibrary.data~$ECHO "#define NAME $libname" > $output_objdir/a2ixlibrary.data~$ECHO "#define LIBRARY_ID 1" >> $output_objdir/a2ixlibrary.data~$ECHO "#define VERSION $major" >> $output_objdir/a2ixlibrary.data~$ECHO "#define REVISION $revision" >> $output_objdir/a2ixlibrary.data~$AR $AR_FLAGS $lib $libobjs~$RANLIB $lib~(cd $output_objdir && a2ixlibrary -32)' + hardcode_libdir_flag_spec='-L$libdir' + hardcode_minus_L=yes + ;; + esac + ;; + + beos*) + if $LD --help 2>&1 | $GREP ': supported targets:.* elf' > /dev/null; then + allow_undefined_flag=unsupported + # Joseph Beckenbach says some releases of gcc + # support --undefined. This deserves some investigation. FIXME + archive_cmds='$CC -nostart $libobjs $deplibs $compiler_flags $wl-soname $wl$soname -o $lib' + else + ld_shlibs=no + fi + ;; + + cygwin* | mingw* | pw32* | cegcc*) + # _LT_TAGVAR(hardcode_libdir_flag_spec, ) is actually meaningless, + # as there is no search path for DLLs. + hardcode_libdir_flag_spec='-L$libdir' + export_dynamic_flag_spec='$wl--export-all-symbols' + allow_undefined_flag=unsupported + always_export_symbols=no + enable_shared_with_static_runtimes=yes + export_symbols_cmds='$NM $libobjs $convenience | $global_symbol_pipe | $SED -e '\''/^[BCDGRS][ ]/s/.*[ ]\([^ ]*\)/\1 DATA/;s/^.*[ ]__nm__\([^ ]*\)[ ][^ ]*/\1 DATA/;/^I[ ]/d;/^[AITW][ ]/s/.* //'\'' | sort | uniq > $export_symbols' + exclude_expsyms='[_]+GLOBAL_OFFSET_TABLE_|[_]+GLOBAL__[FID]_.*|[_]+head_[A-Za-z0-9_]+_dll|[A-Za-z0-9_]+_dll_iname' + + if $LD --help 2>&1 | $GREP 'auto-import' > /dev/null; then + archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags -o $output_objdir/$soname $wl--enable-auto-image-base -Xlinker --out-implib -Xlinker $lib' + # If the export-symbols file already is a .def file, use it as + # is; otherwise, prepend EXPORTS... + archive_expsym_cmds='if test DEF = "`$SED -n -e '\''s/^[ ]*//'\'' -e '\''/^\(;.*\)*$/d'\'' -e '\''s/^\(EXPORTS\|LIBRARY\)\([ ].*\)*$/DEF/p'\'' -e q $export_symbols`" ; then + cp $export_symbols $output_objdir/$soname.def; + else + echo EXPORTS > $output_objdir/$soname.def; + cat $export_symbols >> $output_objdir/$soname.def; + fi~ + $CC -shared $output_objdir/$soname.def $libobjs $deplibs $compiler_flags -o $output_objdir/$soname $wl--enable-auto-image-base -Xlinker --out-implib -Xlinker $lib' + else + ld_shlibs=no + fi + ;; + + haiku*) + archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags $wl-soname $wl$soname -o $lib' + link_all_deplibs=yes + ;; + + os2*) + hardcode_libdir_flag_spec='-L$libdir' + hardcode_minus_L=yes + allow_undefined_flag=unsupported + shrext_cmds=.dll + archive_cmds='$ECHO "LIBRARY ${soname%$shared_ext} INITINSTANCE TERMINSTANCE" > $output_objdir/$libname.def~ + $ECHO "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~ + $ECHO "DATA MULTIPLE NONSHARED" >> $output_objdir/$libname.def~ + $ECHO EXPORTS >> $output_objdir/$libname.def~ + emxexp $libobjs | $SED /"_DLL_InitTerm"/d >> $output_objdir/$libname.def~ + $CC -Zdll -Zcrtdll -o $output_objdir/$soname $libobjs $deplibs $compiler_flags $output_objdir/$libname.def~ + emximp -o $lib $output_objdir/$libname.def' + archive_expsym_cmds='$ECHO "LIBRARY ${soname%$shared_ext} INITINSTANCE TERMINSTANCE" > $output_objdir/$libname.def~ + $ECHO "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~ + $ECHO "DATA MULTIPLE NONSHARED" >> $output_objdir/$libname.def~ + $ECHO EXPORTS >> $output_objdir/$libname.def~ + prefix_cmds="$SED"~ + if test EXPORTS = "`$SED 1q $export_symbols`"; then + prefix_cmds="$prefix_cmds -e 1d"; + fi~ + prefix_cmds="$prefix_cmds -e \"s/^\(.*\)$/_\1/g\""~ + cat $export_symbols | $prefix_cmds >> $output_objdir/$libname.def~ + $CC -Zdll -Zcrtdll -o $output_objdir/$soname $libobjs $deplibs $compiler_flags $output_objdir/$libname.def~ + emximp -o $lib $output_objdir/$libname.def' + old_archive_From_new_cmds='emximp -o $output_objdir/${libname}_dll.a $output_objdir/$libname.def' + enable_shared_with_static_runtimes=yes + ;; + + interix[3-9]*) + hardcode_direct=no + hardcode_shlibpath_var=no + hardcode_libdir_flag_spec='$wl-rpath,$libdir' + export_dynamic_flag_spec='$wl-E' + # Hack: On Interix 3.x, we cannot compile PIC because of a broken gcc. + # Instead, shared libraries are loaded at an image base (0x10000000 by + # default) and relocated if they conflict, which is a slow very memory + # consuming and fragmenting process. To avoid this, we pick a random, + # 256 KiB-aligned image base between 0x50000000 and 0x6FFC0000 at link + # time. Moving up from 0x10000000 also allows more sbrk(2) space. + archive_cmds='$CC -shared $pic_flag $libobjs $deplibs $compiler_flags $wl-h,$soname $wl--image-base,`expr ${RANDOM-$$} % 4096 / 2 \* 262144 + 1342177280` -o $lib' + archive_expsym_cmds='sed "s|^|_|" $export_symbols >$output_objdir/$soname.expsym~$CC -shared $pic_flag $libobjs $deplibs $compiler_flags $wl-h,$soname $wl--retain-symbols-file,$output_objdir/$soname.expsym $wl--image-base,`expr ${RANDOM-$$} % 4096 / 2 \* 262144 + 1342177280` -o $lib' + ;; + + gnu* | linux* | tpf* | k*bsd*-gnu | kopensolaris*-gnu) + tmp_diet=no + if test linux-dietlibc = "$host_os"; then + case $cc_basename in + diet\ *) tmp_diet=yes;; # linux-dietlibc with static linking (!diet-dyn) + esac + fi + if $LD --help 2>&1 | $EGREP ': supported targets:.* elf' > /dev/null \ + && test no = "$tmp_diet" + then + tmp_addflag=' $pic_flag' + tmp_sharedflag='-shared' + case $cc_basename,$host_cpu in + pgcc*) # Portland Group C compiler + whole_archive_flag_spec='$wl--whole-archive`for conv in $convenience\"\"; do test -n \"$conv\" && new_convenience=\"$new_convenience,$conv\"; done; func_echo_all \"$new_convenience\"` $wl--no-whole-archive' + tmp_addflag=' $pic_flag' + ;; + pgf77* | pgf90* | pgf95* | pgfortran*) + # Portland Group f77 and f90 compilers + whole_archive_flag_spec='$wl--whole-archive`for conv in $convenience\"\"; do test -n \"$conv\" && new_convenience=\"$new_convenience,$conv\"; done; func_echo_all \"$new_convenience\"` $wl--no-whole-archive' + tmp_addflag=' $pic_flag -Mnomain' ;; + ecc*,ia64* | icc*,ia64*) # Intel C compiler on ia64 + tmp_addflag=' -i_dynamic' ;; + efc*,ia64* | ifort*,ia64*) # Intel Fortran compiler on ia64 + tmp_addflag=' -i_dynamic -nofor_main' ;; + ifc* | ifort*) # Intel Fortran compiler + tmp_addflag=' -nofor_main' ;; + lf95*) # Lahey Fortran 8.1 + whole_archive_flag_spec= + tmp_sharedflag='--shared' ;; + nagfor*) # NAGFOR 5.3 + tmp_sharedflag='-Wl,-shared' ;; + xl[cC]* | bgxl[cC]* | mpixl[cC]*) # IBM XL C 8.0 on PPC (deal with xlf below) + tmp_sharedflag='-qmkshrobj' + tmp_addflag= ;; + nvcc*) # Cuda Compiler Driver 2.2 + whole_archive_flag_spec='$wl--whole-archive`for conv in $convenience\"\"; do test -n \"$conv\" && new_convenience=\"$new_convenience,$conv\"; done; func_echo_all \"$new_convenience\"` $wl--no-whole-archive' + compiler_needs_object=yes + ;; + esac + case `$CC -V 2>&1 | sed 5q` in + *Sun\ C*) # Sun C 5.9 + whole_archive_flag_spec='$wl--whole-archive`new_convenience=; for conv in $convenience\"\"; do test -z \"$conv\" || new_convenience=\"$new_convenience,$conv\"; done; func_echo_all \"$new_convenience\"` $wl--no-whole-archive' + compiler_needs_object=yes + tmp_sharedflag='-G' ;; + *Sun\ F*) # Sun Fortran 8.3 + tmp_sharedflag='-G' ;; + esac + archive_cmds='$CC '"$tmp_sharedflag""$tmp_addflag"' $libobjs $deplibs $compiler_flags $wl-soname $wl$soname -o $lib' + + if test yes = "$supports_anon_versioning"; then + archive_expsym_cmds='echo "{ global:" > $output_objdir/$libname.ver~ + cat $export_symbols | sed -e "s/\(.*\)/\1;/" >> $output_objdir/$libname.ver~ + echo "local: *; };" >> $output_objdir/$libname.ver~ + $CC '"$tmp_sharedflag""$tmp_addflag"' $libobjs $deplibs $compiler_flags $wl-soname $wl$soname $wl-version-script $wl$output_objdir/$libname.ver -o $lib' + fi + + case $cc_basename in + tcc*) + export_dynamic_flag_spec='-rdynamic' + ;; + xlf* | bgf* | bgxlf* | mpixlf*) + # IBM XL Fortran 10.1 on PPC cannot create shared libs itself + whole_archive_flag_spec='--whole-archive$convenience --no-whole-archive' + hardcode_libdir_flag_spec='$wl-rpath $wl$libdir' + archive_cmds='$LD -shared $libobjs $deplibs $linker_flags -soname $soname -o $lib' + if test yes = "$supports_anon_versioning"; then + archive_expsym_cmds='echo "{ global:" > $output_objdir/$libname.ver~ + cat $export_symbols | sed -e "s/\(.*\)/\1;/" >> $output_objdir/$libname.ver~ + echo "local: *; };" >> $output_objdir/$libname.ver~ + $LD -shared $libobjs $deplibs $linker_flags -soname $soname -version-script $output_objdir/$libname.ver -o $lib' + fi + ;; + esac + else + ld_shlibs=no + fi + ;; + + netbsd*) + if echo __ELF__ | $CC -E - | $GREP __ELF__ >/dev/null; then + archive_cmds='$LD -Bshareable $libobjs $deplibs $linker_flags -o $lib' + wlarc= + else + archive_cmds='$CC -shared $pic_flag $libobjs $deplibs $compiler_flags $wl-soname $wl$soname -o $lib' + archive_expsym_cmds='$CC -shared $pic_flag $libobjs $deplibs $compiler_flags $wl-soname $wl$soname $wl-retain-symbols-file $wl$export_symbols -o $lib' + fi + ;; + + solaris*) + if $LD -v 2>&1 | $GREP 'BFD 2\.8' > /dev/null; then + ld_shlibs=no + cat <<_LT_EOF 1>&2 + +*** Warning: The releases 2.8.* of the GNU linker cannot reliably +*** create shared libraries on Solaris systems. Therefore, libtool +*** is disabling shared libraries support. We urge you to upgrade GNU +*** binutils to release 2.9.1 or newer. Another option is to modify +*** your PATH or compiler configuration so that the native linker is +*** used, and then restart. + +_LT_EOF + elif $LD --help 2>&1 | $GREP ': supported targets:.* elf' > /dev/null; then + archive_cmds='$CC -shared $pic_flag $libobjs $deplibs $compiler_flags $wl-soname $wl$soname -o $lib' + archive_expsym_cmds='$CC -shared $pic_flag $libobjs $deplibs $compiler_flags $wl-soname $wl$soname $wl-retain-symbols-file $wl$export_symbols -o $lib' + else + ld_shlibs=no + fi + ;; + + sysv5* | sco3.2v5* | sco5v6* | unixware* | OpenUNIX*) + case `$LD -v 2>&1` in + *\ [01].* | *\ 2.[0-9].* | *\ 2.1[0-5].*) + ld_shlibs=no + cat <<_LT_EOF 1>&2 + +*** Warning: Releases of the GNU linker prior to 2.16.91.0.3 cannot +*** reliably create shared libraries on SCO systems. Therefore, libtool +*** is disabling shared libraries support. We urge you to upgrade GNU +*** binutils to release 2.16.91.0.3 or newer. Another option is to modify +*** your PATH or compiler configuration so that the native linker is +*** used, and then restart. + +_LT_EOF + ;; + *) + # For security reasons, it is highly recommended that you always + # use absolute paths for naming shared libraries, and exclude the + # DT_RUNPATH tag from executables and libraries. But doing so + # requires that you compile everything twice, which is a pain. + if $LD --help 2>&1 | $GREP ': supported targets:.* elf' > /dev/null; then + hardcode_libdir_flag_spec='$wl-rpath $wl$libdir' + archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags $wl-soname $wl$soname -o $lib' + archive_expsym_cmds='$CC -shared $libobjs $deplibs $compiler_flags $wl-soname $wl$soname $wl-retain-symbols-file $wl$export_symbols -o $lib' + else + ld_shlibs=no + fi + ;; + esac + ;; + + sunos4*) + archive_cmds='$LD -assert pure-text -Bshareable -o $lib $libobjs $deplibs $linker_flags' + wlarc= + hardcode_direct=yes + hardcode_shlibpath_var=no + ;; + + *) + if $LD --help 2>&1 | $GREP ': supported targets:.* elf' > /dev/null; then + archive_cmds='$CC -shared $pic_flag $libobjs $deplibs $compiler_flags $wl-soname $wl$soname -o $lib' + archive_expsym_cmds='$CC -shared $pic_flag $libobjs $deplibs $compiler_flags $wl-soname $wl$soname $wl-retain-symbols-file $wl$export_symbols -o $lib' + else + ld_shlibs=no + fi + ;; + esac + + if test no = "$ld_shlibs"; then + runpath_var= + hardcode_libdir_flag_spec= + export_dynamic_flag_spec= + whole_archive_flag_spec= + fi + else + # PORTME fill in a description of your system's linker (not GNU ld) + case $host_os in + aix3*) + allow_undefined_flag=unsupported + always_export_symbols=yes + archive_expsym_cmds='$LD -o $output_objdir/$soname $libobjs $deplibs $linker_flags -bE:$export_symbols -T512 -H512 -bM:SRE~$AR $AR_FLAGS $lib $output_objdir/$soname' + # Note: this linker hardcodes the directories in LIBPATH if there + # are no directories specified by -L. + hardcode_minus_L=yes + if test yes = "$GCC" && test -z "$lt_prog_compiler_static"; then + # Neither direct hardcoding nor static linking is supported with a + # broken collect2. + hardcode_direct=unsupported + fi + ;; + + aix[4-9]*) + if test ia64 = "$host_cpu"; then + # On IA64, the linker does run time linking by default, so we don't + # have to do anything special. + aix_use_runtimelinking=no + exp_sym_flag='-Bexport' + no_entry_flag= + else + # If we're using GNU nm, then we don't want the "-C" option. + # -C means demangle to GNU nm, but means don't demangle to AIX nm. + # Without the "-l" option, or with the "-B" option, AIX nm treats + # weak defined symbols like other global defined symbols, whereas + # GNU nm marks them as "W". + # While the 'weak' keyword is ignored in the Export File, we need + # it in the Import File for the 'aix-soname' feature, so we have + # to replace the "-B" option with "-P" for AIX nm. + if $NM -V 2>&1 | $GREP 'GNU' > /dev/null; then + export_symbols_cmds='$NM -Bpg $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "W")) && (substr(\$ 3,1,1) != ".")) { if (\$ 2 == "W") { print \$ 3 " weak" } else { print \$ 3 } } }'\'' | sort -u > $export_symbols' + else + export_symbols_cmds='`func_echo_all $NM | $SED -e '\''s/B\([^B]*\)$/P\1/'\''` -PCpgl $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) && (substr(\$ 1,1,1) != ".")) { if ((\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) { print \$ 1 " weak" } else { print \$ 1 } } }'\'' | sort -u > $export_symbols' + fi + aix_use_runtimelinking=no + + # Test if we are trying to use run time linking or normal + # AIX style linking. If -brtl is somewhere in LDFLAGS, we + # have runtime linking enabled, and use it for executables. + # For shared libraries, we enable/disable runtime linking + # depending on the kind of the shared library created - + # when "with_aix_soname,aix_use_runtimelinking" is: + # "aix,no" lib.a(lib.so.V) shared, rtl:no, for executables + # "aix,yes" lib.so shared, rtl:yes, for executables + # lib.a static archive + # "both,no" lib.so.V(shr.o) shared, rtl:yes + # lib.a(lib.so.V) shared, rtl:no, for executables + # "both,yes" lib.so.V(shr.o) shared, rtl:yes, for executables + # lib.a(lib.so.V) shared, rtl:no + # "svr4,*" lib.so.V(shr.o) shared, rtl:yes, for executables + # lib.a static archive + case $host_os in aix4.[23]|aix4.[23].*|aix[5-9]*) + for ld_flag in $LDFLAGS; do + if (test x-brtl = "x$ld_flag" || test x-Wl,-brtl = "x$ld_flag"); then + aix_use_runtimelinking=yes + break + fi + done + if test svr4,no = "$with_aix_soname,$aix_use_runtimelinking"; then + # With aix-soname=svr4, we create the lib.so.V shared archives only, + # so we don't have lib.a shared libs to link our executables. + # We have to force runtime linking in this case. + aix_use_runtimelinking=yes + LDFLAGS="$LDFLAGS -Wl,-brtl" + fi + ;; + esac + + exp_sym_flag='-bexport' + no_entry_flag='-bnoentry' + fi + + # When large executables or shared objects are built, AIX ld can + # have problems creating the table of contents. If linking a library + # or program results in "error TOC overflow" add -mminimal-toc to + # CXXFLAGS/CFLAGS for g++/gcc. In the cases where that is not + # enough to fix the problem, add -Wl,-bbigtoc to LDFLAGS. + + archive_cmds='' + hardcode_direct=yes + hardcode_direct_absolute=yes + hardcode_libdir_separator=':' + link_all_deplibs=yes + file_list_spec='$wl-f,' + case $with_aix_soname,$aix_use_runtimelinking in + aix,*) ;; # traditional, no import file + svr4,* | *,yes) # use import file + # The Import File defines what to hardcode. + hardcode_direct=no + hardcode_direct_absolute=no + ;; + esac + + if test yes = "$GCC"; then + case $host_os in aix4.[012]|aix4.[012].*) + # We only want to do this on AIX 4.2 and lower, the check + # below for broken collect2 doesn't work under 4.3+ + collect2name=`$CC -print-prog-name=collect2` + if test -f "$collect2name" && + strings "$collect2name" | $GREP resolve_lib_name >/dev/null + then + # We have reworked collect2 + : + else + # We have old collect2 + hardcode_direct=unsupported + # It fails to find uninstalled libraries when the uninstalled + # path is not listed in the libpath. Setting hardcode_minus_L + # to unsupported forces relinking + hardcode_minus_L=yes + hardcode_libdir_flag_spec='-L$libdir' + hardcode_libdir_separator= + fi + ;; + esac + shared_flag='-shared' + if test yes = "$aix_use_runtimelinking"; then + shared_flag="$shared_flag "'$wl-G' + fi + # Need to ensure runtime linking is disabled for the traditional + # shared library, or the linker may eventually find shared libraries + # /with/ Import File - we do not want to mix them. + shared_flag_aix='-shared' + shared_flag_svr4='-shared $wl-G' + else + # not using gcc + if test ia64 = "$host_cpu"; then + # VisualAge C++, Version 5.5 for AIX 5L for IA-64, Beta 3 Release + # chokes on -Wl,-G. The following line is correct: + shared_flag='-G' + else + if test yes = "$aix_use_runtimelinking"; then + shared_flag='$wl-G' + else + shared_flag='$wl-bM:SRE' + fi + shared_flag_aix='$wl-bM:SRE' + shared_flag_svr4='$wl-G' + fi + fi + + export_dynamic_flag_spec='$wl-bexpall' + # It seems that -bexpall does not export symbols beginning with + # underscore (_), so it is better to generate a list of symbols to export. + always_export_symbols=yes + if test aix,yes = "$with_aix_soname,$aix_use_runtimelinking"; then + # Warning - without using the other runtime loading flags (-brtl), + # -berok will link without error, but may produce a broken library. + allow_undefined_flag='-berok' + # Determine the default libpath from the value encoded in an + # empty executable. + if test set = "${lt_cv_aix_libpath+set}"; then + aix_libpath=$lt_cv_aix_libpath +else + if ${lt_cv_aix_libpath_+:} false; then : + $as_echo_n "(cached) " >&6 +else + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + + lt_aix_libpath_sed=' + /Import File Strings/,/^$/ { + /^0/ { + s/^0 *\([^ ]*\) *$/\1/ + p + } + }' + lt_cv_aix_libpath_=`dump -H conftest$ac_exeext 2>/dev/null | $SED -n -e "$lt_aix_libpath_sed"` + # Check for a 64-bit object if we didn't find anything. + if test -z "$lt_cv_aix_libpath_"; then + lt_cv_aix_libpath_=`dump -HX64 conftest$ac_exeext 2>/dev/null | $SED -n -e "$lt_aix_libpath_sed"` + fi +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext + if test -z "$lt_cv_aix_libpath_"; then + lt_cv_aix_libpath_=/usr/lib:/lib + fi + +fi + + aix_libpath=$lt_cv_aix_libpath_ +fi + + hardcode_libdir_flag_spec='$wl-blibpath:$libdir:'"$aix_libpath" + archive_expsym_cmds='$CC -o $output_objdir/$soname $libobjs $deplibs $wl'$no_entry_flag' $compiler_flags `if test -n "$allow_undefined_flag"; then func_echo_all "$wl$allow_undefined_flag"; else :; fi` $wl'$exp_sym_flag:\$export_symbols' '$shared_flag + else + if test ia64 = "$host_cpu"; then + hardcode_libdir_flag_spec='$wl-R $libdir:/usr/lib:/lib' + allow_undefined_flag="-z nodefs" + archive_expsym_cmds="\$CC $shared_flag"' -o $output_objdir/$soname $libobjs $deplibs '"\$wl$no_entry_flag"' $compiler_flags $wl$allow_undefined_flag '"\$wl$exp_sym_flag:\$export_symbols" + else + # Determine the default libpath from the value encoded in an + # empty executable. + if test set = "${lt_cv_aix_libpath+set}"; then + aix_libpath=$lt_cv_aix_libpath +else + if ${lt_cv_aix_libpath_+:} false; then : + $as_echo_n "(cached) " >&6 +else + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + + lt_aix_libpath_sed=' + /Import File Strings/,/^$/ { + /^0/ { + s/^0 *\([^ ]*\) *$/\1/ + p + } + }' + lt_cv_aix_libpath_=`dump -H conftest$ac_exeext 2>/dev/null | $SED -n -e "$lt_aix_libpath_sed"` + # Check for a 64-bit object if we didn't find anything. + if test -z "$lt_cv_aix_libpath_"; then + lt_cv_aix_libpath_=`dump -HX64 conftest$ac_exeext 2>/dev/null | $SED -n -e "$lt_aix_libpath_sed"` + fi +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext + if test -z "$lt_cv_aix_libpath_"; then + lt_cv_aix_libpath_=/usr/lib:/lib + fi + +fi + + aix_libpath=$lt_cv_aix_libpath_ +fi + + hardcode_libdir_flag_spec='$wl-blibpath:$libdir:'"$aix_libpath" + # Warning - without using the other run time loading flags, + # -berok will link without error, but may produce a broken library. + no_undefined_flag=' $wl-bernotok' + allow_undefined_flag=' $wl-berok' + if test yes = "$with_gnu_ld"; then + # We only use this code for GNU lds that support --whole-archive. + whole_archive_flag_spec='$wl--whole-archive$convenience $wl--no-whole-archive' + else + # Exported symbols can be pulled into shared objects from archives + whole_archive_flag_spec='$convenience' + fi + archive_cmds_need_lc=yes + archive_expsym_cmds='$RM -r $output_objdir/$realname.d~$MKDIR $output_objdir/$realname.d' + # -brtl affects multiple linker settings, -berok does not and is overridden later + compiler_flags_filtered='`func_echo_all "$compiler_flags " | $SED -e "s%-brtl\\([, ]\\)%-berok\\1%g"`' + if test svr4 != "$with_aix_soname"; then + # This is similar to how AIX traditionally builds its shared libraries. + archive_expsym_cmds="$archive_expsym_cmds"'~$CC '$shared_flag_aix' -o $output_objdir/$realname.d/$soname $libobjs $deplibs $wl-bnoentry '$compiler_flags_filtered'$wl-bE:$export_symbols$allow_undefined_flag~$AR $AR_FLAGS $output_objdir/$libname$release.a $output_objdir/$realname.d/$soname' + fi + if test aix != "$with_aix_soname"; then + archive_expsym_cmds="$archive_expsym_cmds"'~$CC '$shared_flag_svr4' -o $output_objdir/$realname.d/$shared_archive_member_spec.o $libobjs $deplibs $wl-bnoentry '$compiler_flags_filtered'$wl-bE:$export_symbols$allow_undefined_flag~$STRIP -e $output_objdir/$realname.d/$shared_archive_member_spec.o~( func_echo_all "#! $soname($shared_archive_member_spec.o)"; if test shr_64 = "$shared_archive_member_spec"; then func_echo_all "# 64"; else func_echo_all "# 32"; fi; cat $export_symbols ) > $output_objdir/$realname.d/$shared_archive_member_spec.imp~$AR $AR_FLAGS $output_objdir/$soname $output_objdir/$realname.d/$shared_archive_member_spec.o $output_objdir/$realname.d/$shared_archive_member_spec.imp' + else + # used by -dlpreopen to get the symbols + archive_expsym_cmds="$archive_expsym_cmds"'~$MV $output_objdir/$realname.d/$soname $output_objdir' + fi + archive_expsym_cmds="$archive_expsym_cmds"'~$RM -r $output_objdir/$realname.d' + fi + fi + ;; + + amigaos*) + case $host_cpu in + powerpc) + # see comment about AmigaOS4 .so support + archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags $wl-soname $wl$soname -o $lib' + archive_expsym_cmds='' + ;; + m68k) + archive_cmds='$RM $output_objdir/a2ixlibrary.data~$ECHO "#define NAME $libname" > $output_objdir/a2ixlibrary.data~$ECHO "#define LIBRARY_ID 1" >> $output_objdir/a2ixlibrary.data~$ECHO "#define VERSION $major" >> $output_objdir/a2ixlibrary.data~$ECHO "#define REVISION $revision" >> $output_objdir/a2ixlibrary.data~$AR $AR_FLAGS $lib $libobjs~$RANLIB $lib~(cd $output_objdir && a2ixlibrary -32)' + hardcode_libdir_flag_spec='-L$libdir' + hardcode_minus_L=yes + ;; + esac + ;; + + bsdi[45]*) + export_dynamic_flag_spec=-rdynamic + ;; + + cygwin* | mingw* | pw32* | cegcc*) + # When not using gcc, we currently assume that we are using + # Microsoft Visual C++. + # hardcode_libdir_flag_spec is actually meaningless, as there is + # no search path for DLLs. + case $cc_basename in + cl*) + # Native MSVC + hardcode_libdir_flag_spec=' ' + allow_undefined_flag=unsupported + always_export_symbols=yes + file_list_spec='@' + # Tell ltmain to make .lib files, not .a files. + libext=lib + # Tell ltmain to make .dll files, not .so files. + shrext_cmds=.dll + # FIXME: Setting linknames here is a bad hack. + archive_cmds='$CC -o $output_objdir/$soname $libobjs $compiler_flags $deplibs -Wl,-DLL,-IMPLIB:"$tool_output_objdir$libname.dll.lib"~linknames=' + archive_expsym_cmds='if test DEF = "`$SED -n -e '\''s/^[ ]*//'\'' -e '\''/^\(;.*\)*$/d'\'' -e '\''s/^\(EXPORTS\|LIBRARY\)\([ ].*\)*$/DEF/p'\'' -e q $export_symbols`" ; then + cp "$export_symbols" "$output_objdir/$soname.def"; + echo "$tool_output_objdir$soname.def" > "$output_objdir/$soname.exp"; + else + $SED -e '\''s/^/-link -EXPORT:/'\'' < $export_symbols > $output_objdir/$soname.exp; + fi~ + $CC -o $tool_output_objdir$soname $libobjs $compiler_flags $deplibs "@$tool_output_objdir$soname.exp" -Wl,-DLL,-IMPLIB:"$tool_output_objdir$libname.dll.lib"~ + linknames=' + # The linker will not automatically build a static lib if we build a DLL. + # _LT_TAGVAR(old_archive_from_new_cmds, )='true' + enable_shared_with_static_runtimes=yes + exclude_expsyms='_NULL_IMPORT_DESCRIPTOR|_IMPORT_DESCRIPTOR_.*' + export_symbols_cmds='$NM $libobjs $convenience | $global_symbol_pipe | $SED -e '\''/^[BCDGRS][ ]/s/.*[ ]\([^ ]*\)/\1,DATA/'\'' | $SED -e '\''/^[AITW][ ]/s/.*[ ]//'\'' | sort | uniq > $export_symbols' + # Don't use ranlib + old_postinstall_cmds='chmod 644 $oldlib' + postlink_cmds='lt_outputfile="@OUTPUT@"~ + lt_tool_outputfile="@TOOL_OUTPUT@"~ + case $lt_outputfile in + *.exe|*.EXE) ;; + *) + lt_outputfile=$lt_outputfile.exe + lt_tool_outputfile=$lt_tool_outputfile.exe + ;; + esac~ + if test : != "$MANIFEST_TOOL" && test -f "$lt_outputfile.manifest"; then + $MANIFEST_TOOL -manifest "$lt_tool_outputfile.manifest" -outputresource:"$lt_tool_outputfile" || exit 1; + $RM "$lt_outputfile.manifest"; + fi' + ;; + *) + # Assume MSVC wrapper + hardcode_libdir_flag_spec=' ' + allow_undefined_flag=unsupported + # Tell ltmain to make .lib files, not .a files. + libext=lib + # Tell ltmain to make .dll files, not .so files. + shrext_cmds=.dll + # FIXME: Setting linknames here is a bad hack. + archive_cmds='$CC -o $lib $libobjs $compiler_flags `func_echo_all "$deplibs" | $SED '\''s/ -lc$//'\''` -link -dll~linknames=' + # The linker will automatically build a .lib file if we build a DLL. + old_archive_from_new_cmds='true' + # FIXME: Should let the user specify the lib program. + old_archive_cmds='lib -OUT:$oldlib$oldobjs$old_deplibs' + enable_shared_with_static_runtimes=yes + ;; + esac + ;; + + darwin* | rhapsody*) + + + archive_cmds_need_lc=no + hardcode_direct=no + hardcode_automatic=yes + hardcode_shlibpath_var=unsupported + if test yes = "$lt_cv_ld_force_load"; then + whole_archive_flag_spec='`for conv in $convenience\"\"; do test -n \"$conv\" && new_convenience=\"$new_convenience $wl-force_load,$conv\"; done; func_echo_all \"$new_convenience\"`' + + else + whole_archive_flag_spec='' + fi + link_all_deplibs=yes + allow_undefined_flag=$_lt_dar_allow_undefined + case $cc_basename in + ifort*|nagfor*) _lt_dar_can_shared=yes ;; + *) _lt_dar_can_shared=$GCC ;; + esac + if test yes = "$_lt_dar_can_shared"; then + output_verbose_link_cmd=func_echo_all + archive_cmds="\$CC -dynamiclib \$allow_undefined_flag -o \$lib \$libobjs \$deplibs \$compiler_flags -install_name \$rpath/\$soname \$verstring $_lt_dar_single_mod$_lt_dsymutil" + module_cmds="\$CC \$allow_undefined_flag -o \$lib -bundle \$libobjs \$deplibs \$compiler_flags$_lt_dsymutil" + archive_expsym_cmds="sed 's|^|_|' < \$export_symbols > \$output_objdir/\$libname-symbols.expsym~\$CC -dynamiclib \$allow_undefined_flag -o \$lib \$libobjs \$deplibs \$compiler_flags -install_name \$rpath/\$soname \$verstring $_lt_dar_single_mod$_lt_dar_export_syms$_lt_dsymutil" + module_expsym_cmds="sed -e 's|^|_|' < \$export_symbols > \$output_objdir/\$libname-symbols.expsym~\$CC \$allow_undefined_flag -o \$lib -bundle \$libobjs \$deplibs \$compiler_flags$_lt_dar_export_syms$_lt_dsymutil" + + else + ld_shlibs=no + fi + + ;; + + dgux*) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_libdir_flag_spec='-L$libdir' + hardcode_shlibpath_var=no + ;; + + # FreeBSD 2.2.[012] allows us to include c++rt0.o to get C++ constructor + # support. Future versions do this automatically, but an explicit c++rt0.o + # does not break anything, and helps significantly (at the cost of a little + # extra space). + freebsd2.2*) + archive_cmds='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags /usr/lib/c++rt0.o' + hardcode_libdir_flag_spec='-R$libdir' + hardcode_direct=yes + hardcode_shlibpath_var=no + ;; + + # Unfortunately, older versions of FreeBSD 2 do not have this feature. + freebsd2.*) + archive_cmds='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags' + hardcode_direct=yes + hardcode_minus_L=yes + hardcode_shlibpath_var=no + ;; + + # FreeBSD 3 and greater uses gcc -shared to do shared libraries. + freebsd* | dragonfly*) + archive_cmds='$CC -shared $pic_flag -o $lib $libobjs $deplibs $compiler_flags' + hardcode_libdir_flag_spec='-R$libdir' + hardcode_direct=yes + hardcode_shlibpath_var=no + ;; + + hpux9*) + if test yes = "$GCC"; then + archive_cmds='$RM $output_objdir/$soname~$CC -shared $pic_flag $wl+b $wl$install_libdir -o $output_objdir/$soname $libobjs $deplibs $compiler_flags~test "x$output_objdir/$soname" = "x$lib" || mv $output_objdir/$soname $lib' + else + archive_cmds='$RM $output_objdir/$soname~$LD -b +b $install_libdir -o $output_objdir/$soname $libobjs $deplibs $linker_flags~test "x$output_objdir/$soname" = "x$lib" || mv $output_objdir/$soname $lib' + fi + hardcode_libdir_flag_spec='$wl+b $wl$libdir' + hardcode_libdir_separator=: + hardcode_direct=yes + + # hardcode_minus_L: Not really in the search PATH, + # but as the default location of the library. + hardcode_minus_L=yes + export_dynamic_flag_spec='$wl-E' + ;; + + hpux10*) + if test yes,no = "$GCC,$with_gnu_ld"; then + archive_cmds='$CC -shared $pic_flag $wl+h $wl$soname $wl+b $wl$install_libdir -o $lib $libobjs $deplibs $compiler_flags' + else + archive_cmds='$LD -b +h $soname +b $install_libdir -o $lib $libobjs $deplibs $linker_flags' + fi + if test no = "$with_gnu_ld"; then + hardcode_libdir_flag_spec='$wl+b $wl$libdir' + hardcode_libdir_separator=: + hardcode_direct=yes + hardcode_direct_absolute=yes + export_dynamic_flag_spec='$wl-E' + # hardcode_minus_L: Not really in the search PATH, + # but as the default location of the library. + hardcode_minus_L=yes + fi + ;; + + hpux11*) + if test yes,no = "$GCC,$with_gnu_ld"; then + case $host_cpu in + hppa*64*) + archive_cmds='$CC -shared $wl+h $wl$soname -o $lib $libobjs $deplibs $compiler_flags' + ;; + ia64*) + archive_cmds='$CC -shared $pic_flag $wl+h $wl$soname $wl+nodefaultrpath -o $lib $libobjs $deplibs $compiler_flags' + ;; + *) + archive_cmds='$CC -shared $pic_flag $wl+h $wl$soname $wl+b $wl$install_libdir -o $lib $libobjs $deplibs $compiler_flags' + ;; + esac + else + case $host_cpu in + hppa*64*) + archive_cmds='$CC -b $wl+h $wl$soname -o $lib $libobjs $deplibs $compiler_flags' + ;; + ia64*) + archive_cmds='$CC -b $wl+h $wl$soname $wl+nodefaultrpath -o $lib $libobjs $deplibs $compiler_flags' + ;; + *) + + # Older versions of the 11.00 compiler do not understand -b yet + # (HP92453-01 A.11.01.20 doesn't, HP92453-01 B.11.X.35175-35176.GP does) + { $as_echo "$as_me:${as_lineno-$LINENO}: checking if $CC understands -b" >&5 +$as_echo_n "checking if $CC understands -b... " >&6; } +if ${lt_cv_prog_compiler__b+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_prog_compiler__b=no + save_LDFLAGS=$LDFLAGS + LDFLAGS="$LDFLAGS -b" + echo "$lt_simple_link_test_code" > conftest.$ac_ext + if (eval $ac_link 2>conftest.err) && test -s conftest$ac_exeext; then + # The linker can only warn and ignore the option if not recognized + # So say no if there are warnings + if test -s conftest.err; then + # Append any errors to the config.log. + cat conftest.err 1>&5 + $ECHO "$_lt_linker_boilerplate" | $SED '/^$/d' > conftest.exp + $SED '/^$/d; /^ *+/d' conftest.err >conftest.er2 + if diff conftest.exp conftest.er2 >/dev/null; then + lt_cv_prog_compiler__b=yes + fi + else + lt_cv_prog_compiler__b=yes + fi + fi + $RM -r conftest* + LDFLAGS=$save_LDFLAGS + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_prog_compiler__b" >&5 +$as_echo "$lt_cv_prog_compiler__b" >&6; } + +if test yes = "$lt_cv_prog_compiler__b"; then + archive_cmds='$CC -b $wl+h $wl$soname $wl+b $wl$install_libdir -o $lib $libobjs $deplibs $compiler_flags' +else + archive_cmds='$LD -b +h $soname +b $install_libdir -o $lib $libobjs $deplibs $linker_flags' +fi + + ;; + esac + fi + if test no = "$with_gnu_ld"; then + hardcode_libdir_flag_spec='$wl+b $wl$libdir' + hardcode_libdir_separator=: + + case $host_cpu in + hppa*64*|ia64*) + hardcode_direct=no + hardcode_shlibpath_var=no + ;; + *) + hardcode_direct=yes + hardcode_direct_absolute=yes + export_dynamic_flag_spec='$wl-E' + + # hardcode_minus_L: Not really in the search PATH, + # but as the default location of the library. + hardcode_minus_L=yes + ;; + esac + fi + ;; + + irix5* | irix6* | nonstopux*) + if test yes = "$GCC"; then + archive_cmds='$CC -shared $pic_flag $libobjs $deplibs $compiler_flags $wl-soname $wl$soname `test -n "$verstring" && func_echo_all "$wl-set_version $wl$verstring"` $wl-update_registry $wl$output_objdir/so_locations -o $lib' + # Try to use the -exported_symbol ld option, if it does not + # work, assume that -exports_file does not work either and + # implicitly export all symbols. + # This should be the same for all languages, so no per-tag cache variable. + { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether the $host_os linker accepts -exported_symbol" >&5 +$as_echo_n "checking whether the $host_os linker accepts -exported_symbol... " >&6; } +if ${lt_cv_irix_exported_symbol+:} false; then : + $as_echo_n "(cached) " >&6 +else + save_LDFLAGS=$LDFLAGS + LDFLAGS="$LDFLAGS -shared $wl-exported_symbol ${wl}foo $wl-update_registry $wl/dev/null" + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +int foo (void) { return 0; } +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + lt_cv_irix_exported_symbol=yes +else + lt_cv_irix_exported_symbol=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext + LDFLAGS=$save_LDFLAGS +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_irix_exported_symbol" >&5 +$as_echo "$lt_cv_irix_exported_symbol" >&6; } + if test yes = "$lt_cv_irix_exported_symbol"; then + archive_expsym_cmds='$CC -shared $pic_flag $libobjs $deplibs $compiler_flags $wl-soname $wl$soname `test -n "$verstring" && func_echo_all "$wl-set_version $wl$verstring"` $wl-update_registry $wl$output_objdir/so_locations $wl-exports_file $wl$export_symbols -o $lib' + fi + else + archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags -soname $soname `test -n "$verstring" && func_echo_all "-set_version $verstring"` -update_registry $output_objdir/so_locations -o $lib' + archive_expsym_cmds='$CC -shared $libobjs $deplibs $compiler_flags -soname $soname `test -n "$verstring" && func_echo_all "-set_version $verstring"` -update_registry $output_objdir/so_locations -exports_file $export_symbols -o $lib' + fi + archive_cmds_need_lc='no' + hardcode_libdir_flag_spec='$wl-rpath $wl$libdir' + hardcode_libdir_separator=: + inherit_rpath=yes + link_all_deplibs=yes + ;; + + linux*) + case $cc_basename in + tcc*) + # Fabrice Bellard et al's Tiny C Compiler + ld_shlibs=yes + archive_cmds='$CC -shared $pic_flag -o $lib $libobjs $deplibs $compiler_flags' + ;; + esac + ;; + + netbsd*) + if echo __ELF__ | $CC -E - | $GREP __ELF__ >/dev/null; then + archive_cmds='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags' # a.out + else + archive_cmds='$LD -shared -o $lib $libobjs $deplibs $linker_flags' # ELF + fi + hardcode_libdir_flag_spec='-R$libdir' + hardcode_direct=yes + hardcode_shlibpath_var=no + ;; + + newsos6) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_direct=yes + hardcode_libdir_flag_spec='$wl-rpath $wl$libdir' + hardcode_libdir_separator=: + hardcode_shlibpath_var=no + ;; + + *nto* | *qnx*) + ;; + + openbsd* | bitrig*) + if test -f /usr/libexec/ld.so; then + hardcode_direct=yes + hardcode_shlibpath_var=no + hardcode_direct_absolute=yes + if test -z "`echo __ELF__ | $CC -E - | $GREP __ELF__`"; then + archive_cmds='$CC -shared $pic_flag -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds='$CC -shared $pic_flag -o $lib $libobjs $deplibs $compiler_flags $wl-retain-symbols-file,$export_symbols' + hardcode_libdir_flag_spec='$wl-rpath,$libdir' + export_dynamic_flag_spec='$wl-E' + else + archive_cmds='$CC -shared $pic_flag -o $lib $libobjs $deplibs $compiler_flags' + hardcode_libdir_flag_spec='$wl-rpath,$libdir' + fi + else + ld_shlibs=no + fi + ;; + + os2*) + hardcode_libdir_flag_spec='-L$libdir' + hardcode_minus_L=yes + allow_undefined_flag=unsupported + shrext_cmds=.dll + archive_cmds='$ECHO "LIBRARY ${soname%$shared_ext} INITINSTANCE TERMINSTANCE" > $output_objdir/$libname.def~ + $ECHO "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~ + $ECHO "DATA MULTIPLE NONSHARED" >> $output_objdir/$libname.def~ + $ECHO EXPORTS >> $output_objdir/$libname.def~ + emxexp $libobjs | $SED /"_DLL_InitTerm"/d >> $output_objdir/$libname.def~ + $CC -Zdll -Zcrtdll -o $output_objdir/$soname $libobjs $deplibs $compiler_flags $output_objdir/$libname.def~ + emximp -o $lib $output_objdir/$libname.def' + archive_expsym_cmds='$ECHO "LIBRARY ${soname%$shared_ext} INITINSTANCE TERMINSTANCE" > $output_objdir/$libname.def~ + $ECHO "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~ + $ECHO "DATA MULTIPLE NONSHARED" >> $output_objdir/$libname.def~ + $ECHO EXPORTS >> $output_objdir/$libname.def~ + prefix_cmds="$SED"~ + if test EXPORTS = "`$SED 1q $export_symbols`"; then + prefix_cmds="$prefix_cmds -e 1d"; + fi~ + prefix_cmds="$prefix_cmds -e \"s/^\(.*\)$/_\1/g\""~ + cat $export_symbols | $prefix_cmds >> $output_objdir/$libname.def~ + $CC -Zdll -Zcrtdll -o $output_objdir/$soname $libobjs $deplibs $compiler_flags $output_objdir/$libname.def~ + emximp -o $lib $output_objdir/$libname.def' + old_archive_From_new_cmds='emximp -o $output_objdir/${libname}_dll.a $output_objdir/$libname.def' + enable_shared_with_static_runtimes=yes + ;; + + osf3*) + if test yes = "$GCC"; then + allow_undefined_flag=' $wl-expect_unresolved $wl\*' + archive_cmds='$CC -shared$allow_undefined_flag $libobjs $deplibs $compiler_flags $wl-soname $wl$soname `test -n "$verstring" && func_echo_all "$wl-set_version $wl$verstring"` $wl-update_registry $wl$output_objdir/so_locations -o $lib' + else + allow_undefined_flag=' -expect_unresolved \*' + archive_cmds='$CC -shared$allow_undefined_flag $libobjs $deplibs $compiler_flags -soname $soname `test -n "$verstring" && func_echo_all "-set_version $verstring"` -update_registry $output_objdir/so_locations -o $lib' + fi + archive_cmds_need_lc='no' + hardcode_libdir_flag_spec='$wl-rpath $wl$libdir' + hardcode_libdir_separator=: + ;; + + osf4* | osf5*) # as osf3* with the addition of -msym flag + if test yes = "$GCC"; then + allow_undefined_flag=' $wl-expect_unresolved $wl\*' + archive_cmds='$CC -shared$allow_undefined_flag $pic_flag $libobjs $deplibs $compiler_flags $wl-msym $wl-soname $wl$soname `test -n "$verstring" && func_echo_all "$wl-set_version $wl$verstring"` $wl-update_registry $wl$output_objdir/so_locations -o $lib' + hardcode_libdir_flag_spec='$wl-rpath $wl$libdir' + else + allow_undefined_flag=' -expect_unresolved \*' + archive_cmds='$CC -shared$allow_undefined_flag $libobjs $deplibs $compiler_flags -msym -soname $soname `test -n "$verstring" && func_echo_all "-set_version $verstring"` -update_registry $output_objdir/so_locations -o $lib' + archive_expsym_cmds='for i in `cat $export_symbols`; do printf "%s %s\\n" -exported_symbol "\$i" >> $lib.exp; done; printf "%s\\n" "-hidden">> $lib.exp~ + $CC -shared$allow_undefined_flag $wl-input $wl$lib.exp $compiler_flags $libobjs $deplibs -soname $soname `test -n "$verstring" && $ECHO "-set_version $verstring"` -update_registry $output_objdir/so_locations -o $lib~$RM $lib.exp' + + # Both c and cxx compiler support -rpath directly + hardcode_libdir_flag_spec='-rpath $libdir' + fi + archive_cmds_need_lc='no' + hardcode_libdir_separator=: + ;; + + solaris*) + no_undefined_flag=' -z defs' + if test yes = "$GCC"; then + wlarc='$wl' + archive_cmds='$CC -shared $pic_flag $wl-z ${wl}text $wl-h $wl$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds='echo "{ global:" > $lib.exp~cat $export_symbols | $SED -e "s/\(.*\)/\1;/" >> $lib.exp~echo "local: *; };" >> $lib.exp~ + $CC -shared $pic_flag $wl-z ${wl}text $wl-M $wl$lib.exp $wl-h $wl$soname -o $lib $libobjs $deplibs $compiler_flags~$RM $lib.exp' + else + case `$CC -V 2>&1` in + *"Compilers 5.0"*) + wlarc='' + archive_cmds='$LD -G$allow_undefined_flag -h $soname -o $lib $libobjs $deplibs $linker_flags' + archive_expsym_cmds='echo "{ global:" > $lib.exp~cat $export_symbols | $SED -e "s/\(.*\)/\1;/" >> $lib.exp~echo "local: *; };" >> $lib.exp~ + $LD -G$allow_undefined_flag -M $lib.exp -h $soname -o $lib $libobjs $deplibs $linker_flags~$RM $lib.exp' + ;; + *) + wlarc='$wl' + archive_cmds='$CC -G$allow_undefined_flag -h $soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds='echo "{ global:" > $lib.exp~cat $export_symbols | $SED -e "s/\(.*\)/\1;/" >> $lib.exp~echo "local: *; };" >> $lib.exp~ + $CC -G$allow_undefined_flag -M $lib.exp -h $soname -o $lib $libobjs $deplibs $compiler_flags~$RM $lib.exp' + ;; + esac + fi + hardcode_libdir_flag_spec='-R$libdir' + hardcode_shlibpath_var=no + case $host_os in + solaris2.[0-5] | solaris2.[0-5].*) ;; + *) + # The compiler driver will combine and reorder linker options, + # but understands '-z linker_flag'. GCC discards it without '$wl', + # but is careful enough not to reorder. + # Supported since Solaris 2.6 (maybe 2.5.1?) + if test yes = "$GCC"; then + whole_archive_flag_spec='$wl-z ${wl}allextract$convenience $wl-z ${wl}defaultextract' + else + whole_archive_flag_spec='-z allextract$convenience -z defaultextract' + fi + ;; + esac + link_all_deplibs=yes + ;; + + sunos4*) + if test sequent = "$host_vendor"; then + # Use $CC to link under sequent, because it throws in some extra .o + # files that make .init and .fini sections work. + archive_cmds='$CC -G $wl-h $soname -o $lib $libobjs $deplibs $compiler_flags' + else + archive_cmds='$LD -assert pure-text -Bstatic -o $lib $libobjs $deplibs $linker_flags' + fi + hardcode_libdir_flag_spec='-L$libdir' + hardcode_direct=yes + hardcode_minus_L=yes + hardcode_shlibpath_var=no + ;; + + sysv4) + case $host_vendor in + sni) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_direct=yes # is this really true??? + ;; + siemens) + ## LD is ld it makes a PLAMLIB + ## CC just makes a GrossModule. + archive_cmds='$LD -G -o $lib $libobjs $deplibs $linker_flags' + reload_cmds='$CC -r -o $output$reload_objs' + hardcode_direct=no + ;; + motorola) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_direct=no #Motorola manual says yes, but my tests say they lie + ;; + esac + runpath_var='LD_RUN_PATH' + hardcode_shlibpath_var=no + ;; + + sysv4.3*) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_shlibpath_var=no + export_dynamic_flag_spec='-Bexport' + ;; + + sysv4*MP*) + if test -d /usr/nec; then + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_shlibpath_var=no + runpath_var=LD_RUN_PATH + hardcode_runpath_var=yes + ld_shlibs=yes + fi + ;; + + sysv4*uw2* | sysv5OpenUNIX* | sysv5UnixWare7.[01].[10]* | unixware7* | sco3.2v5.0.[024]*) + no_undefined_flag='$wl-z,text' + archive_cmds_need_lc=no + hardcode_shlibpath_var=no + runpath_var='LD_RUN_PATH' + + if test yes = "$GCC"; then + archive_cmds='$CC -shared $wl-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds='$CC -shared $wl-Bexport:$export_symbols $wl-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + else + archive_cmds='$CC -G $wl-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds='$CC -G $wl-Bexport:$export_symbols $wl-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + fi + ;; + + sysv5* | sco3.2v5* | sco5v6*) + # Note: We CANNOT use -z defs as we might desire, because we do not + # link with -lc, and that would cause any symbols used from libc to + # always be unresolved, which means just about no library would + # ever link correctly. If we're not using GNU ld we use -z text + # though, which does catch some bad symbols but isn't as heavy-handed + # as -z defs. + no_undefined_flag='$wl-z,text' + allow_undefined_flag='$wl-z,nodefs' + archive_cmds_need_lc=no + hardcode_shlibpath_var=no + hardcode_libdir_flag_spec='$wl-R,$libdir' + hardcode_libdir_separator=':' + link_all_deplibs=yes + export_dynamic_flag_spec='$wl-Bexport' + runpath_var='LD_RUN_PATH' + + if test yes = "$GCC"; then + archive_cmds='$CC -shared $wl-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds='$CC -shared $wl-Bexport:$export_symbols $wl-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + else + archive_cmds='$CC -G $wl-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds='$CC -G $wl-Bexport:$export_symbols $wl-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + fi + ;; + + uts4*) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_libdir_flag_spec='-L$libdir' + hardcode_shlibpath_var=no + ;; + + *) + ld_shlibs=no + ;; + esac + + if test sni = "$host_vendor"; then + case $host in + sysv4 | sysv4.2uw2* | sysv4.3* | sysv5*) + export_dynamic_flag_spec='$wl-Blargedynsym' + ;; + esac + fi + fi + +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ld_shlibs" >&5 +$as_echo "$ld_shlibs" >&6; } +test no = "$ld_shlibs" && can_build_shared=no + +with_gnu_ld=$with_gnu_ld + + + + + + + + + + + + + + + +# +# Do we need to explicitly link libc? +# +case "x$archive_cmds_need_lc" in +x|xyes) + # Assume -lc should be added + archive_cmds_need_lc=yes + + if test yes,yes = "$GCC,$enable_shared"; then + case $archive_cmds in + *'~'*) + # FIXME: we may have to deal with multi-command sequences. + ;; + '$CC '*) + # Test whether the compiler implicitly links with -lc since on some + # systems, -lgcc has to come before -lc. If gcc already passes -lc + # to ld, don't add -lc before -lgcc. + { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether -lc should be explicitly linked in" >&5 +$as_echo_n "checking whether -lc should be explicitly linked in... " >&6; } +if ${lt_cv_archive_cmds_need_lc+:} false; then : + $as_echo_n "(cached) " >&6 +else + $RM conftest* + echo "$lt_simple_compile_test_code" > conftest.$ac_ext + + if { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$ac_compile\""; } >&5 + (eval $ac_compile) 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } 2>conftest.err; then + soname=conftest + lib=conftest + libobjs=conftest.$ac_objext + deplibs= + wl=$lt_prog_compiler_wl + pic_flag=$lt_prog_compiler_pic + compiler_flags=-v + linker_flags=-v + verstring= + output_objdir=. + libname=conftest + lt_save_allow_undefined_flag=$allow_undefined_flag + allow_undefined_flag= + if { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$archive_cmds 2\>\&1 \| $GREP \" -lc \" \>/dev/null 2\>\&1\""; } >&5 + (eval $archive_cmds 2\>\&1 \| $GREP \" -lc \" \>/dev/null 2\>\&1) 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } + then + lt_cv_archive_cmds_need_lc=no + else + lt_cv_archive_cmds_need_lc=yes + fi + allow_undefined_flag=$lt_save_allow_undefined_flag + else + cat conftest.err 1>&5 + fi + $RM conftest* + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_archive_cmds_need_lc" >&5 +$as_echo "$lt_cv_archive_cmds_need_lc" >&6; } + archive_cmds_need_lc=$lt_cv_archive_cmds_need_lc + ;; + esac + fi + ;; +esac + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + { $as_echo "$as_me:${as_lineno-$LINENO}: checking dynamic linker characteristics" >&5 +$as_echo_n "checking dynamic linker characteristics... " >&6; } + +if test yes = "$GCC"; then + case $host_os in + darwin*) lt_awk_arg='/^libraries:/,/LR/' ;; + *) lt_awk_arg='/^libraries:/' ;; + esac + case $host_os in + mingw* | cegcc*) lt_sed_strip_eq='s|=\([A-Za-z]:\)|\1|g' ;; + *) lt_sed_strip_eq='s|=/|/|g' ;; + esac + lt_search_path_spec=`$CC -print-search-dirs | awk $lt_awk_arg | $SED -e "s/^libraries://" -e $lt_sed_strip_eq` + case $lt_search_path_spec in + *\;*) + # if the path contains ";" then we assume it to be the separator + # otherwise default to the standard path separator (i.e. ":") - it is + # assumed that no part of a normal pathname contains ";" but that should + # okay in the real world where ";" in dirpaths is itself problematic. + lt_search_path_spec=`$ECHO "$lt_search_path_spec" | $SED 's/;/ /g'` + ;; + *) + lt_search_path_spec=`$ECHO "$lt_search_path_spec" | $SED "s/$PATH_SEPARATOR/ /g"` + ;; + esac + # Ok, now we have the path, separated by spaces, we can step through it + # and add multilib dir if necessary... + lt_tmp_lt_search_path_spec= + lt_multi_os_dir=/`$CC $CPPFLAGS $CFLAGS $LDFLAGS -print-multi-os-directory 2>/dev/null` + # ...but if some path component already ends with the multilib dir we assume + # that all is fine and trust -print-search-dirs as is (GCC 4.2? or newer). + case "$lt_multi_os_dir; $lt_search_path_spec " in + "/; "* | "/.; "* | "/./; "* | *"$lt_multi_os_dir "* | *"$lt_multi_os_dir/ "*) + lt_multi_os_dir= + ;; + esac + for lt_sys_path in $lt_search_path_spec; do + if test -d "$lt_sys_path$lt_multi_os_dir"; then + lt_tmp_lt_search_path_spec="$lt_tmp_lt_search_path_spec $lt_sys_path$lt_multi_os_dir" + elif test -n "$lt_multi_os_dir"; then + test -d "$lt_sys_path" && \ + lt_tmp_lt_search_path_spec="$lt_tmp_lt_search_path_spec $lt_sys_path" + fi + done + lt_search_path_spec=`$ECHO "$lt_tmp_lt_search_path_spec" | awk ' +BEGIN {RS = " "; FS = "/|\n";} { + lt_foo = ""; + lt_count = 0; + for (lt_i = NF; lt_i > 0; lt_i--) { + if ($lt_i != "" && $lt_i != ".") { + if ($lt_i == "..") { + lt_count++; + } else { + if (lt_count == 0) { + lt_foo = "/" $lt_i lt_foo; + } else { + lt_count--; + } + } + } + } + if (lt_foo != "") { lt_freq[lt_foo]++; } + if (lt_freq[lt_foo] == 1) { print lt_foo; } +}'` + # AWK program above erroneously prepends '/' to C:/dos/paths + # for these hosts. + case $host_os in + mingw* | cegcc*) lt_search_path_spec=`$ECHO "$lt_search_path_spec" |\ + $SED 's|/\([A-Za-z]:\)|\1|g'` ;; + esac + sys_lib_search_path_spec=`$ECHO "$lt_search_path_spec" | $lt_NL2SP` +else + sys_lib_search_path_spec="/lib /usr/lib /usr/local/lib" +fi +library_names_spec= +libname_spec='lib$name' +soname_spec= +shrext_cmds=.so +postinstall_cmds= +postuninstall_cmds= +finish_cmds= +finish_eval= +shlibpath_var= +shlibpath_overrides_runpath=unknown +version_type=none +dynamic_linker="$host_os ld.so" +sys_lib_dlsearch_path_spec="/lib /usr/lib" +need_lib_prefix=unknown +hardcode_into_libs=no + +# when you set need_version to no, make sure it does not cause -set_version +# flags to be left without arguments +need_version=unknown + + + +case $host_os in +aix3*) + version_type=linux # correct to gnu/linux during the next big refactor + library_names_spec='$libname$release$shared_ext$versuffix $libname.a' + shlibpath_var=LIBPATH + + # AIX 3 has no versioning support, so we append a major version to the name. + soname_spec='$libname$release$shared_ext$major' + ;; + +aix[4-9]*) + version_type=linux # correct to gnu/linux during the next big refactor + need_lib_prefix=no + need_version=no + hardcode_into_libs=yes + if test ia64 = "$host_cpu"; then + # AIX 5 supports IA64 + library_names_spec='$libname$release$shared_ext$major $libname$release$shared_ext$versuffix $libname$shared_ext' + shlibpath_var=LD_LIBRARY_PATH + else + # With GCC up to 2.95.x, collect2 would create an import file + # for dependence libraries. The import file would start with + # the line '#! .'. This would cause the generated library to + # depend on '.', always an invalid library. This was fixed in + # development snapshots of GCC prior to 3.0. + case $host_os in + aix4 | aix4.[01] | aix4.[01].*) + if { echo '#if __GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 97)' + echo ' yes ' + echo '#endif'; } | $CC -E - | $GREP yes > /dev/null; then + : + else + can_build_shared=no + fi + ;; + esac + # Using Import Files as archive members, it is possible to support + # filename-based versioning of shared library archives on AIX. While + # this would work for both with and without runtime linking, it will + # prevent static linking of such archives. So we do filename-based + # shared library versioning with .so extension only, which is used + # when both runtime linking and shared linking is enabled. + # Unfortunately, runtime linking may impact performance, so we do + # not want this to be the default eventually. Also, we use the + # versioned .so libs for executables only if there is the -brtl + # linker flag in LDFLAGS as well, or --with-aix-soname=svr4 only. + # To allow for filename-based versioning support, we need to create + # libNAME.so.V as an archive file, containing: + # *) an Import File, referring to the versioned filename of the + # archive as well as the shared archive member, telling the + # bitwidth (32 or 64) of that shared object, and providing the + # list of exported symbols of that shared object, eventually + # decorated with the 'weak' keyword + # *) the shared object with the F_LOADONLY flag set, to really avoid + # it being seen by the linker. + # At run time we better use the real file rather than another symlink, + # but for link time we create the symlink libNAME.so -> libNAME.so.V + + case $with_aix_soname,$aix_use_runtimelinking in + # AIX (on Power*) has no versioning support, so currently we cannot hardcode correct + # soname into executable. Probably we can add versioning support to + # collect2, so additional links can be useful in future. + aix,yes) # traditional libtool + dynamic_linker='AIX unversionable lib.so' + # If using run time linking (on AIX 4.2 or later) use lib.so + # instead of lib.a to let people know that these are not + # typical AIX shared libraries. + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + ;; + aix,no) # traditional AIX only + dynamic_linker='AIX lib.a(lib.so.V)' + # We preserve .a as extension for shared libraries through AIX4.2 + # and later when we are not doing run time linking. + library_names_spec='$libname$release.a $libname.a' + soname_spec='$libname$release$shared_ext$major' + ;; + svr4,*) # full svr4 only + dynamic_linker="AIX lib.so.V($shared_archive_member_spec.o)" + library_names_spec='$libname$release$shared_ext$major $libname$shared_ext' + # We do not specify a path in Import Files, so LIBPATH fires. + shlibpath_overrides_runpath=yes + ;; + *,yes) # both, prefer svr4 + dynamic_linker="AIX lib.so.V($shared_archive_member_spec.o), lib.a(lib.so.V)" + library_names_spec='$libname$release$shared_ext$major $libname$shared_ext' + # unpreferred sharedlib libNAME.a needs extra handling + postinstall_cmds='test -n "$linkname" || linkname="$realname"~func_stripname "" ".so" "$linkname"~$install_shared_prog "$dir/$func_stripname_result.$libext" "$destdir/$func_stripname_result.$libext"~test -z "$tstripme" || test -z "$striplib" || $striplib "$destdir/$func_stripname_result.$libext"' + postuninstall_cmds='for n in $library_names $old_library; do :; done~func_stripname "" ".so" "$n"~test "$func_stripname_result" = "$n" || func_append rmfiles " $odir/$func_stripname_result.$libext"' + # We do not specify a path in Import Files, so LIBPATH fires. + shlibpath_overrides_runpath=yes + ;; + *,no) # both, prefer aix + dynamic_linker="AIX lib.a(lib.so.V), lib.so.V($shared_archive_member_spec.o)" + library_names_spec='$libname$release.a $libname.a' + soname_spec='$libname$release$shared_ext$major' + # unpreferred sharedlib libNAME.so.V and symlink libNAME.so need extra handling + postinstall_cmds='test -z "$dlname" || $install_shared_prog $dir/$dlname $destdir/$dlname~test -z "$tstripme" || test -z "$striplib" || $striplib $destdir/$dlname~test -n "$linkname" || linkname=$realname~func_stripname "" ".a" "$linkname"~(cd "$destdir" && $LN_S -f $dlname $func_stripname_result.so)' + postuninstall_cmds='test -z "$dlname" || func_append rmfiles " $odir/$dlname"~for n in $old_library $library_names; do :; done~func_stripname "" ".a" "$n"~func_append rmfiles " $odir/$func_stripname_result.so"' + ;; + esac + shlibpath_var=LIBPATH + fi + ;; + +amigaos*) + case $host_cpu in + powerpc) + # Since July 2007 AmigaOS4 officially supports .so libraries. + # When compiling the executable, add -use-dynld -Lsobjs: to the compileline. + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + ;; + m68k) + library_names_spec='$libname.ixlibrary $libname.a' + # Create ${libname}_ixlibrary.a entries in /sys/libs. + finish_eval='for lib in `ls $libdir/*.ixlibrary 2>/dev/null`; do libname=`func_echo_all "$lib" | $SED '\''s%^.*/\([^/]*\)\.ixlibrary$%\1%'\''`; $RM /sys/libs/${libname}_ixlibrary.a; $show "cd /sys/libs && $LN_S $lib ${libname}_ixlibrary.a"; cd /sys/libs && $LN_S $lib ${libname}_ixlibrary.a || exit 1; done' + ;; + esac + ;; + +beos*) + library_names_spec='$libname$shared_ext' + dynamic_linker="$host_os ld.so" + shlibpath_var=LIBRARY_PATH + ;; + +bsdi[45]*) + version_type=linux # correct to gnu/linux during the next big refactor + need_version=no + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + soname_spec='$libname$release$shared_ext$major' + finish_cmds='PATH="\$PATH:/sbin" ldconfig $libdir' + shlibpath_var=LD_LIBRARY_PATH + sys_lib_search_path_spec="/shlib /usr/lib /usr/X11/lib /usr/contrib/lib /lib /usr/local/lib" + sys_lib_dlsearch_path_spec="/shlib /usr/lib /usr/local/lib" + # the default ld.so.conf also contains /usr/contrib/lib and + # /usr/X11R6/lib (/usr/X11 is a link to /usr/X11R6), but let us allow + # libtool to hard-code these into programs + ;; + +cygwin* | mingw* | pw32* | cegcc*) + version_type=windows + shrext_cmds=.dll + need_version=no + need_lib_prefix=no + + case $GCC,$cc_basename in + yes,*) + # gcc + library_names_spec='$libname.dll.a' + # DLL is installed to $(libdir)/../bin by postinstall_cmds + postinstall_cmds='base_file=`basename \$file`~ + dlpath=`$SHELL 2>&1 -c '\''. $dir/'\''\$base_file'\''i; echo \$dlname'\''`~ + dldir=$destdir/`dirname \$dlpath`~ + test -d \$dldir || mkdir -p \$dldir~ + $install_prog $dir/$dlname \$dldir/$dlname~ + chmod a+x \$dldir/$dlname~ + if test -n '\''$stripme'\'' && test -n '\''$striplib'\''; then + eval '\''$striplib \$dldir/$dlname'\'' || exit \$?; + fi' + postuninstall_cmds='dldll=`$SHELL 2>&1 -c '\''. $file; echo \$dlname'\''`~ + dlpath=$dir/\$dldll~ + $RM \$dlpath' + shlibpath_overrides_runpath=yes + + case $host_os in + cygwin*) + # Cygwin DLLs use 'cyg' prefix rather than 'lib' + soname_spec='`echo $libname | sed -e 's/^lib/cyg/'``echo $release | $SED -e 's/[.]/-/g'`$versuffix$shared_ext' + + sys_lib_search_path_spec="$sys_lib_search_path_spec /usr/lib/w32api" + ;; + mingw* | cegcc*) + # MinGW DLLs use traditional 'lib' prefix + soname_spec='$libname`echo $release | $SED -e 's/[.]/-/g'`$versuffix$shared_ext' + ;; + pw32*) + # pw32 DLLs use 'pw' prefix rather than 'lib' + library_names_spec='`echo $libname | sed -e 's/^lib/pw/'``echo $release | $SED -e 's/[.]/-/g'`$versuffix$shared_ext' + ;; + esac + dynamic_linker='Win32 ld.exe' + ;; + + *,cl*) + # Native MSVC + libname_spec='$name' + soname_spec='$libname`echo $release | $SED -e 's/[.]/-/g'`$versuffix$shared_ext' + library_names_spec='$libname.dll.lib' + + case $build_os in + mingw*) + sys_lib_search_path_spec= + lt_save_ifs=$IFS + IFS=';' + for lt_path in $LIB + do + IFS=$lt_save_ifs + # Let DOS variable expansion print the short 8.3 style file name. + lt_path=`cd "$lt_path" 2>/dev/null && cmd //C "for %i in (".") do @echo %~si"` + sys_lib_search_path_spec="$sys_lib_search_path_spec $lt_path" + done + IFS=$lt_save_ifs + # Convert to MSYS style. + sys_lib_search_path_spec=`$ECHO "$sys_lib_search_path_spec" | sed -e 's|\\\\|/|g' -e 's| \\([a-zA-Z]\\):| /\\1|g' -e 's|^ ||'` + ;; + cygwin*) + # Convert to unix form, then to dos form, then back to unix form + # but this time dos style (no spaces!) so that the unix form looks + # like /cygdrive/c/PROGRA~1:/cygdr... + sys_lib_search_path_spec=`cygpath --path --unix "$LIB"` + sys_lib_search_path_spec=`cygpath --path --dos "$sys_lib_search_path_spec" 2>/dev/null` + sys_lib_search_path_spec=`cygpath --path --unix "$sys_lib_search_path_spec" | $SED -e "s/$PATH_SEPARATOR/ /g"` + ;; + *) + sys_lib_search_path_spec=$LIB + if $ECHO "$sys_lib_search_path_spec" | $GREP ';[c-zC-Z]:/' >/dev/null; then + # It is most probably a Windows format PATH. + sys_lib_search_path_spec=`$ECHO "$sys_lib_search_path_spec" | $SED -e 's/;/ /g'` + else + sys_lib_search_path_spec=`$ECHO "$sys_lib_search_path_spec" | $SED -e "s/$PATH_SEPARATOR/ /g"` + fi + # FIXME: find the short name or the path components, as spaces are + # common. (e.g. "Program Files" -> "PROGRA~1") + ;; + esac + + # DLL is installed to $(libdir)/../bin by postinstall_cmds + postinstall_cmds='base_file=`basename \$file`~ + dlpath=`$SHELL 2>&1 -c '\''. $dir/'\''\$base_file'\''i; echo \$dlname'\''`~ + dldir=$destdir/`dirname \$dlpath`~ + test -d \$dldir || mkdir -p \$dldir~ + $install_prog $dir/$dlname \$dldir/$dlname' + postuninstall_cmds='dldll=`$SHELL 2>&1 -c '\''. $file; echo \$dlname'\''`~ + dlpath=$dir/\$dldll~ + $RM \$dlpath' + shlibpath_overrides_runpath=yes + dynamic_linker='Win32 link.exe' + ;; + + *) + # Assume MSVC wrapper + library_names_spec='$libname`echo $release | $SED -e 's/[.]/-/g'`$versuffix$shared_ext $libname.lib' + dynamic_linker='Win32 ld.exe' + ;; + esac + # FIXME: first we should search . and the directory the executable is in + shlibpath_var=PATH + ;; + +darwin* | rhapsody*) + dynamic_linker="$host_os dyld" + version_type=darwin + need_lib_prefix=no + need_version=no + library_names_spec='$libname$release$major$shared_ext $libname$shared_ext' + soname_spec='$libname$release$major$shared_ext' + shlibpath_overrides_runpath=yes + shlibpath_var=DYLD_LIBRARY_PATH + shrext_cmds='`test .$module = .yes && echo .so || echo .dylib`' + + sys_lib_search_path_spec="$sys_lib_search_path_spec /usr/local/lib" + sys_lib_dlsearch_path_spec='/usr/local/lib /lib /usr/lib' + ;; + +dgux*) + version_type=linux # correct to gnu/linux during the next big refactor + need_lib_prefix=no + need_version=no + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + soname_spec='$libname$release$shared_ext$major' + shlibpath_var=LD_LIBRARY_PATH + ;; + +freebsd* | dragonfly*) + # DragonFly does not have aout. When/if they implement a new + # versioning mechanism, adjust this. + if test -x /usr/bin/objformat; then + objformat=`/usr/bin/objformat` + else + case $host_os in + freebsd[23].*) objformat=aout ;; + *) objformat=elf ;; + esac + fi + version_type=freebsd-$objformat + case $version_type in + freebsd-elf*) + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + soname_spec='$libname$release$shared_ext$major' + need_version=no + need_lib_prefix=no + ;; + freebsd-*) + library_names_spec='$libname$release$shared_ext$versuffix $libname$shared_ext$versuffix' + need_version=yes + ;; + esac + shlibpath_var=LD_LIBRARY_PATH + case $host_os in + freebsd2.*) + shlibpath_overrides_runpath=yes + ;; + freebsd3.[01]* | freebsdelf3.[01]*) + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + ;; + freebsd3.[2-9]* | freebsdelf3.[2-9]* | \ + freebsd4.[0-5] | freebsdelf4.[0-5] | freebsd4.1.1 | freebsdelf4.1.1) + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + ;; + *) # from 4.6 on, and DragonFly + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + ;; + esac + ;; + +haiku*) + version_type=linux # correct to gnu/linux during the next big refactor + need_lib_prefix=no + need_version=no + dynamic_linker="$host_os runtime_loader" + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + soname_spec='$libname$release$shared_ext$major' + shlibpath_var=LIBRARY_PATH + shlibpath_overrides_runpath=no + sys_lib_dlsearch_path_spec='/boot/home/config/lib /boot/common/lib /boot/system/lib' + hardcode_into_libs=yes + ;; + +hpux9* | hpux10* | hpux11*) + # Give a soname corresponding to the major version so that dld.sl refuses to + # link against other versions. + version_type=sunos + need_lib_prefix=no + need_version=no + case $host_cpu in + ia64*) + shrext_cmds='.so' + hardcode_into_libs=yes + dynamic_linker="$host_os dld.so" + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes # Unless +noenvvar is specified. + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + soname_spec='$libname$release$shared_ext$major' + if test 32 = "$HPUX_IA64_MODE"; then + sys_lib_search_path_spec="/usr/lib/hpux32 /usr/local/lib/hpux32 /usr/local/lib" + sys_lib_dlsearch_path_spec=/usr/lib/hpux32 + else + sys_lib_search_path_spec="/usr/lib/hpux64 /usr/local/lib/hpux64" + sys_lib_dlsearch_path_spec=/usr/lib/hpux64 + fi + ;; + hppa*64*) + shrext_cmds='.sl' + hardcode_into_libs=yes + dynamic_linker="$host_os dld.sl" + shlibpath_var=LD_LIBRARY_PATH # How should we handle SHLIB_PATH + shlibpath_overrides_runpath=yes # Unless +noenvvar is specified. + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + soname_spec='$libname$release$shared_ext$major' + sys_lib_search_path_spec="/usr/lib/pa20_64 /usr/ccs/lib/pa20_64" + sys_lib_dlsearch_path_spec=$sys_lib_search_path_spec + ;; + *) + shrext_cmds='.sl' + dynamic_linker="$host_os dld.sl" + shlibpath_var=SHLIB_PATH + shlibpath_overrides_runpath=no # +s is required to enable SHLIB_PATH + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + soname_spec='$libname$release$shared_ext$major' + ;; + esac + # HP-UX runs *really* slowly unless shared libraries are mode 555, ... + postinstall_cmds='chmod 555 $lib' + # or fails outright, so override atomically: + install_override_mode=555 + ;; + +interix[3-9]*) + version_type=linux # correct to gnu/linux during the next big refactor + need_lib_prefix=no + need_version=no + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + soname_spec='$libname$release$shared_ext$major' + dynamic_linker='Interix 3.x ld.so.1 (PE, like ELF)' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + ;; + +irix5* | irix6* | nonstopux*) + case $host_os in + nonstopux*) version_type=nonstopux ;; + *) + if test yes = "$lt_cv_prog_gnu_ld"; then + version_type=linux # correct to gnu/linux during the next big refactor + else + version_type=irix + fi ;; + esac + need_lib_prefix=no + need_version=no + soname_spec='$libname$release$shared_ext$major' + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$release$shared_ext $libname$shared_ext' + case $host_os in + irix5* | nonstopux*) + libsuff= shlibsuff= + ;; + *) + case $LD in # libtool.m4 will add one of these switches to LD + *-32|*"-32 "|*-melf32bsmip|*"-melf32bsmip ") + libsuff= shlibsuff= libmagic=32-bit;; + *-n32|*"-n32 "|*-melf32bmipn32|*"-melf32bmipn32 ") + libsuff=32 shlibsuff=N32 libmagic=N32;; + *-64|*"-64 "|*-melf64bmip|*"-melf64bmip ") + libsuff=64 shlibsuff=64 libmagic=64-bit;; + *) libsuff= shlibsuff= libmagic=never-match;; + esac + ;; + esac + shlibpath_var=LD_LIBRARY${shlibsuff}_PATH + shlibpath_overrides_runpath=no + sys_lib_search_path_spec="/usr/lib$libsuff /lib$libsuff /usr/local/lib$libsuff" + sys_lib_dlsearch_path_spec="/usr/lib$libsuff /lib$libsuff" + hardcode_into_libs=yes + ;; + +# No shared lib support for Linux oldld, aout, or coff. +linux*oldld* | linux*aout* | linux*coff*) + dynamic_linker=no + ;; + +linux*android*) + version_type=none # Android doesn't support versioned libraries. + need_lib_prefix=no + need_version=no + library_names_spec='$libname$release$shared_ext' + soname_spec='$libname$release$shared_ext' + finish_cmds= + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + + # This implies no fast_install, which is unacceptable. + # Some rework will be needed to allow for fast_install + # before this can be enabled. + hardcode_into_libs=yes + + dynamic_linker='Android linker' + # Don't embed -rpath directories since the linker doesn't support them. + hardcode_libdir_flag_spec='-L$libdir' + ;; + +# This must be glibc/ELF. +linux* | k*bsd*-gnu | kopensolaris*-gnu | gnu*) + version_type=linux # correct to gnu/linux during the next big refactor + need_lib_prefix=no + need_version=no + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + soname_spec='$libname$release$shared_ext$major' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -n $libdir' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + + # Some binutils ld are patched to set DT_RUNPATH + if ${lt_cv_shlibpath_overrides_runpath+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_shlibpath_overrides_runpath=no + save_LDFLAGS=$LDFLAGS + save_libdir=$libdir + eval "libdir=/foo; wl=\"$lt_prog_compiler_wl\"; \ + LDFLAGS=\"\$LDFLAGS $hardcode_libdir_flag_spec\"" + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + if ($OBJDUMP -p conftest$ac_exeext) 2>/dev/null | grep "RUNPATH.*$libdir" >/dev/null; then : + lt_cv_shlibpath_overrides_runpath=yes +fi +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext + LDFLAGS=$save_LDFLAGS + libdir=$save_libdir + +fi + + shlibpath_overrides_runpath=$lt_cv_shlibpath_overrides_runpath + + # This implies no fast_install, which is unacceptable. + # Some rework will be needed to allow for fast_install + # before this can be enabled. + hardcode_into_libs=yes + + # Ideally, we could use ldconfig to report *all* directores which are + # searched for libraries, however this is still not possible. Aside from not + # being certain /sbin/ldconfig is available, command + # 'ldconfig -N -X -v | grep ^/' on 64bit Fedora does not report /usr/lib64, + # even though it is searched at run-time. Try to do the best guess by + # appending ld.so.conf contents (and includes) to the search path. + if test -f /etc/ld.so.conf; then + lt_ld_extra=`awk '/^include / { system(sprintf("cd /etc; cat %s 2>/dev/null", \$2)); skip = 1; } { if (!skip) print \$0; skip = 0; }' < /etc/ld.so.conf | $SED -e 's/#.*//;/^[ ]*hwcap[ ]/d;s/[:, ]/ /g;s/=[^=]*$//;s/=[^= ]* / /g;s/"//g;/^$/d' | tr '\n' ' '` + sys_lib_dlsearch_path_spec="/lib /usr/lib $lt_ld_extra" + fi + + # We used to test for /lib/ld.so.1 and disable shared libraries on + # powerpc, because MkLinux only supported shared libraries with the + # GNU dynamic linker. Since this was broken with cross compilers, + # most powerpc-linux boxes support dynamic linking these days and + # people can always --disable-shared, the test was removed, and we + # assume the GNU/Linux dynamic linker is in use. + dynamic_linker='GNU/Linux ld.so' + ;; + +netbsd*) + version_type=sunos + need_lib_prefix=no + need_version=no + if echo __ELF__ | $CC -E - | $GREP __ELF__ >/dev/null; then + library_names_spec='$libname$release$shared_ext$versuffix $libname$shared_ext$versuffix' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -m $libdir' + dynamic_linker='NetBSD (a.out) ld.so' + else + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + soname_spec='$libname$release$shared_ext$major' + dynamic_linker='NetBSD ld.elf_so' + fi + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + ;; + +newsos6) + version_type=linux # correct to gnu/linux during the next big refactor + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + ;; + +*nto* | *qnx*) + version_type=qnx + need_lib_prefix=no + need_version=no + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + soname_spec='$libname$release$shared_ext$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + dynamic_linker='ldqnx.so' + ;; + +openbsd* | bitrig*) + version_type=sunos + sys_lib_dlsearch_path_spec=/usr/lib + need_lib_prefix=no + if test -z "`echo __ELF__ | $CC -E - | $GREP __ELF__`"; then + need_version=no + else + need_version=yes + fi + library_names_spec='$libname$release$shared_ext$versuffix $libname$shared_ext$versuffix' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -m $libdir' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + ;; + +os2*) + libname_spec='$name' + version_type=windows + shrext_cmds=.dll + need_version=no + need_lib_prefix=no + # OS/2 can only load a DLL with a base name of 8 characters or less. + soname_spec='`test -n "$os2dllname" && libname="$os2dllname"; + v=$($ECHO $release$versuffix | tr -d .-); + n=$($ECHO $libname | cut -b -$((8 - ${#v})) | tr . _); + $ECHO $n$v`$shared_ext' + library_names_spec='${libname}_dll.$libext' + dynamic_linker='OS/2 ld.exe' + shlibpath_var=BEGINLIBPATH + sys_lib_search_path_spec="/lib /usr/lib /usr/local/lib" + sys_lib_dlsearch_path_spec=$sys_lib_search_path_spec + postinstall_cmds='base_file=`basename \$file`~ + dlpath=`$SHELL 2>&1 -c '\''. $dir/'\''\$base_file'\''i; $ECHO \$dlname'\''`~ + dldir=$destdir/`dirname \$dlpath`~ + test -d \$dldir || mkdir -p \$dldir~ + $install_prog $dir/$dlname \$dldir/$dlname~ + chmod a+x \$dldir/$dlname~ + if test -n '\''$stripme'\'' && test -n '\''$striplib'\''; then + eval '\''$striplib \$dldir/$dlname'\'' || exit \$?; + fi' + postuninstall_cmds='dldll=`$SHELL 2>&1 -c '\''. $file; $ECHO \$dlname'\''`~ + dlpath=$dir/\$dldll~ + $RM \$dlpath' + ;; + +osf3* | osf4* | osf5*) + version_type=osf + need_lib_prefix=no + need_version=no + soname_spec='$libname$release$shared_ext$major' + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + shlibpath_var=LD_LIBRARY_PATH + sys_lib_search_path_spec="/usr/shlib /usr/ccs/lib /usr/lib/cmplrs/cc /usr/lib /usr/local/lib /var/shlib" + sys_lib_dlsearch_path_spec=$sys_lib_search_path_spec + ;; + +rdos*) + dynamic_linker=no + ;; + +solaris*) + version_type=linux # correct to gnu/linux during the next big refactor + need_lib_prefix=no + need_version=no + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + soname_spec='$libname$release$shared_ext$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + # ldd complains unless libraries are executable + postinstall_cmds='chmod +x $lib' + ;; + +sunos4*) + version_type=sunos + library_names_spec='$libname$release$shared_ext$versuffix $libname$shared_ext$versuffix' + finish_cmds='PATH="\$PATH:/usr/etc" ldconfig $libdir' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + if test yes = "$with_gnu_ld"; then + need_lib_prefix=no + fi + need_version=yes + ;; + +sysv4 | sysv4.3*) + version_type=linux # correct to gnu/linux during the next big refactor + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + soname_spec='$libname$release$shared_ext$major' + shlibpath_var=LD_LIBRARY_PATH + case $host_vendor in + sni) + shlibpath_overrides_runpath=no + need_lib_prefix=no + runpath_var=LD_RUN_PATH + ;; + siemens) + need_lib_prefix=no + ;; + motorola) + need_lib_prefix=no + need_version=no + shlibpath_overrides_runpath=no + sys_lib_search_path_spec='/lib /usr/lib /usr/ccs/lib' + ;; + esac + ;; + +sysv4*MP*) + if test -d /usr/nec; then + version_type=linux # correct to gnu/linux during the next big refactor + library_names_spec='$libname$shared_ext.$versuffix $libname$shared_ext.$major $libname$shared_ext' + soname_spec='$libname$shared_ext.$major' + shlibpath_var=LD_LIBRARY_PATH + fi + ;; + +sysv5* | sco3.2v5* | sco5v6* | unixware* | OpenUNIX* | sysv4*uw2*) + version_type=sco + need_lib_prefix=no + need_version=no + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext $libname$shared_ext' + soname_spec='$libname$release$shared_ext$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + if test yes = "$with_gnu_ld"; then + sys_lib_search_path_spec='/usr/local/lib /usr/gnu/lib /usr/ccs/lib /usr/lib /lib' + else + sys_lib_search_path_spec='/usr/ccs/lib /usr/lib' + case $host_os in + sco3.2v5*) + sys_lib_search_path_spec="$sys_lib_search_path_spec /lib" + ;; + esac + fi + sys_lib_dlsearch_path_spec='/usr/lib' + ;; + +tpf*) + # TPF is a cross-target only. Preferred cross-host = GNU/Linux. + version_type=linux # correct to gnu/linux during the next big refactor + need_lib_prefix=no + need_version=no + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + ;; + +uts4*) + version_type=linux # correct to gnu/linux during the next big refactor + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + soname_spec='$libname$release$shared_ext$major' + shlibpath_var=LD_LIBRARY_PATH + ;; + +*) + dynamic_linker=no + ;; +esac +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $dynamic_linker" >&5 +$as_echo "$dynamic_linker" >&6; } +test no = "$dynamic_linker" && can_build_shared=no + +variables_saved_for_relink="PATH $shlibpath_var $runpath_var" +if test yes = "$GCC"; then + variables_saved_for_relink="$variables_saved_for_relink GCC_EXEC_PREFIX COMPILER_PATH LIBRARY_PATH" +fi + +if test set = "${lt_cv_sys_lib_search_path_spec+set}"; then + sys_lib_search_path_spec=$lt_cv_sys_lib_search_path_spec +fi + +if test set = "${lt_cv_sys_lib_dlsearch_path_spec+set}"; then + sys_lib_dlsearch_path_spec=$lt_cv_sys_lib_dlsearch_path_spec +fi + +# remember unaugmented sys_lib_dlsearch_path content for libtool script decls... +configure_time_dlsearch_path=$sys_lib_dlsearch_path_spec + +# ... but it needs LT_SYS_LIBRARY_PATH munging for other configure-time code +func_munge_path_list sys_lib_dlsearch_path_spec "$LT_SYS_LIBRARY_PATH" + +# to be used as default LT_SYS_LIBRARY_PATH value in generated libtool +configure_time_lt_sys_library_path=$LT_SYS_LIBRARY_PATH + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + { $as_echo "$as_me:${as_lineno-$LINENO}: checking how to hardcode library paths into programs" >&5 +$as_echo_n "checking how to hardcode library paths into programs... " >&6; } +hardcode_action= +if test -n "$hardcode_libdir_flag_spec" || + test -n "$runpath_var" || + test yes = "$hardcode_automatic"; then + + # We can hardcode non-existent directories. + if test no != "$hardcode_direct" && + # If the only mechanism to avoid hardcoding is shlibpath_var, we + # have to relink, otherwise we might link with an installed library + # when we should be linking with a yet-to-be-installed one + ## test no != "$_LT_TAGVAR(hardcode_shlibpath_var, )" && + test no != "$hardcode_minus_L"; then + # Linking always hardcodes the temporary library directory. + hardcode_action=relink + else + # We can link without hardcoding, and we can hardcode nonexisting dirs. + hardcode_action=immediate + fi +else + # We cannot hardcode anything, or else we can only hardcode existing + # directories. + hardcode_action=unsupported +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $hardcode_action" >&5 +$as_echo "$hardcode_action" >&6; } + +if test relink = "$hardcode_action" || + test yes = "$inherit_rpath"; then + # Fast installation is not supported + enable_fast_install=no +elif test yes = "$shlibpath_overrides_runpath" || + test no = "$enable_shared"; then + # Fast installation is not necessary + enable_fast_install=needless +fi + + + + + + + if test yes != "$enable_dlopen"; then + enable_dlopen=unknown + enable_dlopen_self=unknown + enable_dlopen_self_static=unknown +else + lt_cv_dlopen=no + lt_cv_dlopen_libs= + + case $host_os in + beos*) + lt_cv_dlopen=load_add_on + lt_cv_dlopen_libs= + lt_cv_dlopen_self=yes + ;; + + mingw* | pw32* | cegcc*) + lt_cv_dlopen=LoadLibrary + lt_cv_dlopen_libs= + ;; + + cygwin*) + lt_cv_dlopen=dlopen + lt_cv_dlopen_libs= + ;; + + darwin*) + # if libdl is installed we need to link against it + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for dlopen in -ldl" >&5 +$as_echo_n "checking for dlopen in -ldl... " >&6; } +if ${ac_cv_lib_dl_dlopen+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-ldl $LIBS" +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char dlopen (); +int +main () +{ +return dlopen (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ac_cv_lib_dl_dlopen=yes +else + ac_cv_lib_dl_dlopen=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_dl_dlopen" >&5 +$as_echo "$ac_cv_lib_dl_dlopen" >&6; } +if test "x$ac_cv_lib_dl_dlopen" = xyes; then : + lt_cv_dlopen=dlopen lt_cv_dlopen_libs=-ldl +else + + lt_cv_dlopen=dyld + lt_cv_dlopen_libs= + lt_cv_dlopen_self=yes + +fi + + ;; + + tpf*) + # Don't try to run any link tests for TPF. We know it's impossible + # because TPF is a cross-compiler, and we know how we open DSOs. + lt_cv_dlopen=dlopen + lt_cv_dlopen_libs= + lt_cv_dlopen_self=no + ;; + + *) + ac_fn_c_check_func "$LINENO" "shl_load" "ac_cv_func_shl_load" +if test "x$ac_cv_func_shl_load" = xyes; then : + lt_cv_dlopen=shl_load +else + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for shl_load in -ldld" >&5 +$as_echo_n "checking for shl_load in -ldld... " >&6; } +if ${ac_cv_lib_dld_shl_load+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-ldld $LIBS" +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char shl_load (); +int +main () +{ +return shl_load (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ac_cv_lib_dld_shl_load=yes +else + ac_cv_lib_dld_shl_load=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_dld_shl_load" >&5 +$as_echo "$ac_cv_lib_dld_shl_load" >&6; } +if test "x$ac_cv_lib_dld_shl_load" = xyes; then : + lt_cv_dlopen=shl_load lt_cv_dlopen_libs=-ldld +else + ac_fn_c_check_func "$LINENO" "dlopen" "ac_cv_func_dlopen" +if test "x$ac_cv_func_dlopen" = xyes; then : + lt_cv_dlopen=dlopen +else + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for dlopen in -ldl" >&5 +$as_echo_n "checking for dlopen in -ldl... " >&6; } +if ${ac_cv_lib_dl_dlopen+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-ldl $LIBS" +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char dlopen (); +int +main () +{ +return dlopen (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ac_cv_lib_dl_dlopen=yes +else + ac_cv_lib_dl_dlopen=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_dl_dlopen" >&5 +$as_echo "$ac_cv_lib_dl_dlopen" >&6; } +if test "x$ac_cv_lib_dl_dlopen" = xyes; then : + lt_cv_dlopen=dlopen lt_cv_dlopen_libs=-ldl +else + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for dlopen in -lsvld" >&5 +$as_echo_n "checking for dlopen in -lsvld... " >&6; } +if ${ac_cv_lib_svld_dlopen+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-lsvld $LIBS" +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char dlopen (); +int +main () +{ +return dlopen (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ac_cv_lib_svld_dlopen=yes +else + ac_cv_lib_svld_dlopen=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_svld_dlopen" >&5 +$as_echo "$ac_cv_lib_svld_dlopen" >&6; } +if test "x$ac_cv_lib_svld_dlopen" = xyes; then : + lt_cv_dlopen=dlopen lt_cv_dlopen_libs=-lsvld +else + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for dld_link in -ldld" >&5 +$as_echo_n "checking for dld_link in -ldld... " >&6; } +if ${ac_cv_lib_dld_dld_link+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-ldld $LIBS" +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char dld_link (); +int +main () +{ +return dld_link (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ac_cv_lib_dld_dld_link=yes +else + ac_cv_lib_dld_dld_link=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_dld_dld_link" >&5 +$as_echo "$ac_cv_lib_dld_dld_link" >&6; } +if test "x$ac_cv_lib_dld_dld_link" = xyes; then : + lt_cv_dlopen=dld_link lt_cv_dlopen_libs=-ldld +fi + + +fi + + +fi + + +fi + + +fi + + +fi + + ;; + esac + + if test no = "$lt_cv_dlopen"; then + enable_dlopen=no + else + enable_dlopen=yes + fi + + case $lt_cv_dlopen in + dlopen) + save_CPPFLAGS=$CPPFLAGS + test yes = "$ac_cv_header_dlfcn_h" && CPPFLAGS="$CPPFLAGS -DHAVE_DLFCN_H" + + save_LDFLAGS=$LDFLAGS + wl=$lt_prog_compiler_wl eval LDFLAGS=\"\$LDFLAGS $export_dynamic_flag_spec\" + + save_LIBS=$LIBS + LIBS="$lt_cv_dlopen_libs $LIBS" + + { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether a program can dlopen itself" >&5 +$as_echo_n "checking whether a program can dlopen itself... " >&6; } +if ${lt_cv_dlopen_self+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test yes = "$cross_compiling"; then : + lt_cv_dlopen_self=cross +else + lt_dlunknown=0; lt_dlno_uscore=1; lt_dlneed_uscore=2 + lt_status=$lt_dlunknown + cat > conftest.$ac_ext <<_LT_EOF +#line $LINENO "configure" +#include "confdefs.h" + +#if HAVE_DLFCN_H +#include +#endif + +#include + +#ifdef RTLD_GLOBAL +# define LT_DLGLOBAL RTLD_GLOBAL +#else +# ifdef DL_GLOBAL +# define LT_DLGLOBAL DL_GLOBAL +# else +# define LT_DLGLOBAL 0 +# endif +#endif + +/* We may have to define LT_DLLAZY_OR_NOW in the command line if we + find out it does not work in some platform. */ +#ifndef LT_DLLAZY_OR_NOW +# ifdef RTLD_LAZY +# define LT_DLLAZY_OR_NOW RTLD_LAZY +# else +# ifdef DL_LAZY +# define LT_DLLAZY_OR_NOW DL_LAZY +# else +# ifdef RTLD_NOW +# define LT_DLLAZY_OR_NOW RTLD_NOW +# else +# ifdef DL_NOW +# define LT_DLLAZY_OR_NOW DL_NOW +# else +# define LT_DLLAZY_OR_NOW 0 +# endif +# endif +# endif +# endif +#endif + +/* When -fvisibility=hidden is used, assume the code has been annotated + correspondingly for the symbols needed. */ +#if defined __GNUC__ && (((__GNUC__ == 3) && (__GNUC_MINOR__ >= 3)) || (__GNUC__ > 3)) +int fnord () __attribute__((visibility("default"))); +#endif + +int fnord () { return 42; } +int main () +{ + void *self = dlopen (0, LT_DLGLOBAL|LT_DLLAZY_OR_NOW); + int status = $lt_dlunknown; + + if (self) + { + if (dlsym (self,"fnord")) status = $lt_dlno_uscore; + else + { + if (dlsym( self,"_fnord")) status = $lt_dlneed_uscore; + else puts (dlerror ()); + } + /* dlclose (self); */ + } + else + puts (dlerror ()); + + return status; +} +_LT_EOF + if { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$ac_link\""; } >&5 + (eval $ac_link) 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } && test -s "conftest$ac_exeext" 2>/dev/null; then + (./conftest; exit; ) >&5 2>/dev/null + lt_status=$? + case x$lt_status in + x$lt_dlno_uscore) lt_cv_dlopen_self=yes ;; + x$lt_dlneed_uscore) lt_cv_dlopen_self=yes ;; + x$lt_dlunknown|x*) lt_cv_dlopen_self=no ;; + esac + else : + # compilation failed + lt_cv_dlopen_self=no + fi +fi +rm -fr conftest* + + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_dlopen_self" >&5 +$as_echo "$lt_cv_dlopen_self" >&6; } + + if test yes = "$lt_cv_dlopen_self"; then + wl=$lt_prog_compiler_wl eval LDFLAGS=\"\$LDFLAGS $lt_prog_compiler_static\" + { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether a statically linked program can dlopen itself" >&5 +$as_echo_n "checking whether a statically linked program can dlopen itself... " >&6; } +if ${lt_cv_dlopen_self_static+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test yes = "$cross_compiling"; then : + lt_cv_dlopen_self_static=cross +else + lt_dlunknown=0; lt_dlno_uscore=1; lt_dlneed_uscore=2 + lt_status=$lt_dlunknown + cat > conftest.$ac_ext <<_LT_EOF +#line $LINENO "configure" +#include "confdefs.h" + +#if HAVE_DLFCN_H +#include +#endif + +#include + +#ifdef RTLD_GLOBAL +# define LT_DLGLOBAL RTLD_GLOBAL +#else +# ifdef DL_GLOBAL +# define LT_DLGLOBAL DL_GLOBAL +# else +# define LT_DLGLOBAL 0 +# endif +#endif + +/* We may have to define LT_DLLAZY_OR_NOW in the command line if we + find out it does not work in some platform. */ +#ifndef LT_DLLAZY_OR_NOW +# ifdef RTLD_LAZY +# define LT_DLLAZY_OR_NOW RTLD_LAZY +# else +# ifdef DL_LAZY +# define LT_DLLAZY_OR_NOW DL_LAZY +# else +# ifdef RTLD_NOW +# define LT_DLLAZY_OR_NOW RTLD_NOW +# else +# ifdef DL_NOW +# define LT_DLLAZY_OR_NOW DL_NOW +# else +# define LT_DLLAZY_OR_NOW 0 +# endif +# endif +# endif +# endif +#endif + +/* When -fvisibility=hidden is used, assume the code has been annotated + correspondingly for the symbols needed. */ +#if defined __GNUC__ && (((__GNUC__ == 3) && (__GNUC_MINOR__ >= 3)) || (__GNUC__ > 3)) +int fnord () __attribute__((visibility("default"))); +#endif + +int fnord () { return 42; } +int main () +{ + void *self = dlopen (0, LT_DLGLOBAL|LT_DLLAZY_OR_NOW); + int status = $lt_dlunknown; + + if (self) + { + if (dlsym (self,"fnord")) status = $lt_dlno_uscore; + else + { + if (dlsym( self,"_fnord")) status = $lt_dlneed_uscore; + else puts (dlerror ()); + } + /* dlclose (self); */ + } + else + puts (dlerror ()); + + return status; +} +_LT_EOF + if { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$ac_link\""; } >&5 + (eval $ac_link) 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } && test -s "conftest$ac_exeext" 2>/dev/null; then + (./conftest; exit; ) >&5 2>/dev/null + lt_status=$? + case x$lt_status in + x$lt_dlno_uscore) lt_cv_dlopen_self_static=yes ;; + x$lt_dlneed_uscore) lt_cv_dlopen_self_static=yes ;; + x$lt_dlunknown|x*) lt_cv_dlopen_self_static=no ;; + esac + else : + # compilation failed + lt_cv_dlopen_self_static=no + fi +fi +rm -fr conftest* + + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $lt_cv_dlopen_self_static" >&5 +$as_echo "$lt_cv_dlopen_self_static" >&6; } + fi + + CPPFLAGS=$save_CPPFLAGS + LDFLAGS=$save_LDFLAGS + LIBS=$save_LIBS + ;; + esac + + case $lt_cv_dlopen_self in + yes|no) enable_dlopen_self=$lt_cv_dlopen_self ;; + *) enable_dlopen_self=unknown ;; + esac + + case $lt_cv_dlopen_self_static in + yes|no) enable_dlopen_self_static=$lt_cv_dlopen_self_static ;; + *) enable_dlopen_self_static=unknown ;; + esac +fi + + + + + + + + + + + + + + + + + +striplib= +old_striplib= +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether stripping libraries is possible" >&5 +$as_echo_n "checking whether stripping libraries is possible... " >&6; } +if test -n "$STRIP" && $STRIP -V 2>&1 | $GREP "GNU strip" >/dev/null; then + test -z "$old_striplib" && old_striplib="$STRIP --strip-debug" + test -z "$striplib" && striplib="$STRIP --strip-unneeded" + { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5 +$as_echo "yes" >&6; } +else +# FIXME - insert some real tests, host_os isn't really good enough + case $host_os in + darwin*) + if test -n "$STRIP"; then + striplib="$STRIP -x" + old_striplib="$STRIP -S" + { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5 +$as_echo "yes" >&6; } + else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } + fi + ;; + *) + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } + ;; + esac +fi + + + + + + + + + + + + + # Report what library types will actually be built + { $as_echo "$as_me:${as_lineno-$LINENO}: checking if libtool supports shared libraries" >&5 +$as_echo_n "checking if libtool supports shared libraries... " >&6; } + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $can_build_shared" >&5 +$as_echo "$can_build_shared" >&6; } + + { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to build shared libraries" >&5 +$as_echo_n "checking whether to build shared libraries... " >&6; } + test no = "$can_build_shared" && enable_shared=no + + # On AIX, shared libraries and static libraries use the same namespace, and + # are all built from PIC. + case $host_os in + aix3*) + test yes = "$enable_shared" && enable_static=no + if test -n "$RANLIB"; then + archive_cmds="$archive_cmds~\$RANLIB \$lib" + postinstall_cmds='$RANLIB $lib' + fi + ;; + + aix[4-9]*) + if test ia64 != "$host_cpu"; then + case $enable_shared,$with_aix_soname,$aix_use_runtimelinking in + yes,aix,yes) ;; # shared object as lib.so file only + yes,svr4,*) ;; # shared object as lib.so archive member only + yes,*) enable_static=no ;; # shared object in lib.a archive as well + esac + fi + ;; + esac + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $enable_shared" >&5 +$as_echo "$enable_shared" >&6; } + + { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to build static libraries" >&5 +$as_echo_n "checking whether to build static libraries... " >&6; } + # Make sure either enable_shared or enable_static is yes. + test yes = "$enable_shared" || enable_static=yes + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $enable_static" >&5 +$as_echo "$enable_static" >&6; } + + + + +fi +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + +CC=$lt_save_CC + + + + + + + + + + + + + + + + ac_config_commands="$ac_config_commands libtool" + + + + +# Only expand once: + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether ln -s works" >&5 +$as_echo_n "checking whether ln -s works... " >&6; } +LN_S=$as_ln_s +if test "$LN_S" = "ln -s"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5 +$as_echo "yes" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no, using $LN_S" >&5 +$as_echo "no, using $LN_S" >&6; } +fi + + +# Check for GCC visibility feature + + + + VISIBILITY_CFLAGS= + VISIBILITY_CXXFLAGS= + HAVE_VISIBILITY=0 + if test -n "$GCC"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether the -Werror option is usable" >&5 +$as_echo_n "checking whether the -Werror option is usable... " >&6; } + if ${pcre2_cv_cc_vis_werror+:} false; then : + $as_echo_n "(cached) " >&6 +else + + pcre2_save_CFLAGS="$CFLAGS" + CFLAGS="$CFLAGS -Werror" + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + pcre2_cv_cc_vis_werror=yes +else + pcre2_cv_cc_vis_werror=no +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext + CFLAGS="$pcre2_save_CFLAGS" +fi + + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $pcre2_cv_cc_vis_werror" >&5 +$as_echo "$pcre2_cv_cc_vis_werror" >&6; } + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for simple visibility declarations" >&5 +$as_echo_n "checking for simple visibility declarations... " >&6; } + if ${pcre2_cv_cc_visibility+:} false; then : + $as_echo_n "(cached) " >&6 +else + + pcre2_save_CFLAGS="$CFLAGS" + CFLAGS="$CFLAGS -fvisibility=hidden" + if test $pcre2_cv_cc_vis_werror = yes; then + CFLAGS="$CFLAGS -Werror" + fi + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +extern __attribute__((__visibility__("hidden"))) int hiddenvar; + extern __attribute__((__visibility__("default"))) int exportedvar; + extern __attribute__((__visibility__("hidden"))) int hiddenfunc (void); + extern __attribute__((__visibility__("default"))) int exportedfunc (void); + void dummyfunc (void) {} + +int +main () +{ + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + pcre2_cv_cc_visibility=yes +else + pcre2_cv_cc_visibility=no +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext + CFLAGS="$pcre2_save_CFLAGS" +fi + + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $pcre2_cv_cc_visibility" >&5 +$as_echo "$pcre2_cv_cc_visibility" >&6; } + if test $pcre2_cv_cc_visibility = yes; then + VISIBILITY_CFLAGS="-fvisibility=hidden" + VISIBILITY_CXXFLAGS="-fvisibility=hidden -fvisibility-inlines-hidden" + HAVE_VISIBILITY=1 + +$as_echo "#define PCRE2_EXP_DECL extern __attribute__ ((visibility (\"default\")))" >>confdefs.h + + +$as_echo "#define PCRE2_EXP_DEFN __attribute__ ((visibility (\"default\")))" >>confdefs.h + + +$as_echo "#define PCRE2POSIX_EXP_DECL extern __attribute__ ((visibility (\"default\")))" >>confdefs.h + + +$as_echo "#define PCRE2POSIX_EXP_DEFN extern __attribute__ ((visibility (\"default\")))" >>confdefs.h + + fi + fi + + + + +cat >>confdefs.h <<_ACEOF +#define HAVE_VISIBILITY $HAVE_VISIBILITY +_ACEOF + + + +# Versioning + +PCRE2_MAJOR="10" +PCRE2_MINOR="20" +PCRE2_PRERELEASE="" +PCRE2_DATE="2015-06-30" + +if test "$PCRE2_MINOR" = "08" -o "$PCRE2_MINOR" = "09" +then + echo "***" + echo "*** Minor version number $PCRE2_MINOR must not be used. ***" + echo "*** Use only 00 to 07 or 10 onwards, to avoid octal issues. ***" + echo "***" + exit 1 +fi + + + + + + +# Set a more sensible default value for $(htmldir). +if test "x$htmldir" = 'x${docdir}' +then + htmldir='${docdir}/html' +fi + +# Force an error for PCRE1 size options +# Check whether --enable-pcre8 was given. +if test "${enable_pcre8+set}" = set; then : + enableval=$enable_pcre8; +else + enable_pcre8=no +fi + +# Check whether --enable-pcre16 was given. +if test "${enable_pcre16+set}" = set; then : + enableval=$enable_pcre16; +else + enable_pcre16=no +fi + +# Check whether --enable-pcre32 was given. +if test "${enable_pcre32+set}" = set; then : + enableval=$enable_pcre32; +else + enable_pcre32=no +fi + + +if test "$enable_pcre8$enable_pcre16$enable_pcre32" != "nonono" +then + echo "** ERROR: Use --[en|dis]able-pcre2-[8|16|32], not --[en|dis]able-pcre[8|16|32]" + exit 1 +fi + +# Handle --disable-pcre2-8 (enabled by default) +# Check whether --enable-pcre2-8 was given. +if test "${enable_pcre2_8+set}" = set; then : + enableval=$enable_pcre2_8; +else + enable_pcre2_8=unset +fi + + + +# Handle --enable-pcre2-16 (disabled by default) +# Check whether --enable-pcre2-16 was given. +if test "${enable_pcre2_16+set}" = set; then : + enableval=$enable_pcre2_16; +else + enable_pcre2_16=unset +fi + + + +# Handle --enable-pcre2-32 (disabled by default) +# Check whether --enable-pcre2-32 was given. +if test "${enable_pcre2_32+set}" = set; then : + enableval=$enable_pcre2_32; +else + enable_pcre2_32=unset +fi + + + +# Handle --dnable-debug (disabled by default) +# Check whether --enable-debug was given. +if test "${enable_debug+set}" = set; then : + enableval=$enable_debug; +else + enable_debug=no +fi + + +# Handle --enable-jit (disabled by default) +# Check whether --enable-jit was given. +if test "${enable_jit+set}" = set; then : + enableval=$enable_jit; +else + enable_jit=no +fi + + +# Handle --disable-pcre2grep-jit (enabled by default) +# Check whether --enable-pcre2grep-jit was given. +if test "${enable_pcre2grep_jit+set}" = set; then : + enableval=$enable_pcre2grep_jit; +else + enable_pcre2grep_jit=yes +fi + + +# Handle --enable-rebuild-chartables +# Check whether --enable-rebuild-chartables was given. +if test "${enable_rebuild_chartables+set}" = set; then : + enableval=$enable_rebuild_chartables; +else + enable_rebuild_chartables=no +fi + + +# Handle --disable-unicode (enabled by default) +# Check whether --enable-unicode was given. +if test "${enable_unicode+set}" = set; then : + enableval=$enable_unicode; +else + enable_unicode=unset +fi + + +# Handle newline options +ac_pcre2_newline=lf +# Check whether --enable-newline-is-cr was given. +if test "${enable_newline_is_cr+set}" = set; then : + enableval=$enable_newline_is_cr; ac_pcre2_newline=cr +fi + +# Check whether --enable-newline-is-lf was given. +if test "${enable_newline_is_lf+set}" = set; then : + enableval=$enable_newline_is_lf; ac_pcre2_newline=lf +fi + +# Check whether --enable-newline-is-crlf was given. +if test "${enable_newline_is_crlf+set}" = set; then : + enableval=$enable_newline_is_crlf; ac_pcre2_newline=crlf +fi + +# Check whether --enable-newline-is-anycrlf was given. +if test "${enable_newline_is_anycrlf+set}" = set; then : + enableval=$enable_newline_is_anycrlf; ac_pcre2_newline=anycrlf +fi + +# Check whether --enable-newline-is-any was given. +if test "${enable_newline_is_any+set}" = set; then : + enableval=$enable_newline_is_any; ac_pcre2_newline=any +fi + +enable_newline="$ac_pcre2_newline" + +# Handle --enable-bsr-anycrlf +# Check whether --enable-bsr-anycrlf was given. +if test "${enable_bsr_anycrlf+set}" = set; then : + enableval=$enable_bsr_anycrlf; +else + enable_bsr_anycrlf=no +fi + + +# Handle --enable-ebcdic +# Check whether --enable-ebcdic was given. +if test "${enable_ebcdic+set}" = set; then : + enableval=$enable_ebcdic; +else + enable_ebcdic=no +fi + + +# Handle --enable-ebcdic-nl25 +# Check whether --enable-ebcdic-nl25 was given. +if test "${enable_ebcdic_nl25+set}" = set; then : + enableval=$enable_ebcdic_nl25; +else + enable_ebcdic_nl25=no +fi + + +# Handle --disable-stack-for-recursion +# Check whether --enable-stack-for-recursion was given. +if test "${enable_stack_for_recursion+set}" = set; then : + enableval=$enable_stack_for_recursion; +else + enable_stack_for_recursion=yes +fi + + +# Handle --enable-pcre2grep-libz +# Check whether --enable-pcre2grep-libz was given. +if test "${enable_pcre2grep_libz+set}" = set; then : + enableval=$enable_pcre2grep_libz; +else + enable_pcre2grep_libz=no +fi + + +# Handle --enable-pcre2grep-libbz2 +# Check whether --enable-pcre2grep-libbz2 was given. +if test "${enable_pcre2grep_libbz2+set}" = set; then : + enableval=$enable_pcre2grep_libbz2; +else + enable_pcre2grep_libbz2=no +fi + + +# Handle --with-pcre2grep-bufsize=N + +# Check whether --with-pcre2grep-bufsize was given. +if test "${with_pcre2grep_bufsize+set}" = set; then : + withval=$with_pcre2grep_bufsize; +else + with_pcre2grep_bufsize=20480 +fi + + +# Handle --enable-pcre2test-libedit +# Check whether --enable-pcre2test-libedit was given. +if test "${enable_pcre2test_libedit+set}" = set; then : + enableval=$enable_pcre2test_libedit; +else + enable_pcre2test_libedit=no +fi + + +# Handle --enable-pcre2test-libreadline +# Check whether --enable-pcre2test-libreadline was given. +if test "${enable_pcre2test_libreadline+set}" = set; then : + enableval=$enable_pcre2test_libreadline; +else + enable_pcre2test_libreadline=no +fi + + +# Handle --with-link-size=N + +# Check whether --with-link-size was given. +if test "${with_link_size+set}" = set; then : + withval=$with_link_size; +else + with_link_size=2 +fi + + +# Handle --with-parens-nest-limit=N + +# Check whether --with-parens-nest-limit was given. +if test "${with_parens_nest_limit+set}" = set; then : + withval=$with_parens_nest_limit; +else + with_parens_nest_limit=250 +fi + + +# Handle --with-match-limit=N + +# Check whether --with-match-limit was given. +if test "${with_match_limit+set}" = set; then : + withval=$with_match_limit; +else + with_match_limit=10000000 +fi + + +# Handle --with-match-limit_recursion=N +# +# Note: In config.h, the default is to define MATCH_LIMIT_RECURSION +# symbolically as MATCH_LIMIT, which in turn is defined to be some numeric +# value (e.g. 10000000). MATCH_LIMIT_RECURSION can otherwise be set to some +# different numeric value (or even the same numeric value as MATCH_LIMIT, +# though no longer defined in terms of the latter). +# + +# Check whether --with-match-limit-recursion was given. +if test "${with_match_limit_recursion+set}" = set; then : + withval=$with_match_limit_recursion; +else + with_match_limit_recursion=MATCH_LIMIT +fi + + +# Handle --enable-valgrind +# Check whether --enable-valgrind was given. +if test "${enable_valgrind+set}" = set; then : + enableval=$enable_valgrind; +else + enable_valgrind=no +fi + + +# Enable code coverage reports using gcov +# Check whether --enable-coverage was given. +if test "${enable_coverage+set}" = set; then : + enableval=$enable_coverage; +else + enable_coverage=no +fi + + +# Set the default value for pcre2-8 +if test "x$enable_pcre2_8" = "xunset" +then + enable_pcre2_8=yes +fi + +# Set the default value for pcre2-16 +if test "x$enable_pcre2_16" = "xunset" +then + enable_pcre2_16=no +fi + +# Set the default value for pcre2-32 +if test "x$enable_pcre2_32" = "xunset" +then + enable_pcre2_32=no +fi + +# Make sure at least one library is selected +if test "x$enable_pcre2_8$enable_pcre2_16$enable_pcre2_32" = "xnonono" +then + as_fn_error $? "At least one of the 8, 16 or 32 bit libraries must be enabled" "$LINENO" 5 +fi + +# Unicode is enabled by default. +if test "x$enable_unicode" = "xunset" +then + enable_unicode=yes +fi + +# Convert the newline identifier into the appropriate integer value. These must +# agree with the PCRE2_NEWLINE_xxx values in pcre2.h. + +case "$enable_newline" in + cr) ac_pcre2_newline_value=1 ;; + lf) ac_pcre2_newline_value=2 ;; + crlf) ac_pcre2_newline_value=3 ;; + any) ac_pcre2_newline_value=4 ;; + anycrlf) ac_pcre2_newline_value=5 ;; + *) + as_fn_error $? "invalid argument \"$enable_newline\" to --enable-newline option" "$LINENO" 5 + ;; +esac + +# --enable-ebcdic-nl25 implies --enable-ebcdic +if test "x$enable_ebcdic_nl25" = "xyes"; then + enable_ebcdic=yes +fi + +# Make sure that if enable_ebcdic is set, rebuild_chartables is also enabled. +# Also check that UTF support is not requested, because PCRE2 cannot handle +# EBCDIC and UTF in the same build. To do so it would need to use different +# character constants depending on the mode. +# +if test "x$enable_ebcdic" = "xyes"; then + enable_rebuild_chartables=yes + if test "x$enable_unicode" = "xyes"; then + as_fn_error $? "support for EBCDIC and Unicode cannot be enabled at the same time" "$LINENO" 5 + fi +fi + +# Check argument to --with-link-size +case "$with_link_size" in + 2|3|4) ;; + *) + as_fn_error $? "invalid argument \"$with_link_size\" to --with-link-size option" "$LINENO" 5 + ;; +esac + + + +# Checks for header files. +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for ANSI C header files" >&5 +$as_echo_n "checking for ANSI C header files... " >&6; } +if ${ac_cv_header_stdc+:} false; then : + $as_echo_n "(cached) " >&6 +else + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#include +#include +#include +#include + +int +main () +{ + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + ac_cv_header_stdc=yes +else + ac_cv_header_stdc=no +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext + +if test $ac_cv_header_stdc = yes; then + # SunOS 4.x string.h does not declare mem*, contrary to ANSI. + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#include + +_ACEOF +if (eval "$ac_cpp conftest.$ac_ext") 2>&5 | + $EGREP "memchr" >/dev/null 2>&1; then : + +else + ac_cv_header_stdc=no +fi +rm -f conftest* + +fi + +if test $ac_cv_header_stdc = yes; then + # ISC 2.0.2 stdlib.h does not declare free, contrary to ANSI. + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#include + +_ACEOF +if (eval "$ac_cpp conftest.$ac_ext") 2>&5 | + $EGREP "free" >/dev/null 2>&1; then : + +else + ac_cv_header_stdc=no +fi +rm -f conftest* + +fi + +if test $ac_cv_header_stdc = yes; then + # /bin/cc in Irix-4.0.5 gets non-ANSI ctype macros unless using -ansi. + if test "$cross_compiling" = yes; then : + : +else + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#include +#include +#if ((' ' & 0x0FF) == 0x020) +# define ISLOWER(c) ('a' <= (c) && (c) <= 'z') +# define TOUPPER(c) (ISLOWER(c) ? 'A' + ((c) - 'a') : (c)) +#else +# define ISLOWER(c) \ + (('a' <= (c) && (c) <= 'i') \ + || ('j' <= (c) && (c) <= 'r') \ + || ('s' <= (c) && (c) <= 'z')) +# define TOUPPER(c) (ISLOWER(c) ? ((c) | 0x40) : (c)) +#endif + +#define XOR(e, f) (((e) && !(f)) || (!(e) && (f))) +int +main () +{ + int i; + for (i = 0; i < 256; i++) + if (XOR (islower (i), ISLOWER (i)) + || toupper (i) != TOUPPER (i)) + return 2; + return 0; +} +_ACEOF +if ac_fn_c_try_run "$LINENO"; then : + +else + ac_cv_header_stdc=no +fi +rm -f core *.core core.conftest.* gmon.out bb.out conftest$ac_exeext \ + conftest.$ac_objext conftest.beam conftest.$ac_ext +fi + +fi +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_header_stdc" >&5 +$as_echo "$ac_cv_header_stdc" >&6; } +if test $ac_cv_header_stdc = yes; then + +$as_echo "#define STDC_HEADERS 1" >>confdefs.h + +fi + +for ac_header in limits.h sys/types.h sys/stat.h dirent.h +do : + as_ac_Header=`$as_echo "ac_cv_header_$ac_header" | $as_tr_sh` +ac_fn_c_check_header_mongrel "$LINENO" "$ac_header" "$as_ac_Header" "$ac_includes_default" +if eval test \"x\$"$as_ac_Header"\" = x"yes"; then : + cat >>confdefs.h <<_ACEOF +#define `$as_echo "HAVE_$ac_header" | $as_tr_cpp` 1 +_ACEOF + +fi + +done + +for ac_header in windows.h +do : + ac_fn_c_check_header_mongrel "$LINENO" "windows.h" "ac_cv_header_windows_h" "$ac_includes_default" +if test "x$ac_cv_header_windows_h" = xyes; then : + cat >>confdefs.h <<_ACEOF +#define HAVE_WINDOWS_H 1 +_ACEOF + HAVE_WINDOWS_H=1 +fi + +done + + +# Conditional compilation + if test "x$enable_pcre2_8" = "xyes"; then + WITH_PCRE2_8_TRUE= + WITH_PCRE2_8_FALSE='#' +else + WITH_PCRE2_8_TRUE='#' + WITH_PCRE2_8_FALSE= +fi + + if test "x$enable_pcre2_16" = "xyes"; then + WITH_PCRE2_16_TRUE= + WITH_PCRE2_16_FALSE='#' +else + WITH_PCRE2_16_TRUE='#' + WITH_PCRE2_16_FALSE= +fi + + if test "x$enable_pcre2_32" = "xyes"; then + WITH_PCRE2_32_TRUE= + WITH_PCRE2_32_FALSE='#' +else + WITH_PCRE2_32_TRUE='#' + WITH_PCRE2_32_FALSE= +fi + + if test "x$enable_debug" = "xyes"; then + WITH_DEBUG_TRUE= + WITH_DEBUG_FALSE='#' +else + WITH_DEBUG_TRUE='#' + WITH_DEBUG_FALSE= +fi + + if test "x$enable_rebuild_chartables" = "xyes"; then + WITH_REBUILD_CHARTABLES_TRUE= + WITH_REBUILD_CHARTABLES_FALSE='#' +else + WITH_REBUILD_CHARTABLES_TRUE='#' + WITH_REBUILD_CHARTABLES_FALSE= +fi + + if test "x$enable_jit" = "xyes"; then + WITH_JIT_TRUE= + WITH_JIT_FALSE='#' +else + WITH_JIT_TRUE='#' + WITH_JIT_FALSE= +fi + + if test "x$enable_unicode" = "xyes"; then + WITH_UNICODE_TRUE= + WITH_UNICODE_FALSE='#' +else + WITH_UNICODE_TRUE='#' + WITH_UNICODE_FALSE= +fi + + if test "x$enable_valgrind" = "xyes"; then + WITH_VALGRIND_TRUE= + WITH_VALGRIND_FALSE='#' +else + WITH_VALGRIND_TRUE='#' + WITH_VALGRIND_FALSE= +fi + + +# Checks for typedefs, structures, and compiler characteristics. + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for an ANSI C-conforming const" >&5 +$as_echo_n "checking for an ANSI C-conforming const... " >&6; } +if ${ac_cv_c_const+:} false; then : + $as_echo_n "(cached) " >&6 +else + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +int +main () +{ + +#ifndef __cplusplus + /* Ultrix mips cc rejects this sort of thing. */ + typedef int charset[2]; + const charset cs = { 0, 0 }; + /* SunOS 4.1.1 cc rejects this. */ + char const *const *pcpcc; + char **ppc; + /* NEC SVR4.0.2 mips cc rejects this. */ + struct point {int x, y;}; + static struct point const zero = {0,0}; + /* AIX XL C 1.02.0.0 rejects this. + It does not let you subtract one const X* pointer from another in + an arm of an if-expression whose if-part is not a constant + expression */ + const char *g = "string"; + pcpcc = &g + (g ? g-g : 0); + /* HPUX 7.0 cc rejects these. */ + ++pcpcc; + ppc = (char**) pcpcc; + pcpcc = (char const *const *) ppc; + { /* SCO 3.2v4 cc rejects this sort of thing. */ + char tx; + char *t = &tx; + char const *s = 0 ? (char *) 0 : (char const *) 0; + + *t++ = 0; + if (s) return 0; + } + { /* Someone thinks the Sun supposedly-ANSI compiler will reject this. */ + int x[] = {25, 17}; + const int *foo = &x[0]; + ++foo; + } + { /* Sun SC1.0 ANSI compiler rejects this -- but not the above. */ + typedef const int *iptr; + iptr p = 0; + ++p; + } + { /* AIX XL C 1.02.0.0 rejects this sort of thing, saying + "k.c", line 2.27: 1506-025 (S) Operand must be a modifiable lvalue. */ + struct s { int j; const int *ap[3]; } bx; + struct s *b = &bx; b->j = 5; + } + { /* ULTRIX-32 V3.1 (Rev 9) vcc rejects this */ + const int foo = 10; + if (!foo) return 0; + } + return !cs[0] && !zero.x; +#endif + + ; + return 0; +} +_ACEOF +if ac_fn_c_try_compile "$LINENO"; then : + ac_cv_c_const=yes +else + ac_cv_c_const=no +fi +rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_c_const" >&5 +$as_echo "$ac_cv_c_const" >&6; } +if test $ac_cv_c_const = no; then + +$as_echo "#define const /**/" >>confdefs.h + +fi + +ac_fn_c_check_type "$LINENO" "size_t" "ac_cv_type_size_t" "$ac_includes_default" +if test "x$ac_cv_type_size_t" = xyes; then : + +else + +cat >>confdefs.h <<_ACEOF +#define size_t unsigned int +_ACEOF + +fi + + +# Checks for library functions. + +for ac_func in bcopy memmove strerror +do : + as_ac_var=`$as_echo "ac_cv_func_$ac_func" | $as_tr_sh` +ac_fn_c_check_func "$LINENO" "$ac_func" "$as_ac_var" +if eval test \"x\$"$as_ac_var"\" = x"yes"; then : + cat >>confdefs.h <<_ACEOF +#define `$as_echo "HAVE_$ac_func" | $as_tr_cpp` 1 +_ACEOF + +fi +done + + +# Check for the availability of libz (aka zlib) + +for ac_header in zlib.h +do : + ac_fn_c_check_header_mongrel "$LINENO" "zlib.h" "ac_cv_header_zlib_h" "$ac_includes_default" +if test "x$ac_cv_header_zlib_h" = xyes; then : + cat >>confdefs.h <<_ACEOF +#define HAVE_ZLIB_H 1 +_ACEOF + HAVE_ZLIB_H=1 +fi + +done + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for gzopen in -lz" >&5 +$as_echo_n "checking for gzopen in -lz... " >&6; } +if ${ac_cv_lib_z_gzopen+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-lz $LIBS" +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char gzopen (); +int +main () +{ +return gzopen (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ac_cv_lib_z_gzopen=yes +else + ac_cv_lib_z_gzopen=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_z_gzopen" >&5 +$as_echo "$ac_cv_lib_z_gzopen" >&6; } +if test "x$ac_cv_lib_z_gzopen" = xyes; then : + HAVE_LIBZ=1 +fi + + +# Check for the availability of libbz2. Originally we just used AC_CHECK_LIB, +# as for libz. However, this had the following problem, diagnosed and fixed by +# a user: +# +# - libbz2 uses the Pascal calling convention (WINAPI) for the functions +# under Win32. +# - The standard autoconf AC_CHECK_LIB fails to include "bzlib.h", +# therefore missing the function definition. +# - The compiler thus generates a "C" signature for the test function. +# - The linker fails to find the "C" function. +# - PCRE2 fails to configure if asked to do so against libbz2. +# +# Solution: +# +# - Replace the AC_CHECK_LIB test with a custom test. + +for ac_header in bzlib.h +do : + ac_fn_c_check_header_mongrel "$LINENO" "bzlib.h" "ac_cv_header_bzlib_h" "$ac_includes_default" +if test "x$ac_cv_header_bzlib_h" = xyes; then : + cat >>confdefs.h <<_ACEOF +#define HAVE_BZLIB_H 1 +_ACEOF + HAVE_BZLIB_H=1 +fi + +done + +# Original test +# AC_CHECK_LIB([bz2], [BZ2_bzopen], [HAVE_LIBBZ2=1]) +# +# Custom test follows + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for libbz2" >&5 +$as_echo_n "checking for libbz2... " >&6; } +OLD_LIBS="$LIBS" +LIBS="$LIBS -lbz2" +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +#ifdef HAVE_BZLIB_H +#include +#endif +int +main () +{ +return (int)BZ2_bzopen("conftest", "rb"); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5 +$as_echo "yes" >&6; };HAVE_LIBBZ2=1; break; +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS="$OLD_LIBS" + +# Check for the availabiity of libreadline + +if test "$enable_pcre2test_libreadline" = "yes"; then + for ac_header in readline/readline.h +do : + ac_fn_c_check_header_mongrel "$LINENO" "readline/readline.h" "ac_cv_header_readline_readline_h" "$ac_includes_default" +if test "x$ac_cv_header_readline_readline_h" = xyes; then : + cat >>confdefs.h <<_ACEOF +#define HAVE_READLINE_READLINE_H 1 +_ACEOF + HAVE_READLINE_H=1 +fi + +done + + for ac_header in readline/history.h +do : + ac_fn_c_check_header_mongrel "$LINENO" "readline/history.h" "ac_cv_header_readline_history_h" "$ac_includes_default" +if test "x$ac_cv_header_readline_history_h" = xyes; then : + cat >>confdefs.h <<_ACEOF +#define HAVE_READLINE_HISTORY_H 1 +_ACEOF + HAVE_HISTORY_H=1 +fi + +done + + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for readline in -lreadline" >&5 +$as_echo_n "checking for readline in -lreadline... " >&6; } +if ${ac_cv_lib_readline_readline+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-lreadline $LIBS" +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char readline (); +int +main () +{ +return readline (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ac_cv_lib_readline_readline=yes +else + ac_cv_lib_readline_readline=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_readline_readline" >&5 +$as_echo "$ac_cv_lib_readline_readline" >&6; } +if test "x$ac_cv_lib_readline_readline" = xyes; then : + LIBREADLINE="-lreadline" +else + unset ac_cv_lib_readline_readline; + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for readline in -lreadline" >&5 +$as_echo_n "checking for readline in -lreadline... " >&6; } +if ${ac_cv_lib_readline_readline+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-lreadline -ltinfo $LIBS" +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char readline (); +int +main () +{ +return readline (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ac_cv_lib_readline_readline=yes +else + ac_cv_lib_readline_readline=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_readline_readline" >&5 +$as_echo "$ac_cv_lib_readline_readline" >&6; } +if test "x$ac_cv_lib_readline_readline" = xyes; then : + LIBREADLINE="-ltinfo" +else + unset ac_cv_lib_readline_readline; + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for readline in -lreadline" >&5 +$as_echo_n "checking for readline in -lreadline... " >&6; } +if ${ac_cv_lib_readline_readline+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-lreadline -lcurses $LIBS" +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char readline (); +int +main () +{ +return readline (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ac_cv_lib_readline_readline=yes +else + ac_cv_lib_readline_readline=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_readline_readline" >&5 +$as_echo "$ac_cv_lib_readline_readline" >&6; } +if test "x$ac_cv_lib_readline_readline" = xyes; then : + LIBREADLINE="-lcurses" +else + unset ac_cv_lib_readline_readline; + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for readline in -lreadline" >&5 +$as_echo_n "checking for readline in -lreadline... " >&6; } +if ${ac_cv_lib_readline_readline+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-lreadline -lncurses $LIBS" +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char readline (); +int +main () +{ +return readline (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ac_cv_lib_readline_readline=yes +else + ac_cv_lib_readline_readline=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_readline_readline" >&5 +$as_echo "$ac_cv_lib_readline_readline" >&6; } +if test "x$ac_cv_lib_readline_readline" = xyes; then : + LIBREADLINE="-lncurses" +else + unset ac_cv_lib_readline_readline; + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for readline in -lreadline" >&5 +$as_echo_n "checking for readline in -lreadline... " >&6; } +if ${ac_cv_lib_readline_readline+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-lreadline -lncursesw $LIBS" +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char readline (); +int +main () +{ +return readline (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ac_cv_lib_readline_readline=yes +else + ac_cv_lib_readline_readline=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_readline_readline" >&5 +$as_echo "$ac_cv_lib_readline_readline" >&6; } +if test "x$ac_cv_lib_readline_readline" = xyes; then : + LIBREADLINE="-lncursesw" +else + unset ac_cv_lib_readline_readline; + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for readline in -lreadline" >&5 +$as_echo_n "checking for readline in -lreadline... " >&6; } +if ${ac_cv_lib_readline_readline+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-lreadline -ltermcap $LIBS" +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char readline (); +int +main () +{ +return readline (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ac_cv_lib_readline_readline=yes +else + ac_cv_lib_readline_readline=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_readline_readline" >&5 +$as_echo "$ac_cv_lib_readline_readline" >&6; } +if test "x$ac_cv_lib_readline_readline" = xyes; then : + LIBREADLINE="-ltermcap" +else + LIBREADLINE="" +fi + +fi + +fi + +fi + +fi + +fi + + + if test -n "$LIBREADLINE"; then + if test "$LIBREADLINE" != "-lreadline"; then + echo "-lreadline needs $LIBREADLINE" + LIBREADLINE="-lreadline $LIBREADLINE" + fi + fi +fi + + +# Check for the availability of libedit. Different distributions put its +# headers in different places. Try to cover the most common ones. + +if test "$enable_pcre2test_libedit" = "yes"; then + for ac_header in editline/readline.h +do : + ac_fn_c_check_header_mongrel "$LINENO" "editline/readline.h" "ac_cv_header_editline_readline_h" "$ac_includes_default" +if test "x$ac_cv_header_editline_readline_h" = xyes; then : + cat >>confdefs.h <<_ACEOF +#define HAVE_EDITLINE_READLINE_H 1 +_ACEOF + HAVE_EDITLINE_READLINE_H=1 +else + for ac_header in edit/readline/readline.h +do : + ac_fn_c_check_header_mongrel "$LINENO" "edit/readline/readline.h" "ac_cv_header_edit_readline_readline_h" "$ac_includes_default" +if test "x$ac_cv_header_edit_readline_readline_h" = xyes; then : + cat >>confdefs.h <<_ACEOF +#define HAVE_EDIT_READLINE_READLINE_H 1 +_ACEOF + HAVE_READLINE_READLINE_H=1 +else + for ac_header in readline/readline.h +do : + ac_fn_c_check_header_mongrel "$LINENO" "readline/readline.h" "ac_cv_header_readline_readline_h" "$ac_includes_default" +if test "x$ac_cv_header_readline_readline_h" = xyes; then : + cat >>confdefs.h <<_ACEOF +#define HAVE_READLINE_READLINE_H 1 +_ACEOF + HAVE_READLINE_READLINE_H=1 +fi + +done + +fi + +done + +fi + +done + + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for readline in -ledit" >&5 +$as_echo_n "checking for readline in -ledit... " >&6; } +if ${ac_cv_lib_edit_readline+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-ledit $LIBS" +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char readline (); +int +main () +{ +return readline (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ac_cv_lib_edit_readline=yes +else + ac_cv_lib_edit_readline=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_edit_readline" >&5 +$as_echo "$ac_cv_lib_edit_readline" >&6; } +if test "x$ac_cv_lib_edit_readline" = xyes; then : + LIBEDIT="-ledit" +fi + +fi + +# This facilitates -ansi builds under Linux + +PCRE2_STATIC_CFLAG="" +if test "x$enable_shared" = "xno" ; then + +$as_echo "#define PCRE2_STATIC 1" >>confdefs.h + + PCRE2_STATIC_CFLAG="-DPCRE2_STATIC" +fi + + +# Here is where PCRE2-specific defines are handled + +if test "$enable_pcre2_8" = "yes"; then + +$as_echo "#define SUPPORT_PCRE2_8 /**/" >>confdefs.h + +fi + +if test "$enable_pcre2_16" = "yes"; then + +$as_echo "#define SUPPORT_PCRE2_16 /**/" >>confdefs.h + +fi + +if test "$enable_pcre2_32" = "yes"; then + +$as_echo "#define SUPPORT_PCRE2_32 /**/" >>confdefs.h + +fi + +if test "$enable_debug" = "yes"; then + +$as_echo "#define PCRE2_DEBUG /**/" >>confdefs.h + +fi + +# Unless running under Windows, JIT support requires pthreads. + +if test "$enable_jit" = "yes"; then + if test "$HAVE_WINDOWS_H" != "1"; then + + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + +ax_pthread_ok=no + +# We used to check for pthread.h first, but this fails if pthread.h +# requires special compiler flags (e.g. on True64 or Sequent). +# It gets checked for in the link test anyway. + +# First of all, check if the user has set any of the PTHREAD_LIBS, +# etcetera environment variables, and if threads linking works using +# them: +if test x"$PTHREAD_LIBS$PTHREAD_CFLAGS" != x; then + save_CFLAGS="$CFLAGS" + CFLAGS="$CFLAGS $PTHREAD_CFLAGS" + save_LIBS="$LIBS" + LIBS="$PTHREAD_LIBS $LIBS" + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for pthread_join in LIBS=$PTHREAD_LIBS with CFLAGS=$PTHREAD_CFLAGS" >&5 +$as_echo_n "checking for pthread_join in LIBS=$PTHREAD_LIBS with CFLAGS=$PTHREAD_CFLAGS... " >&6; } + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char pthread_join (); +int +main () +{ +return pthread_join (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ax_pthread_ok=yes +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ax_pthread_ok" >&5 +$as_echo "$ax_pthread_ok" >&6; } + if test x"$ax_pthread_ok" = xno; then + PTHREAD_LIBS="" + PTHREAD_CFLAGS="" + fi + LIBS="$save_LIBS" + CFLAGS="$save_CFLAGS" +fi + +# We must check for the threads library under a number of different +# names; the ordering is very important because some systems +# (e.g. DEC) have both -lpthread and -lpthreads, where one of the +# libraries is broken (non-POSIX). + +# Create a list of thread flags to try. Items starting with a "-" are +# C compiler flags, and other items are library names, except for "none" +# which indicates that we try without any flags at all, and "pthread-config" +# which is a program returning the flags for the Pth emulation library. + +ax_pthread_flags="pthreads none -Kthread -kthread lthread -pthread -pthreads -mthreads pthread --thread-safe -mt pthread-config" + +# The ordering *is* (sometimes) important. Some notes on the +# individual items follow: + +# pthreads: AIX (must check this before -lpthread) +# none: in case threads are in libc; should be tried before -Kthread and +# other compiler flags to prevent continual compiler warnings +# -Kthread: Sequent (threads in libc, but -Kthread needed for pthread.h) +# -kthread: FreeBSD kernel threads (preferred to -pthread since SMP-able) +# lthread: LinuxThreads port on FreeBSD (also preferred to -pthread) +# -pthread: Linux/gcc (kernel threads), BSD/gcc (userland threads) +# -pthreads: Solaris/gcc +# -mthreads: Mingw32/gcc, Lynx/gcc +# -mt: Sun Workshop C (may only link SunOS threads [-lthread], but it +# doesn't hurt to check since this sometimes defines pthreads too; +# also defines -D_REENTRANT) +# ... -mt is also the pthreads flag for HP/aCC +# pthread: Linux, etcetera +# --thread-safe: KAI C++ +# pthread-config: use pthread-config program (for GNU Pth library) + +case ${host_os} in + solaris*) + + # On Solaris (at least, for some versions), libc contains stubbed + # (non-functional) versions of the pthreads routines, so link-based + # tests will erroneously succeed. (We need to link with -pthreads/-mt/ + # -lpthread.) (The stubs are missing pthread_cleanup_push, or rather + # a function called by this macro, so we could check for that, but + # who knows whether they'll stub that too in a future libc.) So, + # we'll just look for -pthreads and -lpthread first: + + ax_pthread_flags="-pthreads pthread -mt -pthread $ax_pthread_flags" + ;; + + darwin*) + ax_pthread_flags="-pthread $ax_pthread_flags" + ;; +esac + +if test x"$ax_pthread_ok" = xno; then +for flag in $ax_pthread_flags; do + + case $flag in + none) + { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether pthreads work without any flags" >&5 +$as_echo_n "checking whether pthreads work without any flags... " >&6; } + ;; + + -*) + { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether pthreads work with $flag" >&5 +$as_echo_n "checking whether pthreads work with $flag... " >&6; } + PTHREAD_CFLAGS="$flag" + ;; + + pthread-config) + # Extract the first word of "pthread-config", so it can be a program name with args. +set dummy pthread-config; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_ax_pthread_config+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$ax_pthread_config"; then + ac_cv_prog_ax_pthread_config="$ax_pthread_config" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ax_pthread_config="yes" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + + test -z "$ac_cv_prog_ax_pthread_config" && ac_cv_prog_ax_pthread_config="no" +fi +fi +ax_pthread_config=$ac_cv_prog_ax_pthread_config +if test -n "$ax_pthread_config"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ax_pthread_config" >&5 +$as_echo "$ax_pthread_config" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + if test x"$ax_pthread_config" = xno; then continue; fi + PTHREAD_CFLAGS="`pthread-config --cflags`" + PTHREAD_LIBS="`pthread-config --ldflags` `pthread-config --libs`" + ;; + + *) + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for the pthreads library -l$flag" >&5 +$as_echo_n "checking for the pthreads library -l$flag... " >&6; } + PTHREAD_LIBS="-l$flag" + ;; + esac + + save_LIBS="$LIBS" + save_CFLAGS="$CFLAGS" + LIBS="$PTHREAD_LIBS $LIBS" + CFLAGS="$CFLAGS $PTHREAD_CFLAGS" + + # Check for various functions. We must include pthread.h, + # since some functions may be macros. (On the Sequent, we + # need a special flag -Kthread to make this header compile.) + # We check for pthread_join because it is in -lpthread on IRIX + # while pthread_create is in libc. We check for pthread_attr_init + # due to DEC craziness with -lpthreads. We check for + # pthread_cleanup_push because it is one of the few pthread + # functions on Solaris that doesn't have a non-functional libc stub. + # We try pthread_create on general principles. + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#include + static void routine(void *a) { a = 0; } + static void *start_routine(void *a) { return a; } +int +main () +{ +pthread_t th; pthread_attr_t attr; + pthread_create(&th, 0, start_routine, 0); + pthread_join(th, 0); + pthread_attr_init(&attr); + pthread_cleanup_push(routine, 0); + pthread_cleanup_pop(0) /* ; */ + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ax_pthread_ok=yes +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext + + LIBS="$save_LIBS" + CFLAGS="$save_CFLAGS" + + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ax_pthread_ok" >&5 +$as_echo "$ax_pthread_ok" >&6; } + if test "x$ax_pthread_ok" = xyes; then + break; + fi + + PTHREAD_LIBS="" + PTHREAD_CFLAGS="" +done +fi + +# Various other checks: +if test "x$ax_pthread_ok" = xyes; then + save_LIBS="$LIBS" + LIBS="$PTHREAD_LIBS $LIBS" + save_CFLAGS="$CFLAGS" + CFLAGS="$CFLAGS $PTHREAD_CFLAGS" + + # Detect AIX lossage: JOINABLE attribute is called UNDETACHED. + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for joinable pthread attribute" >&5 +$as_echo_n "checking for joinable pthread attribute... " >&6; } + attr_name=unknown + for attr in PTHREAD_CREATE_JOINABLE PTHREAD_CREATE_UNDETACHED; do + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ +#include +int +main () +{ +int attr = $attr; return attr /* ; */ + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + attr_name=$attr; break +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext + done + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $attr_name" >&5 +$as_echo "$attr_name" >&6; } + if test "$attr_name" != PTHREAD_CREATE_JOINABLE; then + +cat >>confdefs.h <<_ACEOF +#define PTHREAD_CREATE_JOINABLE $attr_name +_ACEOF + + fi + + { $as_echo "$as_me:${as_lineno-$LINENO}: checking if more special flags are required for pthreads" >&5 +$as_echo_n "checking if more special flags are required for pthreads... " >&6; } + flag=no + case ${host_os} in + aix* | freebsd* | darwin*) flag="-D_THREAD_SAFE";; + osf* | hpux*) flag="-D_REENTRANT";; + solaris*) + if test "$GCC" = "yes"; then + flag="-D_REENTRANT" + else + flag="-mt -D_REENTRANT" + fi + ;; + esac + { $as_echo "$as_me:${as_lineno-$LINENO}: result: ${flag}" >&5 +$as_echo "${flag}" >&6; } + if test "x$flag" != xno; then + PTHREAD_CFLAGS="$flag $PTHREAD_CFLAGS" + fi + + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for PTHREAD_PRIO_INHERIT" >&5 +$as_echo_n "checking for PTHREAD_PRIO_INHERIT... " >&6; } +if ${ax_cv_PTHREAD_PRIO_INHERIT+:} false; then : + $as_echo_n "(cached) " >&6 +else + + cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + + #include +int +main () +{ +int i = PTHREAD_PRIO_INHERIT; + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ax_cv_PTHREAD_PRIO_INHERIT=yes +else + ax_cv_PTHREAD_PRIO_INHERIT=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ax_cv_PTHREAD_PRIO_INHERIT" >&5 +$as_echo "$ax_cv_PTHREAD_PRIO_INHERIT" >&6; } + if test "x$ax_cv_PTHREAD_PRIO_INHERIT" = "xyes"; then : + +$as_echo "#define HAVE_PTHREAD_PRIO_INHERIT 1" >>confdefs.h + +fi + + LIBS="$save_LIBS" + CFLAGS="$save_CFLAGS" + + # More AIX lossage: must compile with xlc_r or cc_r + if test x"$GCC" != xyes; then + for ac_prog in xlc_r cc_r +do + # Extract the first word of "$ac_prog", so it can be a program name with args. +set dummy $ac_prog; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_prog_PTHREAD_CC+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test -n "$PTHREAD_CC"; then + ac_cv_prog_PTHREAD_CC="$PTHREAD_CC" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_PTHREAD_CC="$ac_prog" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + +fi +fi +PTHREAD_CC=$ac_cv_prog_PTHREAD_CC +if test -n "$PTHREAD_CC"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $PTHREAD_CC" >&5 +$as_echo "$PTHREAD_CC" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + test -n "$PTHREAD_CC" && break +done +test -n "$PTHREAD_CC" || PTHREAD_CC="${CC}" + + else + PTHREAD_CC=$CC + fi +else + PTHREAD_CC="$CC" +fi + + + + + +# Finally, execute ACTION-IF-FOUND/ACTION-IF-NOT-FOUND: +if test x"$ax_pthread_ok" = xyes; then + +$as_echo "#define HAVE_PTHREAD 1" >>confdefs.h + + : +else + ax_pthread_ok=no + as_fn_error $? "JIT support requires pthreads" "$LINENO" 5 +fi +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + + + CC="$PTHREAD_CC" + CFLAGS="$PTHREAD_CFLAGS $CFLAGS" + LIBS="$PTHREAD_LIBS $LIBS" + fi + +$as_echo "#define SUPPORT_JIT /**/" >>confdefs.h + +else + enable_pcre2grep_jit="no" +fi + +if test "$enable_pcre2grep_jit" = "yes"; then + +$as_echo "#define SUPPORT_PCRE2GREP_JIT /**/" >>confdefs.h + +fi + +if test "$enable_unicode" = "yes"; then + +$as_echo "#define SUPPORT_UNICODE /**/" >>confdefs.h + +fi + +if test "$enable_stack_for_recursion" = "no"; then + +$as_echo "#define HEAP_MATCH_RECURSE /**/" >>confdefs.h + +fi + +if test "$enable_pcre2grep_libz" = "yes"; then + +$as_echo "#define SUPPORT_LIBZ /**/" >>confdefs.h + +fi + +if test "$enable_pcre2grep_libbz2" = "yes"; then + +$as_echo "#define SUPPORT_LIBBZ2 /**/" >>confdefs.h + +fi + +if test $with_pcre2grep_bufsize -lt 8192 ; then + { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $with_pcre2grep_bufsize is too small for --with-pcre2grep-bufsize; using 8192" >&5 +$as_echo "$as_me: WARNING: $with_pcre2grep_bufsize is too small for --with-pcre2grep-bufsize; using 8192" >&2;} + with_pcre2grep_bufsize="8192" +else + if test $? -gt 1 ; then + as_fn_error $? "Bad value for --with-pcre2grep-bufsize" "$LINENO" 5 + fi +fi + + +cat >>confdefs.h <<_ACEOF +#define PCRE2GREP_BUFSIZE $with_pcre2grep_bufsize +_ACEOF + + +if test "$enable_pcre2test_libedit" = "yes"; then + +$as_echo "#define SUPPORT_LIBEDIT /**/" >>confdefs.h + + LIBREADLINE="$LIBEDIT" +elif test "$enable_pcre2test_libreadline" = "yes"; then + +$as_echo "#define SUPPORT_LIBREADLINE /**/" >>confdefs.h + +fi + + +cat >>confdefs.h <<_ACEOF +#define NEWLINE_DEFAULT $ac_pcre2_newline_value +_ACEOF + + +if test "$enable_bsr_anycrlf" = "yes"; then + +$as_echo "#define BSR_ANYCRLF /**/" >>confdefs.h + +fi + + +cat >>confdefs.h <<_ACEOF +#define LINK_SIZE $with_link_size +_ACEOF + + + +cat >>confdefs.h <<_ACEOF +#define PARENS_NEST_LIMIT $with_parens_nest_limit +_ACEOF + + + +cat >>confdefs.h <<_ACEOF +#define MATCH_LIMIT $with_match_limit +_ACEOF + + + +cat >>confdefs.h <<_ACEOF +#define MATCH_LIMIT_RECURSION $with_match_limit_recursion +_ACEOF + + + +$as_echo "#define MAX_NAME_SIZE 32" >>confdefs.h + + + +$as_echo "#define MAX_NAME_COUNT 10000" >>confdefs.h + + + + +if test "$enable_ebcdic" = "yes"; then + +cat >>confdefs.h <<_ACEOF +#define EBCDIC /**/ +_ACEOF + +fi + +if test "$enable_ebcdic_nl25" = "yes"; then + +cat >>confdefs.h <<_ACEOF +#define EBCDIC_NL25 /**/ +_ACEOF + +fi + +if test "$enable_valgrind" = "yes"; then + +cat >>confdefs.h <<_ACEOF +#define SUPPORT_VALGRIND /**/ +_ACEOF + +fi + +# Platform specific issues +NO_UNDEFINED= +EXPORT_ALL_SYMBOLS= +case $host_os in + cygwin* | mingw* ) + if test X"$enable_shared" = Xyes; then + NO_UNDEFINED="-no-undefined" + EXPORT_ALL_SYMBOLS="-Wl,--export-all-symbols" + fi + ;; +esac + +# The extra LDFLAGS for each particular library. The libpcre2*_version values +# are m4 variables, assigned above. + +EXTRA_LIBPCRE2_8_LDFLAGS="$EXTRA_LIBPCRE2_8_LDFLAGS \ + $NO_UNDEFINED -version-info 2:0:2" + +EXTRA_LIBPCRE2_16_LDFLAGS="$EXTRA_LIBPCRE2_16_LDFLAGS \ + $NO_UNDEFINED -version-info 2:0:2" + +EXTRA_LIBPCRE2_32_LDFLAGS="$EXTRA_LIBPCRE2_32_LDFLAGS \ + $NO_UNDEFINED -version-info 2:0:2" + +EXTRA_LIBPCRE2_POSIX_LDFLAGS="$EXTRA_LIBPCRE2_POSIX_LDFLAGS \ + $NO_UNDEFINED -version-info 0:0:0" + + + + + + +# When we run 'make distcheck', use these arguments. Turning off compiler +# optimization makes it run faster. +DISTCHECK_CONFIGURE_FLAGS="CFLAGS='' CXXFLAGS='' --enable-pcre2-16 --enable-pcre2-32 --enable-jit --enable-utf" + + +# Check that, if --enable-pcre2grep-libz or --enable-pcre2grep-libbz2 is +# specified, the relevant library is available. + +if test "$enable_pcre2grep_libz" = "yes"; then + if test "$HAVE_ZLIB_H" != "1"; then + echo "** Cannot --enable-pcre2grep-libz because zlib.h was not found" + exit 1 + fi + if test "$HAVE_LIBZ" != "1"; then + echo "** Cannot --enable-pcre2grep-libz because libz was not found" + exit 1 + fi + LIBZ="-lz" +fi + + +if test "$enable_pcre2grep_libbz2" = "yes"; then + if test "$HAVE_BZLIB_H" != "1"; then + echo "** Cannot --enable-pcre2grep-libbz2 because bzlib.h was not found" + exit 1 + fi + if test "$HAVE_LIBBZ2" != "1"; then + echo "** Cannot --enable-pcre2grep-libbz2 because libbz2 was not found" + exit 1 + fi + LIBBZ2="-lbz2" +fi + + +# Similarly for --enable-pcre2test-readline + +if test "$enable_pcre2test_libedit" = "yes"; then + if test "$enable_pcre2test_libreadline" = "yes"; then + echo "** Cannot use both --enable-pcre2test-libedit and --enable-pcre2test-readline" + exit 1 + fi + if test "$HAVE_EDITLINE_READLINE_H" != "1" -a \ + "$HAVE_READLINE_READLINE_H" != "1"; then + echo "** Cannot --enable-pcre2test-libedit because neither editline/readline.h" + echo "** nor readline/readline.h was found." + exit 1 + fi + if test -z "$LIBEDIT"; then + echo "** Cannot --enable-pcre2test-libedit because libedit library was not found." + exit 1 + fi +fi + +if test "$enable_pcre2test_libreadline" = "yes"; then + if test "$HAVE_READLINE_H" != "1"; then + echo "** Cannot --enable-pcre2test-readline because readline/readline.h was not found." + exit 1 + fi + if test "$HAVE_HISTORY_H" != "1"; then + echo "** Cannot --enable-pcre2test-readline because readline/history.h was not found." + exit 1 + fi + if test -z "$LIBREADLINE"; then + echo "** Cannot --enable-pcre2test-readline because readline library was not found." + exit 1 + fi +fi + +# Handle valgrind support + +if test "$enable_valgrind" = "yes"; then + + + + + + + +if test "x$ac_cv_env_PKG_CONFIG_set" != "xset"; then + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}pkg-config", so it can be a program name with args. +set dummy ${ac_tool_prefix}pkg-config; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_path_PKG_CONFIG+:} false; then : + $as_echo_n "(cached) " >&6 +else + case $PKG_CONFIG in + [\\/]* | ?:[\\/]*) + ac_cv_path_PKG_CONFIG="$PKG_CONFIG" # Let the user override the test with a path. + ;; + *) + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_path_PKG_CONFIG="$as_dir/$ac_word$ac_exec_ext" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + + ;; +esac +fi +PKG_CONFIG=$ac_cv_path_PKG_CONFIG +if test -n "$PKG_CONFIG"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $PKG_CONFIG" >&5 +$as_echo "$PKG_CONFIG" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_path_PKG_CONFIG"; then + ac_pt_PKG_CONFIG=$PKG_CONFIG + # Extract the first word of "pkg-config", so it can be a program name with args. +set dummy pkg-config; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_path_ac_pt_PKG_CONFIG+:} false; then : + $as_echo_n "(cached) " >&6 +else + case $ac_pt_PKG_CONFIG in + [\\/]* | ?:[\\/]*) + ac_cv_path_ac_pt_PKG_CONFIG="$ac_pt_PKG_CONFIG" # Let the user override the test with a path. + ;; + *) + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_path_ac_pt_PKG_CONFIG="$as_dir/$ac_word$ac_exec_ext" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + + ;; +esac +fi +ac_pt_PKG_CONFIG=$ac_cv_path_ac_pt_PKG_CONFIG +if test -n "$ac_pt_PKG_CONFIG"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_pt_PKG_CONFIG" >&5 +$as_echo "$ac_pt_PKG_CONFIG" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_pt_PKG_CONFIG" = x; then + PKG_CONFIG="" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + PKG_CONFIG=$ac_pt_PKG_CONFIG + fi +else + PKG_CONFIG="$ac_cv_path_PKG_CONFIG" +fi + +fi +if test -n "$PKG_CONFIG"; then + _pkg_min_version=0.9.0 + { $as_echo "$as_me:${as_lineno-$LINENO}: checking pkg-config is at least version $_pkg_min_version" >&5 +$as_echo_n "checking pkg-config is at least version $_pkg_min_version... " >&6; } + if $PKG_CONFIG --atleast-pkgconfig-version $_pkg_min_version; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5 +$as_echo "yes" >&6; } + else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } + PKG_CONFIG="" + fi +fi + +pkg_failed=no +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for VALGRIND" >&5 +$as_echo_n "checking for VALGRIND... " >&6; } + +if test -n "$VALGRIND_CFLAGS"; then + pkg_cv_VALGRIND_CFLAGS="$VALGRIND_CFLAGS" + elif test -n "$PKG_CONFIG"; then + if test -n "$PKG_CONFIG" && \ + { { $as_echo "$as_me:${as_lineno-$LINENO}: \$PKG_CONFIG --exists --print-errors \"valgrind\""; } >&5 + ($PKG_CONFIG --exists --print-errors "valgrind") 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; }; then + pkg_cv_VALGRIND_CFLAGS=`$PKG_CONFIG --cflags "valgrind" 2>/dev/null` + test "x$?" != "x0" && pkg_failed=yes +else + pkg_failed=yes +fi + else + pkg_failed=untried +fi +if test -n "$VALGRIND_LIBS"; then + pkg_cv_VALGRIND_LIBS="$VALGRIND_LIBS" + elif test -n "$PKG_CONFIG"; then + if test -n "$PKG_CONFIG" && \ + { { $as_echo "$as_me:${as_lineno-$LINENO}: \$PKG_CONFIG --exists --print-errors \"valgrind\""; } >&5 + ($PKG_CONFIG --exists --print-errors "valgrind") 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; }; then + pkg_cv_VALGRIND_LIBS=`$PKG_CONFIG --libs "valgrind" 2>/dev/null` + test "x$?" != "x0" && pkg_failed=yes +else + pkg_failed=yes +fi + else + pkg_failed=untried +fi + + + +if test $pkg_failed = yes; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } + +if $PKG_CONFIG --atleast-pkgconfig-version 0.20; then + _pkg_short_errors_supported=yes +else + _pkg_short_errors_supported=no +fi + if test $_pkg_short_errors_supported = yes; then + VALGRIND_PKG_ERRORS=`$PKG_CONFIG --short-errors --print-errors --cflags --libs "valgrind" 2>&1` + else + VALGRIND_PKG_ERRORS=`$PKG_CONFIG --print-errors --cflags --libs "valgrind" 2>&1` + fi + # Put the nasty error message in config.log where it belongs + echo "$VALGRIND_PKG_ERRORS" >&5 + + as_fn_error $? "Package requirements (valgrind) were not met: + +$VALGRIND_PKG_ERRORS + +Consider adjusting the PKG_CONFIG_PATH environment variable if you +installed software in a non-standard prefix. + +Alternatively, you may set the environment variables VALGRIND_CFLAGS +and VALGRIND_LIBS to avoid the need to call pkg-config. +See the pkg-config man page for more details." "$LINENO" 5 +elif test $pkg_failed = untried; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } + { { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5 +$as_echo "$as_me: error: in \`$ac_pwd':" >&2;} +as_fn_error $? "The pkg-config script could not be found or is too old. Make sure it +is in your PATH or set the PKG_CONFIG environment variable to the full +path to pkg-config. + +Alternatively, you may set the environment variables VALGRIND_CFLAGS +and VALGRIND_LIBS to avoid the need to call pkg-config. +See the pkg-config man page for more details. + +To get pkg-config, see . +See \`config.log' for more details" "$LINENO" 5; } +else + VALGRIND_CFLAGS=$pkg_cv_VALGRIND_CFLAGS + VALGRIND_LIBS=$pkg_cv_VALGRIND_LIBS + { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5 +$as_echo "yes" >&6; } + +fi +fi + +# Handle code coverage reporting support +if test "$enable_coverage" = "yes"; then + if test "x$GCC" != "xyes"; then + as_fn_error $? "Code coverage reports can only be generated when using GCC" "$LINENO" 5 + fi + + # ccache is incompatible with gcov + # Extract the first word of "shtool", so it can be a program name with args. +set dummy shtool; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_path_SHTOOL+:} false; then : + $as_echo_n "(cached) " >&6 +else + case $SHTOOL in + [\\/]* | ?:[\\/]*) + ac_cv_path_SHTOOL="$SHTOOL" # Let the user override the test with a path. + ;; + *) + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_path_SHTOOL="$as_dir/$ac_word$ac_exec_ext" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + + test -z "$ac_cv_path_SHTOOL" && ac_cv_path_SHTOOL="false" + ;; +esac +fi +SHTOOL=$ac_cv_path_SHTOOL +if test -n "$SHTOOL"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $SHTOOL" >&5 +$as_echo "$SHTOOL" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + case `$SHTOOL path $CC` in + *ccache*) cc_ccache=yes;; + *) cc_ccache=no;; + esac + + if test "$cc_ccache" = "yes"; then + if test -z "$CCACHE_DISABLE" -o "$CCACHE_DISABLE" != "1"; then + as_fn_error $? "must export CCACHE_DISABLE=1 to disable ccache for code coverage" "$LINENO" 5 + fi + fi + + + # Extract the first word of "lcov", so it can be a program name with args. +set dummy lcov; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_path_LCOV+:} false; then : + $as_echo_n "(cached) " >&6 +else + case $LCOV in + [\\/]* | ?:[\\/]*) + ac_cv_path_LCOV="$LCOV" # Let the user override the test with a path. + ;; + *) + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_path_LCOV="$as_dir/$ac_word$ac_exec_ext" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + + test -z "$ac_cv_path_LCOV" && ac_cv_path_LCOV="false" + ;; +esac +fi +LCOV=$ac_cv_path_LCOV +if test -n "$LCOV"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $LCOV" >&5 +$as_echo "$LCOV" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + if test "x$LCOV" = "xfalse"; then + as_fn_error $? "lcov not found" "$LINENO" 5 + fi + + + # Extract the first word of "genhtml", so it can be a program name with args. +set dummy genhtml; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_path_GENHTML+:} false; then : + $as_echo_n "(cached) " >&6 +else + case $GENHTML in + [\\/]* | ?:[\\/]*) + ac_cv_path_GENHTML="$GENHTML" # Let the user override the test with a path. + ;; + *) + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_path_GENHTML="$as_dir/$ac_word$ac_exec_ext" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + + test -z "$ac_cv_path_GENHTML" && ac_cv_path_GENHTML="false" + ;; +esac +fi +GENHTML=$ac_cv_path_GENHTML +if test -n "$GENHTML"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $GENHTML" >&5 +$as_echo "$GENHTML" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + if test "x$GENHTML" = "xfalse"; then + as_fn_error $? "genhtml not found" "$LINENO" 5 + fi + + # Set flags needed for gcov + GCOV_CFLAGS="-O0 -ggdb3 -fprofile-arcs -ftest-coverage" + GCOV_CXXFLAGS="-O0 -ggdb3 -fprofile-arcs -ftest-coverage" + GCOV_LIBS="-lgcov" + + + +fi # enable_coverage + + if test "x$enable_coverage" = "xyes"; then + WITH_GCOV_TRUE= + WITH_GCOV_FALSE='#' +else + WITH_GCOV_TRUE='#' + WITH_GCOV_FALSE= +fi + + +# Produce these files, in addition to config.h. +ac_config_files="$ac_config_files Makefile libpcre2-8.pc libpcre2-16.pc libpcre2-32.pc libpcre2-posix.pc pcre2-config src/pcre2.h" + + +# Make the generated script files executable. +ac_config_commands="$ac_config_commands script-chmod" + + +# Make sure that pcre2_chartables.c is removed in case the method for +# creating it was changed by reconfiguration. +ac_config_commands="$ac_config_commands delete-old-chartables" + + +cat >confcache <<\_ACEOF +# This file is a shell script that caches the results of configure +# tests run on this system so they can be shared between configure +# scripts and configure runs, see configure's option --config-cache. +# It is not useful on other systems. If it contains results you don't +# want to keep, you may remove or edit it. +# +# config.status only pays attention to the cache file if you give it +# the --recheck option to rerun configure. +# +# `ac_cv_env_foo' variables (set or unset) will be overridden when +# loading this file, other *unset* `ac_cv_foo' will be assigned the +# following values. + +_ACEOF + +# The following way of writing the cache mishandles newlines in values, +# but we know of no workaround that is simple, portable, and efficient. +# So, we kill variables containing newlines. +# Ultrix sh set writes to stderr and can't be redirected directly, +# and sets the high bit in the cache file unless we assign to the vars. +( + for ac_var in `(set) 2>&1 | sed -n 's/^\([a-zA-Z_][a-zA-Z0-9_]*\)=.*/\1/p'`; do + eval ac_val=\$$ac_var + case $ac_val in #( + *${as_nl}*) + case $ac_var in #( + *_cv_*) { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: cache variable $ac_var contains a newline" >&5 +$as_echo "$as_me: WARNING: cache variable $ac_var contains a newline" >&2;} ;; + esac + case $ac_var in #( + _ | IFS | as_nl) ;; #( + BASH_ARGV | BASH_SOURCE) eval $ac_var= ;; #( + *) { eval $ac_var=; unset $ac_var;} ;; + esac ;; + esac + done + + (set) 2>&1 | + case $as_nl`(ac_space=' '; set) 2>&1` in #( + *${as_nl}ac_space=\ *) + # `set' does not quote correctly, so add quotes: double-quote + # substitution turns \\\\ into \\, and sed turns \\ into \. + sed -n \ + "s/'/'\\\\''/g; + s/^\\([_$as_cr_alnum]*_cv_[_$as_cr_alnum]*\\)=\\(.*\\)/\\1='\\2'/p" + ;; #( + *) + # `set' quotes correctly as required by POSIX, so do not add quotes. + sed -n "/^[_$as_cr_alnum]*_cv_[_$as_cr_alnum]*=/p" + ;; + esac | + sort +) | + sed ' + /^ac_cv_env_/b end + t clear + :clear + s/^\([^=]*\)=\(.*[{}].*\)$/test "${\1+set}" = set || &/ + t end + s/^\([^=]*\)=\(.*\)$/\1=${\1=\2}/ + :end' >>confcache +if diff "$cache_file" confcache >/dev/null 2>&1; then :; else + if test -w "$cache_file"; then + if test "x$cache_file" != "x/dev/null"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: updating cache $cache_file" >&5 +$as_echo "$as_me: updating cache $cache_file" >&6;} + if test ! -f "$cache_file" || test -h "$cache_file"; then + cat confcache >"$cache_file" + else + case $cache_file in #( + */* | ?:*) + mv -f confcache "$cache_file"$$ && + mv -f "$cache_file"$$ "$cache_file" ;; #( + *) + mv -f confcache "$cache_file" ;; + esac + fi + fi + else + { $as_echo "$as_me:${as_lineno-$LINENO}: not updating unwritable cache $cache_file" >&5 +$as_echo "$as_me: not updating unwritable cache $cache_file" >&6;} + fi +fi +rm -f confcache + +test "x$prefix" = xNONE && prefix=$ac_default_prefix +# Let make expand exec_prefix. +test "x$exec_prefix" = xNONE && exec_prefix='${prefix}' + +DEFS=-DHAVE_CONFIG_H + +ac_libobjs= +ac_ltlibobjs= +U= +for ac_i in : $LIBOBJS; do test "x$ac_i" = x: && continue + # 1. Remove the extension, and $U if already installed. + ac_script='s/\$U\././;s/\.o$//;s/\.obj$//' + ac_i=`$as_echo "$ac_i" | sed "$ac_script"` + # 2. Prepend LIBOBJDIR. When used with automake>=1.10 LIBOBJDIR + # will be set to the directory where LIBOBJS objects are built. + as_fn_append ac_libobjs " \${LIBOBJDIR}$ac_i\$U.$ac_objext" + as_fn_append ac_ltlibobjs " \${LIBOBJDIR}$ac_i"'$U.lo' +done +LIBOBJS=$ac_libobjs + +LTLIBOBJS=$ac_ltlibobjs + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking that generated files are newer than configure" >&5 +$as_echo_n "checking that generated files are newer than configure... " >&6; } + if test -n "$am_sleep_pid"; then + # Hide warnings about reused PIDs. + wait $am_sleep_pid 2>/dev/null + fi + { $as_echo "$as_me:${as_lineno-$LINENO}: result: done" >&5 +$as_echo "done" >&6; } + if test -n "$EXEEXT"; then + am__EXEEXT_TRUE= + am__EXEEXT_FALSE='#' +else + am__EXEEXT_TRUE='#' + am__EXEEXT_FALSE= +fi + +if test -z "${AMDEP_TRUE}" && test -z "${AMDEP_FALSE}"; then + as_fn_error $? "conditional \"AMDEP\" was never defined. +Usually this means the macro was only invoked conditionally." "$LINENO" 5 +fi +if test -z "${am__fastdepCC_TRUE}" && test -z "${am__fastdepCC_FALSE}"; then + as_fn_error $? "conditional \"am__fastdepCC\" was never defined. +Usually this means the macro was only invoked conditionally." "$LINENO" 5 +fi +if test -z "${am__fastdepCC_TRUE}" && test -z "${am__fastdepCC_FALSE}"; then + as_fn_error $? "conditional \"am__fastdepCC\" was never defined. +Usually this means the macro was only invoked conditionally." "$LINENO" 5 +fi +if test -z "${WITH_PCRE2_8_TRUE}" && test -z "${WITH_PCRE2_8_FALSE}"; then + as_fn_error $? "conditional \"WITH_PCRE2_8\" was never defined. +Usually this means the macro was only invoked conditionally." "$LINENO" 5 +fi +if test -z "${WITH_PCRE2_16_TRUE}" && test -z "${WITH_PCRE2_16_FALSE}"; then + as_fn_error $? "conditional \"WITH_PCRE2_16\" was never defined. +Usually this means the macro was only invoked conditionally." "$LINENO" 5 +fi +if test -z "${WITH_PCRE2_32_TRUE}" && test -z "${WITH_PCRE2_32_FALSE}"; then + as_fn_error $? "conditional \"WITH_PCRE2_32\" was never defined. +Usually this means the macro was only invoked conditionally." "$LINENO" 5 +fi +if test -z "${WITH_DEBUG_TRUE}" && test -z "${WITH_DEBUG_FALSE}"; then + as_fn_error $? "conditional \"WITH_DEBUG\" was never defined. +Usually this means the macro was only invoked conditionally." "$LINENO" 5 +fi +if test -z "${WITH_REBUILD_CHARTABLES_TRUE}" && test -z "${WITH_REBUILD_CHARTABLES_FALSE}"; then + as_fn_error $? "conditional \"WITH_REBUILD_CHARTABLES\" was never defined. +Usually this means the macro was only invoked conditionally." "$LINENO" 5 +fi +if test -z "${WITH_JIT_TRUE}" && test -z "${WITH_JIT_FALSE}"; then + as_fn_error $? "conditional \"WITH_JIT\" was never defined. +Usually this means the macro was only invoked conditionally." "$LINENO" 5 +fi +if test -z "${WITH_UNICODE_TRUE}" && test -z "${WITH_UNICODE_FALSE}"; then + as_fn_error $? "conditional \"WITH_UNICODE\" was never defined. +Usually this means the macro was only invoked conditionally." "$LINENO" 5 +fi +if test -z "${WITH_VALGRIND_TRUE}" && test -z "${WITH_VALGRIND_FALSE}"; then + as_fn_error $? "conditional \"WITH_VALGRIND\" was never defined. +Usually this means the macro was only invoked conditionally." "$LINENO" 5 +fi +if test -z "${WITH_GCOV_TRUE}" && test -z "${WITH_GCOV_FALSE}"; then + as_fn_error $? "conditional \"WITH_GCOV\" was never defined. +Usually this means the macro was only invoked conditionally." "$LINENO" 5 +fi + +: "${CONFIG_STATUS=./config.status}" +ac_write_fail=0 +ac_clean_files_save=$ac_clean_files +ac_clean_files="$ac_clean_files $CONFIG_STATUS" +{ $as_echo "$as_me:${as_lineno-$LINENO}: creating $CONFIG_STATUS" >&5 +$as_echo "$as_me: creating $CONFIG_STATUS" >&6;} +as_write_fail=0 +cat >$CONFIG_STATUS <<_ASEOF || as_write_fail=1 +#! $SHELL +# Generated by $as_me. +# Run this file to recreate the current configuration. +# Compiler output produced by configure, useful for debugging +# configure, is in config.log if it exists. + +debug=false +ac_cs_recheck=false +ac_cs_silent=false + +SHELL=\${CONFIG_SHELL-$SHELL} +export SHELL +_ASEOF +cat >>$CONFIG_STATUS <<\_ASEOF || as_write_fail=1 +## -------------------- ## +## M4sh Initialization. ## +## -------------------- ## + +# Be more Bourne compatible +DUALCASE=1; export DUALCASE # for MKS sh +if test -n "${ZSH_VERSION+set}" && (emulate sh) >/dev/null 2>&1; then : + emulate sh + NULLCMD=: + # Pre-4.2 versions of Zsh do word splitting on ${1+"$@"}, which + # is contrary to our usage. Disable this feature. + alias -g '${1+"$@"}'='"$@"' + setopt NO_GLOB_SUBST +else + case `(set -o) 2>/dev/null` in #( + *posix*) : + set -o posix ;; #( + *) : + ;; +esac +fi + + +as_nl=' +' +export as_nl +# Printing a long string crashes Solaris 7 /usr/bin/printf. +as_echo='\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\' +as_echo=$as_echo$as_echo$as_echo$as_echo$as_echo +as_echo=$as_echo$as_echo$as_echo$as_echo$as_echo$as_echo +# Prefer a ksh shell builtin over an external printf program on Solaris, +# but without wasting forks for bash or zsh. +if test -z "$BASH_VERSION$ZSH_VERSION" \ + && (test "X`print -r -- $as_echo`" = "X$as_echo") 2>/dev/null; then + as_echo='print -r --' + as_echo_n='print -rn --' +elif (test "X`printf %s $as_echo`" = "X$as_echo") 2>/dev/null; then + as_echo='printf %s\n' + as_echo_n='printf %s' +else + if test "X`(/usr/ucb/echo -n -n $as_echo) 2>/dev/null`" = "X-n $as_echo"; then + as_echo_body='eval /usr/ucb/echo -n "$1$as_nl"' + as_echo_n='/usr/ucb/echo -n' + else + as_echo_body='eval expr "X$1" : "X\\(.*\\)"' + as_echo_n_body='eval + arg=$1; + case $arg in #( + *"$as_nl"*) + expr "X$arg" : "X\\(.*\\)$as_nl"; + arg=`expr "X$arg" : ".*$as_nl\\(.*\\)"`;; + esac; + expr "X$arg" : "X\\(.*\\)" | tr -d "$as_nl" + ' + export as_echo_n_body + as_echo_n='sh -c $as_echo_n_body as_echo' + fi + export as_echo_body + as_echo='sh -c $as_echo_body as_echo' +fi + +# The user is always right. +if test "${PATH_SEPARATOR+set}" != set; then + PATH_SEPARATOR=: + (PATH='/bin;/bin'; FPATH=$PATH; sh -c :) >/dev/null 2>&1 && { + (PATH='/bin:/bin'; FPATH=$PATH; sh -c :) >/dev/null 2>&1 || + PATH_SEPARATOR=';' + } +fi + + +# IFS +# We need space, tab and new line, in precisely that order. Quoting is +# there to prevent editors from complaining about space-tab. +# (If _AS_PATH_WALK were called with IFS unset, it would disable word +# splitting by setting IFS to empty value.) +IFS=" "" $as_nl" + +# Find who we are. Look in the path if we contain no directory separator. +as_myself= +case $0 in #(( + *[\\/]* ) as_myself=$0 ;; + *) as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + test -r "$as_dir/$0" && as_myself=$as_dir/$0 && break + done +IFS=$as_save_IFS + + ;; +esac +# We did not find ourselves, most probably we were run as `sh COMMAND' +# in which case we are not to be found in the path. +if test "x$as_myself" = x; then + as_myself=$0 +fi +if test ! -f "$as_myself"; then + $as_echo "$as_myself: error: cannot find myself; rerun with an absolute file name" >&2 + exit 1 +fi + +# Unset variables that we do not need and which cause bugs (e.g. in +# pre-3.0 UWIN ksh). But do not cause bugs in bash 2.01; the "|| exit 1" +# suppresses any "Segmentation fault" message there. '((' could +# trigger a bug in pdksh 5.2.14. +for as_var in BASH_ENV ENV MAIL MAILPATH +do eval test x\${$as_var+set} = xset \ + && ( (unset $as_var) || exit 1) >/dev/null 2>&1 && unset $as_var || : +done +PS1='$ ' +PS2='> ' +PS4='+ ' + +# NLS nuisances. +LC_ALL=C +export LC_ALL +LANGUAGE=C +export LANGUAGE + +# CDPATH. +(unset CDPATH) >/dev/null 2>&1 && unset CDPATH + + +# as_fn_error STATUS ERROR [LINENO LOG_FD] +# ---------------------------------------- +# Output "`basename $0`: error: ERROR" to stderr. If LINENO and LOG_FD are +# provided, also output the error to LOG_FD, referencing LINENO. Then exit the +# script with STATUS, using 1 if that was 0. +as_fn_error () +{ + as_status=$1; test $as_status -eq 0 && as_status=1 + if test "$4"; then + as_lineno=${as_lineno-"$3"} as_lineno_stack=as_lineno_stack=$as_lineno_stack + $as_echo "$as_me:${as_lineno-$LINENO}: error: $2" >&$4 + fi + $as_echo "$as_me: error: $2" >&2 + as_fn_exit $as_status +} # as_fn_error + + +# as_fn_set_status STATUS +# ----------------------- +# Set $? to STATUS, without forking. +as_fn_set_status () +{ + return $1 +} # as_fn_set_status + +# as_fn_exit STATUS +# ----------------- +# Exit the shell with STATUS, even in a "trap 0" or "set -e" context. +as_fn_exit () +{ + set +e + as_fn_set_status $1 + exit $1 +} # as_fn_exit + +# as_fn_unset VAR +# --------------- +# Portably unset VAR. +as_fn_unset () +{ + { eval $1=; unset $1;} +} +as_unset=as_fn_unset +# as_fn_append VAR VALUE +# ---------------------- +# Append the text in VALUE to the end of the definition contained in VAR. Take +# advantage of any shell optimizations that allow amortized linear growth over +# repeated appends, instead of the typical quadratic growth present in naive +# implementations. +if (eval "as_var=1; as_var+=2; test x\$as_var = x12") 2>/dev/null; then : + eval 'as_fn_append () + { + eval $1+=\$2 + }' +else + as_fn_append () + { + eval $1=\$$1\$2 + } +fi # as_fn_append + +# as_fn_arith ARG... +# ------------------ +# Perform arithmetic evaluation on the ARGs, and store the result in the +# global $as_val. Take advantage of shells that can avoid forks. The arguments +# must be portable across $(()) and expr. +if (eval "test \$(( 1 + 1 )) = 2") 2>/dev/null; then : + eval 'as_fn_arith () + { + as_val=$(( $* )) + }' +else + as_fn_arith () + { + as_val=`expr "$@" || test $? -eq 1` + } +fi # as_fn_arith + + +if expr a : '\(a\)' >/dev/null 2>&1 && + test "X`expr 00001 : '.*\(...\)'`" = X001; then + as_expr=expr +else + as_expr=false +fi + +if (basename -- /) >/dev/null 2>&1 && test "X`basename -- / 2>&1`" = "X/"; then + as_basename=basename +else + as_basename=false +fi + +if (as_dir=`dirname -- /` && test "X$as_dir" = X/) >/dev/null 2>&1; then + as_dirname=dirname +else + as_dirname=false +fi + +as_me=`$as_basename -- "$0" || +$as_expr X/"$0" : '.*/\([^/][^/]*\)/*$' \| \ + X"$0" : 'X\(//\)$' \| \ + X"$0" : 'X\(/\)' \| . 2>/dev/null || +$as_echo X/"$0" | + sed '/^.*\/\([^/][^/]*\)\/*$/{ + s//\1/ + q + } + /^X\/\(\/\/\)$/{ + s//\1/ + q + } + /^X\/\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'` + +# Avoid depending upon Character Ranges. +as_cr_letters='abcdefghijklmnopqrstuvwxyz' +as_cr_LETTERS='ABCDEFGHIJKLMNOPQRSTUVWXYZ' +as_cr_Letters=$as_cr_letters$as_cr_LETTERS +as_cr_digits='0123456789' +as_cr_alnum=$as_cr_Letters$as_cr_digits + +ECHO_C= ECHO_N= ECHO_T= +case `echo -n x` in #((((( +-n*) + case `echo 'xy\c'` in + *c*) ECHO_T=' ';; # ECHO_T is single tab character. + xy) ECHO_C='\c';; + *) echo `echo ksh88 bug on AIX 6.1` > /dev/null + ECHO_T=' ';; + esac;; +*) + ECHO_N='-n';; +esac + +rm -f conf$$ conf$$.exe conf$$.file +if test -d conf$$.dir; then + rm -f conf$$.dir/conf$$.file +else + rm -f conf$$.dir + mkdir conf$$.dir 2>/dev/null +fi +if (echo >conf$$.file) 2>/dev/null; then + if ln -s conf$$.file conf$$ 2>/dev/null; then + as_ln_s='ln -s' + # ... but there are two gotchas: + # 1) On MSYS, both `ln -s file dir' and `ln file dir' fail. + # 2) DJGPP < 2.04 has no symlinks; `ln -s' creates a wrapper executable. + # In both cases, we have to default to `cp -pR'. + ln -s conf$$.file conf$$.dir 2>/dev/null && test ! -f conf$$.exe || + as_ln_s='cp -pR' + elif ln conf$$.file conf$$ 2>/dev/null; then + as_ln_s=ln + else + as_ln_s='cp -pR' + fi +else + as_ln_s='cp -pR' +fi +rm -f conf$$ conf$$.exe conf$$.dir/conf$$.file conf$$.file +rmdir conf$$.dir 2>/dev/null + + +# as_fn_mkdir_p +# ------------- +# Create "$as_dir" as a directory, including parents if necessary. +as_fn_mkdir_p () +{ + + case $as_dir in #( + -*) as_dir=./$as_dir;; + esac + test -d "$as_dir" || eval $as_mkdir_p || { + as_dirs= + while :; do + case $as_dir in #( + *\'*) as_qdir=`$as_echo "$as_dir" | sed "s/'/'\\\\\\\\''/g"`;; #'( + *) as_qdir=$as_dir;; + esac + as_dirs="'$as_qdir' $as_dirs" + as_dir=`$as_dirname -- "$as_dir" || +$as_expr X"$as_dir" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X"$as_dir" : 'X\(//\)[^/]' \| \ + X"$as_dir" : 'X\(//\)$' \| \ + X"$as_dir" : 'X\(/\)' \| . 2>/dev/null || +$as_echo X"$as_dir" | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ + s//\1/ + q + } + /^X\(\/\/\)[^/].*/{ + s//\1/ + q + } + /^X\(\/\/\)$/{ + s//\1/ + q + } + /^X\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'` + test -d "$as_dir" && break + done + test -z "$as_dirs" || eval "mkdir $as_dirs" + } || test -d "$as_dir" || as_fn_error $? "cannot create directory $as_dir" + + +} # as_fn_mkdir_p +if mkdir -p . 2>/dev/null; then + as_mkdir_p='mkdir -p "$as_dir"' +else + test -d ./-p && rmdir ./-p + as_mkdir_p=false +fi + + +# as_fn_executable_p FILE +# ----------------------- +# Test if FILE is an executable regular file. +as_fn_executable_p () +{ + test -f "$1" && test -x "$1" +} # as_fn_executable_p +as_test_x='test -x' +as_executable_p=as_fn_executable_p + +# Sed expression to map a string onto a valid CPP name. +as_tr_cpp="eval sed 'y%*$as_cr_letters%P$as_cr_LETTERS%;s%[^_$as_cr_alnum]%_%g'" + +# Sed expression to map a string onto a valid variable name. +as_tr_sh="eval sed 'y%*+%pp%;s%[^_$as_cr_alnum]%_%g'" + + +exec 6>&1 +## ----------------------------------- ## +## Main body of $CONFIG_STATUS script. ## +## ----------------------------------- ## +_ASEOF +test $as_write_fail = 0 && chmod +x $CONFIG_STATUS || ac_write_fail=1 + +cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1 +# Save the log message, to keep $0 and so on meaningful, and to +# report actual input values of CONFIG_FILES etc. instead of their +# values after options handling. +ac_log=" +This file was extended by PCRE2 $as_me 10.20, which was +generated by GNU Autoconf 2.69. Invocation command line was + + CONFIG_FILES = $CONFIG_FILES + CONFIG_HEADERS = $CONFIG_HEADERS + CONFIG_LINKS = $CONFIG_LINKS + CONFIG_COMMANDS = $CONFIG_COMMANDS + $ $0 $@ + +on `(hostname || uname -n) 2>/dev/null | sed 1q` +" + +_ACEOF + +case $ac_config_files in *" +"*) set x $ac_config_files; shift; ac_config_files=$*;; +esac + +case $ac_config_headers in *" +"*) set x $ac_config_headers; shift; ac_config_headers=$*;; +esac + + +cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1 +# Files that config.status was made for. +config_files="$ac_config_files" +config_headers="$ac_config_headers" +config_commands="$ac_config_commands" + +_ACEOF + +cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1 +ac_cs_usage="\ +\`$as_me' instantiates files and other configuration actions +from templates according to the current configuration. Unless the files +and actions are specified as TAGs, all are instantiated by default. + +Usage: $0 [OPTION]... [TAG]... + + -h, --help print this help, then exit + -V, --version print version number and configuration settings, then exit + --config print configuration, then exit + -q, --quiet, --silent + do not print progress messages + -d, --debug don't remove temporary files + --recheck update $as_me by reconfiguring in the same conditions + --file=FILE[:TEMPLATE] + instantiate the configuration file FILE + --header=FILE[:TEMPLATE] + instantiate the configuration header FILE + +Configuration files: +$config_files + +Configuration headers: +$config_headers + +Configuration commands: +$config_commands + +Report bugs to the package provider." + +_ACEOF +cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1 +ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`" +ac_cs_version="\\ +PCRE2 config.status 10.20 +configured by $0, generated by GNU Autoconf 2.69, + with options \\"\$ac_cs_config\\" + +Copyright (C) 2012 Free Software Foundation, Inc. +This config.status script is free software; the Free Software Foundation +gives unlimited permission to copy, distribute and modify it." + +ac_pwd='$ac_pwd' +srcdir='$srcdir' +INSTALL='$INSTALL' +MKDIR_P='$MKDIR_P' +AWK='$AWK' +test -n "\$AWK" || AWK=awk +_ACEOF + +cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1 +# The default lists apply if the user does not specify any file. +ac_need_defaults=: +while test $# != 0 +do + case $1 in + --*=?*) + ac_option=`expr "X$1" : 'X\([^=]*\)='` + ac_optarg=`expr "X$1" : 'X[^=]*=\(.*\)'` + ac_shift=: + ;; + --*=) + ac_option=`expr "X$1" : 'X\([^=]*\)='` + ac_optarg= + ac_shift=: + ;; + *) + ac_option=$1 + ac_optarg=$2 + ac_shift=shift + ;; + esac + + case $ac_option in + # Handling of the options. + -recheck | --recheck | --rechec | --reche | --rech | --rec | --re | --r) + ac_cs_recheck=: ;; + --version | --versio | --versi | --vers | --ver | --ve | --v | -V ) + $as_echo "$ac_cs_version"; exit ;; + --config | --confi | --conf | --con | --co | --c ) + $as_echo "$ac_cs_config"; exit ;; + --debug | --debu | --deb | --de | --d | -d ) + debug=: ;; + --file | --fil | --fi | --f ) + $ac_shift + case $ac_optarg in + *\'*) ac_optarg=`$as_echo "$ac_optarg" | sed "s/'/'\\\\\\\\''/g"` ;; + '') as_fn_error $? "missing file argument" ;; + esac + as_fn_append CONFIG_FILES " '$ac_optarg'" + ac_need_defaults=false;; + --header | --heade | --head | --hea ) + $ac_shift + case $ac_optarg in + *\'*) ac_optarg=`$as_echo "$ac_optarg" | sed "s/'/'\\\\\\\\''/g"` ;; + esac + as_fn_append CONFIG_HEADERS " '$ac_optarg'" + ac_need_defaults=false;; + --he | --h) + # Conflict between --help and --header + as_fn_error $? "ambiguous option: \`$1' +Try \`$0 --help' for more information.";; + --help | --hel | -h ) + $as_echo "$ac_cs_usage"; exit ;; + -q | -quiet | --quiet | --quie | --qui | --qu | --q \ + | -silent | --silent | --silen | --sile | --sil | --si | --s) + ac_cs_silent=: ;; + + # This is an error. + -*) as_fn_error $? "unrecognized option: \`$1' +Try \`$0 --help' for more information." ;; + + *) as_fn_append ac_config_targets " $1" + ac_need_defaults=false ;; + + esac + shift +done + +ac_configure_extra_args= + +if $ac_cs_silent; then + exec 6>/dev/null + ac_configure_extra_args="$ac_configure_extra_args --silent" +fi + +_ACEOF +cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1 +if \$ac_cs_recheck; then + set X $SHELL '$0' $ac_configure_args \$ac_configure_extra_args --no-create --no-recursion + shift + \$as_echo "running CONFIG_SHELL=$SHELL \$*" >&6 + CONFIG_SHELL='$SHELL' + export CONFIG_SHELL + exec "\$@" +fi + +_ACEOF +cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1 +exec 5>>config.log +{ + echo + sed 'h;s/./-/g;s/^.../## /;s/...$/ ##/;p;x;p;x' <<_ASBOX +## Running $as_me. ## +_ASBOX + $as_echo "$ac_log" +} >&5 + +_ACEOF +cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1 +# +# INIT-COMMANDS +# +AMDEP_TRUE="$AMDEP_TRUE" ac_aux_dir="$ac_aux_dir" + + +# The HP-UX ksh and POSIX shell print the target directory to stdout +# if CDPATH is set. +(unset CDPATH) >/dev/null 2>&1 && unset CDPATH + +sed_quote_subst='$sed_quote_subst' +double_quote_subst='$double_quote_subst' +delay_variable_subst='$delay_variable_subst' +AS='`$ECHO "$AS" | $SED "$delay_single_quote_subst"`' +DLLTOOL='`$ECHO "$DLLTOOL" | $SED "$delay_single_quote_subst"`' +OBJDUMP='`$ECHO "$OBJDUMP" | $SED "$delay_single_quote_subst"`' +macro_version='`$ECHO "$macro_version" | $SED "$delay_single_quote_subst"`' +macro_revision='`$ECHO "$macro_revision" | $SED "$delay_single_quote_subst"`' +enable_shared='`$ECHO "$enable_shared" | $SED "$delay_single_quote_subst"`' +enable_static='`$ECHO "$enable_static" | $SED "$delay_single_quote_subst"`' +pic_mode='`$ECHO "$pic_mode" | $SED "$delay_single_quote_subst"`' +enable_fast_install='`$ECHO "$enable_fast_install" | $SED "$delay_single_quote_subst"`' +shared_archive_member_spec='`$ECHO "$shared_archive_member_spec" | $SED "$delay_single_quote_subst"`' +SHELL='`$ECHO "$SHELL" | $SED "$delay_single_quote_subst"`' +ECHO='`$ECHO "$ECHO" | $SED "$delay_single_quote_subst"`' +PATH_SEPARATOR='`$ECHO "$PATH_SEPARATOR" | $SED "$delay_single_quote_subst"`' +host_alias='`$ECHO "$host_alias" | $SED "$delay_single_quote_subst"`' +host='`$ECHO "$host" | $SED "$delay_single_quote_subst"`' +host_os='`$ECHO "$host_os" | $SED "$delay_single_quote_subst"`' +build_alias='`$ECHO "$build_alias" | $SED "$delay_single_quote_subst"`' +build='`$ECHO "$build" | $SED "$delay_single_quote_subst"`' +build_os='`$ECHO "$build_os" | $SED "$delay_single_quote_subst"`' +SED='`$ECHO "$SED" | $SED "$delay_single_quote_subst"`' +Xsed='`$ECHO "$Xsed" | $SED "$delay_single_quote_subst"`' +GREP='`$ECHO "$GREP" | $SED "$delay_single_quote_subst"`' +EGREP='`$ECHO "$EGREP" | $SED "$delay_single_quote_subst"`' +FGREP='`$ECHO "$FGREP" | $SED "$delay_single_quote_subst"`' +LD='`$ECHO "$LD" | $SED "$delay_single_quote_subst"`' +NM='`$ECHO "$NM" | $SED "$delay_single_quote_subst"`' +LN_S='`$ECHO "$LN_S" | $SED "$delay_single_quote_subst"`' +max_cmd_len='`$ECHO "$max_cmd_len" | $SED "$delay_single_quote_subst"`' +ac_objext='`$ECHO "$ac_objext" | $SED "$delay_single_quote_subst"`' +exeext='`$ECHO "$exeext" | $SED "$delay_single_quote_subst"`' +lt_unset='`$ECHO "$lt_unset" | $SED "$delay_single_quote_subst"`' +lt_SP2NL='`$ECHO "$lt_SP2NL" | $SED "$delay_single_quote_subst"`' +lt_NL2SP='`$ECHO "$lt_NL2SP" | $SED "$delay_single_quote_subst"`' +lt_cv_to_host_file_cmd='`$ECHO "$lt_cv_to_host_file_cmd" | $SED "$delay_single_quote_subst"`' +lt_cv_to_tool_file_cmd='`$ECHO "$lt_cv_to_tool_file_cmd" | $SED "$delay_single_quote_subst"`' +reload_flag='`$ECHO "$reload_flag" | $SED "$delay_single_quote_subst"`' +reload_cmds='`$ECHO "$reload_cmds" | $SED "$delay_single_quote_subst"`' +deplibs_check_method='`$ECHO "$deplibs_check_method" | $SED "$delay_single_quote_subst"`' +file_magic_cmd='`$ECHO "$file_magic_cmd" | $SED "$delay_single_quote_subst"`' +file_magic_glob='`$ECHO "$file_magic_glob" | $SED "$delay_single_quote_subst"`' +want_nocaseglob='`$ECHO "$want_nocaseglob" | $SED "$delay_single_quote_subst"`' +sharedlib_from_linklib_cmd='`$ECHO "$sharedlib_from_linklib_cmd" | $SED "$delay_single_quote_subst"`' +AR='`$ECHO "$AR" | $SED "$delay_single_quote_subst"`' +AR_FLAGS='`$ECHO "$AR_FLAGS" | $SED "$delay_single_quote_subst"`' +archiver_list_spec='`$ECHO "$archiver_list_spec" | $SED "$delay_single_quote_subst"`' +STRIP='`$ECHO "$STRIP" | $SED "$delay_single_quote_subst"`' +RANLIB='`$ECHO "$RANLIB" | $SED "$delay_single_quote_subst"`' +old_postinstall_cmds='`$ECHO "$old_postinstall_cmds" | $SED "$delay_single_quote_subst"`' +old_postuninstall_cmds='`$ECHO "$old_postuninstall_cmds" | $SED "$delay_single_quote_subst"`' +old_archive_cmds='`$ECHO "$old_archive_cmds" | $SED "$delay_single_quote_subst"`' +lock_old_archive_extraction='`$ECHO "$lock_old_archive_extraction" | $SED "$delay_single_quote_subst"`' +CC='`$ECHO "$CC" | $SED "$delay_single_quote_subst"`' +CFLAGS='`$ECHO "$CFLAGS" | $SED "$delay_single_quote_subst"`' +compiler='`$ECHO "$compiler" | $SED "$delay_single_quote_subst"`' +GCC='`$ECHO "$GCC" | $SED "$delay_single_quote_subst"`' +lt_cv_sys_global_symbol_pipe='`$ECHO "$lt_cv_sys_global_symbol_pipe" | $SED "$delay_single_quote_subst"`' +lt_cv_sys_global_symbol_to_cdecl='`$ECHO "$lt_cv_sys_global_symbol_to_cdecl" | $SED "$delay_single_quote_subst"`' +lt_cv_sys_global_symbol_to_import='`$ECHO "$lt_cv_sys_global_symbol_to_import" | $SED "$delay_single_quote_subst"`' +lt_cv_sys_global_symbol_to_c_name_address='`$ECHO "$lt_cv_sys_global_symbol_to_c_name_address" | $SED "$delay_single_quote_subst"`' +lt_cv_sys_global_symbol_to_c_name_address_lib_prefix='`$ECHO "$lt_cv_sys_global_symbol_to_c_name_address_lib_prefix" | $SED "$delay_single_quote_subst"`' +lt_cv_nm_interface='`$ECHO "$lt_cv_nm_interface" | $SED "$delay_single_quote_subst"`' +nm_file_list_spec='`$ECHO "$nm_file_list_spec" | $SED "$delay_single_quote_subst"`' +lt_sysroot='`$ECHO "$lt_sysroot" | $SED "$delay_single_quote_subst"`' +lt_cv_truncate_bin='`$ECHO "$lt_cv_truncate_bin" | $SED "$delay_single_quote_subst"`' +objdir='`$ECHO "$objdir" | $SED "$delay_single_quote_subst"`' +MAGIC_CMD='`$ECHO "$MAGIC_CMD" | $SED "$delay_single_quote_subst"`' +lt_prog_compiler_no_builtin_flag='`$ECHO "$lt_prog_compiler_no_builtin_flag" | $SED "$delay_single_quote_subst"`' +lt_prog_compiler_pic='`$ECHO "$lt_prog_compiler_pic" | $SED "$delay_single_quote_subst"`' +lt_prog_compiler_wl='`$ECHO "$lt_prog_compiler_wl" | $SED "$delay_single_quote_subst"`' +lt_prog_compiler_static='`$ECHO "$lt_prog_compiler_static" | $SED "$delay_single_quote_subst"`' +lt_cv_prog_compiler_c_o='`$ECHO "$lt_cv_prog_compiler_c_o" | $SED "$delay_single_quote_subst"`' +need_locks='`$ECHO "$need_locks" | $SED "$delay_single_quote_subst"`' +MANIFEST_TOOL='`$ECHO "$MANIFEST_TOOL" | $SED "$delay_single_quote_subst"`' +DSYMUTIL='`$ECHO "$DSYMUTIL" | $SED "$delay_single_quote_subst"`' +NMEDIT='`$ECHO "$NMEDIT" | $SED "$delay_single_quote_subst"`' +LIPO='`$ECHO "$LIPO" | $SED "$delay_single_quote_subst"`' +OTOOL='`$ECHO "$OTOOL" | $SED "$delay_single_quote_subst"`' +OTOOL64='`$ECHO "$OTOOL64" | $SED "$delay_single_quote_subst"`' +libext='`$ECHO "$libext" | $SED "$delay_single_quote_subst"`' +shrext_cmds='`$ECHO "$shrext_cmds" | $SED "$delay_single_quote_subst"`' +extract_expsyms_cmds='`$ECHO "$extract_expsyms_cmds" | $SED "$delay_single_quote_subst"`' +archive_cmds_need_lc='`$ECHO "$archive_cmds_need_lc" | $SED "$delay_single_quote_subst"`' +enable_shared_with_static_runtimes='`$ECHO "$enable_shared_with_static_runtimes" | $SED "$delay_single_quote_subst"`' +export_dynamic_flag_spec='`$ECHO "$export_dynamic_flag_spec" | $SED "$delay_single_quote_subst"`' +whole_archive_flag_spec='`$ECHO "$whole_archive_flag_spec" | $SED "$delay_single_quote_subst"`' +compiler_needs_object='`$ECHO "$compiler_needs_object" | $SED "$delay_single_quote_subst"`' +old_archive_from_new_cmds='`$ECHO "$old_archive_from_new_cmds" | $SED "$delay_single_quote_subst"`' +old_archive_from_expsyms_cmds='`$ECHO "$old_archive_from_expsyms_cmds" | $SED "$delay_single_quote_subst"`' +archive_cmds='`$ECHO "$archive_cmds" | $SED "$delay_single_quote_subst"`' +archive_expsym_cmds='`$ECHO "$archive_expsym_cmds" | $SED "$delay_single_quote_subst"`' +module_cmds='`$ECHO "$module_cmds" | $SED "$delay_single_quote_subst"`' +module_expsym_cmds='`$ECHO "$module_expsym_cmds" | $SED "$delay_single_quote_subst"`' +with_gnu_ld='`$ECHO "$with_gnu_ld" | $SED "$delay_single_quote_subst"`' +allow_undefined_flag='`$ECHO "$allow_undefined_flag" | $SED "$delay_single_quote_subst"`' +no_undefined_flag='`$ECHO "$no_undefined_flag" | $SED "$delay_single_quote_subst"`' +hardcode_libdir_flag_spec='`$ECHO "$hardcode_libdir_flag_spec" | $SED "$delay_single_quote_subst"`' +hardcode_libdir_separator='`$ECHO "$hardcode_libdir_separator" | $SED "$delay_single_quote_subst"`' +hardcode_direct='`$ECHO "$hardcode_direct" | $SED "$delay_single_quote_subst"`' +hardcode_direct_absolute='`$ECHO "$hardcode_direct_absolute" | $SED "$delay_single_quote_subst"`' +hardcode_minus_L='`$ECHO "$hardcode_minus_L" | $SED "$delay_single_quote_subst"`' +hardcode_shlibpath_var='`$ECHO "$hardcode_shlibpath_var" | $SED "$delay_single_quote_subst"`' +hardcode_automatic='`$ECHO "$hardcode_automatic" | $SED "$delay_single_quote_subst"`' +inherit_rpath='`$ECHO "$inherit_rpath" | $SED "$delay_single_quote_subst"`' +link_all_deplibs='`$ECHO "$link_all_deplibs" | $SED "$delay_single_quote_subst"`' +always_export_symbols='`$ECHO "$always_export_symbols" | $SED "$delay_single_quote_subst"`' +export_symbols_cmds='`$ECHO "$export_symbols_cmds" | $SED "$delay_single_quote_subst"`' +exclude_expsyms='`$ECHO "$exclude_expsyms" | $SED "$delay_single_quote_subst"`' +include_expsyms='`$ECHO "$include_expsyms" | $SED "$delay_single_quote_subst"`' +prelink_cmds='`$ECHO "$prelink_cmds" | $SED "$delay_single_quote_subst"`' +postlink_cmds='`$ECHO "$postlink_cmds" | $SED "$delay_single_quote_subst"`' +file_list_spec='`$ECHO "$file_list_spec" | $SED "$delay_single_quote_subst"`' +variables_saved_for_relink='`$ECHO "$variables_saved_for_relink" | $SED "$delay_single_quote_subst"`' +need_lib_prefix='`$ECHO "$need_lib_prefix" | $SED "$delay_single_quote_subst"`' +need_version='`$ECHO "$need_version" | $SED "$delay_single_quote_subst"`' +version_type='`$ECHO "$version_type" | $SED "$delay_single_quote_subst"`' +runpath_var='`$ECHO "$runpath_var" | $SED "$delay_single_quote_subst"`' +shlibpath_var='`$ECHO "$shlibpath_var" | $SED "$delay_single_quote_subst"`' +shlibpath_overrides_runpath='`$ECHO "$shlibpath_overrides_runpath" | $SED "$delay_single_quote_subst"`' +libname_spec='`$ECHO "$libname_spec" | $SED "$delay_single_quote_subst"`' +library_names_spec='`$ECHO "$library_names_spec" | $SED "$delay_single_quote_subst"`' +soname_spec='`$ECHO "$soname_spec" | $SED "$delay_single_quote_subst"`' +install_override_mode='`$ECHO "$install_override_mode" | $SED "$delay_single_quote_subst"`' +postinstall_cmds='`$ECHO "$postinstall_cmds" | $SED "$delay_single_quote_subst"`' +postuninstall_cmds='`$ECHO "$postuninstall_cmds" | $SED "$delay_single_quote_subst"`' +finish_cmds='`$ECHO "$finish_cmds" | $SED "$delay_single_quote_subst"`' +finish_eval='`$ECHO "$finish_eval" | $SED "$delay_single_quote_subst"`' +hardcode_into_libs='`$ECHO "$hardcode_into_libs" | $SED "$delay_single_quote_subst"`' +sys_lib_search_path_spec='`$ECHO "$sys_lib_search_path_spec" | $SED "$delay_single_quote_subst"`' +configure_time_dlsearch_path='`$ECHO "$configure_time_dlsearch_path" | $SED "$delay_single_quote_subst"`' +configure_time_lt_sys_library_path='`$ECHO "$configure_time_lt_sys_library_path" | $SED "$delay_single_quote_subst"`' +hardcode_action='`$ECHO "$hardcode_action" | $SED "$delay_single_quote_subst"`' +enable_dlopen='`$ECHO "$enable_dlopen" | $SED "$delay_single_quote_subst"`' +enable_dlopen_self='`$ECHO "$enable_dlopen_self" | $SED "$delay_single_quote_subst"`' +enable_dlopen_self_static='`$ECHO "$enable_dlopen_self_static" | $SED "$delay_single_quote_subst"`' +old_striplib='`$ECHO "$old_striplib" | $SED "$delay_single_quote_subst"`' +striplib='`$ECHO "$striplib" | $SED "$delay_single_quote_subst"`' + +LTCC='$LTCC' +LTCFLAGS='$LTCFLAGS' +compiler='$compiler_DEFAULT' + +# A function that is used when there is no print builtin or printf. +func_fallback_echo () +{ + eval 'cat <<_LTECHO_EOF +\$1 +_LTECHO_EOF' +} + +# Quote evaled strings. +for var in AS \ +DLLTOOL \ +OBJDUMP \ +SHELL \ +ECHO \ +PATH_SEPARATOR \ +SED \ +GREP \ +EGREP \ +FGREP \ +LD \ +NM \ +LN_S \ +lt_SP2NL \ +lt_NL2SP \ +reload_flag \ +deplibs_check_method \ +file_magic_cmd \ +file_magic_glob \ +want_nocaseglob \ +sharedlib_from_linklib_cmd \ +AR \ +AR_FLAGS \ +archiver_list_spec \ +STRIP \ +RANLIB \ +CC \ +CFLAGS \ +compiler \ +lt_cv_sys_global_symbol_pipe \ +lt_cv_sys_global_symbol_to_cdecl \ +lt_cv_sys_global_symbol_to_import \ +lt_cv_sys_global_symbol_to_c_name_address \ +lt_cv_sys_global_symbol_to_c_name_address_lib_prefix \ +lt_cv_nm_interface \ +nm_file_list_spec \ +lt_cv_truncate_bin \ +lt_prog_compiler_no_builtin_flag \ +lt_prog_compiler_pic \ +lt_prog_compiler_wl \ +lt_prog_compiler_static \ +lt_cv_prog_compiler_c_o \ +need_locks \ +MANIFEST_TOOL \ +DSYMUTIL \ +NMEDIT \ +LIPO \ +OTOOL \ +OTOOL64 \ +shrext_cmds \ +export_dynamic_flag_spec \ +whole_archive_flag_spec \ +compiler_needs_object \ +with_gnu_ld \ +allow_undefined_flag \ +no_undefined_flag \ +hardcode_libdir_flag_spec \ +hardcode_libdir_separator \ +exclude_expsyms \ +include_expsyms \ +file_list_spec \ +variables_saved_for_relink \ +libname_spec \ +library_names_spec \ +soname_spec \ +install_override_mode \ +finish_eval \ +old_striplib \ +striplib; do + case \`eval \\\\\$ECHO \\\\""\\\\\$\$var"\\\\"\` in + *[\\\\\\\`\\"\\\$]*) + eval "lt_\$var=\\\\\\"\\\`\\\$ECHO \\"\\\$\$var\\" | \\\$SED \\"\\\$sed_quote_subst\\"\\\`\\\\\\"" ## exclude from sc_prohibit_nested_quotes + ;; + *) + eval "lt_\$var=\\\\\\"\\\$\$var\\\\\\"" + ;; + esac +done + +# Double-quote double-evaled strings. +for var in reload_cmds \ +old_postinstall_cmds \ +old_postuninstall_cmds \ +old_archive_cmds \ +extract_expsyms_cmds \ +old_archive_from_new_cmds \ +old_archive_from_expsyms_cmds \ +archive_cmds \ +archive_expsym_cmds \ +module_cmds \ +module_expsym_cmds \ +export_symbols_cmds \ +prelink_cmds \ +postlink_cmds \ +postinstall_cmds \ +postuninstall_cmds \ +finish_cmds \ +sys_lib_search_path_spec \ +configure_time_dlsearch_path \ +configure_time_lt_sys_library_path; do + case \`eval \\\\\$ECHO \\\\""\\\\\$\$var"\\\\"\` in + *[\\\\\\\`\\"\\\$]*) + eval "lt_\$var=\\\\\\"\\\`\\\$ECHO \\"\\\$\$var\\" | \\\$SED -e \\"\\\$double_quote_subst\\" -e \\"\\\$sed_quote_subst\\" -e \\"\\\$delay_variable_subst\\"\\\`\\\\\\"" ## exclude from sc_prohibit_nested_quotes + ;; + *) + eval "lt_\$var=\\\\\\"\\\$\$var\\\\\\"" + ;; + esac +done + +ac_aux_dir='$ac_aux_dir' + +# See if we are running on zsh, and set the options that allow our +# commands through without removal of \ escapes INIT. +if test -n "\${ZSH_VERSION+set}"; then + setopt NO_GLOB_SUBST +fi + + + PACKAGE='$PACKAGE' + VERSION='$VERSION' + RM='$RM' + ofile='$ofile' + + + + +_ACEOF + +cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1 + +# Handling of arguments. +for ac_config_target in $ac_config_targets +do + case $ac_config_target in + "src/config.h") CONFIG_HEADERS="$CONFIG_HEADERS src/config.h" ;; + "depfiles") CONFIG_COMMANDS="$CONFIG_COMMANDS depfiles" ;; + "libtool") CONFIG_COMMANDS="$CONFIG_COMMANDS libtool" ;; + "Makefile") CONFIG_FILES="$CONFIG_FILES Makefile" ;; + "libpcre2-8.pc") CONFIG_FILES="$CONFIG_FILES libpcre2-8.pc" ;; + "libpcre2-16.pc") CONFIG_FILES="$CONFIG_FILES libpcre2-16.pc" ;; + "libpcre2-32.pc") CONFIG_FILES="$CONFIG_FILES libpcre2-32.pc" ;; + "libpcre2-posix.pc") CONFIG_FILES="$CONFIG_FILES libpcre2-posix.pc" ;; + "pcre2-config") CONFIG_FILES="$CONFIG_FILES pcre2-config" ;; + "src/pcre2.h") CONFIG_FILES="$CONFIG_FILES src/pcre2.h" ;; + "script-chmod") CONFIG_COMMANDS="$CONFIG_COMMANDS script-chmod" ;; + "delete-old-chartables") CONFIG_COMMANDS="$CONFIG_COMMANDS delete-old-chartables" ;; + + *) as_fn_error $? "invalid argument: \`$ac_config_target'" "$LINENO" 5;; + esac +done + + +# If the user did not use the arguments to specify the items to instantiate, +# then the envvar interface is used. Set only those that are not. +# We use the long form for the default assignment because of an extremely +# bizarre bug on SunOS 4.1.3. +if $ac_need_defaults; then + test "${CONFIG_FILES+set}" = set || CONFIG_FILES=$config_files + test "${CONFIG_HEADERS+set}" = set || CONFIG_HEADERS=$config_headers + test "${CONFIG_COMMANDS+set}" = set || CONFIG_COMMANDS=$config_commands +fi + +# Have a temporary directory for convenience. Make it in the build tree +# simply because there is no reason against having it here, and in addition, +# creating and moving files from /tmp can sometimes cause problems. +# Hook for its removal unless debugging. +# Note that there is a small window in which the directory will not be cleaned: +# after its creation but before its name has been assigned to `$tmp'. +$debug || +{ + tmp= ac_tmp= + trap 'exit_status=$? + : "${ac_tmp:=$tmp}" + { test ! -d "$ac_tmp" || rm -fr "$ac_tmp"; } && exit $exit_status +' 0 + trap 'as_fn_exit 1' 1 2 13 15 +} +# Create a (secure) tmp directory for tmp files. + +{ + tmp=`(umask 077 && mktemp -d "./confXXXXXX") 2>/dev/null` && + test -d "$tmp" +} || +{ + tmp=./conf$$-$RANDOM + (umask 077 && mkdir "$tmp") +} || as_fn_error $? "cannot create a temporary directory in ." "$LINENO" 5 +ac_tmp=$tmp + +# Set up the scripts for CONFIG_FILES section. +# No need to generate them if there are no CONFIG_FILES. +# This happens for instance with `./config.status config.h'. +if test -n "$CONFIG_FILES"; then + + +ac_cr=`echo X | tr X '\015'` +# On cygwin, bash can eat \r inside `` if the user requested igncr. +# But we know of no other shell where ac_cr would be empty at this +# point, so we can use a bashism as a fallback. +if test "x$ac_cr" = x; then + eval ac_cr=\$\'\\r\' +fi +ac_cs_awk_cr=`$AWK 'BEGIN { print "a\rb" }' /dev/null` +if test "$ac_cs_awk_cr" = "a${ac_cr}b"; then + ac_cs_awk_cr='\\r' +else + ac_cs_awk_cr=$ac_cr +fi + +echo 'BEGIN {' >"$ac_tmp/subs1.awk" && +_ACEOF + + +{ + echo "cat >conf$$subs.awk <<_ACEOF" && + echo "$ac_subst_vars" | sed 's/.*/&!$&$ac_delim/' && + echo "_ACEOF" +} >conf$$subs.sh || + as_fn_error $? "could not make $CONFIG_STATUS" "$LINENO" 5 +ac_delim_num=`echo "$ac_subst_vars" | grep -c '^'` +ac_delim='%!_!# ' +for ac_last_try in false false false false false :; do + . ./conf$$subs.sh || + as_fn_error $? "could not make $CONFIG_STATUS" "$LINENO" 5 + + ac_delim_n=`sed -n "s/.*$ac_delim\$/X/p" conf$$subs.awk | grep -c X` + if test $ac_delim_n = $ac_delim_num; then + break + elif $ac_last_try; then + as_fn_error $? "could not make $CONFIG_STATUS" "$LINENO" 5 + else + ac_delim="$ac_delim!$ac_delim _$ac_delim!! " + fi +done +rm -f conf$$subs.sh + +cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1 +cat >>"\$ac_tmp/subs1.awk" <<\\_ACAWK && +_ACEOF +sed -n ' +h +s/^/S["/; s/!.*/"]=/ +p +g +s/^[^!]*!// +:repl +t repl +s/'"$ac_delim"'$// +t delim +:nl +h +s/\(.\{148\}\)..*/\1/ +t more1 +s/["\\]/\\&/g; s/^/"/; s/$/\\n"\\/ +p +n +b repl +:more1 +s/["\\]/\\&/g; s/^/"/; s/$/"\\/ +p +g +s/.\{148\}// +t nl +:delim +h +s/\(.\{148\}\)..*/\1/ +t more2 +s/["\\]/\\&/g; s/^/"/; s/$/"/ +p +b +:more2 +s/["\\]/\\&/g; s/^/"/; s/$/"\\/ +p +g +s/.\{148\}// +t delim +' >$CONFIG_STATUS || ac_write_fail=1 +rm -f conf$$subs.awk +cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1 +_ACAWK +cat >>"\$ac_tmp/subs1.awk" <<_ACAWK && + for (key in S) S_is_set[key] = 1 + FS = "" + +} +{ + line = $ 0 + nfields = split(line, field, "@") + substed = 0 + len = length(field[1]) + for (i = 2; i < nfields; i++) { + key = field[i] + keylen = length(key) + if (S_is_set[key]) { + value = S[key] + line = substr(line, 1, len) "" value "" substr(line, len + keylen + 3) + len += length(value) + length(field[++i]) + substed = 1 + } else + len += 1 + keylen + } + + print line +} + +_ACAWK +_ACEOF +cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1 +if sed "s/$ac_cr//" < /dev/null > /dev/null 2>&1; then + sed "s/$ac_cr\$//; s/$ac_cr/$ac_cs_awk_cr/g" +else + cat +fi < "$ac_tmp/subs1.awk" > "$ac_tmp/subs.awk" \ + || as_fn_error $? "could not setup config files machinery" "$LINENO" 5 +_ACEOF + +# VPATH may cause trouble with some makes, so we remove sole $(srcdir), +# ${srcdir} and @srcdir@ entries from VPATH if srcdir is ".", strip leading and +# trailing colons and then remove the whole line if VPATH becomes empty +# (actually we leave an empty line to preserve line numbers). +if test "x$srcdir" = x.; then + ac_vpsub='/^[ ]*VPATH[ ]*=[ ]*/{ +h +s/// +s/^/:/ +s/[ ]*$/:/ +s/:\$(srcdir):/:/g +s/:\${srcdir}:/:/g +s/:@srcdir@:/:/g +s/^:*// +s/:*$// +x +s/\(=[ ]*\).*/\1/ +G +s/\n// +s/^[^=]*=[ ]*$// +}' +fi + +cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1 +fi # test -n "$CONFIG_FILES" + +# Set up the scripts for CONFIG_HEADERS section. +# No need to generate them if there are no CONFIG_HEADERS. +# This happens for instance with `./config.status Makefile'. +if test -n "$CONFIG_HEADERS"; then +cat >"$ac_tmp/defines.awk" <<\_ACAWK || +BEGIN { +_ACEOF + +# Transform confdefs.h into an awk script `defines.awk', embedded as +# here-document in config.status, that substitutes the proper values into +# config.h.in to produce config.h. + +# Create a delimiter string that does not exist in confdefs.h, to ease +# handling of long lines. +ac_delim='%!_!# ' +for ac_last_try in false false :; do + ac_tt=`sed -n "/$ac_delim/p" confdefs.h` + if test -z "$ac_tt"; then + break + elif $ac_last_try; then + as_fn_error $? "could not make $CONFIG_HEADERS" "$LINENO" 5 + else + ac_delim="$ac_delim!$ac_delim _$ac_delim!! " + fi +done + +# For the awk script, D is an array of macro values keyed by name, +# likewise P contains macro parameters if any. Preserve backslash +# newline sequences. + +ac_word_re=[_$as_cr_Letters][_$as_cr_alnum]* +sed -n ' +s/.\{148\}/&'"$ac_delim"'/g +t rset +:rset +s/^[ ]*#[ ]*define[ ][ ]*/ / +t def +d +:def +s/\\$// +t bsnl +s/["\\]/\\&/g +s/^ \('"$ac_word_re"'\)\(([^()]*)\)[ ]*\(.*\)/P["\1"]="\2"\ +D["\1"]=" \3"/p +s/^ \('"$ac_word_re"'\)[ ]*\(.*\)/D["\1"]=" \2"/p +d +:bsnl +s/["\\]/\\&/g +s/^ \('"$ac_word_re"'\)\(([^()]*)\)[ ]*\(.*\)/P["\1"]="\2"\ +D["\1"]=" \3\\\\\\n"\\/p +t cont +s/^ \('"$ac_word_re"'\)[ ]*\(.*\)/D["\1"]=" \2\\\\\\n"\\/p +t cont +d +:cont +n +s/.\{148\}/&'"$ac_delim"'/g +t clear +:clear +s/\\$// +t bsnlc +s/["\\]/\\&/g; s/^/"/; s/$/"/p +d +:bsnlc +s/["\\]/\\&/g; s/^/"/; s/$/\\\\\\n"\\/p +b cont +' >$CONFIG_STATUS || ac_write_fail=1 + +cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1 + for (key in D) D_is_set[key] = 1 + FS = "" +} +/^[\t ]*#[\t ]*(define|undef)[\t ]+$ac_word_re([\t (]|\$)/ { + line = \$ 0 + split(line, arg, " ") + if (arg[1] == "#") { + defundef = arg[2] + mac1 = arg[3] + } else { + defundef = substr(arg[1], 2) + mac1 = arg[2] + } + split(mac1, mac2, "(") #) + macro = mac2[1] + prefix = substr(line, 1, index(line, defundef) - 1) + if (D_is_set[macro]) { + # Preserve the white space surrounding the "#". + print prefix "define", macro P[macro] D[macro] + next + } else { + # Replace #undef with comments. This is necessary, for example, + # in the case of _POSIX_SOURCE, which is predefined and required + # on some systems where configure will not decide to define it. + if (defundef == "undef") { + print "/*", prefix defundef, macro, "*/" + next + } + } +} +{ print } +_ACAWK +_ACEOF +cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1 + as_fn_error $? "could not setup config headers machinery" "$LINENO" 5 +fi # test -n "$CONFIG_HEADERS" + + +eval set X " :F $CONFIG_FILES :H $CONFIG_HEADERS :C $CONFIG_COMMANDS" +shift +for ac_tag +do + case $ac_tag in + :[FHLC]) ac_mode=$ac_tag; continue;; + esac + case $ac_mode$ac_tag in + :[FHL]*:*);; + :L* | :C*:*) as_fn_error $? "invalid tag \`$ac_tag'" "$LINENO" 5;; + :[FH]-) ac_tag=-:-;; + :[FH]*) ac_tag=$ac_tag:$ac_tag.in;; + esac + ac_save_IFS=$IFS + IFS=: + set x $ac_tag + IFS=$ac_save_IFS + shift + ac_file=$1 + shift + + case $ac_mode in + :L) ac_source=$1;; + :[FH]) + ac_file_inputs= + for ac_f + do + case $ac_f in + -) ac_f="$ac_tmp/stdin";; + *) # Look for the file first in the build tree, then in the source tree + # (if the path is not absolute). The absolute path cannot be DOS-style, + # because $ac_f cannot contain `:'. + test -f "$ac_f" || + case $ac_f in + [\\/$]*) false;; + *) test -f "$srcdir/$ac_f" && ac_f="$srcdir/$ac_f";; + esac || + as_fn_error 1 "cannot find input file: \`$ac_f'" "$LINENO" 5;; + esac + case $ac_f in *\'*) ac_f=`$as_echo "$ac_f" | sed "s/'/'\\\\\\\\''/g"`;; esac + as_fn_append ac_file_inputs " '$ac_f'" + done + + # Let's still pretend it is `configure' which instantiates (i.e., don't + # use $as_me), people would be surprised to read: + # /* config.h. Generated by config.status. */ + configure_input='Generated from '` + $as_echo "$*" | sed 's|^[^:]*/||;s|:[^:]*/|, |g' + `' by configure.' + if test x"$ac_file" != x-; then + configure_input="$ac_file. $configure_input" + { $as_echo "$as_me:${as_lineno-$LINENO}: creating $ac_file" >&5 +$as_echo "$as_me: creating $ac_file" >&6;} + fi + # Neutralize special characters interpreted by sed in replacement strings. + case $configure_input in #( + *\&* | *\|* | *\\* ) + ac_sed_conf_input=`$as_echo "$configure_input" | + sed 's/[\\\\&|]/\\\\&/g'`;; #( + *) ac_sed_conf_input=$configure_input;; + esac + + case $ac_tag in + *:-:* | *:-) cat >"$ac_tmp/stdin" \ + || as_fn_error $? "could not create $ac_file" "$LINENO" 5 ;; + esac + ;; + esac + + ac_dir=`$as_dirname -- "$ac_file" || +$as_expr X"$ac_file" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X"$ac_file" : 'X\(//\)[^/]' \| \ + X"$ac_file" : 'X\(//\)$' \| \ + X"$ac_file" : 'X\(/\)' \| . 2>/dev/null || +$as_echo X"$ac_file" | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ + s//\1/ + q + } + /^X\(\/\/\)[^/].*/{ + s//\1/ + q + } + /^X\(\/\/\)$/{ + s//\1/ + q + } + /^X\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'` + as_dir="$ac_dir"; as_fn_mkdir_p + ac_builddir=. + +case "$ac_dir" in +.) ac_dir_suffix= ac_top_builddir_sub=. ac_top_build_prefix= ;; +*) + ac_dir_suffix=/`$as_echo "$ac_dir" | sed 's|^\.[\\/]||'` + # A ".." for each directory in $ac_dir_suffix. + ac_top_builddir_sub=`$as_echo "$ac_dir_suffix" | sed 's|/[^\\/]*|/..|g;s|/||'` + case $ac_top_builddir_sub in + "") ac_top_builddir_sub=. ac_top_build_prefix= ;; + *) ac_top_build_prefix=$ac_top_builddir_sub/ ;; + esac ;; +esac +ac_abs_top_builddir=$ac_pwd +ac_abs_builddir=$ac_pwd$ac_dir_suffix +# for backward compatibility: +ac_top_builddir=$ac_top_build_prefix + +case $srcdir in + .) # We are building in place. + ac_srcdir=. + ac_top_srcdir=$ac_top_builddir_sub + ac_abs_top_srcdir=$ac_pwd ;; + [\\/]* | ?:[\\/]* ) # Absolute name. + ac_srcdir=$srcdir$ac_dir_suffix; + ac_top_srcdir=$srcdir + ac_abs_top_srcdir=$srcdir ;; + *) # Relative name. + ac_srcdir=$ac_top_build_prefix$srcdir$ac_dir_suffix + ac_top_srcdir=$ac_top_build_prefix$srcdir + ac_abs_top_srcdir=$ac_pwd/$srcdir ;; +esac +ac_abs_srcdir=$ac_abs_top_srcdir$ac_dir_suffix + + + case $ac_mode in + :F) + # + # CONFIG_FILE + # + + case $INSTALL in + [\\/$]* | ?:[\\/]* ) ac_INSTALL=$INSTALL ;; + *) ac_INSTALL=$ac_top_build_prefix$INSTALL ;; + esac + ac_MKDIR_P=$MKDIR_P + case $MKDIR_P in + [\\/$]* | ?:[\\/]* ) ;; + */*) ac_MKDIR_P=$ac_top_build_prefix$MKDIR_P ;; + esac +_ACEOF + +cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1 +# If the template does not know about datarootdir, expand it. +# FIXME: This hack should be removed a few years after 2.60. +ac_datarootdir_hack=; ac_datarootdir_seen= +ac_sed_dataroot=' +/datarootdir/ { + p + q +} +/@datadir@/p +/@docdir@/p +/@infodir@/p +/@localedir@/p +/@mandir@/p' +case `eval "sed -n \"\$ac_sed_dataroot\" $ac_file_inputs"` in +*datarootdir*) ac_datarootdir_seen=yes;; +*@datadir@*|*@docdir@*|*@infodir@*|*@localedir@*|*@mandir@*) + { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $ac_file_inputs seems to ignore the --datarootdir setting" >&5 +$as_echo "$as_me: WARNING: $ac_file_inputs seems to ignore the --datarootdir setting" >&2;} +_ACEOF +cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1 + ac_datarootdir_hack=' + s&@datadir@&$datadir&g + s&@docdir@&$docdir&g + s&@infodir@&$infodir&g + s&@localedir@&$localedir&g + s&@mandir@&$mandir&g + s&\\\${datarootdir}&$datarootdir&g' ;; +esac +_ACEOF + +# Neutralize VPATH when `$srcdir' = `.'. +# Shell code in configure.ac might set extrasub. +# FIXME: do we really want to maintain this feature? +cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1 +ac_sed_extra="$ac_vpsub +$extrasub +_ACEOF +cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1 +:t +/@[a-zA-Z_][a-zA-Z_0-9]*@/!b +s|@configure_input@|$ac_sed_conf_input|;t t +s&@top_builddir@&$ac_top_builddir_sub&;t t +s&@top_build_prefix@&$ac_top_build_prefix&;t t +s&@srcdir@&$ac_srcdir&;t t +s&@abs_srcdir@&$ac_abs_srcdir&;t t +s&@top_srcdir@&$ac_top_srcdir&;t t +s&@abs_top_srcdir@&$ac_abs_top_srcdir&;t t +s&@builddir@&$ac_builddir&;t t +s&@abs_builddir@&$ac_abs_builddir&;t t +s&@abs_top_builddir@&$ac_abs_top_builddir&;t t +s&@INSTALL@&$ac_INSTALL&;t t +s&@MKDIR_P@&$ac_MKDIR_P&;t t +$ac_datarootdir_hack +" +eval sed \"\$ac_sed_extra\" "$ac_file_inputs" | $AWK -f "$ac_tmp/subs.awk" \ + >$ac_tmp/out || as_fn_error $? "could not create $ac_file" "$LINENO" 5 + +test -z "$ac_datarootdir_hack$ac_datarootdir_seen" && + { ac_out=`sed -n '/\${datarootdir}/p' "$ac_tmp/out"`; test -n "$ac_out"; } && + { ac_out=`sed -n '/^[ ]*datarootdir[ ]*:*=/p' \ + "$ac_tmp/out"`; test -z "$ac_out"; } && + { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $ac_file contains a reference to the variable \`datarootdir' +which seems to be undefined. Please make sure it is defined" >&5 +$as_echo "$as_me: WARNING: $ac_file contains a reference to the variable \`datarootdir' +which seems to be undefined. Please make sure it is defined" >&2;} + + rm -f "$ac_tmp/stdin" + case $ac_file in + -) cat "$ac_tmp/out" && rm -f "$ac_tmp/out";; + *) rm -f "$ac_file" && mv "$ac_tmp/out" "$ac_file";; + esac \ + || as_fn_error $? "could not create $ac_file" "$LINENO" 5 + ;; + :H) + # + # CONFIG_HEADER + # + if test x"$ac_file" != x-; then + { + $as_echo "/* $configure_input */" \ + && eval '$AWK -f "$ac_tmp/defines.awk"' "$ac_file_inputs" + } >"$ac_tmp/config.h" \ + || as_fn_error $? "could not create $ac_file" "$LINENO" 5 + if diff "$ac_file" "$ac_tmp/config.h" >/dev/null 2>&1; then + { $as_echo "$as_me:${as_lineno-$LINENO}: $ac_file is unchanged" >&5 +$as_echo "$as_me: $ac_file is unchanged" >&6;} + else + rm -f "$ac_file" + mv "$ac_tmp/config.h" "$ac_file" \ + || as_fn_error $? "could not create $ac_file" "$LINENO" 5 + fi + else + $as_echo "/* $configure_input */" \ + && eval '$AWK -f "$ac_tmp/defines.awk"' "$ac_file_inputs" \ + || as_fn_error $? "could not create -" "$LINENO" 5 + fi +# Compute "$ac_file"'s index in $config_headers. +_am_arg="$ac_file" +_am_stamp_count=1 +for _am_header in $config_headers :; do + case $_am_header in + $_am_arg | $_am_arg:* ) + break ;; + * ) + _am_stamp_count=`expr $_am_stamp_count + 1` ;; + esac +done +echo "timestamp for $_am_arg" >`$as_dirname -- "$_am_arg" || +$as_expr X"$_am_arg" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X"$_am_arg" : 'X\(//\)[^/]' \| \ + X"$_am_arg" : 'X\(//\)$' \| \ + X"$_am_arg" : 'X\(/\)' \| . 2>/dev/null || +$as_echo X"$_am_arg" | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ + s//\1/ + q + } + /^X\(\/\/\)[^/].*/{ + s//\1/ + q + } + /^X\(\/\/\)$/{ + s//\1/ + q + } + /^X\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'`/stamp-h$_am_stamp_count + ;; + + :C) { $as_echo "$as_me:${as_lineno-$LINENO}: executing $ac_file commands" >&5 +$as_echo "$as_me: executing $ac_file commands" >&6;} + ;; + esac + + + case $ac_file$ac_mode in + "depfiles":C) test x"$AMDEP_TRUE" != x"" || { + # Older Autoconf quotes --file arguments for eval, but not when files + # are listed without --file. Let's play safe and only enable the eval + # if we detect the quoting. + case $CONFIG_FILES in + *\'*) eval set x "$CONFIG_FILES" ;; + *) set x $CONFIG_FILES ;; + esac + shift + for mf + do + # Strip MF so we end up with the name of the file. + mf=`echo "$mf" | sed -e 's/:.*$//'` + # Check whether this is an Automake generated Makefile or not. + # We used to match only the files named 'Makefile.in', but + # some people rename them; so instead we look at the file content. + # Grep'ing the first line is not enough: some people post-process + # each Makefile.in and add a new line on top of each file to say so. + # Grep'ing the whole file is not good either: AIX grep has a line + # limit of 2048, but all sed's we know have understand at least 4000. + if sed -n 's,^#.*generated by automake.*,X,p' "$mf" | grep X >/dev/null 2>&1; then + dirpart=`$as_dirname -- "$mf" || +$as_expr X"$mf" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X"$mf" : 'X\(//\)[^/]' \| \ + X"$mf" : 'X\(//\)$' \| \ + X"$mf" : 'X\(/\)' \| . 2>/dev/null || +$as_echo X"$mf" | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ + s//\1/ + q + } + /^X\(\/\/\)[^/].*/{ + s//\1/ + q + } + /^X\(\/\/\)$/{ + s//\1/ + q + } + /^X\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'` + else + continue + fi + # Extract the definition of DEPDIR, am__include, and am__quote + # from the Makefile without running 'make'. + DEPDIR=`sed -n 's/^DEPDIR = //p' < "$mf"` + test -z "$DEPDIR" && continue + am__include=`sed -n 's/^am__include = //p' < "$mf"` + test -z "$am__include" && continue + am__quote=`sed -n 's/^am__quote = //p' < "$mf"` + # Find all dependency output files, they are included files with + # $(DEPDIR) in their names. We invoke sed twice because it is the + # simplest approach to changing $(DEPDIR) to its actual value in the + # expansion. + for file in `sed -n " + s/^$am__include $am__quote\(.*(DEPDIR).*\)$am__quote"'$/\1/p' <"$mf" | \ + sed -e 's/\$(DEPDIR)/'"$DEPDIR"'/g'`; do + # Make sure the directory exists. + test -f "$dirpart/$file" && continue + fdir=`$as_dirname -- "$file" || +$as_expr X"$file" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X"$file" : 'X\(//\)[^/]' \| \ + X"$file" : 'X\(//\)$' \| \ + X"$file" : 'X\(/\)' \| . 2>/dev/null || +$as_echo X"$file" | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ + s//\1/ + q + } + /^X\(\/\/\)[^/].*/{ + s//\1/ + q + } + /^X\(\/\/\)$/{ + s//\1/ + q + } + /^X\(\/\).*/{ + s//\1/ + q + } + s/.*/./; q'` + as_dir=$dirpart/$fdir; as_fn_mkdir_p + # echo "creating $dirpart/$file" + echo '# dummy' > "$dirpart/$file" + done + done +} + ;; + "libtool":C) + + # See if we are running on zsh, and set the options that allow our + # commands through without removal of \ escapes. + if test -n "${ZSH_VERSION+set}"; then + setopt NO_GLOB_SUBST + fi + + cfgfile=${ofile}T + trap "$RM \"$cfgfile\"; exit 1" 1 2 15 + $RM "$cfgfile" + + cat <<_LT_EOF >> "$cfgfile" +#! $SHELL +# Generated automatically by $as_me ($PACKAGE) $VERSION +# Libtool was configured on host `(hostname || uname -n) 2>/dev/null | sed 1q`: +# NOTE: Changes made to this file will be lost: look at ltmain.sh. + +# Provide generalized library-building support services. +# Written by Gordon Matzigkeit, 1996 + +# Copyright (C) 2014 Free Software Foundation, Inc. +# This is free software; see the source for copying conditions. There is NO +# warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + +# GNU Libtool is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of of the License, or +# (at your option) any later version. +# +# As a special exception to the GNU General Public License, if you +# distribute this file as part of a program or library that is built +# using GNU Libtool, you may include this file under the same +# distribution terms that you use for the rest of that program. +# +# GNU Libtool is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see . + + +# The names of the tagged configurations supported by this script. +available_tags='' + +# Configured defaults for sys_lib_dlsearch_path munging. +: \${LT_SYS_LIBRARY_PATH="$configure_time_lt_sys_library_path"} + +# ### BEGIN LIBTOOL CONFIG + +# Assembler program. +AS=$lt_AS + +# DLL creation program. +DLLTOOL=$lt_DLLTOOL + +# Object dumper program. +OBJDUMP=$lt_OBJDUMP + +# Which release of libtool.m4 was used? +macro_version=$macro_version +macro_revision=$macro_revision + +# Whether or not to build shared libraries. +build_libtool_libs=$enable_shared + +# Whether or not to build static libraries. +build_old_libs=$enable_static + +# What type of objects to build. +pic_mode=$pic_mode + +# Whether or not to optimize for fast installation. +fast_install=$enable_fast_install + +# Shared archive member basename,for filename based shared library versioning on AIX. +shared_archive_member_spec=$shared_archive_member_spec + +# Shell to use when invoking shell scripts. +SHELL=$lt_SHELL + +# An echo program that protects backslashes. +ECHO=$lt_ECHO + +# The PATH separator for the build system. +PATH_SEPARATOR=$lt_PATH_SEPARATOR + +# The host system. +host_alias=$host_alias +host=$host +host_os=$host_os + +# The build system. +build_alias=$build_alias +build=$build +build_os=$build_os + +# A sed program that does not truncate output. +SED=$lt_SED + +# Sed that helps us avoid accidentally triggering echo(1) options like -n. +Xsed="\$SED -e 1s/^X//" + +# A grep program that handles long lines. +GREP=$lt_GREP + +# An ERE matcher. +EGREP=$lt_EGREP + +# A literal string matcher. +FGREP=$lt_FGREP + +# A BSD- or MS-compatible name lister. +NM=$lt_NM + +# Whether we need soft or hard links. +LN_S=$lt_LN_S + +# What is the maximum length of a command? +max_cmd_len=$max_cmd_len + +# Object file suffix (normally "o"). +objext=$ac_objext + +# Executable file suffix (normally ""). +exeext=$exeext + +# whether the shell understands "unset". +lt_unset=$lt_unset + +# turn spaces into newlines. +SP2NL=$lt_lt_SP2NL + +# turn newlines into spaces. +NL2SP=$lt_lt_NL2SP + +# convert \$build file names to \$host format. +to_host_file_cmd=$lt_cv_to_host_file_cmd + +# convert \$build files to toolchain format. +to_tool_file_cmd=$lt_cv_to_tool_file_cmd + +# Method to check whether dependent libraries are shared objects. +deplibs_check_method=$lt_deplibs_check_method + +# Command to use when deplibs_check_method = "file_magic". +file_magic_cmd=$lt_file_magic_cmd + +# How to find potential files when deplibs_check_method = "file_magic". +file_magic_glob=$lt_file_magic_glob + +# Find potential files using nocaseglob when deplibs_check_method = "file_magic". +want_nocaseglob=$lt_want_nocaseglob + +# Command to associate shared and link libraries. +sharedlib_from_linklib_cmd=$lt_sharedlib_from_linklib_cmd + +# The archiver. +AR=$lt_AR + +# Flags to create an archive. +AR_FLAGS=$lt_AR_FLAGS + +# How to feed a file listing to the archiver. +archiver_list_spec=$lt_archiver_list_spec + +# A symbol stripping program. +STRIP=$lt_STRIP + +# Commands used to install an old-style archive. +RANLIB=$lt_RANLIB +old_postinstall_cmds=$lt_old_postinstall_cmds +old_postuninstall_cmds=$lt_old_postuninstall_cmds + +# Whether to use a lock for old archive extraction. +lock_old_archive_extraction=$lock_old_archive_extraction + +# A C compiler. +LTCC=$lt_CC + +# LTCC compiler flags. +LTCFLAGS=$lt_CFLAGS + +# Take the output of nm and produce a listing of raw symbols and C names. +global_symbol_pipe=$lt_lt_cv_sys_global_symbol_pipe + +# Transform the output of nm in a proper C declaration. +global_symbol_to_cdecl=$lt_lt_cv_sys_global_symbol_to_cdecl + +# Transform the output of nm into a list of symbols to manually relocate. +global_symbol_to_import=$lt_lt_cv_sys_global_symbol_to_import + +# Transform the output of nm in a C name address pair. +global_symbol_to_c_name_address=$lt_lt_cv_sys_global_symbol_to_c_name_address + +# Transform the output of nm in a C name address pair when lib prefix is needed. +global_symbol_to_c_name_address_lib_prefix=$lt_lt_cv_sys_global_symbol_to_c_name_address_lib_prefix + +# The name lister interface. +nm_interface=$lt_lt_cv_nm_interface + +# Specify filename containing input files for \$NM. +nm_file_list_spec=$lt_nm_file_list_spec + +# The root where to search for dependent libraries,and where our libraries should be installed. +lt_sysroot=$lt_sysroot + +# Command to truncate a binary pipe. +lt_truncate_bin=$lt_lt_cv_truncate_bin + +# The name of the directory that contains temporary libtool files. +objdir=$objdir + +# Used to examine libraries when file_magic_cmd begins with "file". +MAGIC_CMD=$MAGIC_CMD + +# Must we lock files when doing compilation? +need_locks=$lt_need_locks + +# Manifest tool. +MANIFEST_TOOL=$lt_MANIFEST_TOOL + +# Tool to manipulate archived DWARF debug symbol files on Mac OS X. +DSYMUTIL=$lt_DSYMUTIL + +# Tool to change global to local symbols on Mac OS X. +NMEDIT=$lt_NMEDIT + +# Tool to manipulate fat objects and archives on Mac OS X. +LIPO=$lt_LIPO + +# ldd/readelf like tool for Mach-O binaries on Mac OS X. +OTOOL=$lt_OTOOL + +# ldd/readelf like tool for 64 bit Mach-O binaries on Mac OS X 10.4. +OTOOL64=$lt_OTOOL64 + +# Old archive suffix (normally "a"). +libext=$libext + +# Shared library suffix (normally ".so"). +shrext_cmds=$lt_shrext_cmds + +# The commands to extract the exported symbol list from a shared archive. +extract_expsyms_cmds=$lt_extract_expsyms_cmds + +# Variables whose values should be saved in libtool wrapper scripts and +# restored at link time. +variables_saved_for_relink=$lt_variables_saved_for_relink + +# Do we need the "lib" prefix for modules? +need_lib_prefix=$need_lib_prefix + +# Do we need a version for libraries? +need_version=$need_version + +# Library versioning type. +version_type=$version_type + +# Shared library runtime path variable. +runpath_var=$runpath_var + +# Shared library path variable. +shlibpath_var=$shlibpath_var + +# Is shlibpath searched before the hard-coded library search path? +shlibpath_overrides_runpath=$shlibpath_overrides_runpath + +# Format of library name prefix. +libname_spec=$lt_libname_spec + +# List of archive names. First name is the real one, the rest are links. +# The last name is the one that the linker finds with -lNAME +library_names_spec=$lt_library_names_spec + +# The coded name of the library, if different from the real name. +soname_spec=$lt_soname_spec + +# Permission mode override for installation of shared libraries. +install_override_mode=$lt_install_override_mode + +# Command to use after installation of a shared archive. +postinstall_cmds=$lt_postinstall_cmds + +# Command to use after uninstallation of a shared archive. +postuninstall_cmds=$lt_postuninstall_cmds + +# Commands used to finish a libtool library installation in a directory. +finish_cmds=$lt_finish_cmds + +# As "finish_cmds", except a single script fragment to be evaled but +# not shown. +finish_eval=$lt_finish_eval + +# Whether we should hardcode library paths into libraries. +hardcode_into_libs=$hardcode_into_libs + +# Compile-time system search path for libraries. +sys_lib_search_path_spec=$lt_sys_lib_search_path_spec + +# Detected run-time system search path for libraries. +sys_lib_dlsearch_path_spec=$lt_configure_time_dlsearch_path + +# Explicit LT_SYS_LIBRARY_PATH set during ./configure time. +configure_time_lt_sys_library_path=$lt_configure_time_lt_sys_library_path + +# Whether dlopen is supported. +dlopen_support=$enable_dlopen + +# Whether dlopen of programs is supported. +dlopen_self=$enable_dlopen_self + +# Whether dlopen of statically linked programs is supported. +dlopen_self_static=$enable_dlopen_self_static + +# Commands to strip libraries. +old_striplib=$lt_old_striplib +striplib=$lt_striplib + + +# The linker used to build libraries. +LD=$lt_LD + +# How to create reloadable object files. +reload_flag=$lt_reload_flag +reload_cmds=$lt_reload_cmds + +# Commands used to build an old-style archive. +old_archive_cmds=$lt_old_archive_cmds + +# A language specific compiler. +CC=$lt_compiler + +# Is the compiler the GNU compiler? +with_gcc=$GCC + +# Compiler flag to turn off builtin functions. +no_builtin_flag=$lt_lt_prog_compiler_no_builtin_flag + +# Additional compiler flags for building library objects. +pic_flag=$lt_lt_prog_compiler_pic + +# How to pass a linker flag through the compiler. +wl=$lt_lt_prog_compiler_wl + +# Compiler flag to prevent dynamic linking. +link_static_flag=$lt_lt_prog_compiler_static + +# Does compiler simultaneously support -c and -o options? +compiler_c_o=$lt_lt_cv_prog_compiler_c_o + +# Whether or not to add -lc for building shared libraries. +build_libtool_need_lc=$archive_cmds_need_lc + +# Whether or not to disallow shared libs when runtime libs are static. +allow_libtool_libs_with_static_runtimes=$enable_shared_with_static_runtimes + +# Compiler flag to allow reflexive dlopens. +export_dynamic_flag_spec=$lt_export_dynamic_flag_spec + +# Compiler flag to generate shared objects directly from archives. +whole_archive_flag_spec=$lt_whole_archive_flag_spec + +# Whether the compiler copes with passing no objects directly. +compiler_needs_object=$lt_compiler_needs_object + +# Create an old-style archive from a shared archive. +old_archive_from_new_cmds=$lt_old_archive_from_new_cmds + +# Create a temporary old-style archive to link instead of a shared archive. +old_archive_from_expsyms_cmds=$lt_old_archive_from_expsyms_cmds + +# Commands used to build a shared archive. +archive_cmds=$lt_archive_cmds +archive_expsym_cmds=$lt_archive_expsym_cmds + +# Commands used to build a loadable module if different from building +# a shared archive. +module_cmds=$lt_module_cmds +module_expsym_cmds=$lt_module_expsym_cmds + +# Whether we are building with GNU ld or not. +with_gnu_ld=$lt_with_gnu_ld + +# Flag that allows shared libraries with undefined symbols to be built. +allow_undefined_flag=$lt_allow_undefined_flag + +# Flag that enforces no undefined symbols. +no_undefined_flag=$lt_no_undefined_flag + +# Flag to hardcode \$libdir into a binary during linking. +# This must work even if \$libdir does not exist +hardcode_libdir_flag_spec=$lt_hardcode_libdir_flag_spec + +# Whether we need a single "-rpath" flag with a separated argument. +hardcode_libdir_separator=$lt_hardcode_libdir_separator + +# Set to "yes" if using DIR/libNAME\$shared_ext during linking hardcodes +# DIR into the resulting binary. +hardcode_direct=$hardcode_direct + +# Set to "yes" if using DIR/libNAME\$shared_ext during linking hardcodes +# DIR into the resulting binary and the resulting library dependency is +# "absolute",i.e impossible to change by setting \$shlibpath_var if the +# library is relocated. +hardcode_direct_absolute=$hardcode_direct_absolute + +# Set to "yes" if using the -LDIR flag during linking hardcodes DIR +# into the resulting binary. +hardcode_minus_L=$hardcode_minus_L + +# Set to "yes" if using SHLIBPATH_VAR=DIR during linking hardcodes DIR +# into the resulting binary. +hardcode_shlibpath_var=$hardcode_shlibpath_var + +# Set to "yes" if building a shared library automatically hardcodes DIR +# into the library and all subsequent libraries and executables linked +# against it. +hardcode_automatic=$hardcode_automatic + +# Set to yes if linker adds runtime paths of dependent libraries +# to runtime path list. +inherit_rpath=$inherit_rpath + +# Whether libtool must link a program against all its dependency libraries. +link_all_deplibs=$link_all_deplibs + +# Set to "yes" if exported symbols are required. +always_export_symbols=$always_export_symbols + +# The commands to list exported symbols. +export_symbols_cmds=$lt_export_symbols_cmds + +# Symbols that should not be listed in the preloaded symbols. +exclude_expsyms=$lt_exclude_expsyms + +# Symbols that must always be exported. +include_expsyms=$lt_include_expsyms + +# Commands necessary for linking programs (against libraries) with templates. +prelink_cmds=$lt_prelink_cmds + +# Commands necessary for finishing linking programs. +postlink_cmds=$lt_postlink_cmds + +# Specify filename containing input files. +file_list_spec=$lt_file_list_spec + +# How to hardcode a shared library path into an executable. +hardcode_action=$hardcode_action + +# ### END LIBTOOL CONFIG + +_LT_EOF + + cat <<'_LT_EOF' >> "$cfgfile" + +# ### BEGIN FUNCTIONS SHARED WITH CONFIGURE + +# func_munge_path_list VARIABLE PATH +# ----------------------------------- +# VARIABLE is name of variable containing _space_ separated list of +# directories to be munged by the contents of PATH, which is string +# having a format: +# "DIR[:DIR]:" +# string "DIR[ DIR]" will be prepended to VARIABLE +# ":DIR[:DIR]" +# string "DIR[ DIR]" will be appended to VARIABLE +# "DIRP[:DIRP]::[DIRA:]DIRA" +# string "DIRP[ DIRP]" will be prepended to VARIABLE and string +# "DIRA[ DIRA]" will be appended to VARIABLE +# "DIR[:DIR]" +# VARIABLE will be replaced by "DIR[ DIR]" +func_munge_path_list () +{ + case x$2 in + x) + ;; + *:) + eval $1=\"`$ECHO $2 | $SED 's/:/ /g'` \$$1\" + ;; + x:*) + eval $1=\"\$$1 `$ECHO $2 | $SED 's/:/ /g'`\" + ;; + *::*) + eval $1=\"\$$1\ `$ECHO $2 | $SED -e 's/.*:://' -e 's/:/ /g'`\" + eval $1=\"`$ECHO $2 | $SED -e 's/::.*//' -e 's/:/ /g'`\ \$$1\" + ;; + *) + eval $1=\"`$ECHO $2 | $SED 's/:/ /g'`\" + ;; + esac +} + + +# Calculate cc_basename. Skip known compiler wrappers and cross-prefix. +func_cc_basename () +{ + for cc_temp in $*""; do + case $cc_temp in + compile | *[\\/]compile | ccache | *[\\/]ccache ) ;; + distcc | *[\\/]distcc | purify | *[\\/]purify ) ;; + \-*) ;; + *) break;; + esac + done + func_cc_basename_result=`$ECHO "$cc_temp" | $SED "s%.*/%%; s%^$host_alias-%%"` +} + + +# ### END FUNCTIONS SHARED WITH CONFIGURE + +_LT_EOF + + case $host_os in + aix3*) + cat <<\_LT_EOF >> "$cfgfile" +# AIX sometimes has problems with the GCC collect2 program. For some +# reason, if we set the COLLECT_NAMES environment variable, the problems +# vanish in a puff of smoke. +if test set != "${COLLECT_NAMES+set}"; then + COLLECT_NAMES= + export COLLECT_NAMES +fi +_LT_EOF + ;; + esac + + +ltmain=$ac_aux_dir/ltmain.sh + + + # We use sed instead of cat because bash on DJGPP gets confused if + # if finds mixed CR/LF and LF-only lines. Since sed operates in + # text mode, it properly converts lines to CR/LF. This bash problem + # is reportedly fixed, but why not run on old versions too? + sed '$q' "$ltmain" >> "$cfgfile" \ + || (rm -f "$cfgfile"; exit 1) + + mv -f "$cfgfile" "$ofile" || + (rm -f "$ofile" && cp "$cfgfile" "$ofile" && rm -f "$cfgfile") + chmod +x "$ofile" + + ;; + "script-chmod":C) chmod a+x pcre2-config ;; + "delete-old-chartables":C) rm -f pcre2_chartables.c ;; + + esac +done # for ac_tag + + +as_fn_exit 0 +_ACEOF +ac_clean_files=$ac_clean_files_save + +test $ac_write_fail = 0 || + as_fn_error $? "write failure creating $CONFIG_STATUS" "$LINENO" 5 + + +# configure is writing to config.log, and then calls config.status. +# config.status does its own redirection, appending to config.log. +# Unfortunately, on DOS this fails, as config.log is still kept open +# by configure, so config.status won't be able to write to it; its +# output is simply discarded. So we exec the FD to /dev/null, +# effectively closing config.log, so it can be properly (re)opened and +# appended to by config.status. When coming back to configure, we +# need to make the FD available again. +if test "$no_create" != yes; then + ac_cs_success=: + ac_config_status_args= + test "$silent" = yes && + ac_config_status_args="$ac_config_status_args --quiet" + exec 5>/dev/null + $SHELL $CONFIG_STATUS $ac_config_status_args || ac_cs_success=false + exec 5>>config.log + # Use ||, not &&, to avoid exiting from the if with $? = 1, which + # would make configure fail if this is the last instruction. + $ac_cs_success || as_fn_exit 1 +fi +if test -n "$ac_unrecognized_opts" && test "$enable_option_checking" != no; then + { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: unrecognized options: $ac_unrecognized_opts" >&5 +$as_echo "$as_me: WARNING: unrecognized options: $ac_unrecognized_opts" >&2;} +fi + + +# Print out a nice little message after configure is run displaying the +# chosen options. + +ebcdic_nl_code=n/a +if test "$enable_ebcdic_nl25" = "yes"; then + ebcdic_nl_code=0x25 +elif test "$enable_ebcdic" = "yes"; then + ebcdic_nl_code=0x15 +fi + +cat < Delete Cache". + +1. Install the latest CMake version available from http://www.cmake.org/, and + ensure that cmake\bin is on your path. + +2. Unzip (retaining folder structure) the PCRE2 source tree into a source + directory such as C:\pcre2. You should ensure your local date and time + is not earlier than the file dates in your source dir if the release is + very new. + +3. Create a new, empty build directory, preferably a subdirectory of the + source dir. For example, C:\pcre2\pcre2-xx\build. + +4. Run cmake-gui from the Shell envirornment of your build tool, for example, + Msys for Msys/MinGW or Visual Studio Command Prompt for VC/VC++. Do not try + to start Cmake from the Windows Start menu, as this can lead to errors. + +5. Enter C:\pcre2\pcre2-xx and C:\pcre2\pcre2-xx\build for the source and + build directories, respectively. + +6. Hit the "Configure" button. + +7. Select the particular IDE / build tool that you are using (Visual + Studio, MSYS makefiles, MinGW makefiles, etc.) + +8. The GUI will then list several configuration options. This is where + you can disable Unicode support or select other PCRE2 optional features. + +9. Hit "Configure" again. The adjacent "Generate" button should now be + active. + +10. Hit "Generate". + +11. The build directory should now contain a usable build system, be it a + solution file for Visual Studio, makefiles for MinGW, etc. Exit from + cmake-gui and use the generated build system with your compiler or IDE. + E.g., for MinGW you can run "make", or for Visual Studio, open the PCRE2 + solution, select the desired configuration (Debug, or Release, etc.) and + build the ALL_BUILD project. + +12. If during configuration with cmake-gui you've elected to build the test + programs, you can execute them by building the test project. E.g., for + MinGW: "make test"; for Visual Studio build the RUN_TESTS project. The + most recent build configuration is targeted by the tests. A summary of + test results is presented. Complete test output is subsequently + available for review in Testing\Temporary under your build dir. + + +TESTING WITH RUNTEST.BAT + +If configured with CMake, building the test project ("make test" or building +ALL_TESTS in Visual Studio) creates (and runs) pcre2_test.bat (and depending +on your configuration options, possibly other test programs) in the build +directory. The pcre2_test.bat script runs RunTest.bat with correct source and +exe paths. + +For manual testing with RunTest.bat, provided the build dir is a subdirectory +of the source directory: Open command shell window. Chdir to the location +of your pcre2test.exe and pcre2grep.exe programs. Call RunTest.bat with +"..\RunTest.Bat" or "..\..\RunTest.bat" as appropriate. + +To run only a particular test with RunTest.Bat provide a test number argument. + +Otherwise: + +1. Copy RunTest.bat into the directory where pcre2test.exe and pcre2grep.exe + have been created. + +2. Edit RunTest.bat to indentify the full or relative location of + the pcre2 source (wherein which the testdata folder resides), e.g.: + + set srcdir=C:\pcre2\pcre2-10.00 + +3. In a Windows command environment, chdir to the location of your bat and + exe programs. + +4. Run RunTest.bat. Test outputs will automatically be compared to expected + results, and discrepancies will be identified in the console output. + +To independently test the just-in-time compiler, run pcre2_jit_test.exe. + + +BUILDING PCRE2 ON NATIVE Z/OS AND Z/VM + +z/OS and z/VM are operating systems for mainframe computers, produced by IBM. +The character code used is EBCDIC, not ASCII or Unicode. In z/OS, UNIX APIs and +applications can be supported through UNIX System Services, and in such an +environment PCRE2 can be built in the same way as in other systems. However, in +native z/OS (without UNIX System Services) and in z/VM, special ports are +required. For details, please see this web site: + + http://www.zaconsultants.net + +The site currently has ports for PCRE1 releases, but PCRE2 should follow in due +course. + +You may also download PCRE1 from WWW.CBTTAPE.ORG, file 882. Everything, source +and executable, is in EBCDIC and native z/OS file formats and this is the +recommended download site. + +============================= +Last Updated: 15 June 2015 diff --git a/pcre2-10.20/doc/html/README.txt b/pcre2-10.20/doc/html/README.txt new file mode 100644 index 000000000..7367924c8 --- /dev/null +++ b/pcre2-10.20/doc/html/README.txt @@ -0,0 +1,835 @@ +README file for PCRE2 (Perl-compatible regular expression library) +------------------------------------------------------------------ + +PCRE2 is a re-working of the original PCRE library to provide an entirely new +API. The latest release of PCRE2 is always available in three alternative +formats from: + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre2-xxx.tar.gz + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre2-xxx.tar.bz2 + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre2-xxx.zip + +There is a mailing list for discussion about the development of PCRE (both the +original and new APIs) at pcre-dev@exim.org. You can access the archives and +subscribe or manage your subscription here: + + https://lists.exim.org/mailman/listinfo/pcre-dev + +Please read the NEWS file if you are upgrading from a previous release. +The contents of this README file are: + + The PCRE2 APIs + Documentation for PCRE2 + Contributions by users of PCRE2 + Building PCRE2 on non-Unix-like systems + Building PCRE2 without using autotools + Building PCRE2 using autotools + Retrieving configuration information + Shared libraries + Cross-compiling using autotools + Making new tarballs + Testing PCRE2 + Character tables + File manifest + + +The PCRE2 APIs +-------------- + +PCRE2 is written in C, and it has its own API. There are three sets of +functions, one for the 8-bit library, which processes strings of bytes, one for +the 16-bit library, which processes strings of 16-bit values, and one for the +32-bit library, which processes strings of 32-bit values. There are no C++ +wrappers. + +The distribution does contain a set of C wrapper functions for the 8-bit +library that are based on the POSIX regular expression API (see the pcre2posix +man page). These can be found in a library called libpcre2posix. Note that this +just provides a POSIX calling interface to PCRE2; the regular expressions +themselves still follow Perl syntax and semantics. The POSIX API is restricted, +and does not give full access to all of PCRE2's facilities. + +The header file for the POSIX-style functions is called pcre2posix.h. The +official POSIX name is regex.h, but I did not want to risk possible problems +with existing files of that name by distributing it that way. To use PCRE2 with +an existing program that uses the POSIX API, pcre2posix.h will have to be +renamed or pointed at by a link. + +If you are using the POSIX interface to PCRE2 and there is already a POSIX +regex library installed on your system, as well as worrying about the regex.h +header file (as mentioned above), you must also take care when linking programs +to ensure that they link with PCRE2's libpcre2posix library. Otherwise they may +pick up the POSIX functions of the same name from the other library. + +One way of avoiding this confusion is to compile PCRE2 with the addition of +-Dregcomp=PCRE2regcomp (and similarly for the other POSIX functions) to the +compiler flags (CFLAGS if you are using "configure" -- see below). This has the +effect of renaming the functions so that the names no longer clash. Of course, +you have to do the same thing for your applications, or write them using the +new names. + + +Documentation for PCRE2 +----------------------- + +If you install PCRE2 in the normal way on a Unix-like system, you will end up +with a set of man pages whose names all start with "pcre2". The one that is +just called "pcre2" lists all the others. In addition to these man pages, the +PCRE2 documentation is supplied in two other forms: + + 1. There are files called doc/pcre2.txt, doc/pcre2grep.txt, and + doc/pcre2test.txt in the source distribution. The first of these is a + concatenation of the text forms of all the section 3 man pages except the + listing of pcre2demo.c and those that summarize individual functions. The + other two are the text forms of the section 1 man pages for the pcre2grep + and pcre2test commands. These text forms are provided for ease of scanning + with text editors or similar tools. They are installed in + /share/doc/pcre2, where is the installation prefix + (defaulting to /usr/local). + + 2. A set of files containing all the documentation in HTML form, hyperlinked + in various ways, and rooted in a file called index.html, is distributed in + doc/html and installed in /share/doc/pcre2/html. + + +Building PCRE2 on non-Unix-like systems +--------------------------------------- + +For a non-Unix-like system, please read the comments in the file +NON-AUTOTOOLS-BUILD, though if your system supports the use of "configure" and +"make" you may be able to build PCRE2 using autotools in the same way as for +many Unix-like systems. + +PCRE2 can also be configured using CMake, which can be run in various ways +(command line, GUI, etc). This creates Makefiles, solution files, etc. The file +NON-AUTOTOOLS-BUILD has information about CMake. + +PCRE2 has been compiled on many different operating systems. It should be +straightforward to build PCRE2 on any system that has a Standard C compiler and +library, because it uses only Standard C functions. + + +Building PCRE2 without using autotools +-------------------------------------- + +The use of autotools (in particular, libtool) is problematic in some +environments, even some that are Unix or Unix-like. See the NON-AUTOTOOLS-BUILD +file for ways of building PCRE2 without using autotools. + + +Building PCRE2 using autotools +------------------------------ + +The following instructions assume the use of the widely used "configure; make; +make install" (autotools) process. + +To build PCRE2 on system that supports autotools, first run the "configure" +command from the PCRE2 distribution directory, with your current directory set +to the directory where you want the files to be created. This command is a +standard GNU "autoconf" configuration script, for which generic instructions +are supplied in the file INSTALL. + +Most commonly, people build PCRE2 within its own distribution directory, and in +this case, on many systems, just running "./configure" is sufficient. However, +the usual methods of changing standard defaults are available. For example: + +CFLAGS='-O2 -Wall' ./configure --prefix=/opt/local + +This command specifies that the C compiler should be run with the flags '-O2 +-Wall' instead of the default, and that "make install" should install PCRE2 +under /opt/local instead of the default /usr/local. + +If you want to build in a different directory, just run "configure" with that +directory as current. For example, suppose you have unpacked the PCRE2 source +into /source/pcre2/pcre2-xxx, but you want to build it in +/build/pcre2/pcre2-xxx: + +cd /build/pcre2/pcre2-xxx +/source/pcre2/pcre2-xxx/configure + +PCRE2 is written in C and is normally compiled as a C library. However, it is +possible to build it as a C++ library, though the provided building apparatus +does not have any features to support this. + +There are some optional features that can be included or omitted from the PCRE2 +library. They are also documented in the pcre2build man page. + +. By default, both shared and static libraries are built. You can change this + by adding one of these options to the "configure" command: + + --disable-shared + --disable-static + + (See also "Shared libraries on Unix-like systems" below.) + +. By default, only the 8-bit library is built. If you add --enable-pcre2-16 to + the "configure" command, the 16-bit library is also built. If you add + --enable-pcre2-32 to the "configure" command, the 32-bit library is also + built. If you want only the 16-bit or 32-bit library, use --disable-pcre2-8 + to disable building the 8-bit library. + +. If you want to include support for just-in-time compiling, which can give + large performance improvements on certain platforms, add --enable-jit to the + "configure" command. This support is available only for certain hardware + architectures. If you try to enable it on an unsupported architecture, there + will be a compile time error. + +. When JIT support is enabled, pcre2grep automatically makes use of it, unless + you add --disable-pcre2grep-jit to the "configure" command. + +. If you do not want to make use of the support for UTF-8 Unicode character + strings in the 8-bit library, UTF-16 Unicode character strings in the 16-bit + library, or UTF-32 Unicode character strings in the 32-bit library, you can + add --disable-unicode to the "configure" command. This reduces the size of + the libraries. It is not possible to configure one library with Unicode + support, and another without, in the same configuration. + + When Unicode support is available, the use of a UTF encoding still has to be + enabled by setting the PCRE2_UTF option at run time or starting a pattern + with (*UTF). When PCRE2 is compiled with Unicode support, its input can only + either be ASCII or UTF-8/16/32, even when running on EBCDIC platforms. It is + not possible to use both --enable-unicode and --enable-ebcdic at the same + time. + + As well as supporting UTF strings, Unicode support includes support for the + \P, \p, and \X sequences that recognize Unicode character properties. + However, only the basic two-letter properties such as Lu are supported. + Escape sequences such as \d and \w in patterns do not by default make use of + Unicode properties, but can be made to do so by setting the PCRE2_UCP option + or starting a pattern with (*UCP). + +. You can build PCRE2 to recognize either CR or LF or the sequence CRLF, or any + of the preceding, or any of the Unicode newline sequences, as indicating the + end of a line. Whatever you specify at build time is the default; the caller + of PCRE2 can change the selection at run time. The default newline indicator + is a single LF character (the Unix standard). You can specify the default + newline indicator by adding --enable-newline-is-cr, --enable-newline-is-lf, + --enable-newline-is-crlf, --enable-newline-is-anycrlf, or + --enable-newline-is-any to the "configure" command, respectively. + + If you specify --enable-newline-is-cr or --enable-newline-is-crlf, some of + the standard tests will fail, because the lines in the test files end with + LF. Even if the files are edited to change the line endings, there are likely + to be some failures. With --enable-newline-is-anycrlf or + --enable-newline-is-any, many tests should succeed, but there may be some + failures. + +. By default, the sequence \R in a pattern matches any Unicode line ending + sequence. This is independent of the option specifying what PCRE2 considers + to be the end of a line (see above). However, the caller of PCRE2 can + restrict \R to match only CR, LF, or CRLF. You can make this the default by + adding --enable-bsr-anycrlf to the "configure" command (bsr = "backslash R"). + +. PCRE2 has a counter that limits the depth of nesting of parentheses in a + pattern. This limits the amount of system stack that a pattern uses when it + is compiled. The default is 250, but you can change it by setting, for + example, + + --with-parens-nest-limit=500 + +. PCRE2 has a counter that can be set to limit the amount of resources it uses + when matching a pattern. If the limit is exceeded during a match, the match + fails. The default is ten million. You can change the default by setting, for + example, + + --with-match-limit=500000 + + on the "configure" command. This is just the default; individual calls to + pcre2_match() can supply their own value. There is more discussion on the + pcre2api man page. + +. There is a separate counter that limits the depth of recursive function calls + during a matching process. This also has a default of ten million, which is + essentially "unlimited". You can change the default by setting, for example, + + --with-match-limit-recursion=500000 + + Recursive function calls use up the runtime stack; running out of stack can + cause programs to crash in strange ways. There is a discussion about stack + sizes in the pcre2stack man page. + +. In the 8-bit library, the default maximum compiled pattern size is around + 64K. You can increase this by adding --with-link-size=3 to the "configure" + command. PCRE2 then uses three bytes instead of two for offsets to different + parts of the compiled pattern. In the 16-bit library, --with-link-size=3 is + the same as --with-link-size=4, which (in both libraries) uses four-byte + offsets. Increasing the internal link size reduces performance in the 8-bit + and 16-bit libraries. In the 32-bit library, the link size setting is + ignored, as 4-byte offsets are always used. + +. You can build PCRE2 so that its internal match() function that is called from + pcre2_match() does not call itself recursively. Instead, it uses memory + blocks obtained from the heap to save data that would otherwise be saved on + the stack. To build PCRE2 like this, use + + --disable-stack-for-recursion + + on the "configure" command. PCRE2 runs more slowly in this mode, but it may + be necessary in environments with limited stack sizes. This applies only to + the normal execution of the pcre2_match() function; if JIT support is being + successfully used, it is not relevant. Equally, it does not apply to + pcre2_dfa_match(), which does not use deeply nested recursion. There is a + discussion about stack sizes in the pcre2stack man page. + +. For speed, PCRE2 uses four tables for manipulating and identifying characters + whose code point values are less than 256. By default, it uses a set of + tables for ASCII encoding that is part of the distribution. If you specify + + --enable-rebuild-chartables + + a program called dftables is compiled and run in the default C locale when + you obey "make". It builds a source file called pcre2_chartables.c. If you do + not specify this option, pcre2_chartables.c is created as a copy of + pcre2_chartables.c.dist. See "Character tables" below for further + information. + +. It is possible to compile PCRE2 for use on systems that use EBCDIC as their + character code (as opposed to ASCII/Unicode) by specifying + + --enable-ebcdic --disable-unicode + + This automatically implies --enable-rebuild-chartables (see above). However, + when PCRE2 is built this way, it always operates in EBCDIC. It cannot support + both EBCDIC and UTF-8/16/32. There is a second option, --enable-ebcdic-nl25, + which specifies that the code value for the EBCDIC NL character is 0x25 + instead of the default 0x15. + +. If you specify --enable-debug, additional debugging code is included in the + build. This option is intended for use by the PCRE2 maintainers. + +. In environments where valgrind is installed, if you specify + + --enable-valgrind + + PCRE2 will use valgrind annotations to mark certain memory regions as + unaddressable. This allows it to detect invalid memory accesses, and is + mostly useful for debugging PCRE2 itself. + +. In environments where the gcc compiler is used and lcov version 1.6 or above + is installed, if you specify + + --enable-coverage + + the build process implements a code coverage report for the test suite. The + report is generated by running "make coverage". If ccache is installed on + your system, it must be disabled when building PCRE2 for coverage reporting. + You can do this by setting the environment variable CCACHE_DISABLE=1 before + running "make" to build PCRE2. There is more information about coverage + reporting in the "pcre2build" documentation. + +. The pcre2grep program currently supports only 8-bit data files, and so + requires the 8-bit PCRE2 library. It is possible to compile pcre2grep to use + libz and/or libbz2, in order to read .gz and .bz2 files (respectively), by + specifying one or both of + + --enable-pcre2grep-libz + --enable-pcre2grep-libbz2 + + Of course, the relevant libraries must be installed on your system. + +. The default size (in bytes) of the internal buffer used by pcre2grep can be + set by, for example: + + --with-pcre2grep-bufsize=51200 + + The value must be a plain integer. The default is 20480. + +. It is possible to compile pcre2test so that it links with the libreadline + or libedit libraries, by specifying, respectively, + + --enable-pcre2test-libreadline or --enable-pcre2test-libedit + + If this is done, when pcre2test's input is from a terminal, it reads it using + the readline() function. This provides line-editing and history facilities. + Note that libreadline is GPL-licenced, so if you distribute a binary of + pcre2test linked in this way, there may be licensing issues. These can be + avoided by linking with libedit (which has a BSD licence) instead. + + Enabling libreadline causes the -lreadline option to be added to the + pcre2test build. In many operating environments with a sytem-installed + readline library this is sufficient. However, in some environments (e.g. if + an unmodified distribution version of readline is in use), it may be + necessary to specify something like LIBS="-lncurses" as well. This is + because, to quote the readline INSTALL, "Readline uses the termcap functions, + but does not link with the termcap or curses library itself, allowing + applications which link with readline the to choose an appropriate library." + If you get error messages about missing functions tgetstr, tgetent, tputs, + tgetflag, or tgoto, this is the problem, and linking with the ncurses library + should fix it. + +The "configure" script builds the following files for the basic C library: + +. Makefile the makefile that builds the library +. src/config.h build-time configuration options for the library +. src/pcre2.h the public PCRE2 header file +. pcre2-config script that shows the building settings such as CFLAGS + that were set for "configure" +. libpcre2-8.pc ) +. libpcre2-16.pc ) data for the pkg-config command +. libpcre2-32.pc ) +. libpcre2-posix.pc ) +. libtool script that builds shared and/or static libraries + +Versions of config.h and pcre2.h are distributed in the src directory of PCRE2 +tarballs under the names config.h.generic and pcre2.h.generic. These are +provided for those who have to build PCRE2 without using "configure" or CMake. +If you use "configure" or CMake, the .generic versions are not used. + +The "configure" script also creates config.status, which is an executable +script that can be run to recreate the configuration, and config.log, which +contains compiler output from tests that "configure" runs. + +Once "configure" has run, you can run "make". This builds whichever of the +libraries libpcre2-8, libpcre2-16 and libpcre2-32 are configured, and a test +program called pcre2test. If you enabled JIT support with --enable-jit, another +test program called pcre2_jit_test is built as well. If the 8-bit library is +built, libpcre2-posix and the pcre2grep command are also built. Running +"make" with the -j option may speed up compilation on multiprocessor systems. + +The command "make check" runs all the appropriate tests. Details of the PCRE2 +tests are given below in a separate section of this document. The -j option of +"make" can also be used when running the tests. + +You can use "make install" to install PCRE2 into live directories on your +system. The following are installed (file names are all relative to the + that is set when "configure" is run): + + Commands (bin): + pcre2test + pcre2grep (if 8-bit support is enabled) + pcre2-config + + Libraries (lib): + libpcre2-8 (if 8-bit support is enabled) + libpcre2-16 (if 16-bit support is enabled) + libpcre2-32 (if 32-bit support is enabled) + libpcre2-posix (if 8-bit support is enabled) + + Configuration information (lib/pkgconfig): + libpcre2-8.pc + libpcre2-16.pc + libpcre2-32.pc + libpcre2-posix.pc + + Header files (include): + pcre2.h + pcre2posix.h + + Man pages (share/man/man{1,3}): + pcre2grep.1 + pcre2test.1 + pcre2-config.1 + pcre2.3 + pcre2*.3 (lots more pages, all starting "pcre2") + + HTML documentation (share/doc/pcre2/html): + index.html + *.html (lots more pages, hyperlinked from index.html) + + Text file documentation (share/doc/pcre2): + AUTHORS + COPYING + ChangeLog + LICENCE + NEWS + README + pcre2.txt (a concatenation of the man(3) pages) + pcre2test.txt the pcre2test man page + pcre2grep.txt the pcre2grep man page + pcre2-config.txt the pcre2-config man page + +If you want to remove PCRE2 from your system, you can run "make uninstall". +This removes all the files that "make install" installed. However, it does not +remove any directories, because these are often shared with other programs. + + +Retrieving configuration information +------------------------------------ + +Running "make install" installs the command pcre2-config, which can be used to +recall information about the PCRE2 configuration and installation. For example: + + pcre2-config --version + +prints the version number, and + + pcre2-config --libs8 + +outputs information about where the 8-bit library is installed. This command +can be included in makefiles for programs that use PCRE2, saving the programmer +from having to remember too many details. Run pcre2-config with no arguments to +obtain a list of possible arguments. + +The pkg-config command is another system for saving and retrieving information +about installed libraries. Instead of separate commands for each library, a +single command is used. For example: + + pkg-config --libs libpcre2-16 + +The data is held in *.pc files that are installed in a directory called +/lib/pkgconfig. + + +Shared libraries +---------------- + +The default distribution builds PCRE2 as shared libraries and static libraries, +as long as the operating system supports shared libraries. Shared library +support relies on the "libtool" script which is built as part of the +"configure" process. + +The libtool script is used to compile and link both shared and static +libraries. They are placed in a subdirectory called .libs when they are newly +built. The programs pcre2test and pcre2grep are built to use these uninstalled +libraries (by means of wrapper scripts in the case of shared libraries). When +you use "make install" to install shared libraries, pcre2grep and pcre2test are +automatically re-built to use the newly installed shared libraries before being +installed themselves. However, the versions left in the build directory still +use the uninstalled libraries. + +To build PCRE2 using static libraries only you must use --disable-shared when +configuring it. For example: + +./configure --prefix=/usr/gnu --disable-shared + +Then run "make" in the usual way. Similarly, you can use --disable-static to +build only shared libraries. + + +Cross-compiling using autotools +------------------------------- + +You can specify CC and CFLAGS in the normal way to the "configure" command, in +order to cross-compile PCRE2 for some other host. However, you should NOT +specify --enable-rebuild-chartables, because if you do, the dftables.c source +file is compiled and run on the local host, in order to generate the inbuilt +character tables (the pcre2_chartables.c file). This will probably not work, +because dftables.c needs to be compiled with the local compiler, not the cross +compiler. + +When --enable-rebuild-chartables is not specified, pcre2_chartables.c is +created by making a copy of pcre2_chartables.c.dist, which is a default set of +tables that assumes ASCII code. Cross-compiling with the default tables should +not be a problem. + +If you need to modify the character tables when cross-compiling, you should +move pcre2_chartables.c.dist out of the way, then compile dftables.c by hand +and run it on the local host to make a new version of pcre2_chartables.c.dist. +Then when you cross-compile PCRE2 this new version of the tables will be used. + + +Making new tarballs +------------------- + +The command "make dist" creates three PCRE2 tarballs, in tar.gz, tar.bz2, and +zip formats. The command "make distcheck" does the same, but then does a trial +build of the new distribution to ensure that it works. + +If you have modified any of the man page sources in the doc directory, you +should first run the PrepareRelease script before making a distribution. This +script creates the .txt and HTML forms of the documentation from the man pages. + + +Testing PCRE2 +------------ + +To test the basic PCRE2 library on a Unix-like system, run the RunTest script. +There is another script called RunGrepTest that tests the pcre2grep command. +When JIT support is enabled, a third test program called pcre2_jit_test is +built. Both the scripts and all the program tests are run if you obey "make +check". For other environments, see the instructions in NON-AUTOTOOLS-BUILD. + +The RunTest script runs the pcre2test test program (which is documented in its +own man page) on each of the relevant testinput files in the testdata +directory, and compares the output with the contents of the corresponding +testoutput files. RunTest uses a file called testtry to hold the main output +from pcre2test. Other files whose names begin with "test" are used as working +files in some tests. + +Some tests are relevant only when certain build-time options were selected. For +example, the tests for UTF-8/16/32 features are run only when Unicode support +is available. RunTest outputs a comment when it skips a test. + +Many (but not all) of the tests that are not skipped are run twice if JIT +support is available. On the second run, JIT compilation is forced. This +testing can be suppressed by putting "nojit" on the RunTest command line. + +The entire set of tests is run once for each of the 8-bit, 16-bit and 32-bit +libraries that are enabled. If you want to run just one set of tests, call +RunTest with either the -8, -16 or -32 option. + +If valgrind is installed, you can run the tests under it by putting "valgrind" +on the RunTest command line. To run pcre2test on just one or more specific test +files, give their numbers as arguments to RunTest, for example: + + RunTest 2 7 11 + +You can also specify ranges of tests such as 3-6 or 3- (meaning 3 to the +end), or a number preceded by ~ to exclude a test. For example: + + Runtest 3-15 ~10 + +This runs tests 3 to 15, excluding test 10, and just ~13 runs all the tests +except test 13. Whatever order the arguments are in, the tests are always run +in numerical order. + +You can also call RunTest with the single argument "list" to cause it to output +a list of tests. + +The test sequence starts with "test 0", which is a special test that has no +input file, and whose output is not checked. This is because it will be +different on different hardware and with different configurations. The test +exists in order to exercise some of pcre2test's code that would not otherwise +be run. + +Tests 1 and 2 can always be run, as they expect only plain text strings (not +UTF) and make no use of Unicode properties. The first test file can be fed +directly into the perltest.sh script to check that Perl gives the same results. +The only difference you should see is in the first few lines, where the Perl +version is given instead of the PCRE2 version. The second set of tests check +auxiliary functions, error detection, and run-time flags that are specific to +PCRE2. It also uses the debugging flags to check some of the internals of +pcre2_compile(). + +If you build PCRE2 with a locale setting that is not the standard C locale, the +character tables may be different (see next paragraph). In some cases, this may +cause failures in the second set of tests. For example, in a locale where the +isprint() function yields TRUE for characters in the range 128-255, the use of +[:isascii:] inside a character class defines a different set of characters, and +this shows up in this test as a difference in the compiled code, which is being +listed for checking. For example, where the comparison test output contains +[\x00-\x7f] the test might contain [\x00-\xff], and similarly in some other +cases. This is not a bug in PCRE2. + +Test 3 checks pcre2_maketables(), the facility for building a set of character +tables for a specific locale and using them instead of the default tables. The +script uses the "locale" command to check for the availability of the "fr_FR", +"french", or "fr" locale, and uses the first one that it finds. If the "locale" +command fails, or if its output doesn't include "fr_FR", "french", or "fr" in +the list of available locales, the third test cannot be run, and a comment is +output to say why. If running this test produces an error like this: + + ** Failed to set locale "fr_FR" + +it means that the given locale is not available on your system, despite being +listed by "locale". This does not mean that PCRE2 is broken. There are three +alternative output files for the third test, because three different versions +of the French locale have been encountered. The test passes if its output +matches any one of them. + +Tests 4 and 5 check UTF and Unicode property support, test 4 being compatible +with the perltest.sh script, and test 5 checking PCRE2-specific things. + +Tests 6 and 7 check the pcre2_dfa_match() alternative matching function, in +non-UTF mode and UTF-mode with Unicode property support, respectively. + +Test 8 checks some internal offsets and code size features; it is run only when +the default "link size" of 2 is set (in other cases the sizes change) and when +Unicode support is enabled. + +Tests 9 and 10 are run only in 8-bit mode, and tests 11 and 12 are run only in +16-bit and 32-bit modes. These are tests that generate different output in +8-bit mode. Each pair are for general cases and Unicode support, respectively. +Test 13 checks the handling of non-UTF characters greater than 255 by +pcre2_dfa_match() in 16-bit and 32-bit modes. + +Test 14 contains a number of tests that must not be run with JIT. They check, +among other non-JIT things, the match-limiting features of the intepretive +matcher. + +Test 15 is run only when JIT support is not available. It checks that an +attempt to use JIT has the expected behaviour. + +Test 16 is run only when JIT support is available. It checks JIT complete and +partial modes, match-limiting under JIT, and other JIT-specific features. + +Tests 17 and 18 are run only in 8-bit mode. They check the POSIX interface to +the 8-bit library, without and with Unicode support, respectively. + +Test 19 checks the serialization functions by writing a set of compiled +patterns to a file, and then reloading and checking them. + + +Character tables +---------------- + +For speed, PCRE2 uses four tables for manipulating and identifying characters +whose code point values are less than 256. By default, a set of tables that is +built into the library is used. The pcre2_maketables() function can be called +by an application to create a new set of tables in the current locale. This are +passed to PCRE2 by calling pcre2_set_character_tables() to put a pointer into a +compile context. + +The source file called pcre2_chartables.c contains the default set of tables. +By default, this is created as a copy of pcre2_chartables.c.dist, which +contains tables for ASCII coding. However, if --enable-rebuild-chartables is +specified for ./configure, a different version of pcre2_chartables.c is built +by the program dftables (compiled from dftables.c), which uses the ANSI C +character handling functions such as isalnum(), isalpha(), isupper(), +islower(), etc. to build the table sources. This means that the default C +locale which is set for your system will control the contents of these default +tables. You can change the default tables by editing pcre2_chartables.c and +then re-building PCRE2. If you do this, you should take care to ensure that the +file does not get automatically re-generated. The best way to do this is to +move pcre2_chartables.c.dist out of the way and replace it with your customized +tables. + +When the dftables program is run as a result of --enable-rebuild-chartables, +it uses the default C locale that is set on your system. It does not pay +attention to the LC_xxx environment variables. In other words, it uses the +system's default locale rather than whatever the compiling user happens to have +set. If you really do want to build a source set of character tables in a +locale that is specified by the LC_xxx variables, you can run the dftables +program by hand with the -L option. For example: + + ./dftables -L pcre2_chartables.c.special + +The first two 256-byte tables provide lower casing and case flipping functions, +respectively. The next table consists of three 32-byte bit maps which identify +digits, "word" characters, and white space, respectively. These are used when +building 32-byte bit maps that represent character classes for code points less +than 256. The final 256-byte table has bits indicating various character types, +as follows: + + 1 white space character + 2 letter + 4 decimal digit + 8 hexadecimal digit + 16 alphanumeric or '_' + 128 regular expression metacharacter or binary zero + +You should not alter the set of characters that contain the 128 bit, as that +will cause PCRE2 to malfunction. + + +File manifest +------------- + +The distribution should contain the files listed below. + +(A) Source files for the PCRE2 library functions and their headers are found in + the src directory: + + src/dftables.c auxiliary program for building pcre2_chartables.c + when --enable-rebuild-chartables is specified + + src/pcre2_chartables.c.dist a default set of character tables that assume + ASCII coding; unless --enable-rebuild-chartables is + specified, used by copying to pcre2_chartables.c + + src/pcre2posix.c ) + src/pcre2_auto_possess.c ) + src/pcre2_compile.c ) + src/pcre2_config.c ) + src/pcre2_context.c ) + src/pcre2_dfa_match.c ) + src/pcre2_error.c ) + src/pcre2_jit_compile.c ) + src/pcre2_jit_match.c ) sources for the functions in the library, + src/pcre2_jit_misc.c ) and some internal functions that they use + src/pcre2_maketables.c ) + src/pcre2_match.c ) + src/pcre2_match_data.c ) + src/pcre2_newline.c ) + src/pcre2_ord2utf.c ) + src/pcre2_pattern_info.c ) + src/pcre2_serialize.c ) + src/pcre2_string_utils.c ) + src/pcre2_study.c ) + src/pcre2_substitute.c ) + src/pcre2_substring.c ) + src/pcre2_tables.c ) + src/pcre2_ucd.c ) + src/pcre2_valid_utf.c ) + src/pcre2_xclass.c ) + + src/pcre2_printint.c debugging function that is used by pcre2test, + + src/config.h.in template for config.h, when built by "configure" + src/pcre2.h.in template for pcre2.h when built by "configure" + src/pcre2posix.h header for the external POSIX wrapper API + src/pcre2_internal.h header for internal use + src/pcre2_intmodedep.h a mode-specific internal header + src/pcre2_ucp.h header for Unicode property handling + + sljit/* source files for the JIT compiler + +(B) Source files for programs that use PCRE2: + + src/pcre2demo.c simple demonstration of coding calls to PCRE2 + src/pcre2grep.c source of a grep utility that uses PCRE2 + src/pcre2test.c comprehensive test program + src/pcre2_printint.c part of pcre2test + src/pcre2_jit_test.c JIT test program + +(C) Auxiliary files: + + 132html script to turn "man" pages into HTML + AUTHORS information about the author of PCRE2 + ChangeLog log of changes to the code + CleanTxt script to clean nroff output for txt man pages + Detrail script to remove trailing spaces + HACKING some notes about the internals of PCRE2 + INSTALL generic installation instructions + LICENCE conditions for the use of PCRE2 + COPYING the same, using GNU's standard name + Makefile.in ) template for Unix Makefile, which is built by + ) "configure" + Makefile.am ) the automake input that was used to create + ) Makefile.in + NEWS important changes in this release + NON-AUTOTOOLS-BUILD notes on building PCRE2 without using autotools + PrepareRelease script to make preparations for "make dist" + README this file + RunTest a Unix shell script for running tests + RunGrepTest a Unix shell script for pcre2grep tests + aclocal.m4 m4 macros (generated by "aclocal") + config.guess ) files used by libtool, + config.sub ) used only when building a shared library + configure a configuring shell script (built by autoconf) + configure.ac ) the autoconf input that was used to build + ) "configure" and config.h + depcomp ) script to find program dependencies, generated by + ) automake + doc/*.3 man page sources for PCRE2 + doc/*.1 man page sources for pcre2grep and pcre2test + doc/index.html.src the base HTML page + doc/html/* HTML documentation + doc/pcre2.txt plain text version of the man pages + doc/pcre2test.txt plain text documentation of test program + install-sh a shell script for installing files + libpcre2-8.pc.in template for libpcre2-8.pc for pkg-config + libpcre2-16.pc.in template for libpcre2-16.pc for pkg-config + libpcre2-32.pc.in template for libpcre2-32.pc for pkg-config + libpcre2posix.pc.in template for libpcre2posix.pc for pkg-config + ltmain.sh file used to build a libtool script + missing ) common stub for a few missing GNU programs while + ) installing, generated by automake + mkinstalldirs script for making install directories + perltest.sh Script for running a Perl test program + pcre2-config.in source of script which retains PCRE2 information + testdata/testinput* test data for main library tests + testdata/testoutput* expected test results + testdata/grep* input and output for pcre2grep tests + testdata/* other supporting test files + +(D) Auxiliary files for cmake support + + cmake/COPYING-CMAKE-SCRIPTS + cmake/FindPackageHandleStandardArgs.cmake + cmake/FindEditline.cmake + cmake/FindReadline.cmake + CMakeLists.txt + config-cmake.h.in + +(E) Auxiliary files for building PCRE2 "by hand" + + pcre2.h.generic ) a version of the public PCRE2 header file + ) for use in non-"configure" environments + config.h.generic ) a version of config.h for use in non-"configure" + ) environments + +Philip Hazel +Email local part: ph10 +Email domain: cam.ac.uk +Last updated: 24 April 2015 diff --git a/pcre2-10.20/doc/html/index.html b/pcre2-10.20/doc/html/index.html new file mode 100644 index 000000000..ae938fd3c --- /dev/null +++ b/pcre2-10.20/doc/html/index.html @@ -0,0 +1,264 @@ + + + +PCRE2 specification + + +

Perl-compatible Regular Expressions (revised API: PCRE2)

+

+The HTML documentation for PCRE2 consists of a number of pages that are listed +below in alphabetical order. If you are new to PCRE2, please read the first one +first. +

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
pcre2  Introductory page
pcre2-config  Information about the installation configuration
pcre2api  PCRE2's native API
pcre2build  Building PCRE2
pcre2callout  The callout facility
pcre2compat  Compability with Perl
pcre2demo  A demonstration C program that uses the PCRE2 library
pcre2grep  The pcre2grep command
pcre2jit  Discussion of the just-in-time optimization support
pcre2limits  Details of size and other limits
pcre2matching  Discussion of the two matching algorithms
pcre2partial  Using PCRE2 for partial matching
pcre2pattern  Specification of the regular expressions supported by PCRE2
pcre2perform  Some comments on performance
pcre2posix  The POSIX API to the PCRE2 8-bit library
pcre2sample  Discussion of the pcre2demo program
pcre2serialize  Serializing functions for saving precompiled patterns
pcre2stack  Discussion of PCRE2's stack usage
pcre2syntax  Syntax quick-reference summary
pcre2test  The pcre2test command for testing PCRE2
pcre2unicode  Discussion of Unicode and UTF-8/UTF-16/UTF-32 support
+ +

+There are also individual pages that summarize the interface for each function +in the library. +

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
pcre2_callout_enumerate  Enumerate callouts in a compiled pattern
pcre2_code_free  Free a compiled pattern
pcre2_compile  Compile a regular expression pattern
pcre2_compile_context_copy  Copy a compile context
pcre2_compile_context_create  Create a compile context
pcre2_compile_context_free  Free a compile context
pcre2_config  Show build-time configuration options
pcre2_dfa_match  Match a compiled pattern to a subject string + (DFA algorithm; not Perl compatible)
pcre2_general_context_copy  Copy a general context
pcre2_general_context_create  Create a general context
pcre2_general_context_free  Free a general context
pcre2_get_error_message  Free study data
pcre2_get_mark  Get a (*MARK) name
pcre2_get_ovector_count  Get the ovector count
pcre2_get_ovector_pointer  Get a pointer to the ovector
pcre2_get_startchar  Get the starting character offset
pcre2_jit_compile  Process a compiled pattern with the JIT compiler
pcre2_jit_free_unused_memory  Free unused JIT memory
pcre2_jit_match  Fast path interface to JIT matching
pcre2_jit_stack_assign  Assign stack for JIT matching
pcre2_jit_stack_create  Create a stack for JIT matching
pcre2_jit_stack_free  Free a JIT matching stack
pcre2_maketables  Build character tables in current locale
pcre2_match  Match a compiled pattern to a subject string + (Perl compatible)
pcre2_match_context_copy  Copy a match context
pcre2_match_context_create  Create a match context
pcre2_match_context_free  Free a match context
pcre2_match_data_create  Create a match data block
pcre2_match_data_create_from_pattern  Create a match data block getting size from pattern
pcre2_match_data_free  Free a match data block
pcre2_pattern_info  Extract information about a pattern
pcre2_serialize_decode  Decode serialized compiled patterns
pcre2_serialize_encode  Serialize compiled patterns for save/restore
pcre2_serialize_free  Free serialized compiled patterns
pcre2_serialize_get_number_of_codes  Get number of serialized compiled patterns
pcre2_set_bsr  Set \R convention
pcre2_set_callout  Set up a callout function
pcre2_set_character_tables  Set character tables
pcre2_set_compile_recursion_guard  Set up a compile recursion guard function
pcre2_set_match_limit  Set the match limit
pcre2_set_newline  Set the newline convention
pcre2_set_parens_nest_limit  Set the parentheses nesting limit
pcre2_set_recursion_limit  Set the match recursion limit
pcre2_set_recursion_memory_management  Set match recursion memory management
pcre2_substitute  Match a compiled pattern to a subject string and do + substitutions
pcre2_substring_copy_byname  Extract named substring into given buffer
pcre2_substring_copy_bynumber  Extract numbered substring into given buffer
pcre2_substring_free  Free extracted substring
pcre2_substring_get_byname  Extract named substring into new memory
pcre2_substring_get_bynumber  Extract numbered substring into new memory
pcre2_substring_length_byname  Find length of named substring
pcre2_substring_length_bynumber  Find length of numbered substring
pcre2_substring_list_free  Free list of extracted substrings
pcre2_substring_list_get  Extract all substrings into new memory
pcre2_substring_nametable_scan  Find table entries for given string name
pcre2_substring_number_from_name  Convert captured string name to number
+ + + diff --git a/pcre2-10.20/doc/html/pcre2-config.html b/pcre2-10.20/doc/html/pcre2-config.html new file mode 100644 index 000000000..b71d76026 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2-config.html @@ -0,0 +1,102 @@ + + +pcre2-config specification + + +

pcre2-config man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+

+
SYNOPSIS
+

+pcre2-config [--prefix] [--exec-prefix] [--version] + [--libs8] [--libs16] [--libs32] [--libs-posix] + [--cflags] [--cflags-posix] +

+
DESCRIPTION
+

+pcre2-config returns the configuration of the installed PCRE2 libraries +and the options required to compile a program to use them. Some of the options +apply only to the 8-bit, or 16-bit, or 32-bit libraries, respectively, and are +not available for libraries that have not been built. If an unavailable option +is encountered, the "usage" information is output. +

+
OPTIONS
+

+--prefix +Writes the directory prefix used in the PCRE2 installation for architecture +independent files (/usr on many systems, /usr/local on some +systems) to the standard output. +

+

+--exec-prefix +Writes the directory prefix used in the PCRE2 installation for architecture +dependent files (normally the same as --prefix) to the standard output. +

+

+--version +Writes the version number of the installed PCRE2 libraries to the standard +output. +

+

+--libs8 +Writes to the standard output the command line options required to link +with the 8-bit PCRE2 library (-lpcre2-8 on many systems). +

+

+--libs16 +Writes to the standard output the command line options required to link +with the 16-bit PCRE2 library (-lpcre2-16 on many systems). +

+

+--libs32 +Writes to the standard output the command line options required to link +with the 32-bit PCRE2 library (-lpcre2-32 on many systems). +

+

+--libs-posix +Writes to the standard output the command line options required to link with +PCRE2's POSIX API wrapper library (-lpcre2-posix -lpcre2-8 on many +systems). +

+

+--cflags +Writes to the standard output the command line options required to compile +files that use PCRE2 (this may include some -I options, but is blank on +many systems). +

+

+--cflags-posix +Writes to the standard output the command line options required to compile +files that use PCRE2's POSIX API wrapper library (this may include some +-I options, but is blank on many systems). +

+
SEE ALSO
+

+pcre2(3) +

+
AUTHOR
+

+This manual page was originally written by Mark Baker for the Debian GNU/Linux +system. It has been subsequently revised as a generic PCRE2 man page. +

+
REVISION
+

+Last updated: 28 September 2014 +
+

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2.html b/pcre2-10.20/doc/html/pcre2.html new file mode 100644 index 000000000..e94b355a3 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2.html @@ -0,0 +1,196 @@ + + +pcre2 specification + + +

pcre2 man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+

+
INTRODUCTION
+

+PCRE2 is the name used for a revised API for the PCRE library, which is a set +of functions, written in C, that implement regular expression pattern matching +using the same syntax and semantics as Perl, with just a few differences. Some +features that appeared in Python and the original PCRE before they appeared in +Perl are also available using the Python syntax. There is also some support for +one or two .NET and Oniguruma syntax items, and there are options for +requesting some minor changes that give better ECMAScript (aka JavaScript) +compatibility. +

+

+The source code for PCRE2 can be compiled to support 8-bit, 16-bit, or 32-bit +code units, which means that up to three separate libraries may be installed. +The original work to extend PCRE to 16-bit and 32-bit code units was done by +Zoltan Herczeg and Christian Persch, respectively. In all three cases, strings +can be interpreted either as one character per code unit, or as UTF-encoded +Unicode, with support for Unicode general category properties. Unicode support +is optional at build time (but is the default). However, processing strings as +UTF code units must be enabled explicitly at run time. The version of Unicode +in use can be discovered by running +

+  pcre2test -C
+
+

+

+The three libraries contain identical sets of functions, with names ending in +_8, _16, or _32, respectively (for example, pcre2_compile_8()). However, +by defining PCRE2_CODE_UNIT_WIDTH to be 8, 16, or 32, a program that uses just +one code unit width can be written using generic names such as +pcre2_compile(), and the documentation is written assuming that this is +the case. +

+

+In addition to the Perl-compatible matching function, PCRE2 contains an +alternative function that matches the same compiled patterns in a different +way. In certain circumstances, the alternative function has some advantages. +For a discussion of the two matching algorithms, see the +pcre2matching +page. +

+

+Details of exactly which Perl regular expression features are and are not +supported by PCRE2 are given in separate documents. See the +pcre2pattern +and +pcre2compat +pages. There is a syntax summary in the +pcre2syntax +page. +

+

+Some features of PCRE2 can be included, excluded, or changed when the library +is built. The +pcre2_config() +function makes it possible for a client to discover which features are +available. The features themselves are described in the +pcre2build +page. Documentation about building PCRE2 for various operating systems can be +found in the +README +and +NON-AUTOTOOLS_BUILD +files in the source distribution. +

+

+The libraries contains a number of undocumented internal functions and data +tables that are used by more than one of the exported external functions, but +which are not intended for use by external callers. Their names all begin with +"_pcre2", which hopefully will not provoke any name clashes. In some +environments, it is possible to control which external symbols are exported +when a shared library is built, and in these cases the undocumented symbols are +not exported. +

+
SECURITY CONSIDERATIONS
+

+If you are using PCRE2 in a non-UTF application that permits users to supply +arbitrary patterns for compilation, you should be aware of a feature that +allows users to turn on UTF support from within a pattern. For example, an +8-bit pattern that begins with "(*UTF)" turns on UTF-8 mode, which interprets +patterns and subjects as strings of UTF-8 code units instead of individual +8-bit characters. This causes both the pattern and any data against which it is +matched to be checked for UTF-8 validity. If the data string is very long, such +a check might use sufficiently many resources as to cause your application to +lose performance. +

+

+One way of guarding against this possibility is to use the +pcre2_pattern_info() function to check the compiled pattern's options for +PCRE2_UTF. Alternatively, you can set the PCRE2_NEVER_UTF option when calling +pcre2_compile(). This causes an compile time error if a pattern contains +a UTF-setting sequence. +

+

+The use of Unicode properties for character types such as \d can also be +enabled from within the pattern, by specifying "(*UCP)". This feature can be +disallowed by setting the PCRE2_NEVER_UCP option. +

+

+If your application is one that supports UTF, be aware that validity checking +can take time. If the same data string is to be matched many times, you can use +the PCRE2_NO_UTF_CHECK option for the second and subsequent matches to avoid +running redundant checks. +

+

+The use of the \C escape sequence in a UTF-8 or UTF-16 pattern can lead to +problems, because it may leave the current matching point in the middle of a +multi-code-unit character. The PCRE2_NEVER_BACKSLASH_C option can be used to +lock out the use of \C, causing a compile-time error if it is encountered. +

+

+Another way that performance can be hit is by running a pattern that has a very +large search tree against a string that will never match. Nested unlimited +repeats in a pattern are a common example. PCRE2 provides some protection +against this: see the pcre2_set_match_limit() function in the +pcre2api +page. +

+
USER DOCUMENTATION
+

+The user documentation for PCRE2 comprises a number of different sections. In +the "man" format, each of these is a separate "man page". In the HTML format, +each is a separate page, linked from the index page. In the plain text format, +the descriptions of the pcre2grep and pcre2test programs are in +files called pcre2grep.txt and pcre2test.txt, respectively. The +remaining sections, except for the pcre2demo section (which is a program +listing), and the short pages for individual functions, are concatenated in +pcre2.txt, for ease of searching. The sections are as follows: +

+  pcre2              this document
+  pcre2-config       show PCRE2 installation configuration information
+  pcre2api           details of PCRE2's native C API
+  pcre2build         building PCRE2
+  pcre2callout       details of the callout feature
+  pcre2compat        discussion of Perl compatibility
+  pcre2demo          a demonstration C program that uses PCRE2
+  pcre2grep          description of the pcre2grep command (8-bit only)
+  pcre2jit           discussion of just-in-time optimization support
+  pcre2limits        details of size and other limits
+  pcre2matching      discussion of the two matching algorithms
+  pcre2partial       details of the partial matching facility
+  pcre2pattern       syntax and semantics of supported regular expression patterns
+  pcre2perform       discussion of performance issues
+  pcre2posix         the POSIX-compatible C API for the 8-bit library
+  pcre2sample        discussion of the pcre2demo program
+  pcre2stack         discussion of stack usage
+  pcre2syntax        quick syntax reference
+  pcre2test          description of the pcre2test command
+  pcre2unicode       discussion of Unicode and UTF support
+
+In the "man" and HTML formats, there is also a short page for each C library +function, listing its arguments and results. +

+
AUTHOR
+

+Philip Hazel +
+University Computing Service +
+Cambridge, England. +
+

+

+Putting an actual email address here is a spam magnet. If you want to email me, +use my two initials, followed by the two digits 10, at the domain cam.ac.uk. +

+
REVISION
+

+Last updated: 13 April 2015 +
+Copyright © 1997-2015 University of Cambridge. +
+

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_callout_enumerate.html b/pcre2-10.20/doc/html/pcre2_callout_enumerate.html new file mode 100644 index 000000000..6c2cdb87a --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_callout_enumerate.html @@ -0,0 +1,62 @@ + + +pcre2_callout_enumerate specification + + +

pcre2_callout_enumerate man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_callout_enumerate(const pcre2_code *code, + int (*callback)(pcre2_callout_enumerate_block *, void *), + void *callout_data); +

+
+DESCRIPTION +
+

+This function scans a compiled regular expression and calls the callback() +function for each callout within the pattern. The yield of the function is zero +for success and non-zero otherwise. The arguments are: +

+  code           Points to the compiled pattern
+  callback       The callback function
+  callout_data   User data that is passed to the callback
+
+The callback() function is passed a pointer to a data block containing +the following fields: +
+  version                Block version number
+  pattern_position       Offset to next item in pattern
+  next_item_length       Length of next item in pattern
+  callout_number         Number for numbered callouts
+  callout_string_offset  Offset to string within pattern
+  callout_string_length  Length of callout string
+  callout_string         Points to callout string or is NULL
+
+The second argument is the callout data that was passed to +pcre2_callout_enumerate(). The callback() function must return zero +for success. Any other value causes the pattern scan to stop, with the value +being passed back as the result of pcre2_callout_enumerate(). +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_code_free.html b/pcre2-10.20/doc/html/pcre2_code_free.html new file mode 100644 index 000000000..405d16466 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_code_free.html @@ -0,0 +1,39 @@ + + +pcre2_code_free specification + + +

pcre2_code_free man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+pcre2_code_free(pcre2_code *code); +

+
+DESCRIPTION +
+

+This function frees the memory used for a compiled pattern, including any +memory used by the JIT compiler. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_compile.html b/pcre2-10.20/doc/html/pcre2_compile.html new file mode 100644 index 000000000..544f4feb4 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_compile.html @@ -0,0 +1,91 @@ + + +pcre2_compile specification + + +

pcre2_compile man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+pcre2_code *pcre2_compile(PCRE2_SPTR pattern, PCRE2_SIZE length, + uint32_t options, int *errorcode, PCRE2_SIZE *erroroffset, + pcre2_compile_context *ccontext); +

+
+DESCRIPTION +
+

+This function compiles a regular expression pattern into an internal form. Its +arguments are: +

+  pattern       A string containing expression to be compiled
+  length        The length of the string or PCRE2_ZERO_TERMINATED
+  options       Option bits
+  errorcode     Where to put an error code
+  erroffset     Where to put an error offset
+  ccontext      Pointer to a compile context or NULL
+
+The length of the string and any error offset that is returned are in code +units, not characters. A compile context is needed only if you want to change +
+  What \R matches (Unicode newlines or CR, LF, CRLF only)
+  PCRE2's character tables
+  The newline character sequence
+  The compile time nested parentheses limit
+
+or provide an external function for stack size checking. The option bits are: +
+  PCRE2_ANCHORED           Force pattern anchoring
+  PCRE2_ALT_BSUX           Alternative handling of \u, \U, and \x
+  PCRE2_ALT_CIRCUMFLEX     Alternative handling of ^ in multiline mode
+  PCRE2_AUTO_CALLOUT       Compile automatic callouts
+  PCRE2_CASELESS           Do caseless matching
+  PCRE2_DOLLAR_ENDONLY     $ not to match newline at end
+  PCRE2_DOTALL             . matches anything including NL
+  PCRE2_DUPNAMES           Allow duplicate names for subpatterns
+  PCRE2_EXTENDED           Ignore white space and # comments
+  PCRE2_FIRSTLINE          Force matching to be before newline
+  PCRE2_MATCH_UNSET_BACKREF  Match unset back references
+  PCRE2_MULTILINE          ^ and $ match newlines within data
+  PCRE2_NEVER_BACKSLASH_C  Lock out the use of \C in patterns
+  PCRE2_NEVER_UCP          Lock out PCRE2_UCP, e.g. via (*UCP)
+  PCRE2_NEVER_UTF          Lock out PCRE2_UTF, e.g. via (*UTF)
+  PCRE2_NO_AUTO_CAPTURE    Disable numbered capturing paren-
+                            theses (named ones available)
+  PCRE2_NO_AUTO_POSSESS    Disable auto-possessification
+  PCRE2_NO_DOTSTAR_ANCHOR  Disable automatic anchoring for .*
+  PCRE2_NO_START_OPTIMIZE  Disable match-time start optimizations
+  PCRE2_NO_UTF_CHECK       Do not check the pattern for UTF validity
+                             (only relevant if PCRE2_UTF is set)
+  PCRE2_UCP                Use Unicode properties for \d, \w, etc.
+  PCRE2_UNGREEDY           Invert greediness of quantifiers
+  PCRE2_UTF                Treat pattern and subjects as UTF strings
+
+PCRE2 must be built with Unicode support in order to use PCRE2_UTF, PCRE2_UCP +and related options. +

+

+The yield of the function is a pointer to a private data structure that +contains the compiled pattern, or NULL if an error was detected. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_compile_context_copy.html b/pcre2-10.20/doc/html/pcre2_compile_context_copy.html new file mode 100644 index 000000000..9e9884b83 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_compile_context_copy.html @@ -0,0 +1,41 @@ + + +pcre2_compile_context_copy specification + + +

pcre2_compile_context_copy man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+pcre2_compile_context *pcre2_compile_context_copy( + pcre2_compile_context *ccontext); +

+
+DESCRIPTION +
+

+This function makes a new copy of a compile context, using the memory +allocation function that was used for the original context. The result is NULL +if the memory cannot be obtained. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_compile_context_create.html b/pcre2-10.20/doc/html/pcre2_compile_context_create.html new file mode 100644 index 000000000..5eacd4ec7 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_compile_context_create.html @@ -0,0 +1,42 @@ + + +pcre2_compile_context_create specification + + +

pcre2_compile_context_create man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+pcre2_compile_context *pcre2_compile_context_create( + pcre2_general_context *gcontext); +

+
+DESCRIPTION +
+

+This function creates and initializes a new compile context. If its argument is +NULL, malloc() is used to get the necessary memory; otherwise the memory +allocation function within the general context is used. The result is NULL if +the memory could not be obtained. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_compile_context_free.html b/pcre2-10.20/doc/html/pcre2_compile_context_free.html new file mode 100644 index 000000000..ea67a18a0 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_compile_context_free.html @@ -0,0 +1,40 @@ + + +pcre2_compile_context_free specification + + +

pcre2_compile_context_free man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+void pcre2_compile_context_free(pcre2_compile_context *ccontext); +

+
+DESCRIPTION +
+

+This function frees the memory occupied by a compile context, using the memory +freeing function from the general context with which it was created, or +free() if that was not set. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_config.html b/pcre2-10.20/doc/html/pcre2_config.html new file mode 100644 index 000000000..a51b0c7b0 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_config.html @@ -0,0 +1,83 @@ + + +pcre2_config specification + + +

pcre2_config man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_config(uint32_t what, void *where); +

+
+DESCRIPTION +
+

+This function makes it possible for a client program to find out which optional +features are available in the version of the PCRE2 library it is using. The +arguments are as follows: +

+  what     A code specifying what information is required
+  where    Points to where to put the information
+
+If where is NULL, the function returns the amount of memory needed for +the requested information. When the information is a string, the value is in +code units; for other types of data it is in bytes. +

+

+If where is not NULL, for PCRE2_CONFIG_JITTARGET, +PCRE2_CONFIG_UNICODE_VERSION, and PCRE2_CONFIG_VERSION it must point to a +buffer that is large enough to hold the string. For all other codes it must +point to a uint32_t integer variable. The available codes are: +

+  PCRE2_CONFIG_BSR             Indicates what \R matches by default:
+                                 PCRE2_BSR_UNICODE
+                                 PCRE2_BSR_ANYCRLF
+  PCRE2_CONFIG_JIT             Availability of just-in-time compiler
+                                support (1=yes 0=no)
+  PCRE2_CONFIG_JITTARGET       Information about the target archi-
+                                 tecture for the JIT compiler
+  PCRE2_CONFIG_LINKSIZE        Configured internal link size (2, 3, 4)
+  PCRE2_CONFIG_MATCHLIMIT      Default internal resource limit
+  PCRE2_CONFIG_NEWLINE         Code for the default newline sequence:
+                                 PCRE2_NEWLINE_CR
+                                 PCRE2_NEWLINE_LF
+                                 PCRE2_NEWLINE_CRLF
+                                 PCRE2_NEWLINE_ANY
+                                 PCRE2_NEWLINE_ANYCRLF
+  PCRE2_CONFIG_PARENSLIMIT     Default parentheses nesting limit
+  PCRE2_CONFIG_RECURSIONLIMIT  Internal recursion depth limit
+  PCRE2_CONFIG_STACKRECURSE    Recursion implementation (1=stack
+                                 0=heap)
+  PCRE2_CONFIG_UNICODE         Availability of Unicode support (1=yes
+                                 0=no)
+  PCRE2_CONFIG_UNICODE_VERSION The Unicode version (a string)
+  PCRE2_CONFIG_VERSION         The PCRE2 version (a string)
+
+The function yields a non-negative value on success or the negative value +PCRE2_ERROR_BADOPTION otherwise. This is also the result for the +PCRE2_CONFIG_JITTARGET code if JIT support is not available. When a string is +requested, the function returns the number of code units used, including the +terminating zero. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_dfa_match.html b/pcre2-10.20/doc/html/pcre2_dfa_match.html new file mode 100644 index 000000000..e137a14a8 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_dfa_match.html @@ -0,0 +1,79 @@ + + +pcre2_dfa_match specification + + +

pcre2_dfa_match man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_dfa_match(const pcre2_code *code, PCRE2_SPTR subject, + PCRE2_SIZE length, PCRE2_SIZE startoffset, + uint32_t options, pcre2_match_data *match_data, + pcre2_match_context *mcontext, + int *workspace, PCRE2_SIZE wscount); +

+
+DESCRIPTION +
+

+This function matches a compiled regular expression against a given subject +string, using an alternative matching algorithm that scans the subject string +just once (not Perl-compatible). (The Perl-compatible matching function +is pcre2_match().) The arguments for this function are: +

+  code         Points to the compiled pattern
+  subject      Points to the subject string
+  length       Length of the subject string
+  startoffset  Offset in the subject at which to start matching
+  options      Option bits
+  match_data   Points to a match data block, for results
+  mcontext     Points to a match context, or is NULL
+  workspace    Points to a vector of ints used as working space
+  wscount      Number of elements in the vector
+
+For pcre2_dfa_match(), a match context is needed only if you want to set +up a callout function. The length and startoffset values are code +units, not characters. The options are: +
+  PCRE2_ANCHORED          Match only at the first position
+  PCRE2_NOTBOL            Subject is not the beginning of a line
+  PCRE2_NOTEOL            Subject is not the end of a line
+  PCRE2_NOTEMPTY          An empty string is not a valid match
+  PCRE2_NOTEMPTY_ATSTART  An empty string at the start of the subject
+                           is not a valid match
+  PCRE2_NO_UTF_CHECK      Do not check the subject for UTF
+                           validity (only relevant if PCRE2_UTF
+                           was set at compile time)
+  PCRE2_PARTIAL_SOFT      Return PCRE2_ERROR_PARTIAL for a partial
+                            match if no full matches are found
+  PCRE2_PARTIAL_HARD      Return PCRE2_ERROR_PARTIAL for a partial match
+                           even if there is a full match as well
+  PCRE2_DFA_RESTART       Restart after a partial match
+  PCRE2_DFA_SHORTEST      Return only the shortest match
+
+There are restrictions on what may appear in a pattern when using this matching +function. Details are given in the +pcre2matching +documentation. For details of partial matching, see the +pcre2partial +page. There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_general_context_copy.html b/pcre2-10.20/doc/html/pcre2_general_context_copy.html new file mode 100644 index 000000000..001853468 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_general_context_copy.html @@ -0,0 +1,42 @@ + + +pcre2_general_context_copy specification + + +

pcre2_general_context_copy man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+pcre2_general_context *pcre2_general_context_copy( + pcre2_general_context *gcontext); +

+
+DESCRIPTION +
+

+This function makes a new copy of a general context, using the memory +allocation functions in the context, if set, to get the necessary memory. +Otherwise malloc() is used. The result is NULL if the memory cannot be +obtained. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_general_context_create.html b/pcre2-10.20/doc/html/pcre2_general_context_create.html new file mode 100644 index 000000000..bc31ee82f --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_general_context_create.html @@ -0,0 +1,44 @@ + + +pcre2_general_context_create specification + + +

pcre2_general_context_create man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+pcre2_general_context *pcre2_general_context_create( + void *(*private_malloc)(PCRE2_SIZE, void *), + void (*private_free)(void *, void *), void *memory_data); +

+
+DESCRIPTION +
+

+This function creates and initializes a general context. The arguments define +custom memory management functions and a data value that is passed to them when +they are called. The private_malloc() function is used to get memory for +the context. If either of the first two arguments is NULL, the system memory +management function is used. The result is NULL if no memory could be obtained. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_general_context_free.html b/pcre2-10.20/doc/html/pcre2_general_context_free.html new file mode 100644 index 000000000..ec818efde --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_general_context_free.html @@ -0,0 +1,39 @@ + + +pcre2_general_context_free specification + + +

pcre2_general_context_free man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+void pcre2_general_context_free(pcre2_general_context *gcontext); +

+
+DESCRIPTION +
+

+This function frees the memory occupied by a general context, using the memory +freeing function within the context, if set. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_get_error_message.html b/pcre2-10.20/doc/html/pcre2_get_error_message.html new file mode 100644 index 000000000..5d422913e --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_get_error_message.html @@ -0,0 +1,48 @@ + + +pcre2_get_error_message specification + + +

pcre2_get_error_message man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_get_error_message(int errorcode, PCRE2_UCHAR *buffer, + PCRE2_SIZE bufflen); +

+
+DESCRIPTION +
+

+This function provides a textual error message for each PCRE2 error code. +Compilation errors are positive numbers; UTF formatting errors and matching +errors are negative numbers. The arguments are: +

+  errorcode   an error code (positive or negative)
+  buffer      where to put the message
+  bufflen     the length of the buffer (code units)
+
+The function returns the length of the message, excluding the trailing zero, or +a negative error code if the buffer is too small. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_get_mark.html b/pcre2-10.20/doc/html/pcre2_get_mark.html new file mode 100644 index 000000000..f8e50e388 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_get_mark.html @@ -0,0 +1,43 @@ + + +pcre2_get_mark specification + + +

pcre2_get_mark man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+PCRE2_SPTR pcre2_get_mark(pcre2_match_data *match_data); +

+
+DESCRIPTION +
+

+After a call of pcre2_match() that was passed the match block that is +this function's argument, this function returns a pointer to the last (*MARK) +name that was encountered. The name is zero-terminated, and is within the +compiled pattern. If no (*MARK) name is available, NULL is returned. A (*MARK) +name may be available after a failed match or a partial match, as well as after +a successful one. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_get_ovector_count.html b/pcre2-10.20/doc/html/pcre2_get_ovector_count.html new file mode 100644 index 000000000..05aacb6de --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_get_ovector_count.html @@ -0,0 +1,39 @@ + + +pcre2_get_ovector_count specification + + +

pcre2_get_ovector_count man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+uint32_t pcre2_get_ovector_count(pcre2_match_data *match_data); +

+
+DESCRIPTION +
+

+This function returns the number of pairs of offsets in the ovector that forms +part of the given match data block. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_get_ovector_pointer.html b/pcre2-10.20/doc/html/pcre2_get_ovector_pointer.html new file mode 100644 index 000000000..ff6317efc --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_get_ovector_pointer.html @@ -0,0 +1,40 @@ + + +pcre2_get_ovector_pointer specification + + +

pcre2_get_ovector_pointer man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *match_data); +

+
+DESCRIPTION +
+

+This function returns a pointer to the vector of offsets that forms part of the +given match data block. The number of pairs can be found by calling +pcre2_get_ovector_count(). +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_get_startchar.html b/pcre2-10.20/doc/html/pcre2_get_startchar.html new file mode 100644 index 000000000..d2c28b2ab --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_get_startchar.html @@ -0,0 +1,44 @@ + + +pcre2_get_startchar specification + + +

pcre2_get_startchar man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *match_data); +

+
+DESCRIPTION +
+

+After a successful call of pcre2_match() that was passed the match block +that is this function's argument, this function returns the code unit offset of +the character at which the successful match started. For a non-partial match, +this can be different to the value of ovector[0] if the pattern contains +the \K escape sequence. After a partial match, however, this value is always +the same as ovector[0] because \K does not affect the result of a +partial match. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_jit_compile.html b/pcre2-10.20/doc/html/pcre2_jit_compile.html new file mode 100644 index 000000000..15b0138b1 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_jit_compile.html @@ -0,0 +1,56 @@ + + +pcre2_jit_compile specification + + +

pcre2_jit_compile man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_jit_compile(pcre2_code *code, uint32_t options); +

+
+DESCRIPTION +
+

+This function requests JIT compilation, which, if the just-in-time compiler is +available, further processes a compiled pattern into machine code that executes +much faster than the pcre2_match() interpretive matching function. Full +details are given in the +pcre2jit +documentation. +

+

+The first argument is a pointer that was returned by a successful call to +pcre2_compile(), and the second must contain one or more of the following +bits: +

+  PCRE2_JIT_COMPLETE      compile code for full matching
+  PCRE2_JIT_PARTIAL_SOFT  compile code for soft partial matching
+  PCRE2_JIT_PARTIAL_HARD  compile code for hard partial matching
+
+The yield of the function is 0 for success, or a negative error code otherwise. +In particular, PCRE2_ERROR_JIT_BADOPTION is returned if JIT is not supported or +if an unknown bit is set in options. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_jit_free_unused_memory.html b/pcre2-10.20/doc/html/pcre2_jit_free_unused_memory.html new file mode 100644 index 000000000..8b59b8e17 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_jit_free_unused_memory.html @@ -0,0 +1,43 @@ + + +pcre2_jit_free_unused_memory specification + + +

pcre2_jit_free_unused_memory man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+void pcre2_jit_free_unused_memory(pcre2_general_context *gcontext); +

+
+DESCRIPTION +
+

+This function frees unused JIT executable memory. The argument is a general +context, for custom memory management, or NULL for standard memory management. +JIT memory allocation retains some memory in order to improve future JIT +compilation speed. In low memory conditions, +\fBpcre2_jit_free_unused_memory()\fB can be used to cause this memory to be +freed. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_jit_match.html b/pcre2-10.20/doc/html/pcre2_jit_match.html new file mode 100644 index 000000000..1d59667cc --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_jit_match.html @@ -0,0 +1,58 @@ + + +pcre2_jit_match specification + + +

pcre2_jit_match man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_jit_match(const pcre2_code *code, PCRE2_SPTR subject, + PCRE2_SIZE length, PCRE2_SIZE startoffset, + uint32_t options, pcre2_match_data *match_data, + pcre2_match_context *mcontext); +

+
+DESCRIPTION +
+

+This function matches a compiled regular expression that has been successfully +processed by the JIT compiler against a given subject string, using a matching +algorithm that is similar to Perl's. It is a "fast path" interface to JIT, and +it bypasses some of the sanity checks that pcre2_match() applies. +Its arguments are exactly the same as for +pcre2_match(). +

+

+The supported options are PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, +PCRE2_NOTEMPTY_ATSTART, PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. Unsupported +options are ignored. The subject string is not checked for UTF validity. +

+

+The return values are the same as for pcre2_match() plus +PCRE2_ERROR_JIT_BADOPTION if a matching mode (partial or complete) is requested +that was not compiled. For details of partial matching, see the +pcre2partial +page. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the JIT API in the +pcre2jit +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_jit_stack_assign.html b/pcre2-10.20/doc/html/pcre2_jit_stack_assign.html new file mode 100644 index 000000000..e7e3a6adb --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_jit_stack_assign.html @@ -0,0 +1,70 @@ + + +pcre2_jit_stack_assign specification + + +

pcre2_jit_stack_assign man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+void pcre2_jit_stack_assign(pcre2_match_context *mcontext, + pcre2_jit_callback callback_function, void *callback_data); +

+
+DESCRIPTION +
+

+This function provides control over the memory used by JIT as a run-time stack +when pcre2_match() or pcre2_jit_match() is called with a pattern +that has been successfully processed by the JIT compiler. The information that +determines which stack is used is put into a match context that is subsequently +passed to a matching function. The arguments of this function are: +

+  mcontext       a pointer to a match context
+  callback       a callback function
+  callback_data  a JIT stack or a value to be passed to the callback
+
+

+

+If callback is NULL and callback_data is NULL, an internal 32K +block on the machine stack is used. +

+

+If callback is NULL and callback_data is not NULL, +callback_data must be a valid JIT stack, the result of calling +pcre2_jit_stack_create(). +

+

+If callback not NULL, it is called with callback_data as an +argument at the start of matching, in order to set up a JIT stack. If the +result is NULL, the internal 32K stack is used; otherwise the return value must +be a valid JIT stack, the result of calling pcre2_jit_stack_create(). +

+

+You may safely use the same JIT stack for multiple patterns, as long as they +are all matched in the same thread. In a multithread application, each thread +must use its own JIT stack. For more details, see the +pcre2jit +page. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_jit_stack_create.html b/pcre2-10.20/doc/html/pcre2_jit_stack_create.html new file mode 100644 index 000000000..a668e348e --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_jit_stack_create.html @@ -0,0 +1,50 @@ + + +pcre2_jit_stack_create specification + + +

pcre2_jit_stack_create man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE startsize, + PCRE2_SIZE maxsize, pcre2_general_context *gcontext); +

+
+DESCRIPTION +
+

+This function is used to create a stack for use by the code compiled by the JIT +compiler. The first two arguments are a starting size for the stack, and a +maximum size to which it is allowed to grow. The final argument is a general +context, for memory allocation functions, or NULL for standard memory +allocation. The result can be passed to the JIT run-time code by calling +pcre2_jit_stack_assign() to associate the stack with a compiled pattern, +which can then be processed by pcre2_match(). If the "fast path" JIT +matcher, pcre2_jit_match() is used, the stack can be passed directly as +an argument. A maximum stack size of 512K to 1M should be more than enough for +any pattern. For more details, see the +pcre2jit +page. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_jit_stack_free.html b/pcre2-10.20/doc/html/pcre2_jit_stack_free.html new file mode 100644 index 000000000..21ac27677 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_jit_stack_free.html @@ -0,0 +1,42 @@ + + +pcre2_jit_stack_free specification + + +

pcre2_jit_stack_free man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+void pcre2_jit_stack_free(pcre2_jit_stack *jit_stack); +

+
+DESCRIPTION +
+

+This function is used to free a JIT stack that was created by +pcre2_jit_stack_create() when it is no longer needed. For more details, +see the +pcre2jit +page. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_maketables.html b/pcre2-10.20/doc/html/pcre2_maketables.html new file mode 100644 index 000000000..068e6d4ec --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_maketables.html @@ -0,0 +1,48 @@ + + +pcre2_maketables specification + + +

pcre2_maketables man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+const unsigned char *pcre2_maketables(pcre22_general_context *gcontext); +

+
+DESCRIPTION +
+

+This function builds a set of character tables for character values less than +256. These can be passed to pcre2_compile() in a compile context in order +to override the internal, built-in tables (which were either defaulted or made +by pcre2_maketables() when PCRE2 was compiled). See the +pcre2_set_character_tables() +page. You might want to do this if you are using a non-standard locale. +

+

+If the argument is NULL, malloc() is used to get memory for the tables. +Otherwise it must point to a general context, which can supply pointers to a +custom memory manager. The function yields a pointer to the tables. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_match.html b/pcre2-10.20/doc/html/pcre2_match.html new file mode 100644 index 000000000..0e389ebb7 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_match.html @@ -0,0 +1,76 @@ + + +pcre2_match specification + + +

pcre2_match man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_match(const pcre2_code *code, PCRE2_SPTR subject, + PCRE2_SIZE length, PCRE2_SIZE startoffset, + uint32_t options, pcre2_match_data *match_data, + pcre2_match_context *mcontext); +

+
+DESCRIPTION +
+

+This function matches a compiled regular expression against a given subject +string, using a matching algorithm that is similar to Perl's. It returns +offsets to captured substrings. Its arguments are: +

+  code         Points to the compiled pattern
+  subject      Points to the subject string
+  length       Length of the subject string
+  startoffset  Offset in the subject at which to start matching
+  options      Option bits
+  match_data   Points to a match data block, for results
+  mcontext     Points to a match context, or is NULL
+
+A match context is needed only if you want to: +
+  Set up a callout function
+  Change the limit for calling the internal function match()
+  Change the limit for calling match() recursively
+  Set custom memory management when the heap is used for recursion
+
+The length and startoffset values are code +units, not characters. The options are: +
+  PCRE2_ANCHORED          Match only at the first position
+  PCRE2_NOTBOL            Subject string is not the beginning of a line
+  PCRE2_NOTEOL            Subject string is not the end of a line
+  PCRE2_NOTEMPTY          An empty string is not a valid match
+  PCRE2_NOTEMPTY_ATSTART  An empty string at the start of the subject
+                           is not a valid match
+  PCRE2_NO_UTF_CHECK      Do not check the subject for UTF
+                           validity (only relevant if PCRE2_UTF
+                           was set at compile time)
+  PCRE2_PARTIAL_SOFT      Return PCRE2_ERROR_PARTIAL for a partial
+                            match if no full matches are found
+  PCRE2_PARTIAL_HARD      Return PCRE2_ERROR_PARTIAL for a partial match
+                           if that is found before a full match
+
+For details of partial matching, see the +pcre2partial +page. There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_match_context_copy.html b/pcre2-10.20/doc/html/pcre2_match_context_copy.html new file mode 100644 index 000000000..4a719d691 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_match_context_copy.html @@ -0,0 +1,41 @@ + + +pcre2_match_context_copy specification + + +

pcre2_match_context_copy man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+pcre2_match_context *pcre2_match_context_copy( + pcre2_match_context *mcontext); +

+
+DESCRIPTION +
+

+This function makes a new copy of a match context, using the memory +allocation function that was used for the original context. The result is NULL +if the memory cannot be obtained. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_match_context_create.html b/pcre2-10.20/doc/html/pcre2_match_context_create.html new file mode 100644 index 000000000..f7f273513 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_match_context_create.html @@ -0,0 +1,42 @@ + + +pcre2_match_context_create specification + + +

pcre2_match_context_create man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+pcre2_match_context *pcre2_match_context_create( + pcre2_general_context *gcontext); +

+
+DESCRIPTION +
+

+This function creates and initializes a new match context. If its argument is +NULL, malloc() is used to get the necessary memory; otherwise the memory +allocation function within the general context is used. The result is NULL if +the memory could not be obtained. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_match_context_free.html b/pcre2-10.20/doc/html/pcre2_match_context_free.html new file mode 100644 index 000000000..824897436 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_match_context_free.html @@ -0,0 +1,40 @@ + + +pcre2_match_context_free specification + + +

pcre2_match_context_free man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+void pcre2_match_context_free(pcre2_match_context *mcontext); +

+
+DESCRIPTION +
+

+This function frees the memory occupied by a match context, using the memory +freeing function from the general context with which it was created, or +free() if that was not set. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_match_data_create.html b/pcre2-10.20/doc/html/pcre2_match_data_create.html new file mode 100644 index 000000000..03cbe244a --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_match_data_create.html @@ -0,0 +1,49 @@ + + +pcre2_match_data_create specification + + +

pcre2_match_data_create man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+pcre2_match_data_create(uint32_t ovecsize, + pcre2_general_context *gcontext); +

+
+DESCRIPTION +
+

+This function creates a new match data block, which is used for holding the +result of a match. The first argument specifies the number of pairs of offsets +that are required. These form the "output vector" (ovector) within the match +data block, and are used to identify the matched string and any captured +substrings. There is always one pair of offsets; if ovecsize is zero, it +is treated as one. +

+

+The second argument points to a general context, for custom memory management, +or is NULL for system memory management. The result of the function is NULL if +the memory for the block could not be obtained. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_match_data_create_from_pattern.html b/pcre2-10.20/doc/html/pcre2_match_data_create_from_pattern.html new file mode 100644 index 000000000..3f8d3f51a --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_match_data_create_from_pattern.html @@ -0,0 +1,50 @@ + + +pcre2_match_data_create_from_pattern specification + + +

pcre2_match_data_create_from_pattern man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+pcre2_match_data_create_from_pattern(const pcre2_code *code, + pcre2_general_context *gcontext); +

+
+DESCRIPTION +
+

+This function creates a new match data block, which is used for holding the +result of a match. The first argument points to a compiled pattern. The number +of capturing parentheses within the pattern is used to compute the number of +pairs of offsets that are required in the match data block. These form the +"output vector" (ovector) within the match data block, and are used to identify +the matched string and any captured substrings. +

+

+The second argument points to a general context, for custom memory management, +or is NULL to use the same memory allocator as was used for the compiled +pattern. The result of the function is NULL if the memory for the block could +not be obtained. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_match_data_free.html b/pcre2-10.20/doc/html/pcre2_match_data_free.html new file mode 100644 index 000000000..70e107ed0 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_match_data_free.html @@ -0,0 +1,40 @@ + + +pcre2_match_data_free specification + + +

pcre2_match_data_free man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+void pcre2_match_data_free(pcre2_match_data *match_data); +

+
+DESCRIPTION +
+

+This function frees the memory occupied by a match data block, using the memory +freeing function from the general context with which it was created, or +free() if that was not set. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_pattern_info.html b/pcre2-10.20/doc/html/pcre2_pattern_info.html new file mode 100644 index 000000000..4e007ee4c --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_pattern_info.html @@ -0,0 +1,106 @@ + + +pcre2_pattern_info specification + + +

pcre2_pattern_info man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_pattern_info(const pcre2 *code, uint32_t what, void *where); +

+
+DESCRIPTION +
+

+This function returns information about a compiled pattern. Its arguments are: +

+  code     Pointer to a compiled regular expression
+  what     What information is required
+  where    Where to put the information
+
+The recognized values for the what argument, and the information they +request are as follows: +
+  PCRE2_INFO_ALLOPTIONS      Final options after compiling
+  PCRE2_INFO_ARGOPTIONS      Options passed to pcre2_compile()
+  PCRE2_INFO_BACKREFMAX      Number of highest back reference
+  PCRE2_INFO_BSR             What \R matches:
+                               PCRE2_BSR_UNICODE: Unicode line endings
+                               PCRE2_BSR_ANYCRLF: CR, LF, or CRLF only
+  PCRE2_INFO_CAPTURECOUNT    Number of capturing subpatterns
+  PCRE2_INFO_FIRSTBITMAP     Bitmap of first code units, or NULL
+  PCRE2_INFO_FIRSTCODEUNIT   First code unit when type is 1
+  PCRE2_INFO_FIRSTCODETYPE   Type of start-of-match information
+                               0 nothing set
+                               1 first code unit is set
+                               2 start of string or after newline
+  PCRE2_INFO_HASCRORLF       Return 1 if explicit CR or LF matches
+                               exist in the pattern
+  PCRE2_INFO_JCHANGED        Return 1 if (?J) or (?-J) was used
+  PCRE2_INFO_JITSIZE         Size of JIT compiled code, or 0
+  PCRE2_INFO_LASTCODEUNIT    Last code unit when type is 1
+  PCRE2_INFO_LASTCODETYPE    Type of must-be-present information
+                               0 nothing set
+                               1 code unit is set
+  PCRE2_INFO_MATCHEMPTY      1 if the pattern can match an
+                               empty string, 0 otherwise
+  PCRE2_INFO_MATCHLIMIT      Match limit if set,
+                               otherwise PCRE2_ERROR_UNSET
+  PCRE2_INFO_MAXLOOKBEHIND   Length (in characters) of the longest
+                               lookbehind assertion
+  PCRE2_INFO_MINLENGTH       Lower bound length of matching strings
+  PCRE2_INFO_NAMEENTRYSIZE   Size of name table entries
+  PCRE2_INFO_NAMECOUNT       Number of named subpatterns
+  PCRE2_INFO_NAMETABLE       Pointer to name table
+  PCRE2_CONFIG_NEWLINE       Code for the newline sequence:
+                               PCRE2_NEWLINE_CR
+                               PCRE2_NEWLINE_LF
+                               PCRE2_NEWLINE_CRLF
+                               PCRE2_NEWLINE_ANY
+                               PCRE2_NEWLINE_ANYCRLF
+  PCRE2_INFO_RECURSIONLIMIT  Recursion limit if set,
+                               otherwise PCRE2_ERROR_UNSET
+  PCRE2_INFO_SIZE            Size of compiled pattern
+
+If where is NULL, the function returns the amount of memory needed for +the requested information, in bytes. Otherwise, the where argument must +point to an unsigned 32-bit integer (uint32_t variable), except for the +following what values, when it must point to a variable of the type +shown: +
+  PCRE2_INFO_FIRSTBITMAP     const uint8_t *
+  PCRE2_INFO_JITSIZE         size_t
+  PCRE2_INFO_NAMETABLE       PCRE2_SPTR
+  PCRE2_INFO_SIZE            size_t
+
+The yield of the function is zero on success or: +
+  PCRE2_ERROR_NULL           the argument code is NULL
+  PCRE2_ERROR_BADMAGIC       the "magic number" was not found
+  PCRE2_ERROR_BADOPTION      the value of what is invalid
+  PCRE2_ERROR_BADMODE        the pattern was compiled in the wrong mode
+  PCRE2_ERROR_UNSET          the requested information is not set
+
+

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_serialize_decode.html b/pcre2-10.20/doc/html/pcre2_serialize_decode.html new file mode 100644 index 000000000..26948bdea --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_serialize_decode.html @@ -0,0 +1,62 @@ + + +pcre2_serialize_decode specification + + +

pcre2_serialize_decode man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int32_t pcre2_serialize_decode(pcre2_code **codes, + int32_t number_of_codes, const uint32_t *bytes, + pcre2_general_context *gcontext); +

+
+DESCRIPTION +
+

+This function decodes a serialized set of compiled patterns back into a list of +individual patterns. Its arguments are: +

+  codes            pointer to a vector in which to build the list
+  number_of_codes  number of slots in the vector
+  bytes            the serialized byte stream
+  gcontext         pointer to a general context or NULL
+
+The bytes argument must point to a block of data that was originally +created by pcre2_serialize_encode(), though it may have been saved on +disc or elsewhere in the meantime. If there are more codes in the serialized +data than slots in the list, only those compiled patterns that will fit are +decoded. The yield of the function is the number of decoded patterns, or one of +the following negative error codes: +
+  PCRE2_ERROR_BADDATA   number_of_codes is zero or less
+  PCRE2_ERROR_BADMAGIC  mismatch of id bytes in bytes
+  PCRE2_ERROR_BADMODE   mismatch of variable unit size or PCRE version
+  PCRE2_ERROR_MEMORY    memory allocation failed
+  PCRE2_ERROR_NULL      codes or bytes is NULL
+
+PCRE2_ERROR_BADMAGIC may mean that the data is corrupt, or that it was compiled +on a system with different endianness. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_serialize_encode.html b/pcre2-10.20/doc/html/pcre2_serialize_encode.html new file mode 100644 index 000000000..a6efcd7d0 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_serialize_encode.html @@ -0,0 +1,61 @@ + + +pcre2_serialize_encode specification + + +

pcre2_serialize_encode man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int32_t pcre2_serialize_encode(pcre2_code **codes, + int32_t number_of_codes, uint32_t **serialized_bytes, + PCRE2_SIZE *serialized_size, pcre2_general_context *gcontext); +

+
+DESCRIPTION +
+

+This function encodes a list of compiled patterns into a byte stream that can +be saved on disc or elsewhere. Its arguments are: +

+  codes             pointer to a vector containing the list
+  number_of_codes   number of slots in the vector
+  serialized_bytes  set to point to the serialized byte stream
+  serialized_size   set to the number of bytes in the byte stream
+  gcontext          pointer to a general context or NULL
+
+The context argument is used to obtain memory for the byte stream. When the +serialized data is no longer needed, it must be freed by calling +pcre2_serialize_free(). The yield of the function is the number of +serialized patterns, or one of the following negative error codes: +
+  PCRE2_ERROR_BADDATA      number_of_codes is zero or less
+  PCRE2_ERROR_BADMAGIC     mismatch of id bytes in one of the patterns
+  PCRE2_ERROR_MEMORY       memory allocation failed
+  PCRE2_ERROR_MIXEDTABLES  the patterns do not all use the same tables
+  PCRE2_ERROR_NULL         an argument other than gcontext is NULL
+
+PCRE2_ERROR_BADMAGIC means either that a pattern's code has been corrupted, or +that a slot in the vector does not point to a compiled pattern. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_serialize_free.html b/pcre2-10.20/doc/html/pcre2_serialize_free.html new file mode 100644 index 000000000..10695dc7f --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_serialize_free.html @@ -0,0 +1,40 @@ + + +pcre2_serialize_free specification + + +

pcre2_serialize_free man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+void pcre2_serialize_free(uint8_t *bytes); +

+
+DESCRIPTION +
+

+This function frees the memory that was obtained by +pcre2_serialize_encode() to hold a serialized byte stream. The argument +must point to such a byte stream. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_serialize_get_number_of_codes.html b/pcre2-10.20/doc/html/pcre2_serialize_get_number_of_codes.html new file mode 100644 index 000000000..3bab45a7c --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_serialize_get_number_of_codes.html @@ -0,0 +1,49 @@ + + +pcre2_serialize_get_number_of_codes specification + + +

pcre2_serialize_get_number_of_codes man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int32_t pcre2_serialize_get_number_of_codes(const uint8_t *bytes); +

+
+DESCRIPTION +
+

+The bytes argument must point to a serialized byte stream that was +originally created by pcre2_serialize_encode() (though it may have been +saved on disc or elsewhere in the meantime). The function returns the number of +serialized patterns in the byte stream, or one of the following negative error +codes: +

+  PCRE2_ERROR_BADMAGIC  mismatch of id bytes in bytes
+  PCRE2_ERROR_BADMODE   mismatch of variable unit size or PCRE version
+  PCRE2_ERROR_NULL      the argument is NULL
+
+PCRE2_ERROR_BADMAGIC may mean that the data is corrupt, or that it was compiled +on a system with different endianness. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_set_bsr.html b/pcre2-10.20/doc/html/pcre2_set_bsr.html new file mode 100644 index 000000000..8a62f18a6 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_set_bsr.html @@ -0,0 +1,42 @@ + + +pcre2_set_bsr specification + + +

pcre2_set_bsr man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_set_bsr(pcre2_compile_context *ccontext, + uint32_t value); +

+
+DESCRIPTION +
+

+This function sets the convention for processing \R within a compile context. +The second argument must be one of PCRE2_BSR_ANYCRLF or PCRE2_BSR_UNICODE. The +result is zero for success or PCRE2_ERROR_BADDATA if the second argument is +invalid. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_set_callout.html b/pcre2-10.20/doc/html/pcre2_set_callout.html new file mode 100644 index 000000000..635e0c29e --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_set_callout.html @@ -0,0 +1,43 @@ + + +pcre2_set_callout specification + + +

pcre2_set_callout man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_set_callout(pcre2_match_context *mcontext, + int (*callout_function)(pcre2_callout_block *), + void *callout_data); +

+
+DESCRIPTION +
+

+This function sets the callout fields in a match context (the first argument). +The second argument specifies a callout function, and the third argument is an +opaque data time that is passed to it. The result of this function is always +zero. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_set_character_tables.html b/pcre2-10.20/doc/html/pcre2_set_character_tables.html new file mode 100644 index 000000000..5a1bd20ef --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_set_character_tables.html @@ -0,0 +1,42 @@ + + +pcre2_set_character_tables specification + + +

pcre2_set_character_tables man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_set_character_tables(pcre2_compile_context *ccontext, + const unsigned char *tables); +

+
+DESCRIPTION +
+

+This function sets a pointer to custom character tables within a compile +context. The second argument must be the result of a call to +pcre2_maketables() or NULL to request the default tables. The result is +always zero. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_set_compile_recursion_guard.html b/pcre2-10.20/doc/html/pcre2_set_compile_recursion_guard.html new file mode 100644 index 000000000..c09942ce2 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_set_compile_recursion_guard.html @@ -0,0 +1,46 @@ + + +pcre2_set_compile_recursion_guard specification + + +

pcre2_set_compile_recursion_guard man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_set_compile_recursion_guard(pcre2_compile_context *ccontext, + int (*guard_function)(uint32_t, void *), void *user_data); +

+
+DESCRIPTION +
+

+This function defines, within a compile context, a function that is called +whenever pcre2_compile() starts to compile a parenthesized part of a +pattern. The first argument to the function gives the current depth of +parenthesis nesting, and the second is user data that is supplied when the +function is set up. The callout function should return zero if all is well, or +non-zero to force an error. This feature is provided so that applications can +check the available system stack space, in order to avoid running out. The +result of pcre2_set_compile_recursion_guard() is always zero. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_set_match_limit.html b/pcre2-10.20/doc/html/pcre2_set_match_limit.html new file mode 100644 index 000000000..e840c744e --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_set_match_limit.html @@ -0,0 +1,40 @@ + + +pcre2_set_match_limit specification + + +

pcre2_set_match_limit man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_set_match_limit(pcre2_match_context *mcontext, + uint32_t value); +

+
+DESCRIPTION +
+

+This function sets the match limit field in a match context. The result is +always zero. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_set_newline.html b/pcre2-10.20/doc/html/pcre2_set_newline.html new file mode 100644 index 000000000..ae6332aca --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_set_newline.html @@ -0,0 +1,50 @@ + + +pcre2_set_newline specification + + +

pcre2_set_newline man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_set_newline(pcre2_compile_context *ccontext, + uint32_t value); +

+
+DESCRIPTION +
+

+This function sets the newline convention within a compile context. This +specifies which character(s) are recognized as newlines when compiling and +matching patterns. The second argument must be one of: +

+  PCRE2_NEWLINE_CR        Carriage return only
+  PCRE2_NEWLINE_LF        Linefeed only
+  PCRE2_NEWLINE_CRLF      CR followed by LF only
+  PCRE2_NEWLINE_ANYCRLF   Any of the above
+  PCRE2_NEWLINE_ANY       Any Unicode newline sequence
+
+The result is zero for success or PCRE2_ERROR_BADDATA if the second argument is +invalid. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_set_parens_nest_limit.html b/pcre2-10.20/doc/html/pcre2_set_parens_nest_limit.html new file mode 100644 index 000000000..95fd31c33 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_set_parens_nest_limit.html @@ -0,0 +1,40 @@ + + +pcre2_set_parens_nest_limit specification + + +

pcre2_set_parens_nest_limit man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_set_parens_nest_limit(pcre2_compile_context *ccontext, + uint32_t value); +

+
+DESCRIPTION +
+

+This function sets, in a compile context, the maximum depth of nested +parentheses in a pattern. The result is always zero. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_set_recursion_limit.html b/pcre2-10.20/doc/html/pcre2_set_recursion_limit.html new file mode 100644 index 000000000..5adcc9986 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_set_recursion_limit.html @@ -0,0 +1,40 @@ + + +pcre2_set_recursion_limit specification + + +

pcre2_set_recursion_limit man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_set_recursion_limit(pcre2_match_context *mcontext, + uint32_t value); +

+
+DESCRIPTION +
+

+This function sets the recursion limit field in a match context. The result is +always zero. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_set_recursion_memory_management.html b/pcre2-10.20/doc/html/pcre2_set_recursion_memory_management.html new file mode 100644 index 000000000..ec18947cd --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_set_recursion_memory_management.html @@ -0,0 +1,47 @@ + + +pcre2_set_recursion_memory_management specification + + +

pcre2_set_recursion_memory_management man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_set_recursion_memory_management( + pcre2_match_context *mcontext, + void *(*private_malloc)(PCRE2_SIZE, void *), + void (*private_free)(void *, void *), void *memory_data); +

+
+DESCRIPTION +
+

+This function sets the match context fields for custom memory management when +PCRE2 is compiled to use the heap instead of the system stack for recursive +function calls while matching. When PCRE2 is compiled to use the stack (the +default) this function does nothing. The first argument is a match context, the +second and third specify the memory allocation and freeing functions, and the +final argument is an opaque value that is passed to them whenever they are +called. The result of this function is always zero. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_substitute.html b/pcre2-10.20/doc/html/pcre2_substitute.html new file mode 100644 index 000000000..0976947dd --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_substitute.html @@ -0,0 +1,85 @@ + + +pcre2_substitute specification + + +

pcre2_substitute man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_substitute(const pcre2_code *code, PCRE2_SPTR subject, + PCRE2_SIZE length, PCRE2_SIZE startoffset, + uint32_t options, pcre2_match_data *match_data, + pcre2_match_context *mcontext, PCRE2_SPTR replacement, + PCRE2_SIZE rlength, PCRE2_UCHAR *outputbuffer, + PCRE2_SIZE *outlengthptr); +

+
+DESCRIPTION +
+

+This function matches a compiled regular expression against a given subject +string, using a matching algorithm that is similar to Perl's. It then makes a +copy of the subject, substituting a replacement string for what was matched. +Its arguments are: +

+  code          Points to the compiled pattern
+  subject       Points to the subject string
+  length        Length of the subject string
+  startoffset   Offset in the subject at which to start matching
+  options       Option bits
+  match_data    Points to a match data block, or is NULL
+  mcontext      Points to a match context, or is NULL
+  replacement   Points to the replacement string
+  rlength       Length of the replacement string
+  outputbuffer  Points to the output buffer
+  outlengthptr  Points to the length of the output buffer
+
+A match context is needed only if you want to: +
+  Set up a callout function
+  Change the limit for calling the internal function match()
+  Change the limit for calling match() recursively
+  Set custom memory management when the heap is used for recursion
+
+The length, startoffset and rlength values are code +units, not characters, as is the contents of the variable pointed at by +outlengthptr, which is updated to the actual length of the new string. +The options are: +
+  PCRE2_ANCHORED          Match only at the first position
+  PCRE2_NOTBOL            Subject string is not the beginning of a line
+  PCRE2_NOTEOL            Subject string is not the end of a line
+  PCRE2_NOTEMPTY          An empty string is not a valid match
+  PCRE2_NOTEMPTY_ATSTART  An empty string at the start of the subject
+                           is not a valid match
+  PCRE2_NO_UTF_CHECK      Do not check the subject or replacement for
+                           UTF validity (only relevant if PCRE2_UTF
+                           was set at compile time)
+  PCRE2_SUBSTITUTE_GLOBAL Replace all occurrences in the subject
+
+The function returns the number of substitutions, which may be zero if there +were no matches. The result can be greater than one only when +PCRE2_SUBSTITUTE_GLOBAL is set. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_substring_copy_byname.html b/pcre2-10.20/doc/html/pcre2_substring_copy_byname.html new file mode 100644 index 000000000..fd01805e8 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_substring_copy_byname.html @@ -0,0 +1,58 @@ + + +pcre2_substring_copy_byname specification + + +

pcre2_substring_copy_byname man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_substring_copy_byname(pcre2_match_data *match_data, + PCRE2_SPTR name, PCRE2_UCHAR *buffer, PCRE2_SIZE *bufflen); +

+
+DESCRIPTION +
+

+This is a convenience function for extracting a captured substring, identified +by name, into a given buffer. The arguments are: +

+  match_data    The match data block for the match
+  name          Name of the required substring
+  buffer        Buffer to receive the string
+  bufflen       Length of buffer (code units)
+
+The bufflen variable is updated to contain the length of the extracted +string, excluding the trailing zero. The yield of the function is zero for +success or one of the following error numbers: +
+  PCRE2_ERROR_NOSUBSTRING   there are no groups of that name
+  PCRE2_ERROR_UNAVAILBLE    the ovector was too small for that group
+  PCRE2_ERROR_UNSET         the group did not participate in the match
+  PCRE2_ERROR_NOMEMORY      the buffer is not big enough
+
+If there is more than one group with the given name, the first one that is set +is returned. In this situation PCRE2_ERROR_UNSET means that no group with the +given name was set. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_substring_copy_bynumber.html b/pcre2-10.20/doc/html/pcre2_substring_copy_bynumber.html new file mode 100644 index 000000000..83e1a2720 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_substring_copy_bynumber.html @@ -0,0 +1,57 @@ + + +pcre2_substring_copy_bynumber specification + + +

pcre2_substring_copy_bynumber man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_substring_copy_bynumber(pcre2_match_data *match_data, + uint32_t number, PCRE2_UCHAR *buffer, + PCRE2_SIZE *bufflen); +

+
+DESCRIPTION +
+

+This is a convenience function for extracting a captured substring into a given +buffer. The arguments are: +

+  match_data    The match data block for the match
+  number        Number of the required substring
+  buffer        Buffer to receive the string
+  bufflen       Length of buffer
+
+The bufflen variable is updated with the length of the extracted string, +excluding the terminating zero. The yield of the function is zero for success +or one of the following error numbers: +
+  PCRE2_ERROR_NOSUBSTRING   there are no groups of that number
+  PCRE2_ERROR_UNAVAILBLE    the ovector was too small for that group
+  PCRE2_ERROR_UNSET         the group did not participate in the match
+  PCRE2_ERROR_NOMEMORY      the buffer is too small
+
+
+

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_substring_free.html b/pcre2-10.20/doc/html/pcre2_substring_free.html new file mode 100644 index 000000000..35a5b5577 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_substring_free.html @@ -0,0 +1,41 @@ + + +pcre2_substring_free specification + + +

pcre2_substring_free man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+void pcre2_substring_free(PCRE2_UCHAR *buffer); +

+
+DESCRIPTION +
+

+This is a convenience function for freeing the memory obtained by a previous +call to pcre2_substring_get_byname() or +pcre2_substring_get_bynumber(). Its only argument is a pointer to the +string. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_substring_get_byname.html b/pcre2-10.20/doc/html/pcre2_substring_get_byname.html new file mode 100644 index 000000000..a4b8771de --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_substring_get_byname.html @@ -0,0 +1,60 @@ + + +pcre2_substring_get_byname specification + + +

pcre2_substring_get_byname man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_substring_get_byname(pcre2_match_data *match_data, + PCRE2_SPTR name, PCRE2_UCHAR **bufferptr, PCRE2_SIZE *bufflen); +

+
+DESCRIPTION +
+

+This is a convenience function for extracting a captured substring by name into +newly acquired memory. The arguments are: +

+  match_data    The match data for the match
+  name          Name of the required substring
+  bufferptr     Where to put the string pointer
+  bufflen       Where to put the string length
+
+The memory in which the substring is placed is obtained by calling the same +memory allocation function that was used for the match data block. The +convenience function pcre2_substring_free() can be used to free it when +it is no longer needed. The yield of the function is zero for success or one of +the following error numbers: +
+  PCRE2_ERROR_NOSUBSTRING   there are no groups of that name
+  PCRE2_ERROR_UNAVAILBLE    the ovector was too small for that group
+  PCRE2_ERROR_UNSET         the group did not participate in the match
+  PCRE2_ERROR_NOMEMORY      memory could not be obtained
+
+If there is more than one group with the given name, the first one that is set +is returned. In this situation PCRE2_ERROR_UNSET means that no group with the +given name was set. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_substring_get_bynumber.html b/pcre2-10.20/doc/html/pcre2_substring_get_bynumber.html new file mode 100644 index 000000000..391bc82b0 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_substring_get_bynumber.html @@ -0,0 +1,58 @@ + + +pcre2_substring_get_bynumber specification + + +

pcre2_substring_get_bynumber man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_substring_get_bynumber(pcre2_match_data *match_data, + uint32_t number, PCRE2_UCHAR **bufferptr, PCRE2_SIZE *bufflen); +

+
+DESCRIPTION +
+

+This is a convenience function for extracting a captured substring by number +into newly acquired memory. The arguments are: +

+  match_data    The match data for the match
+  number        Number of the required substring
+  bufferptr     Where to put the string pointer
+  bufflen       Where to put the string length
+
+The memory in which the substring is placed is obtained by calling the same +memory allocation function that was used for the match data block. The +convenience function pcre2_substring_free() can be used to free it when +it is no longer needed. The yield of the function is zero for success or one of +the following error numbers: +
+  PCRE2_ERROR_NOSUBSTRING   there are no groups of that number
+  PCRE2_ERROR_UNAVAILBLE    the ovector was too small for that group
+  PCRE2_ERROR_UNSET         the group did not participate in the match
+  PCRE2_ERROR_NOMEMORY      memory could not be obtained
+
+
+

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_substring_length_byname.html b/pcre2-10.20/doc/html/pcre2_substring_length_byname.html new file mode 100644 index 000000000..213bc949d --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_substring_length_byname.html @@ -0,0 +1,46 @@ + + +pcre2_substring_length_byname specification + + +

pcre2_substring_length_byname man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_substring_length_byname(pcre2_match_data *match_data, + PCRE2_SPTR name, PCRE2_SIZE *length); +

+
+DESCRIPTION +
+

+This function returns the length of a matched substring, identified by name. +The arguments are: +

+  match_data   The match data block for the match
+  name         The substring name
+  length       Where to return the length
+
+The yield is zero on success, or an error code if the substring is not found. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_substring_length_bynumber.html b/pcre2-10.20/doc/html/pcre2_substring_length_bynumber.html new file mode 100644 index 000000000..db01cca41 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_substring_length_bynumber.html @@ -0,0 +1,48 @@ + + +pcre2_substring_length_bynumber specification + + +

pcre2_substring_length_bynumber man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_substring_length_bynumber(pcre2_match_data *match_data, + uint32_t number, PCRE2_SIZE *length); +

+
+DESCRIPTION +
+

+This function returns the length of a matched substring, identified by number. +The arguments are: +

+  match_data   The match data block for the match
+  number       The substring number
+  length       Where to return the length, or NULL
+
+The third argument may be NULL if all you want to know is whether or not a +substring is set. The yield is zero on success, or a negative error code +otherwise. After a partial match, only substring 0 is available. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_substring_list_free.html b/pcre2-10.20/doc/html/pcre2_substring_list_free.html new file mode 100644 index 000000000..d61241dfe --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_substring_list_free.html @@ -0,0 +1,40 @@ + + +pcre2_substring_list_free specification + + +

pcre2_substring_list_free man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+void pcre2_substring_list_free(PCRE2_SPTR *list); +

+
+DESCRIPTION +
+

+This is a convenience function for freeing the store obtained by a previous +call to pcre2substring_list_get(). Its only argument is a pointer to +the list of string pointers. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_substring_list_get.html b/pcre2-10.20/doc/html/pcre2_substring_list_get.html new file mode 100644 index 000000000..fd4362740 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_substring_list_get.html @@ -0,0 +1,56 @@ + + +pcre2_substring_list_get specification + + +

pcre2_substring_list_get man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_substring_list_get(pcre2_match_data *match_data, +" PCRE2_UCHAR ***listptr, PCRE2_SIZE **lengthsptr); +

+
+DESCRIPTION +
+

+This is a convenience function for extracting all the captured substrings after +a pattern match. It builds a list of pointers to the strings, and (optionally) +a second list that contains their lengths (in code units), excluding a +terminating zero that is added to each of them. All this is done in a single +block of memory that is obtained using the same memory allocation function that +was used to get the match data block. The convenience function +pcre2_substring_list_free() can be used to free it when it is no longer +needed. The arguments are: +

+  match_data    The match data block
+  listptr       Where to put a pointer to the list
+  lengthsptr    Where to put a pointer to the lengths, or NULL
+
+A pointer to a list of pointers is put in the variable whose address is in +listptr. The list is terminated by a NULL pointer. If lengthsptr is +not NULL, a matching list of lengths is created, and its address is placed in +lengthsptr. The yield of the function is zero on success or +PCRE2_ERROR_NOMEMORY if sufficient memory could not be obtained. +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_substring_nametable_scan.html b/pcre2-10.20/doc/html/pcre2_substring_nametable_scan.html new file mode 100644 index 000000000..5a44ea9ce --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_substring_nametable_scan.html @@ -0,0 +1,53 @@ + + +pcre2_substring_nametable_scan specification + + +

pcre2_substring_nametable_scan man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_substring_nametable_scan(const pcre2_code *code, + PCRE2_SPTR name, PCRE2_SPTR *first, PCRE2_SPTR *last); +

+
+DESCRIPTION +
+

+This convenience function finds, for a compiled pattern, the first and last +entries for a given name in the table that translates capturing parenthesis +names into numbers. +

+  code    Compiled regular expression
+  name    Name whose entries required
+  first   Where to return a pointer to the first entry
+  last    Where to return a pointer to the last entry
+
+When the name is found in the table, if first is NULL, the function +returns a group number, but if there is more than one matching entry, it is not +defined which one. Otherwise, when both pointers have been set, the yield of +the function is the length of each entry in code units. If the name is not +found, PCRE2_ERROR_NOSUBSTRING is returned. +

+

+There is a complete description of the PCRE2 native API, including the format of +the table entries, in the +pcre2api +page, and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2_substring_number_from_name.html b/pcre2-10.20/doc/html/pcre2_substring_number_from_name.html new file mode 100644 index 000000000..160fbda66 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2_substring_number_from_name.html @@ -0,0 +1,50 @@ + + +pcre2_substring_number_from_name specification + + +

pcre2_substring_number_from_name man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_substring_number_from_name(const pcre2_code *code, + PCRE2_SPTR name); +

+
+DESCRIPTION +
+

+This convenience function finds the number of a named substring capturing +parenthesis in a compiled pattern, provided that it is a unique name. The +function arguments are: +

+  code    Compiled regular expression
+  name    Name whose number is required
+
+The yield of the function is the number of the parenthesis if the name is +found, or PCRE2_ERROR_NOSUBSTRING if it is not found. When duplicate names are +allowed (PCRE2_DUPNAMES is set), if the name is not unique, +PCRE2_ERROR_NOUNIQUESUBSTRING is returned. You can obtain the list of numbers +with the same name by calling pcre2_substring_nametable_scan(). +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2api.html b/pcre2-10.20/doc/html/pcre2api.html new file mode 100644 index 000000000..60d2bf569 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2api.html @@ -0,0 +1,2892 @@ + + +pcre2api specification + + +

pcre2api man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+

+

+#include <pcre2.h> +
+
+PCRE2 is a new API for PCRE. This document contains a description of all its +functions. See the +pcre2 +document for an overview of all the PCRE2 documentation. +

+
PCRE2 NATIVE API BASIC FUNCTIONS
+

+pcre2_code *pcre2_compile(PCRE2_SPTR pattern, PCRE2_SIZE length, + uint32_t options, int *errorcode, PCRE2_SIZE *erroroffset, + pcre2_compile_context *ccontext); +
+
+pcre2_code_free(pcre2_code *code); +
+
+pcre2_match_data_create(uint32_t ovecsize, + pcre2_general_context *gcontext); +
+
+pcre2_match_data_create_from_pattern(const pcre2_code *code, + pcre2_general_context *gcontext); +
+
+int pcre2_match(const pcre2_code *code, PCRE2_SPTR subject, + PCRE2_SIZE length, PCRE2_SIZE startoffset, + uint32_t options, pcre2_match_data *match_data, + pcre2_match_context *mcontext); +
+
+int pcre2_dfa_match(const pcre2_code *code, PCRE2_SPTR subject, + PCRE2_SIZE length, PCRE2_SIZE startoffset, + uint32_t options, pcre2_match_data *match_data, + pcre2_match_context *mcontext, + int *workspace, PCRE2_SIZE wscount); +
+
+void pcre2_match_data_free(pcre2_match_data *match_data); +

+
PCRE2 NATIVE API AUXILIARY MATCH FUNCTIONS
+

+PCRE2_SPTR pcre2_get_mark(pcre2_match_data *match_data); +
+
+uint32_t pcre2_get_ovector_count(pcre2_match_data *match_data); +
+
+PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *match_data); +
+
+PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *match_data); +

+
PCRE2 NATIVE API GENERAL CONTEXT FUNCTIONS
+

+pcre2_general_context *pcre2_general_context_create( + void *(*private_malloc)(PCRE2_SIZE, void *), + void (*private_free)(void *, void *), void *memory_data); +
+
+pcre2_general_context *pcre2_general_context_copy( + pcre2_general_context *gcontext); +
+
+void pcre2_general_context_free(pcre2_general_context *gcontext); +

+
PCRE2 NATIVE API COMPILE CONTEXT FUNCTIONS
+

+pcre2_compile_context *pcre2_compile_context_create( + pcre2_general_context *gcontext); +
+
+pcre2_compile_context *pcre2_compile_context_copy( + pcre2_compile_context *ccontext); +
+
+void pcre2_compile_context_free(pcre2_compile_context *ccontext); +
+
+int pcre2_set_bsr(pcre2_compile_context *ccontext, + uint32_t value); +
+
+int pcre2_set_character_tables(pcre2_compile_context *ccontext, + const unsigned char *tables); +
+
+int pcre2_set_newline(pcre2_compile_context *ccontext, + uint32_t value); +
+
+int pcre2_set_parens_nest_limit(pcre2_compile_context *ccontext, + uint32_t value); +
+
+int pcre2_set_compile_recursion_guard(pcre2_compile_context *ccontext, + int (*guard_function)(uint32_t, void *), void *user_data); +

+
PCRE2 NATIVE API MATCH CONTEXT FUNCTIONS
+

+pcre2_match_context *pcre2_match_context_create( + pcre2_general_context *gcontext); +
+
+pcre2_match_context *pcre2_match_context_copy( + pcre2_match_context *mcontext); +
+
+void pcre2_match_context_free(pcre2_match_context *mcontext); +
+
+int pcre2_set_callout(pcre2_match_context *mcontext, + int (*callout_function)(pcre2_callout_block *, void *), + void *callout_data); +
+
+int pcre2_set_match_limit(pcre2_match_context *mcontext, + uint32_t value); +
+
+int pcre2_set_recursion_limit(pcre2_match_context *mcontext, + uint32_t value); +
+
+int pcre2_set_recursion_memory_management( + pcre2_match_context *mcontext, + void *(*private_malloc)(PCRE2_SIZE, void *), + void (*private_free)(void *, void *), void *memory_data); +

+
PCRE2 NATIVE API STRING EXTRACTION FUNCTIONS
+

+int pcre2_substring_copy_byname(pcre2_match_data *match_data, + PCRE2_SPTR name, PCRE2_UCHAR *buffer, PCRE2_SIZE *bufflen); +
+
+int pcre2_substring_copy_bynumber(pcre2_match_data *match_data, + uint32_t number, PCRE2_UCHAR *buffer, + PCRE2_SIZE *bufflen); +
+
+void pcre2_substring_free(PCRE2_UCHAR *buffer); +
+
+int pcre2_substring_get_byname(pcre2_match_data *match_data, + PCRE2_SPTR name, PCRE2_UCHAR **bufferptr, PCRE2_SIZE *bufflen); +
+
+int pcre2_substring_get_bynumber(pcre2_match_data *match_data, + uint32_t number, PCRE2_UCHAR **bufferptr, + PCRE2_SIZE *bufflen); +
+
+int pcre2_substring_length_byname(pcre2_match_data *match_data, + PCRE2_SPTR name, PCRE2_SIZE *length); +
+
+int pcre2_substring_length_bynumber(pcre2_match_data *match_data, + uint32_t number, PCRE2_SIZE *length); +
+
+int pcre2_substring_nametable_scan(const pcre2_code *code, + PCRE2_SPTR name, PCRE2_SPTR *first, PCRE2_SPTR *last); +
+
+int pcre2_substring_number_from_name(const pcre2_code *code, + PCRE2_SPTR name); +
+
+void pcre2_substring_list_free(PCRE2_SPTR *list); +
+
+int pcre2_substring_list_get(pcre2_match_data *match_data, +" PCRE2_UCHAR ***listptr, PCRE2_SIZE **lengthsptr); +

+
PCRE2 NATIVE API STRING SUBSTITUTION FUNCTION
+

+int pcre2_substitute(const pcre2_code *code, PCRE2_SPTR subject, + PCRE2_SIZE length, PCRE2_SIZE startoffset, + uint32_t options, pcre2_match_data *match_data, + pcre2_match_context *mcontext, PCRE2_SPTR \fIreplacementzfP, + PCRE2_SIZE rlength, PCRE2_UCHAR *outputbuffer, + PCRE2_SIZE *outlengthptr); +

+
PCRE2 NATIVE API JIT FUNCTIONS
+

+int pcre2_jit_compile(pcre2_code *code, uint32_t options); +
+
+int pcre2_jit_match(const pcre2_code *code, PCRE2_SPTR subject, + PCRE2_SIZE length, PCRE2_SIZE startoffset, + uint32_t options, pcre2_match_data *match_data, + pcre2_match_context *mcontext); +
+
+void pcre2_jit_free_unused_memory(pcre2_general_context *gcontext); +
+
+pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE startsize, + PCRE2_SIZE maxsize, pcre2_general_context *gcontext); +
+
+void pcre2_jit_stack_assign(pcre2_match_context *mcontext, + pcre2_jit_callback callback_function, void *callback_data); +
+
+void pcre2_jit_stack_free(pcre2_jit_stack *jit_stack); +

+
PCRE2 NATIVE API SERIALIZATION FUNCTIONS
+

+int32_t pcre2_serialize_decode(pcre2_code **codes, + int32_t number_of_codes, const uint32_t *bytes, + pcre2_general_context *gcontext); +
+
+int32_t pcre2_serialize_encode(pcre2_code **codes, + int32_t number_of_codes, uint32_t **serialized_bytes, + PCRE2_SIZE *serialized_size, pcre2_general_context *gcontext); +
+
+void pcre2_serialize_free(uint8_t *bytes); +
+
+int32_t pcre2_serialize_get_number_of_codes(const uint8_t *bytes); +

+
PCRE2 NATIVE API AUXILIARY FUNCTIONS
+

+int pcre2_get_error_message(int errorcode, PCRE2_UCHAR *buffer, + PCRE2_SIZE bufflen); +
+
+const unsigned char *pcre2_maketables(pcre2_general_context *gcontext); +
+
+int pcre2_pattern_info(const pcre2 *code, uint32_t what, void *where); +
+
+int pcre2_callout_enumerate(const pcre2_code *code, + int (*callback)(pcre2_callout_enumerate_block *, void *), + void *user_data); +
+
+int pcre2_config(uint32_t what, void *where); +

+
PCRE2 8-BIT, 16-BIT, AND 32-BIT LIBRARIES
+

+There are three PCRE2 libraries, supporting 8-bit, 16-bit, and 32-bit code +units, respectively. However, there is just one header file, pcre2.h. +This contains the function prototypes and other definitions for all three +libraries. One, two, or all three can be installed simultaneously. On Unix-like +systems the libraries are called libpcre2-8, libpcre2-16, and +libpcre2-32, and they can also co-exist with the original PCRE libraries. +

+

+Character strings are passed to and from a PCRE2 library as a sequence of +unsigned integers in code units of the appropriate width. Every PCRE2 function +comes in three different forms, one for each library, for example: +

+  pcre2_compile_8()
+  pcre2_compile_16()
+  pcre2_compile_32()
+
+There are also three different sets of data types: +
+  PCRE2_UCHAR8, PCRE2_UCHAR16, PCRE2_UCHAR32
+  PCRE2_SPTR8,  PCRE2_SPTR16,  PCRE2_SPTR32
+
+The UCHAR types define unsigned code units of the appropriate widths. For +example, PCRE2_UCHAR16 is usually defined as `uint16_t'. The SPTR types are +constant pointers to the equivalent UCHAR types, that is, they are pointers to +vectors of unsigned code units. +

+

+Many applications use only one code unit width. For their convenience, macros +are defined whose names are the generic forms such as pcre2_compile() and +PCRE2_SPTR. These macros use the value of the macro PCRE2_CODE_UNIT_WIDTH to +generate the appropriate width-specific function and macro names. +PCRE2_CODE_UNIT_WIDTH is not defined by default. An application must define it +to be 8, 16, or 32 before including pcre2.h in order to make use of the +generic names. +

+

+Applications that use more than one code unit width can be linked with more +than one PCRE2 library, but must define PCRE2_CODE_UNIT_WIDTH to be 0 before +including pcre2.h, and then use the real function names. Any code that is +to be included in an environment where the value of PCRE2_CODE_UNIT_WIDTH is +unknown should also use the real function names. (Unfortunately, it is not +possible in C code to save and restore the value of a macro.) +

+

+If PCRE2_CODE_UNIT_WIDTH is not defined before including pcre2.h, a +compiler error occurs. +

+

+When using multiple libraries in an application, you must take care when +processing any particular pattern to use only functions from a single library. +For example, if you want to run a match using a pattern that was compiled with +pcre2_compile_16(), you must do so with pcre2_match_16(), not +pcre2_match_8(). +

+

+In the function summaries above, and in the rest of this document and other +PCRE2 documents, functions and data types are described using their generic +names, without the 8, 16, or 32 suffix. +

+
PCRE2 API OVERVIEW
+

+PCRE2 has its own native API, which is described in this document. There are +also some wrapper functions for the 8-bit library that correspond to the +POSIX regular expression API, but they do not give access to all the +functionality. They are described in the +pcre2posix +documentation. Both these APIs define a set of C function calls. +

+

+The native API C data types, function prototypes, option values, and error +codes are defined in the header file pcre2.h, which contains definitions +of PCRE2_MAJOR and PCRE2_MINOR, the major and minor release numbers for the +library. Applications can use these to include support for different releases +of PCRE2. +

+

+In a Windows environment, if you want to statically link an application program +against a non-dll PCRE2 library, you must define PCRE2_STATIC before including +pcre2.h. +

+

+The functions pcre2_compile(), and pcre2_match() are used for +compiling and matching regular expressions in a Perl-compatible manner. A +sample program that demonstrates the simplest way of using them is provided in +the file called pcre2demo.c in the PCRE2 source distribution. A listing +of this program is given in the +pcre2demo +documentation, and the +pcre2sample +documentation describes how to compile and run it. +

+

+Just-in-time compiler support is an optional feature of PCRE2 that can be built +in appropriate hardware environments. It greatly speeds up the matching +performance of many patterns. Programs can request that it be used if +available, by calling pcre2_jit_compile() after a pattern has been +successfully compiled by pcre2_compile(). This does nothing if JIT +support is not available. +

+

+More complicated programs might need to make use of the specialist functions +pcre2_jit_stack_create(), pcre2_jit_stack_free(), and +pcre2_jit_stack_assign() in order to control the JIT code's memory usage. +

+

+JIT matching is automatically used by pcre2_match() if it is available. +There is also a direct interface for JIT matching, which gives improved +performance. The JIT-specific functions are discussed in the +pcre2jit +documentation. +

+

+A second matching function, pcre2_dfa_match(), which is not +Perl-compatible, is also provided. This uses a different algorithm for the +matching. The alternative algorithm finds all possible matches (at a given +point in the subject), and scans the subject just once (unless there are +lookbehind assertions). However, this algorithm does not return captured +substrings. A description of the two matching algorithms and their advantages +and disadvantages is given in the +pcre2matching +documentation. There is no JIT support for pcre2_dfa_match(). +

+

+In addition to the main compiling and matching functions, there are convenience +functions for extracting captured substrings from a subject string that has +been matched by pcre2_match(). They are: +

+  pcre2_substring_copy_byname()
+  pcre2_substring_copy_bynumber()
+  pcre2_substring_get_byname()
+  pcre2_substring_get_bynumber()
+  pcre2_substring_list_get()
+  pcre2_substring_length_byname()
+  pcre2_substring_length_bynumber()
+  pcre2_substring_nametable_scan()
+  pcre2_substring_number_from_name()
+
+pcre2_substring_free() and pcre2_substring_list_free() are also +provided, to free the memory used for extracted strings. +

+

+The function pcre2_substitute() can be called to match a pattern and +return a copy of the subject string with substitutions for parts that were +matched. +

+

+Finally, there are functions for finding out information about a compiled +pattern (pcre2_pattern_info()) and about the configuration with which +PCRE2 was built (pcre2_config()). +

+
STRING LENGTHS AND OFFSETS
+

+The PCRE2 API uses string lengths and offsets into strings of code units in +several places. These values are always of type PCRE2_SIZE, which is an +unsigned integer type, currently always defined as size_t. The largest +value that can be stored in such a type (that is ~(PCRE2_SIZE)0) is reserved +as a special indicator for zero-terminated strings and unset offsets. +Therefore, the longest string that can be handled is one less than this +maximum. +

+
NEWLINES
+

+PCRE2 supports five different conventions for indicating line breaks in +strings: a single CR (carriage return) character, a single LF (linefeed) +character, the two-character sequence CRLF, any of the three preceding, or any +Unicode newline sequence. The Unicode newline sequences are the three just +mentioned, plus the single characters VT (vertical tab, U+000B), FF (form feed, +U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS +(paragraph separator, U+2029). +

+

+Each of the first three conventions is used by at least one operating system as +its standard newline sequence. When PCRE2 is built, a default can be specified. +The default default is LF, which is the Unix standard. However, the newline +convention can be changed by an application when calling pcre2_compile(), +or it can be specified by special text at the start of the pattern itself; this +overrides any other settings. See the +pcre2pattern +page for details of the special character sequences. +

+

+In the PCRE2 documentation the word "newline" is used to mean "the character or +pair of characters that indicate a line break". The choice of newline +convention affects the handling of the dot, circumflex, and dollar +metacharacters, the handling of #-comments in /x mode, and, when CRLF is a +recognized line ending sequence, the match position advancement for a +non-anchored pattern. There is more detail about this in the +section on pcre2_match() options +below. +

+

+The choice of newline convention does not affect the interpretation of +the \n or \r escape sequences, nor does it affect what \R matches; this has +its own separate convention. +

+
MULTITHREADING
+

+In a multithreaded application it is important to keep thread-specific data +separate from data that can be shared between threads. The PCRE2 library code +itself is thread-safe: it contains no static or global variables. The API is +designed to be fairly simple for non-threaded applications while at the same +time ensuring that multithreaded applications can use it. +

+

+There are several different blocks of data that are used to pass information +between the application and the PCRE2 libraries. +

+

+(1) A pointer to the compiled form of a pattern is returned to the user when +pcre2_compile() is successful. The data in the compiled pattern is fixed, +and does not change when the pattern is matched. Therefore, it is thread-safe, +that is, the same compiled pattern can be used by more than one thread +simultaneously. An application can compile all its patterns at the start, +before forking off multiple threads that use them. However, if the just-in-time +optimization feature is being used, it needs separate memory stack areas for +each thread. See the +pcre2jit +documentation for more details. +

+

+(2) The next section below introduces the idea of "contexts" in which PCRE2 +functions are called. A context is nothing more than a collection of parameters +that control the way PCRE2 operates. Grouping a number of parameters together +in a context is a convenient way of passing them to a PCRE2 function without +using lots of arguments. The parameters that are stored in contexts are in some +sense "advanced features" of the API. Many straightforward applications will +not need to use contexts. +

+

+In a multithreaded application, if the parameters in a context are values that +are never changed, the same context can be used by all the threads. However, if +any thread needs to change any value in a context, it must make its own +thread-specific copy. +

+

+(3) The matching functions need a block of memory for working space and for +storing the results of a match. This includes details of what was matched, as +well as additional information such as the name of a (*MARK) setting. Each +thread must provide its own version of this memory. +

+
PCRE2 CONTEXTS
+

+Some PCRE2 functions have a lot of parameters, many of which are used only by +specialist applications, for example, those that use custom memory management +or non-standard character tables. To keep function argument lists at a +reasonable size, and at the same time to keep the API extensible, "uncommon" +parameters are passed to certain functions in a context instead of +directly. A context is just a block of memory that holds the parameter values. +Applications that do not need to adjust any of the context parameters can pass +NULL when a context pointer is required. +

+

+There are three different types of context: a general context that is relevant +for several PCRE2 operations, a compile-time context, and a match-time context. +

+
+The general context +
+

+At present, this context just contains pointers to (and data for) external +memory management functions that are called from several places in the PCRE2 +library. The context is named `general' rather than specifically `memory' +because in future other fields may be added. If you do not want to supply your +own custom memory management functions, you do not need to bother with a +general context. A general context is created by: +pcre2_general_context *pcre2_general_context_create( + void *(*private_malloc)(PCRE2_SIZE, void *), + void (*private_free)(void *, void *), void *memory_data); +
+
+The two function pointers specify custom memory management functions, whose +prototypes are: +

+  void *private_malloc(PCRE2_SIZE, void *);
+  void  private_free(void *, void *);
+
+Whenever code in PCRE2 calls these functions, the final argument is the value +of memory_data. Either of the first two arguments of the creation +function may be NULL, in which case the system memory management functions +malloc() and free() are used. (This is not currently useful, as +there are no other fields in a general context, but in future there might be.) +The private_malloc() function is used (if supplied) to obtain memory for +storing the context, and all three values are saved as part of the context. +

+

+Whenever PCRE2 creates a data block of any kind, the block contains a pointer +to the free() function that matches the malloc() function that was +used. When the time comes to free the block, this function is called. +

+

+A general context can be copied by calling: +pcre2_general_context *pcre2_general_context_copy( + pcre2_general_context *gcontext); +
+
+The memory used for a general context should be freed by calling: +void pcre2_general_context_free(pcre2_general_context *gcontext); +

+
+The compile context +
+

+A compile context is required if you want to change the default values of any +of the following compile-time parameters: +

+  What \R matches (Unicode newlines or CR, LF, CRLF only)
+  PCRE2's character tables
+  The newline character sequence
+  The compile time nested parentheses limit
+  An external function for stack checking
+
+A compile context is also required if you are using custom memory management. +If none of these apply, just pass NULL as the context argument of +pcre2_compile(). +

+

+A compile context is created, copied, and freed by the following functions: +pcre2_compile_context *pcre2_compile_context_create( + pcre2_general_context *gcontext); +
+
+pcre2_compile_context *pcre2_compile_context_copy( + pcre2_compile_context *ccontext); +
+
+void pcre2_compile_context_free(pcre2_compile_context *ccontext); +
+
+A compile context is created with default values for its parameters. These can +be changed by calling the following functions, which return 0 on success, or +PCRE2_ERROR_BADDATA if invalid data is detected. +int pcre2_set_bsr(pcre2_compile_context *ccontext, + uint32_t value); +
+
+The value must be PCRE2_BSR_ANYCRLF, to specify that \R matches only CR, LF, +or CRLF, or PCRE2_BSR_UNICODE, to specify that \R matches any Unicode line +ending sequence. The value is used by the JIT compiler and by the two +interpreted matching functions, pcre2_match() and +pcre2_dfa_match(). +int pcre2_set_character_tables(pcre2_compile_context *ccontext, + const unsigned char *tables); +
+
+The value must be the result of a call to pcre2_maketables(), whose only +argument is a general context. This function builds a set of character tables +in the current locale. +int pcre2_set_newline(pcre2_compile_context *ccontext, + uint32_t value); +
+
+This specifies which characters or character sequences are to be recognized as +newlines. The value must be one of PCRE2_NEWLINE_CR (carriage return only), +PCRE2_NEWLINE_LF (linefeed only), PCRE2_NEWLINE_CRLF (the two-character +sequence CR followed by LF), PCRE2_NEWLINE_ANYCRLF (any of the above), or +PCRE2_NEWLINE_ANY (any Unicode newline sequence). +

+

+When a pattern is compiled with the PCRE2_EXTENDED option, the value of this +parameter affects the recognition of white space and the end of internal +comments starting with #. The value is saved with the compiled pattern for +subsequent use by the JIT compiler and by the two interpreted matching +functions, pcre2_match() and pcre2_dfa_match(). +int pcre2_set_parens_nest_limit(pcre2_compile_context *ccontext, + uint32_t value); +
+
+This parameter ajusts the limit, set when PCRE2 is built (default 250), on the +depth of parenthesis nesting in a pattern. This limit stops rogue patterns +using up too much system stack when being compiled. +int pcre2_set_compile_recursion_guard(pcre2_compile_context *ccontext, + int (*guard_function)(uint32_t, void *), void *user_data); +
+
+There is at least one application that runs PCRE2 in threads with very limited +system stack, where running out of stack is to be avoided at all costs. The +parenthesis limit above cannot take account of how much stack is actually +available. For a finer control, you can supply a function that is called +whenever pcre2_compile() starts to compile a parenthesized part of a +pattern. This function can check the actual stack size (or anything else that +it wants to, of course). +

+

+The first argument to the callout function gives the current depth of +nesting, and the second is user data that is set up by the last argument of +pcre2_set_compile_recursion_guard(). The callout function should return +zero if all is well, or non-zero to force an error. +

+
+The match context +
+

+A match context is required if you want to change the default values of any +of the following match-time parameters: +

+  A callout function
+  The limit for calling match()
+  The limit for calling match() recursively
+
+A match context is also required if you are using custom memory management. +If none of these apply, just pass NULL as the context argument of +pcre2_match(), pcre2_dfa_match(), or pcre2_jit_match(). +

+

+A match context is created, copied, and freed by the following functions: +pcre2_match_context *pcre2_match_context_create( + pcre2_general_context *gcontext); +
+
+pcre2_match_context *pcre2_match_context_copy( + pcre2_match_context *mcontext); +
+
+void pcre2_match_context_free(pcre2_match_context *mcontext); +
+
+A match context is created with default values for its parameters. These can +be changed by calling the following functions, which return 0 on success, or +PCRE2_ERROR_BADDATA if invalid data is detected. +int pcre2_set_callout(pcre2_match_context *mcontext, + int (*callout_function)(pcre2_callout_block *, void *), + void *callout_data); +
+
+This sets up a "callout" function, which PCRE2 will call at specified points +during a matching operation. Details are given in the +pcre2callout +documentation. +int pcre2_set_match_limit(pcre2_match_context *mcontext, + uint32_t value); +
+
+The match_limit parameter provides a means of preventing PCRE2 from using +up too many resources when processing patterns that are not going to match, but +which have a very large number of possibilities in their search trees. The +classic example is a pattern that uses nested unlimited repeats. +

+

+Internally, pcre2_match() uses a function called match(), which it +calls repeatedly (sometimes recursively). The limit set by match_limit is +imposed on the number of times this function is called during a match, which +has the effect of limiting the amount of backtracking that can take place. For +patterns that are not anchored, the count restarts from zero for each position +in the subject string. This limit is not relevant to pcre2_dfa_match(), +which ignores it. +

+

+When pcre2_match() is called with a pattern that was successfully +processed by pcre2_jit_compile(), the way in which matching is executed +is entirely different. However, there is still the possibility of runaway +matching that goes on for a very long time, and so the match_limit value +is also used in this case (but in a different way) to limit how long the +matching can continue. +

+

+The default value for the limit can be set when PCRE2 is built; the default +default is 10 million, which handles all but the most extreme cases. If the +limit is exceeded, pcre2_match() returns PCRE2_ERROR_MATCHLIMIT. A value +for the match limit may also be supplied by an item at the start of a pattern +of the form +

+  (*LIMIT_MATCH=ddd)
+
+where ddd is a decimal number. However, such a setting is ignored unless ddd is +less than the limit set by the caller of pcre2_match() or, if no such +limit is set, less than the default. +int pcre2_set_recursion_limit(pcre2_match_context *mcontext, + uint32_t value); +
+
+The recursion_limit parameter is similar to match_limit, but +instead of limiting the total number of times that match() is called, it +limits the depth of recursion. The recursion depth is a smaller number than the +total number of calls, because not all calls to match() are recursive. +This limit is of use only if it is set smaller than match_limit. +

+

+Limiting the recursion depth limits the amount of system stack that can be +used, or, when PCRE2 has been compiled to use memory on the heap instead of the +stack, the amount of heap memory that can be used. This limit is not relevant, +and is ignored, when matching is done using JIT compiled code or by the +pcre2_dfa_match() function. +

+

+The default value for recursion_limit can be set when PCRE2 is built; the +default default is the same value as the default for match_limit. If the +limit is exceeded, pcre2_match() returns PCRE2_ERROR_RECURSIONLIMIT. A +value for the recursion limit may also be supplied by an item at the start of a +pattern of the form +

+  (*LIMIT_RECURSION=ddd)
+
+where ddd is a decimal number. However, such a setting is ignored unless ddd is +less than the limit set by the caller of pcre2_match() or, if no such +limit is set, less than the default. +int pcre2_set_recursion_memory_management( + pcre2_match_context *mcontext, + void *(*private_malloc)(PCRE2_SIZE, void *), + void (*private_free)(void *, void *), void *memory_data); +
+
+This function sets up two additional custom memory management functions for use +by pcre2_match() when PCRE2 is compiled to use the heap for remembering +backtracking data, instead of recursive function calls that use the system +stack. There is a discussion about PCRE2's stack usage in the +pcre2stack +documentation. See the +pcre2build +documentation for details of how to build PCRE2. +

+

+Using the heap for recursion is a non-standard way of building PCRE2, for use +in environments that have limited stacks. Because of the greater use of memory +management, pcre2_match() runs more slowly. Functions that are different +to the general custom memory functions are provided so that special-purpose +external code can be used for this case, because the memory blocks are all the +same size. The blocks are retained by pcre2_match() until it is about to +exit so that they can be re-used when possible during the match. In the absence +of these functions, the normal custom memory management functions are used, if +supplied, otherwise the system functions. +

+
CHECKING BUILD-TIME OPTIONS
+

+int pcre2_config(uint32_t what, void *where); +

+

+The function pcre2_config() makes it possible for a PCRE2 client to +discover which optional features have been compiled into the PCRE2 library. The +pcre2build +documentation has more details about these optional features. +

+

+The first argument for pcre2_config() specifies which information is +required. The second argument is a pointer to memory into which the information +is placed. If NULL is passed, the function returns the amount of memory that is +needed for the requested information. For calls that return numerical values, +the value is in bytes; when requesting these values, where should point +to appropriately aligned memory. For calls that return strings, the required +length is given in code units, not counting the terminating zero. +

+

+When requesting information, the returned value from pcre2_config() is +non-negative on success, or the negative error code PCRE2_ERROR_BADOPTION if +the value in the first argument is not recognized. The following information is +available: +

+  PCRE2_CONFIG_BSR
+
+The output is a uint32_t integer whose value indicates what character +sequences the \R escape sequence matches by default. A value of +PCRE2_BSR_UNICODE means that \R matches any Unicode line ending sequence; a +value of PCRE2_BSR_ANYCRLF means that \R matches only CR, LF, or CRLF. The +default can be overridden when a pattern is compiled. +
+  PCRE2_CONFIG_JIT
+
+The output is a uint32_t integer that is set to one if support for just-in-time +compiling is available; otherwise it is set to zero. +
+  PCRE2_CONFIG_JITTARGET
+
+The where argument should point to a buffer that is at least 48 code +units long. (The exact length required can be found by calling +pcre2_config() with where set to NULL.) The buffer is filled with a +string that contains the name of the architecture for which the JIT compiler is +configured, for example "x86 32bit (little endian + unaligned)". If JIT support +is not available, PCRE2_ERROR_BADOPTION is returned, otherwise the number of +code units used is returned. This is the length of the string, plus one unit +for the terminating zero. +
+  PCRE2_CONFIG_LINKSIZE
+
+The output is a uint32_t integer that contains the number of bytes used for +internal linkage in compiled regular expressions. When PCRE2 is configured, the +value can be set to 2, 3, or 4, with the default being 2. This is the value +that is returned by pcre2_config(). However, when the 16-bit library is +compiled, a value of 3 is rounded up to 4, and when the 32-bit library is +compiled, internal linkages always use 4 bytes, so the configured value is not +relevant. +

+

+The default value of 2 for the 8-bit and 16-bit libraries is sufficient for all +but the most massive patterns, since it allows the size of the compiled pattern +to be up to 64K code units. Larger values allow larger regular expressions to +be compiled by those two libraries, but at the expense of slower matching. +

+  PCRE2_CONFIG_MATCHLIMIT
+
+The output is a uint32_t integer that gives the default limit for the number of +internal matching function calls in a pcre2_match() execution. Further +details are given with pcre2_match() below. +
+  PCRE2_CONFIG_NEWLINE
+
+The output is a uint32_t integer whose value specifies the default character +sequence that is recognized as meaning "newline". The values are: +
+  PCRE2_NEWLINE_CR       Carriage return (CR)
+  PCRE2_NEWLINE_LF       Linefeed (LF)
+  PCRE2_NEWLINE_CRLF     Carriage return, linefeed (CRLF)
+  PCRE2_NEWLINE_ANY      Any Unicode line ending
+  PCRE2_NEWLINE_ANYCRLF  Any of CR, LF, or CRLF
+
+The default should normally correspond to the standard sequence for your +operating system. +
+  PCRE2_CONFIG_PARENSLIMIT
+
+The output is a uint32_t integer that gives the maximum depth of nesting +of parentheses (of any kind) in a pattern. This limit is imposed to cap the +amount of system stack used when a pattern is compiled. It is specified when +PCRE2 is built; the default is 250. This limit does not take into account the +stack that may already be used by the calling application. For finer control +over compilation stack usage, see pcre2_set_compile_recursion_guard(). +
+  PCRE2_CONFIG_RECURSIONLIMIT
+
+The output is a uint32_t integer that gives the default limit for the depth of +recursion when calling the internal matching function in a pcre2_match() +execution. Further details are given with pcre2_match() below. +
+  PCRE2_CONFIG_STACKRECURSE
+
+The output is a uint32_t integer that is set to one if internal recursion when +running pcre2_match() is implemented by recursive function calls that use +the system stack to remember their state. This is the usual way that PCRE2 is +compiled. The output is zero if PCRE2 was compiled to use blocks of data on the +heap instead of recursive function calls. +
+  PCRE2_CONFIG_UNICODE_VERSION
+
+The where argument should point to a buffer that is at least 24 code +units long. (The exact length required can be found by calling +pcre2_config() with where set to NULL.) If PCRE2 has been compiled +without Unicode support, the buffer is filled with the text "Unicode not +supported". Otherwise, the Unicode version string (for example, "7.0.0") is +inserted. The number of code units used is returned. This is the length of the +string plus one unit for the terminating zero. +
+  PCRE2_CONFIG_UNICODE
+
+The output is a uint32_t integer that is set to one if Unicode support is +available; otherwise it is set to zero. Unicode support implies UTF support. +
+  PCRE2_CONFIG_VERSION
+
+The where argument should point to a buffer that is at least 12 code +units long. (The exact length required can be found by calling +pcre2_config() with where set to NULL.) The buffer is filled with +the PCRE2 version string, zero-terminated. The number of code units used is +returned. This is the length of the string plus one unit for the terminating +zero. +

+
COMPILING A PATTERN
+

+pcre2_code *pcre2_compile(PCRE2_SPTR pattern, PCRE2_SIZE length, + uint32_t options, int *errorcode, PCRE2_SIZE *erroroffset, + pcre2_compile_context *ccontext); +
+
+pcre2_code_free(pcre2_code *code); +

+

+The pcre2_compile() function compiles a pattern into an internal form. +The pattern is defined by a pointer to a string of code units and a length, If +the pattern is zero-terminated, the length can be specified as +PCRE2_ZERO_TERMINATED. The function returns a pointer to a block of memory that +contains the compiled pattern and related data. The caller must free the memory +by calling pcre2_code_free() when it is no longer needed. +

+

+NOTE: When one of the matching functions is called, pointers to the compiled +pattern and the subject string are set in the match data block so that they can +be referenced by the extraction functions. After running a match, you must not +free a compiled pattern (or a subject string) until after all operations on the +match data block +have taken place. +

+

+If the compile context argument ccontext is NULL, memory for the compiled +pattern is obtained by calling malloc(). Otherwise, it is obtained from +the same memory function that was used for the compile context. +

+

+The options argument contains various bit settings that affect the +compilation. It should be zero if no options are required. The available +options are described below. Some of them (in particular, those that are +compatible with Perl, but some others as well) can also be set and unset from +within the pattern (see the detailed description in the +pcre2pattern +documentation). +

+

+For those options that can be different in different parts of the pattern, the +contents of the options argument specifies their settings at the start of +compilation. The PCRE2_ANCHORED and PCRE2_NO_UTF_CHECK options can be set at +the time of matching as well as at compile time. +

+

+Other, less frequently required compile-time parameters (for example, the +newline setting) can be provided in a compile context (as described +above). +

+

+If errorcode or erroroffset is NULL, pcre2_compile() returns +NULL immediately. Otherwise, if compilation of a pattern fails, +pcre2_compile() returns NULL, having set these variables to an error code +and an offset (number of code units) within the pattern, respectively. The +pcre2_get_error_message() function provides a textual message for each +error code. Compilation errors are positive numbers, but UTF formatting errors +are negative numbers. For an invalid UTF-8 or UTF-16 string, the offset is that +of the first code unit of the failing character. +

+

+Some errors are not detected until the whole pattern has been scanned; in these +cases, the offset passed back is the length of the pattern. Note that the +offset is in code units, not characters, even in a UTF mode. It may sometimes +point into the middle of a UTF-8 or UTF-16 character. +

+

+This code fragment shows a typical straightforward call to +pcre2_compile(): +

+  pcre2_code *re;
+  PCRE2_SIZE erroffset;
+  int errorcode;
+  re = pcre2_compile(
+    "^A.*Z",                /* the pattern */
+    PCRE2_ZERO_TERMINATED,  /* the pattern is zero-terminated */
+    0,                      /* default options */
+    &errorcode,             /* for error code */
+    &erroffset,             /* for error offset */
+    NULL);                  /* no compile context */
+
+The following names for option bits are defined in the pcre2.h header +file: +
+  PCRE2_ANCHORED
+
+If this bit is set, the pattern is forced to be "anchored", that is, it is +constrained to match only at the first matching point in the string that is +being searched (the "subject string"). This effect can also be achieved by +appropriate constructs in the pattern itself, which is the only way to do it in +Perl. +
+  PCRE2_ALLOW_EMPTY_CLASS
+
+By default, for compatibility with Perl, a closing square bracket that +immediately follows an opening one is treated as a data character for the +class. When PCRE2_ALLOW_EMPTY_CLASS is set, it terminates the class, which +therefore contains no characters and so can never match. +
+  PCRE2_ALT_BSUX
+
+This option request alternative handling of three escape sequences, which +makes PCRE2's behaviour more like ECMAscript (aka JavaScript). When it is set: +

+

+(1) \U matches an upper case "U" character; by default \U causes a compile +time error (Perl uses \U to upper case subsequent characters). +

+

+(2) \u matches a lower case "u" character unless it is followed by four +hexadecimal digits, in which case the hexadecimal number defines the code point +to match. By default, \u causes a compile time error (Perl uses it to upper +case the following character). +

+

+(3) \x matches a lower case "x" character unless it is followed by two +hexadecimal digits, in which case the hexadecimal number defines the code point +to match. By default, as in Perl, a hexadecimal number is always expected after +\x, but it may have zero, one, or two digits (so, for example, \xz matches a +binary zero character followed by z). +

+  PCRE2_ALT_CIRCUMFLEX
+
+In multiline mode (when PCRE2_MULTILINE is set), the circumflex metacharacter +matches at the start of the subject (unless PCRE2_NOTBOL is set), and also +after any internal newline. However, it does not match after a newline at the +end of the subject, for compatibility with Perl. If you want a multiline +circumflex also to match after a terminating newline, you must set +PCRE2_ALT_CIRCUMFLEX. +
+  PCRE2_AUTO_CALLOUT
+
+If this bit is set, pcre2_compile() automatically inserts callout items, +all with number 255, before each pattern item. For discussion of the callout +facility, see the +pcre2callout +documentation. +
+  PCRE2_CASELESS
+
+If this bit is set, letters in the pattern match both upper and lower case +letters in the subject. It is equivalent to Perl's /i option, and it can be +changed within a pattern by a (?i) option setting. +
+  PCRE2_DOLLAR_ENDONLY
+
+If this bit is set, a dollar metacharacter in the pattern matches only at the +end of the subject string. Without this option, a dollar also matches +immediately before a newline at the end of the string (but not before any other +newlines). The PCRE2_DOLLAR_ENDONLY option is ignored if PCRE2_MULTILINE is +set. There is no equivalent to this option in Perl, and no way to set it within +a pattern. +
+  PCRE2_DOTALL
+
+If this bit is set, a dot metacharacter in the pattern matches any character, +including one that indicates a newline. However, it only ever matches one +character, even if newlines are coded as CRLF. Without this option, a dot does +not match when the current position in the subject is at a newline. This option +is equivalent to Perl's /s option, and it can be changed within a pattern by a +(?s) option setting. A negative class such as [^a] always matches newline +characters, independent of the setting of this option. +
+  PCRE2_DUPNAMES
+
+If this bit is set, names used to identify capturing subpatterns need not be +unique. This can be helpful for certain types of pattern when it is known that +only one instance of the named subpattern can ever be matched. There are more +details of named subpatterns below; see also the +pcre2pattern +documentation. +
+  PCRE2_EXTENDED
+
+If this bit is set, most white space characters in the pattern are totally +ignored except when escaped or inside a character class. However, white space +is not allowed within sequences such as (?> that introduce various +parenthesized subpatterns, nor within numerical quantifiers such as {1,3}. +Ignorable white space is permitted between an item and a following quantifier +and between a quantifier and a following + that indicates possessiveness. +

+

+PCRE2_EXTENDED also causes characters between an unescaped # outside a +character class and the next newline, inclusive, to be ignored, which makes it +possible to include comments inside complicated patterns. Note that the end of +this type of comment is a literal newline sequence in the pattern; escape +sequences that happen to represent a newline do not count. PCRE2_EXTENDED is +equivalent to Perl's /x option, and it can be changed within a pattern by a +(?x) option setting. +

+

+Which characters are interpreted as newlines can be specified by a setting in +the compile context that is passed to pcre2_compile() or by a special +sequence at the start of the pattern, as described in the section entitled +"Newline conventions" +in the pcre2pattern documentation. A default is defined when PCRE2 is +built. +

+  PCRE2_FIRSTLINE
+
+If this option is set, an unanchored pattern is required to match before or at +the first newline in the subject string, though the matched text may continue +over the newline. +
+  PCRE2_MATCH_UNSET_BACKREF
+
+If this option is set, a back reference to an unset subpattern group matches an +empty string (by default this causes the current matching alternative to fail). +A pattern such as (\1)(a) succeeds when this option is set (assuming it can +find an "a" in the subject), whereas it fails by default, for Perl +compatibility. Setting this option makes PCRE2 behave more like ECMAscript (aka +JavaScript). +
+  PCRE2_MULTILINE
+
+By default, for the purposes of matching "start of line" and "end of line", +PCRE2 treats the subject string as consisting of a single line of characters, +even if it actually contains newlines. The "start of line" metacharacter (^) +matches only at the start of the string, and the "end of line" metacharacter +($) matches only at the end of the string, or before a terminating newline +(except when PCRE2_DOLLAR_ENDONLY is set). Note, however, that unless +PCRE2_DOTALL is set, the "any character" metacharacter (.) does not match at a +newline. This behaviour (for ^, $, and dot) is the same as Perl. +

+

+When PCRE2_MULTILINE it is set, the "start of line" and "end of line" +constructs match immediately following or immediately before internal newlines +in the subject string, respectively, as well as at the very start and end. This +is equivalent to Perl's /m option, and it can be changed within a pattern by a +(?m) option setting. Note that the "start of line" metacharacter does not match +after a newline at the end of the subject, for compatibility with Perl. +However, you can change this by setting the PCRE2_ALT_CIRCUMFLEX option. If +there are no newlines in a subject string, or no occurrences of ^ or $ in a +pattern, setting PCRE2_MULTILINE has no effect. +

+  PCRE2_NEVER_BACKSLASH_C
+
+This option locks out the use of \C in the pattern that is being compiled. +This escape can cause unpredictable behaviour in UTF-8 or UTF-16 modes, because +it may leave the current matching point in the middle of a multi-code-unit +character. This option may be useful in applications that process patterns from +external sources. +
+  PCRE2_NEVER_UCP
+
+This option locks out the use of Unicode properties for handling \B, \b, \D, +\d, \S, \s, \W, \w, and some of the POSIX character classes, as described +for the PCRE2_UCP option below. In particular, it prevents the creator of the +pattern from enabling this facility by starting the pattern with (*UCP). This +option may be useful in applications that process patterns from external +sources. The option combination PCRE_UCP and PCRE_NEVER_UCP causes an error. +
+  PCRE2_NEVER_UTF
+
+This option locks out interpretation of the pattern as UTF-8, UTF-16, or +UTF-32, depending on which library is in use. In particular, it prevents the +creator of the pattern from switching to UTF interpretation by starting the +pattern with (*UTF). This option may be useful in applications that process +patterns from external sources. The combination of PCRE2_UTF and +PCRE2_NEVER_UTF causes an error. +
+  PCRE2_NO_AUTO_CAPTURE
+
+If this option is set, it disables the use of numbered capturing parentheses in +the pattern. Any opening parenthesis that is not followed by ? behaves as if it +were followed by ?: but named parentheses can still be used for capturing (and +they acquire numbers in the usual way). There is no equivalent of this option +in Perl. +
+  PCRE2_NO_AUTO_POSSESS
+
+If this option is set, it disables "auto-possessification", which is an +optimization that, for example, turns a+b into a++b in order to avoid +backtracks into a+ that can never be successful. However, if callouts are in +use, auto-possessification means that some callouts are never taken. You can +set this option if you want the matching functions to do a full unoptimized +search and run all the callouts, but it is mainly provided for testing +purposes. +
+  PCRE2_NO_DOTSTAR_ANCHOR
+
+If this option is set, it disables an optimization that is applied when .* is +the first significant item in a top-level branch of a pattern, and all the +other branches also start with .* or with \A or \G or ^. The optimization is +automatically disabled for .* if it is inside an atomic group or a capturing +group that is the subject of a back reference, or if the pattern contains +(*PRUNE) or (*SKIP). When the optimization is not disabled, such a pattern is +automatically anchored if PCRE2_DOTALL is set for all the .* items and +PCRE2_MULTILINE is not set for any ^ items. Otherwise, the fact that any match +must start either at the start of the subject or following a newline is +remembered. Like other optimizations, this can cause callouts to be skipped. +
+  PCRE2_NO_START_OPTIMIZE
+
+This is an option whose main effect is at matching time. It does not change +what pcre2_compile() generates, but it does affect the output of the JIT +compiler. +

+

+There are a number of optimizations that may occur at the start of a match, in +order to speed up the process. For example, if it is known that an unanchored +match must start with a specific character, the matching code searches the +subject for that character, and fails immediately if it cannot find it, without +actually running the main matching function. This means that a special item +such as (*COMMIT) at the start of a pattern is not considered until after a +suitable starting point for the match has been found. Also, when callouts or +(*MARK) items are in use, these "start-up" optimizations can cause them to be +skipped if the pattern is never actually used. The start-up optimizations are +in effect a pre-scan of the subject that takes place before the pattern is run. +

+

+The PCRE2_NO_START_OPTIMIZE option disables the start-up optimizations, +possibly causing performance to suffer, but ensuring that in cases where the +result is "no match", the callouts do occur, and that items such as (*COMMIT) +and (*MARK) are considered at every possible starting position in the subject +string. +

+

+Setting PCRE2_NO_START_OPTIMIZE may change the outcome of a matching operation. +Consider the pattern +

+  (*COMMIT)ABC
+
+When this is compiled, PCRE2 records the fact that a match must start with the +character "A". Suppose the subject string is "DEFABC". The start-up +optimization scans along the subject, finds "A" and runs the first match +attempt from there. The (*COMMIT) item means that the pattern must match the +current starting position, which in this case, it does. However, if the same +match is run with PCRE2_NO_START_OPTIMIZE set, the initial scan along the +subject string does not happen. The first match attempt is run starting from +"D" and when this fails, (*COMMIT) prevents any further matches being tried, so +the overall result is "no match". There are also other start-up optimizations. +For example, a minimum length for the subject may be recorded. Consider the +pattern +
+  (*MARK:A)(X|Y)
+
+The minimum length for a match is one character. If the subject is "ABC", there +will be attempts to match "ABC", "BC", and "C". An attempt to match an empty +string at the end of the subject does not take place, because PCRE2 knows that +the subject is now too short, and so the (*MARK) is never encountered. In this +case, the optimization does not affect the overall match result, which is still +"no match", but it does affect the auxiliary information that is returned. +
+  PCRE2_NO_UTF_CHECK
+
+When PCRE2_UTF is set, the validity of the pattern as a UTF string is +automatically checked. There are discussions about the validity of +UTF-8 strings, +UTF-16 strings, +and +UTF-32 strings +in the +pcre2unicode +document. +If an invalid UTF sequence is found, pcre2_compile() returns a negative +error code. +

+

+If you know that your pattern is valid, and you want to skip this check for +performance reasons, you can set the PCRE2_NO_UTF_CHECK option. When it is set, +the effect of passing an invalid UTF string as a pattern is undefined. It may +cause your program to crash or loop. Note that this option can also be passed +to pcre2_match() and pcre_dfa_match(), to suppress validity +checking of the subject string. +

+  PCRE2_UCP
+
+This option changes the way PCRE2 processes \B, \b, \D, \d, \S, \s, \W, +\w, and some of the POSIX character classes. By default, only ASCII characters +are recognized, but if PCRE2_UCP is set, Unicode properties are used instead to +classify characters. More details are given in the section on +generic character types +in the +pcre2pattern +page. If you set PCRE2_UCP, matching one of the items it affects takes much +longer. The option is available only if PCRE2 has been compiled with Unicode +support. +
+  PCRE2_UNGREEDY
+
+This option inverts the "greediness" of the quantifiers so that they are not +greedy by default, but become greedy if followed by "?". It is not compatible +with Perl. It can also be set by a (?U) option setting within the pattern. +
+  PCRE2_UTF
+
+This option causes PCRE2 to regard both the pattern and the subject strings +that are subsequently processed as strings of UTF characters instead of +single-code-unit strings. It is available when PCRE2 is built to include +Unicode support (which is the default). If Unicode support is not available, +the use of this option provokes an error. Details of how this option changes +the behaviour of PCRE2 are given in the +pcre2unicode +page. +

+
COMPILATION ERROR CODES
+

+There are over 80 positive error codes that pcre2_compile() may return if +it finds an error in the pattern. There are also some negative error codes that +are used for invalid UTF strings. These are the same as given by +pcre2_match() and pcre2_dfa_match(), and are described in the +pcre2unicode +page. The pcre2_get_error_message() function can be called to obtain a +textual error message from any error code. +

+
JUST-IN-TIME (JIT) COMPILATION
+

+int pcre2_jit_compile(pcre2_code *code, uint32_t options); +
+
+int pcre2_jit_match(const pcre2_code *code, PCRE2_SPTR subject, + PCRE2_SIZE length, PCRE2_SIZE startoffset, + uint32_t options, pcre2_match_data *match_data, + pcre2_match_context *mcontext); +
+
+void pcre2_jit_free_unused_memory(pcre2_general_context *gcontext); +
+
+pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE startsize, + PCRE2_SIZE maxsize, pcre2_general_context *gcontext); +
+
+void pcre2_jit_stack_assign(pcre2_match_context *mcontext, + pcre2_jit_callback callback_function, void *callback_data); +
+
+void pcre2_jit_stack_free(pcre2_jit_stack *jit_stack); +

+

+These functions provide support for JIT compilation, which, if the just-in-time +compiler is available, further processes a compiled pattern into machine code +that executes much faster than the pcre2_match() interpretive matching +function. Full details are given in the +pcre2jit +documentation. +

+

+JIT compilation is a heavyweight optimization. It can take some time for +patterns to be analyzed, and for one-off matches and simple patterns the +benefit of faster execution might be offset by a much slower compilation time. +Most, but not all patterns can be optimized by the JIT compiler. +

+
LOCALE SUPPORT
+

+PCRE2 handles caseless matching, and determines whether characters are letters, +digits, or whatever, by reference to a set of tables, indexed by character code +point. This applies only to characters whose code points are less than 256. By +default, higher-valued code points never match escapes such as \w or \d. +However, if PCRE2 is built with UTF support, all characters can be tested with +\p and \P, or, alternatively, the PCRE2_UCP option can be set when a pattern +is compiled; this causes \w and friends to use Unicode property support +instead of the built-in tables. +

+

+The use of locales with Unicode is discouraged. If you are handling characters +with code points greater than 128, you should either use Unicode support, or +use locales, but not try to mix the two. +

+

+PCRE2 contains an internal set of character tables that are used by default. +These are sufficient for many applications. Normally, the internal tables +recognize only ASCII characters. However, when PCRE2 is built, it is possible +to cause the internal tables to be rebuilt in the default "C" locale of the +local system, which may cause them to be different. +

+

+The internal tables can be overridden by tables supplied by the application +that calls PCRE2. These may be created in a different locale from the default. +As more and more applications change to using Unicode, the need for this locale +support is expected to die away. +

+

+External tables are built by calling the pcre2_maketables() function, in +the relevant locale. The result can be passed to pcre2_compile() as often +as necessary, by creating a compile context and calling +pcre2_set_character_tables() to set the tables pointer therein. For +example, to build and use tables that are appropriate for the French locale +(where accented characters with values greater than 128 are treated as +letters), the following code could be used: +

+  setlocale(LC_CTYPE, "fr_FR");
+  tables = pcre2_maketables(NULL);
+  ccontext = pcre2_compile_context_create(NULL);
+  pcre2_set_character_tables(ccontext, tables);
+  re = pcre2_compile(..., ccontext);
+
+The locale name "fr_FR" is used on Linux and other Unix-like systems; if you +are using Windows, the name for the French locale is "french". It is the +caller's responsibility to ensure that the memory containing the tables remains +available for as long as it is needed. +

+

+The pointer that is passed (via the compile context) to pcre2_compile() +is saved with the compiled pattern, and the same tables are used by +pcre2_match() and pcre_dfa_match(). Thus, for any single pattern, +compilation, and matching all happen in the same locale, but different patterns +can be processed in different locales. +

+
INFORMATION ABOUT A COMPILED PATTERN
+

+int pcre2_pattern_info(const pcre2 *code, uint32_t what, void *where); +

+

+The pcre2_pattern_info() function returns general information about a +compiled pattern. For information about callouts, see the +next section. +The first argument for pcre2_pattern_info() is a pointer to the compiled +pattern. The second argument specifies which piece of information is required, +and the third argument is a pointer to a variable to receive the data. If the +third argument is NULL, the first argument is ignored, and the function returns +the size in bytes of the variable that is required for the information +requested. Otherwise, The yield of the function is zero for success, or one of +the following negative numbers: +

+  PCRE2_ERROR_NULL           the argument code was NULL
+  PCRE2_ERROR_BADMAGIC       the "magic number" was not found
+  PCRE2_ERROR_BADOPTION      the value of what was invalid
+  PCRE2_ERROR_UNSET          the requested field is not set
+
+The "magic number" is placed at the start of each compiled pattern as an simple +check against passing an arbitrary memory pointer. Here is a typical call of +pcre2_pattern_info(), to obtain the length of the compiled pattern: +
+  int rc;
+  size_t length;
+  rc = pcre2_pattern_info(
+    re,               /* result of pcre2_compile() */
+    PCRE2_INFO_SIZE,  /* what is required */
+    &length);         /* where to put the data */
+
+The possible values for the second argument are defined in pcre2.h, and +are as follows: +
+  PCRE2_INFO_ALLOPTIONS
+  PCRE2_INFO_ARGOPTIONS
+
+Return a copy of the pattern's options. The third argument should point to a +uint32_t variable. PCRE2_INFO_ARGOPTIONS returns exactly the options that +were passed to pcre2_compile(), whereas PCRE2_INFO_ALLOPTIONS returns +the compile options as modified by any top-level option settings at the start +of the pattern itself. In other words, they are the options that will be in +force when matching starts. For example, if the pattern /(?im)abc(?-i)d/ is +compiled with the PCRE2_EXTENDED option, the result is PCRE2_CASELESS, +PCRE2_MULTILINE, and PCRE2_EXTENDED. +

+

+A pattern compiled without PCRE2_ANCHORED is automatically anchored by PCRE2 if +the first significant item in every top-level branch is one of the following: +

+  ^     unless PCRE2_MULTILINE is set
+  \A    always
+  \G    always
+  .*    sometimes - see below
+
+When .* is the first significant item, anchoring is possible only when all the +following are true: +
+  .* is not in an atomic group
+  .* is not in a capturing group that is the subject of a back reference
+  PCRE2_DOTALL is in force for .*
+  Neither (*PRUNE) nor (*SKIP) appears in the pattern.
+  PCRE2_NO_DOTSTAR_ANCHOR is not set.
+
+For patterns that are auto-anchored, the PCRE2_ANCHORED bit is set in the +options returned for PCRE2_INFO_ALLOPTIONS. +
+  PCRE2_INFO_BACKREFMAX
+
+Return the number of the highest back reference in the pattern. The third +argument should point to an uint32_t variable. Named subpatterns acquire +numbers as well as names, and these count towards the highest back reference. +Back references such as \4 or \g{12} match the captured characters of the +given group, but in addition, the check that a capturing group is set in a +conditional subpattern such as (?(3)a|b) is also a back reference. Zero is +returned if there are no back references. +
+  PCRE2_INFO_BSR
+
+The output is a uint32_t whose value indicates what character sequences the \R +escape sequence matches. A value of PCRE2_BSR_UNICODE means that \R matches +any Unicode line ending sequence; a value of PCRE2_BSR_ANYCRLF means that \R +matches only CR, LF, or CRLF. +
+  PCRE2_INFO_CAPTURECOUNT
+
+Return the number of capturing subpatterns in the pattern. The third argument +should point to an uint32_t variable. +
+  PCRE2_INFO_FIRSTCODETYPE
+
+Return information about the first code unit of any matched string, for a +non-anchored pattern. The third argument should point to an uint32_t +variable. +

+

+If there is a fixed first value, for example, the letter "c" from a pattern +such as (cat|cow|coyote), 1 is returned, and the character value can be +retrieved using PCRE2_INFO_FIRSTCODEUNIT. If there is no fixed first value, but +it is known that a match can occur only at the start of the subject or +following a newline in the subject, 2 is returned. Otherwise, and for anchored +patterns, 0 is returned. +

+  PCRE2_INFO_FIRSTCODEUNIT
+
+Return the value of the first code unit of any matched string in the situation +where PCRE2_INFO_FIRSTCODETYPE returns 1; otherwise return 0. The third +argument should point to an uint32_t variable. In the 8-bit library, the +value is always less than 256. In the 16-bit library the value can be up to +0xffff. In the 32-bit library in UTF-32 mode the value can be up to 0x10ffff, +and up to 0xffffffff when not using UTF-32 mode. +
+  PCRE2_INFO_FIRSTBITMAP
+
+In the absence of a single first code unit for a non-anchored pattern, +pcre2_compile() may construct a 256-bit table that defines a fixed set of +values for the first code unit in any match. For example, a pattern that starts +with [abc] results in a table with three bits set. When code unit values +greater than 255 are supported, the flag bit for 255 means "any code unit of +value 255 or above". If such a table was constructed, a pointer to it is +returned. Otherwise NULL is returned. The third argument should point to an +const uint8_t * variable. +
+  PCRE2_INFO_HASCRORLF
+
+Return 1 if the pattern contains any explicit matches for CR or LF characters, +otherwise 0. The third argument should point to an uint32_t variable. An +explicit match is either a literal CR or LF character, or \r or \n. +
+  PCRE2_INFO_JCHANGED
+
+Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise +0. The third argument should point to an uint32_t variable. (?J) and +(?-J) set and unset the local PCRE2_DUPNAMES option, respectively. +
+  PCRE2_INFO_JITSIZE
+
+If the compiled pattern was successfully processed by +pcre2_jit_compile(), return the size of the JIT compiled code, otherwise +return zero. The third argument should point to a size_t variable. +
+  PCRE2_INFO_LASTCODETYPE
+
+Returns 1 if there is a rightmost literal code unit that must exist in any +matched string, other than at its start. The third argument should point to an +uint32_t variable. If there is no such value, 0 is returned. When 1 is +returned, the code unit value itself can be retrieved using +PCRE2_INFO_LASTCODEUNIT. +

+

+For anchored patterns, a last literal value is recorded only if it follows +something of variable length. For example, for the pattern /^a\d+z\d+/ the +returned value is 1 (with "z" returned from PCRE2_INFO_LASTCODEUNIT), but for +/^a\dz\d/ the returned value is 0. +

+  PCRE2_INFO_LASTCODEUNIT
+
+Return the value of the rightmost literal data unit that must exist in any +matched string, other than at its start, if such a value has been recorded. The +third argument should point to an uint32_t variable. If there is no such +value, 0 is returned. +
+  PCRE2_INFO_MATCHEMPTY
+
+Return 1 if the pattern can match an empty string, otherwise 0. The third +argument should point to an uint32_t variable. +
+  PCRE2_INFO_MATCHLIMIT
+
+If the pattern set a match limit by including an item of the form +(*LIMIT_MATCH=nnnn) at the start, the value is returned. The third argument +should point to an unsigned 32-bit integer. If no such value has been set, the +call to pcre2_pattern_info() returns the error PCRE2_ERROR_UNSET. +
+  PCRE2_INFO_MAXLOOKBEHIND
+
+Return the number of characters (not code units) in the longest lookbehind +assertion in the pattern. The third argument should point to an unsigned 32-bit +integer. This information is useful when doing multi-segment matching using the +partial matching facilities. Note that the simple assertions \b and \B +require a one-character lookbehind. \A also registers a one-character +lookbehind, though it does not actually inspect the previous character. This is +to ensure that at least one character from the old segment is retained when a +new segment is processed. Otherwise, if there are no lookbehinds in the +pattern, \A might match incorrectly at the start of a new segment. +
+  PCRE2_INFO_MINLENGTH
+
+If a minimum length for matching subject strings was computed, its value is +returned. Otherwise the returned value is 0. The value is a number of +characters, which in UTF mode may be different from the number of code units. +The third argument should point to an uint32_t variable. The value is a +lower bound to the length of any matching string. There may not be any strings +of that length that do actually match, but every string that does match is at +least that long. +
+  PCRE2_INFO_NAMECOUNT
+  PCRE2_INFO_NAMEENTRYSIZE
+  PCRE2_INFO_NAMETABLE
+
+PCRE2 supports the use of named as well as numbered capturing parentheses. The +names are just an additional way of identifying the parentheses, which still +acquire numbers. Several convenience functions such as +pcre2_substring_get_byname() are provided for extracting captured +substrings by name. It is also possible to extract the data directly, by first +converting the name to a number in order to access the correct pointers in the +output vector (described with pcre2_match() below). To do the conversion, +you need to use the name-to-number map, which is described by these three +values. +

+

+The map consists of a number of fixed-size entries. PCRE2_INFO_NAMECOUNT gives +the number of entries, and PCRE2_INFO_NAMEENTRYSIZE gives the size of each +entry in code units; both of these return a uint32_t value. The entry +size depends on the length of the longest name. +

+

+PCRE2_INFO_NAMETABLE returns a pointer to the first entry of the table. This is +a PCRE2_SPTR pointer to a block of code units. In the 8-bit library, the first +two bytes of each entry are the number of the capturing parenthesis, most +significant byte first. In the 16-bit library, the pointer points to 16-bit +code units, the first of which contains the parenthesis number. In the 32-bit +library, the pointer points to 32-bit code units, the first of which contains +the parenthesis number. The rest of the entry is the corresponding name, zero +terminated. +

+

+The names are in alphabetical order. If (?| is used to create multiple groups +with the same number, as described in the +section on duplicate subpattern numbers +in the +pcre2pattern +page, the groups may be given the same name, but there is only one entry in the +table. Different names for groups of the same number are not permitted. +

+

+Duplicate names for subpatterns with different numbers are permitted, but only +if PCRE2_DUPNAMES is set. They appear in the table in the order in which they +were found in the pattern. In the absence of (?| this is the order of +increasing number; when (?| is used this is not necessarily the case because +later subpatterns may have lower numbers. +

+

+As a simple example of the name/number table, consider the following pattern +after compilation by the 8-bit library (assume PCRE2_EXTENDED is set, so white +space - including newlines - is ignored): +

+  (?<date> (?<year>(\d\d)?\d\d) - (?<month>\d\d) - (?<day>\d\d) )
+
+There are four named subpatterns, so the table has four entries, and each entry +in the table is eight bytes long. The table is as follows, with non-printing +bytes shows in hexadecimal, and undefined bytes shown as ??: +
+  00 01 d  a  t  e  00 ??
+  00 05 d  a  y  00 ?? ??
+  00 04 m  o  n  t  h  00
+  00 02 y  e  a  r  00 ??
+
+When writing code to extract data from named subpatterns using the +name-to-number map, remember that the length of the entries is likely to be +different for each compiled pattern. +
+  PCRE2_INFO_NEWLINE
+
+The output is a uint32_t with one of the following values: +
+  PCRE2_NEWLINE_CR       Carriage return (CR)
+  PCRE2_NEWLINE_LF       Linefeed (LF)
+  PCRE2_NEWLINE_CRLF     Carriage return, linefeed (CRLF)
+  PCRE2_NEWLINE_ANY      Any Unicode line ending
+  PCRE2_NEWLINE_ANYCRLF  Any of CR, LF, or CRLF
+
+This specifies the default character sequence that will be recognized as +meaning "newline" while matching. +
+  PCRE2_INFO_RECURSIONLIMIT
+
+If the pattern set a recursion limit by including an item of the form +(*LIMIT_RECURSION=nnnn) at the start, the value is returned. The third +argument should point to an unsigned 32-bit integer. If no such value has been +set, the call to pcre2_pattern_info() returns the error PCRE2_ERROR_UNSET. +
+  PCRE2_INFO_SIZE
+
+Return the size of the compiled pattern in bytes (for all three libraries). The +third argument should point to a size_t variable. This value includes the +size of the general data block that precedes the code units of the compiled +pattern itself. The value that is used when pcre2_compile() is getting +memory in which to place the compiled pattern may be slightly larger than the +value returned by this option, because there are cases where the code that +calculates the size has to over-estimate. Processing a pattern with the JIT +compiler does not alter the value returned by this option. +

+
INFORMATION ABOUT A PATTERN'S CALLOUTS
+

+int pcre2_callout_enumerate(const pcre2_code *code, + int (*callback)(pcre2_callout_enumerate_block *, void *), + void *user_data); +
+
+A script language that supports the use of string arguments in callouts might +like to scan all the callouts in a pattern before running the match. This can +be done by calling pcre2_callout_enumerate(). The first argument is a +pointer to a compiled pattern, the second points to a callback function, and +the third is arbitrary user data. The callback function is called for every +callout in the pattern in the order in which they appear. Its first argument is +a pointer to a callout enumeration block, and its second argument is the +user_data value that was passed to pcre2_callout_enumerate(). The +contents of the callout enumeration block are described in the +pcre2callout +documentation, which also gives further details about callouts. +

+
SERIALIZATION AND PRECOMPILING
+

+It is possible to save compiled patterns on disc or elsewhere, and reload them +later, subject to a number of restrictions. The functions whose names begin +with pcre2_serialize_ are used for this purpose. They are described in +the +pcre2serialize +documentation. +

+
THE MATCH DATA BLOCK
+

+pcre2_match_data_create(uint32_t ovecsize, + pcre2_general_context *gcontext); +
+
+pcre2_match_data_create_from_pattern(const pcre2_code *code, + pcre2_general_context *gcontext); +
+
+void pcre2_match_data_free(pcre2_match_data *match_data); +

+

+Information about a successful or unsuccessful match is placed in a match +data block, which is an opaque structure that is accessed by function calls. In +particular, the match data block contains a vector of offsets into the subject +string that define the matched part of the subject and any substrings that were +captured. This is know as the ovector. +

+

+Before calling pcre2_match(), pcre2_dfa_match(), or +pcre2_jit_match() you must create a match data block by calling one of +the creation functions above. For pcre2_match_data_create(), the first +argument is the number of pairs of offsets in the ovector. One pair of +offsets is required to identify the string that matched the whole pattern, with +another pair for each captured substring. For example, a value of 4 creates +enough space to record the matched portion of the subject plus three captured +substrings. A minimum of at least 1 pair is imposed by +pcre2_match_data_create(), so it is always possible to return the overall +matched string. +

+

+The second argument of pcre2_match_data_create() is a pointer to a +general context, which can specify custom memory management for obtaining the +memory for the match data block. If you are not using custom memory management, +pass NULL, which causes malloc() to be used. +

+

+For pcre2_match_data_create_from_pattern(), the first argument is a +pointer to a compiled pattern. The ovector is created to be exactly the right +size to hold all the substrings a pattern might capture. The second argument is +again a pointer to a general context, but in this case if NULL is passed, the +memory is obtained using the same allocator that was used for the compiled +pattern (custom or default). +

+

+A match data block can be used many times, with the same or different compiled +patterns. You can extract information from a match data block after a match +operation has finished, using functions that are described in the sections on +matched strings +and +other match data +below. +

+

+When a call of pcre2_match() fails, valid data is available in the match +block only when the error is PCRE2_ERROR_NOMATCH, PCRE2_ERROR_PARTIAL, or one +of the error codes for an invalid UTF string. Exactly what is available depends +on the error, and is detailed below. +

+

+When one of the matching functions is called, pointers to the compiled pattern +and the subject string are set in the match data block so that they can be +referenced by the extraction functions. After running a match, you must not +free a compiled pattern or a subject string until after all operations on the +match data block (for that match) have taken place. +

+

+When a match data block itself is no longer needed, it should be freed by +calling pcre2_match_data_free(). +

+
MATCHING A PATTERN: THE TRADITIONAL FUNCTION
+

+int pcre2_match(const pcre2_code *code, PCRE2_SPTR subject, + PCRE2_SIZE length, PCRE2_SIZE startoffset, + uint32_t options, pcre2_match_data *match_data, + pcre2_match_context *mcontext); +

+

+The function pcre2_match() is called to match a subject string against a +compiled pattern, which is passed in the code argument. You can call +pcre2_match() with the same code argument as many times as you +like, in order to find multiple matches in the subject string or to match +different subject strings with the same pattern. +

+

+This function is the main matching facility of the library, and it operates in +a Perl-like manner. For specialist use there is also an alternative matching +function, which is described +below +in the section about the pcre2_dfa_match() function. +

+

+Here is an example of a simple call to pcre2_match(): +

+  pcre2_match_data *md = pcre2_match_data_create(4, NULL);
+  int rc = pcre2_match(
+    re,             /* result of pcre2_compile() */
+    "some string",  /* the subject string */
+    11,             /* the length of the subject string */
+    0,              /* start at offset 0 in the subject */
+    0,              /* default options */
+    match_data,     /* the match data block */
+    NULL);          /* a match context; NULL means use defaults */
+
+If the subject string is zero-terminated, the length can be given as +PCRE2_ZERO_TERMINATED. A match context must be provided if certain less common +matching parameters are to be changed. For details, see the section on +the match context +above. +

+
+The string to be matched by pcre2_match() +
+

+The subject string is passed to pcre2_match() as a pointer in +subject, a length in length, and a starting offset in +startoffset. The length and offset are in code units, not characters. +That is, they are in bytes for the 8-bit library, 16-bit code units for the +16-bit library, and 32-bit code units for the 32-bit library, whether or not +UTF processing is enabled. +

+

+If startoffset is greater than the length of the subject, +pcre2_match() returns PCRE2_ERROR_BADOFFSET. When the starting offset is +zero, the search for a match starts at the beginning of the subject, and this +is by far the most common case. In UTF-8 or UTF-16 mode, the starting offset +must point to the start of a character, or to the end of the subject (in UTF-32 +mode, one code unit equals one character, so all offsets are valid). Like the +pattern string, the subject may contain binary zeroes. +

+

+A non-zero starting offset is useful when searching for another match in the +same subject by calling pcre2_match() again after a previous success. +Setting startoffset differs from passing over a shortened string and +setting PCRE2_NOTBOL in the case of a pattern that begins with any kind of +lookbehind. For example, consider the pattern +

+  \Biss\B
+
+which finds occurrences of "iss" in the middle of words. (\B matches only if +the current position in the subject is not a word boundary.) When applied to +the string "Mississipi" the first call to pcre2_match() finds the first +occurrence. If pcre2_match() is called again with just the remainder of +the subject, namely "issipi", it does not match, because \B is always false at +the start of the subject, which is deemed to be a word boundary. However, if +pcre2_match() is passed the entire string again, but with +startoffset set to 4, it finds the second occurrence of "iss" because it +is able to look behind the starting point to discover that it is preceded by a +letter. +

+

+Finding all the matches in a subject is tricky when the pattern can match an +empty string. It is possible to emulate Perl's /g behaviour by first trying the +match again at the same offset, with the PCRE2_NOTEMPTY_ATSTART and +PCRE2_ANCHORED options, and then if that fails, advancing the starting offset +and trying an ordinary match again. There is some code that demonstrates how to +do this in the +pcre2demo +sample program. In the most general case, you have to check to see if the +newline convention recognizes CRLF as a newline, and if so, and the current +character is CR followed by LF, advance the starting offset by two characters +instead of one. +

+

+If a non-zero starting offset is passed when the pattern is anchored, one +attempt to match at the given offset is made. This can only succeed if the +pattern does not require the match to be at the start of the subject. +

+
+Option bits for pcre2_match() +
+

+The unused bits of the options argument for pcre2_match() must be +zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL, +PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_UTF_CHECK, +PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. Their action is described below. +

+

+Setting PCRE2_ANCHORED at match time is not supported by the just-in-time (JIT) +compiler. If it is set, JIT matching is disabled and the normal interpretive +code in pcre2_match() is run. The remaining options are supported for JIT +matching. +

+  PCRE2_ANCHORED
+
+The PCRE2_ANCHORED option limits pcre2_match() to matching at the first +matching position. If a pattern was compiled with PCRE2_ANCHORED, or turned out +to be anchored by virtue of its contents, it cannot be made unachored at +matching time. Note that setting the option at match time disables JIT +matching. +
+  PCRE2_NOTBOL
+
+This option specifies that first character of the subject string is not the +beginning of a line, so the circumflex metacharacter should not match before +it. Setting this without having set PCRE2_MULTILINE at compile time causes +circumflex never to match. This option affects only the behaviour of the +circumflex metacharacter. It does not affect \A. +
+  PCRE2_NOTEOL
+
+This option specifies that the end of the subject string is not the end of a +line, so the dollar metacharacter should not match it nor (except in multiline +mode) a newline immediately before it. Setting this without having set +PCRE2_MULTILINE at compile time causes dollar never to match. This option +affects only the behaviour of the dollar metacharacter. It does not affect \Z +or \z. +
+  PCRE2_NOTEMPTY
+
+An empty string is not considered to be a valid match if this option is set. If +there are alternatives in the pattern, they are tried. If all the alternatives +match the empty string, the entire match fails. For example, if the pattern +
+  a?b?
+
+is applied to a string not beginning with "a" or "b", it matches an empty +string at the start of the subject. With PCRE2_NOTEMPTY set, this match is not +valid, so pcre2_match() searches further into the string for occurrences +of "a" or "b". +
+  PCRE2_NOTEMPTY_ATSTART
+
+This is like PCRE2_NOTEMPTY, except that it locks out an empty string match +only at the first matching position, that is, at the start of the subject plus +the starting offset. An empty string match later in the subject is permitted. +If the pattern is anchored, such a match can occur only if the pattern contains +\K. +
+  PCRE2_NO_UTF_CHECK
+
+When PCRE2_UTF is set at compile time, the validity of the subject as a UTF +string is checked by default when pcre2_match() is subsequently called. +The entire string is checked before any other processing takes place, and a +negative error code is returned if the check fails. There are several UTF error +codes for each code unit width, corresponding to different problems with the +code unit sequence. The value of startoffset is also checked, to ensure +that it points to the start of a character or to the end of the subject. There +are discussions about the validity of +UTF-8 strings, +UTF-16 strings, +and +UTF-32 strings +in the +pcre2unicode +page. +

+

+If you know that your subject is valid, and you want to skip these checks for +performance reasons, you can set the PCRE2_NO_UTF_CHECK option when calling +pcre2_match(). You might want to do this for the second and subsequent +calls to pcre2_match() if you are making repeated calls to find all the +matches in a single subject string. +

+

+NOTE: When PCRE2_NO_UTF_CHECK is set, the effect of passing an invalid string +as a subject, or an invalid value of startoffset, is undefined. Your +program may crash or loop indefinitely. +

+  PCRE2_PARTIAL_HARD
+  PCRE2_PARTIAL_SOFT
+
+These options turn on the partial matching feature. A partial match occurs if +the end of the subject string is reached successfully, but there are not enough +subject characters to complete the match. If this happens when +PCRE2_PARTIAL_SOFT (but not PCRE2_PARTIAL_HARD) is set, matching continues by +testing any remaining alternatives. Only if no complete match can be found is +PCRE2_ERROR_PARTIAL returned instead of PCRE2_ERROR_NOMATCH. In other words, +PCRE2_PARTIAL_SOFT specifies that the caller is prepared to handle a partial +match, but only if no complete match can be found. +

+

+If PCRE2_PARTIAL_HARD is set, it overrides PCRE2_PARTIAL_SOFT. In this case, if +a partial match is found, pcre2_match() immediately returns +PCRE2_ERROR_PARTIAL, without considering any other alternatives. In other +words, when PCRE2_PARTIAL_HARD is set, a partial match is considered to be more +important that an alternative complete match. +

+

+There is a more detailed discussion of partial and multi-segment matching, with +examples, in the +pcre2partial +documentation. +

+
NEWLINE HANDLING WHEN MATCHING
+

+When PCRE2 is built, a default newline convention is set; this is usually the +standard convention for the operating system. The default can be overridden in +a +compile context. +During matching, the newline choice affects the behaviour of the dot, +circumflex, and dollar metacharacters. It may also alter the way the match +starting position is advanced after a match failure for an unanchored pattern. +

+

+When PCRE2_NEWLINE_CRLF, PCRE2_NEWLINE_ANYCRLF, or PCRE2_NEWLINE_ANY is set as +the newline convention, and a match attempt for an unanchored pattern fails +when the current starting position is at a CRLF sequence, and the pattern +contains no explicit matches for CR or LF characters, the match position is +advanced by two characters instead of one, in other words, to after the CRLF. +

+

+The above rule is a compromise that makes the most common cases work as +expected. For example, if the pattern is .+A (and the PCRE2_DOTALL option is +not set), it does not match the string "\r\nA" because, after failing at the +start, it skips both the CR and the LF before retrying. However, the pattern +[\r\n]A does match that string, because it contains an explicit CR or LF +reference, and so advances only by one character after the first failure. +

+

+An explicit match for CR of LF is either a literal appearance of one of those +characters in the pattern, or one of the \r or \n escape sequences. Implicit +matches such as [^X] do not count, nor does \s, even though it includes CR and +LF in the characters that it matches. +

+

+Notwithstanding the above, anomalous effects may still occur when CRLF is a +valid newline sequence and explicit \r or \n escapes appear in the pattern. +

+
HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
+

+uint32_t pcre2_get_ovector_count(pcre2_match_data *match_data); +
+
+PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *match_data); +

+

+In general, a pattern matches a certain portion of the subject, and in +addition, further substrings from the subject may be picked out by +parenthesized parts of the pattern. Following the usage in Jeffrey Friedl's +book, this is called "capturing" in what follows, and the phrase "capturing +subpattern" or "capturing group" is used for a fragment of a pattern that picks +out a substring. PCRE2 supports several other kinds of parenthesized subpattern +that do not cause substrings to be captured. The pcre2_pattern_info() +function can be used to find out how many capturing subpatterns there are in a +compiled pattern. +

+

+A successful match returns the overall matched string and any captured +substrings to the caller via a vector of PCRE2_SIZE values. This is called the +ovector, and is contained within the +match data block. +You can obtain direct access to the ovector by calling +pcre2_get_ovector_pointer() to find its address, and +pcre2_get_ovector_count() to find the number of pairs of values it +contains. Alternatively, you can use the auxiliary functions for accessing +captured substrings +by number +or +by name +(see below). +

+

+Within the ovector, the first in each pair of values is set to the offset of +the first code unit of a substring, and the second is set to the offset of the +first code unit after the end of a substring. These values are always code unit +offsets, not character offsets. That is, they are byte offsets in the 8-bit +library, 16-bit offsets in the 16-bit library, and 32-bit offsets in the 32-bit +library. +

+

+After a partial match (error return PCRE2_ERROR_PARTIAL), only the first pair +of offsets (that is, ovector[0] and ovector[1]) are set. They +identify the part of the subject that was partially matched. See the +pcre2partial +documentation for details of partial matching. +

+

+After a successful match, the first pair of offsets identifies the portion of +the subject string that was matched by the entire pattern. The next pair is +used for the first capturing subpattern, and so on. The value returned by +pcre2_match() is one more than the highest numbered pair that has been +set. For example, if two substrings have been captured, the returned value is +3. If there are no capturing subpatterns, the return value from a successful +match is 1, indicating that just the first pair of offsets has been set. +

+

+If a pattern uses the \K escape sequence within a positive assertion, the +reported start of a successful match can be greater than the end of the match. +For example, if the pattern (?=ab\K) is matched against "ab", the start and +end offset values for the match are 2 and 0. +

+

+If a capturing subpattern group is matched repeatedly within a single match +operation, it is the last portion of the subject that it matched that is +returned. +

+

+If the ovector is too small to hold all the captured substring offsets, as much +as possible is filled in, and the function returns a value of zero. If captured +substrings are not of interest, pcre2_match() may be called with a match +data block whose ovector is of minimum length (that is, one pair). However, if +the pattern contains back references and the ovector is not big enough to +remember the related substrings, PCRE2 has to get additional memory for use +during matching. Thus it is usually advisable to set up a match data block +containing an ovector of reasonable size. +

+

+It is possible for capturing subpattern number n+1 to match some part of +the subject when subpattern n has not been used at all. For example, if +the string "abc" is matched against the pattern (a|(z))(bc) the return from the +function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this +happens, both values in the offset pairs corresponding to unused subpatterns +are set to PCRE2_UNSET. +

+

+Offset values that correspond to unused subpatterns at the end of the +expression are also set to PCRE2_UNSET. For example, if the string "abc" is +matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. +The return from the function is 2, because the highest used capturing +subpattern number is 1. The offsets for for the second and third capturing +subpatterns (assuming the vector is large enough, of course) are set to +PCRE2_UNSET. +

+

+Elements in the ovector that do not correspond to capturing parentheses in the +pattern are never changed. That is, if a pattern contains n capturing +parentheses, no more than ovector[0] to ovector[2n+1] are set by +pcre2_match(). The other elements retain whatever values they previously +had. +

+
OTHER INFORMATION ABOUT A MATCH
+

+PCRE2_SPTR pcre2_get_mark(pcre2_match_data *match_data); +
+
+PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *match_data); +

+

+As well as the offsets in the ovector, other information about a match is +retained in the match data block and can be retrieved by the above functions in +appropriate circumstances. If they are called at other times, the result is +undefined. +

+

+After a successful match, a partial match (PCRE2_ERROR_PARTIAL), or a failure +to match (PCRE2_ERROR_NOMATCH), a (*MARK) name may be available, and +pcre2_get_mark() can be called. It returns a pointer to the +zero-terminated name, which is within the compiled pattern. Otherwise NULL is +returned. After a successful match, the (*MARK) name that is returned is the +last one encountered on the matching path through the pattern. After a "no +match" or a partial match, the last encountered (*MARK) name is returned. For +example, consider this pattern: +

+  ^(*MARK:A)((*MARK:B)a|b)c
+
+When it matches "bc", the returned mark is A. The B mark is "seen" in the first +branch of the group, but it is not on the matching path. On the other hand, +when this pattern fails to match "bx", the returned mark is B. +

+

+After a successful match, a partial match, or one of the invalid UTF errors +(for example, PCRE2_ERROR_UTF8_ERR5), pcre2_get_startchar() can be +called. After a successful or partial match it returns the code unit offset of +the character at which the match started. For a non-partial match, this can be +different to the value of ovector[0] if the pattern contains the \K +escape sequence. After a partial match, however, this value is always the same +as ovector[0] because \K does not affect the result of a partial match. +

+

+After a UTF check failure, \fBpcre2_get_startchar()\fB can be used to obtain +the code unit offset of the invalid UTF character. Details are given in the +pcre2unicode +page. +

+
ERROR RETURNS FROM pcre2_match()
+

+If pcre2_match() fails, it returns a negative number. This can be +converted to a text string by calling pcre2_get_error_message(). Negative +error codes are also returned by other functions, and are documented with them. +The codes are given names in the header file. If UTF checking is in force and +an invalid UTF subject string is detected, one of a number of UTF-specific +negative error codes is returned. Details are given in the +pcre2unicode +page. The following are the other errors that may be returned by +pcre2_match(): +

+  PCRE2_ERROR_NOMATCH
+
+The subject string did not match the pattern. +
+  PCRE2_ERROR_PARTIAL
+
+The subject string did not match, but it did match partially. See the +pcre2partial +documentation for details of partial matching. +
+  PCRE2_ERROR_BADMAGIC
+
+PCRE2 stores a 4-byte "magic number" at the start of the compiled code, to +catch the case when it is passed a junk pointer. This is the error that is +returned when the magic number is not present. +
+  PCRE2_ERROR_BADMODE
+
+This error is given when a pattern that was compiled by the 8-bit library is +passed to a 16-bit or 32-bit library function, or vice versa. +
+  PCRE2_ERROR_BADOFFSET
+
+The value of startoffset was greater than the length of the subject. +
+  PCRE2_ERROR_BADOPTION
+
+An unrecognized bit was set in the options argument. +
+  PCRE2_ERROR_BADUTFOFFSET
+
+The UTF code unit sequence that was passed as a subject was checked and found +to be valid (the PCRE2_NO_UTF_CHECK option was not set), but the value of +startoffset did not point to the beginning of a UTF character or the end +of the subject. +
+  PCRE2_ERROR_CALLOUT
+
+This error is never generated by pcre2_match() itself. It is provided for +use by callout functions that want to cause pcre2_match() or +pcre2_callout_enumerate() to return a distinctive error code. See the +pcre2callout +documentation for details. +
+  PCRE2_ERROR_INTERNAL
+
+An unexpected internal error has occurred. This error could be caused by a bug +in PCRE2 or by overwriting of the compiled pattern. +
+  PCRE2_ERROR_JIT_BADOPTION
+
+This error is returned when a pattern that was successfully studied using JIT +is being matched, but the matching mode (partial or complete match) does not +correspond to any JIT compilation mode. When the JIT fast path function is +used, this error may be also given for invalid options. See the +pcre2jit +documentation for more details. +
+  PCRE2_ERROR_JIT_STACKLIMIT
+
+This error is returned when a pattern that was successfully studied using JIT +is being matched, but the memory available for the just-in-time processing +stack is not large enough. See the +pcre2jit +documentation for more details. +
+  PCRE2_ERROR_MATCHLIMIT
+
+The backtracking limit was reached. +
+  PCRE2_ERROR_NOMEMORY
+
+If a pattern contains back references, but the ovector is not big enough to +remember the referenced substrings, PCRE2 gets a block of memory at the start +of matching to use for this purpose. There are some other special cases where +extra memory is needed during matching. This error is given when memory cannot +be obtained. +
+  PCRE2_ERROR_NULL
+
+Either the code, subject, or match_data argument was passed +as NULL. +
+  PCRE2_ERROR_RECURSELOOP
+
+This error is returned when pcre2_match() detects a recursion loop within +the pattern. Specifically, it means that either the whole pattern or a +subpattern has been called recursively for the second time at the same position +in the subject string. Some simple patterns that might do this are detected and +faulted at compile time, but more complicated cases, in particular mutual +recursions between two different subpatterns, cannot be detected until matching +is attempted. +
+  PCRE2_ERROR_RECURSIONLIMIT
+
+The internal recursion limit was reached. +

+
EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
+

+int pcre2_substring_length_bynumber(pcre2_match_data *match_data, + uint32_t number, PCRE2_SIZE *length); +
+
+int pcre2_substring_copy_bynumber(pcre2_match_data *match_data, + uint32_t number, PCRE2_UCHAR *buffer, + PCRE2_SIZE *bufflen); +
+
+int pcre2_substring_get_bynumber(pcre2_match_data *match_data, + uint32_t number, PCRE2_UCHAR **bufferptr, + PCRE2_SIZE *bufflen); +
+
+void pcre2_substring_free(PCRE2_UCHAR *buffer); +

+

+Captured substrings can be accessed directly by using the ovector as described +above. +For convenience, auxiliary functions are provided for extracting captured +substrings as new, separate, zero-terminated strings. A substring that contains +a binary zero is correctly extracted and has a further zero added on the end, +but the result is not, of course, a C string. +

+

+The functions in this section identify substrings by number. The number zero +refers to the entire matched substring, with higher numbers referring to +substrings captured by parenthesized groups. After a partial match, only +substring zero is available. An attempt to extract any other substring gives +the error PCRE2_ERROR_PARTIAL. The next section describes similar functions for +extracting captured substrings by name. +

+

+If a pattern uses the \K escape sequence within a positive assertion, the +reported start of a successful match can be greater than the end of the match. +For example, if the pattern (?=ab\K) is matched against "ab", the start and +end offset values for the match are 2 and 0. In this situation, calling these +functions with a zero substring number extracts a zero-length empty string. +

+

+You can find the length in code units of a captured substring without +extracting it by calling pcre2_substring_length_bynumber(). The first +argument is a pointer to the match data block, the second is the group number, +and the third is a pointer to a variable into which the length is placed. If +you just want to know whether or not the substring has been captured, you can +pass the third argument as NULL. +

+

+The pcre2_substring_copy_bynumber() function copies a captured substring +into a supplied buffer, whereas pcre2_substring_get_bynumber() copies it +into new memory, obtained using the same memory allocation function that was +used for the match data block. The first two arguments of these functions are a +pointer to the match data block and a capturing group number. +

+

+The final arguments of pcre2_substring_copy_bynumber() are a pointer to +the buffer and a pointer to a variable that contains its length in code units. +This is updated to contain the actual number of code units used for the +extracted substring, excluding the terminating zero. +

+

+For pcre2_substring_get_bynumber() the third and fourth arguments point +to variables that are updated with a pointer to the new memory and the number +of code units that comprise the substring, again excluding the terminating +zero. When the substring is no longer needed, the memory should be freed by +calling pcre2_substring_free(). +

+

+The return value from all these functions is zero for success, or a negative +error code. If the pattern match failed, the match failure code is returned. +If a substring number greater than zero is used after a partial match, +PCRE2_ERROR_PARTIAL is returned. Other possible error codes are: +

+  PCRE2_ERROR_NOMEMORY
+
+The buffer was too small for pcre2_substring_copy_bynumber(), or the +attempt to get memory failed for pcre2_substring_get_bynumber(). +
+  PCRE2_ERROR_NOSUBSTRING
+
+There is no substring with that number in the pattern, that is, the number is +greater than the number of capturing parentheses. +
+  PCRE2_ERROR_UNAVAILABLE
+
+The substring number, though not greater than the number of captures in the +pattern, is greater than the number of slots in the ovector, so the substring +could not be captured. +
+  PCRE2_ERROR_UNSET
+
+The substring did not participate in the match. For example, if the pattern is +(abc)|(def) and the subject is "def", and the ovector contains at least two +capturing slots, substring number 1 is unset. +

+
EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS
+

+int pcre2_substring_list_get(pcre2_match_data *match_data, +" PCRE2_UCHAR ***listptr, PCRE2_SIZE **lengthsptr); +
+
+void pcre2_substring_list_free(PCRE2_SPTR *list); +

+

+The pcre2_substring_list_get() function extracts all available substrings +and builds a list of pointers to them. It also (optionally) builds a second +list that contains their lengths (in code units), excluding a terminating zero +that is added to each of them. All this is done in a single block of memory +that is obtained using the same memory allocation function that was used to get +the match data block. +

+

+This function must be called only after a successful match. If called after a +partial match, the error code PCRE2_ERROR_PARTIAL is returned. +

+

+The address of the memory block is returned via listptr, which is also +the start of the list of string pointers. The end of the list is marked by a +NULL pointer. The address of the list of lengths is returned via +lengthsptr. If your strings do not contain binary zeros and you do not +therefore need the lengths, you may supply NULL as the lengthsptr +argument to disable the creation of a list of lengths. The yield of the +function is zero if all went well, or PCRE2_ERROR_NOMEMORY if the memory block +could not be obtained. When the list is no longer needed, it should be freed by +calling pcre2_substring_list_free(). +

+

+If this function encounters a substring that is unset, which can happen when +capturing subpattern number n+1 matches some part of the subject, but +subpattern n has not been used at all, it returns an empty string. This +can be distinguished from a genuine zero-length substring by inspecting the +appropriate offset in the ovector, which contain PCRE2_UNSET for unset +substrings, or by calling pcre2_substring_length_bynumber(). +

+
EXTRACTING CAPTURED SUBSTRINGS BY NAME
+

+int pcre2_substring_number_from_name(const pcre2_code *code, + PCRE2_SPTR name); +
+
+int pcre2_substring_length_byname(pcre2_match_data *match_data, + PCRE2_SPTR name, PCRE2_SIZE *length); +
+
+int pcre2_substring_copy_byname(pcre2_match_data *match_data, + PCRE2_SPTR name, PCRE2_UCHAR *buffer, PCRE2_SIZE *bufflen); +
+
+int pcre2_substring_get_byname(pcre2_match_data *match_data, + PCRE2_SPTR name, PCRE2_UCHAR **bufferptr, PCRE2_SIZE *bufflen); +
+
+void pcre2_substring_free(PCRE2_UCHAR *buffer); +

+

+To extract a substring by name, you first have to find associated number. +For example, for this pattern: +

+  (a+)b(?<xxx>\d+)...
+
+the number of the subpattern called "xxx" is 2. If the name is known to be +unique (PCRE2_DUPNAMES was not set), you can find the number from the name by +calling pcre2_substring_number_from_name(). The first argument is the +compiled pattern, and the second is the name. The yield of the function is the +subpattern number, PCRE2_ERROR_NOSUBSTRING if there is no subpattern of that +name, or PCRE2_ERROR_NOUNIQUESUBSTRING if there is more than one subpattern of +that name. Given the number, you can extract the substring directly, or use one +of the functions described above. +

+

+For convenience, there are also "byname" functions that correspond to the +"bynumber" functions, the only difference being that the second argument is a +name instead of a number. If PCRE2_DUPNAMES is set and there are duplicate +names, these functions scan all the groups with the given name, and return the +first named string that is set. +

+

+If there are no groups with the given name, PCRE2_ERROR_NOSUBSTRING is +returned. If all groups with the name have numbers that are greater than the +number of slots in the ovector, PCRE2_ERROR_UNAVAILABLE is returned. If there +is at least one group with a slot in the ovector, but no group is found to be +set, PCRE2_ERROR_UNSET is returned. +

+

+Warning: If the pattern uses the (?| feature to set up multiple +subpatterns with the same number, as described in the +section on duplicate subpattern numbers +in the +pcre2pattern +page, you cannot use names to distinguish the different subpatterns, because +names are not included in the compiled code. The matching process uses only +numbers. For this reason, the use of different names for subpatterns of the +same number causes an error at compile time. +

+
CREATING A NEW STRING WITH SUBSTITUTIONS
+

+int pcre2_substitute(const pcre2_code *code, PCRE2_SPTR subject, + PCRE2_SIZE length, PCRE2_SIZE startoffset, + uint32_t options, pcre2_match_data *match_data, + pcre2_match_context *mcontext, PCRE2_SPTR \fIreplacementzfP, + PCRE2_SIZE rlength, PCRE2_UCHAR *\fIoutputbuffer\zfP, + PCRE2_SIZE *outlengthptr); +This function calls pcre2_match() and then makes a copy of the subject +string in outputbuffer, replacing the part that was matched with the +replacement string, whose length is supplied in rlength. This can +be given as PCRE2_ZERO_TERMINATED for a zero-terminated string. +

+

+In the replacement string, which is interpreted as a UTF string in UTF mode, +and is checked for UTF validity unless the PCRE2_NO_UTF_CHECK option is set, a +dollar character is an escape character that can specify the insertion of +characters from capturing groups in the pattern. The following forms are +recognized: +

+  $$      insert a dollar character
+  $<n>    insert the contents of group <n>
+  ${<n>}  insert the contents of group <n>
+
+Either a group number or a group name can be given for <n>. Curly brackets are +required only if the following character would be interpreted as part of the +number or name. The number may be zero to include the entire matched string. +For example, if the pattern a(b)c is matched with "=abc=" and the replacement +string "+$1$0$1+", the result is "=+babcb+=". Group insertion is done by +calling pcre2_copy_byname() or pcre2_copy_bynumber() as +appropriate. +

+

+The first seven arguments of pcre2_substitute() are the same as for +pcre2_match(), except that the partial matching options are not +permitted, and match_data may be passed as NULL, in which case a match +data block is obtained and freed within this function, using memory management +functions from the match context, if provided, or else those that were used to +allocate memory for the compiled code. +

+

+There is one additional option, PCRE2_SUBSTITUTE_GLOBAL, which causes the +function to iterate over the subject string, replacing every matching +substring. If this is not set, only the first matching substring is replaced. +

+

+The outlengthptr argument must point to a variable that contains the +length, in code units, of the output buffer. It is updated to contain the +length of the new string, excluding the trailing zero that is automatically +added. +

+

+The function returns the number of replacements that were made. This may be +zero if no matches were found, and is never greater than 1 unless +PCRE2_SUBSTITUTE_GLOBAL is set. In the event of an error, a negative error code +is returned. Except for PCRE2_ERROR_NOMATCH (which is never returned), any +errors from pcre2_match() or the substring copying functions are passed +straight back. PCRE2_ERROR_BADREPLACEMENT is returned for an invalid +replacement string (unrecognized sequence following a dollar sign), and +PCRE2_ERROR_NOMEMORY is returned if the output buffer is not big enough. +

+
DUPLICATE SUBPATTERN NAMES
+

+int pcre2_substring_nametable_scan(const pcre2_code *code, + PCRE2_SPTR name, PCRE2_SPTR *first, PCRE2_SPTR *last); +

+

+When a pattern is compiled with the PCRE2_DUPNAMES option, names for +subpatterns are not required to be unique. Duplicate names are always allowed +for subpatterns with the same number, created by using the (?| feature. Indeed, +if such subpatterns are named, they are required to use the same names. +

+

+Normally, patterns with duplicate names are such that in any one match, only +one of the named subpatterns participates. An example is shown in the +pcre2pattern +documentation. +

+

+When duplicates are present, pcre2_substring_copy_byname() and +pcre2_substring_get_byname() return the first substring corresponding to +the given name that is set. Only if none are set is PCRE2_ERROR_UNSET is +returned. The pcre2_substring_number_from_name() function returns the +error PCRE2_ERROR_NOUNIQUESUBSTRING when there are duplicate names. +

+

+If you want to get full details of all captured substrings for a given name, +you must use the pcre2_substring_nametable_scan() function. The first +argument is the compiled pattern, and the second is the name. If the third and +fourth arguments are NULL, the function returns a group number for a unique +name, or PCRE2_ERROR_NOUNIQUESUBSTRING otherwise. +

+

+When the third and fourth arguments are not NULL, they must be pointers to +variables that are updated by the function. After it has run, they point to the +first and last entries in the name-to-number table for the given name, and the +function returns the length of each entry in code units. In both cases, +PCRE2_ERROR_NOSUBSTRING is returned if there are no entries for the given name. +

+

+The format of the name table is described above in the section entitled +Information about a pattern +above. +Given all the relevant entries for the name, you can extract each of their +numbers, and hence the captured data. +

+
FINDING ALL POSSIBLE MATCHES AT ONE POSITION
+

+The traditional matching function uses a similar algorithm to Perl, which stops +when it finds the first match at a given point in the subject. If you want to +find all possible matches, or the longest possible match at a given position, +consider using the alternative matching function (see below) instead. If you +cannot use the alternative function, you can kludge it up by making use of the +callout facility, which is described in the +pcre2callout +documentation. +

+

+What you have to do is to insert a callout right at the end of the pattern. +When your callout function is called, extract and save the current matched +substring. Then return 1, which forces pcre2_match() to backtrack and try +other alternatives. Ultimately, when it runs out of matches, +pcre2_match() will yield PCRE2_ERROR_NOMATCH. +

+
MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
+

+int pcre2_dfa_match(const pcre2_code *code, PCRE2_SPTR subject, + PCRE2_SIZE length, PCRE2_SIZE startoffset, + uint32_t options, pcre2_match_data *match_data, + pcre2_match_context *mcontext, + int *workspace, PCRE2_SIZE wscount); +

+

+The function pcre2_dfa_match() is called to match a subject string +against a compiled pattern, using a matching algorithm that scans the subject +string just once, and does not backtrack. This has different characteristics to +the normal algorithm, and is not compatible with Perl. Some of the features of +PCRE2 patterns are not supported. Nevertheless, there are times when this kind +of matching can be useful. For a discussion of the two matching algorithms, and +a list of features that pcre2_dfa_match() does not support, see the +pcre2matching +documentation. +

+

+The arguments for the pcre2_dfa_match() function are the same as for +pcre2_match(), plus two extras. The ovector within the match data block +is used in a different way, and this is described below. The other common +arguments are used in the same way as for pcre2_match(), so their +description is not repeated here. +

+

+The two additional arguments provide workspace for the function. The workspace +vector should contain at least 20 elements. It is used for keeping track of +multiple paths through the pattern tree. More workspace is needed for patterns +and subjects where there are a lot of potential matches. +

+

+Here is an example of a simple call to pcre2_dfa_match(): +

+  int wspace[20];
+  pcre2_match_data *md = pcre2_match_data_create(4, NULL);
+  int rc = pcre2_dfa_match(
+    re,             /* result of pcre2_compile() */
+    "some string",  /* the subject string */
+    11,             /* the length of the subject string */
+    0,              /* start at offset 0 in the subject */
+    0,              /* default options */
+    match_data,     /* the match data block */
+    NULL,           /* a match context; NULL means use defaults */
+    wspace,         /* working space vector */
+    20);            /* number of elements (NOT size in bytes) */
+
+

+
+Option bits for pcre_dfa_match() +
+

+The unused bits of the options argument for pcre2_dfa_match() must +be zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL, +PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_UTF_CHECK, +PCRE2_PARTIAL_HARD, PCRE2_PARTIAL_SOFT, PCRE2_DFA_SHORTEST, and +PCRE2_DFA_RESTART. All but the last four of these are exactly the same as for +pcre2_match(), so their description is not repeated here. +

+  PCRE2_PARTIAL_HARD
+  PCRE2_PARTIAL_SOFT
+
+These have the same general effect as they do for pcre2_match(), but the +details are slightly different. When PCRE2_PARTIAL_HARD is set for +pcre2_dfa_match(), it returns PCRE2_ERROR_PARTIAL if the end of the +subject is reached and there is still at least one matching possibility that +requires additional characters. This happens even if some complete matches have +already been found. When PCRE2_PARTIAL_SOFT is set, the return code +PCRE2_ERROR_NOMATCH is converted into PCRE2_ERROR_PARTIAL if the end of the +subject is reached, there have been no complete matches, but there is still at +least one matching possibility. The portion of the string that was inspected +when the longest partial match was found is set as the first matching string in +both cases. There is a more detailed discussion of partial and multi-segment +matching, with examples, in the +pcre2partial +documentation. +
+  PCRE2_DFA_SHORTEST
+
+Setting the PCRE2_DFA_SHORTEST option causes the matching algorithm to stop as +soon as it has found one match. Because of the way the alternative algorithm +works, this is necessarily the shortest possible match at the first possible +matching point in the subject string. +
+  PCRE2_DFA_RESTART
+
+When pcre2_dfa_match() returns a partial match, it is possible to call it +again, with additional subject characters, and have it continue with the same +match. The PCRE2_DFA_RESTART option requests this action; when it is set, the +workspace and wscount options must reference the same vector as +before because data about the match so far is left in them after a partial +match. There is more discussion of this facility in the +pcre2partial +documentation. +

+
+Successful returns from pcre2_dfa_match() +
+

+When pcre2_dfa_match() succeeds, it may have matched more than one +substring in the subject. Note, however, that all the matches from one run of +the function start at the same point in the subject. The shorter matches are +all initial substrings of the longer matches. For example, if the pattern +

+  <.*>
+
+is matched against the string +
+  This is <something> <something else> <something further> no more
+
+the three matched strings are +
+  <something> <something else> <something further>
+  <something> <something else>
+  <something>
+
+On success, the yield of the function is a number greater than zero, which is +the number of matched substrings. The offsets of the substrings are returned in +the ovector, and can be extracted by number in the same way as for +pcre2_match(), but the numbers bear no relation to any capturing groups +that may exist in the pattern, because DFA matching does not support group +capture. +

+

+Calls to the convenience functions that extract substrings by name +return the error PCRE2_ERROR_DFA_UFUNC (unsupported function) if used after a +DFA match. The convenience functions that extract substrings by number never +return PCRE2_ERROR_NOSUBSTRING, and the meanings of some other errors are +slightly different: +

+  PCRE2_ERROR_UNAVAILABLE
+
+The ovector is not big enough to include a slot for the given substring number. +
+  PCRE2_ERROR_UNSET
+
+There is a slot in the ovector for this substring, but there were insufficient +matches to fill it. +

+

+The matched strings are stored in the ovector in reverse order of length; that +is, the longest matching string is first. If there were too many matches to fit +into the ovector, the yield of the function is zero, and the vector is filled +with the longest matches. +

+

+NOTE: PCRE2's "auto-possessification" optimization usually applies to character +repeats at the end of a pattern (as well as internally). For example, the +pattern "a\d+" is compiled as if it were "a\d++". For DFA matching, this +means that only one possible match is found. If you really do want multiple +matches in such cases, either use an ungreedy repeat auch as "a\d+?" or set +the PCRE2_NO_AUTO_POSSESS option when compiling. +

+
+Error returns from pcre2_dfa_match() +
+

+The pcre2_dfa_match() function returns a negative number when it fails. +Many of the errors are the same as for pcre2_match(), as described +above. +There are in addition the following errors that are specific to +pcre2_dfa_match(): +

+  PCRE2_ERROR_DFA_UITEM
+
+This return is given if pcre2_dfa_match() encounters an item in the +pattern that it does not support, for instance, the use of \C or a back +reference. +
+  PCRE2_ERROR_DFA_UCOND
+
+This return is given if pcre2_dfa_match() encounters a condition item +that uses a back reference for the condition, or a test for recursion in a +specific group. These are not supported. +
+  PCRE2_ERROR_DFA_WSSIZE
+
+This return is given if pcre2_dfa_match() runs out of space in the +workspace vector. +
+  PCRE2_ERROR_DFA_RECURSE
+
+When a recursive subpattern is processed, the matching function calls itself +recursively, using private memory for the ovector and workspace. This +error is given if the internal ovector is not large enough. This should be +extremely rare, as a vector of size 1000 is used. +
+  PCRE2_ERROR_DFA_BADRESTART
+
+When pcre2_dfa_match() is called with the PCRE2_DFA_RESTART option, +some plausibility checks are made on the contents of the workspace, which +should contain data about the previous partial match. If any of these checks +fail, this error is given. +

+
SEE ALSO
+

+pcre2build(3), pcre2callout(3), pcre2demo(3), +pcre2matching(3), pcre2partial(3), pcre2posix(3), +pcre2sample(3), pcre2stack(3), pcre2unicode(3). +

+
AUTHOR
+

+Philip Hazel +
+University Computing Service +
+Cambridge, England. +
+

+
REVISION
+

+Last updated: 22 April 2015 +
+Copyright © 1997-2015 University of Cambridge. +
+

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2build.html b/pcre2-10.20/doc/html/pcre2build.html new file mode 100644 index 000000000..8d9f9ce9e --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2build.html @@ -0,0 +1,504 @@ + + +pcre2build specification + + +

pcre2build man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+

+
BUILDING PCRE2
+

+PCRE2 is distributed with a configure script that can be used to build +the library in Unix-like environments using the applications known as +Autotools. Also in the distribution are files to support building using +CMake instead of configure. The text file +README +contains general information about building with Autotools (some of which is +repeated below), and also has some comments about building on various operating +systems. There is a lot more information about building PCRE2 without using +Autotools (including information about using CMake and building "by +hand") in the text file called +NON-AUTOTOOLS-BUILD. +You should consult this file as well as the +README +file if you are building in a non-Unix-like environment. +

+
PCRE2 BUILD-TIME OPTIONS
+

+The rest of this document describes the optional features of PCRE2 that can be +selected when the library is compiled. It assumes use of the configure +script, where the optional features are selected or deselected by providing +options to configure before running the make command. However, the +same options can be selected in both Unix-like and non-Unix-like environments +if you are using CMake instead of configure to build PCRE2. +

+

+If you are not using Autotools or CMake, option selection can be done by +editing the config.h file, or by passing parameter settings to the +compiler, as described in +NON-AUTOTOOLS-BUILD. +

+

+The complete list of options for configure (which includes the standard +ones such as the selection of the installation directory) can be obtained by +running +

+  ./configure --help
+
+The following sections include descriptions of options whose names begin with +--enable or --disable. These settings specify changes to the defaults for the +configure command. Because of the way that configure works, +--enable and --disable always come in pairs, so the complementary option always +exists as well, but as it specifies the default, it is not described. +

+
BUILDING 8-BIT, 16-BIT AND 32-BIT LIBRARIES
+

+By default, a library called libpcre2-8 is built, containing functions +that take string arguments contained in vectors of bytes, interpreted either as +single-byte characters, or UTF-8 strings. You can also build two other +libraries, called libpcre2-16 and libpcre2-32, which process +strings that are contained in vectors of 16-bit and 32-bit code units, +respectively. These can be interpreted either as single-unit characters or +UTF-16/UTF-32 strings. To build these additional libraries, add one or both of +the following to the configure command: +

+  --enable-pcre2-16
+  --enable-pcre2-32
+
+If you do not want the 8-bit library, add +
+  --disable-pcre2-8
+
+as well. At least one of the three libraries must be built. Note that the POSIX +wrapper is for the 8-bit library only, and that pcre2grep is an 8-bit +program. Neither of these are built if you select only the 16-bit or 32-bit +libraries. +

+
BUILDING SHARED AND STATIC LIBRARIES
+

+The Autotools PCRE2 building process uses libtool to build both shared +and static libraries by default. You can suppress an unwanted library by adding +one of +

+  --disable-shared
+  --disable-static
+
+to the configure command. +

+
UNICODE AND UTF SUPPORT
+

+By default, PCRE2 is built with support for Unicode and UTF character strings. +To build it without Unicode support, add +

+  --disable-unicode
+
+to the configure command. This setting applies to all three libraries. It +is not possible to build one library with Unicode support, and another without, +in the same configuration. +

+

+Of itself, Unicode support does not make PCRE2 treat strings as UTF-8, UTF-16 +or UTF-32. To do that, applications that use the library can set the PCRE2_UTF +option when they call pcre2_compile() to compile a pattern. +Alternatively, patterns may be started with (*UTF) unless the application has +locked this out by setting PCRE2_NEVER_UTF. +

+

+UTF support allows the libraries to process character code points up to +0x10ffff in the strings that they handle. It also provides support for +accessing the Unicode properties of such characters, using pattern escapes such +as \P, \p, and \X. Only the general category properties such as Lu and +Nd are supported. Details are given in the +pcre2pattern +documentation. +

+

+Pattern escapes such as \d and \w do not by default make use of Unicode +properties. The application can request that they do by setting the PCRE2_UCP +option. Unless the application has set PCRE2_NEVER_UCP, a pattern may also +request this by starting with (*UCP). +

+

+The \C escape sequence, which matches a single code unit, even in a UTF mode, +can cause unpredictable behaviour because it may leave the current matching +point in the middle of a multi-code-unit character. It can be locked out by +setting the PCRE2_NEVER_BACKSLASH_C option. +

+
JUST-IN-TIME COMPILER SUPPORT
+

+Just-in-time compiler support is included in the build by specifying +

+  --enable-jit
+
+This support is available only for certain hardware architectures. If this +option is set for an unsupported architecture, a building error occurs. +See the +pcre2jit +documentation for a discussion of JIT usage. When JIT support is enabled, +pcre2grep automatically makes use of it, unless you add +
+  --disable-pcre2grep-jit
+
+to the "configure" command. +

+
NEWLINE RECOGNITION
+

+By default, PCRE2 interprets the linefeed (LF) character as indicating the end +of a line. This is the normal newline character on Unix-like systems. You can +compile PCRE2 to use carriage return (CR) instead, by adding +

+  --enable-newline-is-cr
+
+to the configure command. There is also an --enable-newline-is-lf option, +which explicitly specifies linefeed as the newline character. +

+

+Alternatively, you can specify that line endings are to be indicated by the +two-character sequence CRLF (CR immediately followed by LF). If you want this, +add +

+  --enable-newline-is-crlf
+
+to the configure command. There is a fourth option, specified by +
+  --enable-newline-is-anycrlf
+
+which causes PCRE2 to recognize any of the three sequences CR, LF, or CRLF as +indicating a line ending. Finally, a fifth option, specified by +
+  --enable-newline-is-any
+
+causes PCRE2 to recognize any Unicode newline sequence. The Unicode newline +sequences are the three just mentioned, plus the single characters VT (vertical +tab, U+000B), FF (form feed, U+000C), NEL (next line, U+0085), LS (line +separator, U+2028), and PS (paragraph separator, U+2029). +

+

+Whatever default line ending convention is selected when PCRE2 is built can be +overridden by applications that use the library. At build time it is +conventional to use the standard for your operating system. +

+
WHAT \R MATCHES
+

+By default, the sequence \R in a pattern matches any Unicode newline sequence, +independently of what has been selected as the line ending sequence. If you +specify +

+  --enable-bsr-anycrlf
+
+the default is changed so that \R matches only CR, LF, or CRLF. Whatever is +selected when PCRE2 is built can be overridden by applications that use the +called. +

+
HANDLING VERY LARGE PATTERNS
+

+Within a compiled pattern, offset values are used to point from one part to +another (for example, from an opening parenthesis to an alternation +metacharacter). By default, in the 8-bit and 16-bit libraries, two-byte values +are used for these offsets, leading to a maximum size for a compiled pattern of +around 64K code units. This is sufficient to handle all but the most gigantic +patterns. Nevertheless, some people do want to process truly enormous patterns, +so it is possible to compile PCRE2 to use three-byte or four-byte offsets by +adding a setting such as +

+  --with-link-size=3
+
+to the configure command. The value given must be 2, 3, or 4. For the +16-bit library, a value of 3 is rounded up to 4. In these libraries, using +longer offsets slows down the operation of PCRE2 because it has to load +additional data when handling them. For the 32-bit library the value is always +4 and cannot be overridden; the value of --with-link-size is ignored. +

+
AVOIDING EXCESSIVE STACK USAGE
+

+When matching with the pcre2_match() function, PCRE2 implements +backtracking by making recursive calls to an internal function called +match(). In environments where the size of the stack is limited, this can +severely limit PCRE2's operation. (The Unix environment does not usually suffer +from this problem, but it may sometimes be necessary to increase the maximum +stack size. There is a discussion in the +pcre2stack +documentation.) An alternative approach to recursion that uses memory from the +heap to remember data, instead of using recursive function calls, has been +implemented to work round the problem of limited stack size. If you want to +build a version of PCRE2 that works this way, add +

+  --disable-stack-for-recursion
+
+to the configure command. By default, the system functions malloc() +and free() are called to manage the heap memory that is required, but +custom memory management functions can be called instead. PCRE2 runs noticeably +more slowly when built in this way. This option affects only the +pcre2_match() function; it is not relevant for pcre2_dfa_match(). +

+
LIMITING PCRE2 RESOURCE USAGE
+

+Internally, PCRE2 has a function called match(), which it calls +repeatedly (sometimes recursively) when matching a pattern with the +pcre2_match() function. By controlling the maximum number of times this +function may be called during a single matching operation, a limit can be +placed on the resources used by a single call to pcre2_match(). The limit +can be changed at run time, as described in the +pcre2api +documentation. The default is 10 million, but this can be changed by adding a +setting such as +

+  --with-match-limit=500000
+
+to the configure command. This setting has no effect on the +pcre2_dfa_match() matching function. +

+

+In some environments it is desirable to limit the depth of recursive calls of +match() more strictly than the total number of calls, in order to +restrict the maximum amount of stack (or heap, if --disable-stack-for-recursion +is specified) that is used. A second limit controls this; it defaults to the +value that is set for --with-match-limit, which imposes no additional +constraints. However, you can set a lower limit by adding, for example, +

+  --with-match-limit-recursion=10000
+
+to the configure command. This value can also be overridden at run time. +

+
CREATING CHARACTER TABLES AT BUILD TIME
+

+PCRE2 uses fixed tables for processing characters whose code points are less +than 256. By default, PCRE2 is built with a set of tables that are distributed +in the file src/pcre2_chartables.c.dist. These tables are for ASCII codes +only. If you add +

+  --enable-rebuild-chartables
+
+to the configure command, the distributed tables are no longer used. +Instead, a program called dftables is compiled and run. This outputs the +source for new set of tables, created in the default locale of your C run-time +system. (This method of replacing the tables does not work if you are cross +compiling, because dftables is run on the local host. If you need to +create alternative tables when cross compiling, you will have to do so "by +hand".) +

+
USING EBCDIC CODE
+

+PCRE2 assumes by default that it will run in an environment where the character +code is ASCII or Unicode, which is a superset of ASCII. This is the case for +most computer operating systems. PCRE2 can, however, be compiled to run in an +8-bit EBCDIC environment by adding +

+  --enable-ebcdic --disable-unicode
+
+to the configure command. This setting implies +--enable-rebuild-chartables. You should only use it if you know that you are in +an EBCDIC environment (for example, an IBM mainframe operating system). +

+

+It is not possible to support both EBCDIC and UTF-8 codes in the same version +of the library. Consequently, --enable-unicode and --enable-ebcdic are mutually +exclusive. +

+

+The EBCDIC character that corresponds to an ASCII LF is assumed to have the +value 0x15 by default. However, in some EBCDIC environments, 0x25 is used. In +such an environment you should use +

+  --enable-ebcdic-nl25
+
+as well as, or instead of, --enable-ebcdic. The EBCDIC character for CR has the +same value as in ASCII, namely, 0x0d. Whichever of 0x15 and 0x25 is not +chosen as LF is made to correspond to the Unicode NEL character (which, in +Unicode, is 0x85). +

+

+The options that select newline behaviour, such as --enable-newline-is-cr, +and equivalent run-time options, refer to these character values in an EBCDIC +environment. +

+
PCRE2GREP OPTIONS FOR COMPRESSED FILE SUPPORT
+

+By default, pcre2grep reads all files as plain text. You can build it so +that it recognizes files whose names end in .gz or .bz2, and reads +them with libz or libbz2, respectively, by adding one or both of +

+  --enable-pcre2grep-libz
+  --enable-pcre2grep-libbz2
+
+to the configure command. These options naturally require that the +relevant libraries are installed on your system. Configuration will fail if +they are not. +

+
PCRE2GREP BUFFER SIZE
+

+pcre2grep uses an internal buffer to hold a "window" on the file it is +scanning, in order to be able to output "before" and "after" lines when it +finds a match. The size of the buffer is controlled by a parameter whose +default value is 20K. The buffer itself is three times this size, but because +of the way it is used for holding "before" lines, the longest line that is +guaranteed to be processable is the parameter size. You can change the default +parameter value by adding, for example, +

+  --with-pcre2grep-bufsize=50K
+
+to the configure command. The caller of \fPpcre2grep\fP can override this +value by using --buffer-size on the command line.. +

+
PCRE2TEST OPTION FOR LIBREADLINE SUPPORT
+

+If you add one of +

+  --enable-pcre2test-libreadline
+  --enable-pcre2test-libedit
+
+to the configure command, pcre2test is linked with the +libreadline orlibedit library, respectively, and when its input is +from a terminal, it reads it using the readline() function. This provides +line-editing and history facilities. Note that libreadline is +GPL-licensed, so if you distribute a binary of pcre2test linked in this +way, there may be licensing issues. These can be avoided by linking instead +with libedit, which has a BSD licence. +

+

+Setting --enable-pcre2test-libreadline causes the -lreadline option to be +added to the pcre2test build. In many operating environments with a +sytem-installed readline library this is sufficient. However, in some +environments (e.g. if an unmodified distribution version of readline is in +use), some extra configuration may be necessary. The INSTALL file for +libreadline says this: +

+  "Readline uses the termcap functions, but does not link with
+  the termcap or curses library itself, allowing applications
+  which link with readline the to choose an appropriate library."
+
+If your environment has not been set up so that an appropriate library is +automatically included, you may need to add something like +
+  LIBS="-ncurses"
+
+immediately before the configure command. +

+
INCLUDING DEBUGGING CODE
+

+If you add +

+  --enable-debug
+
+to the configure command, additional debugging code is included in the +build. This feature is intended for use by the PCRE2 maintainers. +

+
DEBUGGING WITH VALGRIND SUPPORT
+

+If you add +

+  --enable-valgrind
+
+to the configure command, PCRE2 will use valgrind annotations to mark +certain memory regions as unaddressable. This allows it to detect invalid +memory accesses, and is mostly useful for debugging PCRE2 itself. +

+
CODE COVERAGE REPORTING
+

+If your C compiler is gcc, you can build a version of PCRE2 that can generate a +code coverage report for its test suite. To enable this, you must install +lcov version 1.6 or above. Then specify +

+  --enable-coverage
+
+to the configure command and build PCRE2 in the usual way. +

+

+Note that using ccache (a caching C compiler) is incompatible with code +coverage reporting. If you have configured ccache to run automatically +on your system, you must set the environment variable +

+  CCACHE_DISABLE=1
+
+before running make to build PCRE2, so that ccache is not used. +

+

+When --enable-coverage is used, the following addition targets are added to the +Makefile: +

+  make coverage
+
+This creates a fresh coverage report for the PCRE2 test suite. It is equivalent +to running "make coverage-reset", "make coverage-baseline", "make check", and +then "make coverage-report". +
+  make coverage-reset
+
+This zeroes the coverage counters, but does nothing else. +
+  make coverage-baseline
+
+This captures baseline coverage information. +
+  make coverage-report
+
+This creates the coverage report. +
+  make coverage-clean-report
+
+This removes the generated coverage report without cleaning the coverage data +itself. +
+  make coverage-clean-data
+
+This removes the captured coverage data without removing the coverage files +created at compile time (*.gcno). +
+  make coverage-clean
+
+This cleans all coverage data including the generated coverage report. For more +information about code coverage, see the gcov and lcov +documentation. +

+
SEE ALSO
+

+pcre2api(3), pcre2-config(3). +

+
AUTHOR
+

+Philip Hazel +
+University Computing Service +
+Cambridge, England. +
+

+
REVISION
+

+Last updated: 24 April 2015 +
+Copyright © 1997-2015 University of Cambridge. +
+

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2callout.html b/pcre2-10.20/doc/html/pcre2callout.html new file mode 100644 index 000000000..7e85c9a39 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2callout.html @@ -0,0 +1,408 @@ + + +pcre2callout specification + + +

pcre2callout man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+

+
SYNOPSIS
+

+#include <pcre2.h> +

+

+int (*pcre2_callout)(pcre2_callout_block *, void *); +
+
+int pcre2_callout_enumerate(const pcre2_code *code, + int (*callback)(pcre2_callout_enumerate_block *, void *), + void *user_data); +

+
DESCRIPTION
+

+PCRE2 provides a feature called "callout", which is a means of temporarily +passing control to the caller of PCRE2 in the middle of pattern matching. The +caller of PCRE2 provides an external function by putting its entry point in +a match context (see pcre2_set_callout() in the +pcre2api +documentation). +

+

+Within a regular expression, (?C<arg>) indicates a point at which the external +function is to be called. Different callout points can be identified by putting +a number less than 256 after the letter C. The default value is zero. +Alternatively, the argument may be a delimited string. The starting delimiter +must be one of ` ' " ^ % # $ { and the ending delimiter is the same as the +start, except for {, where the ending delimiter is }. If the ending delimiter +is needed within the string, it must be doubled. For example, this pattern has +two callout points: +

+  (?C1)abc(?C"some ""arbitrary"" text")def
+
+If the PCRE2_AUTO_CALLOUT option bit is set when a pattern is compiled, PCRE2 +automatically inserts callouts, all with number 255, before each item in the +pattern. For example, if PCRE2_AUTO_CALLOUT is used with the pattern +
+  A(\d{2}|--)
+
+it is processed as if it were +
+
+(?C255)A(?C255)((?C255)\d{2}(?C255)|(?C255)-(?C255)-(?C255))(?C255) +
+
+Notice that there is a callout before and after each parenthesis and +alternation bar. If the pattern contains a conditional group whose condition is +an assertion, an automatic callout is inserted immediately before the +condition. Such a callout may also be inserted explicitly, for example: +
+  (?(?C9)(?=a)ab|de)  (?(?C%text%)(?!=d)ab|de)
+
+This applies only to assertion conditions (because they are themselves +independent groups). +

+

+Callouts can be useful for tracking the progress of pattern matching. The +pcre2test +program has a pattern qualifier (/auto_callout) that sets automatic callouts. +When any callouts are present, the output from pcre2test indicates how +the pattern is being matched. This is useful information when you are trying to +optimize the performance of a particular pattern. +

+
MISSING CALLOUTS
+

+You should be aware that, because of optimizations in the way PCRE2 compiles +and matches patterns, callouts sometimes do not happen exactly as you might +expect. +

+
+Auto-possessification +
+

+At compile time, PCRE2 "auto-possessifies" repeated items when it knows that +what follows cannot be part of the repeat. For example, a+[bc] is compiled as +if it were a++[bc]. The pcre2test output when this pattern is compiled +with PCRE2_ANCHORED and PCRE2_AUTO_CALLOUT and then applied to the string +"aaaa" is: +

+  --->aaaa
+   +0 ^        a+
+   +2 ^   ^    [bc]
+  No match
+
+This indicates that when matching [bc] fails, there is no backtracking into a+ +and therefore the callouts that would be taken for the backtracks do not occur. +You can disable the auto-possessify feature by passing PCRE2_NO_AUTO_POSSESS to +pcre2_compile(), or starting the pattern with (*NO_AUTO_POSSESS). In this +case, the output changes to this: +
+  --->aaaa
+   +0 ^        a+
+   +2 ^   ^    [bc]
+   +2 ^  ^     [bc]
+   +2 ^ ^      [bc]
+   +2 ^^       [bc]
+  No match
+
+This time, when matching [bc] fails, the matcher backtracks into a+ and tries +again, repeatedly, until a+ itself fails. +

+
+Automatic .* anchoring +
+

+By default, an optimization is applied when .* is the first significant item in +a pattern. If PCRE2_DOTALL is set, so that the dot can match any character, the +pattern is automatically anchored. If PCRE2_DOTALL is not set, a match can +start only after an internal newline or at the beginning of the subject, and +pcre2_compile() remembers this. This optimization is disabled, however, +if .* is in an atomic group or if there is a back reference to the capturing +group in which it appears. It is also disabled if the pattern contains (*PRUNE) +or (*SKIP). However, the presence of callouts does not affect it. +

+

+For example, if the pattern .*\d is compiled with PCRE2_AUTO_CALLOUT and +applied to the string "aa", the pcre2test output is: +

+  --->aa
+   +0 ^      .*
+   +2 ^ ^    \d
+   +2 ^^     \d
+   +2 ^      \d
+  No match
+
+This shows that all match attempts start at the beginning of the subject. In +other words, the pattern is anchored. You can disable this optimization by +passing PCRE2_NO_DOTSTAR_ANCHOR to pcre2_compile(), or starting the +pattern with (*NO_DOTSTAR_ANCHOR). In this case, the output changes to: +
+  --->aa
+   +0 ^      .*
+   +2 ^ ^    \d
+   +2 ^^     \d
+   +2 ^      \d
+   +0  ^     .*
+   +2  ^^    \d
+   +2  ^     \d
+  No match
+
+This shows more match attempts, starting at the second subject character. +Another optimization, described in the next section, means that there is no +subsequent attempt to match with an empty subject. +

+

+If a pattern has more than one top-level branch, automatic anchoring occurs if +all branches are anchorable. +

+
+Other optimizations +
+

+Other optimizations that provide fast "no match" results also affect callouts. +For example, if the pattern is +

+  ab(?C4)cd
+
+PCRE2 knows that any matching string must contain the letter "d". If the +subject string is "abyz", the lack of "d" means that matching doesn't ever +start, and the callout is never reached. However, with "abyd", though the +result is still no match, the callout is obeyed. +

+

+PCRE2 also knows the minimum length of a matching string, and will immediately +give a "no match" return without actually running a match if the subject is not +long enough, or, for unanchored patterns, if it has been scanned far enough. +

+

+You can disable these optimizations by passing the PCRE2_NO_START_OPTIMIZE +option to pcre2_compile(), or by starting the pattern with +(*NO_START_OPT). This slows down the matching process, but does ensure that +callouts such as the example above are obeyed. +

+
THE CALLOUT INTERFACE
+

+During matching, when PCRE2 reaches a callout point, if an external function is +set in the match context, it is called. This applies to both normal and DFA +matching. The first argument to the callout function is a pointer to a +pcre2_callout block. The second argument is the void * callout data that +was supplied when the callout was set up by calling pcre2_set_callout() +(see the +pcre2api +documentation). The callout block structure contains the following fields: +

+  uint32_t      version;
+  uint32_t      callout_number;
+  uint32_t      capture_top;
+  uint32_t      capture_last;
+  PCRE2_SIZE   *offset_vector;
+  PCRE2_SPTR    mark;
+  PCRE2_SPTR    subject;
+  PCRE2_SIZE    subject_length;
+  PCRE2_SIZE    start_match;
+  PCRE2_SIZE    current_position;
+  PCRE2_SIZE    pattern_position;
+  PCRE2_SIZE    next_item_length;
+  PCRE2_SIZE    callout_string_offset;
+  PCRE2_SIZE    callout_string_length;
+  PCRE2_SPTR    callout_string;
+
+The version field contains the version number of the block format. The +current version is 1; the three callout string fields were added for this +version. If you are writing an application that might use an earlier release of +PCRE2, you should check the version number before accessing any of these +fields. The version number will increase in future if more fields are added, +but the intention is never to remove any of the existing fields. +

+
+Fields for numerical callouts +
+

+For a numerical callout, callout_string is NULL, and callout_number +contains the number of the callout, in the range 0-255. This is the number +that follows (?C for manual callouts; it is 255 for automatically generated +callouts. +

+
+Fields for string callouts +
+

+For callouts with string arguments, callout_number is always zero, and +callout_string points to the string that is contained within the compiled +pattern. Its length is given by callout_string_length. Duplicated ending +delimiters that were present in the original pattern string have been turned +into single characters, but there is no other processing of the callout string +argument. An additional code unit containing binary zero is present after the +string, but is not included in the length. The delimiter that was used to start +the string is also stored within the pattern, immediately before the string +itself. You can access this delimiter as callout_string[-1] if you need +it. +

+

+The callout_string_offset field is the code unit offset to the start of +the callout argument string within the original pattern string. This is +provided for the benefit of applications such as script languages that might +need to report errors in the callout string within the pattern. +

+
+Fields for all callouts +
+

+The remaining fields in the callout block are the same for both kinds of +callout. +

+

+The offset_vector field is a pointer to the vector of capturing offsets +(the "ovector") that was passed to the matching function in the match data +block. When pcre2_match() is used, the contents can be inspected in +order to extract substrings that have been matched so far, in the same way as +for extracting substrings after a match has completed. For the DFA matching +function, this field is not useful. +

+

+The subject and subject_length fields contain copies of the values +that were passed to the matching function. +

+

+The start_match field normally contains the offset within the subject at +which the current match attempt started. However, if the escape sequence \K +has been encountered, this value is changed to reflect the modified starting +point. If the pattern is not anchored, the callout function may be called +several times from the same point in the pattern for different starting points +in the subject. +

+

+The current_position field contains the offset within the subject of the +current match pointer. +

+

+When the pcre2_match() is used, the capture_top field contains one +more than the number of the highest numbered captured substring so far. If no +substrings have been captured, the value of capture_top is one. This is +always the case when the DFA functions are used, because they do not support +captured substrings. +

+

+The capture_last field contains the number of the most recently captured +substring. However, when a recursion exits, the value reverts to what it was +outside the recursion, as do the values of all captured substrings. If no +substrings have been captured, the value of capture_last is 0. This is +always the case for the DFA matching functions. +

+

+The pattern_position field contains the offset in the pattern string to +the next item to be matched. +

+

+The next_item_length field contains the length of the next item to be +matched in the pattern string. When the callout immediately precedes an +alternation bar, a closing parenthesis, or the end of the pattern, the length +is zero. When the callout precedes an opening parenthesis, the length is that +of the entire subpattern. +

+

+The pattern_position and next_item_length fields are intended to +help in distinguishing between different automatic callouts, which all have the +same callout number. However, they are set for all callouts, and are used by +pcre2test to show the next item to be matched when displaying callout +information. +

+

+In callouts from pcre2_match() the mark field contains a pointer to +the zero-terminated name of the most recently passed (*MARK), (*PRUNE), or +(*THEN) item in the match, or NULL if no such items have been passed. Instances +of (*PRUNE) or (*THEN) without a name do not obliterate a previous (*MARK). In +callouts from the DFA matching function this field always contains NULL. +

+
RETURN VALUES FROM CALLOUTS
+

+The external callout function returns an integer to PCRE2. If the value is +zero, matching proceeds as normal. If the value is greater than zero, matching +fails at the current point, but the testing of other matching possibilities +goes ahead, just as if a lookahead assertion had failed. If the value is less +than zero, the match is abandoned, and the matching function returns the +negative value. +

+

+Negative values should normally be chosen from the set of PCRE2_ERROR_xxx +values. In particular, PCRE2_ERROR_NOMATCH forces a standard "no match" +failure. The error number PCRE2_ERROR_CALLOUT is reserved for use by callout +functions; it will never be used by PCRE2 itself. +

+
CALLOUT ENUMERATION
+

+int pcre2_callout_enumerate(const pcre2_code *code, + int (*callback)(pcre2_callout_enumerate_block *, void *), + void *user_data); +
+
+A script language that supports the use of string arguments in callouts might +like to scan all the callouts in a pattern before running the match. This can +be done by calling pcre2_callout_enumerate(). The first argument is a +pointer to a compiled pattern, the second points to a callback function, and +the third is arbitrary user data. The callback function is called for every +callout in the pattern in the order in which they appear. Its first argument is +a pointer to a callout enumeration block, and its second argument is the +user_data value that was passed to pcre2_callout_enumerate(). The +data block contains the following fields: +

+  version                Block version number
+  pattern_position       Offset to next item in pattern
+  next_item_length       Length of next item in pattern
+  callout_number         Number for numbered callouts
+  callout_string_offset  Offset to string within pattern
+  callout_string_length  Length of callout string
+  callout_string         Points to callout string or is NULL
+
+The version number is currently 0. It will increase if new fields are ever +added to the block. The remaining fields are the same as their namesakes in the +pcre2_callout block that is used for callouts during matching, as +described +above. +

+

+Note that the value of pattern_position is unique for each callout. +However, if a callout occurs inside a group that is quantified with a non-zero +minimum or a fixed maximum, the group is replicated inside the compiled +pattern. For example, a pattern such as /(a){2}/ is compiled as if it were +/(a)(a)/. This means that the callout will be enumerated more than once, but +with the same value for pattern_position in each case. +

+

+The callback function should normally return zero. If it returns a non-zero +value, scanning the pattern stops, and that value is returned from +pcre2_callout_enumerate(). +

+
AUTHOR
+

+Philip Hazel +
+University Computing Service +
+Cambridge, England. +
+

+
REVISION
+

+Last updated: 23 March 2015 +
+Copyright © 1997-2015 University of Cambridge. +
+

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2compat.html b/pcre2-10.20/doc/html/pcre2compat.html new file mode 100644 index 000000000..3b29e6fa2 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2compat.html @@ -0,0 +1,223 @@ + + +pcre2compat specification + + +

pcre2compat man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+DIFFERENCES BETWEEN PCRE2 AND PERL +
+

+This document describes the differences in the ways that PCRE2 and Perl handle +regular expressions. The differences described here are with respect to Perl +versions 5.10 and above. +

+

+1. PCRE2 has only a subset of Perl's Unicode support. Details of what it does +have are given in the +pcre2unicode +page. +

+

+2. PCRE2 allows repeat quantifiers only on parenthesized assertions, but they +do not mean what you might think. For example, (?!a){3} does not assert that +the next three characters are not "a". It just asserts that the next character +is not "a" three times (in principle: PCRE2 optimizes this to run the assertion +just once). Perl allows repeat quantifiers on other assertions such as \b, but +these do not seem to have any use. +

+

+3. Capturing subpatterns that occur inside negative lookahead assertions are +counted, but their entries in the offsets vector are never set. Perl sometimes +(but not always) sets its numerical variables from inside negative assertions. +

+

+4. The following Perl escape sequences are not supported: \l, \u, \L, +\U, and \N when followed by a character name or Unicode value. (\N on its +own, matching a non-newline character, is supported.) In fact these are +implemented by Perl's general string-handling and are not part of its pattern +matching engine. If any of these are encountered by PCRE2, an error is +generated by default. However, if the PCRE2_ALT_BSUX option is set, +\U and \u are interpreted as ECMAScript interprets them. +

+

+5. The Perl escape sequences \p, \P, and \X are supported only if PCRE2 is +built with Unicode support. The properties that can be tested with \p and \P +are limited to the general category properties such as Lu and Nd, script names +such as Greek or Han, and the derived properties Any and L&. PCRE2 does support +the Cs (surrogate) property, which Perl does not; the Perl documentation says +"Because Perl hides the need for the user to understand the internal +representation of Unicode characters, there is no need to implement the +somewhat messy concept of surrogates." +

+

+6. PCRE2 does support the \Q...\E escape for quoting substrings. Characters +in between are treated as literals. This is slightly different from Perl in +that $ and @ are also handled as literals inside the quotes. In Perl, they +cause variable interpolation (but of course PCRE2 does not have variables). +Note the following examples: +

+    Pattern            PCRE2 matches      Perl matches
+
+    \Qabc$xyz\E        abc$xyz           abc followed by the contents of $xyz
+    \Qabc\$xyz\E       abc\$xyz          abc\$xyz
+    \Qabc\E\$\Qxyz\E   abc$xyz           abc$xyz
+
+The \Q...\E sequence is recognized both inside and outside character classes. +

+

+7. Fairly obviously, PCRE2 does not support the (?{code}) and (??{code}) +constructions. However, there is support for recursive patterns. This is not +available in Perl 5.8, but it is in Perl 5.10. Also, the PCRE2 "callout" +feature allows an external function to be called during pattern matching. See +the +pcre2callout +documentation for details. +

+

+8. Subroutine calls (whether recursive or not) are treated as atomic groups. +Atomic recursion is like Python, but unlike Perl. Captured values that are set +outside a subroutine call can be referenced from inside in PCRE2, but not in +Perl. There is a discussion that explains these differences in more detail in +the +section on recursion differences from Perl +in the +pcre2pattern +page. +

+

+9. If any of the backtracking control verbs are used in a subpattern that is +called as a subroutine (whether or not recursively), their effect is confined +to that subpattern; it does not extend to the surrounding pattern. This is not +always the case in Perl. In particular, if (*THEN) is present in a group that +is called as a subroutine, its action is limited to that group, even if the +group does not contain any | characters. Note that such subpatterns are +processed as anchored at the point where they are tested. +

+

+10. If a pattern contains more than one backtracking control verb, the first +one that is backtracked onto acts. For example, in the pattern +A(*COMMIT)B(*PRUNE)C a failure in B triggers (*COMMIT), but a failure in C +triggers (*PRUNE). Perl's behaviour is more complex; in many cases it is the +same as PCRE2, but there are examples where it differs. +

+

+11. Most backtracking verbs in assertions have their normal actions. They are +not confined to the assertion. +

+

+12. There are some differences that are concerned with the settings of captured +strings when part of a pattern is repeated. For example, matching "aba" against +the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE2 it is set to +"b". +

+

+13. PCRE2's handling of duplicate subpattern numbers and duplicate subpattern +names is not as general as Perl's. This is a consequence of the fact the PCRE2 +works internally just with numbers, using an external table to translate +between numbers and names. In particular, a pattern such as (?|(?<a>A)|(?<b)B), +where the two capturing parentheses have the same number but different names, +is not supported, and causes an error at compile time. If it were allowed, it +would not be possible to distinguish which parentheses matched, because both +names map to capturing subpattern number 1. To avoid this confusing situation, +an error is given at compile time. +

+

+14. Perl recognizes comments in some places that PCRE2 does not, for example, +between the ( and ? at the start of a subpattern. If the /x modifier is set, +Perl allows white space between ( and ? (though current Perls warn that this is +deprecated) but PCRE2 never does, even if the PCRE2_EXTENDED option is set. +

+

+15. Perl, when in warning mode, gives warnings for character classes such as +[A-\d] or [a-[:digit:]]. It then treats the hyphens as literals. PCRE2 has no +warning features, so it gives an error in these cases because they are almost +certainly user mistakes. +

+

+16. In PCRE2, the upper/lower case character properties Lu and Ll are not +affected when case-independent matching is specified. For example, \p{Lu} +always matches an upper case letter. I think Perl has changed in this respect; +in the release at the time of writing (5.16), \p{Lu} and \p{Ll} match all +letters, regardless of case, when case independence is specified. +

+

+17. PCRE2 provides some extensions to the Perl regular expression facilities. +Perl 5.10 includes new features that are not in earlier versions of Perl, some +of which (such as named parentheses) have been in PCRE2 for some time. This +list is with respect to Perl 5.10: +
+
+(a) Although lookbehind assertions in PCRE2 must match fixed length strings, +each alternative branch of a lookbehind assertion can match a different length +of string. Perl requires them all to have the same length. +
+
+(b) If PCRE2_DOLLAR_ENDONLY is set and PCRE2_MULTILINE is not set, the $ +meta-character matches only at the very end of the string. +
+
+(c) A backslash followed by a letter with no special meaning is faulted. (Perl +can be made to issue a warning.) +
+
+(d) If PCRE2_UNGREEDY is set, the greediness of the repetition quantifiers is +inverted, that is, by default they are not greedy, but if followed by a +question mark they are. +
+
+(e) PCRE2_ANCHORED can be used at matching time to force a pattern to be tried +only at the first matching position in the subject string. +
+
+(f) The PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, and +PCRE2_NO_AUTO_CAPTURE options have no Perl equivalents. +
+
+(g) The \R escape sequence can be restricted to match only CR, LF, or CRLF +by the PCRE2_BSR_ANYCRLF option. +
+
+(h) The callout facility is PCRE2-specific. +
+
+(i) The partial matching facility is PCRE2-specific. +
+
+(j) The alternative matching function (pcre2_dfa_match() matches in a +different way and is not Perl-compatible. +
+
+(k) PCRE2 recognizes some special sequences such as (*CR) at the start of +a pattern that set overall options that cannot be changed within the pattern. +

+
+AUTHOR +
+

+Philip Hazel +
+University Computing Service +
+Cambridge, England. +
+

+
+REVISION +
+

+Last updated: 15 March 2015 +
+Copyright © 1997-2015 University of Cambridge. +
+

+Return to the PCRE2 index page. +

diff --git a/pcre2-10.20/doc/html/pcre2demo.html b/pcre2-10.20/doc/html/pcre2demo.html new file mode 100644 index 000000000..5919117a1 --- /dev/null +++ b/pcre2-10.20/doc/html/pcre2demo.html @@ -0,0 +1,443 @@ + + +pcre2demo specification + + +

pcre2demo man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+

    +
+
+/*************************************************
+*           PCRE2 DEMONSTRATION PROGRAM          *
+*************************************************/
+
+/* This is a demonstration program to illustrate a straightforward way of
+calling the PCRE2 regular expression library from a C program. See the
+pcre2sample documentation for a short discussion ("man pcre2sample" if you have
+the PCRE2 man pages installed). PCRE2 is a revised API for the library, and is
+incompatible with the original PCRE API.
+
+There are actually three libraries, each supporting a different code unit
+width. This demonstration program uses the 8-bit library.
+
+In Unix-like environments, if PCRE2 is installed in your standard system
+libraries, you should be able to compile this program using this command:
+
+gcc -Wall pcre2demo.c -lpcre2-8 -o pcre2demo
+
+If PCRE2 is not installed in a standard place, it is likely to be installed
+with support for the pkg-config mechanism. If you have pkg-config, you can
+compile this program using this command:
+
+gcc -Wall pcre2demo.c `pkg-config --cflags --libs libpcre2-8` -o pcre2demo
+
+If you do not have pkg-config, you may have to use this:
+
+gcc -Wall pcre2demo.c -I/usr/local/include -L/usr/local/lib \
+  -R/usr/local/lib -lpcre2-8 -o pcre2demo
+
+Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and
+library files for PCRE2 are installed on your system. Only some operating
+systems (Solaris is one) use the -R option.
+
+Building under Windows:
+
+If you want to statically link this program against a non-dll .a file, you must
+define PCRE2_STATIC before including pcre2.h, so in this environment, uncomment
+the following line. */
+
+/* #define PCRE2_STATIC */
+
+/* This macro must be defined before including pcre2.h. For a program that uses
+only one code unit width, it makes it possible to use generic function names
+such as pcre2_compile(). */
+
+#define PCRE2_CODE_UNIT_WIDTH 8
+
+#include <stdio.h>
+#include <string.h>
+#include <pcre2.h>
+
+
+/**************************************************************************
+* Here is the program. The API includes the concept of "contexts" for     *
+* setting up unusual interface requirements for compiling and matching,   *
+* such as custom memory managers and non-standard newline definitions.    *
+* This program does not do any of this, so it makes no use of contexts,   *
+* always passing NULL where a context could be given.                     *
+**************************************************************************/
+
+int main(int argc, char **argv)
+{
+pcre2_code *re;
+PCRE2_SPTR pattern;     /* PCRE2_SPTR is a pointer to unsigned code units of */
+PCRE2_SPTR subject;     /* the appropriate width (8, 16, or 32 bits). */
+PCRE2_SPTR name_table;
+
+int crlf_is_newline;
+int errornumber;
+int find_all;
+int i;
+int namecount;
+int name_entry_size;
+int rc;
+int utf8;
+
+uint32_t option_bits;
+uint32_t newline;
+
+PCRE2_SIZE erroroffset;
+PCRE2_SIZE *ovector;
+
+size_t subject_length;
+pcre2_match_data *match_data;
+
+
+
+/**************************************************************************
+* First, sort out the command line. There is only one possible option at  *
+* the moment, "-g" to request repeated matching to find all occurrences,  *
+* like Perl's /g option. We set the variable find_all to a non-zero value *
+* if the -g option is present. Apart from that, there must be exactly two *
+* arguments.                                                              *
+**************************************************************************/
+
+find_all = 0;
+for (i = 1; i < argc; i++)
+  {
+  if (strcmp(argv[i], "-g") == 0) find_all = 1;
+    else break;
+  }
+
+/* After the options, we require exactly two arguments, which are the pattern,
+and the subject string. */
+
+if (argc - i != 2)
+  {
+  printf("Two arguments required: a regex and a subject string\n");
+  return 1;
+  }
+
+/* As pattern and subject are char arguments, they can be straightforwardly
+cast to PCRE2_SPTR as we are working in 8-bit code units. */
+
+pattern = (PCRE2_SPTR)argv[i];
+subject = (PCRE2_SPTR)argv[i+1];
+subject_length = strlen((char *)subject);
+
+
+/*************************************************************************
+* Now we are going to compile the regular expression pattern, and handle *
+* any errors that are detected.                                          *
+*************************************************************************/
+
+re = pcre2_compile(
+  pattern,               /* the pattern */
+  PCRE2_ZERO_TERMINATED, /* indicates pattern is zero-terminated */
+  0,                     /* default options */
+  &errornumber,          /* for error number */
+  &erroroffset,          /* for error offset */
+  NULL);                 /* use default compile context */
+
+/* Compilation failed: print the error message and exit. */
+
+if (re == NULL)
+  {
+  PCRE2_UCHAR buffer[256];
+  pcre2_get_error_message(errornumber, buffer, sizeof(buffer));
+  printf("PCRE2 compilation failed at offset %d: %s\n", (int)erroroffset,
+    buffer);
+  return 1;
+  }
+
+
+/*************************************************************************
+* If the compilation succeeded, we call PCRE again, in order to do a     *
+* pattern match against the subject string. This does just ONE match. If *
+* further matching is needed, it will be done below. Before running the  *
+* match we must set up a match_data block for holding the result.        *
+*************************************************************************/
+
+/* Using this function ensures that the block is exactly the right size for
+the number of capturing parentheses in the pattern. */
+
+match_data = pcre2_match_data_create_from_pattern(re, NULL);
+
+rc = pcre2_match(
+  re,                   /* the compiled pattern */
+  subject,              /* the subject string */
+  subject_length,       /* the length of the subject */
+  0,                    /* start at offset 0 in the subject */
+  0,                    /* default options */
+  match_data,           /* block for storing the result */
+  NULL);                /* use default match context */
+
+/* Matching failed: handle error cases */
+
+if (rc < 0)
+  {
+  switch(rc)
+    {
+    case PCRE2_ERROR_NOMATCH: printf("No match\n"); break;
+    /*
+    Handle other special cases if you like
+    */
+    default: printf("Matching error %d\n", rc); break;
+    }
+  pcre2_match_data_free(match_data);   /* Release memory used for the match */
+  pcre2_code_free(re);                 /* data and the compiled pattern. */
+  return 1;
+  }
+
+/* Match succeded. Get a pointer to the output vector, where string offsets are
+stored. */
+
+ovector = pcre2_get_ovector_pointer(match_data);
+printf("\nMatch succeeded at offset %d\n", (int)ovector[0]);
+
+
+/*************************************************************************
+* We have found the first match within the subject string. If the output *
+* vector wasn't big enough, say so. Then output any substrings that were *
+* captured.                                                              *
+*************************************************************************/
+
+/* The output vector wasn't big enough. This should not happen, because we used
+pcre2_match_data_create_from_pattern() above. */
+
+if (rc == 0)
+  printf("ovector was not big enough for all the captured substrings\n");
+
+/* Show substrings stored in the output vector by number. Obviously, in a real
+application you might want to do things other than print them. */
+
+for (i = 0; i < rc; i++)
+  {
+  PCRE2_SPTR substring_start = subject + ovector[2*i];
+  size_t substring_length = ovector[2*i+1] - ovector[2*i];
+  printf("%2d: %.*s\n", i, (int)substring_length, (char *)substring_start);
+  }
+
+
+/**************************************************************************
+* That concludes the basic part of this demonstration program. We have    *
+* compiled a pattern, and performed a single match. The code that follows *
+* shows first how to access named substrings, and then how to code for    *
+* repeated matches on the same subject.                                   *
+**************************************************************************/
+
+/* See if there are any named substrings, and if so, show them by name. First
+we have to extract the count of named parentheses from the pattern. */
+
+(void)pcre2_pattern_info(
+  re,                   /* the compiled pattern */
+  PCRE2_INFO_NAMECOUNT, /* get the number of named substrings */
+  &namecount);          /* where to put the answer */
+
+if (namecount <= 0) printf("No named substrings\n"); else
+  {
+  PCRE2_SPTR tabptr;
+  printf("Named substrings\n");
+
+  /* Before we can access the substrings, we must extract the table for
+  translating names to numbers, and the size of each entry in the table. */
+
+  (void)pcre2_pattern_info(
+    re,                       /* the compiled pattern */
+    PCRE2_INFO_NAMETABLE,     /* address of the table */
+    &name_table);             /* where to put the answer */
+
+  (void)pcre2_pattern_info(
+    re,                       /* the compiled pattern */
+    PCRE2_INFO_NAMEENTRYSIZE, /* size of each entry in the table */
+    &name_entry_size);        /* where to put the answer */
+
+  /* Now we can scan the table and, for each entry, print the number, the name,
+  and the substring itself. In the 8-bit library the number is held in two
+  bytes, most significant first. */
+
+  tabptr = name_table;
+  for (i = 0; i < namecount; i++)
+    {
+    int n = (tabptr[0] << 8) | tabptr[1];
+    printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2,
+      (int)(ovector[2*n+1] - ovector[2*n]), subject + ovector[2*n]);
+    tabptr += name_entry_size;
+    }
+  }
+
+
+/*************************************************************************
+* If the "-g" option was given on the command line, we want to continue  *
+* to search for additional matches in the subject string, in a similar   *
+* way to the /g option in Perl. This turns out to be trickier than you   *
+* might think because of the possibility of matching an empty string.    *
+* What happens is as follows:                                            *
+*                                                                        *
+* If the previous match was NOT for an empty string, we can just start   *
+* the next match at the end of the previous one.                         *
+*                                                                        *
+* If the previous match WAS for an empty string, we can't do that, as it *
+* would lead to an infinite loop. Instead, a call of pcre2_match() is    *
+* made with the PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED flags set. The *
+* first of these tells PCRE2 that an empty string at the start of the    *
+* subject is not a valid match; other possibilities must be tried. The   *
+* second flag restricts PCRE2 to one match attempt at the initial string *
+* position. If this match succeeds, an alternative to the empty string   *
+* match has been found, and we can print it and proceed round the loop,  *
+* advancing by the length of whatever was found. If this match does not  *
+* succeed, we still stay in the loop, advancing by just one character.   *
+* In UTF-8 mode, which can be set by (*UTF) in the pattern, this may be  *
+* more than one byte.                                                    *
+*                                                                        *
+* However, there is a complication concerned with newlines. When the     *
+* newline convention is such that CRLF is a valid newline, we must       *
+* advance by two characters rather than one. The newline convention can  *
+* be set in the regex by (*CR), etc.; if not, we must find the default.  *
+*************************************************************************/
+
+if (!find_all)     /* Check for -g */
+  {
+  pcre2_match_data_free(match_data);  /* Release the memory that was used */
+  pcre2_code_free(re);                /* for the match data and the pattern. */
+  return 0;                           /* Exit the program. */
+  }
+
+/* Before running the loop, check for UTF-8 and whether CRLF is a valid newline
+sequence. First, find the options with which the regex was compiled and extract
+the UTF state. */
+
+(void)pcre2_pattern_info(re, PCRE2_INFO_ALLOPTIONS, &option_bits);
+utf8 = (option_bits & PCRE2_UTF) != 0;
+
+/* Now find the newline convention and see whether CRLF is a valid newline
+sequence. */
+
+(void)pcre2_pattern_info(re, PCRE2_INFO_NEWLINE, &newline);
+crlf_is_newline = newline == PCRE2_NEWLINE_ANY ||
+                  newline == PCRE2_NEWLINE_CRLF ||
+                  newline == PCRE2_NEWLINE_ANYCRLF;
+
+/* Loop for second and subsequent matches */
+
+for (;;)
+  {
+  uint32_t options = 0;                    /* Normally no options */
+  PCRE2_SIZE start_offset = ovector[1];  /* Start at end of previous match */
+
+  /* If the previous match was for an empty string, we are finished if we are
+  at the end of the subject. Otherwise, arrange to run another match at the
+  same point to see if a non-empty match can be found. */
+
+  if (ovector[0] == ovector[1])
+    {
+    if (ovector[0] == subject_length) break;
+    options = PCRE2_NOTEMPTY_ATSTART | PCRE2_ANCHORED;
+    }
+
+  /* Run the next matching operation */
+
+  rc = pcre2_match(
+    re,                   /* the compiled pattern */
+    subject,              /* the subject string */
+    subject_length,       /* the length of the subject */
+    start_offset,         /* starting offset in the subject */
+    options,              /* options */
+    match_data,           /* block for storing the result */
+    NULL);                /* use default match context */
+
+  /* This time, a result of NOMATCH isn't an error. If the value in "options"
+  is zero, it just means we have found all possible matches, so the loop ends.
+  Otherwise, it means we have failed to find a non-empty-string match at a
+  point where there was a previous empty-string match. In this case, we do what
+  Perl does: advance the matching position by one character, and continue. We
+  do this by setting the "end of previous match" offset, because that is picked
+  up at the top of the loop as the point at which to start again.
+
+  There are two complications: (a) When CRLF is a valid newline sequence, and
+  the current position is just before it, advance by an extra byte. (b)
+  Otherwise we must ensure that we skip an entire UTF character if we are in
+  UTF mode. */
+
+  if (rc == PCRE2_ERROR_NOMATCH)
+    {
+    if (options == 0) break;                    /* All matches found */
+    ovector[1] = start_offset + 1;              /* Advance one code unit */
+    if (crlf_is_newline &&                      /* If CRLF is newline & */
+        start_offset < subject_length - 1 &&    /* we are at CRLF, */
+        subject[start_offset] == '\r' &&
+        subject[start_offset + 1] == '\n')
+      ovector[1] += 1;                          /* Advance by one more. */
+    else if (utf8)                              /* Otherwise, ensure we */
+      {                                         /* advance a whole UTF-8 */
+      while (ovector[1] < subject_length)       /* character. */
+        {
+        if ((subject[ovector[1]] & 0xc0) != 0x80) break;
+        ovector[1] += 1;
+        }
+      }
+    continue;    /* Go round the loop again */
+    }
+
+  /* Other matching errors are not recoverable. */
+
+  if (rc < 0)
+    {
+    printf("Matching error %d\n", rc);
+    pcre2_match_data_free(match_data);
+    pcre2_code_free(re);
+    return 1;
+    }
+
+  /* Match succeded */
+
+  printf("\nMatch succeeded again at offset %d\n", (int)ovector[0]);
+
+  /* The match succeeded, but the output vector wasn't big enough. This
+  should not happen. */
+
+  if (rc == 0)
+    printf("ovector was not big enough for all the captured substrings\n");
+
+  /* As before, show substrings stored in the output vector by number, and then
+  also any named substrings. */
+
+  for (i = 0; i < rc; i++)
+    {
+    PCRE2_SPTR substring_start = subject + ovector[2*i];
+    size_t substring_length = ovector[2*i+1] - ovector[2*i];
+    printf("%2d: %.*s\n", i, (int)substring_length, (char *)substring_start);
+    }
+
+  if (namecount <= 0) printf("No named substrings\n"); else
+    {
+    PCRE2_SPTR tabptr = name_table;
+    printf("Named substrings\n");
+    for (i = 0; i < namecount; i++)
+      {
+      int n = (tabptr[0] << 8) | tabptr[1];
+      printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2,
+        (int)(ovector[2*n+1] - ovector[2*n]), subject + ovector[2*n]);
+      tabptr += name_entry_size;
+      }
+    }
+  }      /* End of loop to find second and subsequent matches */
+
+printf("\n");
+pcre2_match_data_free(match_data);
+pcre2_code_free(re);
+return 0;
+}
+
+/* End of pcre2demo.c */
+

+Return to the PCRE2 index page.
+

diff --git a/pcre2-10.20/doc/html/pcre2grep.html b/pcre2-10.20/doc/html/pcre2grep.html
new file mode 100644
index 000000000..dcfb96f34
--- /dev/null
+++ b/pcre2-10.20/doc/html/pcre2grep.html
@@ -0,0 +1,783 @@
+
+
+pcre2grep specification
+
+
+
pcre2grep man page

+

+Return to the PCRE2 index page.
+

+

+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+

+

+
SYNOPSIS

+

+pcre2grep [options] [long options] [pattern] [path1 path2 ...]
+

+
DESCRIPTION

+

+pcre2grep searches files for character patterns, in the same way as other
+grep commands do, but it uses the PCRE2 regular expression library to support
+patterns that are compatible with the regular expressions of Perl 5. See
+pcre2syntax(3)
+for a quick-reference summary of pattern syntax, or
+pcre2pattern(3)
+for a full description of the syntax and semantics of the regular expressions
+that PCRE2 supports.
+

+

+Patterns, whether supplied on the command line or in a separate file, are given
+without delimiters. For example:
+
+  pcre2grep Thursday /etc/motd
+

+If you attempt to use delimiters (for example, by surrounding a pattern with
+slashes, as is common in Perl scripts), they are interpreted as part of the
+pattern. Quotes can of course be used to delimit patterns on the command line
+because they are interpreted by the shell, and indeed quotes are required if a
+pattern contains white space or shell metacharacters.
+

+

+The first argument that follows any option settings is treated as the single
+pattern to be matched when neither -e nor -f is present.
+Conversely, when one or both of these options are used to specify patterns, all
+arguments are treated as path names. At least one of -e, -f, or an
+argument pattern must be provided.
+

+

+If no files are specified, pcre2grep reads the standard input. The
+standard input can also be referenced by a name consisting of a single hyphen.
+For example:
+
+  pcre2grep some-pattern file1 - file3
+

+Input files are searched line by line. By default, each line that matches a
+pattern is copied to the standard output, and if there is more than one file,
+the file name is output at the start of each line, followed by a colon.
+However, there are options that can change how pcre2grep behaves. In
+particular, the -M option makes it possible to search for strings that
+span line boundaries. What defines a line boundary is controlled by the
+-N (--newline) option.
+

+

+The amount of memory used for buffering files that are being scanned is
+controlled by a parameter that can be set by the --buffer-size option.
+The default value for this parameter is specified when pcre2grep is
+built, with the default default being 20K. A block of memory three times this
+size is used (to allow for buffering "before" and "after" lines). An error
+occurs if a line overflows the buffer.
+

+

+Patterns can be no longer than 8K or BUFSIZ bytes, whichever is the greater.
+BUFSIZ is defined in <stdio.h>. When there is more than one pattern
+(specified by the use of -e and/or -f), each pattern is applied to
+each line in the order in which they are defined, except that all the -e
+patterns are tried before the -f patterns.
+

+

+By default, as soon as one pattern matches a line, no further patterns are
+considered. However, if --colour (or --color) is used to colour the
+matching substrings, or if --only-matching, --file-offsets, or
+--line-offsets is used to output only the part of the line that matched
+(either shown literally, or as an offset), scanning resumes immediately
+following the match, so that further matches on the same line can be found. If
+there are multiple patterns, they are all tried on the remainder of the line,
+but patterns that follow the one that matched are not tried on the earlier part
+of the line.
+

+

+This behaviour means that the order in which multiple patterns are specified
+can affect the output when one of the above options is used. This is no longer
+the same behaviour as GNU grep, which now manages to display earlier matches
+for later patterns (as long as there is no overlap).
+

+

+Patterns that can match an empty string are accepted, but empty string
+matches are never recognized. An example is the pattern "(super)?(man)?", in
+which all components are optional. This pattern finds all occurrences of both
+"super" and "man"; the output differs from matching with "super|man" when only
+the matching substrings are being shown.
+

+

+If the LC_ALL or LC_CTYPE environment variable is set,
+pcre2grep uses the value to set a locale when calling the PCRE2 library.
+The --locale option can be used to override this.
+

+
SUPPORT FOR COMPRESSED FILES

+

+It is possible to compile pcre2grep so that it uses libz or
+libbz2 to read files whose names end in .gz or .bz2,
+respectively. You can find out whether your binary has support for one or both
+of these file types by running it with the --help option. If the
+appropriate support is not present, files are treated as plain text. The
+standard input is always so treated.
+

+
BINARY FILES

+

+By default, a file that contains a binary zero byte within the first 1024 bytes
+is identified as a binary file, and is processed specially. (GNU grep also
+identifies binary files in this manner.) See the --binary-files option
+for a means of changing the way binary files are handled.
+

+
OPTIONS

+

+The order in which some of the options appear can affect the output. For
+example, both the -h and -l options affect the printing of file
+names. Whichever comes later in the command line will be the one that takes
+effect. Similarly, except where noted below, if an option is given twice, the
+later setting is used. Numerical values for options may be followed by K or M,
+to signify multiplication by 1024 or 1024*1024 respectively.
+

+

+--
+This terminates the list of options. It is useful if the next item on the
+command line starts with a hyphen but is not an option. This allows for the
+processing of patterns and file names that start with hyphens.
+

+

+-A number, --after-context=number
+Output number lines of context after each matching line. If file names
+and/or line numbers are being output, a hyphen separator is used instead of a
+colon for the context lines. A line containing "--" is output between each
+group of lines, unless they are in fact contiguous in the input file. The value
+of number is expected to be relatively small. However, pcre2grep
+guarantees to have up to 8K of following text available for context output.
+

+

+-a, --text
+Treat binary files as text. This is equivalent to
+--binary-files=text.
+

+

+-B number, --before-context=number
+Output number lines of context before each matching line. If file names
+and/or line numbers are being output, a hyphen separator is used instead of a
+colon for the context lines. A line containing "--" is output between each
+group of lines, unless they are in fact contiguous in the input file. The value
+of number is expected to be relatively small. However, pcre2grep
+guarantees to have up to 8K of preceding text available for context output.
+

+

+--binary-files=word
+Specify how binary files are to be processed. If the word is "binary" (the
+default), pattern matching is performed on binary files, but the only output is
+"Binary file <name> matches" when a match succeeds. If the word is "text",
+which is equivalent to the -a or --text option, binary files are
+processed in the same way as any other file. In this case, when a match
+succeeds, the output may be binary garbage, which can have nasty effects if
+sent to a terminal. If the word is "without-match", which is equivalent to the
+-I option, binary files are not processed at all; they are assumed not to
+be of interest and are skipped without causing any output or affecting the
+return code.
+

+

+--buffer-size=number
+Set the parameter that controls how much memory is used for buffering files
+that are being scanned.
+

+

+-C number, --context=number
+Output number lines of context both before and after each matching line.
+This is equivalent to setting both -A and -B to the same value.
+

+

+-c, --count
+Do not output lines from the files that are being scanned; instead output the
+number of matches (or non-matches if -v is used) that would otherwise
+have caused lines to be shown. By default, this count is the same as the number
+of suppressed lines, but if the -M (multiline) option is used (without
+-v), there may be more suppressed lines than the number of matches.
+

+

+If no lines are selected, the number zero is output. If several files are are
+being scanned, a count is output for each of them. However, if the
+--files-with-matches option is also used, only those files whose counts
+are greater than zero are listed. When -c is used, the -A,
+-B, and -C options are ignored.
+

+

+--colour, --color
+If this option is given without any data, it is equivalent to "--colour=auto".
+If data is required, it must be given in the same shell item, separated by an
+equals sign.
+

+

+--colour=value, --color=value
+This option specifies under what circumstances the parts of a line that matched
+a pattern should be coloured in the output. By default, the output is not
+coloured. The value (which is optional, see above) may be "never", "always", or
+"auto". In the latter case, colouring happens only if the standard output is
+connected to a terminal. More resources are used when colouring is enabled,
+because pcre2grep has to search for all possible matches in a line, not
+just one, in order to colour them all.
+

+

+The colour that is used can be specified by setting the environment variable
+PCRE2GREP_COLOUR or PCRE2GREP_COLOR. The value of this variable should be a
+string of two numbers, separated by a semicolon. They are copied directly into
+the control string for setting colour on a terminal, so it is your
+responsibility to ensure that they make sense. If neither of the environment
+variables is set, the default is "1;31", which gives red.
+

+

+-D action, --devices=action
+If an input path is not a regular file or a directory, "action" specifies how
+it is to be processed. Valid values are "read" (the default) or "skip"
+(silently skip the path).
+

+

+-d action, --directories=action
+If an input path is a directory, "action" specifies how it is to be processed.
+Valid values are "read" (the default in non-Windows environments, for
+compatibility with GNU grep), "recurse" (equivalent to the -r option), or
+"skip" (silently skip the path, the default in Windows environments). In the
+"read" case, directories are read as if they were ordinary files. In some
+operating systems the effect of reading a directory like this is an immediate
+end-of-file; in others it may provoke an error.
+

+

+-e pattern, --regex=pattern, --regexp=pattern
+Specify a pattern to be matched. This option can be used multiple times in
+order to specify several patterns. It can also be used as a way of specifying a
+single pattern that starts with a hyphen. When -e is used, no argument
+pattern is taken from the command line; all arguments are treated as file
+names. There is no limit to the number of patterns. They are applied to each
+line in the order in which they are defined until one matches.
+

+

+If -f is used with -e, the command line patterns are matched first,
+followed by the patterns from the file(s), independent of the order in which
+these options are specified. Note that multiple use of -e is not the same
+as a single pattern with alternatives. For example, X|Y finds the first
+character in a line that is X or Y, whereas if the two patterns are given
+separately, with X first, pcre2grep finds X if it is present, even if it
+follows Y in the line. It finds Y only if there is no X in the line. This
+matters only if you are using -o or --colo(u)r to show the part(s)
+of the line that matched.
+

+

+--exclude=pattern
+Files (but not directories) whose names match the pattern are skipped without
+being processed. This applies to all files, whether listed on the command line,
+obtained from --file-list, or by scanning a directory. The pattern is a
+PCRE2 regular expression, and is matched against the final component of the
+file name, not the entire path. The -F, -w, and -x options do
+not apply to this pattern. The option may be given any number of times in order
+to specify multiple patterns. If a file name matches both an --include
+and an --exclude pattern, it is excluded. There is no short form for this
+option.
+

+

+--exclude-from=filename
+Treat each non-empty line of the file as the data for an --exclude
+option. What constitutes a newline when reading the file is the operating
+system's default. The --newline option has no effect on this option. This
+option may be given more than once in order to specify a number of files to
+read.
+

+

+--exclude-dir=pattern
+Directories whose names match the pattern are skipped without being processed,
+whatever the setting of the --recursive option. This applies to all
+directories, whether listed on the command line, obtained from
+--file-list, or by scanning a parent directory. The pattern is a PCRE2
+regular expression, and is matched against the final component of the directory
+name, not the entire path. The -F, -w, and -x options do not
+apply to this pattern. The option may be given any number of times in order to
+specify more than one pattern. If a directory matches both --include-dir
+and --exclude-dir, it is excluded. There is no short form for this
+option.
+

+

+-F, --fixed-strings
+Interpret each data-matching pattern as a list of fixed strings, separated by
+newlines, instead of as a regular expression. What constitutes a newline for
+this purpose is controlled by the --newline option. The -w (match
+as a word) and -x (match whole line) options can be used with -F.
+They apply to each of the fixed strings. A line is selected if any of the fixed
+strings are found in it (subject to -w or -x, if present). This
+option applies only to the patterns that are matched against the contents of
+files; it does not apply to patterns specified by any of the --include or
+--exclude options.
+

+

+-f filename, --file=filename
+Read patterns from the file, one per line, and match them against
+each line of input. What constitutes a newline when reading the file is the
+operating system's default. The --newline option has no effect on this
+option. Trailing white space is removed from each line, and blank lines are
+ignored. An empty file contains no patterns and therefore matches nothing. See
+also the comments about multiple patterns versus a single pattern with
+alternatives in the description of -e above.
+

+

+If this option is given more than once, all the specified files are
+read. A data line is output if any of the patterns match it. A file name can
+be given as "-" to refer to the standard input. When -f is used, patterns
+specified on the command line using -e may also be present; they are
+tested before the file's patterns. However, no other pattern is taken from the
+command line; all arguments are treated as the names of paths to be searched.
+

+

+--file-list=filename
+Read a list of files and/or directories that are to be scanned from the given
+file, one per line. Trailing white space is removed from each line, and blank
+lines are ignored. These paths are processed before any that are listed on the
+command line. The file name can be given as "-" to refer to the standard input.
+If --file and --file-list are both specified as "-", patterns are
+read first. This is useful only when the standard input is a terminal, from
+which further lines (the list of files) can be read after an end-of-file
+indication. If this option is given more than once, all the specified files are
+read.
+

+

+--file-offsets
+Instead of showing lines or parts of lines that match, show each match as an
+offset from the start of the file and a length, separated by a comma. In this
+mode, no context is shown. That is, the -A, -B, and -C
+options are ignored. If there is more than one match in a line, each of them is
+shown separately. This option is mutually exclusive with --line-offsets
+and --only-matching.
+

+

+-H, --with-filename
+Force the inclusion of the file name at the start of output lines when
+searching a single file. By default, the file name is not shown in this case.
+For matching lines, the file name is followed by a colon; for context lines, a
+hyphen separator is used. If a line number is also being output, it follows the
+file name. When the -M option causes a pattern to match more than one
+line, only the first is preceded by the file name.
+

+

+-h, --no-filename
+Suppress the output file names when searching multiple files. By default,
+file names are shown when multiple files are searched. For matching lines, the
+file name is followed by a colon; for context lines, a hyphen separator is used.
+If a line number is also being output, it follows the file name.
+

+

+--help
+Output a help message, giving brief details of the command options and file
+type support, and then exit. Anything else on the command line is
+ignored.
+

+

+-I
+Ignore binary files. This is equivalent to
+--binary-files=without-match.
+

+

+-i, --ignore-case
+Ignore upper/lower case distinctions during comparisons.
+

+

+--include=pattern
+If any --include patterns are specified, the only files that are
+processed are those that match one of the patterns (and do not match an
+--exclude pattern). This option does not affect directories, but it
+applies to all files, whether listed on the command line, obtained from
+--file-list, or by scanning a directory. The pattern is a PCRE2 regular
+expression, and is matched against the final component of the file name, not
+the entire path. The -F, -w, and -x options do not apply to
+this pattern. The option may be given any number of times. If a file name
+matches both an --include and an --exclude pattern, it is excluded.
+There is no short form for this option.
+

+

+--include-from=filename
+Treat each non-empty line of the file as the data for an --include
+option. What constitutes a newline for this purpose is the operating system's
+default. The --newline option has no effect on this option. This option
+may be given any number of times; all the files are read.
+

+

+--include-dir=pattern
+If any --include-dir patterns are specified, the only directories that
+are processed are those that match one of the patterns (and do not match an
+--exclude-dir pattern). This applies to all directories, whether listed
+on the command line, obtained from --file-list, or by scanning a parent
+directory. The pattern is a PCRE2 regular expression, and is matched against
+the final component of the directory name, not the entire path. The -F,
+-w, and -x options do not apply to this pattern. The option may be
+given any number of times. If a directory matches both --include-dir and
+--exclude-dir, it is excluded. There is no short form for this option.
+

+

+-L, --files-without-match
+Instead of outputting lines from the files, just output the names of the files
+that do not contain any lines that would have been output. Each file name is
+output once, on a separate line.
+

+

+-l, --files-with-matches
+Instead of outputting lines from the files, just output the names of the files
+containing lines that would have been output. Each file name is output
+once, on a separate line. Searching normally stops as soon as a matching line
+is found in a file. However, if the -c (count) option is also used,
+matching continues in order to obtain the correct count, and those files that
+have at least one match are listed along with their counts. Using this option
+with -c is a way of suppressing the listing of files with no matches.
+

+

+--label=name
+This option supplies a name to be used for the standard input when file names
+are being output. If not supplied, "(standard input)" is used. There is no
+short form for this option.
+

+

+--line-buffered
+When this option is given, input is read and processed line by line, and the
+output is flushed after each write. By default, input is read in large chunks,
+unless pcre2grep can determine that it is reading from a terminal (which
+is currently possible only in Unix-like environments). Output to terminal is
+normally automatically flushed by the operating system. This option can be
+useful when the input or output is attached to a pipe and you do not want
+pcre2grep to buffer up large amounts of data. However, its use will
+affect performance, and the -M (multiline) option ceases to work.
+

+

+--line-offsets
+Instead of showing lines or parts of lines that match, show each match as a
+line number, the offset from the start of the line, and a length. The line
+number is terminated by a colon (as usual; see the -n option), and the
+offset and length are separated by a comma. In this mode, no context is shown.
+That is, the -A, -B, and -C options are ignored. If there is
+more than one match in a line, each of them is shown separately. This option is
+mutually exclusive with --file-offsets and --only-matching.
+

+

+--locale=locale-name
+This option specifies a locale to be used for pattern matching. It overrides
+the value in the LC_ALL or LC_CTYPE environment variables. If no
+locale is specified, the PCRE2 library's default (usually the "C" locale) is
+used. There is no short form for this option.
+

+

+--match-limit=number
+Processing some regular expression patterns can require a very large amount of
+memory, leading in some cases to a program crash if not enough is available.
+Other patterns may take a very long time to search for all possible matching
+strings. The pcre2_match() function that is called by pcre2grep to
+do the matching has two parameters that can limit the resources that it uses.
+

+

+The --match-limit option provides a means of limiting resource usage
+when processing patterns that are not going to match, but which have a very
+large number of possibilities in their search trees. The classic example is a
+pattern that uses nested unlimited repeats. Internally, PCRE2 uses a function
+called match() which it calls repeatedly (sometimes recursively). The
+limit set by --match-limit is imposed on the number of times this
+function is called during a match, which has the effect of limiting the amount
+of backtracking that can take place.
+

+

+The --recursion-limit option is similar to --match-limit, but
+instead of limiting the total number of times that match() is called, it
+limits the depth of recursive calls, which in turn limits the amount of memory
+that can be used. The recursion depth is a smaller number than the total number
+of calls, because not all calls to match() are recursive. This limit is
+of use only if it is set smaller than --match-limit.
+

+

+There are no short forms for these options. The default settings are specified
+when the PCRE2 library is compiled, with the default default being 10 million.
+

+

+-M, --multiline
+Allow patterns to match more than one line. When this option is given, patterns
+may usefully contain literal newline characters and internal occurrences of ^
+and $ characters. The output for a successful match may consist of more than
+one line. The first is the line in which the match started, and the last is the
+line in which the match ended. If the matched string ends with a newline
+sequence the output ends at the end of that line.
+

+

+When this option is set, the PCRE2 library is called in "multiline" mode.
+However, pcre2grep still processes the input line by line. The difference
+is that a matched string may extend past the end of a line and continue on
+one or more subsequent lines. The newline sequence must be matched as part of
+the pattern. For example, to find the phrase "regular expression" in a file
+where "regular" might be at the end of a line and "expression" at the start of
+the next line, you could use this command:
+
+  pcre2grep -M 'regular\s+expression' <file>
+

+The \s escape sequence matches any white space character, including newlines,
+and is followed by + so as to match trailing white space on the first line as
+well as possibly handling a two-character newline sequence.
+

+

+There is a limit to the number of lines that can be matched, imposed by the way
+that pcre2grep buffers the input file as it scans it. However,
+pcre2grep ensures that at least 8K characters or the rest of the file
+(whichever is the shorter) are available for forward matching, and similarly
+the previous 8K characters (or all the previous characters, if fewer than 8K)
+are guaranteed to be available for lookbehind assertions. The -M option
+does not work when input is read line by line (see \fP--line-buffered\fP.)
+

+

+-N newline-type, --newline=newline-type
+The PCRE2 library supports five different conventions for indicating
+the ends of lines. They are the single-character sequences CR (carriage return)
+and LF (linefeed), the two-character sequence CRLF, an "anycrlf" convention,
+which recognizes any of the preceding three types, and an "any" convention, in
+which any Unicode line ending sequence is assumed to end a line. The Unicode
+sequences are the three just mentioned, plus VT (vertical tab, U+000B), FF
+(form feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and
+PS (paragraph separator, U+2029).
+

+

+When the PCRE2 library is built, a default line-ending sequence is specified.
+This is normally the standard sequence for the operating system. Unless
+otherwise specified by this option, pcre2grep uses the library's default.
+The possible values for this option are CR, LF, CRLF, ANYCRLF, or ANY. This
+makes it possible to use pcre2grep to scan files that have come from
+other environments without having to modify their line endings. If the data
+that is being scanned does not agree with the convention set by this option,
+pcre2grep may behave in strange ways. Note that this option does not
+apply to files specified by the -f, --exclude-from, or
+--include-from options, which are expected to use the operating system's
+standard newline sequence.
+

+

+-n, --line-number
+Precede each output line by its line number in the file, followed by a colon
+for matching lines or a hyphen for context lines. If the file name is also
+being output, it precedes the line number. When the -M option causes a
+pattern to match more than one line, only the first is preceded by its line
+number. This option is forced if --line-offsets is used.
+

+

+--no-jit
+If the PCRE2 library is built with support for just-in-time compiling (which
+speeds up matching), pcre2grep automatically makes use of this, unless it
+was explicitly disabled at build time. This option can be used to disable the
+use of JIT at run time. It is provided for testing and working round problems.
+It should never be needed in normal use.
+

+

+-o, --only-matching
+Show only the part of the line that matched a pattern instead of the whole
+line. In this mode, no context is shown. That is, the -A, -B, and
+-C options are ignored. If there is more than one match in a line, each
+of them is shown separately. If -o is combined with -v (invert the
+sense of the match to find non-matching lines), no output is generated, but the
+return code is set appropriately. If the matched portion of the line is empty,
+nothing is output unless the file name or line number are being printed, in
+which case they are shown on an otherwise empty line. This option is mutually
+exclusive with --file-offsets and --line-offsets.
+

+

+-onumber, --only-matching=number
+Show only the part of the line that matched the capturing parentheses of the
+given number. Up to 32 capturing parentheses are supported, and -o0 is
+equivalent to -o without a number. Because these options can be given
+without an argument (see above), if an argument is present, it must be given in
+the same shell item, for example, -o3 or --only-matching=2. The comments given
+for the non-argument case above also apply to this case. If the specified
+capturing parentheses do not exist in the pattern, or were not set in the
+match, nothing is output unless the file name or line number are being output.
+

+

+If this option is given multiple times, multiple substrings are output, in the
+order the options are given. For example, -o3 -o1 -o3 causes the substrings
+matched by capturing parentheses 3 and 1 and then 3 again to be output. By
+default, there is no separator (but see the next option).
+

+

+--om-separator=text
+Specify a separating string for multiple occurrences of -o. The default
+is an empty string. Separating strings are never coloured.
+

+

+-q, --quiet
+Work quietly, that is, display nothing except error messages. The exit
+status indicates whether or not any matches were found.
+

+

+-r, --recursive
+If any given path is a directory, recursively scan the files it contains,
+taking note of any --include and --exclude settings. By default, a
+directory is read as a normal file; in some operating systems this gives an
+immediate end-of-file. This option is a shorthand for setting the -d
+option to "recurse".
+

+

+--recursion-limit=number
+See --match-limit above.
+

+

+-s, --no-messages
+Suppress error messages about non-existent or unreadable files. Such files are
+quietly skipped. However, the return code is still 2, even if matches were
+found in other files.
+

+

+-u, --utf-8
+Operate in UTF-8 mode. This option is available only if PCRE2 has been compiled
+with UTF-8 support. All patterns (including those for any --exclude and
+--include options) and all subject lines that are scanned must be valid
+strings of UTF-8 characters.
+

+

+-V, --version
+Write the version numbers of pcre2grep and the PCRE2 library to the
+standard output and then exit. Anything else on the command line is
+ignored.
+

+

+-v, --invert-match
+Invert the sense of the match, so that lines which do not match any of
+the patterns are the ones that are found.
+

+

+-w, --word-regex, --word-regexp
+Force the patterns to match only whole words. This is equivalent to having \b
+at the start and end of the pattern. This option applies only to the patterns
+that are matched against the contents of files; it does not apply to patterns
+specified by any of the --include or --exclude options.
+

+

+-x, --line-regex, --line-regexp
+Force the patterns to be anchored (each must start matching at the beginning of
+a line) and in addition, require them to match entire lines. This is equivalent
+to having ^ and $ characters at the start and end of each alternative top-level
+branch in every pattern. This option applies only to the patterns that are
+matched against the contents of files; it does not apply to patterns specified
+by any of the --include or --exclude options.
+

+
ENVIRONMENT VARIABLES

+

+The environment variables LC_ALL and LC_CTYPE are examined, in that
+order, for a locale. The first one that is set is used. This can be overridden
+by the --locale option. If no locale is set, the PCRE2 library's default
+(usually the "C" locale) is used.
+

+
NEWLINES

+

+The -N (--newline) option allows pcre2grep to scan files with
+different newline conventions from the default. Any parts of the input files
+that are written to the standard output are copied identically, with whatever
+newline sequences they have in the input. However, the setting of this option
+does not affect the interpretation of files specified by the -f,
+--exclude-from, or --include-from options, which are assumed to use
+the operating system's standard newline sequence, nor does it affect the way in
+which pcre2grep writes informational messages to the standard error and
+output streams. For these it uses the string "\n" to indicate newlines,
+relying on the C I/O library to convert this to an appropriate sequence.
+

+
OPTIONS COMPATIBILITY

+

+Many of the short and long forms of pcre2grep's options are the same
+as in the GNU grep program. Any long option of the form
+--xxx-regexp (GNU terminology) is also available as --xxx-regex
+(PCRE2 terminology). However, the --file-list, --file-offsets,
+--include-dir, --line-offsets, --locale, --match-limit,
+-M, --multiline, -N, --newline, --om-separator,
+--recursion-limit, -u, and --utf-8 options are specific to
+pcre2grep, as is the use of the --only-matching option with a
+capturing parentheses number.
+

+

+Although most of the common options work the same way, a few are different in
+pcre2grep. For example, the --include option's argument is a glob
+for GNU grep, but a regular expression for pcre2grep. If both the
+-c and -l options are given, GNU grep lists only file names,
+without counts, but pcre2grep gives the counts as well.
+

+
OPTIONS WITH DATA

+

+There are four different ways in which an option with data can be specified.
+If a short form option is used, the data may follow immediately, or (with one
+exception) in the next command line item. For example:
+
+  -f/some/file
+  -f /some/file
+

+The exception is the -o option, which may appear with or without data.
+Because of this, if data is present, it must follow immediately in the same
+item, for example -o3.
+

+

+If a long form option is used, the data may appear in the same command line
+item, separated by an equals character, or (with two exceptions) it may appear
+in the next command line item. For example:
+
+  --file=/some/file
+  --file /some/file
+

+Note, however, that if you want to supply a file name beginning with ~ as data
+in a shell command, and have the shell expand ~ to a home directory, you must
+separate the file name from the option, because the shell does not treat ~
+specially unless it is at the start of an item.
+

+

+The exceptions to the above are the --colour (or --color) and
+--only-matching options, for which the data is optional. If one of these
+options does have data, it must be given in the first form, using an equals
+character. Otherwise pcre2grep will assume that it has no data.
+

+
MATCHING ERRORS

+

+It is possible to supply a regular expression that takes a very long time to
+fail to match certain lines. Such patterns normally involve nested indefinite
+repeats, for example: (a+)*\d when matched against a line of a's with no final
+digit. The PCRE2 matching function has a resource limit that causes it to abort
+in these circumstances. If this happens, pcre2grep outputs an error
+message and the line that caused the problem to the standard error stream. If
+there are more than 20 such errors, pcre2grep gives up.
+

+

+The --match-limit option of pcre2grep can be used to set the
+overall resource limit; there is a second option called --recursion-limit
+that sets a limit on the amount of memory (usually stack) that is used (see the
+discussion of these options above).
+

+
DIAGNOSTICS

+

+Exit status is 0 if any matches were found, 1 if no matches were found, and 2
+for syntax errors, overlong lines, non-existent or inaccessible files (even if
+matches were found in other files) or too many matching errors. Using the
+-s option to suppress error messages about inaccessible files does not
+affect the return code.
+

+
SEE ALSO

+

+pcre2pattern(3), pcre2syntax(3).
+

+
AUTHOR

+

+Philip Hazel
+

+University Computing Service
+

+Cambridge, England.
+

+

+
REVISION

+

+Last updated: 03 January 2015
+

+Copyright © 1997-2015 University of Cambridge.
+

+

+Return to the PCRE2 index page.
+

diff --git a/pcre2-10.20/doc/html/pcre2jit.html b/pcre2-10.20/doc/html/pcre2jit.html
new file mode 100644
index 000000000..9e3207340
--- /dev/null
+++ b/pcre2-10.20/doc/html/pcre2jit.html
@@ -0,0 +1,428 @@
+
+
+pcre2jit specification
+
+
+
pcre2jit man page

+

+Return to the PCRE2 index page.
+

+

+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+

+

+
PCRE2 JUST-IN-TIME COMPILER SUPPORT

+

+Just-in-time compiling is a heavyweight optimization that can greatly speed up
+pattern matching. However, it comes at the cost of extra processing before the
+match is performed, so it is of most benefit when the same pattern is going to
+be matched many times. This does not necessarily mean many calls of a matching
+function; if the pattern is not anchored, matching attempts may take place many
+times at various positions in the subject, even for a single call. Therefore,
+if the subject string is very long, it may still pay to use JIT even for
+one-off matches. JIT support is available for all of the 8-bit, 16-bit and
+32-bit PCRE2 libraries.
+

+

+JIT support applies only to the traditional Perl-compatible matching function.
+It does not apply when the DFA matching function is being used. The code for
+this support was written by Zoltan Herczeg.
+

+
AVAILABILITY OF JIT SUPPORT

+

+JIT support is an optional feature of PCRE2. The "configure" option
+--enable-jit (or equivalent CMake option) must be set when PCRE2 is built if
+you want to use JIT. The support is limited to the following hardware
+platforms:
+
+  ARM 32-bit (v5, v7, and Thumb2)
+  ARM 64-bit
+  Intel x86 32-bit and 64-bit
+  MIPS 32-bit and 64-bit
+  Power PC 32-bit and 64-bit
+  SPARC 32-bit
+

+If --enable-jit is set on an unsupported platform, compilation fails.
+

+

+A program can tell if JIT support is available by calling pcre2_config()
+with the PCRE2_CONFIG_JIT option. The result is 1 when JIT is available, and 0
+otherwise. However, a simple program does not need to check this in order to
+use JIT. The API is implemented in a way that falls back to the interpretive
+code if JIT is not available. For programs that need the best possible
+performance, there is also a "fast path" API that is JIT-specific.
+

+
SIMPLE USE OF JIT

+

+To make use of the JIT support in the simplest way, all you have to do is to
+call pcre2_jit_compile() after successfully compiling a pattern with
+pcre2_compile(). This function has two arguments: the first is the
+compiled pattern pointer that was returned by pcre2_compile(), and the
+second is zero or more of the following option bits: PCRE2_JIT_COMPLETE,
+PCRE2_JIT_PARTIAL_HARD, or PCRE2_JIT_PARTIAL_SOFT.
+

+

+If JIT support is not available, a call to pcre2_jit_compile() does
+nothing and returns PCRE2_ERROR_JIT_BADOPTION. Otherwise, the compiled pattern
+is passed to the JIT compiler, which turns it into machine code that executes
+much faster than the normal interpretive code, but yields exactly the same
+results. The returned value from pcre2_jit_compile() is zero on success,
+or a negative error code.
+

+

+PCRE2_JIT_COMPLETE requests the JIT compiler to generate code for complete
+matches. If you want to run partial matches using the PCRE2_PARTIAL_HARD or
+PCRE2_PARTIAL_SOFT options of pcre2_match(), you should set one or both
+of the other options as well as, or instead of PCRE2_JIT_COMPLETE. The JIT
+compiler generates different optimized code for each of the three modes
+(normal, soft partial, hard partial). When pcre2_match() is called, the
+appropriate code is run if it is available. Otherwise, the pattern is matched
+using interpretive code.
+

+

+You can call pcre2_jit_compile() multiple times for the same compiled
+pattern. It does nothing if it has previously compiled code for any of the
+option bits. For example, you can call it once with PCRE2_JIT_COMPLETE and
+(perhaps later, when you find you need partial matching) again with
+PCRE2_JIT_COMPLETE and PCRE2_JIT_PARTIAL_HARD. This time it will ignore
+PCRE2_JIT_COMPLETE and just compile code for partial matching. If
+pcre2_jit_compile() is called with no option bits set, it immediately
+returns zero. This is an alternative way of testing whether JIT is available.
+

+

+At present, it is not possible to free JIT compiled code except when the entire
+compiled pattern is freed by calling pcre2_code_free().
+

+

+In some circumstances you may need to call additional functions. These are
+described in the section entitled
+"Controlling the JIT stack"
+below.
+

+

+There are some pcre2_match() options that are not supported by JIT, and
+there are also some pattern items that JIT cannot handle. Details are given
+below. In both cases, matching automatically falls back to the interpretive
+code. If you want to know whether JIT was actually used for a particular match,
+you should arrange for a JIT callback function to be set up as described in the
+section entitled
+"Controlling the JIT stack"
+below, even if you do not need to supply a non-default JIT stack. Such a
+callback function is called whenever JIT code is about to be obeyed. If the
+match-time options are not right for JIT execution, the callback function is
+not obeyed.
+

+

+If the JIT compiler finds an unsupported item, no JIT data is generated. You
+can find out if JIT matching is available after compiling a pattern by calling
+pcre2_pattern_info() with the PCRE2_INFO_JITSIZE option. A non-zero
+result means that JIT compilation was successful. A result of 0 means that JIT
+support is not available, or the pattern was not processed by
+pcre2_jit_compile(), or the JIT compiler was not able to handle the
+pattern.
+

+
UNSUPPORTED OPTIONS AND PATTERN ITEMS

+

+The pcre2_match() options that are supported for JIT matching are
+PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART,
+PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. The
+PCRE2_ANCHORED option is not supported at match time.
+

+

+The only unsupported pattern items are \C (match a single data unit) when
+running in a UTF mode, and a callout immediately before an assertion condition
+in a conditional group.
+

+
RETURN VALUES FROM JIT MATCHING

+

+When a pattern is matched using JIT matching, the return values are the same
+as those given by the interpretive pcre2_match() code, with the addition
+of one new error code: PCRE2_ERROR_JIT_STACKLIMIT. This means that the memory
+used for the JIT stack was insufficient. See
+"Controlling the JIT stack"
+below for a discussion of JIT stack usage.
+

+

+The error code PCRE2_ERROR_MATCHLIMIT is returned by the JIT code if searching
+a very large pattern tree goes on for too long, as it is in the same
+circumstance when JIT is not used, but the details of exactly what is counted
+are not the same. The PCRE2_ERROR_RECURSIONLIMIT error code is never returned
+when JIT matching is used.
+

+
CONTROLLING THE JIT STACK

+

+When the compiled JIT code runs, it needs a block of memory to use as a stack.
+By default, it uses 32K on the machine stack. However, some large or
+complicated patterns need more than this. The error PCRE2_ERROR_JIT_STACKLIMIT
+is given when there is not enough stack. Three functions are provided for
+managing blocks of memory for use as JIT stacks. There is further discussion
+about the use of JIT stacks in the section entitled
+"JIT stack FAQ"
+below.
+

+

+The pcre2_jit_stack_create() function creates a JIT stack. Its arguments
+are a starting size, a maximum size, and a general context (for memory
+allocation functions, or NULL for standard memory allocation). It returns a
+pointer to an opaque structure of type pcre2_jit_stack, or NULL if there
+is an error. The pcre2_jit_stack_free() function is used to free a stack
+that is no longer needed. (For the technically minded: the address space is
+allocated by mmap or VirtualAlloc.)
+

+

+JIT uses far less memory for recursion than the interpretive code,
+and a maximum stack size of 512K to 1M should be more than enough for any
+pattern.
+

+

+The pcre2_jit_stack_assign() function specifies which stack JIT code
+should use. Its arguments are as follows:
+
+  pcre2_match_context  *mcontext
+  pcre2_jit_callback    callback
+  void                 *data
+

+The first argument is a pointer to a match context. When this is subsequently
+passed to a matching function, its information determines which JIT stack is
+used. There are three cases for the values of the other two options:
+
+  (1) If callback is NULL and data is NULL, an internal 32K block
+      on the machine stack is used. This is the default when a match
+      context is created.
+
+  (2) If callback is NULL and data is not NULL, data must be
+      a pointer to a valid JIT stack, the result of calling
+      pcre2_jit_stack_create().
+
+  (3) If callback is not NULL, it must point to a function that is
+      called with data as an argument at the start of matching, in
+      order to set up a JIT stack. If the return from the callback
+      function is NULL, the internal 32K stack is used; otherwise the
+      return value must be a valid JIT stack, the result of calling
+      pcre2_jit_stack_create().
+

+A callback function is obeyed whenever JIT code is about to be run; it is not
+obeyed when pcre2_match() is called with options that are incompatible
+for JIT matching. A callback function can therefore be used to determine
+whether a match operation was executed by JIT or by the interpreter.
+

+

+You may safely use the same JIT stack for more than one pattern (either by
+assigning directly or by callback), as long as the patterns are all matched
+sequentially in the same thread. In a multithread application, if you do not
+specify a JIT stack, or if you assign or pass back NULL from a callback, that
+is thread-safe, because each thread has its own machine stack. However, if you
+assign or pass back a non-NULL JIT stack, this must be a different stack for
+each thread so that the application is thread-safe.
+

+

+Strictly speaking, even more is allowed. You can assign the same non-NULL stack
+to a match context that is used by any number of patterns, as long as they are
+not used for matching by multiple threads at the same time. For example, you
+could use the same stack in all compiled patterns, with a global mutex in the
+callback to wait until the stack is available for use. However, this is an
+inefficient solution, and not recommended.
+

+

+This is a suggestion for how a multithreaded program that needs to set up
+non-default JIT stacks might operate:
+
+  During thread initalization
+    thread_local_var = pcre2_jit_stack_create(...)
+
+  During thread exit
+    pcre2_jit_stack_free(thread_local_var)
+
+  Use a one-line callback function
+    return thread_local_var
+

+All the functions described in this section do nothing if JIT is not available.
+

+
JIT STACK FAQ

+

+(1) Why do we need JIT stacks?
+

+

+PCRE2 (and JIT) is a recursive, depth-first engine, so it needs a stack where
+the local data of the current node is pushed before checking its child nodes.
+Allocating real machine stack on some platforms is difficult. For example, the
+stack chain needs to be updated every time if we extend the stack on PowerPC.
+Although it is possible, its updating time overhead decreases performance. So
+we do the recursion in memory.
+

+

+(2) Why don't we simply allocate blocks of memory with malloc()?
+

+

+Modern operating systems have a nice feature: they can reserve an address space
+instead of allocating memory. We can safely allocate memory pages inside this
+address space, so the stack could grow without moving memory data (this is
+important because of pointers). Thus we can allocate 1M address space, and use
+only a single memory page (usually 4K) if that is enough. However, we can still
+grow up to 1M anytime if needed.
+

+

+(3) Who "owns" a JIT stack?
+

+

+The owner of the stack is the user program, not the JIT studied pattern or
+anything else. The user program must ensure that if a stack is being used by
+pcre2_match(), (that is, it is assigned to a match context that is passed
+to the pattern currently running), that stack must not be used by any other
+threads (to avoid overwriting the same memory area). The best practice for
+multithreaded programs is to allocate a stack for each thread, and return this
+stack through the JIT callback function.
+

+

+(4) When should a JIT stack be freed?
+

+

+You can free a JIT stack at any time, as long as it will not be used by
+pcre2_match() again. When you assign the stack to a match context, only a
+pointer is set. There is no reference counting or any other magic. You can free
+compiled patterns, contexts, and stacks in any order, anytime. Just \fIdo
+not\fP call pcre2_match() with a match context pointing to an already
+freed stack, as that will cause SEGFAULT. (Also, do not free a stack currently
+used by pcre2_match() in another thread). You can also replace the stack
+in a context at any time when it is not in use. You should free the previous
+stack before assigning a replacement.
+

+

+(5) Should I allocate/free a stack every time before/after calling
+pcre2_match()?
+

+

+No, because this is too costly in terms of resources. However, you could
+implement some clever idea which release the stack if it is not used in let's
+say two minutes. The JIT callback can help to achieve this without keeping a
+list of patterns.
+

+

+(6) OK, the stack is for long term memory allocation. But what happens if a
+pattern causes stack overflow with a stack of 1M? Is that 1M kept until the
+stack is freed?
+

+

+Especially on embedded sytems, it might be a good idea to release memory
+sometimes without freeing the stack. There is no API for this at the moment.
+Probably a function call which returns with the currently allocated memory for
+any stack and another which allows releasing memory (shrinking the stack) would
+be a good idea if someone needs this.
+

+

+(7) This is too much of a headache. Isn't there any better solution for JIT
+stack handling?
+

+

+No, thanks to Windows. If POSIX threads were used everywhere, we could throw
+out this complicated API.
+

+
FREEING JIT SPECULATIVE MEMORY

+

+void pcre2_jit_free_unused_memory(pcre2_general_context *gcontext);
+

+

+The JIT executable allocator does not free all memory when it is possible.
+It expects new allocations, and keeps some free memory around to improve
+allocation speed. However, in low memory conditions, it might be better to free
+all possible memory. You can cause this to happen by calling
+pcre2_jit_free_unused_memory(). Its argument is a general context, for custom
+memory management, or NULL for standard memory management.
+

+
EXAMPLE CODE

+

+This is a single-threaded example that specifies a JIT stack without using a
+callback. A real program should include error checking after all the function
+calls.
+
+  int rc;
+  pcre2_code *re;
+  pcre2_match_data *match_data;
+  pcre2_match_context *mcontext;
+  pcre2_jit_stack *jit_stack;
+
+  re = pcre2_compile(pattern, PCRE2_ZERO_TERMINATED, 0,
+    &errornumber, &erroffset, NULL);
+  rc = pcre2_jit_compile(re, PCRE2_JIT_COMPLETE);
+  mcontext = pcre2_match_context_create(NULL);
+  jit_stack = pcre2_jit_stack_create(32*1024, 512*1024, NULL);
+  pcre2_jit_stack_assign(mcontext, NULL, jit_stack);
+  match_data = pcre2_match_data_create(re, 10);
+  rc = pcre2_match(re, subject, length, 0, 0, match_data, mcontext);
+  /* Process result */
+
+  pcre2_code_free(re);
+  pcre2_match_data_free(match_data);
+  pcre2_match_context_free(mcontext);
+  pcre2_jit_stack_free(jit_stack);
+
+

+

+
JIT FAST PATH API

+

+Because the API described above falls back to interpreted matching when JIT is
+not available, it is convenient for programs that are written for general use
+in many environments. However, calling JIT via pcre2_match() does have a
+performance impact. Programs that are written for use where JIT is known to be
+available, and which need the best possible performance, can instead use a
+"fast path" API to call JIT matching directly instead of calling
+pcre2_match() (obviously only for patterns that have been successfully
+processed by pcre2_jit_compile()).
+

+

+The fast path function is called pcre2_jit_match(), and it takes exactly
+the same arguments as pcre2_match(). The return values are also the same,
+plus PCRE2_ERROR_JIT_BADOPTION if a matching mode (partial or complete) is
+requested that was not compiled. Unsupported option bits (for example,
+PCRE2_ANCHORED) are ignored.
+

+

+When you call pcre2_match(), as well as testing for invalid options, a
+number of other sanity checks are performed on the arguments. For example, if
+the subject pointer is NULL, an immediate error is given. Also, unless
+PCRE2_NO_UTF_CHECK is set, a UTF subject string is tested for validity. In the
+interests of speed, these checks do not happen on the JIT fast path, and if
+invalid data is passed, the result is undefined.
+

+

+Bypassing the sanity checks and the pcre2_match() wrapping can give
+speedups of more than 10%.
+

+
SEE ALSO

+

+pcre2api(3)
+

+
AUTHOR

+

+Philip Hazel (FAQ by Zoltan Herczeg)
+

+University Computing Service
+

+Cambridge, England.
+

+

+
REVISION

+

+Last updated: 27 November 2014
+

+Copyright © 1997-2014 University of Cambridge.
+

+

+Return to the PCRE2 index page.
+

diff --git a/pcre2-10.20/doc/html/pcre2limits.html b/pcre2-10.20/doc/html/pcre2limits.html
new file mode 100644
index 000000000..b1c06f55f
--- /dev/null
+++ b/pcre2-10.20/doc/html/pcre2limits.html
@@ -0,0 +1,94 @@
+
+
+pcre2limits specification
+
+
+
pcre2limits man page

+

+Return to the PCRE2 index page.
+

+

+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+

+

+SIZE AND OTHER LIMITATIONS
+

+

+There are some size limitations in PCRE2 but it is hoped that they will never
+in practice be relevant.
+

+

+The maximum size of a compiled pattern is approximately 64K code units for the
+8-bit and 16-bit libraries if PCRE2 is compiled with the default internal
+linkage size, which is 2 bytes for these libraries. If you want to process
+regular expressions that are truly enormous, you can compile PCRE2 with an
+internal linkage size of 3 or 4 (when building the 16-bit library, 3 is rounded
+up to 4). See the README file in the source distribution and the
+pcre2build
+documentation for details. In these cases the limit is substantially larger.
+However, the speed of execution is slower. In the 32-bit library, the internal
+linkage size is always 4.
+

+

+The maximum length (in code units) of a subject string is one less than the
+largest number a PCRE2_SIZE variable can hold. PCRE2_SIZE is an unsigned
+integer type, usually defined as size_t. Its maximum value (that is
+~(PCRE2_SIZE)0) is reserved as a special indicator for zero-terminated strings
+and unset offsets.
+

+

+Note that when using the traditional matching function, PCRE2 uses recursion to
+handle subpatterns and indefinite repetition. This means that the available
+stack space may limit the size of a subject string that can be processed by
+certain patterns. For a discussion of stack issues, see the
+pcre2stack
+documentation.
+

+

+All values in repeating quantifiers must be less than 65536.
+

+

+There is no limit to the number of parenthesized subpatterns, but there can be
+no more than 65535 capturing subpatterns. There is, however, a limit to the
+depth of nesting of parenthesized subpatterns of all kinds. This is imposed in
+order to limit the amount of system stack used at compile time. The limit can
+be specified when PCRE2 is built; the default is 250.
+

+

+There is a limit to the number of forward references to subsequent subpatterns
+of around 200,000. Repeated forward references with fixed upper limits, for
+example, (?2){0,100} when subpattern number 2 is to the right, are included in
+the count. There is no limit to the number of backward references.
+

+

+The maximum length of name for a named subpattern is 32 code units, and the
+maximum number of named subpatterns is 10000.
+

+

+The maximum length of a name in a (*MARK), (*PRUNE), (*SKIP), or (*THEN) verb
+is 255 for the 8-bit library and 65535 for the 16-bit and 32-bit libraries.
+

+

+AUTHOR
+

+

+Philip Hazel
+

+University Computing Service
+

+Cambridge, England.
+

+

+

+REVISION
+

+

+Last updated: 25 November 2014
+

+Copyright © 1997-2014 University of Cambridge.
+

+

+Return to the PCRE2 index page.
+

diff --git a/pcre2-10.20/doc/html/pcre2matching.html b/pcre2-10.20/doc/html/pcre2matching.html
new file mode 100644
index 000000000..859bbb356
--- /dev/null
+++ b/pcre2-10.20/doc/html/pcre2matching.html
@@ -0,0 +1,241 @@
+
+
+pcre2matching specification
+
+
+
pcre2matching man page

+

+Return to the PCRE2 index page.
+

+

+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+

+

+
PCRE2 MATCHING ALGORITHMS

+

+This document describes the two different algorithms that are available in
+PCRE2 for matching a compiled regular expression against a given subject
+string. The "standard" algorithm is the one provided by the pcre2_match()
+function. This works in the same as as Perl's matching function, and provide a
+Perl-compatible matching operation. The just-in-time (JIT) optimization that is
+described in the
+pcre2jit
+documentation is compatible with this function.
+

+

+An alternative algorithm is provided by the pcre2_dfa_match() function;
+it operates in a different way, and is not Perl-compatible. This alternative
+has advantages and disadvantages compared with the standard algorithm, and
+these are described below.
+

+

+When there is only one possible way in which a given subject string can match a
+pattern, the two algorithms give the same answer. A difference arises, however,
+when there are multiple possibilities. For example, if the pattern
+
+  ^<.*>
+

+is matched against the string
+
+  <something> <something else> <something further>
+

+there are three possible answers. The standard algorithm finds only one of
+them, whereas the alternative algorithm finds all three.
+

+
REGULAR EXPRESSIONS AS TREES

+

+The set of strings that are matched by a regular expression can be represented
+as a tree structure. An unlimited repetition in the pattern makes the tree of
+infinite size, but it is still a tree. Matching the pattern to a given subject
+string (from a given starting point) can be thought of as a search of the tree.
+There are two ways to search a tree: depth-first and breadth-first, and these
+correspond to the two matching algorithms provided by PCRE2.
+

+
THE STANDARD MATCHING ALGORITHM

+

+In the terminology of Jeffrey Friedl's book "Mastering Regular Expressions",
+the standard algorithm is an "NFA algorithm". It conducts a depth-first search
+of the pattern tree. That is, it proceeds along a single path through the tree,
+checking that the subject matches what is required. When there is a mismatch,
+the algorithm tries any alternatives at the current point, and if they all
+fail, it backs up to the previous branch point in the tree, and tries the next
+alternative branch at that level. This often involves backing up (moving to the
+left) in the subject string as well. The order in which repetition branches are
+tried is controlled by the greedy or ungreedy nature of the quantifier.
+

+

+If a leaf node is reached, a matching string has been found, and at that point
+the algorithm stops. Thus, if there is more than one possible match, this
+algorithm returns the first one that it finds. Whether this is the shortest,
+the longest, or some intermediate length depends on the way the greedy and
+ungreedy repetition quantifiers are specified in the pattern.
+

+

+Because it ends up with a single path through the tree, it is relatively
+straightforward for this algorithm to keep track of the substrings that are
+matched by portions of the pattern in parentheses. This provides support for
+capturing parentheses and back references.
+

+
THE ALTERNATIVE MATCHING ALGORITHM

+

+This algorithm conducts a breadth-first search of the tree. Starting from the
+first matching point in the subject, it scans the subject string from left to
+right, once, character by character, and as it does this, it remembers all the
+paths through the tree that represent valid matches. In Friedl's terminology,
+this is a kind of "DFA algorithm", though it is not implemented as a
+traditional finite state machine (it keeps multiple states active
+simultaneously).
+

+

+Although the general principle of this matching algorithm is that it scans the
+subject string only once, without backtracking, there is one exception: when a
+lookaround assertion is encountered, the characters following or preceding the
+current point have to be independently inspected.
+

+

+The scan continues until either the end of the subject is reached, or there are
+no more unterminated paths. At this point, terminated paths represent the
+different matching possibilities (if there are none, the match has failed).
+Thus, if there is more than one possible match, this algorithm finds all of
+them, and in particular, it finds the longest. The matches are returned in
+decreasing order of length. There is an option to stop the algorithm after the
+first match (which is necessarily the shortest) is found.
+

+

+Note that all the matches that are found start at the same point in the
+subject. If the pattern
+
+  cat(er(pillar)?)?
+

+is matched against the string "the caterpillar catchment", the result is the
+three strings "caterpillar", "cater", and "cat" that start at the fifth
+character of the subject. The algorithm does not automatically move on to find
+matches that start at later positions.
+

+

+PCRE2's "auto-possessification" optimization usually applies to character
+repeats at the end of a pattern (as well as internally). For example, the
+pattern "a\d+" is compiled as if it were "a\d++" because there is no point
+even considering the possibility of backtracking into the repeated digits. For
+DFA matching, this means that only one possible match is found. If you really
+do want multiple matches in such cases, either use an ungreedy repeat
+("a\d+?") or set the PCRE2_NO_AUTO_POSSESS option when compiling.
+

+

+There are a number of features of PCRE2 regular expressions that are not
+supported by the alternative matching algorithm. They are as follows:
+

+

+1. Because the algorithm finds all possible matches, the greedy or ungreedy
+nature of repetition quantifiers is not relevant (though it may affect
+auto-possessification, as just described). During matching, greedy and ungreedy
+quantifiers are treated in exactly the same way. However, possessive
+quantifiers can make a difference when what follows could also match what is
+quantified, for example in a pattern like this:
+
+  ^a++\w!
+

+This pattern matches "aaab!" but not "aaa!", which would be matched by a
+non-possessive quantifier. Similarly, if an atomic group is present, it is
+matched as if it were a standalone pattern at the current point, and the
+longest match is then "locked in" for the rest of the overall pattern.
+

+

+2. When dealing with multiple paths through the tree simultaneously, it is not
+straightforward to keep track of captured substrings for the different matching
+possibilities, and PCRE2's implementation of this algorithm does not attempt to
+do this. This means that no captured substrings are available.
+

+

+3. Because no substrings are captured, back references within the pattern are
+not supported, and cause errors if encountered.
+

+

+4. For the same reason, conditional expressions that use a backreference as the
+condition or test for a specific group recursion are not supported.
+

+

+5. Because many paths through the tree may be active, the \K escape sequence,
+which resets the start of the match when encountered (but may be on some paths
+and not on others), is not supported. It causes an error if encountered.
+

+

+6. Callouts are supported, but the value of the capture_top field is
+always 1, and the value of the capture_last field is always 0.
+

+

+7. The \C escape sequence, which (in the standard algorithm) always matches a
+single code unit, even in a UTF mode, is not supported in these modes, because
+the alternative algorithm moves through the subject string one character (not
+code unit) at a time, for all active paths through the tree.
+

+

+8. Except for (*FAIL), the backtracking control verbs such as (*PRUNE) are not
+supported. (*FAIL) is supported, and behaves like a failing negative assertion.
+

+
ADVANTAGES OF THE ALTERNATIVE ALGORITHM

+

+Using the alternative matching algorithm provides the following advantages:
+

+

+1. All possible matches (at a single point in the subject) are automatically
+found, and in particular, the longest match is found. To find more than one
+match using the standard algorithm, you have to do kludgy things with
+callouts.
+

+

+2. Because the alternative algorithm scans the subject string just once, and
+never needs to backtrack (except for lookbehinds), it is possible to pass very
+long subject strings to the matching function in several pieces, checking for
+partial matching each time. Although it is also possible to do multi-segment
+matching using the standard algorithm, by retaining partially matched
+substrings, it is more complicated. The
+pcre2partial
+documentation gives details of partial matching and discusses multi-segment
+matching.
+

+
DISADVANTAGES OF THE ALTERNATIVE ALGORITHM

+

+The alternative algorithm suffers from a number of disadvantages:
+

+

+1. It is substantially slower than the standard algorithm. This is partly
+because it has to search for all possible matches, but is also because it is
+less susceptible to optimization.
+

+

+2. Capturing parentheses and back references are not supported.
+

+

+3. Although atomic groups are supported, their use does not provide the
+performance advantage that it does for the standard algorithm.
+

+
AUTHOR

+

+Philip Hazel
+

+University Computing Service
+

+Cambridge, England.
+

+

+
REVISION

+

+Last updated: 29 September 2014
+

+Copyright © 1997-2014 University of Cambridge.
+

+

+Return to the PCRE2 index page.
+

diff --git a/pcre2-10.20/doc/html/pcre2partial.html b/pcre2-10.20/doc/html/pcre2partial.html
new file mode 100644
index 000000000..4e156b81e
--- /dev/null
+++ b/pcre2-10.20/doc/html/pcre2partial.html
@@ -0,0 +1,465 @@
+
+
+pcre2partial specification
+
+
+
pcre2partial man page

+

+Return to the PCRE2 index page.
+

+

+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+

+

+
PARTIAL MATCHING IN PCRE2

+

+In normal use of PCRE2, if the subject string that is passed to a matching
+function matches as far as it goes, but is too short to match the entire
+pattern, PCRE2_ERROR_NOMATCH is returned. There are circumstances where it
+might be helpful to distinguish this case from other cases in which there is no
+match.
+

+

+Consider, for example, an application where a human is required to type in data
+for a field with specific formatting requirements. An example might be a date
+in the form ddmmmyy, defined by this pattern:
+
+  ^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$
+

+If the application sees the user's keystrokes one by one, and can check that
+what has been typed so far is potentially valid, it is able to raise an error
+as soon as a mistake is made, by beeping and not reflecting the character that
+has been typed, for example. This immediate feedback is likely to be a better
+user interface than a check that is delayed until the entire string has been
+entered. Partial matching can also be useful when the subject string is very
+long and is not all available at once.
+

+

+PCRE2 supports partial matching by means of the PCRE2_PARTIAL_SOFT and
+PCRE2_PARTIAL_HARD options, which can be set when calling a matching function.
+The difference between the two options is whether or not a partial match is
+preferred to an alternative complete match, though the details differ between
+the two types of matching function. If both options are set, PCRE2_PARTIAL_HARD
+takes precedence.
+

+

+If you want to use partial matching with just-in-time optimized code, you must
+call pcre2_jit_compile() with one or both of these options:
+
+  PCRE2_JIT_PARTIAL_SOFT
+  PCRE2_JIT_PARTIAL_HARD
+

+PCRE2_JIT_COMPLETE should also be set if you are going to run non-partial
+matches on the same pattern. If the appropriate JIT mode has not been compiled,
+interpretive matching code is used.
+

+

+Setting a partial matching option disables two of PCRE2's standard
+optimizations. PCRE2 remembers the last literal code unit in a pattern, and
+abandons matching immediately if it is not present in the subject string. This
+optimization cannot be used for a subject string that might match only
+partially. PCRE2 also knows the minimum length of a matching string, and does
+not bother to run the matching function on shorter strings. This optimization
+is also disabled for partial matching.
+

+
PARTIAL MATCHING USING pcre2_match()

+

+A partial match occurs during a call to pcre2_match() when the end of the
+subject string is reached successfully, but matching cannot continue because
+more characters are needed. However, at least one character in the subject must
+have been inspected. This character need not form part of the final matched
+string; lookbehind assertions and the \K escape sequence provide ways of
+inspecting characters before the start of a matched string. The requirement for
+inspecting at least one character exists because an empty string can always be
+matched; without such a restriction there would always be a partial match of an
+empty string at the end of the subject.
+

+

+When a partial match is returned, the first two elements in the ovector point
+to the portion of the subject that was matched, but the values in the rest of
+the ovector are undefined. The appearance of \K in the pattern has no effect
+for a partial match. Consider this pattern:
+
+  /abc\K123/
+

+If it is matched against "456abc123xyz" the result is a complete match, and the
+ovector defines the matched string as "123", because \K resets the "start of
+match" point. However, if a partial match is requested and the subject string
+is "456abc12", a partial match is found for the string "abc12", because all
+these characters are needed for a subsequent re-match with additional
+characters.
+

+

+What happens when a partial match is identified depends on which of the two
+partial matching options are set.
+

+

+PCRE2_PARTIAL_SOFT WITH pcre2_match()
+

+

+If PCRE2_PARTIAL_SOFT is set when pcre2_match() identifies a partial
+match, the partial match is remembered, but matching continues as normal, and
+other alternatives in the pattern are tried. If no complete match can be found,
+PCRE2_ERROR_PARTIAL is returned instead of PCRE2_ERROR_NOMATCH.
+

+

+This option is "soft" because it prefers a complete match over a partial match.
+All the various matching items in a pattern behave as if the subject string is
+potentially complete. For example, \z, \Z, and $ match at the end of the
+subject, as normal, and for \b and \B the end of the subject is treated as a
+non-alphanumeric.
+

+

+If there is more than one partial match, the first one that was found provides
+the data that is returned. Consider this pattern:
+
+  /123\w+X|dogY/
+

+If this is matched against the subject string "abc123dog", both
+alternatives fail to match, but the end of the subject is reached during
+matching, so PCRE2_ERROR_PARTIAL is returned. The offsets are set to 3 and 9,
+identifying "123dog" as the first partial match that was found. (In this
+example, there are two partial matches, because "dog" on its own partially
+matches the second alternative.)
+

+

+PCRE2_PARTIAL_HARD WITH pcre2_match()
+

+

+If PCRE2_PARTIAL_HARD is set for pcre2_match(), PCRE2_ERROR_PARTIAL is
+returned as soon as a partial match is found, without continuing to search for
+possible complete matches. This option is "hard" because it prefers an earlier
+partial match over a later complete match. For this reason, the assumption is
+made that the end of the supplied subject string may not be the true end of the
+available data, and so, if \z, \Z, \b, \B, or $ are encountered at the end
+of the subject, the result is PCRE2_ERROR_PARTIAL, provided that at least one
+character in the subject has been inspected.
+

+

+Comparing hard and soft partial matching
+

+

+The difference between the two partial matching options can be illustrated by a
+pattern such as:
+
+  /dog(sbody)?/
+

+This matches either "dog" or "dogsbody", greedily (that is, it prefers the
+longer string if possible). If it is matched against the string "dog" with
+PCRE2_PARTIAL_SOFT, it yields a complete match for "dog". However, if
+PCRE2_PARTIAL_HARD is set, the result is PCRE2_ERROR_PARTIAL. On the other
+hand, if the pattern is made ungreedy the result is different:
+
+  /dog(sbody)??/
+

+In this case the result is always a complete match because that is found first,
+and matching never continues after finding a complete match. It might be easier
+to follow this explanation by thinking of the two patterns like this:
+
+  /dog(sbody)?/    is the same as  /dogsbody|dog/
+  /dog(sbody)??/   is the same as  /dog|dogsbody/
+

+The second pattern will never match "dogsbody", because it will always find the
+shorter match first.
+

+
PARTIAL MATCHING USING pcre2_dfa_match()

+

+The DFA functions move along the subject string character by character, without
+backtracking, searching for all possible matches simultaneously. If the end of
+the subject is reached before the end of the pattern, there is the possibility
+of a partial match, again provided that at least one character has been
+inspected.
+

+

+When PCRE2_PARTIAL_SOFT is set, PCRE2_ERROR_PARTIAL is returned only if there
+have been no complete matches. Otherwise, the complete matches are returned.
+However, if PCRE2_PARTIAL_HARD is set, a partial match takes precedence over
+any complete matches. The portion of the string that was matched when the
+longest partial match was found is set as the first matching string.
+

+

+Because the DFA functions always search for all possible matches, and there is
+no difference between greedy and ungreedy repetition, their behaviour is
+different from the standard functions when PCRE2_PARTIAL_HARD is set. Consider
+the string "dog" matched against the ungreedy pattern shown above:
+
+  /dog(sbody)??/
+

+Whereas the standard function stops as soon as it finds the complete match for
+"dog", the DFA function also finds the partial match for "dogsbody", and so
+returns that when PCRE2_PARTIAL_HARD is set.
+

+
PARTIAL MATCHING AND WORD BOUNDARIES

+

+If a pattern ends with one of sequences \b or \B, which test for word
+boundaries, partial matching with PCRE2_PARTIAL_SOFT can give counter-intuitive
+results. Consider this pattern:
+
+  /\bcat\b/
+

+This matches "cat", provided there is a word boundary at either end. If the
+subject string is "the cat", the comparison of the final "t" with a following
+character cannot take place, so a partial match is found. However, normal
+matching carries on, and \b matches at the end of the subject when the last
+character is a letter, so a complete match is found. The result, therefore, is
+not PCRE2_ERROR_PARTIAL. Using PCRE2_PARTIAL_HARD in this case does yield
+PCRE2_ERROR_PARTIAL, because then the partial match takes precedence.
+

+
EXAMPLE OF PARTIAL MATCHING USING PCRE2TEST

+

+If the partial_soft (or ps) modifier is present on a
+pcre2test data line, the PCRE2_PARTIAL_SOFT option is used for the match.
+Here is a run of pcre2test that uses the date example quoted above:
+
+    re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
+  data> 25jun04\=ps
+   0: 25jun04
+   1: jun
+  data> 25dec3\=ps
+  Partial match: 23dec3
+  data> 3ju\=ps
+  Partial match: 3ju
+  data> 3juj\=ps
+  No match
+  data> j\=ps
+  No match
+

+The first data string is matched completely, so pcre2test shows the
+matched substrings. The remaining four strings do not match the complete
+pattern, but the first two are partial matches. Similar output is obtained
+if DFA matching is used.
+

+

+If the partial_hard (or ph) modifier is present on a
+pcre2test data line, the PCRE2_PARTIAL_HARD option is set for the match.
+

+
MULTI-SEGMENT MATCHING WITH pcre2_dfa_match()

+

+When a partial match has been found using a DFA matching function, it is
+possible to continue the match by providing additional subject data and calling
+the function again with the same compiled regular expression, this time setting
+the PCRE2_DFA_RESTART option. You must pass the same working space as before,
+because this is where details of the previous partial match are stored. Here is
+an example using pcre2test:
+
+    re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
+  data> 23ja\=dfa,ps
+  Partial match: 23ja
+  data> n05\=dfa,dfa_restart
+   0: n05
+

+The first call has "23ja" as the subject, and requests partial matching; the
+second call has "n05" as the subject for the continued (restarted) match.
+Notice that when the match is complete, only the last part is shown; PCRE2 does
+not retain the previously partially-matched string. It is up to the calling
+program to do that if it needs to.
+

+

+That means that, for an unanchored pattern, if a continued match fails, it is
+not possible to try again at a new starting point. All this facility is capable
+of doing is continuing with the previous match attempt. In the previous
+example, if the second set of data is "ug23" the result is no match, even
+though there would be a match for "aug23" if the entire string were given at
+once. Depending on the application, this may or may not be what you want.
+The only way to allow for starting again at the next character is to retain the
+matched part of the subject and try a new complete match.
+

+

+You can set the PCRE2_PARTIAL_SOFT or PCRE2_PARTIAL_HARD options with
+PCRE2_DFA_RESTART to continue partial matching over multiple segments. This
+facility can be used to pass very long subject strings to the DFA matching
+functions.
+

+
MULTI-SEGMENT MATCHING WITH pcre2_match()

+

+Unlike the DFA function, it is not possible to restart the previous match with
+a new segment of data when using pcre2_match(). Instead, new data must be
+added to the previous subject string, and the entire match re-run, starting
+from the point where the partial match occurred. Earlier data can be discarded.
+

+

+It is best to use PCRE2_PARTIAL_HARD in this situation, because it does not
+treat the end of a segment as the end of the subject when matching \z, \Z,
+\b, \B, and $. Consider an unanchored pattern that matches dates:
+
+    re> /\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d/
+  data> The date is 23ja\=ph
+  Partial match: 23ja
+

+At this stage, an application could discard the text preceding "23ja", add on
+text from the next segment, and call the matching function again. Unlike the
+DFA matching function, the entire matching string must always be available,
+and the complete matching process occurs for each call, so more memory and more
+processing time is needed.
+

+
ISSUES WITH MULTI-SEGMENT MATCHING

+

+Certain types of pattern may give problems with multi-segment matching,
+whichever matching function is used.
+

+

+1. If the pattern contains a test for the beginning of a line, you need to pass
+the PCRE2_NOTBOL option when the subject string for any call does start at the
+beginning of a line. There is also a PCRE2_NOTEOL option, but in practice when
+doing multi-segment matching you should be using PCRE2_PARTIAL_HARD, which
+includes the effect of PCRE2_NOTEOL.
+

+

+2. If a pattern contains a lookbehind assertion, characters that precede the
+start of the partial match may have been inspected during the matching process.
+When using pcre2_match(), sufficient characters must be retained for the
+next match attempt. You can ensure that enough characters are retained by doing
+the following:
+

+

+Before doing any matching, find the length of the longest lookbehind in the
+pattern by calling pcre2_pattern_info() with the PCRE2_INFO_MAXLOOKBEHIND
+option. Note that the resulting count is in characters, not code units. After a
+partial match, moving back from the ovector[0] offset in the subject by the
+number of characters given for the maximum lookbehind gets you to the earliest
+character that must be retained. In a non-UTF or a 32-bit situation, moving
+back is just a subtraction, but in UTF-8 or UTF-16 you have to count characters
+while moving back through the code units.
+

+

+Characters before the point you have now reached can be discarded, and after
+the next segment has been added to what is retained, you should run the next
+match with the startoffset argument set so that the match begins at the
+same point as before.
+

+

+For example, if the pattern "(?<=123)abc" is partially matched against the
+string "xx123ab", the ovector offsets are 5 and 7 ("ab"). The maximum
+lookbehind count is 3, so all characters before offset 2 can be discarded. The
+value of startoffset for the next match should be 3. When pcre2test
+displays a partial match, it indicates the lookbehind characters with '<'
+characters:
+
+    re> "(?<=123)abc"
+  data> xx123ab\=ph
+  Partial match: 123ab
+                 <<<
+

+

+

+3. Because a partial match must always contain at least one character, what
+might be considered a partial match of an empty string actually gives a "no
+match" result. For example:
+
+    re> /c(?<=abc)x/
+  data> ab\=ps
+  No match
+

+If the next segment begins "cx", a match should be found, but this will only
+happen if characters from the previous segment are retained. For this reason, a
+"no match" result should be interpreted as "partial match of an empty string"
+when the pattern contains lookbehinds.
+

+

+4. Matching a subject string that is split into multiple segments may not
+always produce exactly the same result as matching over one single long string,
+especially when PCRE2_PARTIAL_SOFT is used. The section "Partial Matching and
+Word Boundaries" above describes an issue that arises if the pattern ends with
+\b or \B. Another kind of difference may occur when there are multiple
+matching possibilities, because (for PCRE2_PARTIAL_SOFT) a partial match result
+is given only when there are no completed matches. This means that as soon as
+the shortest match has been found, continuation to a new subject segment is no
+longer possible. Consider this pcre2test example:
+
+    re> /dog(sbody)?/
+  data> dogsb\=ps
+   0: dog
+  data> do\=ps,dfa
+  Partial match: do
+  data> gsb\=ps,dfa,dfa_restart
+   0: g
+  data> dogsbody\=dfa
+   0: dogsbody
+   1: dog
+

+The first data line passes the string "dogsb" to a standard matching function,
+setting the PCRE2_PARTIAL_SOFT option. Although the string is a partial match
+for "dogsbody", the result is not PCRE2_ERROR_PARTIAL, because the shorter
+string "dog" is a complete match. Similarly, when the subject is presented to
+a DFA matching function in several parts ("do" and "gsb" being the first two)
+the match stops when "dog" has been found, and it is not possible to continue.
+On the other hand, if "dogsbody" is presented as a single string, a DFA
+matching function finds both matches.
+

+

+Because of these problems, it is best to use PCRE2_PARTIAL_HARD when matching
+multi-segment data. The example above then behaves differently:
+
+    re> /dog(sbody)?/
+  data> dogsb\=ph
+  Partial match: dogsb
+  data> do\=ps,dfa
+  Partial match: do
+  data> gsb\=ph,dfa,dfa_restart
+  Partial match: gsb
+

+5. Patterns that contain alternatives at the top level which do not all start
+with the same pattern item may not work as expected when PCRE2_DFA_RESTART is
+used. For example, consider this pattern:
+
+  1234|3789
+

+If the first part of the subject is "ABC123", a partial match of the first
+alternative is found at offset 3. There is no partial match for the second
+alternative, because such a match does not start at the same point in the
+subject string. Attempting to continue with the string "7890" does not yield a
+match because only those alternatives that match at one point in the subject
+are remembered. The problem arises because the start of the second alternative
+matches within the first alternative. There is no problem with anchored
+patterns or patterns such as:
+
+  1234|ABCD
+

+where no string can be a partial match for both alternatives. This is not a
+problem if a standard matching function is used, because the entire match has
+to be rerun each time:
+
+    re> /1234|3789/
+  data> ABC123\=ph
+  Partial match: 123
+  data> 1237890
+   0: 3789
+

+Of course, instead of using PCRE2_DFA_RESTART, the same technique of re-running
+the entire match can also be used with the DFA matching function. Another
+possibility is to work with two buffers. If a partial match at offset n
+in the first buffer is followed by "no match" when PCRE2_DFA_RESTART is used on
+the second buffer, you can then try a new match starting at offset n+1 in
+the first buffer.
+

+
AUTHOR

+

+Philip Hazel
+

+University Computing Service
+

+Cambridge, England.
+

+

+
REVISION

+

+Last updated: 22 December 2014
+

+Copyright © 1997-2014 University of Cambridge.
+

+

+Return to the PCRE2 index page.
+

diff --git a/pcre2-10.20/doc/html/pcre2pattern.html b/pcre2-10.20/doc/html/pcre2pattern.html
new file mode 100644
index 000000000..a9ca60e62
--- /dev/null
+++ b/pcre2-10.20/doc/html/pcre2pattern.html
@@ -0,0 +1,3332 @@
+
+
+pcre2pattern specification
+
+
+
pcre2pattern man page

+

+Return to the PCRE2 index page.
+

+

+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+

+

+
PCRE2 REGULAR EXPRESSION DETAILS

+

+The syntax and semantics of the regular expressions that are supported by PCRE2
+are described in detail below. There is a quick-reference syntax summary in the
+pcre2syntax
+page. PCRE2 tries to match Perl syntax and semantics as closely as it can.
+PCRE2 also supports some alternative regular expression syntax (which does not
+conflict with the Perl syntax) in order to provide some compatibility with
+regular expressions in Python, .NET, and Oniguruma.
+

+

+Perl's regular expressions are described in its own documentation, and regular
+expressions in general are covered in a number of books, some of which have
+copious examples. Jeffrey Friedl's "Mastering Regular Expressions", published
+by O'Reilly, covers regular expressions in great detail. This description of
+PCRE2's regular expressions is intended as reference material.
+

+

+This document discusses the patterns that are supported by PCRE2 when its main
+matching function, pcre2_match(), is used. PCRE2 also has an alternative
+matching function, pcre2_dfa_match(), which matches using a different
+algorithm that is not Perl-compatible. Some of the features discussed below are
+not available when DFA matching is used. The advantages and disadvantages of
+the alternative function, and how it differs from the normal function, are
+discussed in the
+pcre2matching
+page.
+

+
SPECIAL START-OF-PATTERN ITEMS

+

+A number of options that can be passed to pcre2_compile() can also be set
+by special items at the start of a pattern. These are not Perl-compatible, but
+are provided to make these options accessible to pattern writers who are not
+able to change the program that processes the pattern. Any number of these
+items may appear, but they must all be together right at the start of the
+pattern string, and the letters must be in upper case.
+

+

+UTF support
+

+

+In the 8-bit and 16-bit PCRE2 libraries, characters may be coded either as
+single code units, or as multiple UTF-8 or UTF-16 code units. UTF-32 can be
+specified for the 32-bit library, in which case it constrains the character
+values to valid Unicode code points. To process UTF strings, PCRE2 must be
+built to include Unicode support (which is the default). When using UTF strings
+you must either call the compiling function with the PCRE2_UTF option, or the
+pattern must start with the special sequence (*UTF), which is equivalent to
+setting the relevant option. How setting a UTF mode affects pattern matching is
+mentioned in several places below. There is also a summary of features in the
+pcre2unicode
+page.
+

+

+Some applications that allow their users to supply patterns may wish to
+restrict them to non-UTF data for security reasons. If the PCRE2_NEVER_UTF
+option is passed to pcre2_compile(), (*UTF) is not allowed, and its
+appearance in a pattern causes an error.
+

+

+Unicode property support
+

+

+Another special sequence that may appear at the start of a pattern is (*UCP).
+This has the same effect as setting the PCRE2_UCP option: it causes sequences
+such as \d and \w to use Unicode properties to determine character types,
+instead of recognizing only characters with codes less than 256 via a lookup
+table.
+

+

+Some applications that allow their users to supply patterns may wish to
+restrict them for security reasons. If the PCRE2_NEVER_UCP option is passed to
+pcre2_compile(), (*UCP) is not allowed, and its appearance in a pattern
+causes an error.
+

+

+Locking out empty string matching
+

+

+Starting a pattern with (*NOTEMPTY) or (*NOTEMPTY_ATSTART) has the same effect
+as passing the PCRE2_NOTEMPTY or PCRE2_NOTEMPTY_ATSTART option to whichever
+matching function is subsequently called to match the pattern. These options
+lock out the matching of empty strings, either entirely, or only at the start
+of the subject.
+

+

+Disabling auto-possessification
+

+

+If a pattern starts with (*NO_AUTO_POSSESS), it has the same effect as setting
+the PCRE2_NO_AUTO_POSSESS option. This stops PCRE2 from making quantifiers
+possessive when what follows cannot match the repeated item. For example, by
+default a+b is treated as a++b. For more details, see the
+pcre2api
+documentation.
+

+

+Disabling start-up optimizations
+

+

+If a pattern starts with (*NO_START_OPT), it has the same effect as setting the
+PCRE2_NO_START_OPTIMIZE option. This disables several optimizations for quickly
+reaching "no match" results. For more details, see the
+pcre2api
+documentation.
+

+

+Disabling automatic anchoring
+

+

+If a pattern starts with (*NO_DOTSTAR_ANCHOR), it has the same effect as
+setting the PCRE2_NO_DOTSTAR_ANCHOR option. This disables optimizations that
+apply to patterns whose top-level branches all start with .* (match any number
+of arbitrary characters). For more details, see the
+pcre2api
+documentation.
+

+

+Disabling JIT compilation
+

+

+If a pattern that starts with (*NO_JIT) is successfully compiled, an attempt by
+the application to apply the JIT optimization by calling
+pcre2_jit_compile() is ignored.
+

+

+Setting match and recursion limits
+

+

+The caller of pcre2_match() can set a limit on the number of times the
+internal match() function is called and on the maximum depth of
+recursive calls. These facilities are provided to catch runaway matches that
+are provoked by patterns with huge matching trees (a typical example is a
+pattern with nested unlimited repeats) and to avoid running out of system stack
+by too much recursion. When one of these limits is reached, pcre2_match()
+gives an error return. The limits can also be set by items at the start of the
+pattern of the form
+
+  (*LIMIT_MATCH=d)
+  (*LIMIT_RECURSION=d)
+

+where d is any number of decimal digits. However, the value of the setting must
+be less than the value set (or defaulted) by the caller of pcre2_match()
+for it to have any effect. In other words, the pattern writer can lower the
+limits set by the programmer, but not raise them. If there is more than one
+setting of one of these limits, the lower value is used.
+

+

+Newline conventions
+

+

+PCRE2 supports five different conventions for indicating line breaks in
+strings: a single CR (carriage return) character, a single LF (linefeed)
+character, the two-character sequence CRLF, any of the three preceding, or any
+Unicode newline sequence. The
+pcre2api
+page has
+further discussion
+about newlines, and shows how to set the newline convention when calling
+pcre2_compile().
+

+

+It is also possible to specify a newline convention by starting a pattern
+string with one of the following five sequences:
+
+  (*CR)        carriage return
+  (*LF)        linefeed
+  (*CRLF)      carriage return, followed by linefeed
+  (*ANYCRLF)   any of the three above
+  (*ANY)       all Unicode newline sequences
+

+These override the default and the options given to the compiling function. For
+example, on a Unix system where LF is the default newline sequence, the pattern
+
+  (*CR)a.b
+

+changes the convention to CR. That pattern matches "a\nb" because LF is no
+longer a newline. If more than one of these settings is present, the last one
+is used.
+

+

+The newline convention affects where the circumflex and dollar assertions are
+true. It also affects the interpretation of the dot metacharacter when
+PCRE2_DOTALL is not set, and the behaviour of \N. However, it does not affect
+what the \R escape sequence matches. By default, this is any Unicode newline
+sequence, for Perl compatibility. However, this can be changed; see the
+description of \R in the section entitled
+"Newline sequences"
+below. A change of \R setting can be combined with a change of newline
+convention.
+

+

+Specifying what \R matches
+

+

+It is possible to restrict \R to match only CR, LF, or CRLF (instead of the
+complete set of Unicode line endings) by setting the option PCRE2_BSR_ANYCRLF
+at compile time. This effect can also be achieved by starting a pattern with
+(*BSR_ANYCRLF). For completeness, (*BSR_UNICODE) is also recognized,
+corresponding to PCRE2_BSR_UNICODE.
+

+
EBCDIC CHARACTER CODES

+

+PCRE2 can be compiled to run in an environment that uses EBCDIC as its
+character code rather than ASCII or Unicode (typically a mainframe system). In
+the sections below, character code values are ASCII or Unicode; in an EBCDIC
+environment these characters may have different code values, and there are no
+code points greater than 255.
+

+
CHARACTERS AND METACHARACTERS

+

+A regular expression is a pattern that is matched against a subject string from
+left to right. Most characters stand for themselves in a pattern, and match the
+corresponding characters in the subject. As a trivial example, the pattern
+
+  The quick brown fox
+

+matches a portion of a subject string that is identical to itself. When
+caseless matching is specified (the PCRE2_CASELESS option), letters are matched
+independently of case.
+

+

+The power of regular expressions comes from the ability to include alternatives
+and repetitions in the pattern. These are encoded in the pattern by the use of
+metacharacters, which do not stand for themselves but instead are
+interpreted in some special way.
+

+

+There are two different sets of metacharacters: those that are recognized
+anywhere in the pattern except within square brackets, and those that are
+recognized within square brackets. Outside square brackets, the metacharacters
+are as follows:
+
+  \      general escape character with several uses
+  ^      assert start of string (or line, in multiline mode)
+  $      assert end of string (or line, in multiline mode)
+  .      match any character except newline (by default)
+  [      start character class definition
+  |      start of alternative branch
+  (      start subpattern
+  )      end subpattern
+  ?      extends the meaning of (
+         also 0 or 1 quantifier
+         also quantifier minimizer
+  *      0 or more quantifier
+  +      1 or more quantifier
+         also "possessive quantifier"
+  {      start min/max quantifier
+

+Part of a pattern that is in square brackets is called a "character class". In
+a character class the only metacharacters are:
+
+  \      general escape character
+  ^      negate the class, but only if the first character
+  -      indicates character range
+  [      POSIX character class (only if followed by POSIX syntax)
+  ]      terminates the character class
+

+The following sections describe the use of each of the metacharacters.
+

+
BACKSLASH

+

+The backslash character has several uses. Firstly, if it is followed by a
+character that is not a number or a letter, it takes away any special meaning
+that character may have. This use of backslash as an escape character applies
+both inside and outside character classes.
+

+

+For example, if you want to match a * character, you write \* in the pattern.
+This escaping action applies whether or not the following character would
+otherwise be interpreted as a metacharacter, so it is always safe to precede a
+non-alphanumeric with backslash to specify that it stands for itself. In
+particular, if you want to match a backslash, you write \\.
+

+

+In a UTF mode, only ASCII numbers and letters have any special meaning after a
+backslash. All other characters (in particular, those whose codepoints are
+greater than 127) are treated as literals.
+

+

+If a pattern is compiled with the PCRE2_EXTENDED option, most white space in
+the pattern (other than in a character class), and characters between a #
+outside a character class and the next newline, inclusive, are ignored. An
+escaping backslash can be used to include a white space or # character as part
+of the pattern.
+

+

+If you want to remove the special meaning from a sequence of characters, you
+can do so by putting them between \Q and \E. This is different from Perl in
+that $ and @ are handled as literals in \Q...\E sequences in PCRE2, whereas
+in Perl, $ and @ cause variable interpolation. Note the following examples:
+
+  Pattern            PCRE2 matches   Perl matches
+
+  \Qabc$xyz\E        abc$xyz        abc followed by the contents of $xyz
+  \Qabc\$xyz\E       abc\$xyz       abc\$xyz
+  \Qabc\E\$\Qxyz\E   abc$xyz        abc$xyz
+

+The \Q...\E sequence is recognized both inside and outside character classes.
+An isolated \E that is not preceded by \Q is ignored. If \Q is not followed
+by \E later in the pattern, the literal interpretation continues to the end of
+the pattern (that is, \E is assumed at the end). If the isolated \Q is inside
+a character class, this causes an error, because the character class is not
+terminated.
+

+

+Non-printing characters
+

+

+A second use of backslash provides a way of encoding non-printing characters
+in patterns in a visible manner. There is no restriction on the appearance of
+non-printing characters in a pattern, but when a pattern is being prepared by
+text editing, it is often easier to use one of the following escape sequences
+than the binary character it represents. In an ASCII or Unicode environment,
+these escapes are as follows:
+
+  \a        alarm, that is, the BEL character (hex 07)
+  \cx       "control-x", where x is any printable ASCII character
+  \e        escape (hex 1B)
+  \f        form feed (hex 0C)
+  \n        linefeed (hex 0A)
+  \r        carriage return (hex 0D)
+  \t        tab (hex 09)
+  \0dd      character with octal code 0dd
+  \ddd      character with octal code ddd, or back reference
+  \o{ddd..} character with octal code ddd..
+  \xhh      character with hex code hh
+  \x{hhh..} character with hex code hhh.. (default mode)
+  \uhhhh    character with hex code hhhh (when PCRE2_ALT_BSUX is set)
+

+The precise effect of \cx on ASCII characters is as follows: if x is a lower
+case letter, it is converted to upper case. Then bit 6 of the character (hex
+40) is inverted. Thus \cA to \cZ become hex 01 to hex 1A (A is 41, Z is 5A),
+but \c{ becomes hex 3B ({ is 7B), and \c; becomes hex 7B (; is 3B). If the
+code unit following \c has a value less than 32 or greater than 126, a
+compile-time error occurs. This locks out non-printable ASCII characters in all
+modes.
+

+

+When PCRE2 is compiled in EBCDIC mode, \a, \e, \f, \n, \r, and \t
+generate the appropriate EBCDIC code values. The \c escape is processed
+as specified for Perl in the perlebcdic document. The only characters
+that are allowed after \c are A-Z, a-z, or one of @, [, \, ], ^, _, or ?. Any
+other character provokes a compile-time error. The sequence \@ encodes
+character code 0; the letters (in either case) encode characters 1-26 (hex 01
+to hex 1A); [, \, ], ^, and _ encode characters 27-31 (hex 1B to hex 1F), and
+\? becomes either 255 (hex FF) or 95 (hex 5F).
+

+

+Thus, apart from \?, these escapes generate the same character code values as
+they do in an ASCII environment, though the meanings of the values mostly
+differ. For example, \G always generates code value 7, which is BEL in ASCII
+but DEL in EBCDIC.
+

+

+The sequence \? generates DEL (127, hex 7F) in an ASCII environment, but
+because 127 is not a control character in EBCDIC, Perl makes it generate the
+APC character. Unfortunately, there are several variants of EBCDIC. In most of
+them the APC character has the value 255 (hex FF), but in the one Perl calls
+POSIX-BC its value is 95 (hex 5F). If certain other characters have POSIX-BC
+values, PCRE2 makes \? generate 95; otherwise it generates 255.
+

+

+After \0 up to two further octal digits are read. If there are fewer than two
+digits, just those that are present are used. Thus the sequence \0\x\015
+specifies two binary zeros followed by a CR character (code value 13). Make
+sure you supply two digits after the initial zero if the pattern character that
+follows is itself an octal digit.
+

+

+The escape \o must be followed by a sequence of octal digits, enclosed in
+braces. An error occurs if this is not the case. This escape is a recent
+addition to Perl; it provides way of specifying character code points as octal
+numbers greater than 0777, and it also allows octal numbers and back references
+to be unambiguously specified.
+

+

+For greater clarity and unambiguity, it is best to avoid following \ by a
+digit greater than zero. Instead, use \o{} or \x{} to specify character
+numbers, and \g{} to specify back references. The following paragraphs
+describe the old, ambiguous syntax.
+

+

+The handling of a backslash followed by a digit other than 0 is complicated,
+and Perl has changed over time, causing PCRE2 also to change.
+

+

+Outside a character class, PCRE2 reads the digit and any following digits as a
+decimal number. If the number is less than 10, begins with the digit 8 or 9, or
+if there are at least that many previous capturing left parentheses in the
+expression, the entire sequence is taken as a back reference. A
+description of how this works is given
+later,
+following the discussion of
+parenthesized subpatterns.
+Otherwise, up to three octal digits are read to form a character code.
+

+

+Inside a character class, PCRE2 handles \8 and \9 as the literal characters
+"8" and "9", and otherwise reads up to three octal digits following the
+backslash, using them to generate a data character. Any subsequent digits stand
+for themselves. For example, outside a character class:
+
+  \040   is another way of writing an ASCII space
+  \40    is the same, provided there are fewer than 40 previous capturing subpatterns
+  \7     is always a back reference
+  \11    might be a back reference, or another way of writing a tab
+  \011   is always a tab
+  \0113  is a tab followed by the character "3"
+  \113   might be a back reference, otherwise the character with octal code 113
+  \377   might be a back reference, otherwise the value 255 (decimal)
+  \81    is always a back reference .sp
+

+Note that octal values of 100 or greater that are specified using this syntax
+must not be introduced by a leading zero, because no more than three octal
+digits are ever read.
+

+

+By default, after \x that is not followed by {, from zero to two hexadecimal
+digits are read (letters can be in upper or lower case). Any number of
+hexadecimal digits may appear between \x{ and }. If a character other than
+a hexadecimal digit appears between \x{ and }, or if there is no terminating
+}, an error occurs.
+

+

+If the PCRE2_ALT_BSUX option is set, the interpretation of \x is as just
+described only when it is followed by two hexadecimal digits. Otherwise, it
+matches a literal "x" character. In this mode mode, support for code points
+greater than 256 is provided by \u, which must be followed by four hexadecimal
+digits; otherwise it matches a literal "u" character.
+

+

+Characters whose value is less than 256 can be defined by either of the two
+syntaxes for \x (or by \u in PCRE2_ALT_BSUX mode). There is no difference in
+the way they are handled. For example, \xdc is exactly the same as \x{dc} (or
+\u00dc in PCRE2_ALT_BSUX mode).
+

+

+Constraints on character values
+

+

+Characters that are specified using octal or hexadecimal numbers are
+limited to certain values, as follows:
+
+  8-bit non-UTF mode    less than 0x100
+  8-bit UTF-8 mode      less than 0x10ffff and a valid codepoint
+  16-bit non-UTF mode   less than 0x10000
+  16-bit UTF-16 mode    less than 0x10ffff and a valid codepoint
+  32-bit non-UTF mode   less than 0x100000000
+  32-bit UTF-32 mode    less than 0x10ffff and a valid codepoint
+

+Invalid Unicode codepoints are the range 0xd800 to 0xdfff (the so-called
+"surrogate" codepoints), and 0xffef.
+

+

+Escape sequences in character classes
+

+

+All the sequences that define a single character value can be used both inside
+and outside character classes. In addition, inside a character class, \b is
+interpreted as the backspace character (hex 08).
+

+

+\N is not allowed in a character class. \B, \R, and \X are not special
+inside a character class. Like other unrecognized alphabetic escape sequences,
+they cause an error. Outside a character class, these sequences have different
+meanings.
+

+

+Unsupported escape sequences
+

+

+In Perl, the sequences \l, \L, \u, and \U are recognized by its string
+handler and used to modify the case of following characters. By default, PCRE2
+does not support these escape sequences. However, if the PCRE2_ALT_BSUX option
+is set, \U matches a "U" character, and \u can be used to define a character
+by code point, as described in the previous section.
+

+

+Absolute and relative back references
+

+

+The sequence \g followed by an unsigned or a negative number, optionally
+enclosed in braces, is an absolute or relative back reference. A named back
+reference can be coded as \g{name}. Back references are discussed
+later,
+following the discussion of
+parenthesized subpatterns.
+

+

+Absolute and relative subroutine calls
+

+

+For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or
+a number enclosed either in angle brackets or single quotes, is an alternative
+syntax for referencing a subpattern as a "subroutine". Details are discussed
+later.
+Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are not
+synonymous. The former is a back reference; the latter is a
+subroutine
+call.
+

+

+Generic character types
+

+

+Another use of backslash is for specifying generic character types:
+
+  \d     any decimal digit
+  \D     any character that is not a decimal digit
+  \h     any horizontal white space character
+  \H     any character that is not a horizontal white space character
+  \s     any white space character
+  \S     any character that is not a white space character
+  \v     any vertical white space character
+  \V     any character that is not a vertical white space character
+  \w     any "word" character
+  \W     any "non-word" character
+

+There is also the single sequence \N, which matches a non-newline character.
+This is the same as
+the "." metacharacter
+when PCRE2_DOTALL is not set. Perl also uses \N to match characters by name;
+PCRE2 does not support this.
+

+

+Each pair of lower and upper case escape sequences partitions the complete set
+of characters into two disjoint sets. Any given character matches one, and only
+one, of each pair. The sequences can appear both inside and outside character
+classes. They each match one character of the appropriate type. If the current
+matching point is at the end of the subject string, all of them fail, because
+there is no character to match.
+

+

+The default \s characters are HT (9), LF (10), VT (11), FF (12), CR (13), and
+space (32), which are defined as white space in the "C" locale. This list may
+vary if locale-specific matching is taking place. For example, in some locales
+the "non-breaking space" character (\xA0) is recognized as white space, and in
+others the VT character is not.
+

+

+A "word" character is an underscore or any character that is a letter or digit.
+By default, the definition of letters and digits is controlled by PCRE2's
+low-valued character tables, and may vary if locale-specific matching is taking
+place (see
+"Locale support"
+in the
+pcre2api
+page). For example, in a French locale such as "fr_FR" in Unix-like systems,
+or "french" in Windows, some character codes greater than 127 are used for
+accented letters, and these are then matched by \w. The use of locales with
+Unicode is discouraged.
+

+

+By default, characters whose code points are greater than 127 never match \d,
+\s, or \w, and always match \D, \S, and \W, although this may be different
+for characters in the range 128-255 when locale-specific matching is happening.
+These escape sequences retain their original meanings from before Unicode
+support was available, mainly for efficiency reasons. If the PCRE2_UCP option
+is set, the behaviour is changed so that Unicode properties are used to
+determine character types, as follows:
+
+  \d  any character that matches \p{Nd} (decimal digit)
+  \s  any character that matches \p{Z} or \h or \v
+  \w  any character that matches \p{L} or \p{N}, plus underscore
+

+The upper case escapes match the inverse sets of characters. Note that \d
+matches only decimal digits, whereas \w matches any Unicode digit, as well as
+any Unicode letter, and underscore. Note also that PCRE2_UCP affects \b, and
+\B because they are defined in terms of \w and \W. Matching these sequences
+is noticeably slower when PCRE2_UCP is set.
+

+

+The sequences \h, \H, \v, and \V, in contrast to the other sequences, which
+match only ASCII characters by default, always match a specific list of code
+points, whether or not PCRE2_UCP is set. The horizontal space characters are:
+
+  U+0009     Horizontal tab (HT)
+  U+0020     Space
+  U+00A0     Non-break space
+  U+1680     Ogham space mark
+  U+180E     Mongolian vowel separator
+  U+2000     En quad
+  U+2001     Em quad
+  U+2002     En space
+  U+2003     Em space
+  U+2004     Three-per-em space
+  U+2005     Four-per-em space
+  U+2006     Six-per-em space
+  U+2007     Figure space
+  U+2008     Punctuation space
+  U+2009     Thin space
+  U+200A     Hair space
+  U+202F     Narrow no-break space
+  U+205F     Medium mathematical space
+  U+3000     Ideographic space
+

+The vertical space characters are:
+
+  U+000A     Linefeed (LF)
+  U+000B     Vertical tab (VT)
+  U+000C     Form feed (FF)
+  U+000D     Carriage return (CR)
+  U+0085     Next line (NEL)
+  U+2028     Line separator
+  U+2029     Paragraph separator
+

+In 8-bit, non-UTF-8 mode, only the characters with code points less than 256
+are relevant.
+

+

+Newline sequences
+

+

+Outside a character class, by default, the escape sequence \R matches any
+Unicode newline sequence. In 8-bit non-UTF-8 mode \R is equivalent to the
+following:
+
+  (?>\r\n|\n|\x0b|\f|\r|\x85)
+

+This is an example of an "atomic group", details of which are given
+below.
+This particular group matches either the two-character sequence CR followed by
+LF, or one of the single characters LF (linefeed, U+000A), VT (vertical tab,
+U+000B), FF (form feed, U+000C), CR (carriage return, U+000D), or NEL (next
+line, U+0085). The two-character sequence is treated as a single unit that
+cannot be split.
+

+

+In other modes, two additional characters whose codepoints are greater than 255
+are added: LS (line separator, U+2028) and PS (paragraph separator, U+2029).
+Unicode support is not needed for these characters to be recognized.
+

+

+It is possible to restrict \R to match only CR, LF, or CRLF (instead of the
+complete set of Unicode line endings) by setting the option PCRE2_BSR_ANYCRLF
+at compile time. (BSR is an abbrevation for "backslash R".) This can be made
+the default when PCRE2 is built; if this is the case, the other behaviour can
+be requested via the PCRE2_BSR_UNICODE option. It is also possible to specify
+these settings by starting a pattern string with one of the following
+sequences:
+
+  (*BSR_ANYCRLF)   CR, LF, or CRLF only
+  (*BSR_UNICODE)   any Unicode newline sequence
+

+These override the default and the options given to the compiling function.
+Note that these special settings, which are not Perl-compatible, are recognized
+only at the very start of a pattern, and that they must be in upper case. If
+more than one of them is present, the last one is used. They can be combined
+with a change of newline convention; for example, a pattern can start with:
+
+  (*ANY)(*BSR_ANYCRLF)
+

+They can also be combined with the (*UTF) or (*UCP) special sequences. Inside a
+character class, \R is treated as an unrecognized escape sequence, and causes
+an error.
+

+

+Unicode character properties
+

+

+When PCRE2 is built with Unicode support (the default), three additional escape
+sequences that match characters with specific properties are available. In
+8-bit non-UTF-8 mode, these sequences are of course limited to testing
+characters whose codepoints are less than 256, but they do work in this mode.
+The extra escape sequences are:
+
+  \p{xx}   a character with the xx property
+  \P{xx}   a character without the xx property
+  \X       a Unicode extended grapheme cluster
+

+The property names represented by xx above are limited to the Unicode
+script names, the general category properties, "Any", which matches any
+character (including newline), and some special PCRE2 properties (described
+in the
+next section).
+Other Perl properties such as "InMusicalSymbols" are not supported by PCRE2.
+Note that \P{Any} does not match any characters, so always causes a match
+failure.
+

+

+Sets of Unicode characters are defined as belonging to certain scripts. A
+character from one of these sets can be matched using a script name. For
+example:
+
+  \p{Greek}
+  \P{Han}
+

+Those that are not part of an identified script are lumped together as
+"Common". The current list of scripts is:
+

+

+Arabic,
+Armenian,
+Avestan,
+Balinese,
+Bamum,
+Bassa_Vah,
+Batak,
+Bengali,
+Bopomofo,
+Brahmi,
+Braille,
+Buginese,
+Buhid,
+Canadian_Aboriginal,
+Carian,
+Caucasian_Albanian,
+Chakma,
+Cham,
+Cherokee,
+Common,
+Coptic,
+Cuneiform,
+Cypriot,
+Cyrillic,
+Deseret,
+Devanagari,
+Duployan,
+Egyptian_Hieroglyphs,
+Elbasan,
+Ethiopic,
+Georgian,
+Glagolitic,
+Gothic,
+Grantha,
+Greek,
+Gujarati,
+Gurmukhi,
+Han,
+Hangul,
+Hanunoo,
+Hebrew,
+Hiragana,
+Imperial_Aramaic,
+Inherited,
+Inscriptional_Pahlavi,
+Inscriptional_Parthian,
+Javanese,
+Kaithi,
+Kannada,
+Katakana,
+Kayah_Li,
+Kharoshthi,
+Khmer,
+Khojki,
+Khudawadi,
+Lao,
+Latin,
+Lepcha,
+Limbu,
+Linear_A,
+Linear_B,
+Lisu,
+Lycian,
+Lydian,
+Mahajani,
+Malayalam,
+Mandaic,
+Manichaean,
+Meetei_Mayek,
+Mende_Kikakui,
+Meroitic_Cursive,
+Meroitic_Hieroglyphs,
+Miao,
+Modi,
+Mongolian,
+Mro,
+Myanmar,
+Nabataean,
+New_Tai_Lue,
+Nko,
+Ogham,
+Ol_Chiki,
+Old_Italic,
+Old_North_Arabian,
+Old_Permic,
+Old_Persian,
+Old_South_Arabian,
+Old_Turkic,
+Oriya,
+Osmanya,
+Pahawh_Hmong,
+Palmyrene,
+Pau_Cin_Hau,
+Phags_Pa,
+Phoenician,
+Psalter_Pahlavi,
+Rejang,
+Runic,
+Samaritan,
+Saurashtra,
+Sharada,
+Shavian,
+Siddham,
+Sinhala,
+Sora_Sompeng,
+Sundanese,
+Syloti_Nagri,
+Syriac,
+Tagalog,
+Tagbanwa,
+Tai_Le,
+Tai_Tham,
+Tai_Viet,
+Takri,
+Tamil,
+Telugu,
+Thaana,
+Thai,
+Tibetan,
+Tifinagh,
+Tirhuta,
+Ugaritic,
+Vai,
+Warang_Citi,
+Yi.
+

+

+Each character has exactly one Unicode general category property, specified by
+a two-letter abbreviation. For compatibility with Perl, negation can be
+specified by including a circumflex between the opening brace and the property
+name. For example, \p{^Lu} is the same as \P{Lu}.
+

+

+If only one letter is specified with \p or \P, it includes all the general
+category properties that start with that letter. In this case, in the absence
+of negation, the curly brackets in the escape sequence are optional; these two
+examples have the same effect:
+
+  \p{L}
+  \pL
+

+The following general category property codes are supported:
+
+  C     Other
+  Cc    Control
+  Cf    Format
+  Cn    Unassigned
+  Co    Private use
+  Cs    Surrogate
+
+  L     Letter
+  Ll    Lower case letter
+  Lm    Modifier letter
+  Lo    Other letter
+  Lt    Title case letter
+  Lu    Upper case letter
+
+  M     Mark
+  Mc    Spacing mark
+  Me    Enclosing mark
+  Mn    Non-spacing mark
+
+  N     Number
+  Nd    Decimal number
+  Nl    Letter number
+  No    Other number
+
+  P     Punctuation
+  Pc    Connector punctuation
+  Pd    Dash punctuation
+  Pe    Close punctuation
+  Pf    Final punctuation
+  Pi    Initial punctuation
+  Po    Other punctuation
+  Ps    Open punctuation
+
+  S     Symbol
+  Sc    Currency symbol
+  Sk    Modifier symbol
+  Sm    Mathematical symbol
+  So    Other symbol
+
+  Z     Separator
+  Zl    Line separator
+  Zp    Paragraph separator
+  Zs    Space separator
+

+The special property L& is also supported: it matches a character that has
+the Lu, Ll, or Lt property, in other words, a letter that is not classified as
+a modifier or "other".
+

+

+The Cs (Surrogate) property applies only to characters in the range U+D800 to
+U+DFFF. Such characters are not valid in Unicode strings and so
+cannot be tested by PCRE2, unless UTF validity checking has been turned off
+(see the discussion of PCRE2_NO_UTF_CHECK in the
+pcre2api
+page). Perl does not support the Cs property.
+

+

+The long synonyms for property names that Perl supports (such as \p{Letter})
+are not supported by PCRE2, nor is it permitted to prefix any of these
+properties with "Is".
+

+

+No character that is in the Unicode table has the Cn (unassigned) property.
+Instead, this property is assumed for any code point that is not in the
+Unicode table.
+

+

+Specifying caseless matching does not affect these escape sequences. For
+example, \p{Lu} always matches only upper case letters. This is different from
+the behaviour of current versions of Perl.
+

+

+Matching characters by Unicode property is not fast, because PCRE2 has to do a
+multistage table lookup in order to find a character's property. That is why
+the traditional escape sequences such as \d and \w do not use Unicode
+properties in PCRE2 by default, though you can make them do so by setting the
+PCRE2_UCP option or by starting the pattern with (*UCP).
+

+

+Extended grapheme clusters
+

+

+The \X escape matches any number of Unicode characters that form an "extended
+grapheme cluster", and treats the sequence as an atomic group
+(see below).
+Unicode supports various kinds of composite character by giving each character
+a grapheme breaking property, and having rules that use these properties to
+define the boundaries of extended grapheme clusters. \X always matches at
+least one character. Then it decides whether to add additional characters
+according to the following rules for ending a cluster:
+

+

+1. End at the end of the subject string.
+

+

+2. Do not end between CR and LF; otherwise end after any control character.
+

+

+3. Do not break Hangul (a Korean script) syllable sequences. Hangul characters
+are of five types: L, V, T, LV, and LVT. An L character may be followed by an
+L, V, LV, or LVT character; an LV or V character may be followed by a V or T
+character; an LVT or T character may be follwed only by a T character.
+

+

+4. Do not end before extending characters or spacing marks. Characters with
+the "mark" property always have the "extend" grapheme breaking property.
+

+

+5. Do not end after prepend characters.
+

+

+6. Otherwise, end the cluster.
+

+

+PCRE2's additional properties
+

+

+As well as the standard Unicode properties described above, PCRE2 supports four
+more that make it possible to convert traditional escape sequences such as \w
+and \s to use Unicode properties. PCRE2 uses these non-standard, non-Perl
+properties internally when PCRE2_UCP is set. However, they may also be used
+explicitly. These properties are:
+
+  Xan   Any alphanumeric character
+  Xps   Any POSIX space character
+  Xsp   Any Perl space character
+  Xwd   Any Perl "word" character
+

+Xan matches characters that have either the L (letter) or the N (number)
+property. Xps matches the characters tab, linefeed, vertical tab, form feed, or
+carriage return, and any other character that has the Z (separator) property.
+Xsp is the same as Xps; in PCRE1 it used to exclude vertical tab, for Perl
+compatibility, but Perl changed. Xwd matches the same characters as Xan, plus
+underscore.
+

+

+There is another non-standard property, Xuc, which matches any character that
+can be represented by a Universal Character Name in C++ and other programming
+languages. These are the characters $, @, ` (grave accent), and all characters
+with Unicode code points greater than or equal to U+00A0, except for the
+surrogates U+D800 to U+DFFF. Note that most base (ASCII) characters are
+excluded. (Universal Character Names are of the form \uHHHH or \UHHHHHHHH
+where H is a hexadecimal digit. Note that the Xuc property does not match these
+sequences but the characters that they represent.)
+

+

+Resetting the match start
+

+

+The escape sequence \K causes any previously matched characters not to be
+included in the final matched sequence. For example, the pattern:
+
+  foo\Kbar
+

+matches "foobar", but reports that it has matched "bar". This feature is
+similar to a lookbehind assertion
+(described below).
+However, in this case, the part of the subject before the real match does not
+have to be of fixed length, as lookbehind assertions do. The use of \K does
+not interfere with the setting of
+captured substrings.
+For example, when the pattern
+
+  (foo)\Kbar
+

+matches "foobar", the first substring is still set to "foo".
+

+

+Perl documents that the use of \K within assertions is "not well defined". In
+PCRE2, \K is acted upon when it occurs inside positive assertions, but is
+ignored in negative assertions. Note that when a pattern such as (?=ab\K)
+matches, the reported start of the match can be greater than the end of the
+match.
+

+

+Simple assertions
+

+

+The final use of backslash is for certain simple assertions. An assertion
+specifies a condition that has to be met at a particular point in a match,
+without consuming any characters from the subject string. The use of
+subpatterns for more complicated assertions is described
+below.
+The backslashed assertions are:
+
+  \b     matches at a word boundary
+  \B     matches when not at a word boundary
+  \A     matches at the start of the subject
+  \Z     matches at the end of the subject
+          also matches before a newline at the end of the subject
+  \z     matches only at the end of the subject
+  \G     matches at the first matching position in the subject
+

+Inside a character class, \b has a different meaning; it matches the backspace
+character. If any other of these assertions appears in a character class, an
+"invalid escape sequence" error is generated.
+

+

+A word boundary is a position in the subject string where the current character
+and the previous character do not both match \w or \W (i.e. one matches
+\w and the other matches \W), or the start or end of the string if the
+first or last character matches \w, respectively. In a UTF mode, the meanings
+of \w and \W can be changed by setting the PCRE2_UCP option. When this is
+done, it also affects \b and \B. Neither PCRE2 nor Perl has a separate "start
+of word" or "end of word" metasequence. However, whatever follows \b normally
+determines which it is. For example, the fragment \ba matches "a" at the start
+of a word.
+

+

+The \A, \Z, and \z assertions differ from the traditional circumflex and
+dollar (described in the next section) in that they only ever match at the very
+start and end of the subject string, whatever options are set. Thus, they are
+independent of multiline mode. These three assertions are not affected by the
+PCRE2_NOTBOL or PCRE2_NOTEOL options, which affect only the behaviour of the
+circumflex and dollar metacharacters. However, if the startoffset
+argument of pcre2_match() is non-zero, indicating that matching is to
+start at a point other than the beginning of the subject, \A can never match.
+The difference between \Z and \z is that \Z matches before a newline at the
+end of the string as well as at the very end, whereas \z matches only at the
+end.
+

+

+The \G assertion is true only when the current matching position is at the
+start point of the match, as specified by the startoffset argument of
+pcre2_match(). It differs from \A when the value of startoffset is
+non-zero. By calling pcre2_match() multiple times with appropriate
+arguments, you can mimic Perl's /g option, and it is in this kind of
+implementation where \G can be useful.
+

+

+Note, however, that PCRE2's interpretation of \G, as the start of the current
+match, is subtly different from Perl's, which defines it as the end of the
+previous match. In Perl, these can be different when the previously matched
+string was empty. Because PCRE2 does just one match at a time, it cannot
+reproduce this behaviour.
+

+

+If all the alternatives of a pattern begin with \G, the expression is anchored
+to the starting match position, and the "anchored" flag is set in the compiled
+regular expression.
+

+
CIRCUMFLEX AND DOLLAR

+

+The circumflex and dollar metacharacters are zero-width assertions. That is,
+they test for a particular condition being true without consuming any
+characters from the subject string. These two metacharacters are concerned with
+matching the starts and ends of lines. If the newline convention is set so that
+only the two-character sequence CRLF is recognized as a newline, isolated CR
+and LF characters are treated as ordinary data characters, and are not
+recognized as newlines.
+

+

+Outside a character class, in the default matching mode, the circumflex
+character is an assertion that is true only if the current matching point is at
+the start of the subject string. If the startoffset argument of
+pcre2_match() is non-zero, or if PCRE2_NOTBOL is set, circumflex can
+never match if the PCRE2_MULTILINE option is unset. Inside a character class,
+circumflex has an entirely different meaning
+(see below).
+

+

+Circumflex need not be the first character of the pattern if a number of
+alternatives are involved, but it should be the first thing in each alternative
+in which it appears if the pattern is ever to match that branch. If all
+possible alternatives start with a circumflex, that is, if the pattern is
+constrained to match only at the start of the subject, it is said to be an
+"anchored" pattern. (There are also other constructs that can cause a pattern
+to be anchored.)
+

+

+The dollar character is an assertion that is true only if the current matching
+point is at the end of the subject string, or immediately before a newline at
+the end of the string (by default), unless PCRE2_NOTEOL is set. Note, however,
+that it does not actually match the newline. Dollar need not be the last
+character of the pattern if a number of alternatives are involved, but it
+should be the last item in any branch in which it appears. Dollar has no
+special meaning in a character class.
+

+

+The meaning of dollar can be changed so that it matches only at the very end of
+the string, by setting the PCRE2_DOLLAR_ENDONLY option at compile time. This
+does not affect the \Z assertion.
+

+

+The meanings of the circumflex and dollar metacharacters are changed if the
+PCRE2_MULTILINE option is set. When this is the case, a dollar character
+matches before any newlines in the string, as well as at the very end, and a
+circumflex matches immediately after internal newlines as well as at the start
+of the subject string. It does not match after a newline that ends the string,
+for compatibility with Perl. However, this can be changed by setting the
+PCRE2_ALT_CIRCUMFLEX option.
+

+

+For example, the pattern /^abc$/ matches the subject string "def\nabc" (where
+\n represents a newline) in multiline mode, but not otherwise. Consequently,
+patterns that are anchored in single line mode because all branches start with
+^ are not anchored in multiline mode, and a match for circumflex is possible
+when the startoffset argument of pcre2_match() is non-zero. The
+PCRE2_DOLLAR_ENDONLY option is ignored if PCRE2_MULTILINE is set.
+

+

+Note that the sequences \A, \Z, and \z can be used to match the start and
+end of the subject in both modes, and if all branches of a pattern start with
+\A it is always anchored, whether or not PCRE2_MULTILINE is set.
+

+
FULL STOP (PERIOD, DOT) AND \N

+

+Outside a character class, a dot in the pattern matches any one character in
+the subject string except (by default) a character that signifies the end of a
+line.
+

+

+When a line ending is defined as a single character, dot never matches that
+character; when the two-character sequence CRLF is used, dot does not match CR
+if it is immediately followed by LF, but otherwise it matches all characters
+(including isolated CRs and LFs). When any Unicode line endings are being
+recognized, dot does not match CR or LF or any of the other line ending
+characters.
+

+

+The behaviour of dot with regard to newlines can be changed. If the
+PCRE2_DOTALL option is set, a dot matches any one character, without exception.
+If the two-character sequence CRLF is present in the subject string, it takes
+two dots to match it.
+

+

+The handling of dot is entirely independent of the handling of circumflex and
+dollar, the only relationship being that they both involve newlines. Dot has no
+special meaning in a character class.
+

+

+The escape sequence \N behaves like a dot, except that it is not affected by
+the PCRE2_DOTALL option. In other words, it matches any character except one
+that signifies the end of a line. Perl also uses \N to match characters by
+name; PCRE2 does not support this.
+

+
MATCHING A SINGLE CODE UNIT

+

+Outside a character class, the escape sequence \C matches any one code unit,
+whether or not a UTF mode is set. In the 8-bit library, one code unit is one
+byte; in the 16-bit library it is a 16-bit unit; in the 32-bit library it is a
+32-bit unit. Unlike a dot, \C always matches line-ending characters. The
+feature is provided in Perl in order to match individual bytes in UTF-8 mode,
+but it is unclear how it can usefully be used.
+

+

+Because \C breaks up characters into individual code units, matching one unit
+with \C in UTF-8 or UTF-16 mode means that the rest of the string may start
+with a malformed UTF character. This has undefined results, because PCRE2
+assumes that it is matching character by character in a valid UTF string (by
+default it checks the subject string's validity at the start of processing
+unless the PCRE2_NO_UTF_CHECK option is used). An application can lock out the
+use of \C by setting the PCRE2_NEVER_BACKSLASH_C option.
+

+

+PCRE2 does not allow \C to appear in lookbehind assertions
+(described below)
+in a UTF mode, because this would make it impossible to calculate the length of
+the lookbehind.
+

+

+In general, the \C escape sequence is best avoided. However, one way of using
+it that avoids the problem of malformed UTF characters is to use a lookahead to
+check the length of the next character, as in this pattern, which could be used
+with a UTF-8 string (ignore white space and line breaks):
+
+  (?| (?=[\x00-\x7f])(\C) |
+      (?=[\x80-\x{7ff}])(\C)(\C) |
+      (?=[\x{800}-\x{ffff}])(\C)(\C)(\C) |
+      (?=[\x{10000}-\x{1fffff}])(\C)(\C)(\C)(\C))
+

+In this example, a group that starts with (?| resets the capturing parentheses
+numbers in each alternative (see
+"Duplicate Subpattern Numbers"
+below). The assertions at the start of each branch check the next UTF-8
+character for values whose encoding uses 1, 2, 3, or 4 bytes, respectively. The
+character's individual bytes are then captured by the appropriate number of
+\C groups.
+

+
SQUARE BRACKETS AND CHARACTER CLASSES

+

+An opening square bracket introduces a character class, terminated by a closing
+square bracket. A closing square bracket on its own is not special by default.
+If a closing square bracket is required as a member of the class, it should be
+the first data character in the class (after an initial circumflex, if present)
+or escaped with a backslash. This means that, by default, an empty class cannot
+be defined. However, if the PCRE2_ALLOW_EMPTY_CLASS option is set, a closing
+square bracket at the start does end the (empty) class.
+

+

+A character class matches a single character in the subject. A matched
+character must be in the set of characters defined by the class, unless the
+first character in the class definition is a circumflex, in which case the
+subject character must not be in the set defined by the class. If a circumflex
+is actually required as a member of the class, ensure it is not the first
+character, or escape it with a backslash.
+

+

+For example, the character class [aeiou] matches any lower case vowel, while
+[^aeiou] matches any character that is not a lower case vowel. Note that a
+circumflex is just a convenient notation for specifying the characters that
+are in the class by enumerating those that are not. A class that starts with a
+circumflex is not an assertion; it still consumes a character from the subject
+string, and therefore it fails if the current pointer is at the end of the
+string.
+

+

+When caseless matching is set, any letters in a class represent both their
+upper case and lower case versions, so for example, a caseless [aeiou] matches
+"A" as well as "a", and a caseless [^aeiou] does not match "A", whereas a
+caseful version would.
+

+

+Characters that might indicate line breaks are never treated in any special way
+when matching character classes, whatever line-ending sequence is in use, and
+whatever setting of the PCRE2_DOTALL and PCRE2_MULTILINE options is used. A
+class such as [^a] always matches one of these characters.
+

+

+The minus (hyphen) character can be used to specify a range of characters in a
+character class. For example, [d-m] matches any letter between d and m,
+inclusive. If a minus character is required in a class, it must be escaped with
+a backslash or appear in a position where it cannot be interpreted as
+indicating a range, typically as the first or last character in the class, or
+immediately after a range. For example, [b-d-z] matches letters in the range b
+to d, a hyphen character, or z.
+

+

+It is not possible to have the literal character "]" as the end character of a
+range. A pattern such as [W-]46] is interpreted as a class of two characters
+("W" and "-") followed by a literal string "46]", so it would match "W46]" or
+"-46]". However, if the "]" is escaped with a backslash it is interpreted as
+the end of range, so [W-\]46] is interpreted as a class containing a range
+followed by two other characters. The octal or hexadecimal representation of
+"]" can also be used to end a range.
+

+

+An error is generated if a POSIX character class (see below) or an escape
+sequence other than one that defines a single character appears at a point
+where a range ending character is expected. For example, [z-\xff] is valid,
+but [A-\d] and [A-[:digit:]] are not.
+

+

+Ranges operate in the collating sequence of character values. They can also be
+used for characters specified numerically, for example [\000-\037]. Ranges
+can include any characters that are valid for the current mode.
+

+

+If a range that includes letters is used when caseless matching is set, it
+matches the letters in either case. For example, [W-c] is equivalent to
+[][\\^_`wxyzabc], matched caselessly, and in a non-UTF mode, if character
+tables for a French locale are in use, [\xc8-\xcb] matches accented E
+characters in both cases.
+

+

+The character escape sequences \d, \D, \h, \H, \p, \P, \s, \S, \v,
+\V, \w, and \W may appear in a character class, and add the characters that
+they match to the class. For example, [\dABCDEF] matches any hexadecimal
+digit. In UTF modes, the PCRE2_UCP option affects the meanings of \d, \s, \w
+and their upper case partners, just as it does when they appear outside a
+character class, as described in the section entitled
+"Generic character types"
+above. The escape sequence \b has a different meaning inside a character
+class; it matches the backspace character. The sequences \B, \N, \R, and \X
+are not special inside a character class. Like any other unrecognized escape
+sequences, they cause an error.
+

+

+A circumflex can conveniently be used with the upper case character types to
+specify a more restricted set of characters than the matching lower case type.
+For example, the class [^\W_] matches any letter or digit, but not underscore,
+whereas [\w] includes underscore. A positive character class should be read as
+"something OR something OR ..." and a negative class as "NOT something AND NOT
+something AND NOT ...".
+

+

+The only metacharacters that are recognized in character classes are backslash,
+hyphen (only where it can be interpreted as specifying a range), circumflex
+(only at the start), opening square bracket (only when it can be interpreted as
+introducing a POSIX class name, or for a special compatibility feature - see
+the next two sections), and the terminating closing square bracket. However,
+escaping other non-alphanumeric characters does no harm.
+

+
POSIX CHARACTER CLASSES

+

+Perl supports the POSIX notation for character classes. This uses names
+enclosed by [: and :] within the enclosing square brackets. PCRE2 also supports
+this notation. For example,
+
+  [01[:alpha:]%]
+

+matches "0", "1", any alphabetic character, or "%". The supported class names
+are:
+
+  alnum    letters and digits
+  alpha    letters
+  ascii    character codes 0 - 127
+  blank    space or tab only
+  cntrl    control characters
+  digit    decimal digits (same as \d)
+  graph    printing characters, excluding space
+  lower    lower case letters
+  print    printing characters, including space
+  punct    printing characters, excluding letters and digits and space
+  space    white space (the same as \s from PCRE2 8.34)
+  upper    upper case letters
+  word     "word" characters (same as \w)
+  xdigit   hexadecimal digits
+

+The default "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13),
+and space (32). If locale-specific matching is taking place, the list of space
+characters may be different; there may be fewer or more of them. "Space" and
+\s match the same set of characters.
+

+

+The name "word" is a Perl extension, and "blank" is a GNU extension from Perl
+5.8. Another Perl extension is negation, which is indicated by a ^ character
+after the colon. For example,
+
+  [12[:^digit:]]
+

+matches "1", "2", or any non-digit. PCRE2 (and Perl) also recognize the POSIX
+syntax [.ch.] and [=ch=] where "ch" is a "collating element", but these are not
+supported, and an error is given if they are encountered.
+

+

+By default, characters with values greater than 127 do not match any of the
+POSIX character classes, although this may be different for characters in the
+range 128-255 when locale-specific matching is happening. However, if the
+PCRE2_UCP option is passed to pcre2_compile(), some of the classes are
+changed so that Unicode character properties are used. This is achieved by
+replacing certain POSIX classes with other sequences, as follows:
+
+  [:alnum:]  becomes  \p{Xan}
+  [:alpha:]  becomes  \p{L}
+  [:blank:]  becomes  \h
+  [:cntrl:]  becomes  \p{Cc}
+  [:digit:]  becomes  \p{Nd}
+  [:lower:]  becomes  \p{Ll}
+  [:space:]  becomes  \p{Xps}
+  [:upper:]  becomes  \p{Lu}
+  [:word:]   becomes  \p{Xwd}
+

+Negated versions, such as [:^alpha:] use \P instead of \p. Three other POSIX
+classes are handled specially in UCP mode:
+

+

+[:graph:]
+This matches characters that have glyphs that mark the page when printed. In
+Unicode property terms, it matches all characters with the L, M, N, P, S, or Cf
+properties, except for:
+
+  U+061C           Arabic Letter Mark
+  U+180E           Mongolian Vowel Separator
+  U+2066 - U+2069  Various "isolate"s
+
+

+

+

+[:print:]
+This matches the same characters as [:graph:] plus space characters that are
+not controls, that is, characters with the Zs property.
+

+

+[:punct:]
+This matches all characters that have the Unicode P (punctuation) property,
+plus those characters with code points less than 256 that have the S (Symbol)
+property.
+

+

+The other POSIX classes are unchanged, and match only characters with code
+points less than 256.
+

+
COMPATIBILITY FEATURE FOR WORD BOUNDARIES

+

+In the POSIX.2 compliant library that was included in 4.4BSD Unix, the ugly
+syntax [[:<:]] and [[:>:]] is used for matching "start of word" and "end of
+word". PCRE2 treats these items as follows:
+
+  [[:<:]]  is converted to  \b(?=\w)
+  [[:>:]]  is converted to  \b(?<=\w)
+

+Only these exact character sequences are recognized. A sequence such as
+[a[:<:]b] provokes error for an unrecognized POSIX class name. This support is
+not compatible with Perl. It is provided to help migrations from other
+environments, and is best not used in any new patterns. Note that \b matches
+at the start and the end of a word (see
+"Simple assertions"
+above), and in a Perl-style pattern the preceding or following character
+normally shows which is wanted, without the need for the assertions that are
+used above in order to give exactly the POSIX behaviour.
+

+
VERTICAL BAR

+

+Vertical bar characters are used to separate alternative patterns. For example,
+the pattern
+
+  gilbert|sullivan
+

+matches either "gilbert" or "sullivan". Any number of alternatives may appear,
+and an empty alternative is permitted (matching the empty string). The matching
+process tries each alternative in turn, from left to right, and the first one
+that succeeds is used. If the alternatives are within a subpattern
+(defined below),
+"succeeds" means matching the rest of the main pattern as well as the
+alternative in the subpattern.
+

+
INTERNAL OPTION SETTING

+

+The settings of the PCRE2_CASELESS, PCRE2_MULTILINE, PCRE2_DOTALL, and
+PCRE2_EXTENDED options (which are Perl-compatible) can be changed from within
+the pattern by a sequence of Perl option letters enclosed between "(?" and ")".
+The option letters are
+
+  i  for PCRE2_CASELESS
+  m  for PCRE2_MULTILINE
+  s  for PCRE2_DOTALL
+  x  for PCRE2_EXTENDED
+

+For example, (?im) sets caseless, multiline matching. It is also possible to
+unset these options by preceding the letter with a hyphen, and a combined
+setting and unsetting such as (?im-sx), which sets PCRE2_CASELESS and
+PCRE2_MULTILINE while unsetting PCRE2_DOTALL and PCRE2_EXTENDED, is also
+permitted. If a letter appears both before and after the hyphen, the option is
+unset. An empty options setting "(?)" is allowed. Needless to say, it has no
+effect.
+

+

+The PCRE2-specific options PCRE2_DUPNAMES and PCRE2_UNGREEDY can be changed in
+the same way as the Perl-compatible options by using the characters J and U
+respectively.
+

+

+When one of these option changes occurs at top level (that is, not inside
+subpattern parentheses), the change applies to the remainder of the pattern
+that follows. If the change is placed right at the start of a pattern, PCRE2
+extracts it into the global options (and it will therefore show up in data
+extracted by the pcre2_pattern_info() function).
+

+

+An option change within a subpattern (see below for a description of
+subpatterns) affects only that part of the subpattern that follows it, so
+
+  (a(?i)b)c
+

+matches abc and aBc and no other strings (assuming PCRE2_CASELESS is not used).
+By this means, options can be made to have different settings in different
+parts of the pattern. Any changes made in one alternative do carry on
+into subsequent branches within the same subpattern. For example,
+
+  (a(?i)b|c)
+

+matches "ab", "aB", "c", and "C", even though when matching "C" the first
+branch is abandoned before the option setting. This is because the effects of
+option settings happen at compile time. There would be some very weird
+behaviour otherwise.
+

+

+As a convenient shorthand, if any option settings are required at the start of
+a non-capturing subpattern (see the next section), the option letters may
+appear between the "?" and the ":". Thus the two patterns
+
+  (?i:saturday|sunday)
+  (?:(?i)saturday|sunday)
+

+match exactly the same set of strings.
+

+

+Note: There are other PCRE2-specific options that can be set by the
+application when the compiling function is called. The pattern can contain
+special leading sequences such as (*CRLF) to override what the application has
+set or what has been defaulted. Details are given in the section entitled
+"Newline sequences"
+above. There are also the (*UTF) and (*UCP) leading sequences that can be used
+to set UTF and Unicode property modes; they are equivalent to setting the
+PCRE2_UTF and PCRE2_UCP options, respectively. However, the application can set
+the PCRE2_NEVER_UTF and PCRE2_NEVER_UCP options, which lock out the use of the
+(*UTF) and (*UCP) sequences.
+

+
SUBPATTERNS

+

+Subpatterns are delimited by parentheses (round brackets), which can be nested.
+Turning part of a pattern into a subpattern does two things:
+

+

+1. It localizes a set of alternatives. For example, the pattern
+
+  cat(aract|erpillar|)
+

+matches "cataract", "caterpillar", or "cat". Without the parentheses, it would
+match "cataract", "erpillar" or an empty string.
+

+

+2. It sets up the subpattern as a capturing subpattern. This means that, when
+the whole pattern matches, the portion of the subject string that matched the
+subpattern is passed back to the caller, separately from the portion that
+matched the whole pattern. (This applies only to the traditional matching
+function; the DFA matching function does not support capturing.)
+

+

+Opening parentheses are counted from left to right (starting from 1) to obtain
+numbers for the capturing subpatterns. For example, if the string "the red
+king" is matched against the pattern
+
+  the ((red|white) (king|queen))
+

+the captured substrings are "red king", "red", and "king", and are numbered 1,
+2, and 3, respectively.
+

+

+The fact that plain parentheses fulfil two functions is not always helpful.
+There are often times when a grouping subpattern is required without a
+capturing requirement. If an opening parenthesis is followed by a question mark
+and a colon, the subpattern does not do any capturing, and is not counted when
+computing the number of any subsequent capturing subpatterns. For example, if
+the string "the white queen" is matched against the pattern
+
+  the ((?:red|white) (king|queen))
+

+the captured substrings are "white queen" and "queen", and are numbered 1 and
+2. The maximum number of capturing subpatterns is 65535.
+

+

+As a convenient shorthand, if any option settings are required at the start of
+a non-capturing subpattern, the option letters may appear between the "?" and
+the ":". Thus the two patterns
+
+  (?i:saturday|sunday)
+  (?:(?i)saturday|sunday)
+

+match exactly the same set of strings. Because alternative branches are tried
+from left to right, and options are not reset until the end of the subpattern
+is reached, an option setting in one branch does affect subsequent branches, so
+the above patterns match "SUNDAY" as well as "Saturday".
+

+
DUPLICATE SUBPATTERN NUMBERS

+

+Perl 5.10 introduced a feature whereby each alternative in a subpattern uses
+the same numbers for its capturing parentheses. Such a subpattern starts with
+(?| and is itself a non-capturing subpattern. For example, consider this
+pattern:
+
+  (?|(Sat)ur|(Sun))day
+

+Because the two alternatives are inside a (?| group, both sets of capturing
+parentheses are numbered one. Thus, when the pattern matches, you can look
+at captured substring number one, whichever alternative matched. This construct
+is useful when you want to capture part, but not all, of one of a number of
+alternatives. Inside a (?| group, parentheses are numbered as usual, but the
+number is reset at the start of each branch. The numbers of any capturing
+parentheses that follow the subpattern start after the highest number used in
+any branch. The following example is taken from the Perl documentation. The
+numbers underneath show in which buffer the captured content will be stored.
+
+  # before  ---------------branch-reset----------- after
+  / ( a )  (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x
+  # 1            2         2  3        2     3     4
+

+A back reference to a numbered subpattern uses the most recent value that is
+set for that number by any subpattern. The following pattern matches "abcabc"
+or "defdef":
+
+  /(?|(abc)|(def))\1/
+

+In contrast, a subroutine call to a numbered subpattern always refers to the
+first one in the pattern with the given number. The following pattern matches
+"abcabc" or "defabc":
+
+  /(?|(abc)|(def))(?1)/
+

+If a
+condition test
+for a subpattern's having matched refers to a non-unique number, the test is
+true if any of the subpatterns of that number have matched.
+

+

+An alternative approach to using this "branch reset" feature is to use
+duplicate named subpatterns, as described in the next section.
+

+
NAMED SUBPATTERNS

+

+Identifying capturing parentheses by number is simple, but it can be very hard
+to keep track of the numbers in complicated regular expressions. Furthermore,
+if an expression is modified, the numbers may change. To help with this
+difficulty, PCRE2 supports the naming of subpatterns. This feature was not
+added to Perl until release 5.10. Python had the feature earlier, and PCRE1
+introduced it at release 4.0, using the Python syntax. PCRE2 supports both the
+Perl and the Python syntax. Perl allows identically numbered subpatterns to
+have different names, but PCRE2 does not.
+

+

+In PCRE2, a subpattern can be named in one of three ways: (?<name>...) or
+(?'name'...) as in Perl, or (?P<name>...) as in Python. References to capturing
+parentheses from other parts of the pattern, such as
+back references,
+recursion,
+and
+conditions,
+can be made by name as well as by number.
+

+

+Names consist of up to 32 alphanumeric characters and underscores, but must
+start with a non-digit. Named capturing parentheses are still allocated numbers
+as well as names, exactly as if the names were not present. The PCRE2 API
+provides function calls for extracting the name-to-number translation table
+from a compiled pattern. There are also convenience functions for extracting a
+captured substring by name.
+

+

+By default, a name must be unique within a pattern, but it is possible to relax
+this constraint by setting the PCRE2_DUPNAMES option at compile time.
+(Duplicate names are also always permitted for subpatterns with the same
+number, set up as described in the previous section.) Duplicate names can be
+useful for patterns where only one instance of the named parentheses can match.
+Suppose you want to match the name of a weekday, either as a 3-letter
+abbreviation or as the full name, and in both cases you want to extract the
+abbreviation. This pattern (ignoring the line breaks) does the job:
+
+  (?<DN>Mon|Fri|Sun)(?:day)?|
+  (?<DN>Tue)(?:sday)?|
+  (?<DN>Wed)(?:nesday)?|
+  (?<DN>Thu)(?:rsday)?|
+  (?<DN>Sat)(?:urday)?
+

+There are five capturing substrings, but only one is ever set after a match.
+(An alternative way of solving this problem is to use a "branch reset"
+subpattern, as described in the previous section.)
+

+

+The convenience functions for extracting the data by name returns the substring
+for the first (and in this example, the only) subpattern of that name that
+matched. This saves searching to find which numbered subpattern it was.
+

+

+If you make a back reference to a non-unique named subpattern from elsewhere in
+the pattern, the subpatterns to which the name refers are checked in the order
+in which they appear in the overall pattern. The first one that is set is used
+for the reference. For example, this pattern matches both "foofoo" and
+"barbar" but not "foobar" or "barfoo":
+
+  (?:(?<n>foo)|(?<n>bar))\k<n>
+
+

+

+

+If you make a subroutine call to a non-unique named subpattern, the one that
+corresponds to the first occurrence of the name is used. In the absence of
+duplicate numbers (see the previous section) this is the one with the lowest
+number.
+

+

+If you use a named reference in a condition
+test (see the
+section about conditions
+below), either to check whether a subpattern has matched, or to check for
+recursion, all subpatterns with the same name are tested. If the condition is
+true for any one of them, the overall condition is true. This is the same
+behaviour as testing by number. For further details of the interfaces for
+handling named subpatterns, see the
+pcre2api
+documentation.
+

+

+Warning: You cannot use different names to distinguish between two
+subpatterns with the same number because PCRE2 uses only the numbers when
+matching. For this reason, an error is given at compile time if different names
+are given to subpatterns with the same number. However, you can always give the
+same name to subpatterns with the same number, even when PCRE2_DUPNAMES is not
+set.
+

+
REPETITION

+

+Repetition is specified by quantifiers, which can follow any of the following
+items:
+
+  a literal data character
+  the dot metacharacter
+  the \C escape sequence
+  the \X escape sequence
+  the \R escape sequence
+  an escape such as \d or \pL that matches a single character
+  a character class
+  a back reference
+  a parenthesized subpattern (including most assertions)
+  a subroutine call to a subpattern (recursive or otherwise)
+

+The general repetition quantifier specifies a minimum and maximum number of
+permitted matches, by giving the two numbers in curly brackets (braces),
+separated by a comma. The numbers must be less than 65536, and the first must
+be less than or equal to the second. For example:
+
+  z{2,4}
+

+matches "zz", "zzz", or "zzzz". A closing brace on its own is not a special
+character. If the second number is omitted, but the comma is present, there is
+no upper limit; if the second number and the comma are both omitted, the
+quantifier specifies an exact number of required matches. Thus
+
+  [aeiou]{3,}
+

+matches at least 3 successive vowels, but may match many more, whereas
+
+  \d{8}
+

+matches exactly 8 digits. An opening curly bracket that appears in a position
+where a quantifier is not allowed, or one that does not match the syntax of a
+quantifier, is taken as a literal character. For example, {,6} is not a
+quantifier, but a literal string of four characters.
+

+

+In UTF modes, quantifiers apply to characters rather than to individual code
+units. Thus, for example, \x{100}{2} matches two characters, each of
+which is represented by a two-byte sequence in a UTF-8 string. Similarly,
+\X{3} matches three Unicode extended grapheme clusters, each of which may be
+several code units long (and they may be of different lengths).
+

+

+The quantifier {0} is permitted, causing the expression to behave as if the
+previous item and the quantifier were not present. This may be useful for
+subpatterns that are referenced as
+subroutines
+from elsewhere in the pattern (but see also the section entitled
+"Defining subpatterns for use by reference only"
+below). Items other than subpatterns that have a {0} quantifier are omitted
+from the compiled pattern.
+

+

+For convenience, the three most common quantifiers have single-character
+abbreviations:
+
+  *    is equivalent to {0,}
+  +    is equivalent to {1,}
+  ?    is equivalent to {0,1}
+

+It is possible to construct infinite loops by following a subpattern that can
+match no characters with a quantifier that has no upper limit, for example:
+
+  (a?)*
+

+Earlier versions of Perl and PCRE1 used to give an error at compile time for
+such patterns. However, because there are cases where this can be useful, such
+patterns are now accepted, but if any repetition of the subpattern does in fact
+match no characters, the loop is forcibly broken.
+

+

+By default, the quantifiers are "greedy", that is, they match as much as
+possible (up to the maximum number of permitted times), without causing the
+rest of the pattern to fail. The classic example of where this gives problems
+is in trying to match comments in C programs. These appear between /* and */
+and within the comment, individual * and / characters may appear. An attempt to
+match C comments by applying the pattern
+
+  /\*.*\*/
+

+to the string
+
+  /* first comment */  not comment  /* second comment */
+

+fails, because it matches the entire string owing to the greediness of the .*
+item.
+

+

+If a quantifier is followed by a question mark, it ceases to be greedy, and
+instead matches the minimum number of times possible, so the pattern
+
+  /\*.*?\*/
+

+does the right thing with the C comments. The meaning of the various
+quantifiers is not otherwise changed, just the preferred number of matches.
+Do not confuse this use of question mark with its use as a quantifier in its
+own right. Because it has two uses, it can sometimes appear doubled, as in
+
+  \d??\d
+

+which matches one digit by preference, but can match two if that is the only
+way the rest of the pattern matches.
+

+

+If the PCRE2_UNGREEDY option is set (an option that is not available in Perl),
+the quantifiers are not greedy by default, but individual ones can be made
+greedy by following them with a question mark. In other words, it inverts the
+default behaviour.
+

+

+When a parenthesized subpattern is quantified with a minimum repeat count that
+is greater than 1 or with a limited maximum, more memory is required for the
+compiled pattern, in proportion to the size of the minimum or maximum.
+

+

+If a pattern starts with .* or .{0,} and the PCRE2_DOTALL option (equivalent
+to Perl's /s) is set, thus allowing the dot to match newlines, the pattern is
+implicitly anchored, because whatever follows will be tried against every
+character position in the subject string, so there is no point in retrying the
+overall match at any position after the first. PCRE2 normally treats such a
+pattern as though it were preceded by \A.
+

+

+In cases where it is known that the subject string contains no newlines, it is
+worth setting PCRE2_DOTALL in order to obtain this optimization, or
+alternatively, using ^ to indicate anchoring explicitly.
+

+

+However, there are some cases where the optimization cannot be used. When .*
+is inside capturing parentheses that are the subject of a back reference
+elsewhere in the pattern, a match at the start may fail where a later one
+succeeds. Consider, for example:
+
+  (.*)abc\1
+

+If the subject is "xyz123abc123" the match point is the fourth character. For
+this reason, such a pattern is not implicitly anchored.
+

+

+Another case where implicit anchoring is not applied is when the leading .* is
+inside an atomic group. Once again, a match at the start may fail where a later
+one succeeds. Consider this pattern:
+
+  (?>.*?a)b
+

+It matches "ab" in the subject "aab". The use of the backtracking control verbs
+(*PRUNE) and (*SKIP) also disable this optimization, and there is an option,
+PCRE2_NO_DOTSTAR_ANCHOR, to do so explicitly.
+

+

+When a capturing subpattern is repeated, the value captured is the substring
+that matched the final iteration. For example, after
+
+  (tweedle[dume]{3}\s*)+
+

+has matched "tweedledum tweedledee" the value of the captured substring is
+"tweedledee". However, if there are nested capturing subpatterns, the
+corresponding captured values may have been set in previous iterations. For
+example, after
+
+  (a|(b))+
+

+matches "aba" the value of the second captured substring is "b".
+

+
ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS

+

+With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy")
+repetition, failure of what follows normally causes the repeated item to be
+re-evaluated to see if a different number of repeats allows the rest of the
+pattern to match. Sometimes it is useful to prevent this, either to change the
+nature of the match, or to cause it fail earlier than it otherwise might, when
+the author of the pattern knows there is no point in carrying on.
+

+

+Consider, for example, the pattern \d+foo when applied to the subject line
+
+  123456bar
+

+After matching all 6 digits and then failing to match "foo", the normal
+action of the matcher is to try again with only 5 digits matching the \d+
+item, and then with 4, and so on, before ultimately failing. "Atomic grouping"
+(a term taken from Jeffrey Friedl's book) provides the means for specifying
+that once a subpattern has matched, it is not to be re-evaluated in this way.
+

+

+If we use atomic grouping for the previous example, the matcher gives up
+immediately on failing to match "foo" the first time. The notation is a kind of
+special parenthesis, starting with (?> as in this example:
+
+  (?>\d+)foo
+

+This kind of parenthesis "locks up" the  part of the pattern it contains once
+it has matched, and a failure further into the pattern is prevented from
+backtracking into it. Backtracking past it to previous items, however, works as
+normal.
+

+

+An alternative description is that a subpattern of this type matches exactly
+the string of characters that an identical standalone pattern would match, if
+anchored at the current point in the subject string.
+

+

+Atomic grouping subpatterns are not capturing subpatterns. Simple cases such as
+the above example can be thought of as a maximizing repeat that must swallow
+everything it can. So, while both \d+ and \d+? are prepared to adjust the
+number of digits they match in order to make the rest of the pattern match,
+(?>\d+) can only match an entire sequence of digits.
+

+

+Atomic groups in general can of course contain arbitrarily complicated
+subpatterns, and can be nested. However, when the subpattern for an atomic
+group is just a single repeated item, as in the example above, a simpler
+notation, called a "possessive quantifier" can be used. This consists of an
+additional + character following a quantifier. Using this notation, the
+previous example can be rewritten as
+
+  \d++foo
+

+Note that a possessive quantifier can be used with an entire group, for
+example:
+
+  (abc|xyz){2,3}+
+

+Possessive quantifiers are always greedy; the setting of the PCRE2_UNGREEDY
+option is ignored. They are a convenient notation for the simpler forms of
+atomic group. However, there is no difference in the meaning of a possessive
+quantifier and the equivalent atomic group, though there may be a performance
+difference; possessive quantifiers should be slightly faster.
+

+

+The possessive quantifier syntax is an extension to the Perl 5.8 syntax.
+Jeffrey Friedl originated the idea (and the name) in the first edition of his
+book. Mike McCloskey liked it, so implemented it when he built Sun's Java
+package, and PCRE1 copied it from there. It ultimately found its way into Perl
+at release 5.10.
+

+

+PCRE2 has an optimization that automatically "possessifies" certain simple
+pattern constructs. For example, the sequence A+B is treated as A++B because
+there is no point in backtracking into a sequence of A's when B must follow.
+This feature can be disabled by the PCRE2_NO_AUTOPOSSESS option, or starting
+the pattern with (*NO_AUTO_POSSESS).
+

+

+When a pattern contains an unlimited repeat inside a subpattern that can itself
+be repeated an unlimited number of times, the use of an atomic group is the
+only way to avoid some failing matches taking a very long time indeed. The
+pattern
+
+  (\D+|<\d+>)*[!?]
+

+matches an unlimited number of substrings that either consist of non-digits, or
+digits enclosed in <>, followed by either ! or ?. When it matches, it runs
+quickly. However, if it is applied to
+
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+

+it takes a long time before reporting failure. This is because the string can
+be divided between the internal \D+ repeat and the external * repeat in a
+large number of ways, and all have to be tried. (The example uses [!?] rather
+than a single character at the end, because both PCRE2 and Perl have an
+optimization that allows for fast failure when a single character is used. They
+remember the last single character that is required for a match, and fail early
+if it is not present in the string.) If the pattern is changed so that it uses
+an atomic group, like this:
+
+  ((?>\D+)|<\d+>)*[!?]
+

+sequences of non-digits cannot be broken, and failure happens quickly.
+

+
BACK REFERENCES

+

+Outside a character class, a backslash followed by a digit greater than 0 (and
+possibly further digits) is a back reference to a capturing subpattern earlier
+(that is, to its left) in the pattern, provided there have been that many
+previous capturing left parentheses.
+

+

+However, if the decimal number following the backslash is less than 8, it is
+always taken as a back reference, and causes an error only if there are not
+that many capturing left parentheses in the entire pattern. In other words, the
+parentheses that are referenced need not be to the left of the reference for
+numbers less than 8. A "forward back reference" of this type can make sense
+when a repetition is involved and the subpattern to the right has participated
+in an earlier iteration.
+

+

+It is not possible to have a numerical "forward back reference" to a subpattern
+whose number is 8 or more using this syntax because a sequence such as \50 is
+interpreted as a character defined in octal. See the subsection entitled
+"Non-printing characters"
+above
+for further details of the handling of digits following a backslash. There is
+no such problem when named parentheses are used. A back reference to any
+subpattern is possible using named parentheses (see below).
+

+

+Another way of avoiding the ambiguity inherent in the use of digits following a
+backslash is to use the \g escape sequence. This escape must be followed by an
+unsigned number or a negative number, optionally enclosed in braces. These
+examples are all identical:
+
+  (ring), \1
+  (ring), \g1
+  (ring), \g{1}
+

+An unsigned number specifies an absolute reference without the ambiguity that
+is present in the older syntax. It is also useful when literal digits follow
+the reference. A negative number is a relative reference. Consider this
+example:
+
+  (abc(def)ghi)\g{-1}
+

+The sequence \g{-1} is a reference to the most recently started capturing
+subpattern before \g, that is, is it equivalent to \2 in this example.
+Similarly, \g{-2} would be equivalent to \1. The use of relative references
+can be helpful in long patterns, and also in patterns that are created by
+joining together fragments that contain references within themselves.
+

+

+A back reference matches whatever actually matched the capturing subpattern in
+the current subject string, rather than anything matching the subpattern
+itself (see
+"Subpatterns as subroutines"
+below for a way of doing that). So the pattern
+
+  (sens|respons)e and \1ibility
+

+matches "sense and sensibility" and "response and responsibility", but not
+"sense and responsibility". If caseful matching is in force at the time of the
+back reference, the case of letters is relevant. For example,
+
+  ((?i)rah)\s+\1
+

+matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original
+capturing subpattern is matched caselessly.
+

+

+There are several different ways of writing back references to named
+subpatterns. The .NET syntax \k{name} and the Perl syntax \k<name> or
+\k'name' are supported, as is the Python syntax (?P=name). Perl 5.10's unified
+back reference syntax, in which \g can be used for both numeric and named
+references, is also supported. We could rewrite the above example in any of
+the following ways:
+
+  (?<p1>(?i)rah)\s+\k<p1>
+  (?'p1'(?i)rah)\s+\k{p1}
+  (?P<p1>(?i)rah)\s+(?P=p1)
+  (?<p1>(?i)rah)\s+\g{p1}
+

+A subpattern that is referenced by name may appear in the pattern before or
+after the reference.
+

+

+There may be more than one back reference to the same subpattern. If a
+subpattern has not actually been used in a particular match, any back
+references to it always fail by default. For example, the pattern
+
+  (a|(bc))\2
+

+always fails if it starts to match "a" rather than "bc". However, if the
+PCRE2_MATCH_UNSET_BACKREF option is set at compile time, a back reference to an
+unset value matches an empty string.
+

+

+Because there may be many capturing parentheses in a pattern, all digits
+following a backslash are taken as part of a potential back reference number.
+If the pattern continues with a digit character, some delimiter must be used to
+terminate the back reference. If the PCRE2_EXTENDED option is set, this can be
+white space. Otherwise, the \g{ syntax or an empty comment (see
+"Comments"
+below) can be used.
+

+

+Recursive back references
+

+

+A back reference that occurs inside the parentheses to which it refers fails
+when the subpattern is first used, so, for example, (a\1) never matches.
+However, such references can be useful inside repeated subpatterns. For
+example, the pattern
+
+  (a|b\1)+
+

+matches any number of "a"s and also "aba", "ababbaa" etc. At each iteration of
+the subpattern, the back reference matches the character string corresponding
+to the previous iteration. In order for this to work, the pattern must be such
+that the first iteration does not need to match the back reference. This can be
+done using alternation, as in the example above, or by a quantifier with a
+minimum of zero.
+

+

+Back references of this type cause the group that they reference to be treated
+as an
+atomic group.
+Once the whole group has been matched, a subsequent matching failure cannot
+cause backtracking into the middle of the group.
+

+
ASSERTIONS

+

+An assertion is a test on the characters following or preceding the current
+matching point that does not consume any characters. The simple assertions
+coded as \b, \B, \A, \G, \Z, \z, ^ and $ are described
+above.
+

+

+More complicated assertions are coded as subpatterns. There are two kinds:
+those that look ahead of the current position in the subject string, and those
+that look behind it. An assertion subpattern is matched in the normal way,
+except that it does not cause the current matching position to be changed.
+

+

+Assertion subpatterns are not capturing subpatterns. If such an assertion
+contains capturing subpatterns within it, these are counted for the purposes of
+numbering the capturing subpatterns in the whole pattern. However, substring
+capturing is carried out only for positive assertions. (Perl sometimes, but not
+always, does do capturing in negative assertions.)
+

+

+For compatibility with Perl, most assertion subpatterns may be repeated; though
+it makes no sense to assert the same thing several times, the side effect of
+capturing parentheses may occasionally be useful. However, an assertion that
+forms the condition for a conditional subpattern may not be quantified. In
+practice, for other assertions, there only three cases:
+

+

+(1) If the quantifier is {0}, the assertion is never obeyed during matching.
+However, it may contain internal capturing parenthesized groups that are called
+from elsewhere via the
+subroutine mechanism.
+

+

+(2) If quantifier is {0,n} where n is greater than zero, it is treated as if it
+were {0,1}. At run time, the rest of the pattern match is tried with and
+without the assertion, the order depending on the greediness of the quantifier.
+

+

+(3) If the minimum repetition is greater than zero, the quantifier is ignored.
+The assertion is obeyed just once when encountered during matching.
+

+

+Lookahead assertions
+

+

+Lookahead assertions start with (?= for positive assertions and (?! for
+negative assertions. For example,
+
+  \w+(?=;)
+

+matches a word followed by a semicolon, but does not include the semicolon in
+the match, and
+
+  foo(?!bar)
+

+matches any occurrence of "foo" that is not followed by "bar". Note that the
+apparently similar pattern
+
+  (?!foo)bar
+

+does not find an occurrence of "bar" that is preceded by something other than
+"foo"; it finds any occurrence of "bar" whatsoever, because the assertion
+(?!foo) is always true when the next three characters are "bar". A
+lookbehind assertion is needed to achieve the other effect.
+

+

+If you want to force a matching failure at some point in a pattern, the most
+convenient way to do it is with (?!) because an empty string always matches, so
+an assertion that requires there not to be an empty string must always fail.
+The backtracking control verb (*FAIL) or (*F) is a synonym for (?!).
+

+

+Lookbehind assertions
+

+

+Lookbehind assertions start with (?<= for positive assertions and (?<! for
+negative assertions. For example,
+
+  (?<!foo)bar
+

+does find an occurrence of "bar" that is not preceded by "foo". The contents of
+a lookbehind assertion are restricted such that all the strings it matches must
+have a fixed length. However, if there are several top-level alternatives, they
+do not all have to have the same fixed length. Thus
+
+  (?<=bullock|donkey)
+

+is permitted, but
+
+  (?<!dogs?|cats?)
+

+causes an error at compile time. Branches that match different length strings
+are permitted only at the top level of a lookbehind assertion. This is an
+extension compared with Perl, which requires all branches to match the same
+length of string. An assertion such as
+
+  (?<=ab(c|de))
+

+is not permitted, because its single top-level branch can match two different
+lengths, but it is acceptable to PCRE2 if rewritten to use two top-level
+branches:
+
+  (?<=abc|abde)
+

+In some cases, the escape sequence \K
+(see above)
+can be used instead of a lookbehind assertion to get round the fixed-length
+restriction.
+

+

+The implementation of lookbehind assertions is, for each alternative, to
+temporarily move the current position back by the fixed length and then try to
+match. If there are insufficient characters before the current position, the
+assertion fails.
+

+

+In a UTF mode, PCRE2 does not allow the \C escape (which matches a single code
+unit even in a UTF mode) to appear in lookbehind assertions, because it makes
+it impossible to calculate the length of the lookbehind. The \X and \R
+escapes, which can match different numbers of code units, are also not
+permitted.
+

+

+"Subroutine"
+calls (see below) such as (?2) or (?&X) are permitted in lookbehinds, as long
+as the subpattern matches a fixed-length string.
+Recursion,
+however, is not supported.
+

+

+Possessive quantifiers can be used in conjunction with lookbehind assertions to
+specify efficient matching of fixed-length strings at the end of subject
+strings. Consider a simple pattern such as
+
+  abcd$
+

+when applied to a long string that does not match. Because matching proceeds
+from left to right, PCRE2 will look for each "a" in the subject and then see if
+what follows matches the rest of the pattern. If the pattern is specified as
+
+  ^.*abcd$
+

+the initial .* matches the entire string at first, but when this fails (because
+there is no following "a"), it backtracks to match all but the last character,
+then all but the last two characters, and so on. Once again the search for "a"
+covers the entire string, from right to left, so we are no better off. However,
+if the pattern is written as
+
+  ^.*+(?<=abcd)
+

+there can be no backtracking for the .*+ item because of the possessive
+quantifier; it can match only the entire string. The subsequent lookbehind
+assertion does a single test on the last four characters. If it fails, the
+match fails immediately. For long strings, this approach makes a significant
+difference to the processing time.
+

+

+Using multiple assertions
+

+

+Several assertions (of any sort) may occur in succession. For example,
+
+  (?<=\d{3})(?<!999)foo
+

+matches "foo" preceded by three digits that are not "999". Notice that each of
+the assertions is applied independently at the same point in the subject
+string. First there is a check that the previous three characters are all
+digits, and then there is a check that the same three characters are not "999".
+This pattern does not match "foo" preceded by six characters, the first
+of which are digits and the last three of which are not "999". For example, it
+doesn't match "123abcfoo". A pattern to do that is
+
+  (?<=\d{3}...)(?<!999)foo
+

+This time the first assertion looks at the preceding six characters, checking
+that the first three are digits, and then the second assertion checks that the
+preceding three characters are not "999".
+

+

+Assertions can be nested in any combination. For example,
+
+  (?<=(?<!foo)bar)baz
+

+matches an occurrence of "baz" that is preceded by "bar" which in turn is not
+preceded by "foo", while
+
+  (?<=\d{3}(?!999)...)foo
+

+is another pattern that matches "foo" preceded by three digits and any three
+characters that are not "999".
+

+
CONDITIONAL SUBPATTERNS

+

+It is possible to cause the matching process to obey a subpattern
+conditionally or to choose between two alternative subpatterns, depending on
+the result of an assertion, or whether a specific capturing subpattern has
+already been matched. The two possible forms of conditional subpattern are:
+
+  (?(condition)yes-pattern)
+  (?(condition)yes-pattern|no-pattern)
+

+If the condition is satisfied, the yes-pattern is used; otherwise the
+no-pattern (if present) is used. If there are more than two alternatives in the
+subpattern, a compile-time error occurs. Each of the two alternatives may
+itself contain nested subpatterns of any form, including conditional
+subpatterns; the restriction to two alternatives applies only at the level of
+the condition. This pattern fragment is an example where the alternatives are
+complex:
+
+  (?(1) (A|B|C) | (D | (?(2)E|F) | E) )
+
+

+

+

+There are five kinds of condition: references to subpatterns, references to
+recursion, two pseudo-conditions called DEFINE and VERSION, and assertions.
+

+

+Checking for a used subpattern by number
+

+

+If the text between the parentheses consists of a sequence of digits, the
+condition is true if a capturing subpattern of that number has previously
+matched. If there is more than one capturing subpattern with the same number
+(see the earlier
+section about duplicate subpattern numbers),
+the condition is true if any of them have matched. An alternative notation is
+to precede the digits with a plus or minus sign. In this case, the subpattern
+number is relative rather than absolute. The most recently opened parentheses
+can be referenced by (?(-1), the next most recent by (?(-2), and so on. Inside
+loops it can also make sense to refer to subsequent groups. The next
+parentheses to be opened can be referenced as (?(+1), and so on. (The value
+zero in any of these forms is not used; it provokes a compile-time error.)
+

+

+Consider the following pattern, which contains non-significant white space to
+make it more readable (assume the PCRE2_EXTENDED option) and to divide it into
+three parts for ease of discussion:
+
+  ( \( )?    [^()]+    (?(1) \) )
+

+The first part matches an optional opening parenthesis, and if that
+character is present, sets it as the first captured substring. The second part
+matches one or more characters that are not parentheses. The third part is a
+conditional subpattern that tests whether or not the first set of parentheses
+matched. If they did, that is, if subject started with an opening parenthesis,
+the condition is true, and so the yes-pattern is executed and a closing
+parenthesis is required. Otherwise, since no-pattern is not present, the
+subpattern matches nothing. In other words, this pattern matches a sequence of
+non-parentheses, optionally enclosed in parentheses.
+

+

+If you were embedding this pattern in a larger one, you could use a relative
+reference:
+
+  ...other stuff... ( \( )?    [^()]+    (?(-1) \) ) ...
+

+This makes the fragment independent of the parentheses in the larger pattern.
+

+

+Checking for a used subpattern by name
+

+

+Perl uses the syntax (?(<name>)...) or (?('name')...) to test for a used
+subpattern by name. For compatibility with earlier versions of PCRE1, which had
+this facility before Perl, the syntax (?(name)...) is also recognized.
+

+

+Rewriting the above example to use a named subpattern gives this:
+
+  (?<OPEN> \( )?    [^()]+    (?(<OPEN>) \) )
+

+If the name used in a condition of this kind is a duplicate, the test is
+applied to all subpatterns of the same name, and is true if any one of them has
+matched.
+

+

+Checking for pattern recursion
+

+

+If the condition is the string (R), and there is no subpattern with the name R,
+the condition is true if a recursive call to the whole pattern or any
+subpattern has been made. If digits or a name preceded by ampersand follow the
+letter R, for example:
+
+  (?(R3)...) or (?(R&name)...)
+

+the condition is true if the most recent recursion is into a subpattern whose
+number or name is given. This condition does not check the entire recursion
+stack. If the name used in a condition of this kind is a duplicate, the test is
+applied to all subpatterns of the same name, and is true if any one of them is
+the most recent recursion.
+

+

+At "top level", all these recursion test conditions are false.
+The syntax for recursive patterns
+is described below.
+

+

+Defining subpatterns for use by reference only
+

+

+If the condition is the string (DEFINE), and there is no subpattern with the
+name DEFINE, the condition is always false. In this case, there may be only one
+alternative in the subpattern. It is always skipped if control reaches this
+point in the pattern; the idea of DEFINE is that it can be used to define
+subroutines that can be referenced from elsewhere. (The use of
+subroutines
+is described below.) For example, a pattern to match an IPv4 address such as
+"192.168.23.245" could be written like this (ignore white space and line
+breaks):
+
+  (?(DEFINE) (?<byte> 2[0-4]\d | 25[0-5] | 1\d\d | [1-9]?\d) )
+  \b (?&byte) (\.(?&byte)){3} \b
+

+The first part of the pattern is a DEFINE group inside which a another group
+named "byte" is defined. This matches an individual component of an IPv4
+address (a number less than 256). When matching takes place, this part of the
+pattern is skipped because DEFINE acts like a false condition. The rest of the
+pattern uses references to the named group to match the four dot-separated
+components of an IPv4 address, insisting on a word boundary at each end.
+

+

+Checking the PCRE2 version
+

+

+Programs that link with a PCRE2 library can check the version by calling
+pcre2_config() with appropriate arguments. Users of applications that do
+not have access to the underlying code cannot do this. A special "condition"
+called VERSION exists to allow such users to discover which version of PCRE2
+they are dealing with by using this condition to match a string such as
+"yesno". VERSION must be followed either by "=" or ">=" and a version number.
+For example:
+
+  (?(VERSION>=10.4)yes|no)
+

+This pattern matches "yes" if the PCRE2 version is greater or equal to 10.4, or
+"no" otherwise.
+

+

+Assertion conditions
+

+

+If the condition is not in any of the above formats, it must be an assertion.
+This may be a positive or negative lookahead or lookbehind assertion. Consider
+this pattern, again containing non-significant white space, and with the two
+alternatives on the second line:
+
+  (?(?=[^a-z]*[a-z])
+  \d{2}-[a-z]{3}-\d{2}  |  \d{2}-\d{2}-\d{2} )
+

+The condition is a positive lookahead assertion that matches an optional
+sequence of non-letters followed by a letter. In other words, it tests for the
+presence of at least one letter in the subject. If a letter is found, the
+subject is matched against the first alternative; otherwise it is matched
+against the second. This pattern matches strings in one of the two forms
+dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits.
+

+
COMMENTS

+

+There are two ways of including comments in patterns that are processed by
+PCRE2. In both cases, the start of the comment must not be in a character
+class, nor in the middle of any other sequence of related characters such as
+(?: or a subpattern name or number. The characters that make up a comment play
+no part in the pattern matching.
+

+

+The sequence (?# marks the start of a comment that continues up to the next
+closing parenthesis. Nested parentheses are not permitted. If the
+PCRE2_EXTENDED option is set, an unescaped # character also introduces a
+comment, which in this case continues to immediately after the next newline
+character or character sequence in the pattern. Which characters are
+interpreted as newlines is controlled by an option passed to the compiling
+function or by a special sequence at the start of the pattern, as described in
+the section entitled
+"Newline conventions"
+above. Note that the end of this type of comment is a literal newline sequence
+in the pattern; escape sequences that happen to represent a newline do not
+count. For example, consider this pattern when PCRE2_EXTENDED is set, and the
+default newline convention (a single linefeed character) is in force:
+
+  abc #comment \n still comment
+

+On encountering the # character, pcre2_compile() skips along, looking for
+a newline in the pattern. The sequence \n is still literal at this stage, so
+it does not terminate the comment. Only an actual character with the code value
+0x0a (the default newline) does so.
+

+
RECURSIVE PATTERNS

+

+Consider the problem of matching a string in parentheses, allowing for
+unlimited nested parentheses. Without the use of recursion, the best that can
+be done is to use a pattern that matches up to some fixed depth of nesting. It
+is not possible to handle an arbitrary nesting depth.
+

+

+For some time, Perl has provided a facility that allows regular expressions to
+recurse (amongst other things). It does this by interpolating Perl code in the
+expression at run time, and the code can refer to the expression itself. A Perl
+pattern using code interpolation to solve the parentheses problem can be
+created like this:
+
+  $re = qr{\( (?: (?>[^()]+) | (?p{$re}) )* \)}x;
+

+The (?p{...}) item interpolates Perl code at run time, and in this case refers
+recursively to the pattern in which it appears.
+

+

+Obviously, PCRE2 cannot support the interpolation of Perl code. Instead, it
+supports special syntax for recursion of the entire pattern, and also for
+individual subpattern recursion. After its introduction in PCRE1 and Python,
+this kind of recursion was subsequently introduced into Perl at release 5.10.
+

+

+A special item that consists of (? followed by a number greater than zero and a
+closing parenthesis is a recursive subroutine call of the subpattern of the
+given number, provided that it occurs inside that subpattern. (If not, it is a
+non-recursive subroutine
+call, which is described in the next section.) The special item (?R) or (?0) is
+a recursive call of the entire regular expression.
+

+

+This PCRE2 pattern solves the nested parentheses problem (assume the
+PCRE2_EXTENDED option is set so that white space is ignored):
+
+  \( ( [^()]++ | (?R) )* \)
+

+First it matches an opening parenthesis. Then it matches any number of
+substrings which can either be a sequence of non-parentheses, or a recursive
+match of the pattern itself (that is, a correctly parenthesized substring).
+Finally there is a closing parenthesis. Note the use of a possessive quantifier
+to avoid backtracking into sequences of non-parentheses.
+

+

+If this were part of a larger pattern, you would not want to recurse the entire
+pattern, so instead you could use this:
+
+  ( \( ( [^()]++ | (?1) )* \) )
+

+We have put the pattern into parentheses, and caused the recursion to refer to
+them instead of the whole pattern.
+

+

+In a larger pattern, keeping track of parenthesis numbers can be tricky. This
+is made easier by the use of relative references. Instead of (?1) in the
+pattern above you can write (?-2) to refer to the second most recently opened
+parentheses preceding the recursion. In other words, a negative number counts
+capturing parentheses leftwards from the point at which it is encountered.
+

+

+It is also possible to refer to subsequently opened parentheses, by writing
+references such as (?+2). However, these cannot be recursive because the
+reference is not inside the parentheses that are referenced. They are always
+non-recursive subroutine
+calls, as described in the next section.
+

+

+An alternative approach is to use named parentheses. The Perl syntax for this
+is (?&name); PCRE1's earlier syntax (?P>name) is also supported. We could
+rewrite the above example as follows:
+
+  (?<pn> \( ( [^()]++ | (?&pn) )* \) )
+

+If there is more than one subpattern with the same name, the earliest one is
+used.
+

+

+The example pattern that we have been looking at contains nested unlimited
+repeats, and so the use of a possessive quantifier for matching strings of
+non-parentheses is important when applying the pattern to strings that do not
+match. For example, when this pattern is applied to
+
+  (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa()
+

+it yields "no match" quickly. However, if a possessive quantifier is not used,
+the match runs for a very long time indeed because there are so many different
+ways the + and * repeats can carve up the subject, and all have to be tested
+before failure can be reported.
+

+

+At the end of a match, the values of capturing parentheses are those from
+the outermost level. If you want to obtain intermediate values, a callout
+function can be used (see below and the
+pcre2callout
+documentation). If the pattern above is matched against
+
+  (ab(cd)ef)
+

+the value for the inner capturing parentheses (numbered 2) is "ef", which is
+the last value taken on at the top level. If a capturing subpattern is not
+matched at the top level, its final captured value is unset, even if it was
+(temporarily) set at a deeper level during the matching process.
+

+

+If there are more than 15 capturing parentheses in a pattern, PCRE2 has to
+obtain extra memory from the heap to store data during a recursion. If no
+memory can be obtained, the match fails with the PCRE2_ERROR_NOMEMORY error.
+

+

+Do not confuse the (?R) item with the condition (R), which tests for recursion.
+Consider this pattern, which matches text in angle brackets, allowing for
+arbitrary nesting. Only digits are allowed in nested brackets (that is, when
+recursing), whereas any characters are permitted at the outer level.
+
+  < (?: (?(R) \d++  | [^<>]*+) | (?R)) * >
+

+In this pattern, (?(R) is the start of a conditional subpattern, with two
+different alternatives for the recursive and non-recursive cases. The (?R) item
+is the actual recursive call.
+

+

+Differences in recursion processing between PCRE2 and Perl
+

+

+Recursion processing in PCRE2 differs from Perl in two important ways. In PCRE2
+(like Python, but unlike Perl), a recursive subpattern call is always treated
+as an atomic group. That is, once it has matched some of the subject string, it
+is never re-entered, even if it contains untried alternatives and there is a
+subsequent matching failure. This can be illustrated by the following pattern,
+which purports to match a palindromic string that contains an odd number of
+characters (for example, "a", "aba", "abcba", "abcdcba"):
+
+  ^(.|(.)(?1)\2)$
+

+The idea is that it either matches a single character, or two identical
+characters surrounding a sub-palindrome. In Perl, this pattern works; in PCRE2
+it does not if the pattern is longer than three characters. Consider the
+subject string "abcba":
+

+

+At the top level, the first character is matched, but as it is not at the end
+of the string, the first alternative fails; the second alternative is taken
+and the recursion kicks in. The recursive call to subpattern 1 successfully
+matches the next character ("b"). (Note that the beginning and end of line
+tests are not part of the recursion).
+

+

+Back at the top level, the next character ("c") is compared with what
+subpattern 2 matched, which was "a". This fails. Because the recursion is
+treated as an atomic group, there are now no backtracking points, and so the
+entire match fails. (Perl is able, at this point, to re-enter the recursion and
+try the second alternative.) However, if the pattern is written with the
+alternatives in the other order, things are different:
+
+  ^((.)(?1)\2|.)$
+

+This time, the recursing alternative is tried first, and continues to recurse
+until it runs out of characters, at which point the recursion fails. But this
+time we do have another alternative to try at the higher level. That is the big
+difference: in the previous case the remaining alternative is at a deeper
+recursion level, which PCRE2 cannot use.
+

+

+To change the pattern so that it matches all palindromic strings, not just
+those with an odd number of characters, it is tempting to change the pattern to
+this:
+
+  ^((.)(?1)\2|.?)$
+

+Again, this works in Perl, but not in PCRE2, and for the same reason. When a
+deeper recursion has matched a single character, it cannot be entered again in
+order to match an empty string. The solution is to separate the two cases, and
+write out the odd and even cases as alternatives at the higher level:
+
+  ^(?:((.)(?1)\2|)|((.)(?3)\4|.))
+

+If you want to match typical palindromic phrases, the pattern has to ignore all
+non-word characters, which can be done like this:
+
+  ^\W*+(?:((.)\W*+(?1)\W*+\2|)|((.)\W*+(?3)\W*+\4|\W*+.\W*+))\W*+$
+

+If run with the PCRE2_CASELESS option, this pattern matches phrases such as "A
+man, a plan, a canal: Panama!" and it works in both PCRE2 and Perl. Note the
+use of the possessive quantifier *+ to avoid backtracking into sequences of
+non-word characters. Without this, PCRE2 takes a great deal longer (ten times
+or more) to match typical phrases, and Perl takes so long that you think it has
+gone into a loop.
+

+

+WARNING: The palindrome-matching patterns above work only if the subject
+string does not start with a palindrome that is shorter than the entire string.
+For example, although "abcba" is correctly matched, if the subject is "ababa",
+PCRE2 finds the palindrome "aba" at the start, then fails at top level because
+the end of the string does not follow. Once again, it cannot jump back into the
+recursion to try other alternatives, so the entire match fails.
+

+

+The second way in which PCRE2 and Perl differ in their recursion processing is
+in the handling of captured values. In Perl, when a subpattern is called
+recursively or as a subpattern (see the next section), it has no access to any
+values that were captured outside the recursion, whereas in PCRE2 these values
+can be referenced. Consider this pattern:
+
+  ^(.)(\1|a(?2))
+

+In PCRE2, this pattern matches "bab". The first capturing parentheses match "b",
+then in the second group, when the back reference \1 fails to match "b", the
+second alternative matches "a" and then recurses. In the recursion, \1 does
+now match "b" and so the whole match succeeds. In Perl, the pattern fails to
+match because inside the recursive call \1 cannot access the externally set
+value.
+

+
SUBPATTERNS AS SUBROUTINES

+

+If the syntax for a recursive subpattern call (either by number or by
+name) is used outside the parentheses to which it refers, it operates like a
+subroutine in a programming language. The called subpattern may be defined
+before or after the reference. A numbered reference can be absolute or
+relative, as in these examples:
+
+  (...(absolute)...)...(?2)...
+  (...(relative)...)...(?-1)...
+  (...(?+1)...(relative)...
+

+An earlier example pointed out that the pattern
+
+  (sens|respons)e and \1ibility
+

+matches "sense and sensibility" and "response and responsibility", but not
+"sense and responsibility". If instead the pattern
+
+  (sens|respons)e and (?1)ibility
+

+is used, it does match "sense and responsibility" as well as the other two
+strings. Another example is given in the discussion of DEFINE above.
+

+

+All subroutine calls, whether recursive or not, are always treated as atomic
+groups. That is, once a subroutine has matched some of the subject string, it
+is never re-entered, even if it contains untried alternatives and there is a
+subsequent matching failure. Any capturing parentheses that are set during the
+subroutine call revert to their previous values afterwards.
+

+

+Processing options such as case-independence are fixed when a subpattern is
+defined, so if it is used as a subroutine, such options cannot be changed for
+different calls. For example, consider this pattern:
+
+  (abc)(?i:(?-1))
+

+It matches "abcabc". It does not match "abcABC" because the change of
+processing option does not affect the called subpattern.
+

+
ONIGURUMA SUBROUTINE SYNTAX

+

+For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or
+a number enclosed either in angle brackets or single quotes, is an alternative
+syntax for referencing a subpattern as a subroutine, possibly recursively. Here
+are two of the examples used above, rewritten using this syntax:
+
+  (?<pn> \( ( (?>[^()]+) | \g<pn> )* \) )
+  (sens|respons)e and \g'1'ibility
+

+PCRE2 supports an extension to Oniguruma: if a number is preceded by a
+plus or a minus sign it is taken as a relative reference. For example:
+
+  (abc)(?i:\g<-1>)
+

+Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are not
+synonymous. The former is a back reference; the latter is a subroutine call.
+

+
CALLOUTS

+

+Perl has a feature whereby using the sequence (?{...}) causes arbitrary Perl
+code to be obeyed in the middle of matching a regular expression. This makes it
+possible, amongst other things, to extract different substrings that match the
+same pair of parentheses when there is a repetition.
+

+

+PCRE2 provides a similar feature, but of course it cannot obey arbitrary Perl
+code. The feature is called "callout". The caller of PCRE2 provides an external
+function by putting its entry point in a match context using the function
+pcre2_set_callout(), and then passing that context to pcre2_match()
+or pcre2_dfa_match(). If no match context is passed, or if the callout
+entry point is set to NULL, callouts are disabled.
+

+

+Within a regular expression, (?C<arg>) indicates a point at which the external
+function is to be called. There are two kinds of callout: those with a
+numerical argument and those with a string argument. (?C) on its own with no
+argument is treated as (?C0). A numerical argument allows the application to
+distinguish between different callouts. String arguments were added for release
+10.20 to make it possible for script languages that use PCRE2 to embed short
+scripts within patterns in a similar way to Perl.
+

+

+During matching, when PCRE2 reaches a callout point, the external function is
+called. It is provided with the number or string argument of the callout, the
+position in the pattern, and one item of data that is also set in the match
+block. The callout function may cause matching to proceed, to backtrack, or to
+fail.
+

+

+By default, PCRE2 implements a number of optimizations at matching time, and
+one side-effect is that sometimes callouts are skipped. If you need all
+possible callouts to happen, you need to set options that disable the relevant
+optimizations. More details, including a complete description of the
+programming interface to the callout function, are given in the
+pcre2callout
+documentation.
+

+

+Callouts with numerical arguments
+

+

+If you just want to have a means of identifying different callout points, put a
+number less than 256 after the letter C. For example, this pattern has two
+callout points:
+
+  (?C1)abc(?C2)def
+

+If the PCRE2_AUTO_CALLOUT flag is passed to pcre2_compile(), numerical
+callouts are automatically installed before each item in the pattern. They are
+all numbered 255. If there is a conditional group in the pattern whose
+condition is an assertion, an additional callout is inserted just before the
+condition. An explicit callout may also be set at this position, as in this
+example:
+
+  (?(?C9)(?=a)abc|def)
+

+Note that this applies only to assertion conditions, not to other types of
+condition.
+

+

+Callouts with string arguments
+

+

+A delimited string may be used instead of a number as a callout argument. The
+starting delimiter must be one of ` ' " ^ % # $ { and the ending delimiter is
+the same as the start, except for {, where the ending delimiter is }. If the
+ending delimiter is needed within the string, it must be doubled. For
+example:
+
+  (?C'ab ''c'' d')xyz(?C{any text})pqr
+

+The doubling is removed before the string is passed to the callout function.
+

+
BACKTRACKING CONTROL

+

+Perl 5.10 introduced a number of "Special Backtracking Control Verbs", which
+are still described in the Perl documentation as "experimental and subject to
+change or removal in a future version of Perl". It goes on to say: "Their usage
+in production code should be noted to avoid problems during upgrades." The same
+remarks apply to the PCRE2 features described in this section.
+

+

+The new verbs make use of what was previously invalid syntax: an opening
+parenthesis followed by an asterisk. They are generally of the form
+(*VERB) or (*VERB:NAME). Some may take either form, possibly behaving
+differently depending on whether or not a name is present. A name is any
+sequence of characters that does not include a closing parenthesis. The maximum
+length of name is 255 in the 8-bit library and 65535 in the 16-bit and 32-bit
+libraries. If the name is empty, that is, if the closing parenthesis
+immediately follows the colon, the effect is as if the colon were not there.
+Any number of these verbs may occur in a pattern.
+

+

+Since these verbs are specifically related to backtracking, most of them can be
+used only when the pattern is to be matched using the traditional matching
+function, because these use a backtracking algorithm. With the exception of
+(*FAIL), which behaves like a failing negative assertion, the backtracking
+control verbs cause an error if encountered by the DFA matching function.
+

+

+The behaviour of these verbs in
+repeated groups,
+assertions,
+and in
+subpatterns called as subroutines
+(whether or not recursively) is documented below.
+

+

+Optimizations that affect backtracking verbs
+

+

+PCRE2 contains some optimizations that are used to speed up matching by running
+some checks at the start of each match attempt. For example, it may know the
+minimum length of matching subject, or that a particular character must be
+present. When one of these optimizations bypasses the running of a match, any
+included backtracking verbs will not, of course, be processed. You can suppress
+the start-of-match optimizations by setting the PCRE2_NO_START_OPTIMIZE option
+when calling pcre2_compile(), or by starting the pattern with
+(*NO_START_OPT). There is more discussion of this option in the section
+entitled
+"Compiling a pattern"
+in the
+pcre2api
+documentation.
+

+

+Experiments with Perl suggest that it too has similar optimizations, sometimes
+leading to anomalous results.
+

+

+Verbs that act immediately
+

+

+The following verbs act as soon as they are encountered. They may not be
+followed by a name.
+
+   (*ACCEPT)
+

+This verb causes the match to end successfully, skipping the remainder of the
+pattern. However, when it is inside a subpattern that is called as a
+subroutine, only that subpattern is ended successfully. Matching then continues
+at the outer level. If (*ACCEPT) in triggered in a positive assertion, the
+assertion succeeds; in a negative assertion, the assertion fails.
+

+

+If (*ACCEPT) is inside capturing parentheses, the data so far is captured. For
+example:
+
+  A((?:A|B(*ACCEPT)|C)D)
+

+This matches "AB", "AAD", or "ACD"; when it matches "AB", "B" is captured by
+the outer parentheses.
+
+  (*FAIL) or (*F)
+

+This verb causes a matching failure, forcing backtracking to occur. It is
+equivalent to (?!) but easier to read. The Perl documentation notes that it is
+probably useful only when combined with (?{}) or (??{}). Those are, of course,
+Perl features that are not present in PCRE2. The nearest equivalent is the
+callout feature, as for example in this pattern:
+
+  a+(?C)(*FAIL)
+

+A match with the string "aaaa" always fails, but the callout is taken before
+each backtrack happens (in this example, 10 times).
+

+

+Recording which path was taken
+

+

+There is one verb whose main purpose is to track how a match was arrived at,
+though it also has a secondary use in conjunction with advancing the match
+starting point (see (*SKIP) below).
+
+  (*MARK:NAME) or (*:NAME)
+

+A name is always required with this verb. There may be as many instances of
+(*MARK) as you like in a pattern, and their names do not have to be unique.
+

+

+When a match succeeds, the name of the last-encountered (*MARK:NAME),
+(*PRUNE:NAME), or (*THEN:NAME) on the matching path is passed back to the
+caller as described in the section entitled
+"Other information about the match"
+in the
+pcre2api
+documentation. Here is an example of pcre2test output, where the "mark"
+modifier requests the retrieval and outputting of (*MARK) data:
+
+    re> /X(*MARK:A)Y|X(*MARK:B)Z/mark
+  data> XY
+   0: XY
+  MK: A
+  XZ
+   0: XZ
+  MK: B
+

+The (*MARK) name is tagged with "MK:" in this output, and in this example it
+indicates which of the two alternatives matched. This is a more efficient way
+of obtaining this information than putting each alternative in its own
+capturing parentheses.
+

+

+If a verb with a name is encountered in a positive assertion that is true, the
+name is recorded and passed back if it is the last-encountered. This does not
+happen for negative assertions or failing positive assertions.
+

+

+After a partial match or a failed match, the last encountered name in the
+entire match process is returned. For example:
+
+    re> /X(*MARK:A)Y|X(*MARK:B)Z/mark
+  data> XP
+  No match, mark = B
+

+Note that in this unanchored example the mark is retained from the match
+attempt that started at the letter "X" in the subject. Subsequent match
+attempts starting at "P" and then with an empty string do not get as far as the
+(*MARK) item, but nevertheless do not reset it.
+

+

+If you are interested in (*MARK) values after failed matches, you should
+probably set the PCRE2_NO_START_OPTIMIZE option
+(see above)
+to ensure that the match is always attempted.
+

+

+Verbs that act after backtracking
+

+

+The following verbs do nothing when they are encountered. Matching continues
+with what follows, but if there is no subsequent match, causing a backtrack to
+the verb, a failure is forced. That is, backtracking cannot pass to the left of
+the verb. However, when one of these verbs appears inside an atomic group
+(which includes any group that is called as a subroutine) or in an assertion
+that is true, its effect is confined to that group, because once the group has
+been matched, there is never any backtracking into it. In this situation,
+backtracking has to jump to the left of the entire atomic group or assertion.
+

+

+These verbs differ in exactly what kind of failure occurs when backtracking
+reaches them. The behaviour described below is what happens when the verb is
+not in a subroutine or an assertion. Subsequent sections cover these special
+cases.
+
+  (*COMMIT)
+

+This verb, which may not be followed by a name, causes the whole match to fail
+outright if there is a later matching failure that causes backtracking to reach
+it. Even if the pattern is unanchored, no further attempts to find a match by
+advancing the starting point take place. If (*COMMIT) is the only backtracking
+verb that is encountered, once it has been passed pcre2_match() is
+committed to finding a match at the current starting point, or not at all. For
+example:
+
+  a+(*COMMIT)b
+

+This matches "xxaab" but not "aacaab". It can be thought of as a kind of
+dynamic anchor, or "I've started, so I must finish." The name of the most
+recently passed (*MARK) in the path is passed back when (*COMMIT) forces a
+match failure.
+

+

+If there is more than one backtracking verb in a pattern, a different one that
+follows (*COMMIT) may be triggered first, so merely passing (*COMMIT) during a
+match does not always guarantee that a match must be at this starting point.
+

+

+Note that (*COMMIT) at the start of a pattern is not the same as an anchor,
+unless PCRE2's start-of-match optimizations are turned off, as shown in this
+output from pcre2test:
+
+    re> /(*COMMIT)abc/
+  data> xyzabc
+   0: abc
+  data>
+  re> /(*COMMIT)abc/no_start_optimize
+  data> xyzabc
+  No match
+

+For the first pattern, PCRE2 knows that any match must start with "a", so the
+optimization skips along the subject to "a" before applying the pattern to the
+first set of data. The match attempt then succeeds. The second pattern disables
+the optimization that skips along to the first character. The pattern is now
+applied starting at "x", and so the (*COMMIT) causes the match to fail without
+trying any other starting points.
+
+  (*PRUNE) or (*PRUNE:NAME)
+

+This verb causes the match to fail at the current starting position in the
+subject if there is a later matching failure that causes backtracking to reach
+it. If the pattern is unanchored, the normal "bumpalong" advance to the next
+starting character then happens. Backtracking can occur as usual to the left of
+(*PRUNE), before it is reached, or when matching to the right of (*PRUNE), but
+if there is no match to the right, backtracking cannot cross (*PRUNE). In
+simple cases, the use of (*PRUNE) is just an alternative to an atomic group or
+possessive quantifier, but there are some uses of (*PRUNE) that cannot be
+expressed in any other way. In an anchored pattern (*PRUNE) has the same effect
+as (*COMMIT).
+

+

+The behaviour of (*PRUNE:NAME) is the not the same as (*MARK:NAME)(*PRUNE).
+It is like (*MARK:NAME) in that the name is remembered for passing back to the
+caller. However, (*SKIP:NAME) searches only for names set with (*MARK),
+ignoring those set by (*PRUNE) or (*THEN).
+
+  (*SKIP)
+

+This verb, when given without a name, is like (*PRUNE), except that if the
+pattern is unanchored, the "bumpalong" advance is not to the next character,
+but to the position in the subject where (*SKIP) was encountered. (*SKIP)
+signifies that whatever text was matched leading up to it cannot be part of a
+successful match. Consider:
+
+  a+(*SKIP)b
+

+If the subject is "aaaac...", after the first match attempt fails (starting at
+the first character in the string), the starting point skips on to start the
+next attempt at "c". Note that a possessive quantifer does not have the same
+effect as this example; although it would suppress backtracking during the
+first match attempt, the second attempt would start at the second character
+instead of skipping on to "c".
+
+  (*SKIP:NAME)
+

+When (*SKIP) has an associated name, its behaviour is modified. When it is
+triggered, the previous path through the pattern is searched for the most
+recent (*MARK) that has the same name. If one is found, the "bumpalong" advance
+is to the subject position that corresponds to that (*MARK) instead of to where
+(*SKIP) was encountered. If no (*MARK) with a matching name is found, the
+(*SKIP) is ignored.
+

+

+Note that (*SKIP:NAME) searches only for names set by (*MARK:NAME). It ignores
+names that are set by (*PRUNE:NAME) or (*THEN:NAME).
+
+  (*THEN) or (*THEN:NAME)
+

+This verb causes a skip to the next innermost alternative when backtracking
+reaches it. That is, it cancels any further backtracking within the current
+alternative. Its name comes from the observation that it can be used for a
+pattern-based if-then-else block:
+
+  ( COND1 (*THEN) FOO | COND2 (*THEN) BAR | COND3 (*THEN) BAZ ) ...
+

+If the COND1 pattern matches, FOO is tried (and possibly further items after
+the end of the group if FOO succeeds); on failure, the matcher skips to the
+second alternative and tries COND2, without backtracking into COND1. If that
+succeeds and BAR fails, COND3 is tried. If subsequently BAZ fails, there are no
+more alternatives, so there is a backtrack to whatever came before the entire
+group. If (*THEN) is not inside an alternation, it acts like (*PRUNE).
+

+

+The behaviour of (*THEN:NAME) is the not the same as (*MARK:NAME)(*THEN).
+It is like (*MARK:NAME) in that the name is remembered for passing back to the
+caller. However, (*SKIP:NAME) searches only for names set with (*MARK),
+ignoring those set by (*PRUNE) and (*THEN).
+

+

+A subpattern that does not contain a | character is just a part of the
+enclosing alternative; it is not a nested alternation with only one
+alternative. The effect of (*THEN) extends beyond such a subpattern to the
+enclosing alternative. Consider this pattern, where A, B, etc. are complex
+pattern fragments that do not contain any | characters at this level:
+
+  A (B(*THEN)C) | D
+

+If A and B are matched, but there is a failure in C, matching does not
+backtrack into A; instead it moves to the next alternative, that is, D.
+However, if the subpattern containing (*THEN) is given an alternative, it
+behaves differently:
+
+  A (B(*THEN)C | (*FAIL)) | D
+

+The effect of (*THEN) is now confined to the inner subpattern. After a failure
+in C, matching moves to (*FAIL), which causes the whole subpattern to fail
+because there are no more alternatives to try. In this case, matching does now
+backtrack into A.
+

+

+Note that a conditional subpattern is not considered as having two
+alternatives, because only one is ever used. In other words, the | character in
+a conditional subpattern has a different meaning. Ignoring white space,
+consider:
+
+  ^.*? (?(?=a) a | b(*THEN)c )
+

+If the subject is "ba", this pattern does not match. Because .*? is ungreedy,
+it initially matches zero characters. The condition (?=a) then fails, the
+character "b" is matched, but "c" is not. At this point, matching does not
+backtrack to .*? as might perhaps be expected from the presence of the |
+character. The conditional subpattern is part of the single alternative that
+comprises the whole pattern, and so the match fails. (If there was a backtrack
+into .*?, allowing it to match "b", the match would succeed.)
+

+

+The verbs just described provide four different "strengths" of control when
+subsequent matching fails. (*THEN) is the weakest, carrying on the match at the
+next alternative. (*PRUNE) comes next, failing the match at the current
+starting position, but allowing an advance to the next character (for an
+unanchored pattern). (*SKIP) is similar, except that the advance may be more
+than one character. (*COMMIT) is the strongest, causing the entire match to
+fail.
+

+

+More than one backtracking verb
+

+

+If more than one backtracking verb is present in a pattern, the one that is
+backtracked onto first acts. For example, consider this pattern, where A, B,
+etc. are complex pattern fragments:
+
+  (A(*COMMIT)B(*THEN)C|ABD)
+

+If A matches but B fails, the backtrack to (*COMMIT) causes the entire match to
+fail. However, if A and B match, but C fails, the backtrack to (*THEN) causes
+the next alternative (ABD) to be tried. This behaviour is consistent, but is
+not always the same as Perl's. It means that if two or more backtracking verbs
+appear in succession, all the the last of them has no effect. Consider this
+example:
+
+  ...(*COMMIT)(*PRUNE)...
+

+If there is a matching failure to the right, backtracking onto (*PRUNE) causes
+it to be triggered, and its action is taken. There can never be a backtrack
+onto (*COMMIT).
+

+

+Backtracking verbs in repeated groups
+

+

+PCRE2 differs from Perl in its handling of backtracking verbs in repeated
+groups. For example, consider:
+
+  /(a(*COMMIT)b)+ac/
+

+If the subject is "abac", Perl matches, but PCRE2 fails because the (*COMMIT)
+in the second repeat of the group acts.
+

+

+Backtracking verbs in assertions
+

+

+(*FAIL) in an assertion has its normal effect: it forces an immediate
+backtrack.
+

+

+(*ACCEPT) in a positive assertion causes the assertion to succeed without any
+further processing. In a negative assertion, (*ACCEPT) causes the assertion to
+fail without any further processing.
+

+

+The other backtracking verbs are not treated specially if they appear in a
+positive assertion. In particular, (*THEN) skips to the next alternative in the
+innermost enclosing group that has alternations, whether or not this is within
+the assertion.
+

+

+Negative assertions are, however, different, in order to ensure that changing a
+positive assertion into a negative assertion changes its result. Backtracking
+into (*COMMIT), (*SKIP), or (*PRUNE) causes a negative assertion to be true,
+without considering any further alternative branches in the assertion.
+Backtracking into (*THEN) causes it to skip to the next enclosing alternative
+within the assertion (the normal behaviour), but if the assertion does not have
+such an alternative, (*THEN) behaves like (*PRUNE).
+

+

+Backtracking verbs in subroutines
+

+

+These behaviours occur whether or not the subpattern is called recursively.
+Perl's treatment of subroutines is different in some cases.
+

+

+(*FAIL) in a subpattern called as a subroutine has its normal effect: it forces
+an immediate backtrack.
+

+

+(*ACCEPT) in a subpattern called as a subroutine causes the subroutine match to
+succeed without any further processing. Matching then continues after the
+subroutine call.
+

+

+(*COMMIT), (*SKIP), and (*PRUNE) in a subpattern called as a subroutine cause
+the subroutine match to fail.
+

+

+(*THEN) skips to the next alternative in the innermost enclosing group within
+the subpattern that has alternatives. If there is no such group within the
+subpattern, (*THEN) causes the subroutine match to fail.
+

+
SEE ALSO

+

+pcre2api(3), pcre2callout(3), pcre2matching(3),
+pcre2syntax(3), pcre2(3).
+

+
AUTHOR

+

+Philip Hazel
+

+University Computing Service
+

+Cambridge, England.
+

+

+
REVISION

+

+Last updated: 13 June 2015
+

+Copyright © 1997-2015 University of Cambridge.
+

+

+Return to the PCRE2 index page.
+

diff --git a/pcre2-10.20/doc/html/pcre2perform.html b/pcre2-10.20/doc/html/pcre2perform.html
new file mode 100644
index 000000000..3b6a4a6c8
--- /dev/null
+++ b/pcre2-10.20/doc/html/pcre2perform.html
@@ -0,0 +1,201 @@
+
+
+pcre2perform specification
+
+
+
pcre2perform man page

+

+Return to the PCRE2 index page.
+

+

+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+

+

+PCRE2 PERFORMANCE
+

+

+Two aspects of performance are discussed below: memory usage and processing
+time. The way you express your pattern as a regular expression can affect both
+of them.
+

+

+COMPILED PATTERN MEMORY USAGE
+

+

+Patterns are compiled by PCRE2 into a reasonably efficient interpretive code,
+so that most simple patterns do not use much memory. However, there is one case
+where the memory usage of a compiled pattern can be unexpectedly large. If a
+parenthesized subpattern has a quantifier with a minimum greater than 1 and/or
+a limited maximum, the whole subpattern is repeated in the compiled code. For
+example, the pattern
+
+  (abc|def){2,4}
+

+is compiled as if it were
+
+  (abc|def)(abc|def)((abc|def)(abc|def)?)?
+

+(Technical aside: It is done this way so that backtrack points within each of
+the repetitions can be independently maintained.)
+

+

+For regular expressions whose quantifiers use only small numbers, this is not
+usually a problem. However, if the numbers are large, and particularly if such
+repetitions are nested, the memory usage can become an embarrassment. For
+example, the very simple pattern
+
+  ((ab){1,1000}c){1,3}
+

+uses 51K bytes when compiled using the 8-bit library. When PCRE2 is compiled
+with its default internal pointer size of two bytes, the size limit on a
+compiled pattern is 64K code units in the 8-bit and 16-bit libraries, and this
+is reached with the above pattern if the outer repetition is increased from 3
+to 4. PCRE2 can be compiled to use larger internal pointers and thus handle
+larger compiled patterns, but it is better to try to rewrite your pattern to
+use less memory if you can.
+

+

+One way of reducing the memory usage for such patterns is to make use of
+PCRE2's
+"subroutine"
+facility. Re-writing the above pattern as
+
+  ((ab)(?2){0,999}c)(?1){0,2}
+

+reduces the memory requirements to 18K, and indeed it remains under 20K even
+with the outer repetition increased to 100. However, this pattern is not
+exactly equivalent, because the "subroutine" calls are treated as
+atomic groups
+into which there can be no backtracking if there is a subsequent matching
+failure. Therefore, PCRE2 cannot do this kind of rewriting automatically.
+Furthermore, there is a noticeable loss of speed when executing the modified
+pattern. Nevertheless, if the atomic grouping is not a problem and the loss of
+speed is acceptable, this kind of rewriting will allow you to process patterns
+that PCRE2 cannot otherwise handle.
+

+

+STACK USAGE AT RUN TIME
+

+

+When pcre2_match() is used for matching, certain kinds of pattern can
+cause it to use large amounts of the process stack. In some environments the
+default process stack is quite small, and if it runs out the result is often
+SIGSEGV. Rewriting your pattern can often help. The
+pcre2stack
+documentation discusses this issue in detail.
+

+

+PROCESSING TIME
+

+

+Certain items in regular expression patterns are processed more efficiently
+than others. It is more efficient to use a character class like [aeiou] than a
+set of single-character alternatives such as (a|e|i|o|u). In general, the
+simplest construction that provides the required behaviour is usually the most
+efficient. Jeffrey Friedl's book contains a lot of useful general discussion
+about optimizing regular expressions for efficient performance. This document
+contains a few observations about PCRE2.
+

+

+Using Unicode character properties (the \p, \P, and \X escapes) is slow,
+because PCRE2 has to use a multi-stage table lookup whenever it needs a
+character's property. If you can find an alternative pattern that does not use
+character properties, it will probably be faster.
+

+

+By default, the escape sequences \b, \d, \s, and \w, and the POSIX
+character classes such as [:alpha:] do not use Unicode properties, partly for
+backwards compatibility, and partly for performance reasons. However, you can
+set the PCRE2_UCP option or start the pattern with (*UCP) if you want Unicode
+character properties to be used. This can double the matching time for items
+such as \d, when matched with pcre2_match(); the performance loss is
+less with a DFA matching function, and in both cases there is not much
+difference for \b.
+

+

+When a pattern begins with .* not in atomic parentheses, nor in parentheses
+that are the subject of a backreference, and the PCRE2_DOTALL option is set,
+the pattern is implicitly anchored by PCRE2, since it can match only at the
+start of a subject string. If the pattern has multiple top-level branches, they
+must all be anchorable. The optimization can be disabled by the
+PCRE2_NO_DOTSTAR_ANCHOR option, and is automatically disabled if the pattern
+contains (*PRUNE) or (*SKIP).
+

+

+If PCRE2_DOTALL is not set, PCRE2 cannot make this optimization, because the
+dot metacharacter does not then match a newline, and if the subject string
+contains newlines, the pattern may match from the character immediately
+following one of them instead of from the very start. For example, the pattern
+
+  .*second
+

+matches the subject "first\nand second" (where \n stands for a newline
+character), with the match starting at the seventh character. In order to do
+this, PCRE2 has to retry the match starting after every newline in the subject.
+

+

+If you are using such a pattern with subject strings that do not contain
+newlines, the best performance is obtained by setting PCRE2_DOTALL, or starting
+the pattern with ^.* or ^.*? to indicate explicit anchoring. That saves PCRE2
+from having to scan along the subject looking for a newline to restart at.
+

+

+Beware of patterns that contain nested indefinite repeats. These can take a
+long time to run when applied to a string that does not match. Consider the
+pattern fragment
+
+  ^(a+)*
+

+This can match "aaaa" in 16 different ways, and this number increases very
+rapidly as the string gets longer. (The * repeat can match 0, 1, 2, 3, or 4
+times, and for each of those cases other than 0 or 4, the + repeats can match
+different numbers of times.) When the remainder of the pattern is such that the
+entire match is going to fail, PCRE2 has in principle to try every possible
+variation, and this can take an extremely long time, even for relatively short
+strings.
+

+

+An optimization catches some of the more simple cases such as
+
+  (a+)*b
+

+where a literal character follows. Before embarking on the standard matching
+procedure, PCRE2 checks that there is a "b" later in the subject string, and if
+there is not, it fails the match immediately. However, when there is no
+following literal this optimization cannot be used. You can see the difference
+by comparing the behaviour of
+
+  (a+)*\d
+

+with the pattern above. The former gives a failure almost instantly when
+applied to a whole line of "a" characters, whereas the latter takes an
+appreciable time with strings longer than about 20 characters.
+

+

+In many cases, the solution to this kind of performance issue is to use an
+atomic group or a possessive quantifier.
+

+

+AUTHOR
+

+

+Philip Hazel
+

+University Computing Service
+

+Cambridge, England.
+

+

+

+REVISION
+

+

+Last updated: 02 January 2015
+

+Copyright © 1997-2015 University of Cambridge.
+

+

+Return to the PCRE2 index page.
+

diff --git a/pcre2-10.20/doc/html/pcre2posix.html b/pcre2-10.20/doc/html/pcre2posix.html
new file mode 100644
index 000000000..5e4b5a3b4
--- /dev/null
+++ b/pcre2-10.20/doc/html/pcre2posix.html
@@ -0,0 +1,292 @@
+
+
+pcre2posix specification
+
+
+
pcre2posix man page

+

+Return to the PCRE2 index page.
+

+

+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+

+

+
SYNOPSIS

+

+#include <pcre2posix.h>
+

+

+int regcomp(regex_t *preg, const char *pattern,
+     int cflags);
+

+

+int regexec(const regex_t *preg, const char *string,
+     size_t nmatch, regmatch_t pmatch[], int eflags);
+

+

+size_t regerror(int errcode, const regex_t *preg,
+     char *errbuf, size_t errbuf_size);
+

+

+void regfree(regex_t *preg);
+

+
DESCRIPTION

+

+This set of functions provides a POSIX-style API for the PCRE2 regular
+expression 8-bit library. See the
+pcre2api
+documentation for a description of PCRE2's native API, which contains much
+additional functionality. There is no POSIX-style wrapper for PCRE2's 16-bit
+and 32-bit libraries.
+

+

+The functions described here are just wrapper functions that ultimately call
+the PCRE2 native API. Their prototypes are defined in the pcre2posix.h
+header file, and on Unix systems the library itself is called
+libpcre2-posix.a, so can be accessed by adding -lpcre2-posix to the
+command for linking an application that uses them. Because the POSIX functions
+call the native ones, it is also necessary to add -lpcre2-8.
+

+

+Those POSIX option bits that can reasonably be mapped to PCRE2 native options
+have been implemented. In addition, the option REG_EXTENDED is defined with the
+value zero. This has no effect, but since programs that are written to the
+POSIX interface often use it, this makes it easier to slot in PCRE2 as a
+replacement library. Other POSIX options are not even defined.
+

+

+There are also some other options that are not defined by POSIX. These have
+been added at the request of users who want to make use of certain
+PCRE2-specific features via the POSIX calling interface.
+

+

+When PCRE2 is called via these functions, it is only the API that is POSIX-like
+in style. The syntax and semantics of the regular expressions themselves are
+still those of Perl, subject to the setting of various PCRE2 options, as
+described below. "POSIX-like in style" means that the API approximates to the
+POSIX definition; it is not fully POSIX-compatible, and in multi-unit encoding
+domains it is probably even less compatible.
+

+

+The header for these functions is supplied as pcre2posix.h to avoid any
+potential clash with other POSIX libraries. It can, of course, be renamed or
+aliased as regex.h, which is the "correct" name. It provides two
+structure types, regex_t for compiled internal forms, and
+regmatch_t for returning captured substrings. It also defines some
+constants whose names start with "REG_"; these are used for setting options and
+identifying error codes.
+

+
COMPILING A PATTERN

+

+The function regcomp() is called to compile a pattern into an
+internal form. The pattern is a C string terminated by a binary zero, and
+is passed in the argument pattern. The preg argument is a pointer
+to a regex_t structure that is used as a base for storing information
+about the compiled regular expression.
+

+

+The argument cflags is either zero, or contains one or more of the bits
+defined by the following macros:
+
+  REG_DOTALL
+

+The PCRE2_DOTALL option is set when the regular expression is passed for
+compilation to the native function. Note that REG_DOTALL is not part of the
+POSIX standard.
+
+  REG_ICASE
+

+The PCRE2_CASELESS option is set when the regular expression is passed for
+compilation to the native function.
+
+  REG_NEWLINE
+

+The PCRE2_MULTILINE option is set when the regular expression is passed for
+compilation to the native function. Note that this does not mimic the
+defined POSIX behaviour for REG_NEWLINE (see the following section).
+
+  REG_NOSUB
+

+The PCRE2_NO_AUTO_CAPTURE option is set when the regular expression is passed
+for compilation to the native function. In addition, when a pattern that is
+compiled with this flag is passed to regexec() for matching, the
+nmatch and pmatch arguments are ignored, and no captured strings
+are returned.
+
+  REG_UCP
+

+The PCRE2_UCP option is set when the regular expression is passed for
+compilation to the native function. This causes PCRE2 to use Unicode properties
+when matchine \d, \w, etc., instead of just recognizing ASCII values. Note
+that REG_UCP is not part of the POSIX standard.
+
+  REG_UNGREEDY
+

+The PCRE2_UNGREEDY option is set when the regular expression is passed for
+compilation to the native function. Note that REG_UNGREEDY is not part of the
+POSIX standard.
+
+  REG_UTF
+

+The PCRE2_UTF option is set when the regular expression is passed for
+compilation to the native function. This causes the pattern itself and all data
+strings used for matching it to be treated as UTF-8 strings. Note that REG_UTF
+is not part of the POSIX standard.
+

+

+In the absence of these flags, no options are passed to the native function.
+This means the the regex is compiled with PCRE2 default semantics. In
+particular, the way it handles newline characters in the subject string is the
+Perl way, not the POSIX way. Note that setting PCRE2_MULTILINE has only
+some of the effects specified for REG_NEWLINE. It does not affect the way
+newlines are matched by the dot metacharacter (they are not) or by a negative
+class such as [^a] (they are).
+

+

+The yield of regcomp() is zero on success, and non-zero otherwise. The
+preg structure is filled in on success, and one member of the structure
+is public: re_nsub contains the number of capturing subpatterns in
+the regular expression. Various error codes are defined in the header file.
+

+

+NOTE: If the yield of regcomp() is non-zero, you must not attempt to
+use the contents of the preg structure. If, for example, you pass it to
+regexec(), the result is undefined and your program is likely to crash.
+

+
MATCHING NEWLINE CHARACTERS

+

+This area is not simple, because POSIX and Perl take different views of things.
+It is not possible to get PCRE2 to obey POSIX semantics, but then PCRE2 was
+never intended to be a POSIX engine. The following table lists the different
+possibilities for matching newline characters in PCRE2:
+
+                          Default   Change with
+
+  . matches newline          no     PCRE2_DOTALL
+  newline matches [^a]       yes    not changeable
+  $ matches \n at end        yes    PCRE2_DOLLAR_ENDONLY
+  $ matches \n in middle     no     PCRE2_MULTILINE
+  ^ matches \n in middle     no     PCRE2_MULTILINE
+

+This is the equivalent table for POSIX:
+
+                          Default   Change with
+
+  . matches newline          yes    REG_NEWLINE
+  newline matches [^a]       yes    REG_NEWLINE
+  $ matches \n at end        no     REG_NEWLINE
+  $ matches \n in middle     no     REG_NEWLINE
+  ^ matches \n in middle     no     REG_NEWLINE
+

+PCRE2's behaviour is the same as Perl's, except that there is no equivalent for
+PCRE2_DOLLAR_ENDONLY in Perl. In both PCRE2 and Perl, there is no way to stop
+newline from matching [^a].
+

+

+The default POSIX newline handling can be obtained by setting PCRE2_DOTALL and
+PCRE2_DOLLAR_ENDONLY, but there is no way to make PCRE2 behave exactly as for
+the REG_NEWLINE action.
+

+
MATCHING A PATTERN

+

+The function regexec() is called to match a compiled pattern preg
+against a given string, which is by default terminated by a zero byte
+(but see REG_STARTEND below), subject to the options in eflags. These can
+be:
+
+  REG_NOTBOL
+

+The PCRE2_NOTBOL option is set when calling the underlying PCRE2 matching
+function.
+
+  REG_NOTEMPTY
+

+The PCRE2_NOTEMPTY option is set when calling the underlying PCRE2 matching
+function. Note that REG_NOTEMPTY is not part of the POSIX standard. However,
+setting this option can give more POSIX-like behaviour in some situations.
+
+  REG_NOTEOL
+

+The PCRE2_NOTEOL option is set when calling the underlying PCRE2 matching
+function.
+
+  REG_STARTEND
+

+The string is considered to start at string + pmatch[0].rm_so and
+to have a terminating NUL located at string + pmatch[0].rm_eo
+(there need not actually be a NUL at that location), regardless of the value of
+nmatch. This is a BSD extension, compatible with but not specified by
+IEEE Standard 1003.2 (POSIX.2), and should be used with caution in software
+intended to be portable to other systems. Note that a non-zero rm_so does
+not imply REG_NOTBOL; REG_STARTEND affects only the location of the string, not
+how it is matched.
+

+

+If the pattern was compiled with the REG_NOSUB flag, no data about any matched
+strings is returned. The nmatch and pmatch arguments of
+regexec() are ignored.
+

+

+If the value of nmatch is zero, or if the value pmatch is NULL,
+no data about any matched strings is returned.
+

+

+Otherwise,the portion of the string that was matched, and also any captured
+substrings, are returned via the pmatch argument, which points to an
+array of nmatch structures of type regmatch_t, containing the
+members rm_so and rm_eo. These contain the byte offset to the first
+character of each substring and the offset to the first character after the end
+of each substring, respectively. The 0th element of the vector relates to the
+entire portion of string that was matched; subsequent elements relate to
+the capturing subpatterns of the regular expression. Unused entries in the
+array have both structure members set to -1.
+

+

+A successful match yields a zero return; various error codes are defined in the
+header file, of which REG_NOMATCH is the "expected" failure code.
+

+
ERROR MESSAGES

+

+The regerror() function maps a non-zero errorcode from either
+regcomp() or regexec() to a printable message. If preg is not
+NULL, the error should have arisen from the use of that structure. A message
+terminated by a binary zero is placed in errbuf. The length of the
+message, including the zero, is limited to errbuf_size. The yield of the
+function is the size of buffer needed to hold the whole message.
+

+
MEMORY USAGE

+

+Compiling a regular expression causes memory to be allocated and associated
+with the preg structure. The function regfree() frees all such
+memory, after which preg may no longer be used as a compiled expression.
+

+
AUTHOR

+

+Philip Hazel
+

+University Computing Service
+

+Cambridge, England.
+

+

+
REVISION

+

+Last updated: 20 October 2014
+

+Copyright © 1997-2014 University of Cambridge.
+

+

+Return to the PCRE2 index page.
+

diff --git a/pcre2-10.20/doc/html/pcre2sample.html b/pcre2-10.20/doc/html/pcre2sample.html
new file mode 100644
index 000000000..60a928bcc
--- /dev/null
+++ b/pcre2-10.20/doc/html/pcre2sample.html
@@ -0,0 +1,106 @@
+
+
+pcre2sample specification
+
+
+
pcre2sample man page

+

+Return to the PCRE2 index page.
+

+

+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+

+

+PCRE2 SAMPLE PROGRAM
+

+

+A simple, complete demonstration program to get you started with using PCRE2 is
+supplied in the file pcre2demo.c in the src directory in the PCRE2
+distribution. A listing of this program is given in the
+pcre2demo
+documentation. If you do not have a copy of the PCRE2 distribution, you can
+save this listing to re-create the contents of pcre2demo.c.
+

+

+The demonstration program, which uses the PCRE2 8-bit library, compiles the
+regular expression that is its first argument, and matches it against the
+subject string in its second argument. No PCRE2 options are set, and default
+character tables are used. If matching succeeds, the program outputs the
+portion of the subject that matched, together with the contents of any captured
+substrings.
+

+

+If the -g option is given on the command line, the program then goes on to
+check for further matches of the same regular expression in the same subject
+string. The logic is a little bit tricky because of the possibility of matching
+an empty string. Comments in the code explain what is going on.
+

+

+If PCRE2 is installed in the standard include and library directories for your
+operating system, you should be able to compile the demonstration program using
+this command:
+
+  gcc -o pcre2demo pcre2demo.c -lpcre2-8
+

+If PCRE2 is installed elsewhere, you may need to add additional options to the
+command line. For example, on a Unix-like system that has PCRE2 installed in
+/usr/local, you can compile the demonstration program using a command
+like this:
+
+  gcc -o pcre2demo -I/usr/local/include pcre2demo.c -L/usr/local/lib -lpcre2-8
+
+

+

+

+Once you have compiled and linked the demonstration program, you can run simple
+tests like this:
+
+  ./pcre2demo 'cat|dog' 'the cat sat on the mat'
+  ./pcre2demo -g 'cat|dog' 'the dog sat on the cat'
+

+Note that there is a much more comprehensive test program, called
+pcre2test,
+which supports many more facilities for testing regular expressions using the
+PCRE2 libraries. The
+pcre2demo
+program is provided as a simple coding example.
+

+

+If you try to run
+pcre2demo
+when PCRE2 is not installed in the standard library directory, you may get an
+error like this on some operating systems (e.g. Solaris):
+
+  ld.so.1: a.out: fatal: libpcre2.so.0: open failed: No such file or directory
+

+This is caused by the way shared library support works on those systems. You
+need to add
+
+  -R/usr/local/lib
+

+(for example) to the compile command to get round this problem.
+

+

+AUTHOR
+

+

+Philip Hazel
+

+University Computing Service
+

+Cambridge, England.
+

+

+

+REVISION
+

+

+Last updated: 20 October 2014
+

+Copyright © 1997-2014 University of Cambridge.
+

+

+Return to the PCRE2 index page.
+

diff --git a/pcre2-10.20/doc/html/pcre2serialize.html b/pcre2-10.20/doc/html/pcre2serialize.html
new file mode 100644
index 000000000..c32ebe034
--- /dev/null
+++ b/pcre2-10.20/doc/html/pcre2serialize.html
@@ -0,0 +1,184 @@
+
+
+pcre2serialize specification
+
+
+
pcre2serialize man page

+

+Return to the PCRE2 index page.
+

+

+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+

+

+
SAVING AND RE-USING PRECOMPILED PCRE2 PATTERNS

+

+int32_t pcre2_serialize_decode(pcre2_code **codes,
+  int32_t number_of_codes, const uint32_t *bytes,
+  pcre2_general_context *gcontext);
+

+

+int32_t pcre2_serialize_encode(pcre2_code **codes,
+  int32_t number_of_codes, uint32_t **serialized_bytes,
+  PCRE2_SIZE *serialized_size, pcre2_general_context *gcontext);
+

+

+void pcre2_serialize_free(uint8_t *bytes);
+

+

+int32_t pcre2_serialize_get_number_of_codes(const uint8_t *bytes);
+

+

+If you are running an application that uses a large number of regular
+expression patterns, it may be useful to store them in a precompiled form
+instead of having to compile them every time the application is run. However,
+if you are using the just-in-time optimization feature, it is not possible to
+save and reload the JIT data, because it is position-dependent. In addition,
+the host on which the patterns are reloaded must be running the same version of
+PCRE2, with the same code unit width, and must also have the same endianness,
+pointer width and PCRE2_SIZE type. For example, patterns compiled on a 32-bit
+system using PCRE2's 16-bit library cannot be reloaded on a 64-bit system, nor
+can they be reloaded using the 8-bit library.
+

+
SAVING COMPILED PATTERNS

+

+Before compiled patterns can be saved they must be serialized, that is,
+converted to a stream of bytes. A single byte stream may contain any number of
+compiled patterns, but they must all use the same character tables. A single
+copy of the tables is included in the byte stream (its size is 1088 bytes). For
+more details of character tables, see the
+section on locale support
+in the
+pcre2api
+documentation.
+

+

+The function pcre2_serialize_encode() creates a serialized byte stream
+from a list of compiled patterns. Its first two arguments specify the list,
+being a pointer to a vector of pointers to compiled patterns, and the length of
+the vector. The third and fourth arguments point to variables which are set to
+point to the created byte stream and its length, respectively. The final
+argument is a pointer to a general context, which can be used to specify custom
+memory mangagement functions. If this argument is NULL, malloc() is used
+to obtain memory for the byte stream. The yield of the function is the number
+of serialized patterns, or one of the following negative error codes:
+
+  PCRE2_ERROR_BADDATA      the number of patterns is zero or less
+  PCRE2_ERROR_BADMAGIC     mismatch of id bytes in one of the patterns
+  PCRE2_ERROR_MEMORY       memory allocation failed
+  PCRE2_ERROR_MIXEDTABLES  the patterns do not all use the same tables
+  PCRE2_ERROR_NULL         the 1st, 3rd, or 4th argument is NULL
+

+PCRE2_ERROR_BADMAGIC means either that a pattern's code has been corrupted, or
+that a slot in the vector does not point to a compiled pattern.
+

+

+Once a set of patterns has been serialized you can save the data in any
+appropriate manner. Here is sample code that compiles two patterns and writes
+them to a file. It assumes that the variable fd refers to a file that is
+open for output. The error checking that should be present in a real
+application has been omitted for simplicity.
+
+  int errorcode;
+  uint8_t *bytes;
+  PCRE2_SIZE erroroffset;
+  PCRE2_SIZE bytescount;
+  pcre2_code *list_of_codes[2];
+  list_of_codes[0] = pcre2_compile("first pattern",
+    PCRE2_ZERO_TERMINATED, 0, &errorcode, &erroroffset, NULL);
+  list_of_codes[1] = pcre2_compile("second pattern",
+    PCRE2_ZERO_TERMINATED, 0, &errorcode, &erroroffset, NULL);
+  errorcode = pcre2_serialize_encode(list_of_codes, 2, &bytes,
+    &bytescount, NULL);
+  errorcode = fwrite(bytes, 1, bytescount, fd);
+

+Note that the serialized data is binary data that may contain any of the 256
+possible byte values. On systems that make a distinction between binary and
+non-binary data, be sure that the file is opened for binary output.
+

+

+Serializing a set of patterns leaves the original data untouched, so they can
+still be used for matching. Their memory must eventually be freed in the usual
+way by calling pcre2_code_free(). When you have finished with the byte
+stream, it too must be freed by calling pcre2_serialize_free().
+

+
RE-USING PRECOMPILED PATTERNS

+

+In order to re-use a set of saved patterns you must first make the serialized
+byte stream available in main memory (for example, by reading from a file). The
+management of this memory block is up to the application. You can use the
+pcre2_serialize_get_number_of_codes() function to find out how many
+compiled patterns are in the serialized data without actually decoding the
+patterns:
+
+  uint8_t *bytes = <serialized data>;
+  int32_t number_of_codes = pcre2_serialize_get_number_of_codes(bytes);
+

+The pcre2_serialize_decode() function reads a byte stream and recreates
+the compiled patterns in new memory blocks, setting pointers to them in a
+vector. The first two arguments are a pointer to a suitable vector and its
+length, and the third argument points to a byte stream. The final argument is a
+pointer to a general context, which can be used to specify custom memory
+mangagement functions for the decoded patterns. If this argument is NULL,
+malloc() and free() are used. After deserialization, the byte
+stream is no longer needed and can be discarded.
+
+  int32_t number_of_codes;
+  pcre2_code *list_of_codes[2];
+  uint8_t *bytes = <serialized data>;
+  int32_t number_of_codes =
+    pcre2_serialize_decode(list_of_codes, 2, bytes, NULL);
+

+If the vector is not large enough for all the patterns in the byte stream, it
+is filled with those that fit, and the remainder are ignored. The yield of the
+function is the number of decoded patterns, or one of the following negative
+error codes:
+
+  PCRE2_ERROR_BADDATA   second argument is zero or less
+  PCRE2_ERROR_BADMAGIC  mismatch of id bytes in the data
+  PCRE2_ERROR_BADMODE   mismatch of variable unit size or PCRE2 version
+  PCRE2_ERROR_MEMORY    memory allocation failed
+  PCRE2_ERROR_NULL      first or third argument is NULL
+

+PCRE2_ERROR_BADMAGIC may mean that the data is corrupt, or that it was compiled
+on a system with different endianness.
+

+

+Decoded patterns can be used for matching in the usual way, and must be freed
+by calling pcre2_code_free() as normal. A single copy of the character
+tables is used by all the decoded patterns. A reference count is used to
+arrange for its memory to be automatically freed when the last pattern is
+freed.
+

+

+If a pattern was processed by pcre2_jit_compile() before being
+serialized, the JIT data is discarded and so is no longer available after a
+save/restore cycle. You can, however, process a restored pattern with
+pcre2_jit_compile() if you wish.
+

+
AUTHOR

+

+Philip Hazel
+

+University Computing Service
+

+Cambridge, England.
+

+

+
REVISION

+

+Last updated: 20 January 2015
+

+Copyright © 1997-2015 University of Cambridge.
+

+

+Return to the PCRE2 index page.
+

diff --git a/pcre2-10.20/doc/html/pcre2stack.html b/pcre2-10.20/doc/html/pcre2stack.html
new file mode 100644
index 000000000..2942c7a7a
--- /dev/null
+++ b/pcre2-10.20/doc/html/pcre2stack.html
@@ -0,0 +1,207 @@
+
+
+pcre2stack specification
+
+
+
pcre2stack man page

+

+Return to the PCRE2 index page.
+

+

+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+

+

+PCRE2 DISCUSSION OF STACK USAGE
+

+

+When you call pcre2_match(), it makes use of an internal function called
+match(). This calls itself recursively at branch points in the pattern,
+in order to remember the state of the match so that it can back up and try a
+different alternative after a failure. As matching proceeds deeper and deeper
+into the tree of possibilities, the recursion depth increases. The
+match() function is also called in other circumstances, for example,
+whenever a parenthesized sub-pattern is entered, and in certain cases of
+repetition.
+

+

+Not all calls of match() increase the recursion depth; for an item such
+as a* it may be called several times at the same level, after matching
+different numbers of a's. Furthermore, in a number of cases where the result of
+the recursive call would immediately be passed back as the result of the
+current call (a "tail recursion"), the function is just restarted instead.
+

+

+Each time the internal match() function is called recursively, it uses
+memory from the process stack. For certain kinds of pattern and data, very
+large amounts of stack may be needed, despite the recognition of "tail
+recursion". Note that if PCRE2 is compiled with the -fsanitize=address option
+of the GCC compiler, the stack requirements are greatly increased.
+

+

+The above comments apply when pcre2_match() is run in its normal
+interpretive manner. If the compiled pattern was processed by
+pcre2_jit_compile(), and just-in-time compiling was successful, and the
+options passed to pcre2_match() were not incompatible, the matching
+process uses the JIT-compiled code instead of the match() function. In
+this case, the memory requirements are handled entirely differently. See the
+pcre2jit
+documentation for details.
+

+

+The pcre2_dfa_match() function operates in a different way to
+pcre2_match(), and uses recursion only when there is a regular expression
+recursion or subroutine call in the pattern. This includes the processing of
+assertion and "once-only" subpatterns, which are handled like subroutine calls.
+Normally, these are never very deep, and the limit on the complexity of
+pcre2_dfa_match() is controlled by the amount of workspace it is given.
+However, it is possible to write patterns with runaway infinite recursions;
+such patterns will cause pcre2_dfa_match() to run out of stack. At
+present, there is no protection against this.
+

+

+The comments that follow do NOT apply to pcre2_dfa_match(); they are
+relevant only for pcre2_match() without the JIT optimization.
+

+

+Reducing pcre2_match()'s stack usage
+

+

+You can often reduce the amount of recursion, and therefore the
+amount of stack used, by modifying the pattern that is being matched. Consider,
+for example, this pattern:
+
+  ([^<]|<(?!inet))+
+

+It matches from wherever it starts until it encounters "<inet" or the end of
+the data, and is the kind of pattern that might be used when processing an XML
+file. Each iteration of the outer parentheses matches either one character that
+is not "<" or a "<" that is not followed by "inet". However, each time a
+parenthesis is processed, a recursion occurs, so this formulation uses a stack
+frame for each matched character. For a long string, a lot of stack is
+required. Consider now this rewritten pattern, which matches exactly the same
+strings:
+
+  ([^<]++|<(?!inet))+
+

+This uses very much less stack, because runs of characters that do not contain
+"<" are "swallowed" in one item inside the parentheses. Recursion happens only
+when a "<" character that is not followed by "inet" is encountered (and we
+assume this is relatively rare). A possessive quantifier is used to stop any
+backtracking into the runs of non-"<" characters, but that is not related to
+stack usage.
+

+

+This example shows that one way of avoiding stack problems when matching long
+subject strings is to write repeated parenthesized subpatterns to match more
+than one character whenever possible.
+

+

+Compiling PCRE2 to use heap instead of stack for pcre2_match()
+

+

+In environments where stack memory is constrained, you might want to compile
+PCRE2 to use heap memory instead of stack for remembering back-up points when
+pcre2_match() is running. This makes it run more slowly, however. Details
+of how to do this are given in the
+pcre2build
+documentation. When built in this way, instead of using the stack, PCRE2
+gets memory for remembering backup points from the heap. By default, the memory
+is obtained by calling the system malloc() function, but you can arrange
+to supply your own memory management function. For details, see the section
+entitled
+"The match context"
+in the
+pcre2api
+documentation. Since the block sizes are always the same, it may be possible to
+implement customized a memory handler that is more efficient than the standard
+function. The memory blocks obtained for this purpose are retained and re-used
+if possible while pcre2_match() is running. They are all freed just
+before it exits.
+

+

+Limiting pcre2_match()'s stack usage
+

+

+You can set limits on the number of times the internal match() function
+is called, both in total and recursively. If a limit is exceeded,
+pcre2_match() returns an error code. Setting suitable limits should
+prevent it from running out of stack. The default values of the limits are very
+large, and unlikely ever to operate. They can be changed when PCRE2 is built,
+and they can also be set when pcre2_match() is called. For details of
+these interfaces, see the
+pcre2build
+documentation and the section entitled
+"The match context"
+in the
+pcre2api
+documentation.
+

+

+As a very rough rule of thumb, you should reckon on about 500 bytes per
+recursion. Thus, if you want to limit your stack usage to 8Mb, you should set
+the limit at 16000 recursions. A 64Mb stack, on the other hand, can support
+around 128000 recursions.
+

+

+The pcre2test test program has a modifier called "find_limits" which, if
+applied to a subject line, causes it to find the smallest limits that allow a a
+pattern to match. This is done by calling pcre2_match() repeatedly with
+different limits.
+

+

+Changing stack size in Unix-like systems
+

+

+In Unix-like environments, there is not often a problem with the stack unless
+very long strings are involved, though the default limit on stack size varies
+from system to system. Values from 8Mb to 64Mb are common. You can find your
+default limit by running the command:
+
+  ulimit -s
+

+Unfortunately, the effect of running out of stack is often SIGSEGV, though
+sometimes a more explicit error message is given. You can normally increase the
+limit on stack size by code such as this:
+
+  struct rlimit rlim;
+  getrlimit(RLIMIT_STACK, &rlim);
+  rlim.rlim_cur = 100*1024*1024;
+  setrlimit(RLIMIT_STACK, &rlim);
+

+This reads the current limits (soft and hard) using getrlimit(), then
+attempts to increase the soft limit to 100Mb using setrlimit(). You must
+do this before calling pcre2_match().
+

+

+Changing stack size in Mac OS X
+

+

+Using setrlimit(), as described above, should also work on Mac OS X. It
+is also possible to set a stack size when linking a program. There is a
+discussion about stack sizes in Mac OS X at this web site:
+http://developer.apple.com/qa/qa2005/qa1419.html.
+

+

+AUTHOR
+

+

+Philip Hazel
+

+University Computing Service
+

+Cambridge, England.
+

+

+

+REVISION
+

+

+Last updated: 21 November 2014
+

+Copyright © 1997-2014 University of Cambridge.
+

+

+Return to the PCRE2 index page.
+

diff --git a/pcre2-10.20/doc/html/pcre2syntax.html b/pcre2-10.20/doc/html/pcre2syntax.html
new file mode 100644
index 000000000..28ba02362
--- /dev/null
+++ b/pcre2-10.20/doc/html/pcre2syntax.html
@@ -0,0 +1,591 @@
+
+
+pcre2syntax specification
+
+
+
pcre2syntax man page

+

+Return to the PCRE2 index page.
+

+

+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+

+

+
PCRE2 REGULAR EXPRESSION SYNTAX SUMMARY

+

+The full syntax and semantics of the regular expressions that are supported by
+PCRE2 are described in the
+pcre2pattern
+documentation. This document contains a quick-reference summary of the syntax.
+

+
QUOTING

+

+
+  \x         where x is non-alphanumeric is a literal x
+  \Q...\E    treat enclosed characters as literal
+

+

+
ESCAPED CHARACTERS

+

+This table applies to ASCII and Unicode environments.
+
+  \a         alarm, that is, the BEL character (hex 07)
+  \cx        "control-x", where x is any ASCII printing character
+  \e         escape (hex 1B)
+  \f         form feed (hex 0C)
+  \n         newline (hex 0A)
+  \r         carriage return (hex 0D)
+  \t         tab (hex 09)
+  \0dd       character with octal code 0dd
+  \ddd       character with octal code ddd, or backreference
+  \o{ddd..}  character with octal code ddd..
+  \U         "U" if PCRE2_ALT_BSUX is set (otherwise is an error)
+  \uhhhh     character with hex code hhhh (if PCRE2_ALT_BSUX is set)
+  \xhh       character with hex code hh
+  \x{hhh..}  character with hex code hhh..
+

+Note that \0dd is always an octal code. The treatment of backslash followed by
+a non-zero digit is complicated; for details see the section
+"Non-printing characters"
+in the
+pcre2pattern
+documentation, where details of escape processing in EBCDIC environments are
+also given.
+

+

+When \x is not followed by {, from zero to two hexadecimal digits are read,
+but if PCRE2_ALT_BSUX is set, \x must be followed by two hexadecimal digits to
+be recognized as a hexadecimal escape; otherwise it matches a literal "x".
+Likewise, if \u (in ALT_BSUX mode) is not followed by four hexadecimal digits,
+it matches a literal "u".
+

+
CHARACTER TYPES

+

+
+  .          any character except newline;
+               in dotall mode, any character whatsoever
+  \C         one code unit, even in UTF mode (best avoided)
+  \d         a decimal digit
+  \D         a character that is not a decimal digit
+  \h         a horizontal white space character
+  \H         a character that is not a horizontal white space character
+  \N         a character that is not a newline
+  \p{xx}     a character with the xx property
+  \P{xx}     a character without the xx property
+  \R         a newline sequence
+  \s         a white space character
+  \S         a character that is not a white space character
+  \v         a vertical white space character
+  \V         a character that is not a vertical white space character
+  \w         a "word" character
+  \W         a "non-word" character
+  \X         a Unicode extended grapheme cluster
+

+The application can lock out the use of \C by setting the
+PCRE2_NEVER_BACKSLASH_C option. It is dangerous because it may leave the
+current matching point in the middle of a UTF-8 or UTF-16 character.
+

+

+By default, \d, \s, and \w match only ASCII characters, even in UTF-8 mode
+or in the 16-bit and 32-bit libraries. However, if locale-specific matching is
+happening, \s and \w may also match characters with code points in the range
+128-255. If the PCRE2_UCP option is set, the behaviour of these escape
+sequences is changed to use Unicode properties and they match many more
+characters.
+

+
GENERAL CATEGORY PROPERTIES FOR \p and \P

+

+
+  C          Other
+  Cc         Control
+  Cf         Format
+  Cn         Unassigned
+  Co         Private use
+  Cs         Surrogate
+
+  L          Letter
+  Ll         Lower case letter
+  Lm         Modifier letter
+  Lo         Other letter
+  Lt         Title case letter
+  Lu         Upper case letter
+  L&         Ll, Lu, or Lt
+
+  M          Mark
+  Mc         Spacing mark
+  Me         Enclosing mark
+  Mn         Non-spacing mark
+
+  N          Number
+  Nd         Decimal number
+  Nl         Letter number
+  No         Other number
+
+  P          Punctuation
+  Pc         Connector punctuation
+  Pd         Dash punctuation
+  Pe         Close punctuation
+  Pf         Final punctuation
+  Pi         Initial punctuation
+  Po         Other punctuation
+  Ps         Open punctuation
+
+  S          Symbol
+  Sc         Currency symbol
+  Sk         Modifier symbol
+  Sm         Mathematical symbol
+  So         Other symbol
+
+  Z          Separator
+  Zl         Line separator
+  Zp         Paragraph separator
+  Zs         Space separator
+

+

+
PCRE2 SPECIAL CATEGORY PROPERTIES FOR \p and \P

+

+
+  Xan        Alphanumeric: union of properties L and N
+  Xps        POSIX space: property Z or tab, NL, VT, FF, CR
+  Xsp        Perl space: property Z or tab, NL, VT, FF, CR
+  Xuc        Univerally-named character: one that can be
+               represented by a Universal Character Name
+  Xwd        Perl word: property Xan or underscore
+

+Perl and POSIX space are now the same. Perl added VT to its space character set
+at release 5.18.
+

+
SCRIPT NAMES FOR \p AND \P

+

+Arabic,
+Armenian,
+Avestan,
+Balinese,
+Bamum,
+Bassa_Vah,
+Batak,
+Bengali,
+Bopomofo,
+Brahmi,
+Braille,
+Buginese,
+Buhid,
+Canadian_Aboriginal,
+Carian,
+Caucasian_Albanian,
+Chakma,
+Cham,
+Cherokee,
+Common,
+Coptic,
+Cuneiform,
+Cypriot,
+Cyrillic,
+Deseret,
+Devanagari,
+Duployan,
+Egyptian_Hieroglyphs,
+Elbasan,
+Ethiopic,
+Georgian,
+Glagolitic,
+Gothic,
+Grantha,
+Greek,
+Gujarati,
+Gurmukhi,
+Han,
+Hangul,
+Hanunoo,
+Hebrew,
+Hiragana,
+Imperial_Aramaic,
+Inherited,
+Inscriptional_Pahlavi,
+Inscriptional_Parthian,
+Javanese,
+Kaithi,
+Kannada,
+Katakana,
+Kayah_Li,
+Kharoshthi,
+Khmer,
+Khojki,
+Khudawadi,
+Lao,
+Latin,
+Lepcha,
+Limbu,
+Linear_A,
+Linear_B,
+Lisu,
+Lycian,
+Lydian,
+Mahajani,
+Malayalam,
+Mandaic,
+Manichaean,
+Meetei_Mayek,
+Mende_Kikakui,
+Meroitic_Cursive,
+Meroitic_Hieroglyphs,
+Miao,
+Modi,
+Mongolian,
+Mro,
+Myanmar,
+Nabataean,
+New_Tai_Lue,
+Nko,
+Ogham,
+Ol_Chiki,
+Old_Italic,
+Old_North_Arabian,
+Old_Permic,
+Old_Persian,
+Old_South_Arabian,
+Old_Turkic,
+Oriya,
+Osmanya,
+Pahawh_Hmong,
+Palmyrene,
+Pau_Cin_Hau,
+Phags_Pa,
+Phoenician,
+Psalter_Pahlavi,
+Rejang,
+Runic,
+Samaritan,
+Saurashtra,
+Sharada,
+Shavian,
+Siddham,
+Sinhala,
+Sora_Sompeng,
+Sundanese,
+Syloti_Nagri,
+Syriac,
+Tagalog,
+Tagbanwa,
+Tai_Le,
+Tai_Tham,
+Tai_Viet,
+Takri,
+Tamil,
+Telugu,
+Thaana,
+Thai,
+Tibetan,
+Tifinagh,
+Tirhuta,
+Ugaritic,
+Vai,
+Warang_Citi,
+Yi.
+

+
CHARACTER CLASSES

+

+
+  [...]       positive character class
+  [^...]      negative character class
+  [x-y]       range (can be used for hex characters)
+  [[:xxx:]]   positive POSIX named set
+  [[:^xxx:]]  negative POSIX named set
+
+  alnum       alphanumeric
+  alpha       alphabetic
+  ascii       0-127
+  blank       space or tab
+  cntrl       control character
+  digit       decimal digit
+  graph       printing, excluding space
+  lower       lower case letter
+  print       printing, including space
+  punct       printing, excluding alphanumeric
+  space       white space
+  upper       upper case letter
+  word        same as \w
+  xdigit      hexadecimal digit
+

+In PCRE2, POSIX character set names recognize only ASCII characters by default,
+but some of them use Unicode properties if PCRE2_UCP is set. You can use
+\Q...\E inside a character class.
+

+
QUANTIFIERS

+

+
+  ?           0 or 1, greedy
+  ?+          0 or 1, possessive
+  ??          0 or 1, lazy
+  *           0 or more, greedy
+  *+          0 or more, possessive
+  *?          0 or more, lazy
+  +           1 or more, greedy
+  ++          1 or more, possessive
+  +?          1 or more, lazy
+  {n}         exactly n
+  {n,m}       at least n, no more than m, greedy
+  {n,m}+      at least n, no more than m, possessive
+  {n,m}?      at least n, no more than m, lazy
+  {n,}        n or more, greedy
+  {n,}+       n or more, possessive
+  {n,}?       n or more, lazy
+

+

+
ANCHORS AND SIMPLE ASSERTIONS

+

+
+  \b          word boundary
+  \B          not a word boundary
+  ^           start of subject
+                also after an internal newline in multiline mode
+                (after any newline if PCRE2_ALT_CIRCUMFLEX is set)
+  \A          start of subject
+  $           end of subject
+                also before newline at end of subject
+                also before internal newline in multiline mode
+  \Z          end of subject
+                also before newline at end of subject
+  \z          end of subject
+  \G          first matching position in subject
+

+

+
MATCH POINT RESET

+

+
+  \K          reset start of match
+

+\K is honoured in positive assertions, but ignored in negative ones.
+

+
ALTERNATION

+

+
+  expr|expr|expr...
+

+

+
CAPTURING

+

+
+  (...)           capturing group
+  (?<name>...)    named capturing group (Perl)
+  (?'name'...)    named capturing group (Perl)
+  (?P<name>...)   named capturing group (Python)
+  (?:...)         non-capturing group
+  (?|...)         non-capturing group; reset group numbers for
+                   capturing groups in each alternative
+

+

+
ATOMIC GROUPS

+

+
+  (?>...)         atomic, non-capturing group
+

+

+
COMMENT

+

+
+  (?#....)        comment (not nestable)
+

+

+
OPTION SETTING

+

+
+  (?i)            caseless
+  (?J)            allow duplicate names
+  (?m)            multiline
+  (?s)            single line (dotall)
+  (?U)            default ungreedy (lazy)
+  (?x)            extended (ignore white space)
+  (?-...)         unset option(s)
+

+The following are recognized only at the very start of a pattern or after one
+of the newline or \R options with similar syntax. More than one of them may
+appear.
+
+  (*LIMIT_MATCH=d) set the match limit to d (decimal number)
+  (*LIMIT_RECURSION=d) set the recursion limit to d (decimal number)
+  (*NOTEMPTY)     set PCRE2_NOTEMPTY when matching
+  (*NOTEMPTY_ATSTART) set PCRE2_NOTEMPTY_ATSTART when matching
+  (*NO_AUTO_POSSESS) no auto-possessification (PCRE2_NO_AUTO_POSSESS)
+  (*NO_DOTSTAR_ANCHOR) no .* anchoring (PCRE2_NO_DOTSTAR_ANCHOR)
+  (*NO_JIT)       disable JIT optimization
+  (*NO_START_OPT) no start-match optimization (PCRE2_NO_START_OPTIMIZE)
+  (*UTF)          set appropriate UTF mode for the library in use
+  (*UCP)          set PCRE2_UCP (use Unicode properties for \d etc)
+

+Note that LIMIT_MATCH and LIMIT_RECURSION can only reduce the value of the
+limits set by the caller of pcre2_match(), not increase them. The application
+can lock out the use of (*UTF) and (*UCP) by setting the PCRE2_NEVER_UTF or
+PCRE2_NEVER_UCP options, respectively, at compile time.
+

+
NEWLINE CONVENTION

+

+These are recognized only at the very start of the pattern or after option
+settings with a similar syntax.
+
+  (*CR)           carriage return only
+  (*LF)           linefeed only
+  (*CRLF)         carriage return followed by linefeed
+  (*ANYCRLF)      all three of the above
+  (*ANY)          any Unicode newline sequence
+

+

+
WHAT \R MATCHES

+

+These are recognized only at the very start of the pattern or after option
+setting with a similar syntax.
+
+  (*BSR_ANYCRLF)  CR, LF, or CRLF
+  (*BSR_UNICODE)  any Unicode newline sequence
+

+

+
LOOKAHEAD AND LOOKBEHIND ASSERTIONS

+

+
+  (?=...)         positive look ahead
+  (?!...)         negative look ahead
+  (?<=...)        positive look behind
+  (?<!...)        negative look behind
+

+Each top-level branch of a look behind must be of a fixed length.
+

+
BACKREFERENCES

+

+
+  \n              reference by number (can be ambiguous)
+  \gn             reference by number
+  \g{n}           reference by number
+  \g{-n}          relative reference by number
+  \k<name>        reference by name (Perl)
+  \k'name'        reference by name (Perl)
+  \g{name}        reference by name (Perl)
+  \k{name}        reference by name (.NET)
+  (?P=name)       reference by name (Python)
+

+

+
SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)

+

+
+  (?R)            recurse whole pattern
+  (?n)            call subpattern by absolute number
+  (?+n)           call subpattern by relative number
+  (?-n)           call subpattern by relative number
+  (?&name)        call subpattern by name (Perl)
+  (?P>name)       call subpattern by name (Python)
+  \g<name>        call subpattern by name (Oniguruma)
+  \g'name'        call subpattern by name (Oniguruma)
+  \g<n>           call subpattern by absolute number (Oniguruma)
+  \g'n'           call subpattern by absolute number (Oniguruma)
+  \g<+n>          call subpattern by relative number (PCRE2 extension)
+  \g'+n'          call subpattern by relative number (PCRE2 extension)
+  \g<-n>          call subpattern by relative number (PCRE2 extension)
+  \g'-n'          call subpattern by relative number (PCRE2 extension)
+

+

+
CONDITIONAL PATTERNS

+

+
+  (?(condition)yes-pattern)
+  (?(condition)yes-pattern|no-pattern)
+
+  (?(n)               absolute reference condition
+  (?(+n)              relative reference condition
+  (?(-n)              relative reference condition
+  (?(<name>)          named reference condition (Perl)
+  (?('name')          named reference condition (Perl)
+  (?(name)            named reference condition (PCRE2)
+  (?(R)               overall recursion condition
+  (?(Rn)              specific group recursion condition
+  (?(R&name)          specific recursion condition
+  (?(DEFINE)          define subpattern for reference
+  (?(VERSION[>]=n.m)  test PCRE2 version
+  (?(assert)          assertion condition
+

+

+
BACKTRACKING CONTROL

+

+The following act immediately they are reached:
+
+  (*ACCEPT)       force successful match
+  (*FAIL)         force backtrack; synonym (*F)
+  (*MARK:NAME)    set name to be passed back; synonym (*:NAME)
+

+The following act only when a subsequent match failure causes a backtrack to
+reach them. They all force a match failure, but they differ in what happens
+afterwards. Those that advance the start-of-match point do so only if the
+pattern is not anchored.
+
+  (*COMMIT)       overall failure, no advance of starting point
+  (*PRUNE)        advance to next starting character
+  (*PRUNE:NAME)   equivalent to (*MARK:NAME)(*PRUNE)
+  (*SKIP)         advance to current matching position
+  (*SKIP:NAME)    advance to position corresponding to an earlier
+                  (*MARK:NAME); if not found, the (*SKIP) is ignored
+  (*THEN)         local failure, backtrack to next alternation
+  (*THEN:NAME)    equivalent to (*MARK:NAME)(*THEN)
+

+

+
CALLOUTS

+

+
+  (?C)            callout (assumed number 0)
+  (?Cn)           callout with numerical data n
+  (?C"text")      callout with string data
+

+The allowed string delimiters are ` ' " ^ % # $ (which are the same for the
+start and the end), and the starting delimiter { matched with the ending
+delimiter }. To encode the ending delimiter within the string, double it.
+

+
SEE ALSO

+

+pcre2pattern(3), pcre2api(3), pcre2callout(3),
+pcre2matching(3), pcre2(3).
+

+
AUTHOR

+

+Philip Hazel
+

+University Computing Service
+

+Cambridge, England.
+

+

+
REVISION

+

+Last updated: 13 June 2015
+

+Copyright © 1997-2015 University of Cambridge.
+

+

+Return to the PCRE2 index page.
+

diff --git a/pcre2-10.20/doc/html/pcre2test.html b/pcre2-10.20/doc/html/pcre2test.html
new file mode 100644
index 000000000..5165c1e54
--- /dev/null
+++ b/pcre2-10.20/doc/html/pcre2test.html
@@ -0,0 +1,1478 @@
+
+
+pcre2test specification
+
+
+
pcre2test man page

+

+Return to the PCRE2 index page.
+

+

+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+

+

+
SYNOPSIS

+

+pcre2test [options] [input file [output file]]
+

+

+pcre2test is a test program for the PCRE2 regular expression libraries,
+but it can also be used for experimenting with regular expressions. This
+document describes the features of the test program; for details of the regular
+expressions themselves, see the
+pcre2pattern
+documentation. For details of the PCRE2 library function calls and their
+options, see the
+pcre2api
+documentation.
+

+

+The input for pcre2test is a sequence of regular expression patterns and
+subject strings to be matched. There are also command lines for setting
+defaults and controlling some special actions. The output shows the result of
+each match attempt. Modifiers on external or internal command lines, the
+patterns, and the subject lines specify PCRE2 function options, control how the
+subject is processed, and what output is produced.
+

+

+As the original fairly simple PCRE library evolved, it acquired many different
+features, and as a result, the original pcretest program ended up with a
+lot of options in a messy, arcane syntax, for testing all the features. The
+move to the new PCRE2 API provided an opportunity to re-implement the test
+program as pcre2test, with a cleaner modifier syntax. Nevertheless, there
+are still many obscure modifiers, some of which are specifically designed for
+use in conjunction with the test script and data files that are distributed as
+part of PCRE2. All the modifiers are documented here, some without much
+justification, but many of them are unlikely to be of use except when testing
+the libraries.
+

+
PCRE2's 8-BIT, 16-BIT AND 32-BIT LIBRARIES

+

+Different versions of the PCRE2 library can be built to support character
+strings that are encoded in 8-bit, 16-bit, or 32-bit code units. One, two, or
+all three of these libraries may be simultaneously installed. The
+pcre2test program can be used to test all the libraries. However, its own
+input and output are always in 8-bit format. When testing the 16-bit or 32-bit
+libraries, patterns and subject strings are converted to 16- or 32-bit format
+before being passed to the library functions. Results are converted back to
+8-bit code units for output.
+

+

+In the rest of this document, the names of library functions and structures
+are given in generic form, for example, pcre_compile(). The actual
+names used in the libraries have a suffix _8, _16, or _32, as appropriate.
+

+
INPUT ENCODING

+

+Input to pcre2test is processed line by line, either by calling the C
+library's fgets() function, or via the libreadline library (see
+below). The input is processed using using C's string functions, so must not
+contain binary zeroes, even though in Unix-like environments, fgets()
+treats any bytes other than newline as data characters. In some Windows
+environments character 26 (hex 1A) causes an immediate end of file, and no
+further data is read.
+

+

+For maximum portability, therefore, it is safest to avoid non-printing
+characters in pcre2test input files. There is a facility for specifying a
+pattern's characters as hexadecimal pairs, thus making it possible to include
+binary zeroes in a pattern for testing purposes. Subject lines are processed
+for backslash escapes, which makes it possible to include any data value.
+

+
COMMAND LINE OPTIONS

+

+-8
+If the 8-bit library has been built, this option causes it to be used (this is
+the default). If the 8-bit library has not been built, this option causes an
+error.
+

+

+-16
+If the 16-bit library has been built, this option causes it to be used. If only
+the 16-bit library has been built, this is the default. If the 16-bit library
+has not been built, this option causes an error.
+

+

+-32
+If the 32-bit library has been built, this option causes it to be used. If only
+the 32-bit library has been built, this is the default. If the 32-bit library
+has not been built, this option causes an error.
+

+

+-b
+Behave as if each pattern has the /fullbincode modifier; the full
+internal binary form of the pattern is output after compilation.
+

+

+-C
+Output the version number of the PCRE2 library, and all available information
+about the optional features that are included, and then exit with zero exit
+code. All other options are ignored.
+

+

+-C option
+Output information about a specific build-time option, then exit. This
+functionality is intended for use in scripts such as RunTest. The
+following options output the value and set the exit code as indicated:
+
+  ebcdic-nl  the code for LF (= NL) in an EBCDIC environment:
+               0x15 or 0x25
+               0 if used in an ASCII environment
+               exit code is always 0
+  linksize   the configured internal link size (2, 3, or 4)
+               exit code is set to the link size
+  newline    the default newline setting:
+               CR, LF, CRLF, ANYCRLF, or ANY
+               exit code is always 0
+  bsr        the default setting for what \R matches:
+               ANYCRLF or ANY
+               exit code is always 0
+

+The following options output 1 for true or 0 for false, and set the exit code
+to the same value:
+
+  ebcdic     compiled for an EBCDIC environment
+  jit        just-in-time support is available
+  pcre2-16   the 16-bit library was built
+  pcre2-32   the 32-bit library was built
+  pcre2-8    the 8-bit library was built
+  unicode    Unicode support is available
+

+If an unknown option is given, an error message is output; the exit code is 0.
+

+

+-d
+Behave as if each pattern has the debug modifier; the internal
+form and information about the compiled pattern is output after compilation;
+-d is equivalent to -b -i.
+

+

+-dfa
+Behave as if each subject line has the dfa modifier; matching is done
+using the pcre2_dfa_match() function instead of the default
+pcre2_match().
+

+

+-help
+Output a brief summary these options and then exit.
+

+

+-i
+Behave as if each pattern has the /info modifier; information about the
+compiled pattern is given after compilation.
+

+

+-jit
+Behave as if each pattern line has the jit modifier; after successful
+compilation, each pattern is passed to the just-in-time compiler, if available.
+

+

+\fB-pattern\fB modifier-list
+Behave as if each pattern line contains the given modifiers.
+

+

+-q
+Do not output the version number of pcre2test at the start of execution.
+

+

+-S size
+On Unix-like systems, set the size of the run-time stack to size
+megabytes.
+

+

+-subject modifier-list
+Behave as if each subject line contains the given modifiers.
+

+

+-t
+Run each compile and match many times with a timer, and output the resulting
+times per compile or match. When JIT is used, separate times are given for the
+initial compile and the JIT compile. You can control the number of iterations
+that are used for timing by following -t with a number (as a separate
+item on the command line). For example, "-t 1000" iterates 1000 times. The
+default is to iterate 500,000 times.
+

+

+-tm
+This is like -t except that it times only the matching phase, not the
+compile phase.
+

+

+-T -TM
+These behave like -t and -tm, but in addition, at the end of a run,
+the total times for all compiles and matches are output.
+

+

+-version
+Output the PCRE2 version number and then exit.
+

+
DESCRIPTION

+

+If pcre2test is given two filename arguments, it reads from the first and
+writes to the second. If the first name is "-", input is taken from the
+standard input. If pcre2test is given only one argument, it reads from
+that file and writes to stdout. Otherwise, it reads from stdin and writes to
+stdout.
+

+

+When pcre2test is built, a configuration option can specify that it
+should be linked with the libreadline or libedit library. When this
+is done, if the input is from a terminal, it is read using the readline()
+function. This provides line-editing and history facilities. The output from
+the -help option states whether or not readline() will be used.
+

+

+The program handles any number of tests, each of which consists of a set of
+input lines. Each set starts with a regular expression pattern, followed by any
+number of subject lines to be matched against that pattern. In between sets of
+test data, command lines that begin with # may appear. This file format, with
+some restrictions, can also be processed by the perltest.sh script that
+is distributed with PCRE2 as a means of checking that the behaviour of PCRE2
+and Perl is the same.
+

+

+When the input is a terminal, pcre2test prompts for each line of input,
+using "re>" to prompt for regular expression patterns, and "data>" to prompt
+for subject lines. Command lines starting with # can be entered only in
+response to the "re>" prompt.
+

+

+Each subject line is matched separately and independently. If you want to do
+multi-line matches, you have to use the \n escape sequence (or \r or \r\n,
+etc., depending on the newline setting) in a single line of input to encode the
+newline sequences. There is no limit on the length of subject lines; the input
+buffer is automatically extended if it is too small. There is a replication
+feature that makes it possible to generate long subject lines without having to
+supply them explicitly.
+

+

+An empty line or the end of the file signals the end of the subject lines for a
+test, at which point a new pattern or command line is expected if there is
+still input to be read.
+

+
COMMAND LINES

+

+In between sets of test data, a line that begins with # is interpreted as a
+command line. If the first character is followed by white space or an
+exclamation mark, the line is treated as a comment, and ignored. Otherwise, the
+following commands are recognized:
+
+  #forbid_utf
+

+Subsequent patterns automatically have the PCRE2_NEVER_UTF and PCRE2_NEVER_UCP
+options set, which locks out the use of the PCRE2_UTF and PCRE2_UCP options and
+the use of (*UTF) and (*UCP) at the start of patterns. This command also forces
+an error if a subsequent pattern contains any occurrences of \P, \p, or \X,
+which are still supported when PCRE2_UTF is not set, but which require Unicode
+property support to be included in the library.
+

+

+This is a trigger guard that is used in test files to ensure that UTF or
+Unicode property tests are not accidentally added to files that are used when
+Unicode support is not included in the library. Setting PCRE2_NEVER_UTF and
+PCRE2_NEVER_UCP as a default can also be obtained by the use of #pattern;
+the difference is that #forbid_utf cannot be unset, and the automatic
+options are not displayed in pattern information, to avoid cluttering up test
+output.
+
+  #load <filename>
+

+This command is used to load a set of precompiled patterns from a file, as
+described in the section entitled "Saving and restoring compiled patterns"
+below.
+
+  #pattern <modifier-list>
+

+This command sets a default modifier list that applies to all subsequent
+patterns. Modifiers on a pattern can change these settings.
+
+  #perltest
+

+The appearance of this line causes all subsequent modifier settings to be
+checked for compatibility with the perltest.sh script, which is used to
+confirm that Perl gives the same results as PCRE2. Also, apart from comment
+lines, none of the other command lines are permitted, because they and many
+of the modifiers are specific to pcre2test, and should not be used in
+test files that are also processed by perltest.sh. The #perltest
+command helps detect tests that are accidentally put in the wrong file.
+
+  #pop [<modifiers>]
+

+This command is used to manipulate the stack of compiled patterns, as described
+in the section entitled "Saving and restoring compiled patterns"
+below.
+
+  #save <filename>
+

+This command is used to save a set of compiled patterns to a file, as described
+in the section entitled "Saving and restoring compiled patterns"
+below.
+
+  #subject <modifier-list>
+

+This command sets a default modifier list that applies to all subsequent
+subject lines. Modifiers on a subject line can change these settings.
+

+
MODIFIER SYNTAX

+

+Modifier lists are used with both pattern and subject lines. Items in a list
+are separated by commas and optional white space. Some modifiers may be given
+for both patterns and subject lines, whereas others are valid for one or the
+other only. Each modifier has a long name, for example "anchored", and some of
+them must be followed by an equals sign and a value, for example, "offset=12".
+Modifiers that do not take values may be preceded by a minus sign to turn off a
+previous setting.
+

+

+A few of the more common modifiers can also be specified as single letters, for
+example "i" for "caseless". In documentation, following the Perl convention,
+these are written with a slash ("the /i modifier") for clarity. Abbreviated
+modifiers must all be concatenated in the first item of a modifier list. If the
+first item is not recognized as a long modifier name, it is interpreted as a
+sequence of these abbreviations. For example:
+
+  /abc/ig,newline=cr,jit=3
+

+This is a pattern line whose modifier list starts with two one-letter modifiers
+(/i and /g). The lower-case abbreviated modifiers are the same as used in Perl.
+

+
PATTERN SYNTAX

+

+A pattern line must start with one of the following characters (common symbols,
+excluding pattern meta-characters):
+
+  / ! " ' ` - = _ : ; , % & @ ~
+

+This is interpreted as the pattern's delimiter. A regular expression may be
+continued over several input lines, in which case the newline characters are
+included within it. It is possible to include the delimiter within the pattern
+by escaping it with a backslash, for example
+
+  /abc\/def/
+

+If you do this, the escape and the delimiter form part of the pattern, but
+since the delimiters are all non-alphanumeric, this does not affect its
+interpretation. If the terminating delimiter is immediately followed by a
+backslash, for example,
+
+  /abc/\
+

+then a backslash is added to the end of the pattern. This is done to provide a
+way of testing the error condition that arises if a pattern finishes with a
+backslash, because
+
+  /abc\/
+

+is interpreted as the first line of a pattern that starts with "abc/", causing
+pcre2test to read the next line as a continuation of the regular expression.
+

+

+A pattern can be followed by a modifier list (details below).
+

+
SUBJECT LINE SYNTAX

+

+Before each subject line is passed to pcre2_match() or
+pcre2_dfa_match(), leading and trailing white space is removed, and the
+line is scanned for backslash escapes. The following provide a means of
+encoding non-printing characters in a visible way:
+
+  \a         alarm (BEL, \x07)
+  \b         backspace (\x08)
+  \e         escape (\x27)
+  \f         form feed (\x0c)
+  \n         newline (\x0a)
+  \r         carriage return (\x0d)
+  \t         tab (\x09)
+  \v         vertical tab (\x0b)
+  \nnn       octal character (up to 3 octal digits); always
+               a byte unless > 255 in UTF-8 or 16-bit or 32-bit mode
+  \o{dd...}  octal character (any number of octal digits}
+  \xhh       hexadecimal byte (up to 2 hex digits)
+  \x{hh...}  hexadecimal character (any number of hex digits)
+

+The use of \x{hh...} is not dependent on the use of the utf modifier on
+the pattern. It is recognized always. There may be any number of hexadecimal
+digits inside the braces; invalid values provoke error messages.
+

+

+Note that \xhh specifies one byte rather than one character in UTF-8 mode;
+this makes it possible to construct invalid UTF-8 sequences for testing
+purposes. On the other hand, \x{hh} is interpreted as a UTF-8 character in
+UTF-8 mode, generating more than one byte if the value is greater than 127.
+When testing the 8-bit library not in UTF-8 mode, \x{hh} generates one byte
+for values less than 256, and causes an error for greater values.
+

+

+In UTF-16 mode, all 4-digit \x{hhhh} values are accepted. This makes it
+possible to construct invalid UTF-16 sequences for testing purposes.
+

+

+In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This makes it
+possible to construct invalid UTF-32 sequences for testing purposes.
+

+

+There is a special backslash sequence that specifies replication of one or more
+characters:
+
+  \[<characters>]{<count>}
+

+This makes it possible to test long strings without having to provide them as
+part of the file. For example:
+
+  \[abc]{4}
+

+is converted to "abcabcabcabc". This feature does not support nesting. To
+include a closing square bracket in the characters, code it as \x5D.
+

+

+A backslash followed by an equals sign marks the end of the subject string and
+the start of a modifier list. For example:
+
+  abc\=notbol,notempty
+

+A backslash followed by any other non-alphanumeric character just escapes that
+character. A backslash followed by anything else causes an error. However, if
+the very last character in the line is a backslash (and there is no modifier
+list), it is ignored. This gives a way of passing an empty line as data, since
+a real empty line terminates the data input.
+

+
PATTERN MODIFIERS

+

+There are three types of modifier that can appear in pattern lines, two of
+which may also be used in a #pattern command. A pattern's modifier list
+can add to or override default modifiers that were set by a previous
+#pattern command.
+

+

+Setting compilation options
+

+

+The following modifiers set options for pcre2_compile(). The most common
+ones have single-letter abbreviations. See
+pcreapi
+for a description of their effects.
+
+      allow_empty_class         set PCRE2_ALLOW_EMPTY_CLASS
+      alt_bsux                  set PCRE2_ALT_BSUX
+      alt_circumflex            set PCRE2_ALT_CIRCUMFLEX
+      anchored                  set PCRE2_ANCHORED
+      auto_callout              set PCRE2_AUTO_CALLOUT
+  /i  caseless                  set PCRE2_CASELESS
+      dollar_endonly            set PCRE2_DOLLAR_ENDONLY
+  /s  dotall                    set PCRE2_DOTALL
+      dupnames                  set PCRE2_DUPNAMES
+  /x  extended                  set PCRE2_EXTENDED
+      firstline                 set PCRE2_FIRSTLINE
+      match_unset_backref       set PCRE2_MATCH_UNSET_BACKREF
+  /m  multiline                 set PCRE2_MULTILINE
+      never_backslash_c         set PCRE2_NEVER_BACKSLASH_C
+      never_ucp                 set PCRE2_NEVER_UCP
+      never_utf                 set PCRE2_NEVER_UTF
+      no_auto_capture           set PCRE2_NO_AUTO_CAPTURE
+      no_auto_possess           set PCRE2_NO_AUTO_POSSESS
+      no_dotstar_anchor         set PCRE2_NO_DOTSTAR_ANCHOR
+      no_start_optimize         set PCRE2_NO_START_OPTIMIZE
+      no_utf_check              set PCRE2_NO_UTF_CHECK
+      ucp                       set PCRE2_UCP
+      ungreedy                  set PCRE2_UNGREEDY
+      utf                       set PCRE2_UTF
+

+As well as turning on the PCRE2_UTF option, the utf modifier causes all
+non-printing characters in output strings to be printed using the \x{hh...}
+notation. Otherwise, those less than 0x100 are output in hex without the curly
+brackets.
+

+

+Setting compilation controls
+

+

+The following modifiers affect the compilation process or request information
+about the pattern:
+
+      bsr=[anycrlf|unicode]     specify \R handling
+  /B  bincode                   show binary code without lengths
+      callout_info              show callout information
+      debug                     same as info,fullbincode
+      fullbincode               show binary code with lengths
+  /I  info                      show info about compiled pattern
+      hex                       pattern is coded in hexadecimal
+      jit[=<number>]            use JIT
+      jitfast                   use JIT fast path
+      jitverify                 verify JIT use
+      locale=<name>             use this locale
+      memory                    show memory used
+      newline=<type>            set newline type
+      parens_nest_limit=<n>     set maximum parentheses depth
+      posix                     use the POSIX API
+      push                      push compiled pattern onto the stack
+      stackguard=<number>       test the stackguard feature
+      tables=[0|1|2]            select internal tables
+

+The effects of these modifiers are described in the following sections.
+

+

+Newline and \R handling
+

+

+The bsr modifier specifies what \R in a pattern should match. If it is
+set to "anycrlf", \R matches CR, LF, or CRLF only. If it is set to "unicode",
+\R matches any Unicode newline sequence. The default is specified when PCRE2
+is built, with the default default being Unicode.
+

+

+The newline modifier specifies which characters are to be interpreted as
+newlines, both in the pattern and in subject lines. The type must be one of CR,
+LF, CRLF, ANYCRLF, or ANY (in upper or lower case).
+

+

+Information about a pattern
+

+

+The debug modifier is a shorthand for info,fullbincode, requesting
+all available information.
+

+

+The bincode modifier causes a representation of the compiled code to be
+output after compilation. This information does not contain length and offset
+values, which ensures that the same output is generated for different internal
+link sizes and different code unit widths. By using bincode, the same
+regression tests can be used in different environments.
+

+

+The fullbincode modifier, by contrast, does include length and
+offset values. This is used in a few special tests that run only for specific
+code unit widths and link sizes, and is also useful for one-off tests.
+

+

+The info modifier requests information about the compiled pattern
+(whether it is anchored, has a fixed first character, and so on). The
+information is obtained from the pcre2_pattern_info() function. Here are
+some typical examples:
+
+    re> /(?i)(^a|^b)/m,info
+  Capturing subpattern count = 1
+  Compile options: multiline
+  Overall options: caseless multiline
+  First code unit at start or follows newline
+  Subject length lower bound = 1
+
+    re> /(?i)abc/info
+  Capturing subpattern count = 0
+  Compile options: <none>
+  Overall options: caseless
+  First code unit = 'a' (caseless)
+  Last code unit = 'c' (caseless)
+  Subject length lower bound = 3
+

+"Compile options" are those specified by modifiers; "overall options" have
+added options that are taken or deduced from the pattern. If both sets of
+options are the same, just a single "options" line is output; if there are no
+options, the line is omitted. "First code unit" is where any match must start;
+if there is more than one they are listed as "starting code units". "Last code
+unit" is the last literal code unit that must be present in any match. This is
+not necessarily the last character. These lines are omitted if no starting or
+ending code units are recorded.
+

+

+The callout_info modifier requests information about all the callouts in
+the pattern. A list of them is output at the end of any other information that
+is requested. For each callout, either its number or string is given, followed
+by the item that follows it in the pattern.
+

+

+Specifying a pattern in hex
+

+

+The hex modifier specifies that the characters of the pattern are to be
+interpreted as pairs of hexadecimal digits. White space is permitted between
+pairs. For example:
+
+  /ab 32 59/hex
+

+This feature is provided as a way of creating patterns that contain binary zero
+and other non-printing characters. By default, pcre2test passes patterns
+as zero-terminated strings to pcre2_compile(), giving the length as
+PCRE2_ZERO_TERMINATED. However, for patterns specified in hexadecimal, the
+actual length of the pattern is passed.
+

+

+JIT compilation
+

+

+The /jit modifier may optionally be followed by an equals sign and a
+number in the range 0 to 7:
+
+  0  disable JIT
+  1  use JIT for normal match only
+  2  use JIT for soft partial match only
+  3  use JIT for normal match and soft partial match
+  4  use JIT for hard partial match only
+  6  use JIT for soft and hard partial match
+  7  all three modes
+

+If no number is given, 7 is assumed. If JIT compilation is successful, the
+compiled JIT code will automatically be used when pcre2_match() is run
+for the appropriate type of match, except when incompatible run-time options
+are specified. For more details, see the
+pcre2jit
+documentation. See also the jitstack modifier below for a way of
+setting the size of the JIT stack.
+

+

+If the jitfast modifier is specified, matching is done using the JIT
+"fast path" interface, pcre2_jit_match(), which skips some of the sanity
+checks that are done by pcre2_match(), and of course does not work when
+JIT is not supported. If jitfast is specified without jit, jit=7 is
+assumed.
+

+

+If the jitverify modifier is specified, information about the compiled
+pattern shows whether JIT compilation was or was not successful. If
+jitverify is specified without jit, jit=7 is assumed. If JIT
+compilation is successful when jitverify is set, the text "(JIT)" is
+added to the first output line after a match or non match when JIT-compiled
+code was actually used in the match.
+

+

+Setting a locale
+

+

+The /locale modifier must specify the name of a locale, for example:
+
+  /pattern/locale=fr_FR
+

+The given locale is set, pcre2_maketables() is called to build a set of
+character tables for the locale, and this is then passed to
+pcre2_compile() when compiling the regular expression. The same tables
+are used when matching the following subject lines. The /locale modifier
+applies only to the pattern on which it appears, but can be given in a
+#pattern command if a default is needed. Setting a locale and alternate
+character tables are mutually exclusive.
+

+

+Showing pattern memory
+

+

+The /memory modifier causes the size in bytes of the memory used to hold
+the compiled pattern to be output. This does not include the size of the
+pcre2_code block; it is just the actual compiled data. If the pattern is
+subsequently passed to the JIT compiler, the size of the JIT compiled code is
+also output. Here is an example:
+
+    re> /a(b)c/jit,memory
+  Memory allocation (code space): 21
+  Memory allocation (JIT code): 1910
+
+

+

+

+Limiting nested parentheses
+

+

+The parens_nest_limit modifier sets a limit on the depth of nested
+parentheses in a pattern. Breaching the limit causes a compilation error.
+The default for the library is set when PCRE2 is built, but pcre2test
+sets its own default of 220, which is required for running the standard test
+suite.
+

+

+Using the POSIX wrapper API
+

+

+The /posix modifier causes pcre2test to call PCRE2 via the POSIX
+wrapper API rather than its native API. This supports only the 8-bit library.
+When the POSIX API is being used, the following pattern modifiers set options
+for the regcomp() function:
+
+  caseless           REG_ICASE
+  multiline          REG_NEWLINE
+  no_auto_capture    REG_NOSUB
+  dotall             REG_DOTALL     )
+  ungreedy           REG_UNGREEDY   ) These options are not part of
+  ucp                REG_UCP        )   the POSIX standard
+  utf                REG_UTF8       )
+

+The aftertext and allaftertext subject modifiers work as described
+below. All other modifiers cause an error.
+

+

+Testing the stack guard feature
+

+

+The /stackguard modifier is used to test the use of
+pcre2_set_compile_recursion_guard(), a function that is provided to
+enable stack availability to be checked during compilation (see the
+pcre2api
+documentation for details). If the number specified by the modifier is greater
+than zero, pcre2_set_compile_recursion_guard() is called to set up
+callback from pcre2_compile() to a local function. The argument it
+receives is the current nesting parenthesis depth; if this is greater than the
+value given by the modifier, non-zero is returned, causing the compilation to
+be aborted.
+

+

+Using alternative character tables
+

+

+The value specified for the /tables modifier must be one of the digits 0,
+1, or 2. It causes a specific set of built-in character tables to be passed to
+pcre2_compile(). This is used in the PCRE2 tests to check behaviour with
+different character tables. The digit specifies the tables as follows:
+
+  0   do not pass any special character tables
+  1   the default ASCII tables, as distributed in
+        pcre2_chartables.c.dist
+  2   a set of tables defining ISO 8859 characters
+

+In table 2, some characters whose codes are greater than 128 are identified as
+letters, digits, spaces, etc. Setting alternate character tables and a locale
+are mutually exclusive.
+

+

+Setting certain match controls
+

+

+The following modifiers are really subject modifiers, and are described below.
+However, they may be included in a pattern's modifier list, in which case they
+are applied to every subject line that is processed with that pattern. They do
+not affect the compilation process.
+
+      aftertext           show text after match
+      allaftertext        show text after captures
+      allcaptures         show all captures
+      allusedtext         show all consulted text
+  /g  global              global matching
+      mark                show mark values
+      replace=<string>    specify a replacement string
+      startchar           show starting character when relevant
+

+These modifiers may not appear in a #pattern command. If you want them as
+defaults, set them in a #subject command.
+

+

+Saving a compiled pattern
+

+

+When a pattern with the push modifier is successfully compiled, it is
+pushed onto a stack of compiled patterns, and pcre2test expects the next
+line to contain a new pattern (or a command) instead of a subject line. This
+facility is used when saving compiled patterns to a file, as described in the
+section entitled "Saving and restoring compiled patterns"
+below.
+The push modifier is incompatible with compilation modifiers such as
+global that act at match time. Any that are specified are ignored, with a
+warning message, except for replace, which causes an error. Note that,
+jitverify, which is allowed, does not carry through to any subsequent
+matching that uses this pattern.
+

+
SUBJECT MODIFIERS

+

+The modifiers that can appear in subject lines and the #subject
+command are of two types.
+

+

+Setting match options
+

+

+The following modifiers set options for pcre2_match() or
+pcre2_dfa_match(). See
+pcreapi
+for a description of their effects.
+
+      anchored                  set PCRE2_ANCHORED
+      dfa_restart               set PCRE2_DFA_RESTART
+      dfa_shortest              set PCRE2_DFA_SHORTEST
+      no_utf_check              set PCRE2_NO_UTF_CHECK
+      notbol                    set PCRE2_NOTBOL
+      notempty                  set PCRE2_NOTEMPTY
+      notempty_atstart          set PCRE2_NOTEMPTY_ATSTART
+      noteol                    set PCRE2_NOTEOL
+      partial_hard (or ph)      set PCRE2_PARTIAL_HARD
+      partial_soft (or ps)      set PCRE2_PARTIAL_SOFT
+

+The partial matching modifiers are provided with abbreviations because they
+appear frequently in tests.
+

+

+If the /posix modifier was present on the pattern, causing the POSIX
+wrapper API to be used, the only option-setting modifiers that have any effect
+are notbol, notempty, and noteol, causing REG_NOTBOL,
+REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to regexec().
+Any other modifiers cause an error.
+

+

+Setting match controls
+

+

+The following modifiers affect the matching process or request additional
+information. Some of them may also be specified on a pattern line (see above),
+in which case they apply to every subject line that is matched against that
+pattern.
+
+      aftertext                 show text after match
+      allaftertext              show text after captures
+      allcaptures               show all captures
+      allusedtext               show all consulted text (non-JIT only)
+      altglobal                 alternative global matching
+      callout_capture           show captures at callout time
+      callout_data=<n>          set a value to pass via callouts
+      callout_fail=<n>[:<m>]    control callout failure
+      callout_none              do not supply a callout function
+      copy=<number or name>     copy captured substring
+      dfa                       use pcre2_dfa_match()
+      find_limits               find match and recursion limits
+      get=<number or name>      extract captured substring
+      getall                    extract all captured substrings
+  /g  global                    global matching
+      jitstack=<n>              set size of JIT stack
+      mark                      show mark values
+      match_limit=>n>           set a match limit
+      memory                    show memory usage
+      offset=<n>                set starting offset
+      ovector=<n>               set size of output vector
+      recursion_limit=<n>       set a recursion limit
+      replace=<string>          specify a replacement string
+      startchar                 show startchar when relevant
+      zero_terminate            pass the subject as zero-terminated
+

+The effects of these modifiers are described in the following sections.
+

+

+Showing more text
+

+

+The aftertext modifier requests that as well as outputting the part of
+the subject string that matched the entire pattern, pcre2test should in
+addition output the remainder of the subject string. This is useful for tests
+where the subject contains multiple copies of the same substring. The
+allaftertext modifier requests the same action for captured substrings as
+well as the main matched substring. In each case the remainder is output on the
+following line with a plus character following the capture number.
+

+

+The allusedtext modifier requests that all the text that was consulted
+during a successful pattern match by the interpreter should be shown. This
+feature is not supported for JIT matching, and if requested with JIT it is
+ignored (with a warning message). Setting this modifier affects the output if
+there is a lookbehind at the start of a match, or a lookahead at the end, or if
+\K is used in the pattern. Characters that precede or follow the start and end
+of the actual match are indicated in the output by '<' or '>' characters
+underneath them. Here is an example:
+
+    re> /(?<=pqr)abc(?=xyz)/
+  data> 123pqrabcxyz456\=allusedtext
+   0: pqrabcxyz
+      <<<   >>>
+

+This shows that the matched string is "abc", with the preceding and following
+strings "pqr" and "xyz" having been consulted during the match (when processing
+the assertions).
+

+

+The startchar modifier requests that the starting character for the match
+be indicated, if it is different to the start of the matched string. The only
+time when this occurs is when \K has been processed as part of the match. In
+this situation, the output for the matched string is displayed from the
+starting character instead of from the match point, with circumflex characters
+under the earlier characters. For example:
+
+    re> /abc\Kxyz/
+  data> abcxyz\=startchar
+   0: abcxyz
+      ^^^
+

+Unlike allusedtext, the startchar modifier can be used with JIT.
+However, these two modifiers are mutually exclusive.
+

+

+Showing the value of all capture groups
+

+

+The allcaptures modifier requests that the values of all potential
+captured parentheses be output after a match. By default, only those up to the
+highest one actually used in the match are output (corresponding to the return
+code from pcre2_match()). Groups that did not take part in the match
+are output as "<unset>".
+

+

+Testing callouts
+

+

+A callout function is supplied when pcre2test calls the library matching
+functions, unless callout_none is specified. If callout_capture is
+set, the current captured groups are output when a callout occurs.
+

+

+The callout_fail modifier can be given one or two numbers. If there is
+only one number, 1 is returned instead of 0 when a callout of that number is
+reached. If two numbers are given, 1 is returned when callout <n> is reached
+for the <m>th time. Note that callouts with string arguments are always given
+the number zero. See "Callouts" below for a description of the output when a
+callout it taken.
+

+

+The callout_data modifier can be given an unsigned or a negative number.
+This is set as the "user data" that is passed to the matching function, and
+passed back when the callout function is invoked. Any value other than zero is
+used as a return from pcre2test's callout function.
+

+

+Finding all matches in a string
+

+

+Searching for all possible matches within a subject can be requested by the
+global or /altglobal modifier. After finding a match, the matching
+function is called again to search the remainder of the subject. The difference
+between global and altglobal is that the former uses the
+start_offset argument to pcre2_match() or pcre2_dfa_match()
+to start searching at a new point within the entire string (which is what Perl
+does), whereas the latter passes over a shortened subject. This makes a
+difference to the matching process if the pattern begins with a lookbehind
+assertion (including \b or \B).
+

+

+If an empty string is matched, the next match is done with the
+PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED flags set, in order to search for
+another, non-empty, match at the same point in the subject. If this match
+fails, the start offset is advanced, and the normal match is retried. This
+imitates the way Perl handles such cases when using the /g modifier or
+the split() function. Normally, the start offset is advanced by one
+character, but if the newline convention recognizes CRLF as a newline, and the
+current character is CR followed by LF, an advance of two characters occurs.
+

+

+Testing substring extraction functions
+

+

+The copy and get modifiers can be used to test the
+pcre2_substring_copy_xxx() and pcre2_substring_get_xxx() functions.
+They can be given more than once, and each can specify a group name or number,
+for example:
+
+   abcd\=copy=1,copy=3,get=G1
+

+If the #subject command is used to set default copy and/or get lists,
+these can be unset by specifying a negative number to cancel all numbered
+groups and an empty name to cancel all named groups.
+

+

+The getall modifier tests pcre2_substring_list_get(), which
+extracts all captured substrings.
+

+

+If the subject line is successfully matched, the substrings extracted by the
+convenience functions are output with C, G, or L after the string number
+instead of a colon. This is in addition to the normal full list. The string
+length (that is, the return from the extraction function) is given in
+parentheses after each substring, followed by the name when the extraction was
+by name.
+

+

+Testing the substitution function
+

+

+If the replace modifier is set, the pcre2_substitute() function is
+called instead of one of the matching functions. Unlike subject strings,
+pcre2test does not process replacement strings for escape sequences. In
+UTF mode, a replacement string is checked to see if it is a valid UTF-8 string.
+If so, it is correctly converted to a UTF string of the appropriate code unit
+width. If it is not a valid UTF-8 string, the individual code units are copied
+directly. This provides a means of passing an invalid UTF-8 string for testing
+purposes.
+

+

+If the global modifier is set, PCRE2_SUBSTITUTE_GLOBAL is passed to
+pcre2_substitute(). After a successful substitution, the modified string
+is output, preceded by the number of replacements. This may be zero if there
+were no matches. Here is a simple example of a substitution test:
+
+  /abc/replace=xxx
+      =abc=abc=
+   1: =xxx=abc=
+      =abc=abc=\=global
+   2: =xxx=xxx=
+

+Subject and replacement strings should be kept relatively short for
+substitution tests, as fixed-size buffers are used. To make it easy to test for
+buffer overflow, if the replacement string starts with a number in square
+brackets, that number is passed to pcre2_substitute() as the size of the
+output buffer, with the replacement string starting at the next character. Here
+is an example that tests the edge case:
+
+  /abc/
+      123abc123\=replace=[10]XYZ
+   1: 123XYZ123
+      123abc123\=replace=[9]XYZ
+  Failed: error -47: no more memory
+

+A replacement string is ignored with POSIX and DFA matching. Specifying partial
+matching provokes an error return ("bad option value") from
+pcre2_substitute().
+

+

+Setting the JIT stack size
+

+

+The jitstack modifier provides a way of setting the maximum stack size
+that is used by the just-in-time optimization code. It is ignored if JIT
+optimization is not being used. The value is a number of kilobytes. Providing a
+stack that is larger than the default 32K is necessary only for very
+complicated patterns.
+

+

+Setting match and recursion limits
+

+

+The match_limit and recursion_limit modifiers set the appropriate
+limits in the match context. These values are ignored when the
+find_limits modifier is specified.
+

+

+Finding minimum limits
+

+

+If the find_limits modifier is present, pcre2test calls
+pcre2_match() several times, setting different values in the match
+context via pcre2_set_match_limit() and pcre2_set_recursion_limit()
+until it finds the minimum values for each parameter that allow
+pcre2_match() to complete without error.
+

+

+If JIT is being used, only the match limit is relevant. If DFA matching is
+being used, neither limit is relevant, and this modifier is ignored (with a
+warning message).
+

+

+The match_limit number is a measure of the amount of backtracking
+that takes place, and learning the minimum value can be instructive. For most
+simple matches, the number is quite small, but for patterns with very large
+numbers of matching possibilities, it can become large very quickly with
+increasing length of subject string. The match_limit_recursion number is
+a measure of how much stack (or, if PCRE2 is compiled with NO_RECURSE, how much
+heap) memory is needed to complete the match attempt.
+

+

+Showing MARK names
+

+

+The mark modifier causes the names from backtracking control verbs that
+are returned from calls to pcre2_match() to be displayed. If a mark is
+returned for a match, non-match, or partial match, pcre2test shows it.
+For a match, it is on a line by itself, tagged with "MK:". Otherwise, it
+is added to the non-match message.
+

+

+Showing memory usage
+

+

+The memory modifier causes pcre2test to log all memory allocation
+and freeing calls that occur during a match operation.
+

+

+Setting a starting offset
+

+

+The offset modifier sets an offset in the subject string at which
+matching starts. Its value is a number of code units, not characters.
+

+

+Setting the size of the output vector
+

+

+The ovector modifier applies only to the subject line in which it
+appears, though of course it can also be used to set a default in a
+#subject command. It specifies the number of pairs of offsets that are
+available for storing matching information. The default is 15.
+

+

+A value of zero is useful when testing the POSIX API because it causes
+regexec() to be called with a NULL capture vector. When not testing the
+POSIX API, a value of zero is used to cause
+pcre2_match_data_create_from_pattern() to be called, in order to create a
+match block of exactly the right size for the pattern. (It is not possible to
+create a match block with a zero-length ovector; there is always at least one
+pair of offsets.)
+

+

+Passing the subject as zero-terminated
+

+

+By default, the subject string is passed to a native API matching function with
+its correct length. In order to test the facility for passing a zero-terminated
+string, the zero_terminate modifier is provided. It causes the length to
+be passed as PCRE2_ZERO_TERMINATED. (When matching via the POSIX interface,
+this modifier has no effect, as there is no facility for passing a length.)
+

+

+When testing pcre2_substitute(), this modifier also has the effect of
+passing the replacement string as zero-terminated.
+

+
THE ALTERNATIVE MATCHING FUNCTION

+

+By default, pcre2test uses the standard PCRE2 matching function,
+pcre2_match() to match each subject line. PCRE2 also supports an
+alternative matching function, pcre2_dfa_match(), which operates in a
+different way, and has some restrictions. The differences between the two
+functions are described in the
+pcre2matching
+documentation.
+

+

+If the dfa modifier is set, the alternative matching function is used.
+This function finds all possible matches at a given point in the subject. If,
+however, the dfa_shortest modifier is set, processing stops after the
+first match is found. This is always the shortest possible match.
+

+
DEFAULT OUTPUT FROM pcre2test

+

+This section describes the output when the normal matching function,
+pcre2_match(), is being used.
+

+

+When a match succeeds, pcre2test outputs the list of captured substrings,
+starting with number 0 for the string that matched the whole pattern.
+Otherwise, it outputs "No match" when the return is PCRE2_ERROR_NOMATCH, or
+"Partial match:" followed by the partially matching substring when the
+return is PCRE2_ERROR_PARTIAL. (Note that this is the
+entire substring that was inspected during the partial match; it may include
+characters before the actual match start if a lookbehind assertion, \K, \b,
+or \B was involved.)
+

+

+For any other return, pcre2test outputs the PCRE2 negative error number
+and a short descriptive phrase. If the error is a failed UTF string check, the
+code unit offset of the start of the failing character is also output. Here is
+an example of an interactive pcre2test run.
+
+  $ pcre2test
+  PCRE2 version 9.00 2014-05-10
+
+    re> /^abc(\d+)/
+  data> abc123
+   0: abc123
+   1: 123
+  data> xyz
+  No match
+

+Unset capturing substrings that are not followed by one that is set are not
+shown by pcre2test unless the allcaptures modifier is specified. In
+the following example, there are two capturing substrings, but when the first
+data line is matched, the second, unset substring is not shown. An "internal"
+unset substring is shown as "<unset>", as for the second data line.
+
+    re> /(a)|(b)/
+  data> a
+   0: a
+   1: a
+  data> b
+   0: b
+   1: <unset>
+   2: b
+

+If the strings contain any non-printing characters, they are output as \xhh
+escapes if the value is less than 256 and UTF mode is not set. Otherwise they
+are output as \x{hh...} escapes. See below for the definition of non-printing
+characters. If the /aftertext modifier is set, the output for substring
+0 is followed by the the rest of the subject string, identified by "0+" like
+this:
+
+    re> /cat/aftertext
+  data> cataract
+   0: cat
+   0+ aract
+

+If global matching is requested, the results of successive matching attempts
+are output in sequence, like this:
+
+    re> /\Bi(\w\w)/g
+  data> Mississippi
+   0: iss
+   1: ss
+   0: iss
+   1: ss
+   0: ipp
+   1: pp
+

+"No match" is output only if the first match attempt fails. Here is an example
+of a failure message (the offset 4 that is specified by the offset
+modifier is past the end of the subject string):
+
+    re> /xyz/
+  data> xyz\=offset=4
+  Error -24 (bad offset value)
+

+

+

+Note that whereas patterns can be continued over several lines (a plain ">"
+prompt is used for continuations), subject lines may not. However newlines can
+be included in a subject by means of the \n escape (or \r, \r\n, etc.,
+depending on the newline sequence setting).
+

+
OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION

+

+When the alternative matching function, pcre2_dfa_match(), is used, the
+output consists of a list of all the matches that start at the first point in
+the subject where there is at least one match. For example:
+
+    re> /(tang|tangerine|tan)/
+  data> yellow tangerine\=dfa
+   0: tangerine
+   1: tang
+   2: tan
+

+Using the normal matching function on this data finds only "tang". The
+longest matching string is always given first (and numbered zero). After a
+PCRE2_ERROR_PARTIAL return, the output is "Partial match:", followed by the
+partially matching substring. Note that this is the entire substring that was
+inspected during the partial match; it may include characters before the actual
+match start if a lookbehind assertion, \b, or \B was involved. (\K is not
+supported for DFA matching.)
+

+

+If global matching is requested, the search for further matches resumes
+at the end of the longest match. For example:
+
+    re> /(tang|tangerine|tan)/g
+  data> yellow tangerine and tangy sultana\=dfa
+   0: tangerine
+   1: tang
+   2: tan
+   0: tang
+   1: tan
+   0: tan
+

+The alternative matching function does not support substring capture, so the
+modifiers that are concerned with captured substrings are not relevant.
+

+
RESTARTING AFTER A PARTIAL MATCH

+

+When the alternative matching function has given the PCRE2_ERROR_PARTIAL
+return, indicating that the subject partially matched the pattern, you can
+restart the match with additional subject data by means of the
+dfa_restart modifier. For example:
+
+    re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
+  data> 23ja\=P,dfa
+  Partial match: 23ja
+  data> n05\=dfa,dfa_restart
+   0: n05
+

+For further information about partial matching, see the
+pcre2partial
+documentation.
+

+
CALLOUTS

+

+If the pattern contains any callout requests, pcre2test's callout
+function is called during matching unless callout_none is specified.
+This works with both matching functions.
+

+

+The callout function in pcre2test returns zero (carry on matching) by
+default, but you can use a callout_fail modifier in a subject line (as
+described above) to change this and other parameters of the callout.
+

+

+Inserting callouts can be helpful when using pcre2test to check
+complicated regular expressions. For further information about callouts, see
+the
+pcre2callout
+documentation.
+

+

+The output for callouts with numerical arguments and those with string
+arguments is slightly different.
+

+

+Callouts with numerical arguments
+

+

+By default, the callout function displays the callout number, the start and
+current positions in the subject text at the callout time, and the next pattern
+item to be tested. For example:
+
+  --->pqrabcdef
+    0    ^  ^     \d
+

+This output indicates that callout number 0 occurred for a match attempt
+starting at the fourth character of the subject string, when the pointer was at
+the seventh character, and when the next pattern item was \d. Just
+one circumflex is output if the start and current positions are the same.
+

+

+Callouts numbered 255 are assumed to be automatic callouts, inserted as a
+result of the /auto_callout pattern modifier. In this case, instead of
+showing the callout number, the offset in the pattern, preceded by a plus, is
+output. For example:
+
+    re> /\d?[A-E]\*/auto_callout
+  data> E*
+  --->E*
+   +0 ^      \d?
+   +3 ^      [A-E]
+   +8 ^^     \*
+  +10 ^ ^
+   0: E*
+

+If a pattern contains (*MARK) items, an additional line is output whenever
+a change of latest mark is passed to the callout function. For example:
+
+    re> /a(*MARK:X)bc/auto_callout
+  data> abc
+  --->abc
+   +0 ^       a
+   +1 ^^      (*MARK:X)
+  +10 ^^      b
+  Latest Mark: X
+  +11 ^ ^     c
+  +12 ^  ^
+   0: abc
+

+The mark changes between matching "a" and "b", but stays the same for the rest
+of the match, so nothing more is output. If, as a result of backtracking, the
+mark reverts to being unset, the text "<unset>" is output.
+

+

+Callouts with string arguments
+

+

+The output for a callout with a string argument is similar, except that instead
+of outputting a callout number before the position indicators, the callout
+string and its offset in the pattern string are output before the reflection of
+the subject string, and the subject string is reflected for each callout. For
+example:
+
+    re> /^ab(?C'first')cd(?C"second")ef/
+  data> abcdefg
+  Callout (7): 'first'
+  --->abcdefg
+      ^ ^         c
+  Callout (20): "second"
+  --->abcdefg
+      ^   ^       e
+   0: abcdef
+
+

+

+
NON-PRINTING CHARACTERS

+

+When pcre2test is outputting text in the compiled version of a pattern,
+bytes other than 32-126 are always treated as non-printing characters and are
+therefore shown as hex escapes.
+

+

+When pcre2test is outputting text that is a matched part of a subject
+string, it behaves in the same way, unless a different locale has been set for
+the pattern (using the /locale modifier). In this case, the
+isprint() function is used to distinguish printing and non-printing
+characters.
+

+
SAVING AND RESTORING COMPILED PATTERNS

+

+It is possible to save compiled patterns on disc or elsewhere, and reload them
+later, subject to a number of restrictions. JIT data cannot be saved. The host
+on which the patterns are reloaded must be running the same version of PCRE2,
+with the same code unit width, and must also have the same endianness, pointer
+width and PCRE2_SIZE type. Before compiled patterns can be saved they must be
+serialized, that is, converted to a stream of bytes. A single byte stream may
+contain any number of compiled patterns, but they must all use the same
+character tables. A single copy of the tables is included in the byte stream
+(its size is 1088 bytes).
+

+

+The functions whose names begin with pcre2_serialize_ are used
+for serializing and de-serializing. They are described in the
+pcre2serialize
+documentation. In this section we describe the features of pcre2test that
+can be used to test these functions.
+

+

+When a pattern with push modifier is successfully compiled, it is pushed
+onto a stack of compiled patterns, and pcre2test expects the next line to
+contain a new pattern (or command) instead of a subject line. By this means, a
+number of patterns can be compiled and retained. The push modifier is
+incompatible with posix, and control modifiers that act at match time are
+ignored (with a message). The jitverify modifier applies only at compile
+time. The command
+
+  #save <filename>
+

+causes all the stacked patterns to be serialized and the result written to the
+named file. Afterwards, all the stacked patterns are freed. The command
+
+  #load <filename>
+

+reads the data in the file, and then arranges for it to be de-serialized, with
+the resulting compiled patterns added to the pattern stack. The pattern on the
+top of the stack can be retrieved by the #pop command, which must be followed
+by lines of subjects that are to be matched with the pattern, terminated as
+usual by an empty line or end of file. This command may be followed by a
+modifier list containing only
+control modifiers
+that act after a pattern has been compiled. In particular, hex,
+posix, and push are not allowed, nor are any
+option-setting modifiers.
+The JIT modifiers are, however permitted. Here is an example that saves and
+reloads two patterns.
+
+  /abc/push
+  /xyz/push
+  #save tempfile
+  #load tempfile
+  #pop info
+  xyz
+
+  #pop jit,bincode
+  abc
+

+If jitverify is used with #pop, it does not automatically imply
+jit, which is different behaviour from when it is used on a pattern.
+

+
SEE ALSO

+

+pcre2(3), pcre2api(3), pcre2callout(3),
+pcre2jit, pcre2matching(3), pcre2partial(d),
+pcre2pattern(3), pcre2serialize(3).
+

+
AUTHOR

+

+Philip Hazel
+

+University Computing Service
+

+Cambridge, England.
+

+

+
REVISION

+

+Last updated: 20 May 2015
+

+Copyright © 1997-2015 University of Cambridge.
+

+

+Return to the PCRE2 index page.
+

diff --git a/pcre2-10.20/doc/html/pcre2unicode.html b/pcre2-10.20/doc/html/pcre2unicode.html
new file mode 100644
index 000000000..22c1792d9
--- /dev/null
+++ b/pcre2-10.20/doc/html/pcre2unicode.html
@@ -0,0 +1,273 @@
+
+
+pcre2unicode specification
+
+
+
pcre2unicode man page

+

+Return to the PCRE2 index page.
+

+

+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+

+

+UNICODE AND UTF SUPPORT
+

+

+When PCRE2 is built with Unicode support (which is the default), it has
+knowledge of Unicode character properties and can process text strings in
+UTF-8, UTF-16, or UTF-32 format (depending on the code unit width). However, by
+default, PCRE2 assumes that one code unit is one character. To process a
+pattern as a UTF string, where a character may require more than one code unit,
+you must call
+pcre2_compile()
+with the PCRE2_UTF option flag, or the pattern must start with the sequence
+(*UTF). When either of these is the case, both the pattern and any subject
+strings that are matched against it are treated as UTF strings instead of
+strings of individual one-code-unit characters.
+

+

+If you do not need Unicode support you can build PCRE2 without it, in which
+case the library will be smaller.
+

+

+UNICODE PROPERTY SUPPORT
+

+

+When PCRE2 is built with Unicode support, the escape sequences \p{..},
+\P{..}, and \X can be used. The Unicode properties that can be tested are
+limited to the general category properties such as Lu for an upper case letter
+or Nd for a decimal number, the Unicode script names such as Arabic or Han, and
+the derived properties Any and L&. Full lists are given in the
+pcre2pattern
+and
+pcre2syntax
+documentation. Only the short names for properties are supported. For example,
+\p{L} matches a letter. Its Perl synonym, \p{Letter}, is not supported.
+Furthermore, in Perl, many properties may optionally be prefixed by "Is", for
+compatibility with Perl 5.6. PCRE does not support this.
+

+

+WIDE CHARACTERS AND UTF MODES
+

+

+Codepoints less than 256 can be specified in patterns by either braced or
+unbraced hexadecimal escape sequences (for example, \x{b3} or \xb3). Larger
+values have to use braced sequences. Unbraced octal code points up to \777 are
+also recognized; larger ones can be coded using \o{...}.
+

+

+In UTF modes, repeat quantifiers apply to complete UTF characters, not to
+individual code units.
+

+

+In UTF modes, the dot metacharacter matches one UTF character instead of a
+single code unit.
+

+

+The escape sequence \C can be used to match a single code unit, in a UTF mode,
+but its use can lead to some strange effects because it breaks up multi-unit
+characters (see the description of \C in the
+pcre2pattern
+documentation). The use of \C is not supported in the alternative matching
+function pcre2_dfa_match(), nor is it supported in UTF mode by the JIT
+optimization. If JIT optimization is requested for a UTF pattern that contains
+\C, it will not succeed, and so the matching will be carried out by the normal
+interpretive function.
+

+

+The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly test
+characters of any code value, but, by default, the characters that PCRE2
+recognizes as digits, spaces, or word characters remain the same set as in
+non-UTF mode, all with code points less than 256. This remains true even when
+PCRE2 is built to include Unicode support, because to do otherwise would slow
+down matching in many common cases. Note that this also applies to \b
+and \B, because they are defined in terms of \w and \W. If you want
+to test for a wider sense of, say, "digit", you can use explicit Unicode
+property tests such as \p{Nd}. Alternatively, if you set the PCRE2_UCP option,
+the way that the character escapes work is changed so that Unicode properties
+are used to determine which characters match. There are more details in the
+section on
+generic character types
+in the
+pcre2pattern
+documentation.
+

+

+Similarly, characters that match the POSIX named character classes are all
+low-valued characters, unless the PCRE2_UCP option is set.
+

+

+However, the special horizontal and vertical white space matching escapes (\h,
+\H, \v, and \V) do match all the appropriate Unicode characters, whether or
+not PCRE2_UCP is set.
+

+

+Case-insensitive matching in UTF mode makes use of Unicode properties. A few
+Unicode characters such as Greek sigma have more than two codepoints that are
+case-equivalent, and these are treated as such.
+

+

+VALIDITY OF UTF STRINGS
+

+

+When the PCRE2_UTF option is set, the strings passed as patterns and subjects
+are (by default) checked for validity on entry to the relevant functions.
+If an invalid UTF string is passed, an negative error code is returned. The
+code unit offset to the offending character can be extracted from the match
+data block by calling pcre2_get_startchar(), which is used for this
+purpose after a UTF error.
+

+

+UTF-16 and UTF-32 strings can indicate their endianness by special code knows
+as a byte-order mark (BOM). The PCRE2 functions do not handle this, expecting
+strings to be in host byte order.
+

+

+The entire string is checked before any other processing takes place. In
+addition to checking the format of the string, there is a check to ensure that
+all code points lie in the range U+0 to U+10FFFF, excluding the surrogate area.
+The so-called "non-character" code points are not excluded because Unicode
+corrigendum #9 makes it clear that they should not be.
+

+

+Characters in the "Surrogate Area" of Unicode are reserved for use by UTF-16,
+where they are used in pairs to encode code points with values greater than
+0xFFFF. The code points that are encoded by UTF-16 pairs are available
+independently in the UTF-8 and UTF-32 encodings. (In other words, the whole
+surrogate thing is a fudge for UTF-16 which unfortunately messes up UTF-8 and
+UTF-32.)
+

+

+In some situations, you may already know that your strings are valid, and
+therefore want to skip these checks in order to improve performance, for
+example in the case of a long subject string that is being scanned repeatedly.
+If you set the PCRE2_NO_UTF_CHECK option at compile time or at match time,
+PCRE2 assumes that the pattern or subject it is given (respectively) contains
+only valid UTF code unit sequences.
+

+

+Passing PCRE2_NO_UTF_CHECK to pcre2_compile() just disables the check for
+the pattern; it does not also apply to subject strings. If you want to disable
+the check for a subject string you must pass this option to pcre2_match()
+or pcre2_dfa_match().
+

+

+If you pass an invalid UTF string when PCRE2_NO_UTF_CHECK is set, the result
+is undefined and your program may crash or loop indefinitely.
+

+

+Errors in UTF-8 strings
+

+

+The following negative error codes are given for invalid UTF-8 strings:
+
+  PCRE2_ERROR_UTF8_ERR1
+  PCRE2_ERROR_UTF8_ERR2
+  PCRE2_ERROR_UTF8_ERR3
+  PCRE2_ERROR_UTF8_ERR4
+  PCRE2_ERROR_UTF8_ERR5
+

+The string ends with a truncated UTF-8 character; the code specifies how many
+bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 characters to be
+no longer than 4 bytes, the encoding scheme (originally defined by RFC 2279)
+allows for up to 6 bytes, and this is checked first; hence the possibility of
+4 or 5 missing bytes.
+
+  PCRE2_ERROR_UTF8_ERR6
+  PCRE2_ERROR_UTF8_ERR7
+  PCRE2_ERROR_UTF8_ERR8
+  PCRE2_ERROR_UTF8_ERR9
+  PCRE2_ERROR_UTF8_ERR10
+

+The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of the
+character do not have the binary value 0b10 (that is, either the most
+significant bit is 0, or the next bit is 1).
+
+  PCRE2_ERROR_UTF8_ERR11
+  PCRE2_ERROR_UTF8_ERR12
+

+A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long;
+these code points are excluded by RFC 3629.
+
+  PCRE2_ERROR_UTF8_ERR13
+

+A 4-byte character has a value greater than 0x10fff; these code points are
+excluded by RFC 3629.
+
+  PCRE2_ERROR_UTF8_ERR14
+

+A 3-byte character has a value in the range 0xd800 to 0xdfff; this range of
+code points are reserved by RFC 3629 for use with UTF-16, and so are excluded
+from UTF-8.
+
+  PCRE2_ERROR_UTF8_ERR15
+  PCRE2_ERROR_UTF8_ERR16
+  PCRE2_ERROR_UTF8_ERR17
+  PCRE2_ERROR_UTF8_ERR18
+  PCRE2_ERROR_UTF8_ERR19
+

+A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes for a
+value that can be represented by fewer bytes, which is invalid. For example,
+the two bytes 0xc0, 0xae give the value 0x2e, whose correct coding uses just
+one byte.
+
+  PCRE2_ERROR_UTF8_ERR20
+

+The two most significant bits of the first byte of a character have the binary
+value 0b10 (that is, the most significant bit is 1 and the second is 0). Such a
+byte can only validly occur as the second or subsequent byte of a multi-byte
+character.
+
+  PCRE2_ERROR_UTF8_ERR21
+

+The first byte of a character has the value 0xfe or 0xff. These values can
+never occur in a valid UTF-8 string.
+

+

+Errors in UTF-16 strings
+

+

+The following negative error codes are given for invalid UTF-16 strings:
+
+  PCRE_UTF16_ERR1  Missing low surrogate at end of string
+  PCRE_UTF16_ERR2  Invalid low surrogate follows high surrogate
+  PCRE_UTF16_ERR3  Isolated low surrogate
+
+

+

+

+Errors in UTF-32 strings
+

+

+The following negative error codes are given for invalid UTF-32 strings:
+
+  PCRE_UTF32_ERR1  Surrogate character (range from 0xd800 to 0xdfff)
+  PCRE_UTF32_ERR2  Code point is greater than 0x10ffff
+
+

+

+

+AUTHOR
+

+

+Philip Hazel
+

+University Computing Service
+

+Cambridge, England.
+

+

+

+REVISION
+

+

+Last updated: 23 November 2014
+

+Copyright © 1997-2014 University of Cambridge.
+

+

+Return to the PCRE2 index page.
+

diff --git a/pcre2-10.20/doc/index.html.src b/pcre2-10.20/doc/index.html.src
new file mode 100644
index 000000000..ae938fd3c
--- /dev/null
+++ b/pcre2-10.20/doc/index.html.src
@@ -0,0 +1,264 @@
+
+
+
+PCRE2 specification
+
+
+
Perl-compatible Regular Expressions (revised API: PCRE2)

+

+The HTML documentation for PCRE2 consists of a number of pages that are listed
+below in alphabetical order. If you are new to PCRE2, please read the first one
+first.
+

+
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
pcre2  Introductory page
pcre2-config  Information about the installation configuration
pcre2api  PCRE2's native API
pcre2build  Building PCRE2
pcre2callout  The callout facility
pcre2compat  Compability with Perl
pcre2demo  A demonstration C program that uses the PCRE2 library
pcre2grep  The pcre2grep command
pcre2jit  Discussion of the just-in-time optimization support
pcre2limits  Details of size and other limits
pcre2matching  Discussion of the two matching algorithms
pcre2partial  Using PCRE2 for partial matching
pcre2pattern  Specification of the regular expressions supported by PCRE2
pcre2perform  Some comments on performance
pcre2posix  The POSIX API to the PCRE2 8-bit library
pcre2sample  Discussion of the pcre2demo program
pcre2serialize  Serializing functions for saving precompiled patterns
pcre2stack  Discussion of PCRE2's stack usage
pcre2syntax  Syntax quick-reference summary
pcre2test  The pcre2test command for testing PCRE2
pcre2unicode  Discussion of Unicode and UTF-8/UTF-16/UTF-32 support

+
+

+There are also individual pages that summarize the interface for each function
+in the library.
+

+
+
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
+
+    
+
pcre2_callout_enumerate  Enumerate callouts in a compiled pattern
pcre2_code_free  Free a compiled pattern
pcre2_compile  Compile a regular expression pattern
pcre2_compile_context_copy  Copy a compile context
pcre2_compile_context_create  Create a compile context
pcre2_compile_context_free  Free a compile context
pcre2_config  Show build-time configuration options
pcre2_dfa_match  Match a compiled pattern to a subject string
+    (DFA algorithm; not Perl compatible)
pcre2_general_context_copy  Copy a general context
pcre2_general_context_create  Create a general context
pcre2_general_context_free  Free a general context
pcre2_get_error_message  Free study data
pcre2_get_mark  Get a (*MARK) name
pcre2_get_ovector_count  Get the ovector count
pcre2_get_ovector_pointer  Get a pointer to the ovector
pcre2_get_startchar  Get the starting character offset
pcre2_jit_compile  Process a compiled pattern with the JIT compiler
pcre2_jit_free_unused_memory  Free unused JIT memory
pcre2_jit_match  Fast path interface to JIT matching
pcre2_jit_stack_assign  Assign stack for JIT matching
pcre2_jit_stack_create  Create a stack for JIT matching
pcre2_jit_stack_free  Free a JIT matching stack
pcre2_maketables  Build character tables in current locale
pcre2_match  Match a compiled pattern to a subject string
+    (Perl compatible)
pcre2_match_context_copy  Copy a match context
pcre2_match_context_create  Create a match context
pcre2_match_context_free  Free a match context
pcre2_match_data_create  Create a match data block
pcre2_match_data_create_from_pattern  Create a match data block getting size from pattern
pcre2_match_data_free  Free a match data block
pcre2_pattern_info  Extract information about a pattern
pcre2_serialize_decode  Decode serialized compiled patterns
pcre2_serialize_encode  Serialize compiled patterns for save/restore
pcre2_serialize_free  Free serialized compiled patterns
pcre2_serialize_get_number_of_codes  Get number of serialized compiled patterns
pcre2_set_bsr  Set \R convention
pcre2_set_callout  Set up a callout function
pcre2_set_character_tables  Set character tables
pcre2_set_compile_recursion_guard  Set up a compile recursion guard function
pcre2_set_match_limit  Set the match limit
pcre2_set_newline  Set the newline convention
pcre2_set_parens_nest_limit  Set the parentheses nesting limit
pcre2_set_recursion_limit  Set the match recursion limit
pcre2_set_recursion_memory_management  Set match recursion memory management
pcre2_substitute  Match a compiled pattern to a subject string and do
+    substitutions
pcre2_substring_copy_byname  Extract named substring into given buffer
pcre2_substring_copy_bynumber  Extract numbered substring into given buffer
pcre2_substring_free  Free extracted substring
pcre2_substring_get_byname  Extract named substring into new memory
pcre2_substring_get_bynumber  Extract numbered substring into new memory
pcre2_substring_length_byname  Find length of named substring
pcre2_substring_length_bynumber  Find length of numbered substring
pcre2_substring_list_free  Free list of extracted substrings
pcre2_substring_list_get  Extract all substrings into new memory
pcre2_substring_nametable_scan  Find table entries for given string name
pcre2_substring_number_from_name  Convert captured string name to number

+
+
+
diff --git a/pcre2-10.20/doc/pcre2-config.1 b/pcre2-10.20/doc/pcre2-config.1
new file mode 100644
index 000000000..7fa0a0912
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2-config.1
@@ -0,0 +1,86 @@
+.TH PCRE2-CONFIG 1 "28 September 2014" "PCRE2 10.00"
+.SH NAME
+pcre2-config - program to return PCRE2 configuration
+.SH SYNOPSIS
+.rs
+.sp
+.nf
+.B pcre2-config  [--prefix] [--exec-prefix] [--version]
+.B "             [--libs8] [--libs16] [--libs32] [--libs-posix]"
+.B "             [--cflags] [--cflags-posix]"
+.fi
+.
+.
+.SH DESCRIPTION
+.rs
+.sp
+\fBpcre2-config\fP returns the configuration of the installed PCRE2 libraries
+and the options required to compile a program to use them. Some of the options
+apply only to the 8-bit, or 16-bit, or 32-bit libraries, respectively, and are
+not available for libraries that have not been built. If an unavailable option
+is encountered, the "usage" information is output.
+.
+.
+.SH OPTIONS
+.rs
+.TP 10
+\fB--prefix\fP
+Writes the directory prefix used in the PCRE2 installation for architecture
+independent files (\fI/usr\fP on many systems, \fI/usr/local\fP on some
+systems) to the standard output.
+.TP 10
+\fB--exec-prefix\fP
+Writes the directory prefix used in the PCRE2 installation for architecture
+dependent files (normally the same as \fB--prefix\fP) to the standard output.
+.TP 10
+\fB--version\fP
+Writes the version number of the installed PCRE2 libraries to the standard
+output.
+.TP 10
+\fB--libs8\fP
+Writes to the standard output the command line options required to link
+with the 8-bit PCRE2 library (\fB-lpcre2-8\fP on many systems).
+.TP 10
+\fB--libs16\fP
+Writes to the standard output the command line options required to link
+with the 16-bit PCRE2 library (\fB-lpcre2-16\fP on many systems).
+.TP 10
+\fB--libs32\fP
+Writes to the standard output the command line options required to link
+with the 32-bit PCRE2 library (\fB-lpcre2-32\fP on many systems).
+.TP 10
+\fB--libs-posix\fP
+Writes to the standard output the command line options required to link with
+PCRE2's POSIX API wrapper library (\fB-lpcre2-posix\fP \fB-lpcre2-8\fP on many
+systems).
+.TP 10
+\fB--cflags\fP
+Writes to the standard output the command line options required to compile
+files that use PCRE2 (this may include some \fB-I\fP options, but is blank on
+many systems).
+.TP 10
+\fB--cflags-posix\fP
+Writes to the standard output the command line options required to compile
+files that use PCRE2's POSIX API wrapper library (this may include some
+\fB-I\fP options, but is blank on many systems).
+.
+.
+.SH "SEE ALSO"
+.rs
+.sp
+\fBpcre2(3)\fP
+.
+.
+.SH AUTHOR
+.rs
+.sp
+This manual page was originally written by Mark Baker for the Debian GNU/Linux
+system. It has been subsequently revised as a generic PCRE2 man page.
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 28 September 2014
+.fi
diff --git a/pcre2-10.20/doc/pcre2-config.txt b/pcre2-10.20/doc/pcre2-config.txt
new file mode 100644
index 000000000..8ddea2a3a
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2-config.txt
@@ -0,0 +1,81 @@
+PCRE2-CONFIG(1)             General Commands Manual            PCRE2-CONFIG(1)
+
+
+
+NAME
+       pcre2-config - program to return PCRE2 configuration
+
+SYNOPSIS
+
+       pcre2-config [--prefix] [--exec-prefix] [--version]
+                    [--libs8] [--libs16] [--libs32] [--libs-posix]
+                    [--cflags] [--cflags-posix]
+
+
+DESCRIPTION
+
+       pcre2-config returns the configuration of the installed PCRE2 libraries
+       and the options required to compile a program to use them. Some of  the
+       options  apply  only  to  the  8-bit,  or  16-bit, or 32-bit libraries,
+       respectively, and are not available for libraries that  have  not  been
+       built. If an unavailable option is encountered, the "usage" information
+       is output.
+
+
+OPTIONS
+
+       --prefix  Writes the directory prefix used in  the  PCRE2  installation
+                 for  architecture  independent  files  (/usr on many systems,
+                 /usr/local on some systems) to the standard output.
+
+       --exec-prefix
+                 Writes the directory prefix used in  the  PCRE2  installation
+                 for architecture dependent files (normally the same as --pre-
+                 fix) to the standard output.
+
+       --version Writes the version number of the installed PCRE2 libraries to
+                 the standard output.
+
+       --libs8   Writes  to  the  standard  output  the  command  line options
+                 required to link with the 8-bit PCRE2 library  (-lpcre2-8  on
+                 many systems).
+
+       --libs16  Writes  to  the  standard  output  the  command  line options
+                 required to link with the 16-bit PCRE2 library (-lpcre2-16 on
+                 many systems).
+
+       --libs32  Writes  to  the  standard  output  the  command  line options
+                 required to link with the 32-bit PCRE2 library (-lpcre2-32 on
+                 many systems).
+
+       --libs-posix
+                 Writes  to  the  standard  output  the  command  line options
+                 required to link  with  PCRE2's  POSIX  API  wrapper  library
+                 (-lpcre2-posix -lpcre2-8 on many systems).
+
+       --cflags  Writes  to  the  standard  output  the  command  line options
+                 required to compile files that use PCRE2  (this  may  include
+                 some -I options, but is blank on many systems).
+
+       --cflags-posix
+                 Writes  to  the  standard  output  the  command  line options
+                 required to compile files that use PCRE2's POSIX API  wrapper
+                 library  (this  may  include some -I options, but is blank on
+                 many systems).
+
+
+SEE ALSO
+
+       pcre2(3)
+
+
+AUTHOR
+
+       This manual page was originally written by Mark Baker  for  the  Debian
+       GNU/Linux  system.  It has been subsequently revised as a generic PCRE2
+       man page.
+
+
+REVISION
+
+       Last updated: 28 September 2014
diff --git a/pcre2-10.20/doc/pcre2.3 b/pcre2-10.20/doc/pcre2.3
new file mode 100644
index 000000000..e315bbb60
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2.3
@@ -0,0 +1,192 @@
+.TH PCRE2 3 "13 April 2015" "PCRE2 10.20"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH INTRODUCTION
+.rs
+.sp
+PCRE2 is the name used for a revised API for the PCRE library, which is a set
+of functions, written in C, that implement regular expression pattern matching
+using the same syntax and semantics as Perl, with just a few differences. Some
+features that appeared in Python and the original PCRE before they appeared in
+Perl are also available using the Python syntax. There is also some support for
+one or two .NET and Oniguruma syntax items, and there are options for
+requesting some minor changes that give better ECMAScript (aka JavaScript)
+compatibility.
+.P
+The source code for PCRE2 can be compiled to support 8-bit, 16-bit, or 32-bit
+code units, which means that up to three separate libraries may be installed.
+The original work to extend PCRE to 16-bit and 32-bit code units was done by
+Zoltan Herczeg and Christian Persch, respectively. In all three cases, strings
+can be interpreted either as one character per code unit, or as UTF-encoded
+Unicode, with support for Unicode general category properties. Unicode support
+is optional at build time (but is the default). However, processing strings as
+UTF code units must be enabled explicitly at run time. The version of Unicode
+in use can be discovered by running
+.sp
+  pcre2test -C
+.P
+The three libraries contain identical sets of functions, with names ending in
+_8, _16, or _32, respectively (for example, \fBpcre2_compile_8()\fP). However,
+by defining PCRE2_CODE_UNIT_WIDTH to be 8, 16, or 32, a program that uses just
+one code unit width can be written using generic names such as
+\fBpcre2_compile()\fP, and the documentation is written assuming that this is
+the case.
+.P
+In addition to the Perl-compatible matching function, PCRE2 contains an
+alternative function that matches the same compiled patterns in a different
+way. In certain circumstances, the alternative function has some advantages.
+For a discussion of the two matching algorithms, see the
+.\" HREF
+\fBpcre2matching\fP
+.\"
+page.
+.P
+Details of exactly which Perl regular expression features are and are not
+supported by PCRE2 are given in separate documents. See the
+.\" HREF
+\fBpcre2pattern\fP
+.\"
+and
+.\" HREF
+\fBpcre2compat\fP
+.\"
+pages. There is a syntax summary in the
+.\" HREF
+\fBpcre2syntax\fP
+.\"
+page.
+.P
+Some features of PCRE2 can be included, excluded, or changed when the library
+is built. The
+.\" HREF
+\fBpcre2_config()\fP
+.\"
+function makes it possible for a client to discover which features are
+available. The features themselves are described in the
+.\" HREF
+\fBpcre2build\fP
+.\"
+page. Documentation about building PCRE2 for various operating systems can be
+found in the
+.\" HTML 
+.\" 
+\fBREADME\fP
+.\"
+and
+.\" HTML 
+.\" 
+\fBNON-AUTOTOOLS_BUILD\fP
+.\"
+files in the source distribution.
+.P
+The libraries contains a number of undocumented internal functions and data
+tables that are used by more than one of the exported external functions, but
+which are not intended for use by external callers. Their names all begin with
+"_pcre2", which hopefully will not provoke any name clashes. In some
+environments, it is possible to control which external symbols are exported
+when a shared library is built, and in these cases the undocumented symbols are
+not exported.
+.
+.
+.SH "SECURITY CONSIDERATIONS"
+.rs
+.sp
+If you are using PCRE2 in a non-UTF application that permits users to supply
+arbitrary patterns for compilation, you should be aware of a feature that
+allows users to turn on UTF support from within a pattern. For example, an
+8-bit pattern that begins with "(*UTF)" turns on UTF-8 mode, which interprets
+patterns and subjects as strings of UTF-8 code units instead of individual
+8-bit characters. This causes both the pattern and any data against which it is
+matched to be checked for UTF-8 validity. If the data string is very long, such
+a check might use sufficiently many resources as to cause your application to
+lose performance.
+.P
+One way of guarding against this possibility is to use the
+\fBpcre2_pattern_info()\fP function to check the compiled pattern's options for
+PCRE2_UTF. Alternatively, you can set the PCRE2_NEVER_UTF option when calling
+\fBpcre2_compile()\fP. This causes an compile time error if a pattern contains
+a UTF-setting sequence.
+.P
+The use of Unicode properties for character types such as \ed can also be
+enabled from within the pattern, by specifying "(*UCP)". This feature can be
+disallowed by setting the PCRE2_NEVER_UCP option.
+.P
+If your application is one that supports UTF, be aware that validity checking
+can take time. If the same data string is to be matched many times, you can use
+the PCRE2_NO_UTF_CHECK option for the second and subsequent matches to avoid
+running redundant checks.
+.P
+The use of the \eC escape sequence in a UTF-8 or UTF-16 pattern can lead to
+problems, because it may leave the current matching point in the middle of a
+multi-code-unit character. The PCRE2_NEVER_BACKSLASH_C option can be used to
+lock out the use of \eC, causing a compile-time error if it is encountered.
+.P
+Another way that performance can be hit is by running a pattern that has a very
+large search tree against a string that will never match. Nested unlimited
+repeats in a pattern are a common example. PCRE2 provides some protection
+against this: see the \fBpcre2_set_match_limit()\fP function in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page.
+.
+.
+.SH "USER DOCUMENTATION"
+.rs
+.sp
+The user documentation for PCRE2 comprises a number of different sections. In
+the "man" format, each of these is a separate "man page". In the HTML format,
+each is a separate page, linked from the index page. In the plain text format,
+the descriptions of the \fBpcre2grep\fP and \fBpcre2test\fP programs are in
+files called \fBpcre2grep.txt\fP and \fBpcre2test.txt\fP, respectively. The
+remaining sections, except for the \fBpcre2demo\fP section (which is a program
+listing), and the short pages for individual functions, are concatenated in
+\fBpcre2.txt\fP, for ease of searching. The sections are as follows:
+.sp
+  pcre2              this document
+  pcre2-config       show PCRE2 installation configuration information
+  pcre2api           details of PCRE2's native C API
+  pcre2build         building PCRE2
+  pcre2callout       details of the callout feature
+  pcre2compat        discussion of Perl compatibility
+  pcre2demo          a demonstration C program that uses PCRE2
+  pcre2grep          description of the \fBpcre2grep\fP command (8-bit only)
+  pcre2jit           discussion of just-in-time optimization support
+  pcre2limits        details of size and other limits
+  pcre2matching      discussion of the two matching algorithms
+  pcre2partial       details of the partial matching facility
+.\" JOIN
+  pcre2pattern       syntax and semantics of supported regular
+                       expression patterns
+  pcre2perform       discussion of performance issues
+  pcre2posix         the POSIX-compatible C API for the 8-bit library
+  pcre2sample        discussion of the pcre2demo program
+  pcre2stack         discussion of stack usage
+  pcre2syntax        quick syntax reference
+  pcre2test          description of the \fBpcre2test\fP command
+  pcre2unicode       discussion of Unicode and UTF support
+.sp
+In the "man" and HTML formats, there is also a short page for each C library
+function, listing its arguments and results.
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel
+University Computing Service
+Cambridge, England.
+.fi
+.P
+Putting an actual email address here is a spam magnet. If you want to email me,
+use my two initials, followed by the two digits 10, at the domain cam.ac.uk.
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 13 April 2015
+Copyright (c) 1997-2015 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/doc/pcre2.txt b/pcre2-10.20/doc/pcre2.txt
new file mode 100644
index 000000000..3193d3054
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2.txt
@@ -0,0 +1,5199 @@
+-----------------------------------------------------------------------------
+This file contains a concatenation of the PCRE2 man pages, converted to plain
+text format for ease of searching with a text editor, or for use on systems
+that do not have a man page processor. The small individual files that give
+synopses of each function in the library have not been included. Neither has
+the pcre2demo program. There are separate text files for the pcre2grep and
+pcre2test commands.
+-----------------------------------------------------------------------------
+
+
+PCRE2(3)                   Library Functions Manual                   PCRE2(3)
+
+
+
+NAME
+       PCRE2 - Perl-compatible regular expressions (revised API)
+
+INTRODUCTION
+
+       PCRE2 is the name used for a revised API for the PCRE library, which is
+       a set of functions, written in C,  that  implement  regular  expression
+       pattern matching using the same syntax and semantics as Perl, with just
+       a few differences. Some features that appeared in Python and the origi-
+       nal  PCRE  before  they  appeared  in Perl are also available using the
+       Python syntax. There is also some support for one or two .NET and Onig-
+       uruma  syntax  items,  and  there are options for requesting some minor
+       changes that give better ECMAScript (aka JavaScript) compatibility.
+
+       The source code for PCRE2 can be compiled to support 8-bit, 16-bit,  or
+       32-bit  code units, which means that up to three separate libraries may
+       be installed.  The original work to extend PCRE to  16-bit  and  32-bit
+       code  units  was  done  by Zoltan Herczeg and Christian Persch, respec-
+       tively. In all three cases, strings can be interpreted  either  as  one
+       character  per  code  unit, or as UTF-encoded Unicode, with support for
+       Unicode general category properties. Unicode  support  is  optional  at
+       build  time  (but  is  the default). However, processing strings as UTF
+       code units must be enabled explicitly at run time. The version of  Uni-
+       code in use can be discovered by running
+
+         pcre2test -C
+
+       The  three  libraries  contain  identical sets of functions, with names
+       ending in _8,  _16,  or  _32,  respectively  (for  example,  pcre2_com-
+       pile_8()).  However,  by defining PCRE2_CODE_UNIT_WIDTH to be 8, 16, or
+       32, a program that uses just one code unit width can be  written  using
+       generic names such as pcre2_compile(), and the documentation is written
+       assuming that this is the case.
+
+       In addition to the Perl-compatible matching function, PCRE2 contains an
+       alternative  function that matches the same compiled patterns in a dif-
+       ferent way. In certain circumstances, the alternative function has some
+       advantages.   For  a discussion of the two matching algorithms, see the
+       pcre2matching page.
+
+       Details of exactly which Perl regular expression features are  and  are
+       not  supported  by  PCRE2  are  given  in  separate  documents. See the
+       pcre2pattern and pcre2compat pages. There is a syntax  summary  in  the
+       pcre2syntax page.
+
+       Some  features  of PCRE2 can be included, excluded, or changed when the
+       library is built. The pcre2_config() function makes it possible  for  a
+       client  to  discover  which  features are available. The features them-
+       selves are described in the pcre2build page. Documentation about build-
+       ing  PCRE2 for various operating systems can be found in the README and
+       NON-AUTOTOOLS_BUILD files in the source distribution.
+
+       The libraries contains a number of undocumented internal functions  and
+       data  tables  that  are  used by more than one of the exported external
+       functions, but which are not intended  for  use  by  external  callers.
+       Their  names  all begin with "_pcre2", which hopefully will not provoke
+       any name clashes. In some environments, it is possible to control which
+       external  symbols  are  exported when a shared library is built, and in
+       these cases the undocumented symbols are not exported.
+
+
+SECURITY CONSIDERATIONS
+
+       If you are using PCRE2 in a non-UTF application that permits  users  to
+       supply  arbitrary  patterns  for  compilation, you should be aware of a
+       feature that allows users to turn on UTF support from within a pattern.
+       For  example, an 8-bit pattern that begins with "(*UTF)" turns on UTF-8
+       mode, which interprets patterns and subjects as strings of  UTF-8  code
+       units instead of individual 8-bit characters. This causes both the pat-
+       tern and any data against which it is matched to be checked  for  UTF-8
+       validity.  If the data string is very long, such a check might use suf-
+       ficiently many resources as to cause your application to  lose  perfor-
+       mance.
+
+       One  way  of guarding against this possibility is to use the pcre2_pat-
+       tern_info() function  to  check  the  compiled  pattern's  options  for
+       PCRE2_UTF.  Alternatively,  you can set the PCRE2_NEVER_UTF option when
+       calling pcre2_compile(). This causes an compile time error if a pattern
+       contains a UTF-setting sequence.
+
+       The  use  of Unicode properties for character types such as \d can also
+       be enabled from within the pattern, by specifying "(*UCP)".  This  fea-
+       ture can be disallowed by setting the PCRE2_NEVER_UCP option.
+
+       If  your  application  is one that supports UTF, be aware that validity
+       checking can take time. If the same data string is to be  matched  many
+       times,  you  can  use  the PCRE2_NO_UTF_CHECK option for the second and
+       subsequent matches to avoid running redundant checks.
+
+       The use of the \C escape sequence in a UTF-8 or UTF-16 pattern can lead
+       to  problems,  because  it  may leave the current matching point in the
+       middle of  a  multi-code-unit  character.  The  PCRE2_NEVER_BACKSLASH_C
+       option  can  be  used to lock out the use of \C, causing a compile-time
+       error if it is encountered.
+
+       Another way that performance can be hit is by running  a  pattern  that
+       has  a  very  large search tree against a string that will never match.
+       Nested unlimited repeats in a pattern are a common example. PCRE2  pro-
+       vides  some  protection  against  this: see the pcre2_set_match_limit()
+       function in the pcre2api page.
+
+
+USER DOCUMENTATION
+
+       The user documentation for PCRE2 comprises a number of  different  sec-
+       tions.  In the "man" format, each of these is a separate "man page". In
+       the HTML format, each is a separate page, linked from the  index  page.
+       In  the  plain  text  format,  the  descriptions  of  the pcre2grep and
+       pcre2test programs are in files called pcre2grep.txt and pcre2test.txt,
+       respectively.  The remaining sections, except for the pcre2demo section
+       (which is a program listing), and the short pages for individual  func-
+       tions,  are  concatenated in pcre2.txt, for ease of searching. The sec-
+       tions are as follows:
+
+         pcre2              this document
+         pcre2-config       show PCRE2 installation configuration information
+         pcre2api           details of PCRE2's native C API
+         pcre2build         building PCRE2
+         pcre2callout       details of the callout feature
+         pcre2compat        discussion of Perl compatibility
+         pcre2demo          a demonstration C program that uses PCRE2
+         pcre2grep          description of the pcre2grep command (8-bit only)
+         pcre2jit           discussion of just-in-time optimization support
+         pcre2limits        details of size and other limits
+         pcre2matching      discussion of the two matching algorithms
+         pcre2partial       details of the partial matching facility
+         pcre2pattern       syntax and semantics of supported regular
+                              expression patterns
+         pcre2perform       discussion of performance issues
+         pcre2posix         the POSIX-compatible C API for the 8-bit library
+         pcre2sample        discussion of the pcre2demo program
+         pcre2stack         discussion of stack usage
+         pcre2syntax        quick syntax reference
+         pcre2test          description of the pcre2test command
+         pcre2unicode       discussion of Unicode and UTF support
+
+       In the "man" and HTML formats, there is also a short page  for  each  C
+       library function, listing its arguments and results.
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge, England.
+
+       Putting  an  actual email address here is a spam magnet. If you want to
+       email me, use my two initials, followed by the two digits  10,  at  the
+       domain cam.ac.uk.
+
+
+REVISION
+
+       Last updated: 13 April 2015
+       Copyright (c) 1997-2015 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCRE2API(3)                Library Functions Manual                PCRE2API(3)
+
+
+
+NAME
+       PCRE2 - Perl-compatible regular expressions (revised API)
+
+       #include 
+
+       PCRE2  is  a  new API for PCRE. This document contains a description of
+       all its functions. See the pcre2 document for an overview  of  all  the
+       PCRE2 documentation.
+
+
+PCRE2 NATIVE API BASIC FUNCTIONS
+
+       pcre2_code *pcre2_compile(PCRE2_SPTR pattern, PCRE2_SIZE length,
+         uint32_t options, int *errorcode, PCRE2_SIZE *erroroffset,
+         pcre2_compile_context *ccontext);
+
+       pcre2_code_free(pcre2_code *code);
+
+       pcre2_match_data_create(uint32_t ovecsize,
+         pcre2_general_context *gcontext);
+
+       pcre2_match_data_create_from_pattern(const pcre2_code *code,
+         pcre2_general_context *gcontext);
+
+       int pcre2_match(const pcre2_code *code, PCRE2_SPTR subject,
+         PCRE2_SIZE length, PCRE2_SIZE startoffset,
+         uint32_t options, pcre2_match_data *match_data,
+         pcre2_match_context *mcontext);
+
+       int pcre2_dfa_match(const pcre2_code *code, PCRE2_SPTR subject,
+         PCRE2_SIZE length, PCRE2_SIZE startoffset,
+         uint32_t options, pcre2_match_data *match_data,
+         pcre2_match_context *mcontext,
+         int *workspace, PCRE2_SIZE wscount);
+
+       void pcre2_match_data_free(pcre2_match_data *match_data);
+
+
+PCRE2 NATIVE API AUXILIARY MATCH FUNCTIONS
+
+       PCRE2_SPTR pcre2_get_mark(pcre2_match_data *match_data);
+
+       uint32_t pcre2_get_ovector_count(pcre2_match_data *match_data);
+
+       PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *match_data);
+
+       PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *match_data);
+
+
+PCRE2 NATIVE API GENERAL CONTEXT FUNCTIONS
+
+       pcre2_general_context *pcre2_general_context_create(
+         void *(*private_malloc)(PCRE2_SIZE, void *),
+         void (*private_free)(void *, void *), void *memory_data);
+
+       pcre2_general_context *pcre2_general_context_copy(
+         pcre2_general_context *gcontext);
+
+       void pcre2_general_context_free(pcre2_general_context *gcontext);
+
+
+PCRE2 NATIVE API COMPILE CONTEXT FUNCTIONS
+
+       pcre2_compile_context *pcre2_compile_context_create(
+         pcre2_general_context *gcontext);
+
+       pcre2_compile_context *pcre2_compile_context_copy(
+         pcre2_compile_context *ccontext);
+
+       void pcre2_compile_context_free(pcre2_compile_context *ccontext);
+
+       int pcre2_set_bsr(pcre2_compile_context *ccontext,
+         uint32_t value);
+
+       int pcre2_set_character_tables(pcre2_compile_context *ccontext,
+         const unsigned char *tables);
+
+       int pcre2_set_newline(pcre2_compile_context *ccontext,
+         uint32_t value);
+
+       int pcre2_set_parens_nest_limit(pcre2_compile_context *ccontext,
+         uint32_t value);
+
+       int pcre2_set_compile_recursion_guard(pcre2_compile_context *ccontext,
+         int (*guard_function)(uint32_t, void *), void *user_data);
+
+
+PCRE2 NATIVE API MATCH CONTEXT FUNCTIONS
+
+       pcre2_match_context *pcre2_match_context_create(
+         pcre2_general_context *gcontext);
+
+       pcre2_match_context *pcre2_match_context_copy(
+         pcre2_match_context *mcontext);
+
+       void pcre2_match_context_free(pcre2_match_context *mcontext);
+
+       int pcre2_set_callout(pcre2_match_context *mcontext,
+         int (*callout_function)(pcre2_callout_block *, void *),
+         void *callout_data);
+
+       int pcre2_set_match_limit(pcre2_match_context *mcontext,
+         uint32_t value);
+
+       int pcre2_set_recursion_limit(pcre2_match_context *mcontext,
+         uint32_t value);
+
+       int pcre2_set_recursion_memory_management(
+         pcre2_match_context *mcontext,
+         void *(*private_malloc)(PCRE2_SIZE, void *),
+         void (*private_free)(void *, void *), void *memory_data);
+
+
+PCRE2 NATIVE API STRING EXTRACTION FUNCTIONS
+
+       int pcre2_substring_copy_byname(pcre2_match_data *match_data,
+         PCRE2_SPTR name, PCRE2_UCHAR *buffer, PCRE2_SIZE *bufflen);
+
+       int pcre2_substring_copy_bynumber(pcre2_match_data *match_data,
+         uint32_t number, PCRE2_UCHAR *buffer,
+         PCRE2_SIZE *bufflen);
+
+       void pcre2_substring_free(PCRE2_UCHAR *buffer);
+
+       int pcre2_substring_get_byname(pcre2_match_data *match_data,
+         PCRE2_SPTR name, PCRE2_UCHAR **bufferptr, PCRE2_SIZE *bufflen);
+
+       int pcre2_substring_get_bynumber(pcre2_match_data *match_data,
+         uint32_t number, PCRE2_UCHAR **bufferptr,
+         PCRE2_SIZE *bufflen);
+
+       int pcre2_substring_length_byname(pcre2_match_data *match_data,
+         PCRE2_SPTR name, PCRE2_SIZE *length);
+
+       int pcre2_substring_length_bynumber(pcre2_match_data *match_data,
+         uint32_t number, PCRE2_SIZE *length);
+
+       int pcre2_substring_nametable_scan(const pcre2_code *code,
+         PCRE2_SPTR name, PCRE2_SPTR *first, PCRE2_SPTR *last);
+
+       int pcre2_substring_number_from_name(const pcre2_code *code,
+         PCRE2_SPTR name);
+
+       void pcre2_substring_list_free(PCRE2_SPTR *list);
+
+       int pcre2_substring_list_get(pcre2_match_data *match_data,
+         PCRE2_UCHAR ***listptr, PCRE2_SIZE **lengthsptr);
+
+
+PCRE2 NATIVE API STRING SUBSTITUTION FUNCTION
+
+       int pcre2_substitute(const pcre2_code *code, PCRE2_SPTR subject,
+         PCRE2_SIZE length, PCRE2_SIZE startoffset,
+         uint32_t options, pcre2_match_data *match_data,
+         pcre2_match_context *mcontext, PCRE2_SPTR replacementzfP,
+         PCRE2_SIZE rlength, PCRE2_UCHAR *outputbuffer,
+         PCRE2_SIZE *outlengthptr);
+
+
+PCRE2 NATIVE API JIT FUNCTIONS
+
+       int pcre2_jit_compile(pcre2_code *code, uint32_t options);
+
+       int pcre2_jit_match(const pcre2_code *code, PCRE2_SPTR subject,
+         PCRE2_SIZE length, PCRE2_SIZE startoffset,
+         uint32_t options, pcre2_match_data *match_data,
+         pcre2_match_context *mcontext);
+
+       void pcre2_jit_free_unused_memory(pcre2_general_context *gcontext);
+
+       pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE startsize,
+         PCRE2_SIZE maxsize, pcre2_general_context *gcontext);
+
+       void pcre2_jit_stack_assign(pcre2_match_context *mcontext,
+         pcre2_jit_callback callback_function, void *callback_data);
+
+       void pcre2_jit_stack_free(pcre2_jit_stack *jit_stack);
+
+
+PCRE2 NATIVE API SERIALIZATION FUNCTIONS
+
+       int32_t pcre2_serialize_decode(pcre2_code **codes,
+         int32_t number_of_codes, const uint32_t *bytes,
+         pcre2_general_context *gcontext);
+
+       int32_t pcre2_serialize_encode(pcre2_code **codes,
+         int32_t number_of_codes, uint32_t **serialized_bytes,
+         PCRE2_SIZE *serialized_size, pcre2_general_context *gcontext);
+
+       void pcre2_serialize_free(uint8_t *bytes);
+
+       int32_t pcre2_serialize_get_number_of_codes(const uint8_t *bytes);
+
+
+PCRE2 NATIVE API AUXILIARY FUNCTIONS
+
+       int pcre2_get_error_message(int errorcode, PCRE2_UCHAR *buffer,
+         PCRE2_SIZE bufflen);
+
+       const unsigned char *pcre2_maketables(pcre2_general_context *gcontext);
+
+       int pcre2_pattern_info(const pcre2 *code, uint32_t what, void *where);
+
+       int pcre2_callout_enumerate(const pcre2_code *code,
+         int (*callback)(pcre2_callout_enumerate_block *, void *),
+         void *user_data);
+
+       int pcre2_config(uint32_t what, void *where);
+
+
+PCRE2 8-BIT, 16-BIT, AND 32-BIT LIBRARIES
+
+       There  are  three PCRE2 libraries, supporting 8-bit, 16-bit, and 32-bit
+       code units, respectively. However,  there  is  just  one  header  file,
+       pcre2.h.   This  contains the function prototypes and other definitions
+       for all three libraries. One, two, or all three can be installed simul-
+       taneously.  On  Unix-like  systems the libraries are called libpcre2-8,
+       libpcre2-16, and libpcre2-32, and they can also co-exist with the orig-
+       inal PCRE libraries.
+
+       Character  strings are passed to and from a PCRE2 library as a sequence
+       of unsigned integers in code units  of  the  appropriate  width.  Every
+       PCRE2  function  comes  in three different forms, one for each library,
+       for example:
+
+         pcre2_compile_8()
+         pcre2_compile_16()
+         pcre2_compile_32()
+
+       There are also three different sets of data types:
+
+         PCRE2_UCHAR8, PCRE2_UCHAR16, PCRE2_UCHAR32
+         PCRE2_SPTR8,  PCRE2_SPTR16,  PCRE2_SPTR32
+
+       The UCHAR types define unsigned code units of the  appropriate  widths.
+       For  example,  PCRE2_UCHAR16 is usually defined as `uint16_t'. The SPTR
+       types are constant pointers to the equivalent  UCHAR  types,  that  is,
+       they are pointers to vectors of unsigned code units.
+
+       Many  applications use only one code unit width. For their convenience,
+       macros are defined whose names are the generic forms such as pcre2_com-
+       pile()  and  PCRE2_SPTR.  These  macros  use  the  value  of  the macro
+       PCRE2_CODE_UNIT_WIDTH to generate the appropriate width-specific  func-
+       tion and macro names.  PCRE2_CODE_UNIT_WIDTH is not defined by default.
+       An application must define it to be  8,  16,  or  32  before  including
+       pcre2.h in order to make use of the generic names.
+
+       Applications  that use more than one code unit width can be linked with
+       more than one PCRE2 library, but must define  PCRE2_CODE_UNIT_WIDTH  to
+       be  0  before  including pcre2.h, and then use the real function names.
+       Any code that is to be included in an environment where  the  value  of
+       PCRE2_CODE_UNIT_WIDTH  is  unknown  should  also  use the real function
+       names. (Unfortunately, it is not possible in C code to save and restore
+       the value of a macro.)
+
+       If  PCRE2_CODE_UNIT_WIDTH  is  not  defined before including pcre2.h, a
+       compiler error occurs.
+
+       When using multiple libraries in an application,  you  must  take  care
+       when  processing  any  particular  pattern to use only functions from a
+       single library.  For example, if you want to run a match using  a  pat-
+       tern  that  was  compiled  with pcre2_compile_16(), you must do so with
+       pcre2_match_16(), not pcre2_match_8().
+
+       In the function summaries above, and in the rest of this  document  and
+       other  PCRE2  documents,  functions  and data types are described using
+       their generic names, without the 8, 16, or 32 suffix.
+
+
+PCRE2 API OVERVIEW
+
+       PCRE2 has its own native API, which  is  described  in  this  document.
+       There are also some wrapper functions for the 8-bit library that corre-
+       spond to the POSIX regular expression API, but they do not give  access
+       to all the functionality. They are described in the pcre2posix documen-
+       tation. Both these APIs define a set of C function calls.
+
+       The native API C data types, function prototypes,  option  values,  and
+       error codes are defined in the header file pcre2.h, which contains def-
+       initions of PCRE2_MAJOR and PCRE2_MINOR, the major  and  minor  release
+       numbers  for the library. Applications can use these to include support
+       for different releases of PCRE2.
+
+       In a Windows environment, if you want to statically link an application
+       program  against  a non-dll PCRE2 library, you must define PCRE2_STATIC
+       before including pcre2.h.
+
+       The functions pcre2_compile(), and pcre2_match() are used for compiling
+       and  matching regular expressions in a Perl-compatible manner. A sample
+       program that demonstrates the simplest way of using them is provided in
+       the file called pcre2demo.c in the PCRE2 source distribution. A listing
+       of this program is  given  in  the  pcre2demo  documentation,  and  the
+       pcre2sample documentation describes how to compile and run it.
+
+       Just-in-time  compiler support is an optional feature of PCRE2 that can
+       be built in appropriate hardware environments. It greatly speeds up the
+       matching  performance of many patterns. Programs can request that it be
+       used if available, by calling pcre2_jit_compile() after a  pattern  has
+       been successfully compiled by pcre2_compile(). This does nothing if JIT
+       support is not available.
+
+       More complicated programs might need to  make  use  of  the  specialist
+       functions    pcre2_jit_stack_create(),    pcre2_jit_stack_free(),   and
+       pcre2_jit_stack_assign() in order to  control  the  JIT  code's  memory
+       usage.
+
+       JIT matching is automatically used by pcre2_match() if it is available.
+       There is also a direct interface for JIT matching, which gives improved
+       performance.  The  JIT-specific functions are discussed in the pcre2jit
+       documentation.
+
+       A second matching function, pcre2_dfa_match(), which is  not  Perl-com-
+       patible,  is  also  provided.  This  uses a different algorithm for the
+       matching. The alternative algorithm finds all possible  matches  (at  a
+       given  point  in  the subject), and scans the subject just once (unless
+       there are lookbehind assertions).  However,  this  algorithm  does  not
+       return  captured  substrings.  A  description of the two matching algo-
+       rithms  and  their  advantages  and  disadvantages  is  given  in   the
+       pcre2matching    documentation.   There   is   no   JIT   support   for
+       pcre2_dfa_match().
+
+       In addition to the main compiling and  matching  functions,  there  are
+       convenience functions for extracting captured substrings from a subject
+       string that has been matched by pcre2_match(). They are:
+
+         pcre2_substring_copy_byname()
+         pcre2_substring_copy_bynumber()
+         pcre2_substring_get_byname()
+         pcre2_substring_get_bynumber()
+         pcre2_substring_list_get()
+         pcre2_substring_length_byname()
+         pcre2_substring_length_bynumber()
+         pcre2_substring_nametable_scan()
+         pcre2_substring_number_from_name()
+
+       pcre2_substring_free() and pcre2_substring_list_free()  are  also  pro-
+       vided, to free the memory used for extracted strings.
+
+       The  function  pcre2_substitute()  can be called to match a pattern and
+       return a copy of the subject string with substitutions for  parts  that
+       were matched.
+
+       Finally,  there  are functions for finding out information about a com-
+       piled pattern (pcre2_pattern_info()) and about the  configuration  with
+       which PCRE2 was built (pcre2_config()).
+
+
+STRING LENGTHS AND OFFSETS
+
+       The  PCRE2  API  uses  string  lengths and offsets into strings of code
+       units in several places. These values are always  of  type  PCRE2_SIZE,
+       which  is an unsigned integer type, currently always defined as size_t.
+       The largest  value  that  can  be  stored  in  such  a  type  (that  is
+       ~(PCRE2_SIZE)0)  is reserved as a special indicator for zero-terminated
+       strings and unset offsets.  Therefore, the longest string that  can  be
+       handled is one less than this maximum.
+
+
+NEWLINES
+
+       PCRE2 supports five different conventions for indicating line breaks in
+       strings: a single CR (carriage return) character, a  single  LF  (line-
+       feed) character, the two-character sequence CRLF, any of the three pre-
+       ceding, or any Unicode newline sequence. The Unicode newline  sequences
+       are  the  three just mentioned, plus the single characters VT (vertical
+       tab, U+000B), FF (form feed, U+000C), NEL (next line, U+0085), LS (line
+       separator, U+2028), and PS (paragraph separator, U+2029).
+
+       Each  of  the first three conventions is used by at least one operating
+       system as its standard newline sequence. When PCRE2 is built, a default
+       can  be  specified.  The default default is LF, which is the Unix stan-
+       dard. However, the newline convention can be changed by an  application
+       when calling pcre2_compile(), or it can be specified by special text at
+       the start of the pattern itself; this overrides any other settings. See
+       the pcre2pattern page for details of the special character sequences.
+
+       In  the  PCRE2  documentation  the  word "newline" is used to mean "the
+       character or pair of characters that indicate a line break". The choice
+       of  newline convention affects the handling of the dot, circumflex, and
+       dollar metacharacters, the handling of #-comments in /x mode, and, when
+       CRLF  is a recognized line ending sequence, the match position advance-
+       ment for a non-anchored pattern. There is more detail about this in the
+       section on pcre2_match() options below.
+
+       The  choice of newline convention does not affect the interpretation of
+       the \n or \r escape sequences, nor does it affect what \R matches; this
+       has its own separate convention.
+
+
+MULTITHREADING
+
+       In  a multithreaded application it is important to keep thread-specific
+       data separate from data that can be shared between threads.  The  PCRE2
+       library  code  itself  is  thread-safe: it contains no static or global
+       variables. The API is designed to be  fairly  simple  for  non-threaded
+       applications  while at the same time ensuring that multithreaded appli-
+       cations can use it.
+
+       There are several different blocks of data that are used to pass infor-
+       mation between the application and the PCRE2 libraries.
+
+       (1) A pointer to the compiled form of a pattern is returned to the user
+       when pcre2_compile() is successful. The data in the compiled pattern is
+       fixed,  and  does not change when the pattern is matched. Therefore, it
+       is thread-safe, that is, the same compiled pattern can be used by  more
+       than one thread simultaneously. An application can compile all its pat-
+       terns at the start, before forking off multiple threads that use  them.
+       However,  if  the  just-in-time  optimization feature is being used, it
+       needs separate memory stack areas for each  thread.  See  the  pcre2jit
+       documentation for more details.
+
+       (2)  The  next section below introduces the idea of "contexts" in which
+       PCRE2 functions are called. A context is nothing more than a collection
+       of parameters that control the way PCRE2 operates. Grouping a number of
+       parameters together in a context is a convenient way of passing them to
+       a  PCRE2  function without using lots of arguments. The parameters that
+       are stored in contexts are in some sense  "advanced  features"  of  the
+       API. Many straightforward applications will not need to use contexts.
+
+       In a multithreaded application, if the parameters in a context are val-
+       ues that are never changed, the same context can be  used  by  all  the
+       threads. However, if any thread needs to change any value in a context,
+       it must make its own thread-specific copy.
+
+       (3) The matching functions need a block of memory for working space and
+       for  storing  the results of a match. This includes details of what was
+       matched, as well as additional  information  such  as  the  name  of  a
+       (*MARK)  setting. Each thread must provide its own version of this mem-
+       ory.
+
+
+PCRE2 CONTEXTS
+
+       Some PCRE2 functions have a lot of parameters, many of which  are  used
+       only  by  specialist  applications,  for example, those that use custom
+       memory management or non-standard character tables.  To  keep  function
+       argument  lists  at a reasonable size, and at the same time to keep the
+       API extensible, "uncommon" parameters are passed to  certain  functions
+       in  a  context instead of directly. A context is just a block of memory
+       that holds the parameter values.  Applications  that  do  not  need  to
+       adjust  any  of  the  context  parameters  can pass NULL when a context
+       pointer is required.
+
+       There are three different types of context: a general context  that  is
+       relevant  for  several  PCRE2 operations, a compile-time context, and a
+       match-time context.
+
+   The general context
+
+       At present, this context just  contains  pointers  to  (and  data  for)
+       external  memory  management  functions  that  are  called from several
+       places in the PCRE2 library. The context is named `general' rather than
+       specifically  `memory'  because in future other fields may be added. If
+       you do not want to supply your own custom memory management  functions,
+       you  do not need to bother with a general context. A general context is
+       created by:
+
+       pcre2_general_context *pcre2_general_context_create(
+         void *(*private_malloc)(PCRE2_SIZE, void *),
+         void (*private_free)(void *, void *), void *memory_data);
+
+       The two function pointers specify custom memory  management  functions,
+       whose prototypes are:
+
+         void *private_malloc(PCRE2_SIZE, void *);
+         void  private_free(void *, void *);
+
+       Whenever code in PCRE2 calls these functions, the final argument is the
+       value of memory_data. Either of the first two arguments of the creation
+       function  may be NULL, in which case the system memory management func-
+       tions malloc() and free() are used. (This is not currently  useful,  as
+       there  are  no  other  fields in a general context, but in future there
+       might be.)  The private_malloc() function  is  used  (if  supplied)  to
+       obtain  memory  for storing the context, and all three values are saved
+       as part of the context.
+
+       Whenever PCRE2 creates a data block of any kind, the block  contains  a
+       pointer  to the free() function that matches the malloc() function that
+       was used. When the time comes to  free  the  block,  this  function  is
+       called.
+
+       A general context can be copied by calling:
+
+       pcre2_general_context *pcre2_general_context_copy(
+         pcre2_general_context *gcontext);
+
+       The memory used for a general context should be freed by calling:
+
+       void pcre2_general_context_free(pcre2_general_context *gcontext);
+
+
+   The compile context
+
+       A  compile context is required if you want to change the default values
+       of any of the following compile-time parameters:
+
+         What \R matches (Unicode newlines or CR, LF, CRLF only)
+         PCRE2's character tables
+         The newline character sequence
+         The compile time nested parentheses limit
+         An external function for stack checking
+
+       A compile context is also required if you are using custom memory  man-
+       agement.   If  none of these apply, just pass NULL as the context argu-
+       ment of pcre2_compile().
+
+       A compile context is created, copied, and freed by the following  func-
+       tions:
+
+       pcre2_compile_context *pcre2_compile_context_create(
+         pcre2_general_context *gcontext);
+
+       pcre2_compile_context *pcre2_compile_context_copy(
+         pcre2_compile_context *ccontext);
+
+       void pcre2_compile_context_free(pcre2_compile_context *ccontext);
+
+       A  compile  context  is created with default values for its parameters.
+       These can be changed by calling the following functions, which return 0
+       on success, or PCRE2_ERROR_BADDATA if invalid data is detected.
+
+       int pcre2_set_bsr(pcre2_compile_context *ccontext,
+         uint32_t value);
+
+       The  value  must  be PCRE2_BSR_ANYCRLF, to specify that \R matches only
+       CR, LF, or CRLF, or PCRE2_BSR_UNICODE, to specify that \R  matches  any
+       Unicode line ending sequence. The value is used by the JIT compiler and
+       by  the  two  interpreted   matching   functions,   pcre2_match()   and
+       pcre2_dfa_match().
+
+       int pcre2_set_character_tables(pcre2_compile_context *ccontext,
+         const unsigned char *tables);
+
+       The  value  must  be  the result of a call to pcre2_maketables(), whose
+       only argument is a general context. This function builds a set of char-
+       acter tables in the current locale.
+
+       int pcre2_set_newline(pcre2_compile_context *ccontext,
+         uint32_t value);
+
+       This specifies which characters or character sequences are to be recog-
+       nized as newlines. The value must be one of PCRE2_NEWLINE_CR  (carriage
+       return only), PCRE2_NEWLINE_LF (linefeed only), PCRE2_NEWLINE_CRLF (the
+       two-character sequence CR followed by LF),  PCRE2_NEWLINE_ANYCRLF  (any
+       of the above), or PCRE2_NEWLINE_ANY (any Unicode newline sequence).
+
+       When a pattern is compiled with the PCRE2_EXTENDED option, the value of
+       this parameter affects the recognition of white space and  the  end  of
+       internal comments starting with #. The value is saved with the compiled
+       pattern for subsequent use by the JIT compiler and by  the  two  inter-
+       preted matching functions, pcre2_match() and pcre2_dfa_match().
+
+       int pcre2_set_parens_nest_limit(pcre2_compile_context *ccontext,
+         uint32_t value);
+
+       This parameter ajusts the limit, set when PCRE2 is built (default 250),
+       on the depth of parenthesis nesting in  a  pattern.  This  limit  stops
+       rogue patterns using up too much system stack when being compiled.
+
+       int pcre2_set_compile_recursion_guard(pcre2_compile_context *ccontext,
+         int (*guard_function)(uint32_t, void *), void *user_data);
+
+       There  is at least one application that runs PCRE2 in threads with very
+       limited system stack, where running out of stack is to  be  avoided  at
+       all  costs. The parenthesis limit above cannot take account of how much
+       stack is actually available. For a finer  control,  you  can  supply  a
+       function  that  is  called whenever pcre2_compile() starts to compile a
+       parenthesized part of a pattern. This function  can  check  the  actual
+       stack size (or anything else that it wants to, of course).
+
+       The  first  argument to the callout function gives the current depth of
+       nesting, and the second is user data that is set up by the  last  argu-
+       ment   of  pcre2_set_compile_recursion_guard().  The  callout  function
+       should return zero if all is well, or non-zero to force an error.
+
+   The match context
+
+       A match context is required if you want to change the default values of
+       any of the following match-time parameters:
+
+         A callout function
+         The limit for calling match()
+         The limit for calling match() recursively
+
+       A match context is also required if you are using custom memory manage-
+       ment.  If none of these apply, just pass NULL as the  context  argument
+       of pcre2_match(), pcre2_dfa_match(), or pcre2_jit_match().
+
+       A  match  context  is created, copied, and freed by the following func-
+       tions:
+
+       pcre2_match_context *pcre2_match_context_create(
+         pcre2_general_context *gcontext);
+
+       pcre2_match_context *pcre2_match_context_copy(
+         pcre2_match_context *mcontext);
+
+       void pcre2_match_context_free(pcre2_match_context *mcontext);
+
+       A match context is created with  default  values  for  its  parameters.
+       These can be changed by calling the following functions, which return 0
+       on success, or PCRE2_ERROR_BADDATA if invalid data is detected.
+
+       int pcre2_set_callout(pcre2_match_context *mcontext,
+         int (*callout_function)(pcre2_callout_block *, void *),
+         void *callout_data);
+
+       This sets up a "callout" function, which PCRE2 will call  at  specified
+       points during a matching operation. Details are given in the pcre2call-
+       out documentation.
+
+       int pcre2_set_match_limit(pcre2_match_context *mcontext,
+         uint32_t value);
+
+       The match_limit parameter provides a means  of  preventing  PCRE2  from
+       using up too many resources when processing patterns that are not going
+       to match, but which have a very large number of possibilities in  their
+       search  trees. The classic example is a pattern that uses nested unlim-
+       ited repeats.
+
+       Internally, pcre2_match() uses a  function  called  match(),  which  it
+       calls  repeatedly (sometimes recursively). The limit set by match_limit
+       is imposed on the number of times this  function  is  called  during  a
+       match, which has the effect of limiting the amount of backtracking that
+       can take place. For patterns that are not anchored, the count  restarts
+       from  zero  for  each position in the subject string. This limit is not
+       relevant to pcre2_dfa_match(), which ignores it.
+
+       When pcre2_match() is called with a pattern that was successfully  pro-
+       cessed by pcre2_jit_compile(), the way in which matching is executed is
+       entirely different. However, there is still the possibility of  runaway
+       matching  that  goes  on  for  a very long time, and so the match_limit
+       value is also used in this case (but in a different way) to  limit  how
+       long the matching can continue.
+
+       The  default  value  for  the limit can be set when PCRE2 is built; the
+       default default is 10 million, which handles all but the  most  extreme
+       cases.    If    the    limit   is   exceeded,   pcre2_match()   returns
+       PCRE2_ERROR_MATCHLIMIT. A value for the match limit may  also  be  sup-
+       plied by an item at the start of a pattern of the form
+
+         (*LIMIT_MATCH=ddd)
+
+       where  ddd  is  a  decimal  number.  However, such a setting is ignored
+       unless ddd is less than the limit set by the  caller  of  pcre2_match()
+       or, if no such limit is set, less than the default.
+
+       int pcre2_set_recursion_limit(pcre2_match_context *mcontext,
+         uint32_t value);
+
+       The recursion_limit parameter is similar to match_limit, but instead of
+       limiting the total number of times that match() is  called,  it  limits
+       the  depth  of  recursion. The recursion depth is a smaller number than
+       the total number of calls, because not all calls to match() are  recur-
+       sive.  This limit is of use only if it is set smaller than match_limit.
+
+       Limiting the recursion depth limits the amount of system stack that can
+       be used, or, when PCRE2 has been compiled to use  memory  on  the  heap
+       instead  of the stack, the amount of heap memory that can be used. This
+       limit is not relevant, and is ignored, when matching is done using  JIT
+       compiled code or by the pcre2_dfa_match() function.
+
+       The  default  value for recursion_limit can be set when PCRE2 is built;
+       the default default is the same value as the default  for  match_limit.
+       If  the limit is exceeded, pcre2_match() returns PCRE2_ERROR_RECURSION-
+       LIMIT. A value for the recursion limit may also be supplied by an  item
+       at the start of a pattern of the form
+
+         (*LIMIT_RECURSION=ddd)
+
+       where  ddd  is  a  decimal  number.  However, such a setting is ignored
+       unless ddd is less than the limit set by the  caller  of  pcre2_match()
+       or, if no such limit is set, less than the default.
+
+       int pcre2_set_recursion_memory_management(
+         pcre2_match_context *mcontext,
+         void *(*private_malloc)(PCRE2_SIZE, void *),
+         void (*private_free)(void *, void *), void *memory_data);
+
+       This function sets up two additional custom memory management functions
+       for use by pcre2_match() when PCRE2 is compiled to  use  the  heap  for
+       remembering backtracking data, instead of recursive function calls that
+       use the system stack. There is a discussion about PCRE2's  stack  usage
+       in  the  pcre2stack documentation. See the pcre2build documentation for
+       details of how to build PCRE2.
+
+       Using the heap for recursion is a non-standard way of  building  PCRE2,
+       for  use  in  environments  that  have  limited  stacks. Because of the
+       greater use of memory management, pcre2_match() runs more slowly. Func-
+       tions  that  are  different  to the general custom memory functions are
+       provided so that special-purpose external code can  be  used  for  this
+       case,  because  the memory blocks are all the same size. The blocks are
+       retained by pcre2_match() until it is about to exit so that they can be
+       re-used  when  possible during the match. In the absence of these func-
+       tions, the normal custom memory management functions are used, if  sup-
+       plied, otherwise the system functions.
+
+
+CHECKING BUILD-TIME OPTIONS
+
+       int pcre2_config(uint32_t what, void *where);
+
+       The  function  pcre2_config()  makes  it possible for a PCRE2 client to
+       discover which optional features have  been  compiled  into  the  PCRE2
+       library.  The  pcre2build  documentation  has  more details about these
+       optional features.
+
+       The first argument for pcre2_config() specifies  which  information  is
+       required.  The  second  argument  is a pointer to memory into which the
+       information is placed. If NULL is  passed,  the  function  returns  the
+       amount  of  memory  that  is  needed for the requested information. For
+       calls that return  numerical  values,  the  value  is  in  bytes;  when
+       requesting  these  values,  where should point to appropriately aligned
+       memory. For calls that return strings, the required length is given  in
+       code units, not counting the terminating zero.
+
+       When  requesting information, the returned value from pcre2_config() is
+       non-negative on success, or the negative error code  PCRE2_ERROR_BADOP-
+       TION  if the value in the first argument is not recognized. The follow-
+       ing information is available:
+
+         PCRE2_CONFIG_BSR
+
+       The output is a uint32_t integer whose value indicates  what  character
+       sequences  the  \R  escape  sequence  matches  by  default.  A value of
+       PCRE2_BSR_UNICODE  means  that  \R  matches  any  Unicode  line  ending
+       sequence;  a  value of PCRE2_BSR_ANYCRLF means that \R matches only CR,
+       LF, or CRLF. The default can be overridden when a pattern is compiled.
+
+         PCRE2_CONFIG_JIT
+
+       The output is a uint32_t integer that is set  to  one  if  support  for
+       just-in-time compiling is available; otherwise it is set to zero.
+
+         PCRE2_CONFIG_JITTARGET
+
+       The  where  argument  should point to a buffer that is at least 48 code
+       units long.  (The  exact  length  required  can  be  found  by  calling
+       pcre2_config()  with  where  set  to NULL.) The buffer is filled with a
+       string that contains the name of the architecture  for  which  the  JIT
+       compiler  is  configured,  for  example  "x86  32bit  (little  endian +
+       unaligned)". If JIT support is not available, PCRE2_ERROR_BADOPTION  is
+       returned,  otherwise the number of code units used is returned. This is
+       the length of the string, plus one unit for the terminating zero.
+
+         PCRE2_CONFIG_LINKSIZE
+
+       The output is a uint32_t integer that contains the number of bytes used
+       for  internal  linkage  in  compiled regular expressions. When PCRE2 is
+       configured, the value can be set to 2, 3, or 4, with the default  being
+       2.  This is the value that is returned by pcre2_config(). However, when
+       the 16-bit library is compiled, a value of 3 is rounded up  to  4,  and
+       when  the  32-bit  library  is compiled, internal linkages always use 4
+       bytes, so the configured value is not relevant.
+
+       The default value of 2 for the 8-bit and 16-bit libraries is sufficient
+       for  all but the most massive patterns, since it allows the size of the
+       compiled pattern to be up to 64K code units. Larger values allow larger
+       regular  expressions  to be compiled by those two libraries, but at the
+       expense of slower matching.
+
+         PCRE2_CONFIG_MATCHLIMIT
+
+       The output is a uint32_t integer that gives the default limit  for  the
+       number  of  internal  matching function calls in a pcre2_match() execu-
+       tion. Further details are given with pcre2_match() below.
+
+         PCRE2_CONFIG_NEWLINE
+
+       The output is a uint32_t integer  whose  value  specifies  the  default
+       character  sequence that is recognized as meaning "newline". The values
+       are:
+
+         PCRE2_NEWLINE_CR       Carriage return (CR)
+         PCRE2_NEWLINE_LF       Linefeed (LF)
+         PCRE2_NEWLINE_CRLF     Carriage return, linefeed (CRLF)
+         PCRE2_NEWLINE_ANY      Any Unicode line ending
+         PCRE2_NEWLINE_ANYCRLF  Any of CR, LF, or CRLF
+
+       The default should normally correspond to  the  standard  sequence  for
+       your operating system.
+
+         PCRE2_CONFIG_PARENSLIMIT
+
+       The  output is a uint32_t integer that gives the maximum depth of nest-
+       ing of parentheses (of any kind) in a pattern. This limit is imposed to
+       cap  the  amount of system stack used when a pattern is compiled. It is
+       specified when PCRE2 is built; the default is 250. This limit does  not
+       take  into  account  the  stack that may already be used by the calling
+       application. For  finer  control  over  compilation  stack  usage,  see
+       pcre2_set_compile_recursion_guard().
+
+         PCRE2_CONFIG_RECURSIONLIMIT
+
+       The  output  is a uint32_t integer that gives the default limit for the
+       depth of recursion when calling the internal  matching  function  in  a
+       pcre2_match()  execution.  Further details are given with pcre2_match()
+       below.
+
+         PCRE2_CONFIG_STACKRECURSE
+
+       The output is a uint32_t integer that is set to one if internal  recur-
+       sion  when  running  pcre2_match() is implemented by recursive function
+       calls that use the system stack to remember their state.  This  is  the
+       usual  way that PCRE2 is compiled. The output is zero if PCRE2 was com-
+       piled to use blocks of data on the heap instead of  recursive  function
+       calls.
+
+         PCRE2_CONFIG_UNICODE_VERSION
+
+       The  where  argument  should point to a buffer that is at least 24 code
+       units long.  (The  exact  length  required  can  be  found  by  calling
+       pcre2_config()  with  where  set  to  NULL.) If PCRE2 has been compiled
+       without Unicode support, the buffer is filled with  the  text  "Unicode
+       not  supported".  Otherwise,  the  Unicode version string (for example,
+       "7.0.0") is inserted. The number of code units used is  returned.  This
+       is the length of the string plus one unit for the terminating zero.
+
+         PCRE2_CONFIG_UNICODE
+
+       The  output is a uint32_t integer that is set to one if Unicode support
+       is available; otherwise it is set to zero. Unicode support implies  UTF
+       support.
+
+         PCRE2_CONFIG_VERSION
+
+       The  where  argument  should point to a buffer that is at least 12 code
+       units long.  (The  exact  length  required  can  be  found  by  calling
+       pcre2_config()  with  where set to NULL.) The buffer is filled with the
+       PCRE2 version string, zero-terminated. The number of code units used is
+       returned. This is the length of the string plus one unit for the termi-
+       nating zero.
+
+
+COMPILING A PATTERN
+
+       pcre2_code *pcre2_compile(PCRE2_SPTR pattern, PCRE2_SIZE length,
+         uint32_t options, int *errorcode, PCRE2_SIZE *erroroffset,
+         pcre2_compile_context *ccontext);
+
+       pcre2_code_free(pcre2_code *code);
+
+       The pcre2_compile() function compiles a pattern into an internal  form.
+       The  pattern  is  defined  by a pointer to a string of code units and a
+       length, If the pattern is zero-terminated, the length can be  specified
+       as  PCRE2_ZERO_TERMINATED. The function returns a pointer to a block of
+       memory that contains the compiled pattern and related data. The  caller
+       must  free the memory by calling pcre2_code_free() when it is no longer
+       needed.
+
+       NOTE: When one of the matching functions is  called,  pointers  to  the
+       compiled pattern and the subject string are set in the match data block
+       so that they can be referenced by the extraction functions. After  run-
+       ning  a  match,  you  must  not  free  a compiled pattern (or a subject
+       string) until after all operations on the match data block  have  taken
+       place.
+
+       If  the  compile context argument ccontext is NULL, memory for the com-
+       piled pattern  is  obtained  by  calling  malloc().  Otherwise,  it  is
+       obtained  from  the  same memory function that was used for the compile
+       context.
+
+       The options argument contains various bit settings that affect the com-
+       pilation.  It  should be zero if no options are required. The available
+       options are described below. Some of them (in  particular,  those  that
+       are  compatible with Perl, but some others as well) can also be set and
+       unset from within the pattern (see  the  detailed  description  in  the
+       pcre2pattern documentation).
+
+       For  those options that can be different in different parts of the pat-
+       tern, the contents of the options argument specifies their settings  at
+       the  start  of  compilation.  The PCRE2_ANCHORED and PCRE2_NO_UTF_CHECK
+       options can be set at the time of matching as well as at compile time.
+
+       Other, less frequently required compile-time parameters  (for  example,
+       the newline setting) can be provided in a compile context (as described
+       above).
+
+       If errorcode or erroroffset is NULL, pcre2_compile() returns NULL imme-
+       diately.  Otherwise, if compilation of a pattern fails, pcre2_compile()
+       returns NULL, having set these variables to an error code and an offset
+       (number   of   code   units)  within  the  pattern,  respectively.  The
+       pcre2_get_error_message() function provides a textual message for  each
+       error code. Compilation errors are positive numbers, but UTF formatting
+       errors are negative numbers. For an invalid UTF-8 or UTF-16 string, the
+       offset is that of the first code unit of the failing character.
+
+       Some  errors are not detected until the whole pattern has been scanned;
+       in these cases, the offset passed back is the length  of  the  pattern.
+       Note  that  the  offset is in code units, not characters, even in a UTF
+       mode. It may sometimes point into the middle of a UTF-8 or UTF-16 char-
+       acter.
+
+       This  code  fragment shows a typical straightforward call to pcre2_com-
+       pile():
+
+         pcre2_code *re;
+         PCRE2_SIZE erroffset;
+         int errorcode;
+         re = pcre2_compile(
+           "^A.*Z",                /* the pattern */
+           PCRE2_ZERO_TERMINATED,  /* the pattern is zero-terminated */
+           0,                      /* default options */
+           &errorcode,             /* for error code */
+           &erroffset,             /* for error offset */
+           NULL);                  /* no compile context */
+
+       The following names for option bits are defined in the  pcre2.h  header
+       file:
+
+         PCRE2_ANCHORED
+
+       If this bit is set, the pattern is forced to be "anchored", that is, it
+       is constrained to match only at the first matching point in the  string
+       that  is being searched (the "subject string"). This effect can also be
+       achieved by appropriate constructs in the pattern itself, which is  the
+       only way to do it in Perl.
+
+         PCRE2_ALLOW_EMPTY_CLASS
+
+       By  default, for compatibility with Perl, a closing square bracket that
+       immediately follows an opening one is treated as a data  character  for
+       the  class.  When  PCRE2_ALLOW_EMPTY_CLASS  is  set,  it terminates the
+       class, which therefore contains no characters and so can never match.
+
+         PCRE2_ALT_BSUX
+
+       This option request alternative handling  of  three  escape  sequences,
+       which  makes  PCRE2's  behaviour more like ECMAscript (aka JavaScript).
+       When it is set:
+
+       (1) \U matches an upper case "U" character; by default \U causes a com-
+       pile time error (Perl uses \U to upper case subsequent characters).
+
+       (2) \u matches a lower case "u" character unless it is followed by four
+       hexadecimal digits, in which case the hexadecimal  number  defines  the
+       code  point  to match. By default, \u causes a compile time error (Perl
+       uses it to upper case the following character).
+
+       (3) \x matches a lower case "x" character unless it is followed by  two
+       hexadecimal  digits,  in  which case the hexadecimal number defines the
+       code point to match. By default, as in Perl, a  hexadecimal  number  is
+       always expected after \x, but it may have zero, one, or two digits (so,
+       for example, \xz matches a binary zero character followed by z).
+
+         PCRE2_ALT_CIRCUMFLEX
+
+       In  multiline  mode  (when  PCRE2_MULTILINE  is  set),  the  circumflex
+       metacharacter  matches at the start of the subject (unless PCRE2_NOTBOL
+       is set), and also after any internal  newline.  However,  it  does  not
+       match after a newline at the end of the subject, for compatibility with
+       Perl. If you want a multiline circumflex also to match after  a  termi-
+       nating newline, you must set PCRE2_ALT_CIRCUMFLEX.
+
+         PCRE2_AUTO_CALLOUT
+
+       If  this  bit  is  set,  pcre2_compile()  automatically inserts callout
+       items, all with number 255, before each pattern item. For discussion of
+       the callout facility, see the pcre2callout documentation.
+
+         PCRE2_CASELESS
+
+       If  this  bit is set, letters in the pattern match both upper and lower
+       case letters in the subject. It is equivalent to Perl's /i option,  and
+       it can be changed within a pattern by a (?i) option setting.
+
+         PCRE2_DOLLAR_ENDONLY
+
+       If  this bit is set, a dollar metacharacter in the pattern matches only
+       at the end of the subject string. Without this option,  a  dollar  also
+       matches  immediately before a newline at the end of the string (but not
+       before any other newlines). The PCRE2_DOLLAR_ENDONLY option is  ignored
+       if  PCRE2_MULTILINE  is  set.  There is no equivalent to this option in
+       Perl, and no way to set it within a pattern.
+
+         PCRE2_DOTALL
+
+       If this bit is set, a dot metacharacter  in  the  pattern  matches  any
+       character,  including  one  that  indicates a newline. However, it only
+       ever matches one character, even if newlines are coded as CRLF. Without
+       this option, a dot does not match when the current position in the sub-
+       ject is at a newline. This option is equivalent to  Perl's  /s  option,
+       and it can be changed within a pattern by a (?s) option setting. A neg-
+       ative class such as [^a] always matches newline characters, independent
+       of the setting of this option.
+
+         PCRE2_DUPNAMES
+
+       If  this  bit is set, names used to identify capturing subpatterns need
+       not be unique. This can be helpful for certain types of pattern when it
+       is  known  that  only  one instance of the named subpattern can ever be
+       matched. There are more details of named subpatterns  below;  see  also
+       the pcre2pattern documentation.
+
+         PCRE2_EXTENDED
+
+       If  this  bit  is  set,  most white space characters in the pattern are
+       totally ignored except when escaped or inside a character  class.  How-
+       ever,  white  space  is  not  allowed within sequences such as (?> that
+       introduce various parenthesized subpatterns, nor within numerical quan-
+       tifiers  such  as {1,3}.  Ignorable white space is permitted between an
+       item and a following quantifier and between a quantifier and a  follow-
+       ing + that indicates possessiveness.
+
+       PCRE2_EXTENDED  also causes characters between an unescaped # outside a
+       character class and the next newline, inclusive, to be  ignored,  which
+       makes it possible to include comments inside complicated patterns. Note
+       that the end of this type of comment is a literal newline  sequence  in
+       the pattern; escape sequences that happen to represent a newline do not
+       count. PCRE2_EXTENDED is equivalent to Perl's /x option, and it can  be
+       changed within a pattern by a (?x) option setting.
+
+       Which characters are interpreted as newlines can be specified by a set-
+       ting in the compile context that is passed to pcre2_compile() or  by  a
+       special  sequence at the start of the pattern, as described in the sec-
+       tion entitled "Newline conventions" in the pcre2pattern  documentation.
+       A default is defined when PCRE2 is built.
+
+         PCRE2_FIRSTLINE
+
+       If  this  option  is  set,  an  unanchored pattern is required to match
+       before or at the first  newline  in  the  subject  string,  though  the
+       matched text may continue over the newline.
+
+         PCRE2_MATCH_UNSET_BACKREF
+
+       If  this  option  is set, a back reference to an unset subpattern group
+       matches an empty string (by default this causes  the  current  matching
+       alternative  to  fail).   A  pattern such as (\1)(a) succeeds when this
+       option is set (assuming it can find an "a" in the subject), whereas  it
+       fails  by  default,  for  Perl compatibility. Setting this option makes
+       PCRE2 behave more like ECMAscript (aka JavaScript).
+
+         PCRE2_MULTILINE
+
+       By default, for the purposes of matching "start of line"  and  "end  of
+       line",  PCRE2  treats the subject string as consisting of a single line
+       of characters, even if it actually contains  newlines.  The  "start  of
+       line"  metacharacter  (^)  matches only at the start of the string, and
+       the "end of line" metacharacter ($) matches only  at  the  end  of  the
+       string,  or  before  a  terminating  newline  (except  when  PCRE2_DOL-
+       LAR_ENDONLY is set). Note, however, that unless  PCRE2_DOTALL  is  set,
+       the "any character" metacharacter (.) does not match at a newline. This
+       behaviour (for ^, $, and dot) is the same as Perl.
+
+       When PCRE2_MULTILINE it is set, the "start of line" and "end  of  line"
+       constructs  match  immediately following or immediately before internal
+       newlines in the subject string, respectively, as well as  at  the  very
+       start  and  end.  This is equivalent to Perl's /m option, and it can be
+       changed within a pattern by a (?m) option setting. Note that the "start
+       of line" metacharacter does not match after a newline at the end of the
+       subject, for compatibility with Perl.  However, you can change this  by
+       setting  the PCRE2_ALT_CIRCUMFLEX option. If there are no newlines in a
+       subject string, or no occurrences of ^  or  $  in  a  pattern,  setting
+       PCRE2_MULTILINE has no effect.
+
+         PCRE2_NEVER_BACKSLASH_C
+
+       This  option  locks out the use of \C in the pattern that is being com-
+       piled.  This escape can  cause  unpredictable  behaviour  in  UTF-8  or
+       UTF-16  modes,  because  it may leave the current matching point in the
+       middle of a multi-code-unit character. This option  may  be  useful  in
+       applications that process patterns from external sources.
+
+         PCRE2_NEVER_UCP
+
+       This  option  locks  out the use of Unicode properties for handling \B,
+       \b, \D, \d, \S, \s, \W, \w, and some of the POSIX character classes, as
+       described  for  the  PCRE2_UCP option below. In particular, it prevents
+       the creator of the pattern from enabling this facility by starting  the
+       pattern  with  (*UCP).  This  option may be useful in applications that
+       process patterns from external sources. The option combination PCRE_UCP
+       and PCRE_NEVER_UCP causes an error.
+
+         PCRE2_NEVER_UTF
+
+       This  option  locks out interpretation of the pattern as UTF-8, UTF-16,
+       or UTF-32, depending on which library is in use. In particular, it pre-
+       vents  the  creator of the pattern from switching to UTF interpretation
+       by starting the pattern with (*UTF).  This  option  may  be  useful  in
+       applications  that process patterns from external sources. The combina-
+       tion of PCRE2_UTF and PCRE2_NEVER_UTF causes an error.
+
+         PCRE2_NO_AUTO_CAPTURE
+
+       If this option is set, it disables the use of numbered capturing paren-
+       theses  in the pattern. Any opening parenthesis that is not followed by
+       ? behaves as if it were followed by ?: but named parentheses can  still
+       be  used  for  capturing  (and  they acquire numbers in the usual way).
+       There is no equivalent of this option in Perl.
+
+         PCRE2_NO_AUTO_POSSESS
+
+       If this option is set, it disables "auto-possessification", which is an
+       optimization  that,  for example, turns a+b into a++b in order to avoid
+       backtracks into a+ that can never be successful. However,  if  callouts
+       are  in  use,  auto-possessification means that some callouts are never
+       taken. You can set this option if you want the matching functions to do
+       a  full  unoptimized  search and run all the callouts, but it is mainly
+       provided for testing purposes.
+
+         PCRE2_NO_DOTSTAR_ANCHOR
+
+       If this option is set, it disables an optimization that is applied when
+       .*  is  the  first significant item in a top-level branch of a pattern,
+       and all the other branches also start with .* or with \A or  \G  or  ^.
+       The  optimization  is  automatically disabled for .* if it is inside an
+       atomic group or a capturing group that is the subject of a back  refer-
+       ence,  or  if  the pattern contains (*PRUNE) or (*SKIP). When the opti-
+       mization is not disabled, such a pattern is automatically  anchored  if
+       PCRE2_DOTALL is set for all the .* items and PCRE2_MULTILINE is not set
+       for any ^ items. Otherwise, the fact that any match must  start  either
+       at  the start of the subject or following a newline is remembered. Like
+       other optimizations, this can cause callouts to be skipped.
+
+         PCRE2_NO_START_OPTIMIZE
+
+       This is an option whose main effect is at matching time.  It  does  not
+       change what pcre2_compile() generates, but it does affect the output of
+       the JIT compiler.
+
+       There are a number of optimizations that may occur at the  start  of  a
+       match,  in  order  to speed up the process. For example, if it is known
+       that an unanchored match must start  with  a  specific  character,  the
+       matching  code searches the subject for that character, and fails imme-
+       diately if it cannot find it, without actually running the main  match-
+       ing  function.  This means that a special item such as (*COMMIT) at the
+       start of a pattern is not considered until after  a  suitable  starting
+       point  for  the  match  has  been found. Also, when callouts or (*MARK)
+       items are in use, these "start-up" optimizations can cause them  to  be
+       skipped  if  the pattern is never actually used. The start-up optimiza-
+       tions are in effect a pre-scan of the subject that takes  place  before
+       the pattern is run.
+
+       The PCRE2_NO_START_OPTIMIZE option disables the start-up optimizations,
+       possibly causing performance to suffer,  but  ensuring  that  in  cases
+       where  the  result is "no match", the callouts do occur, and that items
+       such as (*COMMIT) and (*MARK) are considered at every possible starting
+       position in the subject string.
+
+       Setting  PCRE2_NO_START_OPTIMIZE  may  change the outcome of a matching
+       operation.  Consider the pattern
+
+         (*COMMIT)ABC
+
+       When this is compiled, PCRE2 records the fact that a match  must  start
+       with  the  character  "A".  Suppose the subject string is "DEFABC". The
+       start-up optimization scans along the subject, finds "A" and  runs  the
+       first  match attempt from there. The (*COMMIT) item means that the pat-
+       tern must match the current starting position, which in this  case,  it
+       does.  However,  if  the same match is run with PCRE2_NO_START_OPTIMIZE
+       set, the initial scan along the subject string  does  not  happen.  The
+       first  match  attempt  is  run  starting  from "D" and when this fails,
+       (*COMMIT) prevents any further matches  being  tried,  so  the  overall
+       result is "no match". There are also other start-up optimizations.  For
+       example, a minimum length for the subject may be recorded. Consider the
+       pattern
+
+         (*MARK:A)(X|Y)
+
+       The  minimum  length  for  a  match is one character. If the subject is
+       "ABC", there will be attempts to match "ABC", "BC", and "C". An attempt
+       to match an empty string at the end of the subject does not take place,
+       because PCRE2 knows that the subject is  now  too  short,  and  so  the
+       (*MARK)  is  never encountered. In this case, the optimization does not
+       affect the overall match result, which is still "no match", but it does
+       affect the auxiliary information that is returned.
+
+         PCRE2_NO_UTF_CHECK
+
+       When  PCRE2_UTF  is set, the validity of the pattern as a UTF string is
+       automatically checked. There are  discussions  about  the  validity  of
+       UTF-8  strings,  UTF-16 strings, and UTF-32 strings in the pcre2unicode
+       document.  If an invalid UTF sequence is found, pcre2_compile() returns
+       a negative error code.
+
+       If you know that your pattern is valid, and you want to skip this check
+       for performance reasons, you can  set  the  PCRE2_NO_UTF_CHECK  option.
+       When  it  is set, the effect of passing an invalid UTF string as a pat-
+       tern is undefined. It may cause your program to  crash  or  loop.  Note
+       that   this   option   can   also   be   passed  to  pcre2_match()  and
+       pcre_dfa_match(), to suppress validity checking of the subject string.
+
+         PCRE2_UCP
+
+       This option changes the way PCRE2 processes \B, \b, \D, \d, \S, \s, \W,
+       \w,  and  some  of  the POSIX character classes. By default, only ASCII
+       characters are recognized, but if PCRE2_UCP is set, Unicode  properties
+       are  used instead to classify characters. More details are given in the
+       section on generic character types in the pcre2pattern page. If you set
+       PCRE2_UCP,  matching one of the items it affects takes much longer. The
+       option is available only if PCRE2 has been compiled with  Unicode  sup-
+       port.
+
+         PCRE2_UNGREEDY
+
+       This  option  inverts  the "greediness" of the quantifiers so that they
+       are not greedy by default, but become greedy if followed by "?". It  is
+       not  compatible  with Perl. It can also be set by a (?U) option setting
+       within the pattern.
+
+         PCRE2_UTF
+
+       This option causes PCRE2 to regard both the  pattern  and  the  subject
+       strings  that  are  subsequently processed as strings of UTF characters
+       instead of single-code-unit strings. It  is  available  when  PCRE2  is
+       built  to  include  Unicode  support (which is the default). If Unicode
+       support is not available, the use of this  option  provokes  an  error.
+       Details  of how this option changes the behaviour of PCRE2 are given in
+       the pcre2unicode page.
+
+
+COMPILATION ERROR CODES
+
+       There are over 80 positive error codes that pcre2_compile() may  return
+       if it finds an error in the pattern. There are also some negative error
+       codes that are used for invalid UTF strings.  These  are  the  same  as
+       given  by pcre2_match() and pcre2_dfa_match(), and are described in the
+       pcre2unicode page. The pcre2_get_error_message() function can be called
+       to obtain a textual error message from any error code.
+
+
+JUST-IN-TIME (JIT) COMPILATION
+
+       int pcre2_jit_compile(pcre2_code *code, uint32_t options);
+
+       int pcre2_jit_match(const pcre2_code *code, PCRE2_SPTR subject,
+         PCRE2_SIZE length, PCRE2_SIZE startoffset,
+         uint32_t options, pcre2_match_data *match_data,
+         pcre2_match_context *mcontext);
+
+       void pcre2_jit_free_unused_memory(pcre2_general_context *gcontext);
+
+       pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE startsize,
+         PCRE2_SIZE maxsize, pcre2_general_context *gcontext);
+
+       void pcre2_jit_stack_assign(pcre2_match_context *mcontext,
+         pcre2_jit_callback callback_function, void *callback_data);
+
+       void pcre2_jit_stack_free(pcre2_jit_stack *jit_stack);
+
+       These  functions  provide  support  for  JIT compilation, which, if the
+       just-in-time compiler is available, further processes a  compiled  pat-
+       tern into machine code that executes much faster than the pcre2_match()
+       interpretive matching function. Full details are given in the  pcre2jit
+       documentation.
+
+       JIT  compilation  is  a heavyweight optimization. It can take some time
+       for patterns to be analyzed, and for one-off matches  and  simple  pat-
+       terns  the benefit of faster execution might be offset by a much slower
+       compilation time.  Most, but not all patterns can be optimized  by  the
+       JIT compiler.
+
+
+LOCALE SUPPORT
+
+       PCRE2  handles caseless matching, and determines whether characters are
+       letters, digits, or whatever, by reference to a set of tables,  indexed
+       by  character  code  point.  This applies only to characters whose code
+       points are less than 256. By default, higher-valued code  points  never
+       match  escapes  such  as \w or \d.  However, if PCRE2 is built with UTF
+       support, all characters can be tested with  \p  and  \P,  or,  alterna-
+       tively,  the  PCRE2_UCP  option  can be set when a pattern is compiled;
+       this causes \w and friends to use Unicode property support  instead  of
+       the built-in tables.
+
+       The  use  of  locales  with Unicode is discouraged. If you are handling
+       characters with code points greater than 128,  you  should  either  use
+       Unicode support, or use locales, but not try to mix the two.
+
+       PCRE2  contains  an  internal  set of character tables that are used by
+       default.  These are sufficient for  many  applications.  Normally,  the
+       internal tables recognize only ASCII characters. However, when PCRE2 is
+       built, it is possible to cause the internal tables to be rebuilt in the
+       default "C" locale of the local system, which may cause them to be dif-
+       ferent.
+
+       The internal tables can be overridden by tables supplied by the  appli-
+       cation  that  calls  PCRE2.  These may be created in a different locale
+       from the default.  As more and more applications change to  using  Uni-
+       code, the need for this locale support is expected to die away.
+
+       External  tables  are built by calling the pcre2_maketables() function,
+       in the relevant locale. The result can be passed to pcre2_compile()  as
+       often   as  necessary,  by  creating  a  compile  context  and  calling
+       pcre2_set_character_tables() to set the  tables  pointer  therein.  For
+       example,  to  build  and use tables that are appropriate for the French
+       locale (where accented characters with  values  greater  than  128  are
+       treated as letters), the following code could be used:
+
+         setlocale(LC_CTYPE, "fr_FR");
+         tables = pcre2_maketables(NULL);
+         ccontext = pcre2_compile_context_create(NULL);
+         pcre2_set_character_tables(ccontext, tables);
+         re = pcre2_compile(..., ccontext);
+
+       The  locale  name "fr_FR" is used on Linux and other Unix-like systems;
+       if you are using Windows, the name for the French locale  is  "french".
+       It  is the caller's responsibility to ensure that the memory containing
+       the tables remains available for as long as it is needed.
+
+       The pointer that is passed (via the compile context) to pcre2_compile()
+       is  saved  with  the  compiled pattern, and the same tables are used by
+       pcre2_match() and pcre_dfa_match(). Thus, for any single pattern,  com-
+       pilation,  and  matching  all  happen in the same locale, but different
+       patterns can be processed in different locales.
+
+
+INFORMATION ABOUT A COMPILED PATTERN
+
+       int pcre2_pattern_info(const pcre2 *code, uint32_t what, void *where);
+
+       The pcre2_pattern_info() function returns general information  about  a
+       compiled pattern. For information about callouts, see the next section.
+       The first argument for pcre2_pattern_info() is a pointer  to  the  com-
+       piled pattern. The second argument specifies which piece of information
+       is required, and the third argument is  a  pointer  to  a  variable  to
+       receive  the data. If the third argument is NULL, the first argument is
+       ignored, and the function returns the size in  bytes  of  the  variable
+       that is required for the information requested. Otherwise, The yield of
+       the function is zero for success, or one of the following negative num-
+       bers:
+
+         PCRE2_ERROR_NULL           the argument code was NULL
+         PCRE2_ERROR_BADMAGIC       the "magic number" was not found
+         PCRE2_ERROR_BADOPTION      the value of what was invalid
+         PCRE2_ERROR_UNSET          the requested field is not set
+
+       The  "magic  number" is placed at the start of each compiled pattern as
+       an simple check against passing an arbitrary memory pointer. Here is  a
+       typical  call of pcre2_pattern_info(), to obtain the length of the com-
+       piled pattern:
+
+         int rc;
+         size_t length;
+         rc = pcre2_pattern_info(
+           re,               /* result of pcre2_compile() */
+           PCRE2_INFO_SIZE,  /* what is required */
+           &length);         /* where to put the data */
+
+       The possible values for the second argument are defined in pcre2.h, and
+       are as follows:
+
+         PCRE2_INFO_ALLOPTIONS
+         PCRE2_INFO_ARGOPTIONS
+
+       Return a copy of the pattern's options. The third argument should point
+       to a  uint32_t  variable.  PCRE2_INFO_ARGOPTIONS  returns  exactly  the
+       options  that were passed to pcre2_compile(), whereas PCRE2_INFO_ALLOP-
+       TIONS returns the compile options as modified by any  top-level  option
+       settings  at  the start of the pattern itself. In other words, they are
+       the options that will be in force when matching starts. For example, if
+       the  pattern  /(?im)abc(?-i)d/  is  compiled  with  the  PCRE2_EXTENDED
+       option,   the   result   is   PCRE2_CASELESS,   PCRE2_MULTILINE,    and
+       PCRE2_EXTENDED.
+
+       A  pattern compiled without PCRE2_ANCHORED is automatically anchored by
+       PCRE2 if the first significant item in every top-level branch is one of
+       the following:
+
+         ^     unless PCRE2_MULTILINE is set
+         \A    always
+         \G    always
+         .*    sometimes - see below
+
+       When  .* is the first significant item, anchoring is possible only when
+       all the following are true:
+
+         .* is not in an atomic group
+         .* is not in a capturing group that is the subject
+              of a back reference
+         PCRE2_DOTALL is in force for .*
+         Neither (*PRUNE) nor (*SKIP) appears in the pattern.
+         PCRE2_NO_DOTSTAR_ANCHOR is not set.
+
+       For patterns that are auto-anchored, the PCRE2_ANCHORED bit is  set  in
+       the options returned for PCRE2_INFO_ALLOPTIONS.
+
+         PCRE2_INFO_BACKREFMAX
+
+       Return  the  number  of  the highest back reference in the pattern. The
+       third argument should point to an uint32_t variable. Named  subpatterns
+       acquire  numbers  as well as names, and these count towards the highest
+       back reference.  Back references such as \4 or \g{12}  match  the  cap-
+       tured  characters of the given group, but in addition, the check that a
+       capturing group is set in a conditional subpattern such as (?(3)a|b) is
+       also  a  back  reference.  Zero is returned if there are no back refer-
+       ences.
+
+         PCRE2_INFO_BSR
+
+       The output is a uint32_t whose value indicates what character sequences
+       the \R escape sequence matches. A value of PCRE2_BSR_UNICODE means that
+       \R matches any Unicode line ending sequence; a value of  PCRE2_BSR_ANY-
+       CRLF means that \R matches only CR, LF, or CRLF.
+
+         PCRE2_INFO_CAPTURECOUNT
+
+       Return  the  number  of capturing subpatterns in the pattern. The third
+       argument should point to an uint32_t variable.
+
+         PCRE2_INFO_FIRSTCODETYPE
+
+       Return information about the first code unit of any matched string, for
+       a  non-anchored pattern. The third argument should point to an uint32_t
+       variable.
+
+       If there is a fixed first value, for example, the  letter  "c"  from  a
+       pattern  such  as  (cat|cow|coyote),  1  is returned, and the character
+       value can be retrieved using PCRE2_INFO_FIRSTCODEUNIT. If there  is  no
+       fixed  first  value, but it is known that a match can occur only at the
+       start of the subject or following  a  newline  in  the  subject,  2  is
+       returned. Otherwise, and for anchored patterns, 0 is returned.
+
+         PCRE2_INFO_FIRSTCODEUNIT
+
+       Return  the  value  of the first code unit of any matched string in the
+       situation where PCRE2_INFO_FIRSTCODETYPE returns 1; otherwise return 0.
+       The  third  argument should point to an uint32_t variable. In the 8-bit
+       library, the value is always less than 256. In the 16-bit  library  the
+       value  can  be  up  to 0xffff. In the 32-bit library in UTF-32 mode the
+       value can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32
+       mode.
+
+         PCRE2_INFO_FIRSTBITMAP
+
+       In  the absence of a single first code unit for a non-anchored pattern,
+       pcre2_compile() may construct a 256-bit table that defines a fixed  set
+       of  values for the first code unit in any match. For example, a pattern
+       that starts with [abc] results in a table with  three  bits  set.  When
+       code  unit  values greater than 255 are supported, the flag bit for 255
+       means "any code unit of value 255 or above". If such a table  was  con-
+       structed,  a pointer to it is returned. Otherwise NULL is returned. The
+       third argument should point to an const uint8_t * variable.
+
+         PCRE2_INFO_HASCRORLF
+
+       Return 1 if the pattern contains any explicit  matches  for  CR  or  LF
+       characters, otherwise 0. The third argument should point to an uint32_t
+       variable. An explicit match is either a literal CR or LF character,  or
+       \r or \n.
+
+         PCRE2_INFO_JCHANGED
+
+       Return  1  if  the (?J) or (?-J) option setting is used in the pattern,
+       otherwise 0. The third argument should point to an  uint32_t  variable.
+       (?J)  and  (?-J) set and unset the local PCRE2_DUPNAMES option, respec-
+       tively.
+
+         PCRE2_INFO_JITSIZE
+
+       If the compiled pattern was successfully  processed  by  pcre2_jit_com-
+       pile(),  return  the  size  of  the JIT compiled code, otherwise return
+       zero. The third argument should point to a size_t variable.
+
+         PCRE2_INFO_LASTCODETYPE
+
+       Returns 1 if there is a rightmost literal code unit that must exist  in
+       any  matched string, other than at its start. The third argument should
+       point to an uint32_t  variable.  If  there  is  no  such  value,  0  is
+       returned.  When  1  is  returned,  the  code  unit  value itself can be
+       retrieved using PCRE2_INFO_LASTCODEUNIT.
+
+       For anchored patterns, a last literal value is recorded only if it fol-
+       lows  something  of  variable  length.  For  example,  for  the pattern
+       /^a\d+z\d+/  the  returned  value  is  1  (with   "z"   returned   from
+       PCRE2_INFO_LASTCODEUNIT), but for /^a\dz\d/ the returned value is 0.
+
+         PCRE2_INFO_LASTCODEUNIT
+
+       Return  the value of the rightmost literal data unit that must exist in
+       any matched string, other than at its start, if such a value  has  been
+       recorded.  The  third argument should point to an uint32_t variable. If
+       there is no such value, 0 is returned.
+
+         PCRE2_INFO_MATCHEMPTY
+
+       Return 1 if the pattern can match an empty  string,  otherwise  0.  The
+       third argument should point to an uint32_t variable.
+
+         PCRE2_INFO_MATCHLIMIT
+
+       If  the  pattern  set  a  match  limit by including an item of the form
+       (*LIMIT_MATCH=nnnn) at the start, the  value  is  returned.  The  third
+       argument  should  point to an unsigned 32-bit integer. If no such value
+       has been set,  the  call  to  pcre2_pattern_info()  returns  the  error
+       PCRE2_ERROR_UNSET.
+
+         PCRE2_INFO_MAXLOOKBEHIND
+
+       Return the number of characters (not code units) in the longest lookbe-
+       hind assertion in the pattern. The third argument should  point  to  an
+       unsigned  32-bit  integer. This information is useful when doing multi-
+       segment matching using the partial matching facilities. Note  that  the
+       simple assertions \b and \B require a one-character lookbehind. \A also
+       registers a one-character  lookbehind,  though  it  does  not  actually
+       inspect  the  previous  character.  This is to ensure that at least one
+       character from the old segment is retained when a new segment  is  pro-
+       cessed. Otherwise, if there are no lookbehinds in the pattern, \A might
+       match incorrectly at the start of a new segment.
+
+         PCRE2_INFO_MINLENGTH
+
+       If a minimum length for matching  subject  strings  was  computed,  its
+       value  is  returned.  Otherwise the returned value is 0. The value is a
+       number of characters, which in UTF mode may be different from the  num-
+       ber  of  code  units.   The  third argument should point to an uint32_t
+       variable. The value is a lower bound to  the  length  of  any  matching
+       string.  There  may  not be any strings of that length that do actually
+       match, but every string that does match is at least that long.
+
+         PCRE2_INFO_NAMECOUNT
+         PCRE2_INFO_NAMEENTRYSIZE
+         PCRE2_INFO_NAMETABLE
+
+       PCRE2 supports the use of named as well as numbered capturing parenthe-
+       ses.  The names are just an additional way of identifying the parenthe-
+       ses, which still acquire numbers. Several convenience functions such as
+       pcre2_substring_get_byname()  are provided for extracting captured sub-
+       strings by name. It is also possible to extract the data  directly,  by
+       first  converting  the  name to a number in order to access the correct
+       pointers in the output vector (described with pcre2_match() below).  To
+       do  the  conversion,  you  need to use the name-to-number map, which is
+       described by these three values.
+
+       The map consists of a number of  fixed-size  entries.  PCRE2_INFO_NAME-
+       COUNT  gives  the number of entries, and PCRE2_INFO_NAMEENTRYSIZE gives
+       the size of each entry in code units; both of these return  a  uint32_t
+       value. The entry size depends on the length of the longest name.
+
+       PCRE2_INFO_NAMETABLE returns a pointer to the first entry of the table.
+       This is a PCRE2_SPTR pointer to a block of code  units.  In  the  8-bit
+       library,  the  first two bytes of each entry are the number of the cap-
+       turing parenthesis, most significant byte first. In the 16-bit library,
+       the  pointer  points  to 16-bit code units, the first of which contains
+       the parenthesis number. In the 32-bit library, the  pointer  points  to
+       32-bit  code units, the first of which contains the parenthesis number.
+       The rest of the entry is the corresponding name, zero terminated.
+
+       The names are in alphabetical order. If (?| is used to create  multiple
+       groups  with  the same number, as described in the section on duplicate
+       subpattern numbers in the pcre2pattern page, the groups  may  be  given
+       the  same  name,  but  there  is only one entry in the table. Different
+       names for groups of the same number are not permitted.
+
+       Duplicate names for subpatterns with different numbers  are  permitted,
+       but  only  if  PCRE2_DUPNAMES  is  set. They appear in the table in the
+       order in which they were found in the pattern. In the  absence  of  (?|
+       this  is  the  order of increasing number; when (?| is used this is not
+       necessarily the case because later subpatterns may have lower numbers.
+
+       As a simple example of the name/number table,  consider  the  following
+       pattern  after  compilation by the 8-bit library (assume PCRE2_EXTENDED
+       is set, so white space - including newlines - is ignored):
+
+         (? (?(\d\d)?\d\d) -
+         (?\d\d) - (?\d\d) )
+
+       There are four named subpatterns, so the table has  four  entries,  and
+       each  entry  in the table is eight bytes long. The table is as follows,
+       with non-printing bytes shows in hexadecimal, and undefined bytes shown
+       as ??:
+
+         00 01 d  a  t  e  00 ??
+         00 05 d  a  y  00 ?? ??
+         00 04 m  o  n  t  h  00
+         00 02 y  e  a  r  00 ??
+
+       When  writing  code  to  extract  data from named subpatterns using the
+       name-to-number map, remember that the length of the entries  is  likely
+       to be different for each compiled pattern.
+
+         PCRE2_INFO_NEWLINE
+
+       The output is a uint32_t with one of the following values:
+
+         PCRE2_NEWLINE_CR       Carriage return (CR)
+         PCRE2_NEWLINE_LF       Linefeed (LF)
+         PCRE2_NEWLINE_CRLF     Carriage return, linefeed (CRLF)
+         PCRE2_NEWLINE_ANY      Any Unicode line ending
+         PCRE2_NEWLINE_ANYCRLF  Any of CR, LF, or CRLF
+
+       This  specifies  the default character sequence that will be recognized
+       as meaning "newline" while matching.
+
+         PCRE2_INFO_RECURSIONLIMIT
+
+       If the pattern set a recursion limit by including an item of  the  form
+       (*LIMIT_RECURSION=nnnn)  at the start, the value is returned. The third
+       argument should point to an unsigned 32-bit integer. If no  such  value
+       has  been  set,  the  call  to  pcre2_pattern_info()  returns the error
+       PCRE2_ERROR_UNSET.
+
+         PCRE2_INFO_SIZE
+
+       Return the size of  the  compiled  pattern  in  bytes  (for  all  three
+       libraries).  The third argument should point to a size_t variable. This
+       value includes the size of the general data  block  that  precedes  the
+       code  units of the compiled pattern itself. The value that is used when
+       pcre2_compile() is getting memory in which to place the  compiled  pat-
+       tern  may  be  slightly  larger than the value returned by this option,
+       because there are cases where the code that calculates the size has  to
+       over-estimate.  Processing  a  pattern  with  the JIT compiler does not
+       alter the value returned by this option.
+
+
+INFORMATION ABOUT A PATTERN'S CALLOUTS
+
+       int pcre2_callout_enumerate(const pcre2_code *code,
+         int (*callback)(pcre2_callout_enumerate_block *, void *),
+         void *user_data);
+
+       A script language that supports the use of string arguments in callouts
+       might  like  to  scan  all the callouts in a pattern before running the
+       match. This can be done by calling pcre2_callout_enumerate(). The first
+       argument  is  a  pointer  to a compiled pattern, the second points to a
+       callback function, and the third is arbitrary user data.  The  callback
+       function  is  called  for  every callout in the pattern in the order in
+       which they appear. Its first argument is a pointer to a callout enumer-
+       ation  block,  and  its second argument is the user_data value that was
+       passed to pcre2_callout_enumerate(). The contents of the  callout  enu-
+       meration  block  are described in the pcre2callout documentation, which
+       also gives further details about callouts.
+
+
+SERIALIZATION AND PRECOMPILING
+
+       It is possible to save compiled patterns  on  disc  or  elsewhere,  and
+       reload  them  later, subject to a number of restrictions. The functions
+       whose names begin with pcre2_serialize_ are used for this purpose. They
+       are described in the pcre2serialize documentation.
+
+
+THE MATCH DATA BLOCK
+
+       pcre2_match_data_create(uint32_t ovecsize,
+         pcre2_general_context *gcontext);
+
+       pcre2_match_data_create_from_pattern(const pcre2_code *code,
+         pcre2_general_context *gcontext);
+
+       void pcre2_match_data_free(pcre2_match_data *match_data);
+
+       Information  about  a  successful  or unsuccessful match is placed in a
+       match data block, which is an opaque  structure  that  is  accessed  by
+       function  calls.  In particular, the match data block contains a vector
+       of offsets into the subject string that define the matched part of  the
+       subject  and  any  substrings  that  were captured. This is know as the
+       ovector.
+
+       Before calling pcre2_match(), pcre2_dfa_match(),  or  pcre2_jit_match()
+       you must create a match data block by calling one of the creation func-
+       tions above. For pcre2_match_data_create(), the first argument  is  the
+       number  of  pairs  of  offsets  in  the ovector. One pair of offsets is
+       required to identify the string that matched the  whole  pattern,  with
+       another  pair  for  each  captured substring. For example, a value of 4
+       creates enough space to record the matched portion of the subject  plus
+       three  captured  substrings. A minimum of at least 1 pair is imposed by
+       pcre2_match_data_create(), so it is always possible to return the over-
+       all matched string.
+
+       The second argument of pcre2_match_data_create() is a pointer to a gen-
+       eral context, which can specify custom memory management for  obtaining
+       the memory for the match data block. If you are not using custom memory
+       management, pass NULL, which causes malloc() to be used.
+
+       For pcre2_match_data_create_from_pattern(), the  first  argument  is  a
+       pointer to a compiled pattern. The ovector is created to be exactly the
+       right size to hold all the substrings a pattern might capture. The sec-
+       ond  argument is again a pointer to a general context, but in this case
+       if NULL is passed, the memory is obtained using the same allocator that
+       was used for the compiled pattern (custom or default).
+
+       A  match  data block can be used many times, with the same or different
+       compiled patterns. You can extract information from a match data  block
+       after  a  match  operation  has  finished,  using  functions  that  are
+       described in the sections on  matched  strings  and  other  match  data
+       below.
+
+       When  a  call  of  pcre2_match()  fails, valid data is available in the
+       match   block   only   when   the   error    is    PCRE2_ERROR_NOMATCH,
+       PCRE2_ERROR_PARTIAL,  or  one  of  the  error  codes for an invalid UTF
+       string. Exactly what is available depends on the error, and is detailed
+       below.
+
+       When  one of the matching functions is called, pointers to the compiled
+       pattern and the subject string are set in the match data block so  that
+       they  can  be  referenced  by the extraction functions. After running a
+       match, you must not free a compiled pattern or a subject  string  until
+       after  all  operations  on  the  match data block (for that match) have
+       taken place.
+
+       When a match data block itself is no longer needed, it should be  freed
+       by calling pcre2_match_data_free().
+
+
+MATCHING A PATTERN: THE TRADITIONAL FUNCTION
+
+       int pcre2_match(const pcre2_code *code, PCRE2_SPTR subject,
+         PCRE2_SIZE length, PCRE2_SIZE startoffset,
+         uint32_t options, pcre2_match_data *match_data,
+         pcre2_match_context *mcontext);
+
+       The  function pcre2_match() is called to match a subject string against
+       a compiled pattern, which is passed in the code argument. You can  call
+       pcre2_match() with the same code argument as many times as you like, in
+       order to find multiple matches in the subject string or to  match  dif-
+       ferent subject strings with the same pattern.
+
+       This  function  is  the  main  matching facility of the library, and it
+       operates in a Perl-like manner. For specialist use  there  is  also  an
+       alternative  matching function, which is described below in the section
+       about the pcre2_dfa_match() function.
+
+       Here is an example of a simple call to pcre2_match():
+
+         pcre2_match_data *md = pcre2_match_data_create(4, NULL);
+         int rc = pcre2_match(
+           re,             /* result of pcre2_compile() */
+           "some string",  /* the subject string */
+           11,             /* the length of the subject string */
+           0,              /* start at offset 0 in the subject */
+           0,              /* default options */
+           match_data,     /* the match data block */
+           NULL);          /* a match context; NULL means use defaults */
+
+       If the subject string is zero-terminated, the length can  be  given  as
+       PCRE2_ZERO_TERMINATED. A match context must be provided if certain less
+       common matching parameters are to be changed. For details, see the sec-
+       tion on the match context above.
+
+   The string to be matched by pcre2_match()
+
+       The  subject string is passed to pcre2_match() as a pointer in subject,
+       a length in length, and a starting offset in  startoffset.  The  length
+       and  offset  are  in  code units, not characters.  That is, they are in
+       bytes for the 8-bit library, 16-bit code units for the 16-bit  library,
+       and  32-bit  code units for the 32-bit library, whether or not UTF pro-
+       cessing is enabled.
+
+       If startoffset is greater than the length of the subject, pcre2_match()
+       returns  PCRE2_ERROR_BADOFFSET.  When  the starting offset is zero, the
+       search for a match starts at the beginning of the subject, and this  is
+       by far the most common case. In UTF-8 or UTF-16 mode, the starting off-
+       set must point to the start of a character, or to the end of  the  sub-
+       ject  (in  UTF-32 mode, one code unit equals one character, so all off-
+       sets are valid). Like the  pattern  string,  the  subject  may  contain
+       binary zeroes.
+
+       A  non-zero  starting offset is useful when searching for another match
+       in the same subject by calling pcre2_match()  again  after  a  previous
+       success.   Setting  startoffset  differs  from passing over a shortened
+       string and setting PCRE2_NOTBOL in the case of a  pattern  that  begins
+       with any kind of lookbehind. For example, consider the pattern
+
+         \Biss\B
+
+       which  finds  occurrences  of "iss" in the middle of words. (\B matches
+       only if the current position in the subject is not  a  word  boundary.)
+       When applied to the string "Mississipi" the first call to pcre2_match()
+       finds the first occurrence. If pcre2_match() is called again with  just
+       the  remainder  of  the  subject,  namely  "issipi", it does not match,
+       because \B is always false at the start of the subject, which is deemed
+       to  be  a word boundary. However, if pcre2_match() is passed the entire
+       string again, but with startoffset set to 4, it finds the second occur-
+       rence  of "iss" because it is able to look behind the starting point to
+       discover that it is preceded by a letter.
+
+       Finding all the matches in a subject is tricky  when  the  pattern  can
+       match an empty string. It is possible to emulate Perl's /g behaviour by
+       first  trying  the  match  again  at  the   same   offset,   with   the
+       PCRE2_NOTEMPTY_ATSTART  and  PCRE2_ANCHORED  options,  and then if that
+       fails, advancing the starting  offset  and  trying  an  ordinary  match
+       again.  There  is  some  code  that  demonstrates how to do this in the
+       pcre2demo sample program. In the most general case, you have  to  check
+       to  see  if the newline convention recognizes CRLF as a newline, and if
+       so, and the current character is CR followed by LF, advance the  start-
+       ing offset by two characters instead of one.
+
+       If  a  non-zero starting offset is passed when the pattern is anchored,
+       one attempt to match at the given offset is made. This can only succeed
+       if  the  pattern  does  not require the match to be at the start of the
+       subject.
+
+   Option bits for pcre2_match()
+
+       The unused bits of the options argument for pcre2_match() must be zero.
+       The  only  bits  that  may  be  set  are  PCRE2_ANCHORED, PCRE2_NOTBOL,
+       PCRE2_NOTEOL,          PCRE2_NOTEMPTY,          PCRE2_NOTEMPTY_ATSTART,
+       PCRE2_NO_UTF_CHECK,  PCRE2_PARTIAL_HARD,  and PCRE2_PARTIAL_SOFT. Their
+       action is described below.
+
+       Setting PCRE2_ANCHORED at match time is not supported by  the  just-in-
+       time  (JIT)  compiler.  If  it is set, JIT matching is disabled and the
+       normal interpretive code in pcre2_match() is run. The remaining options
+       are supported for JIT matching.
+
+         PCRE2_ANCHORED
+
+       The PCRE2_ANCHORED option limits pcre2_match() to matching at the first
+       matching position. If a pattern was compiled  with  PCRE2_ANCHORED,  or
+       turned  out to be anchored by virtue of its contents, it cannot be made
+       unachored at matching time. Note that setting the option at match  time
+       disables JIT matching.
+
+         PCRE2_NOTBOL
+
+       This option specifies that first character of the subject string is not
+       the beginning of a line, so the  circumflex  metacharacter  should  not
+       match  before  it.  Setting  this without having set PCRE2_MULTILINE at
+       compile time causes circumflex never to match. This option affects only
+       the behaviour of the circumflex metacharacter. It does not affect \A.
+
+         PCRE2_NOTEOL
+
+       This option specifies that the end of the subject string is not the end
+       of a line, so the dollar metacharacter should not match it nor  (except
+       in  multiline mode) a newline immediately before it. Setting this with-
+       out having set PCRE2_MULTILINE at compile time causes dollar  never  to
+       match. This option affects only the behaviour of the dollar metacharac-
+       ter. It does not affect \Z or \z.
+
+         PCRE2_NOTEMPTY
+
+       An empty string is not considered to be a valid match if this option is
+       set.  If  there are alternatives in the pattern, they are tried. If all
+       the alternatives match the empty string, the entire  match  fails.  For
+       example, if the pattern
+
+         a?b?
+
+       is  applied  to  a  string not beginning with "a" or "b", it matches an
+       empty string at the start of the subject. With PCRE2_NOTEMPTY set, this
+       match  is  not valid, so pcre2_match() searches further into the string
+       for occurrences of "a" or "b".
+
+         PCRE2_NOTEMPTY_ATSTART
+
+       This is like PCRE2_NOTEMPTY, except that it locks out an  empty  string
+       match only at the first matching position, that is, at the start of the
+       subject plus the starting offset. An empty string match  later  in  the
+       subject  is  permitted.   If  the pattern is anchored, such a match can
+       occur only if the pattern contains \K.
+
+         PCRE2_NO_UTF_CHECK
+
+       When PCRE2_UTF is set at compile time, the validity of the subject as a
+       UTF  string  is  checked  by default when pcre2_match() is subsequently
+       called.  The entire string is checked before any other processing takes
+       place,  and a negative error code is returned if the check fails. There
+       are several UTF error codes for each code unit width, corresponding  to
+       different  problems with the code unit sequence. The value of startoff-
+       set is also checked, to ensure that it points to the start of a charac-
+       ter  or  to  the  end  of  the subject. There are discussions about the
+       validity of UTF-8 strings, UTF-16 strings, and UTF-32  strings  in  the
+       pcre2unicode page.
+
+       If  you  know  that  your  subject is valid, and you want to skip these
+       checks for performance reasons,  you  can  set  the  PCRE2_NO_UTF_CHECK
+       option  when  calling  pcre2_match(). You might want to do this for the
+       second and subsequent calls to pcre2_match() if you are making repeated
+       calls to find all the matches in a single subject string.
+
+       NOTE:  When PCRE2_NO_UTF_CHECK is set, the effect of passing an invalid
+       string as a subject, or an invalid value of startoffset, is  undefined.
+       Your program may crash or loop indefinitely.
+
+         PCRE2_PARTIAL_HARD
+         PCRE2_PARTIAL_SOFT
+
+       These  options  turn  on  the partial matching feature. A partial match
+       occurs if the end of the subject string is  reached  successfully,  but
+       there  are not enough subject characters to complete the match. If this
+       happens when PCRE2_PARTIAL_SOFT (but not  PCRE2_PARTIAL_HARD)  is  set,
+       matching  continues  by  testing any remaining alternatives. Only if no
+       complete match can be found is PCRE2_ERROR_PARTIAL returned instead  of
+       PCRE2_ERROR_NOMATCH.  In other words, PCRE2_PARTIAL_SOFT specifies that
+       the caller is prepared to handle a partial match, but only if  no  com-
+       plete match can be found.
+
+       If  PCRE2_PARTIAL_HARD is set, it overrides PCRE2_PARTIAL_SOFT. In this
+       case, if a partial match is found,  pcre2_match()  immediately  returns
+       PCRE2_ERROR_PARTIAL,  without  considering  any  other alternatives. In
+       other words, when PCRE2_PARTIAL_HARD is set, a partial match is consid-
+       ered to be more important that an alternative complete match.
+
+       There is a more detailed discussion of partial and multi-segment match-
+       ing, with examples, in the pcre2partial documentation.
+
+
+NEWLINE HANDLING WHEN MATCHING
+
+       When PCRE2 is built, a default newline convention is set; this is  usu-
+       ally  the standard convention for the operating system. The default can
+       be overridden in a  compile  context.   During  matching,  the  newline
+       choice  affects  the  behaviour  of  the  dot,  circumflex,  and dollar
+       metacharacters. It may also alter the way the match  starting  position
+       is advanced after a match failure for an unanchored pattern.
+
+       When PCRE2_NEWLINE_CRLF, PCRE2_NEWLINE_ANYCRLF, or PCRE2_NEWLINE_ANY is
+       set as the newline convention, and a match attempt  for  an  unanchored
+       pattern fails when the current starting position is at a CRLF sequence,
+       and the pattern contains no explicit matches for CR or  LF  characters,
+       the  match  position  is  advanced by two characters instead of one, in
+       other words, to after the CRLF.
+
+       The above rule is a compromise that makes the most common cases work as
+       expected.  For  example,  if  the  pattern is .+A (and the PCRE2_DOTALL
+       option is not set), it does not match the string "\r\nA" because, after
+       failing  at the start, it skips both the CR and the LF before retrying.
+       However, the pattern [\r\n]A does match that string,  because  it  con-
+       tains an explicit CR or LF reference, and so advances only by one char-
+       acter after the first failure.
+
+       An explicit match for CR of LF is either a literal appearance of one of
+       those  characters  in  the  pattern,  or  one  of  the  \r or \n escape
+       sequences. Implicit matches such as [^X] do not  count,  nor  does  \s,
+       even though it includes CR and LF in the characters that it matches.
+
+       Notwithstanding  the above, anomalous effects may still occur when CRLF
+       is a valid newline sequence and explicit \r or \n escapes appear in the
+       pattern.
+
+
+HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
+
+       uint32_t pcre2_get_ovector_count(pcre2_match_data *match_data);
+
+       PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *match_data);
+
+       In  general, a pattern matches a certain portion of the subject, and in
+       addition, further substrings from the subject  may  be  picked  out  by
+       parenthesized  parts  of  the  pattern.  Following the usage in Jeffrey
+       Friedl's book, this is called "capturing"  in  what  follows,  and  the
+       phrase  "capturing subpattern" or "capturing group" is used for a frag-
+       ment of a pattern that picks out a substring.  PCRE2  supports  several
+       other kinds of parenthesized subpattern that do not cause substrings to
+       be captured. The pcre2_pattern_info() function can be used to find  out
+       how many capturing subpatterns there are in a compiled pattern.
+
+       A  successful match returns the overall matched string and any captured
+       substrings to the caller via a vector of  PCRE2_SIZE  values.  This  is
+       called  the ovector, and is contained within the match data block.  You
+       can obtain direct access to  the  ovector  by  calling  pcre2_get_ovec-
+       tor_pointer()  to  find  its  address, and pcre2_get_ovector_count() to
+       find the number of pairs of values it contains. Alternatively, you  can
+       use the auxiliary functions for accessing captured substrings by number
+       or by name (see below).
+
+       Within the ovector, the first in each pair of values is set to the off-
+       set of the first code unit of a substring, and the second is set to the
+       offset of the first code unit after the end of a substring. These  val-
+       ues  are always code unit offsets, not character offsets. That is, they
+       are byte offsets in the 8-bit library, 16-bit  offsets  in  the  16-bit
+       library, and 32-bit offsets in the 32-bit library.
+
+       After  a  partial  match  (error  return PCRE2_ERROR_PARTIAL), only the
+       first pair of offsets (that is, ovector[0]  and  ovector[1])  are  set.
+       They  identify  the part of the subject that was partially matched. See
+       the pcre2partial documentation for details of partial matching.
+
+       After a successful match, the first pair of offsets identifies the por-
+       tion  of the subject string that was matched by the entire pattern. The
+       next pair is used for the first capturing subpattern, and  so  on.  The
+       value  returned  by pcre2_match() is one more than the highest numbered
+       pair that has been set. For example, if two substrings have  been  cap-
+       tured,  the returned value is 3. If there are no capturing subpatterns,
+       the return value from a successful match is 1, indicating that just the
+       first pair of offsets has been set.
+
+       If  a  pattern uses the \K escape sequence within a positive assertion,
+       the reported start of a successful match can be greater than the end of
+       the  match.   For  example,  if the pattern (?=ab\K) is matched against
+       "ab", the start and end offset values for the match are 2 and 0.
+
+       If a capturing subpattern group is matched repeatedly within  a  single
+       match  operation, it is the last portion of the subject that it matched
+       that is returned.
+
+       If the ovector is too small to hold all the captured substring offsets,
+       as  much  as possible is filled in, and the function returns a value of
+       zero. If captured substrings are not of interest, pcre2_match() may  be
+       called with a match data block whose ovector is of minimum length (that
+       is, one pair). However, if the pattern contains back references and the
+       ovector is not big enough to remember the related substrings, PCRE2 has
+       to get additional memory for use during matching. Thus  it  is  usually
+       advisable to set up a match data block containing an ovector of reason-
+       able size.
+
+       It is possible for capturing subpattern number n+1 to match  some  part
+       of the subject when subpattern n has not been used at all. For example,
+       if the string "abc" is matched  against  the  pattern  (a|(z))(bc)  the
+       return from the function is 4, and subpatterns 1 and 3 are matched, but
+       2 is not. When this happens, both values in  the  offset  pairs  corre-
+       sponding to unused subpatterns are set to PCRE2_UNSET.
+
+       Offset  values  that correspond to unused subpatterns at the end of the
+       expression are also set to PCRE2_UNSET.  For  example,  if  the  string
+       "abc" is matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3
+       are not matched.  The return from the function is 2, because the  high-
+       est used capturing subpattern number is 1. The offsets for for the sec-
+       ond and third capturing  subpatterns  (assuming  the  vector  is  large
+       enough, of course) are set to PCRE2_UNSET.
+
+       Elements in the ovector that do not correspond to capturing parentheses
+       in the pattern are never changed. That is, if a pattern contains n cap-
+       turing parentheses, no more than ovector[0] to ovector[2n+1] are set by
+       pcre2_match(). The other elements retain whatever  values  they  previ-
+       ously had.
+
+
+OTHER INFORMATION ABOUT A MATCH
+
+       PCRE2_SPTR pcre2_get_mark(pcre2_match_data *match_data);
+
+       PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *match_data);
+
+       As  well as the offsets in the ovector, other information about a match
+       is retained in the match data block and can be retrieved by  the  above
+       functions  in  appropriate  circumstances.  If they are called at other
+       times, the result is undefined.
+
+       After a successful match, a partial match (PCRE2_ERROR_PARTIAL),  or  a
+       failure  to  match  (PCRE2_ERROR_NOMATCH), a (*MARK) name may be avail-
+       able, and pcre2_get_mark() can be called. It returns a pointer  to  the
+       zero-terminated  name,  which is within the compiled pattern. Otherwise
+       NULL is returned. After a successful match, the (*MARK)  name  that  is
+       returned  is  the last one encountered on the matching path through the
+       pattern. After a "no match" or a partial match,  the  last  encountered
+       (*MARK) name is returned. For example, consider this pattern:
+
+         ^(*MARK:A)((*MARK:B)a|b)c
+
+       When  it  matches "bc", the returned mark is A. The B mark is "seen" in
+       the first branch of the group, but it is not on the matching  path.  On
+       the  other  hand,  when  this pattern fails to match "bx", the returned
+       mark is B.
+
+       After a successful match, a partial match, or one of  the  invalid  UTF
+       errors  (for example, PCRE2_ERROR_UTF8_ERR5), pcre2_get_startchar() can
+       be called. After a successful or partial match it returns the code unit
+       offset  of  the character at which the match started. For a non-partial
+       match, this can be different to the value of ovector[0] if the  pattern
+       contains  the  \K escape sequence. After a partial match, however, this
+       value is always the same as ovector[0] because \K does not  affect  the
+       result of a partial match.
+
+       After  a UTF check failure, pcre2_get_startchar() can be used to obtain
+       the code unit offset of the invalid UTF character. Details are given in
+       the pcre2unicode page.
+
+
+ERROR RETURNS FROM pcre2_match()
+
+       If  pcre2_match() fails, it returns a negative number. This can be con-
+       verted to a text string by calling pcre2_get_error_message().  Negative
+       error  codes  are  also returned by other functions, and are documented
+       with them.  The codes are given names in the header file. If UTF check-
+       ing is in force and an invalid UTF subject string is detected, one of a
+       number of UTF-specific negative error codes is  returned.  Details  are
+       given in the pcre2unicode page. The following are the other errors that
+       may be returned by pcre2_match():
+
+         PCRE2_ERROR_NOMATCH
+
+       The subject string did not match the pattern.
+
+         PCRE2_ERROR_PARTIAL
+
+       The subject string did not match, but it did match partially.  See  the
+       pcre2partial documentation for details of partial matching.
+
+         PCRE2_ERROR_BADMAGIC
+
+       PCRE2 stores a 4-byte "magic number" at the start of the compiled code,
+       to catch the case when it is passed a junk pointer. This is  the  error
+       that is returned when the magic number is not present.
+
+         PCRE2_ERROR_BADMODE
+
+       This  error  is  given  when  a  pattern that was compiled by the 8-bit
+       library is passed to a 16-bit  or  32-bit  library  function,  or  vice
+       versa.
+
+         PCRE2_ERROR_BADOFFSET
+
+       The value of startoffset was greater than the length of the subject.
+
+         PCRE2_ERROR_BADOPTION
+
+       An unrecognized bit was set in the options argument.
+
+         PCRE2_ERROR_BADUTFOFFSET
+
+       The UTF code unit sequence that was passed as a subject was checked and
+       found to be valid (the PCRE2_NO_UTF_CHECK option was not set), but  the
+       value  of startoffset did not point to the beginning of a UTF character
+       or the end of the subject.
+
+         PCRE2_ERROR_CALLOUT
+
+       This error is never generated by pcre2_match() itself. It  is  provided
+       for  use  by  callout  functions  that  want  to cause pcre2_match() or
+       pcre2_callout_enumerate() to return a distinctive error code.  See  the
+       pcre2callout documentation for details.
+
+         PCRE2_ERROR_INTERNAL
+
+       An  unexpected  internal error has occurred. This error could be caused
+       by a bug in PCRE2 or by overwriting of the compiled pattern.
+
+         PCRE2_ERROR_JIT_BADOPTION
+
+       This error is returned when a pattern  that  was  successfully  studied
+       using  JIT is being matched, but the matching mode (partial or complete
+       match) does not correspond to any JIT compilation mode.  When  the  JIT
+       fast  path  function  is used, this error may be also given for invalid
+       options. See the pcre2jit documentation for more details.
+
+         PCRE2_ERROR_JIT_STACKLIMIT
+
+       This error is returned when a pattern  that  was  successfully  studied
+       using  JIT  is being matched, but the memory available for the just-in-
+       time processing stack is not large enough. See the pcre2jit  documenta-
+       tion for more details.
+
+         PCRE2_ERROR_MATCHLIMIT
+
+       The backtracking limit was reached.
+
+         PCRE2_ERROR_NOMEMORY
+
+       If  a  pattern  contains  back  references,  but the ovector is not big
+       enough to remember the referenced substrings, PCRE2  gets  a  block  of
+       memory at the start of matching to use for this purpose. There are some
+       other special cases where extra memory is needed during matching.  This
+       error is given when memory cannot be obtained.
+
+         PCRE2_ERROR_NULL
+
+       Either the code, subject, or match_data argument was passed as NULL.
+
+         PCRE2_ERROR_RECURSELOOP
+
+       This  error  is  returned  when  pcre2_match() detects a recursion loop
+       within the pattern. Specifically, it means that either the  whole  pat-
+       tern or a subpattern has been called recursively for the second time at
+       the same position in the subject  string.  Some  simple  patterns  that
+       might  do  this are detected and faulted at compile time, but more com-
+       plicated cases, in particular mutual recursions between  two  different
+       subpatterns, cannot be detected until matching is attempted.
+
+         PCRE2_ERROR_RECURSIONLIMIT
+
+       The internal recursion limit was reached.
+
+
+EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
+
+       int pcre2_substring_length_bynumber(pcre2_match_data *match_data,
+         uint32_t number, PCRE2_SIZE *length);
+
+       int pcre2_substring_copy_bynumber(pcre2_match_data *match_data,
+         uint32_t number, PCRE2_UCHAR *buffer,
+         PCRE2_SIZE *bufflen);
+
+       int pcre2_substring_get_bynumber(pcre2_match_data *match_data,
+         uint32_t number, PCRE2_UCHAR **bufferptr,
+         PCRE2_SIZE *bufflen);
+
+       void pcre2_substring_free(PCRE2_UCHAR *buffer);
+
+       Captured  substrings  can  be accessed directly by using the ovector as
+       described above.  For convenience, auxiliary functions are provided for
+       extracting   captured  substrings  as  new,  separate,  zero-terminated
+       strings. A substring that contains a binary zero is correctly extracted
+       and  has  a  further  zero  added on the end, but the result is not, of
+       course, a C string.
+
+       The functions in this section identify substrings by number. The number
+       zero refers to the entire matched substring, with higher numbers refer-
+       ring to substrings captured by parenthesized groups.  After  a  partial
+       match,  only  substring  zero  is  available. An attempt to extract any
+       other substring gives the error PCRE2_ERROR_PARTIAL. The  next  section
+       describes similar functions for extracting captured substrings by name.
+
+       If  a  pattern uses the \K escape sequence within a positive assertion,
+       the reported start of a successful match can be greater than the end of
+       the  match.   For  example,  if the pattern (?=ab\K) is matched against
+       "ab", the start and end offset values for the match are  2  and  0.  In
+       this  situation,  calling  these functions with a zero substring number
+       extracts a zero-length empty string.
+
+       You can find the length in code units of a captured  substring  without
+       extracting  it  by calling pcre2_substring_length_bynumber(). The first
+       argument is a pointer to the match data block, the second is the  group
+       number,  and the third is a pointer to a variable into which the length
+       is placed. If you just want to know whether or not  the  substring  has
+       been captured, you can pass the third argument as NULL.
+
+       The  pcre2_substring_copy_bynumber()  function  copies  a captured sub-
+       string into a supplied buffer,  whereas  pcre2_substring_get_bynumber()
+       copies  it  into  new memory, obtained using the same memory allocation
+       function that was used for the match data block. The  first  two  argu-
+       ments  of  these  functions are a pointer to the match data block and a
+       capturing group number.
+
+       The final arguments of pcre2_substring_copy_bynumber() are a pointer to
+       the buffer and a pointer to a variable that contains its length in code
+       units.  This is updated to contain the actual number of code units used
+       for the extracted substring, excluding the terminating zero.
+
+       For pcre2_substring_get_bynumber() the third and fourth arguments point
+       to variables that are updated with a pointer to the new memory and  the
+       number  of  code units that comprise the substring, again excluding the
+       terminating zero. When the substring is no longer  needed,  the  memory
+       should be freed by calling pcre2_substring_free().
+
+       The  return  value  from  all these functions is zero for success, or a
+       negative error code. If the pattern match  failed,  the  match  failure
+       code  is  returned.   If  a  substring number greater than zero is used
+       after a partial match, PCRE2_ERROR_PARTIAL is returned. Other  possible
+       error codes are:
+
+         PCRE2_ERROR_NOMEMORY
+
+       The  buffer  was  too small for pcre2_substring_copy_bynumber(), or the
+       attempt to get memory failed for pcre2_substring_get_bynumber().
+
+         PCRE2_ERROR_NOSUBSTRING
+
+       There is no substring with that number in the  pattern,  that  is,  the
+       number is greater than the number of capturing parentheses.
+
+         PCRE2_ERROR_UNAVAILABLE
+
+       The substring number, though not greater than the number of captures in
+       the pattern, is greater than the number of slots in the ovector, so the
+       substring could not be captured.
+
+         PCRE2_ERROR_UNSET
+
+       The  substring  did  not  participate in the match. For example, if the
+       pattern is (abc)|(def) and the subject is "def", and the  ovector  con-
+       tains at least two capturing slots, substring number 1 is unset.
+
+
+EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS
+
+       int pcre2_substring_list_get(pcre2_match_data *match_data,
+         PCRE2_UCHAR ***listptr, PCRE2_SIZE **lengthsptr);
+
+       void pcre2_substring_list_free(PCRE2_SPTR *list);
+
+       The  pcre2_substring_list_get()  function  extracts  all available sub-
+       strings and builds a list of pointers to  them.  It  also  (optionally)
+       builds  a  second  list  that  contains  their lengths (in code units),
+       excluding a terminating zero that is added to each of them. All this is
+       done in a single block of memory that is obtained using the same memory
+       allocation function that was used to get the match data block.
+
+       This function must be called only after a successful match.  If  called
+       after a partial match, the error code PCRE2_ERROR_PARTIAL is returned.
+
+       The  address of the memory block is returned via listptr, which is also
+       the start of the list of string pointers. The end of the list is marked
+       by  a  NULL pointer. The address of the list of lengths is returned via
+       lengthsptr. If your strings do not contain binary zeros and you do  not
+       therefore need the lengths, you may supply NULL as the lengthsptr argu-
+       ment to disable the creation of a list of lengths.  The  yield  of  the
+       function  is zero if all went well, or PCRE2_ERROR_NOMEMORY if the mem-
+       ory block could not be obtained. When the list is no longer needed,  it
+       should be freed by calling pcre2_substring_list_free().
+
+       If this function encounters a substring that is unset, which can happen
+       when capturing subpattern number n+1 matches some part of the  subject,
+       but  subpattern n has not been used at all, it returns an empty string.
+       This can be distinguished  from  a  genuine  zero-length  substring  by
+       inspecting  the  appropriate  offset  in  the  ovector,  which  contain
+       PCRE2_UNSET  for   unset   substrings,   or   by   calling   pcre2_sub-
+       string_length_bynumber().
+
+
+EXTRACTING CAPTURED SUBSTRINGS BY NAME
+
+       int pcre2_substring_number_from_name(const pcre2_code *code,
+         PCRE2_SPTR name);
+
+       int pcre2_substring_length_byname(pcre2_match_data *match_data,
+         PCRE2_SPTR name, PCRE2_SIZE *length);
+
+       int pcre2_substring_copy_byname(pcre2_match_data *match_data,
+         PCRE2_SPTR name, PCRE2_UCHAR *buffer, PCRE2_SIZE *bufflen);
+
+       int pcre2_substring_get_byname(pcre2_match_data *match_data,
+         PCRE2_SPTR name, PCRE2_UCHAR **bufferptr, PCRE2_SIZE *bufflen);
+
+       void pcre2_substring_free(PCRE2_UCHAR *buffer);
+
+       To  extract a substring by name, you first have to find associated num-
+       ber.  For example, for this pattern:
+
+         (a+)b(?\d+)...
+
+       the number of the subpattern called "xxx" is 2. If the name is known to
+       be  unique  (PCRE2_DUPNAMES  was not set), you can find the number from
+       the name by calling pcre2_substring_number_from_name(). The first argu-
+       ment  is the compiled pattern, and the second is the name. The yield of
+       the function is the subpattern number, PCRE2_ERROR_NOSUBSTRING if there
+       is  no  subpattern  of  that  name, or PCRE2_ERROR_NOUNIQUESUBSTRING if
+       there is more than one subpattern of that name. Given the  number,  you
+       can  extract  the  substring  directly,  or  use  one  of the functions
+       described above.
+
+       For convenience, there are also "byname" functions that  correspond  to
+       the  "bynumber"  functions,  the  only difference being that the second
+       argument is a name instead of a number. If PCRE2_DUPNAMES  is  set  and
+       there are duplicate names, these functions scan all the groups with the
+       given name, and return the first named string that is set.
+
+       If there are no groups with the given name, PCRE2_ERROR_NOSUBSTRING  is
+       returned.  If  all  groups  with the name have numbers that are greater
+       than the number of slots in  the  ovector,  PCRE2_ERROR_UNAVAILABLE  is
+       returned.  If  there  is at least one group with a slot in the ovector,
+       but no group is found to be set, PCRE2_ERROR_UNSET is returned.
+
+       Warning: If the pattern uses the (?| feature to set up multiple subpat-
+       terns  with  the  same number, as described in the section on duplicate
+       subpattern numbers in the pcre2pattern page, you cannot  use  names  to
+       distinguish  the  different subpatterns, because names are not included
+       in the compiled code. The matching process uses only numbers. For  this
+       reason,  the  use of different names for subpatterns of the same number
+       causes an error at compile time.
+
+
+CREATING A NEW STRING WITH SUBSTITUTIONS
+
+       int pcre2_substitute(const pcre2_code *code, PCRE2_SPTR subject,
+         PCRE2_SIZE length, PCRE2_SIZE startoffset,
+         uint32_t options, pcre2_match_data *match_data,
+         pcre2_match_context *mcontext, PCRE2_SPTR replacementzfP,
+         PCRE2_SIZE rlength, PCRE2_UCHAR *outputbufferP,
+         PCRE2_SIZE *outlengthptr);
+       This function calls pcre2_match() and then makes a copy of the  subject
+       string  in  outputbuffer,  replacing the part that was matched with the
+       replacement string, whose length is supplied in rlength.  This  can  be
+       given as PCRE2_ZERO_TERMINATED for a zero-terminated string.
+
+       In  the replacement string, which is interpreted as a UTF string in UTF
+       mode, and is checked for UTF  validity  unless  the  PCRE2_NO_UTF_CHECK
+       option is set, a dollar character is an escape character that can spec-
+       ify the insertion of characters from capturing groups in  the  pattern.
+       The following forms are recognized:
+
+         $$      insert a dollar character
+         $    insert the contents of group 
+         ${}  insert the contents of group 
+
+       Either  a  group  number  or  a  group name can be given for . Curly
+       brackets are required only if the following character would  be  inter-
+       preted as part of the number or name. The number may be zero to include
+       the entire matched string.   For  example,  if  the  pattern  a(b)c  is
+       matched  with "=abc=" and the replacement string "+$1$0$1+", the result
+       is "=+babcb+=". Group insertion is done by calling  pcre2_copy_byname()
+       or pcre2_copy_bynumber() as appropriate.
+
+       The  first  seven  arguments  of pcre2_substitute() are the same as for
+       pcre2_match(), except that the partial matching options are not permit-
+       ted,  and  match_data may be passed as NULL, in which case a match data
+       block is obtained and freed within this function, using memory  manage-
+       ment  functions from the match context, if provided, or else those that
+       were used to allocate memory for the compiled code.
+
+       There is one additional option, PCRE2_SUBSTITUTE_GLOBAL,  which  causes
+       the function to iterate over the subject string, replacing every match-
+       ing substring. If this is not set, only the first matching substring is
+       replaced.
+
+       The  outlengthptr  argument  must point to a variable that contains the
+       length, in code units, of the output buffer. It is updated  to  contain
+       the length of the new string, excluding the trailing zero that is auto-
+       matically added.
+
+       The function returns the number of replacements that  were  made.  This
+       may  be  zero  if  no  matches  were found, and is never greater than 1
+       unless PCRE2_SUBSTITUTE_GLOBAL is set. In the event of an error, a neg-
+       ative  error code is returned. Except for PCRE2_ERROR_NOMATCH (which is
+       never returned), any errors from pcre2_match() or the substring copying
+       functions  are  passed  straight  back.  PCRE2_ERROR_BADREPLACEMENT  is
+       returned for an invalid replacement string (unrecognized sequence  fol-
+       lowing a dollar sign), and PCRE2_ERROR_NOMEMORY is returned if the out-
+       put buffer is not big enough.
+
+
+DUPLICATE SUBPATTERN NAMES
+
+       int pcre2_substring_nametable_scan(const pcre2_code *code,
+         PCRE2_SPTR name, PCRE2_SPTR *first, PCRE2_SPTR *last);
+
+       When a pattern is compiled with the PCRE2_DUPNAMES  option,  names  for
+       subpatterns  are  not required to be unique. Duplicate names are always
+       allowed for subpatterns with the same number, created by using the  (?|
+       feature.  Indeed,  if  such subpatterns are named, they are required to
+       use the same names.
+
+       Normally, patterns with duplicate names are such that in any one match,
+       only  one of the named subpatterns participates. An example is shown in
+       the pcre2pattern documentation.
+
+       When  duplicates   are   present,   pcre2_substring_copy_byname()   and
+       pcre2_substring_get_byname()  return  the first substring corresponding
+       to  the  given  name  that  is  set.  Only   if   none   are   set   is
+       PCRE2_ERROR_UNSET  is  returned. The pcre2_substring_number_from_name()
+       function returns the error PCRE2_ERROR_NOUNIQUESUBSTRING when there are
+       duplicate names.
+
+       If  you want to get full details of all captured substrings for a given
+       name, you must use the pcre2_substring_nametable_scan()  function.  The
+       first  argument is the compiled pattern, and the second is the name. If
+       the third and fourth arguments are NULL, the function returns  a  group
+       number for a unique name, or PCRE2_ERROR_NOUNIQUESUBSTRING otherwise.
+
+       When the third and fourth arguments are not NULL, they must be pointers
+       to variables that are updated by the function. After it has  run,  they
+       point to the first and last entries in the name-to-number table for the
+       given name, and the function returns the length of each entry  in  code
+       units.  In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there are
+       no entries for the given name.
+
+       The format of the name table is described above in the section entitled
+       Information  about a pattern above.  Given all the relevant entries for
+       the name, you can extract each of their numbers, and hence the captured
+       data.
+
+
+FINDING ALL POSSIBLE MATCHES AT ONE POSITION
+
+       The  traditional  matching  function  uses a similar algorithm to Perl,
+       which stops when it finds the first match at a given point in the  sub-
+       ject. If you want to find all possible matches, or the longest possible
+       match at a given position,  consider  using  the  alternative  matching
+       function  (see  below) instead. If you cannot use the alternative func-
+       tion, you can kludge it up by making use of the callout facility, which
+       is described in the pcre2callout documentation.
+
+       What you have to do is to insert a callout right at the end of the pat-
+       tern.  When your callout function is called, extract and save the  cur-
+       rent  matched  substring.  Then return 1, which forces pcre2_match() to
+       backtrack and try other alternatives. Ultimately, when it runs  out  of
+       matches, pcre2_match() will yield PCRE2_ERROR_NOMATCH.
+
+
+MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
+
+       int pcre2_dfa_match(const pcre2_code *code, PCRE2_SPTR subject,
+         PCRE2_SIZE length, PCRE2_SIZE startoffset,
+         uint32_t options, pcre2_match_data *match_data,
+         pcre2_match_context *mcontext,
+         int *workspace, PCRE2_SIZE wscount);
+
+       The  function  pcre2_dfa_match()  is  called  to match a subject string
+       against a compiled pattern, using a matching algorithm that  scans  the
+       subject  string  just  once, and does not backtrack. This has different
+       characteristics to the normal algorithm, and  is  not  compatible  with
+       Perl.  Some of the features of PCRE2 patterns are not supported. Never-
+       theless, there are times when this kind of matching can be useful.  For
+       a  discussion  of  the  two matching algorithms, and a list of features
+       that pcre2_dfa_match() does not support, see the pcre2matching documen-
+       tation.
+
+       The  arguments  for  the pcre2_dfa_match() function are the same as for
+       pcre2_match(), plus two extras. The ovector within the match data block
+       is used in a different way, and this is described below. The other com-
+       mon arguments are used in the same way as for pcre2_match(),  so  their
+       description is not repeated here.
+
+       The  two  additional  arguments provide workspace for the function. The
+       workspace vector should contain at least 20 elements. It  is  used  for
+       keeping  track  of  multiple  paths  through  the  pattern  tree.  More
+       workspace is needed for patterns and subjects where there are a lot  of
+       potential matches.
+
+       Here is an example of a simple call to pcre2_dfa_match():
+
+         int wspace[20];
+         pcre2_match_data *md = pcre2_match_data_create(4, NULL);
+         int rc = pcre2_dfa_match(
+           re,             /* result of pcre2_compile() */
+           "some string",  /* the subject string */
+           11,             /* the length of the subject string */
+           0,              /* start at offset 0 in the subject */
+           0,              /* default options */
+           match_data,     /* the match data block */
+           NULL,           /* a match context; NULL means use defaults */
+           wspace,         /* working space vector */
+           20);            /* number of elements (NOT size in bytes) */
+
+   Option bits for pcre_dfa_match()
+
+       The  unused  bits of the options argument for pcre2_dfa_match() must be
+       zero. The only bits that may be set are  PCRE2_ANCHORED,  PCRE2_NOTBOL,
+       PCRE2_NOTEOL,          PCRE2_NOTEMPTY,          PCRE2_NOTEMPTY_ATSTART,
+       PCRE2_NO_UTF_CHECK,       PCRE2_PARTIAL_HARD,       PCRE2_PARTIAL_SOFT,
+       PCRE2_DFA_SHORTEST,  and  PCRE2_DFA_RESTART.  All  but the last four of
+       these are exactly the same as for pcre2_match(), so  their  description
+       is not repeated here.
+
+         PCRE2_PARTIAL_HARD
+         PCRE2_PARTIAL_SOFT
+
+       These  have  the  same general effect as they do for pcre2_match(), but
+       the details are slightly different. When PCRE2_PARTIAL_HARD is set  for
+       pcre2_dfa_match(),  it  returns  PCRE2_ERROR_PARTIAL  if the end of the
+       subject is reached and there is still at least one matching possibility
+       that requires additional characters. This happens even if some complete
+       matches have already been found. When PCRE2_PARTIAL_SOFT  is  set,  the
+       return  code  PCRE2_ERROR_NOMATCH is converted into PCRE2_ERROR_PARTIAL
+       if the end of the subject is  reached,  there  have  been  no  complete
+       matches, but there is still at least one matching possibility. The por-
+       tion of the string that was inspected when the  longest  partial  match
+       was found is set as the first matching string in both cases. There is a
+       more detailed discussion of partial and  multi-segment  matching,  with
+       examples, in the pcre2partial documentation.
+
+         PCRE2_DFA_SHORTEST
+
+       Setting  the PCRE2_DFA_SHORTEST option causes the matching algorithm to
+       stop as soon as it has found one match. Because of the way the alterna-
+       tive  algorithm  works, this is necessarily the shortest possible match
+       at the first possible matching point in the subject string.
+
+         PCRE2_DFA_RESTART
+
+       When pcre2_dfa_match() returns a partial match, it is possible to  call
+       it again, with additional subject characters, and have it continue with
+       the same match. The PCRE2_DFA_RESTART option requests this action; when
+       it  is  set,  the workspace and wscount options must reference the same
+       vector as before because data about the match so far is  left  in  them
+       after a partial match. There is more discussion of this facility in the
+       pcre2partial documentation.
+
+   Successful returns from pcre2_dfa_match()
+
+       When pcre2_dfa_match() succeeds, it may have matched more than one sub-
+       string in the subject. Note, however, that all the matches from one run
+       of the function start at the same point in  the  subject.  The  shorter
+       matches  are all initial substrings of the longer matches. For example,
+       if the pattern
+
+         <.*>
+
+       is matched against the string
+
+         This is    no more
+
+       the three matched strings are
+
+           
+          
+         
+
+       On success, the yield of the function is a number  greater  than  zero,
+       which  is  the  number  of  matched substrings. The offsets of the sub-
+       strings are returned in the ovector, and can be extracted by number  in
+       the  same way as for pcre2_match(), but the numbers bear no relation to
+       any capturing groups that may exist in the pattern, because DFA  match-
+       ing does not support group capture.
+
+       Calls  to  the  convenience  functions  that extract substrings by name
+       return the error PCRE2_ERROR_DFA_UFUNC (unsupported function)  if  used
+       after a DFA match. The convenience functions that extract substrings by
+       number never return PCRE2_ERROR_NOSUBSTRING, and the meanings  of  some
+       other errors are slightly different:
+
+         PCRE2_ERROR_UNAVAILABLE
+
+       The ovector is not big enough to include a slot for the given substring
+       number.
+
+         PCRE2_ERROR_UNSET
+
+       There is a slot in the ovector  for  this  substring,  but  there  were
+       insufficient matches to fill it.
+
+       The  matched  strings  are  stored  in  the ovector in reverse order of
+       length; that is, the longest matching string is first.  If  there  were
+       too  many matches to fit into the ovector, the yield of the function is
+       zero, and the vector is filled with the longest matches.
+
+       NOTE: PCRE2's "auto-possessification" optimization usually  applies  to
+       character  repeats at the end of a pattern (as well as internally). For
+       example, the pattern "a\d+" is compiled as if it were "a\d++". For  DFA
+       matching,  this  means  that  only  one possible match is found. If you
+       really do want multiple matches in such cases, either use  an  ungreedy
+       repeat  auch  as  "a\d+?"  or set the PCRE2_NO_AUTO_POSSESS option when
+       compiling.
+
+   Error returns from pcre2_dfa_match()
+
+       The pcre2_dfa_match() function returns a negative number when it fails.
+       Many  of  the  errors  are  the same as for pcre2_match(), as described
+       above.  There are in addition the following errors that are specific to
+       pcre2_dfa_match():
+
+         PCRE2_ERROR_DFA_UITEM
+
+       This  return  is  given  if pcre2_dfa_match() encounters an item in the
+       pattern that it does not support, for instance, the use of \C or a back
+       reference.
+
+         PCRE2_ERROR_DFA_UCOND
+
+       This  return  is given if pcre2_dfa_match() encounters a condition item
+       that uses a back reference for the condition, or a test  for  recursion
+       in a specific group. These are not supported.
+
+         PCRE2_ERROR_DFA_WSSIZE
+
+       This  return  is  given  if  pcre2_dfa_match() runs out of space in the
+       workspace vector.
+
+         PCRE2_ERROR_DFA_RECURSE
+
+       When a recursive subpattern is processed, the matching  function  calls
+       itself recursively, using private memory for the ovector and workspace.
+       This error is given if the internal ovector is not large  enough.  This
+       should be extremely rare, as a vector of size 1000 is used.
+
+         PCRE2_ERROR_DFA_BADRESTART
+
+       When  pcre2_dfa_match()  is  called  with the PCRE2_DFA_RESTART option,
+       some plausibility checks are made on the  contents  of  the  workspace,
+       which  should  contain data about the previous partial match. If any of
+       these checks fail, this error is given.
+
+
+SEE ALSO
+
+       pcre2build(3),   pcre2callout(3),    pcre2demo(3),    pcre2matching(3),
+       pcre2partial(3),    pcre2posix(3),    pcre2sample(3),    pcre2stack(3),
+       pcre2unicode(3).
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge, England.
+
+
+REVISION
+
+       Last updated: 22 April 2015
+       Copyright (c) 1997-2015 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCRE2BUILD(3)              Library Functions Manual              PCRE2BUILD(3)
+
+
+
+NAME
+       PCRE2 - Perl-compatible regular expressions (revised API)
+
+BUILDING PCRE2
+
+       PCRE2  is distributed with a configure script that can be used to build
+       the library in Unix-like environments using the applications  known  as
+       Autotools. Also in the distribution are files to support building using
+       CMake instead of configure.  The  text  file  README  contains  general
+       information  about  building  with Autotools (some of which is repeated
+       below), and also has some comments about building on various  operating
+       systems.  There  is a lot more information about building PCRE2 without
+       using Autotools (including information about using CMake  and  building
+       "by  hand")  in  the  text file called NON-AUTOTOOLS-BUILD.  You should
+       consult this file as well as the README file if you are building  in  a
+       non-Unix-like environment.
+
+
+PCRE2 BUILD-TIME OPTIONS
+
+       The rest of this document describes the optional features of PCRE2 that
+       can be selected when the library is compiled. It  assumes  use  of  the
+       configure  script,  where  the  optional features are selected or dese-
+       lected by providing options to configure before running the  make  com-
+       mand.  However,  the same options can be selected in both Unix-like and
+       non-Unix-like environments if you are using CMake instead of  configure
+       to build PCRE2.
+
+       If  you  are not using Autotools or CMake, option selection can be done
+       by editing the config.h file, or by passing parameter settings  to  the
+       compiler, as described in NON-AUTOTOOLS-BUILD.
+
+       The complete list of options for configure (which includes the standard
+       ones such as the  selection  of  the  installation  directory)  can  be
+       obtained by running
+
+         ./configure --help
+
+       The  following  sections  include  descriptions  of options whose names
+       begin with --enable or --disable. These settings specify changes to the
+       defaults  for  the configure command. Because of the way that configure
+       works, --enable and --disable always come in pairs, so  the  complemen-
+       tary  option always exists as well, but as it specifies the default, it
+       is not described.
+
+
+BUILDING 8-BIT, 16-BIT AND 32-BIT LIBRARIES
+
+       By default, a library called libpcre2-8 is built, containing  functions
+       that  take  string arguments contained in vectors of bytes, interpreted
+       either as single-byte characters, or UTF-8 strings. You can also  build
+       two  other libraries, called libpcre2-16 and libpcre2-32, which process
+       strings that are contained in vectors of 16-bit and 32-bit code  units,
+       respectively. These can be interpreted either as single-unit characters
+       or UTF-16/UTF-32 strings. To build these additional libraries, add  one
+       or both of the following to the configure command:
+
+         --enable-pcre2-16
+         --enable-pcre2-32
+
+       If you do not want the 8-bit library, add
+
+         --disable-pcre2-8
+
+       as  well.  At least one of the three libraries must be built. Note that
+       the POSIX wrapper is for the 8-bit library only, and that pcre2grep  is
+       an  8-bit  program.  Neither  of these are built if you select only the
+       16-bit or 32-bit libraries.
+
+
+BUILDING SHARED AND STATIC LIBRARIES
+
+       The Autotools PCRE2 building process uses libtool to build both  shared
+       and  static  libraries by default. You can suppress an unwanted library
+       by adding one of
+
+         --disable-shared
+         --disable-static
+
+       to the configure command.
+
+
+UNICODE AND UTF SUPPORT
+
+       By default, PCRE2 is built with support for Unicode and  UTF  character
+       strings.  To build it without Unicode support, add
+
+         --disable-unicode
+
+       to  the configure command. This setting applies to all three libraries.
+       It is not possible to build  one  library  with  Unicode  support,  and
+       another without, in the same configuration.
+
+       Of  itself, Unicode support does not make PCRE2 treat strings as UTF-8,
+       UTF-16 or UTF-32. To do that, applications that use the library can set
+       the  PCRE2_UTF  option when they call pcre2_compile() to compile a pat-
+       tern.  Alternatively, patterns may be started with  (*UTF)  unless  the
+       application has locked this out by setting PCRE2_NEVER_UTF.
+
+       UTF support allows the libraries to process character code points up to
+       0x10ffff in the strings that they handle. It also provides support  for
+       accessing  the  Unicode  properties  of  such characters, using pattern
+       escapes such as \P, \p, and \X. Only the  general  category  properties
+       such  as Lu and Nd are supported. Details are given in the pcre2pattern
+       documentation.
+
+       Pattern escapes such as \d and \w do not by default make use of Unicode
+       properties.  The  application  can  request that they do by setting the
+       PCRE2_UCP option. Unless the application  has  set  PCRE2_NEVER_UCP,  a
+       pattern may also request this by starting with (*UCP).
+
+       The \C escape sequence, which matches a single code unit, even in a UTF
+       mode, can cause unpredictable behaviour because it may leave  the  cur-
+       rent  matching  point  in the middle of a multi-code-unit character. It
+       can be locked out by setting the PCRE2_NEVER_BACKSLASH_C option.
+
+
+JUST-IN-TIME COMPILER SUPPORT
+
+       Just-in-time compiler support is included in the build by specifying
+
+         --enable-jit
+
+       This support is available only for certain hardware  architectures.  If
+       this  option  is  set for an unsupported architecture, a building error
+       occurs.  See the pcre2jit documentation for a discussion of JIT  usage.
+       When  JIT  support is enabled, pcre2grep automatically makes use of it,
+       unless you add
+
+         --disable-pcre2grep-jit
+
+       to the "configure" command.
+
+
+NEWLINE RECOGNITION
+
+       By default, PCRE2 interprets the linefeed (LF) character as  indicating
+       the  end  of  a line. This is the normal newline character on Unix-like
+       systems. You can compile PCRE2 to use carriage return (CR) instead,  by
+       adding
+
+         --enable-newline-is-cr
+
+       to  the  configure  command.  There  is  also an --enable-newline-is-lf
+       option, which explicitly specifies linefeed as the newline character.
+
+       Alternatively, you can specify that line endings are to be indicated by
+       the two-character sequence CRLF (CR immediately followed by LF). If you
+       want this, add
+
+         --enable-newline-is-crlf
+
+       to the configure command. There is a fourth option, specified by
+
+         --enable-newline-is-anycrlf
+
+       which causes PCRE2 to recognize any of the three sequences CR,  LF,  or
+       CRLF as indicating a line ending. Finally, a fifth option, specified by
+
+         --enable-newline-is-any
+
+       causes  PCRE2  to  recognize  any Unicode newline sequence. The Unicode
+       newline sequences are the three just mentioned, plus the single charac-
+       ters VT (vertical tab, U+000B), FF (form feed, U+000C), NEL (next line,
+       U+0085), LS (line separator,  U+2028),  and  PS  (paragraph  separator,
+       U+2029).
+
+       Whatever default line ending convention is selected when PCRE2 is built
+       can be overridden by applications that use the library. At  build  time
+       it is conventional to use the standard for your operating system.
+
+
+WHAT \R MATCHES
+
+       By  default,  the  sequence \R in a pattern matches any Unicode newline
+       sequence, independently of what has been selected as  the  line  ending
+       sequence. If you specify
+
+         --enable-bsr-anycrlf
+
+       the  default  is changed so that \R matches only CR, LF, or CRLF. What-
+       ever is selected when PCRE2 is built can be overridden by  applications
+       that use the called.
+
+
+HANDLING VERY LARGE PATTERNS
+
+       Within  a  compiled  pattern,  offset values are used to point from one
+       part to another (for example, from an opening parenthesis to an  alter-
+       nation  metacharacter).  By default, in the 8-bit and 16-bit libraries,
+       two-byte values are used for these offsets, leading to a  maximum  size
+       for  a compiled pattern of around 64K code units. This is sufficient to
+       handle all but the most gigantic patterns. Nevertheless, some people do
+       want  to  process truly enormous patterns, so it is possible to compile
+       PCRE2 to use three-byte or four-byte offsets by adding a  setting  such
+       as
+
+         --with-link-size=3
+
+       to  the  configure command. The value given must be 2, 3, or 4. For the
+       16-bit library, a value of 3 is rounded up to 4.  In  these  libraries,
+       using  longer  offsets slows down the operation of PCRE2 because it has
+       to load additional data when handling them. For the 32-bit library  the
+       value  is  always 4 and cannot be overridden; the value of --with-link-
+       size is ignored.
+
+
+AVOIDING EXCESSIVE STACK USAGE
+
+       When matching with the pcre2_match() function, PCRE2  implements  back-
+       tracking  by  making  recursive  calls  to  an internal function called
+       match(). In environments where the size of the stack is  limited,  this
+       can  severely  limit  PCRE2's operation. (The Unix environment does not
+       usually suffer from this problem, but it may sometimes be necessary  to
+       increase  the  maximum  stack  size.  There  is  a  discussion  in  the
+       pcre2stack documentation.) An alternative approach  to  recursion  that
+       uses  memory from the heap to remember data, instead of using recursive
+       function calls, has been implemented to work round the problem of  lim-
+       ited  stack  size.  If  you want to build a version of PCRE2 that works
+       this way, add
+
+         --disable-stack-for-recursion
+
+       to the configure command. By default, the system functions malloc() and
+       free()  are called to manage the heap memory that is required, but cus-
+       tom memory management functions  can  be  called  instead.  PCRE2  runs
+       noticeably more slowly when built in this way. This option affects only
+       the pcre2_match() function; it is not relevant for pcre2_dfa_match().
+
+
+LIMITING PCRE2 RESOURCE USAGE
+
+       Internally, PCRE2 has a function called match(), which it calls repeat-
+       edly   (sometimes   recursively)  when  matching  a  pattern  with  the
+       pcre2_match() function. By controlling the maximum number of times this
+       function  may be called during a single matching operation, a limit can
+       be placed on the resources used by a single call to pcre2_match().  The
+       limit can be changed at run time, as described in the pcre2api documen-
+       tation. The default is 10 million, but this can be changed by adding  a
+       setting such as
+
+         --with-match-limit=500000
+
+       to   the   configure  command.  This  setting  has  no  effect  on  the
+       pcre2_dfa_match() matching function.
+
+       In some environments it is desirable to limit the  depth  of  recursive
+       calls of match() more strictly than the total number of calls, in order
+       to restrict the maximum amount of stack (or heap,  if  --disable-stack-
+       for-recursion is specified) that is used. A second limit controls this;
+       it defaults to the value that  is  set  for  --with-match-limit,  which
+       imposes  no  additional constraints. However, you can set a lower limit
+       by adding, for example,
+
+         --with-match-limit-recursion=10000
+
+       to the configure command. This value can  also  be  overridden  at  run
+       time.
+
+
+CREATING CHARACTER TABLES AT BUILD TIME
+
+       PCRE2 uses fixed tables for processing characters whose code points are
+       less than 256. By default, PCRE2 is built with a set of tables that are
+       distributed  in  the file src/pcre2_chartables.c.dist. These tables are
+       for ASCII codes only. If you add
+
+         --enable-rebuild-chartables
+
+       to the configure command, the distributed tables are  no  longer  used.
+       Instead,  a  program  called dftables is compiled and run. This outputs
+       the source for new set of tables, created in the default locale of your
+       C  run-time  system. (This method of replacing the tables does not work
+       if you are cross compiling, because dftables is run on the local  host.
+       If you need to create alternative tables when cross compiling, you will
+       have to do so "by hand".)
+
+
+USING EBCDIC CODE
+
+       PCRE2 assumes by default that it will run in an environment  where  the
+       character  code is ASCII or Unicode, which is a superset of ASCII. This
+       is the case for most computer operating systems. PCRE2 can, however, be
+       compiled to run in an 8-bit EBCDIC environment by adding
+
+         --enable-ebcdic --disable-unicode
+
+       to the configure command. This setting implies --enable-rebuild-charta-
+       bles. You should only use it if you know that  you  are  in  an  EBCDIC
+       environment (for example, an IBM mainframe operating system).
+
+       It  is  not possible to support both EBCDIC and UTF-8 codes in the same
+       version of the library. Consequently,  --enable-unicode  and  --enable-
+       ebcdic are mutually exclusive.
+
+       The EBCDIC character that corresponds to an ASCII LF is assumed to have
+       the value 0x15 by default. However, in some EBCDIC  environments,  0x25
+       is used. In such an environment you should use
+
+         --enable-ebcdic-nl25
+
+       as well as, or instead of, --enable-ebcdic. The EBCDIC character for CR
+       has the same value as in ASCII, namely, 0x0d.  Whichever  of  0x15  and
+       0x25 is not chosen as LF is made to correspond to the Unicode NEL char-
+       acter (which, in Unicode, is 0x85).
+
+       The options that select newline behaviour, such as --enable-newline-is-
+       cr, and equivalent run-time options, refer to these character values in
+       an EBCDIC environment.
+
+
+PCRE2GREP OPTIONS FOR COMPRESSED FILE SUPPORT
+
+       By default, pcre2grep reads all files as plain text. You can  build  it
+       so  that  it recognizes files whose names end in .gz or .bz2, and reads
+       them with libz or libbz2, respectively, by adding one or both of
+
+         --enable-pcre2grep-libz
+         --enable-pcre2grep-libbz2
+
+       to the configure command. These options naturally require that the rel-
+       evant  libraries  are installed on your system. Configuration will fail
+       if they are not.
+
+
+PCRE2GREP BUFFER SIZE
+
+       pcre2grep uses an internal buffer to hold a "window" on the file it  is
+       scanning, in order to be able to output "before" and "after" lines when
+       it finds a match. The size of the buffer is controlled by  a  parameter
+       whose default value is 20K. The buffer itself is three times this size,
+       but because of the way it is used for holding "before" lines, the long-
+       est  line  that  is guaranteed to be processable is the parameter size.
+       You can change the default parameter value by adding, for example,
+
+         --with-pcre2grep-bufsize=50K
+
+       to the configure command. The caller of  pcre2grep  can  override  this
+       value by using --buffer-size on the command line..
+
+
+PCRE2TEST OPTION FOR LIBREADLINE SUPPORT
+
+       If you add one of
+
+         --enable-pcre2test-libreadline
+         --enable-pcre2test-libedit
+
+       to  the  configure  command,  pcre2test  is linked with the libreadline
+       orlibedit library, respectively, and when its input is from a terminal,
+       it  reads  it using the readline() function. This provides line-editing
+       and history facilities. Note that libreadline is  GPL-licensed,  so  if
+       you  distribute  a binary of pcre2test linked in this way, there may be
+       licensing issues. These can be avoided by linking instead with libedit,
+       which has a BSD licence.
+
+       Setting  --enable-pcre2test-libreadline causes the -lreadline option to
+       be added to the pcre2test build. In many operating environments with  a
+       sytem-installed  readline  library this is sufficient. However, in some
+       environments (e.g. if an unmodified distribution version of readline is
+       in  use),  some  extra configuration may be necessary. The INSTALL file
+       for libreadline says this:
+
+         "Readline uses the termcap functions, but does not link with
+         the termcap or curses library itself, allowing applications
+         which link with readline the to choose an appropriate library."
+
+       If your environment has not been set up so that an appropriate  library
+       is automatically included, you may need to add something like
+
+         LIBS="-ncurses"
+
+       immediately before the configure command.
+
+
+INCLUDING DEBUGGING CODE
+
+       If you add
+
+         --enable-debug
+
+       to  the configure command, additional debugging code is included in the
+       build. This feature is intended for use by the PCRE2 maintainers.
+
+
+DEBUGGING WITH VALGRIND SUPPORT
+
+       If you add
+
+         --enable-valgrind
+
+       to the configure command, PCRE2 will use valgrind annotations  to  mark
+       certain  memory  regions  as  unaddressable.  This  allows it to detect
+       invalid memory accesses, and  is  mostly  useful  for  debugging  PCRE2
+       itself.
+
+
+CODE COVERAGE REPORTING
+
+       If  your  C  compiler is gcc, you can build a version of PCRE2 that can
+       generate a code coverage report for its test suite. To enable this, you
+       must install lcov version 1.6 or above. Then specify
+
+         --enable-coverage
+
+       to the configure command and build PCRE2 in the usual way.
+
+       Note that using ccache (a caching C compiler) is incompatible with code
+       coverage reporting. If you have configured ccache to run  automatically
+       on your system, you must set the environment variable
+
+         CCACHE_DISABLE=1
+
+       before running make to build PCRE2, so that ccache is not used.
+
+       When  --enable-coverage  is  used,  the  following addition targets are
+       added to the Makefile:
+
+         make coverage
+
+       This creates a fresh coverage report for the PCRE2 test  suite.  It  is
+       equivalent  to running "make coverage-reset", "make coverage-baseline",
+       "make check", and then "make coverage-report".
+
+         make coverage-reset
+
+       This zeroes the coverage counters, but does nothing else.
+
+         make coverage-baseline
+
+       This captures baseline coverage information.
+
+         make coverage-report
+
+       This creates the coverage report.
+
+         make coverage-clean-report
+
+       This removes the generated coverage report without cleaning the  cover-
+       age data itself.
+
+         make coverage-clean-data
+
+       This  removes  the captured coverage data without removing the coverage
+       files created at compile time (*.gcno).
+
+         make coverage-clean
+
+       This cleans all coverage data including the generated coverage  report.
+       For  more  information about code coverage, see the gcov and lcov docu-
+       mentation.
+
+
+SEE ALSO
+
+       pcre2api(3), pcre2-config(3).
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge, England.
+
+
+REVISION
+
+       Last updated: 24 April 2015
+       Copyright (c) 1997-2015 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCRE2CALLOUT(3)            Library Functions Manual            PCRE2CALLOUT(3)
+
+
+
+NAME
+       PCRE2 - Perl-compatible regular expressions (revised API)
+
+SYNOPSIS
+
+       #include 
+
+       int (*pcre2_callout)(pcre2_callout_block *, void *);
+
+       int pcre2_callout_enumerate(const pcre2_code *code,
+         int (*callback)(pcre2_callout_enumerate_block *, void *),
+         void *user_data);
+
+
+DESCRIPTION
+
+       PCRE2  provides  a feature called "callout", which is a means of tempo-
+       rarily passing control to the caller of PCRE2 in the middle of  pattern
+       matching.  The caller of PCRE2 provides an external function by putting
+       its entry point in a match  context  (see  pcre2_set_callout()  in  the
+       pcre2api documentation).
+
+       Within  a  regular expression, (?C) indicates a point at which the
+       external function is to be called.  Different  callout  points  can  be
+       identified  by  putting  a number less than 256 after the letter C. The
+       default value is zero.  Alternatively, the argument may be a  delimited
+       string.  The  starting delimiter must be one of ` ' " ^ % # $ { and the
+       ending delimiter is the same as the start, except for {, where the end-
+       ing  delimiter  is  }.  If  the  ending  delimiter is needed within the
+       string, it must be doubled. For example, this pattern has  two  callout
+       points:
+
+         (?C1)abc(?C"some ""arbitrary"" text")def
+
+       If the PCRE2_AUTO_CALLOUT option bit is set when a pattern is compiled,
+       PCRE2 automatically inserts callouts, all with number 255, before  each
+       item  in  the  pattern. For example, if PCRE2_AUTO_CALLOUT is used with
+       the pattern
+
+         A(\d{2}|--)
+
+       it is processed as if it were
+
+       (?C255)A(?C255)((?C255)\d{2}(?C255)|(?C255)-(?C255)-(?C255))(?C255)
+
+       Notice that there is a callout before and after  each  parenthesis  and
+       alternation bar. If the pattern contains a conditional group whose con-
+       dition is an assertion, an automatic callout  is  inserted  immediately
+       before  the  condition. Such a callout may also be inserted explicitly,
+       for example:
+
+         (?(?C9)(?=a)ab|de)  (?(?C%text%)(?!=d)ab|de)
+
+       This applies only to assertion conditions (because they are  themselves
+       independent groups).
+
+       Callouts  can  be useful for tracking the progress of pattern matching.
+       The pcre2test program has a pattern qualifier (/auto_callout) that sets
+       automatic  callouts.   When  any  callouts are present, the output from
+       pcre2test indicates how the pattern is being matched.  This  is  useful
+       information  when  you are trying to optimize the performance of a par-
+       ticular pattern.
+
+
+MISSING CALLOUTS
+
+       You should be aware that, because of optimizations  in  the  way  PCRE2
+       compiles and matches patterns, callouts sometimes do not happen exactly
+       as you might expect.
+
+   Auto-possessification
+
+       At compile time, PCRE2 "auto-possessifies" repeated items when it knows
+       that  what follows cannot be part of the repeat. For example, a+[bc] is
+       compiled as if it were a++[bc]. The pcre2test output when this  pattern
+       is compiled with PCRE2_ANCHORED and PCRE2_AUTO_CALLOUT and then applied
+       to the string "aaaa" is:
+
+         --->aaaa
+          +0 ^        a+
+          +2 ^   ^    [bc]
+         No match
+
+       This indicates that when matching [bc] fails, there is no  backtracking
+       into  a+  and  therefore the callouts that would be taken for the back-
+       tracks do not occur.  You can disable the  auto-possessify  feature  by
+       passing  PCRE2_NO_AUTO_POSSESS to pcre2_compile(), or starting the pat-
+       tern with (*NO_AUTO_POSSESS). In this case, the output changes to this:
+
+         --->aaaa
+          +0 ^        a+
+          +2 ^   ^    [bc]
+          +2 ^  ^     [bc]
+          +2 ^ ^      [bc]
+          +2 ^^       [bc]
+         No match
+
+       This time, when matching [bc] fails, the matcher backtracks into a+ and
+       tries again, repeatedly, until a+ itself fails.
+
+   Automatic .* anchoring
+
+       By default, an optimization is applied when .* is the first significant
+       item in a pattern. If PCRE2_DOTALL is set, so that the  dot  can  match
+       any  character,  the pattern is automatically anchored. If PCRE2_DOTALL
+       is not set, a match can start only after an internal newline or at  the
+       beginning  of  the  subject,  and  pcre2_compile() remembers this. This
+       optimization is disabled, however, if .* is in an atomic  group  or  if
+       there  is  a back reference to the capturing group in which it appears.
+       It is also disabled if the pattern contains (*PRUNE) or  (*SKIP).  How-
+       ever, the presence of callouts does not affect it.
+
+       For  example,  if  the pattern .*\d is compiled with PCRE2_AUTO_CALLOUT
+       and applied to the string "aa", the pcre2test output is:
+
+         --->aa
+          +0 ^      .*
+          +2 ^ ^    \d
+          +2 ^^     \d
+          +2 ^      \d
+         No match
+
+       This shows that all match attempts start at the beginning of  the  sub-
+       ject.  In  other  words,  the pattern is anchored. You can disable this
+       optimization by passing PCRE2_NO_DOTSTAR_ANCHOR to pcre2_compile(),  or
+       starting  the pattern with (*NO_DOTSTAR_ANCHOR). In this case, the out-
+       put changes to:
+
+         --->aa
+          +0 ^      .*
+          +2 ^ ^    \d
+          +2 ^^     \d
+          +2 ^      \d
+          +0  ^     .*
+          +2  ^^    \d
+          +2  ^     \d
+         No match
+
+       This shows more match attempts, starting at the second subject  charac-
+       ter.   Another  optimization, described in the next section, means that
+       there is no subsequent attempt to match with an empty subject.
+
+       If a pattern has more than one top-level  branch,  automatic  anchoring
+       occurs if all branches are anchorable.
+
+   Other optimizations
+
+       Other  optimizations  that  provide fast "no match" results also affect
+       callouts.  For example, if the pattern is
+
+         ab(?C4)cd
+
+       PCRE2 knows that any matching string must contain the  letter  "d".  If
+       the  subject  string  is  "abyz",  the  lack of "d" means that matching
+       doesn't ever start, and the callout is  never  reached.  However,  with
+       "abyd", though the result is still no match, the callout is obeyed.
+
+       PCRE2  also  knows  the  minimum  length of a matching string, and will
+       immediately give a "no match" return without actually running  a  match
+       if  the  subject is not long enough, or, for unanchored patterns, if it
+       has been scanned far enough.
+
+       You can disable these optimizations by passing the PCRE2_NO_START_OPTI-
+       MIZE  option  to  pcre2_compile(),  or  by  starting  the  pattern with
+       (*NO_START_OPT). This slows down the matching process, but does  ensure
+       that callouts such as the example above are obeyed.
+
+
+THE CALLOUT INTERFACE
+
+       During  matching,  when  PCRE2  reaches a callout point, if an external
+       function is set in the match context, it is  called.  This  applies  to
+       both  normal  and DFA matching. The first argument to the callout func-
+       tion is a pointer to a pcre2_callout block. The second argument is  the
+       void  *  callout  data that was supplied when the callout was set up by
+       calling pcre2_set_callout() (see the pcre2api documentation). The call-
+       out block structure contains the following fields:
+
+         uint32_t      version;
+         uint32_t      callout_number;
+         uint32_t      capture_top;
+         uint32_t      capture_last;
+         PCRE2_SIZE   *offset_vector;
+         PCRE2_SPTR    mark;
+         PCRE2_SPTR    subject;
+         PCRE2_SIZE    subject_length;
+         PCRE2_SIZE    start_match;
+         PCRE2_SIZE    current_position;
+         PCRE2_SIZE    pattern_position;
+         PCRE2_SIZE    next_item_length;
+         PCRE2_SIZE    callout_string_offset;
+         PCRE2_SIZE    callout_string_length;
+         PCRE2_SPTR    callout_string;
+
+       The  version field contains the version number of the block format. The
+       current version is 1; the three callout string fields  were  added  for
+       this  version. If you are writing an application that might use an ear-
+       lier release of PCRE2, you  should  check  the  version  number  before
+       accessing  any  of  these  fields.  The version number will increase in
+       future if more fields are added, but the intention is never  to  remove
+       any of the existing fields.
+
+   Fields for numerical callouts
+
+       For  a  numerical  callout,  callout_string is NULL, and callout_number
+       contains the number of the callout, in the range  0-255.  This  is  the
+       number  that  follows  (?C for manual callouts; it is 255 for automati-
+       cally generated callouts.
+
+   Fields for string callouts
+
+       For callouts with string arguments, callout_number is always zero,  and
+       callout_string  points  to the string that is contained within the com-
+       piled pattern. Its length is given by callout_string_length. Duplicated
+       ending delimiters that were present in the original pattern string have
+       been turned into single characters, but there is no other processing of
+       the  callout string argument. An additional code unit containing binary
+       zero is present after the string, but is not included  in  the  length.
+       The  delimiter  that was used to start the string is also stored within
+       the pattern, immediately before the string itself. You can access  this
+       delimiter as callout_string[-1] if you need it.
+
+       The callout_string_offset field is the code unit offset to the start of
+       the callout argument string within the original pattern string. This is
+       provided  for the benefit of applications such as script languages that
+       might need to report errors in the callout string within the pattern.
+
+   Fields for all callouts
+
+       The remaining fields in the callout block are the same for  both  kinds
+       of callout.
+
+       The offset_vector field is a pointer to the vector of capturing offsets
+       (the "ovector") that was passed to the matching function in  the  match
+       data  block.  When pcre2_match() is used, the contents can be inspected
+       in order to extract substrings that have been matched so  far,  in  the
+       same  way as for extracting substrings after a match has completed. For
+       the DFA matching function, this field is not useful.
+
+       The subject and subject_length fields contain copies of the values that
+       were passed to the matching function.
+
+       The  start_match  field normally contains the offset within the subject
+       at which the current match attempt  started.  However,  if  the  escape
+       sequence  \K has been encountered, this value is changed to reflect the
+       modified starting point. If the pattern is not  anchored,  the  callout
+       function may be called several times from the same point in the pattern
+       for different starting points in the subject.
+
+       The current_position field contains the offset within  the  subject  of
+       the current match pointer.
+
+       When the pcre2_match() is used, the capture_top field contains one more
+       than the number of the highest numbered captured substring so  far.  If
+       no substrings have been captured, the value of capture_top is one. This
+       is always the case when the DFA functions are used, because they do not
+       support captured substrings.
+
+       The  capture_last  field  contains the number of the most recently cap-
+       tured substring. However, when a recursion exits, the value reverts  to
+       what  it  was  outside  the recursion, as do the values of all captured
+       substrings. If no substrings have been  captured,  the  value  of  cap-
+       ture_last is 0. This is always the case for the DFA matching functions.
+
+       The pattern_position field contains the offset in the pattern string to
+       the next item to be matched.
+
+       The next_item_length field contains the length of the next item  to  be
+       matched in the pattern string. When the callout immediately precedes an
+       alternation bar, a closing parenthesis, or the end of the pattern,  the
+       length  is  zero. When the callout precedes an opening parenthesis, the
+       length is that of the entire subpattern.
+
+       The pattern_position and next_item_length fields are intended  to  help
+       in  distinguishing between different automatic callouts, which all have
+       the same callout number. However, they are set for  all  callouts,  and
+       are used by pcre2test to show the next item to be matched when display-
+       ing callout information.
+
+       In callouts from pcre2_match() the mark field contains a pointer to the
+       zero-terminated  name of the most recently passed (*MARK), (*PRUNE), or
+       (*THEN) item in the match, or NULL if no such items have  been  passed.
+       Instances  of  (*PRUNE)  or  (*THEN) without a name do not obliterate a
+       previous (*MARK). In callouts from the DFA matching function this field
+       always contains NULL.
+
+
+RETURN VALUES FROM CALLOUTS
+
+       The external callout function returns an integer to PCRE2. If the value
+       is zero, matching proceeds as normal. If  the  value  is  greater  than
+       zero,  matching  fails  at  the current point, but the testing of other
+       matching possibilities goes ahead, just as if a lookahead assertion had
+       failed. If the value is less than zero, the match is abandoned, and the
+       matching function returns the negative value.
+
+       Negative  values  should  normally  be   chosen   from   the   set   of
+       PCRE2_ERROR_xxx  values.  In  particular,  PCRE2_ERROR_NOMATCH forces a
+       standard "no match" failure. The error  number  PCRE2_ERROR_CALLOUT  is
+       reserved  for  use by callout functions; it will never be used by PCRE2
+       itself.
+
+
+CALLOUT ENUMERATION
+
+       int pcre2_callout_enumerate(const pcre2_code *code,
+         int (*callback)(pcre2_callout_enumerate_block *, void *),
+         void *user_data);
+
+       A script language that supports the use of string arguments in callouts
+       might  like  to  scan  all the callouts in a pattern before running the
+       match. This can be done by calling pcre2_callout_enumerate(). The first
+       argument  is  a  pointer  to a compiled pattern, the second points to a
+       callback function, and the third is arbitrary user data.  The  callback
+       function  is  called  for  every callout in the pattern in the order in
+       which they appear. Its first argument is a pointer to a callout enumer-
+       ation  block,  and  its second argument is the user_data value that was
+       passed to pcre2_callout_enumerate(). The data block contains  the  fol-
+       lowing fields:
+
+         version                Block version number
+         pattern_position       Offset to next item in pattern
+         next_item_length       Length of next item in pattern
+         callout_number         Number for numbered callouts
+         callout_string_offset  Offset to string within pattern
+         callout_string_length  Length of callout string
+         callout_string         Points to callout string or is NULL
+
+       The  version  number is currently 0. It will increase if new fields are
+       ever added to the block. The remaining fields are  the  same  as  their
+       namesakes  in  the pcre2_callout block that is used for callouts during
+       matching, as described above.
+
+       Note that the value of pattern_position is  unique  for  each  callout.
+       However,  if  a callout occurs inside a group that is quantified with a
+       non-zero minimum or a fixed maximum, the group is replicated inside the
+       compiled  pattern.  For example, a pattern such as /(a){2}/ is compiled
+       as if it were /(a)(a)/. This means that the callout will be  enumerated
+       more  than  once,  but with the same value for pattern_position in each
+       case.
+
+       The callback function should normally return zero. If it returns a non-
+       zero value, scanning the pattern stops, and that value is returned from
+       pcre2_callout_enumerate().
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge, England.
+
+
+REVISION
+
+       Last updated: 23 March 2015
+       Copyright (c) 1997-2015 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCRE2COMPAT(3)             Library Functions Manual             PCRE2COMPAT(3)
+
+
+
+NAME
+       PCRE2 - Perl-compatible regular expressions (revised API)
+
+DIFFERENCES BETWEEN PCRE2 AND PERL
+
+       This document describes the differences in the ways that PCRE2 and Perl
+       handle regular expressions. The differences  described  here  are  with
+       respect to Perl versions 5.10 and above.
+
+       1.  PCRE2  has only a subset of Perl's Unicode support. Details of what
+       it does have are given in the pcre2unicode page.
+
+       2. PCRE2 allows repeat quantifiers only  on  parenthesized  assertions,
+       but  they  do not mean what you might think. For example, (?!a){3} does
+       not assert that the next three characters are not "a". It just  asserts
+       that  the  next  character  is not "a" three times (in principle: PCRE2
+       optimizes this to run the assertion  just  once).  Perl  allows  repeat
+       quantifiers  on  other  assertions such as \b, but these do not seem to
+       have any use.
+
+       3. Capturing subpatterns that occur inside  negative  lookahead  asser-
+       tions  are  counted,  but their entries in the offsets vector are never
+       set. Perl sometimes (but not always) sets its numerical variables  from
+       inside negative assertions.
+
+       4.  The  following Perl escape sequences are not supported: \l, \u, \L,
+       \U, and \N when followed by a character name or Unicode value.  (\N  on
+       its own, matching a non-newline character, is supported.) In fact these
+       are implemented by Perl's general string-handling and are not  part  of
+       its  pattern matching engine. If any of these are encountered by PCRE2,
+       an error is generated by default. However, if the PCRE2_ALT_BSUX option
+       is set, \U and \u are interpreted as ECMAScript interprets them.
+
+       5. The Perl escape sequences \p, \P, and \X are supported only if PCRE2
+       is built with Unicode support. The properties that can be  tested  with
+       \p and \P are limited to the general category properties such as Lu and
+       Nd, script names such as Greek or Han, and the derived  properties  Any
+       and L&. PCRE2 does support the Cs (surrogate) property, which Perl does
+       not; the Perl documentation says "Because Perl hides the need  for  the
+       user  to  understand the internal representation of Unicode characters,
+       there is no need to implement the  somewhat  messy  concept  of  surro-
+       gates."
+
+       6.  PCRE2 does support the \Q...\E escape for quoting substrings. Char-
+       acters in between are treated as literals. This is  slightly  different
+       from  Perl  in  that  $  and  @ are also handled as literals inside the
+       quotes. In Perl, they cause variable interpolation (but of course PCRE2
+       does not have variables).  Note the following examples:
+
+           Pattern            PCRE2 matches      Perl matches
+
+           \Qabc$xyz\E        abc$xyz           abc followed by the
+                                                  contents of $xyz
+           \Qabc\$xyz\E       abc\$xyz          abc\$xyz
+           \Qabc\E\$\Qxyz\E   abc$xyz           abc$xyz
+
+       The  \Q...\E  sequence  is recognized both inside and outside character
+       classes.
+
+       7.  Fairly  obviously,  PCRE2  does  not  support  the  (?{code})   and
+       (??{code})  constructions. However, there is support for recursive pat-
+       terns. This is not available in Perl 5.8, but it is in Perl 5.10. Also,
+       the  PCRE2  "callout"  feature allows an external function to be called
+       during  pattern  matching.  See  the  pcre2callout  documentation   for
+       details.
+
+       8.  Subroutine  calls  (whether recursive or not) are treated as atomic
+       groups.  Atomic recursion is like Python,  but  unlike  Perl.  Captured
+       values  that  are  set outside a subroutine call can be referenced from
+       inside in PCRE2, but not in Perl. There is a discussion  that  explains
+       these  differences  in  more detail in the section on recursion differ-
+       ences from Perl in the pcre2pattern page.
+
+       9. If any of the backtracking control verbs are used  in  a  subpattern
+       that  is  called  as  a  subroutine (whether or not recursively), their
+       effect is confined to that subpattern; it does not extend to  the  sur-
+       rounding  pattern.  This is not always the case in Perl. In particular,
+       if (*THEN) is present in a group that is called as  a  subroutine,  its
+       action is limited to that group, even if the group does not contain any
+       | characters. Note that such subpatterns are processed as  anchored  at
+       the point where they are tested.
+
+       10.  If a pattern contains more than one backtracking control verb, the
+       first one that is backtracked onto acts. For example,  in  the  pattern
+       A(*COMMIT)B(*PRUNE)C  a  failure in B triggers (*COMMIT), but a failure
+       in C triggers (*PRUNE). Perl's behaviour is more complex; in many cases
+       it is the same as PCRE2, but there are examples where it differs.
+
+       11.  Most  backtracking  verbs in assertions have their normal actions.
+       They are not confined to the assertion.
+
+       12. There are some differences that are concerned with the settings  of
+       captured  strings  when  part  of  a  pattern is repeated. For example,
+       matching "aba" against the  pattern  /^(a(b)?)+$/  in  Perl  leaves  $2
+       unset, but in PCRE2 it is set to "b".
+
+       13. PCRE2's handling of duplicate subpattern numbers and duplicate sub-
+       pattern names is not as general as Perl's. This is a consequence of the
+       fact  the  PCRE2  works internally just with numbers, using an external
+       table to translate between numbers and names. In particular, a  pattern
+       such  as  (?|(?A)|(?
+
+       is matched against the string
+
+           
+
+       there are three possible answers. The standard algorithm finds only one
+       of them, whereas the alternative algorithm finds all three.
+
+
+REGULAR EXPRESSIONS AS TREES
+
+       The set of strings that are matched by a regular expression can be rep-
+       resented  as  a  tree structure. An unlimited repetition in the pattern
+       makes the tree of infinite size, but it is still a tree.  Matching  the
+       pattern  to a given subject string (from a given starting point) can be
+       thought of as a search of the tree.  There are two  ways  to  search  a
+       tree:  depth-first  and  breadth-first, and these correspond to the two
+       matching algorithms provided by PCRE2.
+
+
+THE STANDARD MATCHING ALGORITHM
+
+       In the terminology of Jeffrey Friedl's book "Mastering Regular  Expres-
+       sions",  the  standard  algorithm  is an "NFA algorithm". It conducts a
+       depth-first search of the pattern tree. That is, it  proceeds  along  a
+       single path through the tree, checking that the subject matches what is
+       required. When there is a mismatch, the algorithm  tries  any  alterna-
+       tives  at  the  current point, and if they all fail, it backs up to the
+       previous branch point in the  tree,  and  tries  the  next  alternative
+       branch  at  that  level.  This often involves backing up (moving to the
+       left) in the subject string as well.  The  order  in  which  repetition
+       branches  are  tried  is controlled by the greedy or ungreedy nature of
+       the quantifier.
+
+       If a leaf node is reached, a matching string has  been  found,  and  at
+       that  point the algorithm stops. Thus, if there is more than one possi-
+       ble match, this algorithm returns the first one that it finds.  Whether
+       this  is the shortest, the longest, or some intermediate length depends
+       on the way the greedy and ungreedy repetition quantifiers are specified
+       in the pattern.
+
+       Because  it  ends  up  with a single path through the tree, it is rela-
+       tively straightforward for this algorithm to keep  track  of  the  sub-
+       strings  that  are  matched  by portions of the pattern in parentheses.
+       This provides support for capturing parentheses and back references.
+
+
+THE ALTERNATIVE MATCHING ALGORITHM
+
+       This algorithm conducts a breadth-first search of  the  tree.  Starting
+       from  the  first  matching  point  in the subject, it scans the subject
+       string from left to right, once, character by character, and as it does
+       this,  it remembers all the paths through the tree that represent valid
+       matches. In Friedl's terminology, this is a kind  of  "DFA  algorithm",
+       though  it is not implemented as a traditional finite state machine (it
+       keeps multiple states active simultaneously).
+
+       Although the general principle of this matching algorithm  is  that  it
+       scans  the subject string only once, without backtracking, there is one
+       exception: when a lookaround assertion is encountered,  the  characters
+       following  or  preceding  the  current  point  have to be independently
+       inspected.
+
+       The scan continues until either the end of the subject is  reached,  or
+       there  are  no more unterminated paths. At this point, terminated paths
+       represent the different matching possibilities (if there are none,  the
+       match  has  failed).   Thus,  if there is more than one possible match,
+       this algorithm finds all of them, and in particular, it finds the long-
+       est.  The  matches are returned in decreasing order of length. There is
+       an option to stop the algorithm after the first match (which is  neces-
+       sarily the shortest) is found.
+
+       Note that all the matches that are found start at the same point in the
+       subject. If the pattern
+
+         cat(er(pillar)?)?
+
+       is matched against the string "the caterpillar catchment",  the  result
+       is  the  three  strings "caterpillar", "cater", and "cat" that start at
+       the fifth character of the subject. The algorithm  does  not  automati-
+       cally move on to find matches that start at later positions.
+
+       PCRE2's "auto-possessification" optimization usually applies to charac-
+       ter repeats at the end of a pattern (as well as internally). For  exam-
+       ple, the pattern "a\d+" is compiled as if it were "a\d++" because there
+       is no point even considering the possibility of backtracking  into  the
+       repeated  digits.  For  DFA matching, this means that only one possible
+       match is found. If you really do want multiple matches in  such  cases,
+       either  use  an ungreedy repeat ("a\d+?") or set the PCRE2_NO_AUTO_POS-
+       SESS option when compiling.
+
+       There are a number of features of PCRE2 regular  expressions  that  are
+       not  supported  by the alternative matching algorithm. They are as fol-
+       lows:
+
+       1. Because the algorithm finds all  possible  matches,  the  greedy  or
+       ungreedy  nature  of  repetition quantifiers is not relevant (though it
+       may affect auto-possessification, as just described). During  matching,
+       greedy  and  ungreedy  quantifiers are treated in exactly the same way.
+       However, possessive quantifiers can make a difference when what follows
+       could  also  match  what  is  quantified, for example in a pattern like
+       this:
+
+         ^a++\w!
+
+       This pattern matches "aaab!" but not "aaa!", which would be matched  by
+       a  non-possessive quantifier. Similarly, if an atomic group is present,
+       it is matched as if it were a standalone pattern at the current  point,
+       and  the  longest match is then "locked in" for the rest of the overall
+       pattern.
+
+       2. When dealing with multiple paths through the tree simultaneously, it
+       is  not  straightforward  to  keep track of captured substrings for the
+       different matching possibilities, and PCRE2's  implementation  of  this
+       algorithm does not attempt to do this. This means that no captured sub-
+       strings are available.
+
+       3. Because no substrings are captured, back references within the  pat-
+       tern are not supported, and cause errors if encountered.
+
+       4.  For  the same reason, conditional expressions that use a backrefer-
+       ence as the condition or test for a specific group  recursion  are  not
+       supported.
+
+       5.  Because  many  paths  through the tree may be active, the \K escape
+       sequence, which resets the start of the match when encountered (but may
+       be  on  some  paths  and not on others), is not supported. It causes an
+       error if encountered.
+
+       6. Callouts are supported, but the value of the  capture_top  field  is
+       always 1, and the value of the capture_last field is always 0.
+
+       7.  The  \C  escape  sequence, which (in the standard algorithm) always
+       matches a single code unit, even in a UTF mode,  is  not  supported  in
+       these  modes,  because the alternative algorithm moves through the sub-
+       ject string one character (not code unit) at a  time,  for  all  active
+       paths through the tree.
+
+       8.  Except for (*FAIL), the backtracking control verbs such as (*PRUNE)
+       are not supported. (*FAIL) is supported, and  behaves  like  a  failing
+       negative assertion.
+
+
+ADVANTAGES OF THE ALTERNATIVE ALGORITHM
+
+       Using  the alternative matching algorithm provides the following advan-
+       tages:
+
+       1. All possible matches (at a single point in the subject) are automat-
+       ically  found,  and  in particular, the longest match is found. To find
+       more than one match using the standard algorithm, you have to do kludgy
+       things with callouts.
+
+       2.  Because  the  alternative  algorithm  scans the subject string just
+       once, and never needs to backtrack (except for lookbehinds), it is pos-
+       sible  to  pass  very  long subject strings to the matching function in
+       several pieces, checking for partial matching each time. Although it is
+       also  possible  to  do  multi-segment matching using the standard algo-
+       rithm, by retaining partially matched substrings, it  is  more  compli-
+       cated. The pcre2partial documentation gives details of partial matching
+       and discusses multi-segment matching.
+
+
+DISADVANTAGES OF THE ALTERNATIVE ALGORITHM
+
+       The alternative algorithm suffers from a number of disadvantages:
+
+       1. It is substantially slower than  the  standard  algorithm.  This  is
+       partly  because  it has to search for all possible matches, but is also
+       because it is less susceptible to optimization.
+
+       2. Capturing parentheses and back references are not supported.
+
+       3. Although atomic groups are supported, their use does not provide the
+       performance advantage that it does for the standard algorithm.
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge, England.
+
+
+REVISION
+
+       Last updated: 29 September 2014
+       Copyright (c) 1997-2014 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCRE2PARTIAL(3)            Library Functions Manual            PCRE2PARTIAL(3)
+
+
+
+NAME
+       PCRE2 - Perl-compatible regular expressions
+
+PARTIAL MATCHING IN PCRE2
+
+       In  normal  use  of  PCRE2,  if  the subject string that is passed to a
+       matching function matches as far as it goes, but is too short to  match
+       the  entire pattern, PCRE2_ERROR_NOMATCH is returned. There are circum-
+       stances where it might be helpful to distinguish this case  from  other
+       cases in which there is no match.
+
+       Consider, for example, an application where a human is required to type
+       in data for a field with specific formatting requirements.  An  example
+       might be a date in the form ddmmmyy, defined by this pattern:
+
+         ^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$
+
+       If the application sees the user's keystrokes one by one, and can check
+       that what has been typed so far is potentially valid,  it  is  able  to
+       raise  an  error  as  soon  as  a  mistake  is made, by beeping and not
+       reflecting the character that has been typed, for example. This immedi-
+       ate  feedback is likely to be a better user interface than a check that
+       is delayed until the entire string has been entered.  Partial  matching
+       can  also be useful when the subject string is very long and is not all
+       available at once.
+
+       PCRE2 supports partial matching by means of the PCRE2_PARTIAL_SOFT  and
+       PCRE2_PARTIAL_HARD  options,  which  can be set when calling a matching
+       function.  The difference between the two options is whether or  not  a
+       partial match is preferred to an alternative complete match, though the
+       details differ between the two types  of  matching  function.  If  both
+       options are set, PCRE2_PARTIAL_HARD takes precedence.
+
+       If  you  want to use partial matching with just-in-time optimized code,
+       you must call pcre2_jit_compile() with one or both of these options:
+
+         PCRE2_JIT_PARTIAL_SOFT
+         PCRE2_JIT_PARTIAL_HARD
+
+       PCRE2_JIT_COMPLETE should also be set if you are going to run  non-par-
+       tial  matches  on the same pattern. If the appropriate JIT mode has not
+       been compiled, interpretive matching code is used.
+
+       Setting a partial matching option  disables  two  of  PCRE2's  standard
+       optimizations. PCRE2 remembers the last literal code unit in a pattern,
+       and abandons matching immediately if it is not present in  the  subject
+       string.  This  optimization  cannot  be  used for a subject string that
+       might match only partially. PCRE2 also knows the minimum  length  of  a
+       matching  string,  and  does not bother to run the matching function on
+       shorter strings. This optimization is also disabled for partial  match-
+       ing.
+
+
+PARTIAL MATCHING USING pcre2_match()
+
+       A  partial  match occurs during a call to pcre2_match() when the end of
+       the subject string is reached successfully, but  matching  cannot  con-
+       tinue because more characters are needed. However, at least one charac-
+       ter in the subject must have been inspected. This  character  need  not
+       form part of the final matched string; lookbehind assertions and the \K
+       escape sequence provide ways of inspecting characters before the  start
+       of  a matched string. The requirement for inspecting at least one char-
+       acter exists because an empty string can  always  be  matched;  without
+       such  a  restriction  there would always be a partial match of an empty
+       string at the end of the subject.
+
+       When a partial match is returned, the first two elements in the ovector
+       point to the portion of the subject that was matched, but the values in
+       the rest of the ovector are undefined. The appearance of \K in the pat-
+       tern has no effect for a partial match. Consider this pattern:
+
+         /abc\K123/
+
+       If it is matched against "456abc123xyz" the result is a complete match,
+       and the ovector defines the matched string as "123", because \K  resets
+       the  "start  of  match" point. However, if a partial match is requested
+       and the subject string is "456abc12", a partial match is found for  the
+       string  "abc12",  because  all these characters are needed for a subse-
+       quent re-match with additional characters.
+
+       What happens when a partial match is identified depends on which of the
+       two partial matching options are set.
+
+   PCRE2_PARTIAL_SOFT WITH pcre2_match()
+
+       If  PCRE2_PARTIAL_SOFT  is  set when pcre2_match() identifies a partial
+       match, the partial match is remembered, but matching continues as  nor-
+       mal,  and  other  alternatives in the pattern are tried. If no complete
+       match  can  be  found,  PCRE2_ERROR_PARTIAL  is  returned  instead   of
+       PCRE2_ERROR_NOMATCH.
+
+       This  option  is "soft" because it prefers a complete match over a par-
+       tial match.  All the various matching items in a pattern behave  as  if
+       the  subject string is potentially complete. For example, \z, \Z, and $
+       match at the end of the subject, as normal, and for \b and \B  the  end
+       of the subject is treated as a non-alphanumeric.
+
+       If  there  is more than one partial match, the first one that was found
+       provides the data that is returned. Consider this pattern:
+
+         /123\w+X|dogY/
+
+       If this is matched against the subject string "abc123dog", both  alter-
+       natives  fail  to  match,  but the end of the subject is reached during
+       matching, so PCRE2_ERROR_PARTIAL is returned. The offsets are set to  3
+       and  9, identifying "123dog" as the first partial match that was found.
+       (In this example, there are two partial matches, because "dog"  on  its
+       own partially matches the second alternative.)
+
+   PCRE2_PARTIAL_HARD WITH pcre2_match()
+
+       If  PCRE2_PARTIAL_HARD is set for pcre2_match(), PCRE2_ERROR_PARTIAL is
+       returned as soon as a partial match is  found,  without  continuing  to
+       search  for possible complete matches. This option is "hard" because it
+       prefers an earlier partial match over a later complete match. For  this
+       reason,  the  assumption  is  made that the end of the supplied subject
+       string may not be the true end of the available data, and  so,  if  \z,
+       \Z,  \b, \B, or $ are encountered at the end of the subject, the result
+       is PCRE2_ERROR_PARTIAL, provided that at least  one  character  in  the
+       subject has been inspected.
+
+   Comparing hard and soft partial matching
+
+       The  difference  between the two partial matching options can be illus-
+       trated by a pattern such as:
+
+         /dog(sbody)?/
+
+       This matches either "dog" or "dogsbody", greedily (that is, it  prefers
+       the  longer  string  if  possible). If it is matched against the string
+       "dog" with PCRE2_PARTIAL_SOFT, it yields a complete  match  for  "dog".
+       However,  if  PCRE2_PARTIAL_HARD is set, the result is PCRE2_ERROR_PAR-
+       TIAL. On the other hand, if the pattern is made ungreedy the result  is
+       different:
+
+         /dog(sbody)??/
+
+       In  this  case  the  result  is always a complete match because that is
+       found first, and matching never  continues  after  finding  a  complete
+       match. It might be easier to follow this explanation by thinking of the
+       two patterns like this:
+
+         /dog(sbody)?/    is the same as  /dogsbody|dog/
+         /dog(sbody)??/   is the same as  /dog|dogsbody/
+
+       The second pattern will never match "dogsbody", because it will  always
+       find the shorter match first.
+
+
+PARTIAL MATCHING USING pcre2_dfa_match()
+
+       The DFA functions move along the subject string character by character,
+       without backtracking, searching for  all  possible  matches  simultane-
+       ously.  If the end of the subject is reached before the end of the pat-
+       tern, there is the possibility of a partial match, again provided  that
+       at least one character has been inspected.
+
+       When PCRE2_PARTIAL_SOFT is set, PCRE2_ERROR_PARTIAL is returned only if
+       there have been no complete matches. Otherwise,  the  complete  matches
+       are  returned.   However, if PCRE2_PARTIAL_HARD is set, a partial match
+       takes precedence over any complete matches. The portion of  the  string
+       that was matched when the longest partial match was found is set as the
+       first matching string.
+
+       Because the DFA functions always search for all possible  matches,  and
+       there  is  no  difference between greedy and ungreedy repetition, their
+       behaviour is different from  the  standard  functions  when  PCRE2_PAR-
+       TIAL_HARD  is  set.  Consider  the  string  "dog"  matched  against the
+       ungreedy pattern shown above:
+
+         /dog(sbody)??/
+
+       Whereas the standard function stops as soon as it  finds  the  complete
+       match  for  "dog",  the  DFA  function also finds the partial match for
+       "dogsbody", and so returns that when PCRE2_PARTIAL_HARD is set.
+
+
+PARTIAL MATCHING AND WORD BOUNDARIES
+
+       If a pattern ends with one of sequences \b or \B, which test  for  word
+       boundaries,  partial matching with PCRE2_PARTIAL_SOFT can give counter-
+       intuitive results. Consider this pattern:
+
+         /\bcat\b/
+
+       This matches "cat", provided there is a word boundary at either end. If
+       the subject string is "the cat", the comparison of the final "t" with a
+       following character cannot take place, so a  partial  match  is  found.
+       However,  normal  matching carries on, and \b matches at the end of the
+       subject when the last character is a letter, so  a  complete  match  is
+       found.   The  result,  therefore,  is  not  PCRE2_ERROR_PARTIAL.  Using
+       PCRE2_PARTIAL_HARD in this case does yield PCRE2_ERROR_PARTIAL, because
+       then the partial match takes precedence.
+
+
+EXAMPLE OF PARTIAL MATCHING USING PCRE2TEST
+
+       If  the  partial_soft  (or  ps) modifier is present on a pcre2test data
+       line, the PCRE2_PARTIAL_SOFT option is used for the match.  Here  is  a
+       run of pcre2test that uses the date example quoted above:
+
+           re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
+         data> 25jun04\=ps
+          0: 25jun04
+          1: jun
+         data> 25dec3\=ps
+         Partial match: 23dec3
+         data> 3ju\=ps
+         Partial match: 3ju
+         data> 3juj\=ps
+         No match
+         data> j\=ps
+         No match
+
+       The  first  data  string  is matched completely, so pcre2test shows the
+       matched substrings. The remaining four strings do not  match  the  com-
+       plete pattern, but the first two are partial matches. Similar output is
+       obtained if DFA matching is used.
+
+       If the partial_hard (or ph) modifier is present  on  a  pcre2test  data
+       line, the PCRE2_PARTIAL_HARD option is set for the match.
+
+
+MULTI-SEGMENT MATCHING WITH pcre2_dfa_match()
+
+       When  a  partial match has been found using a DFA matching function, it
+       is possible to continue the match by providing additional subject  data
+       and  calling  the function again with the same compiled regular expres-
+       sion, this time setting the PCRE2_DFA_RESTART option. You must pass the
+       same working space as before, because this is where details of the pre-
+       vious partial match are stored. Here is an example using pcre2test:
+
+           re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
+         data> 23ja\=dfa,ps
+         Partial match: 23ja
+         data> n05\=dfa,dfa_restart
+          0: n05
+
+       The first call has "23ja" as the subject, and requests  partial  match-
+       ing;  the  second  call  has  "n05"  as  the  subject for the continued
+       (restarted) match.  Notice that when the match is  complete,  only  the
+       last  part  is  shown;  PCRE2 does not retain the previously partially-
+       matched string. It is up to the calling program to do that if it  needs
+       to.
+
+       That means that, for an unanchored pattern, if a continued match fails,
+       it is not possible to try again at  a  new  starting  point.  All  this
+       facility  is  capable  of  doing  is continuing with the previous match
+       attempt. In the previous example, if the second set of data  is  "ug23"
+       the  result is no match, even though there would be a match for "aug23"
+       if the entire string were given at once. Depending on the  application,
+       this may or may not be what you want.  The only way to allow for start-
+       ing again at the next character is to retain the matched  part  of  the
+       subject and try a new complete match.
+
+       You  can  set the PCRE2_PARTIAL_SOFT or PCRE2_PARTIAL_HARD options with
+       PCRE2_DFA_RESTART to continue partial matching over multiple  segments.
+       This  facility can be used to pass very long subject strings to the DFA
+       matching functions.
+
+
+MULTI-SEGMENT MATCHING WITH pcre2_match()
+
+       Unlike the DFA function, it is not possible  to  restart  the  previous
+       match with a new segment of data when using pcre2_match(). Instead, new
+       data must be added to the previous subject string, and the entire match
+       re-run,  starting from the point where the partial match occurred. Ear-
+       lier data can be discarded.
+
+       It is best to use PCRE2_PARTIAL_HARD in this situation, because it does
+       not  treat the end of a segment as the end of the subject when matching
+       \z, \Z, \b, \B, and $. Consider  an  unanchored  pattern  that  matches
+       dates:
+
+           re> /\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d/
+         data> The date is 23ja\=ph
+         Partial match: 23ja
+
+       At  this stage, an application could discard the text preceding "23ja",
+       add on text from the next  segment,  and  call  the  matching  function
+       again.  Unlike  the  DFA  matching function, the entire matching string
+       must always be available, and the complete matching process occurs  for
+       each call, so more memory and more processing time is needed.
+
+
+ISSUES WITH MULTI-SEGMENT MATCHING
+
+       Certain types of pattern may give problems with multi-segment matching,
+       whichever matching function is used.
+
+       1. If the pattern contains a test for the beginning of a line, you need
+       to  pass  the  PCRE2_NOTBOL option when the subject string for any call
+       does start at the beginning of a line. There  is  also  a  PCRE2_NOTEOL
+       option, but in practice when doing multi-segment matching you should be
+       using PCRE2_PARTIAL_HARD, which includes the effect of PCRE2_NOTEOL.
+
+       2. If a pattern contains a lookbehind assertion, characters  that  pre-
+       cede  the start of the partial match may have been inspected during the
+       matching process.  When using pcre2_match(), sufficient characters must
+       be  retained  for  the  next  match attempt. You can ensure that enough
+       characters are retained by doing the following:
+
+       Before doing any matching, find the length of the longest lookbehind in
+       the     pattern    by    calling    pcre2_pattern_info()    with    the
+       PCRE2_INFO_MAXLOOKBEHIND option. Note that the resulting  count  is  in
+       characters, not code units. After a partial match, moving back from the
+       ovector[0] offset in the subject by the number of characters given  for
+       the  maximum lookbehind gets you to the earliest character that must be
+       retained. In a non-UTF or a 32-bit situation, moving  back  is  just  a
+       subtraction,  but in UTF-8 or UTF-16 you have to count characters while
+       moving back through the code units.
+
+       Characters before the point you have now reached can be discarded,  and
+       after  the  next segment has been added to what is retained, you should
+       run the next match with the startoffset argument set so that the  match
+       begins at the same point as before.
+
+       For  example, if the pattern "(?<=123)abc" is partially matched against
+       the string "xx123ab", the ovector offsets are 5 and 7 ("ab"). The maxi-
+       mum  lookbehind  count  is  3, so all characters before offset 2 can be
+       discarded. The value of startoffset for the next  match  should  be  3.
+       When  pcre2test  displays  a partial match, it indicates the lookbehind
+       characters with '<' characters:
+
+           re> "(?<=123)abc"
+         data> xx123ab\=ph
+         Partial match: 123ab
+                        <<<
+
+       3. Because a partial match must always contain at least one  character,
+       what  might  be  considered a partial match of an empty string actually
+       gives a "no match" result. For example:
+
+           re> /c(?<=abc)x/
+         data> ab\=ps
+         No match
+
+       If the next segment begins "cx", a match should be found, but this will
+       only  happen  if characters from the previous segment are retained. For
+       this reason, a "no match" result  should  be  interpreted  as  "partial
+       match of an empty string" when the pattern contains lookbehinds.
+
+       4.  Matching  a subject string that is split into multiple segments may
+       not always produce exactly the same result as matching over one  single
+       long  string,  especially  when PCRE2_PARTIAL_SOFT is used. The section
+       "Partial Matching and Word Boundaries" above describes  an  issue  that
+       arises  if  the  pattern ends with \b or \B. Another kind of difference
+       may occur when there are multiple matching possibilities, because  (for
+       PCRE2_PARTIAL_SOFT) a partial match result is given only when there are
+       no completed matches. This means that as soon as the shortest match has
+       been  found,  continuation to a new subject segment is no longer possi-
+       ble. Consider this pcre2test example:
+
+           re> /dog(sbody)?/
+         data> dogsb\=ps
+          0: dog
+         data> do\=ps,dfa
+         Partial match: do
+         data> gsb\=ps,dfa,dfa_restart
+          0: g
+         data> dogsbody\=dfa
+          0: dogsbody
+          1: dog
+
+       The first data line passes the string "dogsb" to  a  standard  matching
+       function, setting the PCRE2_PARTIAL_SOFT option. Although the string is
+       a partial match for "dogsbody", the result is not  PCRE2_ERROR_PARTIAL,
+       because  the  shorter string "dog" is a complete match. Similarly, when
+       the subject is presented to a DFA matching function  in  several  parts
+       ("do"  and  "gsb"  being  the first two) the match stops when "dog" has
+       been found, and it is not possible to continue.  On the other hand,  if
+       "dogsbody"  is  presented  as  a single string, a DFA matching function
+       finds both matches.
+
+       Because of these problems, it is best to  use  PCRE2_PARTIAL_HARD  when
+       matching  multi-segment  data.  The  example above then behaves differ-
+       ently:
+
+           re> /dog(sbody)?/
+         data> dogsb\=ph
+         Partial match: dogsb
+         data> do\=ps,dfa
+         Partial match: do
+         data> gsb\=ph,dfa,dfa_restart
+         Partial match: gsb
+
+       5. Patterns that contain alternatives at the top level which do not all
+       start  with  the  same  pattern  item  may  not  work  as expected when
+       PCRE2_DFA_RESTART is used. For example, consider this pattern:
+
+         1234|3789
+
+       If the first part of the subject is "ABC123", a partial  match  of  the
+       first  alternative  is found at offset 3. There is no partial match for
+       the second alternative, because such a match does not start at the same
+       point  in  the  subject  string. Attempting to continue with the string
+       "7890" does not yield a match  because  only  those  alternatives  that
+       match  at  one  point in the subject are remembered. The problem arises
+       because the start of the second alternative matches  within  the  first
+       alternative.  There  is  no  problem with anchored patterns or patterns
+       such as:
+
+         1234|ABCD
+
+       where no string can be a partial match for both alternatives.  This  is
+       not  a  problem  if  a  standard matching function is used, because the
+       entire match has to be rerun each time:
+
+           re> /1234|3789/
+         data> ABC123\=ph
+         Partial match: 123
+         data> 1237890
+          0: 3789
+
+       Of course, instead of using PCRE2_DFA_RESTART, the  same  technique  of
+       re-running  the  entire  match  can  also be used with the DFA matching
+       function. Another possibility is to work with two buffers. If a partial
+       match  at  offset  n in the first buffer is followed by "no match" when
+       PCRE2_DFA_RESTART is used on the second buffer, you can then try a  new
+       match starting at offset n+1 in the first buffer.
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge, England.
+
+
+REVISION
+
+       Last updated: 22 December 2014
+       Copyright (c) 1997-2014 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCRE2UNICODE(3)            Library Functions Manual            PCRE2UNICODE(3)
+
+
+
+NAME
+       PCRE - Perl-compatible regular expressions (revised API)
+
+UNICODE AND UTF SUPPORT
+
+       When PCRE2 is built with Unicode support (which is the default), it has
+       knowledge of Unicode character properties and can process text  strings
+       in  UTF-8, UTF-16, or UTF-32 format (depending on the code unit width).
+       However, by default, PCRE2 assumes that one code unit is one character.
+       To  process  a  pattern  as a UTF string, where a character may require
+       more than one  code  unit,  you  must  call  pcre2_compile()  with  the
+       PCRE2_UTF  option  flag,  or  the  pattern must start with the sequence
+       (*UTF). When either of these is the case, both the pattern and any sub-
+       ject  strings  that  are  matched against it are treated as UTF strings
+       instead of strings of individual one-code-unit characters.
+
+       If you do not need Unicode support you can build PCRE2 without  it,  in
+       which case the library will be smaller.
+
+
+UNICODE PROPERTY SUPPORT
+
+       When  PCRE2 is built with Unicode support, the escape sequences \p{..},
+       \P{..}, and \X can be used. The Unicode properties that can  be  tested
+       are  limited to the general category properties such as Lu for an upper
+       case letter or Nd for a decimal number, the Unicode script  names  such
+       as Arabic or Han, and the derived properties Any and L&. Full lists are
+       given in the pcre2pattern and pcre2syntax documentation. Only the short
+       names  for  properties are supported. For example, \p{L} matches a let-
+       ter. Its Perl synonym, \p{Letter}, is not supported.   Furthermore,  in
+       Perl,  many properties may optionally be prefixed by "Is", for compati-
+       bility with Perl 5.6. PCRE does not support this.
+
+
+WIDE CHARACTERS AND UTF MODES
+
+       Codepoints less than 256 can be specified in patterns by either  braced
+       or unbraced hexadecimal escape sequences (for example, \x{b3} or \xb3).
+       Larger values have to use braced sequences. Unbraced octal code  points
+       up to \777 are also recognized; larger ones can be coded using \o{...}.
+
+       In  UTF modes, repeat quantifiers apply to complete UTF characters, not
+       to individual code units.
+
+       In UTF modes, the dot metacharacter matches one UTF  character  instead
+       of a single code unit.
+
+       The  escape  sequence  \C can be used to match a single code unit, in a
+       UTF mode, but its use can lead  to  some  strange  effects  because  it
+       breaks  up  multi-unit  characters  (see  the  description of \C in the
+       pcre2pattern documentation). The use of \C  is  not  supported  in  the
+       alternative matching function pcre2_dfa_match(), nor is it supported in
+       UTF mode by the JIT optimization. If JIT optimization is requested  for
+       a  UTF pattern that contains \C, it will not succeed, and so the match-
+       ing will be carried out by the normal interpretive function.
+
+       The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly test
+       characters  of  any  code  value,  but, by default, the characters that
+       PCRE2 recognizes as digits, spaces, or word characters remain the  same
+       set  as  in  non-UTF  mode,  all  with  code points less than 256. This
+       remains true even when PCRE2  is  built  to  include  Unicode  support,
+       because  to do otherwise would slow down matching in many common cases.
+       Note that this also applies to \b and \B, because they are  defined  in
+       terms  of  \w  and  \W.  If you want to test for a wider sense of, say,
+       "digit", you can use explicit Unicode property tests  such  as  \p{Nd}.
+       Alternatively,  if you set the PCRE2_UCP option, the way that the char-
+       acter escapes work is changed so that Unicode properties  are  used  to
+       determine which characters match. There are more details in the section
+       on generic character types in the pcre2pattern documentation.
+
+       Similarly, characters that match the POSIX named character classes  are
+       all low-valued characters, unless the PCRE2_UCP option is set.
+
+       However,  the  special  horizontal  and  vertical  white space matching
+       escapes (\h, \H, \v, and \V) do match all the appropriate Unicode char-
+       acters, whether or not PCRE2_UCP is set.
+
+       Case-insensitive  matching in UTF mode makes use of Unicode properties.
+       A few Unicode characters such as Greek sigma have more than  two  code-
+       points that are case-equivalent, and these are treated as such.
+
+
+VALIDITY OF UTF STRINGS
+
+       When  the  PCRE2_UTF  option is set, the strings passed as patterns and
+       subjects are (by default) checked for validity on entry to the relevant
+       functions.   If an invalid UTF string is passed, an negative error code
+       is returned. The code unit offset to the  offending  character  can  be
+       extracted  from  the match data block by calling pcre2_get_startchar(),
+       which is used for this purpose after a UTF error.
+
+       UTF-16 and UTF-32 strings can indicate their endianness by special code
+       knows  as  a  byte-order  mark (BOM). The PCRE2 functions do not handle
+       this, expecting strings to be in host byte order.
+
+       The entire string is checked before any other processing  takes  place.
+       In  addition  to checking the format of the string, there is a check to
+       ensure that all code points lie in the range U+0 to U+10FFFF, excluding
+       the  surrogate area.  The so-called "non-character" code points are not
+       excluded because Unicode corrigendum #9 makes it clear that they should
+       not be.
+
+       Characters  in  the "Surrogate Area" of Unicode are reserved for use by
+       UTF-16, where they are used in pairs to encode code points with  values
+       greater  than  0xFFFF. The code points that are encoded by UTF-16 pairs
+       are available independently in the  UTF-8  and  UTF-32  encodings.  (In
+       other  words,  the  whole  surrogate  thing is a fudge for UTF-16 which
+       unfortunately messes up UTF-8 and UTF-32.)
+
+       In some situations, you may already know that your strings  are  valid,
+       and  therefore  want  to  skip these checks in order to improve perfor-
+       mance, for example in the case of a long subject string that  is  being
+       scanned  repeatedly.   If you set the PCRE2_NO_UTF_CHECK option at com-
+       pile time or at match time, PCRE2 assumes that the pattern  or  subject
+       it is given (respectively) contains only valid UTF code unit sequences.
+
+       Passing  PCRE2_NO_UTF_CHECK  to pcre2_compile() just disables the check
+       for the pattern; it does not also apply to subject strings. If you want
+       to  disable the check for a subject string you must pass this option to
+       pcre2_match() or pcre2_dfa_match().
+
+       If you pass an invalid UTF string when PCRE2_NO_UTF_CHECK is  set,  the
+       result is undefined and your program may crash or loop indefinitely.
+
+   Errors in UTF-8 strings
+
+       The following negative error codes are given for invalid UTF-8 strings:
+
+         PCRE2_ERROR_UTF8_ERR1
+         PCRE2_ERROR_UTF8_ERR2
+         PCRE2_ERROR_UTF8_ERR3
+         PCRE2_ERROR_UTF8_ERR4
+         PCRE2_ERROR_UTF8_ERR5
+
+       The  string  ends  with a truncated UTF-8 character; the code specifies
+       how many bytes are missing (1 to 5). Although RFC 3629 restricts  UTF-8
+       characters  to  be  no longer than 4 bytes, the encoding scheme (origi-
+       nally defined by RFC 2279) allows for  up  to  6  bytes,  and  this  is
+       checked first; hence the possibility of 4 or 5 missing bytes.
+
+         PCRE2_ERROR_UTF8_ERR6
+         PCRE2_ERROR_UTF8_ERR7
+         PCRE2_ERROR_UTF8_ERR8
+         PCRE2_ERROR_UTF8_ERR9
+         PCRE2_ERROR_UTF8_ERR10
+
+       The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of
+       the character do not have the binary value 0b10 (that  is,  either  the
+       most significant bit is 0, or the next bit is 1).
+
+         PCRE2_ERROR_UTF8_ERR11
+         PCRE2_ERROR_UTF8_ERR12
+
+       A  character that is valid by the RFC 2279 rules is either 5 or 6 bytes
+       long; these code points are excluded by RFC 3629.
+
+         PCRE2_ERROR_UTF8_ERR13
+
+       A 4-byte character has a value greater than 0x10fff; these code  points
+       are excluded by RFC 3629.
+
+         PCRE2_ERROR_UTF8_ERR14
+
+       A  3-byte  character  has  a  value in the range 0xd800 to 0xdfff; this
+       range of code points are reserved by RFC 3629 for use with UTF-16,  and
+       so are excluded from UTF-8.
+
+         PCRE2_ERROR_UTF8_ERR15
+         PCRE2_ERROR_UTF8_ERR16
+         PCRE2_ERROR_UTF8_ERR17
+         PCRE2_ERROR_UTF8_ERR18
+         PCRE2_ERROR_UTF8_ERR19
+
+       A  2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes
+       for a value that can be represented by fewer bytes, which  is  invalid.
+       For  example,  the two bytes 0xc0, 0xae give the value 0x2e, whose cor-
+       rect coding uses just one byte.
+
+         PCRE2_ERROR_UTF8_ERR20
+
+       The two most significant bits of the first byte of a character have the
+       binary  value 0b10 (that is, the most significant bit is 1 and the sec-
+       ond is 0). Such a byte can only validly occur as the second  or  subse-
+       quent byte of a multi-byte character.
+
+         PCRE2_ERROR_UTF8_ERR21
+
+       The  first byte of a character has the value 0xfe or 0xff. These values
+       can never occur in a valid UTF-8 string.
+
+   Errors in UTF-16 strings
+
+       The following  negative  error  codes  are  given  for  invalid  UTF-16
+       strings:
+
+         PCRE_UTF16_ERR1  Missing low surrogate at end of string
+         PCRE_UTF16_ERR2  Invalid low surrogate follows high surrogate
+         PCRE_UTF16_ERR3  Isolated low surrogate
+
+
+   Errors in UTF-32 strings
+
+       The  following  negative  error  codes  are  given  for  invalid UTF-32
+       strings:
+
+         PCRE_UTF32_ERR1  Surrogate character (range from 0xd800 to 0xdfff)
+         PCRE_UTF32_ERR2  Code point is greater than 0x10ffff
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge, England.
+
+
+REVISION
+
+       Last updated: 23 November 2014
+       Copyright (c) 1997-2014 University of Cambridge.
+------------------------------------------------------------------------------
+
+
diff --git a/pcre2-10.20/doc/pcre2_callout_enumerate.3 b/pcre2-10.20/doc/pcre2_callout_enumerate.3
new file mode 100644
index 000000000..4573bb4a8
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_callout_enumerate.3
@@ -0,0 +1,50 @@
+.TH PCRE2_COMPILE 3 "23 March 2015" "PCRE2 10.20"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_callout_enumerate(const pcre2_code *\fIcode\fP,
+.B "  int (*\fIcallback\fP)(pcre2_callout_enumerate_block *, void *),"
+.B "  void *\fIcallout_data\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function scans a compiled regular expression and calls the \fIcallback()\fP
+function for each callout within the pattern. The yield of the function is zero
+for success and non-zero otherwise. The arguments are:
+.sp
+  \fIcode\fP           Points to the compiled pattern
+  \fIcallback\fP       The callback function
+  \fIcallout_data\fP   User data that is passed to the callback
+.sp
+The \fIcallback()\fP function is passed a pointer to a data block containing
+the following fields:
+.sp
+  \fIversion\fP                Block version number
+  \fIpattern_position\fP       Offset to next item in pattern
+  \fInext_item_length\fP       Length of next item in pattern
+  \fIcallout_number\fP         Number for numbered callouts
+  \fIcallout_string_offset\fP  Offset to string within pattern
+  \fIcallout_string_length\fP  Length of callout string
+  \fIcallout_string\fP         Points to callout string or is NULL
+.sp
+The second argument is the callout data that was passed to
+\fBpcre2_callout_enumerate()\fP. The \fBcallback()\fP function must return zero
+for success. Any other value causes the pattern scan to stop, with the value
+being passed back as the result of \fBpcre2_callout_enumerate()\fP.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_code_free.3 b/pcre2-10.20/doc/pcre2_code_free.3
new file mode 100644
index 000000000..3a1c7d885
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_code_free.3
@@ -0,0 +1,27 @@
+.TH PCRE2_CODE_FREE 3 "21 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B pcre2_code_free(pcre2_code *\fIcode\fP);
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function frees the memory used for a compiled pattern, including any
+memory used by the JIT compiler.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_compile.3 b/pcre2-10.20/doc/pcre2_compile.3
new file mode 100644
index 000000000..1e0dca5dd
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_compile.3
@@ -0,0 +1,78 @@
+.TH PCRE2_COMPILE 3 "22 April 2015" "PCRE2 10.20"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B pcre2_code *pcre2_compile(PCRE2_SPTR \fIpattern\fP, PCRE2_SIZE \fIlength\fP,
+.B "  uint32_t \fIoptions\fP, int *\fIerrorcode\fP, PCRE2_SIZE *\fIerroroffset,\fP"
+.B "  pcre2_compile_context *\fIccontext\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function compiles a regular expression pattern into an internal form. Its
+arguments are:
+.sp
+  \fIpattern\fP       A string containing expression to be compiled
+  \fIlength\fP        The length of the string or PCRE2_ZERO_TERMINATED
+  \fIoptions\fP       Option bits
+  \fIerrorcode\fP     Where to put an error code
+  \fIerroffset\fP     Where to put an error offset
+  \fIccontext\fP      Pointer to a compile context or NULL
+.sp
+The length of the string and any error offset that is returned are in code
+units, not characters. A compile context is needed only if you want to change
+.sp
+  What \eR matches (Unicode newlines or CR, LF, CRLF only)
+  PCRE2's character tables
+  The newline character sequence
+  The compile time nested parentheses limit
+.sp
+or provide an external function for stack size checking. The option bits are:
+.sp
+  PCRE2_ANCHORED           Force pattern anchoring
+  PCRE2_ALT_BSUX           Alternative handling of \eu, \eU, and \ex
+  PCRE2_ALT_CIRCUMFLEX     Alternative handling of ^ in multiline mode
+  PCRE2_AUTO_CALLOUT       Compile automatic callouts
+  PCRE2_CASELESS           Do caseless matching
+  PCRE2_DOLLAR_ENDONLY     $ not to match newline at end
+  PCRE2_DOTALL             . matches anything including NL
+  PCRE2_DUPNAMES           Allow duplicate names for subpatterns
+  PCRE2_EXTENDED           Ignore white space and # comments
+  PCRE2_FIRSTLINE          Force matching to be before newline
+  PCRE2_MATCH_UNSET_BACKREF  Match unset back references
+  PCRE2_MULTILINE          ^ and $ match newlines within data
+  PCRE2_NEVER_BACKSLASH_C  Lock out the use of \eC in patterns
+  PCRE2_NEVER_UCP          Lock out PCRE2_UCP, e.g. via (*UCP)
+  PCRE2_NEVER_UTF          Lock out PCRE2_UTF, e.g. via (*UTF)
+  PCRE2_NO_AUTO_CAPTURE    Disable numbered capturing paren-
+                            theses (named ones available)
+  PCRE2_NO_AUTO_POSSESS    Disable auto-possessification
+  PCRE2_NO_DOTSTAR_ANCHOR  Disable automatic anchoring for .*
+  PCRE2_NO_START_OPTIMIZE  Disable match-time start optimizations
+  PCRE2_NO_UTF_CHECK       Do not check the pattern for UTF validity
+                             (only relevant if PCRE2_UTF is set)
+  PCRE2_UCP                Use Unicode properties for \ed, \ew, etc.
+  PCRE2_UNGREEDY           Invert greediness of quantifiers
+  PCRE2_UTF                Treat pattern and subjects as UTF strings
+.sp
+PCRE2 must be built with Unicode support in order to use PCRE2_UTF, PCRE2_UCP
+and related options.
+.P
+The yield of the function is a pointer to a private data structure that
+contains the compiled pattern, or NULL if an error was detected.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_compile_context_copy.3 b/pcre2-10.20/doc/pcre2_compile_context_copy.3
new file mode 100644
index 000000000..aea118756
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_compile_context_copy.3
@@ -0,0 +1,29 @@
+.TH PCRE2_COMPILE_CONTEXT_COPY 3 "22 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B pcre2_compile_context *pcre2_compile_context_copy(
+.B "  pcre2_compile_context *\fIccontext\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function makes a new copy of a compile context, using the memory
+allocation function that was used for the original context. The result is NULL
+if the memory cannot be obtained.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_compile_context_create.3 b/pcre2-10.20/doc/pcre2_compile_context_create.3
new file mode 100644
index 000000000..3053df430
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_compile_context_create.3
@@ -0,0 +1,30 @@
+.TH PCRE2_COMPILE_CONTEXT_CREATE 3 "22 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B pcre2_compile_context *pcre2_compile_context_create(
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function creates and initializes a new compile context. If its argument is
+NULL, \fBmalloc()\fP is used to get the necessary memory; otherwise the memory
+allocation function within the general context is used. The result is NULL if
+the memory could not be obtained.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_compile_context_free.3 b/pcre2-10.20/doc/pcre2_compile_context_free.3
new file mode 100644
index 000000000..0c6d78754
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_compile_context_free.3
@@ -0,0 +1,28 @@
+.TH PCRE2_COMPILE_CONTEXT_FREE 3 "22 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B void pcre2_compile_context_free(pcre2_compile_context *\fIccontext\fP);
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function frees the memory occupied by a compile context, using the memory
+freeing function from the general context with which it was created, or
+\fBfree()\fP if that was not set.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_config.3 b/pcre2-10.20/doc/pcre2_config.3
new file mode 100644
index 000000000..0c29ce6a1
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_config.3
@@ -0,0 +1,69 @@
+.TH PCRE2_CONFIG 3 "20 April 2014" "PCRE2 10.0"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.SM
+.B int pcre2_config(uint32_t \fIwhat\fP, void *\fIwhere\fP);
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function makes it possible for a client program to find out which optional
+features are available in the version of the PCRE2 library it is using. The
+arguments are as follows:
+.sp
+  \fIwhat\fP     A code specifying what information is required
+  \fIwhere\fP    Points to where to put the information
+.sp
+If \fIwhere\fP is NULL, the function returns the amount of memory needed for
+the requested information. When the information is a string, the value is in
+code units; for other types of data it is in bytes.
+.P
+If \fBwhere\fP is not NULL, for PCRE2_CONFIG_JITTARGET,
+PCRE2_CONFIG_UNICODE_VERSION, and PCRE2_CONFIG_VERSION it must point to a
+buffer that is large enough to hold the string. For all other codes it must
+point to a uint32_t integer variable. The available codes are:
+.sp
+  PCRE2_CONFIG_BSR             Indicates what \eR matches by default:
+                                 PCRE2_BSR_UNICODE
+                                 PCRE2_BSR_ANYCRLF
+  PCRE2_CONFIG_JIT             Availability of just-in-time compiler
+                                support (1=yes 0=no)
+  PCRE2_CONFIG_JITTARGET       Information about the target archi-
+                                 tecture for the JIT compiler
+  PCRE2_CONFIG_LINKSIZE        Configured internal link size (2, 3, 4)
+  PCRE2_CONFIG_MATCHLIMIT      Default internal resource limit
+  PCRE2_CONFIG_NEWLINE         Code for the default newline sequence:
+                                 PCRE2_NEWLINE_CR
+                                 PCRE2_NEWLINE_LF
+                                 PCRE2_NEWLINE_CRLF
+                                 PCRE2_NEWLINE_ANY
+                                 PCRE2_NEWLINE_ANYCRLF
+  PCRE2_CONFIG_PARENSLIMIT     Default parentheses nesting limit
+  PCRE2_CONFIG_RECURSIONLIMIT  Internal recursion depth limit
+  PCRE2_CONFIG_STACKRECURSE    Recursion implementation (1=stack
+                                 0=heap)
+  PCRE2_CONFIG_UNICODE         Availability of Unicode support (1=yes
+                                 0=no)
+  PCRE2_CONFIG_UNICODE_VERSION The Unicode version (a string)
+  PCRE2_CONFIG_VERSION         The PCRE2 version (a string)
+.sp
+The function yields a non-negative value on success or the negative value
+PCRE2_ERROR_BADOPTION otherwise. This is also the result for the
+PCRE2_CONFIG_JITTARGET code if JIT support is not available. When a string is
+requested, the function returns the number of code units used, including the
+terminating zero.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_dfa_match.3 b/pcre2-10.20/doc/pcre2_dfa_match.3
new file mode 100644
index 000000000..f45da0df7
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_dfa_match.3
@@ -0,0 +1,72 @@
+.TH PCRE2_DFA_MATCH 3 "12 May 2013" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_dfa_match(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
+.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
+.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
+.B "  pcre2_match_context *\fImcontext\fP,"
+.B "  int *\fIworkspace\fP, PCRE2_SIZE \fIwscount\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function matches a compiled regular expression against a given subject
+string, using an alternative matching algorithm that scans the subject string
+just once (\fInot\fP Perl-compatible). (The Perl-compatible matching function
+is \fBpcre2_match()\fP.) The arguments for this function are:
+.sp
+  \fIcode\fP         Points to the compiled pattern
+  \fIsubject\fP      Points to the subject string
+  \fIlength\fP       Length of the subject string
+  \fIstartoffset\fP  Offset in the subject at which to start matching
+  \fIoptions\fP      Option bits
+  \fImatch_data\fP   Points to a match data block, for results
+  \fImcontext\fP     Points to a match context, or is NULL
+  \fIworkspace\fP    Points to a vector of ints used as working space
+  \fIwscount\fP      Number of elements in the vector
+.sp
+For \fBpcre2_dfa_match()\fP, a match context is needed only if you want to set
+up a callout function. The \fIlength\fP and \fIstartoffset\fP values are code
+units, not characters. The options are:
+.sp
+  PCRE2_ANCHORED          Match only at the first position
+  PCRE2_NOTBOL            Subject is not the beginning of a line
+  PCRE2_NOTEOL            Subject is not the end of a line
+  PCRE2_NOTEMPTY          An empty string is not a valid match
+  PCRE2_NOTEMPTY_ATSTART  An empty string at the start of the subject
+                           is not a valid match
+  PCRE2_NO_UTF_CHECK      Do not check the subject for UTF
+                           validity (only relevant if PCRE2_UTF
+                           was set at compile time)
+  PCRE2_PARTIAL_SOFT      Return PCRE2_ERROR_PARTIAL for a partial
+                            match if no full matches are found
+  PCRE2_PARTIAL_HARD      Return PCRE2_ERROR_PARTIAL for a partial match
+                           even if there is a full match as well
+  PCRE2_DFA_RESTART       Restart after a partial match
+  PCRE2_DFA_SHORTEST      Return only the shortest match
+.sp
+There are restrictions on what may appear in a pattern when using this matching
+function. Details are given in the
+.\" HREF
+\fBpcre2matching\fP
+.\"
+documentation. For details of partial matching, see the
+.\" HREF
+\fBpcre2partial\fP
+.\"
+page. There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_general_context_copy.3 b/pcre2-10.20/doc/pcre2_general_context_copy.3
new file mode 100644
index 000000000..637e565fe
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_general_context_copy.3
@@ -0,0 +1,30 @@
+.TH PCRE2_GENERAL_CONTEXT_COPY 3 "22 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B pcre2_general_context *pcre2_general_context_copy(
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function makes a new copy of a general context, using the memory
+allocation functions in the context, if set, to get the necessary memory.
+Otherwise \fBmalloc()\fP is used. The result is NULL if the memory cannot be
+obtained.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_general_context_create.3 b/pcre2-10.20/doc/pcre2_general_context_create.3
new file mode 100644
index 000000000..a3e6c10ce
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_general_context_create.3
@@ -0,0 +1,32 @@
+.TH PCRE2_GENERAL_CONTEXT_CREATE 3 "22 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B pcre2_general_context *pcre2_general_context_create(
+.B "  void *(*\fIprivate_malloc\fP)(PCRE2_SIZE, void *),"
+.B "  void (*\fIprivate_free\fP)(void *, void *), void *\fImemory_data\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function creates and initializes a general context. The arguments define
+custom memory management functions and a data value that is passed to them when
+they are called. The \fBprivate_malloc()\fP function is used to get memory for
+the context. If either of the first two arguments is NULL, the system memory
+management function is used. The result is NULL if no memory could be obtained.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_general_context_free.3 b/pcre2-10.20/doc/pcre2_general_context_free.3
new file mode 100644
index 000000000..6285332a5
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_general_context_free.3
@@ -0,0 +1,27 @@
+.TH PCRE2_GENERAL_CONTEXT_FREE 3 "22 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B void pcre2_general_context_free(pcre2_general_context *\fIgcontext\fP);
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function frees the memory occupied by a general context, using the memory
+freeing function within the context, if set.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_get_error_message.3 b/pcre2-10.20/doc/pcre2_get_error_message.3
new file mode 100644
index 000000000..9ff53420d
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_get_error_message.3
@@ -0,0 +1,36 @@
+.TH PCRE2_GET_ERROR_MESSAGE 3 "21 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_get_error_message(int \fIerrorcode\fP, PCRE2_UCHAR *\fIbuffer\fP,
+.B "  PCRE2_SIZE \fIbufflen\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function provides a textual error message for each PCRE2 error code.
+Compilation errors are positive numbers; UTF formatting errors and matching
+errors are negative numbers. The arguments are:
+.sp
+  \fIerrorcode\fP   an error code (positive or negative)
+  \fIbuffer\fP      where to put the message
+  \fIbufflen\fP     the length of the buffer (code units)
+.sp
+The function returns the length of the message, excluding the trailing zero, or
+a negative error code if the buffer is too small.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_get_mark.3 b/pcre2-10.20/doc/pcre2_get_mark.3
new file mode 100644
index 000000000..e741dfe14
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_get_mark.3
@@ -0,0 +1,31 @@
+.TH PCRE2_GET_MARK 3 "24 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B PCRE2_SPTR pcre2_get_mark(pcre2_match_data *\fImatch_data\fP);
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+After a call of \fBpcre2_match()\fP that was passed the match block that is
+this function's argument, this function returns a pointer to the last (*MARK)
+name that was encountered. The name is zero-terminated, and is within the
+compiled pattern. If no (*MARK) name is available, NULL is returned. A (*MARK)
+name may be available after a failed match or a partial match, as well as after
+a successful one.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_get_ovector_count.3 b/pcre2-10.20/doc/pcre2_get_ovector_count.3
new file mode 100644
index 000000000..3f6d74882
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_get_ovector_count.3
@@ -0,0 +1,27 @@
+.TH PCRE2_GET_OVECTOR_COUNT 3 "24 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B uint32_t pcre2_get_ovector_count(pcre2_match_data *\fImatch_data\fP);
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function returns the number of pairs of offsets in the ovector that forms
+part of the given match data block.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_get_ovector_pointer.3 b/pcre2-10.20/doc/pcre2_get_ovector_pointer.3
new file mode 100644
index 000000000..261d652d3
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_get_ovector_pointer.3
@@ -0,0 +1,28 @@
+.TH PCRE2_GET_OVECTOR_POINTER 3 "24 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *\fImatch_data\fP);
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function returns a pointer to the vector of offsets that forms part of the
+given match data block. The number of pairs can be found by calling
+\fBpcre2_get_ovector_count()\fP.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_get_startchar.3 b/pcre2-10.20/doc/pcre2_get_startchar.3
new file mode 100644
index 000000000..c6ac8b01f
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_get_startchar.3
@@ -0,0 +1,32 @@
+.TH PCRE2_GET_STARTCHAR 3 "24 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *\fImatch_data\fP);
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+After a successful call of \fBpcre2_match()\fP that was passed the match block
+that is this function's argument, this function returns the code unit offset of
+the character at which the successful match started. For a non-partial match,
+this can be different to the value of \fIovector[0]\fP if the pattern contains
+the \eK escape sequence. After a partial match, however, this value is always
+the same as \fIovector[0]\fP because \eK does not affect the result of a
+partial match.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_jit_compile.3 b/pcre2-10.20/doc/pcre2_jit_compile.3
new file mode 100644
index 000000000..a11d949d9
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_jit_compile.3
@@ -0,0 +1,45 @@
+.TH PCRE2_JIT_COMPILE 3 "21 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_jit_compile(pcre2_code *\fIcode\fP, uint32_t \fIoptions\fP);
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function requests JIT compilation, which, if the just-in-time compiler is
+available, further processes a compiled pattern into machine code that executes
+much faster than the \fBpcre2_match()\fP interpretive matching function. Full
+details are given in the
+.\" HREF
+\fBpcre2jit\fP
+.\"
+documentation.
+.P
+The first argument is a pointer that was returned by a successful call to
+\fBpcre2_compile()\fP, and the second must contain one or more of the following
+bits:
+.sp
+  PCRE2_JIT_COMPLETE      compile code for full matching
+  PCRE2_JIT_PARTIAL_SOFT  compile code for soft partial matching
+  PCRE2_JIT_PARTIAL_HARD  compile code for hard partial matching
+.sp
+The yield of the function is 0 for success, or a negative error code otherwise.
+In particular, PCRE2_ERROR_JIT_BADOPTION is returned if JIT is not supported or
+if an unknown bit is set in \fIoptions\fP.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_jit_free_unused_memory.3 b/pcre2-10.20/doc/pcre2_jit_free_unused_memory.3
new file mode 100644
index 000000000..bf050c8a0
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_jit_free_unused_memory.3
@@ -0,0 +1,31 @@
+.TH PCRE2_JIT_FREE_UNUSED_MEMORY 3 "27 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B void pcre2_jit_free_unused_memory(pcre2_general_context *\fIgcontext\fP);
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function frees unused JIT executable memory. The argument is a general
+context, for custom memory management, or NULL for standard memory management.
+JIT memory allocation retains some memory in order to improve future JIT
+compilation speed. In low memory conditions,
+\fBpcre2_jit_free_unused_memory()\fB can be used to cause this memory to be
+freed.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_jit_match.3 b/pcre2-10.20/doc/pcre2_jit_match.3
new file mode 100644
index 000000000..b0cc197db
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_jit_match.3
@@ -0,0 +1,48 @@
+.TH PCRE2_JIT_MATCH 3 "03 November 2014" "PCRE2 10.0"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_jit_match(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
+.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
+.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
+.B "  pcre2_match_context *\fImcontext\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function matches a compiled regular expression that has been successfully
+processed by the JIT compiler against a given subject string, using a matching
+algorithm that is similar to Perl's. It is a "fast path" interface to JIT, and
+it bypasses some of the sanity checks that \fBpcre2_match()\fP applies.
+Its arguments are exactly the same as for
+.\" HREF
+\fBpcre2_match()\fP.
+.\"
+.P
+The supported options are PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY,
+PCRE2_NOTEMPTY_ATSTART, PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. Unsupported
+options are ignored. The subject string is not checked for UTF validity.
+.P
+The return values are the same as for \fBpcre2_match()\fP plus
+PCRE2_ERROR_JIT_BADOPTION if a matching mode (partial or complete) is requested
+that was not compiled. For details of partial matching, see the
+.\" HREF
+\fBpcre2partial\fP
+.\"
+page.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the JIT API in the
+.\" HREF
+\fBpcre2jit\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_jit_stack_assign.3 b/pcre2-10.20/doc/pcre2_jit_stack_assign.3
new file mode 100644
index 000000000..66b809548
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_jit_stack_assign.3
@@ -0,0 +1,55 @@
+.TH PCRE2_JIT_STACK_ASSIGN 3 "08 November 2014" "PCRE2 10.0"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B void pcre2_jit_stack_assign(pcre2_match_context *\fImcontext\fP,
+.B "  pcre2_jit_callback \fIcallback_function\fP, void *\fIcallback_data\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function provides control over the memory used by JIT as a run-time stack
+when \fBpcre2_match()\fP or \fBpcre2_jit_match()\fP is called with a pattern
+that has been successfully processed by the JIT compiler. The information that
+determines which stack is used is put into a match context that is subsequently
+passed to a matching function. The arguments of this function are:
+.sp
+  mcontext       a pointer to a match context
+  callback       a callback function
+  callback_data  a JIT stack or a value to be passed to the callback
+.P
+If \fIcallback\fP is NULL and \fIcallback_data\fP is NULL, an internal 32K
+block on the machine stack is used.
+.P
+If \fIcallback\fP is NULL and \fIcallback_data\fP is not NULL,
+\fIcallback_data\fP must be a valid JIT stack, the result of calling
+\fBpcre2_jit_stack_create()\fP.
+.P
+If \fIcallback\fP not NULL, it is called with \fIcallback_data\fP as an
+argument at the start of matching, in order to set up a JIT stack. If the
+result is NULL, the internal 32K stack is used; otherwise the return value must
+be a valid JIT stack, the result of calling \fBpcre2_jit_stack_create()\fP.
+.P
+You may safely use the same JIT stack for multiple patterns, as long as they
+are all matched in the same thread. In a multithread application, each thread
+must use its own JIT stack. For more details, see the
+.\" HREF
+\fBpcre2jit\fP
+.\"
+page.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_jit_stack_create.3 b/pcre2-10.20/doc/pcre2_jit_stack_create.3
new file mode 100644
index 000000000..d530d5067
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_jit_stack_create.3
@@ -0,0 +1,40 @@
+.TH PCRE2_JIT_STACK_CREATE 3 "03 November 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE \fIstartsize\fP,
+.B "  PCRE2_SIZE \fImaxsize\fP, pcre2_general_context *\fIgcontext\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function is used to create a stack for use by the code compiled by the JIT
+compiler. The first two arguments are a starting size for the stack, and a
+maximum size to which it is allowed to grow. The final argument is a general
+context, for memory allocation functions, or NULL for standard memory
+allocation. The result can be passed to the JIT run-time code by calling
+\fBpcre2_jit_stack_assign()\fP to associate the stack with a compiled pattern,
+which can then be processed by \fBpcre2_match()\fP. If the "fast path" JIT
+matcher, \fBpcre2_jit_match()\fP is used, the stack can be passed directly as
+an argument. A maximum stack size of 512K to 1M should be more than enough for
+any pattern. For more details, see the
+.\" HREF
+\fBpcre2jit\fP
+.\"
+page.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_jit_stack_free.3 b/pcre2-10.20/doc/pcre2_jit_stack_free.3
new file mode 100644
index 000000000..bfa4f797c
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_jit_stack_free.3
@@ -0,0 +1,31 @@
+.TH PCRE2_JIT_STACK_FREE 3 "21 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.SM
+.B void pcre2_jit_stack_free(pcre2_jit_stack *\fIjit_stack\fP);
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function is used to free a JIT stack that was created by
+\fBpcre2_jit_stack_create()\fP when it is no longer needed. For more details,
+see the
+.\" HREF
+\fBpcre2jit\fP
+.\"
+page.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_maketables.3 b/pcre2-10.20/doc/pcre2_maketables.3
new file mode 100644
index 000000000..322dba7d8
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_maketables.3
@@ -0,0 +1,36 @@
+.TH PCRE2_MAKETABLES 3 "21 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.SM
+.B const unsigned char *pcre2_maketables(pcre22_general_context *\fIgcontext\fP);
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function builds a set of character tables for character values less than
+256. These can be passed to \fBpcre2_compile()\fP in a compile context in order
+to override the internal, built-in tables (which were either defaulted or made
+by \fBpcre2_maketables()\fP when PCRE2 was compiled). See the
+.\" HREF
+\fBpcre2_set_character_tables()\fP
+.\"
+page. You might want to do this if you are using a non-standard locale.
+.P
+If the argument is NULL, \fBmalloc()\fP is used to get memory for the tables.
+Otherwise it must point to a general context, which can supply pointers to a
+custom memory manager. The function yields a pointer to the tables.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_match.3 b/pcre2-10.20/doc/pcre2_match.3
new file mode 100644
index 000000000..f25cacedf
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_match.3
@@ -0,0 +1,67 @@
+.TH PCRE2_MATCH 3 "21 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_match(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
+.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
+.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
+.B "  pcre2_match_context *\fImcontext\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function matches a compiled regular expression against a given subject
+string, using a matching algorithm that is similar to Perl's. It returns
+offsets to captured substrings. Its arguments are:
+.sp
+  \fIcode\fP         Points to the compiled pattern
+  \fIsubject\fP      Points to the subject string
+  \fIlength\fP       Length of the subject string
+  \fIstartoffset\fP  Offset in the subject at which to start matching
+  \fIoptions\fP      Option bits
+  \fImatch_data\fP   Points to a match data block, for results
+  \fImcontext\fP     Points to a match context, or is NULL
+.sp
+A match context is needed only if you want to:
+.sp
+  Set up a callout function
+  Change the limit for calling the internal function \fImatch()\fP
+  Change the limit for calling \fImatch()\fP recursively
+  Set custom memory management when the heap is used for recursion
+.sp
+The \fIlength\fP and \fIstartoffset\fP values are code
+units, not characters. The options are:
+.sp
+  PCRE2_ANCHORED          Match only at the first position
+  PCRE2_NOTBOL            Subject string is not the beginning of a line
+  PCRE2_NOTEOL            Subject string is not the end of a line
+  PCRE2_NOTEMPTY          An empty string is not a valid match
+  PCRE2_NOTEMPTY_ATSTART  An empty string at the start of the subject
+                           is not a valid match
+  PCRE2_NO_UTF_CHECK      Do not check the subject for UTF
+                           validity (only relevant if PCRE2_UTF
+                           was set at compile time)
+  PCRE2_PARTIAL_SOFT      Return PCRE2_ERROR_PARTIAL for a partial
+                            match if no full matches are found
+  PCRE2_PARTIAL_HARD      Return PCRE2_ERROR_PARTIAL for a partial match
+                           if that is found before a full match
+.sp
+For details of partial matching, see the
+.\" HREF
+\fBpcre2partial\fP
+.\"
+page. There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_match_context_copy.3 b/pcre2-10.20/doc/pcre2_match_context_copy.3
new file mode 100644
index 000000000..26c33a693
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_match_context_copy.3
@@ -0,0 +1,29 @@
+.TH PCRE2_MATCH_CONTEXT_COPY 3 "22 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B pcre2_match_context *pcre2_match_context_copy(
+.B "  pcre2_match_context *\fImcontext\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function makes a new copy of a match context, using the memory
+allocation function that was used for the original context. The result is NULL
+if the memory cannot be obtained.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_match_context_create.3 b/pcre2-10.20/doc/pcre2_match_context_create.3
new file mode 100644
index 000000000..d4a26653a
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_match_context_create.3
@@ -0,0 +1,30 @@
+.TH PCRE2_MATCH_CONTEXT_CREATE 3 "22 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B pcre2_match_context *pcre2_match_context_create(
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function creates and initializes a new match context. If its argument is
+NULL, \fBmalloc()\fP is used to get the necessary memory; otherwise the memory
+allocation function within the general context is used. The result is NULL if
+the memory could not be obtained.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_match_context_free.3 b/pcre2-10.20/doc/pcre2_match_context_free.3
new file mode 100644
index 000000000..71b97837f
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_match_context_free.3
@@ -0,0 +1,28 @@
+.TH PCRE2_MATCH_CONTEXT_FREE 3 "22 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B void pcre2_match_context_free(pcre2_match_context *\fImcontext\fP);
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function frees the memory occupied by a match context, using the memory
+freeing function from the general context with which it was created, or
+\fBfree()\fP if that was not set.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_match_data_create.3 b/pcre2-10.20/doc/pcre2_match_data_create.3
new file mode 100644
index 000000000..2a92f0bcb
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_match_data_create.3
@@ -0,0 +1,36 @@
+.TH PCRE2_MATCH_DATA_CREATE 3 "22 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B pcre2_match_data_create(uint32_t \fIovecsize\fP,
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function creates a new match data block, which is used for holding the
+result of a match. The first argument specifies the number of pairs of offsets
+that are required. These form the "output vector" (ovector) within the match
+data block, and are used to identify the matched string and any captured
+substrings. There is always one pair of offsets; if \fBovecsize\fP is zero, it
+is treated as one.
+.P
+The second argument points to a general context, for custom memory management,
+or is NULL for system memory management. The result of the function is NULL if
+the memory for the block could not be obtained.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_match_data_create_from_pattern.3 b/pcre2-10.20/doc/pcre2_match_data_create_from_pattern.3
new file mode 100644
index 000000000..83267d6f7
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_match_data_create_from_pattern.3
@@ -0,0 +1,37 @@
+.TH PCRE2_MATCH_DATA_CREATE_FROM_PATTERN 3 "24 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B pcre2_match_data_create_from_pattern(const pcre2_code *\fIcode\fP,
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function creates a new match data block, which is used for holding the
+result of a match. The first argument points to a compiled pattern. The number
+of capturing parentheses within the pattern is used to compute the number of
+pairs of offsets that are required in the match data block. These form the
+"output vector" (ovector) within the match data block, and are used to identify
+the matched string and any captured substrings.
+.P
+The second argument points to a general context, for custom memory management,
+or is NULL to use the same memory allocator as was used for the compiled
+pattern. The result of the function is NULL if the memory for the block could
+not be obtained.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_match_data_free.3 b/pcre2-10.20/doc/pcre2_match_data_free.3
new file mode 100644
index 000000000..5e4bc6275
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_match_data_free.3
@@ -0,0 +1,28 @@
+.TH PCRE2_MATCH_DATA_FREE 3 "24 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B void pcre2_match_data_free(pcre2_match_data *\fImatch_data\fP);
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function frees the memory occupied by a match data block, using the memory
+freeing function from the general context with which it was created, or
+\fBfree()\fP if that was not set.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_pattern_info.3 b/pcre2-10.20/doc/pcre2_pattern_info.3
new file mode 100644
index 000000000..8424e6f58
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_pattern_info.3
@@ -0,0 +1,93 @@
+.TH PCRE2_PATTERN_INFO 3 "01 December 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_pattern_info(const pcre2 *\fIcode\fP, uint32_t \fIwhat\fP, void *\fIwhere\fP);
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function returns information about a compiled pattern. Its arguments are:
+.sp
+  \fIcode\fP     Pointer to a compiled regular expression
+  \fIwhat\fP     What information is required
+  \fIwhere\fP    Where to put the information
+.sp
+The recognized values for the \fIwhat\fP argument, and the information they
+request are as follows:
+.sp
+  PCRE2_INFO_ALLOPTIONS      Final options after compiling
+  PCRE2_INFO_ARGOPTIONS      Options passed to \fBpcre2_compile()\fP
+  PCRE2_INFO_BACKREFMAX      Number of highest back reference
+  PCRE2_INFO_BSR             What \eR matches:
+                               PCRE2_BSR_UNICODE: Unicode line endings
+                               PCRE2_BSR_ANYCRLF: CR, LF, or CRLF only
+  PCRE2_INFO_CAPTURECOUNT    Number of capturing subpatterns
+  PCRE2_INFO_FIRSTBITMAP     Bitmap of first code units, or NULL
+  PCRE2_INFO_FIRSTCODEUNIT   First code unit when type is 1
+  PCRE2_INFO_FIRSTCODETYPE   Type of start-of-match information
+                               0 nothing set
+                               1 first code unit is set
+                               2 start of string or after newline
+  PCRE2_INFO_HASCRORLF       Return 1 if explicit CR or LF matches
+                               exist in the pattern
+  PCRE2_INFO_JCHANGED        Return 1 if (?J) or (?-J) was used
+  PCRE2_INFO_JITSIZE         Size of JIT compiled code, or 0
+  PCRE2_INFO_LASTCODEUNIT    Last code unit when type is 1
+  PCRE2_INFO_LASTCODETYPE    Type of must-be-present information
+                               0 nothing set
+                               1 code unit is set
+  PCRE2_INFO_MATCHEMPTY      1 if the pattern can match an
+                               empty string, 0 otherwise
+  PCRE2_INFO_MATCHLIMIT      Match limit if set,
+                               otherwise PCRE2_ERROR_UNSET
+  PCRE2_INFO_MAXLOOKBEHIND   Length (in characters) of the longest
+                               lookbehind assertion
+  PCRE2_INFO_MINLENGTH       Lower bound length of matching strings
+  PCRE2_INFO_NAMEENTRYSIZE   Size of name table entries
+  PCRE2_INFO_NAMECOUNT       Number of named subpatterns
+  PCRE2_INFO_NAMETABLE       Pointer to name table
+  PCRE2_CONFIG_NEWLINE       Code for the newline sequence:
+                               PCRE2_NEWLINE_CR
+                               PCRE2_NEWLINE_LF
+                               PCRE2_NEWLINE_CRLF
+                               PCRE2_NEWLINE_ANY
+                               PCRE2_NEWLINE_ANYCRLF
+  PCRE2_INFO_RECURSIONLIMIT  Recursion limit if set,
+                               otherwise PCRE2_ERROR_UNSET
+  PCRE2_INFO_SIZE            Size of compiled pattern
+.sp
+If \fIwhere\fP is NULL, the function returns the amount of memory needed for
+the requested information, in bytes. Otherwise, the \fIwhere\fP argument must
+point to an unsigned 32-bit integer (uint32_t variable), except for the
+following \fIwhat\fP values, when it must point to a variable of the type
+shown:
+.sp
+  PCRE2_INFO_FIRSTBITMAP     const uint8_t *
+  PCRE2_INFO_JITSIZE         size_t
+  PCRE2_INFO_NAMETABLE       PCRE2_SPTR
+  PCRE2_INFO_SIZE            size_t
+.sp
+The yield of the function is zero on success or:
+.sp
+  PCRE2_ERROR_NULL           the argument \fIcode\fP is NULL
+  PCRE2_ERROR_BADMAGIC       the "magic number" was not found
+  PCRE2_ERROR_BADOPTION      the value of \fIwhat\fP is invalid
+  PCRE2_ERROR_BADMODE        the pattern was compiled in the wrong mode
+  PCRE2_ERROR_UNSET          the requested information is not set
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_serialize_decode.3 b/pcre2-10.20/doc/pcre2_serialize_decode.3
new file mode 100644
index 000000000..b362fcdff
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_serialize_decode.3
@@ -0,0 +1,50 @@
+.TH PCRE2_SERIALIZE_DECODE 3 "19 January 2015" "PCRE2 10.10"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int32_t pcre2_serialize_decode(pcre2_code **\fIcodes\fP,
+.B "  int32_t \fInumber_of_codes\fP, const uint32_t *\fIbytes\fP,"
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function decodes a serialized set of compiled patterns back into a list of
+individual patterns. Its arguments are:
+.sp
+  \fIcodes\fP            pointer to a vector in which to build the list
+  \fInumber_of_codes\fP  number of slots in the vector
+  \fIbytes\fP            the serialized byte stream
+  \fIgcontext\fP         pointer to a general context or NULL
+.sp
+The \fIbytes\fP argument must point to a block of data that was originally
+created by \fBpcre2_serialize_encode()\fP, though it may have been saved on
+disc or elsewhere in the meantime. If there are more codes in the serialized
+data than slots in the list, only those compiled patterns that will fit are
+decoded. The yield of the function is the number of decoded patterns, or one of
+the following negative error codes:
+.sp
+  PCRE2_ERROR_BADDATA   \fInumber_of_codes\fP is zero or less
+  PCRE2_ERROR_BADMAGIC  mismatch of id bytes in \fIbytes\fP
+  PCRE2_ERROR_BADMODE   mismatch of variable unit size or PCRE version
+  PCRE2_ERROR_MEMORY    memory allocation failed
+  PCRE2_ERROR_NULL      \fIcodes\fP or \fIbytes\fP is NULL
+.sp
+PCRE2_ERROR_BADMAGIC may mean that the data is corrupt, or that it was compiled
+on a system with different endianness.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_serialize_encode.3 b/pcre2-10.20/doc/pcre2_serialize_encode.3
new file mode 100644
index 000000000..57077eb1e
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_serialize_encode.3
@@ -0,0 +1,49 @@
+.TH PCRE2_SERIALIZE_ENCODE 3 "19 January 2015" "PCRE2 10.10"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int32_t pcre2_serialize_encode(pcre2_code **\fIcodes\fP,
+.B "  int32_t \fInumber_of_codes\fP, uint32_t **\fIserialized_bytes\fP,"
+.B "  PCRE2_SIZE *\fIserialized_size\fP, pcre2_general_context *\fIgcontext\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function encodes a list of compiled patterns into a byte stream that can
+be saved on disc or elsewhere. Its arguments are:
+.sp
+  \fIcodes\fP             pointer to a vector containing the list
+  \fInumber_of_codes\fP   number of slots in the vector
+  \fIserialized_bytes\fP  set to point to the serialized byte stream
+  \fIserialized_size\fP   set to the number of bytes in the byte stream
+  \fIgcontext\fP          pointer to a general context or NULL
+.sp
+The context argument is used to obtain memory for the byte stream. When the
+serialized data is no longer needed, it must be freed by calling
+\fBpcre2_serialize_free()\fP. The yield of the function is the number of
+serialized patterns, or one of the following negative error codes:
+.sp
+  PCRE2_ERROR_BADDATA      \fInumber_of_codes\fP is zero or less
+  PCRE2_ERROR_BADMAGIC     mismatch of id bytes in one of the patterns
+  PCRE2_ERROR_MEMORY       memory allocation failed
+  PCRE2_ERROR_MIXEDTABLES  the patterns do not all use the same tables
+  PCRE2_ERROR_NULL         an argument other than \fIgcontext\fP is NULL
+.sp
+PCRE2_ERROR_BADMAGIC means either that a pattern's code has been corrupted, or
+that a slot in the vector does not point to a compiled pattern.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_serialize_free.3 b/pcre2-10.20/doc/pcre2_serialize_free.3
new file mode 100644
index 000000000..9daa94b15
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_serialize_free.3
@@ -0,0 +1,28 @@
+.TH PCRE2_SERIALIZE_FREE 3 "19 January 2015" "PCRE2 10.10"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B void pcre2_serialize_free(uint8_t *\fIbytes\fP);
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function frees the memory that was obtained by
+\fBpcre2_serialize_encode()\fP to hold a serialized byte stream. The argument
+must point to such a byte stream.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_serialize_get_number_of_codes.3 b/pcre2-10.20/doc/pcre2_serialize_get_number_of_codes.3
new file mode 100644
index 000000000..d8ce6a167
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_serialize_get_number_of_codes.3
@@ -0,0 +1,37 @@
+.TH PCRE2_SERIALIZE_GET_NUMBER_OF_CODES 3 "19 January 2015" "PCRE2 10.10"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int32_t pcre2_serialize_get_number_of_codes(const uint8_t *\fIbytes\fP);
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+The \fIbytes\fP argument must point to a serialized byte stream that was
+originally created by \fBpcre2_serialize_encode()\fP (though it may have been
+saved on disc or elsewhere in the meantime). The function returns the number of
+serialized patterns in the byte stream, or one of the following negative error
+codes:
+.sp
+  PCRE2_ERROR_BADMAGIC  mismatch of id bytes in \fIbytes\fP
+  PCRE2_ERROR_BADMODE   mismatch of variable unit size or PCRE version
+  PCRE2_ERROR_NULL      the argument is NULL
+.sp
+PCRE2_ERROR_BADMAGIC may mean that the data is corrupt, or that it was compiled
+on a system with different endianness.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_set_bsr.3 b/pcre2-10.20/doc/pcre2_set_bsr.3
new file mode 100644
index 000000000..ecf2437f5
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_set_bsr.3
@@ -0,0 +1,30 @@
+.TH PCRE2_SET_BSR 3 "22 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_set_bsr(pcre2_compile_context *\fIccontext\fP,
+.B "  uint32_t \fIvalue\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function sets the convention for processing \eR within a compile context.
+The second argument must be one of PCRE2_BSR_ANYCRLF or PCRE2_BSR_UNICODE. The
+result is zero for success or PCRE2_ERROR_BADDATA if the second argument is
+invalid.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_set_callout.3 b/pcre2-10.20/doc/pcre2_set_callout.3
new file mode 100644
index 000000000..2f86f6906
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_set_callout.3
@@ -0,0 +1,31 @@
+.TH PCRE2_SET_CALLOUT 3 "24 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_set_callout(pcre2_match_context *\fImcontext\fP,
+.B "  int (*\fIcallout_function\fP)(pcre2_callout_block *),"
+.B "  void *\fIcallout_data\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function sets the callout fields in a match context (the first argument).
+The second argument specifies a callout function, and the third argument is an
+opaque data time that is passed to it. The result of this function is always
+zero.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_set_character_tables.3 b/pcre2-10.20/doc/pcre2_set_character_tables.3
new file mode 100644
index 000000000..1ede4f91b
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_set_character_tables.3
@@ -0,0 +1,30 @@
+.TH PCRE2_SET_CHARACTER_TABLES 3 "22 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_set_character_tables(pcre2_compile_context *\fIccontext\fP,
+.B "  const unsigned char *\fItables\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function sets a pointer to custom character tables within a compile
+context. The second argument must be the result of a call to
+\fBpcre2_maketables()\fP or NULL to request the default tables. The result is
+always zero.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_set_compile_recursion_guard.3 b/pcre2-10.20/doc/pcre2_set_compile_recursion_guard.3
new file mode 100644
index 000000000..0575f9409
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_set_compile_recursion_guard.3
@@ -0,0 +1,34 @@
+.TH PCRE2_SET_COMPILE_RECURSION_GUARD 3 "22 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_set_compile_recursion_guard(pcre2_compile_context *\fIccontext\fP,
+.B "  int (*\fIguard_function\fP)(uint32_t, void *), void *\fIuser_data\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function defines, within a compile context, a function that is called
+whenever \fBpcre2_compile()\fP starts to compile a parenthesized part of a
+pattern. The first argument to the function gives the current depth of
+parenthesis nesting, and the second is user data that is supplied when the
+function is set up. The callout function should return zero if all is well, or
+non-zero to force an error. This feature is provided so that applications can
+check the available system stack space, in order to avoid running out. The
+result of \fBpcre2_set_compile_recursion_guard()\fP is always zero.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_set_match_limit.3 b/pcre2-10.20/doc/pcre2_set_match_limit.3
new file mode 100644
index 000000000..523e97f2c
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_set_match_limit.3
@@ -0,0 +1,28 @@
+.TH PCRE2_SET_MATCH_LIMIT 3 "24 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_set_match_limit(pcre2_match_context *\fImcontext\fP,
+.B "  uint32_t \fIvalue\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function sets the match limit field in a match context. The result is
+always zero.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_set_newline.3 b/pcre2-10.20/doc/pcre2_set_newline.3
new file mode 100644
index 000000000..8237500f5
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_set_newline.3
@@ -0,0 +1,38 @@
+.TH PCRE2_SET_NEWLINE 3 "22 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_set_newline(pcre2_compile_context *\fIccontext\fP,
+.B "  uint32_t \fIvalue\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function sets the newline convention within a compile context. This
+specifies which character(s) are recognized as newlines when compiling and
+matching patterns. The second argument must be one of:
+.sp
+  PCRE2_NEWLINE_CR        Carriage return only
+  PCRE2_NEWLINE_LF        Linefeed only
+  PCRE2_NEWLINE_CRLF      CR followed by LF only
+  PCRE2_NEWLINE_ANYCRLF   Any of the above
+  PCRE2_NEWLINE_ANY       Any Unicode newline sequence
+.sp
+The result is zero for success or PCRE2_ERROR_BADDATA if the second argument is
+invalid.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_set_parens_nest_limit.3 b/pcre2-10.20/doc/pcre2_set_parens_nest_limit.3
new file mode 100644
index 000000000..03676193d
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_set_parens_nest_limit.3
@@ -0,0 +1,28 @@
+.TH PCRE2_SET_PARENS_NEST_LIMIT 3 "22 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_set_parens_nest_limit(pcre2_compile_context *\fIccontext\fP,
+.B "  uint32_t \fIvalue\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function sets, in a compile context, the maximum depth of nested
+parentheses in a pattern. The result is always zero.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_set_recursion_limit.3 b/pcre2-10.20/doc/pcre2_set_recursion_limit.3
new file mode 100644
index 000000000..ab1f3cda0
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_set_recursion_limit.3
@@ -0,0 +1,28 @@
+.TH PCRE2_SET_RECURSION_LIMIT 3 "24 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_set_recursion_limit(pcre2_match_context *\fImcontext\fP,
+.B "  uint32_t \fIvalue\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function sets the recursion limit field in a match context. The result is
+always zero.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_set_recursion_memory_management.3 b/pcre2-10.20/doc/pcre2_set_recursion_memory_management.3
new file mode 100644
index 000000000..9b5887a9a
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_set_recursion_memory_management.3
@@ -0,0 +1,35 @@
+.TH PCRE2_SET_RECURSION_MEMORY_MANAGEMENT 3 "24 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_set_recursion_memory_management(
+.B "  pcre2_match_context *\fImcontext\fP,"
+.B "  void *(*\fIprivate_malloc\fP)(PCRE2_SIZE, void *),"
+.B "  void (*\fIprivate_free\fP)(void *, void *), void *\fImemory_data\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function sets the match context fields for custom memory management when
+PCRE2 is compiled to use the heap instead of the system stack for recursive
+function calls while matching. When PCRE2 is compiled to use the stack (the
+default) this function does nothing. The first argument is a match context, the
+second and third specify the memory allocation and freeing functions, and the
+final argument is an opaque value that is passed to them whenever they are
+called. The result of this function is always zero.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_substitute.3 b/pcre2-10.20/doc/pcre2_substitute.3
new file mode 100644
index 000000000..edfcb0432
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_substitute.3
@@ -0,0 +1,73 @@
+.TH PCRE2_SUBSTITUTE 3 "11 November 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_substitute(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
+.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
+.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
+.B "  pcre2_match_context *\fImcontext\fP, PCRE2_SPTR \fIreplacement\fP,"
+.B "  PCRE2_SIZE \fIrlength\fP, PCRE2_UCHAR *\fIoutputbuffer\fP,"
+.B "  PCRE2_SIZE *\fIoutlengthptr\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function matches a compiled regular expression against a given subject
+string, using a matching algorithm that is similar to Perl's. It then makes a
+copy of the subject, substituting a replacement string for what was matched.
+Its arguments are:
+.sp
+  \fIcode\fP          Points to the compiled pattern
+  \fIsubject\fP       Points to the subject string
+  \fIlength\fP        Length of the subject string
+  \fIstartoffset\fP   Offset in the subject at which to start matching
+  \fIoptions\fP       Option bits
+  \fImatch_data\fP    Points to a match data block, or is NULL
+  \fImcontext\fP      Points to a match context, or is NULL
+  \fIreplacement\fP   Points to the replacement string
+  \fIrlength\fP       Length of the replacement string
+  \fIoutputbuffer\fP  Points to the output buffer
+  \fIoutlengthptr\fP  Points to the length of the output buffer
+.sp
+A match context is needed only if you want to:
+.sp
+  Set up a callout function
+  Change the limit for calling the internal function \fImatch()\fP
+  Change the limit for calling \fImatch()\fP recursively
+  Set custom memory management when the heap is used for recursion
+.sp
+The \fIlength\fP, \fIstartoffset\fP and \fIrlength\fP values are code
+units, not characters, as is the contents of the variable pointed at by
+\fIoutlengthptr\fP, which is updated to the actual length of the new string.
+The options are:
+.sp
+  PCRE2_ANCHORED          Match only at the first position
+  PCRE2_NOTBOL            Subject string is not the beginning of a line
+  PCRE2_NOTEOL            Subject string is not the end of a line
+  PCRE2_NOTEMPTY          An empty string is not a valid match
+  PCRE2_NOTEMPTY_ATSTART  An empty string at the start of the subject
+                           is not a valid match
+  PCRE2_NO_UTF_CHECK      Do not check the subject or replacement for
+                           UTF validity (only relevant if PCRE2_UTF
+                           was set at compile time)
+  PCRE2_SUBSTITUTE_GLOBAL Replace all occurrences in the subject
+.sp
+The function returns the number of substitutions, which may be zero if there
+were no matches. The result can be greater than one only when
+PCRE2_SUBSTITUTE_GLOBAL is set.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_substring_copy_byname.3 b/pcre2-10.20/doc/pcre2_substring_copy_byname.3
new file mode 100644
index 000000000..d2af63bf7
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_substring_copy_byname.3
@@ -0,0 +1,46 @@
+.TH PCRE2_SUBSTRING_COPY_BYNAME 3 "21 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_substring_copy_byname(pcre2_match_data *\fImatch_data\fP,
+.B "  PCRE2_SPTR \fIname\fP, PCRE2_UCHAR *\fIbuffer\fP, PCRE2_SIZE *\fIbufflen\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This is a convenience function for extracting a captured substring, identified
+by name, into a given buffer. The arguments are:
+.sp
+  \fImatch_data\fP    The match data block for the match
+  \fIname\fP          Name of the required substring
+  \fIbuffer\fP        Buffer to receive the string
+  \fIbufflen\fP       Length of buffer (code units)
+.sp
+The \fIbufflen\fP variable is updated to contain the length of the extracted
+string, excluding the trailing zero. The yield of the function is zero for
+success or one of the following error numbers:
+.sp
+  PCRE2_ERROR_NOSUBSTRING   there are no groups of that name
+  PCRE2_ERROR_UNAVAILBLE    the ovector was too small for that group
+  PCRE2_ERROR_UNSET         the group did not participate in the match
+  PCRE2_ERROR_NOMEMORY      the buffer is not big enough
+.sp
+If there is more than one group with the given name, the first one that is set
+is returned. In this situation PCRE2_ERROR_UNSET means that no group with the
+given name was set.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_substring_copy_bynumber.3 b/pcre2-10.20/doc/pcre2_substring_copy_bynumber.3
new file mode 100644
index 000000000..4cee2b423
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_substring_copy_bynumber.3
@@ -0,0 +1,44 @@
+.TH PCRE2_SUBSTRING_COPY_BYNUMBER 3 "13 December 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_substring_copy_bynumber(pcre2_match_data *\fImatch_data\fP,
+.B "  uint32_t \fInumber\fP, PCRE2_UCHAR *\fIbuffer\fP,"
+.B "  PCRE2_SIZE *\fIbufflen\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This is a convenience function for extracting a captured substring into a given
+buffer. The arguments are:
+.sp
+  \fImatch_data\fP    The match data block for the match
+  \fInumber\fP        Number of the required substring
+  \fIbuffer\fP        Buffer to receive the string
+  \fIbufflen\fP       Length of buffer
+.sp
+The \fIbufflen\fP variable is updated with the length of the extracted string,
+excluding the terminating zero. The yield of the function is zero for success
+or one of the following error numbers:
+.sp
+  PCRE2_ERROR_NOSUBSTRING   there are no groups of that number
+  PCRE2_ERROR_UNAVAILBLE    the ovector was too small for that group
+  PCRE2_ERROR_UNSET         the group did not participate in the match
+  PCRE2_ERROR_NOMEMORY      the buffer is too small
+.sp
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_substring_free.3 b/pcre2-10.20/doc/pcre2_substring_free.3
new file mode 100644
index 000000000..ca94e7860
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_substring_free.3
@@ -0,0 +1,28 @@
+.TH PCRE2_SUBSTRING_FREE 3 "21 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.SM
+.B void pcre2_substring_free(PCRE2_UCHAR *\fIbuffer\fP);
+.
+.SH DESCRIPTION
+.rs
+.sp
+This is a convenience function for freeing the memory obtained by a previous
+call to \fBpcre2_substring_get_byname()\fP or
+\fBpcre2_substring_get_bynumber()\fP. Its only argument is a pointer to the
+string.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_substring_get_byname.3 b/pcre2-10.20/doc/pcre2_substring_get_byname.3
new file mode 100644
index 000000000..6c3f7d571
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_substring_get_byname.3
@@ -0,0 +1,48 @@
+.TH PCRE2_SUBSTRING_GET_BYNAME 3 "21 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_substring_get_byname(pcre2_match_data *\fImatch_data\fP,
+.B "  PCRE2_SPTR \fIname\fP, PCRE2_UCHAR **\fIbufferptr\fP, PCRE2_SIZE *\fIbufflen\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This is a convenience function for extracting a captured substring by name into
+newly acquired memory. The arguments are:
+.sp
+  \fImatch_data\fP    The match data for the match
+  \fIname\fP          Name of the required substring
+  \fIbufferptr\fP     Where to put the string pointer
+  \fIbufflen\fP       Where to put the string length
+.sp
+The memory in which the substring is placed is obtained by calling the same
+memory allocation function that was used for the match data block. The
+convenience function \fBpcre2_substring_free()\fP can be used to free it when
+it is no longer needed. The yield of the function is zero for success or one of
+the following error numbers:
+.sp
+  PCRE2_ERROR_NOSUBSTRING   there are no groups of that name
+  PCRE2_ERROR_UNAVAILBLE    the ovector was too small for that group
+  PCRE2_ERROR_UNSET         the group did not participate in the match
+  PCRE2_ERROR_NOMEMORY      memory could not be obtained
+.sp
+If there is more than one group with the given name, the first one that is set
+is returned. In this situation PCRE2_ERROR_UNSET means that no group with the
+given name was set.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_substring_get_bynumber.3 b/pcre2-10.20/doc/pcre2_substring_get_bynumber.3
new file mode 100644
index 000000000..51b6a0493
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_substring_get_bynumber.3
@@ -0,0 +1,45 @@
+.TH PCRE2_SUBSTRING_GET_BYNUMBER 3 "13 December 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_substring_get_bynumber(pcre2_match_data *\fImatch_data\fP,
+.B "  uint32_t \fInumber\fP, PCRE2_UCHAR **\fIbufferptr\fP, PCRE2_SIZE *\fIbufflen\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This is a convenience function for extracting a captured substring by number
+into newly acquired memory. The arguments are:
+.sp
+  \fImatch_data\fP    The match data for the match
+  \fInumber\fP        Number of the required substring
+  \fIbufferptr\fP     Where to put the string pointer
+  \fIbufflen\fP       Where to put the string length
+.sp
+The memory in which the substring is placed is obtained by calling the same
+memory allocation function that was used for the match data block. The
+convenience function \fBpcre2_substring_free()\fP can be used to free it when
+it is no longer needed. The yield of the function is zero for success or one of
+the following error numbers:
+.sp
+  PCRE2_ERROR_NOSUBSTRING   there are no groups of that number
+  PCRE2_ERROR_UNAVAILBLE    the ovector was too small for that group
+  PCRE2_ERROR_UNSET         the group did not participate in the match
+  PCRE2_ERROR_NOMEMORY      memory could not be obtained
+.sp
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_substring_length_byname.3 b/pcre2-10.20/doc/pcre2_substring_length_byname.3
new file mode 100644
index 000000000..84cdc6a58
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_substring_length_byname.3
@@ -0,0 +1,34 @@
+.TH PCRE2_SUBSTRING_LENGTH_BYNAME 3 "21 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_substring_length_byname(pcre2_match_data *\fImatch_data\fP,
+.B "  PCRE2_SPTR \fIname\fP, PCRE2_SIZE *\fIlength\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function returns the length of a matched substring, identified by name.
+The arguments are:
+.sp
+  \fImatch_data\fP   The match data block for the match
+  \fIname\fP         The substring name
+  \fIlength\fP       Where to return the length
+.sp
+The yield is zero on success, or an error code if the substring is not found.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_substring_length_bynumber.3 b/pcre2-10.20/doc/pcre2_substring_length_bynumber.3
new file mode 100644
index 000000000..12778d618
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_substring_length_bynumber.3
@@ -0,0 +1,36 @@
+.TH PCRE2_SUBSTRING_LENGTH_BYNUMBER 3 "22 December 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_substring_length_bynumber(pcre2_match_data *\fImatch_data\fP,
+.B "  uint32_t \fInumber\fP, PCRE2_SIZE *\fIlength\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function returns the length of a matched substring, identified by number.
+The arguments are:
+.sp
+  \fImatch_data\fP   The match data block for the match
+  \fInumber\fP       The substring number
+  \fIlength\fP       Where to return the length, or NULL
+.sp
+The third argument may be NULL if all you want to know is whether or not a
+substring is set. The yield is zero on success, or a negative error code
+otherwise. After a partial match, only substring 0 is available.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_substring_list_free.3 b/pcre2-10.20/doc/pcre2_substring_list_free.3
new file mode 100644
index 000000000..4725f9c00
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_substring_list_free.3
@@ -0,0 +1,27 @@
+.TH PCRE2_SUBSTRING_LIST_FREE 3 "21 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.SM
+.B void pcre2_substring_list_free(PCRE2_SPTR *\fIlist\fP);
+.
+.SH DESCRIPTION
+.rs
+.sp
+This is a convenience function for freeing the store obtained by a previous
+call to \fBpcre2substring_list_get()\fP. Its only argument is a pointer to
+the list of string pointers.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_substring_list_get.3 b/pcre2-10.20/doc/pcre2_substring_list_get.3
new file mode 100644
index 000000000..bdc400eca
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_substring_list_get.3
@@ -0,0 +1,44 @@
+.TH PCRE2_SUBSTRING_LIST_GET 3 "21 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_substring_list_get(pcre2_match_data *\fImatch_data\fP,
+.B "  PCRE2_UCHAR ***\fIlistptr\fP, PCRE2_SIZE **\fIlengthsptr\fP);
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This is a convenience function for extracting all the captured substrings after
+a pattern match. It builds a list of pointers to the strings, and (optionally)
+a second list that contains their lengths (in code units), excluding a
+terminating zero that is added to each of them. All this is done in a single
+block of memory that is obtained using the same memory allocation function that
+was used to get the match data block. The convenience function
+\fBpcre2_substring_list_free()\fP can be used to free it when it is no longer
+needed. The arguments are:
+.sp
+  \fImatch_data\fP    The match data block
+  \fIlistptr\fP       Where to put a pointer to the list
+  \fIlengthsptr\fP    Where to put a pointer to the lengths, or NULL
+.sp
+A pointer to a list of pointers is put in the variable whose address is in
+\fIlistptr\fP. The list is terminated by a NULL pointer. If \fIlengthsptr\fP is
+not NULL, a matching list of lengths is created, and its address is placed in
+\fIlengthsptr\fP. The yield of the function is zero on success or
+PCRE2_ERROR_NOMEMORY if sufficient memory could not be obtained.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_substring_nametable_scan.3 b/pcre2-10.20/doc/pcre2_substring_nametable_scan.3
new file mode 100644
index 000000000..4342f9887
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_substring_nametable_scan.3
@@ -0,0 +1,41 @@
+.TH PCRE2_SUBSTRING_NAMETABLE_SCAN 3 "21 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_substring_nametable_scan(const pcre2_code *\fIcode\fP,
+.B "  PCRE2_SPTR \fIname\fP, PCRE2_SPTR *\fIfirst\fP, PCRE2_SPTR *\fIlast\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This convenience function finds, for a compiled pattern, the first and last
+entries for a given name in the table that translates capturing parenthesis
+names into numbers.
+.sp
+  \fIcode\fP    Compiled regular expression
+  \fIname\fP    Name whose entries required
+  \fIfirst\fP   Where to return a pointer to the first entry
+  \fIlast\fP    Where to return a pointer to the last entry
+.sp
+When the name is found in the table, if \fIfirst\fP is NULL, the function
+returns a group number, but if there is more than one matching entry, it is not
+defined which one. Otherwise, when both pointers have been set, the yield of
+the function is the length of each entry in code units. If the name is not
+found, PCRE2_ERROR_NOSUBSTRING is returned.
+.P
+There is a complete description of the PCRE2 native API, including the format of
+the table entries, in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page, and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2_substring_number_from_name.3 b/pcre2-10.20/doc/pcre2_substring_number_from_name.3
new file mode 100644
index 000000000..b077b1d2f
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2_substring_number_from_name.3
@@ -0,0 +1,38 @@
+.TH PCRE2_SUBSTRING_NUMBER_FROM_NAME 3 "21 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_substring_number_from_name(const pcre2_code *\fIcode\fP,
+.B "  PCRE2_SPTR \fIname\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This convenience function finds the number of a named substring capturing
+parenthesis in a compiled pattern, provided that it is a unique name. The
+function arguments are:
+.sp
+  \fIcode\fP    Compiled regular expression
+  \fIname\fP    Name whose number is required
+.sp
+The yield of the function is the number of the parenthesis if the name is
+found, or PCRE2_ERROR_NOSUBSTRING if it is not found. When duplicate names are
+allowed (PCRE2_DUPNAMES is set), if the name is not unique,
+PCRE2_ERROR_NOUNIQUESUBSTRING is returned. You can obtain the list of numbers
+with the same name by calling \fBpcre2_substring_nametable_scan()\fP.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2-10.20/doc/pcre2api.3 b/pcre2-10.20/doc/pcre2api.3
new file mode 100644
index 000000000..1147f89d4
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2api.3
@@ -0,0 +1,2944 @@
+.TH PCRE2API 3 "22 April 2015" "PCRE2 10.20"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.sp
+.B #include 
+.sp
+PCRE2 is a new API for PCRE. This document contains a description of all its
+functions. See the
+.\" HREF
+\fBpcre2\fP
+.\"
+document for an overview of all the PCRE2 documentation.
+.
+.
+.SH "PCRE2 NATIVE API BASIC FUNCTIONS"
+.rs
+.sp
+.nf
+.B pcre2_code *pcre2_compile(PCRE2_SPTR \fIpattern\fP, PCRE2_SIZE \fIlength\fP,
+.B "  uint32_t \fIoptions\fP, int *\fIerrorcode\fP, PCRE2_SIZE *\fIerroroffset,\fP"
+.B "  pcre2_compile_context *\fIccontext\fP);"
+.sp
+.B pcre2_code_free(pcre2_code *\fIcode\fP);
+.sp
+.B pcre2_match_data_create(uint32_t \fIovecsize\fP,
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.sp
+.B pcre2_match_data_create_from_pattern(const pcre2_code *\fIcode\fP,
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.sp
+.B int pcre2_match(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
+.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
+.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
+.B "  pcre2_match_context *\fImcontext\fP);"
+.sp
+.B int pcre2_dfa_match(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
+.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
+.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
+.B "  pcre2_match_context *\fImcontext\fP,"
+.B "  int *\fIworkspace\fP, PCRE2_SIZE \fIwscount\fP);"
+.sp
+.B void pcre2_match_data_free(pcre2_match_data *\fImatch_data\fP);
+.fi
+.
+.
+.SH "PCRE2 NATIVE API AUXILIARY MATCH FUNCTIONS"
+.rs
+.sp
+.nf
+.B PCRE2_SPTR pcre2_get_mark(pcre2_match_data *\fImatch_data\fP);
+.sp
+.B uint32_t pcre2_get_ovector_count(pcre2_match_data *\fImatch_data\fP);
+.sp
+.B PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *\fImatch_data\fP);
+.sp
+.B PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *\fImatch_data\fP);
+.fi
+.
+.
+.SH "PCRE2 NATIVE API GENERAL CONTEXT FUNCTIONS"
+.rs
+.sp
+.nf
+.B pcre2_general_context *pcre2_general_context_create(
+.B "  void *(*\fIprivate_malloc\fP)(PCRE2_SIZE, void *),"
+.B "  void (*\fIprivate_free\fP)(void *, void *), void *\fImemory_data\fP);"
+.sp
+.B pcre2_general_context *pcre2_general_context_copy(
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.sp
+.B void pcre2_general_context_free(pcre2_general_context *\fIgcontext\fP);
+.fi
+.
+.
+.SH "PCRE2 NATIVE API COMPILE CONTEXT FUNCTIONS"
+.rs
+.sp
+.nf
+.B pcre2_compile_context *pcre2_compile_context_create(
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.sp
+.B pcre2_compile_context *pcre2_compile_context_copy(
+.B "  pcre2_compile_context *\fIccontext\fP);"
+.sp
+.B void pcre2_compile_context_free(pcre2_compile_context *\fIccontext\fP);
+.sp
+.B int pcre2_set_bsr(pcre2_compile_context *\fIccontext\fP,
+.B "  uint32_t \fIvalue\fP);"
+.sp
+.B int pcre2_set_character_tables(pcre2_compile_context *\fIccontext\fP,
+.B "  const unsigned char *\fItables\fP);"
+.sp
+.B int pcre2_set_newline(pcre2_compile_context *\fIccontext\fP,
+.B "  uint32_t \fIvalue\fP);"
+.sp
+.B int pcre2_set_parens_nest_limit(pcre2_compile_context *\fIccontext\fP,
+.B "  uint32_t \fIvalue\fP);"
+.sp
+.B int pcre2_set_compile_recursion_guard(pcre2_compile_context *\fIccontext\fP,
+.B "  int (*\fIguard_function\fP)(uint32_t, void *), void *\fIuser_data\fP);"
+.fi
+.
+.
+.SH "PCRE2 NATIVE API MATCH CONTEXT FUNCTIONS"
+.rs
+.sp
+.nf
+.B pcre2_match_context *pcre2_match_context_create(
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.sp
+.B pcre2_match_context *pcre2_match_context_copy(
+.B "  pcre2_match_context *\fImcontext\fP);"
+.sp
+.B void pcre2_match_context_free(pcre2_match_context *\fImcontext\fP);
+.sp
+.B int pcre2_set_callout(pcre2_match_context *\fImcontext\fP,
+.B "  int (*\fIcallout_function\fP)(pcre2_callout_block *, void *),"
+.B "  void *\fIcallout_data\fP);"
+.sp
+.B int pcre2_set_match_limit(pcre2_match_context *\fImcontext\fP,
+.B "  uint32_t \fIvalue\fP);"
+.sp
+.B int pcre2_set_recursion_limit(pcre2_match_context *\fImcontext\fP,
+.B "  uint32_t \fIvalue\fP);"
+.sp
+.B int pcre2_set_recursion_memory_management(
+.B "  pcre2_match_context *\fImcontext\fP,"
+.B "  void *(*\fIprivate_malloc\fP)(PCRE2_SIZE, void *),"
+.B "  void (*\fIprivate_free\fP)(void *, void *), void *\fImemory_data\fP);"
+.fi
+.
+.
+.SH "PCRE2 NATIVE API STRING EXTRACTION FUNCTIONS"
+.rs
+.sp
+.nf
+.B int pcre2_substring_copy_byname(pcre2_match_data *\fImatch_data\fP,
+.B "  PCRE2_SPTR \fIname\fP, PCRE2_UCHAR *\fIbuffer\fP, PCRE2_SIZE *\fIbufflen\fP);"
+.sp
+.B int pcre2_substring_copy_bynumber(pcre2_match_data *\fImatch_data\fP,
+.B "  uint32_t \fInumber\fP, PCRE2_UCHAR *\fIbuffer\fP,"
+.B "  PCRE2_SIZE *\fIbufflen\fP);"
+.sp
+.B void pcre2_substring_free(PCRE2_UCHAR *\fIbuffer\fP);
+.sp
+.B int pcre2_substring_get_byname(pcre2_match_data *\fImatch_data\fP,
+.B "  PCRE2_SPTR \fIname\fP, PCRE2_UCHAR **\fIbufferptr\fP, PCRE2_SIZE *\fIbufflen\fP);"
+.sp
+.B int pcre2_substring_get_bynumber(pcre2_match_data *\fImatch_data\fP,
+.B "  uint32_t \fInumber\fP, PCRE2_UCHAR **\fIbufferptr\fP,"
+.B "  PCRE2_SIZE *\fIbufflen\fP);"
+.sp
+.B int pcre2_substring_length_byname(pcre2_match_data *\fImatch_data\fP,
+.B "  PCRE2_SPTR \fIname\fP, PCRE2_SIZE *\fIlength\fP);"
+.sp
+.B int pcre2_substring_length_bynumber(pcre2_match_data *\fImatch_data\fP,
+.B "  uint32_t \fInumber\fP, PCRE2_SIZE *\fIlength\fP);"
+.sp
+.B int pcre2_substring_nametable_scan(const pcre2_code *\fIcode\fP,
+.B "  PCRE2_SPTR \fIname\fP, PCRE2_SPTR *\fIfirst\fP, PCRE2_SPTR *\fIlast\fP);"
+.sp
+.B int pcre2_substring_number_from_name(const pcre2_code *\fIcode\fP,
+.B "  PCRE2_SPTR \fIname\fP);"
+.sp
+.B void pcre2_substring_list_free(PCRE2_SPTR *\fIlist\fP);
+.sp
+.B int pcre2_substring_list_get(pcre2_match_data *\fImatch_data\fP,
+.B "  PCRE2_UCHAR ***\fIlistptr\fP, PCRE2_SIZE **\fIlengthsptr\fP);
+.fi
+.
+.
+.SH "PCRE2 NATIVE API STRING SUBSTITUTION FUNCTION"
+.rs
+.sp
+.nf
+.B int pcre2_substitute(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
+.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
+.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
+.B "  pcre2_match_context *\fImcontext\fP, PCRE2_SPTR \fIreplacementzfP,"
+.B "  PCRE2_SIZE \fIrlength\fP, PCRE2_UCHAR *\fIoutputbuffer\fP,"
+.B "  PCRE2_SIZE *\fIoutlengthptr\fP);"
+.fi
+.
+.
+.SH "PCRE2 NATIVE API JIT FUNCTIONS"
+.rs
+.sp
+.nf
+.B int pcre2_jit_compile(pcre2_code *\fIcode\fP, uint32_t \fIoptions\fP);
+.sp
+.B int pcre2_jit_match(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
+.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
+.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
+.B "  pcre2_match_context *\fImcontext\fP);"
+.sp
+.B void pcre2_jit_free_unused_memory(pcre2_general_context *\fIgcontext\fP);
+.sp
+.B pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE \fIstartsize\fP,
+.B "  PCRE2_SIZE \fImaxsize\fP, pcre2_general_context *\fIgcontext\fP);"
+.sp
+.B void pcre2_jit_stack_assign(pcre2_match_context *\fImcontext\fP,
+.B "  pcre2_jit_callback \fIcallback_function\fP, void *\fIcallback_data\fP);"
+.sp
+.B void pcre2_jit_stack_free(pcre2_jit_stack *\fIjit_stack\fP);
+.fi
+.
+.
+.SH "PCRE2 NATIVE API SERIALIZATION FUNCTIONS"
+.rs
+.sp
+.nf
+.B int32_t pcre2_serialize_decode(pcre2_code **\fIcodes\fP,
+.B "  int32_t \fInumber_of_codes\fP, const uint32_t *\fIbytes\fP,"
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.sp
+.B int32_t pcre2_serialize_encode(pcre2_code **\fIcodes\fP,
+.B "  int32_t \fInumber_of_codes\fP, uint32_t **\fIserialized_bytes\fP,"
+.B "  PCRE2_SIZE *\fIserialized_size\fP, pcre2_general_context *\fIgcontext\fP);"
+.sp
+.B void pcre2_serialize_free(uint8_t *\fIbytes\fP);
+.sp
+.B int32_t pcre2_serialize_get_number_of_codes(const uint8_t *\fIbytes\fP);
+.fi
+.
+.
+.SH "PCRE2 NATIVE API AUXILIARY FUNCTIONS"
+.rs
+.sp
+.nf
+.B int pcre2_get_error_message(int \fIerrorcode\fP, PCRE2_UCHAR *\fIbuffer\fP,
+.B "  PCRE2_SIZE \fIbufflen\fP);"
+.sp
+.B const unsigned char *pcre2_maketables(pcre2_general_context *\fIgcontext\fP);
+.sp
+.B int pcre2_pattern_info(const pcre2 *\fIcode\fP, uint32_t \fIwhat\fP, void *\fIwhere\fP);
+.sp
+.B int pcre2_callout_enumerate(const pcre2_code *\fIcode\fP,
+.B "  int (*\fIcallback\fP)(pcre2_callout_enumerate_block *, void *),"
+.B "  void *\fIuser_data\fP);"
+.sp
+.B int pcre2_config(uint32_t \fIwhat\fP, void *\fIwhere\fP);
+.fi
+.
+.
+.SH "PCRE2 8-BIT, 16-BIT, AND 32-BIT LIBRARIES"
+.rs
+.sp
+There are three PCRE2 libraries, supporting 8-bit, 16-bit, and 32-bit code
+units, respectively. However, there is just one header file, \fBpcre2.h\fP.
+This contains the function prototypes and other definitions for all three
+libraries. One, two, or all three can be installed simultaneously. On Unix-like
+systems the libraries are called \fBlibpcre2-8\fP, \fBlibpcre2-16\fP, and
+\fBlibpcre2-32\fP, and they can also co-exist with the original PCRE libraries.
+.P
+Character strings are passed to and from a PCRE2 library as a sequence of
+unsigned integers in code units of the appropriate width. Every PCRE2 function
+comes in three different forms, one for each library, for example:
+.sp
+  \fBpcre2_compile_8()\fP
+  \fBpcre2_compile_16()\fP
+  \fBpcre2_compile_32()\fP
+.sp
+There are also three different sets of data types:
+.sp
+  \fBPCRE2_UCHAR8, PCRE2_UCHAR16, PCRE2_UCHAR32\fP
+  \fBPCRE2_SPTR8,  PCRE2_SPTR16,  PCRE2_SPTR32\fP
+.sp
+The UCHAR types define unsigned code units of the appropriate widths. For
+example, PCRE2_UCHAR16 is usually defined as `uint16_t'. The SPTR types are
+constant pointers to the equivalent UCHAR types, that is, they are pointers to
+vectors of unsigned code units.
+.P
+Many applications use only one code unit width. For their convenience, macros
+are defined whose names are the generic forms such as \fBpcre2_compile()\fP and
+PCRE2_SPTR. These macros use the value of the macro PCRE2_CODE_UNIT_WIDTH to
+generate the appropriate width-specific function and macro names.
+PCRE2_CODE_UNIT_WIDTH is not defined by default. An application must define it
+to be 8, 16, or 32 before including \fBpcre2.h\fP in order to make use of the
+generic names.
+.P
+Applications that use more than one code unit width can be linked with more
+than one PCRE2 library, but must define PCRE2_CODE_UNIT_WIDTH to be 0 before
+including \fBpcre2.h\fP, and then use the real function names. Any code that is
+to be included in an environment where the value of PCRE2_CODE_UNIT_WIDTH is
+unknown should also use the real function names. (Unfortunately, it is not
+possible in C code to save and restore the value of a macro.)
+.P
+If PCRE2_CODE_UNIT_WIDTH is not defined before including \fBpcre2.h\fP, a
+compiler error occurs.
+.P
+When using multiple libraries in an application, you must take care when
+processing any particular pattern to use only functions from a single library.
+For example, if you want to run a match using a pattern that was compiled with
+\fBpcre2_compile_16()\fP, you must do so with \fBpcre2_match_16()\fP, not
+\fBpcre2_match_8()\fP.
+.P
+In the function summaries above, and in the rest of this document and other
+PCRE2 documents, functions and data types are described using their generic
+names, without the 8, 16, or 32 suffix.
+.
+.
+.SH "PCRE2 API OVERVIEW"
+.rs
+.sp
+PCRE2 has its own native API, which is described in this document. There are
+also some wrapper functions for the 8-bit library that correspond to the
+POSIX regular expression API, but they do not give access to all the
+functionality. They are described in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+documentation. Both these APIs define a set of C function calls.
+.P
+The native API C data types, function prototypes, option values, and error
+codes are defined in the header file \fBpcre2.h\fP, which contains definitions
+of PCRE2_MAJOR and PCRE2_MINOR, the major and minor release numbers for the
+library. Applications can use these to include support for different releases
+of PCRE2.
+.P
+In a Windows environment, if you want to statically link an application program
+against a non-dll PCRE2 library, you must define PCRE2_STATIC before including
+\fBpcre2.h\fP.
+.P
+The functions \fBpcre2_compile()\fP, and \fBpcre2_match()\fP are used for
+compiling and matching regular expressions in a Perl-compatible manner. A
+sample program that demonstrates the simplest way of using them is provided in
+the file called \fIpcre2demo.c\fP in the PCRE2 source distribution. A listing
+of this program is given in the
+.\" HREF
+\fBpcre2demo\fP
+.\"
+documentation, and the
+.\" HREF
+\fBpcre2sample\fP
+.\"
+documentation describes how to compile and run it.
+.P
+Just-in-time compiler support is an optional feature of PCRE2 that can be built
+in appropriate hardware environments. It greatly speeds up the matching
+performance of many patterns. Programs can request that it be used if
+available, by calling \fBpcre2_jit_compile()\fP after a pattern has been
+successfully compiled by \fBpcre2_compile()\fP. This does nothing if JIT
+support is not available.
+.P
+More complicated programs might need to make use of the specialist functions
+\fBpcre2_jit_stack_create()\fP, \fBpcre2_jit_stack_free()\fP, and
+\fBpcre2_jit_stack_assign()\fP in order to control the JIT code's memory usage.
+.P
+JIT matching is automatically used by \fBpcre2_match()\fP if it is available.
+There is also a direct interface for JIT matching, which gives improved
+performance. The JIT-specific functions are discussed in the
+.\" HREF
+\fBpcre2jit\fP
+.\"
+documentation.
+.P
+A second matching function, \fBpcre2_dfa_match()\fP, which is not
+Perl-compatible, is also provided. This uses a different algorithm for the
+matching. The alternative algorithm finds all possible matches (at a given
+point in the subject), and scans the subject just once (unless there are
+lookbehind assertions). However, this algorithm does not return captured
+substrings. A description of the two matching algorithms and their advantages
+and disadvantages is given in the
+.\" HREF
+\fBpcre2matching\fP
+.\"
+documentation. There is no JIT support for \fBpcre2_dfa_match()\fP.
+.P
+In addition to the main compiling and matching functions, there are convenience
+functions for extracting captured substrings from a subject string that has
+been matched by \fBpcre2_match()\fP. They are:
+.sp
+  \fBpcre2_substring_copy_byname()\fP
+  \fBpcre2_substring_copy_bynumber()\fP
+  \fBpcre2_substring_get_byname()\fP
+  \fBpcre2_substring_get_bynumber()\fP
+  \fBpcre2_substring_list_get()\fP
+  \fBpcre2_substring_length_byname()\fP
+  \fBpcre2_substring_length_bynumber()\fP
+  \fBpcre2_substring_nametable_scan()\fP
+  \fBpcre2_substring_number_from_name()\fP
+.sp
+\fBpcre2_substring_free()\fP and \fBpcre2_substring_list_free()\fP are also
+provided, to free the memory used for extracted strings.
+.P
+The function \fBpcre2_substitute()\fP can be called to match a pattern and
+return a copy of the subject string with substitutions for parts that were
+matched.
+.P
+Finally, there are functions for finding out information about a compiled
+pattern (\fBpcre2_pattern_info()\fP) and about the configuration with which
+PCRE2 was built (\fBpcre2_config()\fP).
+.
+.
+.SH "STRING LENGTHS AND OFFSETS"
+.rs
+.sp
+The PCRE2 API uses string lengths and offsets into strings of code units in
+several places. These values are always of type PCRE2_SIZE, which is an
+unsigned integer type, currently always defined as \fIsize_t\fP. The largest
+value that can be stored in such a type (that is ~(PCRE2_SIZE)0) is reserved
+as a special indicator for zero-terminated strings and unset offsets.
+Therefore, the longest string that can be handled is one less than this
+maximum.
+.
+.
+.\" HTML 
+.SH NEWLINES
+.rs
+.sp
+PCRE2 supports five different conventions for indicating line breaks in
+strings: a single CR (carriage return) character, a single LF (linefeed)
+character, the two-character sequence CRLF, any of the three preceding, or any
+Unicode newline sequence. The Unicode newline sequences are the three just
+mentioned, plus the single characters VT (vertical tab, U+000B), FF (form feed,
+U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
+(paragraph separator, U+2029).
+.P
+Each of the first three conventions is used by at least one operating system as
+its standard newline sequence. When PCRE2 is built, a default can be specified.
+The default default is LF, which is the Unix standard. However, the newline
+convention can be changed by an application when calling \fBpcre2_compile()\fP,
+or it can be specified by special text at the start of the pattern itself; this
+overrides any other settings. See the
+.\" HREF
+\fBpcre2pattern\fP
+.\"
+page for details of the special character sequences.
+.P
+In the PCRE2 documentation the word "newline" is used to mean "the character or
+pair of characters that indicate a line break". The choice of newline
+convention affects the handling of the dot, circumflex, and dollar
+metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
+recognized line ending sequence, the match position advancement for a
+non-anchored pattern. There is more detail about this in the
+.\" HTML 
+.\" 
+section on \fBpcre2_match()\fP options
+.\"
+below.
+.P
+The choice of newline convention does not affect the interpretation of
+the \en or \er escape sequences, nor does it affect what \eR matches; this has
+its own separate convention.
+.
+.
+.SH MULTITHREADING
+.rs
+.sp
+In a multithreaded application it is important to keep thread-specific data
+separate from data that can be shared between threads. The PCRE2 library code
+itself is thread-safe: it contains no static or global variables. The API is
+designed to be fairly simple for non-threaded applications while at the same
+time ensuring that multithreaded applications can use it.
+.P
+There are several different blocks of data that are used to pass information
+between the application and the PCRE2 libraries.
+.P
+(1) A pointer to the compiled form of a pattern is returned to the user when
+\fBpcre2_compile()\fP is successful. The data in the compiled pattern is fixed,
+and does not change when the pattern is matched. Therefore, it is thread-safe,
+that is, the same compiled pattern can be used by more than one thread
+simultaneously. An application can compile all its patterns at the start,
+before forking off multiple threads that use them. However, if the just-in-time
+optimization feature is being used, it needs separate memory stack areas for
+each thread. See the
+.\" HREF
+\fBpcre2jit\fP
+.\"
+documentation for more details.
+.P
+(2) The next section below introduces the idea of "contexts" in which PCRE2
+functions are called. A context is nothing more than a collection of parameters
+that control the way PCRE2 operates. Grouping a number of parameters together
+in a context is a convenient way of passing them to a PCRE2 function without
+using lots of arguments. The parameters that are stored in contexts are in some
+sense "advanced features" of the API. Many straightforward applications will
+not need to use contexts.
+.P
+In a multithreaded application, if the parameters in a context are values that
+are never changed, the same context can be used by all the threads. However, if
+any thread needs to change any value in a context, it must make its own
+thread-specific copy.
+.P
+(3) The matching functions need a block of memory for working space and for
+storing the results of a match. This includes details of what was matched, as
+well as additional information such as the name of a (*MARK) setting. Each
+thread must provide its own version of this memory.
+.
+.
+.SH "PCRE2 CONTEXTS"
+.rs
+.sp
+Some PCRE2 functions have a lot of parameters, many of which are used only by
+specialist applications, for example, those that use custom memory management
+or non-standard character tables. To keep function argument lists at a
+reasonable size, and at the same time to keep the API extensible, "uncommon"
+parameters are passed to certain functions in a \fBcontext\fP instead of
+directly. A context is just a block of memory that holds the parameter values.
+Applications that do not need to adjust any of the context parameters can pass
+NULL when a context pointer is required.
+.P
+There are three different types of context: a general context that is relevant
+for several PCRE2 operations, a compile-time context, and a match-time context.
+.
+.
+.SS "The general context"
+.rs
+.sp
+At present, this context just contains pointers to (and data for) external
+memory management functions that are called from several places in the PCRE2
+library. The context is named `general' rather than specifically `memory'
+because in future other fields may be added. If you do not want to supply your
+own custom memory management functions, you do not need to bother with a
+general context. A general context is created by:
+.sp
+.nf
+.B pcre2_general_context *pcre2_general_context_create(
+.B "  void *(*\fIprivate_malloc\fP)(PCRE2_SIZE, void *),"
+.B "  void (*\fIprivate_free\fP)(void *, void *), void *\fImemory_data\fP);"
+.fi
+.sp
+The two function pointers specify custom memory management functions, whose
+prototypes are:
+.sp
+  \fBvoid *private_malloc(PCRE2_SIZE, void *);\fP
+  \fBvoid  private_free(void *, void *);\fP
+.sp
+Whenever code in PCRE2 calls these functions, the final argument is the value
+of \fImemory_data\fP. Either of the first two arguments of the creation
+function may be NULL, in which case the system memory management functions
+\fImalloc()\fP and \fIfree()\fP are used. (This is not currently useful, as
+there are no other fields in a general context, but in future there might be.)
+The \fIprivate_malloc()\fP function is used (if supplied) to obtain memory for
+storing the context, and all three values are saved as part of the context.
+.P
+Whenever PCRE2 creates a data block of any kind, the block contains a pointer
+to the \fIfree()\fP function that matches the \fImalloc()\fP function that was
+used. When the time comes to free the block, this function is called.
+.P
+A general context can be copied by calling:
+.sp
+.nf
+.B pcre2_general_context *pcre2_general_context_copy(
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.fi
+.sp
+The memory used for a general context should be freed by calling:
+.sp
+.nf
+.B void pcre2_general_context_free(pcre2_general_context *\fIgcontext\fP);
+.fi
+.sp
+.
+.
+.\" HTML 
+.SS "The compile context"
+.rs
+.sp
+A compile context is required if you want to change the default values of any
+of the following compile-time parameters:
+.sp
+  What \eR matches (Unicode newlines or CR, LF, CRLF only)
+  PCRE2's character tables
+  The newline character sequence
+  The compile time nested parentheses limit
+  An external function for stack checking
+.sp
+A compile context is also required if you are using custom memory management.
+If none of these apply, just pass NULL as the context argument of
+\fIpcre2_compile()\fP.
+.P
+A compile context is created, copied, and freed by the following functions:
+.sp
+.nf
+.B pcre2_compile_context *pcre2_compile_context_create(
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.sp
+.B pcre2_compile_context *pcre2_compile_context_copy(
+.B "  pcre2_compile_context *\fIccontext\fP);"
+.sp
+.B void pcre2_compile_context_free(pcre2_compile_context *\fIccontext\fP);
+.fi
+.sp
+A compile context is created with default values for its parameters. These can
+be changed by calling the following functions, which return 0 on success, or
+PCRE2_ERROR_BADDATA if invalid data is detected.
+.sp
+.nf
+.B int pcre2_set_bsr(pcre2_compile_context *\fIccontext\fP,
+.B "  uint32_t \fIvalue\fP);"
+.fi
+.sp
+The value must be PCRE2_BSR_ANYCRLF, to specify that \eR matches only CR, LF,
+or CRLF, or PCRE2_BSR_UNICODE, to specify that \eR matches any Unicode line
+ending sequence. The value is used by the JIT compiler and by the two
+interpreted matching functions, \fIpcre2_match()\fP and
+\fIpcre2_dfa_match()\fP.
+.sp
+.nf
+.B int pcre2_set_character_tables(pcre2_compile_context *\fIccontext\fP,
+.B "  const unsigned char *\fItables\fP);"
+.fi
+.sp
+The value must be the result of a call to \fIpcre2_maketables()\fP, whose only
+argument is a general context. This function builds a set of character tables
+in the current locale.
+.sp
+.nf
+.B int pcre2_set_newline(pcre2_compile_context *\fIccontext\fP,
+.B "  uint32_t \fIvalue\fP);"
+.fi
+.sp
+This specifies which characters or character sequences are to be recognized as
+newlines. The value must be one of PCRE2_NEWLINE_CR (carriage return only),
+PCRE2_NEWLINE_LF (linefeed only), PCRE2_NEWLINE_CRLF (the two-character
+sequence CR followed by LF), PCRE2_NEWLINE_ANYCRLF (any of the above), or
+PCRE2_NEWLINE_ANY (any Unicode newline sequence).
+.P
+When a pattern is compiled with the PCRE2_EXTENDED option, the value of this
+parameter affects the recognition of white space and the end of internal
+comments starting with #. The value is saved with the compiled pattern for
+subsequent use by the JIT compiler and by the two interpreted matching
+functions, \fIpcre2_match()\fP and \fIpcre2_dfa_match()\fP.
+.sp
+.nf
+.B int pcre2_set_parens_nest_limit(pcre2_compile_context *\fIccontext\fP,
+.B "  uint32_t \fIvalue\fP);"
+.fi
+.sp
+This parameter ajusts the limit, set when PCRE2 is built (default 250), on the
+depth of parenthesis nesting in a pattern. This limit stops rogue patterns
+using up too much system stack when being compiled.
+.sp
+.nf
+.B int pcre2_set_compile_recursion_guard(pcre2_compile_context *\fIccontext\fP,
+.B "  int (*\fIguard_function\fP)(uint32_t, void *), void *\fIuser_data\fP);"
+.fi
+.sp
+There is at least one application that runs PCRE2 in threads with very limited
+system stack, where running out of stack is to be avoided at all costs. The
+parenthesis limit above cannot take account of how much stack is actually
+available. For a finer control, you can supply a function that is called
+whenever \fBpcre2_compile()\fP starts to compile a parenthesized part of a
+pattern. This function can check the actual stack size (or anything else that
+it wants to, of course).
+.P
+The first argument to the callout function gives the current depth of
+nesting, and the second is user data that is set up by the last argument of
+\fBpcre2_set_compile_recursion_guard()\fP. The callout function should return
+zero if all is well, or non-zero to force an error.
+.
+.
+.\" HTML 
+.SS "The match context"
+.rs
+.sp
+A match context is required if you want to change the default values of any
+of the following match-time parameters:
+.sp
+  A callout function
+  The limit for calling \fImatch()\fP
+  The limit for calling \fImatch()\fP recursively
+.sp
+A match context is also required if you are using custom memory management.
+If none of these apply, just pass NULL as the context argument of
+\fBpcre2_match()\fP, \fBpcre2_dfa_match()\fP, or \fBpcre2_jit_match()\fP.
+.P
+A match context is created, copied, and freed by the following functions:
+.sp
+.nf
+.B pcre2_match_context *pcre2_match_context_create(
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.sp
+.B pcre2_match_context *pcre2_match_context_copy(
+.B "  pcre2_match_context *\fImcontext\fP);"
+.sp
+.B void pcre2_match_context_free(pcre2_match_context *\fImcontext\fP);
+.fi
+.sp
+A match context is created with default values for its parameters. These can
+be changed by calling the following functions, which return 0 on success, or
+PCRE2_ERROR_BADDATA if invalid data is detected.
+.sp
+.nf
+.B int pcre2_set_callout(pcre2_match_context *\fImcontext\fP,
+.B "  int (*\fIcallout_function\fP)(pcre2_callout_block *, void *),"
+.B "  void *\fIcallout_data\fP);"
+.fi
+.sp
+This sets up a "callout" function, which PCRE2 will call at specified points
+during a matching operation. Details are given in the
+.\" HREF
+\fBpcre2callout\fP
+.\"
+documentation.
+.sp
+.nf
+.B int pcre2_set_match_limit(pcre2_match_context *\fImcontext\fP,
+.B "  uint32_t \fIvalue\fP);"
+.fi
+.sp
+The \fImatch_limit\fP parameter provides a means of preventing PCRE2 from using
+up too many resources when processing patterns that are not going to match, but
+which have a very large number of possibilities in their search trees. The
+classic example is a pattern that uses nested unlimited repeats.
+.P
+Internally, \fBpcre2_match()\fP uses a function called \fBmatch()\fP, which it
+calls repeatedly (sometimes recursively). The limit set by \fImatch_limit\fP is
+imposed on the number of times this function is called during a match, which
+has the effect of limiting the amount of backtracking that can take place. For
+patterns that are not anchored, the count restarts from zero for each position
+in the subject string. This limit is not relevant to \fBpcre2_dfa_match()\fP,
+which ignores it.
+.P
+When \fBpcre2_match()\fP is called with a pattern that was successfully
+processed by \fBpcre2_jit_compile()\fP, the way in which matching is executed
+is entirely different. However, there is still the possibility of runaway
+matching that goes on for a very long time, and so the \fImatch_limit\fP value
+is also used in this case (but in a different way) to limit how long the
+matching can continue.
+.P
+The default value for the limit can be set when PCRE2 is built; the default
+default is 10 million, which handles all but the most extreme cases. If the
+limit is exceeded, \fBpcre2_match()\fP returns PCRE2_ERROR_MATCHLIMIT. A value
+for the match limit may also be supplied by an item at the start of a pattern
+of the form
+.sp
+  (*LIMIT_MATCH=ddd)
+.sp
+where ddd is a decimal number. However, such a setting is ignored unless ddd is
+less than the limit set by the caller of \fBpcre2_match()\fP or, if no such
+limit is set, less than the default.
+.sp
+.nf
+.B int pcre2_set_recursion_limit(pcre2_match_context *\fImcontext\fP,
+.B "  uint32_t \fIvalue\fP);"
+.fi
+.sp
+The \fIrecursion_limit\fP parameter is similar to \fImatch_limit\fP, but
+instead of limiting the total number of times that \fBmatch()\fP is called, it
+limits the depth of recursion. The recursion depth is a smaller number than the
+total number of calls, because not all calls to \fBmatch()\fP are recursive.
+This limit is of use only if it is set smaller than \fImatch_limit\fP.
+.P
+Limiting the recursion depth limits the amount of system stack that can be
+used, or, when PCRE2 has been compiled to use memory on the heap instead of the
+stack, the amount of heap memory that can be used. This limit is not relevant,
+and is ignored, when matching is done using JIT compiled code or by the
+\fBpcre2_dfa_match()\fP function.
+.P
+The default value for \fIrecursion_limit\fP can be set when PCRE2 is built; the
+default default is the same value as the default for \fImatch_limit\fP. If the
+limit is exceeded, \fBpcre2_match()\fP returns PCRE2_ERROR_RECURSIONLIMIT. A
+value for the recursion limit may also be supplied by an item at the start of a
+pattern of the form
+.sp
+  (*LIMIT_RECURSION=ddd)
+.sp
+where ddd is a decimal number. However, such a setting is ignored unless ddd is
+less than the limit set by the caller of \fBpcre2_match()\fP or, if no such
+limit is set, less than the default.
+.sp
+.nf
+.B int pcre2_set_recursion_memory_management(
+.B "  pcre2_match_context *\fImcontext\fP,"
+.B "  void *(*\fIprivate_malloc\fP)(PCRE2_SIZE, void *),"
+.B "  void (*\fIprivate_free\fP)(void *, void *), void *\fImemory_data\fP);"
+.fi
+.sp
+This function sets up two additional custom memory management functions for use
+by \fBpcre2_match()\fP when PCRE2 is compiled to use the heap for remembering
+backtracking data, instead of recursive function calls that use the system
+stack. There is a discussion about PCRE2's stack usage in the
+.\" HREF
+\fBpcre2stack\fP
+.\"
+documentation. See the
+.\" HREF
+\fBpcre2build\fP
+.\"
+documentation for details of how to build PCRE2.
+.P
+Using the heap for recursion is a non-standard way of building PCRE2, for use
+in environments that have limited stacks. Because of the greater use of memory
+management, \fBpcre2_match()\fP runs more slowly. Functions that are different
+to the general custom memory functions are provided so that special-purpose
+external code can be used for this case, because the memory blocks are all the
+same size. The blocks are retained by \fBpcre2_match()\fP until it is about to
+exit so that they can be re-used when possible during the match. In the absence
+of these functions, the normal custom memory management functions are used, if
+supplied, otherwise the system functions.
+.
+.
+.SH "CHECKING BUILD-TIME OPTIONS"
+.rs
+.sp
+.B int pcre2_config(uint32_t \fIwhat\fP, void *\fIwhere\fP);
+.P
+The function \fBpcre2_config()\fP makes it possible for a PCRE2 client to
+discover which optional features have been compiled into the PCRE2 library. The
+.\" HREF
+\fBpcre2build\fP
+.\"
+documentation has more details about these optional features.
+.P
+The first argument for \fBpcre2_config()\fP specifies which information is
+required. The second argument is a pointer to memory into which the information
+is placed. If NULL is passed, the function returns the amount of memory that is
+needed for the requested information. For calls that return numerical values,
+the value is in bytes; when requesting these values, \fIwhere\fP should point
+to appropriately aligned memory. For calls that return strings, the required
+length is given in code units, not counting the terminating zero.
+.P
+When requesting information, the returned value from \fBpcre2_config()\fP is
+non-negative on success, or the negative error code PCRE2_ERROR_BADOPTION if
+the value in the first argument is not recognized. The following information is
+available:
+.sp
+  PCRE2_CONFIG_BSR
+.sp
+The output is a uint32_t integer whose value indicates what character
+sequences the \eR escape sequence matches by default. A value of
+PCRE2_BSR_UNICODE means that \eR matches any Unicode line ending sequence; a
+value of PCRE2_BSR_ANYCRLF means that \eR matches only CR, LF, or CRLF. The
+default can be overridden when a pattern is compiled.
+.sp
+  PCRE2_CONFIG_JIT
+.sp
+The output is a uint32_t integer that is set to one if support for just-in-time
+compiling is available; otherwise it is set to zero.
+.sp
+  PCRE2_CONFIG_JITTARGET
+.sp
+The \fIwhere\fP argument should point to a buffer that is at least 48 code
+units long. (The exact length required can be found by calling
+\fBpcre2_config()\fP with \fBwhere\fP set to NULL.) The buffer is filled with a
+string that contains the name of the architecture for which the JIT compiler is
+configured, for example "x86 32bit (little endian + unaligned)". If JIT support
+is not available, PCRE2_ERROR_BADOPTION is returned, otherwise the number of
+code units used is returned. This is the length of the string, plus one unit
+for the terminating zero.
+.sp
+  PCRE2_CONFIG_LINKSIZE
+.sp
+The output is a uint32_t integer that contains the number of bytes used for
+internal linkage in compiled regular expressions. When PCRE2 is configured, the
+value can be set to 2, 3, or 4, with the default being 2. This is the value
+that is returned by \fBpcre2_config()\fP. However, when the 16-bit library is
+compiled, a value of 3 is rounded up to 4, and when the 32-bit library is
+compiled, internal linkages always use 4 bytes, so the configured value is not
+relevant.
+.P
+The default value of 2 for the 8-bit and 16-bit libraries is sufficient for all
+but the most massive patterns, since it allows the size of the compiled pattern
+to be up to 64K code units. Larger values allow larger regular expressions to
+be compiled by those two libraries, but at the expense of slower matching.
+.sp
+  PCRE2_CONFIG_MATCHLIMIT
+.sp
+The output is a uint32_t integer that gives the default limit for the number of
+internal matching function calls in a \fBpcre2_match()\fP execution. Further
+details are given with \fBpcre2_match()\fP below.
+.sp
+  PCRE2_CONFIG_NEWLINE
+.sp
+The output is a uint32_t integer whose value specifies the default character
+sequence that is recognized as meaning "newline". The values are:
+.sp
+  PCRE2_NEWLINE_CR       Carriage return (CR)
+  PCRE2_NEWLINE_LF       Linefeed (LF)
+  PCRE2_NEWLINE_CRLF     Carriage return, linefeed (CRLF)
+  PCRE2_NEWLINE_ANY      Any Unicode line ending
+  PCRE2_NEWLINE_ANYCRLF  Any of CR, LF, or CRLF
+.sp
+The default should normally correspond to the standard sequence for your
+operating system.
+.sp
+  PCRE2_CONFIG_PARENSLIMIT
+.sp
+The output is a uint32_t integer that gives the maximum depth of nesting
+of parentheses (of any kind) in a pattern. This limit is imposed to cap the
+amount of system stack used when a pattern is compiled. It is specified when
+PCRE2 is built; the default is 250. This limit does not take into account the
+stack that may already be used by the calling application. For finer control
+over compilation stack usage, see \fBpcre2_set_compile_recursion_guard()\fP.
+.sp
+  PCRE2_CONFIG_RECURSIONLIMIT
+.sp
+The output is a uint32_t integer that gives the default limit for the depth of
+recursion when calling the internal matching function in a \fBpcre2_match()\fP
+execution. Further details are given with \fBpcre2_match()\fP below.
+.sp
+  PCRE2_CONFIG_STACKRECURSE
+.sp
+The output is a uint32_t integer that is set to one if internal recursion when
+running \fBpcre2_match()\fP is implemented by recursive function calls that use
+the system stack to remember their state. This is the usual way that PCRE2 is
+compiled. The output is zero if PCRE2 was compiled to use blocks of data on the
+heap instead of recursive function calls.
+.sp
+  PCRE2_CONFIG_UNICODE_VERSION
+.sp
+The \fIwhere\fP argument should point to a buffer that is at least 24 code
+units long. (The exact length required can be found by calling
+\fBpcre2_config()\fP with \fBwhere\fP set to NULL.) If PCRE2 has been compiled
+without Unicode support, the buffer is filled with the text "Unicode not
+supported". Otherwise, the Unicode version string (for example, "7.0.0") is
+inserted. The number of code units used is returned. This is the length of the
+string plus one unit for the terminating zero.
+.sp
+  PCRE2_CONFIG_UNICODE
+.sp
+The output is a uint32_t integer that is set to one if Unicode support is
+available; otherwise it is set to zero. Unicode support implies UTF support.
+.sp
+  PCRE2_CONFIG_VERSION
+.sp
+The \fIwhere\fP argument should point to a buffer that is at least 12 code
+units long. (The exact length required can be found by calling
+\fBpcre2_config()\fP with \fBwhere\fP set to NULL.) The buffer is filled with
+the PCRE2 version string, zero-terminated. The number of code units used is
+returned. This is the length of the string plus one unit for the terminating
+zero.
+.
+.
+.\" HTML 
+.SH "COMPILING A PATTERN"
+.rs
+.sp
+.nf
+.B pcre2_code *pcre2_compile(PCRE2_SPTR \fIpattern\fP, PCRE2_SIZE \fIlength\fP,
+.B "  uint32_t \fIoptions\fP, int *\fIerrorcode\fP, PCRE2_SIZE *\fIerroroffset,\fP"
+.B "  pcre2_compile_context *\fIccontext\fP);"
+.sp
+.B pcre2_code_free(pcre2_code *\fIcode\fP);
+.fi
+.P
+The \fBpcre2_compile()\fP function compiles a pattern into an internal form.
+The pattern is defined by a pointer to a string of code units and a length, If
+the pattern is zero-terminated, the length can be specified as
+PCRE2_ZERO_TERMINATED. The function returns a pointer to a block of memory that
+contains the compiled pattern and related data. The caller must free the memory
+by calling \fBpcre2_code_free()\fP when it is no longer needed.
+.P
+NOTE: When one of the matching functions is called, pointers to the compiled
+pattern and the subject string are set in the match data block so that they can
+be referenced by the extraction functions. After running a match, you must not
+free a compiled pattern (or a subject string) until after all operations on the
+.\" HTML 
+.\" 
+match data block
+.\"
+have taken place.
+.P
+If the compile context argument \fIccontext\fP is NULL, memory for the compiled
+pattern is obtained by calling \fBmalloc()\fP. Otherwise, it is obtained from
+the same memory function that was used for the compile context.
+.P
+The \fIoptions\fP argument contains various bit settings that affect the
+compilation. It should be zero if no options are required. The available
+options are described below. Some of them (in particular, those that are
+compatible with Perl, but some others as well) can also be set and unset from
+within the pattern (see the detailed description in the
+.\" HREF
+\fBpcre2pattern\fP
+.\"
+documentation).
+.P
+For those options that can be different in different parts of the pattern, the
+contents of the \fIoptions\fP argument specifies their settings at the start of
+compilation. The PCRE2_ANCHORED and PCRE2_NO_UTF_CHECK options can be set at
+the time of matching as well as at compile time.
+.P
+Other, less frequently required compile-time parameters (for example, the
+newline setting) can be provided in a compile context (as described
+.\" HTML 
+.\" 
+above).
+.\"
+.P
+If \fIerrorcode\fP or \fIerroroffset\fP is NULL, \fBpcre2_compile()\fP returns
+NULL immediately. Otherwise, if compilation of a pattern fails,
+\fBpcre2_compile()\fP returns NULL, having set these variables to an error code
+and an offset (number of code units) within the pattern, respectively. The
+\fBpcre2_get_error_message()\fP function provides a textual message for each
+error code. Compilation errors are positive numbers, but UTF formatting errors
+are negative numbers. For an invalid UTF-8 or UTF-16 string, the offset is that
+of the first code unit of the failing character.
+.P
+Some errors are not detected until the whole pattern has been scanned; in these
+cases, the offset passed back is the length of the pattern. Note that the
+offset is in code units, not characters, even in a UTF mode. It may sometimes
+point into the middle of a UTF-8 or UTF-16 character.
+.P
+This code fragment shows a typical straightforward call to
+\fBpcre2_compile()\fP:
+.sp
+  pcre2_code *re;
+  PCRE2_SIZE erroffset;
+  int errorcode;
+  re = pcre2_compile(
+    "^A.*Z",                /* the pattern */
+    PCRE2_ZERO_TERMINATED,  /* the pattern is zero-terminated */
+    0,                      /* default options */
+    &errorcode,             /* for error code */
+    &erroffset,             /* for error offset */
+    NULL);                  /* no compile context */
+.sp
+The following names for option bits are defined in the \fBpcre2.h\fP header
+file:
+.sp
+  PCRE2_ANCHORED
+.sp
+If this bit is set, the pattern is forced to be "anchored", that is, it is
+constrained to match only at the first matching point in the string that is
+being searched (the "subject string"). This effect can also be achieved by
+appropriate constructs in the pattern itself, which is the only way to do it in
+Perl.
+.sp
+  PCRE2_ALLOW_EMPTY_CLASS
+.sp
+By default, for compatibility with Perl, a closing square bracket that
+immediately follows an opening one is treated as a data character for the
+class. When PCRE2_ALLOW_EMPTY_CLASS is set, it terminates the class, which
+therefore contains no characters and so can never match.
+.sp
+  PCRE2_ALT_BSUX
+.sp
+This option request alternative handling of three escape sequences, which
+makes PCRE2's behaviour more like ECMAscript (aka JavaScript). When it is set:
+.P
+(1) \eU matches an upper case "U" character; by default \eU causes a compile
+time error (Perl uses \eU to upper case subsequent characters).
+.P
+(2) \eu matches a lower case "u" character unless it is followed by four
+hexadecimal digits, in which case the hexadecimal number defines the code point
+to match. By default, \eu causes a compile time error (Perl uses it to upper
+case the following character).
+.P
+(3) \ex matches a lower case "x" character unless it is followed by two
+hexadecimal digits, in which case the hexadecimal number defines the code point
+to match. By default, as in Perl, a hexadecimal number is always expected after
+\ex, but it may have zero, one, or two digits (so, for example, \exz matches a
+binary zero character followed by z).
+.sp
+  PCRE2_ALT_CIRCUMFLEX
+.sp
+In multiline mode (when PCRE2_MULTILINE is set), the circumflex metacharacter
+matches at the start of the subject (unless PCRE2_NOTBOL is set), and also
+after any internal newline. However, it does not match after a newline at the
+end of the subject, for compatibility with Perl. If you want a multiline
+circumflex also to match after a terminating newline, you must set
+PCRE2_ALT_CIRCUMFLEX.
+.sp
+  PCRE2_AUTO_CALLOUT
+.sp
+If this bit is set, \fBpcre2_compile()\fP automatically inserts callout items,
+all with number 255, before each pattern item. For discussion of the callout
+facility, see the
+.\" HREF
+\fBpcre2callout\fP
+.\"
+documentation.
+.sp
+  PCRE2_CASELESS
+.sp
+If this bit is set, letters in the pattern match both upper and lower case
+letters in the subject. It is equivalent to Perl's /i option, and it can be
+changed within a pattern by a (?i) option setting.
+.sp
+  PCRE2_DOLLAR_ENDONLY
+.sp
+If this bit is set, a dollar metacharacter in the pattern matches only at the
+end of the subject string. Without this option, a dollar also matches
+immediately before a newline at the end of the string (but not before any other
+newlines). The PCRE2_DOLLAR_ENDONLY option is ignored if PCRE2_MULTILINE is
+set. There is no equivalent to this option in Perl, and no way to set it within
+a pattern.
+.sp
+  PCRE2_DOTALL
+.sp
+If this bit is set, a dot metacharacter in the pattern matches any character,
+including one that indicates a newline. However, it only ever matches one
+character, even if newlines are coded as CRLF. Without this option, a dot does
+not match when the current position in the subject is at a newline. This option
+is equivalent to Perl's /s option, and it can be changed within a pattern by a
+(?s) option setting. A negative class such as [^a] always matches newline
+characters, independent of the setting of this option.
+.sp
+  PCRE2_DUPNAMES
+.sp
+If this bit is set, names used to identify capturing subpatterns need not be
+unique. This can be helpful for certain types of pattern when it is known that
+only one instance of the named subpattern can ever be matched. There are more
+details of named subpatterns below; see also the
+.\" HREF
+\fBpcre2pattern\fP
+.\"
+documentation.
+.sp
+  PCRE2_EXTENDED
+.sp
+If this bit is set, most white space characters in the pattern are totally
+ignored except when escaped or inside a character class. However, white space
+is not allowed within sequences such as (?> that introduce various
+parenthesized subpatterns, nor within numerical quantifiers such as {1,3}.
+Ignorable white space is permitted between an item and a following quantifier
+and between a quantifier and a following + that indicates possessiveness.
+.P
+PCRE2_EXTENDED also causes characters between an unescaped # outside a
+character class and the next newline, inclusive, to be ignored, which makes it
+possible to include comments inside complicated patterns. Note that the end of
+this type of comment is a literal newline sequence in the pattern; escape
+sequences that happen to represent a newline do not count. PCRE2_EXTENDED is
+equivalent to Perl's /x option, and it can be changed within a pattern by a
+(?x) option setting.
+.P
+Which characters are interpreted as newlines can be specified by a setting in
+the compile context that is passed to \fBpcre2_compile()\fP or by a special
+sequence at the start of the pattern, as described in the section entitled
+.\" HTML 
+.\" 
+"Newline conventions"
+.\"
+in the \fBpcre2pattern\fP documentation. A default is defined when PCRE2 is
+built.
+.sp
+  PCRE2_FIRSTLINE
+.sp
+If this option is set, an unanchored pattern is required to match before or at
+the first newline in the subject string, though the matched text may continue
+over the newline.
+.sp
+  PCRE2_MATCH_UNSET_BACKREF
+.sp
+If this option is set, a back reference to an unset subpattern group matches an
+empty string (by default this causes the current matching alternative to fail).
+A pattern such as (\e1)(a) succeeds when this option is set (assuming it can
+find an "a" in the subject), whereas it fails by default, for Perl
+compatibility. Setting this option makes PCRE2 behave more like ECMAscript (aka
+JavaScript).
+.sp
+  PCRE2_MULTILINE
+.sp
+By default, for the purposes of matching "start of line" and "end of line",
+PCRE2 treats the subject string as consisting of a single line of characters,
+even if it actually contains newlines. The "start of line" metacharacter (^)
+matches only at the start of the string, and the "end of line" metacharacter
+($) matches only at the end of the string, or before a terminating newline
+(except when PCRE2_DOLLAR_ENDONLY is set). Note, however, that unless
+PCRE2_DOTALL is set, the "any character" metacharacter (.) does not match at a
+newline. This behaviour (for ^, $, and dot) is the same as Perl.
+.P
+When PCRE2_MULTILINE it is set, the "start of line" and "end of line"
+constructs match immediately following or immediately before internal newlines
+in the subject string, respectively, as well as at the very start and end. This
+is equivalent to Perl's /m option, and it can be changed within a pattern by a
+(?m) option setting. Note that the "start of line" metacharacter does not match
+after a newline at the end of the subject, for compatibility with Perl.
+However, you can change this by setting the PCRE2_ALT_CIRCUMFLEX option. If
+there are no newlines in a subject string, or no occurrences of ^ or $ in a
+pattern, setting PCRE2_MULTILINE has no effect.
+.sp
+  PCRE2_NEVER_BACKSLASH_C
+.sp
+This option locks out the use of \eC in the pattern that is being compiled.
+This escape can cause unpredictable behaviour in UTF-8 or UTF-16 modes, because
+it may leave the current matching point in the middle of a multi-code-unit
+character. This option may be useful in applications that process patterns from
+external sources.
+.sp
+  PCRE2_NEVER_UCP
+.sp
+This option locks out the use of Unicode properties for handling \eB, \eb, \eD,
+\ed, \eS, \es, \eW, \ew, and some of the POSIX character classes, as described
+for the PCRE2_UCP option below. In particular, it prevents the creator of the
+pattern from enabling this facility by starting the pattern with (*UCP). This
+option may be useful in applications that process patterns from external
+sources. The option combination PCRE_UCP and PCRE_NEVER_UCP causes an error.
+.sp
+  PCRE2_NEVER_UTF
+.sp
+This option locks out interpretation of the pattern as UTF-8, UTF-16, or
+UTF-32, depending on which library is in use. In particular, it prevents the
+creator of the pattern from switching to UTF interpretation by starting the
+pattern with (*UTF). This option may be useful in applications that process
+patterns from external sources. The combination of PCRE2_UTF and
+PCRE2_NEVER_UTF causes an error.
+.sp
+  PCRE2_NO_AUTO_CAPTURE
+.sp
+If this option is set, it disables the use of numbered capturing parentheses in
+the pattern. Any opening parenthesis that is not followed by ? behaves as if it
+were followed by ?: but named parentheses can still be used for capturing (and
+they acquire numbers in the usual way). There is no equivalent of this option
+in Perl.
+.sp
+  PCRE2_NO_AUTO_POSSESS
+.sp
+If this option is set, it disables "auto-possessification", which is an
+optimization that, for example, turns a+b into a++b in order to avoid
+backtracks into a+ that can never be successful. However, if callouts are in
+use, auto-possessification means that some callouts are never taken. You can
+set this option if you want the matching functions to do a full unoptimized
+search and run all the callouts, but it is mainly provided for testing
+purposes.
+.sp
+  PCRE2_NO_DOTSTAR_ANCHOR
+.sp
+If this option is set, it disables an optimization that is applied when .* is
+the first significant item in a top-level branch of a pattern, and all the
+other branches also start with .* or with \eA or \eG or ^. The optimization is
+automatically disabled for .* if it is inside an atomic group or a capturing
+group that is the subject of a back reference, or if the pattern contains
+(*PRUNE) or (*SKIP). When the optimization is not disabled, such a pattern is
+automatically anchored if PCRE2_DOTALL is set for all the .* items and
+PCRE2_MULTILINE is not set for any ^ items. Otherwise, the fact that any match
+must start either at the start of the subject or following a newline is
+remembered. Like other optimizations, this can cause callouts to be skipped.
+.sp
+  PCRE2_NO_START_OPTIMIZE
+.sp
+This is an option whose main effect is at matching time. It does not change
+what \fBpcre2_compile()\fP generates, but it does affect the output of the JIT
+compiler.
+.P
+There are a number of optimizations that may occur at the start of a match, in
+order to speed up the process. For example, if it is known that an unanchored
+match must start with a specific character, the matching code searches the
+subject for that character, and fails immediately if it cannot find it, without
+actually running the main matching function. This means that a special item
+such as (*COMMIT) at the start of a pattern is not considered until after a
+suitable starting point for the match has been found. Also, when callouts or
+(*MARK) items are in use, these "start-up" optimizations can cause them to be
+skipped if the pattern is never actually used. The start-up optimizations are
+in effect a pre-scan of the subject that takes place before the pattern is run.
+.P
+The PCRE2_NO_START_OPTIMIZE option disables the start-up optimizations,
+possibly causing performance to suffer, but ensuring that in cases where the
+result is "no match", the callouts do occur, and that items such as (*COMMIT)
+and (*MARK) are considered at every possible starting position in the subject
+string.
+.P
+Setting PCRE2_NO_START_OPTIMIZE may change the outcome of a matching operation.
+Consider the pattern
+.sp
+  (*COMMIT)ABC
+.sp
+When this is compiled, PCRE2 records the fact that a match must start with the
+character "A". Suppose the subject string is "DEFABC". The start-up
+optimization scans along the subject, finds "A" and runs the first match
+attempt from there. The (*COMMIT) item means that the pattern must match the
+current starting position, which in this case, it does. However, if the same
+match is run with PCRE2_NO_START_OPTIMIZE set, the initial scan along the
+subject string does not happen. The first match attempt is run starting from
+"D" and when this fails, (*COMMIT) prevents any further matches being tried, so
+the overall result is "no match". There are also other start-up optimizations.
+For example, a minimum length for the subject may be recorded. Consider the
+pattern
+.sp
+  (*MARK:A)(X|Y)
+.sp
+The minimum length for a match is one character. If the subject is "ABC", there
+will be attempts to match "ABC", "BC", and "C". An attempt to match an empty
+string at the end of the subject does not take place, because PCRE2 knows that
+the subject is now too short, and so the (*MARK) is never encountered. In this
+case, the optimization does not affect the overall match result, which is still
+"no match", but it does affect the auxiliary information that is returned.
+.sp
+  PCRE2_NO_UTF_CHECK
+.sp
+When PCRE2_UTF is set, the validity of the pattern as a UTF string is
+automatically checked. There are discussions about the validity of
+.\" HTML 
+.\" 
+UTF-8 strings,
+.\"
+.\" HTML 
+.\" 
+UTF-16 strings,
+.\"
+and
+.\" HTML 
+.\" 
+UTF-32 strings
+.\"
+in the
+.\" HREF
+\fBpcre2unicode\fP
+.\"
+document.
+If an invalid UTF sequence is found, \fBpcre2_compile()\fP returns a negative
+error code.
+.P
+If you know that your pattern is valid, and you want to skip this check for
+performance reasons, you can set the PCRE2_NO_UTF_CHECK option. When it is set,
+the effect of passing an invalid UTF string as a pattern is undefined. It may
+cause your program to crash or loop. Note that this option can also be passed
+to \fBpcre2_match()\fP and \fBpcre_dfa_match()\fP, to suppress validity
+checking of the subject string.
+.sp
+  PCRE2_UCP
+.sp
+This option changes the way PCRE2 processes \eB, \eb, \eD, \ed, \eS, \es, \eW,
+\ew, and some of the POSIX character classes. By default, only ASCII characters
+are recognized, but if PCRE2_UCP is set, Unicode properties are used instead to
+classify characters. More details are given in the section on
+.\" HTML 
+.\" 
+generic character types
+.\"
+in the
+.\" HREF
+\fBpcre2pattern\fP
+.\"
+page. If you set PCRE2_UCP, matching one of the items it affects takes much
+longer. The option is available only if PCRE2 has been compiled with Unicode
+support.
+.sp
+  PCRE2_UNGREEDY
+.sp
+This option inverts the "greediness" of the quantifiers so that they are not
+greedy by default, but become greedy if followed by "?". It is not compatible
+with Perl. It can also be set by a (?U) option setting within the pattern.
+.sp
+  PCRE2_UTF
+.sp
+This option causes PCRE2 to regard both the pattern and the subject strings
+that are subsequently processed as strings of UTF characters instead of
+single-code-unit strings. It is available when PCRE2 is built to include
+Unicode support (which is the default). If Unicode support is not available,
+the use of this option provokes an error. Details of how this option changes
+the behaviour of PCRE2 are given in the
+.\" HREF
+\fBpcre2unicode\fP
+.\"
+page.
+.
+.
+.SH "COMPILATION ERROR CODES"
+.rs
+.sp
+There are over 80 positive error codes that \fBpcre2_compile()\fP may return if
+it finds an error in the pattern. There are also some negative error codes that
+are used for invalid UTF strings. These are the same as given by
+\fBpcre2_match()\fP and \fBpcre2_dfa_match()\fP, and are described in the
+.\" HREF
+\fBpcre2unicode\fP
+.\"
+page. The \fBpcre2_get_error_message()\fP function can be called to obtain a
+textual error message from any error code.
+.
+.
+.SH "JUST-IN-TIME (JIT) COMPILATION"
+.rs
+.sp
+.nf
+.B int pcre2_jit_compile(pcre2_code *\fIcode\fP, uint32_t \fIoptions\fP);
+.sp
+.B int pcre2_jit_match(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
+.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
+.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
+.B "  pcre2_match_context *\fImcontext\fP);"
+.sp
+.B void pcre2_jit_free_unused_memory(pcre2_general_context *\fIgcontext\fP);
+.sp
+.B pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE \fIstartsize\fP,
+.B "  PCRE2_SIZE \fImaxsize\fP, pcre2_general_context *\fIgcontext\fP);"
+.sp
+.B void pcre2_jit_stack_assign(pcre2_match_context *\fImcontext\fP,
+.B "  pcre2_jit_callback \fIcallback_function\fP, void *\fIcallback_data\fP);"
+.sp
+.B void pcre2_jit_stack_free(pcre2_jit_stack *\fIjit_stack\fP);
+.fi
+.P
+These functions provide support for JIT compilation, which, if the just-in-time
+compiler is available, further processes a compiled pattern into machine code
+that executes much faster than the \fBpcre2_match()\fP interpretive matching
+function. Full details are given in the
+.\" HREF
+\fBpcre2jit\fP
+.\"
+documentation.
+.P
+JIT compilation is a heavyweight optimization. It can take some time for
+patterns to be analyzed, and for one-off matches and simple patterns the
+benefit of faster execution might be offset by a much slower compilation time.
+Most, but not all patterns can be optimized by the JIT compiler.
+.
+.
+.\" HTML 
+.SH "LOCALE SUPPORT"
+.rs
+.sp
+PCRE2 handles caseless matching, and determines whether characters are letters,
+digits, or whatever, by reference to a set of tables, indexed by character code
+point. This applies only to characters whose code points are less than 256. By
+default, higher-valued code points never match escapes such as \ew or \ed.
+However, if PCRE2 is built with UTF support, all characters can be tested with
+\ep and \eP, or, alternatively, the PCRE2_UCP option can be set when a pattern
+is compiled; this causes \ew and friends to use Unicode property support
+instead of the built-in tables.
+.P
+The use of locales with Unicode is discouraged. If you are handling characters
+with code points greater than 128, you should either use Unicode support, or
+use locales, but not try to mix the two.
+.P
+PCRE2 contains an internal set of character tables that are used by default.
+These are sufficient for many applications. Normally, the internal tables
+recognize only ASCII characters. However, when PCRE2 is built, it is possible
+to cause the internal tables to be rebuilt in the default "C" locale of the
+local system, which may cause them to be different.
+.P
+The internal tables can be overridden by tables supplied by the application
+that calls PCRE2. These may be created in a different locale from the default.
+As more and more applications change to using Unicode, the need for this locale
+support is expected to die away.
+.P
+External tables are built by calling the \fBpcre2_maketables()\fP function, in
+the relevant locale. The result can be passed to \fBpcre2_compile()\fP as often
+as necessary, by creating a compile context and calling
+\fBpcre2_set_character_tables()\fP to set the tables pointer therein. For
+example, to build and use tables that are appropriate for the French locale
+(where accented characters with values greater than 128 are treated as
+letters), the following code could be used:
+.sp
+  setlocale(LC_CTYPE, "fr_FR");
+  tables = pcre2_maketables(NULL);
+  ccontext = pcre2_compile_context_create(NULL);
+  pcre2_set_character_tables(ccontext, tables);
+  re = pcre2_compile(..., ccontext);
+.sp
+The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
+are using Windows, the name for the French locale is "french". It is the
+caller's responsibility to ensure that the memory containing the tables remains
+available for as long as it is needed.
+.P
+The pointer that is passed (via the compile context) to \fBpcre2_compile()\fP
+is saved with the compiled pattern, and the same tables are used by
+\fBpcre2_match()\fP and \fBpcre_dfa_match()\fP. Thus, for any single pattern,
+compilation, and matching all happen in the same locale, but different patterns
+can be processed in different locales.
+.
+.
+.\" HTML 
+.SH "INFORMATION ABOUT A COMPILED PATTERN"
+.rs
+.sp
+.nf
+.B int pcre2_pattern_info(const pcre2 *\fIcode\fP, uint32_t \fIwhat\fP, void *\fIwhere\fP);
+.fi
+.P
+The \fBpcre2_pattern_info()\fP function returns general information about a
+compiled pattern. For information about callouts, see the
+.\" HTML 
+.\" 
+next section.
+.\"
+The first argument for \fBpcre2_pattern_info()\fP is a pointer to the compiled
+pattern. The second argument specifies which piece of information is required,
+and the third argument is a pointer to a variable to receive the data. If the
+third argument is NULL, the first argument is ignored, and the function returns
+the size in bytes of the variable that is required for the information
+requested. Otherwise, The yield of the function is zero for success, or one of
+the following negative numbers:
+.sp
+  PCRE2_ERROR_NULL           the argument \fIcode\fP was NULL
+  PCRE2_ERROR_BADMAGIC       the "magic number" was not found
+  PCRE2_ERROR_BADOPTION      the value of \fIwhat\fP was invalid
+  PCRE2_ERROR_UNSET          the requested field is not set
+.sp
+The "magic number" is placed at the start of each compiled pattern as an simple
+check against passing an arbitrary memory pointer. Here is a typical call of
+\fBpcre2_pattern_info()\fP, to obtain the length of the compiled pattern:
+.sp
+  int rc;
+  size_t length;
+  rc = pcre2_pattern_info(
+    re,               /* result of pcre2_compile() */
+    PCRE2_INFO_SIZE,  /* what is required */
+    &length);         /* where to put the data */
+.sp
+The possible values for the second argument are defined in \fBpcre2.h\fP, and
+are as follows:
+.sp
+  PCRE2_INFO_ALLOPTIONS
+  PCRE2_INFO_ARGOPTIONS
+.sp
+Return a copy of the pattern's options. The third argument should point to a
+\fBuint32_t\fP variable. PCRE2_INFO_ARGOPTIONS returns exactly the options that
+were passed to \fBpcre2_compile()\fP, whereas PCRE2_INFO_ALLOPTIONS returns
+the compile options as modified by any top-level option settings at the start
+of the pattern itself. In other words, they are the options that will be in
+force when matching starts. For example, if the pattern /(?im)abc(?-i)d/ is
+compiled with the PCRE2_EXTENDED option, the result is PCRE2_CASELESS,
+PCRE2_MULTILINE, and PCRE2_EXTENDED.
+.P
+A pattern compiled without PCRE2_ANCHORED is automatically anchored by PCRE2 if
+the first significant item in every top-level branch is one of the following:
+.sp
+  ^     unless PCRE2_MULTILINE is set
+  \eA    always
+  \eG    always
+  .*    sometimes - see below
+.sp
+When .* is the first significant item, anchoring is possible only when all the
+following are true:
+.sp
+  .* is not in an atomic group
+.\" JOIN
+  .* is not in a capturing group that is the subject
+       of a back reference
+  PCRE2_DOTALL is in force for .*
+  Neither (*PRUNE) nor (*SKIP) appears in the pattern.
+  PCRE2_NO_DOTSTAR_ANCHOR is not set.
+.sp
+For patterns that are auto-anchored, the PCRE2_ANCHORED bit is set in the
+options returned for PCRE2_INFO_ALLOPTIONS.
+.sp
+  PCRE2_INFO_BACKREFMAX
+.sp
+Return the number of the highest back reference in the pattern. The third
+argument should point to an \fBuint32_t\fP variable. Named subpatterns acquire
+numbers as well as names, and these count towards the highest back reference.
+Back references such as \e4 or \eg{12} match the captured characters of the
+given group, but in addition, the check that a capturing group is set in a
+conditional subpattern such as (?(3)a|b) is also a back reference. Zero is
+returned if there are no back references.
+.sp
+  PCRE2_INFO_BSR
+.sp
+The output is a uint32_t whose value indicates what character sequences the \eR
+escape sequence matches. A value of PCRE2_BSR_UNICODE means that \eR matches
+any Unicode line ending sequence; a value of PCRE2_BSR_ANYCRLF means that \eR
+matches only CR, LF, or CRLF.
+.sp
+  PCRE2_INFO_CAPTURECOUNT
+.sp
+Return the number of capturing subpatterns in the pattern. The third argument
+should point to an \fBuint32_t\fP variable.
+.sp
+  PCRE2_INFO_FIRSTCODETYPE
+.sp
+Return information about the first code unit of any matched string, for a
+non-anchored pattern. The third argument should point to an \fBuint32_t\fP
+variable.
+.P
+If there is a fixed first value, for example, the letter "c" from a pattern
+such as (cat|cow|coyote), 1 is returned, and the character value can be
+retrieved using PCRE2_INFO_FIRSTCODEUNIT. If there is no fixed first value, but
+it is known that a match can occur only at the start of the subject or
+following a newline in the subject, 2 is returned. Otherwise, and for anchored
+patterns, 0 is returned.
+.sp
+  PCRE2_INFO_FIRSTCODEUNIT
+.sp
+Return the value of the first code unit of any matched string in the situation
+where PCRE2_INFO_FIRSTCODETYPE returns 1; otherwise return 0. The third
+argument should point to an \fBuint32_t\fP variable. In the 8-bit library, the
+value is always less than 256. In the 16-bit library the value can be up to
+0xffff. In the 32-bit library in UTF-32 mode the value can be up to 0x10ffff,
+and up to 0xffffffff when not using UTF-32 mode.
+.sp
+  PCRE2_INFO_FIRSTBITMAP
+.sp
+In the absence of a single first code unit for a non-anchored pattern,
+\fBpcre2_compile()\fP may construct a 256-bit table that defines a fixed set of
+values for the first code unit in any match. For example, a pattern that starts
+with [abc] results in a table with three bits set. When code unit values
+greater than 255 are supported, the flag bit for 255 means "any code unit of
+value 255 or above". If such a table was constructed, a pointer to it is
+returned. Otherwise NULL is returned. The third argument should point to an
+\fBconst uint8_t *\fP variable.
+.sp
+  PCRE2_INFO_HASCRORLF
+.sp
+Return 1 if the pattern contains any explicit matches for CR or LF characters,
+otherwise 0. The third argument should point to an \fBuint32_t\fP variable. An
+explicit match is either a literal CR or LF character, or \er or \en.
+.sp
+  PCRE2_INFO_JCHANGED
+.sp
+Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
+0. The third argument should point to an \fBuint32_t\fP variable. (?J) and
+(?-J) set and unset the local PCRE2_DUPNAMES option, respectively.
+.sp
+  PCRE2_INFO_JITSIZE
+.sp
+If the compiled pattern was successfully processed by
+\fBpcre2_jit_compile()\fP, return the size of the JIT compiled code, otherwise
+return zero. The third argument should point to a \fBsize_t\fP variable.
+.sp
+  PCRE2_INFO_LASTCODETYPE
+.sp
+Returns 1 if there is a rightmost literal code unit that must exist in any
+matched string, other than at its start. The third argument should  point to an
+\fBuint32_t\fP variable. If there is no such value, 0 is returned. When 1 is
+returned, the code unit value itself can be retrieved using
+PCRE2_INFO_LASTCODEUNIT.
+.P
+For anchored patterns, a last literal value is recorded only if it follows
+something of variable length. For example, for the pattern /^a\ed+z\ed+/ the
+returned value is 1 (with "z" returned from PCRE2_INFO_LASTCODEUNIT), but for
+/^a\edz\ed/ the returned value is 0.
+.sp
+  PCRE2_INFO_LASTCODEUNIT
+.sp
+Return the value of the rightmost literal data unit that must exist in any
+matched string, other than at its start, if such a value has been recorded. The
+third argument should point to an \fBuint32_t\fP variable. If there is no such
+value, 0 is returned.
+.sp
+  PCRE2_INFO_MATCHEMPTY
+.sp
+Return 1 if the pattern can match an empty string, otherwise 0. The third
+argument should point to an \fBuint32_t\fP variable.
+.sp
+  PCRE2_INFO_MATCHLIMIT
+.sp
+If the pattern set a match limit by including an item of the form
+(*LIMIT_MATCH=nnnn) at the start, the value is returned. The third argument
+should point to an unsigned 32-bit integer. If no such value has been set, the
+call to \fBpcre2_pattern_info()\fP returns the error PCRE2_ERROR_UNSET.
+.sp
+  PCRE2_INFO_MAXLOOKBEHIND
+.sp
+Return the number of characters (not code units) in the longest lookbehind
+assertion in the pattern. The third argument should point to an unsigned 32-bit
+integer. This information is useful when doing multi-segment matching using the
+partial matching facilities. Note that the simple assertions \eb and \eB
+require a one-character lookbehind. \eA also registers a one-character
+lookbehind, though it does not actually inspect the previous character. This is
+to ensure that at least one character from the old segment is retained when a
+new segment is processed. Otherwise, if there are no lookbehinds in the
+pattern, \eA might match incorrectly at the start of a new segment.
+.sp
+  PCRE2_INFO_MINLENGTH
+.sp
+If a minimum length for matching subject strings was computed, its value is
+returned. Otherwise the returned value is 0. The value is a number of
+characters, which in UTF mode may be different from the number of code units.
+The third argument should point to an \fBuint32_t\fP variable. The value is a
+lower bound to the length of any matching string. There may not be any strings
+of that length that do actually match, but every string that does match is at
+least that long.
+.sp
+  PCRE2_INFO_NAMECOUNT
+  PCRE2_INFO_NAMEENTRYSIZE
+  PCRE2_INFO_NAMETABLE
+.sp
+PCRE2 supports the use of named as well as numbered capturing parentheses. The
+names are just an additional way of identifying the parentheses, which still
+acquire numbers. Several convenience functions such as
+\fBpcre2_substring_get_byname()\fP are provided for extracting captured
+substrings by name. It is also possible to extract the data directly, by first
+converting the name to a number in order to access the correct pointers in the
+output vector (described with \fBpcre2_match()\fP below). To do the conversion,
+you need to use the name-to-number map, which is described by these three
+values.
+.P
+The map consists of a number of fixed-size entries. PCRE2_INFO_NAMECOUNT gives
+the number of entries, and PCRE2_INFO_NAMEENTRYSIZE gives the size of each
+entry in code units; both of these return a \fBuint32_t\fP value. The entry
+size depends on the length of the longest name.
+.P
+PCRE2_INFO_NAMETABLE returns a pointer to the first entry of the table. This is
+a PCRE2_SPTR pointer to a block of code units. In the 8-bit library, the first
+two bytes of each entry are the number of the capturing parenthesis, most
+significant byte first. In the 16-bit library, the pointer points to 16-bit
+code units, the first of which contains the parenthesis number. In the 32-bit
+library, the pointer points to 32-bit code units, the first of which contains
+the parenthesis number. The rest of the entry is the corresponding name, zero
+terminated.
+.P
+The names are in alphabetical order. If (?| is used to create multiple groups
+with the same number, as described in the
+.\" HTML 
+.\" 
+section on duplicate subpattern numbers
+.\"
+in the
+.\" HREF
+\fBpcre2pattern\fP
+.\"
+page, the groups may be given the same name, but there is only one entry in the
+table. Different names for groups of the same number are not permitted.
+.P
+Duplicate names for subpatterns with different numbers are permitted, but only
+if PCRE2_DUPNAMES is set. They appear in the table in the order in which they
+were found in the pattern. In the absence of (?| this is the order of
+increasing number; when (?| is used this is not necessarily the case because
+later subpatterns may have lower numbers.
+.P
+As a simple example of the name/number table, consider the following pattern
+after compilation by the 8-bit library (assume PCRE2_EXTENDED is set, so white
+space - including newlines - is ignored):
+.sp
+.\" JOIN
+  (? (?(\ed\ed)?\ed\ed) -
+  (?\ed\ed) - (?\ed\ed) )
+.sp
+There are four named subpatterns, so the table has four entries, and each entry
+in the table is eight bytes long. The table is as follows, with non-printing
+bytes shows in hexadecimal, and undefined bytes shown as ??:
+.sp
+  00 01 d  a  t  e  00 ??
+  00 05 d  a  y  00 ?? ??
+  00 04 m  o  n  t  h  00
+  00 02 y  e  a  r  00 ??
+.sp
+When writing code to extract data from named subpatterns using the
+name-to-number map, remember that the length of the entries is likely to be
+different for each compiled pattern.
+.sp
+  PCRE2_INFO_NEWLINE
+.sp
+The output is a \fBuint32_t\fP with one of the following values:
+.sp
+  PCRE2_NEWLINE_CR       Carriage return (CR)
+  PCRE2_NEWLINE_LF       Linefeed (LF)
+  PCRE2_NEWLINE_CRLF     Carriage return, linefeed (CRLF)
+  PCRE2_NEWLINE_ANY      Any Unicode line ending
+  PCRE2_NEWLINE_ANYCRLF  Any of CR, LF, or CRLF
+.sp
+This specifies the default character sequence that will be recognized as
+meaning "newline" while matching.
+.sp
+  PCRE2_INFO_RECURSIONLIMIT
+.sp
+If the pattern set a recursion limit by including an item of the form
+(*LIMIT_RECURSION=nnnn) at the start, the value is returned. The third
+argument should point to an unsigned 32-bit integer. If no such value has been
+set, the call to \fBpcre2_pattern_info()\fP returns the error PCRE2_ERROR_UNSET.
+.sp
+  PCRE2_INFO_SIZE
+.sp
+Return the size of the compiled pattern in bytes (for all three libraries). The
+third argument should point to a \fBsize_t\fP variable. This value includes the
+size of the general data block that precedes the code units of the compiled
+pattern itself. The value that is used when \fBpcre2_compile()\fP is getting
+memory in which to place the compiled pattern may be slightly larger than the
+value returned by this option, because there are cases where the code that
+calculates the size has to over-estimate. Processing a pattern with the JIT
+compiler does not alter the value returned by this option.
+.
+.
+.\" HTML 
+.SH "INFORMATION ABOUT A PATTERN'S CALLOUTS"
+.rs
+.sp
+.nf
+.B int pcre2_callout_enumerate(const pcre2_code *\fIcode\fP,
+.B "  int (*\fIcallback\fP)(pcre2_callout_enumerate_block *, void *),"
+.B "  void *\fIuser_data\fP);"
+.fi
+.sp
+A script language that supports the use of string arguments in callouts might
+like to scan all the callouts in a pattern before running the match. This can
+be done by calling \fBpcre2_callout_enumerate()\fP. The first argument is a
+pointer to a compiled pattern, the second points to a callback function, and
+the third is arbitrary user data. The callback function is called for every
+callout in the pattern in the order in which they appear. Its first argument is
+a pointer to a callout enumeration block, and its second argument is the
+\fIuser_data\fP value that was passed to \fBpcre2_callout_enumerate()\fP. The
+contents of the callout enumeration block are described in the
+.\" HREF
+\fBpcre2callout\fP
+.\"
+documentation, which also gives further details about callouts.
+.
+.
+.SH "SERIALIZATION AND PRECOMPILING"
+.rs
+.sp
+It is possible to save compiled patterns on disc or elsewhere, and reload them
+later, subject to a number of restrictions. The functions whose names begin
+with \fBpcre2_serialize_\fP are used for this purpose. They are described in
+the
+.\" HREF
+\fBpcre2serialize\fP
+.\"
+documentation.
+.
+.
+.\" HTML 
+.SH "THE MATCH DATA BLOCK"
+.rs
+.sp
+.nf
+.B pcre2_match_data_create(uint32_t \fIovecsize\fP,
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.sp
+.B pcre2_match_data_create_from_pattern(const pcre2_code *\fIcode\fP,
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.sp
+.B void pcre2_match_data_free(pcre2_match_data *\fImatch_data\fP);
+.fi
+.P
+Information about a successful or unsuccessful match is placed in a match
+data block, which is an opaque structure that is accessed by function calls. In
+particular, the match data block contains a vector of offsets into the subject
+string that define the matched part of the subject and any substrings that were
+captured. This is know as the \fIovector\fP.
+.P
+Before calling \fBpcre2_match()\fP, \fBpcre2_dfa_match()\fP, or
+\fBpcre2_jit_match()\fP you must create a match data block by calling one of
+the creation functions above. For \fBpcre2_match_data_create()\fP, the first
+argument is the number of pairs of offsets in the \fIovector\fP. One pair of
+offsets is required to identify the string that matched the whole pattern, with
+another pair for each captured substring. For example, a value of 4 creates
+enough space to record the matched portion of the subject plus three captured
+substrings. A minimum of at least 1 pair is imposed by
+\fBpcre2_match_data_create()\fP, so it is always possible to return the overall
+matched string.
+.P
+The second argument of \fBpcre2_match_data_create()\fP is a pointer to a
+general context, which can specify custom memory management for obtaining the
+memory for the match data block. If you are not using custom memory management,
+pass NULL, which causes \fBmalloc()\fP to be used.
+.P
+For \fBpcre2_match_data_create_from_pattern()\fP, the first argument is a
+pointer to a compiled pattern. The ovector is created to be exactly the right
+size to hold all the substrings a pattern might capture. The second argument is
+again a pointer to a general context, but in this case if NULL is passed, the
+memory is obtained using the same allocator that was used for the compiled
+pattern (custom or default).
+.P
+A match data block can be used many times, with the same or different compiled
+patterns. You can extract information from a match data block after a match
+operation has finished, using functions that are described in the sections on
+.\" HTML 
+.\" 
+matched strings
+.\"
+and
+.\" HTML 
+.\" 
+other match data
+.\"
+below.
+.P
+When a call of \fBpcre2_match()\fP fails, valid data is available in the match
+block only when the error is PCRE2_ERROR_NOMATCH, PCRE2_ERROR_PARTIAL, or one
+of the error codes for an invalid UTF string. Exactly what is available depends
+on the error, and is detailed below.
+.P
+When one of the matching functions is called, pointers to the compiled pattern
+and the subject string are set in the match data block so that they can be
+referenced by the extraction functions. After running a match, you must not
+free a compiled pattern or a subject string until after all operations on the
+match data block (for that match) have taken place.
+.P
+When a match data block itself is no longer needed, it should be freed by
+calling \fBpcre2_match_data_free()\fP.
+.
+.
+.SH "MATCHING A PATTERN: THE TRADITIONAL FUNCTION"
+.rs
+.sp
+.nf
+.B int pcre2_match(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
+.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
+.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
+.B "  pcre2_match_context *\fImcontext\fP);"
+.fi
+.P
+The function \fBpcre2_match()\fP is called to match a subject string against a
+compiled pattern, which is passed in the \fIcode\fP argument. You can call
+\fBpcre2_match()\fP with the same \fIcode\fP argument as many times as you
+like, in order to find multiple matches in the subject string or to match
+different subject strings with the same pattern.
+.P
+This function is the main matching facility of the library, and it operates in
+a Perl-like manner. For specialist use there is also an alternative matching
+function, which is described
+.\" HTML 
+.\" 
+below
+.\"
+in the section about the \fBpcre2_dfa_match()\fP function.
+.P
+Here is an example of a simple call to \fBpcre2_match()\fP:
+.sp
+  pcre2_match_data *md = pcre2_match_data_create(4, NULL);
+  int rc = pcre2_match(
+    re,             /* result of pcre2_compile() */
+    "some string",  /* the subject string */
+    11,             /* the length of the subject string */
+    0,              /* start at offset 0 in the subject */
+    0,              /* default options */
+    match_data,     /* the match data block */
+    NULL);          /* a match context; NULL means use defaults */
+.sp
+If the subject string is zero-terminated, the length can be given as
+PCRE2_ZERO_TERMINATED. A match context must be provided if certain less common
+matching parameters are to be changed. For details, see the section on
+.\" HTML 
+.\" 
+the match context
+.\"
+above.
+.
+.
+.SS "The string to be matched by \fBpcre2_match()\fP"
+.rs
+.sp
+The subject string is passed to \fBpcre2_match()\fP as a pointer in
+\fIsubject\fP, a length in \fIlength\fP, and a starting offset in
+\fIstartoffset\fP. The length and offset are in code units, not characters.
+That is, they are in bytes for the 8-bit library, 16-bit code units for the
+16-bit library, and 32-bit code units for the 32-bit library, whether or not
+UTF processing is enabled.
+.P
+If \fIstartoffset\fP is greater than the length of the subject,
+\fBpcre2_match()\fP returns PCRE2_ERROR_BADOFFSET. When the starting offset is
+zero, the search for a match starts at the beginning of the subject, and this
+is by far the most common case. In UTF-8 or UTF-16 mode, the starting offset
+must point to the start of a character, or to the end of the subject (in UTF-32
+mode, one code unit equals one character, so all offsets are valid). Like the
+pattern string, the subject may contain binary zeroes.
+.P
+A non-zero starting offset is useful when searching for another match in the
+same subject by calling \fBpcre2_match()\fP again after a previous success.
+Setting \fIstartoffset\fP differs from passing over a shortened string and
+setting PCRE2_NOTBOL in the case of a pattern that begins with any kind of
+lookbehind. For example, consider the pattern
+.sp
+  \eBiss\eB
+.sp
+which finds occurrences of "iss" in the middle of words. (\eB matches only if
+the current position in the subject is not a word boundary.) When applied to
+the string "Mississipi" the first call to \fBpcre2_match()\fP finds the first
+occurrence. If \fBpcre2_match()\fP is called again with just the remainder of
+the subject, namely "issipi", it does not match, because \eB is always false at
+the start of the subject, which is deemed to be a word boundary. However, if
+\fBpcre2_match()\fP is passed the entire string again, but with
+\fIstartoffset\fP set to 4, it finds the second occurrence of "iss" because it
+is able to look behind the starting point to discover that it is preceded by a
+letter.
+.P
+Finding all the matches in a subject is tricky when the pattern can match an
+empty string. It is possible to emulate Perl's /g behaviour by first trying the
+match again at the same offset, with the PCRE2_NOTEMPTY_ATSTART and
+PCRE2_ANCHORED options, and then if that fails, advancing the starting offset
+and trying an ordinary match again. There is some code that demonstrates how to
+do this in the
+.\" HREF
+\fBpcre2demo\fP
+.\"
+sample program. In the most general case, you have to check to see if the
+newline convention recognizes CRLF as a newline, and if so, and the current
+character is CR followed by LF, advance the starting offset by two characters
+instead of one.
+.P
+If a non-zero starting offset is passed when the pattern is anchored, one
+attempt to match at the given offset is made. This can only succeed if the
+pattern does not require the match to be at the start of the subject.
+.
+.
+.\" HTML 
+.SS "Option bits for \fBpcre2_match()\fP"
+.rs
+.sp
+The unused bits of the \fIoptions\fP argument for \fBpcre2_match()\fP must be
+zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL,
+PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_UTF_CHECK,
+PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. Their action is described below.
+.P
+Setting PCRE2_ANCHORED at match time is not supported by the just-in-time (JIT)
+compiler. If it is set, JIT matching is disabled and the normal interpretive
+code in \fBpcre2_match()\fP is run. The remaining options are supported for JIT
+matching.
+.sp
+  PCRE2_ANCHORED
+.sp
+The PCRE2_ANCHORED option limits \fBpcre2_match()\fP to matching at the first
+matching position. If a pattern was compiled with PCRE2_ANCHORED, or turned out
+to be anchored by virtue of its contents, it cannot be made unachored at
+matching time. Note that setting the option at match time disables JIT
+matching.
+.sp
+  PCRE2_NOTBOL
+.sp
+This option specifies that first character of the subject string is not the
+beginning of a line, so the circumflex metacharacter should not match before
+it. Setting this without having set PCRE2_MULTILINE at compile time causes
+circumflex never to match. This option affects only the behaviour of the
+circumflex metacharacter. It does not affect \eA.
+.sp
+  PCRE2_NOTEOL
+.sp
+This option specifies that the end of the subject string is not the end of a
+line, so the dollar metacharacter should not match it nor (except in multiline
+mode) a newline immediately before it. Setting this without having set
+PCRE2_MULTILINE at compile time causes dollar never to match. This option
+affects only the behaviour of the dollar metacharacter. It does not affect \eZ
+or \ez.
+.sp
+  PCRE2_NOTEMPTY
+.sp
+An empty string is not considered to be a valid match if this option is set. If
+there are alternatives in the pattern, they are tried. If all the alternatives
+match the empty string, the entire match fails. For example, if the pattern
+.sp
+  a?b?
+.sp
+is applied to a string not beginning with "a" or "b", it matches an empty
+string at the start of the subject. With PCRE2_NOTEMPTY set, this match is not
+valid, so \fBpcre2_match()\fP searches further into the string for occurrences
+of "a" or "b".
+.sp
+  PCRE2_NOTEMPTY_ATSTART
+.sp
+This is like PCRE2_NOTEMPTY, except that it locks out an empty string match
+only at the first matching position, that is, at the start of the subject plus
+the starting offset. An empty string match later in the subject is permitted.
+If the pattern is anchored, such a match can occur only if the pattern contains
+\eK.
+.sp
+  PCRE2_NO_UTF_CHECK
+.sp
+When PCRE2_UTF is set at compile time, the validity of the subject as a UTF
+string is checked by default when \fBpcre2_match()\fP is subsequently called.
+The entire string is checked before any other processing takes place, and a
+negative error code is returned if the check fails. There are several UTF error
+codes for each code unit width, corresponding to different problems with the
+code unit sequence. The value of \fIstartoffset\fP is also checked, to ensure
+that it points to the start of a character or to the end of the subject. There
+are discussions about the validity of
+.\" HTML 
+.\" 
+UTF-8 strings,
+.\"
+.\" HTML 
+.\" 
+UTF-16 strings,
+.\"
+and
+.\" HTML 
+.\" 
+UTF-32 strings
+.\"
+in the
+.\" HREF
+\fBpcre2unicode\fP
+.\"
+page.
+.P
+If you know that your subject is valid, and you want to skip these checks for
+performance reasons, you can set the PCRE2_NO_UTF_CHECK option when calling
+\fBpcre2_match()\fP. You might want to do this for the second and subsequent
+calls to \fBpcre2_match()\fP if you are making repeated calls to find all the
+matches in a single subject string.
+.P
+NOTE: When PCRE2_NO_UTF_CHECK is set, the effect of passing an invalid string
+as a subject, or an invalid value of \fIstartoffset\fP, is undefined. Your
+program may crash or loop indefinitely.
+.sp
+  PCRE2_PARTIAL_HARD
+  PCRE2_PARTIAL_SOFT
+.sp
+These options turn on the partial matching feature. A partial match occurs if
+the end of the subject string is reached successfully, but there are not enough
+subject characters to complete the match. If this happens when
+PCRE2_PARTIAL_SOFT (but not PCRE2_PARTIAL_HARD) is set, matching continues by
+testing any remaining alternatives. Only if no complete match can be found is
+PCRE2_ERROR_PARTIAL returned instead of PCRE2_ERROR_NOMATCH. In other words,
+PCRE2_PARTIAL_SOFT specifies that the caller is prepared to handle a partial
+match, but only if no complete match can be found.
+.P
+If PCRE2_PARTIAL_HARD is set, it overrides PCRE2_PARTIAL_SOFT. In this case, if
+a partial match is found, \fBpcre2_match()\fP immediately returns
+PCRE2_ERROR_PARTIAL, without considering any other alternatives. In other
+words, when PCRE2_PARTIAL_HARD is set, a partial match is considered to be more
+important that an alternative complete match.
+.P
+There is a more detailed discussion of partial and multi-segment matching, with
+examples, in the
+.\" HREF
+\fBpcre2partial\fP
+.\"
+documentation.
+.
+.
+.
+.SH "NEWLINE HANDLING WHEN MATCHING"
+.rs
+.sp
+When PCRE2 is built, a default newline convention is set; this is usually the
+standard convention for the operating system. The default can be overridden in
+a
+.\" HTML 
+.\" 
+compile context.
+.\"
+During matching, the newline choice affects the behaviour of the dot,
+circumflex, and dollar metacharacters. It may also alter the way the match
+starting position is advanced after a match failure for an unanchored pattern.
+.P
+When PCRE2_NEWLINE_CRLF, PCRE2_NEWLINE_ANYCRLF, or PCRE2_NEWLINE_ANY is set as
+the newline convention, and a match attempt for an unanchored pattern fails
+when the current starting position is at a CRLF sequence, and the pattern
+contains no explicit matches for CR or LF characters, the match position is
+advanced by two characters instead of one, in other words, to after the CRLF.
+.P
+The above rule is a compromise that makes the most common cases work as
+expected. For example, if the pattern is .+A (and the PCRE2_DOTALL option is
+not set), it does not match the string "\er\enA" because, after failing at the
+start, it skips both the CR and the LF before retrying. However, the pattern
+[\er\en]A does match that string, because it contains an explicit CR or LF
+reference, and so advances only by one character after the first failure.
+.P
+An explicit match for CR of LF is either a literal appearance of one of those
+characters in the pattern, or one of the \er or \en escape sequences. Implicit
+matches such as [^X] do not count, nor does \es, even though it includes CR and
+LF in the characters that it matches.
+.P
+Notwithstanding the above, anomalous effects may still occur when CRLF is a
+valid newline sequence and explicit \er or \en escapes appear in the pattern.
+.
+.
+.\" HTML 
+.SH "HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS"
+.rs
+.sp
+.nf
+.B uint32_t pcre2_get_ovector_count(pcre2_match_data *\fImatch_data\fP);
+.sp
+.B PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *\fImatch_data\fP);
+.fi
+.P
+In general, a pattern matches a certain portion of the subject, and in
+addition, further substrings from the subject may be picked out by
+parenthesized parts of the pattern. Following the usage in Jeffrey Friedl's
+book, this is called "capturing" in what follows, and the phrase "capturing
+subpattern" or "capturing group" is used for a fragment of a pattern that picks
+out a substring. PCRE2 supports several other kinds of parenthesized subpattern
+that do not cause substrings to be captured. The \fBpcre2_pattern_info()\fP
+function can be used to find out how many capturing subpatterns there are in a
+compiled pattern.
+.P
+A successful match returns the overall matched string and any captured
+substrings to the caller via a vector of PCRE2_SIZE values. This is called the
+\fBovector\fP, and is contained within the
+.\" HTML 
+.\" 
+match data block.
+.\"
+You can obtain direct access to the ovector by calling
+\fBpcre2_get_ovector_pointer()\fP to find its address, and
+\fBpcre2_get_ovector_count()\fP to find the number of pairs of values it
+contains. Alternatively, you can use the auxiliary functions for accessing
+captured substrings
+.\" HTML 
+.\" 
+by number
+.\"
+or
+.\" HTML 
+.\" 
+by name
+.\"
+(see below).
+.P
+Within the ovector, the first in each pair of values is set to the offset of
+the first code unit of a substring, and the second is set to the offset of the
+first code unit after the end of a substring. These values are always code unit
+offsets, not character offsets. That is, they are byte offsets in the 8-bit
+library, 16-bit offsets in the 16-bit library, and 32-bit offsets in the 32-bit
+library.
+.P
+After a partial match (error return PCRE2_ERROR_PARTIAL), only the first pair
+of offsets (that is, \fIovector[0]\fP and \fIovector[1]\fP) are set. They
+identify the part of the subject that was partially matched. See the
+.\" HREF
+\fBpcre2partial\fP
+.\"
+documentation for details of partial matching.
+.P
+After a successful match, the first pair of offsets identifies the portion of
+the subject string that was matched by the entire pattern. The next pair is
+used for the first capturing subpattern, and so on. The value returned by
+\fBpcre2_match()\fP is one more than the highest numbered pair that has been
+set. For example, if two substrings have been captured, the returned value is
+3. If there are no capturing subpatterns, the return value from a successful
+match is 1, indicating that just the first pair of offsets has been set.
+.P
+If a pattern uses the \eK escape sequence within a positive assertion, the
+reported start of a successful match can be greater than the end of the match.
+For example, if the pattern (?=ab\eK) is matched against "ab", the start and
+end offset values for the match are 2 and 0.
+.P
+If a capturing subpattern group is matched repeatedly within a single match
+operation, it is the last portion of the subject that it matched that is
+returned.
+.P
+If the ovector is too small to hold all the captured substring offsets, as much
+as possible is filled in, and the function returns a value of zero. If captured
+substrings are not of interest, \fBpcre2_match()\fP may be called with a match
+data block whose ovector is of minimum length (that is, one pair). However, if
+the pattern contains back references and the \fIovector\fP is not big enough to
+remember the related substrings, PCRE2 has to get additional memory for use
+during matching. Thus it is usually advisable to set up a match data block
+containing an ovector of reasonable size.
+.P
+It is possible for capturing subpattern number \fIn+1\fP to match some part of
+the subject when subpattern \fIn\fP has not been used at all. For example, if
+the string "abc" is matched against the pattern (a|(z))(bc) the return from the
+function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
+happens, both values in the offset pairs corresponding to unused subpatterns
+are set to PCRE2_UNSET.
+.P
+Offset values that correspond to unused subpatterns at the end of the
+expression are also set to PCRE2_UNSET. For example, if the string "abc" is
+matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched.
+The return from the function is 2, because the highest used capturing
+subpattern number is 1. The offsets for for the second and third capturing
+subpatterns (assuming the vector is large enough, of course) are set to
+PCRE2_UNSET.
+.P
+Elements in the ovector that do not correspond to capturing parentheses in the
+pattern are never changed. That is, if a pattern contains \fIn\fP capturing
+parentheses, no more than \fIovector[0]\fP to \fIovector[2n+1]\fP are set by
+\fBpcre2_match()\fP. The other elements retain whatever values they previously
+had.
+.
+.
+.\" HTML 
+.SH "OTHER INFORMATION ABOUT A MATCH"
+.rs
+.sp
+.nf
+.B PCRE2_SPTR pcre2_get_mark(pcre2_match_data *\fImatch_data\fP);
+.sp
+.B PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *\fImatch_data\fP);
+.fi
+.P
+As well as the offsets in the ovector, other information about a match is
+retained in the match data block and can be retrieved by the above functions in
+appropriate circumstances. If they are called at other times, the result is
+undefined.
+.P
+After a successful match, a partial match (PCRE2_ERROR_PARTIAL), or a failure
+to match (PCRE2_ERROR_NOMATCH), a (*MARK) name may be available, and
+\fBpcre2_get_mark()\fP can be called. It returns a pointer to the
+zero-terminated name, which is within the compiled pattern. Otherwise NULL is
+returned. After a successful match, the (*MARK) name that is returned is the
+last one encountered on the matching path through the pattern. After a "no
+match" or a partial match, the last encountered (*MARK) name is returned. For
+example, consider this pattern:
+.sp
+  ^(*MARK:A)((*MARK:B)a|b)c
+.sp
+When it matches "bc", the returned mark is A. The B mark is "seen" in the first
+branch of the group, but it is not on the matching path. On the other hand,
+when this pattern fails to match "bx", the returned mark is B.
+.P
+After a successful match, a partial match, or one of the invalid UTF errors
+(for example, PCRE2_ERROR_UTF8_ERR5), \fBpcre2_get_startchar()\fP can be
+called. After a successful or partial match it returns the code unit offset of
+the character at which the match started. For a non-partial match, this can be
+different to the value of \fIovector[0]\fP if the pattern contains the \eK
+escape sequence. After a partial match, however, this value is always the same
+as \fIovector[0]\fP because \eK does not affect the result of a partial match.
+.P
+After a UTF check failure, \fBpcre2_get_startchar()\fB can be used to obtain
+the code unit offset of the invalid UTF character. Details are given in the
+.\" HREF
+\fBpcre2unicode\fP
+.\"
+page.
+.
+.
+.\" HTML 
+.SH "ERROR RETURNS FROM \fBpcre2_match()\fP"
+.rs
+.sp
+If \fBpcre2_match()\fP fails, it returns a negative number. This can be
+converted to a text string by calling \fBpcre2_get_error_message()\fP. Negative
+error codes are also returned by other functions, and are documented with them.
+The codes are given names in the header file. If UTF checking is in force and
+an invalid UTF subject string is detected, one of a number of UTF-specific
+negative error codes is returned. Details are given in the
+.\" HREF
+\fBpcre2unicode\fP
+.\"
+page. The following are the other errors that may be returned by
+\fBpcre2_match()\fP:
+.sp
+  PCRE2_ERROR_NOMATCH
+.sp
+The subject string did not match the pattern.
+.sp
+  PCRE2_ERROR_PARTIAL
+.sp
+The subject string did not match, but it did match partially. See the
+.\" HREF
+\fBpcre2partial\fP
+.\"
+documentation for details of partial matching.
+.sp
+  PCRE2_ERROR_BADMAGIC
+.sp
+PCRE2 stores a 4-byte "magic number" at the start of the compiled code, to
+catch the case when it is passed a junk pointer. This is the error that is
+returned when the magic number is not present.
+.sp
+  PCRE2_ERROR_BADMODE
+.sp
+This error is given when a pattern that was compiled by the 8-bit library is
+passed to a 16-bit or 32-bit library function, or vice versa.
+.sp
+  PCRE2_ERROR_BADOFFSET
+.sp
+The value of \fIstartoffset\fP was greater than the length of the subject.
+.sp
+  PCRE2_ERROR_BADOPTION
+.sp
+An unrecognized bit was set in the \fIoptions\fP argument.
+.sp
+  PCRE2_ERROR_BADUTFOFFSET
+.sp
+The UTF code unit sequence that was passed as a subject was checked and found
+to be valid (the PCRE2_NO_UTF_CHECK option was not set), but the value of
+\fIstartoffset\fP did not point to the beginning of a UTF character or the end
+of the subject.
+.sp
+  PCRE2_ERROR_CALLOUT
+.sp
+This error is never generated by \fBpcre2_match()\fP itself. It is provided for
+use by callout functions that want to cause \fBpcre2_match()\fP or
+\fBpcre2_callout_enumerate()\fP to return a distinctive error code. See the
+.\" HREF
+\fBpcre2callout\fP
+.\"
+documentation for details.
+.sp
+  PCRE2_ERROR_INTERNAL
+.sp
+An unexpected internal error has occurred. This error could be caused by a bug
+in PCRE2 or by overwriting of the compiled pattern.
+.sp
+  PCRE2_ERROR_JIT_BADOPTION
+.sp
+This error is returned when a pattern that was successfully studied using JIT
+is being matched, but the matching mode (partial or complete match) does not
+correspond to any JIT compilation mode. When the JIT fast path function is
+used, this error may be also given for invalid options. See the
+.\" HREF
+\fBpcre2jit\fP
+.\"
+documentation for more details.
+.sp
+  PCRE2_ERROR_JIT_STACKLIMIT
+.sp
+This error is returned when a pattern that was successfully studied using JIT
+is being matched, but the memory available for the just-in-time processing
+stack is not large enough. See the
+.\" HREF
+\fBpcre2jit\fP
+.\"
+documentation for more details.
+.sp
+  PCRE2_ERROR_MATCHLIMIT
+.sp
+The backtracking limit was reached.
+.sp
+  PCRE2_ERROR_NOMEMORY
+.sp
+If a pattern contains back references, but the ovector is not big enough to
+remember the referenced substrings, PCRE2 gets a block of memory at the start
+of matching to use for this purpose. There are some other special cases where
+extra memory is needed during matching. This error is given when memory cannot
+be obtained.
+.sp
+  PCRE2_ERROR_NULL
+.sp
+Either the \fIcode\fP, \fIsubject\fP, or \fImatch_data\fP argument was passed
+as NULL.
+.sp
+  PCRE2_ERROR_RECURSELOOP
+.sp
+This error is returned when \fBpcre2_match()\fP detects a recursion loop within
+the pattern. Specifically, it means that either the whole pattern or a
+subpattern has been called recursively for the second time at the same position
+in the subject string. Some simple patterns that might do this are detected and
+faulted at compile time, but more complicated cases, in particular mutual
+recursions between two different subpatterns, cannot be detected until matching
+is attempted.
+.sp
+  PCRE2_ERROR_RECURSIONLIMIT
+.sp
+The internal recursion limit was reached.
+.
+.
+.\" HTML 
+.SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
+.rs
+.sp
+.nf
+.B int pcre2_substring_length_bynumber(pcre2_match_data *\fImatch_data\fP,
+.B "  uint32_t \fInumber\fP, PCRE2_SIZE *\fIlength\fP);"
+.sp
+.B int pcre2_substring_copy_bynumber(pcre2_match_data *\fImatch_data\fP,
+.B "  uint32_t \fInumber\fP, PCRE2_UCHAR *\fIbuffer\fP,"
+.B "  PCRE2_SIZE *\fIbufflen\fP);"
+.sp
+.B int pcre2_substring_get_bynumber(pcre2_match_data *\fImatch_data\fP,
+.B "  uint32_t \fInumber\fP, PCRE2_UCHAR **\fIbufferptr\fP,"
+.B "  PCRE2_SIZE *\fIbufflen\fP);"
+.sp
+.B void pcre2_substring_free(PCRE2_UCHAR *\fIbuffer\fP);
+.fi
+.P
+Captured substrings can be accessed directly by using the ovector as described
+.\" HTML 
+.\" 
+above.
+.\"
+For convenience, auxiliary functions are provided for extracting captured
+substrings as new, separate, zero-terminated strings. A substring that contains
+a binary zero is correctly extracted and has a further zero added on the end,
+but the result is not, of course, a C string.
+.P
+The functions in this section identify substrings by number. The number zero
+refers to the entire matched substring, with higher numbers referring to
+substrings captured by parenthesized groups. After a partial match, only
+substring zero is available. An attempt to extract any other substring gives
+the error PCRE2_ERROR_PARTIAL. The next section describes similar functions for
+extracting captured substrings by name.
+.P
+If a pattern uses the \eK escape sequence within a positive assertion, the
+reported start of a successful match can be greater than the end of the match.
+For example, if the pattern (?=ab\eK) is matched against "ab", the start and
+end offset values for the match are 2 and 0. In this situation, calling these
+functions with a zero substring number extracts a zero-length empty string.
+.P
+You can find the length in code units of a captured substring without
+extracting it by calling \fBpcre2_substring_length_bynumber()\fP. The first
+argument is a pointer to the match data block, the second is the group number,
+and the third is a pointer to a variable into which the length is placed. If
+you just want to know whether or not the substring has been captured, you can
+pass the third argument as NULL.
+.P
+The \fBpcre2_substring_copy_bynumber()\fP function copies a captured substring
+into a supplied buffer, whereas \fBpcre2_substring_get_bynumber()\fP copies it
+into new memory, obtained using the same memory allocation function that was
+used for the match data block. The first two arguments of these functions are a
+pointer to the match data block and a capturing group number.
+.P
+The final arguments of \fBpcre2_substring_copy_bynumber()\fP are a pointer to
+the buffer and a pointer to a variable that contains its length in code units.
+This is updated to contain the actual number of code units used for the
+extracted substring, excluding the terminating zero.
+.P
+For \fBpcre2_substring_get_bynumber()\fP the third and fourth arguments point
+to variables that are updated with a pointer to the new memory and the number
+of code units that comprise the substring, again excluding the terminating
+zero. When the substring is no longer needed, the memory should be freed by
+calling \fBpcre2_substring_free()\fP.
+.P
+The return value from all these functions is zero for success, or a negative
+error code. If the pattern match failed, the match failure code is returned.
+If a substring number greater than zero is used after a partial match,
+PCRE2_ERROR_PARTIAL is returned. Other possible error codes are:
+.sp
+  PCRE2_ERROR_NOMEMORY
+.sp
+The buffer was too small for \fBpcre2_substring_copy_bynumber()\fP, or the
+attempt to get memory failed for \fBpcre2_substring_get_bynumber()\fP.
+.sp
+  PCRE2_ERROR_NOSUBSTRING
+.sp
+There is no substring with that number in the pattern, that is, the number is
+greater than the number of capturing parentheses.
+.sp
+  PCRE2_ERROR_UNAVAILABLE
+.sp
+The substring number, though not greater than the number of captures in the
+pattern, is greater than the number of slots in the ovector, so the substring
+could not be captured.
+.sp
+  PCRE2_ERROR_UNSET
+.sp
+The substring did not participate in the match. For example, if the pattern is
+(abc)|(def) and the subject is "def", and the ovector contains at least two
+capturing slots, substring number 1 is unset.
+.
+.
+.SH "EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS"
+.rs
+.sp
+.nf
+.B int pcre2_substring_list_get(pcre2_match_data *\fImatch_data\fP,
+.B "  PCRE2_UCHAR ***\fIlistptr\fP, PCRE2_SIZE **\fIlengthsptr\fP);
+.sp
+.B void pcre2_substring_list_free(PCRE2_SPTR *\fIlist\fP);
+.fi
+.P
+The \fBpcre2_substring_list_get()\fP function extracts all available substrings
+and builds a list of pointers to them. It also (optionally) builds a second
+list that contains their lengths (in code units), excluding a terminating zero
+that is added to each of them. All this is done in a single block of memory
+that is obtained using the same memory allocation function that was used to get
+the match data block.
+.P
+This function must be called only after a successful match. If called after a
+partial match, the error code PCRE2_ERROR_PARTIAL is returned.
+.P
+The address of the memory block is returned via \fIlistptr\fP, which is also
+the start of the list of string pointers. The end of the list is marked by a
+NULL pointer. The address of the list of lengths is returned via
+\fIlengthsptr\fP. If your strings do not contain binary zeros and you do not
+therefore need the lengths, you may supply NULL as the \fBlengthsptr\fP
+argument to disable the creation of a list of lengths. The yield of the
+function is zero if all went well, or PCRE2_ERROR_NOMEMORY if the memory block
+could not be obtained. When the list is no longer needed, it should be freed by
+calling \fBpcre2_substring_list_free()\fP.
+.P
+If this function encounters a substring that is unset, which can happen when
+capturing subpattern number \fIn+1\fP matches some part of the subject, but
+subpattern \fIn\fP has not been used at all, it returns an empty string. This
+can be distinguished from a genuine zero-length substring by inspecting the
+appropriate offset in the ovector, which contain PCRE2_UNSET for unset
+substrings, or by calling \fBpcre2_substring_length_bynumber()\fP.
+.
+.
+.\" HTML 
+.SH "EXTRACTING CAPTURED SUBSTRINGS BY NAME"
+.rs
+.sp
+.nf
+.B int pcre2_substring_number_from_name(const pcre2_code *\fIcode\fP,
+.B "  PCRE2_SPTR \fIname\fP);"
+.sp
+.B int pcre2_substring_length_byname(pcre2_match_data *\fImatch_data\fP,
+.B "  PCRE2_SPTR \fIname\fP, PCRE2_SIZE *\fIlength\fP);"
+.sp
+.B int pcre2_substring_copy_byname(pcre2_match_data *\fImatch_data\fP,
+.B "  PCRE2_SPTR \fIname\fP, PCRE2_UCHAR *\fIbuffer\fP, PCRE2_SIZE *\fIbufflen\fP);"
+.sp
+.B int pcre2_substring_get_byname(pcre2_match_data *\fImatch_data\fP,
+.B "  PCRE2_SPTR \fIname\fP, PCRE2_UCHAR **\fIbufferptr\fP, PCRE2_SIZE *\fIbufflen\fP);"
+.sp
+.B void pcre2_substring_free(PCRE2_UCHAR *\fIbuffer\fP);
+.fi
+.P
+To extract a substring by name, you first have to find associated number.
+For example, for this pattern:
+.sp
+  (a+)b(?\ed+)...
+.sp
+the number of the subpattern called "xxx" is 2. If the name is known to be
+unique (PCRE2_DUPNAMES was not set), you can find the number from the name by
+calling \fBpcre2_substring_number_from_name()\fP. The first argument is the
+compiled pattern, and the second is the name. The yield of the function is the
+subpattern number, PCRE2_ERROR_NOSUBSTRING if there is no subpattern of that
+name, or PCRE2_ERROR_NOUNIQUESUBSTRING if there is more than one subpattern of
+that name. Given the number, you can extract the substring directly, or use one
+of the functions described above.
+.P
+For convenience, there are also "byname" functions that correspond to the
+"bynumber" functions, the only difference being that the second argument is a
+name instead of a number. If PCRE2_DUPNAMES is set and there are duplicate
+names, these functions scan all the groups with the given name, and return the
+first named string that is set.
+.P
+If there are no groups with the given name, PCRE2_ERROR_NOSUBSTRING is
+returned. If all groups with the name have numbers that are greater than the
+number of slots in the ovector, PCRE2_ERROR_UNAVAILABLE is returned. If there
+is at least one group with a slot in the ovector, but no group is found to be
+set, PCRE2_ERROR_UNSET is returned.
+.P
+\fBWarning:\fP If the pattern uses the (?| feature to set up multiple
+subpatterns with the same number, as described in the
+.\" HTML 
+.\" 
+section on duplicate subpattern numbers
+.\"
+in the
+.\" HREF
+\fBpcre2pattern\fP
+.\"
+page, you cannot use names to distinguish the different subpatterns, because
+names are not included in the compiled code. The matching process uses only
+numbers. For this reason, the use of different names for subpatterns of the
+same number causes an error at compile time.
+.
+.
+.SH "CREATING A NEW STRING WITH SUBSTITUTIONS"
+.rs
+.sp
+.nf
+.B int pcre2_substitute(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
+.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
+.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
+.B "  pcre2_match_context *\fImcontext\fP, PCRE2_SPTR \fIreplacementzfP,"
+.B "  PCRE2_SIZE \fIrlength\fP, PCRE2_UCHAR *\fIoutputbuffer\zfP,"
+.B "  PCRE2_SIZE *\fIoutlengthptr\fP);"
+.fi
+This function calls \fBpcre2_match()\fP and then makes a copy of the subject
+string in \fIoutputbuffer\fP, replacing the part that was matched with the
+\fIreplacement\fP string, whose length is supplied in \fBrlength\fP. This can
+be given as PCRE2_ZERO_TERMINATED for a zero-terminated string.
+.P
+In the replacement string, which is interpreted as a UTF string in UTF mode,
+and is checked for UTF validity unless the PCRE2_NO_UTF_CHECK option is set, a
+dollar character is an escape character that can specify the insertion of
+characters from capturing groups in the pattern. The following forms are
+recognized:
+.sp
+  $$      insert a dollar character
+  $    insert the contents of group 
+  ${}  insert the contents of group 
+.sp
+Either a group number or a group name can be given for . Curly brackets are
+required only if the following character would be interpreted as part of the
+number or name. The number may be zero to include the entire matched string.
+For example, if the pattern a(b)c is matched with "=abc=" and the replacement
+string "+$1$0$1+", the result is "=+babcb+=". Group insertion is done by
+calling \fBpcre2_copy_byname()\fP or \fBpcre2_copy_bynumber()\fP as
+appropriate.
+.P
+The first seven arguments of \fBpcre2_substitute()\fP are the same as for
+\fBpcre2_match()\fP, except that the partial matching options are not
+permitted, and \fImatch_data\fP may be passed as NULL, in which case a match
+data block is obtained and freed within this function, using memory management
+functions from the match context, if provided, or else those that were used to
+allocate memory for the compiled code.
+.P
+There is one additional option, PCRE2_SUBSTITUTE_GLOBAL, which causes the
+function to iterate over the subject string, replacing every matching
+substring. If this is not set, only the first matching substring is replaced.
+.P
+The \fIoutlengthptr\fP argument must point to a variable that contains the
+length, in code units, of the output buffer. It is updated to contain the
+length of the new string, excluding the trailing zero that is automatically
+added.
+.P
+The function returns the number of replacements that were made. This may be
+zero if no matches were found, and is never greater than 1 unless
+PCRE2_SUBSTITUTE_GLOBAL is set. In the event of an error, a negative error code
+is returned. Except for PCRE2_ERROR_NOMATCH (which is never returned), any
+errors from \fBpcre2_match()\fP or the substring copying functions are passed
+straight back. PCRE2_ERROR_BADREPLACEMENT is returned for an invalid
+replacement string (unrecognized sequence following a dollar sign), and
+PCRE2_ERROR_NOMEMORY is returned if the output buffer is not big enough.
+.
+.
+.SH "DUPLICATE SUBPATTERN NAMES"
+.rs
+.sp
+.nf
+.B int pcre2_substring_nametable_scan(const pcre2_code *\fIcode\fP,
+.B "  PCRE2_SPTR \fIname\fP, PCRE2_SPTR *\fIfirst\fP, PCRE2_SPTR *\fIlast\fP);"
+.fi
+.P
+When a pattern is compiled with the PCRE2_DUPNAMES option, names for
+subpatterns are not required to be unique. Duplicate names are always allowed
+for subpatterns with the same number, created by using the (?| feature. Indeed,
+if such subpatterns are named, they are required to use the same names.
+.P
+Normally, patterns with duplicate names are such that in any one match, only
+one of the named subpatterns participates. An example is shown in the
+.\" HREF
+\fBpcre2pattern\fP
+.\"
+documentation.
+.P
+When duplicates are present, \fBpcre2_substring_copy_byname()\fP and
+\fBpcre2_substring_get_byname()\fP return the first substring corresponding to
+the given name that is set. Only if none are set is PCRE2_ERROR_UNSET is
+returned. The \fBpcre2_substring_number_from_name()\fP function returns the
+error PCRE2_ERROR_NOUNIQUESUBSTRING when there are duplicate names.
+.P
+If you want to get full details of all captured substrings for a given name,
+you must use the \fBpcre2_substring_nametable_scan()\fP function. The first
+argument is the compiled pattern, and the second is the name. If the third and
+fourth arguments are NULL, the function returns a group number for a unique
+name, or PCRE2_ERROR_NOUNIQUESUBSTRING otherwise.
+.P
+When the third and fourth arguments are not NULL, they must be pointers to
+variables that are updated by the function. After it has run, they point to the
+first and last entries in the name-to-number table for the given name, and the
+function returns the length of each entry in code units. In both cases,
+PCRE2_ERROR_NOSUBSTRING is returned if there are no entries for the given name.
+.P
+The format of the name table is described above in the section entitled
+\fIInformation about a pattern\fP
+.\" HTML 
+.\" 
+above.
+.\"
+Given all the relevant entries for the name, you can extract each of their
+numbers, and hence the captured data.
+.
+.
+.SH "FINDING ALL POSSIBLE MATCHES AT ONE POSITION"
+.rs
+.sp
+The traditional matching function uses a similar algorithm to Perl, which stops
+when it finds the first match at a given point in the subject. If you want to
+find all possible matches, or the longest possible match at a given position,
+consider using the alternative matching function (see below) instead. If you
+cannot use the alternative function, you can kludge it up by making use of the
+callout facility, which is described in the
+.\" HREF
+\fBpcre2callout\fP
+.\"
+documentation.
+.P
+What you have to do is to insert a callout right at the end of the pattern.
+When your callout function is called, extract and save the current matched
+substring. Then return 1, which forces \fBpcre2_match()\fP to backtrack and try
+other alternatives. Ultimately, when it runs out of matches,
+\fBpcre2_match()\fP will yield PCRE2_ERROR_NOMATCH.
+.
+.
+.\" HTML 
+.SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"
+.rs
+.sp
+.nf
+.B int pcre2_dfa_match(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
+.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
+.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
+.B "  pcre2_match_context *\fImcontext\fP,"
+.B "  int *\fIworkspace\fP, PCRE2_SIZE \fIwscount\fP);"
+.fi
+.P
+The function \fBpcre2_dfa_match()\fP is called to match a subject string
+against a compiled pattern, using a matching algorithm that scans the subject
+string just once, and does not backtrack. This has different characteristics to
+the normal algorithm, and is not compatible with Perl. Some of the features of
+PCRE2 patterns are not supported. Nevertheless, there are times when this kind
+of matching can be useful. For a discussion of the two matching algorithms, and
+a list of features that \fBpcre2_dfa_match()\fP does not support, see the
+.\" HREF
+\fBpcre2matching\fP
+.\"
+documentation.
+.P
+The arguments for the \fBpcre2_dfa_match()\fP function are the same as for
+\fBpcre2_match()\fP, plus two extras. The ovector within the match data block
+is used in a different way, and this is described below. The other common
+arguments are used in the same way as for \fBpcre2_match()\fP, so their
+description is not repeated here.
+.P
+The two additional arguments provide workspace for the function. The workspace
+vector should contain at least 20 elements. It is used for keeping track of
+multiple paths through the pattern tree. More workspace is needed for patterns
+and subjects where there are a lot of potential matches.
+.P
+Here is an example of a simple call to \fBpcre2_dfa_match()\fP:
+.sp
+  int wspace[20];
+  pcre2_match_data *md = pcre2_match_data_create(4, NULL);
+  int rc = pcre2_dfa_match(
+    re,             /* result of pcre2_compile() */
+    "some string",  /* the subject string */
+    11,             /* the length of the subject string */
+    0,              /* start at offset 0 in the subject */
+    0,              /* default options */
+    match_data,     /* the match data block */
+    NULL,           /* a match context; NULL means use defaults */
+    wspace,         /* working space vector */
+    20);            /* number of elements (NOT size in bytes) */
+.
+.SS "Option bits for \fBpcre_dfa_match()\fP"
+.rs
+.sp
+The unused bits of the \fIoptions\fP argument for \fBpcre2_dfa_match()\fP must
+be zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL,
+PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_UTF_CHECK,
+PCRE2_PARTIAL_HARD, PCRE2_PARTIAL_SOFT, PCRE2_DFA_SHORTEST, and
+PCRE2_DFA_RESTART. All but the last four of these are exactly the same as for
+\fBpcre2_match()\fP, so their description is not repeated here.
+.sp
+  PCRE2_PARTIAL_HARD
+  PCRE2_PARTIAL_SOFT
+.sp
+These have the same general effect as they do for \fBpcre2_match()\fP, but the
+details are slightly different. When PCRE2_PARTIAL_HARD is set for
+\fBpcre2_dfa_match()\fP, it returns PCRE2_ERROR_PARTIAL if the end of the
+subject is reached and there is still at least one matching possibility that
+requires additional characters. This happens even if some complete matches have
+already been found. When PCRE2_PARTIAL_SOFT is set, the return code
+PCRE2_ERROR_NOMATCH is converted into PCRE2_ERROR_PARTIAL if the end of the
+subject is reached, there have been no complete matches, but there is still at
+least one matching possibility. The portion of the string that was inspected
+when the longest partial match was found is set as the first matching string in
+both cases. There is a more detailed discussion of partial and multi-segment
+matching, with examples, in the
+.\" HREF
+\fBpcre2partial\fP
+.\"
+documentation.
+.sp
+  PCRE2_DFA_SHORTEST
+.sp
+Setting the PCRE2_DFA_SHORTEST option causes the matching algorithm to stop as
+soon as it has found one match. Because of the way the alternative algorithm
+works, this is necessarily the shortest possible match at the first possible
+matching point in the subject string.
+.sp
+  PCRE2_DFA_RESTART
+.sp
+When \fBpcre2_dfa_match()\fP returns a partial match, it is possible to call it
+again, with additional subject characters, and have it continue with the same
+match. The PCRE2_DFA_RESTART option requests this action; when it is set, the
+\fIworkspace\fP and \fIwscount\fP options must reference the same vector as
+before because data about the match so far is left in them after a partial
+match. There is more discussion of this facility in the
+.\" HREF
+\fBpcre2partial\fP
+.\"
+documentation.
+.
+.
+.SS "Successful returns from \fBpcre2_dfa_match()\fP"
+.rs
+.sp
+When \fBpcre2_dfa_match()\fP succeeds, it may have matched more than one
+substring in the subject. Note, however, that all the matches from one run of
+the function start at the same point in the subject. The shorter matches are
+all initial substrings of the longer matches. For example, if the pattern
+.sp
+  <.*>
+.sp
+is matched against the string
+.sp
+  This is    no more
+.sp
+the three matched strings are
+.sp
+    
+   
+  
+.sp
+On success, the yield of the function is a number greater than zero, which is
+the number of matched substrings. The offsets of the substrings are returned in
+the ovector, and can be extracted by number in the same way as for
+\fBpcre2_match()\fP, but the numbers bear no relation to any capturing groups
+that may exist in the pattern, because DFA matching does not support group
+capture.
+.P
+Calls to the convenience functions that extract substrings by name
+return the error PCRE2_ERROR_DFA_UFUNC (unsupported function) if used after a
+DFA match. The convenience functions that extract substrings by number never
+return PCRE2_ERROR_NOSUBSTRING, and the meanings of some other errors are
+slightly different:
+.sp
+  PCRE2_ERROR_UNAVAILABLE
+.sp
+The ovector is not big enough to include a slot for the given substring number.
+.sp
+  PCRE2_ERROR_UNSET
+.sp
+There is a slot in the ovector for this substring, but there were insufficient
+matches to fill it.
+.P
+The matched strings are stored in the ovector in reverse order of length; that
+is, the longest matching string is first. If there were too many matches to fit
+into the ovector, the yield of the function is zero, and the vector is filled
+with the longest matches.
+.P
+NOTE: PCRE2's "auto-possessification" optimization usually applies to character
+repeats at the end of a pattern (as well as internally). For example, the
+pattern "a\ed+" is compiled as if it were "a\ed++". For DFA matching, this
+means that only one possible match is found. If you really do want multiple
+matches in such cases, either use an ungreedy repeat auch as "a\ed+?" or set
+the PCRE2_NO_AUTO_POSSESS option when compiling.
+.
+.
+.SS "Error returns from \fBpcre2_dfa_match()\fP"
+.rs
+.sp
+The \fBpcre2_dfa_match()\fP function returns a negative number when it fails.
+Many of the errors are the same as for \fBpcre2_match()\fP, as described
+.\" HTML 
+.\" 
+above.
+.\"
+There are in addition the following errors that are specific to
+\fBpcre2_dfa_match()\fP:
+.sp
+  PCRE2_ERROR_DFA_UITEM
+.sp
+This return is given if \fBpcre2_dfa_match()\fP encounters an item in the
+pattern that it does not support, for instance, the use of \eC or a back
+reference.
+.sp
+  PCRE2_ERROR_DFA_UCOND
+.sp
+This return is given if \fBpcre2_dfa_match()\fP encounters a condition item
+that uses a back reference for the condition, or a test for recursion in a
+specific group. These are not supported.
+.sp
+  PCRE2_ERROR_DFA_WSSIZE
+.sp
+This return is given if \fBpcre2_dfa_match()\fP runs out of space in the
+\fIworkspace\fP vector.
+.sp
+  PCRE2_ERROR_DFA_RECURSE
+.sp
+When a recursive subpattern is processed, the matching function calls itself
+recursively, using private memory for the ovector and \fIworkspace\fP. This
+error is given if the internal ovector is not large enough. This should be
+extremely rare, as a vector of size 1000 is used.
+.sp
+  PCRE2_ERROR_DFA_BADRESTART
+.sp
+When \fBpcre2_dfa_match()\fP is called with the \fBPCRE2_DFA_RESTART\fP option,
+some plausibility checks are made on the contents of the workspace, which
+should contain data about the previous partial match. If any of these checks
+fail, this error is given.
+.
+.
+.SH "SEE ALSO"
+.rs
+.sp
+\fBpcre2build\fP(3), \fBpcre2callout\fP(3), \fBpcre2demo(3)\fP,
+\fBpcre2matching\fP(3), \fBpcre2partial\fP(3), \fBpcre2posix\fP(3),
+\fBpcre2sample\fP(3), \fBpcre2stack\fP(3), \fBpcre2unicode\fP(3).
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel
+University Computing Service
+Cambridge, England.
+.fi
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 22 April 2015
+Copyright (c) 1997-2015 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/doc/pcre2build.3 b/pcre2-10.20/doc/pcre2build.3
new file mode 100644
index 000000000..8f74e9b6b
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2build.3
@@ -0,0 +1,515 @@
+.TH PCRE2BUILD 3 "23 April 2015" "PCRE2 10.20"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.
+.
+.SH "BUILDING PCRE2"
+.rs
+.sp
+PCRE2 is distributed with a \fBconfigure\fP script that can be used to build
+the library in Unix-like environments using the applications known as
+Autotools. Also in the distribution are files to support building using
+\fBCMake\fP instead of \fBconfigure\fP. The text file
+.\" HTML 
+.\" 
+\fBREADME\fP
+.\"
+contains general information about building with Autotools (some of which is
+repeated below), and also has some comments about building on various operating
+systems. There is a lot more information about building PCRE2 without using
+Autotools (including information about using \fBCMake\fP and building "by
+hand") in the text file called
+.\" HTML 
+.\" 
+\fBNON-AUTOTOOLS-BUILD\fP.
+.\"
+You should consult this file as well as the
+.\" HTML 
+.\" 
+\fBREADME\fP
+.\"
+file if you are building in a non-Unix-like environment.
+.
+.
+.SH "PCRE2 BUILD-TIME OPTIONS"
+.rs
+.sp
+The rest of this document describes the optional features of PCRE2 that can be
+selected when the library is compiled. It assumes use of the \fBconfigure\fP
+script, where the optional features are selected or deselected by providing
+options to \fBconfigure\fP before running the \fBmake\fP command. However, the
+same options can be selected in both Unix-like and non-Unix-like environments
+if you are using \fBCMake\fP instead of \fBconfigure\fP to build PCRE2.
+.P
+If you are not using Autotools or \fBCMake\fP, option selection can be done by
+editing the \fBconfig.h\fP file, or by passing parameter settings to the
+compiler, as described in
+.\" HTML 
+.\" 
+\fBNON-AUTOTOOLS-BUILD\fP.
+.\"
+.P
+The complete list of options for \fBconfigure\fP (which includes the standard
+ones such as the selection of the installation directory) can be obtained by
+running
+.sp
+  ./configure --help
+.sp
+The following sections include descriptions of options whose names begin with
+--enable or --disable. These settings specify changes to the defaults for the
+\fBconfigure\fP command. Because of the way that \fBconfigure\fP works,
+--enable and --disable always come in pairs, so the complementary option always
+exists as well, but as it specifies the default, it is not described.
+.
+.
+.SH "BUILDING 8-BIT, 16-BIT AND 32-BIT LIBRARIES"
+.rs
+.sp
+By default, a library called \fBlibpcre2-8\fP is built, containing functions
+that take string arguments contained in vectors of bytes, interpreted either as
+single-byte characters, or UTF-8 strings. You can also build two other
+libraries, called \fBlibpcre2-16\fP and \fBlibpcre2-32\fP, which process
+strings that are contained in vectors of 16-bit and 32-bit code units,
+respectively. These can be interpreted either as single-unit characters or
+UTF-16/UTF-32 strings. To build these additional libraries, add one or both of
+the following to the \fBconfigure\fP command:
+.sp
+  --enable-pcre2-16
+  --enable-pcre2-32
+.sp
+If you do not want the 8-bit library, add
+.sp
+  --disable-pcre2-8
+.sp
+as well. At least one of the three libraries must be built. Note that the POSIX
+wrapper is for the 8-bit library only, and that \fBpcre2grep\fP is an 8-bit
+program. Neither of these are built if you select only the 16-bit or 32-bit
+libraries.
+.
+.
+.SH "BUILDING SHARED AND STATIC LIBRARIES"
+.rs
+.sp
+The Autotools PCRE2 building process uses \fBlibtool\fP to build both shared
+and static libraries by default. You can suppress an unwanted library by adding
+one of
+.sp
+  --disable-shared
+  --disable-static
+.sp
+to the \fBconfigure\fP command.
+.
+.
+.SH "UNICODE AND UTF SUPPORT"
+.rs
+.sp
+By default, PCRE2 is built with support for Unicode and UTF character strings.
+To build it without Unicode support, add
+.sp
+  --disable-unicode
+.sp
+to the \fBconfigure\fP command. This setting applies to all three libraries. It
+is not possible to build one library with Unicode support, and another without,
+in the same configuration.
+.P
+Of itself, Unicode support does not make PCRE2 treat strings as UTF-8, UTF-16
+or UTF-32. To do that, applications that use the library can set the PCRE2_UTF
+option when they call \fBpcre2_compile()\fP to compile a pattern.
+Alternatively, patterns may be started with (*UTF) unless the application has
+locked this out by setting PCRE2_NEVER_UTF.
+.P
+UTF support allows the libraries to process character code points up to
+0x10ffff in the strings that they handle. It also provides support for
+accessing the Unicode properties of such characters, using pattern escapes such
+as \eP, \ep, and \eX. Only the general category properties such as \fILu\fP and
+\fINd\fP are supported. Details are given in the
+.\" HREF
+\fBpcre2pattern\fP
+.\"
+documentation.
+.P
+Pattern escapes such as \ed and \ew do not by default make use of Unicode
+properties. The application can request that they do by setting the PCRE2_UCP
+option. Unless the application has set PCRE2_NEVER_UCP, a pattern may also
+request this by starting with (*UCP).
+.P
+The \eC escape sequence, which matches a single code unit, even in a UTF mode,
+can cause unpredictable behaviour because it may leave the current matching
+point in the middle of a multi-code-unit character. It can be locked out by
+setting the PCRE2_NEVER_BACKSLASH_C option.
+.
+.
+.SH "JUST-IN-TIME COMPILER SUPPORT"
+.rs
+.sp
+Just-in-time compiler support is included in the build by specifying
+.sp
+  --enable-jit
+.sp
+This support is available only for certain hardware architectures. If this
+option is set for an unsupported architecture, a building error occurs.
+See the
+.\" HREF
+\fBpcre2jit\fP
+.\"
+documentation for a discussion of JIT usage. When JIT support is enabled,
+pcre2grep automatically makes use of it, unless you add
+.sp
+  --disable-pcre2grep-jit
+.sp
+to the "configure" command.
+.
+.
+.SH "NEWLINE RECOGNITION"
+.rs
+.sp
+By default, PCRE2 interprets the linefeed (LF) character as indicating the end
+of a line. This is the normal newline character on Unix-like systems. You can
+compile PCRE2 to use carriage return (CR) instead, by adding
+.sp
+  --enable-newline-is-cr
+.sp
+to the \fBconfigure\fP command. There is also an --enable-newline-is-lf option,
+which explicitly specifies linefeed as the newline character.
+.P
+Alternatively, you can specify that line endings are to be indicated by the
+two-character sequence CRLF (CR immediately followed by LF). If you want this,
+add
+.sp
+  --enable-newline-is-crlf
+.sp
+to the \fBconfigure\fP command. There is a fourth option, specified by
+.sp
+  --enable-newline-is-anycrlf
+.sp
+which causes PCRE2 to recognize any of the three sequences CR, LF, or CRLF as
+indicating a line ending. Finally, a fifth option, specified by
+.sp
+  --enable-newline-is-any
+.sp
+causes PCRE2 to recognize any Unicode newline sequence. The Unicode newline
+sequences are the three just mentioned, plus the single characters VT (vertical
+tab, U+000B), FF (form feed, U+000C), NEL (next line, U+0085), LS (line
+separator, U+2028), and PS (paragraph separator, U+2029).
+.P
+Whatever default line ending convention is selected when PCRE2 is built can be
+overridden by applications that use the library. At build time it is
+conventional to use the standard for your operating system.
+.
+.
+.SH "WHAT \eR MATCHES"
+.rs
+.sp
+By default, the sequence \eR in a pattern matches any Unicode newline sequence,
+independently of what has been selected as the line ending sequence. If you
+specify
+.sp
+  --enable-bsr-anycrlf
+.sp
+the default is changed so that \eR matches only CR, LF, or CRLF. Whatever is
+selected when PCRE2 is built can be overridden by applications that use the
+called.
+.
+.
+.SH "HANDLING VERY LARGE PATTERNS"
+.rs
+.sp
+Within a compiled pattern, offset values are used to point from one part to
+another (for example, from an opening parenthesis to an alternation
+metacharacter). By default, in the 8-bit and 16-bit libraries, two-byte values
+are used for these offsets, leading to a maximum size for a compiled pattern of
+around 64K code units. This is sufficient to handle all but the most gigantic
+patterns. Nevertheless, some people do want to process truly enormous patterns,
+so it is possible to compile PCRE2 to use three-byte or four-byte offsets by
+adding a setting such as
+.sp
+  --with-link-size=3
+.sp
+to the \fBconfigure\fP command. The value given must be 2, 3, or 4. For the
+16-bit library, a value of 3 is rounded up to 4. In these libraries, using
+longer offsets slows down the operation of PCRE2 because it has to load
+additional data when handling them. For the 32-bit library the value is always
+4 and cannot be overridden; the value of --with-link-size is ignored.
+.
+.
+.SH "AVOIDING EXCESSIVE STACK USAGE"
+.rs
+.sp
+When matching with the \fBpcre2_match()\fP function, PCRE2 implements
+backtracking by making recursive calls to an internal function called
+\fBmatch()\fP. In environments where the size of the stack is limited, this can
+severely limit PCRE2's operation. (The Unix environment does not usually suffer
+from this problem, but it may sometimes be necessary to increase the maximum
+stack size. There is a discussion in the
+.\" HREF
+\fBpcre2stack\fP
+.\"
+documentation.) An alternative approach to recursion that uses memory from the
+heap to remember data, instead of using recursive function calls, has been
+implemented to work round the problem of limited stack size. If you want to
+build a version of PCRE2 that works this way, add
+.sp
+  --disable-stack-for-recursion
+.sp
+to the \fBconfigure\fP command. By default, the system functions \fBmalloc()\fP
+and \fBfree()\fP are called to manage the heap memory that is required, but
+custom memory management functions can be called instead. PCRE2 runs noticeably
+more slowly when built in this way. This option affects only the
+\fBpcre2_match()\fP function; it is not relevant for \fBpcre2_dfa_match()\fP.
+.
+.
+.SH "LIMITING PCRE2 RESOURCE USAGE"
+.rs
+.sp
+Internally, PCRE2 has a function called \fBmatch()\fP, which it calls
+repeatedly (sometimes recursively) when matching a pattern with the
+\fBpcre2_match()\fP function. By controlling the maximum number of times this
+function may be called during a single matching operation, a limit can be
+placed on the resources used by a single call to \fBpcre2_match()\fP. The limit
+can be changed at run time, as described in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+documentation. The default is 10 million, but this can be changed by adding a
+setting such as
+.sp
+  --with-match-limit=500000
+.sp
+to the \fBconfigure\fP command. This setting has no effect on the
+\fBpcre2_dfa_match()\fP matching function.
+.P
+In some environments it is desirable to limit the depth of recursive calls of
+\fBmatch()\fP more strictly than the total number of calls, in order to
+restrict the maximum amount of stack (or heap, if --disable-stack-for-recursion
+is specified) that is used. A second limit controls this; it defaults to the
+value that is set for --with-match-limit, which imposes no additional
+constraints. However, you can set a lower limit by adding, for example,
+.sp
+  --with-match-limit-recursion=10000
+.sp
+to the \fBconfigure\fP command. This value can also be overridden at run time.
+.
+.
+.SH "CREATING CHARACTER TABLES AT BUILD TIME"
+.rs
+.sp
+PCRE2 uses fixed tables for processing characters whose code points are less
+than 256. By default, PCRE2 is built with a set of tables that are distributed
+in the file \fIsrc/pcre2_chartables.c.dist\fP. These tables are for ASCII codes
+only. If you add
+.sp
+  --enable-rebuild-chartables
+.sp
+to the \fBconfigure\fP command, the distributed tables are no longer used.
+Instead, a program called \fBdftables\fP is compiled and run. This outputs the
+source for new set of tables, created in the default locale of your C run-time
+system. (This method of replacing the tables does not work if you are cross
+compiling, because \fBdftables\fP is run on the local host. If you need to
+create alternative tables when cross compiling, you will have to do so "by
+hand".)
+.
+.
+.SH "USING EBCDIC CODE"
+.rs
+.sp
+PCRE2 assumes by default that it will run in an environment where the character
+code is ASCII or Unicode, which is a superset of ASCII. This is the case for
+most computer operating systems. PCRE2 can, however, be compiled to run in an
+8-bit EBCDIC environment by adding
+.sp
+  --enable-ebcdic --disable-unicode
+.sp
+to the \fBconfigure\fP command. This setting implies
+--enable-rebuild-chartables. You should only use it if you know that you are in
+an EBCDIC environment (for example, an IBM mainframe operating system).
+.P
+It is not possible to support both EBCDIC and UTF-8 codes in the same version
+of the library. Consequently, --enable-unicode and --enable-ebcdic are mutually
+exclusive.
+.P
+The EBCDIC character that corresponds to an ASCII LF is assumed to have the
+value 0x15 by default. However, in some EBCDIC environments, 0x25 is used. In
+such an environment you should use
+.sp
+  --enable-ebcdic-nl25
+.sp
+as well as, or instead of, --enable-ebcdic. The EBCDIC character for CR has the
+same value as in ASCII, namely, 0x0d. Whichever of 0x15 and 0x25 is \fInot\fP
+chosen as LF is made to correspond to the Unicode NEL character (which, in
+Unicode, is 0x85).
+.P
+The options that select newline behaviour, such as --enable-newline-is-cr,
+and equivalent run-time options, refer to these character values in an EBCDIC
+environment.
+.
+.
+.SH "PCRE2GREP OPTIONS FOR COMPRESSED FILE SUPPORT"
+.rs
+.sp
+By default, \fBpcre2grep\fP reads all files as plain text. You can build it so
+that it recognizes files whose names end in \fB.gz\fP or \fB.bz2\fP, and reads
+them with \fBlibz\fP or \fBlibbz2\fP, respectively, by adding one or both of
+.sp
+  --enable-pcre2grep-libz
+  --enable-pcre2grep-libbz2
+.sp
+to the \fBconfigure\fP command. These options naturally require that the
+relevant libraries are installed on your system. Configuration will fail if
+they are not.
+.
+.
+.SH "PCRE2GREP BUFFER SIZE"
+.rs
+.sp
+\fBpcre2grep\fP uses an internal buffer to hold a "window" on the file it is
+scanning, in order to be able to output "before" and "after" lines when it
+finds a match. The size of the buffer is controlled by a parameter whose
+default value is 20K. The buffer itself is three times this size, but because
+of the way it is used for holding "before" lines, the longest line that is
+guaranteed to be processable is the parameter size. You can change the default
+parameter value by adding, for example,
+.sp
+  --with-pcre2grep-bufsize=50K
+.sp
+to the \fBconfigure\fP command. The caller of \fPpcre2grep\fP can override this
+value by using --buffer-size on the command line..
+.
+.
+.SH "PCRE2TEST OPTION FOR LIBREADLINE SUPPORT"
+.rs
+.sp
+If you add one of
+.sp
+  --enable-pcre2test-libreadline
+  --enable-pcre2test-libedit
+.sp
+to the \fBconfigure\fP command, \fBpcre2test\fP is linked with the
+\fBlibreadline\fP or\fBlibedit\fP library, respectively, and when its input is
+from a terminal, it reads it using the \fBreadline()\fP function. This provides
+line-editing and history facilities. Note that \fBlibreadline\fP is
+GPL-licensed, so if you distribute a binary of \fBpcre2test\fP linked in this
+way, there may be licensing issues. These can be avoided by linking instead
+with \fBlibedit\fP, which has a BSD licence.
+.P
+Setting --enable-pcre2test-libreadline causes the \fB-lreadline\fP option to be
+added to the \fBpcre2test\fP build. In many operating environments with a
+sytem-installed readline library this is sufficient. However, in some
+environments (e.g. if an unmodified distribution version of readline is in
+use), some extra configuration may be necessary. The INSTALL file for
+\fBlibreadline\fP says this:
+.sp
+  "Readline uses the termcap functions, but does not link with
+  the termcap or curses library itself, allowing applications
+  which link with readline the to choose an appropriate library."
+.sp
+If your environment has not been set up so that an appropriate library is
+automatically included, you may need to add something like
+.sp
+  LIBS="-ncurses"
+.sp
+immediately before the \fBconfigure\fP command.
+.
+.
+.SH "INCLUDING DEBUGGING CODE"
+.rs
+.sp
+If you add
+.sp
+  --enable-debug
+.sp
+to the \fBconfigure\fP command, additional debugging code is included in the
+build. This feature is intended for use by the PCRE2 maintainers.
+.
+.
+.SH "DEBUGGING WITH VALGRIND SUPPORT"
+.rs
+.sp
+If you add
+.sp
+  --enable-valgrind
+.sp
+to the \fBconfigure\fP command, PCRE2 will use valgrind annotations to mark
+certain memory regions as unaddressable. This allows it to detect invalid
+memory accesses, and is mostly useful for debugging PCRE2 itself.
+.
+.
+.SH "CODE COVERAGE REPORTING"
+.rs
+.sp
+If your C compiler is gcc, you can build a version of PCRE2 that can generate a
+code coverage report for its test suite. To enable this, you must install
+\fBlcov\fP version 1.6 or above. Then specify
+.sp
+  --enable-coverage
+.sp
+to the \fBconfigure\fP command and build PCRE2 in the usual way.
+.P
+Note that using \fBccache\fP (a caching C compiler) is incompatible with code
+coverage reporting. If you have configured \fBccache\fP to run automatically
+on your system, you must set the environment variable
+.sp
+  CCACHE_DISABLE=1
+.sp
+before running \fBmake\fP to build PCRE2, so that \fBccache\fP is not used.
+.P
+When --enable-coverage is used, the following addition targets are added to the
+\fIMakefile\fP:
+.sp
+  make coverage
+.sp
+This creates a fresh coverage report for the PCRE2 test suite. It is equivalent
+to running "make coverage-reset", "make coverage-baseline", "make check", and
+then "make coverage-report".
+.sp
+  make coverage-reset
+.sp
+This zeroes the coverage counters, but does nothing else.
+.sp
+  make coverage-baseline
+.sp
+This captures baseline coverage information.
+.sp
+  make coverage-report
+.sp
+This creates the coverage report.
+.sp
+  make coverage-clean-report
+.sp
+This removes the generated coverage report without cleaning the coverage data
+itself.
+.sp
+  make coverage-clean-data
+.sp
+This removes the captured coverage data without removing the coverage files
+created at compile time (*.gcno).
+.sp
+  make coverage-clean
+.sp
+This cleans all coverage data including the generated coverage report. For more
+information about code coverage, see the \fBgcov\fP and \fBlcov\fP
+documentation.
+.
+.
+.SH "SEE ALSO"
+.rs
+.sp
+\fBpcre2api\fP(3), \fBpcre2-config\fP(3).
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel
+University Computing Service
+Cambridge, England.
+.fi
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 24 April 2015
+Copyright (c) 1997-2015 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/doc/pcre2callout.3 b/pcre2-10.20/doc/pcre2callout.3
new file mode 100644
index 000000000..6919f5a61
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2callout.3
@@ -0,0 +1,387 @@
+.TH PCRE2CALLOUT 3 "23 March 2015" "PCRE2 10.20"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.SM
+.nf
+.B int (*pcre2_callout)(pcre2_callout_block *, void *);
+.sp
+.B int pcre2_callout_enumerate(const pcre2_code *\fIcode\fP,
+.B "  int (*\fIcallback\fP)(pcre2_callout_enumerate_block *, void *),"
+.B "  void *\fIuser_data\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+PCRE2 provides a feature called "callout", which is a means of temporarily
+passing control to the caller of PCRE2 in the middle of pattern matching. The
+caller of PCRE2 provides an external function by putting its entry point in
+a match context (see \fBpcre2_set_callout()\fP in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+documentation).
+.P
+Within a regular expression, (?C) indicates a point at which the external
+function is to be called. Different callout points can be identified by putting
+a number less than 256 after the letter C. The default value is zero.
+Alternatively, the argument may be a delimited string. The starting delimiter
+must be one of ` ' " ^ % # $ { and the ending delimiter is the same as the
+start, except for {, where the ending delimiter is }. If the ending delimiter
+is needed within the string, it must be doubled. For example, this pattern has
+two callout points:
+.sp
+  (?C1)abc(?C"some ""arbitrary"" text")def
+.sp
+If the PCRE2_AUTO_CALLOUT option bit is set when a pattern is compiled, PCRE2
+automatically inserts callouts, all with number 255, before each item in the
+pattern. For example, if PCRE2_AUTO_CALLOUT is used with the pattern
+.sp
+  A(\ed{2}|--)
+.sp
+it is processed as if it were
+.sp
+(?C255)A(?C255)((?C255)\ed{2}(?C255)|(?C255)-(?C255)-(?C255))(?C255)
+.sp
+Notice that there is a callout before and after each parenthesis and
+alternation bar. If the pattern contains a conditional group whose condition is
+an assertion, an automatic callout is inserted immediately before the
+condition. Such a callout may also be inserted explicitly, for example:
+.sp
+  (?(?C9)(?=a)ab|de)  (?(?C%text%)(?!=d)ab|de)
+.sp
+This applies only to assertion conditions (because they are themselves
+independent groups).
+.P
+Callouts can be useful for tracking the progress of pattern matching. The
+.\" HREF
+\fBpcre2test\fP
+.\"
+program has a pattern qualifier (/auto_callout) that sets automatic callouts.
+When any callouts are present, the output from \fBpcre2test\fP indicates how
+the pattern is being matched. This is useful information when you are trying to
+optimize the performance of a particular pattern.
+.
+.
+.SH "MISSING CALLOUTS"
+.rs
+.sp
+You should be aware that, because of optimizations in the way PCRE2 compiles
+and matches patterns, callouts sometimes do not happen exactly as you might
+expect.
+.
+.
+.SS "Auto-possessification"
+.rs
+.sp
+At compile time, PCRE2 "auto-possessifies" repeated items when it knows that
+what follows cannot be part of the repeat. For example, a+[bc] is compiled as
+if it were a++[bc]. The \fBpcre2test\fP output when this pattern is compiled
+with PCRE2_ANCHORED and PCRE2_AUTO_CALLOUT and then applied to the string
+"aaaa" is:
+.sp
+  --->aaaa
+   +0 ^        a+
+   +2 ^   ^    [bc]
+  No match
+.sp
+This indicates that when matching [bc] fails, there is no backtracking into a+
+and therefore the callouts that would be taken for the backtracks do not occur.
+You can disable the auto-possessify feature by passing PCRE2_NO_AUTO_POSSESS to
+\fBpcre2_compile()\fP, or starting the pattern with (*NO_AUTO_POSSESS). In this
+case, the output changes to this:
+.sp
+  --->aaaa
+   +0 ^        a+
+   +2 ^   ^    [bc]
+   +2 ^  ^     [bc]
+   +2 ^ ^      [bc]
+   +2 ^^       [bc]
+  No match
+.sp
+This time, when matching [bc] fails, the matcher backtracks into a+ and tries
+again, repeatedly, until a+ itself fails.
+.
+.
+.SS "Automatic .* anchoring"
+.rs
+.sp
+By default, an optimization is applied when .* is the first significant item in
+a pattern. If PCRE2_DOTALL is set, so that the dot can match any character, the
+pattern is automatically anchored. If PCRE2_DOTALL is not set, a match can
+start only after an internal newline or at the beginning of the subject, and
+\fBpcre2_compile()\fP remembers this. This optimization is disabled, however,
+if .* is in an atomic group or if there is a back reference to the capturing
+group in which it appears. It is also disabled if the pattern contains (*PRUNE)
+or (*SKIP). However, the presence of callouts does not affect it.
+.P
+For example, if the pattern .*\ed is compiled with PCRE2_AUTO_CALLOUT and
+applied to the string "aa", the \fBpcre2test\fP output is:
+.sp
+  --->aa
+   +0 ^      .*
+   +2 ^ ^    \ed
+   +2 ^^     \ed
+   +2 ^      \ed
+  No match
+.sp
+This shows that all match attempts start at the beginning of the subject. In
+other words, the pattern is anchored. You can disable this optimization by
+passing PCRE2_NO_DOTSTAR_ANCHOR to \fBpcre2_compile()\fP, or starting the
+pattern with (*NO_DOTSTAR_ANCHOR). In this case, the output changes to:
+.sp
+  --->aa
+   +0 ^      .*
+   +2 ^ ^    \ed
+   +2 ^^     \ed
+   +2 ^      \ed
+   +0  ^     .*
+   +2  ^^    \ed
+   +2  ^     \ed
+  No match
+.sp
+This shows more match attempts, starting at the second subject character.
+Another optimization, described in the next section, means that there is no
+subsequent attempt to match with an empty subject.
+.P
+If a pattern has more than one top-level branch, automatic anchoring occurs if
+all branches are anchorable.
+.
+.
+.SS "Other optimizations"
+.rs
+.sp
+Other optimizations that provide fast "no match" results also affect callouts.
+For example, if the pattern is
+.sp
+  ab(?C4)cd
+.sp
+PCRE2 knows that any matching string must contain the letter "d". If the
+subject string is "abyz", the lack of "d" means that matching doesn't ever
+start, and the callout is never reached. However, with "abyd", though the
+result is still no match, the callout is obeyed.
+.P
+PCRE2 also knows the minimum length of a matching string, and will immediately
+give a "no match" return without actually running a match if the subject is not
+long enough, or, for unanchored patterns, if it has been scanned far enough.
+.P
+You can disable these optimizations by passing the PCRE2_NO_START_OPTIMIZE
+option to \fBpcre2_compile()\fP, or by starting the pattern with
+(*NO_START_OPT). This slows down the matching process, but does ensure that
+callouts such as the example above are obeyed.
+.
+.
+.\" HTML 
+.SH "THE CALLOUT INTERFACE"
+.rs
+.sp
+During matching, when PCRE2 reaches a callout point, if an external function is
+set in the match context, it is called. This applies to both normal and DFA
+matching. The first argument to the callout function is a pointer to a
+\fBpcre2_callout\fP block. The second argument is the void * callout data that
+was supplied when the callout was set up by calling \fBpcre2_set_callout()\fP
+(see the
+.\" HREF
+\fBpcre2api\fP
+.\"
+documentation). The callout block structure contains the following fields:
+.sp
+  uint32_t      \fIversion\fP;
+  uint32_t      \fIcallout_number\fP;
+  uint32_t      \fIcapture_top\fP;
+  uint32_t      \fIcapture_last\fP;
+  PCRE2_SIZE   *\fIoffset_vector\fP;
+  PCRE2_SPTR    \fImark\fP;
+  PCRE2_SPTR    \fIsubject\fP;
+  PCRE2_SIZE    \fIsubject_length\fP;
+  PCRE2_SIZE    \fIstart_match\fP;
+  PCRE2_SIZE    \fIcurrent_position\fP;
+  PCRE2_SIZE    \fIpattern_position\fP;
+  PCRE2_SIZE    \fInext_item_length\fP;
+  PCRE2_SIZE    \fIcallout_string_offset\fP;
+  PCRE2_SIZE    \fIcallout_string_length\fP;
+  PCRE2_SPTR    \fIcallout_string\fP;
+.sp
+The \fIversion\fP field contains the version number of the block format. The
+current version is 1; the three callout string fields were added for this
+version. If you are writing an application that might use an earlier release of
+PCRE2, you should check the version number before accessing any of these
+fields. The version number will increase in future if more fields are added,
+but the intention is never to remove any of the existing fields.
+.
+.
+.SS "Fields for numerical callouts"
+.rs
+.sp
+For a numerical callout, \fIcallout_string\fP is NULL, and \fIcallout_number\fP
+contains the number of the callout, in the range 0-255. This is the number
+that follows (?C for manual callouts; it is 255 for automatically generated
+callouts.
+.
+.
+.SS "Fields for string callouts"
+.rs
+.sp
+For callouts with string arguments, \fIcallout_number\fP is always zero, and
+\fIcallout_string\fP points to the string that is contained within the compiled
+pattern. Its length is given by \fIcallout_string_length\fP. Duplicated ending
+delimiters that were present in the original pattern string have been turned
+into single characters, but there is no other processing of the callout string
+argument. An additional code unit containing binary zero is present after the
+string, but is not included in the length. The delimiter that was used to start
+the string is also stored within the pattern, immediately before the string
+itself. You can access this delimiter as \fIcallout_string\fP[-1] if you need
+it.
+.P
+The \fIcallout_string_offset\fP field is the code unit offset to the start of
+the callout argument string within the original pattern string. This is
+provided for the benefit of applications such as script languages that might
+need to report errors in the callout string within the pattern.
+.
+.
+.SS "Fields for all callouts"
+.rs
+.sp
+The remaining fields in the callout block are the same for both kinds of
+callout.
+.P
+The \fIoffset_vector\fP field is a pointer to the vector of capturing offsets
+(the "ovector") that was passed to the matching function in the match data
+block. When \fBpcre2_match()\fP is used, the contents can be inspected in
+order to extract substrings that have been matched so far, in the same way as
+for extracting substrings after a match has completed. For the DFA matching
+function, this field is not useful.
+.P
+The \fIsubject\fP and \fIsubject_length\fP fields contain copies of the values
+that were passed to the matching function.
+.P
+The \fIstart_match\fP field normally contains the offset within the subject at
+which the current match attempt started. However, if the escape sequence \eK
+has been encountered, this value is changed to reflect the modified starting
+point. If the pattern is not anchored, the callout function may be called
+several times from the same point in the pattern for different starting points
+in the subject.
+.P
+The \fIcurrent_position\fP field contains the offset within the subject of the
+current match pointer.
+.P
+When the \fBpcre2_match()\fP is used, the \fIcapture_top\fP field contains one
+more than the number of the highest numbered captured substring so far. If no
+substrings have been captured, the value of \fIcapture_top\fP is one. This is
+always the case when the DFA functions are used, because they do not support
+captured substrings.
+.P
+The \fIcapture_last\fP field contains the number of the most recently captured
+substring. However, when a recursion exits, the value reverts to what it was
+outside the recursion, as do the values of all captured substrings. If no
+substrings have been captured, the value of \fIcapture_last\fP is 0. This is
+always the case for the DFA matching functions.
+.P
+The \fIpattern_position\fP field contains the offset in the pattern string to
+the next item to be matched.
+.P
+The \fInext_item_length\fP field contains the length of the next item to be
+matched in the pattern string. When the callout immediately precedes an
+alternation bar, a closing parenthesis, or the end of the pattern, the length
+is zero. When the callout precedes an opening parenthesis, the length is that
+of the entire subpattern.
+.P
+The \fIpattern_position\fP and \fInext_item_length\fP fields are intended to
+help in distinguishing between different automatic callouts, which all have the
+same callout number. However, they are set for all callouts, and are used by
+\fBpcre2test\fP to show the next item to be matched when displaying callout
+information.
+.P
+In callouts from \fBpcre2_match()\fP the \fImark\fP field contains a pointer to
+the zero-terminated name of the most recently passed (*MARK), (*PRUNE), or
+(*THEN) item in the match, or NULL if no such items have been passed. Instances
+of (*PRUNE) or (*THEN) without a name do not obliterate a previous (*MARK). In
+callouts from the DFA matching function this field always contains NULL.
+.
+.
+.SH "RETURN VALUES FROM CALLOUTS"
+.rs
+.sp
+The external callout function returns an integer to PCRE2. If the value is
+zero, matching proceeds as normal. If the value is greater than zero, matching
+fails at the current point, but the testing of other matching possibilities
+goes ahead, just as if a lookahead assertion had failed. If the value is less
+than zero, the match is abandoned, and the matching function returns the
+negative value.
+.P
+Negative values should normally be chosen from the set of PCRE2_ERROR_xxx
+values. In particular, PCRE2_ERROR_NOMATCH forces a standard "no match"
+failure. The error number PCRE2_ERROR_CALLOUT is reserved for use by callout
+functions; it will never be used by PCRE2 itself.
+.
+.
+.SH "CALLOUT ENUMERATION"
+.rs
+.sp
+.nf
+.B int pcre2_callout_enumerate(const pcre2_code *\fIcode\fP,
+.B "  int (*\fIcallback\fP)(pcre2_callout_enumerate_block *, void *),"
+.B "  void *\fIuser_data\fP);"
+.fi
+.sp
+A script language that supports the use of string arguments in callouts might
+like to scan all the callouts in a pattern before running the match. This can
+be done by calling \fBpcre2_callout_enumerate()\fP. The first argument is a
+pointer to a compiled pattern, the second points to a callback function, and
+the third is arbitrary user data. The callback function is called for every
+callout in the pattern in the order in which they appear. Its first argument is
+a pointer to a callout enumeration block, and its second argument is the
+\fIuser_data\fP value that was passed to \fBpcre2_callout_enumerate()\fP. The
+data block contains the following fields:
+.sp
+  \fIversion\fP                Block version number
+  \fIpattern_position\fP       Offset to next item in pattern
+  \fInext_item_length\fP       Length of next item in pattern
+  \fIcallout_number\fP         Number for numbered callouts
+  \fIcallout_string_offset\fP  Offset to string within pattern
+  \fIcallout_string_length\fP  Length of callout string
+  \fIcallout_string\fP         Points to callout string or is NULL
+.sp
+The version number is currently 0. It will increase if new fields are ever
+added to the block. The remaining fields are the same as their namesakes in the
+\fBpcre2_callout\fP block that is used for callouts during matching, as
+described
+.\" HTML 
+.\" 
+above.
+.\"
+.P
+Note that the value of \fIpattern_position\fP is unique for each callout.
+However, if a callout occurs inside a group that is quantified with a non-zero
+minimum or a fixed maximum, the group is replicated inside the compiled
+pattern. For example, a pattern such as /(a){2}/ is compiled as if it were
+/(a)(a)/. This means that the callout will be enumerated more than once, but
+with the same value for \fIpattern_position\fP in each case.
+.P
+The callback function should normally return zero. If it returns a non-zero
+value, scanning the pattern stops, and that value is returned from
+\fBpcre2_callout_enumerate()\fP.
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel
+University Computing Service
+Cambridge, England.
+.fi
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 23 March 2015
+Copyright (c) 1997-2015 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/doc/pcre2compat.3 b/pcre2-10.20/doc/pcre2compat.3
new file mode 100644
index 000000000..a3306d782
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2compat.3
@@ -0,0 +1,190 @@
+.TH PCRE2COMPAT 3 "15 March 2015" "PCRE2 10.20"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH "DIFFERENCES BETWEEN PCRE2 AND PERL"
+.rs
+.sp
+This document describes the differences in the ways that PCRE2 and Perl handle
+regular expressions. The differences described here are with respect to Perl
+versions 5.10 and above.
+.P
+1. PCRE2 has only a subset of Perl's Unicode support. Details of what it does
+have are given in the
+.\" HREF
+\fBpcre2unicode\fP
+.\"
+page.
+.P
+2. PCRE2 allows repeat quantifiers only on parenthesized assertions, but they
+do not mean what you might think. For example, (?!a){3} does not assert that
+the next three characters are not "a". It just asserts that the next character
+is not "a" three times (in principle: PCRE2 optimizes this to run the assertion
+just once). Perl allows repeat quantifiers on other assertions such as \eb, but
+these do not seem to have any use.
+.P
+3. Capturing subpatterns that occur inside negative lookahead assertions are
+counted, but their entries in the offsets vector are never set. Perl sometimes
+(but not always) sets its numerical variables from inside negative assertions.
+.P
+4. The following Perl escape sequences are not supported: \el, \eu, \eL,
+\eU, and \eN when followed by a character name or Unicode value. (\eN on its
+own, matching a non-newline character, is supported.) In fact these are
+implemented by Perl's general string-handling and are not part of its pattern
+matching engine. If any of these are encountered by PCRE2, an error is
+generated by default. However, if the PCRE2_ALT_BSUX option is set,
+\eU and \eu are interpreted as ECMAScript interprets them.
+.P
+5. The Perl escape sequences \ep, \eP, and \eX are supported only if PCRE2 is
+built with Unicode support. The properties that can be tested with \ep and \eP
+are limited to the general category properties such as Lu and Nd, script names
+such as Greek or Han, and the derived properties Any and L&. PCRE2 does support
+the Cs (surrogate) property, which Perl does not; the Perl documentation says
+"Because Perl hides the need for the user to understand the internal
+representation of Unicode characters, there is no need to implement the
+somewhat messy concept of surrogates."
+.P
+6. PCRE2 does support the \eQ...\eE escape for quoting substrings. Characters
+in between are treated as literals. This is slightly different from Perl in
+that $ and @ are also handled as literals inside the quotes. In Perl, they
+cause variable interpolation (but of course PCRE2 does not have variables).
+Note the following examples:
+.sp
+    Pattern            PCRE2 matches      Perl matches
+.sp
+.\" JOIN
+    \eQabc$xyz\eE        abc$xyz           abc followed by the
+                                           contents of $xyz
+    \eQabc\e$xyz\eE       abc\e$xyz          abc\e$xyz
+    \eQabc\eE\e$\eQxyz\eE   abc$xyz           abc$xyz
+.sp
+The \eQ...\eE sequence is recognized both inside and outside character classes.
+.P
+7. Fairly obviously, PCRE2 does not support the (?{code}) and (??{code})
+constructions. However, there is support for recursive patterns. This is not
+available in Perl 5.8, but it is in Perl 5.10. Also, the PCRE2 "callout"
+feature allows an external function to be called during pattern matching. See
+the
+.\" HREF
+\fBpcre2callout\fP
+.\"
+documentation for details.
+.P
+8. Subroutine calls (whether recursive or not) are treated as atomic groups.
+Atomic recursion is like Python, but unlike Perl. Captured values that are set
+outside a subroutine call can be referenced from inside in PCRE2, but not in
+Perl. There is a discussion that explains these differences in more detail in
+the
+.\" HTML 
+.\" 
+section on recursion differences from Perl
+.\"
+in the
+.\" HREF
+\fBpcre2pattern\fP
+.\"
+page.
+.P
+9. If any of the backtracking control verbs are used in a subpattern that is
+called as a subroutine (whether or not recursively), their effect is confined
+to that subpattern; it does not extend to the surrounding pattern. This is not
+always the case in Perl. In particular, if (*THEN) is present in a group that
+is called as a subroutine, its action is limited to that group, even if the
+group does not contain any | characters. Note that such subpatterns are
+processed as anchored at the point where they are tested.
+.P
+10. If a pattern contains more than one backtracking control verb, the first
+one that is backtracked onto acts. For example, in the pattern
+A(*COMMIT)B(*PRUNE)C a failure in B triggers (*COMMIT), but a failure in C
+triggers (*PRUNE). Perl's behaviour is more complex; in many cases it is the
+same as PCRE2, but there are examples where it differs.
+.P
+11. Most backtracking verbs in assertions have their normal actions. They are
+not confined to the assertion.
+.P
+12. There are some differences that are concerned with the settings of captured
+strings when part of a pattern is repeated. For example, matching "aba" against
+the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE2 it is set to
+"b".
+.P
+13. PCRE2's handling of duplicate subpattern numbers and duplicate subpattern
+names is not as general as Perl's. This is a consequence of the fact the PCRE2
+works internally just with numbers, using an external table to translate
+between numbers and names. In particular, a pattern such as (?|(?A)|(?
+#include 
+#include 
+
+
+/**************************************************************************
+* Here is the program. The API includes the concept of "contexts" for     *
+* setting up unusual interface requirements for compiling and matching,   *
+* such as custom memory managers and non-standard newline definitions.    *
+* This program does not do any of this, so it makes no use of contexts,   *
+* always passing NULL where a context could be given.                     *
+**************************************************************************/
+
+int main(int argc, char **argv)
+{
+pcre2_code *re;
+PCRE2_SPTR pattern;     /* PCRE2_SPTR is a pointer to unsigned code units of */
+PCRE2_SPTR subject;     /* the appropriate width (8, 16, or 32 bits). */
+PCRE2_SPTR name_table;
+
+int crlf_is_newline;
+int errornumber;
+int find_all;
+int i;
+int namecount;
+int name_entry_size;
+int rc;
+int utf8;
+
+uint32_t option_bits;
+uint32_t newline;
+
+PCRE2_SIZE erroroffset;
+PCRE2_SIZE *ovector;
+
+size_t subject_length;
+pcre2_match_data *match_data;
+
+
+
+/**************************************************************************
+* First, sort out the command line. There is only one possible option at  *
+* the moment, "-g" to request repeated matching to find all occurrences,  *
+* like Perl's /g option. We set the variable find_all to a non-zero value *
+* if the -g option is present. Apart from that, there must be exactly two *
+* arguments.                                                              *
+**************************************************************************/
+
+find_all = 0;
+for (i = 1; i < argc; i++)
+  {
+  if (strcmp(argv[i], "-g") == 0) find_all = 1;
+    else break;
+  }
+
+/* After the options, we require exactly two arguments, which are the pattern,
+and the subject string. */
+
+if (argc - i != 2)
+  {
+  printf("Two arguments required: a regex and a subject string\en");
+  return 1;
+  }
+
+/* As pattern and subject are char arguments, they can be straightforwardly
+cast to PCRE2_SPTR as we are working in 8-bit code units. */
+
+pattern = (PCRE2_SPTR)argv[i];
+subject = (PCRE2_SPTR)argv[i+1];
+subject_length = strlen((char *)subject);
+
+
+/*************************************************************************
+* Now we are going to compile the regular expression pattern, and handle *
+* any errors that are detected.                                          *
+*************************************************************************/
+
+re = pcre2_compile(
+  pattern,               /* the pattern */
+  PCRE2_ZERO_TERMINATED, /* indicates pattern is zero-terminated */
+  0,                     /* default options */
+  &errornumber,          /* for error number */
+  &erroroffset,          /* for error offset */
+  NULL);                 /* use default compile context */
+
+/* Compilation failed: print the error message and exit. */
+
+if (re == NULL)
+  {
+  PCRE2_UCHAR buffer[256];
+  pcre2_get_error_message(errornumber, buffer, sizeof(buffer));
+  printf("PCRE2 compilation failed at offset %d: %s\en", (int)erroroffset,
+    buffer);
+  return 1;
+  }
+
+
+/*************************************************************************
+* If the compilation succeeded, we call PCRE again, in order to do a     *
+* pattern match against the subject string. This does just ONE match. If *
+* further matching is needed, it will be done below. Before running the  *
+* match we must set up a match_data block for holding the result.        *
+*************************************************************************/
+
+/* Using this function ensures that the block is exactly the right size for
+the number of capturing parentheses in the pattern. */
+
+match_data = pcre2_match_data_create_from_pattern(re, NULL);
+
+rc = pcre2_match(
+  re,                   /* the compiled pattern */
+  subject,              /* the subject string */
+  subject_length,       /* the length of the subject */
+  0,                    /* start at offset 0 in the subject */
+  0,                    /* default options */
+  match_data,           /* block for storing the result */
+  NULL);                /* use default match context */
+
+/* Matching failed: handle error cases */
+
+if (rc < 0)
+  {
+  switch(rc)
+    {
+    case PCRE2_ERROR_NOMATCH: printf("No match\en"); break;
+    /*
+    Handle other special cases if you like
+    */
+    default: printf("Matching error %d\en", rc); break;
+    }
+  pcre2_match_data_free(match_data);   /* Release memory used for the match */
+  pcre2_code_free(re);                 /* data and the compiled pattern. */
+  return 1;
+  }
+
+/* Match succeded. Get a pointer to the output vector, where string offsets are
+stored. */
+
+ovector = pcre2_get_ovector_pointer(match_data);
+printf("\enMatch succeeded at offset %d\en", (int)ovector[0]);
+
+
+/*************************************************************************
+* We have found the first match within the subject string. If the output *
+* vector wasn't big enough, say so. Then output any substrings that were *
+* captured.                                                              *
+*************************************************************************/
+
+/* The output vector wasn't big enough. This should not happen, because we used
+pcre2_match_data_create_from_pattern() above. */
+
+if (rc == 0)
+  printf("ovector was not big enough for all the captured substrings\en");
+
+/* Show substrings stored in the output vector by number. Obviously, in a real
+application you might want to do things other than print them. */
+
+for (i = 0; i < rc; i++)
+  {
+  PCRE2_SPTR substring_start = subject + ovector[2*i];
+  size_t substring_length = ovector[2*i+1] - ovector[2*i];
+  printf("%2d: %.*s\en", i, (int)substring_length, (char *)substring_start);
+  }
+
+
+/**************************************************************************
+* That concludes the basic part of this demonstration program. We have    *
+* compiled a pattern, and performed a single match. The code that follows *
+* shows first how to access named substrings, and then how to code for    *
+* repeated matches on the same subject.                                   *
+**************************************************************************/
+
+/* See if there are any named substrings, and if so, show them by name. First
+we have to extract the count of named parentheses from the pattern. */
+
+(void)pcre2_pattern_info(
+  re,                   /* the compiled pattern */
+  PCRE2_INFO_NAMECOUNT, /* get the number of named substrings */
+  &namecount);          /* where to put the answer */
+
+if (namecount <= 0) printf("No named substrings\en"); else
+  {
+  PCRE2_SPTR tabptr;
+  printf("Named substrings\en");
+
+  /* Before we can access the substrings, we must extract the table for
+  translating names to numbers, and the size of each entry in the table. */
+
+  (void)pcre2_pattern_info(
+    re,                       /* the compiled pattern */
+    PCRE2_INFO_NAMETABLE,     /* address of the table */
+    &name_table);             /* where to put the answer */
+
+  (void)pcre2_pattern_info(
+    re,                       /* the compiled pattern */
+    PCRE2_INFO_NAMEENTRYSIZE, /* size of each entry in the table */
+    &name_entry_size);        /* where to put the answer */
+
+  /* Now we can scan the table and, for each entry, print the number, the name,
+  and the substring itself. In the 8-bit library the number is held in two
+  bytes, most significant first. */
+
+  tabptr = name_table;
+  for (i = 0; i < namecount; i++)
+    {
+    int n = (tabptr[0] << 8) | tabptr[1];
+    printf("(%d) %*s: %.*s\en", n, name_entry_size - 3, tabptr + 2,
+      (int)(ovector[2*n+1] - ovector[2*n]), subject + ovector[2*n]);
+    tabptr += name_entry_size;
+    }
+  }
+
+
+/*************************************************************************
+* If the "-g" option was given on the command line, we want to continue  *
+* to search for additional matches in the subject string, in a similar   *
+* way to the /g option in Perl. This turns out to be trickier than you   *
+* might think because of the possibility of matching an empty string.    *
+* What happens is as follows:                                            *
+*                                                                        *
+* If the previous match was NOT for an empty string, we can just start   *
+* the next match at the end of the previous one.                         *
+*                                                                        *
+* If the previous match WAS for an empty string, we can't do that, as it *
+* would lead to an infinite loop. Instead, a call of pcre2_match() is    *
+* made with the PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED flags set. The *
+* first of these tells PCRE2 that an empty string at the start of the    *
+* subject is not a valid match; other possibilities must be tried. The   *
+* second flag restricts PCRE2 to one match attempt at the initial string *
+* position. If this match succeeds, an alternative to the empty string   *
+* match has been found, and we can print it and proceed round the loop,  *
+* advancing by the length of whatever was found. If this match does not  *
+* succeed, we still stay in the loop, advancing by just one character.   *
+* In UTF-8 mode, which can be set by (*UTF) in the pattern, this may be  *
+* more than one byte.                                                    *
+*                                                                        *
+* However, there is a complication concerned with newlines. When the     *
+* newline convention is such that CRLF is a valid newline, we must       *
+* advance by two characters rather than one. The newline convention can  *
+* be set in the regex by (*CR), etc.; if not, we must find the default.  *
+*************************************************************************/
+
+if (!find_all)     /* Check for -g */
+  {
+  pcre2_match_data_free(match_data);  /* Release the memory that was used */
+  pcre2_code_free(re);                /* for the match data and the pattern. */
+  return 0;                           /* Exit the program. */
+  }
+
+/* Before running the loop, check for UTF-8 and whether CRLF is a valid newline
+sequence. First, find the options with which the regex was compiled and extract
+the UTF state. */
+
+(void)pcre2_pattern_info(re, PCRE2_INFO_ALLOPTIONS, &option_bits);
+utf8 = (option_bits & PCRE2_UTF) != 0;
+
+/* Now find the newline convention and see whether CRLF is a valid newline
+sequence. */
+
+(void)pcre2_pattern_info(re, PCRE2_INFO_NEWLINE, &newline);
+crlf_is_newline = newline == PCRE2_NEWLINE_ANY ||
+                  newline == PCRE2_NEWLINE_CRLF ||
+                  newline == PCRE2_NEWLINE_ANYCRLF;
+
+/* Loop for second and subsequent matches */
+
+for (;;)
+  {
+  uint32_t options = 0;                    /* Normally no options */
+  PCRE2_SIZE start_offset = ovector[1];  /* Start at end of previous match */
+
+  /* If the previous match was for an empty string, we are finished if we are
+  at the end of the subject. Otherwise, arrange to run another match at the
+  same point to see if a non-empty match can be found. */
+
+  if (ovector[0] == ovector[1])
+    {
+    if (ovector[0] == subject_length) break;
+    options = PCRE2_NOTEMPTY_ATSTART | PCRE2_ANCHORED;
+    }
+
+  /* Run the next matching operation */
+
+  rc = pcre2_match(
+    re,                   /* the compiled pattern */
+    subject,              /* the subject string */
+    subject_length,       /* the length of the subject */
+    start_offset,         /* starting offset in the subject */
+    options,              /* options */
+    match_data,           /* block for storing the result */
+    NULL);                /* use default match context */
+
+  /* This time, a result of NOMATCH isn't an error. If the value in "options"
+  is zero, it just means we have found all possible matches, so the loop ends.
+  Otherwise, it means we have failed to find a non-empty-string match at a
+  point where there was a previous empty-string match. In this case, we do what
+  Perl does: advance the matching position by one character, and continue. We
+  do this by setting the "end of previous match" offset, because that is picked
+  up at the top of the loop as the point at which to start again.
+
+  There are two complications: (a) When CRLF is a valid newline sequence, and
+  the current position is just before it, advance by an extra byte. (b)
+  Otherwise we must ensure that we skip an entire UTF character if we are in
+  UTF mode. */
+
+  if (rc == PCRE2_ERROR_NOMATCH)
+    {
+    if (options == 0) break;                    /* All matches found */
+    ovector[1] = start_offset + 1;              /* Advance one code unit */
+    if (crlf_is_newline &&                      /* If CRLF is newline & */
+        start_offset < subject_length - 1 &&    /* we are at CRLF, */
+        subject[start_offset] == '\er' &&
+        subject[start_offset + 1] == '\en')
+      ovector[1] += 1;                          /* Advance by one more. */
+    else if (utf8)                              /* Otherwise, ensure we */
+      {                                         /* advance a whole UTF-8 */
+      while (ovector[1] < subject_length)       /* character. */
+        {
+        if ((subject[ovector[1]] & 0xc0) != 0x80) break;
+        ovector[1] += 1;
+        }
+      }
+    continue;    /* Go round the loop again */
+    }
+
+  /* Other matching errors are not recoverable. */
+
+  if (rc < 0)
+    {
+    printf("Matching error %d\en", rc);
+    pcre2_match_data_free(match_data);
+    pcre2_code_free(re);
+    return 1;
+    }
+
+  /* Match succeded */
+
+  printf("\enMatch succeeded again at offset %d\en", (int)ovector[0]);
+
+  /* The match succeeded, but the output vector wasn't big enough. This
+  should not happen. */
+
+  if (rc == 0)
+    printf("ovector was not big enough for all the captured substrings\en");
+
+  /* As before, show substrings stored in the output vector by number, and then
+  also any named substrings. */
+
+  for (i = 0; i < rc; i++)
+    {
+    PCRE2_SPTR substring_start = subject + ovector[2*i];
+    size_t substring_length = ovector[2*i+1] - ovector[2*i];
+    printf("%2d: %.*s\en", i, (int)substring_length, (char *)substring_start);
+    }
+
+  if (namecount <= 0) printf("No named substrings\en"); else
+    {
+    PCRE2_SPTR tabptr = name_table;
+    printf("Named substrings\en");
+    for (i = 0; i < namecount; i++)
+      {
+      int n = (tabptr[0] << 8) | tabptr[1];
+      printf("(%d) %*s: %.*s\en", n, name_entry_size - 3, tabptr + 2,
+        (int)(ovector[2*n+1] - ovector[2*n]), subject + ovector[2*n]);
+      tabptr += name_entry_size;
+      }
+    }
+  }      /* End of loop to find second and subsequent matches */
+
+printf("\en");
+pcre2_match_data_free(match_data);
+pcre2_code_free(re);
+return 0;
+}
+
+/* End of pcre2demo.c */
+.EE
diff --git a/pcre2-10.20/doc/pcre2grep.1 b/pcre2-10.20/doc/pcre2grep.1
new file mode 100644
index 000000000..028a91e4e
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2grep.1
@@ -0,0 +1,705 @@
+.TH PCRE2GREP 1 "03 January 2015" "PCRE2 10.00"
+.SH NAME
+pcre2grep - a grep with Perl-compatible regular expressions.
+.SH SYNOPSIS
+.B pcre2grep [options] [long options] [pattern] [path1 path2 ...]
+.
+.SH DESCRIPTION
+.rs
+.sp
+\fBpcre2grep\fP searches files for character patterns, in the same way as other
+grep commands do, but it uses the PCRE2 regular expression library to support
+patterns that are compatible with the regular expressions of Perl 5. See
+.\" HREF
+\fBpcre2syntax\fP(3)
+.\"
+for a quick-reference summary of pattern syntax, or
+.\" HREF
+\fBpcre2pattern\fP(3)
+.\"
+for a full description of the syntax and semantics of the regular expressions
+that PCRE2 supports.
+.P
+Patterns, whether supplied on the command line or in a separate file, are given
+without delimiters. For example:
+.sp
+  pcre2grep Thursday /etc/motd
+.sp
+If you attempt to use delimiters (for example, by surrounding a pattern with
+slashes, as is common in Perl scripts), they are interpreted as part of the
+pattern. Quotes can of course be used to delimit patterns on the command line
+because they are interpreted by the shell, and indeed quotes are required if a
+pattern contains white space or shell metacharacters.
+.P
+The first argument that follows any option settings is treated as the single
+pattern to be matched when neither \fB-e\fP nor \fB-f\fP is present.
+Conversely, when one or both of these options are used to specify patterns, all
+arguments are treated as path names. At least one of \fB-e\fP, \fB-f\fP, or an
+argument pattern must be provided.
+.P
+If no files are specified, \fBpcre2grep\fP reads the standard input. The
+standard input can also be referenced by a name consisting of a single hyphen.
+For example:
+.sp
+  pcre2grep some-pattern file1 - file3
+.sp
+Input files are searched line by line. By default, each line that matches a
+pattern is copied to the standard output, and if there is more than one file,
+the file name is output at the start of each line, followed by a colon.
+However, there are options that can change how \fBpcre2grep\fP behaves. In
+particular, the \fB-M\fP option makes it possible to search for strings that
+span line boundaries. What defines a line boundary is controlled by the
+\fB-N\fP (\fB--newline\fP) option.
+.P
+The amount of memory used for buffering files that are being scanned is
+controlled by a parameter that can be set by the \fB--buffer-size\fP option.
+The default value for this parameter is specified when \fBpcre2grep\fP is
+built, with the default default being 20K. A block of memory three times this
+size is used (to allow for buffering "before" and "after" lines). An error
+occurs if a line overflows the buffer.
+.P
+Patterns can be no longer than 8K or BUFSIZ bytes, whichever is the greater.
+BUFSIZ is defined in \fB\fP. When there is more than one pattern
+(specified by the use of \fB-e\fP and/or \fB-f\fP), each pattern is applied to
+each line in the order in which they are defined, except that all the \fB-e\fP
+patterns are tried before the \fB-f\fP patterns.
+.P
+By default, as soon as one pattern matches a line, no further patterns are
+considered. However, if \fB--colour\fP (or \fB--color\fP) is used to colour the
+matching substrings, or if \fB--only-matching\fP, \fB--file-offsets\fP, or
+\fB--line-offsets\fP is used to output only the part of the line that matched
+(either shown literally, or as an offset), scanning resumes immediately
+following the match, so that further matches on the same line can be found. If
+there are multiple patterns, they are all tried on the remainder of the line,
+but patterns that follow the one that matched are not tried on the earlier part
+of the line.
+.P
+This behaviour means that the order in which multiple patterns are specified
+can affect the output when one of the above options is used. This is no longer
+the same behaviour as GNU grep, which now manages to display earlier matches
+for later patterns (as long as there is no overlap).
+.P
+Patterns that can match an empty string are accepted, but empty string
+matches are never recognized. An example is the pattern "(super)?(man)?", in
+which all components are optional. This pattern finds all occurrences of both
+"super" and "man"; the output differs from matching with "super|man" when only
+the matching substrings are being shown.
+.P
+If the \fBLC_ALL\fP or \fBLC_CTYPE\fP environment variable is set,
+\fBpcre2grep\fP uses the value to set a locale when calling the PCRE2 library.
+The \fB--locale\fP option can be used to override this.
+.
+.
+.SH "SUPPORT FOR COMPRESSED FILES"
+.rs
+.sp
+It is possible to compile \fBpcre2grep\fP so that it uses \fBlibz\fP or
+\fBlibbz2\fP to read files whose names end in \fB.gz\fP or \fB.bz2\fP,
+respectively. You can find out whether your binary has support for one or both
+of these file types by running it with the \fB--help\fP option. If the
+appropriate support is not present, files are treated as plain text. The
+standard input is always so treated.
+.
+.
+.SH "BINARY FILES"
+.rs
+.sp
+By default, a file that contains a binary zero byte within the first 1024 bytes
+is identified as a binary file, and is processed specially. (GNU grep also
+identifies binary files in this manner.) See the \fB--binary-files\fP option
+for a means of changing the way binary files are handled.
+.
+.
+.SH OPTIONS
+.rs
+.sp
+The order in which some of the options appear can affect the output. For
+example, both the \fB-h\fP and \fB-l\fP options affect the printing of file
+names. Whichever comes later in the command line will be the one that takes
+effect. Similarly, except where noted below, if an option is given twice, the
+later setting is used. Numerical values for options may be followed by K or M,
+to signify multiplication by 1024 or 1024*1024 respectively.
+.TP 10
+\fB--\fP
+This terminates the list of options. It is useful if the next item on the
+command line starts with a hyphen but is not an option. This allows for the
+processing of patterns and file names that start with hyphens.
+.TP
+\fB-A\fP \fInumber\fP, \fB--after-context=\fP\fInumber\fP
+Output \fInumber\fP lines of context after each matching line. If file names
+and/or line numbers are being output, a hyphen separator is used instead of a
+colon for the context lines. A line containing "--" is output between each
+group of lines, unless they are in fact contiguous in the input file. The value
+of \fInumber\fP is expected to be relatively small. However, \fBpcre2grep\fP
+guarantees to have up to 8K of following text available for context output.
+.TP
+\fB-a\fP, \fB--text\fP
+Treat binary files as text. This is equivalent to
+\fB--binary-files\fP=\fItext\fP.
+.TP
+\fB-B\fP \fInumber\fP, \fB--before-context=\fP\fInumber\fP
+Output \fInumber\fP lines of context before each matching line. If file names
+and/or line numbers are being output, a hyphen separator is used instead of a
+colon for the context lines. A line containing "--" is output between each
+group of lines, unless they are in fact contiguous in the input file. The value
+of \fInumber\fP is expected to be relatively small. However, \fBpcre2grep\fP
+guarantees to have up to 8K of preceding text available for context output.
+.TP
+\fB--binary-files=\fP\fIword\fP
+Specify how binary files are to be processed. If the word is "binary" (the
+default), pattern matching is performed on binary files, but the only output is
+"Binary file  matches" when a match succeeds. If the word is "text",
+which is equivalent to the \fB-a\fP or \fB--text\fP option, binary files are
+processed in the same way as any other file. In this case, when a match
+succeeds, the output may be binary garbage, which can have nasty effects if
+sent to a terminal. If the word is "without-match", which is equivalent to the
+\fB-I\fP option, binary files are not processed at all; they are assumed not to
+be of interest and are skipped without causing any output or affecting the
+return code.
+.TP
+\fB--buffer-size=\fP\fInumber\fP
+Set the parameter that controls how much memory is used for buffering files
+that are being scanned.
+.TP
+\fB-C\fP \fInumber\fP, \fB--context=\fP\fInumber\fP
+Output \fInumber\fP lines of context both before and after each matching line.
+This is equivalent to setting both \fB-A\fP and \fB-B\fP to the same value.
+.TP
+\fB-c\fP, \fB--count\fP
+Do not output lines from the files that are being scanned; instead output the
+number of matches (or non-matches if \fB-v\fP is used) that would otherwise
+have caused lines to be shown. By default, this count is the same as the number
+of suppressed lines, but if the \fB-M\fP (multiline) option is used (without
+\fB-v\fP), there may be more suppressed lines than the number of matches.
+.sp
+If no lines are selected, the number zero is output. If several files are are
+being scanned, a count is output for each of them. However, if the
+\fB--files-with-matches\fP option is also used, only those files whose counts
+are greater than zero are listed. When \fB-c\fP is used, the \fB-A\fP,
+\fB-B\fP, and \fB-C\fP options are ignored.
+.TP
+\fB--colour\fP, \fB--color\fP
+If this option is given without any data, it is equivalent to "--colour=auto".
+If data is required, it must be given in the same shell item, separated by an
+equals sign.
+.TP
+\fB--colour=\fP\fIvalue\fP, \fB--color=\fP\fIvalue\fP
+This option specifies under what circumstances the parts of a line that matched
+a pattern should be coloured in the output. By default, the output is not
+coloured. The value (which is optional, see above) may be "never", "always", or
+"auto". In the latter case, colouring happens only if the standard output is
+connected to a terminal. More resources are used when colouring is enabled,
+because \fBpcre2grep\fP has to search for all possible matches in a line, not
+just one, in order to colour them all.
+.sp
+The colour that is used can be specified by setting the environment variable
+PCRE2GREP_COLOUR or PCRE2GREP_COLOR. The value of this variable should be a
+string of two numbers, separated by a semicolon. They are copied directly into
+the control string for setting colour on a terminal, so it is your
+responsibility to ensure that they make sense. If neither of the environment
+variables is set, the default is "1;31", which gives red.
+.TP
+\fB-D\fP \fIaction\fP, \fB--devices=\fP\fIaction\fP
+If an input path is not a regular file or a directory, "action" specifies how
+it is to be processed. Valid values are "read" (the default) or "skip"
+(silently skip the path).
+.TP
+\fB-d\fP \fIaction\fP, \fB--directories=\fP\fIaction\fP
+If an input path is a directory, "action" specifies how it is to be processed.
+Valid values are "read" (the default in non-Windows environments, for
+compatibility with GNU grep), "recurse" (equivalent to the \fB-r\fP option), or
+"skip" (silently skip the path, the default in Windows environments). In the
+"read" case, directories are read as if they were ordinary files. In some
+operating systems the effect of reading a directory like this is an immediate
+end-of-file; in others it may provoke an error.
+.TP
+\fB-e\fP \fIpattern\fP, \fB--regex=\fP\fIpattern\fP, \fB--regexp=\fP\fIpattern\fP
+Specify a pattern to be matched. This option can be used multiple times in
+order to specify several patterns. It can also be used as a way of specifying a
+single pattern that starts with a hyphen. When \fB-e\fP is used, no argument
+pattern is taken from the command line; all arguments are treated as file
+names. There is no limit to the number of patterns. They are applied to each
+line in the order in which they are defined until one matches.
+.sp
+If \fB-f\fP is used with \fB-e\fP, the command line patterns are matched first,
+followed by the patterns from the file(s), independent of the order in which
+these options are specified. Note that multiple use of \fB-e\fP is not the same
+as a single pattern with alternatives. For example, X|Y finds the first
+character in a line that is X or Y, whereas if the two patterns are given
+separately, with X first, \fBpcre2grep\fP finds X if it is present, even if it
+follows Y in the line. It finds Y only if there is no X in the line. This
+matters only if you are using \fB-o\fP or \fB--colo(u)r\fP to show the part(s)
+of the line that matched.
+.TP
+\fB--exclude\fP=\fIpattern\fP
+Files (but not directories) whose names match the pattern are skipped without
+being processed. This applies to all files, whether listed on the command line,
+obtained from \fB--file-list\fP, or by scanning a directory. The pattern is a
+PCRE2 regular expression, and is matched against the final component of the
+file name, not the entire path. The \fB-F\fP, \fB-w\fP, and \fB-x\fP options do
+not apply to this pattern. The option may be given any number of times in order
+to specify multiple patterns. If a file name matches both an \fB--include\fP
+and an \fB--exclude\fP pattern, it is excluded. There is no short form for this
+option.
+.TP
+\fB--exclude-from=\fP\fIfilename\fP
+Treat each non-empty line of the file as the data for an \fB--exclude\fP
+option. What constitutes a newline when reading the file is the operating
+system's default. The \fB--newline\fP option has no effect on this option. This
+option may be given more than once in order to specify a number of files to
+read.
+.TP
+\fB--exclude-dir\fP=\fIpattern\fP
+Directories whose names match the pattern are skipped without being processed,
+whatever the setting of the \fB--recursive\fP option. This applies to all
+directories, whether listed on the command line, obtained from
+\fB--file-list\fP, or by scanning a parent directory. The pattern is a PCRE2
+regular expression, and is matched against the final component of the directory
+name, not the entire path. The \fB-F\fP, \fB-w\fP, and \fB-x\fP options do not
+apply to this pattern. The option may be given any number of times in order to
+specify more than one pattern. If a directory matches both \fB--include-dir\fP
+and \fB--exclude-dir\fP, it is excluded. There is no short form for this
+option.
+.TP
+\fB-F\fP, \fB--fixed-strings\fP
+Interpret each data-matching pattern as a list of fixed strings, separated by
+newlines, instead of as a regular expression. What constitutes a newline for
+this purpose is controlled by the \fB--newline\fP option. The \fB-w\fP (match
+as a word) and \fB-x\fP (match whole line) options can be used with \fB-F\fP.
+They apply to each of the fixed strings. A line is selected if any of the fixed
+strings are found in it (subject to \fB-w\fP or \fB-x\fP, if present). This
+option applies only to the patterns that are matched against the contents of
+files; it does not apply to patterns specified by any of the \fB--include\fP or
+\fB--exclude\fP options.
+.TP
+\fB-f\fP \fIfilename\fP, \fB--file=\fP\fIfilename\fP
+Read patterns from the file, one per line, and match them against
+each line of input. What constitutes a newline when reading the file is the
+operating system's default. The \fB--newline\fP option has no effect on this
+option. Trailing white space is removed from each line, and blank lines are
+ignored. An empty file contains no patterns and therefore matches nothing. See
+also the comments about multiple patterns versus a single pattern with
+alternatives in the description of \fB-e\fP above.
+.sp
+If this option is given more than once, all the specified files are
+read. A data line is output if any of the patterns match it. A file name can
+be given as "-" to refer to the standard input. When \fB-f\fP is used, patterns
+specified on the command line using \fB-e\fP may also be present; they are
+tested before the file's patterns. However, no other pattern is taken from the
+command line; all arguments are treated as the names of paths to be searched.
+.TP
+\fB--file-list\fP=\fIfilename\fP
+Read a list of files and/or directories that are to be scanned from the given
+file, one per line. Trailing white space is removed from each line, and blank
+lines are ignored. These paths are processed before any that are listed on the
+command line. The file name can be given as "-" to refer to the standard input.
+If \fB--file\fP and \fB--file-list\fP are both specified as "-", patterns are
+read first. This is useful only when the standard input is a terminal, from
+which further lines (the list of files) can be read after an end-of-file
+indication. If this option is given more than once, all the specified files are
+read.
+.TP
+\fB--file-offsets\fP
+Instead of showing lines or parts of lines that match, show each match as an
+offset from the start of the file and a length, separated by a comma. In this
+mode, no context is shown. That is, the \fB-A\fP, \fB-B\fP, and \fB-C\fP
+options are ignored. If there is more than one match in a line, each of them is
+shown separately. This option is mutually exclusive with \fB--line-offsets\fP
+and \fB--only-matching\fP.
+.TP
+\fB-H\fP, \fB--with-filename\fP
+Force the inclusion of the file name at the start of output lines when
+searching a single file. By default, the file name is not shown in this case.
+For matching lines, the file name is followed by a colon; for context lines, a
+hyphen separator is used. If a line number is also being output, it follows the
+file name. When the \fB-M\fP option causes a pattern to match more than one
+line, only the first is preceded by the file name.
+.TP
+\fB-h\fP, \fB--no-filename\fP
+Suppress the output file names when searching multiple files. By default,
+file names are shown when multiple files are searched. For matching lines, the
+file name is followed by a colon; for context lines, a hyphen separator is used.
+If a line number is also being output, it follows the file name.
+.TP
+\fB--help\fP
+Output a help message, giving brief details of the command options and file
+type support, and then exit. Anything else on the command line is
+ignored.
+.TP
+\fB-I\fP
+Ignore binary files. This is equivalent to
+\fB--binary-files\fP=\fIwithout-match\fP.
+.TP
+\fB-i\fP, \fB--ignore-case\fP
+Ignore upper/lower case distinctions during comparisons.
+.TP
+\fB--include\fP=\fIpattern\fP
+If any \fB--include\fP patterns are specified, the only files that are
+processed are those that match one of the patterns (and do not match an
+\fB--exclude\fP pattern). This option does not affect directories, but it
+applies to all files, whether listed on the command line, obtained from
+\fB--file-list\fP, or by scanning a directory. The pattern is a PCRE2 regular
+expression, and is matched against the final component of the file name, not
+the entire path. The \fB-F\fP, \fB-w\fP, and \fB-x\fP options do not apply to
+this pattern. The option may be given any number of times. If a file name
+matches both an \fB--include\fP and an \fB--exclude\fP pattern, it is excluded.
+There is no short form for this option.
+.TP
+\fB--include-from=\fP\fIfilename\fP
+Treat each non-empty line of the file as the data for an \fB--include\fP
+option. What constitutes a newline for this purpose is the operating system's
+default. The \fB--newline\fP option has no effect on this option. This option
+may be given any number of times; all the files are read.
+.TP
+\fB--include-dir\fP=\fIpattern\fP
+If any \fB--include-dir\fP patterns are specified, the only directories that
+are processed are those that match one of the patterns (and do not match an
+\fB--exclude-dir\fP pattern). This applies to all directories, whether listed
+on the command line, obtained from \fB--file-list\fP, or by scanning a parent
+directory. The pattern is a PCRE2 regular expression, and is matched against
+the final component of the directory name, not the entire path. The \fB-F\fP,
+\fB-w\fP, and \fB-x\fP options do not apply to this pattern. The option may be
+given any number of times. If a directory matches both \fB--include-dir\fP and
+\fB--exclude-dir\fP, it is excluded. There is no short form for this option.
+.TP
+\fB-L\fP, \fB--files-without-match\fP
+Instead of outputting lines from the files, just output the names of the files
+that do not contain any lines that would have been output. Each file name is
+output once, on a separate line.
+.TP
+\fB-l\fP, \fB--files-with-matches\fP
+Instead of outputting lines from the files, just output the names of the files
+containing lines that would have been output. Each file name is output
+once, on a separate line. Searching normally stops as soon as a matching line
+is found in a file. However, if the \fB-c\fP (count) option is also used,
+matching continues in order to obtain the correct count, and those files that
+have at least one match are listed along with their counts. Using this option
+with \fB-c\fP is a way of suppressing the listing of files with no matches.
+.TP
+\fB--label\fP=\fIname\fP
+This option supplies a name to be used for the standard input when file names
+are being output. If not supplied, "(standard input)" is used. There is no
+short form for this option.
+.TP
+\fB--line-buffered\fP
+When this option is given, input is read and processed line by line, and the
+output is flushed after each write. By default, input is read in large chunks,
+unless \fBpcre2grep\fP can determine that it is reading from a terminal (which
+is currently possible only in Unix-like environments). Output to terminal is
+normally automatically flushed by the operating system. This option can be
+useful when the input or output is attached to a pipe and you do not want
+\fBpcre2grep\fP to buffer up large amounts of data. However, its use will
+affect performance, and the \fB-M\fP (multiline) option ceases to work.
+.TP
+\fB--line-offsets\fP
+Instead of showing lines or parts of lines that match, show each match as a
+line number, the offset from the start of the line, and a length. The line
+number is terminated by a colon (as usual; see the \fB-n\fP option), and the
+offset and length are separated by a comma. In this mode, no context is shown.
+That is, the \fB-A\fP, \fB-B\fP, and \fB-C\fP options are ignored. If there is
+more than one match in a line, each of them is shown separately. This option is
+mutually exclusive with \fB--file-offsets\fP and \fB--only-matching\fP.
+.TP
+\fB--locale\fP=\fIlocale-name\fP
+This option specifies a locale to be used for pattern matching. It overrides
+the value in the \fBLC_ALL\fP or \fBLC_CTYPE\fP environment variables. If no
+locale is specified, the PCRE2 library's default (usually the "C" locale) is
+used. There is no short form for this option.
+.TP
+\fB--match-limit\fP=\fInumber\fP
+Processing some regular expression patterns can require a very large amount of
+memory, leading in some cases to a program crash if not enough is available.
+Other patterns may take a very long time to search for all possible matching
+strings. The \fBpcre2_match()\fP function that is called by \fBpcre2grep\fP to
+do the matching has two parameters that can limit the resources that it uses.
+.sp
+The \fB--match-limit\fP option provides a means of limiting resource usage
+when processing patterns that are not going to match, but which have a very
+large number of possibilities in their search trees. The classic example is a
+pattern that uses nested unlimited repeats. Internally, PCRE2 uses a function
+called \fBmatch()\fP which it calls repeatedly (sometimes recursively). The
+limit set by \fB--match-limit\fP is imposed on the number of times this
+function is called during a match, which has the effect of limiting the amount
+of backtracking that can take place.
+.sp
+The \fB--recursion-limit\fP option is similar to \fB--match-limit\fP, but
+instead of limiting the total number of times that \fBmatch()\fP is called, it
+limits the depth of recursive calls, which in turn limits the amount of memory
+that can be used. The recursion depth is a smaller number than the total number
+of calls, because not all calls to \fBmatch()\fP are recursive. This limit is
+of use only if it is set smaller than \fB--match-limit\fP.
+.sp
+There are no short forms for these options. The default settings are specified
+when the PCRE2 library is compiled, with the default default being 10 million.
+.TP
+\fB-M\fP, \fB--multiline\fP
+Allow patterns to match more than one line. When this option is given, patterns
+may usefully contain literal newline characters and internal occurrences of ^
+and $ characters. The output for a successful match may consist of more than
+one line. The first is the line in which the match started, and the last is the
+line in which the match ended. If the matched string ends with a newline
+sequence the output ends at the end of that line.
+.sp
+When this option is set, the PCRE2 library is called in "multiline" mode.
+However, \fBpcre2grep\fP still processes the input line by line. The difference
+is that a matched string may extend past the end of a line and continue on
+one or more subsequent lines. The newline sequence must be matched as part of
+the pattern. For example, to find the phrase "regular expression" in a file
+where "regular" might be at the end of a line and "expression" at the start of
+the next line, you could use this command:
+.sp
+  pcre2grep -M 'regular\es+expression' 
+.sp
+The \es escape sequence matches any white space character, including newlines,
+and is followed by + so as to match trailing white space on the first line as
+well as possibly handling a two-character newline sequence.
+.sp
+There is a limit to the number of lines that can be matched, imposed by the way
+that \fBpcre2grep\fP buffers the input file as it scans it. However,
+\fBpcre2grep\fP ensures that at least 8K characters or the rest of the file
+(whichever is the shorter) are available for forward matching, and similarly
+the previous 8K characters (or all the previous characters, if fewer than 8K)
+are guaranteed to be available for lookbehind assertions. The \fB-M\fP option
+does not work when input is read line by line (see \fP--line-buffered\fP.)
+.TP
+\fB-N\fP \fInewline-type\fP, \fB--newline\fP=\fInewline-type\fP
+The PCRE2 library supports five different conventions for indicating
+the ends of lines. They are the single-character sequences CR (carriage return)
+and LF (linefeed), the two-character sequence CRLF, an "anycrlf" convention,
+which recognizes any of the preceding three types, and an "any" convention, in
+which any Unicode line ending sequence is assumed to end a line. The Unicode
+sequences are the three just mentioned, plus VT (vertical tab, U+000B), FF
+(form feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and
+PS (paragraph separator, U+2029).
+.sp
+When the PCRE2 library is built, a default line-ending sequence is specified.
+This is normally the standard sequence for the operating system. Unless
+otherwise specified by this option, \fBpcre2grep\fP uses the library's default.
+The possible values for this option are CR, LF, CRLF, ANYCRLF, or ANY. This
+makes it possible to use \fBpcre2grep\fP to scan files that have come from
+other environments without having to modify their line endings. If the data
+that is being scanned does not agree with the convention set by this option,
+\fBpcre2grep\fP may behave in strange ways. Note that this option does not
+apply to files specified by the \fB-f\fP, \fB--exclude-from\fP, or
+\fB--include-from\fP options, which are expected to use the operating system's
+standard newline sequence.
+.TP
+\fB-n\fP, \fB--line-number\fP
+Precede each output line by its line number in the file, followed by a colon
+for matching lines or a hyphen for context lines. If the file name is also
+being output, it precedes the line number. When the \fB-M\fP option causes a
+pattern to match more than one line, only the first is preceded by its line
+number. This option is forced if \fB--line-offsets\fP is used.
+.TP
+\fB--no-jit\fP
+If the PCRE2 library is built with support for just-in-time compiling (which
+speeds up matching), \fBpcre2grep\fP automatically makes use of this, unless it
+was explicitly disabled at build time. This option can be used to disable the
+use of JIT at run time. It is provided for testing and working round problems.
+It should never be needed in normal use.
+.TP
+\fB-o\fP, \fB--only-matching\fP
+Show only the part of the line that matched a pattern instead of the whole
+line. In this mode, no context is shown. That is, the \fB-A\fP, \fB-B\fP, and
+\fB-C\fP options are ignored. If there is more than one match in a line, each
+of them is shown separately. If \fB-o\fP is combined with \fB-v\fP (invert the
+sense of the match to find non-matching lines), no output is generated, but the
+return code is set appropriately. If the matched portion of the line is empty,
+nothing is output unless the file name or line number are being printed, in
+which case they are shown on an otherwise empty line. This option is mutually
+exclusive with \fB--file-offsets\fP and \fB--line-offsets\fP.
+.TP
+\fB-o\fP\fInumber\fP, \fB--only-matching\fP=\fInumber\fP
+Show only the part of the line that matched the capturing parentheses of the
+given number. Up to 32 capturing parentheses are supported, and -o0 is
+equivalent to \fB-o\fP without a number. Because these options can be given
+without an argument (see above), if an argument is present, it must be given in
+the same shell item, for example, -o3 or --only-matching=2. The comments given
+for the non-argument case above also apply to this case. If the specified
+capturing parentheses do not exist in the pattern, or were not set in the
+match, nothing is output unless the file name or line number are being output.
+.sp
+If this option is given multiple times, multiple substrings are output, in the
+order the options are given. For example, -o3 -o1 -o3 causes the substrings
+matched by capturing parentheses 3 and 1 and then 3 again to be output. By
+default, there is no separator (but see the next option).
+.TP
+\fB--om-separator\fP=\fItext\fP
+Specify a separating string for multiple occurrences of \fB-o\fP. The default
+is an empty string. Separating strings are never coloured.
+.TP
+\fB-q\fP, \fB--quiet\fP
+Work quietly, that is, display nothing except error messages. The exit
+status indicates whether or not any matches were found.
+.TP
+\fB-r\fP, \fB--recursive\fP
+If any given path is a directory, recursively scan the files it contains,
+taking note of any \fB--include\fP and \fB--exclude\fP settings. By default, a
+directory is read as a normal file; in some operating systems this gives an
+immediate end-of-file. This option is a shorthand for setting the \fB-d\fP
+option to "recurse".
+.TP
+\fB--recursion-limit\fP=\fInumber\fP
+See \fB--match-limit\fP above.
+.TP
+\fB-s\fP, \fB--no-messages\fP
+Suppress error messages about non-existent or unreadable files. Such files are
+quietly skipped. However, the return code is still 2, even if matches were
+found in other files.
+.TP
+\fB-u\fP, \fB--utf-8\fP
+Operate in UTF-8 mode. This option is available only if PCRE2 has been compiled
+with UTF-8 support. All patterns (including those for any \fB--exclude\fP and
+\fB--include\fP options) and all subject lines that are scanned must be valid
+strings of UTF-8 characters.
+.TP
+\fB-V\fP, \fB--version\fP
+Write the version numbers of \fBpcre2grep\fP and the PCRE2 library to the
+standard output and then exit. Anything else on the command line is
+ignored.
+.TP
+\fB-v\fP, \fB--invert-match\fP
+Invert the sense of the match, so that lines which do \fInot\fP match any of
+the patterns are the ones that are found.
+.TP
+\fB-w\fP, \fB--word-regex\fP, \fB--word-regexp\fP
+Force the patterns to match only whole words. This is equivalent to having \eb
+at the start and end of the pattern. This option applies only to the patterns
+that are matched against the contents of files; it does not apply to patterns
+specified by any of the \fB--include\fP or \fB--exclude\fP options.
+.TP
+\fB-x\fP, \fB--line-regex\fP, \fB--line-regexp\fP
+Force the patterns to be anchored (each must start matching at the beginning of
+a line) and in addition, require them to match entire lines. This is equivalent
+to having ^ and $ characters at the start and end of each alternative top-level
+branch in every pattern. This option applies only to the patterns that are
+matched against the contents of files; it does not apply to patterns specified
+by any of the \fB--include\fP or \fB--exclude\fP options.
+.
+.
+.SH "ENVIRONMENT VARIABLES"
+.rs
+.sp
+The environment variables \fBLC_ALL\fP and \fBLC_CTYPE\fP are examined, in that
+order, for a locale. The first one that is set is used. This can be overridden
+by the \fB--locale\fP option. If no locale is set, the PCRE2 library's default
+(usually the "C" locale) is used.
+.
+.
+.SH "NEWLINES"
+.rs
+.sp
+The \fB-N\fP (\fB--newline\fP) option allows \fBpcre2grep\fP to scan files with
+different newline conventions from the default. Any parts of the input files
+that are written to the standard output are copied identically, with whatever
+newline sequences they have in the input. However, the setting of this option
+does not affect the interpretation of files specified by the \fB-f\fP,
+\fB--exclude-from\fP, or \fB--include-from\fP options, which are assumed to use
+the operating system's standard newline sequence, nor does it affect the way in
+which \fBpcre2grep\fP writes informational messages to the standard error and
+output streams. For these it uses the string "\en" to indicate newlines,
+relying on the C I/O library to convert this to an appropriate sequence.
+.
+.
+.SH "OPTIONS COMPATIBILITY"
+.rs
+.sp
+Many of the short and long forms of \fBpcre2grep\fP's options are the same
+as in the GNU \fBgrep\fP program. Any long option of the form
+\fB--xxx-regexp\fP (GNU terminology) is also available as \fB--xxx-regex\fP
+(PCRE2 terminology). However, the \fB--file-list\fP, \fB--file-offsets\fP,
+\fB--include-dir\fP, \fB--line-offsets\fP, \fB--locale\fP, \fB--match-limit\fP,
+\fB-M\fP, \fB--multiline\fP, \fB-N\fP, \fB--newline\fP, \fB--om-separator\fP,
+\fB--recursion-limit\fP, \fB-u\fP, and \fB--utf-8\fP options are specific to
+\fBpcre2grep\fP, as is the use of the \fB--only-matching\fP option with a
+capturing parentheses number.
+.P
+Although most of the common options work the same way, a few are different in
+\fBpcre2grep\fP. For example, the \fB--include\fP option's argument is a glob
+for GNU \fBgrep\fP, but a regular expression for \fBpcre2grep\fP. If both the
+\fB-c\fP and \fB-l\fP options are given, GNU grep lists only file names,
+without counts, but \fBpcre2grep\fP gives the counts as well.
+.
+.
+.SH "OPTIONS WITH DATA"
+.rs
+.sp
+There are four different ways in which an option with data can be specified.
+If a short form option is used, the data may follow immediately, or (with one
+exception) in the next command line item. For example:
+.sp
+  -f/some/file
+  -f /some/file
+.sp
+The exception is the \fB-o\fP option, which may appear with or without data.
+Because of this, if data is present, it must follow immediately in the same
+item, for example -o3.
+.P
+If a long form option is used, the data may appear in the same command line
+item, separated by an equals character, or (with two exceptions) it may appear
+in the next command line item. For example:
+.sp
+  --file=/some/file
+  --file /some/file
+.sp
+Note, however, that if you want to supply a file name beginning with ~ as data
+in a shell command, and have the shell expand ~ to a home directory, you must
+separate the file name from the option, because the shell does not treat ~
+specially unless it is at the start of an item.
+.P
+The exceptions to the above are the \fB--colour\fP (or \fB--color\fP) and
+\fB--only-matching\fP options, for which the data is optional. If one of these
+options does have data, it must be given in the first form, using an equals
+character. Otherwise \fBpcre2grep\fP will assume that it has no data.
+.
+.
+.SH "MATCHING ERRORS"
+.rs
+.sp
+It is possible to supply a regular expression that takes a very long time to
+fail to match certain lines. Such patterns normally involve nested indefinite
+repeats, for example: (a+)*\ed when matched against a line of a's with no final
+digit. The PCRE2 matching function has a resource limit that causes it to abort
+in these circumstances. If this happens, \fBpcre2grep\fP outputs an error
+message and the line that caused the problem to the standard error stream. If
+there are more than 20 such errors, \fBpcre2grep\fP gives up.
+.P
+The \fB--match-limit\fP option of \fBpcre2grep\fP can be used to set the
+overall resource limit; there is a second option called \fB--recursion-limit\fP
+that sets a limit on the amount of memory (usually stack) that is used (see the
+discussion of these options above).
+.
+.
+.SH DIAGNOSTICS
+.rs
+.sp
+Exit status is 0 if any matches were found, 1 if no matches were found, and 2
+for syntax errors, overlong lines, non-existent or inaccessible files (even if
+matches were found in other files) or too many matching errors. Using the
+\fB-s\fP option to suppress error messages about inaccessible files does not
+affect the return code.
+.
+.
+.SH "SEE ALSO"
+.rs
+.sp
+\fBpcre2pattern\fP(3), \fBpcre2syntax\fP(3).
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel
+University Computing Service
+Cambridge, England.
+.fi
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 03 January 2015
+Copyright (c) 1997-2015 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/doc/pcre2grep.txt b/pcre2-10.20/doc/pcre2grep.txt
new file mode 100644
index 000000000..29cd75cfa
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2grep.txt
@@ -0,0 +1,769 @@
+PCRE2GREP(1)                General Commands Manual               PCRE2GREP(1)
+
+
+
+NAME
+       pcre2grep - a grep with Perl-compatible regular expressions.
+
+SYNOPSIS
+       pcre2grep [options] [long options] [pattern] [path1 path2 ...]
+
+
+DESCRIPTION
+
+       pcre2grep  searches  files  for  character patterns, in the same way as
+       other grep commands do,  but  it  uses  the  PCRE2  regular  expression
+       library  to  support  patterns  that  are  compatible  with the regular
+       expressions of Perl 5. See pcre2syntax(3) for a quick-reference summary
+       of  pattern  syntax,  or  pcre2pattern(3) for a full description of the
+       syntax and semantics of the regular expressions that PCRE2 supports.
+
+       Patterns, whether supplied on the command line or in a  separate  file,
+       are given without delimiters. For example:
+
+         pcre2grep Thursday /etc/motd
+
+       If you attempt to use delimiters (for example, by surrounding a pattern
+       with slashes, as is common in Perl scripts), they  are  interpreted  as
+       part  of  the pattern. Quotes can of course be used to delimit patterns
+       on the command line because they are  interpreted  by  the  shell,  and
+       indeed  quotes  are required if a pattern contains white space or shell
+       metacharacters.
+
+       The first argument that follows any option settings is treated  as  the
+       single  pattern  to be matched when neither -e nor -f is present.  Con-
+       versely, when one or both of these options are  used  to  specify  pat-
+       terns, all arguments are treated as path names. At least one of -e, -f,
+       or an argument pattern must be provided.
+
+       If no files are specified, pcre2grep  reads  the  standard  input.  The
+       standard  input can also be referenced by a name consisting of a single
+       hyphen.  For example:
+
+         pcre2grep some-pattern file1 - file3
+
+       Input files are searched line by  line.  By  default,  each  line  that
+       matches  a  pattern  is  copied to the standard output, and if there is
+       more than one file, the file name is output at the start of each  line,
+       followed  by  a  colon.  However, there are options that can change how
+       pcre2grep behaves. In particular, the -M option makes  it  possible  to
+       search  for  strings  that  span  line  boundaries. What defines a line
+       boundary is controlled by the -N (--newline) option.
+
+       The amount of memory used for buffering files that are being scanned is
+       controlled  by a parameter that can be set by the --buffer-size option.
+       The default value for this parameter is  specified  when  pcre2grep  is
+       built,  with  the  default  default  being 20K. A block of memory three
+       times this size is used (to allow for buffering  "before"  and  "after"
+       lines). An error occurs if a line overflows the buffer.
+
+       Patterns  can  be  no  longer than 8K or BUFSIZ bytes, whichever is the
+       greater.  BUFSIZ is defined in . When there is more  than  one
+       pattern (specified by the use of -e and/or -f), each pattern is applied
+       to each line in the order in which they are defined,  except  that  all
+       the -e patterns are tried before the -f patterns.
+
+       By  default, as soon as one pattern matches a line, no further patterns
+       are considered. However, if --colour (or --color) is used to colour the
+       matching  substrings, or if --only-matching, --file-offsets, or --line-
+       offsets is used to output only  the  part  of  the  line  that  matched
+       (either shown literally, or as an offset), scanning resumes immediately
+       following the match, so that further matches on the same  line  can  be
+       found.  If  there  are  multiple  patterns,  they  are all tried on the
+       remainder of the line, but patterns that follow the  one  that  matched
+       are not tried on the earlier part of the line.
+
+       This  behaviour  means  that  the  order in which multiple patterns are
+       specified can affect the output when one of the above options is  used.
+       This  is no longer the same behaviour as GNU grep, which now manages to
+       display earlier matches for later patterns (as  long  as  there  is  no
+       overlap).
+
+       Patterns  that can match an empty string are accepted, but empty string
+       matches   are   never   recognized.   An   example   is   the   pattern
+       "(super)?(man)?",  in  which  all components are optional. This pattern
+       finds all occurrences of both "super" and  "man";  the  output  differs
+       from  matching  with  "super|man" when only the matching substrings are
+       being shown.
+
+       If the LC_ALL or LC_CTYPE environment variable is set,  pcre2grep  uses
+       the value to set a locale when calling the PCRE2 library.  The --locale
+       option can be used to override this.
+
+
+SUPPORT FOR COMPRESSED FILES
+
+       It is possible to compile pcre2grep so that it uses libz or  libbz2  to
+       read  files  whose names end in .gz or .bz2, respectively. You can find
+       out whether your binary has support for one or both of these file types
+       by running it with the --help option. If the appropriate support is not
+       present, files are treated as plain text. The standard input is  always
+       so treated.
+
+
+BINARY FILES
+
+       By  default,  a  file that contains a binary zero byte within the first
+       1024 bytes is identified as a binary file, and is processed  specially.
+       (GNU  grep  also  identifies  binary  files  in  this  manner.) See the
+       --binary-files option for a means of changing the way binary files  are
+       handled.
+
+
+OPTIONS
+
+       The  order  in  which some of the options appear can affect the output.
+       For example, both the -h and -l options affect  the  printing  of  file
+       names.  Whichever  comes later in the command line will be the one that
+       takes effect. Similarly, except where noted  below,  if  an  option  is
+       given  twice,  the  later setting is used. Numerical values for options
+       may be followed by K  or  M,  to  signify  multiplication  by  1024  or
+       1024*1024 respectively.
+
+       --        This terminates the list of options. It is useful if the next
+                 item on the command line starts with a hyphen but is  not  an
+                 option.  This  allows for the processing of patterns and file
+                 names that start with hyphens.
+
+       -A number, --after-context=number
+                 Output number lines of context after each matching  line.  If
+                 file  names  and/or  line  numbers are being output, a hyphen
+                 separator is used instead of a colon for the context lines. A
+                 line  containing  "--" is output between each group of lines,
+                 unless they are in fact contiguous in  the  input  file.  The
+                 value  of number is expected to be relatively small. However,
+                 pcre2grep guarantees to have  up  to  8K  of  following  text
+                 available for context output.
+
+       -a, --text
+                 Treat  binary  files as text. This is equivalent to --binary-
+                 files=text.
+
+       -B number, --before-context=number
+                 Output number lines of context before each matching line.  If
+                 file  names  and/or  line  numbers are being output, a hyphen
+                 separator is used instead of a colon for the context lines. A
+                 line  containing  "--" is output between each group of lines,
+                 unless they are in fact contiguous in  the  input  file.  The
+                 value  of number is expected to be relatively small. However,
+                 pcre2grep guarantees to have  up  to  8K  of  preceding  text
+                 available for context output.
+
+       --binary-files=word
+                 Specify  how binary files are to be processed. If the word is
+                 "binary" (the default),  pattern  matching  is  performed  on
+                 binary  files,  but  the  only  output is "Binary file 
+                 matches" when a match succeeds. If the word is "text",  which
+                 is  equivalent  to  the -a or --text option, binary files are
+                 processed in the same way as any other file.  In  this  case,
+                 when  a  match  succeeds,  the  output may be binary garbage,
+                 which can have nasty effects if sent to a  terminal.  If  the
+                 word  is  "without-match",  which  is  equivalent  to  the -I
+                 option, binary files are  not  processed  at  all;  they  are
+                 assumed not to be of interest and are skipped without causing
+                 any output or affecting the return code.
+
+       --buffer-size=number
+                 Set the parameter that controls how much memory is  used  for
+                 buffering files that are being scanned.
+
+       -C number, --context=number
+                 Output  number  lines  of  context both before and after each
+                 matching line.  This is equivalent to setting both -A and  -B
+                 to the same value.
+
+       -c, --count
+                 Do  not  output  lines from the files that are being scanned;
+                 instead output the number of matches (or non-matches if -v is
+                 used)  that would otherwise have caused lines to be shown. By
+                 default, this count is the same as the number  of  suppressed
+                 lines, but if the -M (multiline) option is used (without -v),
+                 there may  be  more  suppressed  lines  than  the  number  of
+                 matches.
+
+                 If  no lines are selected, the number zero is output. If sev-
+                 eral files are are being scanned, a count is output for  each
+                 of  them. However, if the --files-with-matches option is also
+                 used, only those files whose counts are greater than zero are
+                 listed.  When  -c  is  used,  the  -A, -B, and -C options are
+                 ignored.
+
+       --colour, --color
+                 If this option is given without any data, it is equivalent to
+                 "--colour=auto".   If  data  is required, it must be given in
+                 the same shell item, separated by an equals sign.
+
+       --colour=value, --color=value
+                 This option specifies under what circumstances the parts of a
+                 line that matched a pattern should be coloured in the output.
+                 By default, the output is not coloured. The value  (which  is
+                 optional,  see above) may be "never", "always", or "auto". In
+                 the latter case, colouring happens only if the standard  out-
+                 put  is connected to a terminal. More resources are used when
+                 colouring is enabled, because pcre2grep has to search for all
+                 possible  matches in a line, not just one, in order to colour
+                 them all.
+
+                 The colour that is used can be specified by setting the envi-
+                 ronment  variable  PCRE2GREP_COLOUR  or  PCRE2GREP_COLOR. The
+                 value of this variable should be a  string  of  two  numbers,
+                 separated  by  a semicolon. They are copied directly into the
+                 control string for setting colour on a  terminal,  so  it  is
+                 your  responsibility  to ensure that they make sense. If nei-
+                 ther of the environment variables  is  set,  the  default  is
+                 "1;31", which gives red.
+
+       -D action, --devices=action
+                 If  an  input  path  is  not  a  regular file or a directory,
+                 "action" specifies how it is to be  processed.  Valid  values
+                 are "read" (the default) or "skip" (silently skip the path).
+
+       -d action, --directories=action
+                 If an input path is a directory, "action" specifies how it is
+                 to be processed.  Valid values are  "read"  (the  default  in
+                 non-Windows  environments,  for compatibility with GNU grep),
+                 "recurse" (equivalent to the -r option), or "skip"  (silently
+                 skip  the  path, the default in Windows environments). In the
+                 "read" case, directories are read as if  they  were  ordinary
+                 files.  In  some  operating  systems  the effect of reading a
+                 directory like this is an immediate end-of-file; in others it
+                 may provoke an error.
+
+       -e pattern, --regex=pattern, --regexp=pattern
+                 Specify a pattern to be matched. This option can be used mul-
+                 tiple times in order to specify several patterns. It can also
+                 be  used  as a way of specifying a single pattern that starts
+                 with a hyphen. When -e is used, no argument pattern is  taken
+                 from  the  command  line;  all  arguments are treated as file
+                 names. There is no limit to the number of patterns. They  are
+                 applied  to  each line in the order in which they are defined
+                 until one matches.
+
+                 If -f is used with -e, the command line patterns are  matched
+                 first, followed by the patterns from the file(s), independent
+                 of the order in which these options are specified. Note  that
+                 multiple  use  of -e is not the same as a single pattern with
+                 alternatives. For example, X|Y finds the first character in a
+                 line  that  is  X or Y, whereas if the two patterns are given
+                 separately, with X first, pcre2grep finds X if it is present,
+                 even if it follows Y in the line. It finds Y only if there is
+                 no X in the line. This matters only if you are  using  -o  or
+                 --colo(u)r to show the part(s) of the line that matched.
+
+       --exclude=pattern
+                 Files (but not directories) whose names match the pattern are
+                 skipped without being processed. This applies to  all  files,
+                 whether  listed  on  the  command line, obtained from --file-
+                 list, or by scanning a directory. The pattern is a PCRE2 reg-
+                 ular  expression,  and is matched against the final component
+                 of the file name, not the entire path. The  -F,  -w,  and  -x
+                 options do not apply to this pattern. The option may be given
+                 any number of times in order to specify multiple patterns. If
+                 a  file  name matches both an --include and an --exclude pat-
+                 tern, it is excluded. There is no short form for this option.
+
+       --exclude-from=filename
+                 Treat each non-empty line of the file  as  the  data  for  an
+                 --exclude option. What constitutes a newline when reading the
+                 file is the operating system's default. The --newline  option
+                 has  no  effect on this option. This option may be given more
+                 than once in order to specify a number of files to read.
+
+       --exclude-dir=pattern
+                 Directories whose names match the pattern are skipped without
+                 being  processed,  whatever  the  setting  of the --recursive
+                 option. This applies to all directories,  whether  listed  on
+                 the command line, obtained from --file-list, or by scanning a
+                 parent directory. The pattern is a PCRE2 regular  expression,
+                 and  is  matched against the final component of the directory
+                 name, not the entire path. The -F, -w, and -x options do  not
+                 apply  to this pattern. The option may be given any number of
+                 times in order to specify more than one pattern. If a  direc-
+                 tory  matches  both  --include-dir  and  --exclude-dir, it is
+                 excluded. There is no short form for this option.
+
+       -F, --fixed-strings
+                 Interpret each data-matching  pattern  as  a  list  of  fixed
+                 strings,  separated  by  newlines,  instead  of  as a regular
+                 expression. What constitutes a newline for  this  purpose  is
+                 controlled  by the --newline option. The -w (match as a word)
+                 and -x (match whole line) options can be used with -F.   They
+                 apply to each of the fixed strings. A line is selected if any
+                 of the fixed strings are found in it (subject to -w or -x, if
+                 present).  This  option applies only to the patterns that are
+                 matched against the contents of files; it does not  apply  to
+                 patterns  specified  by  any  of  the  --include or --exclude
+                 options.
+
+       -f filename, --file=filename
+                 Read patterns from the file, one per  line,  and  match  them
+                 against  each  line of input. What constitutes a newline when
+                 reading the file  is  the  operating  system's  default.  The
+                 --newline option has no effect on this option. Trailing white
+                 space is removed from each line, and blank lines are ignored.
+                 An  empty  file  contains  no  patterns and therefore matches
+                 nothing. See also the comments about multiple patterns versus
+                 a  single  pattern with alternatives in the description of -e
+                 above.
+
+                 If this option is given more than  once,  all  the  specified
+                 files  are read. A data line is output if any of the patterns
+                 match it. A file name can be given as "-"  to  refer  to  the
+                 standard  input.  When  -f is used, patterns specified on the
+                 command line using -e may also be present;  they  are  tested
+                 before  the  file's  patterns.  However,  no other pattern is
+                 taken from the command line; all arguments are treated as the
+                 names of paths to be searched.
+
+       --file-list=filename
+                 Read  a  list  of  files  and/or  directories  that are to be
+                 scanned from the given file, one  per  line.  Trailing  white
+                 space is removed from each line, and blank lines are ignored.
+                 These paths are processed before any that are listed  on  the
+                 command  line.  The file name can be given as "-" to refer to
+                 the standard input.  If --file and --file-list are both spec-
+                 ified  as  "-",  patterns are read first. This is useful only
+                 when the standard input is a  terminal,  from  which  further
+                 lines  (the  list  of files) can be read after an end-of-file
+                 indication. If this option is given more than once,  all  the
+                 specified files are read.
+
+       --file-offsets
+                 Instead  of  showing lines or parts of lines that match, show
+                 each match as an offset from the start  of  the  file  and  a
+                 length,  separated  by  a  comma. In this mode, no context is
+                 shown. That is, the -A, -B, and -C options  are  ignored.  If
+                 there is more than one match in a line, each of them is shown
+                 separately. This option is mutually  exclusive  with  --line-
+                 offsets and --only-matching.
+
+       -H, --with-filename
+                 Force  the  inclusion of the file name at the start of output
+                 lines when searching a single file. By default, the file name
+                 is not shown in this case.  For matching lines, the file name
+                 is followed by a colon; for context lines, a hyphen separator
+                 is  used.  If  a line number is also being output, it follows
+                 the file name. When the -M option causes a pattern  to  match
+                 more  than  one  line, only the first is preceded by the file
+                 name.
+
+       -h, --no-filename
+                 Suppress the output file names when searching multiple files.
+                 By  default,  file  names  are  shown when multiple files are
+                 searched. For matching lines, the file name is followed by  a
+                 colon;  for  context lines, a hyphen separator is used.  If a
+                 line number is also being output, it follows the file name.
+
+       --help    Output a help message, giving brief details  of  the  command
+                 options  and  file type support, and then exit. Anything else
+                 on the command line is ignored.
+
+       -I        Ignore  binary  files.  This  is  equivalent   to   --binary-
+                 files=without-match.
+
+       -i, --ignore-case
+                 Ignore upper/lower case distinctions during comparisons.
+
+       --include=pattern
+                 If  any --include patterns are specified, the only files that
+                 are processed are those that match one of the  patterns  (and
+                 do  not  match  an  --exclude  pattern). This option does not
+                 affect directories, but it  applies  to  all  files,  whether
+                 listed  on the command line, obtained from --file-list, or by
+                 scanning a directory. The pattern is a PCRE2 regular  expres-
+                 sion,  and is matched against the final component of the file
+                 name, not the entire path. The -F, -w, and -x options do  not
+                 apply  to this pattern. The option may be given any number of
+                 times. If a file  name  matches  both  an  --include  and  an
+                 --exclude  pattern,  it  is excluded.  There is no short form
+                 for this option.
+
+       --include-from=filename
+                 Treat each non-empty line of the file  as  the  data  for  an
+                 --include option. What constitutes a newline for this purpose
+                 is the operating system's default. The --newline  option  has
+                 no effect on this option. This option may be given any number
+                 of times; all the files are read.
+
+       --include-dir=pattern
+                 If any --include-dir patterns are specified, the only  direc-
+                 tories  that  are  processed  are those that match one of the
+                 patterns (and do not match an  --exclude-dir  pattern).  This
+                 applies  to  all  directories,  whether listed on the command
+                 line, obtained from --file-list,  or  by  scanning  a  parent
+                 directory.  The pattern is a PCRE2 regular expression, and is
+                 matched against the final component of  the  directory  name,
+                 not  the entire path. The -F, -w, and -x options do not apply
+                 to this pattern. The option may be given any number of times.
+                 If  a directory matches both --include-dir and --exclude-dir,
+                 it is excluded. There is no short form for this option.
+
+       -L, --files-without-match
+                 Instead of outputting lines from the files, just  output  the
+                 names  of  the files that do not contain any lines that would
+                 have been output. Each file name is output once, on  a  sepa-
+                 rate line.
+
+       -l, --files-with-matches
+                 Instead  of  outputting lines from the files, just output the
+                 names of the files containing lines that would have been out-
+                 put.  Each  file  name  is  output  once, on a separate line.
+                 Searching normally stops as soon as a matching line is  found
+                 in  a  file.  However, if the -c (count) option is also used,
+                 matching continues in order to obtain the correct count,  and
+                 those  files  that  have  at least one match are listed along
+                 with their counts. Using this option with -c is a way of sup-
+                 pressing the listing of files with no matches.
+
+       --label=name
+                 This option supplies a name to be used for the standard input
+                 when file names are being output. If not supplied, "(standard
+                 input)" is used. There is no short form for this option.
+
+       --line-buffered
+                 When  this  option is given, input is read and processed line
+                 by line, and the output  is  flushed  after  each  write.  By
+                 default,  input is read in large chunks, unless pcre2grep can
+                 determine that it is reading from a terminal (which  is  cur-
+                 rently  possible  only  in Unix-like environments). Output to
+                 terminal is normally automatically flushed by  the  operating
+                 system. This option can be useful when the input or output is
+                 attached to a pipe and you do not want pcre2grep to buffer up
+                 large  amounts  of data. However, its use will affect perfor-
+                 mance, and the -M (multiline) option ceases to work.
+
+       --line-offsets
+                 Instead of showing lines or parts of lines that  match,  show
+                 each match as a line number, the offset from the start of the
+                 line, and a length. The line number is terminated by a  colon
+                 (as  usual; see the -n option), and the offset and length are
+                 separated by a comma. In this  mode,  no  context  is  shown.
+                 That  is, the -A, -B, and -C options are ignored. If there is
+                 more than one match in a line, each of them  is  shown  sepa-
+                 rately. This option is mutually exclusive with --file-offsets
+                 and --only-matching.
+
+       --locale=locale-name
+                 This option specifies a locale to be used for pattern  match-
+                 ing.  It  overrides the value in the LC_ALL or LC_CTYPE envi-
+                 ronment variables. If  no  locale  is  specified,  the  PCRE2
+                 library's  default (usually the "C" locale) is used. There is
+                 no short form for this option.
+
+       --match-limit=number
+                 Processing some regular expression  patterns  can  require  a
+                 very  large amount of memory, leading in some cases to a pro-
+                 gram crash if not enough is available.   Other  patterns  may
+                 take  a  very  long  time to search for all possible matching
+                 strings.  The  pcre2_match()  function  that  is  called   by
+                 pcre2grep  to  do  the  matching  has two parameters that can
+                 limit the resources that it uses.
+
+                 The  --match-limit  option  provides  a  means  of   limiting
+                 resource usage when processing patterns that are not going to
+                 match, but which have a very large number of possibilities in
+                 their  search  trees.  The  classic example is a pattern that
+                 uses nested unlimited repeats. Internally, PCRE2 uses a func-
+                 tion  called  match()  which  it  calls repeatedly (sometimes
+                 recursively). The limit set by --match-limit  is  imposed  on
+                 the  number  of times this function is called during a match,
+                 which has the effect of limiting the amount  of  backtracking
+                 that can take place.
+
+                 The --recursion-limit option is similar to --match-limit, but
+                 instead of limiting the total number of times that match() is
+                 called, it limits the depth of recursive calls, which in turn
+                 limits the amount of memory that can be used.  The  recursion
+                 depth  is  a  smaller  number than the total number of calls,
+                 because not all calls to match() are recursive. This limit is
+                 of use only if it is set smaller than --match-limit.
+
+                 There  are no short forms for these options. The default set-
+                 tings are specified when the PCRE2 library is compiled,  with
+                 the default default being 10 million.
+
+       -M, --multiline
+                 Allow  patterns to match more than one line. When this option
+                 is given, patterns may usefully contain literal newline char-
+                 acters  and  internal  occurrences of ^ and $ characters. The
+                 output for a successful match may consist of  more  than  one
+                 line.  The  first is the line in which the match started, and
+                 the last is the line in which the match ended. If the matched
+                 string  ends  with  a newline sequence the output ends at the
+                 end of that line.
+
+                 When this option is set, the PCRE2 library is called in "mul-
+                 tiline"  mode.   However, pcre2grep still processes the input
+                 line by line. The difference is that  a  matched  string  may
+                 extend  past  the  end  of a line and continue on one or more
+                 subsequent lines. The newline sequence  must  be  matched  as
+                 part of the pattern. For example, to find the phrase "regular
+                 expression" in a file where "regular" might be at the end  of
+                 a  line  and  "expression" at the start of the next line, you
+                 could use this command:
+
+                   pcre2grep -M 'regular\s+expression' 
+
+                 The \s escape sequence matches  any  white  space  character,
+                 including  newlines,  and  is  followed  by  + so as to match
+                 trailing white space on the first line as  well  as  possibly
+                 handling a two-character newline sequence.
+
+                 There  is a limit to the number of lines that can be matched,
+                 imposed by the way that pcre2grep buffers the input  file  as
+                 it  scans  it.  However,  pcre2grep  ensures that at least 8K
+                 characters or the rest of the file (whichever is the shorter)
+                 are  available for forward matching, and similarly the previ-
+                 ous 8K characters (or all the previous characters,  if  fewer
+                 than 8K) are guaranteed to be available for lookbehind asser-
+                 tions. The -M option does not work when input is read line by
+                 line (see --line-buffered.)
+
+       -N newline-type, --newline=newline-type
+                 The  PCRE2  library  supports  five different conventions for
+                 indicating the ends of lines. They are  the  single-character
+                 sequences  CR  (carriage  return) and LF (linefeed), the two-
+                 character sequence CRLF, an "anycrlf" convention, which  rec-
+                 ognizes  any  of the preceding three types, and an "any" con-
+                 vention, in which any Unicode line ending sequence is assumed
+                 to  end a line. The Unicode sequences are the three just men-
+                 tioned, plus  VT  (vertical  tab,  U+000B),  FF  (form  feed,
+                 U+000C),   NEL  (next  line,  U+0085),  LS  (line  separator,
+                 U+2028), and PS (paragraph separator, U+2029).
+
+                 When the  PCRE2  library  is  built,  a  default  line-ending
+                 sequence   is  specified.   This  is  normally  the  standard
+                 sequence for the operating system. Unless otherwise specified
+                 by  this  option,  pcre2grep uses the library's default.  The
+                 possible values for this option are CR, LF, CRLF, ANYCRLF, or
+                 ANY.  This  makes  it possible to use pcre2grep to scan files
+                 that have come from other environments without having to mod-
+                 ify  their  line  endings.  If the data that is being scanned
+                 does not agree  with  the  convention  set  by  this  option,
+                 pcre2grep  may  behave in strange ways. Note that this option
+                 does not apply to files specified by the -f,  --exclude-from,
+                 or  --include-from  options,  which  are  expected to use the
+                 operating system's standard newline sequence.
+
+       -n, --line-number
+                 Precede each output line by its line number in the file, fol-
+                 lowed  by  a colon for matching lines or a hyphen for context
+                 lines. If the file name is also being output, it precedes the
+                 line  number.  When  the  -M option causes a pattern to match
+                 more than one line, only the first is preceded  by  its  line
+                 number. This option is forced if --line-offsets is used.
+
+       --no-jit  If  the  PCRE2 library is built with support for just-in-time
+                 compiling (which speeds up matching), pcre2grep automatically
+                 makes use of this, unless it was explicitly disabled at build
+                 time. This option can be used to disable the use  of  JIT  at
+                 run  time. It is provided for testing and working round prob-
+                 lems.  It should never be needed in normal use.
+
+       -o, --only-matching
+                 Show only the part of the line that matched a pattern instead
+                 of  the  whole  line. In this mode, no context is shown. That
+                 is, the -A, -B, and -C options are ignored. If there is  more
+                 than  one  match in a line, each of them is shown separately.
+                 If -o is combined with -v (invert the sense of the  match  to
+                 find  non-matching  lines),  no  output is generated, but the
+                 return code is set appropriately. If the matched  portion  of
+                 the  line is empty, nothing is output unless the file name or
+                 line number are being printed, in which case they  are  shown
+                 on an otherwise empty line. This option is mutually exclusive
+                 with --file-offsets and --line-offsets.
+
+       -onumber, --only-matching=number
+                 Show only the part of the line  that  matched  the  capturing
+                 parentheses of the given number. Up to 32 capturing parenthe-
+                 ses are supported, and -o0 is equivalent to -o without a num-
+                 ber.  Because  these options can be given without an argument
+                 (see above), if an argument is present, it must be  given  in
+                 the  same  shell item, for example, -o3 or --only-matching=2.
+                 The comments given for the non-argument case above also apply
+                 to  this  case. If the specified capturing parentheses do not
+                 exist in the pattern, or were not set in the  match,  nothing
+                 is  output unless the file name or line number are being out-
+                 put.
+
+                 If this option is given multiple times,  multiple  substrings
+                 are  output, in the order the options are given. For example,
+                 -o3 -o1 -o3 causes the substrings matched by capturing paren-
+                 theses  3  and  1  and then 3 again to be output. By default,
+                 there is no separator (but see the next option).
+
+       --om-separator=text
+                 Specify a separating string for multiple occurrences  of  -o.
+                 The  default is an empty string. Separating strings are never
+                 coloured.
+
+       -q, --quiet
+                 Work quietly, that is, display nothing except error messages.
+                 The  exit  status  indicates  whether or not any matches were
+                 found.
+
+       -r, --recursive
+                 If any given path is a directory, recursively scan the  files
+                 it  contains, taking note of any --include and --exclude set-
+                 tings. By default, a directory is read as a normal  file;  in
+                 some  operating  systems this gives an immediate end-of-file.
+                 This option is a shorthand  for  setting  the  -d  option  to
+                 "recurse".
+
+       --recursion-limit=number
+                 See --match-limit above.
+
+       -s, --no-messages
+                 Suppress  error  messages  about  non-existent  or unreadable
+                 files. Such files are quietly skipped.  However,  the  return
+                 code is still 2, even if matches were found in other files.
+
+       -u, --utf-8
+                 Operate in UTF-8 mode. This option is available only if PCRE2
+                 has been compiled with UTF-8 support. All patterns (including
+                 those  for  any --exclude and --include options) and all sub-
+                 ject lines that are scanned must be valid  strings  of  UTF-8
+                 characters.
+
+       -V, --version
+                 Write  the version numbers of pcre2grep and the PCRE2 library
+                 to the standard output and then exit. Anything  else  on  the
+                 command line is ignored.
+
+       -v, --invert-match
+                 Invert  the  sense  of  the match, so that lines which do not
+                 match any of the patterns are the ones that are found.
+
+       -w, --word-regex, --word-regexp
+                 Force the patterns to match only whole words. This is equiva-
+                 lent  to  having \b at the start and end of the pattern. This
+                 option applies only to the patterns that are matched  against
+                 the  contents  of files; it does not apply to patterns speci-
+                 fied by any of the --include or --exclude options.
+
+       -x, --line-regex, --line-regexp
+                 Force the patterns to be anchored (each must  start  matching
+                 at  the beginning of a line) and in addition, require them to
+                 match entire lines. This is equivalent  to  having  ^  and  $
+                 characters at the start and end of each alternative top-level
+                 branch in every pattern. This option applies only to the pat-
+                 terns that are matched against the contents of files; it does
+                 not apply to patterns specified by any of  the  --include  or
+                 --exclude options.
+
+
+ENVIRONMENT VARIABLES
+
+       The  environment  variables  LC_ALL  and LC_CTYPE are examined, in that
+       order, for a locale. The first one that is set is  used.  This  can  be
+       overridden  by  the  --locale  option.  If  no locale is set, the PCRE2
+       library's default (usually the "C" locale) is used.
+
+
+NEWLINES
+
+       The -N (--newline) option allows pcre2grep to scan files with different
+       newline conventions from the default. Any parts of the input files that
+       are written to the standard output are copied identically,  with  what-
+       ever  newline sequences they have in the input. However, the setting of
+       this option does not affect the interpretation of  files  specified  by
+       the -f, --exclude-from, or --include-from options, which are assumed to
+       use the operating system's  standard  newline  sequence,  nor  does  it
+       affect  the way in which pcre2grep writes informational messages to the
+       standard error and output streams. For these it uses the string "\n" to
+       indicate  newlines,  relying on the C I/O library to convert this to an
+       appropriate sequence.
+
+
+OPTIONS COMPATIBILITY
+
+       Many of the short and long forms of pcre2grep's options are the same as
+       in  the GNU grep program. Any long option of the form --xxx-regexp (GNU
+       terminology) is also available as --xxx-regex (PCRE2 terminology). How-
+       ever,  the  --file-list, --file-offsets, --include-dir, --line-offsets,
+       --locale, --match-limit, -M, --multiline, -N,  --newline,  --om-separa-
+       tor,  --recursion-limit,  -u,  and  --utf-8  options  are  specific  to
+       pcre2grep, as is the use of the --only-matching option with a capturing
+       parentheses number.
+
+       Although  most  of the common options work the same way, a few are dif-
+       ferent in pcre2grep. For example, the --include option's argument is  a
+       glob  for GNU grep, but a regular expression for pcre2grep. If both the
+       -c and -l options are given, GNU grep lists only  file  names,  without
+       counts, but pcre2grep gives the counts as well.
+
+
+OPTIONS WITH DATA
+
+       There are four different ways in which an option with data can be spec-
+       ified.  If a short form option is used, the  data  may  follow  immedi-
+       ately, or (with one exception) in the next command line item. For exam-
+       ple:
+
+         -f/some/file
+         -f /some/file
+
+       The exception is the -o option, which may appear with or without  data.
+       Because  of this, if data is present, it must follow immediately in the
+       same item, for example -o3.
+
+       If a long form option is used, the data may appear in the same  command
+       line  item,  separated by an equals character, or (with two exceptions)
+       it may appear in the next command line item. For example:
+
+         --file=/some/file
+         --file /some/file
+
+       Note, however, that if you want to supply a file name beginning with  ~
+       as  data  in  a  shell  command,  and have the shell expand ~ to a home
+       directory, you must separate the file name from the option, because the
+       shell does not treat ~ specially unless it is at the start of an item.
+
+       The  exceptions  to the above are the --colour (or --color) and --only-
+       matching options, for which the data  is  optional.  If  one  of  these
+       options  does  have  data, it must be given in the first form, using an
+       equals character. Otherwise pcre2grep will assume that it has no data.
+
+
+MATCHING ERRORS
+
+       It is possible to supply a regular expression that takes  a  very  long
+       time  to  fail  to  match certain lines. Such patterns normally involve
+       nested indefinite repeats, for example: (a+)*\d when matched against  a
+       line  of  a's  with  no  final digit. The PCRE2 matching function has a
+       resource limit that causes it to abort in these circumstances. If  this
+       happens,  pcre2grep  outputs  an error message and the line that caused
+       the problem to the standard error stream. If there  are  more  than  20
+       such errors, pcre2grep gives up.
+
+       The  --match-limit  option  of pcre2grep can be used to set the overall
+       resource limit; there is a second option called --recursion-limit  that
+       sets  a limit on the amount of memory (usually stack) that is used (see
+       the discussion of these options above).
+
+
+DIAGNOSTICS
+
+       Exit status is 0 if any matches were found, 1 if no matches were found,
+       and  2  for syntax errors, overlong lines, non-existent or inaccessible
+       files (even if matches were found in other files) or too many  matching
+       errors. Using the -s option to suppress error messages about inaccessi-
+       ble files does not affect the return code.
+
+
+SEE ALSO
+
+       pcre2pattern(3), pcre2syntax(3).
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge, England.
+
+
+REVISION
+
+       Last updated: 03 January 2015
+       Copyright (c) 1997-2015 University of Cambridge.
diff --git a/pcre2-10.20/doc/pcre2jit.3 b/pcre2-10.20/doc/pcre2jit.3
new file mode 100644
index 000000000..3f2071ba2
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2jit.3
@@ -0,0 +1,404 @@
+.TH PCRE2JIT 3 "27 November 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH "PCRE2 JUST-IN-TIME COMPILER SUPPORT"
+.rs
+.sp
+Just-in-time compiling is a heavyweight optimization that can greatly speed up
+pattern matching. However, it comes at the cost of extra processing before the
+match is performed, so it is of most benefit when the same pattern is going to
+be matched many times. This does not necessarily mean many calls of a matching
+function; if the pattern is not anchored, matching attempts may take place many
+times at various positions in the subject, even for a single call. Therefore,
+if the subject string is very long, it may still pay to use JIT even for
+one-off matches. JIT support is available for all of the 8-bit, 16-bit and
+32-bit PCRE2 libraries.
+.P
+JIT support applies only to the traditional Perl-compatible matching function.
+It does not apply when the DFA matching function is being used. The code for
+this support was written by Zoltan Herczeg.
+.
+.
+.SH "AVAILABILITY OF JIT SUPPORT"
+.rs
+.sp
+JIT support is an optional feature of PCRE2. The "configure" option
+--enable-jit (or equivalent CMake option) must be set when PCRE2 is built if
+you want to use JIT. The support is limited to the following hardware
+platforms:
+.sp
+  ARM 32-bit (v5, v7, and Thumb2)
+  ARM 64-bit
+  Intel x86 32-bit and 64-bit
+  MIPS 32-bit and 64-bit
+  Power PC 32-bit and 64-bit
+  SPARC 32-bit
+.sp
+If --enable-jit is set on an unsupported platform, compilation fails.
+.P
+A program can tell if JIT support is available by calling \fBpcre2_config()\fP
+with the PCRE2_CONFIG_JIT option. The result is 1 when JIT is available, and 0
+otherwise. However, a simple program does not need to check this in order to
+use JIT. The API is implemented in a way that falls back to the interpretive
+code if JIT is not available. For programs that need the best possible
+performance, there is also a "fast path" API that is JIT-specific.
+.
+.
+.SH "SIMPLE USE OF JIT"
+.rs
+.sp
+To make use of the JIT support in the simplest way, all you have to do is to
+call \fBpcre2_jit_compile()\fP after successfully compiling a pattern with
+\fBpcre2_compile()\fP. This function has two arguments: the first is the
+compiled pattern pointer that was returned by \fBpcre2_compile()\fP, and the
+second is zero or more of the following option bits: PCRE2_JIT_COMPLETE,
+PCRE2_JIT_PARTIAL_HARD, or PCRE2_JIT_PARTIAL_SOFT.
+.P
+If JIT support is not available, a call to \fBpcre2_jit_compile()\fP does
+nothing and returns PCRE2_ERROR_JIT_BADOPTION. Otherwise, the compiled pattern
+is passed to the JIT compiler, which turns it into machine code that executes
+much faster than the normal interpretive code, but yields exactly the same
+results. The returned value from \fBpcre2_jit_compile()\fP is zero on success,
+or a negative error code.
+.P
+PCRE2_JIT_COMPLETE requests the JIT compiler to generate code for complete
+matches. If you want to run partial matches using the PCRE2_PARTIAL_HARD or
+PCRE2_PARTIAL_SOFT options of \fBpcre2_match()\fP, you should set one or both
+of the other options as well as, or instead of PCRE2_JIT_COMPLETE. The JIT
+compiler generates different optimized code for each of the three modes
+(normal, soft partial, hard partial). When \fBpcre2_match()\fP is called, the
+appropriate code is run if it is available. Otherwise, the pattern is matched
+using interpretive code.
+.P
+You can call \fBpcre2_jit_compile()\fP multiple times for the same compiled
+pattern. It does nothing if it has previously compiled code for any of the
+option bits. For example, you can call it once with PCRE2_JIT_COMPLETE and
+(perhaps later, when you find you need partial matching) again with
+PCRE2_JIT_COMPLETE and PCRE2_JIT_PARTIAL_HARD. This time it will ignore
+PCRE2_JIT_COMPLETE and just compile code for partial matching. If
+\fBpcre2_jit_compile()\fP is called with no option bits set, it immediately
+returns zero. This is an alternative way of testing whether JIT is available.
+.P
+At present, it is not possible to free JIT compiled code except when the entire
+compiled pattern is freed by calling \fBpcre2_code_free()\fP.
+.P
+In some circumstances you may need to call additional functions. These are
+described in the section entitled
+.\" HTML 
+.\" 
+"Controlling the JIT stack"
+.\"
+below.
+.P
+There are some \fBpcre2_match()\fP options that are not supported by JIT, and
+there are also some pattern items that JIT cannot handle. Details are given
+below. In both cases, matching automatically falls back to the interpretive
+code. If you want to know whether JIT was actually used for a particular match,
+you should arrange for a JIT callback function to be set up as described in the
+section entitled
+.\" HTML 
+.\" 
+"Controlling the JIT stack"
+.\"
+below, even if you do not need to supply a non-default JIT stack. Such a
+callback function is called whenever JIT code is about to be obeyed. If the
+match-time options are not right for JIT execution, the callback function is
+not obeyed.
+.P
+If the JIT compiler finds an unsupported item, no JIT data is generated. You
+can find out if JIT matching is available after compiling a pattern by calling
+\fBpcre2_pattern_info()\fP with the PCRE2_INFO_JITSIZE option. A non-zero
+result means that JIT compilation was successful. A result of 0 means that JIT
+support is not available, or the pattern was not processed by
+\fBpcre2_jit_compile()\fP, or the JIT compiler was not able to handle the
+pattern.
+.
+.
+.SH "UNSUPPORTED OPTIONS AND PATTERN ITEMS"
+.rs
+.sp
+The \fBpcre2_match()\fP options that are supported for JIT matching are
+PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART,
+PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. The
+PCRE2_ANCHORED option is not supported at match time.
+.P
+The only unsupported pattern items are \eC (match a single data unit) when
+running in a UTF mode, and a callout immediately before an assertion condition
+in a conditional group.
+.
+.
+.SH "RETURN VALUES FROM JIT MATCHING"
+.rs
+.sp
+When a pattern is matched using JIT matching, the return values are the same
+as those given by the interpretive \fBpcre2_match()\fP code, with the addition
+of one new error code: PCRE2_ERROR_JIT_STACKLIMIT. This means that the memory
+used for the JIT stack was insufficient. See
+.\" HTML 
+.\" 
+"Controlling the JIT stack"
+.\"
+below for a discussion of JIT stack usage.
+.P
+The error code PCRE2_ERROR_MATCHLIMIT is returned by the JIT code if searching
+a very large pattern tree goes on for too long, as it is in the same
+circumstance when JIT is not used, but the details of exactly what is counted
+are not the same. The PCRE2_ERROR_RECURSIONLIMIT error code is never returned
+when JIT matching is used.
+.
+.
+.\" HTML 
+.SH "CONTROLLING THE JIT STACK"
+.rs
+.sp
+When the compiled JIT code runs, it needs a block of memory to use as a stack.
+By default, it uses 32K on the machine stack. However, some large or
+complicated patterns need more than this. The error PCRE2_ERROR_JIT_STACKLIMIT
+is given when there is not enough stack. Three functions are provided for
+managing blocks of memory for use as JIT stacks. There is further discussion
+about the use of JIT stacks in the section entitled
+.\" HTML 
+.\" 
+"JIT stack FAQ"
+.\"
+below.
+.P
+The \fBpcre2_jit_stack_create()\fP function creates a JIT stack. Its arguments
+are a starting size, a maximum size, and a general context (for memory
+allocation functions, or NULL for standard memory allocation). It returns a
+pointer to an opaque structure of type \fBpcre2_jit_stack\fP, or NULL if there
+is an error. The \fBpcre2_jit_stack_free()\fP function is used to free a stack
+that is no longer needed. (For the technically minded: the address space is
+allocated by mmap or VirtualAlloc.)
+.P
+JIT uses far less memory for recursion than the interpretive code,
+and a maximum stack size of 512K to 1M should be more than enough for any
+pattern.
+.P
+The \fBpcre2_jit_stack_assign()\fP function specifies which stack JIT code
+should use. Its arguments are as follows:
+.sp
+  pcre2_match_context  *mcontext
+  pcre2_jit_callback    callback
+  void                 *data
+.sp
+The first argument is a pointer to a match context. When this is subsequently
+passed to a matching function, its information determines which JIT stack is
+used. There are three cases for the values of the other two options:
+.sp
+  (1) If \fIcallback\fP is NULL and \fIdata\fP is NULL, an internal 32K block
+      on the machine stack is used. This is the default when a match
+      context is created.
+.sp
+  (2) If \fIcallback\fP is NULL and \fIdata\fP is not NULL, \fIdata\fP must be
+      a pointer to a valid JIT stack, the result of calling
+      \fBpcre2_jit_stack_create()\fP.
+.sp
+  (3) If \fIcallback\fP is not NULL, it must point to a function that is
+      called with \fIdata\fP as an argument at the start of matching, in
+      order to set up a JIT stack. If the return from the callback
+      function is NULL, the internal 32K stack is used; otherwise the
+      return value must be a valid JIT stack, the result of calling
+      \fBpcre2_jit_stack_create()\fP.
+.sp
+A callback function is obeyed whenever JIT code is about to be run; it is not
+obeyed when \fBpcre2_match()\fP is called with options that are incompatible
+for JIT matching. A callback function can therefore be used to determine
+whether a match operation was executed by JIT or by the interpreter.
+.P
+You may safely use the same JIT stack for more than one pattern (either by
+assigning directly or by callback), as long as the patterns are all matched
+sequentially in the same thread. In a multithread application, if you do not
+specify a JIT stack, or if you assign or pass back NULL from a callback, that
+is thread-safe, because each thread has its own machine stack. However, if you
+assign or pass back a non-NULL JIT stack, this must be a different stack for
+each thread so that the application is thread-safe.
+.P
+Strictly speaking, even more is allowed. You can assign the same non-NULL stack
+to a match context that is used by any number of patterns, as long as they are
+not used for matching by multiple threads at the same time. For example, you
+could use the same stack in all compiled patterns, with a global mutex in the
+callback to wait until the stack is available for use. However, this is an
+inefficient solution, and not recommended.
+.P
+This is a suggestion for how a multithreaded program that needs to set up
+non-default JIT stacks might operate:
+.sp
+  During thread initalization
+    thread_local_var = pcre2_jit_stack_create(...)
+.sp
+  During thread exit
+    pcre2_jit_stack_free(thread_local_var)
+.sp
+  Use a one-line callback function
+    return thread_local_var
+.sp
+All the functions described in this section do nothing if JIT is not available.
+.
+.
+.\" HTML 
+.SH "JIT STACK FAQ"
+.rs
+.sp
+(1) Why do we need JIT stacks?
+.sp
+PCRE2 (and JIT) is a recursive, depth-first engine, so it needs a stack where
+the local data of the current node is pushed before checking its child nodes.
+Allocating real machine stack on some platforms is difficult. For example, the
+stack chain needs to be updated every time if we extend the stack on PowerPC.
+Although it is possible, its updating time overhead decreases performance. So
+we do the recursion in memory.
+.P
+(2) Why don't we simply allocate blocks of memory with \fBmalloc()\fP?
+.sp
+Modern operating systems have a nice feature: they can reserve an address space
+instead of allocating memory. We can safely allocate memory pages inside this
+address space, so the stack could grow without moving memory data (this is
+important because of pointers). Thus we can allocate 1M address space, and use
+only a single memory page (usually 4K) if that is enough. However, we can still
+grow up to 1M anytime if needed.
+.P
+(3) Who "owns" a JIT stack?
+.sp
+The owner of the stack is the user program, not the JIT studied pattern or
+anything else. The user program must ensure that if a stack is being used by
+\fBpcre2_match()\fP, (that is, it is assigned to a match context that is passed
+to the pattern currently running), that stack must not be used by any other
+threads (to avoid overwriting the same memory area). The best practice for
+multithreaded programs is to allocate a stack for each thread, and return this
+stack through the JIT callback function.
+.P
+(4) When should a JIT stack be freed?
+.sp
+You can free a JIT stack at any time, as long as it will not be used by
+\fBpcre2_match()\fP again. When you assign the stack to a match context, only a
+pointer is set. There is no reference counting or any other magic. You can free
+compiled patterns, contexts, and stacks in any order, anytime. Just \fIdo
+not\fP call \fBpcre2_match()\fP with a match context pointing to an already
+freed stack, as that will cause SEGFAULT. (Also, do not free a stack currently
+used by \fBpcre2_match()\fP in another thread). You can also replace the stack
+in a context at any time when it is not in use. You should free the previous
+stack before assigning a replacement.
+.P
+(5) Should I allocate/free a stack every time before/after calling
+\fBpcre2_match()\fP?
+.sp
+No, because this is too costly in terms of resources. However, you could
+implement some clever idea which release the stack if it is not used in let's
+say two minutes. The JIT callback can help to achieve this without keeping a
+list of patterns.
+.P
+(6) OK, the stack is for long term memory allocation. But what happens if a
+pattern causes stack overflow with a stack of 1M? Is that 1M kept until the
+stack is freed?
+.sp
+Especially on embedded sytems, it might be a good idea to release memory
+sometimes without freeing the stack. There is no API for this at the moment.
+Probably a function call which returns with the currently allocated memory for
+any stack and another which allows releasing memory (shrinking the stack) would
+be a good idea if someone needs this.
+.P
+(7) This is too much of a headache. Isn't there any better solution for JIT
+stack handling?
+.sp
+No, thanks to Windows. If POSIX threads were used everywhere, we could throw
+out this complicated API.
+.
+.
+.SH "FREEING JIT SPECULATIVE MEMORY"
+.rs
+.sp
+.nf
+.B void pcre2_jit_free_unused_memory(pcre2_general_context *\fIgcontext\fP);
+.fi
+.P
+The JIT executable allocator does not free all memory when it is possible.
+It expects new allocations, and keeps some free memory around to improve
+allocation speed. However, in low memory conditions, it might be better to free
+all possible memory. You can cause this to happen by calling
+pcre2_jit_free_unused_memory(). Its argument is a general context, for custom
+memory management, or NULL for standard memory management.
+.
+.
+.SH "EXAMPLE CODE"
+.rs
+.sp
+This is a single-threaded example that specifies a JIT stack without using a
+callback. A real program should include error checking after all the function
+calls.
+.sp
+  int rc;
+  pcre2_code *re;
+  pcre2_match_data *match_data;
+  pcre2_match_context *mcontext;
+  pcre2_jit_stack *jit_stack;
+.sp
+  re = pcre2_compile(pattern, PCRE2_ZERO_TERMINATED, 0,
+    &errornumber, &erroffset, NULL);
+  rc = pcre2_jit_compile(re, PCRE2_JIT_COMPLETE);
+  mcontext = pcre2_match_context_create(NULL);
+  jit_stack = pcre2_jit_stack_create(32*1024, 512*1024, NULL);
+  pcre2_jit_stack_assign(mcontext, NULL, jit_stack);
+  match_data = pcre2_match_data_create(re, 10);
+  rc = pcre2_match(re, subject, length, 0, 0, match_data, mcontext);
+  /* Process result */
+.sp
+  pcre2_code_free(re);
+  pcre2_match_data_free(match_data);
+  pcre2_match_context_free(mcontext);
+  pcre2_jit_stack_free(jit_stack);
+.sp
+.
+.
+.SH "JIT FAST PATH API"
+.rs
+.sp
+Because the API described above falls back to interpreted matching when JIT is
+not available, it is convenient for programs that are written for general use
+in many environments. However, calling JIT via \fBpcre2_match()\fP does have a
+performance impact. Programs that are written for use where JIT is known to be
+available, and which need the best possible performance, can instead use a
+"fast path" API to call JIT matching directly instead of calling
+\fBpcre2_match()\fP (obviously only for patterns that have been successfully
+processed by \fBpcre2_jit_compile()\fP).
+.P
+The fast path function is called \fBpcre2_jit_match()\fP, and it takes exactly
+the same arguments as \fBpcre2_match()\fP. The return values are also the same,
+plus PCRE2_ERROR_JIT_BADOPTION if a matching mode (partial or complete) is
+requested that was not compiled. Unsupported option bits (for example,
+PCRE2_ANCHORED) are ignored.
+.P
+When you call \fBpcre2_match()\fP, as well as testing for invalid options, a
+number of other sanity checks are performed on the arguments. For example, if
+the subject pointer is NULL, an immediate error is given. Also, unless
+PCRE2_NO_UTF_CHECK is set, a UTF subject string is tested for validity. In the
+interests of speed, these checks do not happen on the JIT fast path, and if
+invalid data is passed, the result is undefined.
+.P
+Bypassing the sanity checks and the \fBpcre2_match()\fP wrapping can give
+speedups of more than 10%.
+.
+.
+.SH "SEE ALSO"
+.rs
+.sp
+\fBpcre2api\fP(3)
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel (FAQ by Zoltan Herczeg)
+University Computing Service
+Cambridge, England.
+.fi
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 27 November 2014
+Copyright (c) 1997-2014 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/doc/pcre2limits.3 b/pcre2-10.20/doc/pcre2limits.3
new file mode 100644
index 000000000..898254618
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2limits.3
@@ -0,0 +1,74 @@
+.TH PCRE2LIMITS 3 "25 November 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH "SIZE AND OTHER LIMITATIONS"
+.rs
+.sp
+There are some size limitations in PCRE2 but it is hoped that they will never
+in practice be relevant.
+.P
+The maximum size of a compiled pattern is approximately 64K code units for the
+8-bit and 16-bit libraries if PCRE2 is compiled with the default internal
+linkage size, which is 2 bytes for these libraries. If you want to process
+regular expressions that are truly enormous, you can compile PCRE2 with an
+internal linkage size of 3 or 4 (when building the 16-bit library, 3 is rounded
+up to 4). See the \fBREADME\fP file in the source distribution and the
+.\" HREF
+\fBpcre2build\fP
+.\"
+documentation for details. In these cases the limit is substantially larger.
+However, the speed of execution is slower. In the 32-bit library, the internal
+linkage size is always 4.
+.P
+The maximum length (in code units) of a subject string is one less than the
+largest number a PCRE2_SIZE variable can hold. PCRE2_SIZE is an unsigned
+integer type, usually defined as size_t. Its maximum value (that is
+~(PCRE2_SIZE)0) is reserved as a special indicator for zero-terminated strings
+and unset offsets.
+.P
+Note that when using the traditional matching function, PCRE2 uses recursion to
+handle subpatterns and indefinite repetition. This means that the available
+stack space may limit the size of a subject string that can be processed by
+certain patterns. For a discussion of stack issues, see the
+.\" HREF
+\fBpcre2stack\fP
+.\"
+documentation.
+.P
+All values in repeating quantifiers must be less than 65536.
+.P
+There is no limit to the number of parenthesized subpatterns, but there can be
+no more than 65535 capturing subpatterns. There is, however, a limit to the
+depth of nesting of parenthesized subpatterns of all kinds. This is imposed in
+order to limit the amount of system stack used at compile time. The limit can
+be specified when PCRE2 is built; the default is 250.
+.P
+There is a limit to the number of forward references to subsequent subpatterns
+of around 200,000. Repeated forward references with fixed upper limits, for
+example, (?2){0,100} when subpattern number 2 is to the right, are included in
+the count. There is no limit to the number of backward references.
+.P
+The maximum length of name for a named subpattern is 32 code units, and the
+maximum number of named subpatterns is 10000.
+.P
+The maximum length of a name in a (*MARK), (*PRUNE), (*SKIP), or (*THEN) verb
+is 255 for the 8-bit library and 65535 for the 16-bit and 32-bit libraries.
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel
+University Computing Service
+Cambridge, England.
+.fi
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 25 November 2014
+Copyright (c) 1997-2014 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/doc/pcre2matching.3 b/pcre2-10.20/doc/pcre2matching.3
new file mode 100644
index 000000000..3a885e5f6
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2matching.3
@@ -0,0 +1,213 @@
+.TH PCRE2MATCHING 3 "29 September 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH "PCRE2 MATCHING ALGORITHMS"
+.rs
+.sp
+This document describes the two different algorithms that are available in
+PCRE2 for matching a compiled regular expression against a given subject
+string. The "standard" algorithm is the one provided by the \fBpcre2_match()\fP
+function. This works in the same as as Perl's matching function, and provide a
+Perl-compatible matching operation. The just-in-time (JIT) optimization that is
+described in the
+.\" HREF
+\fBpcre2jit\fP
+.\"
+documentation is compatible with this function.
+.P
+An alternative algorithm is provided by the \fBpcre2_dfa_match()\fP function;
+it operates in a different way, and is not Perl-compatible. This alternative
+has advantages and disadvantages compared with the standard algorithm, and
+these are described below.
+.P
+When there is only one possible way in which a given subject string can match a
+pattern, the two algorithms give the same answer. A difference arises, however,
+when there are multiple possibilities. For example, if the pattern
+.sp
+  ^<.*>
+.sp
+is matched against the string
+.sp
+    
+.sp
+there are three possible answers. The standard algorithm finds only one of
+them, whereas the alternative algorithm finds all three.
+.
+.
+.SH "REGULAR EXPRESSIONS AS TREES"
+.rs
+.sp
+The set of strings that are matched by a regular expression can be represented
+as a tree structure. An unlimited repetition in the pattern makes the tree of
+infinite size, but it is still a tree. Matching the pattern to a given subject
+string (from a given starting point) can be thought of as a search of the tree.
+There are two ways to search a tree: depth-first and breadth-first, and these
+correspond to the two matching algorithms provided by PCRE2.
+.
+.
+.SH "THE STANDARD MATCHING ALGORITHM"
+.rs
+.sp
+In the terminology of Jeffrey Friedl's book "Mastering Regular Expressions",
+the standard algorithm is an "NFA algorithm". It conducts a depth-first search
+of the pattern tree. That is, it proceeds along a single path through the tree,
+checking that the subject matches what is required. When there is a mismatch,
+the algorithm tries any alternatives at the current point, and if they all
+fail, it backs up to the previous branch point in the tree, and tries the next
+alternative branch at that level. This often involves backing up (moving to the
+left) in the subject string as well. The order in which repetition branches are
+tried is controlled by the greedy or ungreedy nature of the quantifier.
+.P
+If a leaf node is reached, a matching string has been found, and at that point
+the algorithm stops. Thus, if there is more than one possible match, this
+algorithm returns the first one that it finds. Whether this is the shortest,
+the longest, or some intermediate length depends on the way the greedy and
+ungreedy repetition quantifiers are specified in the pattern.
+.P
+Because it ends up with a single path through the tree, it is relatively
+straightforward for this algorithm to keep track of the substrings that are
+matched by portions of the pattern in parentheses. This provides support for
+capturing parentheses and back references.
+.
+.
+.SH "THE ALTERNATIVE MATCHING ALGORITHM"
+.rs
+.sp
+This algorithm conducts a breadth-first search of the tree. Starting from the
+first matching point in the subject, it scans the subject string from left to
+right, once, character by character, and as it does this, it remembers all the
+paths through the tree that represent valid matches. In Friedl's terminology,
+this is a kind of "DFA algorithm", though it is not implemented as a
+traditional finite state machine (it keeps multiple states active
+simultaneously).
+.P
+Although the general principle of this matching algorithm is that it scans the
+subject string only once, without backtracking, there is one exception: when a
+lookaround assertion is encountered, the characters following or preceding the
+current point have to be independently inspected.
+.P
+The scan continues until either the end of the subject is reached, or there are
+no more unterminated paths. At this point, terminated paths represent the
+different matching possibilities (if there are none, the match has failed).
+Thus, if there is more than one possible match, this algorithm finds all of
+them, and in particular, it finds the longest. The matches are returned in
+decreasing order of length. There is an option to stop the algorithm after the
+first match (which is necessarily the shortest) is found.
+.P
+Note that all the matches that are found start at the same point in the
+subject. If the pattern
+.sp
+  cat(er(pillar)?)?
+.sp
+is matched against the string "the caterpillar catchment", the result is the
+three strings "caterpillar", "cater", and "cat" that start at the fifth
+character of the subject. The algorithm does not automatically move on to find
+matches that start at later positions.
+.P
+PCRE2's "auto-possessification" optimization usually applies to character
+repeats at the end of a pattern (as well as internally). For example, the
+pattern "a\ed+" is compiled as if it were "a\ed++" because there is no point
+even considering the possibility of backtracking into the repeated digits. For
+DFA matching, this means that only one possible match is found. If you really
+do want multiple matches in such cases, either use an ungreedy repeat
+("a\ed+?") or set the PCRE2_NO_AUTO_POSSESS option when compiling.
+.P
+There are a number of features of PCRE2 regular expressions that are not
+supported by the alternative matching algorithm. They are as follows:
+.P
+1. Because the algorithm finds all possible matches, the greedy or ungreedy
+nature of repetition quantifiers is not relevant (though it may affect
+auto-possessification, as just described). During matching, greedy and ungreedy
+quantifiers are treated in exactly the same way. However, possessive
+quantifiers can make a difference when what follows could also match what is
+quantified, for example in a pattern like this:
+.sp
+  ^a++\ew!
+.sp
+This pattern matches "aaab!" but not "aaa!", which would be matched by a
+non-possessive quantifier. Similarly, if an atomic group is present, it is
+matched as if it were a standalone pattern at the current point, and the
+longest match is then "locked in" for the rest of the overall pattern.
+.P
+2. When dealing with multiple paths through the tree simultaneously, it is not
+straightforward to keep track of captured substrings for the different matching
+possibilities, and PCRE2's implementation of this algorithm does not attempt to
+do this. This means that no captured substrings are available.
+.P
+3. Because no substrings are captured, back references within the pattern are
+not supported, and cause errors if encountered.
+.P
+4. For the same reason, conditional expressions that use a backreference as the
+condition or test for a specific group recursion are not supported.
+.P
+5. Because many paths through the tree may be active, the \eK escape sequence,
+which resets the start of the match when encountered (but may be on some paths
+and not on others), is not supported. It causes an error if encountered.
+.P
+6. Callouts are supported, but the value of the \fIcapture_top\fP field is
+always 1, and the value of the \fIcapture_last\fP field is always 0.
+.P
+7. The \eC escape sequence, which (in the standard algorithm) always matches a
+single code unit, even in a UTF mode, is not supported in these modes, because
+the alternative algorithm moves through the subject string one character (not
+code unit) at a time, for all active paths through the tree.
+.P
+8. Except for (*FAIL), the backtracking control verbs such as (*PRUNE) are not
+supported. (*FAIL) is supported, and behaves like a failing negative assertion.
+.
+.
+.SH "ADVANTAGES OF THE ALTERNATIVE ALGORITHM"
+.rs
+.sp
+Using the alternative matching algorithm provides the following advantages:
+.P
+1. All possible matches (at a single point in the subject) are automatically
+found, and in particular, the longest match is found. To find more than one
+match using the standard algorithm, you have to do kludgy things with
+callouts.
+.P
+2. Because the alternative algorithm scans the subject string just once, and
+never needs to backtrack (except for lookbehinds), it is possible to pass very
+long subject strings to the matching function in several pieces, checking for
+partial matching each time. Although it is also possible to do multi-segment
+matching using the standard algorithm, by retaining partially matched
+substrings, it is more complicated. The
+.\" HREF
+\fBpcre2partial\fP
+.\"
+documentation gives details of partial matching and discusses multi-segment
+matching.
+.
+.
+.SH "DISADVANTAGES OF THE ALTERNATIVE ALGORITHM"
+.rs
+.sp
+The alternative algorithm suffers from a number of disadvantages:
+.P
+1. It is substantially slower than the standard algorithm. This is partly
+because it has to search for all possible matches, but is also because it is
+less susceptible to optimization.
+.P
+2. Capturing parentheses and back references are not supported.
+.P
+3. Although atomic groups are supported, their use does not provide the
+performance advantage that it does for the standard algorithm.
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel
+University Computing Service
+Cambridge, England.
+.fi
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 29 September 2014
+Copyright (c) 1997-2014 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/doc/pcre2partial.3 b/pcre2-10.20/doc/pcre2partial.3
new file mode 100644
index 000000000..72a12ed27
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2partial.3
@@ -0,0 +1,434 @@
+.TH PCRE2PARTIAL 3 "22 December 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions
+.SH "PARTIAL MATCHING IN PCRE2"
+.rs
+.sp
+In normal use of PCRE2, if the subject string that is passed to a matching
+function matches as far as it goes, but is too short to match the entire
+pattern, PCRE2_ERROR_NOMATCH is returned. There are circumstances where it
+might be helpful to distinguish this case from other cases in which there is no
+match.
+.P
+Consider, for example, an application where a human is required to type in data
+for a field with specific formatting requirements. An example might be a date
+in the form \fIddmmmyy\fP, defined by this pattern:
+.sp
+  ^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$
+.sp
+If the application sees the user's keystrokes one by one, and can check that
+what has been typed so far is potentially valid, it is able to raise an error
+as soon as a mistake is made, by beeping and not reflecting the character that
+has been typed, for example. This immediate feedback is likely to be a better
+user interface than a check that is delayed until the entire string has been
+entered. Partial matching can also be useful when the subject string is very
+long and is not all available at once.
+.P
+PCRE2 supports partial matching by means of the PCRE2_PARTIAL_SOFT and
+PCRE2_PARTIAL_HARD options, which can be set when calling a matching function.
+The difference between the two options is whether or not a partial match is
+preferred to an alternative complete match, though the details differ between
+the two types of matching function. If both options are set, PCRE2_PARTIAL_HARD
+takes precedence.
+.P
+If you want to use partial matching with just-in-time optimized code, you must
+call \fBpcre2_jit_compile()\fP with one or both of these options:
+.sp
+  PCRE2_JIT_PARTIAL_SOFT
+  PCRE2_JIT_PARTIAL_HARD
+.sp
+PCRE2_JIT_COMPLETE should also be set if you are going to run non-partial
+matches on the same pattern. If the appropriate JIT mode has not been compiled,
+interpretive matching code is used.
+.P
+Setting a partial matching option disables two of PCRE2's standard
+optimizations. PCRE2 remembers the last literal code unit in a pattern, and
+abandons matching immediately if it is not present in the subject string. This
+optimization cannot be used for a subject string that might match only
+partially. PCRE2 also knows the minimum length of a matching string, and does
+not bother to run the matching function on shorter strings. This optimization
+is also disabled for partial matching.
+.
+.
+.SH "PARTIAL MATCHING USING pcre2_match()"
+.rs
+.sp
+A partial match occurs during a call to \fBpcre2_match()\fP when the end of the
+subject string is reached successfully, but matching cannot continue because
+more characters are needed. However, at least one character in the subject must
+have been inspected. This character need not form part of the final matched
+string; lookbehind assertions and the \eK escape sequence provide ways of
+inspecting characters before the start of a matched string. The requirement for
+inspecting at least one character exists because an empty string can always be
+matched; without such a restriction there would always be a partial match of an
+empty string at the end of the subject.
+.P
+When a partial match is returned, the first two elements in the ovector point
+to the portion of the subject that was matched, but the values in the rest of
+the ovector are undefined. The appearance of \eK in the pattern has no effect
+for a partial match. Consider this pattern:
+.sp
+  /abc\eK123/
+.sp
+If it is matched against "456abc123xyz" the result is a complete match, and the
+ovector defines the matched string as "123", because \eK resets the "start of
+match" point. However, if a partial match is requested and the subject string
+is "456abc12", a partial match is found for the string "abc12", because all
+these characters are needed for a subsequent re-match with additional
+characters.
+.P
+What happens when a partial match is identified depends on which of the two
+partial matching options are set.
+.
+.
+.SS "PCRE2_PARTIAL_SOFT WITH pcre2_match()"
+.rs
+.sp
+If PCRE2_PARTIAL_SOFT is set when \fBpcre2_match()\fP identifies a partial
+match, the partial match is remembered, but matching continues as normal, and
+other alternatives in the pattern are tried. If no complete match can be found,
+PCRE2_ERROR_PARTIAL is returned instead of PCRE2_ERROR_NOMATCH.
+.P
+This option is "soft" because it prefers a complete match over a partial match.
+All the various matching items in a pattern behave as if the subject string is
+potentially complete. For example, \ez, \eZ, and $ match at the end of the
+subject, as normal, and for \eb and \eB the end of the subject is treated as a
+non-alphanumeric.
+.P
+If there is more than one partial match, the first one that was found provides
+the data that is returned. Consider this pattern:
+.sp
+  /123\ew+X|dogY/
+.sp
+If this is matched against the subject string "abc123dog", both
+alternatives fail to match, but the end of the subject is reached during
+matching, so PCRE2_ERROR_PARTIAL is returned. The offsets are set to 3 and 9,
+identifying "123dog" as the first partial match that was found. (In this
+example, there are two partial matches, because "dog" on its own partially
+matches the second alternative.)
+.
+.
+.SS "PCRE2_PARTIAL_HARD WITH pcre2_match()"
+.rs
+.sp
+If PCRE2_PARTIAL_HARD is set for \fBpcre2_match()\fP, PCRE2_ERROR_PARTIAL is
+returned as soon as a partial match is found, without continuing to search for
+possible complete matches. This option is "hard" because it prefers an earlier
+partial match over a later complete match. For this reason, the assumption is
+made that the end of the supplied subject string may not be the true end of the
+available data, and so, if \ez, \eZ, \eb, \eB, or $ are encountered at the end
+of the subject, the result is PCRE2_ERROR_PARTIAL, provided that at least one
+character in the subject has been inspected.
+.
+.
+.SS "Comparing hard and soft partial matching"
+.rs
+.sp
+The difference between the two partial matching options can be illustrated by a
+pattern such as:
+.sp
+  /dog(sbody)?/
+.sp
+This matches either "dog" or "dogsbody", greedily (that is, it prefers the
+longer string if possible). If it is matched against the string "dog" with
+PCRE2_PARTIAL_SOFT, it yields a complete match for "dog". However, if
+PCRE2_PARTIAL_HARD is set, the result is PCRE2_ERROR_PARTIAL. On the other
+hand, if the pattern is made ungreedy the result is different:
+.sp
+  /dog(sbody)??/
+.sp
+In this case the result is always a complete match because that is found first,
+and matching never continues after finding a complete match. It might be easier
+to follow this explanation by thinking of the two patterns like this:
+.sp
+  /dog(sbody)?/    is the same as  /dogsbody|dog/
+  /dog(sbody)??/   is the same as  /dog|dogsbody/
+.sp
+The second pattern will never match "dogsbody", because it will always find the
+shorter match first.
+.
+.
+.SH "PARTIAL MATCHING USING pcre2_dfa_match()"
+.rs
+.sp
+The DFA functions move along the subject string character by character, without
+backtracking, searching for all possible matches simultaneously. If the end of
+the subject is reached before the end of the pattern, there is the possibility
+of a partial match, again provided that at least one character has been
+inspected.
+.P
+When PCRE2_PARTIAL_SOFT is set, PCRE2_ERROR_PARTIAL is returned only if there
+have been no complete matches. Otherwise, the complete matches are returned.
+However, if PCRE2_PARTIAL_HARD is set, a partial match takes precedence over
+any complete matches. The portion of the string that was matched when the
+longest partial match was found is set as the first matching string.
+.P
+Because the DFA functions always search for all possible matches, and there is
+no difference between greedy and ungreedy repetition, their behaviour is
+different from the standard functions when PCRE2_PARTIAL_HARD is set. Consider
+the string "dog" matched against the ungreedy pattern shown above:
+.sp
+  /dog(sbody)??/
+.sp
+Whereas the standard function stops as soon as it finds the complete match for
+"dog", the DFA function also finds the partial match for "dogsbody", and so
+returns that when PCRE2_PARTIAL_HARD is set.
+.
+.
+.SH "PARTIAL MATCHING AND WORD BOUNDARIES"
+.rs
+.sp
+If a pattern ends with one of sequences \eb or \eB, which test for word
+boundaries, partial matching with PCRE2_PARTIAL_SOFT can give counter-intuitive
+results. Consider this pattern:
+.sp
+  /\ebcat\eb/
+.sp
+This matches "cat", provided there is a word boundary at either end. If the
+subject string is "the cat", the comparison of the final "t" with a following
+character cannot take place, so a partial match is found. However, normal
+matching carries on, and \eb matches at the end of the subject when the last
+character is a letter, so a complete match is found. The result, therefore, is
+\fInot\fP PCRE2_ERROR_PARTIAL. Using PCRE2_PARTIAL_HARD in this case does yield
+PCRE2_ERROR_PARTIAL, because then the partial match takes precedence.
+.
+.
+.SH "EXAMPLE OF PARTIAL MATCHING USING PCRE2TEST"
+.rs
+.sp
+If the \fBpartial_soft\fP (or \fBps\fP) modifier is present on a
+\fBpcre2test\fP data line, the PCRE2_PARTIAL_SOFT option is used for the match.
+Here is a run of \fBpcre2test\fP that uses the date example quoted above:
+.sp
+    re> /^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$/
+  data> 25jun04\e=ps
+   0: 25jun04
+   1: jun
+  data> 25dec3\e=ps
+  Partial match: 23dec3
+  data> 3ju\e=ps
+  Partial match: 3ju
+  data> 3juj\e=ps
+  No match
+  data> j\e=ps
+  No match
+.sp
+The first data string is matched completely, so \fBpcre2test\fP shows the
+matched substrings. The remaining four strings do not match the complete
+pattern, but the first two are partial matches. Similar output is obtained
+if DFA matching is used.
+.P
+If the \fBpartial_hard\fP (or \fBph\fP) modifier is present on a
+\fBpcre2test\fP data line, the PCRE2_PARTIAL_HARD option is set for the match.
+.
+.
+.SH "MULTI-SEGMENT MATCHING WITH pcre2_dfa_match()"
+.rs
+.sp
+When a partial match has been found using a DFA matching function, it is
+possible to continue the match by providing additional subject data and calling
+the function again with the same compiled regular expression, this time setting
+the PCRE2_DFA_RESTART option. You must pass the same working space as before,
+because this is where details of the previous partial match are stored. Here is
+an example using \fBpcre2test\fP:
+.sp
+    re> /^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$/
+  data> 23ja\e=dfa,ps
+  Partial match: 23ja
+  data> n05\e=dfa,dfa_restart
+   0: n05
+.sp
+The first call has "23ja" as the subject, and requests partial matching; the
+second call has "n05" as the subject for the continued (restarted) match.
+Notice that when the match is complete, only the last part is shown; PCRE2 does
+not retain the previously partially-matched string. It is up to the calling
+program to do that if it needs to.
+.P
+That means that, for an unanchored pattern, if a continued match fails, it is
+not possible to try again at a new starting point. All this facility is capable
+of doing is continuing with the previous match attempt. In the previous
+example, if the second set of data is "ug23" the result is no match, even
+though there would be a match for "aug23" if the entire string were given at
+once. Depending on the application, this may or may not be what you want.
+The only way to allow for starting again at the next character is to retain the
+matched part of the subject and try a new complete match.
+.P
+You can set the PCRE2_PARTIAL_SOFT or PCRE2_PARTIAL_HARD options with
+PCRE2_DFA_RESTART to continue partial matching over multiple segments. This
+facility can be used to pass very long subject strings to the DFA matching
+functions.
+.
+.
+.SH "MULTI-SEGMENT MATCHING WITH pcre2_match()"
+.rs
+.sp
+Unlike the DFA function, it is not possible to restart the previous match with
+a new segment of data when using \fBpcre2_match()\fP. Instead, new data must be
+added to the previous subject string, and the entire match re-run, starting
+from the point where the partial match occurred. Earlier data can be discarded.
+.P
+It is best to use PCRE2_PARTIAL_HARD in this situation, because it does not
+treat the end of a segment as the end of the subject when matching \ez, \eZ,
+\eb, \eB, and $. Consider an unanchored pattern that matches dates:
+.sp
+    re> /\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed/
+  data> The date is 23ja\e=ph
+  Partial match: 23ja
+.sp
+At this stage, an application could discard the text preceding "23ja", add on
+text from the next segment, and call the matching function again. Unlike the
+DFA matching function, the entire matching string must always be available,
+and the complete matching process occurs for each call, so more memory and more
+processing time is needed.
+.
+.
+.SH "ISSUES WITH MULTI-SEGMENT MATCHING"
+.rs
+.sp
+Certain types of pattern may give problems with multi-segment matching,
+whichever matching function is used.
+.P
+1. If the pattern contains a test for the beginning of a line, you need to pass
+the PCRE2_NOTBOL option when the subject string for any call does start at the
+beginning of a line. There is also a PCRE2_NOTEOL option, but in practice when
+doing multi-segment matching you should be using PCRE2_PARTIAL_HARD, which
+includes the effect of PCRE2_NOTEOL.
+.P
+2. If a pattern contains a lookbehind assertion, characters that precede the
+start of the partial match may have been inspected during the matching process.
+When using \fBpcre2_match()\fP, sufficient characters must be retained for the
+next match attempt. You can ensure that enough characters are retained by doing
+the following:
+.P
+Before doing any matching, find the length of the longest lookbehind in the
+pattern by calling \fBpcre2_pattern_info()\fP with the PCRE2_INFO_MAXLOOKBEHIND
+option. Note that the resulting count is in characters, not code units. After a
+partial match, moving back from the ovector[0] offset in the subject by the
+number of characters given for the maximum lookbehind gets you to the earliest
+character that must be retained. In a non-UTF or a 32-bit situation, moving
+back is just a subtraction, but in UTF-8 or UTF-16 you have to count characters
+while moving back through the code units.
+.P
+Characters before the point you have now reached can be discarded, and after
+the next segment has been added to what is retained, you should run the next
+match with the \fBstartoffset\fP argument set so that the match begins at the
+same point as before.
+.P
+For example, if the pattern "(?<=123)abc" is partially matched against the
+string "xx123ab", the ovector offsets are 5 and 7 ("ab"). The maximum
+lookbehind count is 3, so all characters before offset 2 can be discarded. The
+value of \fBstartoffset\fP for the next match should be 3. When \fBpcre2test\fP
+displays a partial match, it indicates the lookbehind characters with '<'
+characters:
+.sp
+    re> "(?<=123)abc"
+  data> xx123ab\e=ph
+  Partial match: 123ab
+                 <<<
+.P
+3. Because a partial match must always contain at least one character, what
+might be considered a partial match of an empty string actually gives a "no
+match" result. For example:
+.sp
+    re> /c(?<=abc)x/
+  data> ab\e=ps
+  No match
+.sp
+If the next segment begins "cx", a match should be found, but this will only
+happen if characters from the previous segment are retained. For this reason, a
+"no match" result should be interpreted as "partial match of an empty string"
+when the pattern contains lookbehinds.
+.P
+4. Matching a subject string that is split into multiple segments may not
+always produce exactly the same result as matching over one single long string,
+especially when PCRE2_PARTIAL_SOFT is used. The section "Partial Matching and
+Word Boundaries" above describes an issue that arises if the pattern ends with
+\eb or \eB. Another kind of difference may occur when there are multiple
+matching possibilities, because (for PCRE2_PARTIAL_SOFT) a partial match result
+is given only when there are no completed matches. This means that as soon as
+the shortest match has been found, continuation to a new subject segment is no
+longer possible. Consider this \fBpcre2test\fP example:
+.sp
+    re> /dog(sbody)?/
+  data> dogsb\e=ps
+   0: dog
+  data> do\e=ps,dfa
+  Partial match: do
+  data> gsb\e=ps,dfa,dfa_restart
+   0: g
+  data> dogsbody\e=dfa
+   0: dogsbody
+   1: dog
+.sp
+The first data line passes the string "dogsb" to a standard matching function,
+setting the PCRE2_PARTIAL_SOFT option. Although the string is a partial match
+for "dogsbody", the result is not PCRE2_ERROR_PARTIAL, because the shorter
+string "dog" is a complete match. Similarly, when the subject is presented to
+a DFA matching function in several parts ("do" and "gsb" being the first two)
+the match stops when "dog" has been found, and it is not possible to continue.
+On the other hand, if "dogsbody" is presented as a single string, a DFA
+matching function finds both matches.
+.P
+Because of these problems, it is best to use PCRE2_PARTIAL_HARD when matching
+multi-segment data. The example above then behaves differently:
+.sp
+    re> /dog(sbody)?/
+  data> dogsb\e=ph
+  Partial match: dogsb
+  data> do\e=ps,dfa
+  Partial match: do
+  data> gsb\e=ph,dfa,dfa_restart
+  Partial match: gsb
+.sp
+5. Patterns that contain alternatives at the top level which do not all start
+with the same pattern item may not work as expected when PCRE2_DFA_RESTART is
+used. For example, consider this pattern:
+.sp
+  1234|3789
+.sp
+If the first part of the subject is "ABC123", a partial match of the first
+alternative is found at offset 3. There is no partial match for the second
+alternative, because such a match does not start at the same point in the
+subject string. Attempting to continue with the string "7890" does not yield a
+match because only those alternatives that match at one point in the subject
+are remembered. The problem arises because the start of the second alternative
+matches within the first alternative. There is no problem with anchored
+patterns or patterns such as:
+.sp
+  1234|ABCD
+.sp
+where no string can be a partial match for both alternatives. This is not a
+problem if a standard matching function is used, because the entire match has
+to be rerun each time:
+.sp
+    re> /1234|3789/
+  data> ABC123\e=ph
+  Partial match: 123
+  data> 1237890
+   0: 3789
+.sp
+Of course, instead of using PCRE2_DFA_RESTART, the same technique of re-running
+the entire match can also be used with the DFA matching function. Another
+possibility is to work with two buffers. If a partial match at offset \fIn\fP
+in the first buffer is followed by "no match" when PCRE2_DFA_RESTART is used on
+the second buffer, you can then try a new match starting at offset \fIn+1\fP in
+the first buffer.
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel
+University Computing Service
+Cambridge, England.
+.fi
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 22 December 2014
+Copyright (c) 1997-2014 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/doc/pcre2pattern.3 b/pcre2-10.20/doc/pcre2pattern.3
new file mode 100644
index 000000000..192859dd3
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2pattern.3
@@ -0,0 +1,3366 @@
+.TH PCRE2PATTERN 3 "13 June 2015" "PCRE2 10.20"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH "PCRE2 REGULAR EXPRESSION DETAILS"
+.rs
+.sp
+The syntax and semantics of the regular expressions that are supported by PCRE2
+are described in detail below. There is a quick-reference syntax summary in the
+.\" HREF
+\fBpcre2syntax\fP
+.\"
+page. PCRE2 tries to match Perl syntax and semantics as closely as it can.
+PCRE2 also supports some alternative regular expression syntax (which does not
+conflict with the Perl syntax) in order to provide some compatibility with
+regular expressions in Python, .NET, and Oniguruma.
+.P
+Perl's regular expressions are described in its own documentation, and regular
+expressions in general are covered in a number of books, some of which have
+copious examples. Jeffrey Friedl's "Mastering Regular Expressions", published
+by O'Reilly, covers regular expressions in great detail. This description of
+PCRE2's regular expressions is intended as reference material.
+.P
+This document discusses the patterns that are supported by PCRE2 when its main
+matching function, \fBpcre2_match()\fP, is used. PCRE2 also has an alternative
+matching function, \fBpcre2_dfa_match()\fP, which matches using a different
+algorithm that is not Perl-compatible. Some of the features discussed below are
+not available when DFA matching is used. The advantages and disadvantages of
+the alternative function, and how it differs from the normal function, are
+discussed in the
+.\" HREF
+\fBpcre2matching\fP
+.\"
+page.
+.
+.
+.SH "SPECIAL START-OF-PATTERN ITEMS"
+.rs
+.sp
+A number of options that can be passed to \fBpcre2_compile()\fP can also be set
+by special items at the start of a pattern. These are not Perl-compatible, but
+are provided to make these options accessible to pattern writers who are not
+able to change the program that processes the pattern. Any number of these
+items may appear, but they must all be together right at the start of the
+pattern string, and the letters must be in upper case.
+.
+.
+.SS "UTF support"
+.rs
+.sp
+In the 8-bit and 16-bit PCRE2 libraries, characters may be coded either as
+single code units, or as multiple UTF-8 or UTF-16 code units. UTF-32 can be
+specified for the 32-bit library, in which case it constrains the character
+values to valid Unicode code points. To process UTF strings, PCRE2 must be
+built to include Unicode support (which is the default). When using UTF strings
+you must either call the compiling function with the PCRE2_UTF option, or the
+pattern must start with the special sequence (*UTF), which is equivalent to
+setting the relevant option. How setting a UTF mode affects pattern matching is
+mentioned in several places below. There is also a summary of features in the
+.\" HREF
+\fBpcre2unicode\fP
+.\"
+page.
+.P
+Some applications that allow their users to supply patterns may wish to
+restrict them to non-UTF data for security reasons. If the PCRE2_NEVER_UTF
+option is passed to \fBpcre2_compile()\fP, (*UTF) is not allowed, and its
+appearance in a pattern causes an error.
+.
+.
+.SS "Unicode property support"
+.rs
+.sp
+Another special sequence that may appear at the start of a pattern is (*UCP).
+This has the same effect as setting the PCRE2_UCP option: it causes sequences
+such as \ed and \ew to use Unicode properties to determine character types,
+instead of recognizing only characters with codes less than 256 via a lookup
+table.
+.P
+Some applications that allow their users to supply patterns may wish to
+restrict them for security reasons. If the PCRE2_NEVER_UCP option is passed to
+\fBpcre2_compile()\fP, (*UCP) is not allowed, and its appearance in a pattern
+causes an error.
+.
+.
+.SS "Locking out empty string matching"
+.rs
+.sp
+Starting a pattern with (*NOTEMPTY) or (*NOTEMPTY_ATSTART) has the same effect
+as passing the PCRE2_NOTEMPTY or PCRE2_NOTEMPTY_ATSTART option to whichever
+matching function is subsequently called to match the pattern. These options
+lock out the matching of empty strings, either entirely, or only at the start
+of the subject.
+.
+.
+.SS "Disabling auto-possessification"
+.rs
+.sp
+If a pattern starts with (*NO_AUTO_POSSESS), it has the same effect as setting
+the PCRE2_NO_AUTO_POSSESS option. This stops PCRE2 from making quantifiers
+possessive when what follows cannot match the repeated item. For example, by
+default a+b is treated as a++b. For more details, see the
+.\" HREF
+\fBpcre2api\fP
+.\"
+documentation.
+.
+.
+.SS "Disabling start-up optimizations"
+.rs
+.sp
+If a pattern starts with (*NO_START_OPT), it has the same effect as setting the
+PCRE2_NO_START_OPTIMIZE option. This disables several optimizations for quickly
+reaching "no match" results. For more details, see the
+.\" HREF
+\fBpcre2api\fP
+.\"
+documentation.
+.
+.
+.SS "Disabling automatic anchoring"
+.rs
+.sp
+If a pattern starts with (*NO_DOTSTAR_ANCHOR), it has the same effect as
+setting the PCRE2_NO_DOTSTAR_ANCHOR option. This disables optimizations that
+apply to patterns whose top-level branches all start with .* (match any number
+of arbitrary characters). For more details, see the
+.\" HREF
+\fBpcre2api\fP
+.\"
+documentation.
+.
+.
+.SS "Disabling JIT compilation"
+.rs
+.sp
+If a pattern that starts with (*NO_JIT) is successfully compiled, an attempt by
+the application to apply the JIT optimization by calling
+\fBpcre2_jit_compile()\fP is ignored.
+.
+.
+.SS "Setting match and recursion limits"
+.rs
+.sp
+The caller of \fBpcre2_match()\fP can set a limit on the number of times the
+internal \fBmatch()\fP function is called and on the maximum depth of
+recursive calls. These facilities are provided to catch runaway matches that
+are provoked by patterns with huge matching trees (a typical example is a
+pattern with nested unlimited repeats) and to avoid running out of system stack
+by too much recursion. When one of these limits is reached, \fBpcre2_match()\fP
+gives an error return. The limits can also be set by items at the start of the
+pattern of the form
+.sp
+  (*LIMIT_MATCH=d)
+  (*LIMIT_RECURSION=d)
+.sp
+where d is any number of decimal digits. However, the value of the setting must
+be less than the value set (or defaulted) by the caller of \fBpcre2_match()\fP
+for it to have any effect. In other words, the pattern writer can lower the
+limits set by the programmer, but not raise them. If there is more than one
+setting of one of these limits, the lower value is used.
+.
+.
+.\" HTML 
+.SS "Newline conventions"
+.rs
+.sp
+PCRE2 supports five different conventions for indicating line breaks in
+strings: a single CR (carriage return) character, a single LF (linefeed)
+character, the two-character sequence CRLF, any of the three preceding, or any
+Unicode newline sequence. The
+.\" HREF
+\fBpcre2api\fP
+.\"
+page has
+.\" HTML 
+.\" 
+further discussion
+.\"
+about newlines, and shows how to set the newline convention when calling
+\fBpcre2_compile()\fP.
+.P
+It is also possible to specify a newline convention by starting a pattern
+string with one of the following five sequences:
+.sp
+  (*CR)        carriage return
+  (*LF)        linefeed
+  (*CRLF)      carriage return, followed by linefeed
+  (*ANYCRLF)   any of the three above
+  (*ANY)       all Unicode newline sequences
+.sp
+These override the default and the options given to the compiling function. For
+example, on a Unix system where LF is the default newline sequence, the pattern
+.sp
+  (*CR)a.b
+.sp
+changes the convention to CR. That pattern matches "a\enb" because LF is no
+longer a newline. If more than one of these settings is present, the last one
+is used.
+.P
+The newline convention affects where the circumflex and dollar assertions are
+true. It also affects the interpretation of the dot metacharacter when
+PCRE2_DOTALL is not set, and the behaviour of \eN. However, it does not affect
+what the \eR escape sequence matches. By default, this is any Unicode newline
+sequence, for Perl compatibility. However, this can be changed; see the
+description of \eR in the section entitled
+.\" HTML 
+.\" 
+"Newline sequences"
+.\"
+below. A change of \eR setting can be combined with a change of newline
+convention.
+.
+.
+.SS "Specifying what \eR matches"
+.rs
+.sp
+It is possible to restrict \eR to match only CR, LF, or CRLF (instead of the
+complete set of Unicode line endings) by setting the option PCRE2_BSR_ANYCRLF
+at compile time. This effect can also be achieved by starting a pattern with
+(*BSR_ANYCRLF). For completeness, (*BSR_UNICODE) is also recognized,
+corresponding to PCRE2_BSR_UNICODE.
+.
+.
+.SH "EBCDIC CHARACTER CODES"
+.rs
+.sp
+PCRE2 can be compiled to run in an environment that uses EBCDIC as its
+character code rather than ASCII or Unicode (typically a mainframe system). In
+the sections below, character code values are ASCII or Unicode; in an EBCDIC
+environment these characters may have different code values, and there are no
+code points greater than 255.
+.
+.
+.SH "CHARACTERS AND METACHARACTERS"
+.rs
+.sp
+A regular expression is a pattern that is matched against a subject string from
+left to right. Most characters stand for themselves in a pattern, and match the
+corresponding characters in the subject. As a trivial example, the pattern
+.sp
+  The quick brown fox
+.sp
+matches a portion of a subject string that is identical to itself. When
+caseless matching is specified (the PCRE2_CASELESS option), letters are matched
+independently of case.
+.P
+The power of regular expressions comes from the ability to include alternatives
+and repetitions in the pattern. These are encoded in the pattern by the use of
+\fImetacharacters\fP, which do not stand for themselves but instead are
+interpreted in some special way.
+.P
+There are two different sets of metacharacters: those that are recognized
+anywhere in the pattern except within square brackets, and those that are
+recognized within square brackets. Outside square brackets, the metacharacters
+are as follows:
+.sp
+  \e      general escape character with several uses
+  ^      assert start of string (or line, in multiline mode)
+  $      assert end of string (or line, in multiline mode)
+  .      match any character except newline (by default)
+  [      start character class definition
+  |      start of alternative branch
+  (      start subpattern
+  )      end subpattern
+  ?      extends the meaning of (
+         also 0 or 1 quantifier
+         also quantifier minimizer
+  *      0 or more quantifier
+  +      1 or more quantifier
+         also "possessive quantifier"
+  {      start min/max quantifier
+.sp
+Part of a pattern that is in square brackets is called a "character class". In
+a character class the only metacharacters are:
+.sp
+  \e      general escape character
+  ^      negate the class, but only if the first character
+  -      indicates character range
+.\" JOIN
+  [      POSIX character class (only if followed by POSIX
+           syntax)
+  ]      terminates the character class
+.sp
+The following sections describe the use of each of the metacharacters.
+.
+.
+.SH BACKSLASH
+.rs
+.sp
+The backslash character has several uses. Firstly, if it is followed by a
+character that is not a number or a letter, it takes away any special meaning
+that character may have. This use of backslash as an escape character applies
+both inside and outside character classes.
+.P
+For example, if you want to match a * character, you write \e* in the pattern.
+This escaping action applies whether or not the following character would
+otherwise be interpreted as a metacharacter, so it is always safe to precede a
+non-alphanumeric with backslash to specify that it stands for itself. In
+particular, if you want to match a backslash, you write \e\e.
+.P
+In a UTF mode, only ASCII numbers and letters have any special meaning after a
+backslash. All other characters (in particular, those whose codepoints are
+greater than 127) are treated as literals.
+.P
+If a pattern is compiled with the PCRE2_EXTENDED option, most white space in
+the pattern (other than in a character class), and characters between a #
+outside a character class and the next newline, inclusive, are ignored. An
+escaping backslash can be used to include a white space or # character as part
+of the pattern.
+.P
+If you want to remove the special meaning from a sequence of characters, you
+can do so by putting them between \eQ and \eE. This is different from Perl in
+that $ and @ are handled as literals in \eQ...\eE sequences in PCRE2, whereas
+in Perl, $ and @ cause variable interpolation. Note the following examples:
+.sp
+  Pattern            PCRE2 matches   Perl matches
+.sp
+.\" JOIN
+  \eQabc$xyz\eE        abc$xyz        abc followed by the
+                                      contents of $xyz
+  \eQabc\e$xyz\eE       abc\e$xyz       abc\e$xyz
+  \eQabc\eE\e$\eQxyz\eE   abc$xyz        abc$xyz
+.sp
+The \eQ...\eE sequence is recognized both inside and outside character classes.
+An isolated \eE that is not preceded by \eQ is ignored. If \eQ is not followed
+by \eE later in the pattern, the literal interpretation continues to the end of
+the pattern (that is, \eE is assumed at the end). If the isolated \eQ is inside
+a character class, this causes an error, because the character class is not
+terminated.
+.
+.
+.\" HTML 
+.SS "Non-printing characters"
+.rs
+.sp
+A second use of backslash provides a way of encoding non-printing characters
+in patterns in a visible manner. There is no restriction on the appearance of
+non-printing characters in a pattern, but when a pattern is being prepared by
+text editing, it is often easier to use one of the following escape sequences
+than the binary character it represents. In an ASCII or Unicode environment,
+these escapes are as follows:
+.sp
+  \ea        alarm, that is, the BEL character (hex 07)
+  \ecx       "control-x", where x is any printable ASCII character
+  \ee        escape (hex 1B)
+  \ef        form feed (hex 0C)
+  \en        linefeed (hex 0A)
+  \er        carriage return (hex 0D)
+  \et        tab (hex 09)
+  \e0dd      character with octal code 0dd
+  \eddd      character with octal code ddd, or back reference
+  \eo{ddd..} character with octal code ddd..
+  \exhh      character with hex code hh
+  \ex{hhh..} character with hex code hhh.. (default mode)
+  \euhhhh    character with hex code hhhh (when PCRE2_ALT_BSUX is set)
+.sp
+The precise effect of \ecx on ASCII characters is as follows: if x is a lower
+case letter, it is converted to upper case. Then bit 6 of the character (hex
+40) is inverted. Thus \ecA to \ecZ become hex 01 to hex 1A (A is 41, Z is 5A),
+but \ec{ becomes hex 3B ({ is 7B), and \ec; becomes hex 7B (; is 3B). If the
+code unit following \ec has a value less than 32 or greater than 126, a
+compile-time error occurs. This locks out non-printable ASCII characters in all
+modes.
+.P
+When PCRE2 is compiled in EBCDIC mode, \ea, \ee, \ef, \en, \er, and \et
+generate the appropriate EBCDIC code values. The \ec escape is processed
+as specified for Perl in the \fBperlebcdic\fP document. The only characters
+that are allowed after \ec are A-Z, a-z, or one of @, [, \e, ], ^, _, or ?. Any
+other character provokes a compile-time error. The sequence \e@ encodes
+character code 0; the letters (in either case) encode characters 1-26 (hex 01
+to hex 1A); [, \e, ], ^, and _ encode characters 27-31 (hex 1B to hex 1F), and
+\e? becomes either 255 (hex FF) or 95 (hex 5F).
+.P
+Thus, apart from \e?, these escapes generate the same character code values as
+they do in an ASCII environment, though the meanings of the values mostly
+differ. For example, \eG always generates code value 7, which is BEL in ASCII
+but DEL in EBCDIC.
+.P
+The sequence \e? generates DEL (127, hex 7F) in an ASCII environment, but
+because 127 is not a control character in EBCDIC, Perl makes it generate the
+APC character. Unfortunately, there are several variants of EBCDIC. In most of
+them the APC character has the value 255 (hex FF), but in the one Perl calls
+POSIX-BC its value is 95 (hex 5F). If certain other characters have POSIX-BC
+values, PCRE2 makes \e? generate 95; otherwise it generates 255.
+.P
+After \e0 up to two further octal digits are read. If there are fewer than two
+digits, just those that are present are used. Thus the sequence \e0\ex\e015
+specifies two binary zeros followed by a CR character (code value 13). Make
+sure you supply two digits after the initial zero if the pattern character that
+follows is itself an octal digit.
+.P
+The escape \eo must be followed by a sequence of octal digits, enclosed in
+braces. An error occurs if this is not the case. This escape is a recent
+addition to Perl; it provides way of specifying character code points as octal
+numbers greater than 0777, and it also allows octal numbers and back references
+to be unambiguously specified.
+.P
+For greater clarity and unambiguity, it is best to avoid following \e by a
+digit greater than zero. Instead, use \eo{} or \ex{} to specify character
+numbers, and \eg{} to specify back references. The following paragraphs
+describe the old, ambiguous syntax.
+.P
+The handling of a backslash followed by a digit other than 0 is complicated,
+and Perl has changed over time, causing PCRE2 also to change.
+.P
+Outside a character class, PCRE2 reads the digit and any following digits as a
+decimal number. If the number is less than 10, begins with the digit 8 or 9, or
+if there are at least that many previous capturing left parentheses in the
+expression, the entire sequence is taken as a \fIback reference\fP. A
+description of how this works is given
+.\" HTML 
+.\" 
+later,
+.\"
+following the discussion of
+.\" HTML 
+.\" 
+parenthesized subpatterns.
+.\"
+Otherwise, up to three octal digits are read to form a character code.
+.P
+Inside a character class, PCRE2 handles \e8 and \e9 as the literal characters
+"8" and "9", and otherwise reads up to three octal digits following the
+backslash, using them to generate a data character. Any subsequent digits stand
+for themselves. For example, outside a character class:
+.sp
+  \e040   is another way of writing an ASCII space
+.\" JOIN
+  \e40    is the same, provided there are fewer than 40
+            previous capturing subpatterns
+  \e7     is always a back reference
+.\" JOIN
+  \e11    might be a back reference, or another way of
+            writing a tab
+  \e011   is always a tab
+  \e0113  is a tab followed by the character "3"
+.\" JOIN
+  \e113   might be a back reference, otherwise the
+            character with octal code 113
+.\" JOIN
+  \e377   might be a back reference, otherwise
+            the value 255 (decimal)
+.\" JOIN
+  \e81    is always a back reference
+.sp
+Note that octal values of 100 or greater that are specified using this syntax
+must not be introduced by a leading zero, because no more than three octal
+digits are ever read.
+.P
+By default, after \ex that is not followed by {, from zero to two hexadecimal
+digits are read (letters can be in upper or lower case). Any number of
+hexadecimal digits may appear between \ex{ and }. If a character other than
+a hexadecimal digit appears between \ex{ and }, or if there is no terminating
+}, an error occurs.
+.P
+If the PCRE2_ALT_BSUX option is set, the interpretation of \ex is as just
+described only when it is followed by two hexadecimal digits. Otherwise, it
+matches a literal "x" character. In this mode mode, support for code points
+greater than 256 is provided by \eu, which must be followed by four hexadecimal
+digits; otherwise it matches a literal "u" character.
+.P
+Characters whose value is less than 256 can be defined by either of the two
+syntaxes for \ex (or by \eu in PCRE2_ALT_BSUX mode). There is no difference in
+the way they are handled. For example, \exdc is exactly the same as \ex{dc} (or
+\eu00dc in PCRE2_ALT_BSUX mode).
+.
+.
+.SS "Constraints on character values"
+.rs
+.sp
+Characters that are specified using octal or hexadecimal numbers are
+limited to certain values, as follows:
+.sp
+  8-bit non-UTF mode    less than 0x100
+  8-bit UTF-8 mode      less than 0x10ffff and a valid codepoint
+  16-bit non-UTF mode   less than 0x10000
+  16-bit UTF-16 mode    less than 0x10ffff and a valid codepoint
+  32-bit non-UTF mode   less than 0x100000000
+  32-bit UTF-32 mode    less than 0x10ffff and a valid codepoint
+.sp
+Invalid Unicode codepoints are the range 0xd800 to 0xdfff (the so-called
+"surrogate" codepoints), and 0xffef.
+.
+.
+.SS "Escape sequences in character classes"
+.rs
+.sp
+All the sequences that define a single character value can be used both inside
+and outside character classes. In addition, inside a character class, \eb is
+interpreted as the backspace character (hex 08).
+.P
+\eN is not allowed in a character class. \eB, \eR, and \eX are not special
+inside a character class. Like other unrecognized alphabetic escape sequences,
+they cause an error. Outside a character class, these sequences have different
+meanings.
+.
+.
+.SS "Unsupported escape sequences"
+.rs
+.sp
+In Perl, the sequences \el, \eL, \eu, and \eU are recognized by its string
+handler and used to modify the case of following characters. By default, PCRE2
+does not support these escape sequences. However, if the PCRE2_ALT_BSUX option
+is set, \eU matches a "U" character, and \eu can be used to define a character
+by code point, as described in the previous section.
+.
+.
+.SS "Absolute and relative back references"
+.rs
+.sp
+The sequence \eg followed by an unsigned or a negative number, optionally
+enclosed in braces, is an absolute or relative back reference. A named back
+reference can be coded as \eg{name}. Back references are discussed
+.\" HTML 
+.\" 
+later,
+.\"
+following the discussion of
+.\" HTML 
+.\" 
+parenthesized subpatterns.
+.\"
+.
+.
+.SS "Absolute and relative subroutine calls"
+.rs
+.sp
+For compatibility with Oniguruma, the non-Perl syntax \eg followed by a name or
+a number enclosed either in angle brackets or single quotes, is an alternative
+syntax for referencing a subpattern as a "subroutine". Details are discussed
+.\" HTML 
+.\" 
+later.
+.\"
+Note that \eg{...} (Perl syntax) and \eg<...> (Oniguruma syntax) are \fInot\fP
+synonymous. The former is a back reference; the latter is a
+.\" HTML 
+.\" 
+subroutine
+.\"
+call.
+.
+.
+.\" HTML 
+.SS "Generic character types"
+.rs
+.sp
+Another use of backslash is for specifying generic character types:
+.sp
+  \ed     any decimal digit
+  \eD     any character that is not a decimal digit
+  \eh     any horizontal white space character
+  \eH     any character that is not a horizontal white space character
+  \es     any white space character
+  \eS     any character that is not a white space character
+  \ev     any vertical white space character
+  \eV     any character that is not a vertical white space character
+  \ew     any "word" character
+  \eW     any "non-word" character
+.sp
+There is also the single sequence \eN, which matches a non-newline character.
+This is the same as
+.\" HTML 
+.\" 
+the "." metacharacter
+.\"
+when PCRE2_DOTALL is not set. Perl also uses \eN to match characters by name;
+PCRE2 does not support this.
+.P
+Each pair of lower and upper case escape sequences partitions the complete set
+of characters into two disjoint sets. Any given character matches one, and only
+one, of each pair. The sequences can appear both inside and outside character
+classes. They each match one character of the appropriate type. If the current
+matching point is at the end of the subject string, all of them fail, because
+there is no character to match.
+.P
+The default \es characters are HT (9), LF (10), VT (11), FF (12), CR (13), and
+space (32), which are defined as white space in the "C" locale. This list may
+vary if locale-specific matching is taking place. For example, in some locales
+the "non-breaking space" character (\exA0) is recognized as white space, and in
+others the VT character is not.
+.P
+A "word" character is an underscore or any character that is a letter or digit.
+By default, the definition of letters and digits is controlled by PCRE2's
+low-valued character tables, and may vary if locale-specific matching is taking
+place (see
+.\" HTML 
+.\" 
+"Locale support"
+.\"
+in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page). For example, in a French locale such as "fr_FR" in Unix-like systems,
+or "french" in Windows, some character codes greater than 127 are used for
+accented letters, and these are then matched by \ew. The use of locales with
+Unicode is discouraged.
+.P
+By default, characters whose code points are greater than 127 never match \ed,
+\es, or \ew, and always match \eD, \eS, and \eW, although this may be different
+for characters in the range 128-255 when locale-specific matching is happening.
+These escape sequences retain their original meanings from before Unicode
+support was available, mainly for efficiency reasons. If the PCRE2_UCP option
+is set, the behaviour is changed so that Unicode properties are used to
+determine character types, as follows:
+.sp
+  \ed  any character that matches \ep{Nd} (decimal digit)
+  \es  any character that matches \ep{Z} or \eh or \ev
+  \ew  any character that matches \ep{L} or \ep{N}, plus underscore
+.sp
+The upper case escapes match the inverse sets of characters. Note that \ed
+matches only decimal digits, whereas \ew matches any Unicode digit, as well as
+any Unicode letter, and underscore. Note also that PCRE2_UCP affects \eb, and
+\eB because they are defined in terms of \ew and \eW. Matching these sequences
+is noticeably slower when PCRE2_UCP is set.
+.P
+The sequences \eh, \eH, \ev, and \eV, in contrast to the other sequences, which
+match only ASCII characters by default, always match a specific list of code
+points, whether or not PCRE2_UCP is set. The horizontal space characters are:
+.sp
+  U+0009     Horizontal tab (HT)
+  U+0020     Space
+  U+00A0     Non-break space
+  U+1680     Ogham space mark
+  U+180E     Mongolian vowel separator
+  U+2000     En quad
+  U+2001     Em quad
+  U+2002     En space
+  U+2003     Em space
+  U+2004     Three-per-em space
+  U+2005     Four-per-em space
+  U+2006     Six-per-em space
+  U+2007     Figure space
+  U+2008     Punctuation space
+  U+2009     Thin space
+  U+200A     Hair space
+  U+202F     Narrow no-break space
+  U+205F     Medium mathematical space
+  U+3000     Ideographic space
+.sp
+The vertical space characters are:
+.sp
+  U+000A     Linefeed (LF)
+  U+000B     Vertical tab (VT)
+  U+000C     Form feed (FF)
+  U+000D     Carriage return (CR)
+  U+0085     Next line (NEL)
+  U+2028     Line separator
+  U+2029     Paragraph separator
+.sp
+In 8-bit, non-UTF-8 mode, only the characters with code points less than 256
+are relevant.
+.
+.
+.\" HTML 
+.SS "Newline sequences"
+.rs
+.sp
+Outside a character class, by default, the escape sequence \eR matches any
+Unicode newline sequence. In 8-bit non-UTF-8 mode \eR is equivalent to the
+following:
+.sp
+  (?>\er\en|\en|\ex0b|\ef|\er|\ex85)
+.sp
+This is an example of an "atomic group", details of which are given
+.\" HTML 
+.\" 
+below.
+.\"
+This particular group matches either the two-character sequence CR followed by
+LF, or one of the single characters LF (linefeed, U+000A), VT (vertical tab,
+U+000B), FF (form feed, U+000C), CR (carriage return, U+000D), or NEL (next
+line, U+0085). The two-character sequence is treated as a single unit that
+cannot be split.
+.P
+In other modes, two additional characters whose codepoints are greater than 255
+are added: LS (line separator, U+2028) and PS (paragraph separator, U+2029).
+Unicode support is not needed for these characters to be recognized.
+.P
+It is possible to restrict \eR to match only CR, LF, or CRLF (instead of the
+complete set of Unicode line endings) by setting the option PCRE2_BSR_ANYCRLF
+at compile time. (BSR is an abbrevation for "backslash R".) This can be made
+the default when PCRE2 is built; if this is the case, the other behaviour can
+be requested via the PCRE2_BSR_UNICODE option. It is also possible to specify
+these settings by starting a pattern string with one of the following
+sequences:
+.sp
+  (*BSR_ANYCRLF)   CR, LF, or CRLF only
+  (*BSR_UNICODE)   any Unicode newline sequence
+.sp
+These override the default and the options given to the compiling function.
+Note that these special settings, which are not Perl-compatible, are recognized
+only at the very start of a pattern, and that they must be in upper case. If
+more than one of them is present, the last one is used. They can be combined
+with a change of newline convention; for example, a pattern can start with:
+.sp
+  (*ANY)(*BSR_ANYCRLF)
+.sp
+They can also be combined with the (*UTF) or (*UCP) special sequences. Inside a
+character class, \eR is treated as an unrecognized escape sequence, and causes
+an error.
+.
+.
+.\" HTML 
+.SS Unicode character properties
+.rs
+.sp
+When PCRE2 is built with Unicode support (the default), three additional escape
+sequences that match characters with specific properties are available. In
+8-bit non-UTF-8 mode, these sequences are of course limited to testing
+characters whose codepoints are less than 256, but they do work in this mode.
+The extra escape sequences are:
+.sp
+  \ep{\fIxx\fP}   a character with the \fIxx\fP property
+  \eP{\fIxx\fP}   a character without the \fIxx\fP property
+  \eX       a Unicode extended grapheme cluster
+.sp
+The property names represented by \fIxx\fP above are limited to the Unicode
+script names, the general category properties, "Any", which matches any
+character (including newline), and some special PCRE2 properties (described
+in the
+.\" HTML 
+.\" 
+next section).
+.\"
+Other Perl properties such as "InMusicalSymbols" are not supported by PCRE2.
+Note that \eP{Any} does not match any characters, so always causes a match
+failure.
+.P
+Sets of Unicode characters are defined as belonging to certain scripts. A
+character from one of these sets can be matched using a script name. For
+example:
+.sp
+  \ep{Greek}
+  \eP{Han}
+.sp
+Those that are not part of an identified script are lumped together as
+"Common". The current list of scripts is:
+.P
+Arabic,
+Armenian,
+Avestan,
+Balinese,
+Bamum,
+Bassa_Vah,
+Batak,
+Bengali,
+Bopomofo,
+Brahmi,
+Braille,
+Buginese,
+Buhid,
+Canadian_Aboriginal,
+Carian,
+Caucasian_Albanian,
+Chakma,
+Cham,
+Cherokee,
+Common,
+Coptic,
+Cuneiform,
+Cypriot,
+Cyrillic,
+Deseret,
+Devanagari,
+Duployan,
+Egyptian_Hieroglyphs,
+Elbasan,
+Ethiopic,
+Georgian,
+Glagolitic,
+Gothic,
+Grantha,
+Greek,
+Gujarati,
+Gurmukhi,
+Han,
+Hangul,
+Hanunoo,
+Hebrew,
+Hiragana,
+Imperial_Aramaic,
+Inherited,
+Inscriptional_Pahlavi,
+Inscriptional_Parthian,
+Javanese,
+Kaithi,
+Kannada,
+Katakana,
+Kayah_Li,
+Kharoshthi,
+Khmer,
+Khojki,
+Khudawadi,
+Lao,
+Latin,
+Lepcha,
+Limbu,
+Linear_A,
+Linear_B,
+Lisu,
+Lycian,
+Lydian,
+Mahajani,
+Malayalam,
+Mandaic,
+Manichaean,
+Meetei_Mayek,
+Mende_Kikakui,
+Meroitic_Cursive,
+Meroitic_Hieroglyphs,
+Miao,
+Modi,
+Mongolian,
+Mro,
+Myanmar,
+Nabataean,
+New_Tai_Lue,
+Nko,
+Ogham,
+Ol_Chiki,
+Old_Italic,
+Old_North_Arabian,
+Old_Permic,
+Old_Persian,
+Old_South_Arabian,
+Old_Turkic,
+Oriya,
+Osmanya,
+Pahawh_Hmong,
+Palmyrene,
+Pau_Cin_Hau,
+Phags_Pa,
+Phoenician,
+Psalter_Pahlavi,
+Rejang,
+Runic,
+Samaritan,
+Saurashtra,
+Sharada,
+Shavian,
+Siddham,
+Sinhala,
+Sora_Sompeng,
+Sundanese,
+Syloti_Nagri,
+Syriac,
+Tagalog,
+Tagbanwa,
+Tai_Le,
+Tai_Tham,
+Tai_Viet,
+Takri,
+Tamil,
+Telugu,
+Thaana,
+Thai,
+Tibetan,
+Tifinagh,
+Tirhuta,
+Ugaritic,
+Vai,
+Warang_Citi,
+Yi.
+.P
+Each character has exactly one Unicode general category property, specified by
+a two-letter abbreviation. For compatibility with Perl, negation can be
+specified by including a circumflex between the opening brace and the property
+name. For example, \ep{^Lu} is the same as \eP{Lu}.
+.P
+If only one letter is specified with \ep or \eP, it includes all the general
+category properties that start with that letter. In this case, in the absence
+of negation, the curly brackets in the escape sequence are optional; these two
+examples have the same effect:
+.sp
+  \ep{L}
+  \epL
+.sp
+The following general category property codes are supported:
+.sp
+  C     Other
+  Cc    Control
+  Cf    Format
+  Cn    Unassigned
+  Co    Private use
+  Cs    Surrogate
+.sp
+  L     Letter
+  Ll    Lower case letter
+  Lm    Modifier letter
+  Lo    Other letter
+  Lt    Title case letter
+  Lu    Upper case letter
+.sp
+  M     Mark
+  Mc    Spacing mark
+  Me    Enclosing mark
+  Mn    Non-spacing mark
+.sp
+  N     Number
+  Nd    Decimal number
+  Nl    Letter number
+  No    Other number
+.sp
+  P     Punctuation
+  Pc    Connector punctuation
+  Pd    Dash punctuation
+  Pe    Close punctuation
+  Pf    Final punctuation
+  Pi    Initial punctuation
+  Po    Other punctuation
+  Ps    Open punctuation
+.sp
+  S     Symbol
+  Sc    Currency symbol
+  Sk    Modifier symbol
+  Sm    Mathematical symbol
+  So    Other symbol
+.sp
+  Z     Separator
+  Zl    Line separator
+  Zp    Paragraph separator
+  Zs    Space separator
+.sp
+The special property L& is also supported: it matches a character that has
+the Lu, Ll, or Lt property, in other words, a letter that is not classified as
+a modifier or "other".
+.P
+The Cs (Surrogate) property applies only to characters in the range U+D800 to
+U+DFFF. Such characters are not valid in Unicode strings and so
+cannot be tested by PCRE2, unless UTF validity checking has been turned off
+(see the discussion of PCRE2_NO_UTF_CHECK in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page). Perl does not support the Cs property.
+.P
+The long synonyms for property names that Perl supports (such as \ep{Letter})
+are not supported by PCRE2, nor is it permitted to prefix any of these
+properties with "Is".
+.P
+No character that is in the Unicode table has the Cn (unassigned) property.
+Instead, this property is assumed for any code point that is not in the
+Unicode table.
+.P
+Specifying caseless matching does not affect these escape sequences. For
+example, \ep{Lu} always matches only upper case letters. This is different from
+the behaviour of current versions of Perl.
+.P
+Matching characters by Unicode property is not fast, because PCRE2 has to do a
+multistage table lookup in order to find a character's property. That is why
+the traditional escape sequences such as \ed and \ew do not use Unicode
+properties in PCRE2 by default, though you can make them do so by setting the
+PCRE2_UCP option or by starting the pattern with (*UCP).
+.
+.
+.SS Extended grapheme clusters
+.rs
+.sp
+The \eX escape matches any number of Unicode characters that form an "extended
+grapheme cluster", and treats the sequence as an atomic group
+.\" HTML 
+.\" 
+(see below).
+.\"
+Unicode supports various kinds of composite character by giving each character
+a grapheme breaking property, and having rules that use these properties to
+define the boundaries of extended grapheme clusters. \eX always matches at
+least one character. Then it decides whether to add additional characters
+according to the following rules for ending a cluster:
+.P
+1. End at the end of the subject string.
+.P
+2. Do not end between CR and LF; otherwise end after any control character.
+.P
+3. Do not break Hangul (a Korean script) syllable sequences. Hangul characters
+are of five types: L, V, T, LV, and LVT. An L character may be followed by an
+L, V, LV, or LVT character; an LV or V character may be followed by a V or T
+character; an LVT or T character may be follwed only by a T character.
+.P
+4. Do not end before extending characters or spacing marks. Characters with
+the "mark" property always have the "extend" grapheme breaking property.
+.P
+5. Do not end after prepend characters.
+.P
+6. Otherwise, end the cluster.
+.
+.
+.\" HTML 
+.SS PCRE2's additional properties
+.rs
+.sp
+As well as the standard Unicode properties described above, PCRE2 supports four
+more that make it possible to convert traditional escape sequences such as \ew
+and \es to use Unicode properties. PCRE2 uses these non-standard, non-Perl
+properties internally when PCRE2_UCP is set. However, they may also be used
+explicitly. These properties are:
+.sp
+  Xan   Any alphanumeric character
+  Xps   Any POSIX space character
+  Xsp   Any Perl space character
+  Xwd   Any Perl "word" character
+.sp
+Xan matches characters that have either the L (letter) or the N (number)
+property. Xps matches the characters tab, linefeed, vertical tab, form feed, or
+carriage return, and any other character that has the Z (separator) property.
+Xsp is the same as Xps; in PCRE1 it used to exclude vertical tab, for Perl
+compatibility, but Perl changed. Xwd matches the same characters as Xan, plus
+underscore.
+.P
+There is another non-standard property, Xuc, which matches any character that
+can be represented by a Universal Character Name in C++ and other programming
+languages. These are the characters $, @, ` (grave accent), and all characters
+with Unicode code points greater than or equal to U+00A0, except for the
+surrogates U+D800 to U+DFFF. Note that most base (ASCII) characters are
+excluded. (Universal Character Names are of the form \euHHHH or \eUHHHHHHHH
+where H is a hexadecimal digit. Note that the Xuc property does not match these
+sequences but the characters that they represent.)
+.
+.
+.\" HTML 
+.SS "Resetting the match start"
+.rs
+.sp
+The escape sequence \eK causes any previously matched characters not to be
+included in the final matched sequence. For example, the pattern:
+.sp
+  foo\eKbar
+.sp
+matches "foobar", but reports that it has matched "bar". This feature is
+similar to a lookbehind assertion
+.\" HTML 
+.\" 
+(described below).
+.\"
+However, in this case, the part of the subject before the real match does not
+have to be of fixed length, as lookbehind assertions do. The use of \eK does
+not interfere with the setting of
+.\" HTML 
+.\" 
+captured substrings.
+.\"
+For example, when the pattern
+.sp
+  (foo)\eKbar
+.sp
+matches "foobar", the first substring is still set to "foo".
+.P
+Perl documents that the use of \eK within assertions is "not well defined". In
+PCRE2, \eK is acted upon when it occurs inside positive assertions, but is
+ignored in negative assertions. Note that when a pattern such as (?=ab\eK)
+matches, the reported start of the match can be greater than the end of the
+match.
+.
+.
+.\" HTML 
+.SS "Simple assertions"
+.rs
+.sp
+The final use of backslash is for certain simple assertions. An assertion
+specifies a condition that has to be met at a particular point in a match,
+without consuming any characters from the subject string. The use of
+subpatterns for more complicated assertions is described
+.\" HTML 
+.\" 
+below.
+.\"
+The backslashed assertions are:
+.sp
+  \eb     matches at a word boundary
+  \eB     matches when not at a word boundary
+  \eA     matches at the start of the subject
+  \eZ     matches at the end of the subject
+          also matches before a newline at the end of the subject
+  \ez     matches only at the end of the subject
+  \eG     matches at the first matching position in the subject
+.sp
+Inside a character class, \eb has a different meaning; it matches the backspace
+character. If any other of these assertions appears in a character class, an
+"invalid escape sequence" error is generated.
+.P
+A word boundary is a position in the subject string where the current character
+and the previous character do not both match \ew or \eW (i.e. one matches
+\ew and the other matches \eW), or the start or end of the string if the
+first or last character matches \ew, respectively. In a UTF mode, the meanings
+of \ew and \eW can be changed by setting the PCRE2_UCP option. When this is
+done, it also affects \eb and \eB. Neither PCRE2 nor Perl has a separate "start
+of word" or "end of word" metasequence. However, whatever follows \eb normally
+determines which it is. For example, the fragment \eba matches "a" at the start
+of a word.
+.P
+The \eA, \eZ, and \ez assertions differ from the traditional circumflex and
+dollar (described in the next section) in that they only ever match at the very
+start and end of the subject string, whatever options are set. Thus, they are
+independent of multiline mode. These three assertions are not affected by the
+PCRE2_NOTBOL or PCRE2_NOTEOL options, which affect only the behaviour of the
+circumflex and dollar metacharacters. However, if the \fIstartoffset\fP
+argument of \fBpcre2_match()\fP is non-zero, indicating that matching is to
+start at a point other than the beginning of the subject, \eA can never match.
+The difference between \eZ and \ez is that \eZ matches before a newline at the
+end of the string as well as at the very end, whereas \ez matches only at the
+end.
+.P
+The \eG assertion is true only when the current matching position is at the
+start point of the match, as specified by the \fIstartoffset\fP argument of
+\fBpcre2_match()\fP. It differs from \eA when the value of \fIstartoffset\fP is
+non-zero. By calling \fBpcre2_match()\fP multiple times with appropriate
+arguments, you can mimic Perl's /g option, and it is in this kind of
+implementation where \eG can be useful.
+.P
+Note, however, that PCRE2's interpretation of \eG, as the start of the current
+match, is subtly different from Perl's, which defines it as the end of the
+previous match. In Perl, these can be different when the previously matched
+string was empty. Because PCRE2 does just one match at a time, it cannot
+reproduce this behaviour.
+.P
+If all the alternatives of a pattern begin with \eG, the expression is anchored
+to the starting match position, and the "anchored" flag is set in the compiled
+regular expression.
+.
+.
+.SH "CIRCUMFLEX AND DOLLAR"
+.rs
+.sp
+The circumflex and dollar metacharacters are zero-width assertions. That is,
+they test for a particular condition being true without consuming any
+characters from the subject string. These two metacharacters are concerned with
+matching the starts and ends of lines. If the newline convention is set so that
+only the two-character sequence CRLF is recognized as a newline, isolated CR
+and LF characters are treated as ordinary data characters, and are not
+recognized as newlines.
+.P
+Outside a character class, in the default matching mode, the circumflex
+character is an assertion that is true only if the current matching point is at
+the start of the subject string. If the \fIstartoffset\fP argument of
+\fBpcre2_match()\fP is non-zero, or if PCRE2_NOTBOL is set, circumflex can
+never match if the PCRE2_MULTILINE option is unset. Inside a character class,
+circumflex has an entirely different meaning
+.\" HTML 
+.\" 
+(see below).
+.\"
+.P
+Circumflex need not be the first character of the pattern if a number of
+alternatives are involved, but it should be the first thing in each alternative
+in which it appears if the pattern is ever to match that branch. If all
+possible alternatives start with a circumflex, that is, if the pattern is
+constrained to match only at the start of the subject, it is said to be an
+"anchored" pattern. (There are also other constructs that can cause a pattern
+to be anchored.)
+.P
+The dollar character is an assertion that is true only if the current matching
+point is at the end of the subject string, or immediately before a newline at
+the end of the string (by default), unless PCRE2_NOTEOL is set. Note, however,
+that it does not actually match the newline. Dollar need not be the last
+character of the pattern if a number of alternatives are involved, but it
+should be the last item in any branch in which it appears. Dollar has no
+special meaning in a character class.
+.P
+The meaning of dollar can be changed so that it matches only at the very end of
+the string, by setting the PCRE2_DOLLAR_ENDONLY option at compile time. This
+does not affect the \eZ assertion.
+.P
+The meanings of the circumflex and dollar metacharacters are changed if the
+PCRE2_MULTILINE option is set. When this is the case, a dollar character
+matches before any newlines in the string, as well as at the very end, and a
+circumflex matches immediately after internal newlines as well as at the start
+of the subject string. It does not match after a newline that ends the string,
+for compatibility with Perl. However, this can be changed by setting the
+PCRE2_ALT_CIRCUMFLEX option.
+.P
+For example, the pattern /^abc$/ matches the subject string "def\enabc" (where
+\en represents a newline) in multiline mode, but not otherwise. Consequently,
+patterns that are anchored in single line mode because all branches start with
+^ are not anchored in multiline mode, and a match for circumflex is possible
+when the \fIstartoffset\fP argument of \fBpcre2_match()\fP is non-zero. The
+PCRE2_DOLLAR_ENDONLY option is ignored if PCRE2_MULTILINE is set.
+.P
+Note that the sequences \eA, \eZ, and \ez can be used to match the start and
+end of the subject in both modes, and if all branches of a pattern start with
+\eA it is always anchored, whether or not PCRE2_MULTILINE is set.
+.
+.
+.\" HTML 
+.SH "FULL STOP (PERIOD, DOT) AND \eN"
+.rs
+.sp
+Outside a character class, a dot in the pattern matches any one character in
+the subject string except (by default) a character that signifies the end of a
+line.
+.P
+When a line ending is defined as a single character, dot never matches that
+character; when the two-character sequence CRLF is used, dot does not match CR
+if it is immediately followed by LF, but otherwise it matches all characters
+(including isolated CRs and LFs). When any Unicode line endings are being
+recognized, dot does not match CR or LF or any of the other line ending
+characters.
+.P
+The behaviour of dot with regard to newlines can be changed. If the
+PCRE2_DOTALL option is set, a dot matches any one character, without exception.
+If the two-character sequence CRLF is present in the subject string, it takes
+two dots to match it.
+.P
+The handling of dot is entirely independent of the handling of circumflex and
+dollar, the only relationship being that they both involve newlines. Dot has no
+special meaning in a character class.
+.P
+The escape sequence \eN behaves like a dot, except that it is not affected by
+the PCRE2_DOTALL option. In other words, it matches any character except one
+that signifies the end of a line. Perl also uses \eN to match characters by
+name; PCRE2 does not support this.
+.
+.
+.SH "MATCHING A SINGLE CODE UNIT"
+.rs
+.sp
+Outside a character class, the escape sequence \eC matches any one code unit,
+whether or not a UTF mode is set. In the 8-bit library, one code unit is one
+byte; in the 16-bit library it is a 16-bit unit; in the 32-bit library it is a
+32-bit unit. Unlike a dot, \eC always matches line-ending characters. The
+feature is provided in Perl in order to match individual bytes in UTF-8 mode,
+but it is unclear how it can usefully be used.
+.P
+Because \eC breaks up characters into individual code units, matching one unit
+with \eC in UTF-8 or UTF-16 mode means that the rest of the string may start
+with a malformed UTF character. This has undefined results, because PCRE2
+assumes that it is matching character by character in a valid UTF string (by
+default it checks the subject string's validity at the start of processing
+unless the PCRE2_NO_UTF_CHECK option is used). An application can lock out the
+use of \eC by setting the PCRE2_NEVER_BACKSLASH_C option.
+.P
+PCRE2 does not allow \eC to appear in lookbehind assertions
+.\" HTML 
+.\" 
+(described below)
+.\"
+in a UTF mode, because this would make it impossible to calculate the length of
+the lookbehind.
+.P
+In general, the \eC escape sequence is best avoided. However, one way of using
+it that avoids the problem of malformed UTF characters is to use a lookahead to
+check the length of the next character, as in this pattern, which could be used
+with a UTF-8 string (ignore white space and line breaks):
+.sp
+  (?| (?=[\ex00-\ex7f])(\eC) |
+      (?=[\ex80-\ex{7ff}])(\eC)(\eC) |
+      (?=[\ex{800}-\ex{ffff}])(\eC)(\eC)(\eC) |
+      (?=[\ex{10000}-\ex{1fffff}])(\eC)(\eC)(\eC)(\eC))
+.sp
+In this example, a group that starts with (?| resets the capturing parentheses
+numbers in each alternative (see
+.\" HTML 
+.\" 
+"Duplicate Subpattern Numbers"
+.\"
+below). The assertions at the start of each branch check the next UTF-8
+character for values whose encoding uses 1, 2, 3, or 4 bytes, respectively. The
+character's individual bytes are then captured by the appropriate number of
+\eC groups.
+.
+.
+.\" HTML 
+.SH "SQUARE BRACKETS AND CHARACTER CLASSES"
+.rs
+.sp
+An opening square bracket introduces a character class, terminated by a closing
+square bracket. A closing square bracket on its own is not special by default.
+If a closing square bracket is required as a member of the class, it should be
+the first data character in the class (after an initial circumflex, if present)
+or escaped with a backslash. This means that, by default, an empty class cannot
+be defined. However, if the PCRE2_ALLOW_EMPTY_CLASS option is set, a closing
+square bracket at the start does end the (empty) class.
+.P
+A character class matches a single character in the subject. A matched
+character must be in the set of characters defined by the class, unless the
+first character in the class definition is a circumflex, in which case the
+subject character must not be in the set defined by the class. If a circumflex
+is actually required as a member of the class, ensure it is not the first
+character, or escape it with a backslash.
+.P
+For example, the character class [aeiou] matches any lower case vowel, while
+[^aeiou] matches any character that is not a lower case vowel. Note that a
+circumflex is just a convenient notation for specifying the characters that
+are in the class by enumerating those that are not. A class that starts with a
+circumflex is not an assertion; it still consumes a character from the subject
+string, and therefore it fails if the current pointer is at the end of the
+string.
+.P
+When caseless matching is set, any letters in a class represent both their
+upper case and lower case versions, so for example, a caseless [aeiou] matches
+"A" as well as "a", and a caseless [^aeiou] does not match "A", whereas a
+caseful version would.
+.P
+Characters that might indicate line breaks are never treated in any special way
+when matching character classes, whatever line-ending sequence is in use, and
+whatever setting of the PCRE2_DOTALL and PCRE2_MULTILINE options is used. A
+class such as [^a] always matches one of these characters.
+.P
+The minus (hyphen) character can be used to specify a range of characters in a
+character class. For example, [d-m] matches any letter between d and m,
+inclusive. If a minus character is required in a class, it must be escaped with
+a backslash or appear in a position where it cannot be interpreted as
+indicating a range, typically as the first or last character in the class, or
+immediately after a range. For example, [b-d-z] matches letters in the range b
+to d, a hyphen character, or z.
+.P
+It is not possible to have the literal character "]" as the end character of a
+range. A pattern such as [W-]46] is interpreted as a class of two characters
+("W" and "-") followed by a literal string "46]", so it would match "W46]" or
+"-46]". However, if the "]" is escaped with a backslash it is interpreted as
+the end of range, so [W-\e]46] is interpreted as a class containing a range
+followed by two other characters. The octal or hexadecimal representation of
+"]" can also be used to end a range.
+.P
+An error is generated if a POSIX character class (see below) or an escape
+sequence other than one that defines a single character appears at a point
+where a range ending character is expected. For example, [z-\exff] is valid,
+but [A-\ed] and [A-[:digit:]] are not.
+.P
+Ranges operate in the collating sequence of character values. They can also be
+used for characters specified numerically, for example [\e000-\e037]. Ranges
+can include any characters that are valid for the current mode.
+.P
+If a range that includes letters is used when caseless matching is set, it
+matches the letters in either case. For example, [W-c] is equivalent to
+[][\e\e^_`wxyzabc], matched caselessly, and in a non-UTF mode, if character
+tables for a French locale are in use, [\exc8-\excb] matches accented E
+characters in both cases.
+.P
+The character escape sequences \ed, \eD, \eh, \eH, \ep, \eP, \es, \eS, \ev,
+\eV, \ew, and \eW may appear in a character class, and add the characters that
+they match to the class. For example, [\edABCDEF] matches any hexadecimal
+digit. In UTF modes, the PCRE2_UCP option affects the meanings of \ed, \es, \ew
+and their upper case partners, just as it does when they appear outside a
+character class, as described in the section entitled
+.\" HTML 
+.\" 
+"Generic character types"
+.\"
+above. The escape sequence \eb has a different meaning inside a character
+class; it matches the backspace character. The sequences \eB, \eN, \eR, and \eX
+are not special inside a character class. Like any other unrecognized escape
+sequences, they cause an error.
+.P
+A circumflex can conveniently be used with the upper case character types to
+specify a more restricted set of characters than the matching lower case type.
+For example, the class [^\eW_] matches any letter or digit, but not underscore,
+whereas [\ew] includes underscore. A positive character class should be read as
+"something OR something OR ..." and a negative class as "NOT something AND NOT
+something AND NOT ...".
+.P
+The only metacharacters that are recognized in character classes are backslash,
+hyphen (only where it can be interpreted as specifying a range), circumflex
+(only at the start), opening square bracket (only when it can be interpreted as
+introducing a POSIX class name, or for a special compatibility feature - see
+the next two sections), and the terminating closing square bracket. However,
+escaping other non-alphanumeric characters does no harm.
+.
+.
+.SH "POSIX CHARACTER CLASSES"
+.rs
+.sp
+Perl supports the POSIX notation for character classes. This uses names
+enclosed by [: and :] within the enclosing square brackets. PCRE2 also supports
+this notation. For example,
+.sp
+  [01[:alpha:]%]
+.sp
+matches "0", "1", any alphabetic character, or "%". The supported class names
+are:
+.sp
+  alnum    letters and digits
+  alpha    letters
+  ascii    character codes 0 - 127
+  blank    space or tab only
+  cntrl    control characters
+  digit    decimal digits (same as \ed)
+  graph    printing characters, excluding space
+  lower    lower case letters
+  print    printing characters, including space
+  punct    printing characters, excluding letters and digits and space
+  space    white space (the same as \es from PCRE2 8.34)
+  upper    upper case letters
+  word     "word" characters (same as \ew)
+  xdigit   hexadecimal digits
+.sp
+The default "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13),
+and space (32). If locale-specific matching is taking place, the list of space
+characters may be different; there may be fewer or more of them. "Space" and
+\es match the same set of characters.
+.P
+The name "word" is a Perl extension, and "blank" is a GNU extension from Perl
+5.8. Another Perl extension is negation, which is indicated by a ^ character
+after the colon. For example,
+.sp
+  [12[:^digit:]]
+.sp
+matches "1", "2", or any non-digit. PCRE2 (and Perl) also recognize the POSIX
+syntax [.ch.] and [=ch=] where "ch" is a "collating element", but these are not
+supported, and an error is given if they are encountered.
+.P
+By default, characters with values greater than 127 do not match any of the
+POSIX character classes, although this may be different for characters in the
+range 128-255 when locale-specific matching is happening. However, if the
+PCRE2_UCP option is passed to \fBpcre2_compile()\fP, some of the classes are
+changed so that Unicode character properties are used. This is achieved by
+replacing certain POSIX classes with other sequences, as follows:
+.sp
+  [:alnum:]  becomes  \ep{Xan}
+  [:alpha:]  becomes  \ep{L}
+  [:blank:]  becomes  \eh
+  [:cntrl:]  becomes  \ep{Cc}
+  [:digit:]  becomes  \ep{Nd}
+  [:lower:]  becomes  \ep{Ll}
+  [:space:]  becomes  \ep{Xps}
+  [:upper:]  becomes  \ep{Lu}
+  [:word:]   becomes  \ep{Xwd}
+.sp
+Negated versions, such as [:^alpha:] use \eP instead of \ep. Three other POSIX
+classes are handled specially in UCP mode:
+.TP 10
+[:graph:]
+This matches characters that have glyphs that mark the page when printed. In
+Unicode property terms, it matches all characters with the L, M, N, P, S, or Cf
+properties, except for:
+.sp
+  U+061C           Arabic Letter Mark
+  U+180E           Mongolian Vowel Separator
+  U+2066 - U+2069  Various "isolate"s
+.sp
+.TP 10
+[:print:]
+This matches the same characters as [:graph:] plus space characters that are
+not controls, that is, characters with the Zs property.
+.TP 10
+[:punct:]
+This matches all characters that have the Unicode P (punctuation) property,
+plus those characters with code points less than 256 that have the S (Symbol)
+property.
+.P
+The other POSIX classes are unchanged, and match only characters with code
+points less than 256.
+.
+.
+.SH "COMPATIBILITY FEATURE FOR WORD BOUNDARIES"
+.rs
+.sp
+In the POSIX.2 compliant library that was included in 4.4BSD Unix, the ugly
+syntax [[:<:]] and [[:>:]] is used for matching "start of word" and "end of
+word". PCRE2 treats these items as follows:
+.sp
+  [[:<:]]  is converted to  \eb(?=\ew)
+  [[:>:]]  is converted to  \eb(?<=\ew)
+.sp
+Only these exact character sequences are recognized. A sequence such as
+[a[:<:]b] provokes error for an unrecognized POSIX class name. This support is
+not compatible with Perl. It is provided to help migrations from other
+environments, and is best not used in any new patterns. Note that \eb matches
+at the start and the end of a word (see
+.\" HTML 
+.\" 
+"Simple assertions"
+.\"
+above), and in a Perl-style pattern the preceding or following character
+normally shows which is wanted, without the need for the assertions that are
+used above in order to give exactly the POSIX behaviour.
+.
+.
+.SH "VERTICAL BAR"
+.rs
+.sp
+Vertical bar characters are used to separate alternative patterns. For example,
+the pattern
+.sp
+  gilbert|sullivan
+.sp
+matches either "gilbert" or "sullivan". Any number of alternatives may appear,
+and an empty alternative is permitted (matching the empty string). The matching
+process tries each alternative in turn, from left to right, and the first one
+that succeeds is used. If the alternatives are within a subpattern
+.\" HTML 
+.\" 
+(defined below),
+.\"
+"succeeds" means matching the rest of the main pattern as well as the
+alternative in the subpattern.
+.
+.
+.SH "INTERNAL OPTION SETTING"
+.rs
+.sp
+The settings of the PCRE2_CASELESS, PCRE2_MULTILINE, PCRE2_DOTALL, and
+PCRE2_EXTENDED options (which are Perl-compatible) can be changed from within
+the pattern by a sequence of Perl option letters enclosed between "(?" and ")".
+The option letters are
+.sp
+  i  for PCRE2_CASELESS
+  m  for PCRE2_MULTILINE
+  s  for PCRE2_DOTALL
+  x  for PCRE2_EXTENDED
+.sp
+For example, (?im) sets caseless, multiline matching. It is also possible to
+unset these options by preceding the letter with a hyphen, and a combined
+setting and unsetting such as (?im-sx), which sets PCRE2_CASELESS and
+PCRE2_MULTILINE while unsetting PCRE2_DOTALL and PCRE2_EXTENDED, is also
+permitted. If a letter appears both before and after the hyphen, the option is
+unset. An empty options setting "(?)" is allowed. Needless to say, it has no
+effect.
+.P
+The PCRE2-specific options PCRE2_DUPNAMES and PCRE2_UNGREEDY can be changed in
+the same way as the Perl-compatible options by using the characters J and U
+respectively.
+.P
+When one of these option changes occurs at top level (that is, not inside
+subpattern parentheses), the change applies to the remainder of the pattern
+that follows. If the change is placed right at the start of a pattern, PCRE2
+extracts it into the global options (and it will therefore show up in data
+extracted by the \fBpcre2_pattern_info()\fP function).
+.P
+An option change within a subpattern (see below for a description of
+subpatterns) affects only that part of the subpattern that follows it, so
+.sp
+  (a(?i)b)c
+.sp
+matches abc and aBc and no other strings (assuming PCRE2_CASELESS is not used).
+By this means, options can be made to have different settings in different
+parts of the pattern. Any changes made in one alternative do carry on
+into subsequent branches within the same subpattern. For example,
+.sp
+  (a(?i)b|c)
+.sp
+matches "ab", "aB", "c", and "C", even though when matching "C" the first
+branch is abandoned before the option setting. This is because the effects of
+option settings happen at compile time. There would be some very weird
+behaviour otherwise.
+.P
+As a convenient shorthand, if any option settings are required at the start of
+a non-capturing subpattern (see the next section), the option letters may
+appear between the "?" and the ":". Thus the two patterns
+.sp
+  (?i:saturday|sunday)
+  (?:(?i)saturday|sunday)
+.sp
+match exactly the same set of strings.
+.P
+\fBNote:\fP There are other PCRE2-specific options that can be set by the
+application when the compiling function is called. The pattern can contain
+special leading sequences such as (*CRLF) to override what the application has
+set or what has been defaulted. Details are given in the section entitled
+.\" HTML 
+.\" 
+"Newline sequences"
+.\"
+above. There are also the (*UTF) and (*UCP) leading sequences that can be used
+to set UTF and Unicode property modes; they are equivalent to setting the
+PCRE2_UTF and PCRE2_UCP options, respectively. However, the application can set
+the PCRE2_NEVER_UTF and PCRE2_NEVER_UCP options, which lock out the use of the
+(*UTF) and (*UCP) sequences.
+.
+.
+.\" HTML 
+.SH SUBPATTERNS
+.rs
+.sp
+Subpatterns are delimited by parentheses (round brackets), which can be nested.
+Turning part of a pattern into a subpattern does two things:
+.sp
+1. It localizes a set of alternatives. For example, the pattern
+.sp
+  cat(aract|erpillar|)
+.sp
+matches "cataract", "caterpillar", or "cat". Without the parentheses, it would
+match "cataract", "erpillar" or an empty string.
+.sp
+2. It sets up the subpattern as a capturing subpattern. This means that, when
+the whole pattern matches, the portion of the subject string that matched the
+subpattern is passed back to the caller, separately from the portion that
+matched the whole pattern. (This applies only to the traditional matching
+function; the DFA matching function does not support capturing.)
+.P
+Opening parentheses are counted from left to right (starting from 1) to obtain
+numbers for the capturing subpatterns. For example, if the string "the red
+king" is matched against the pattern
+.sp
+  the ((red|white) (king|queen))
+.sp
+the captured substrings are "red king", "red", and "king", and are numbered 1,
+2, and 3, respectively.
+.P
+The fact that plain parentheses fulfil two functions is not always helpful.
+There are often times when a grouping subpattern is required without a
+capturing requirement. If an opening parenthesis is followed by a question mark
+and a colon, the subpattern does not do any capturing, and is not counted when
+computing the number of any subsequent capturing subpatterns. For example, if
+the string "the white queen" is matched against the pattern
+.sp
+  the ((?:red|white) (king|queen))
+.sp
+the captured substrings are "white queen" and "queen", and are numbered 1 and
+2. The maximum number of capturing subpatterns is 65535.
+.P
+As a convenient shorthand, if any option settings are required at the start of
+a non-capturing subpattern, the option letters may appear between the "?" and
+the ":". Thus the two patterns
+.sp
+  (?i:saturday|sunday)
+  (?:(?i)saturday|sunday)
+.sp
+match exactly the same set of strings. Because alternative branches are tried
+from left to right, and options are not reset until the end of the subpattern
+is reached, an option setting in one branch does affect subsequent branches, so
+the above patterns match "SUNDAY" as well as "Saturday".
+.
+.
+.\" HTML 
+.SH "DUPLICATE SUBPATTERN NUMBERS"
+.rs
+.sp
+Perl 5.10 introduced a feature whereby each alternative in a subpattern uses
+the same numbers for its capturing parentheses. Such a subpattern starts with
+(?| and is itself a non-capturing subpattern. For example, consider this
+pattern:
+.sp
+  (?|(Sat)ur|(Sun))day
+.sp
+Because the two alternatives are inside a (?| group, both sets of capturing
+parentheses are numbered one. Thus, when the pattern matches, you can look
+at captured substring number one, whichever alternative matched. This construct
+is useful when you want to capture part, but not all, of one of a number of
+alternatives. Inside a (?| group, parentheses are numbered as usual, but the
+number is reset at the start of each branch. The numbers of any capturing
+parentheses that follow the subpattern start after the highest number used in
+any branch. The following example is taken from the Perl documentation. The
+numbers underneath show in which buffer the captured content will be stored.
+.sp
+  # before  ---------------branch-reset----------- after
+  / ( a )  (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x
+  # 1            2         2  3        2     3     4
+.sp
+A back reference to a numbered subpattern uses the most recent value that is
+set for that number by any subpattern. The following pattern matches "abcabc"
+or "defdef":
+.sp
+  /(?|(abc)|(def))\e1/
+.sp
+In contrast, a subroutine call to a numbered subpattern always refers to the
+first one in the pattern with the given number. The following pattern matches
+"abcabc" or "defabc":
+.sp
+  /(?|(abc)|(def))(?1)/
+.sp
+If a
+.\" HTML 
+.\" 
+condition test
+.\"
+for a subpattern's having matched refers to a non-unique number, the test is
+true if any of the subpatterns of that number have matched.
+.P
+An alternative approach to using this "branch reset" feature is to use
+duplicate named subpatterns, as described in the next section.
+.
+.
+.SH "NAMED SUBPATTERNS"
+.rs
+.sp
+Identifying capturing parentheses by number is simple, but it can be very hard
+to keep track of the numbers in complicated regular expressions. Furthermore,
+if an expression is modified, the numbers may change. To help with this
+difficulty, PCRE2 supports the naming of subpatterns. This feature was not
+added to Perl until release 5.10. Python had the feature earlier, and PCRE1
+introduced it at release 4.0, using the Python syntax. PCRE2 supports both the
+Perl and the Python syntax. Perl allows identically numbered subpatterns to
+have different names, but PCRE2 does not.
+.P
+In PCRE2, a subpattern can be named in one of three ways: (?...) or
+(?'name'...) as in Perl, or (?P...) as in Python. References to capturing
+parentheses from other parts of the pattern, such as
+.\" HTML 
+.\" 
+back references,
+.\"
+.\" HTML 
+.\" 
+recursion,
+.\"
+and
+.\" HTML 
+.\" 
+conditions,
+.\"
+can be made by name as well as by number.
+.P
+Names consist of up to 32 alphanumeric characters and underscores, but must
+start with a non-digit. Named capturing parentheses are still allocated numbers
+as well as names, exactly as if the names were not present. The PCRE2 API
+provides function calls for extracting the name-to-number translation table
+from a compiled pattern. There are also convenience functions for extracting a
+captured substring by name.
+.P
+By default, a name must be unique within a pattern, but it is possible to relax
+this constraint by setting the PCRE2_DUPNAMES option at compile time.
+(Duplicate names are also always permitted for subpatterns with the same
+number, set up as described in the previous section.) Duplicate names can be
+useful for patterns where only one instance of the named parentheses can match.
+Suppose you want to match the name of a weekday, either as a 3-letter
+abbreviation or as the full name, and in both cases you want to extract the
+abbreviation. This pattern (ignoring the line breaks) does the job:
+.sp
+  (?Mon|Fri|Sun)(?:day)?|
+  (?Tue)(?:sday)?|
+  (?Wed)(?:nesday)?|
+  (?Thu)(?:rsday)?|
+  (?Sat)(?:urday)?
+.sp
+There are five capturing substrings, but only one is ever set after a match.
+(An alternative way of solving this problem is to use a "branch reset"
+subpattern, as described in the previous section.)
+.P
+The convenience functions for extracting the data by name returns the substring
+for the first (and in this example, the only) subpattern of that name that
+matched. This saves searching to find which numbered subpattern it was.
+.P
+If you make a back reference to a non-unique named subpattern from elsewhere in
+the pattern, the subpatterns to which the name refers are checked in the order
+in which they appear in the overall pattern. The first one that is set is used
+for the reference. For example, this pattern matches both "foofoo" and
+"barbar" but not "foobar" or "barfoo":
+.sp
+  (?:(?foo)|(?bar))\ek
+.sp
+.P
+If you make a subroutine call to a non-unique named subpattern, the one that
+corresponds to the first occurrence of the name is used. In the absence of
+duplicate numbers (see the previous section) this is the one with the lowest
+number.
+.P
+If you use a named reference in a condition
+test (see the
+.\"
+.\" HTML 
+.\" 
+section about conditions
+.\"
+below), either to check whether a subpattern has matched, or to check for
+recursion, all subpatterns with the same name are tested. If the condition is
+true for any one of them, the overall condition is true. This is the same
+behaviour as testing by number. For further details of the interfaces for
+handling named subpatterns, see the
+.\" HREF
+\fBpcre2api\fP
+.\"
+documentation.
+.P
+\fBWarning:\fP You cannot use different names to distinguish between two
+subpatterns with the same number because PCRE2 uses only the numbers when
+matching. For this reason, an error is given at compile time if different names
+are given to subpatterns with the same number. However, you can always give the
+same name to subpatterns with the same number, even when PCRE2_DUPNAMES is not
+set.
+.
+.
+.SH REPETITION
+.rs
+.sp
+Repetition is specified by quantifiers, which can follow any of the following
+items:
+.sp
+  a literal data character
+  the dot metacharacter
+  the \eC escape sequence
+  the \eX escape sequence
+  the \eR escape sequence
+  an escape such as \ed or \epL that matches a single character
+  a character class
+  a back reference
+  a parenthesized subpattern (including most assertions)
+  a subroutine call to a subpattern (recursive or otherwise)
+.sp
+The general repetition quantifier specifies a minimum and maximum number of
+permitted matches, by giving the two numbers in curly brackets (braces),
+separated by a comma. The numbers must be less than 65536, and the first must
+be less than or equal to the second. For example:
+.sp
+  z{2,4}
+.sp
+matches "zz", "zzz", or "zzzz". A closing brace on its own is not a special
+character. If the second number is omitted, but the comma is present, there is
+no upper limit; if the second number and the comma are both omitted, the
+quantifier specifies an exact number of required matches. Thus
+.sp
+  [aeiou]{3,}
+.sp
+matches at least 3 successive vowels, but may match many more, whereas
+.sp
+  \ed{8}
+.sp
+matches exactly 8 digits. An opening curly bracket that appears in a position
+where a quantifier is not allowed, or one that does not match the syntax of a
+quantifier, is taken as a literal character. For example, {,6} is not a
+quantifier, but a literal string of four characters.
+.P
+In UTF modes, quantifiers apply to characters rather than to individual code
+units. Thus, for example, \ex{100}{2} matches two characters, each of
+which is represented by a two-byte sequence in a UTF-8 string. Similarly,
+\eX{3} matches three Unicode extended grapheme clusters, each of which may be
+several code units long (and they may be of different lengths).
+.P
+The quantifier {0} is permitted, causing the expression to behave as if the
+previous item and the quantifier were not present. This may be useful for
+subpatterns that are referenced as
+.\" HTML 
+.\" 
+subroutines
+.\"
+from elsewhere in the pattern (but see also the section entitled
+.\" HTML 
+.\" 
+"Defining subpatterns for use by reference only"
+.\"
+below). Items other than subpatterns that have a {0} quantifier are omitted
+from the compiled pattern.
+.P
+For convenience, the three most common quantifiers have single-character
+abbreviations:
+.sp
+  *    is equivalent to {0,}
+  +    is equivalent to {1,}
+  ?    is equivalent to {0,1}
+.sp
+It is possible to construct infinite loops by following a subpattern that can
+match no characters with a quantifier that has no upper limit, for example:
+.sp
+  (a?)*
+.sp
+Earlier versions of Perl and PCRE1 used to give an error at compile time for
+such patterns. However, because there are cases where this can be useful, such
+patterns are now accepted, but if any repetition of the subpattern does in fact
+match no characters, the loop is forcibly broken.
+.P
+By default, the quantifiers are "greedy", that is, they match as much as
+possible (up to the maximum number of permitted times), without causing the
+rest of the pattern to fail. The classic example of where this gives problems
+is in trying to match comments in C programs. These appear between /* and */
+and within the comment, individual * and / characters may appear. An attempt to
+match C comments by applying the pattern
+.sp
+  /\e*.*\e*/
+.sp
+to the string
+.sp
+  /* first comment */  not comment  /* second comment */
+.sp
+fails, because it matches the entire string owing to the greediness of the .*
+item.
+.P
+If a quantifier is followed by a question mark, it ceases to be greedy, and
+instead matches the minimum number of times possible, so the pattern
+.sp
+  /\e*.*?\e*/
+.sp
+does the right thing with the C comments. The meaning of the various
+quantifiers is not otherwise changed, just the preferred number of matches.
+Do not confuse this use of question mark with its use as a quantifier in its
+own right. Because it has two uses, it can sometimes appear doubled, as in
+.sp
+  \ed??\ed
+.sp
+which matches one digit by preference, but can match two if that is the only
+way the rest of the pattern matches.
+.P
+If the PCRE2_UNGREEDY option is set (an option that is not available in Perl),
+the quantifiers are not greedy by default, but individual ones can be made
+greedy by following them with a question mark. In other words, it inverts the
+default behaviour.
+.P
+When a parenthesized subpattern is quantified with a minimum repeat count that
+is greater than 1 or with a limited maximum, more memory is required for the
+compiled pattern, in proportion to the size of the minimum or maximum.
+.P
+If a pattern starts with .* or .{0,} and the PCRE2_DOTALL option (equivalent
+to Perl's /s) is set, thus allowing the dot to match newlines, the pattern is
+implicitly anchored, because whatever follows will be tried against every
+character position in the subject string, so there is no point in retrying the
+overall match at any position after the first. PCRE2 normally treats such a
+pattern as though it were preceded by \eA.
+.P
+In cases where it is known that the subject string contains no newlines, it is
+worth setting PCRE2_DOTALL in order to obtain this optimization, or
+alternatively, using ^ to indicate anchoring explicitly.
+.P
+However, there are some cases where the optimization cannot be used. When .*
+is inside capturing parentheses that are the subject of a back reference
+elsewhere in the pattern, a match at the start may fail where a later one
+succeeds. Consider, for example:
+.sp
+  (.*)abc\e1
+.sp
+If the subject is "xyz123abc123" the match point is the fourth character. For
+this reason, such a pattern is not implicitly anchored.
+.P
+Another case where implicit anchoring is not applied is when the leading .* is
+inside an atomic group. Once again, a match at the start may fail where a later
+one succeeds. Consider this pattern:
+.sp
+  (?>.*?a)b
+.sp
+It matches "ab" in the subject "aab". The use of the backtracking control verbs
+(*PRUNE) and (*SKIP) also disable this optimization, and there is an option,
+PCRE2_NO_DOTSTAR_ANCHOR, to do so explicitly.
+.P
+When a capturing subpattern is repeated, the value captured is the substring
+that matched the final iteration. For example, after
+.sp
+  (tweedle[dume]{3}\es*)+
+.sp
+has matched "tweedledum tweedledee" the value of the captured substring is
+"tweedledee". However, if there are nested capturing subpatterns, the
+corresponding captured values may have been set in previous iterations. For
+example, after
+.sp
+  (a|(b))+
+.sp
+matches "aba" the value of the second captured substring is "b".
+.
+.
+.\" HTML 
+.SH "ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS"
+.rs
+.sp
+With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy")
+repetition, failure of what follows normally causes the repeated item to be
+re-evaluated to see if a different number of repeats allows the rest of the
+pattern to match. Sometimes it is useful to prevent this, either to change the
+nature of the match, or to cause it fail earlier than it otherwise might, when
+the author of the pattern knows there is no point in carrying on.
+.P
+Consider, for example, the pattern \ed+foo when applied to the subject line
+.sp
+  123456bar
+.sp
+After matching all 6 digits and then failing to match "foo", the normal
+action of the matcher is to try again with only 5 digits matching the \ed+
+item, and then with 4, and so on, before ultimately failing. "Atomic grouping"
+(a term taken from Jeffrey Friedl's book) provides the means for specifying
+that once a subpattern has matched, it is not to be re-evaluated in this way.
+.P
+If we use atomic grouping for the previous example, the matcher gives up
+immediately on failing to match "foo" the first time. The notation is a kind of
+special parenthesis, starting with (?> as in this example:
+.sp
+  (?>\ed+)foo
+.sp
+This kind of parenthesis "locks up" the  part of the pattern it contains once
+it has matched, and a failure further into the pattern is prevented from
+backtracking into it. Backtracking past it to previous items, however, works as
+normal.
+.P
+An alternative description is that a subpattern of this type matches exactly
+the string of characters that an identical standalone pattern would match, if
+anchored at the current point in the subject string.
+.P
+Atomic grouping subpatterns are not capturing subpatterns. Simple cases such as
+the above example can be thought of as a maximizing repeat that must swallow
+everything it can. So, while both \ed+ and \ed+? are prepared to adjust the
+number of digits they match in order to make the rest of the pattern match,
+(?>\ed+) can only match an entire sequence of digits.
+.P
+Atomic groups in general can of course contain arbitrarily complicated
+subpatterns, and can be nested. However, when the subpattern for an atomic
+group is just a single repeated item, as in the example above, a simpler
+notation, called a "possessive quantifier" can be used. This consists of an
+additional + character following a quantifier. Using this notation, the
+previous example can be rewritten as
+.sp
+  \ed++foo
+.sp
+Note that a possessive quantifier can be used with an entire group, for
+example:
+.sp
+  (abc|xyz){2,3}+
+.sp
+Possessive quantifiers are always greedy; the setting of the PCRE2_UNGREEDY
+option is ignored. They are a convenient notation for the simpler forms of
+atomic group. However, there is no difference in the meaning of a possessive
+quantifier and the equivalent atomic group, though there may be a performance
+difference; possessive quantifiers should be slightly faster.
+.P
+The possessive quantifier syntax is an extension to the Perl 5.8 syntax.
+Jeffrey Friedl originated the idea (and the name) in the first edition of his
+book. Mike McCloskey liked it, so implemented it when he built Sun's Java
+package, and PCRE1 copied it from there. It ultimately found its way into Perl
+at release 5.10.
+.P
+PCRE2 has an optimization that automatically "possessifies" certain simple
+pattern constructs. For example, the sequence A+B is treated as A++B because
+there is no point in backtracking into a sequence of A's when B must follow.
+This feature can be disabled by the PCRE2_NO_AUTOPOSSESS option, or starting
+the pattern with (*NO_AUTO_POSSESS).
+.P
+When a pattern contains an unlimited repeat inside a subpattern that can itself
+be repeated an unlimited number of times, the use of an atomic group is the
+only way to avoid some failing matches taking a very long time indeed. The
+pattern
+.sp
+  (\eD+|<\ed+>)*[!?]
+.sp
+matches an unlimited number of substrings that either consist of non-digits, or
+digits enclosed in <>, followed by either ! or ?. When it matches, it runs
+quickly. However, if it is applied to
+.sp
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+.sp
+it takes a long time before reporting failure. This is because the string can
+be divided between the internal \eD+ repeat and the external * repeat in a
+large number of ways, and all have to be tried. (The example uses [!?] rather
+than a single character at the end, because both PCRE2 and Perl have an
+optimization that allows for fast failure when a single character is used. They
+remember the last single character that is required for a match, and fail early
+if it is not present in the string.) If the pattern is changed so that it uses
+an atomic group, like this:
+.sp
+  ((?>\eD+)|<\ed+>)*[!?]
+.sp
+sequences of non-digits cannot be broken, and failure happens quickly.
+.
+.
+.\" HTML 
+.SH "BACK REFERENCES"
+.rs
+.sp
+Outside a character class, a backslash followed by a digit greater than 0 (and
+possibly further digits) is a back reference to a capturing subpattern earlier
+(that is, to its left) in the pattern, provided there have been that many
+previous capturing left parentheses.
+.P
+However, if the decimal number following the backslash is less than 8, it is
+always taken as a back reference, and causes an error only if there are not
+that many capturing left parentheses in the entire pattern. In other words, the
+parentheses that are referenced need not be to the left of the reference for
+numbers less than 8. A "forward back reference" of this type can make sense
+when a repetition is involved and the subpattern to the right has participated
+in an earlier iteration.
+.P
+It is not possible to have a numerical "forward back reference" to a subpattern
+whose number is 8 or more using this syntax because a sequence such as \e50 is
+interpreted as a character defined in octal. See the subsection entitled
+"Non-printing characters"
+.\" HTML 
+.\" 
+above
+.\"
+for further details of the handling of digits following a backslash. There is
+no such problem when named parentheses are used. A back reference to any
+subpattern is possible using named parentheses (see below).
+.P
+Another way of avoiding the ambiguity inherent in the use of digits following a
+backslash is to use the \eg escape sequence. This escape must be followed by an
+unsigned number or a negative number, optionally enclosed in braces. These
+examples are all identical:
+.sp
+  (ring), \e1
+  (ring), \eg1
+  (ring), \eg{1}
+.sp
+An unsigned number specifies an absolute reference without the ambiguity that
+is present in the older syntax. It is also useful when literal digits follow
+the reference. A negative number is a relative reference. Consider this
+example:
+.sp
+  (abc(def)ghi)\eg{-1}
+.sp
+The sequence \eg{-1} is a reference to the most recently started capturing
+subpattern before \eg, that is, is it equivalent to \e2 in this example.
+Similarly, \eg{-2} would be equivalent to \e1. The use of relative references
+can be helpful in long patterns, and also in patterns that are created by
+joining together fragments that contain references within themselves.
+.P
+A back reference matches whatever actually matched the capturing subpattern in
+the current subject string, rather than anything matching the subpattern
+itself (see
+.\" HTML 
+.\" 
+"Subpatterns as subroutines"
+.\"
+below for a way of doing that). So the pattern
+.sp
+  (sens|respons)e and \e1ibility
+.sp
+matches "sense and sensibility" and "response and responsibility", but not
+"sense and responsibility". If caseful matching is in force at the time of the
+back reference, the case of letters is relevant. For example,
+.sp
+  ((?i)rah)\es+\e1
+.sp
+matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original
+capturing subpattern is matched caselessly.
+.P
+There are several different ways of writing back references to named
+subpatterns. The .NET syntax \ek{name} and the Perl syntax \ek or
+\ek'name' are supported, as is the Python syntax (?P=name). Perl 5.10's unified
+back reference syntax, in which \eg can be used for both numeric and named
+references, is also supported. We could rewrite the above example in any of
+the following ways:
+.sp
+  (?(?i)rah)\es+\ek
+  (?'p1'(?i)rah)\es+\ek{p1}
+  (?P(?i)rah)\es+(?P=p1)
+  (?(?i)rah)\es+\eg{p1}
+.sp
+A subpattern that is referenced by name may appear in the pattern before or
+after the reference.
+.P
+There may be more than one back reference to the same subpattern. If a
+subpattern has not actually been used in a particular match, any back
+references to it always fail by default. For example, the pattern
+.sp
+  (a|(bc))\e2
+.sp
+always fails if it starts to match "a" rather than "bc". However, if the
+PCRE2_MATCH_UNSET_BACKREF option is set at compile time, a back reference to an
+unset value matches an empty string.
+.P
+Because there may be many capturing parentheses in a pattern, all digits
+following a backslash are taken as part of a potential back reference number.
+If the pattern continues with a digit character, some delimiter must be used to
+terminate the back reference. If the PCRE2_EXTENDED option is set, this can be
+white space. Otherwise, the \eg{ syntax or an empty comment (see
+.\" HTML 
+.\" 
+"Comments"
+.\"
+below) can be used.
+.
+.
+.SS "Recursive back references"
+.rs
+.sp
+A back reference that occurs inside the parentheses to which it refers fails
+when the subpattern is first used, so, for example, (a\e1) never matches.
+However, such references can be useful inside repeated subpatterns. For
+example, the pattern
+.sp
+  (a|b\e1)+
+.sp
+matches any number of "a"s and also "aba", "ababbaa" etc. At each iteration of
+the subpattern, the back reference matches the character string corresponding
+to the previous iteration. In order for this to work, the pattern must be such
+that the first iteration does not need to match the back reference. This can be
+done using alternation, as in the example above, or by a quantifier with a
+minimum of zero.
+.P
+Back references of this type cause the group that they reference to be treated
+as an
+.\" HTML 
+.\" 
+atomic group.
+.\"
+Once the whole group has been matched, a subsequent matching failure cannot
+cause backtracking into the middle of the group.
+.
+.
+.\" HTML 
+.SH ASSERTIONS
+.rs
+.sp
+An assertion is a test on the characters following or preceding the current
+matching point that does not consume any characters. The simple assertions
+coded as \eb, \eB, \eA, \eG, \eZ, \ez, ^ and $ are described
+.\" HTML 
+.\" 
+above.
+.\"
+.P
+More complicated assertions are coded as subpatterns. There are two kinds:
+those that look ahead of the current position in the subject string, and those
+that look behind it. An assertion subpattern is matched in the normal way,
+except that it does not cause the current matching position to be changed.
+.P
+Assertion subpatterns are not capturing subpatterns. If such an assertion
+contains capturing subpatterns within it, these are counted for the purposes of
+numbering the capturing subpatterns in the whole pattern. However, substring
+capturing is carried out only for positive assertions. (Perl sometimes, but not
+always, does do capturing in negative assertions.)
+.P
+For compatibility with Perl, most assertion subpatterns may be repeated; though
+it makes no sense to assert the same thing several times, the side effect of
+capturing parentheses may occasionally be useful. However, an assertion that
+forms the condition for a conditional subpattern may not be quantified. In
+practice, for other assertions, there only three cases:
+.sp
+(1) If the quantifier is {0}, the assertion is never obeyed during matching.
+However, it may contain internal capturing parenthesized groups that are called
+from elsewhere via the
+.\" HTML 
+.\" 
+subroutine mechanism.
+.\"
+.sp
+(2) If quantifier is {0,n} where n is greater than zero, it is treated as if it
+were {0,1}. At run time, the rest of the pattern match is tried with and
+without the assertion, the order depending on the greediness of the quantifier.
+.sp
+(3) If the minimum repetition is greater than zero, the quantifier is ignored.
+The assertion is obeyed just once when encountered during matching.
+.
+.
+.SS "Lookahead assertions"
+.rs
+.sp
+Lookahead assertions start with (?= for positive assertions and (?! for
+negative assertions. For example,
+.sp
+  \ew+(?=;)
+.sp
+matches a word followed by a semicolon, but does not include the semicolon in
+the match, and
+.sp
+  foo(?!bar)
+.sp
+matches any occurrence of "foo" that is not followed by "bar". Note that the
+apparently similar pattern
+.sp
+  (?!foo)bar
+.sp
+does not find an occurrence of "bar" that is preceded by something other than
+"foo"; it finds any occurrence of "bar" whatsoever, because the assertion
+(?!foo) is always true when the next three characters are "bar". A
+lookbehind assertion is needed to achieve the other effect.
+.P
+If you want to force a matching failure at some point in a pattern, the most
+convenient way to do it is with (?!) because an empty string always matches, so
+an assertion that requires there not to be an empty string must always fail.
+The backtracking control verb (*FAIL) or (*F) is a synonym for (?!).
+.
+.
+.\" HTML 
+.SS "Lookbehind assertions"
+.rs
+.sp
+Lookbehind assertions start with (?<= for positive assertions and (?
+.\" 
+(see above)
+.\"
+can be used instead of a lookbehind assertion to get round the fixed-length
+restriction.
+.P
+The implementation of lookbehind assertions is, for each alternative, to
+temporarily move the current position back by the fixed length and then try to
+match. If there are insufficient characters before the current position, the
+assertion fails.
+.P
+In a UTF mode, PCRE2 does not allow the \eC escape (which matches a single code
+unit even in a UTF mode) to appear in lookbehind assertions, because it makes
+it impossible to calculate the length of the lookbehind. The \eX and \eR
+escapes, which can match different numbers of code units, are also not
+permitted.
+.P
+.\" HTML 
+.\" 
+"Subroutine"
+.\"
+calls (see below) such as (?2) or (?&X) are permitted in lookbehinds, as long
+as the subpattern matches a fixed-length string.
+.\" HTML 
+.\" 
+Recursion,
+.\"
+however, is not supported.
+.P
+Possessive quantifiers can be used in conjunction with lookbehind assertions to
+specify efficient matching of fixed-length strings at the end of subject
+strings. Consider a simple pattern such as
+.sp
+  abcd$
+.sp
+when applied to a long string that does not match. Because matching proceeds
+from left to right, PCRE2 will look for each "a" in the subject and then see if
+what follows matches the rest of the pattern. If the pattern is specified as
+.sp
+  ^.*abcd$
+.sp
+the initial .* matches the entire string at first, but when this fails (because
+there is no following "a"), it backtracks to match all but the last character,
+then all but the last two characters, and so on. Once again the search for "a"
+covers the entire string, from right to left, so we are no better off. However,
+if the pattern is written as
+.sp
+  ^.*+(?<=abcd)
+.sp
+there can be no backtracking for the .*+ item because of the possessive
+quantifier; it can match only the entire string. The subsequent lookbehind
+assertion does a single test on the last four characters. If it fails, the
+match fails immediately. For long strings, this approach makes a significant
+difference to the processing time.
+.
+.
+.SS "Using multiple assertions"
+.rs
+.sp
+Several assertions (of any sort) may occur in succession. For example,
+.sp
+  (?<=\ed{3})(?
+.SH "CONDITIONAL SUBPATTERNS"
+.rs
+.sp
+It is possible to cause the matching process to obey a subpattern
+conditionally or to choose between two alternative subpatterns, depending on
+the result of an assertion, or whether a specific capturing subpattern has
+already been matched. The two possible forms of conditional subpattern are:
+.sp
+  (?(condition)yes-pattern)
+  (?(condition)yes-pattern|no-pattern)
+.sp
+If the condition is satisfied, the yes-pattern is used; otherwise the
+no-pattern (if present) is used. If there are more than two alternatives in the
+subpattern, a compile-time error occurs. Each of the two alternatives may
+itself contain nested subpatterns of any form, including conditional
+subpatterns; the restriction to two alternatives applies only at the level of
+the condition. This pattern fragment is an example where the alternatives are
+complex:
+.sp
+  (?(1) (A|B|C) | (D | (?(2)E|F) | E) )
+.sp
+.P
+There are five kinds of condition: references to subpatterns, references to
+recursion, two pseudo-conditions called DEFINE and VERSION, and assertions.
+.
+.
+.SS "Checking for a used subpattern by number"
+.rs
+.sp
+If the text between the parentheses consists of a sequence of digits, the
+condition is true if a capturing subpattern of that number has previously
+matched. If there is more than one capturing subpattern with the same number
+(see the earlier
+.\"
+.\" HTML 
+.\" 
+section about duplicate subpattern numbers),
+.\"
+the condition is true if any of them have matched. An alternative notation is
+to precede the digits with a plus or minus sign. In this case, the subpattern
+number is relative rather than absolute. The most recently opened parentheses
+can be referenced by (?(-1), the next most recent by (?(-2), and so on. Inside
+loops it can also make sense to refer to subsequent groups. The next
+parentheses to be opened can be referenced as (?(+1), and so on. (The value
+zero in any of these forms is not used; it provokes a compile-time error.)
+.P
+Consider the following pattern, which contains non-significant white space to
+make it more readable (assume the PCRE2_EXTENDED option) and to divide it into
+three parts for ease of discussion:
+.sp
+  ( \e( )?    [^()]+    (?(1) \e) )
+.sp
+The first part matches an optional opening parenthesis, and if that
+character is present, sets it as the first captured substring. The second part
+matches one or more characters that are not parentheses. The third part is a
+conditional subpattern that tests whether or not the first set of parentheses
+matched. If they did, that is, if subject started with an opening parenthesis,
+the condition is true, and so the yes-pattern is executed and a closing
+parenthesis is required. Otherwise, since no-pattern is not present, the
+subpattern matches nothing. In other words, this pattern matches a sequence of
+non-parentheses, optionally enclosed in parentheses.
+.P
+If you were embedding this pattern in a larger one, you could use a relative
+reference:
+.sp
+  ...other stuff... ( \e( )?    [^()]+    (?(-1) \e) ) ...
+.sp
+This makes the fragment independent of the parentheses in the larger pattern.
+.
+.
+.SS "Checking for a used subpattern by name"
+.rs
+.sp
+Perl uses the syntax (?()...) or (?('name')...) to test for a used
+subpattern by name. For compatibility with earlier versions of PCRE1, which had
+this facility before Perl, the syntax (?(name)...) is also recognized.
+.P
+Rewriting the above example to use a named subpattern gives this:
+.sp
+  (? \e( )?    [^()]+    (?() \e) )
+.sp
+If the name used in a condition of this kind is a duplicate, the test is
+applied to all subpatterns of the same name, and is true if any one of them has
+matched.
+.
+.
+.SS "Checking for pattern recursion"
+.rs
+.sp
+If the condition is the string (R), and there is no subpattern with the name R,
+the condition is true if a recursive call to the whole pattern or any
+subpattern has been made. If digits or a name preceded by ampersand follow the
+letter R, for example:
+.sp
+  (?(R3)...) or (?(R&name)...)
+.sp
+the condition is true if the most recent recursion is into a subpattern whose
+number or name is given. This condition does not check the entire recursion
+stack. If the name used in a condition of this kind is a duplicate, the test is
+applied to all subpatterns of the same name, and is true if any one of them is
+the most recent recursion.
+.P
+At "top level", all these recursion test conditions are false.
+.\" HTML 
+.\" 
+The syntax for recursive patterns
+.\"
+is described below.
+.
+.
+.\" HTML 
+.SS "Defining subpatterns for use by reference only"
+.rs
+.sp
+If the condition is the string (DEFINE), and there is no subpattern with the
+name DEFINE, the condition is always false. In this case, there may be only one
+alternative in the subpattern. It is always skipped if control reaches this
+point in the pattern; the idea of DEFINE is that it can be used to define
+subroutines that can be referenced from elsewhere. (The use of
+.\" HTML 
+.\" 
+subroutines
+.\"
+is described below.) For example, a pattern to match an IPv4 address such as
+"192.168.23.245" could be written like this (ignore white space and line
+breaks):
+.sp
+  (?(DEFINE) (? 2[0-4]\ed | 25[0-5] | 1\ed\ed | [1-9]?\ed) )
+  \eb (?&byte) (\e.(?&byte)){3} \eb
+.sp
+The first part of the pattern is a DEFINE group inside which a another group
+named "byte" is defined. This matches an individual component of an IPv4
+address (a number less than 256). When matching takes place, this part of the
+pattern is skipped because DEFINE acts like a false condition. The rest of the
+pattern uses references to the named group to match the four dot-separated
+components of an IPv4 address, insisting on a word boundary at each end.
+.
+.
+.SS "Checking the PCRE2 version"
+.rs
+.sp
+Programs that link with a PCRE2 library can check the version by calling
+\fBpcre2_config()\fP with appropriate arguments. Users of applications that do
+not have access to the underlying code cannot do this. A special "condition"
+called VERSION exists to allow such users to discover which version of PCRE2
+they are dealing with by using this condition to match a string such as
+"yesno". VERSION must be followed either by "=" or ">=" and a version number.
+For example:
+.sp
+  (?(VERSION>=10.4)yes|no)
+.sp
+This pattern matches "yes" if the PCRE2 version is greater or equal to 10.4, or
+"no" otherwise.
+.
+.
+.SS "Assertion conditions"
+.rs
+.sp
+If the condition is not in any of the above formats, it must be an assertion.
+This may be a positive or negative lookahead or lookbehind assertion. Consider
+this pattern, again containing non-significant white space, and with the two
+alternatives on the second line:
+.sp
+  (?(?=[^a-z]*[a-z])
+  \ed{2}-[a-z]{3}-\ed{2}  |  \ed{2}-\ed{2}-\ed{2} )
+.sp
+The condition is a positive lookahead assertion that matches an optional
+sequence of non-letters followed by a letter. In other words, it tests for the
+presence of at least one letter in the subject. If a letter is found, the
+subject is matched against the first alternative; otherwise it is matched
+against the second. This pattern matches strings in one of the two forms
+dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits.
+.
+.
+.\" HTML 
+.SH COMMENTS
+.rs
+.sp
+There are two ways of including comments in patterns that are processed by
+PCRE2. In both cases, the start of the comment must not be in a character
+class, nor in the middle of any other sequence of related characters such as
+(?: or a subpattern name or number. The characters that make up a comment play
+no part in the pattern matching.
+.P
+The sequence (?# marks the start of a comment that continues up to the next
+closing parenthesis. Nested parentheses are not permitted. If the
+PCRE2_EXTENDED option is set, an unescaped # character also introduces a
+comment, which in this case continues to immediately after the next newline
+character or character sequence in the pattern. Which characters are
+interpreted as newlines is controlled by an option passed to the compiling
+function or by a special sequence at the start of the pattern, as described in
+the section entitled
+.\" HTML 
+.\" 
+"Newline conventions"
+.\"
+above. Note that the end of this type of comment is a literal newline sequence
+in the pattern; escape sequences that happen to represent a newline do not
+count. For example, consider this pattern when PCRE2_EXTENDED is set, and the
+default newline convention (a single linefeed character) is in force:
+.sp
+  abc #comment \en still comment
+.sp
+On encountering the # character, \fBpcre2_compile()\fP skips along, looking for
+a newline in the pattern. The sequence \en is still literal at this stage, so
+it does not terminate the comment. Only an actual character with the code value
+0x0a (the default newline) does so.
+.
+.
+.\" HTML 
+.SH "RECURSIVE PATTERNS"
+.rs
+.sp
+Consider the problem of matching a string in parentheses, allowing for
+unlimited nested parentheses. Without the use of recursion, the best that can
+be done is to use a pattern that matches up to some fixed depth of nesting. It
+is not possible to handle an arbitrary nesting depth.
+.P
+For some time, Perl has provided a facility that allows regular expressions to
+recurse (amongst other things). It does this by interpolating Perl code in the
+expression at run time, and the code can refer to the expression itself. A Perl
+pattern using code interpolation to solve the parentheses problem can be
+created like this:
+.sp
+  $re = qr{\e( (?: (?>[^()]+) | (?p{$re}) )* \e)}x;
+.sp
+The (?p{...}) item interpolates Perl code at run time, and in this case refers
+recursively to the pattern in which it appears.
+.P
+Obviously, PCRE2 cannot support the interpolation of Perl code. Instead, it
+supports special syntax for recursion of the entire pattern, and also for
+individual subpattern recursion. After its introduction in PCRE1 and Python,
+this kind of recursion was subsequently introduced into Perl at release 5.10.
+.P
+A special item that consists of (? followed by a number greater than zero and a
+closing parenthesis is a recursive subroutine call of the subpattern of the
+given number, provided that it occurs inside that subpattern. (If not, it is a
+.\" HTML 
+.\" 
+non-recursive subroutine
+.\"
+call, which is described in the next section.) The special item (?R) or (?0) is
+a recursive call of the entire regular expression.
+.P
+This PCRE2 pattern solves the nested parentheses problem (assume the
+PCRE2_EXTENDED option is set so that white space is ignored):
+.sp
+  \e( ( [^()]++ | (?R) )* \e)
+.sp
+First it matches an opening parenthesis. Then it matches any number of
+substrings which can either be a sequence of non-parentheses, or a recursive
+match of the pattern itself (that is, a correctly parenthesized substring).
+Finally there is a closing parenthesis. Note the use of a possessive quantifier
+to avoid backtracking into sequences of non-parentheses.
+.P
+If this were part of a larger pattern, you would not want to recurse the entire
+pattern, so instead you could use this:
+.sp
+  ( \e( ( [^()]++ | (?1) )* \e) )
+.sp
+We have put the pattern into parentheses, and caused the recursion to refer to
+them instead of the whole pattern.
+.P
+In a larger pattern, keeping track of parenthesis numbers can be tricky. This
+is made easier by the use of relative references. Instead of (?1) in the
+pattern above you can write (?-2) to refer to the second most recently opened
+parentheses preceding the recursion. In other words, a negative number counts
+capturing parentheses leftwards from the point at which it is encountered.
+.P
+It is also possible to refer to subsequently opened parentheses, by writing
+references such as (?+2). However, these cannot be recursive because the
+reference is not inside the parentheses that are referenced. They are always
+.\" HTML 
+.\" 
+non-recursive subroutine
+.\"
+calls, as described in the next section.
+.P
+An alternative approach is to use named parentheses. The Perl syntax for this
+is (?&name); PCRE1's earlier syntax (?P>name) is also supported. We could
+rewrite the above example as follows:
+.sp
+  (? \e( ( [^()]++ | (?&pn) )* \e) )
+.sp
+If there is more than one subpattern with the same name, the earliest one is
+used.
+.P
+The example pattern that we have been looking at contains nested unlimited
+repeats, and so the use of a possessive quantifier for matching strings of
+non-parentheses is important when applying the pattern to strings that do not
+match. For example, when this pattern is applied to
+.sp
+  (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa()
+.sp
+it yields "no match" quickly. However, if a possessive quantifier is not used,
+the match runs for a very long time indeed because there are so many different
+ways the + and * repeats can carve up the subject, and all have to be tested
+before failure can be reported.
+.P
+At the end of a match, the values of capturing parentheses are those from
+the outermost level. If you want to obtain intermediate values, a callout
+function can be used (see below and the
+.\" HREF
+\fBpcre2callout\fP
+.\"
+documentation). If the pattern above is matched against
+.sp
+  (ab(cd)ef)
+.sp
+the value for the inner capturing parentheses (numbered 2) is "ef", which is
+the last value taken on at the top level. If a capturing subpattern is not
+matched at the top level, its final captured value is unset, even if it was
+(temporarily) set at a deeper level during the matching process.
+.P
+If there are more than 15 capturing parentheses in a pattern, PCRE2 has to
+obtain extra memory from the heap to store data during a recursion. If no
+memory can be obtained, the match fails with the PCRE2_ERROR_NOMEMORY error.
+.P
+Do not confuse the (?R) item with the condition (R), which tests for recursion.
+Consider this pattern, which matches text in angle brackets, allowing for
+arbitrary nesting. Only digits are allowed in nested brackets (that is, when
+recursing), whereas any characters are permitted at the outer level.
+.sp
+  < (?: (?(R) \ed++  | [^<>]*+) | (?R)) * >
+.sp
+In this pattern, (?(R) is the start of a conditional subpattern, with two
+different alternatives for the recursive and non-recursive cases. The (?R) item
+is the actual recursive call.
+.
+.
+.\" HTML 
+.SS "Differences in recursion processing between PCRE2 and Perl"
+.rs
+.sp
+Recursion processing in PCRE2 differs from Perl in two important ways. In PCRE2
+(like Python, but unlike Perl), a recursive subpattern call is always treated
+as an atomic group. That is, once it has matched some of the subject string, it
+is never re-entered, even if it contains untried alternatives and there is a
+subsequent matching failure. This can be illustrated by the following pattern,
+which purports to match a palindromic string that contains an odd number of
+characters (for example, "a", "aba", "abcba", "abcdcba"):
+.sp
+  ^(.|(.)(?1)\e2)$
+.sp
+The idea is that it either matches a single character, or two identical
+characters surrounding a sub-palindrome. In Perl, this pattern works; in PCRE2
+it does not if the pattern is longer than three characters. Consider the
+subject string "abcba":
+.P
+At the top level, the first character is matched, but as it is not at the end
+of the string, the first alternative fails; the second alternative is taken
+and the recursion kicks in. The recursive call to subpattern 1 successfully
+matches the next character ("b"). (Note that the beginning and end of line
+tests are not part of the recursion).
+.P
+Back at the top level, the next character ("c") is compared with what
+subpattern 2 matched, which was "a". This fails. Because the recursion is
+treated as an atomic group, there are now no backtracking points, and so the
+entire match fails. (Perl is able, at this point, to re-enter the recursion and
+try the second alternative.) However, if the pattern is written with the
+alternatives in the other order, things are different:
+.sp
+  ^((.)(?1)\e2|.)$
+.sp
+This time, the recursing alternative is tried first, and continues to recurse
+until it runs out of characters, at which point the recursion fails. But this
+time we do have another alternative to try at the higher level. That is the big
+difference: in the previous case the remaining alternative is at a deeper
+recursion level, which PCRE2 cannot use.
+.P
+To change the pattern so that it matches all palindromic strings, not just
+those with an odd number of characters, it is tempting to change the pattern to
+this:
+.sp
+  ^((.)(?1)\e2|.?)$
+.sp
+Again, this works in Perl, but not in PCRE2, and for the same reason. When a
+deeper recursion has matched a single character, it cannot be entered again in
+order to match an empty string. The solution is to separate the two cases, and
+write out the odd and even cases as alternatives at the higher level:
+.sp
+  ^(?:((.)(?1)\e2|)|((.)(?3)\e4|.))
+.sp
+If you want to match typical palindromic phrases, the pattern has to ignore all
+non-word characters, which can be done like this:
+.sp
+  ^\eW*+(?:((.)\eW*+(?1)\eW*+\e2|)|((.)\eW*+(?3)\eW*+\e4|\eW*+.\eW*+))\eW*+$
+.sp
+If run with the PCRE2_CASELESS option, this pattern matches phrases such as "A
+man, a plan, a canal: Panama!" and it works in both PCRE2 and Perl. Note the
+use of the possessive quantifier *+ to avoid backtracking into sequences of
+non-word characters. Without this, PCRE2 takes a great deal longer (ten times
+or more) to match typical phrases, and Perl takes so long that you think it has
+gone into a loop.
+.P
+\fBWARNING\fP: The palindrome-matching patterns above work only if the subject
+string does not start with a palindrome that is shorter than the entire string.
+For example, although "abcba" is correctly matched, if the subject is "ababa",
+PCRE2 finds the palindrome "aba" at the start, then fails at top level because
+the end of the string does not follow. Once again, it cannot jump back into the
+recursion to try other alternatives, so the entire match fails.
+.P
+The second way in which PCRE2 and Perl differ in their recursion processing is
+in the handling of captured values. In Perl, when a subpattern is called
+recursively or as a subpattern (see the next section), it has no access to any
+values that were captured outside the recursion, whereas in PCRE2 these values
+can be referenced. Consider this pattern:
+.sp
+  ^(.)(\e1|a(?2))
+.sp
+In PCRE2, this pattern matches "bab". The first capturing parentheses match "b",
+then in the second group, when the back reference \e1 fails to match "b", the
+second alternative matches "a" and then recurses. In the recursion, \e1 does
+now match "b" and so the whole match succeeds. In Perl, the pattern fails to
+match because inside the recursive call \e1 cannot access the externally set
+value.
+.
+.
+.\" HTML 
+.SH "SUBPATTERNS AS SUBROUTINES"
+.rs
+.sp
+If the syntax for a recursive subpattern call (either by number or by
+name) is used outside the parentheses to which it refers, it operates like a
+subroutine in a programming language. The called subpattern may be defined
+before or after the reference. A numbered reference can be absolute or
+relative, as in these examples:
+.sp
+  (...(absolute)...)...(?2)...
+  (...(relative)...)...(?-1)...
+  (...(?+1)...(relative)...
+.sp
+An earlier example pointed out that the pattern
+.sp
+  (sens|respons)e and \e1ibility
+.sp
+matches "sense and sensibility" and "response and responsibility", but not
+"sense and responsibility". If instead the pattern
+.sp
+  (sens|respons)e and (?1)ibility
+.sp
+is used, it does match "sense and responsibility" as well as the other two
+strings. Another example is given in the discussion of DEFINE above.
+.P
+All subroutine calls, whether recursive or not, are always treated as atomic
+groups. That is, once a subroutine has matched some of the subject string, it
+is never re-entered, even if it contains untried alternatives and there is a
+subsequent matching failure. Any capturing parentheses that are set during the
+subroutine call revert to their previous values afterwards.
+.P
+Processing options such as case-independence are fixed when a subpattern is
+defined, so if it is used as a subroutine, such options cannot be changed for
+different calls. For example, consider this pattern:
+.sp
+  (abc)(?i:(?-1))
+.sp
+It matches "abcabc". It does not match "abcABC" because the change of
+processing option does not affect the called subpattern.
+.
+.
+.\" HTML 
+.SH "ONIGURUMA SUBROUTINE SYNTAX"
+.rs
+.sp
+For compatibility with Oniguruma, the non-Perl syntax \eg followed by a name or
+a number enclosed either in angle brackets or single quotes, is an alternative
+syntax for referencing a subpattern as a subroutine, possibly recursively. Here
+are two of the examples used above, rewritten using this syntax:
+.sp
+  (? \e( ( (?>[^()]+) | \eg )* \e) )
+  (sens|respons)e and \eg'1'ibility
+.sp
+PCRE2 supports an extension to Oniguruma: if a number is preceded by a
+plus or a minus sign it is taken as a relative reference. For example:
+.sp
+  (abc)(?i:\eg<-1>)
+.sp
+Note that \eg{...} (Perl syntax) and \eg<...> (Oniguruma syntax) are \fInot\fP
+synonymous. The former is a back reference; the latter is a subroutine call.
+.
+.
+.SH CALLOUTS
+.rs
+.sp
+Perl has a feature whereby using the sequence (?{...}) causes arbitrary Perl
+code to be obeyed in the middle of matching a regular expression. This makes it
+possible, amongst other things, to extract different substrings that match the
+same pair of parentheses when there is a repetition.
+.P
+PCRE2 provides a similar feature, but of course it cannot obey arbitrary Perl
+code. The feature is called "callout". The caller of PCRE2 provides an external
+function by putting its entry point in a match context using the function
+\fBpcre2_set_callout()\fP, and then passing that context to \fBpcre2_match()\fP
+or \fBpcre2_dfa_match()\fP. If no match context is passed, or if the callout
+entry point is set to NULL, callouts are disabled.
+.P
+Within a regular expression, (?C) indicates a point at which the external
+function is to be called. There are two kinds of callout: those with a
+numerical argument and those with a string argument. (?C) on its own with no
+argument is treated as (?C0). A numerical argument allows the application to
+distinguish between different callouts. String arguments were added for release
+10.20 to make it possible for script languages that use PCRE2 to embed short
+scripts within patterns in a similar way to Perl.
+.P
+During matching, when PCRE2 reaches a callout point, the external function is
+called. It is provided with the number or string argument of the callout, the
+position in the pattern, and one item of data that is also set in the match
+block. The callout function may cause matching to proceed, to backtrack, or to
+fail.
+.P
+By default, PCRE2 implements a number of optimizations at matching time, and
+one side-effect is that sometimes callouts are skipped. If you need all
+possible callouts to happen, you need to set options that disable the relevant
+optimizations. More details, including a complete description of the
+programming interface to the callout function, are given in the
+.\" HREF
+\fBpcre2callout\fP
+.\"
+documentation.
+.
+.
+.SS "Callouts with numerical arguments"
+.rs
+.sp
+If you just want to have a means of identifying different callout points, put a
+number less than 256 after the letter C. For example, this pattern has two
+callout points:
+.sp
+  (?C1)abc(?C2)def
+.sp
+If the PCRE2_AUTO_CALLOUT flag is passed to \fBpcre2_compile()\fP, numerical
+callouts are automatically installed before each item in the pattern. They are
+all numbered 255. If there is a conditional group in the pattern whose
+condition is an assertion, an additional callout is inserted just before the
+condition. An explicit callout may also be set at this position, as in this
+example:
+.sp
+  (?(?C9)(?=a)abc|def)
+.sp
+Note that this applies only to assertion conditions, not to other types of
+condition.
+.
+.
+.SS "Callouts with string arguments"
+.rs
+.sp
+A delimited string may be used instead of a number as a callout argument. The
+starting delimiter must be one of ` ' " ^ % # $ { and the ending delimiter is
+the same as the start, except for {, where the ending delimiter is }. If the
+ending delimiter is needed within the string, it must be doubled. For
+example:
+.sp
+  (?C'ab ''c'' d')xyz(?C{any text})pqr
+.sp
+The doubling is removed before the string is passed to the callout function.
+.
+.
+.\" HTML 
+.SH "BACKTRACKING CONTROL"
+.rs
+.sp
+Perl 5.10 introduced a number of "Special Backtracking Control Verbs", which
+are still described in the Perl documentation as "experimental and subject to
+change or removal in a future version of Perl". It goes on to say: "Their usage
+in production code should be noted to avoid problems during upgrades." The same
+remarks apply to the PCRE2 features described in this section.
+.P
+The new verbs make use of what was previously invalid syntax: an opening
+parenthesis followed by an asterisk. They are generally of the form
+(*VERB) or (*VERB:NAME). Some may take either form, possibly behaving
+differently depending on whether or not a name is present. A name is any
+sequence of characters that does not include a closing parenthesis. The maximum
+length of name is 255 in the 8-bit library and 65535 in the 16-bit and 32-bit
+libraries. If the name is empty, that is, if the closing parenthesis
+immediately follows the colon, the effect is as if the colon were not there.
+Any number of these verbs may occur in a pattern.
+.P
+Since these verbs are specifically related to backtracking, most of them can be
+used only when the pattern is to be matched using the traditional matching
+function, because these use a backtracking algorithm. With the exception of
+(*FAIL), which behaves like a failing negative assertion, the backtracking
+control verbs cause an error if encountered by the DFA matching function.
+.P
+The behaviour of these verbs in
+.\" HTML 
+.\" 
+repeated groups,
+.\"
+.\" HTML 
+.\" 
+assertions,
+.\"
+and in
+.\" HTML 
+.\" 
+subpatterns called as subroutines
+.\"
+(whether or not recursively) is documented below.
+.
+.
+.\" HTML 
+.SS "Optimizations that affect backtracking verbs"
+.rs
+.sp
+PCRE2 contains some optimizations that are used to speed up matching by running
+some checks at the start of each match attempt. For example, it may know the
+minimum length of matching subject, or that a particular character must be
+present. When one of these optimizations bypasses the running of a match, any
+included backtracking verbs will not, of course, be processed. You can suppress
+the start-of-match optimizations by setting the PCRE2_NO_START_OPTIMIZE option
+when calling \fBpcre2_compile()\fP, or by starting the pattern with
+(*NO_START_OPT). There is more discussion of this option in the section
+entitled
+.\" HTML 
+.\" 
+"Compiling a pattern"
+.\"
+in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+documentation.
+.P
+Experiments with Perl suggest that it too has similar optimizations, sometimes
+leading to anomalous results.
+.
+.
+.SS "Verbs that act immediately"
+.rs
+.sp
+The following verbs act as soon as they are encountered. They may not be
+followed by a name.
+.sp
+   (*ACCEPT)
+.sp
+This verb causes the match to end successfully, skipping the remainder of the
+pattern. However, when it is inside a subpattern that is called as a
+subroutine, only that subpattern is ended successfully. Matching then continues
+at the outer level. If (*ACCEPT) in triggered in a positive assertion, the
+assertion succeeds; in a negative assertion, the assertion fails.
+.P
+If (*ACCEPT) is inside capturing parentheses, the data so far is captured. For
+example:
+.sp
+  A((?:A|B(*ACCEPT)|C)D)
+.sp
+This matches "AB", "AAD", or "ACD"; when it matches "AB", "B" is captured by
+the outer parentheses.
+.sp
+  (*FAIL) or (*F)
+.sp
+This verb causes a matching failure, forcing backtracking to occur. It is
+equivalent to (?!) but easier to read. The Perl documentation notes that it is
+probably useful only when combined with (?{}) or (??{}). Those are, of course,
+Perl features that are not present in PCRE2. The nearest equivalent is the
+callout feature, as for example in this pattern:
+.sp
+  a+(?C)(*FAIL)
+.sp
+A match with the string "aaaa" always fails, but the callout is taken before
+each backtrack happens (in this example, 10 times).
+.
+.
+.SS "Recording which path was taken"
+.rs
+.sp
+There is one verb whose main purpose is to track how a match was arrived at,
+though it also has a secondary use in conjunction with advancing the match
+starting point (see (*SKIP) below).
+.sp
+  (*MARK:NAME) or (*:NAME)
+.sp
+A name is always required with this verb. There may be as many instances of
+(*MARK) as you like in a pattern, and their names do not have to be unique.
+.P
+When a match succeeds, the name of the last-encountered (*MARK:NAME),
+(*PRUNE:NAME), or (*THEN:NAME) on the matching path is passed back to the
+caller as described in the section entitled
+.\" HTML 
+.\" 
+"Other information about the match"
+.\"
+in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+documentation. Here is an example of \fBpcre2test\fP output, where the "mark"
+modifier requests the retrieval and outputting of (*MARK) data:
+.sp
+    re> /X(*MARK:A)Y|X(*MARK:B)Z/mark
+  data> XY
+   0: XY
+  MK: A
+  XZ
+   0: XZ
+  MK: B
+.sp
+The (*MARK) name is tagged with "MK:" in this output, and in this example it
+indicates which of the two alternatives matched. This is a more efficient way
+of obtaining this information than putting each alternative in its own
+capturing parentheses.
+.P
+If a verb with a name is encountered in a positive assertion that is true, the
+name is recorded and passed back if it is the last-encountered. This does not
+happen for negative assertions or failing positive assertions.
+.P
+After a partial match or a failed match, the last encountered name in the
+entire match process is returned. For example:
+.sp
+    re> /X(*MARK:A)Y|X(*MARK:B)Z/mark
+  data> XP
+  No match, mark = B
+.sp
+Note that in this unanchored example the mark is retained from the match
+attempt that started at the letter "X" in the subject. Subsequent match
+attempts starting at "P" and then with an empty string do not get as far as the
+(*MARK) item, but nevertheless do not reset it.
+.P
+If you are interested in (*MARK) values after failed matches, you should
+probably set the PCRE2_NO_START_OPTIMIZE option
+.\" HTML 
+.\" 
+(see above)
+.\"
+to ensure that the match is always attempted.
+.
+.
+.SS "Verbs that act after backtracking"
+.rs
+.sp
+The following verbs do nothing when they are encountered. Matching continues
+with what follows, but if there is no subsequent match, causing a backtrack to
+the verb, a failure is forced. That is, backtracking cannot pass to the left of
+the verb. However, when one of these verbs appears inside an atomic group
+(which includes any group that is called as a subroutine) or in an assertion
+that is true, its effect is confined to that group, because once the group has
+been matched, there is never any backtracking into it. In this situation,
+backtracking has to jump to the left of the entire atomic group or assertion.
+.P
+These verbs differ in exactly what kind of failure occurs when backtracking
+reaches them. The behaviour described below is what happens when the verb is
+not in a subroutine or an assertion. Subsequent sections cover these special
+cases.
+.sp
+  (*COMMIT)
+.sp
+This verb, which may not be followed by a name, causes the whole match to fail
+outright if there is a later matching failure that causes backtracking to reach
+it. Even if the pattern is unanchored, no further attempts to find a match by
+advancing the starting point take place. If (*COMMIT) is the only backtracking
+verb that is encountered, once it has been passed \fBpcre2_match()\fP is
+committed to finding a match at the current starting point, or not at all. For
+example:
+.sp
+  a+(*COMMIT)b
+.sp
+This matches "xxaab" but not "aacaab". It can be thought of as a kind of
+dynamic anchor, or "I've started, so I must finish." The name of the most
+recently passed (*MARK) in the path is passed back when (*COMMIT) forces a
+match failure.
+.P
+If there is more than one backtracking verb in a pattern, a different one that
+follows (*COMMIT) may be triggered first, so merely passing (*COMMIT) during a
+match does not always guarantee that a match must be at this starting point.
+.P
+Note that (*COMMIT) at the start of a pattern is not the same as an anchor,
+unless PCRE2's start-of-match optimizations are turned off, as shown in this
+output from \fBpcre2test\fP:
+.sp
+    re> /(*COMMIT)abc/
+  data> xyzabc
+   0: abc
+  data>
+  re> /(*COMMIT)abc/no_start_optimize
+  data> xyzabc
+  No match
+.sp
+For the first pattern, PCRE2 knows that any match must start with "a", so the
+optimization skips along the subject to "a" before applying the pattern to the
+first set of data. The match attempt then succeeds. The second pattern disables
+the optimization that skips along to the first character. The pattern is now
+applied starting at "x", and so the (*COMMIT) causes the match to fail without
+trying any other starting points.
+.sp
+  (*PRUNE) or (*PRUNE:NAME)
+.sp
+This verb causes the match to fail at the current starting position in the
+subject if there is a later matching failure that causes backtracking to reach
+it. If the pattern is unanchored, the normal "bumpalong" advance to the next
+starting character then happens. Backtracking can occur as usual to the left of
+(*PRUNE), before it is reached, or when matching to the right of (*PRUNE), but
+if there is no match to the right, backtracking cannot cross (*PRUNE). In
+simple cases, the use of (*PRUNE) is just an alternative to an atomic group or
+possessive quantifier, but there are some uses of (*PRUNE) that cannot be
+expressed in any other way. In an anchored pattern (*PRUNE) has the same effect
+as (*COMMIT).
+.P
+The behaviour of (*PRUNE:NAME) is the not the same as (*MARK:NAME)(*PRUNE).
+It is like (*MARK:NAME) in that the name is remembered for passing back to the
+caller. However, (*SKIP:NAME) searches only for names set with (*MARK),
+ignoring those set by (*PRUNE) or (*THEN).
+.sp
+  (*SKIP)
+.sp
+This verb, when given without a name, is like (*PRUNE), except that if the
+pattern is unanchored, the "bumpalong" advance is not to the next character,
+but to the position in the subject where (*SKIP) was encountered. (*SKIP)
+signifies that whatever text was matched leading up to it cannot be part of a
+successful match. Consider:
+.sp
+  a+(*SKIP)b
+.sp
+If the subject is "aaaac...", after the first match attempt fails (starting at
+the first character in the string), the starting point skips on to start the
+next attempt at "c". Note that a possessive quantifer does not have the same
+effect as this example; although it would suppress backtracking during the
+first match attempt, the second attempt would start at the second character
+instead of skipping on to "c".
+.sp
+  (*SKIP:NAME)
+.sp
+When (*SKIP) has an associated name, its behaviour is modified. When it is
+triggered, the previous path through the pattern is searched for the most
+recent (*MARK) that has the same name. If one is found, the "bumpalong" advance
+is to the subject position that corresponds to that (*MARK) instead of to where
+(*SKIP) was encountered. If no (*MARK) with a matching name is found, the
+(*SKIP) is ignored.
+.P
+Note that (*SKIP:NAME) searches only for names set by (*MARK:NAME). It ignores
+names that are set by (*PRUNE:NAME) or (*THEN:NAME).
+.sp
+  (*THEN) or (*THEN:NAME)
+.sp
+This verb causes a skip to the next innermost alternative when backtracking
+reaches it. That is, it cancels any further backtracking within the current
+alternative. Its name comes from the observation that it can be used for a
+pattern-based if-then-else block:
+.sp
+  ( COND1 (*THEN) FOO | COND2 (*THEN) BAR | COND3 (*THEN) BAZ ) ...
+.sp
+If the COND1 pattern matches, FOO is tried (and possibly further items after
+the end of the group if FOO succeeds); on failure, the matcher skips to the
+second alternative and tries COND2, without backtracking into COND1. If that
+succeeds and BAR fails, COND3 is tried. If subsequently BAZ fails, there are no
+more alternatives, so there is a backtrack to whatever came before the entire
+group. If (*THEN) is not inside an alternation, it acts like (*PRUNE).
+.P
+The behaviour of (*THEN:NAME) is the not the same as (*MARK:NAME)(*THEN).
+It is like (*MARK:NAME) in that the name is remembered for passing back to the
+caller. However, (*SKIP:NAME) searches only for names set with (*MARK),
+ignoring those set by (*PRUNE) and (*THEN).
+.P
+A subpattern that does not contain a | character is just a part of the
+enclosing alternative; it is not a nested alternation with only one
+alternative. The effect of (*THEN) extends beyond such a subpattern to the
+enclosing alternative. Consider this pattern, where A, B, etc. are complex
+pattern fragments that do not contain any | characters at this level:
+.sp
+  A (B(*THEN)C) | D
+.sp
+If A and B are matched, but there is a failure in C, matching does not
+backtrack into A; instead it moves to the next alternative, that is, D.
+However, if the subpattern containing (*THEN) is given an alternative, it
+behaves differently:
+.sp
+  A (B(*THEN)C | (*FAIL)) | D
+.sp
+The effect of (*THEN) is now confined to the inner subpattern. After a failure
+in C, matching moves to (*FAIL), which causes the whole subpattern to fail
+because there are no more alternatives to try. In this case, matching does now
+backtrack into A.
+.P
+Note that a conditional subpattern is not considered as having two
+alternatives, because only one is ever used. In other words, the | character in
+a conditional subpattern has a different meaning. Ignoring white space,
+consider:
+.sp
+  ^.*? (?(?=a) a | b(*THEN)c )
+.sp
+If the subject is "ba", this pattern does not match. Because .*? is ungreedy,
+it initially matches zero characters. The condition (?=a) then fails, the
+character "b" is matched, but "c" is not. At this point, matching does not
+backtrack to .*? as might perhaps be expected from the presence of the |
+character. The conditional subpattern is part of the single alternative that
+comprises the whole pattern, and so the match fails. (If there was a backtrack
+into .*?, allowing it to match "b", the match would succeed.)
+.P
+The verbs just described provide four different "strengths" of control when
+subsequent matching fails. (*THEN) is the weakest, carrying on the match at the
+next alternative. (*PRUNE) comes next, failing the match at the current
+starting position, but allowing an advance to the next character (for an
+unanchored pattern). (*SKIP) is similar, except that the advance may be more
+than one character. (*COMMIT) is the strongest, causing the entire match to
+fail.
+.
+.
+.SS "More than one backtracking verb"
+.rs
+.sp
+If more than one backtracking verb is present in a pattern, the one that is
+backtracked onto first acts. For example, consider this pattern, where A, B,
+etc. are complex pattern fragments:
+.sp
+  (A(*COMMIT)B(*THEN)C|ABD)
+.sp
+If A matches but B fails, the backtrack to (*COMMIT) causes the entire match to
+fail. However, if A and B match, but C fails, the backtrack to (*THEN) causes
+the next alternative (ABD) to be tried. This behaviour is consistent, but is
+not always the same as Perl's. It means that if two or more backtracking verbs
+appear in succession, all the the last of them has no effect. Consider this
+example:
+.sp
+  ...(*COMMIT)(*PRUNE)...
+.sp
+If there is a matching failure to the right, backtracking onto (*PRUNE) causes
+it to be triggered, and its action is taken. There can never be a backtrack
+onto (*COMMIT).
+.
+.
+.\" HTML 
+.SS "Backtracking verbs in repeated groups"
+.rs
+.sp
+PCRE2 differs from Perl in its handling of backtracking verbs in repeated
+groups. For example, consider:
+.sp
+  /(a(*COMMIT)b)+ac/
+.sp
+If the subject is "abac", Perl matches, but PCRE2 fails because the (*COMMIT)
+in the second repeat of the group acts.
+.
+.
+.\" HTML 
+.SS "Backtracking verbs in assertions"
+.rs
+.sp
+(*FAIL) in an assertion has its normal effect: it forces an immediate
+backtrack.
+.P
+(*ACCEPT) in a positive assertion causes the assertion to succeed without any
+further processing. In a negative assertion, (*ACCEPT) causes the assertion to
+fail without any further processing.
+.P
+The other backtracking verbs are not treated specially if they appear in a
+positive assertion. In particular, (*THEN) skips to the next alternative in the
+innermost enclosing group that has alternations, whether or not this is within
+the assertion.
+.P
+Negative assertions are, however, different, in order to ensure that changing a
+positive assertion into a negative assertion changes its result. Backtracking
+into (*COMMIT), (*SKIP), or (*PRUNE) causes a negative assertion to be true,
+without considering any further alternative branches in the assertion.
+Backtracking into (*THEN) causes it to skip to the next enclosing alternative
+within the assertion (the normal behaviour), but if the assertion does not have
+such an alternative, (*THEN) behaves like (*PRUNE).
+.
+.
+.\" HTML 
+.SS "Backtracking verbs in subroutines"
+.rs
+.sp
+These behaviours occur whether or not the subpattern is called recursively.
+Perl's treatment of subroutines is different in some cases.
+.P
+(*FAIL) in a subpattern called as a subroutine has its normal effect: it forces
+an immediate backtrack.
+.P
+(*ACCEPT) in a subpattern called as a subroutine causes the subroutine match to
+succeed without any further processing. Matching then continues after the
+subroutine call.
+.P
+(*COMMIT), (*SKIP), and (*PRUNE) in a subpattern called as a subroutine cause
+the subroutine match to fail.
+.P
+(*THEN) skips to the next alternative in the innermost enclosing group within
+the subpattern that has alternatives. If there is no such group within the
+subpattern, (*THEN) causes the subroutine match to fail.
+.
+.
+.SH "SEE ALSO"
+.rs
+.sp
+\fBpcre2api\fP(3), \fBpcre2callout\fP(3), \fBpcre2matching\fP(3),
+\fBpcre2syntax\fP(3), \fBpcre2\fP(3).
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel
+University Computing Service
+Cambridge, England.
+.fi
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 13 June 2015
+Copyright (c) 1997-2015 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/doc/pcre2perform.3 b/pcre2-10.20/doc/pcre2perform.3
new file mode 100644
index 000000000..ec86fe73c
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2perform.3
@@ -0,0 +1,182 @@
+.TH PCRE2PERFORM 3 "02 January 2015" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH "PCRE2 PERFORMANCE"
+.rs
+.sp
+Two aspects of performance are discussed below: memory usage and processing
+time. The way you express your pattern as a regular expression can affect both
+of them.
+.
+.SH "COMPILED PATTERN MEMORY USAGE"
+.rs
+.sp
+Patterns are compiled by PCRE2 into a reasonably efficient interpretive code,
+so that most simple patterns do not use much memory. However, there is one case
+where the memory usage of a compiled pattern can be unexpectedly large. If a
+parenthesized subpattern has a quantifier with a minimum greater than 1 and/or
+a limited maximum, the whole subpattern is repeated in the compiled code. For
+example, the pattern
+.sp
+  (abc|def){2,4}
+.sp
+is compiled as if it were
+.sp
+  (abc|def)(abc|def)((abc|def)(abc|def)?)?
+.sp
+(Technical aside: It is done this way so that backtrack points within each of
+the repetitions can be independently maintained.)
+.P
+For regular expressions whose quantifiers use only small numbers, this is not
+usually a problem. However, if the numbers are large, and particularly if such
+repetitions are nested, the memory usage can become an embarrassment. For
+example, the very simple pattern
+.sp
+  ((ab){1,1000}c){1,3}
+.sp
+uses 51K bytes when compiled using the 8-bit library. When PCRE2 is compiled
+with its default internal pointer size of two bytes, the size limit on a
+compiled pattern is 64K code units in the 8-bit and 16-bit libraries, and this
+is reached with the above pattern if the outer repetition is increased from 3
+to 4. PCRE2 can be compiled to use larger internal pointers and thus handle
+larger compiled patterns, but it is better to try to rewrite your pattern to
+use less memory if you can.
+.P
+One way of reducing the memory usage for such patterns is to make use of
+PCRE2's
+.\" HTML 
+.\" 
+"subroutine"
+.\"
+facility. Re-writing the above pattern as
+.sp
+  ((ab)(?2){0,999}c)(?1){0,2}
+.sp
+reduces the memory requirements to 18K, and indeed it remains under 20K even
+with the outer repetition increased to 100. However, this pattern is not
+exactly equivalent, because the "subroutine" calls are treated as
+.\" HTML 
+.\" 
+atomic groups
+.\"
+into which there can be no backtracking if there is a subsequent matching
+failure. Therefore, PCRE2 cannot do this kind of rewriting automatically.
+Furthermore, there is a noticeable loss of speed when executing the modified
+pattern. Nevertheless, if the atomic grouping is not a problem and the loss of
+speed is acceptable, this kind of rewriting will allow you to process patterns
+that PCRE2 cannot otherwise handle.
+.
+.
+.SH "STACK USAGE AT RUN TIME"
+.rs
+.sp
+When \fBpcre2_match()\fP is used for matching, certain kinds of pattern can
+cause it to use large amounts of the process stack. In some environments the
+default process stack is quite small, and if it runs out the result is often
+SIGSEGV. Rewriting your pattern can often help. The
+.\" HREF
+\fBpcre2stack\fP
+.\"
+documentation discusses this issue in detail.
+.
+.
+.SH "PROCESSING TIME"
+.rs
+.sp
+Certain items in regular expression patterns are processed more efficiently
+than others. It is more efficient to use a character class like [aeiou] than a
+set of single-character alternatives such as (a|e|i|o|u). In general, the
+simplest construction that provides the required behaviour is usually the most
+efficient. Jeffrey Friedl's book contains a lot of useful general discussion
+about optimizing regular expressions for efficient performance. This document
+contains a few observations about PCRE2.
+.P
+Using Unicode character properties (the \ep, \eP, and \eX escapes) is slow,
+because PCRE2 has to use a multi-stage table lookup whenever it needs a
+character's property. If you can find an alternative pattern that does not use
+character properties, it will probably be faster.
+.P
+By default, the escape sequences \eb, \ed, \es, and \ew, and the POSIX
+character classes such as [:alpha:] do not use Unicode properties, partly for
+backwards compatibility, and partly for performance reasons. However, you can
+set the PCRE2_UCP option or start the pattern with (*UCP) if you want Unicode
+character properties to be used. This can double the matching time for items
+such as \ed, when matched with \fBpcre2_match()\fP; the performance loss is
+less with a DFA matching function, and in both cases there is not much
+difference for \eb.
+.P
+When a pattern begins with .* not in atomic parentheses, nor in parentheses
+that are the subject of a backreference, and the PCRE2_DOTALL option is set,
+the pattern is implicitly anchored by PCRE2, since it can match only at the
+start of a subject string. If the pattern has multiple top-level branches, they
+must all be anchorable. The optimization can be disabled by the
+PCRE2_NO_DOTSTAR_ANCHOR option, and is automatically disabled if the pattern
+contains (*PRUNE) or (*SKIP).
+.P
+If PCRE2_DOTALL is not set, PCRE2 cannot make this optimization, because the
+dot metacharacter does not then match a newline, and if the subject string
+contains newlines, the pattern may match from the character immediately
+following one of them instead of from the very start. For example, the pattern
+.sp
+  .*second
+.sp
+matches the subject "first\enand second" (where \en stands for a newline
+character), with the match starting at the seventh character. In order to do
+this, PCRE2 has to retry the match starting after every newline in the subject.
+.P
+If you are using such a pattern with subject strings that do not contain
+newlines, the best performance is obtained by setting PCRE2_DOTALL, or starting
+the pattern with ^.* or ^.*? to indicate explicit anchoring. That saves PCRE2
+from having to scan along the subject looking for a newline to restart at.
+.P
+Beware of patterns that contain nested indefinite repeats. These can take a
+long time to run when applied to a string that does not match. Consider the
+pattern fragment
+.sp
+  ^(a+)*
+.sp
+This can match "aaaa" in 16 different ways, and this number increases very
+rapidly as the string gets longer. (The * repeat can match 0, 1, 2, 3, or 4
+times, and for each of those cases other than 0 or 4, the + repeats can match
+different numbers of times.) When the remainder of the pattern is such that the
+entire match is going to fail, PCRE2 has in principle to try every possible
+variation, and this can take an extremely long time, even for relatively short
+strings.
+.P
+An optimization catches some of the more simple cases such as
+.sp
+  (a+)*b
+.sp
+where a literal character follows. Before embarking on the standard matching
+procedure, PCRE2 checks that there is a "b" later in the subject string, and if
+there is not, it fails the match immediately. However, when there is no
+following literal this optimization cannot be used. You can see the difference
+by comparing the behaviour of
+.sp
+  (a+)*\ed
+.sp
+with the pattern above. The former gives a failure almost instantly when
+applied to a whole line of "a" characters, whereas the latter takes an
+appreciable time with strings longer than about 20 characters.
+.P
+In many cases, the solution to this kind of performance issue is to use an
+atomic group or a possessive quantifier.
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel
+University Computing Service
+Cambridge, England.
+.fi
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 02 January 2015
+Copyright (c) 1997-2015 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/doc/pcre2posix.3 b/pcre2-10.20/doc/pcre2posix.3
new file mode 100644
index 000000000..b6669752f
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2posix.3
@@ -0,0 +1,268 @@
+.TH PCRE2POSIX 3 "20 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH "SYNOPSIS"
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int regcomp(regex_t *\fIpreg\fP, const char *\fIpattern\fP,
+.B "     int \fIcflags\fP);"
+.sp
+.B int regexec(const regex_t *\fIpreg\fP, const char *\fIstring\fP,
+.B "     size_t \fInmatch\fP, regmatch_t \fIpmatch\fP[], int \fIeflags\fP);"
+.sp
+.B "size_t regerror(int \fIerrcode\fP, const regex_t *\fIpreg\fP,"
+.B "     char *\fIerrbuf\fP, size_t \fIerrbuf_size\fP);"
+.sp
+.B void regfree(regex_t *\fIpreg\fP);
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This set of functions provides a POSIX-style API for the PCRE2 regular
+expression 8-bit library. See the
+.\" HREF
+\fBpcre2api\fP
+.\"
+documentation for a description of PCRE2's native API, which contains much
+additional functionality. There is no POSIX-style wrapper for PCRE2's 16-bit
+and 32-bit libraries.
+.P
+The functions described here are just wrapper functions that ultimately call
+the PCRE2 native API. Their prototypes are defined in the \fBpcre2posix.h\fP
+header file, and on Unix systems the library itself is called
+\fBlibpcre2-posix.a\fP, so can be accessed by adding \fB-lpcre2-posix\fP to the
+command for linking an application that uses them. Because the POSIX functions
+call the native ones, it is also necessary to add \fB-lpcre2-8\fP.
+.P
+Those POSIX option bits that can reasonably be mapped to PCRE2 native options
+have been implemented. In addition, the option REG_EXTENDED is defined with the
+value zero. This has no effect, but since programs that are written to the
+POSIX interface often use it, this makes it easier to slot in PCRE2 as a
+replacement library. Other POSIX options are not even defined.
+.P
+There are also some other options that are not defined by POSIX. These have
+been added at the request of users who want to make use of certain
+PCRE2-specific features via the POSIX calling interface.
+.P
+When PCRE2 is called via these functions, it is only the API that is POSIX-like
+in style. The syntax and semantics of the regular expressions themselves are
+still those of Perl, subject to the setting of various PCRE2 options, as
+described below. "POSIX-like in style" means that the API approximates to the
+POSIX definition; it is not fully POSIX-compatible, and in multi-unit encoding
+domains it is probably even less compatible.
+.P
+The header for these functions is supplied as \fBpcre2posix.h\fP to avoid any
+potential clash with other POSIX libraries. It can, of course, be renamed or
+aliased as \fBregex.h\fP, which is the "correct" name. It provides two
+structure types, \fIregex_t\fP for compiled internal forms, and
+\fIregmatch_t\fP for returning captured substrings. It also defines some
+constants whose names start with "REG_"; these are used for setting options and
+identifying error codes.
+.
+.
+.SH "COMPILING A PATTERN"
+.rs
+.sp
+The function \fBregcomp()\fP is called to compile a pattern into an
+internal form. The pattern is a C string terminated by a binary zero, and
+is passed in the argument \fIpattern\fP. The \fIpreg\fP argument is a pointer
+to a \fBregex_t\fP structure that is used as a base for storing information
+about the compiled regular expression.
+.P
+The argument \fIcflags\fP is either zero, or contains one or more of the bits
+defined by the following macros:
+.sp
+  REG_DOTALL
+.sp
+The PCRE2_DOTALL option is set when the regular expression is passed for
+compilation to the native function. Note that REG_DOTALL is not part of the
+POSIX standard.
+.sp
+  REG_ICASE
+.sp
+The PCRE2_CASELESS option is set when the regular expression is passed for
+compilation to the native function.
+.sp
+  REG_NEWLINE
+.sp
+The PCRE2_MULTILINE option is set when the regular expression is passed for
+compilation to the native function. Note that this does \fInot\fP mimic the
+defined POSIX behaviour for REG_NEWLINE (see the following section).
+.sp
+  REG_NOSUB
+.sp
+The PCRE2_NO_AUTO_CAPTURE option is set when the regular expression is passed
+for compilation to the native function. In addition, when a pattern that is
+compiled with this flag is passed to \fBregexec()\fP for matching, the
+\fInmatch\fP and \fIpmatch\fP arguments are ignored, and no captured strings
+are returned.
+.sp
+  REG_UCP
+.sp
+The PCRE2_UCP option is set when the regular expression is passed for
+compilation to the native function. This causes PCRE2 to use Unicode properties
+when matchine \ed, \ew, etc., instead of just recognizing ASCII values. Note
+that REG_UCP is not part of the POSIX standard.
+.sp
+  REG_UNGREEDY
+.sp
+The PCRE2_UNGREEDY option is set when the regular expression is passed for
+compilation to the native function. Note that REG_UNGREEDY is not part of the
+POSIX standard.
+.sp
+  REG_UTF
+.sp
+The PCRE2_UTF option is set when the regular expression is passed for
+compilation to the native function. This causes the pattern itself and all data
+strings used for matching it to be treated as UTF-8 strings. Note that REG_UTF
+is not part of the POSIX standard.
+.P
+In the absence of these flags, no options are passed to the native function.
+This means the the regex is compiled with PCRE2 default semantics. In
+particular, the way it handles newline characters in the subject string is the
+Perl way, not the POSIX way. Note that setting PCRE2_MULTILINE has only
+\fIsome\fP of the effects specified for REG_NEWLINE. It does not affect the way
+newlines are matched by the dot metacharacter (they are not) or by a negative
+class such as [^a] (they are).
+.P
+The yield of \fBregcomp()\fP is zero on success, and non-zero otherwise. The
+\fIpreg\fP structure is filled in on success, and one member of the structure
+is public: \fIre_nsub\fP contains the number of capturing subpatterns in
+the regular expression. Various error codes are defined in the header file.
+.P
+NOTE: If the yield of \fBregcomp()\fP is non-zero, you must not attempt to
+use the contents of the \fIpreg\fP structure. If, for example, you pass it to
+\fBregexec()\fP, the result is undefined and your program is likely to crash.
+.
+.
+.SH "MATCHING NEWLINE CHARACTERS"
+.rs
+.sp
+This area is not simple, because POSIX and Perl take different views of things.
+It is not possible to get PCRE2 to obey POSIX semantics, but then PCRE2 was
+never intended to be a POSIX engine. The following table lists the different
+possibilities for matching newline characters in PCRE2:
+.sp
+                          Default   Change with
+.sp
+  . matches newline          no     PCRE2_DOTALL
+  newline matches [^a]       yes    not changeable
+  $ matches \en at end        yes    PCRE2_DOLLAR_ENDONLY
+  $ matches \en in middle     no     PCRE2_MULTILINE
+  ^ matches \en in middle     no     PCRE2_MULTILINE
+.sp
+This is the equivalent table for POSIX:
+.sp
+                          Default   Change with
+.sp
+  . matches newline          yes    REG_NEWLINE
+  newline matches [^a]       yes    REG_NEWLINE
+  $ matches \en at end        no     REG_NEWLINE
+  $ matches \en in middle     no     REG_NEWLINE
+  ^ matches \en in middle     no     REG_NEWLINE
+.sp
+PCRE2's behaviour is the same as Perl's, except that there is no equivalent for
+PCRE2_DOLLAR_ENDONLY in Perl. In both PCRE2 and Perl, there is no way to stop
+newline from matching [^a].
+.P
+The default POSIX newline handling can be obtained by setting PCRE2_DOTALL and
+PCRE2_DOLLAR_ENDONLY, but there is no way to make PCRE2 behave exactly as for
+the REG_NEWLINE action.
+.
+.
+.SH "MATCHING A PATTERN"
+.rs
+.sp
+The function \fBregexec()\fP is called to match a compiled pattern \fIpreg\fP
+against a given \fIstring\fP, which is by default terminated by a zero byte
+(but see REG_STARTEND below), subject to the options in \fIeflags\fP. These can
+be:
+.sp
+  REG_NOTBOL
+.sp
+The PCRE2_NOTBOL option is set when calling the underlying PCRE2 matching
+function.
+.sp
+  REG_NOTEMPTY
+.sp
+The PCRE2_NOTEMPTY option is set when calling the underlying PCRE2 matching
+function. Note that REG_NOTEMPTY is not part of the POSIX standard. However,
+setting this option can give more POSIX-like behaviour in some situations.
+.sp
+  REG_NOTEOL
+.sp
+The PCRE2_NOTEOL option is set when calling the underlying PCRE2 matching
+function.
+.sp
+  REG_STARTEND
+.sp
+The string is considered to start at \fIstring\fP + \fIpmatch[0].rm_so\fP and
+to have a terminating NUL located at \fIstring\fP + \fIpmatch[0].rm_eo\fP
+(there need not actually be a NUL at that location), regardless of the value of
+\fInmatch\fP. This is a BSD extension, compatible with but not specified by
+IEEE Standard 1003.2 (POSIX.2), and should be used with caution in software
+intended to be portable to other systems. Note that a non-zero \fIrm_so\fP does
+not imply REG_NOTBOL; REG_STARTEND affects only the location of the string, not
+how it is matched.
+.P
+If the pattern was compiled with the REG_NOSUB flag, no data about any matched
+strings is returned. The \fInmatch\fP and \fIpmatch\fP arguments of
+\fBregexec()\fP are ignored.
+.P
+If the value of \fInmatch\fP is zero, or if the value \fIpmatch\fP is NULL,
+no data about any matched strings is returned.
+.P
+Otherwise,the portion of the string that was matched, and also any captured
+substrings, are returned via the \fIpmatch\fP argument, which points to an
+array of \fInmatch\fP structures of type \fIregmatch_t\fP, containing the
+members \fIrm_so\fP and \fIrm_eo\fP. These contain the byte offset to the first
+character of each substring and the offset to the first character after the end
+of each substring, respectively. The 0th element of the vector relates to the
+entire portion of \fIstring\fP that was matched; subsequent elements relate to
+the capturing subpatterns of the regular expression. Unused entries in the
+array have both structure members set to -1.
+.P
+A successful match yields a zero return; various error codes are defined in the
+header file, of which REG_NOMATCH is the "expected" failure code.
+.
+.
+.SH "ERROR MESSAGES"
+.rs
+.sp
+The \fBregerror()\fP function maps a non-zero errorcode from either
+\fBregcomp()\fP or \fBregexec()\fP to a printable message. If \fIpreg\fP is not
+NULL, the error should have arisen from the use of that structure. A message
+terminated by a binary zero is placed in \fIerrbuf\fP. The length of the
+message, including the zero, is limited to \fIerrbuf_size\fP. The yield of the
+function is the size of buffer needed to hold the whole message.
+.
+.
+.SH MEMORY USAGE
+.rs
+.sp
+Compiling a regular expression causes memory to be allocated and associated
+with the \fIpreg\fP structure. The function \fBregfree()\fP frees all such
+memory, after which \fIpreg\fP may no longer be used as a compiled expression.
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel
+University Computing Service
+Cambridge, England.
+.fi
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 20 October 2014
+Copyright (c) 1997-2014 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/doc/pcre2sample.3 b/pcre2-10.20/doc/pcre2sample.3
new file mode 100644
index 000000000..7b469356b
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2sample.3
@@ -0,0 +1,94 @@
+.TH PCRE2SAMPLE 3 "20 October 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH "PCRE2 SAMPLE PROGRAM"
+.rs
+.sp
+A simple, complete demonstration program to get you started with using PCRE2 is
+supplied in the file \fIpcre2demo.c\fP in the \fBsrc\fP directory in the PCRE2
+distribution. A listing of this program is given in the
+.\" HREF
+\fBpcre2demo\fP
+.\"
+documentation. If you do not have a copy of the PCRE2 distribution, you can
+save this listing to re-create the contents of \fIpcre2demo.c\fP.
+.P
+The demonstration program, which uses the PCRE2 8-bit library, compiles the
+regular expression that is its first argument, and matches it against the
+subject string in its second argument. No PCRE2 options are set, and default
+character tables are used. If matching succeeds, the program outputs the
+portion of the subject that matched, together with the contents of any captured
+substrings.
+.P
+If the -g option is given on the command line, the program then goes on to
+check for further matches of the same regular expression in the same subject
+string. The logic is a little bit tricky because of the possibility of matching
+an empty string. Comments in the code explain what is going on.
+.P
+If PCRE2 is installed in the standard include and library directories for your
+operating system, you should be able to compile the demonstration program using
+this command:
+.sp
+  gcc -o pcre2demo pcre2demo.c -lpcre2-8
+.sp
+If PCRE2 is installed elsewhere, you may need to add additional options to the
+command line. For example, on a Unix-like system that has PCRE2 installed in
+\fI/usr/local\fP, you can compile the demonstration program using a command
+like this:
+.sp
+.\" JOINSH
+  gcc -o pcre2demo -I/usr/local/include pcre2demo.c \e
+      -L/usr/local/lib -lpcre2-8
+.sp
+.P
+Once you have compiled and linked the demonstration program, you can run simple
+tests like this:
+.sp
+  ./pcre2demo 'cat|dog' 'the cat sat on the mat'
+  ./pcre2demo -g 'cat|dog' 'the dog sat on the cat'
+.sp
+Note that there is a much more comprehensive test program, called
+.\" HREF
+\fBpcre2test\fP,
+.\"
+which supports many more facilities for testing regular expressions using the
+PCRE2 libraries. The
+.\" HREF
+\fBpcre2demo\fP
+.\"
+program is provided as a simple coding example.
+.P
+If you try to run
+.\" HREF
+\fBpcre2demo\fP
+.\"
+when PCRE2 is not installed in the standard library directory, you may get an
+error like this on some operating systems (e.g. Solaris):
+.sp
+  ld.so.1: a.out: fatal: libpcre2.so.0: open failed: No such file or directory
+.sp
+This is caused by the way shared library support works on those systems. You
+need to add
+.sp
+  -R/usr/local/lib
+.sp
+(for example) to the compile command to get round this problem.
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel
+University Computing Service
+Cambridge, England.
+.fi
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 20 October 2014
+Copyright (c) 1997-2014 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/doc/pcre2serialize.3 b/pcre2-10.20/doc/pcre2serialize.3
new file mode 100644
index 000000000..a76272b70
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2serialize.3
@@ -0,0 +1,170 @@
+.TH PCRE2SERIALIZE 3 "20 January 2015" "PCRE2 10.10"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH "SAVING AND RE-USING PRECOMPILED PCRE2 PATTERNS"
+.rs
+.sp
+.nf
+.B int32_t pcre2_serialize_decode(pcre2_code **\fIcodes\fP,
+.B "  int32_t \fInumber_of_codes\fP, const uint32_t *\fIbytes\fP,"
+.B "  pcre2_general_context *\fIgcontext\fP);"
+.sp
+.B int32_t pcre2_serialize_encode(pcre2_code **\fIcodes\fP,
+.B "  int32_t \fInumber_of_codes\fP, uint32_t **\fIserialized_bytes\fP,"
+.B "  PCRE2_SIZE *\fIserialized_size\fP, pcre2_general_context *\fIgcontext\fP);"
+.sp
+.B void pcre2_serialize_free(uint8_t *\fIbytes\fP);
+.sp
+.B int32_t pcre2_serialize_get_number_of_codes(const uint8_t *\fIbytes\fP);
+.fi
+.sp
+If you are running an application that uses a large number of regular
+expression patterns, it may be useful to store them in a precompiled form
+instead of having to compile them every time the application is run. However,
+if you are using the just-in-time optimization feature, it is not possible to
+save and reload the JIT data, because it is position-dependent. In addition,
+the host on which the patterns are reloaded must be running the same version of
+PCRE2, with the same code unit width, and must also have the same endianness,
+pointer width and PCRE2_SIZE type. For example, patterns compiled on a 32-bit
+system using PCRE2's 16-bit library cannot be reloaded on a 64-bit system, nor
+can they be reloaded using the 8-bit library.
+.
+.
+.SH "SAVING COMPILED PATTERNS"
+.rs
+.sp
+Before compiled patterns can be saved they must be serialized, that is,
+converted to a stream of bytes. A single byte stream may contain any number of
+compiled patterns, but they must all use the same character tables. A single
+copy of the tables is included in the byte stream (its size is 1088 bytes). For
+more details of character tables, see the
+.\" HTML 
+.\" 
+section on locale support
+.\"
+in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+documentation.
+.P
+The function \fBpcre2_serialize_encode()\fP creates a serialized byte stream
+from a list of compiled patterns. Its first two arguments specify the list,
+being a pointer to a vector of pointers to compiled patterns, and the length of
+the vector. The third and fourth arguments point to variables which are set to
+point to the created byte stream and its length, respectively. The final
+argument is a pointer to a general context, which can be used to specify custom
+memory mangagement functions. If this argument is NULL, \fBmalloc()\fP is used
+to obtain memory for the byte stream. The yield of the function is the number
+of serialized patterns, or one of the following negative error codes:
+.sp
+  PCRE2_ERROR_BADDATA      the number of patterns is zero or less
+  PCRE2_ERROR_BADMAGIC     mismatch of id bytes in one of the patterns
+  PCRE2_ERROR_MEMORY       memory allocation failed
+  PCRE2_ERROR_MIXEDTABLES  the patterns do not all use the same tables
+  PCRE2_ERROR_NULL         the 1st, 3rd, or 4th argument is NULL
+.sp
+PCRE2_ERROR_BADMAGIC means either that a pattern's code has been corrupted, or
+that a slot in the vector does not point to a compiled pattern.
+.P
+Once a set of patterns has been serialized you can save the data in any
+appropriate manner. Here is sample code that compiles two patterns and writes
+them to a file. It assumes that the variable \fIfd\fP refers to a file that is
+open for output. The error checking that should be present in a real
+application has been omitted for simplicity.
+.sp
+  int errorcode;
+  uint8_t *bytes;
+  PCRE2_SIZE erroroffset;
+  PCRE2_SIZE bytescount;
+  pcre2_code *list_of_codes[2];
+  list_of_codes[0] = pcre2_compile("first pattern",
+    PCRE2_ZERO_TERMINATED, 0, &errorcode, &erroroffset, NULL);
+  list_of_codes[1] = pcre2_compile("second pattern",
+    PCRE2_ZERO_TERMINATED, 0, &errorcode, &erroroffset, NULL);
+  errorcode = pcre2_serialize_encode(list_of_codes, 2, &bytes,
+    &bytescount, NULL);
+  errorcode = fwrite(bytes, 1, bytescount, fd);
+.sp
+Note that the serialized data is binary data that may contain any of the 256
+possible byte values. On systems that make a distinction between binary and
+non-binary data, be sure that the file is opened for binary output.
+.P
+Serializing a set of patterns leaves the original data untouched, so they can
+still be used for matching. Their memory must eventually be freed in the usual
+way by calling \fBpcre2_code_free()\fP. When you have finished with the byte
+stream, it too must be freed by calling \fBpcre2_serialize_free()\fP.
+.
+.
+.SH "RE-USING PRECOMPILED PATTERNS"
+.rs
+.sp
+In order to re-use a set of saved patterns you must first make the serialized
+byte stream available in main memory (for example, by reading from a file). The
+management of this memory block is up to the application. You can use the
+\fBpcre2_serialize_get_number_of_codes()\fP function to find out how many
+compiled patterns are in the serialized data without actually decoding the
+patterns:
+.sp
+  uint8_t *bytes = ;
+  int32_t number_of_codes = pcre2_serialize_get_number_of_codes(bytes);
+.sp
+The \fBpcre2_serialize_decode()\fP function reads a byte stream and recreates
+the compiled patterns in new memory blocks, setting pointers to them in a
+vector. The first two arguments are a pointer to a suitable vector and its
+length, and the third argument points to a byte stream. The final argument is a
+pointer to a general context, which can be used to specify custom memory
+mangagement functions for the decoded patterns. If this argument is NULL,
+\fBmalloc()\fP and \fBfree()\fP are used. After deserialization, the byte
+stream is no longer needed and can be discarded.
+.sp
+  int32_t number_of_codes;
+  pcre2_code *list_of_codes[2];
+  uint8_t *bytes = ;
+  int32_t number_of_codes =
+    pcre2_serialize_decode(list_of_codes, 2, bytes, NULL);
+.sp
+If the vector is not large enough for all the patterns in the byte stream, it
+is filled with those that fit, and the remainder are ignored. The yield of the
+function is the number of decoded patterns, or one of the following negative
+error codes:
+.sp
+  PCRE2_ERROR_BADDATA   second argument is zero or less
+  PCRE2_ERROR_BADMAGIC  mismatch of id bytes in the data
+  PCRE2_ERROR_BADMODE   mismatch of variable unit size or PCRE2 version
+  PCRE2_ERROR_MEMORY    memory allocation failed
+  PCRE2_ERROR_NULL      first or third argument is NULL
+.sp
+PCRE2_ERROR_BADMAGIC may mean that the data is corrupt, or that it was compiled
+on a system with different endianness.
+.P
+Decoded patterns can be used for matching in the usual way, and must be freed
+by calling \fBpcre2_code_free()\fP as normal. A single copy of the character
+tables is used by all the decoded patterns. A reference count is used to
+arrange for its memory to be automatically freed when the last pattern is
+freed.
+.P
+If a pattern was processed by \fBpcre2_jit_compile()\fP before being
+serialized, the JIT data is discarded and so is no longer available after a
+save/restore cycle. You can, however, process a restored pattern with
+\fBpcre2_jit_compile()\fP if you wish.
+.
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel
+University Computing Service
+Cambridge, England.
+.fi
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 20 January 2015
+Copyright (c) 1997-2015 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/doc/pcre2stack.3 b/pcre2-10.20/doc/pcre2stack.3
new file mode 100644
index 000000000..871126353
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2stack.3
@@ -0,0 +1,202 @@
+.TH PCRE2STACK 3 "21 November 2014" "PCRE2 10.00"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH "PCRE2 DISCUSSION OF STACK USAGE"
+.rs
+.sp
+When you call \fBpcre2_match()\fP, it makes use of an internal function called
+\fBmatch()\fP. This calls itself recursively at branch points in the pattern,
+in order to remember the state of the match so that it can back up and try a
+different alternative after a failure. As matching proceeds deeper and deeper
+into the tree of possibilities, the recursion depth increases. The
+\fBmatch()\fP function is also called in other circumstances, for example,
+whenever a parenthesized sub-pattern is entered, and in certain cases of
+repetition.
+.P
+Not all calls of \fBmatch()\fP increase the recursion depth; for an item such
+as a* it may be called several times at the same level, after matching
+different numbers of a's. Furthermore, in a number of cases where the result of
+the recursive call would immediately be passed back as the result of the
+current call (a "tail recursion"), the function is just restarted instead.
+.P
+Each time the internal \fBmatch()\fP function is called recursively, it uses
+memory from the process stack. For certain kinds of pattern and data, very
+large amounts of stack may be needed, despite the recognition of "tail
+recursion". Note that if PCRE2 is compiled with the -fsanitize=address option
+of the GCC compiler, the stack requirements are greatly increased.
+.P
+The above comments apply when \fBpcre2_match()\fP is run in its normal
+interpretive manner. If the compiled pattern was processed by
+\fBpcre2_jit_compile()\fP, and just-in-time compiling was successful, and the
+options passed to \fBpcre2_match()\fP were not incompatible, the matching
+process uses the JIT-compiled code instead of the \fBmatch()\fP function. In
+this case, the memory requirements are handled entirely differently. See the
+.\" HREF
+\fBpcre2jit\fP
+.\"
+documentation for details.
+.P
+The \fBpcre2_dfa_match()\fP function operates in a different way to
+\fBpcre2_match()\fP, and uses recursion only when there is a regular expression
+recursion or subroutine call in the pattern. This includes the processing of
+assertion and "once-only" subpatterns, which are handled like subroutine calls.
+Normally, these are never very deep, and the limit on the complexity of
+\fBpcre2_dfa_match()\fP is controlled by the amount of workspace it is given.
+However, it is possible to write patterns with runaway infinite recursions;
+such patterns will cause \fBpcre2_dfa_match()\fP to run out of stack. At
+present, there is no protection against this.
+.P
+The comments that follow do NOT apply to \fBpcre2_dfa_match()\fP; they are
+relevant only for \fBpcre2_match()\fP without the JIT optimization.
+.
+.
+.SS "Reducing \fBpcre2_match()\fP's stack usage"
+.rs
+.sp
+You can often reduce the amount of recursion, and therefore the
+amount of stack used, by modifying the pattern that is being matched. Consider,
+for example, this pattern:
+.sp
+  ([^<]|<(?!inet))+
+.sp
+It matches from wherever it starts until it encounters "
+.\" 
+"The match context"
+.\"
+in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+documentation. Since the block sizes are always the same, it may be possible to
+implement customized a memory handler that is more efficient than the standard
+function. The memory blocks obtained for this purpose are retained and re-used
+if possible while \fBpcre2_match()\fP is running. They are all freed just
+before it exits.
+.
+.
+.SS "Limiting \fBpcre2_match()\fP's stack usage"
+.rs
+.sp
+You can set limits on the number of times the internal \fBmatch()\fP function
+is called, both in total and recursively. If a limit is exceeded,
+\fBpcre2_match()\fP returns an error code. Setting suitable limits should
+prevent it from running out of stack. The default values of the limits are very
+large, and unlikely ever to operate. They can be changed when PCRE2 is built,
+and they can also be set when \fBpcre2_match()\fP is called. For details of
+these interfaces, see the
+.\" HREF
+\fBpcre2build\fP
+.\"
+documentation and the section entitled
+.\" HTML 
+.\" 
+"The match context"
+.\"
+in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+documentation.
+.P
+As a very rough rule of thumb, you should reckon on about 500 bytes per
+recursion. Thus, if you want to limit your stack usage to 8Mb, you should set
+the limit at 16000 recursions. A 64Mb stack, on the other hand, can support
+around 128000 recursions.
+.P
+The \fBpcre2test\fP test program has a modifier called "find_limits" which, if
+applied to a subject line, causes it to find the smallest limits that allow a a
+pattern to match. This is done by calling \fBpcre2_match()\fP repeatedly with
+different limits.
+.
+.
+.SS "Changing stack size in Unix-like systems"
+.rs
+.sp
+In Unix-like environments, there is not often a problem with the stack unless
+very long strings are involved, though the default limit on stack size varies
+from system to system. Values from 8Mb to 64Mb are common. You can find your
+default limit by running the command:
+.sp
+  ulimit -s
+.sp
+Unfortunately, the effect of running out of stack is often SIGSEGV, though
+sometimes a more explicit error message is given. You can normally increase the
+limit on stack size by code such as this:
+.sp
+  struct rlimit rlim;
+  getrlimit(RLIMIT_STACK, &rlim);
+  rlim.rlim_cur = 100*1024*1024;
+  setrlimit(RLIMIT_STACK, &rlim);
+.sp
+This reads the current limits (soft and hard) using \fBgetrlimit()\fP, then
+attempts to increase the soft limit to 100Mb using \fBsetrlimit()\fP. You must
+do this before calling \fBpcre2_match()\fP.
+.
+.
+.SS "Changing stack size in Mac OS X"
+.rs
+.sp
+Using \fBsetrlimit()\fP, as described above, should also work on Mac OS X. It
+is also possible to set a stack size when linking a program. There is a
+discussion about stack sizes in Mac OS X at this web site:
+.\" HTML 
+.\" 
+http://developer.apple.com/qa/qa2005/qa1419.html.
+.\"
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel
+University Computing Service
+Cambridge, England.
+.fi
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 21 November 2014
+Copyright (c) 1997-2014 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/doc/pcre2syntax.3 b/pcre2-10.20/doc/pcre2syntax.3
new file mode 100644
index 000000000..dc34538cc
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2syntax.3
@@ -0,0 +1,575 @@
+.TH PCRE2SYNTAX 3 "13 June 2015" "PCRE2 10.20"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH "PCRE2 REGULAR EXPRESSION SYNTAX SUMMARY"
+.rs
+.sp
+The full syntax and semantics of the regular expressions that are supported by
+PCRE2 are described in the
+.\" HREF
+\fBpcre2pattern\fP
+.\"
+documentation. This document contains a quick-reference summary of the syntax.
+.
+.
+.SH "QUOTING"
+.rs
+.sp
+  \ex         where x is non-alphanumeric is a literal x
+  \eQ...\eE    treat enclosed characters as literal
+.
+.
+.SH "ESCAPED CHARACTERS"
+.rs
+.sp
+This table applies to ASCII and Unicode environments.
+.sp
+  \ea         alarm, that is, the BEL character (hex 07)
+  \ecx        "control-x", where x is any ASCII printing character
+  \ee         escape (hex 1B)
+  \ef         form feed (hex 0C)
+  \en         newline (hex 0A)
+  \er         carriage return (hex 0D)
+  \et         tab (hex 09)
+  \e0dd       character with octal code 0dd
+  \eddd       character with octal code ddd, or backreference
+  \eo{ddd..}  character with octal code ddd..
+  \eU         "U" if PCRE2_ALT_BSUX is set (otherwise is an error)
+  \euhhhh     character with hex code hhhh (if PCRE2_ALT_BSUX is set)
+  \exhh       character with hex code hh
+  \ex{hhh..}  character with hex code hhh..
+.sp
+Note that \e0dd is always an octal code. The treatment of backslash followed by
+a non-zero digit is complicated; for details see the section
+.\" HTML 
+.\" 
+"Non-printing characters"
+.\"
+in the
+.\" HREF
+\fBpcre2pattern\fP
+.\"
+documentation, where details of escape processing in EBCDIC environments are
+also given.
+.P
+When \ex is not followed by {, from zero to two hexadecimal digits are read,
+but if PCRE2_ALT_BSUX is set, \ex must be followed by two hexadecimal digits to
+be recognized as a hexadecimal escape; otherwise it matches a literal "x".
+Likewise, if \eu (in ALT_BSUX mode) is not followed by four hexadecimal digits,
+it matches a literal "u".
+.
+.
+.SH "CHARACTER TYPES"
+.rs
+.sp
+  .          any character except newline;
+               in dotall mode, any character whatsoever
+  \eC         one code unit, even in UTF mode (best avoided)
+  \ed         a decimal digit
+  \eD         a character that is not a decimal digit
+  \eh         a horizontal white space character
+  \eH         a character that is not a horizontal white space character
+  \eN         a character that is not a newline
+  \ep{\fIxx\fP}     a character with the \fIxx\fP property
+  \eP{\fIxx\fP}     a character without the \fIxx\fP property
+  \eR         a newline sequence
+  \es         a white space character
+  \eS         a character that is not a white space character
+  \ev         a vertical white space character
+  \eV         a character that is not a vertical white space character
+  \ew         a "word" character
+  \eW         a "non-word" character
+  \eX         a Unicode extended grapheme cluster
+.sp
+The application can lock out the use of \eC by setting the
+PCRE2_NEVER_BACKSLASH_C option. It is dangerous because it may leave the
+current matching point in the middle of a UTF-8 or UTF-16 character.
+.P
+By default, \ed, \es, and \ew match only ASCII characters, even in UTF-8 mode
+or in the 16-bit and 32-bit libraries. However, if locale-specific matching is
+happening, \es and \ew may also match characters with code points in the range
+128-255. If the PCRE2_UCP option is set, the behaviour of these escape
+sequences is changed to use Unicode properties and they match many more
+characters.
+.
+.
+.SH "GENERAL CATEGORY PROPERTIES FOR \ep and \eP"
+.rs
+.sp
+  C          Other
+  Cc         Control
+  Cf         Format
+  Cn         Unassigned
+  Co         Private use
+  Cs         Surrogate
+.sp
+  L          Letter
+  Ll         Lower case letter
+  Lm         Modifier letter
+  Lo         Other letter
+  Lt         Title case letter
+  Lu         Upper case letter
+  L&         Ll, Lu, or Lt
+.sp
+  M          Mark
+  Mc         Spacing mark
+  Me         Enclosing mark
+  Mn         Non-spacing mark
+.sp
+  N          Number
+  Nd         Decimal number
+  Nl         Letter number
+  No         Other number
+.sp
+  P          Punctuation
+  Pc         Connector punctuation
+  Pd         Dash punctuation
+  Pe         Close punctuation
+  Pf         Final punctuation
+  Pi         Initial punctuation
+  Po         Other punctuation
+  Ps         Open punctuation
+.sp
+  S          Symbol
+  Sc         Currency symbol
+  Sk         Modifier symbol
+  Sm         Mathematical symbol
+  So         Other symbol
+.sp
+  Z          Separator
+  Zl         Line separator
+  Zp         Paragraph separator
+  Zs         Space separator
+.
+.
+.SH "PCRE2 SPECIAL CATEGORY PROPERTIES FOR \ep and \eP"
+.rs
+.sp
+  Xan        Alphanumeric: union of properties L and N
+  Xps        POSIX space: property Z or tab, NL, VT, FF, CR
+  Xsp        Perl space: property Z or tab, NL, VT, FF, CR
+  Xuc        Univerally-named character: one that can be
+               represented by a Universal Character Name
+  Xwd        Perl word: property Xan or underscore
+.sp
+Perl and POSIX space are now the same. Perl added VT to its space character set
+at release 5.18.
+.
+.
+.SH "SCRIPT NAMES FOR \ep AND \eP"
+.rs
+.sp
+Arabic,
+Armenian,
+Avestan,
+Balinese,
+Bamum,
+Bassa_Vah,
+Batak,
+Bengali,
+Bopomofo,
+Brahmi,
+Braille,
+Buginese,
+Buhid,
+Canadian_Aboriginal,
+Carian,
+Caucasian_Albanian,
+Chakma,
+Cham,
+Cherokee,
+Common,
+Coptic,
+Cuneiform,
+Cypriot,
+Cyrillic,
+Deseret,
+Devanagari,
+Duployan,
+Egyptian_Hieroglyphs,
+Elbasan,
+Ethiopic,
+Georgian,
+Glagolitic,
+Gothic,
+Grantha,
+Greek,
+Gujarati,
+Gurmukhi,
+Han,
+Hangul,
+Hanunoo,
+Hebrew,
+Hiragana,
+Imperial_Aramaic,
+Inherited,
+Inscriptional_Pahlavi,
+Inscriptional_Parthian,
+Javanese,
+Kaithi,
+Kannada,
+Katakana,
+Kayah_Li,
+Kharoshthi,
+Khmer,
+Khojki,
+Khudawadi,
+Lao,
+Latin,
+Lepcha,
+Limbu,
+Linear_A,
+Linear_B,
+Lisu,
+Lycian,
+Lydian,
+Mahajani,
+Malayalam,
+Mandaic,
+Manichaean,
+Meetei_Mayek,
+Mende_Kikakui,
+Meroitic_Cursive,
+Meroitic_Hieroglyphs,
+Miao,
+Modi,
+Mongolian,
+Mro,
+Myanmar,
+Nabataean,
+New_Tai_Lue,
+Nko,
+Ogham,
+Ol_Chiki,
+Old_Italic,
+Old_North_Arabian,
+Old_Permic,
+Old_Persian,
+Old_South_Arabian,
+Old_Turkic,
+Oriya,
+Osmanya,
+Pahawh_Hmong,
+Palmyrene,
+Pau_Cin_Hau,
+Phags_Pa,
+Phoenician,
+Psalter_Pahlavi,
+Rejang,
+Runic,
+Samaritan,
+Saurashtra,
+Sharada,
+Shavian,
+Siddham,
+Sinhala,
+Sora_Sompeng,
+Sundanese,
+Syloti_Nagri,
+Syriac,
+Tagalog,
+Tagbanwa,
+Tai_Le,
+Tai_Tham,
+Tai_Viet,
+Takri,
+Tamil,
+Telugu,
+Thaana,
+Thai,
+Tibetan,
+Tifinagh,
+Tirhuta,
+Ugaritic,
+Vai,
+Warang_Citi,
+Yi.
+.
+.
+.SH "CHARACTER CLASSES"
+.rs
+.sp
+  [...]       positive character class
+  [^...]      negative character class
+  [x-y]       range (can be used for hex characters)
+  [[:xxx:]]   positive POSIX named set
+  [[:^xxx:]]  negative POSIX named set
+.sp
+  alnum       alphanumeric
+  alpha       alphabetic
+  ascii       0-127
+  blank       space or tab
+  cntrl       control character
+  digit       decimal digit
+  graph       printing, excluding space
+  lower       lower case letter
+  print       printing, including space
+  punct       printing, excluding alphanumeric
+  space       white space
+  upper       upper case letter
+  word        same as \ew
+  xdigit      hexadecimal digit
+.sp
+In PCRE2, POSIX character set names recognize only ASCII characters by default,
+but some of them use Unicode properties if PCRE2_UCP is set. You can use
+\eQ...\eE inside a character class.
+.
+.
+.SH "QUANTIFIERS"
+.rs
+.sp
+  ?           0 or 1, greedy
+  ?+          0 or 1, possessive
+  ??          0 or 1, lazy
+  *           0 or more, greedy
+  *+          0 or more, possessive
+  *?          0 or more, lazy
+  +           1 or more, greedy
+  ++          1 or more, possessive
+  +?          1 or more, lazy
+  {n}         exactly n
+  {n,m}       at least n, no more than m, greedy
+  {n,m}+      at least n, no more than m, possessive
+  {n,m}?      at least n, no more than m, lazy
+  {n,}        n or more, greedy
+  {n,}+       n or more, possessive
+  {n,}?       n or more, lazy
+.
+.
+.SH "ANCHORS AND SIMPLE ASSERTIONS"
+.rs
+.sp
+  \eb          word boundary
+  \eB          not a word boundary
+  ^           start of subject
+                also after an internal newline in multiline mode
+                (after any newline if PCRE2_ALT_CIRCUMFLEX is set)
+  \eA          start of subject
+  $           end of subject
+                also before newline at end of subject
+                also before internal newline in multiline mode
+  \eZ          end of subject
+                also before newline at end of subject
+  \ez          end of subject
+  \eG          first matching position in subject
+.
+.
+.SH "MATCH POINT RESET"
+.rs
+.sp
+  \eK          reset start of match
+.sp
+\eK is honoured in positive assertions, but ignored in negative ones.
+.
+.
+.SH "ALTERNATION"
+.rs
+.sp
+  expr|expr|expr...
+.
+.
+.SH "CAPTURING"
+.rs
+.sp
+  (...)           capturing group
+  (?...)    named capturing group (Perl)
+  (?'name'...)    named capturing group (Perl)
+  (?P...)   named capturing group (Python)
+  (?:...)         non-capturing group
+  (?|...)         non-capturing group; reset group numbers for
+                   capturing groups in each alternative
+.
+.
+.SH "ATOMIC GROUPS"
+.rs
+.sp
+  (?>...)         atomic, non-capturing group
+.
+.
+.
+.
+.SH "COMMENT"
+.rs
+.sp
+  (?#....)        comment (not nestable)
+.
+.
+.SH "OPTION SETTING"
+.rs
+.sp
+  (?i)            caseless
+  (?J)            allow duplicate names
+  (?m)            multiline
+  (?s)            single line (dotall)
+  (?U)            default ungreedy (lazy)
+  (?x)            extended (ignore white space)
+  (?-...)         unset option(s)
+.sp
+The following are recognized only at the very start of a pattern or after one
+of the newline or \eR options with similar syntax. More than one of them may
+appear.
+.sp
+  (*LIMIT_MATCH=d) set the match limit to d (decimal number)
+  (*LIMIT_RECURSION=d) set the recursion limit to d (decimal number)
+  (*NOTEMPTY)     set PCRE2_NOTEMPTY when matching
+  (*NOTEMPTY_ATSTART) set PCRE2_NOTEMPTY_ATSTART when matching
+  (*NO_AUTO_POSSESS) no auto-possessification (PCRE2_NO_AUTO_POSSESS)
+  (*NO_DOTSTAR_ANCHOR) no .* anchoring (PCRE2_NO_DOTSTAR_ANCHOR)
+  (*NO_JIT)       disable JIT optimization
+  (*NO_START_OPT) no start-match optimization (PCRE2_NO_START_OPTIMIZE)
+  (*UTF)          set appropriate UTF mode for the library in use
+  (*UCP)          set PCRE2_UCP (use Unicode properties for \ed etc)
+.sp
+Note that LIMIT_MATCH and LIMIT_RECURSION can only reduce the value of the
+limits set by the caller of pcre2_match(), not increase them. The application
+can lock out the use of (*UTF) and (*UCP) by setting the PCRE2_NEVER_UTF or
+PCRE2_NEVER_UCP options, respectively, at compile time.
+.
+.
+.SH "NEWLINE CONVENTION"
+.rs
+.sp
+These are recognized only at the very start of the pattern or after option
+settings with a similar syntax.
+.sp
+  (*CR)           carriage return only
+  (*LF)           linefeed only
+  (*CRLF)         carriage return followed by linefeed
+  (*ANYCRLF)      all three of the above
+  (*ANY)          any Unicode newline sequence
+.
+.
+.SH "WHAT \eR MATCHES"
+.rs
+.sp
+These are recognized only at the very start of the pattern or after option
+setting with a similar syntax.
+.sp
+  (*BSR_ANYCRLF)  CR, LF, or CRLF
+  (*BSR_UNICODE)  any Unicode newline sequence
+.
+.
+.SH "LOOKAHEAD AND LOOKBEHIND ASSERTIONS"
+.rs
+.sp
+  (?=...)         positive look ahead
+  (?!...)         negative look ahead
+  (?<=...)        positive look behind
+  (?        reference by name (Perl)
+  \ek'name'        reference by name (Perl)
+  \eg{name}        reference by name (Perl)
+  \ek{name}        reference by name (.NET)
+  (?P=name)       reference by name (Python)
+.
+.
+.SH "SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)"
+.rs
+.sp
+  (?R)            recurse whole pattern
+  (?n)            call subpattern by absolute number
+  (?+n)           call subpattern by relative number
+  (?-n)           call subpattern by relative number
+  (?&name)        call subpattern by name (Perl)
+  (?P>name)       call subpattern by name (Python)
+  \eg        call subpattern by name (Oniguruma)
+  \eg'name'        call subpattern by name (Oniguruma)
+  \eg           call subpattern by absolute number (Oniguruma)
+  \eg'n'           call subpattern by absolute number (Oniguruma)
+  \eg<+n>          call subpattern by relative number (PCRE2 extension)
+  \eg'+n'          call subpattern by relative number (PCRE2 extension)
+  \eg<-n>          call subpattern by relative number (PCRE2 extension)
+  \eg'-n'          call subpattern by relative number (PCRE2 extension)
+.
+.
+.SH "CONDITIONAL PATTERNS"
+.rs
+.sp
+  (?(condition)yes-pattern)
+  (?(condition)yes-pattern|no-pattern)
+.sp
+  (?(n)               absolute reference condition
+  (?(+n)              relative reference condition
+  (?(-n)              relative reference condition
+  (?()          named reference condition (Perl)
+  (?('name')          named reference condition (Perl)
+  (?(name)            named reference condition (PCRE2)
+  (?(R)               overall recursion condition
+  (?(Rn)              specific group recursion condition
+  (?(R&name)          specific recursion condition
+  (?(DEFINE)          define subpattern for reference
+  (?(VERSION[>]=n.m)  test PCRE2 version
+  (?(assert)          assertion condition
+.
+.
+.SH "BACKTRACKING CONTROL"
+.rs
+.sp
+The following act immediately they are reached:
+.sp
+  (*ACCEPT)       force successful match
+  (*FAIL)         force backtrack; synonym (*F)
+  (*MARK:NAME)    set name to be passed back; synonym (*:NAME)
+.sp
+The following act only when a subsequent match failure causes a backtrack to
+reach them. They all force a match failure, but they differ in what happens
+afterwards. Those that advance the start-of-match point do so only if the
+pattern is not anchored.
+.sp
+  (*COMMIT)       overall failure, no advance of starting point
+  (*PRUNE)        advance to next starting character
+  (*PRUNE:NAME)   equivalent to (*MARK:NAME)(*PRUNE)
+  (*SKIP)         advance to current matching position
+  (*SKIP:NAME)    advance to position corresponding to an earlier
+                  (*MARK:NAME); if not found, the (*SKIP) is ignored
+  (*THEN)         local failure, backtrack to next alternation
+  (*THEN:NAME)    equivalent to (*MARK:NAME)(*THEN)
+.
+.
+.SH "CALLOUTS"
+.rs
+.sp
+  (?C)            callout (assumed number 0)
+  (?Cn)           callout with numerical data n
+  (?C"text")      callout with string data
+.sp
+The allowed string delimiters are ` ' " ^ % # $ (which are the same for the
+start and the end), and the starting delimiter { matched with the ending
+delimiter }. To encode the ending delimiter within the string, double it.
+.
+.
+.SH "SEE ALSO"
+.rs
+.sp
+\fBpcre2pattern\fP(3), \fBpcre2api\fP(3), \fBpcre2callout\fP(3),
+\fBpcre2matching\fP(3), \fBpcre2\fP(3).
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel
+University Computing Service
+Cambridge, England.
+.fi
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 13 June 2015
+Copyright (c) 1997-2015 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/doc/pcre2test.1 b/pcre2-10.20/doc/pcre2test.1
new file mode 100644
index 000000000..857adc354
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2test.1
@@ -0,0 +1,1456 @@
+.TH PCRE2TEST 1 "20 May 2015" "PCRE 10.20"
+.SH NAME
+pcre2test - a program for testing Perl-compatible regular expressions.
+.SH SYNOPSIS
+.rs
+.sp
+.B pcre2test "[options] [input file [output file]]"
+.sp
+\fBpcre2test\fP is a test program for the PCRE2 regular expression libraries,
+but it can also be used for experimenting with regular expressions. This
+document describes the features of the test program; for details of the regular
+expressions themselves, see the
+.\" HREF
+\fBpcre2pattern\fP
+.\"
+documentation. For details of the PCRE2 library function calls and their
+options, see the
+.\" HREF
+\fBpcre2api\fP
+.\"
+documentation.
+.P
+The input for \fBpcre2test\fP is a sequence of regular expression patterns and
+subject strings to be matched. There are also command lines for setting
+defaults and controlling some special actions. The output shows the result of
+each match attempt. Modifiers on external or internal command lines, the
+patterns, and the subject lines specify PCRE2 function options, control how the
+subject is processed, and what output is produced.
+.P
+As the original fairly simple PCRE library evolved, it acquired many different
+features, and as a result, the original \fBpcretest\fP program ended up with a
+lot of options in a messy, arcane syntax, for testing all the features. The
+move to the new PCRE2 API provided an opportunity to re-implement the test
+program as \fBpcre2test\fP, with a cleaner modifier syntax. Nevertheless, there
+are still many obscure modifiers, some of which are specifically designed for
+use in conjunction with the test script and data files that are distributed as
+part of PCRE2. All the modifiers are documented here, some without much
+justification, but many of them are unlikely to be of use except when testing
+the libraries.
+.
+.
+.SH "PCRE2's 8-BIT, 16-BIT AND 32-BIT LIBRARIES"
+.rs
+.sp
+Different versions of the PCRE2 library can be built to support character
+strings that are encoded in 8-bit, 16-bit, or 32-bit code units. One, two, or
+all three of these libraries may be simultaneously installed. The
+\fBpcre2test\fP program can be used to test all the libraries. However, its own
+input and output are always in 8-bit format. When testing the 16-bit or 32-bit
+libraries, patterns and subject strings are converted to 16- or 32-bit format
+before being passed to the library functions. Results are converted back to
+8-bit code units for output.
+.P
+In the rest of this document, the names of library functions and structures
+are given in generic form, for example, \fBpcre_compile()\fP. The actual
+names used in the libraries have a suffix _8, _16, or _32, as appropriate.
+.
+.
+.SH "INPUT ENCODING"
+.rs
+.sp
+Input to \fBpcre2test\fP is processed line by line, either by calling the C
+library's \fBfgets()\fP function, or via the \fBlibreadline\fP library (see
+below). The input is processed using using C's string functions, so must not
+contain binary zeroes, even though in Unix-like environments, \fBfgets()\fP
+treats any bytes other than newline as data characters. In some Windows
+environments character 26 (hex 1A) causes an immediate end of file, and no
+further data is read.
+.P
+For maximum portability, therefore, it is safest to avoid non-printing
+characters in \fBpcre2test\fP input files. There is a facility for specifying a
+pattern's characters as hexadecimal pairs, thus making it possible to include
+binary zeroes in a pattern for testing purposes. Subject lines are processed
+for backslash escapes, which makes it possible to include any data value.
+.
+.
+.SH "COMMAND LINE OPTIONS"
+.rs
+.TP 10
+\fB-8\fP
+If the 8-bit library has been built, this option causes it to be used (this is
+the default). If the 8-bit library has not been built, this option causes an
+error.
+.TP 10
+\fB-16\fP
+If the 16-bit library has been built, this option causes it to be used. If only
+the 16-bit library has been built, this is the default. If the 16-bit library
+has not been built, this option causes an error.
+.TP 10
+\fB-32\fP
+If the 32-bit library has been built, this option causes it to be used. If only
+the 32-bit library has been built, this is the default. If the 32-bit library
+has not been built, this option causes an error.
+.TP 10
+\fB-b\fP
+Behave as if each pattern has the \fB/fullbincode\fP modifier; the full
+internal binary form of the pattern is output after compilation.
+.TP 10
+\fB-C\fP
+Output the version number of the PCRE2 library, and all available information
+about the optional features that are included, and then exit with zero exit
+code. All other options are ignored.
+.TP 10
+\fB-C\fP \fIoption\fP
+Output information about a specific build-time option, then exit. This
+functionality is intended for use in scripts such as \fBRunTest\fP. The
+following options output the value and set the exit code as indicated:
+.sp
+  ebcdic-nl  the code for LF (= NL) in an EBCDIC environment:
+               0x15 or 0x25
+               0 if used in an ASCII environment
+               exit code is always 0
+  linksize   the configured internal link size (2, 3, or 4)
+               exit code is set to the link size
+  newline    the default newline setting:
+               CR, LF, CRLF, ANYCRLF, or ANY
+               exit code is always 0
+  bsr        the default setting for what \eR matches:
+               ANYCRLF or ANY
+               exit code is always 0
+.sp
+The following options output 1 for true or 0 for false, and set the exit code
+to the same value:
+.sp
+  ebcdic     compiled for an EBCDIC environment
+  jit        just-in-time support is available
+  pcre2-16   the 16-bit library was built
+  pcre2-32   the 32-bit library was built
+  pcre2-8    the 8-bit library was built
+  unicode    Unicode support is available
+.sp
+If an unknown option is given, an error message is output; the exit code is 0.
+.TP 10
+\fB-d\fP
+Behave as if each pattern has the \fBdebug\fP modifier; the internal
+form and information about the compiled pattern is output after compilation;
+\fB-d\fP is equivalent to \fB-b -i\fP.
+.TP 10
+\fB-dfa\fP
+Behave as if each subject line has the \fBdfa\fP modifier; matching is done
+using the \fBpcre2_dfa_match()\fP function instead of the default
+\fBpcre2_match()\fP.
+.TP 10
+\fB-help\fP
+Output a brief summary these options and then exit.
+.TP 10
+\fB-i\fP
+Behave as if each pattern has the \fB/info\fP modifier; information about the
+compiled pattern is given after compilation.
+.TP 10
+\fB-jit\fP
+Behave as if each pattern line has the \fBjit\fP modifier; after successful
+compilation, each pattern is passed to the just-in-time compiler, if available.
+.TP 10
+\fB-pattern\fB \fImodifier-list\fP
+Behave as if each pattern line contains the given modifiers.
+.TP 10
+\fB-q\fP
+Do not output the version number of \fBpcre2test\fP at the start of execution.
+.TP 10
+\fB-S\fP \fIsize\fP
+On Unix-like systems, set the size of the run-time stack to \fIsize\fP
+megabytes.
+.TP 10
+\fB-subject\fP \fImodifier-list\fP
+Behave as if each subject line contains the given modifiers.
+.TP 10
+\fB-t\fP
+Run each compile and match many times with a timer, and output the resulting
+times per compile or match. When JIT is used, separate times are given for the
+initial compile and the JIT compile. You can control the number of iterations
+that are used for timing by following \fB-t\fP with a number (as a separate
+item on the command line). For example, "-t 1000" iterates 1000 times. The
+default is to iterate 500,000 times.
+.TP 10
+\fB-tm\fP
+This is like \fB-t\fP except that it times only the matching phase, not the
+compile phase.
+.TP 10
+\fB-T\fP \fB-TM\fP
+These behave like \fB-t\fP and \fB-tm\fP, but in addition, at the end of a run,
+the total times for all compiles and matches are output.
+.TP 10
+\fB-version\fP
+Output the PCRE2 version number and then exit.
+.
+.
+.SH "DESCRIPTION"
+.rs
+.sp
+If \fBpcre2test\fP is given two filename arguments, it reads from the first and
+writes to the second. If the first name is "-", input is taken from the
+standard input. If \fBpcre2test\fP is given only one argument, it reads from
+that file and writes to stdout. Otherwise, it reads from stdin and writes to
+stdout.
+.P
+When \fBpcre2test\fP is built, a configuration option can specify that it
+should be linked with the \fBlibreadline\fP or \fBlibedit\fP library. When this
+is done, if the input is from a terminal, it is read using the \fBreadline()\fP
+function. This provides line-editing and history facilities. The output from
+the \fB-help\fP option states whether or not \fBreadline()\fP will be used.
+.P
+The program handles any number of tests, each of which consists of a set of
+input lines. Each set starts with a regular expression pattern, followed by any
+number of subject lines to be matched against that pattern. In between sets of
+test data, command lines that begin with # may appear. This file format, with
+some restrictions, can also be processed by the \fBperltest.sh\fP script that
+is distributed with PCRE2 as a means of checking that the behaviour of PCRE2
+and Perl is the same.
+.P
+When the input is a terminal, \fBpcre2test\fP prompts for each line of input,
+using "re>" to prompt for regular expression patterns, and "data>" to prompt
+for subject lines. Command lines starting with # can be entered only in
+response to the "re>" prompt.
+.P
+Each subject line is matched separately and independently. If you want to do
+multi-line matches, you have to use the \en escape sequence (or \er or \er\en,
+etc., depending on the newline setting) in a single line of input to encode the
+newline sequences. There is no limit on the length of subject lines; the input
+buffer is automatically extended if it is too small. There is a replication
+feature that makes it possible to generate long subject lines without having to
+supply them explicitly.
+.P
+An empty line or the end of the file signals the end of the subject lines for a
+test, at which point a new pattern or command line is expected if there is
+still input to be read.
+.
+.
+.SH "COMMAND LINES"
+.rs
+.sp
+In between sets of test data, a line that begins with # is interpreted as a
+command line. If the first character is followed by white space or an
+exclamation mark, the line is treated as a comment, and ignored. Otherwise, the
+following commands are recognized:
+.sp
+  #forbid_utf
+.sp
+Subsequent patterns automatically have the PCRE2_NEVER_UTF and PCRE2_NEVER_UCP
+options set, which locks out the use of the PCRE2_UTF and PCRE2_UCP options and
+the use of (*UTF) and (*UCP) at the start of patterns. This command also forces
+an error if a subsequent pattern contains any occurrences of \eP, \ep, or \eX,
+which are still supported when PCRE2_UTF is not set, but which require Unicode
+property support to be included in the library.
+.P
+This is a trigger guard that is used in test files to ensure that UTF or
+Unicode property tests are not accidentally added to files that are used when
+Unicode support is not included in the library. Setting PCRE2_NEVER_UTF and
+PCRE2_NEVER_UCP as a default can also be obtained by the use of \fB#pattern\fP;
+the difference is that \fB#forbid_utf\fP cannot be unset, and the automatic
+options are not displayed in pattern information, to avoid cluttering up test
+output.
+.sp
+  #load 
+.sp
+This command is used to load a set of precompiled patterns from a file, as
+described in the section entitled "Saving and restoring compiled patterns"
+.\" HTML 
+.\" 
+below.
+.\"
+.sp
+  #pattern 
+.sp
+This command sets a default modifier list that applies to all subsequent
+patterns. Modifiers on a pattern can change these settings.
+.sp
+  #perltest
+.sp
+The appearance of this line causes all subsequent modifier settings to be
+checked for compatibility with the \fBperltest.sh\fP script, which is used to
+confirm that Perl gives the same results as PCRE2. Also, apart from comment
+lines, none of the other command lines are permitted, because they and many
+of the modifiers are specific to \fBpcre2test\fP, and should not be used in
+test files that are also processed by \fBperltest.sh\fP. The \fB#perltest\fP
+command helps detect tests that are accidentally put in the wrong file.
+.sp
+  #pop []
+.sp
+This command is used to manipulate the stack of compiled patterns, as described
+in the section entitled "Saving and restoring compiled patterns"
+.\" HTML 
+.\" 
+below.
+.\"
+.sp
+  #save 
+.sp
+This command is used to save a set of compiled patterns to a file, as described
+in the section entitled "Saving and restoring compiled patterns"
+.\" HTML 
+.\" 
+below.
+.\"
+.sp
+  #subject 
+.sp
+This command sets a default modifier list that applies to all subsequent
+subject lines. Modifiers on a subject line can change these settings.
+.
+.
+.SH "MODIFIER SYNTAX"
+.rs
+.sp
+Modifier lists are used with both pattern and subject lines. Items in a list
+are separated by commas and optional white space. Some modifiers may be given
+for both patterns and subject lines, whereas others are valid for one or the
+other only. Each modifier has a long name, for example "anchored", and some of
+them must be followed by an equals sign and a value, for example, "offset=12".
+Modifiers that do not take values may be preceded by a minus sign to turn off a
+previous setting.
+.P
+A few of the more common modifiers can also be specified as single letters, for
+example "i" for "caseless". In documentation, following the Perl convention,
+these are written with a slash ("the /i modifier") for clarity. Abbreviated
+modifiers must all be concatenated in the first item of a modifier list. If the
+first item is not recognized as a long modifier name, it is interpreted as a
+sequence of these abbreviations. For example:
+.sp
+  /abc/ig,newline=cr,jit=3
+.sp
+This is a pattern line whose modifier list starts with two one-letter modifiers
+(/i and /g). The lower-case abbreviated modifiers are the same as used in Perl.
+.
+.
+.SH "PATTERN SYNTAX"
+.rs
+.sp
+A pattern line must start with one of the following characters (common symbols,
+excluding pattern meta-characters):
+.sp
+  / ! " ' ` - = _ : ; , % & @ ~
+.sp
+This is interpreted as the pattern's delimiter. A regular expression may be
+continued over several input lines, in which case the newline characters are
+included within it. It is possible to include the delimiter within the pattern
+by escaping it with a backslash, for example
+.sp
+  /abc\e/def/
+.sp
+If you do this, the escape and the delimiter form part of the pattern, but
+since the delimiters are all non-alphanumeric, this does not affect its
+interpretation. If the terminating delimiter is immediately followed by a
+backslash, for example,
+.sp
+  /abc/\e
+.sp
+then a backslash is added to the end of the pattern. This is done to provide a
+way of testing the error condition that arises if a pattern finishes with a
+backslash, because
+.sp
+  /abc\e/
+.sp
+is interpreted as the first line of a pattern that starts with "abc/", causing
+pcre2test to read the next line as a continuation of the regular expression.
+.P
+A pattern can be followed by a modifier list (details below).
+.
+.
+.SH "SUBJECT LINE SYNTAX"
+.rs
+.sp
+Before each subject line is passed to \fBpcre2_match()\fP or
+\fBpcre2_dfa_match()\fP, leading and trailing white space is removed, and the
+line is scanned for backslash escapes. The following provide a means of
+encoding non-printing characters in a visible way:
+.sp
+  \ea         alarm (BEL, \ex07)
+  \eb         backspace (\ex08)
+  \ee         escape (\ex27)
+  \ef         form feed (\ex0c)
+  \en         newline (\ex0a)
+  \er         carriage return (\ex0d)
+  \et         tab (\ex09)
+  \ev         vertical tab (\ex0b)
+  \ennn       octal character (up to 3 octal digits); always
+               a byte unless > 255 in UTF-8 or 16-bit or 32-bit mode
+  \eo{dd...}  octal character (any number of octal digits}
+  \exhh       hexadecimal byte (up to 2 hex digits)
+  \ex{hh...}  hexadecimal character (any number of hex digits)
+.sp
+The use of \ex{hh...} is not dependent on the use of the \fButf\fP modifier on
+the pattern. It is recognized always. There may be any number of hexadecimal
+digits inside the braces; invalid values provoke error messages.
+.P
+Note that \exhh specifies one byte rather than one character in UTF-8 mode;
+this makes it possible to construct invalid UTF-8 sequences for testing
+purposes. On the other hand, \ex{hh} is interpreted as a UTF-8 character in
+UTF-8 mode, generating more than one byte if the value is greater than 127.
+When testing the 8-bit library not in UTF-8 mode, \ex{hh} generates one byte
+for values less than 256, and causes an error for greater values.
+.P
+In UTF-16 mode, all 4-digit \ex{hhhh} values are accepted. This makes it
+possible to construct invalid UTF-16 sequences for testing purposes.
+.P
+In UTF-32 mode, all 4- to 8-digit \ex{...} values are accepted. This makes it
+possible to construct invalid UTF-32 sequences for testing purposes.
+.P
+There is a special backslash sequence that specifies replication of one or more
+characters:
+.sp
+  \e[]{}
+.sp
+This makes it possible to test long strings without having to provide them as
+part of the file. For example:
+.sp
+  \e[abc]{4}
+.sp
+is converted to "abcabcabcabc". This feature does not support nesting. To
+include a closing square bracket in the characters, code it as \ex5D.
+.P
+A backslash followed by an equals sign marks the end of the subject string and
+the start of a modifier list. For example:
+.sp
+  abc\e=notbol,notempty
+.sp
+A backslash followed by any other non-alphanumeric character just escapes that
+character. A backslash followed by anything else causes an error. However, if
+the very last character in the line is a backslash (and there is no modifier
+list), it is ignored. This gives a way of passing an empty line as data, since
+a real empty line terminates the data input.
+.
+.
+.SH "PATTERN MODIFIERS"
+.rs
+.sp
+There are three types of modifier that can appear in pattern lines, two of
+which may also be used in a \fB#pattern\fP command. A pattern's modifier list
+can add to or override default modifiers that were set by a previous
+\fB#pattern\fP command.
+.
+.
+.\" HTML 
+.SS "Setting compilation options"
+.rs
+.sp
+The following modifiers set options for \fBpcre2_compile()\fP. The most common
+ones have single-letter abbreviations. See
+.\" HREF
+\fBpcreapi\fP
+.\"
+for a description of their effects.
+.sp
+      allow_empty_class         set PCRE2_ALLOW_EMPTY_CLASS
+      alt_bsux                  set PCRE2_ALT_BSUX
+      alt_circumflex            set PCRE2_ALT_CIRCUMFLEX
+      anchored                  set PCRE2_ANCHORED
+      auto_callout              set PCRE2_AUTO_CALLOUT
+  /i  caseless                  set PCRE2_CASELESS
+      dollar_endonly            set PCRE2_DOLLAR_ENDONLY
+  /s  dotall                    set PCRE2_DOTALL
+      dupnames                  set PCRE2_DUPNAMES
+  /x  extended                  set PCRE2_EXTENDED
+      firstline                 set PCRE2_FIRSTLINE
+      match_unset_backref       set PCRE2_MATCH_UNSET_BACKREF
+  /m  multiline                 set PCRE2_MULTILINE
+      never_backslash_c         set PCRE2_NEVER_BACKSLASH_C
+      never_ucp                 set PCRE2_NEVER_UCP
+      never_utf                 set PCRE2_NEVER_UTF
+      no_auto_capture           set PCRE2_NO_AUTO_CAPTURE
+      no_auto_possess           set PCRE2_NO_AUTO_POSSESS
+      no_dotstar_anchor         set PCRE2_NO_DOTSTAR_ANCHOR
+      no_start_optimize         set PCRE2_NO_START_OPTIMIZE
+      no_utf_check              set PCRE2_NO_UTF_CHECK
+      ucp                       set PCRE2_UCP
+      ungreedy                  set PCRE2_UNGREEDY
+      utf                       set PCRE2_UTF
+.sp
+As well as turning on the PCRE2_UTF option, the \fButf\fP modifier causes all
+non-printing characters in output strings to be printed using the \ex{hh...}
+notation. Otherwise, those less than 0x100 are output in hex without the curly
+brackets.
+.
+.
+.\" HTML 
+.SS "Setting compilation controls"
+.rs
+.sp
+The following modifiers affect the compilation process or request information
+about the pattern:
+.sp
+      bsr=[anycrlf|unicode]     specify \eR handling
+  /B  bincode                   show binary code without lengths
+      callout_info              show callout information
+      debug                     same as info,fullbincode
+      fullbincode               show binary code with lengths
+  /I  info                      show info about compiled pattern
+      hex                       pattern is coded in hexadecimal
+      jit[=]            use JIT
+      jitfast                   use JIT fast path
+      jitverify                 verify JIT use
+      locale=             use this locale
+      memory                    show memory used
+      newline=            set newline type
+      parens_nest_limit=     set maximum parentheses depth
+      posix                     use the POSIX API
+      push                      push compiled pattern onto the stack
+      stackguard=       test the stackguard feature
+      tables=[0|1|2]            select internal tables
+.sp
+The effects of these modifiers are described in the following sections.
+.
+.
+.SS "Newline and \eR handling"
+.rs
+.sp
+The \fBbsr\fP modifier specifies what \eR in a pattern should match. If it is
+set to "anycrlf", \eR matches CR, LF, or CRLF only. If it is set to "unicode",
+\eR matches any Unicode newline sequence. The default is specified when PCRE2
+is built, with the default default being Unicode.
+.P
+The \fBnewline\fP modifier specifies which characters are to be interpreted as
+newlines, both in the pattern and in subject lines. The type must be one of CR,
+LF, CRLF, ANYCRLF, or ANY (in upper or lower case).
+.
+.
+.SS "Information about a pattern"
+.rs
+.sp
+The \fBdebug\fP modifier is a shorthand for \fBinfo,fullbincode\fP, requesting
+all available information.
+.P
+The \fBbincode\fP modifier causes a representation of the compiled code to be
+output after compilation. This information does not contain length and offset
+values, which ensures that the same output is generated for different internal
+link sizes and different code unit widths. By using \fBbincode\fP, the same
+regression tests can be used in different environments.
+.P
+The \fBfullbincode\fP modifier, by contrast, \fIdoes\fP include length and
+offset values. This is used in a few special tests that run only for specific
+code unit widths and link sizes, and is also useful for one-off tests.
+.P
+The \fBinfo\fP modifier requests information about the compiled pattern
+(whether it is anchored, has a fixed first character, and so on). The
+information is obtained from the \fBpcre2_pattern_info()\fP function. Here are
+some typical examples:
+.sp
+    re> /(?i)(^a|^b)/m,info
+  Capturing subpattern count = 1
+  Compile options: multiline
+  Overall options: caseless multiline
+  First code unit at start or follows newline
+  Subject length lower bound = 1
+.sp
+    re> /(?i)abc/info
+  Capturing subpattern count = 0
+  Compile options: 
+  Overall options: caseless
+  First code unit = 'a' (caseless)
+  Last code unit = 'c' (caseless)
+  Subject length lower bound = 3
+.sp
+"Compile options" are those specified by modifiers; "overall options" have
+added options that are taken or deduced from the pattern. If both sets of
+options are the same, just a single "options" line is output; if there are no
+options, the line is omitted. "First code unit" is where any match must start;
+if there is more than one they are listed as "starting code units". "Last code
+unit" is the last literal code unit that must be present in any match. This is
+not necessarily the last character. These lines are omitted if no starting or
+ending code units are recorded.
+.P
+The \fBcallout_info\fP modifier requests information about all the callouts in
+the pattern. A list of them is output at the end of any other information that
+is requested. For each callout, either its number or string is given, followed
+by the item that follows it in the pattern.
+.
+.
+.SS "Specifying a pattern in hex"
+.rs
+.sp
+The \fBhex\fP modifier specifies that the characters of the pattern are to be
+interpreted as pairs of hexadecimal digits. White space is permitted between
+pairs. For example:
+.sp
+  /ab 32 59/hex
+.sp
+This feature is provided as a way of creating patterns that contain binary zero
+and other non-printing characters. By default, \fBpcre2test\fP passes patterns
+as zero-terminated strings to \fBpcre2_compile()\fP, giving the length as
+PCRE2_ZERO_TERMINATED. However, for patterns specified in hexadecimal, the
+actual length of the pattern is passed.
+.
+.
+.SS "JIT compilation"
+.rs
+.sp
+The \fB/jit\fP modifier may optionally be followed by an equals sign and a
+number in the range 0 to 7:
+.sp
+  0  disable JIT
+  1  use JIT for normal match only
+  2  use JIT for soft partial match only
+  3  use JIT for normal match and soft partial match
+  4  use JIT for hard partial match only
+  6  use JIT for soft and hard partial match
+  7  all three modes
+.sp
+If no number is given, 7 is assumed. If JIT compilation is successful, the
+compiled JIT code will automatically be used when \fBpcre2_match()\fP is run
+for the appropriate type of match, except when incompatible run-time options
+are specified. For more details, see the
+.\" HREF
+\fBpcre2jit\fP
+.\"
+documentation. See also the \fBjitstack\fP modifier below for a way of
+setting the size of the JIT stack.
+.P
+If the \fBjitfast\fP modifier is specified, matching is done using the JIT
+"fast path" interface, \fBpcre2_jit_match()\fP, which skips some of the sanity
+checks that are done by \fBpcre2_match()\fP, and of course does not work when
+JIT is not supported. If \fBjitfast\fP is specified without \fBjit\fP, jit=7 is
+assumed.
+.P
+If the \fBjitverify\fP modifier is specified, information about the compiled
+pattern shows whether JIT compilation was or was not successful. If
+\fBjitverify\fP is specified without \fBjit\fP, jit=7 is assumed. If JIT
+compilation is successful when \fBjitverify\fP is set, the text "(JIT)" is
+added to the first output line after a match or non match when JIT-compiled
+code was actually used in the match.
+.
+.
+.SS "Setting a locale"
+.rs
+.sp
+The \fB/locale\fP modifier must specify the name of a locale, for example:
+.sp
+  /pattern/locale=fr_FR
+.sp
+The given locale is set, \fBpcre2_maketables()\fP is called to build a set of
+character tables for the locale, and this is then passed to
+\fBpcre2_compile()\fP when compiling the regular expression. The same tables
+are used when matching the following subject lines. The \fB/locale\fP modifier
+applies only to the pattern on which it appears, but can be given in a
+\fB#pattern\fP command if a default is needed. Setting a locale and alternate
+character tables are mutually exclusive.
+.
+.
+.SS "Showing pattern memory"
+.rs
+.sp
+The \fB/memory\fP modifier causes the size in bytes of the memory used to hold
+the compiled pattern to be output. This does not include the size of the
+\fBpcre2_code\fP block; it is just the actual compiled data. If the pattern is
+subsequently passed to the JIT compiler, the size of the JIT compiled code is
+also output. Here is an example:
+.sp
+    re> /a(b)c/jit,memory
+  Memory allocation (code space): 21
+  Memory allocation (JIT code): 1910
+.sp
+.
+.
+.SS "Limiting nested parentheses"
+.rs
+.sp
+The \fBparens_nest_limit\fP modifier sets a limit on the depth of nested
+parentheses in a pattern. Breaching the limit causes a compilation error.
+The default for the library is set when PCRE2 is built, but \fBpcre2test\fP
+sets its own default of 220, which is required for running the standard test
+suite.
+.
+.
+.SS "Using the POSIX wrapper API"
+.rs
+.sp
+The \fB/posix\fP modifier causes \fBpcre2test\fP to call PCRE2 via the POSIX
+wrapper API rather than its native API. This supports only the 8-bit library.
+When the POSIX API is being used, the following pattern modifiers set options
+for the \fBregcomp()\fP function:
+.sp
+  caseless           REG_ICASE
+  multiline          REG_NEWLINE
+  no_auto_capture    REG_NOSUB
+  dotall             REG_DOTALL     )
+  ungreedy           REG_UNGREEDY   ) These options are not part of
+  ucp                REG_UCP        )   the POSIX standard
+  utf                REG_UTF8       )
+.sp
+The \fBaftertext\fP and \fBallaftertext\fP subject modifiers work as described
+below. All other modifiers cause an error.
+.
+.
+.SS "Testing the stack guard feature"
+.rs
+.sp
+The \fB/stackguard\fP modifier is used to test the use of
+\fBpcre2_set_compile_recursion_guard()\fP, a function that is provided to
+enable stack availability to be checked during compilation (see the
+.\" HREF
+\fBpcre2api\fP
+.\"
+documentation for details). If the number specified by the modifier is greater
+than zero, \fBpcre2_set_compile_recursion_guard()\fP is called to set up
+callback from \fBpcre2_compile()\fP to a local function. The argument it
+receives is the current nesting parenthesis depth; if this is greater than the
+value given by the modifier, non-zero is returned, causing the compilation to
+be aborted.
+.
+.
+.SS "Using alternative character tables"
+.rs
+.sp
+The value specified for the \fB/tables\fP modifier must be one of the digits 0,
+1, or 2. It causes a specific set of built-in character tables to be passed to
+\fBpcre2_compile()\fP. This is used in the PCRE2 tests to check behaviour with
+different character tables. The digit specifies the tables as follows:
+.sp
+  0   do not pass any special character tables
+  1   the default ASCII tables, as distributed in
+        pcre2_chartables.c.dist
+  2   a set of tables defining ISO 8859 characters
+.sp
+In table 2, some characters whose codes are greater than 128 are identified as
+letters, digits, spaces, etc. Setting alternate character tables and a locale
+are mutually exclusive.
+.
+.
+.SS "Setting certain match controls"
+.rs
+.sp
+The following modifiers are really subject modifiers, and are described below.
+However, they may be included in a pattern's modifier list, in which case they
+are applied to every subject line that is processed with that pattern. They do
+not affect the compilation process.
+.sp
+      aftertext           show text after match
+      allaftertext        show text after captures
+      allcaptures         show all captures
+      allusedtext         show all consulted text
+  /g  global              global matching
+      mark                show mark values
+      replace=    specify a replacement string
+      startchar           show starting character when relevant
+.sp
+These modifiers may not appear in a \fB#pattern\fP command. If you want them as
+defaults, set them in a \fB#subject\fP command.
+.
+.
+.SS "Saving a compiled pattern"
+.rs
+.sp
+When a pattern with the \fBpush\fP modifier is successfully compiled, it is
+pushed onto a stack of compiled patterns, and \fBpcre2test\fP expects the next
+line to contain a new pattern (or a command) instead of a subject line. This
+facility is used when saving compiled patterns to a file, as described in the
+section entitled "Saving and restoring compiled patterns"
+.\" HTML 
+.\" 
+below.
+.\"
+The \fBpush\fP modifier is incompatible with compilation modifiers such as
+\fBglobal\fP that act at match time. Any that are specified are ignored, with a
+warning message, except for \fBreplace\fP, which causes an error. Note that,
+\fBjitverify\fP, which is allowed, does not carry through to any subsequent
+matching that uses this pattern.
+.
+.
+.SH "SUBJECT MODIFIERS"
+.rs
+.sp
+The modifiers that can appear in subject lines and the \fB#subject\fP
+command are of two types.
+.
+.
+.SS "Setting match options"
+.rs
+.sp
+The following modifiers set options for \fBpcre2_match()\fP or
+\fBpcre2_dfa_match()\fP. See
+.\" HREF
+\fBpcreapi\fP
+.\"
+for a description of their effects.
+.sp
+      anchored                  set PCRE2_ANCHORED
+      dfa_restart               set PCRE2_DFA_RESTART
+      dfa_shortest              set PCRE2_DFA_SHORTEST
+      no_utf_check              set PCRE2_NO_UTF_CHECK
+      notbol                    set PCRE2_NOTBOL
+      notempty                  set PCRE2_NOTEMPTY
+      notempty_atstart          set PCRE2_NOTEMPTY_ATSTART
+      noteol                    set PCRE2_NOTEOL
+      partial_hard (or ph)      set PCRE2_PARTIAL_HARD
+      partial_soft (or ps)      set PCRE2_PARTIAL_SOFT
+.sp
+The partial matching modifiers are provided with abbreviations because they
+appear frequently in tests.
+.P
+If the \fB/posix\fP modifier was present on the pattern, causing the POSIX
+wrapper API to be used, the only option-setting modifiers that have any effect
+are \fBnotbol\fP, \fBnotempty\fP, and \fBnoteol\fP, causing REG_NOTBOL,
+REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to \fBregexec()\fP.
+Any other modifiers cause an error.
+.
+.
+.SS "Setting match controls"
+.rs
+.sp
+The following modifiers affect the matching process or request additional
+information. Some of them may also be specified on a pattern line (see above),
+in which case they apply to every subject line that is matched against that
+pattern.
+.sp
+      aftertext                 show text after match
+      allaftertext              show text after captures
+      allcaptures               show all captures
+      allusedtext               show all consulted text (non-JIT only)
+      altglobal                 alternative global matching
+      callout_capture           show captures at callout time
+      callout_data=          set a value to pass via callouts
+      callout_fail=[:]    control callout failure
+      callout_none              do not supply a callout function
+      copy=     copy captured substring
+      dfa                       use \fBpcre2_dfa_match()\fP
+      find_limits               find match and recursion limits
+      get=      extract captured substring
+      getall                    extract all captured substrings
+  /g  global                    global matching
+      jitstack=              set size of JIT stack
+      mark                      show mark values
+      match_limit=>n>           set a match limit
+      memory                    show memory usage
+      offset=                set starting offset
+      ovector=               set size of output vector
+      recursion_limit=       set a recursion limit
+      replace=          specify a replacement string
+      startchar                 show startchar when relevant
+      zero_terminate            pass the subject as zero-terminated
+.sp
+The effects of these modifiers are described in the following sections.
+.
+.
+.SS "Showing more text"
+.rs
+.sp
+The \fBaftertext\fP modifier requests that as well as outputting the part of
+the subject string that matched the entire pattern, \fBpcre2test\fP should in
+addition output the remainder of the subject string. This is useful for tests
+where the subject contains multiple copies of the same substring. The
+\fBallaftertext\fP modifier requests the same action for captured substrings as
+well as the main matched substring. In each case the remainder is output on the
+following line with a plus character following the capture number.
+.P
+The \fBallusedtext\fP modifier requests that all the text that was consulted
+during a successful pattern match by the interpreter should be shown. This
+feature is not supported for JIT matching, and if requested with JIT it is
+ignored (with a warning message). Setting this modifier affects the output if
+there is a lookbehind at the start of a match, or a lookahead at the end, or if
+\eK is used in the pattern. Characters that precede or follow the start and end
+of the actual match are indicated in the output by '<' or '>' characters
+underneath them. Here is an example:
+.sp
+    re> /(?<=pqr)abc(?=xyz)/
+  data> 123pqrabcxyz456\e=allusedtext
+   0: pqrabcxyz
+      <<<   >>>
+.sp
+This shows that the matched string is "abc", with the preceding and following
+strings "pqr" and "xyz" having been consulted during the match (when processing
+the assertions).
+.P
+The \fBstartchar\fP modifier requests that the starting character for the match
+be indicated, if it is different to the start of the matched string. The only
+time when this occurs is when \eK has been processed as part of the match. In
+this situation, the output for the matched string is displayed from the
+starting character instead of from the match point, with circumflex characters
+under the earlier characters. For example:
+.sp
+    re> /abc\eKxyz/
+  data> abcxyz\e=startchar
+   0: abcxyz
+      ^^^
+.sp
+Unlike \fBallusedtext\fP, the \fBstartchar\fP modifier can be used with JIT.
+However, these two modifiers are mutually exclusive.
+.
+.
+.SS "Showing the value of all capture groups"
+.rs
+.sp
+The \fBallcaptures\fP modifier requests that the values of all potential
+captured parentheses be output after a match. By default, only those up to the
+highest one actually used in the match are output (corresponding to the return
+code from \fBpcre2_match()\fP). Groups that did not take part in the match
+are output as "".
+.
+.
+.SS "Testing callouts"
+.rs
+.sp
+A callout function is supplied when \fBpcre2test\fP calls the library matching
+functions, unless \fBcallout_none\fP is specified. If \fBcallout_capture\fP is
+set, the current captured groups are output when a callout occurs.
+.P
+The \fBcallout_fail\fP modifier can be given one or two numbers. If there is
+only one number, 1 is returned instead of 0 when a callout of that number is
+reached. If two numbers are given, 1 is returned when callout  is reached
+for the th time. Note that callouts with string arguments are always given
+the number zero. See "Callouts" below for a description of the output when a
+callout it taken.
+.P
+The \fBcallout_data\fP modifier can be given an unsigned or a negative number.
+This is set as the "user data" that is passed to the matching function, and
+passed back when the callout function is invoked. Any value other than zero is
+used as a return from \fBpcre2test\fP's callout function.
+.
+.
+.SS "Finding all matches in a string"
+.rs
+.sp
+Searching for all possible matches within a subject can be requested by the
+\fBglobal\fP or \fB/altglobal\fP modifier. After finding a match, the matching
+function is called again to search the remainder of the subject. The difference
+between \fBglobal\fP and \fBaltglobal\fP is that the former uses the
+\fIstart_offset\fP argument to \fBpcre2_match()\fP or \fBpcre2_dfa_match()\fP
+to start searching at a new point within the entire string (which is what Perl
+does), whereas the latter passes over a shortened subject. This makes a
+difference to the matching process if the pattern begins with a lookbehind
+assertion (including \eb or \eB).
+.P
+If an empty string is matched, the next match is done with the
+PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED flags set, in order to search for
+another, non-empty, match at the same point in the subject. If this match
+fails, the start offset is advanced, and the normal match is retried. This
+imitates the way Perl handles such cases when using the \fB/g\fP modifier or
+the \fBsplit()\fP function. Normally, the start offset is advanced by one
+character, but if the newline convention recognizes CRLF as a newline, and the
+current character is CR followed by LF, an advance of two characters occurs.
+.
+.
+.SS "Testing substring extraction functions"
+.rs
+.sp
+The \fBcopy\fP and \fBget\fP modifiers can be used to test the
+\fBpcre2_substring_copy_xxx()\fP and \fBpcre2_substring_get_xxx()\fP functions.
+They can be given more than once, and each can specify a group name or number,
+for example:
+.sp
+   abcd\e=copy=1,copy=3,get=G1
+.sp
+If the \fB#subject\fP command is used to set default copy and/or get lists,
+these can be unset by specifying a negative number to cancel all numbered
+groups and an empty name to cancel all named groups.
+.P
+The \fBgetall\fP modifier tests \fBpcre2_substring_list_get()\fP, which
+extracts all captured substrings.
+.P
+If the subject line is successfully matched, the substrings extracted by the
+convenience functions are output with C, G, or L after the string number
+instead of a colon. This is in addition to the normal full list. The string
+length (that is, the return from the extraction function) is given in
+parentheses after each substring, followed by the name when the extraction was
+by name.
+.
+.
+.SS "Testing the substitution function"
+.rs
+.sp
+If the \fBreplace\fP modifier is set, the \fBpcre2_substitute()\fP function is
+called instead of one of the matching functions. Unlike subject strings,
+\fBpcre2test\fP does not process replacement strings for escape sequences. In
+UTF mode, a replacement string is checked to see if it is a valid UTF-8 string.
+If so, it is correctly converted to a UTF string of the appropriate code unit
+width. If it is not a valid UTF-8 string, the individual code units are copied
+directly. This provides a means of passing an invalid UTF-8 string for testing
+purposes.
+.P
+If the \fBglobal\fP modifier is set, PCRE2_SUBSTITUTE_GLOBAL is passed to
+\fBpcre2_substitute()\fP. After a successful substitution, the modified string
+is output, preceded by the number of replacements. This may be zero if there
+were no matches. Here is a simple example of a substitution test:
+.sp
+  /abc/replace=xxx
+      =abc=abc=
+   1: =xxx=abc=
+      =abc=abc=\e=global
+   2: =xxx=xxx=
+.sp
+Subject and replacement strings should be kept relatively short for
+substitution tests, as fixed-size buffers are used. To make it easy to test for
+buffer overflow, if the replacement string starts with a number in square
+brackets, that number is passed to \fBpcre2_substitute()\fP as the size of the
+output buffer, with the replacement string starting at the next character. Here
+is an example that tests the edge case:
+.sp
+  /abc/
+      123abc123\e=replace=[10]XYZ
+   1: 123XYZ123
+      123abc123\e=replace=[9]XYZ
+  Failed: error -47: no more memory
+.sp
+A replacement string is ignored with POSIX and DFA matching. Specifying partial
+matching provokes an error return ("bad option value") from
+\fBpcre2_substitute()\fP.
+.
+.
+.SS "Setting the JIT stack size"
+.rs
+.sp
+The \fBjitstack\fP modifier provides a way of setting the maximum stack size
+that is used by the just-in-time optimization code. It is ignored if JIT
+optimization is not being used. The value is a number of kilobytes. Providing a
+stack that is larger than the default 32K is necessary only for very
+complicated patterns.
+.
+.
+.SS "Setting match and recursion limits"
+.rs
+.sp
+The \fBmatch_limit\fP and \fBrecursion_limit\fP modifiers set the appropriate
+limits in the match context. These values are ignored when the
+\fBfind_limits\fP modifier is specified.
+.
+.
+.SS "Finding minimum limits"
+.rs
+.sp
+If the \fBfind_limits\fP modifier is present, \fBpcre2test\fP calls
+\fBpcre2_match()\fP several times, setting different values in the match
+context via \fBpcre2_set_match_limit()\fP and \fBpcre2_set_recursion_limit()\fP
+until it finds the minimum values for each parameter that allow
+\fBpcre2_match()\fP to complete without error.
+.P
+If JIT is being used, only the match limit is relevant. If DFA matching is
+being used, neither limit is relevant, and this modifier is ignored (with a
+warning message).
+.P
+The \fImatch_limit\fP number is a measure of the amount of backtracking
+that takes place, and learning the minimum value can be instructive. For most
+simple matches, the number is quite small, but for patterns with very large
+numbers of matching possibilities, it can become large very quickly with
+increasing length of subject string. The \fImatch_limit_recursion\fP number is
+a measure of how much stack (or, if PCRE2 is compiled with NO_RECURSE, how much
+heap) memory is needed to complete the match attempt.
+.
+.
+.SS "Showing MARK names"
+.rs
+.sp
+.P
+The \fBmark\fP modifier causes the names from backtracking control verbs that
+are returned from calls to \fBpcre2_match()\fP to be displayed. If a mark is
+returned for a match, non-match, or partial match, \fBpcre2test\fP shows it.
+For a match, it is on a line by itself, tagged with "MK:". Otherwise, it
+is added to the non-match message.
+.
+.
+.SS "Showing memory usage"
+.rs
+.sp
+The \fBmemory\fP modifier causes \fBpcre2test\fP to log all memory allocation
+and freeing calls that occur during a match operation.
+.
+.
+.SS "Setting a starting offset"
+.rs
+.sp
+The \fBoffset\fP modifier sets an offset in the subject string at which
+matching starts. Its value is a number of code units, not characters.
+.
+.
+.SS "Setting the size of the output vector"
+.rs
+.sp
+The \fBovector\fP modifier applies only to the subject line in which it
+appears, though of course it can also be used to set a default in a
+\fB#subject\fP command. It specifies the number of pairs of offsets that are
+available for storing matching information. The default is 15.
+.P
+A value of zero is useful when testing the POSIX API because it causes
+\fBregexec()\fP to be called with a NULL capture vector. When not testing the
+POSIX API, a value of zero is used to cause
+\fBpcre2_match_data_create_from_pattern()\fP to be called, in order to create a
+match block of exactly the right size for the pattern. (It is not possible to
+create a match block with a zero-length ovector; there is always at least one
+pair of offsets.)
+.
+.
+.SS "Passing the subject as zero-terminated"
+.rs
+.sp
+By default, the subject string is passed to a native API matching function with
+its correct length. In order to test the facility for passing a zero-terminated
+string, the \fBzero_terminate\fP modifier is provided. It causes the length to
+be passed as PCRE2_ZERO_TERMINATED. (When matching via the POSIX interface,
+this modifier has no effect, as there is no facility for passing a length.)
+.P
+When testing \fBpcre2_substitute()\fP, this modifier also has the effect of
+passing the replacement string as zero-terminated.
+.
+.
+.SH "THE ALTERNATIVE MATCHING FUNCTION"
+.rs
+.sp
+By default, \fBpcre2test\fP uses the standard PCRE2 matching function,
+\fBpcre2_match()\fP to match each subject line. PCRE2 also supports an
+alternative matching function, \fBpcre2_dfa_match()\fP, which operates in a
+different way, and has some restrictions. The differences between the two
+functions are described in the
+.\" HREF
+\fBpcre2matching\fP
+.\"
+documentation.
+.P
+If the \fBdfa\fP modifier is set, the alternative matching function is used.
+This function finds all possible matches at a given point in the subject. If,
+however, the \fBdfa_shortest\fP modifier is set, processing stops after the
+first match is found. This is always the shortest possible match.
+.
+.
+.SH "DEFAULT OUTPUT FROM pcre2test"
+.rs
+.sp
+This section describes the output when the normal matching function,
+\fBpcre2_match()\fP, is being used.
+.P
+When a match succeeds, \fBpcre2test\fP outputs the list of captured substrings,
+starting with number 0 for the string that matched the whole pattern.
+Otherwise, it outputs "No match" when the return is PCRE2_ERROR_NOMATCH, or
+"Partial match:" followed by the partially matching substring when the
+return is PCRE2_ERROR_PARTIAL. (Note that this is the
+entire substring that was inspected during the partial match; it may include
+characters before the actual match start if a lookbehind assertion, \eK, \eb,
+or \eB was involved.)
+.P
+For any other return, \fBpcre2test\fP outputs the PCRE2 negative error number
+and a short descriptive phrase. If the error is a failed UTF string check, the
+code unit offset of the start of the failing character is also output. Here is
+an example of an interactive \fBpcre2test\fP run.
+.sp
+  $ pcre2test
+  PCRE2 version 9.00 2014-05-10
+.sp
+    re> /^abc(\ed+)/
+  data> abc123
+   0: abc123
+   1: 123
+  data> xyz
+  No match
+.sp
+Unset capturing substrings that are not followed by one that is set are not
+shown by \fBpcre2test\fP unless the \fBallcaptures\fP modifier is specified. In
+the following example, there are two capturing substrings, but when the first
+data line is matched, the second, unset substring is not shown. An "internal"
+unset substring is shown as "", as for the second data line.
+.sp
+    re> /(a)|(b)/
+  data> a
+   0: a
+   1: a
+  data> b
+   0: b
+   1: 
+   2: b
+.sp
+If the strings contain any non-printing characters, they are output as \exhh
+escapes if the value is less than 256 and UTF mode is not set. Otherwise they
+are output as \ex{hh...} escapes. See below for the definition of non-printing
+characters. If the \fB/aftertext\fP modifier is set, the output for substring
+0 is followed by the the rest of the subject string, identified by "0+" like
+this:
+.sp
+    re> /cat/aftertext
+  data> cataract
+   0: cat
+   0+ aract
+.sp
+If global matching is requested, the results of successive matching attempts
+are output in sequence, like this:
+.sp
+    re> /\eBi(\ew\ew)/g
+  data> Mississippi
+   0: iss
+   1: ss
+   0: iss
+   1: ss
+   0: ipp
+   1: pp
+.sp
+"No match" is output only if the first match attempt fails. Here is an example
+of a failure message (the offset 4 that is specified by the \fBoffset\fP
+modifier is past the end of the subject string):
+.sp
+    re> /xyz/
+  data> xyz\e=offset=4
+  Error -24 (bad offset value)
+.P
+Note that whereas patterns can be continued over several lines (a plain ">"
+prompt is used for continuations), subject lines may not. However newlines can
+be included in a subject by means of the \en escape (or \er, \er\en, etc.,
+depending on the newline sequence setting).
+.
+.
+.
+.SH "OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION"
+.rs
+.sp
+When the alternative matching function, \fBpcre2_dfa_match()\fP, is used, the
+output consists of a list of all the matches that start at the first point in
+the subject where there is at least one match. For example:
+.sp
+    re> /(tang|tangerine|tan)/
+  data> yellow tangerine\e=dfa
+   0: tangerine
+   1: tang
+   2: tan
+.sp
+Using the normal matching function on this data finds only "tang". The
+longest matching string is always given first (and numbered zero). After a
+PCRE2_ERROR_PARTIAL return, the output is "Partial match:", followed by the
+partially matching substring. Note that this is the entire substring that was
+inspected during the partial match; it may include characters before the actual
+match start if a lookbehind assertion, \eb, or \eB was involved. (\eK is not
+supported for DFA matching.)
+.P
+If global matching is requested, the search for further matches resumes
+at the end of the longest match. For example:
+.sp
+    re> /(tang|tangerine|tan)/g
+  data> yellow tangerine and tangy sultana\e=dfa
+   0: tangerine
+   1: tang
+   2: tan
+   0: tang
+   1: tan
+   0: tan
+.sp
+The alternative matching function does not support substring capture, so the
+modifiers that are concerned with captured substrings are not relevant.
+.
+.
+.SH "RESTARTING AFTER A PARTIAL MATCH"
+.rs
+.sp
+When the alternative matching function has given the PCRE2_ERROR_PARTIAL
+return, indicating that the subject partially matched the pattern, you can
+restart the match with additional subject data by means of the
+\fBdfa_restart\fP modifier. For example:
+.sp
+    re> /^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$/
+  data> 23ja\e=P,dfa
+  Partial match: 23ja
+  data> n05\e=dfa,dfa_restart
+   0: n05
+.sp
+For further information about partial matching, see the
+.\" HREF
+\fBpcre2partial\fP
+.\"
+documentation.
+.
+.
+.SH CALLOUTS
+.rs
+.sp
+If the pattern contains any callout requests, \fBpcre2test\fP's callout
+function is called during matching unless \fBcallout_none\fP is specified.
+This works with both matching functions.
+.P
+The callout function in \fBpcre2test\fP returns zero (carry on matching) by
+default, but you can use a \fBcallout_fail\fP modifier in a subject line (as
+described above) to change this and other parameters of the callout.
+.P
+Inserting callouts can be helpful when using \fBpcre2test\fP to check
+complicated regular expressions. For further information about callouts, see
+the
+.\" HREF
+\fBpcre2callout\fP
+.\"
+documentation.
+.P
+The output for callouts with numerical arguments and those with string
+arguments is slightly different.
+.
+.
+.SS "Callouts with numerical arguments"
+.rs
+.sp
+By default, the callout function displays the callout number, the start and
+current positions in the subject text at the callout time, and the next pattern
+item to be tested. For example:
+.sp
+  --->pqrabcdef
+    0    ^  ^     \ed
+.sp
+This output indicates that callout number 0 occurred for a match attempt
+starting at the fourth character of the subject string, when the pointer was at
+the seventh character, and when the next pattern item was \ed. Just
+one circumflex is output if the start and current positions are the same.
+.P
+Callouts numbered 255 are assumed to be automatic callouts, inserted as a
+result of the \fB/auto_callout\fP pattern modifier. In this case, instead of
+showing the callout number, the offset in the pattern, preceded by a plus, is
+output. For example:
+.sp
+    re> /\ed?[A-E]\e*/auto_callout
+  data> E*
+  --->E*
+   +0 ^      \ed?
+   +3 ^      [A-E]
+   +8 ^^     \e*
+  +10 ^ ^
+   0: E*
+.sp
+If a pattern contains (*MARK) items, an additional line is output whenever
+a change of latest mark is passed to the callout function. For example:
+.sp
+    re> /a(*MARK:X)bc/auto_callout
+  data> abc
+  --->abc
+   +0 ^       a
+   +1 ^^      (*MARK:X)
+  +10 ^^      b
+  Latest Mark: X
+  +11 ^ ^     c
+  +12 ^  ^
+   0: abc
+.sp
+The mark changes between matching "a" and "b", but stays the same for the rest
+of the match, so nothing more is output. If, as a result of backtracking, the
+mark reverts to being unset, the text "" is output.
+.
+.
+.SS "Callouts with string arguments"
+.rs
+.sp
+The output for a callout with a string argument is similar, except that instead
+of outputting a callout number before the position indicators, the callout
+string and its offset in the pattern string are output before the reflection of
+the subject string, and the subject string is reflected for each callout. For
+example:
+.sp
+    re> /^ab(?C'first')cd(?C"second")ef/
+  data> abcdefg
+  Callout (7): 'first'
+  --->abcdefg
+      ^ ^         c
+  Callout (20): "second"
+  --->abcdefg
+      ^   ^       e
+   0: abcdef
+.sp
+.
+.
+.
+.SH "NON-PRINTING CHARACTERS"
+.rs
+.sp
+When \fBpcre2test\fP is outputting text in the compiled version of a pattern,
+bytes other than 32-126 are always treated as non-printing characters and are
+therefore shown as hex escapes.
+.P
+When \fBpcre2test\fP is outputting text that is a matched part of a subject
+string, it behaves in the same way, unless a different locale has been set for
+the pattern (using the \fB/locale\fP modifier). In this case, the
+\fBisprint()\fP function is used to distinguish printing and non-printing
+characters.
+.
+.
+.
+.\" HTML 
+.SH "SAVING AND RESTORING COMPILED PATTERNS"
+.rs
+.sp
+It is possible to save compiled patterns on disc or elsewhere, and reload them
+later, subject to a number of restrictions. JIT data cannot be saved. The host
+on which the patterns are reloaded must be running the same version of PCRE2,
+with the same code unit width, and must also have the same endianness, pointer
+width and PCRE2_SIZE type. Before compiled patterns can be saved they must be
+serialized, that is, converted to a stream of bytes. A single byte stream may
+contain any number of compiled patterns, but they must all use the same
+character tables. A single copy of the tables is included in the byte stream
+(its size is 1088 bytes).
+.P
+The functions whose names begin with \fBpcre2_serialize_\fP are used
+for serializing and de-serializing. They are described in the
+.\" HREF
+\fBpcre2serialize\fP
+.\"
+documentation. In this section we describe the features of \fBpcre2test\fP that
+can be used to test these functions.
+.P
+When a pattern with \fBpush\fP modifier is successfully compiled, it is pushed
+onto a stack of compiled patterns, and \fBpcre2test\fP expects the next line to
+contain a new pattern (or command) instead of a subject line. By this means, a
+number of patterns can be compiled and retained. The \fBpush\fP modifier is
+incompatible with \fBposix\fP, and control modifiers that act at match time are
+ignored (with a message). The \fBjitverify\fP modifier applies only at compile
+time. The command
+.sp
+  #save 
+.sp
+causes all the stacked patterns to be serialized and the result written to the
+named file. Afterwards, all the stacked patterns are freed. The command
+.sp
+  #load 
+.sp
+reads the data in the file, and then arranges for it to be de-serialized, with
+the resulting compiled patterns added to the pattern stack. The pattern on the
+top of the stack can be retrieved by the #pop command, which must be followed
+by lines of subjects that are to be matched with the pattern, terminated as
+usual by an empty line or end of file. This command may be followed by a
+modifier list containing only
+.\" HTML 
+.\" 
+control modifiers
+.\"
+that act after a pattern has been compiled. In particular, \fBhex\fP,
+\fBposix\fP, and \fBpush\fP are not allowed, nor are any
+.\" HTML 
+.\" 
+option-setting modifiers.
+.\"
+The JIT modifiers are, however permitted. Here is an example that saves and
+reloads two patterns.
+.sp
+  /abc/push
+  /xyz/push
+  #save tempfile
+  #load tempfile
+  #pop info
+  xyz
+.sp
+  #pop jit,bincode
+  abc
+.sp
+If \fBjitverify\fP is used with #pop, it does not automatically imply
+\fBjit\fP, which is different behaviour from when it is used on a pattern.
+.
+.
+.
+.SH "SEE ALSO"
+.rs
+.sp
+\fBpcre2\fP(3), \fBpcre2api\fP(3), \fBpcre2callout\fP(3),
+\fBpcre2jit\fP, \fBpcre2matching\fP(3), \fBpcre2partial\fP(d),
+\fBpcre2pattern\fP(3), \fBpcre2serialize\fP(3).
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel
+University Computing Service
+Cambridge, England.
+.fi
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 20 May 2015
+Copyright (c) 1997-2015 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/doc/pcre2test.txt b/pcre2-10.20/doc/pcre2test.txt
new file mode 100644
index 000000000..c022a9ce5
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2test.txt
@@ -0,0 +1,1334 @@
+PCRE2TEST(1)                General Commands Manual               PCRE2TEST(1)
+
+
+
+NAME
+       pcre2test - a program for testing Perl-compatible regular expressions.
+
+SYNOPSIS
+
+       pcre2test [options] [input file [output file]]
+
+       pcre2test is a test program for the PCRE2 regular expression libraries,
+       but it can also be used for  experimenting  with  regular  expressions.
+       This  document  describes the features of the test program; for details
+       of the regular expressions themselves, see the pcre2pattern  documenta-
+       tion.  For  details  of  the  PCRE2  library  function  calls and their
+       options, see the pcre2api documentation.
+
+       The input for pcre2test is a sequence of  regular  expression  patterns
+       and  subject  strings  to  be matched. There are also command lines for
+       setting defaults and controlling some special actions. The output shows
+       the  result  of  each  match attempt. Modifiers on external or internal
+       command lines, the patterns, and the subject lines specify PCRE2  func-
+       tion  options, control how the subject is processed, and what output is
+       produced.
+
+       As the original fairly simple PCRE library evolved,  it  acquired  many
+       different  features,  and  as  a  result, the original pcretest program
+       ended up with a lot of options in a messy, arcane syntax,  for  testing
+       all the features. The move to the new PCRE2 API provided an opportunity
+       to re-implement the test program as pcre2test, with a cleaner  modifier
+       syntax.  Nevertheless,  there are still many obscure modifiers, some of
+       which are specifically designed for use in conjunction  with  the  test
+       script  and  data  files that are distributed as part of PCRE2. All the
+       modifiers are documented here, some  without  much  justification,  but
+       many  of  them  are  unlikely  to  be  of  use  except when testing the
+       libraries.
+
+
+PCRE2's 8-BIT, 16-BIT AND 32-BIT LIBRARIES
+
+       Different versions of the PCRE2 library can be built to support charac-
+       ter  strings  that  are encoded in 8-bit, 16-bit, or 32-bit code units.
+       One, two, or  all  three  of  these  libraries  may  be  simultaneously
+       installed. The pcre2test program can be used to test all the libraries.
+       However, its own input and output are  always  in  8-bit  format.  When
+       testing  the  16-bit  or 32-bit libraries, patterns and subject strings
+       are converted to 16- or  32-bit  format  before  being  passed  to  the
+       library  functions.  Results are converted back to 8-bit code units for
+       output.
+
+       In the rest of this document, the names of library functions and struc-
+       tures  are  given  in  generic  form,  for example, pcre_compile(). The
+       actual names used in the libraries have a suffix _8, _16,  or  _32,  as
+       appropriate.
+
+
+INPUT ENCODING
+
+       Input  to  pcre2test is processed line by line, either by calling the C
+       library's fgets() function, or via the libreadline library (see below).
+       The  input  is  processed using using C's string functions, so must not
+       contain binary zeroes, even though in Unix-like  environments,  fgets()
+       treats any bytes other than newline as data characters. In some Windows
+       environments character 26 (hex 1A) causes an immediate end of file, and
+       no further data is read.
+
+       For  maximum portability, therefore, it is safest to avoid non-printing
+       characters in pcre2test input files. There is a facility for specifying
+       a pattern's characters as hexadecimal pairs, thus making it possible to
+       include binary zeroes in a pattern for testing purposes. Subject  lines
+       are processed for backslash escapes, which makes it possible to include
+       any data value.
+
+
+COMMAND LINE OPTIONS
+
+       -8        If the 8-bit library has been built, this option causes it to
+                 be  used  (this is the default). If the 8-bit library has not
+                 been built, this option causes an error.
+
+       -16       If the 16-bit library has been built, this option  causes  it
+                 to  be  used. If only the 16-bit library has been built, this
+                 is the default. If the 16-bit library  has  not  been  built,
+                 this option causes an error.
+
+       -32       If  the  32-bit library has been built, this option causes it
+                 to be used. If only the 32-bit library has been  built,  this
+                 is  the  default.  If  the 32-bit library has not been built,
+                 this option causes an error.
+
+       -b        Behave as if each pattern has the /fullbincode modifier;  the
+                 full internal binary form of the pattern is output after com-
+                 pilation.
+
+       -C        Output the version number  of  the  PCRE2  library,  and  all
+                 available  information  about  the optional features that are
+                 included, and then  exit  with  zero  exit  code.  All  other
+                 options are ignored.
+
+       -C option Output  information  about a specific build-time option, then
+                 exit. This functionality is intended for use in scripts  such
+                 as  RunTest.  The  following options output the value and set
+                 the exit code as indicated:
+
+                   ebcdic-nl  the code for LF (= NL) in an EBCDIC environment:
+                                0x15 or 0x25
+                                0 if used in an ASCII environment
+                                exit code is always 0
+                   linksize   the configured internal link size (2, 3, or 4)
+                                exit code is set to the link size
+                   newline    the default newline setting:
+                                CR, LF, CRLF, ANYCRLF, or ANY
+                                exit code is always 0
+                   bsr        the default setting for what \R matches:
+                                ANYCRLF or ANY
+                                exit code is always 0
+
+                 The following options output 1 for true or 0 for  false,  and
+                 set the exit code to the same value:
+
+                   ebcdic     compiled for an EBCDIC environment
+                   jit        just-in-time support is available
+                   pcre2-16   the 16-bit library was built
+                   pcre2-32   the 32-bit library was built
+                   pcre2-8    the 8-bit library was built
+                   unicode    Unicode support is available
+
+                 If  an  unknown  option is given, an error message is output;
+                 the exit code is 0.
+
+       -d        Behave as if each pattern has the debug modifier; the  inter-
+                 nal form and information about the compiled pattern is output
+                 after compilation; -d is equivalent to -b -i.
+
+       -dfa      Behave as if each subject line has the dfa modifier; matching
+                 is  done  using the pcre2_dfa_match() function instead of the
+                 default pcre2_match().
+
+       -help     Output a brief summary these options and then exit.
+
+       -i        Behave as if each pattern has the /info modifier; information
+                 about the compiled pattern is given after compilation.
+
+       -jit      Behave  as  if  each pattern line has the jit modifier; after
+                 successful compilation, each pattern is passed to  the  just-
+                 in-time compiler, if available.
+
+       -pattern modifier-list
+                 Behave as if each pattern line contains the given modifiers.
+
+       -q        Do not output the version number of pcre2test at the start of
+                 execution.
+
+       -S size   On Unix-like systems, set the size of the run-time  stack  to
+                 size megabytes.
+
+       -subject modifier-list
+                 Behave as if each subject line contains the given modifiers.
+
+       -t        Run  each compile and match many times with a timer, and out-
+                 put the resulting times per compile or  match.  When  JIT  is
+                 used,  separate  times  are given for the initial compile and
+                 the JIT compile. You can control  the  number  of  iterations
+                 that  are used for timing by following -t with a number (as a
+                 separate item on the command line). For  example,  "-t  1000"
+                 iterates 1000 times. The default is to iterate 500,000 times.
+
+       -tm       This is like -t except that it times only the matching phase,
+                 not the compile phase.
+
+       -T -TM    These behave like -t and -tm, but in addition, at the end  of
+                 a  run, the total times for all compiles and matches are out-
+                 put.
+
+       -version  Output the PCRE2 version number and then exit.
+
+
+DESCRIPTION
+
+       If pcre2test is given two filename arguments, it reads from  the  first
+       and writes to the second. If the first name is "-", input is taken from
+       the standard input. If pcre2test is given only one argument,  it  reads
+       from that file and writes to stdout. Otherwise, it reads from stdin and
+       writes to stdout.
+
+       When pcre2test is built, a configuration option  can  specify  that  it
+       should  be linked with the libreadline or libedit library. When this is
+       done, if the input is from a terminal, it is read using the  readline()
+       function. This provides line-editing and history facilities. The output
+       from the -help option states whether or not readline() will be used.
+
+       The program handles any number of tests, each of which  consists  of  a
+       set  of input lines. Each set starts with a regular expression pattern,
+       followed by any number of subject lines to be matched against that pat-
+       tern. In between sets of test data, command lines that begin with # may
+       appear. This file format, with some restrictions, can also be processed
+       by  the perltest.sh script that is distributed with PCRE2 as a means of
+       checking that the behaviour of PCRE2 and Perl is the same.
+
+       When the input is a terminal, pcre2test prompts for each line of input,
+       using  "re>"  to prompt for regular expression patterns, and "data>" to
+       prompt for subject lines. Command lines starting with # can be  entered
+       only in response to the "re>" prompt.
+
+       Each  subject line is matched separately and independently. If you want
+       to do multi-line matches, you have to use the \n escape sequence (or \r
+       or  \r\n,  etc.,  depending on the newline setting) in a single line of
+       input to encode the newline sequences. There is no limit on the  length
+       of  subject  lines; the input buffer is automatically extended if it is
+       too small. There is a replication feature that  makes  it  possible  to
+       generate long subject lines without having to supply them explicitly.
+
+       An  empty  line  or  the end of the file signals the end of the subject
+       lines for a test, at which point a  new  pattern  or  command  line  is
+       expected if there is still input to be read.
+
+
+COMMAND LINES
+
+       In  between sets of test data, a line that begins with # is interpreted
+       as a command line. If the first character is followed by white space or
+       an  exclamation  mark,  the  line is treated as a comment, and ignored.
+       Otherwise, the following commands are recognized:
+
+         #forbid_utf
+
+       Subsequent  patterns  automatically  have   the   PCRE2_NEVER_UTF   and
+       PCRE2_NEVER_UCP  options  set, which locks out the use of the PCRE2_UTF
+       and PCRE2_UCP options and the use of (*UTF) and (*UCP) at the start  of
+       patterns.  This  command  also  forces an error if a subsequent pattern
+       contains any occurrences of \P, \p, or \X, which  are  still  supported
+       when  PCRE2_UTF  is not set, but which require Unicode property support
+       to be included in the library.
+
+       This is a trigger guard that is used in test files to ensure  that  UTF
+       or  Unicode property tests are not accidentally added to files that are
+       used when Unicode support is  not  included  in  the  library.  Setting
+       PCRE2_NEVER_UTF  and  PCRE2_NEVER_UCP as a default can also be obtained
+       by the use of #pattern; the difference is that  #forbid_utf  cannot  be
+       unset,  and the automatic options are not displayed in pattern informa-
+       tion, to avoid cluttering up test output.
+
+         #load 
+
+       This command is used to load a set of precompiled patterns from a file,
+       as  described  in  the  section entitled "Saving and restoring compiled
+       patterns" below.
+
+         #pattern 
+
+       This command sets a default modifier list that applies  to  all  subse-
+       quent patterns. Modifiers on a pattern can change these settings.
+
+         #perltest
+
+       The  appearance of this line causes all subsequent modifier settings to
+       be checked for compatibility with the perltest.sh script, which is used
+       to  confirm that Perl gives the same results as PCRE2. Also, apart from
+       comment lines, none of the other command lines are  permitted,  because
+       they  and  many  of the modifiers are specific to pcre2test, and should
+       not be used in test files that are also processed by  perltest.sh.  The
+       #perltest  command  helps detect tests that are accidentally put in the
+       wrong file.
+
+         #pop []
+
+       This command is used to manipulate the stack of compiled  patterns,  as
+       described  in  the section entitled "Saving and restoring compiled pat-
+       terns" below.
+
+         #save 
+
+       This command is used to save a set of compiled patterns to a  file,  as
+       described  in  the section entitled "Saving and restoring compiled pat-
+       terns" below.
+
+         #subject 
+
+       This command sets a default modifier list that applies  to  all  subse-
+       quent  subject lines. Modifiers on a subject line can change these set-
+       tings.
+
+
+MODIFIER SYNTAX
+
+       Modifier lists are used with both pattern and subject lines. Items in a
+       list  are  separated by commas and optional white space. Some modifiers
+       may be given for both patterns and subject lines,  whereas  others  are
+       valid  for  one  or  the other only. Each modifier has a long name, for
+       example "anchored", and some of them must be followed by an equals sign
+       and a value, for example, "offset=12".  Modifiers that do not take val-
+       ues may be preceded by a minus sign to turn off a previous setting.
+
+       A few of the more common modifiers can also be specified as single let-
+       ters,  for  example "i" for "caseless". In documentation, following the
+       Perl convention, these are written with a slash ("the /i modifier") for
+       clarity.  Abbreviated  modifiers  must all be concatenated in the first
+       item of a modifier list. If the first item is not recognized as a  long
+       modifier  name, it is interpreted as a sequence of these abbreviations.
+       For example:
+
+         /abc/ig,newline=cr,jit=3
+
+       This is a pattern line whose modifier list starts with  two  one-letter
+       modifiers  (/i  and  /g).  The lower-case abbreviated modifiers are the
+       same as used in Perl.
+
+
+PATTERN SYNTAX
+
+       A pattern line must start with one of the following characters  (common
+       symbols, excluding pattern meta-characters):
+
+         / ! " ' ` - = _ : ; , % & @ ~
+
+       This  is  interpreted  as the pattern's delimiter. A regular expression
+       may be continued over several input lines, in which  case  the  newline
+       characters are included within it. It is possible to include the delim-
+       iter within the pattern by escaping it with a backslash, for example
+
+         /abc\/def/
+
+       If you do this, the escape and the delimiter form part of the  pattern,
+       but since the delimiters are all non-alphanumeric, this does not affect
+       its interpretation. If the terminating delimiter  is  immediately  fol-
+       lowed by a backslash, for example,
+
+         /abc/\
+
+       then  a  backslash  is added to the end of the pattern. This is done to
+       provide a way of testing the error condition that arises if  a  pattern
+       finishes with a backslash, because
+
+         /abc\/
+
+       is  interpreted as the first line of a pattern that starts with "abc/",
+       causing pcre2test to read the next line as a continuation of the  regu-
+       lar expression.
+
+       A pattern can be followed by a modifier list (details below).
+
+
+SUBJECT LINE SYNTAX
+
+       Before    each   subject   line   is   passed   to   pcre2_match()   or
+       pcre2_dfa_match(), leading and trailing white space is removed, and the
+       line is scanned for backslash escapes. The following provide a means of
+       encoding non-printing characters in a visible way:
+
+         \a         alarm (BEL, \x07)
+         \b         backspace (\x08)
+         \e         escape (\x27)
+         \f         form feed (\x0c)
+         \n         newline (\x0a)
+         \r         carriage return (\x0d)
+         \t         tab (\x09)
+         \v         vertical tab (\x0b)
+         \nnn       octal character (up to 3 octal digits); always
+                      a byte unless > 255 in UTF-8 or 16-bit or 32-bit mode
+         \o{dd...}  octal character (any number of octal digits}
+         \xhh       hexadecimal byte (up to 2 hex digits)
+         \x{hh...}  hexadecimal character (any number of hex digits)
+
+       The use of \x{hh...} is not dependent on the use of the utf modifier on
+       the  pattern. It is recognized always. There may be any number of hexa-
+       decimal digits inside the braces; invalid  values  provoke  error  mes-
+       sages.
+
+       Note  that  \xhh  specifies one byte rather than one character in UTF-8
+       mode; this makes it possible to construct invalid UTF-8  sequences  for
+       testing  purposes.  On the other hand, \x{hh} is interpreted as a UTF-8
+       character in UTF-8 mode, generating more than one byte if the value  is
+       greater  than  127.   When testing the 8-bit library not in UTF-8 mode,
+       \x{hh} generates one byte for values less than 256, and causes an error
+       for greater values.
+
+       In UTF-16 mode, all 4-digit \x{hhhh} values are accepted. This makes it
+       possible to construct invalid UTF-16 sequences for testing purposes.
+
+       In UTF-32 mode, all 4- to 8-digit \x{...}  values  are  accepted.  This
+       makes  it  possible  to  construct invalid UTF-32 sequences for testing
+       purposes.
+
+       There is a special backslash sequence that specifies replication of one
+       or more characters:
+
+         \[]{}
+
+       This  makes  it possible to test long strings without having to provide
+       them as part of the file. For example:
+
+         \[abc]{4}
+
+       is converted to "abcabcabcabc". This feature does not support  nesting.
+       To include a closing square bracket in the characters, code it as \x5D.
+
+       A  backslash  followed  by  an equals sign marks the end of the subject
+       string and the start of a modifier list. For example:
+
+         abc\=notbol,notempty
+
+       A backslash followed  by  any  other  non-alphanumeric  character  just
+       escapes that character. A backslash followed by anything else causes an
+       error. However, if the very last character in the line is  a  backslash
+       (and  there  is  no  modifier list), it is ignored. This gives a way of
+       passing an empty line as data, since a real empty line  terminates  the
+       data input.
+
+
+PATTERN MODIFIERS
+
+       There are three types of modifier that can appear in pattern lines, two
+       of which may also be used in a #pattern command. A  pattern's  modifier
+       list can add to or override default modifiers that were set by a previ-
+       ous #pattern command.
+
+   Setting compilation options
+
+       The following modifiers set options for pcre2_compile(). The most  com-
+       mon  ones  have single-letter abbreviations. See pcreapi for a descrip-
+       tion of their effects.
+
+             allow_empty_class         set PCRE2_ALLOW_EMPTY_CLASS
+             alt_bsux                  set PCRE2_ALT_BSUX
+             alt_circumflex            set PCRE2_ALT_CIRCUMFLEX
+             anchored                  set PCRE2_ANCHORED
+             auto_callout              set PCRE2_AUTO_CALLOUT
+         /i  caseless                  set PCRE2_CASELESS
+             dollar_endonly            set PCRE2_DOLLAR_ENDONLY
+         /s  dotall                    set PCRE2_DOTALL
+             dupnames                  set PCRE2_DUPNAMES
+         /x  extended                  set PCRE2_EXTENDED
+             firstline                 set PCRE2_FIRSTLINE
+             match_unset_backref       set PCRE2_MATCH_UNSET_BACKREF
+         /m  multiline                 set PCRE2_MULTILINE
+             never_backslash_c         set PCRE2_NEVER_BACKSLASH_C
+             never_ucp                 set PCRE2_NEVER_UCP
+             never_utf                 set PCRE2_NEVER_UTF
+             no_auto_capture           set PCRE2_NO_AUTO_CAPTURE
+             no_auto_possess           set PCRE2_NO_AUTO_POSSESS
+             no_dotstar_anchor         set PCRE2_NO_DOTSTAR_ANCHOR
+             no_start_optimize         set PCRE2_NO_START_OPTIMIZE
+             no_utf_check              set PCRE2_NO_UTF_CHECK
+             ucp                       set PCRE2_UCP
+             ungreedy                  set PCRE2_UNGREEDY
+             utf                       set PCRE2_UTF
+
+       As well as turning on the PCRE2_UTF option, the utf modifier causes all
+       non-printing  characters  in  output  strings  to  be printed using the
+       \x{hh...} notation. Otherwise, those less than 0x100 are output in  hex
+       without the curly brackets.
+
+   Setting compilation controls
+
+       The  following  modifiers  affect  the  compilation  process or request
+       information about the pattern:
+
+             bsr=[anycrlf|unicode]     specify \R handling
+         /B  bincode                   show binary code without lengths
+             callout_info              show callout information
+             debug                     same as info,fullbincode
+             fullbincode               show binary code with lengths
+         /I  info                      show info about compiled pattern
+             hex                       pattern is coded in hexadecimal
+             jit[=]            use JIT
+             jitfast                   use JIT fast path
+             jitverify                 verify JIT use
+             locale=             use this locale
+             memory                    show memory used
+             newline=            set newline type
+             parens_nest_limit=     set maximum parentheses depth
+             posix                     use the POSIX API
+             push                      push compiled pattern onto the stack
+             stackguard=       test the stackguard feature
+             tables=[0|1|2]            select internal tables
+
+       The effects of these modifiers are described in the following sections.
+
+   Newline and \R handling
+
+       The bsr modifier specifies what \R in a pattern should match. If it  is
+       set  to  "anycrlf",  \R  matches  CR, LF, or CRLF only. If it is set to
+       "unicode", \R matches any Unicode  newline  sequence.  The  default  is
+       specified when PCRE2 is built, with the default default being Unicode.
+
+       The  newline  modifier specifies which characters are to be interpreted
+       as newlines, both in the pattern and in subject lines. The type must be
+       one of CR, LF, CRLF, ANYCRLF, or ANY (in upper or lower case).
+
+   Information about a pattern
+
+       The  debug modifier is a shorthand for info,fullbincode, requesting all
+       available information.
+
+       The bincode modifier causes a representation of the compiled code to be
+       output  after compilation. This information does not contain length and
+       offset values, which ensures that the same output is generated for dif-
+       ferent  internal  link  sizes  and different code unit widths. By using
+       bincode, the same regression tests can be used  in  different  environ-
+       ments.
+
+       The  fullbincode  modifier, by contrast, does include length and offset
+       values. This is used in a few special tests that run only for  specific
+       code unit widths and link sizes, and is also useful for one-off tests.
+
+       The  info  modifier  requests  information  about  the compiled pattern
+       (whether it is anchored, has a fixed first character, and so  on).  The
+       information  is  obtained  from the pcre2_pattern_info() function. Here
+       are some typical examples:
+
+           re> /(?i)(^a|^b)/m,info
+         Capturing subpattern count = 1
+         Compile options: multiline
+         Overall options: caseless multiline
+         First code unit at start or follows newline
+         Subject length lower bound = 1
+
+           re> /(?i)abc/info
+         Capturing subpattern count = 0
+         Compile options: 
+         Overall options: caseless
+         First code unit = 'a' (caseless)
+         Last code unit = 'c' (caseless)
+         Subject length lower bound = 3
+
+       "Compile options" are those specified by modifiers;  "overall  options"
+       have  added options that are taken or deduced from the pattern. If both
+       sets of options are the same, just a single "options" line  is  output;
+       if  there  are  no  options,  the line is omitted. "First code unit" is
+       where any match must start; if there is more than one they  are  listed
+       as  "starting  code  units".  "Last code unit" is the last literal code
+       unit that must be present in any match. This  is  not  necessarily  the
+       last  character.  These lines are omitted if no starting or ending code
+       units are recorded.
+
+       The callout_info modifier requests information about all  the  callouts
+       in the pattern. A list of them is output at the end of any other infor-
+       mation that is requested. For each callout, either its number or string
+       is given, followed by the item that follows it in the pattern.
+
+   Specifying a pattern in hex
+
+       The hex modifier specifies that the characters of the pattern are to be
+       interpreted as pairs of hexadecimal digits. White  space  is  permitted
+       between pairs. For example:
+
+         /ab 32 59/hex
+
+       This  feature  is  provided  as a way of creating patterns that contain
+       binary zero and other non-printing characters.  By  default,  pcre2test
+       passes  patterns  as zero-terminated strings to pcre2_compile(), giving
+       the length as PCRE2_ZERO_TERMINATED. However, for patterns specified in
+       hexadecimal, the actual length of the pattern is passed.
+
+   JIT compilation
+
+       The  /jit  modifier  may optionally be followed by an equals sign and a
+       number in the range 0 to 7:
+
+         0  disable JIT
+         1  use JIT for normal match only
+         2  use JIT for soft partial match only
+         3  use JIT for normal match and soft partial match
+         4  use JIT for hard partial match only
+         6  use JIT for soft and hard partial match
+         7  all three modes
+
+       If no number is given, 7 is assumed. If JIT compilation is  successful,
+       the  compiled JIT code will automatically be used when pcre2_match() is
+       run for the appropriate type of match, except  when  incompatible  run-
+       time options are specified. For more details, see the pcre2jit documen-
+       tation. See also the jitstack modifier below for a way of  setting  the
+       size of the JIT stack.
+
+       If  the  jitfast  modifier is specified, matching is done using the JIT
+       "fast path" interface, pcre2_jit_match(), which skips some of the  san-
+       ity  checks that are done by pcre2_match(), and of course does not work
+       when JIT is not supported. If jitfast is specified without  jit,  jit=7
+       is assumed.
+
+       If  the jitverify modifier is specified, information about the compiled
+       pattern shows whether JIT compilation was or  was  not  successful.  If
+       jitverify  is  specified without jit, jit=7 is assumed. If JIT compila-
+       tion is successful when jitverify is set, the text "(JIT)" is added  to
+       the first output line after a match or non match when JIT-compiled code
+       was actually used in the match.
+
+   Setting a locale
+
+       The /locale modifier must specify the name of a locale, for example:
+
+         /pattern/locale=fr_FR
+
+       The given locale is set, pcre2_maketables() is called to build a set of
+       character  tables for the locale, and this is then passed to pcre2_com-
+       pile() when compiling the regular expression. The same tables are  used
+       when matching the following subject lines. The /locale modifier applies
+       only to the pattern on which it appears, but can be given in a #pattern
+       command  if a default is needed. Setting a locale and alternate charac-
+       ter tables are mutually exclusive.
+
+   Showing pattern memory
+
+       The /memory modifier causes the size in bytes of  the  memory  used  to
+       hold  the compiled pattern to be output. This does not include the size
+       of the pcre2_code block; it is just the actual compiled  data.  If  the
+       pattern is subsequently passed to the JIT compiler, the size of the JIT
+       compiled code is also output. Here is an example:
+
+           re> /a(b)c/jit,memory
+         Memory allocation (code space): 21
+         Memory allocation (JIT code): 1910
+
+
+   Limiting nested parentheses
+
+       The parens_nest_limit modifier sets a limit  on  the  depth  of  nested
+       parentheses  in  a  pattern.  Breaching  the limit causes a compilation
+       error.  The default for the library is set when  PCRE2  is  built,  but
+       pcre2test  sets  its  own default of 220, which is required for running
+       the standard test suite.
+
+   Using the POSIX wrapper API
+
+       The /posix modifier causes pcre2test to call PCRE2 via the POSIX  wrap-
+       per  API  rather  than  its  native  API.  This supports only the 8-bit
+       library.  When the POSIX API is being used, the following pattern modi-
+       fiers set options for the regcomp() function:
+
+         caseless           REG_ICASE
+         multiline          REG_NEWLINE
+         no_auto_capture    REG_NOSUB
+         dotall             REG_DOTALL     )
+         ungreedy           REG_UNGREEDY   ) These options are not part of
+         ucp                REG_UCP        )   the POSIX standard
+         utf                REG_UTF8       )
+
+       The  aftertext  and  allaftertext  subject  modifiers work as described
+       below. All other modifiers cause an error.
+
+   Testing the stack guard feature
+
+       The /stackguard modifier is used to  test  the  use  of  pcre2_set_com-
+       pile_recursion_guard(),  a  function  that  is provided to enable stack
+       availability to be checked during compilation (see the  pcre2api  docu-
+       mentation  for  details).  If  the  number specified by the modifier is
+       greater than zero, pcre2_set_compile_recursion_guard() is called to set
+       up  callback  from pcre2_compile() to a local function. The argument it
+       receives is the current nesting parenthesis depth; if this  is  greater
+       than the value given by the modifier, non-zero is returned, causing the
+       compilation to be aborted.
+
+   Using alternative character tables
+
+       The value specified for the /tables modifier must be one of the  digits
+       0, 1, or 2. It causes a specific set of built-in character tables to be
+       passed to pcre2_compile(). This is used in the PCRE2 tests to check be-
+       haviour with different character tables. The digit specifies the tables
+       as follows:
+
+         0   do not pass any special character tables
+         1   the default ASCII tables, as distributed in
+               pcre2_chartables.c.dist
+         2   a set of tables defining ISO 8859 characters
+
+       In table 2, some characters whose codes are greater than 128 are  iden-
+       tified  as  letters,  digits,  spaces, etc. Setting alternate character
+       tables and a locale are mutually exclusive.
+
+   Setting certain match controls
+
+       The following modifiers are really subject modifiers, and are described
+       below.   However, they may be included in a pattern's modifier list, in
+       which case they are applied to every subject  line  that  is  processed
+       with that pattern. They do not affect the compilation process.
+
+             aftertext           show text after match
+             allaftertext        show text after captures
+             allcaptures         show all captures
+             allusedtext         show all consulted text
+         /g  global              global matching
+             mark                show mark values
+             replace=    specify a replacement string
+             startchar           show starting character when relevant
+
+       These  modifiers may not appear in a #pattern command. If you want them
+       as defaults, set them in a #subject command.
+
+   Saving a compiled pattern
+
+       When a pattern with the push modifier is successfully compiled,  it  is
+       pushed  onto  a  stack  of compiled patterns, and pcre2test expects the
+       next line to contain a new pattern (or a command) instead of a  subject
+       line. This facility is used when saving compiled patterns to a file, as
+       described in the section entitled "Saving and restoring  compiled  pat-
+       terns" below.  The push modifier is incompatible with compilation modi-
+       fiers such as global that act at match time. Any that are specified are
+       ignored,  with  a  warning message, except for replace, which causes an
+       error. Note that, jitverify, which is allowed, does not  carry  through
+       to any subsequent matching that uses this pattern.
+
+
+SUBJECT MODIFIERS
+
+       The modifiers that can appear in subject lines and the #subject command
+       are of two types.
+
+   Setting match options
+
+       The   following   modifiers   set   options   for   pcre2_match()    or
+       pcre2_dfa_match(). See pcreapi for a description of their effects.
+
+             anchored                  set PCRE2_ANCHORED
+             dfa_restart               set PCRE2_DFA_RESTART
+             dfa_shortest              set PCRE2_DFA_SHORTEST
+             no_utf_check              set PCRE2_NO_UTF_CHECK
+             notbol                    set PCRE2_NOTBOL
+             notempty                  set PCRE2_NOTEMPTY
+             notempty_atstart          set PCRE2_NOTEMPTY_ATSTART
+             noteol                    set PCRE2_NOTEOL
+             partial_hard (or ph)      set PCRE2_PARTIAL_HARD
+             partial_soft (or ps)      set PCRE2_PARTIAL_SOFT
+
+       The  partial matching modifiers are provided with abbreviations because
+       they appear frequently in tests.
+
+       If the /posix modifier was present on the pattern,  causing  the  POSIX
+       wrapper API to be used, the only option-setting modifiers that have any
+       effect  are  notbol,  notempty,   and   noteol,   causing   REG_NOTBOL,
+       REG_NOTEMPTY,  and REG_NOTEOL, respectively, to be passed to regexec().
+       Any other modifiers cause an error.
+
+   Setting match controls
+
+       The following modifiers affect the matching process  or  request  addi-
+       tional  information.  Some  of  them may also be specified on a pattern
+       line (see above), in which case they apply to every subject  line  that
+       is matched against that pattern.
+
+             aftertext                 show text after match
+             allaftertext              show text after captures
+             allcaptures               show all captures
+             allusedtext               show all consulted text (non-JIT only)
+             altglobal                 alternative global matching
+             callout_capture           show captures at callout time
+             callout_data=          set a value to pass via callouts
+             callout_fail=[:]    control callout failure
+             callout_none              do not supply a callout function
+             copy=     copy captured substring
+             dfa                       use pcre2_dfa_match()
+             find_limits               find match and recursion limits
+             get=      extract captured substring
+             getall                    extract all captured substrings
+         /g  global                    global matching
+             jitstack=              set size of JIT stack
+             mark                      show mark values
+             match_limit=>n>           set a match limit
+             memory                    show memory usage
+             offset=                set starting offset
+             ovector=               set size of output vector
+             recursion_limit=       set a recursion limit
+             replace=          specify a replacement string
+             startchar                 show startchar when relevant
+             zero_terminate            pass the subject as zero-terminated
+
+       The effects of these modifiers are described in the following sections.
+
+   Showing more text
+
+       The  aftertext modifier requests that as well as outputting the part of
+       the subject string that matched the entire pattern, pcre2test should in
+       addition output the remainder of the subject string. This is useful for
+       tests where the subject contains multiple copies of the same substring.
+       The  allaftertext  modifier  requests the same action for captured sub-
+       strings as well as the main matched substring. In each case the remain-
+       der is output on the following line with a plus character following the
+       capture number.
+
+       The allusedtext modifier requests that all the text that was  consulted
+       during  a  successful pattern match by the interpreter should be shown.
+       This feature is not supported for JIT matching, and if  requested  with
+       JIT  it  is  ignored  (with  a  warning message). Setting this modifier
+       affects the output if there is a lookbehind at the start of a match, or
+       a  lookahead  at  the  end, or if \K is used in the pattern. Characters
+       that precede or follow the start and end of the actual match are  indi-
+       cated  in  the output by '<' or '>' characters underneath them. Here is
+       an example:
+
+           re> /(?<=pqr)abc(?=xyz)/
+         data> 123pqrabcxyz456\=allusedtext
+          0: pqrabcxyz
+             <<<   >>>
+
+       This shows that the matched string is "abc",  with  the  preceding  and
+       following  strings  "pqr"  and  "xyz"  having been consulted during the
+       match (when processing the assertions).
+
+       The startchar modifier requests that the  starting  character  for  the
+       match  be  indicated,  if  it  is different to the start of the matched
+       string. The only time when this occurs is when \K has been processed as
+       part of the match. In this situation, the output for the matched string
+       is displayed from the starting character  instead  of  from  the  match
+       point,  with  circumflex  characters  under the earlier characters. For
+       example:
+
+           re> /abc\Kxyz/
+         data> abcxyz\=startchar
+          0: abcxyz
+             ^^^
+
+       Unlike allusedtext, the startchar modifier can be used with JIT.   How-
+       ever, these two modifiers are mutually exclusive.
+
+   Showing the value of all capture groups
+
+       The allcaptures modifier requests that the values of all potential cap-
+       tured parentheses be output after a match. By default, only those up to
+       the highest one actually used in the match are output (corresponding to
+       the return code from pcre2_match()). Groups that did not take  part  in
+       the match are output as "".
+
+   Testing callouts
+
+       A  callout function is supplied when pcre2test calls the library match-
+       ing functions, unless callout_none is specified. If callout_capture  is
+       set, the current captured groups are output when a callout occurs.
+
+       The  callout_fail modifier can be given one or two numbers. If there is
+       only one number, 1 is returned instead of 0 when a callout of that num-
+       ber  is  reached.  If two numbers are given, 1 is returned when callout
+        is reached for the th time. Note that callouts with string argu-
+       ments  are  always  given  the  number zero. See "Callouts" below for a
+       description of the output when a callout it taken.
+
+       The callout_data modifier can be given an unsigned or a  negative  num-
+       ber.   This  is  set  as the "user data" that is passed to the matching
+       function, and passed back when the callout  function  is  invoked.  Any
+       value  other  than  zero  is  used as a return from pcre2test's callout
+       function.
+
+   Finding all matches in a string
+
+       Searching for all possible matches within a subject can be requested by
+       the  global or /altglobal modifier. After finding a match, the matching
+       function is called again to search the remainder of  the  subject.  The
+       difference  between  global  and  altglobal is that the former uses the
+       start_offset argument to pcre2_match() or  pcre2_dfa_match()  to  start
+       searching  at  a new point within the entire string (which is what Perl
+       does), whereas the latter passes over a shortened subject. This makes a
+       difference to the matching process if the pattern begins with a lookbe-
+       hind assertion (including \b or \B).
+
+       If an empty string  is  matched,  the  next  match  is  done  with  the
+       PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED flags set, in order to search
+       for another, non-empty, match at the same point in the subject. If this
+       match  fails,  the  start  offset  is advanced, and the normal match is
+       retried. This imitates the way Perl handles such cases when  using  the
+       /g  modifier  or  the  split()  function. Normally, the start offset is
+       advanced by one character, but if  the  newline  convention  recognizes
+       CRLF  as  a newline, and the current character is CR followed by LF, an
+       advance of two characters occurs.
+
+   Testing substring extraction functions
+
+       The copy  and  get  modifiers  can  be  used  to  test  the  pcre2_sub-
+       string_copy_xxx() and pcre2_substring_get_xxx() functions.  They can be
+       given more than once, and each can specify a group name or number,  for
+       example:
+
+          abcd\=copy=1,copy=3,get=G1
+
+       If  the  #subject command is used to set default copy and/or get lists,
+       these can be unset by specifying a negative number to cancel  all  num-
+       bered groups and an empty name to cancel all named groups.
+
+       The  getall  modifier  tests pcre2_substring_list_get(), which extracts
+       all captured substrings.
+
+       If the subject line is successfully matched, the  substrings  extracted
+       by  the  convenience  functions  are  output  with C, G, or L after the
+       string number instead of a colon. This is in  addition  to  the  normal
+       full  list.  The string length (that is, the return from the extraction
+       function) is given in parentheses after each substring, followed by the
+       name when the extraction was by name.
+
+   Testing the substitution function
+
+       If  the  replace  modifier  is  set, the pcre2_substitute() function is
+       called instead  of  one  of  the  matching  functions.  Unlike  subject
+       strings,  pcre2test  does  not  process  replacement strings for escape
+       sequences. In UTF mode, a replacement string is checked to see if it is
+       a valid UTF-8 string.  If so, it is correctly converted to a UTF string
+       of the appropriate code unit width. If it is not a valid UTF-8  string,
+       the individual code units are copied directly. This provides a means of
+       passing an invalid UTF-8 string for testing purposes.
+
+       If the global modifier is set,  PCRE2_SUBSTITUTE_GLOBAL  is  passed  to
+       pcre2_substitute().  After  a  successful  substitution,  the  modified
+       string is output, preceded by the number of replacements. This  may  be
+       zero  if there were no matches. Here is a simple example of a substitu-
+       tion test:
+
+         /abc/replace=xxx
+             =abc=abc=
+          1: =xxx=abc=
+             =abc=abc=\=global
+          2: =xxx=xxx=
+
+       Subject and replacement strings should be  kept  relatively  short  for
+       substitution  tests, as fixed-size buffers are used. To make it easy to
+       test for buffer overflow, if the replacement string starts with a  num-
+       ber  in square brackets, that number is passed to pcre2_substitute() as
+       the size of the output buffer, with the replacement string starting  at
+       the next character. Here is an example that tests the edge case:
+
+         /abc/
+             123abc123\=replace=[10]XYZ
+          1: 123XYZ123
+             123abc123\=replace=[9]XYZ
+         Failed: error -47: no more memory
+
+       A replacement string is ignored with POSIX and DFA matching. Specifying
+       partial matching provokes an error return  ("bad  option  value")  from
+       pcre2_substitute().
+
+   Setting the JIT stack size
+
+       The  jitstack modifier provides a way of setting the maximum stack size
+       that is used by the just-in-time optimization code. It  is  ignored  if
+       JIT optimization is not being used. The value is a number of kilobytes.
+       Providing a stack that is larger than the default 32K is necessary only
+       for very complicated patterns.
+
+   Setting match and recursion limits
+
+       The  match_limit and recursion_limit modifiers set the appropriate lim-
+       its in the match context. These values are ignored when the find_limits
+       modifier is specified.
+
+   Finding minimum limits
+
+       If  the  find_limits modifier is present, pcre2test calls pcre2_match()
+       several times, setting  different  values  in  the  match  context  via
+       pcre2_set_match_limit()  and pcre2_set_recursion_limit() until it finds
+       the minimum values for each parameter that allow pcre2_match() to  com-
+       plete without error.
+
+       If JIT is being used, only the match limit is relevant. If DFA matching
+       is being used, neither limit is relevant, and this modifier is  ignored
+       (with a warning message).
+
+       The  match_limit number is a measure of the amount of backtracking that
+       takes place, and learning the minimum value  can  be  instructive.  For
+       most  simple  matches, the number is quite small, but for patterns with
+       very large numbers of matching possibilities, it can become large  very
+       quickly    with    increasing    length    of   subject   string.   The
+       match_limit_recursion number is a measure of how  much  stack  (or,  if
+       PCRE2  is  compiled with NO_RECURSE, how much heap) memory is needed to
+       complete the match attempt.
+
+   Showing MARK names
+
+
+       The mark modifier causes the names from backtracking control verbs that
+       are  returned from calls to pcre2_match() to be displayed. If a mark is
+       returned for a match, non-match, or partial match, pcre2test shows  it.
+       For  a  match, it is on a line by itself, tagged with "MK:". Otherwise,
+       it is added to the non-match message.
+
+   Showing memory usage
+
+       The memory modifier causes pcre2test to log all memory  allocation  and
+       freeing calls that occur during a match operation.
+
+   Setting a starting offset
+
+       The  offset  modifier  sets  an  offset  in the subject string at which
+       matching starts. Its value is a number of code units, not characters.
+
+   Setting the size of the output vector
+
+       The ovector modifier applies only to  the  subject  line  in  which  it
+       appears,  though  of  course  it can also be used to set a default in a
+       #subject command. It specifies the number of pairs of offsets that  are
+       available for storing matching information. The default is 15.
+
+       A  value of zero is useful when testing the POSIX API because it causes
+       regexec() to be called with a NULL capture vector. When not testing the
+       POSIX  API,  a  value  of  zero  is used to cause pcre2_match_data_cre-
+       ate_from_pattern() to be called, in order to create a  match  block  of
+       exactly the right size for the pattern. (It is not possible to create a
+       match block with a zero-length ovector; there is always  at  least  one
+       pair of offsets.)
+
+   Passing the subject as zero-terminated
+
+       By default, the subject string is passed to a native API matching func-
+       tion with its correct length. In order to test the facility for passing
+       a  zero-terminated  string, the zero_terminate modifier is provided. It
+       causes the length to be passed as PCRE2_ZERO_TERMINATED. (When matching
+       via  the  POSIX  interface, this modifier has no effect, as there is no
+       facility for passing a length.)
+
+       When testing pcre2_substitute(), this modifier also has the  effect  of
+       passing the replacement string as zero-terminated.
+
+
+THE ALTERNATIVE MATCHING FUNCTION
+
+       By  default,  pcre2test  uses  the  standard  PCRE2  matching function,
+       pcre2_match() to match each subject line. PCRE2 also supports an alter-
+       native  matching  function, pcre2_dfa_match(), which operates in a dif-
+       ferent way, and has some restrictions. The differences between the  two
+       functions are described in the pcre2matching documentation.
+
+       If  the dfa modifier is set, the alternative matching function is used.
+       This function finds all possible matches at a given point in  the  sub-
+       ject.  If,  however, the dfa_shortest modifier is set, processing stops
+       after the first match is found. This is always  the  shortest  possible
+       match.
+
+
+DEFAULT OUTPUT FROM pcre2test
+
+       This  section  describes  the output when the normal matching function,
+       pcre2_match(), is being used.
+
+       When a match succeeds, pcre2test outputs  the  list  of  captured  sub-
+       strings,  starting  with number 0 for the string that matched the whole
+       pattern.   Otherwise,  it  outputs  "No  match"  when  the  return   is
+       PCRE2_ERROR_NOMATCH,  or  "Partial  match:"  followed  by the partially
+       matching substring when the return is PCRE2_ERROR_PARTIAL.  (Note  that
+       this  is  the  entire  substring  that was inspected during the partial
+       match; it may include characters before the actual  match  start  if  a
+       lookbehind assertion, \K, \b, or \B was involved.)
+
+       For any other return, pcre2test outputs the PCRE2 negative error number
+       and a short descriptive phrase. If the error is  a  failed  UTF  string
+       check,  the  code  unit offset of the start of the failing character is
+       also output. Here is an example of an interactive pcre2test run.
+
+         $ pcre2test
+         PCRE2 version 9.00 2014-05-10
+
+           re> /^abc(\d+)/
+         data> abc123
+          0: abc123
+          1: 123
+         data> xyz
+         No match
+
+       Unset capturing substrings that are not followed by one that is set are
+       not shown by pcre2test unless the allcaptures modifier is specified. In
+       the following example, there are two capturing substrings, but when the
+       first  data  line is matched, the second, unset substring is not shown.
+       An "internal" unset substring is shown as "", as for the  second
+       data line.
+
+           re> /(a)|(b)/
+         data> a
+          0: a
+          1: a
+         data> b
+          0: b
+          1: 
+          2: b
+
+       If  the strings contain any non-printing characters, they are output as
+       \xhh escapes if the value is less than 256 and UTF  mode  is  not  set.
+       Otherwise they are output as \x{hh...} escapes. See below for the defi-
+       nition of non-printing characters. If the /aftertext modifier  is  set,
+       the  output  for substring 0 is followed by the the rest of the subject
+       string, identified by "0+" like this:
+
+           re> /cat/aftertext
+         data> cataract
+          0: cat
+          0+ aract
+
+       If global matching is requested, the  results  of  successive  matching
+       attempts are output in sequence, like this:
+
+           re> /\Bi(\w\w)/g
+         data> Mississippi
+          0: iss
+          1: ss
+          0: iss
+          1: ss
+          0: ipp
+          1: pp
+
+       "No  match" is output only if the first match attempt fails. Here is an
+       example of a failure message (the offset 4 that  is  specified  by  the
+       offset modifier is past the end of the subject string):
+
+           re> /xyz/
+         data> xyz\=offset=4
+         Error -24 (bad offset value)
+
+       Note that whereas patterns can be continued over several lines (a plain
+       ">" prompt is used for continuations), subject lines may  not.  However
+       newlines can be included in a subject by means of the \n escape (or \r,
+       \r\n, etc., depending on the newline sequence setting).
+
+
+OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION
+
+       When the alternative matching function, pcre2_dfa_match(), is used, the
+       output  consists  of  a list of all the matches that start at the first
+       point in the subject where there is at least one match. For example:
+
+           re> /(tang|tangerine|tan)/
+         data> yellow tangerine\=dfa
+          0: tangerine
+          1: tang
+          2: tan
+
+       Using the normal matching function on this data finds only "tang".  The
+       longest  matching  string  is  always  given first (and numbered zero).
+       After a PCRE2_ERROR_PARTIAL return, the  output  is  "Partial  match:",
+       followed  by  the  partially  matching substring. Note that this is the
+       entire substring that was inspected during the partial  match;  it  may
+       include characters before the actual match start if a lookbehind asser-
+       tion, \b, or \B was involved. (\K is not supported for DFA matching.)
+
+       If global matching is requested, the search for further matches resumes
+       at the end of the longest match. For example:
+
+           re> /(tang|tangerine|tan)/g
+         data> yellow tangerine and tangy sultana\=dfa
+          0: tangerine
+          1: tang
+          2: tan
+          0: tang
+          1: tan
+          0: tan
+
+       The  alternative  matching function does not support substring capture,
+       so the modifiers that are concerned with captured  substrings  are  not
+       relevant.
+
+
+RESTARTING AFTER A PARTIAL MATCH
+
+       When  the  alternative matching function has given the PCRE2_ERROR_PAR-
+       TIAL return, indicating that the subject partially matched the pattern,
+       you  can restart the match with additional subject data by means of the
+       dfa_restart modifier. For example:
+
+           re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
+         data> 23ja\=P,dfa
+         Partial match: 23ja
+         data> n05\=dfa,dfa_restart
+          0: n05
+
+       For further information about partial matching,  see  the  pcre2partial
+       documentation.
+
+
+CALLOUTS
+
+       If the pattern contains any callout requests, pcre2test's callout func-
+       tion is called during matching unless callout_none is specified.   This
+       works with both matching functions.
+
+       The  callout  function in pcre2test returns zero (carry on matching) by
+       default, but you can use a callout_fail modifier in a subject line  (as
+       described above) to change this and other parameters of the callout.
+
+       Inserting callouts can be helpful when using pcre2test to check compli-
+       cated regular expressions. For further information about callouts,  see
+       the pcre2callout documentation.
+
+       The  output for callouts with numerical arguments and those with string
+       arguments is slightly different.
+
+   Callouts with numerical arguments
+
+       By default, the callout function displays the callout number, the start
+       and  current positions in the subject text at the callout time, and the
+       next pattern item to be tested. For example:
+
+         --->pqrabcdef
+           0    ^  ^     \d
+
+       This output indicates that  callout  number  0  occurred  for  a  match
+       attempt  starting  at  the fourth character of the subject string, when
+       the pointer was at the seventh character, and  when  the  next  pattern
+       item  was  \d.  Just  one circumflex is output if the start and current
+       positions are the same.
+
+       Callouts numbered 255 are assumed to be automatic callouts, inserted as
+       a  result  of the /auto_callout pattern modifier. In this case, instead
+       of showing the callout number, the offset in the pattern, preceded by a
+       plus, is output. For example:
+
+           re> /\d?[A-E]\*/auto_callout
+         data> E*
+         --->E*
+          +0 ^      \d?
+          +3 ^      [A-E]
+          +8 ^^     \*
+         +10 ^ ^
+          0: E*
+
+       If a pattern contains (*MARK) items, an additional line is output when-
+       ever a change of latest mark is passed to  the  callout  function.  For
+       example:
+
+           re> /a(*MARK:X)bc/auto_callout
+         data> abc
+         --->abc
+          +0 ^       a
+          +1 ^^      (*MARK:X)
+         +10 ^^      b
+         Latest Mark: X
+         +11 ^ ^     c
+         +12 ^  ^
+          0: abc
+
+       The  mark  changes between matching "a" and "b", but stays the same for
+       the rest of the match, so nothing more is output. If, as  a  result  of
+       backtracking,  the  mark  reverts to being unset, the text "" is
+       output.
+
+   Callouts with string arguments
+
+       The output for a callout with a string argument is similar, except that
+       instead  of outputting a callout number before the position indicators,
+       the callout string and its offset in  the  pattern  string  are  output
+       before  the reflection of the subject string, and the subject string is
+       reflected for each callout. For example:
+
+           re> /^ab(?C'first')cd(?C"second")ef/
+         data> abcdefg
+         Callout (7): 'first'
+         --->abcdefg
+             ^ ^         c
+         Callout (20): "second"
+         --->abcdefg
+             ^   ^       e
+          0: abcdef
+
+
+NON-PRINTING CHARACTERS
+
+       When pcre2test is outputting text in the compiled version of a pattern,
+       bytes  other  than 32-126 are always treated as non-printing characters
+       and are therefore shown as hex escapes.
+
+       When pcre2test is outputting text that is a matched part of  a  subject
+       string,  it behaves in the same way, unless a different locale has been
+       set for the pattern (using the /locale modifier).  In  this  case,  the
+       isprint()  function  is  used  to distinguish printing and non-printing
+       characters.
+
+
+SAVING AND RESTORING COMPILED PATTERNS
+
+       It is possible to save compiled patterns  on  disc  or  elsewhere,  and
+       reload them later, subject to a number of restrictions. JIT data cannot
+       be saved. The host on which the patterns are reloaded must  be  running
+       the same version of PCRE2, with the same code unit width, and must also
+       have the same endianness, pointer width  and  PCRE2_SIZE  type.  Before
+       compiled  patterns  can be saved they must be serialized, that is, con-
+       verted to a stream of bytes. A single byte stream may contain any  num-
+       ber  of  compiled  patterns,  but  they must all use the same character
+       tables. A single copy of the tables is included in the byte stream (its
+       size is 1088 bytes).
+
+       The  functions  whose  names  begin  with pcre2_serialize_ are used for
+       serializing and de-serializing. They are described in the  pcre2serial-
+       ize  documentation.  In  this  section  we  describe  the  features  of
+       pcre2test that can be used to test these functions.
+
+       When a pattern with push  modifier  is  successfully  compiled,  it  is
+       pushed  onto  a  stack  of compiled patterns, and pcre2test expects the
+       next line to contain a new pattern (or command) instead  of  a  subject
+       line. By this means, a number of patterns can be compiled and retained.
+       The push modifier is incompatible with  posix,  and  control  modifiers
+       that act at match time are ignored (with a message). The jitverify mod-
+       ifier applies only at compile time. The command
+
+         #save 
+
+       causes all the stacked patterns to be serialized and the result written
+       to  the named file. Afterwards, all the stacked patterns are freed. The
+       command
+
+         #load 
+
+       reads the data in the file, and then arranges for it to  be  de-serial-
+       ized,  with the resulting compiled patterns added to the pattern stack.
+       The pattern on the top of the stack can be retrieved by the  #pop  com-
+       mand,  which  must  be  followed  by  lines  of subjects that are to be
+       matched with the pattern, terminated as usual by an empty line  or  end
+       of  file.  This  command  may be followed by a modifier list containing
+       only control modifiers that act after a pattern has been  compiled.  In
+       particular,  hex,  posix, and push are not allowed, nor are any option-
+       setting modifiers.  The JIT modifiers are, however permitted.  Here  is
+       an example that saves and reloads two patterns.
+
+         /abc/push
+         /xyz/push
+         #save tempfile
+         #load tempfile
+         #pop info
+         xyz
+
+         #pop jit,bincode
+         abc
+
+       If  jitverify  is  used with #pop, it does not automatically imply jit,
+       which is different behaviour from when it is used on a pattern.
+
+
+SEE ALSO
+
+       pcre2(3),  pcre2api(3),  pcre2callout(3),  pcre2jit,  pcre2matching(3),
+       pcre2partial(d), pcre2pattern(3), pcre2serialize(3).
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge, England.
+
+
+REVISION
+
+       Last updated: 20 May 2015
+       Copyright (c) 1997-2015 University of Cambridge.
diff --git a/pcre2-10.20/doc/pcre2unicode.3 b/pcre2-10.20/doc/pcre2unicode.3
new file mode 100644
index 000000000..6c32bc046
--- /dev/null
+++ b/pcre2-10.20/doc/pcre2unicode.3
@@ -0,0 +1,257 @@
+.TH PCRE2UNICODE 3 "23 November 2014" "PCRE2 10.00"
+.SH NAME
+PCRE - Perl-compatible regular expressions (revised API)
+.SH "UNICODE AND UTF SUPPORT"
+.rs
+.sp
+When PCRE2 is built with Unicode support (which is the default), it has
+knowledge of Unicode character properties and can process text strings in
+UTF-8, UTF-16, or UTF-32 format (depending on the code unit width). However, by
+default, PCRE2 assumes that one code unit is one character. To process a
+pattern as a UTF string, where a character may require more than one code unit,
+you must call
+.\" HREF
+\fBpcre2_compile()\fP
+.\"
+with the PCRE2_UTF option flag, or the pattern must start with the sequence
+(*UTF). When either of these is the case, both the pattern and any subject
+strings that are matched against it are treated as UTF strings instead of
+strings of individual one-code-unit characters.
+.P
+If you do not need Unicode support you can build PCRE2 without it, in which
+case the library will be smaller.
+.
+.
+.SH "UNICODE PROPERTY SUPPORT"
+.rs
+.sp
+When PCRE2 is built with Unicode support, the escape sequences \ep{..},
+\eP{..}, and \eX can be used. The Unicode properties that can be tested are
+limited to the general category properties such as Lu for an upper case letter
+or Nd for a decimal number, the Unicode script names such as Arabic or Han, and
+the derived properties Any and L&. Full lists are given in the
+.\" HREF
+\fBpcre2pattern\fP
+.\"
+and
+.\" HREF
+\fBpcre2syntax\fP
+.\"
+documentation. Only the short names for properties are supported. For example,
+\ep{L} matches a letter. Its Perl synonym, \ep{Letter}, is not supported.
+Furthermore, in Perl, many properties may optionally be prefixed by "Is", for
+compatibility with Perl 5.6. PCRE does not support this.
+.
+.
+.SH "WIDE CHARACTERS AND UTF MODES"
+.rs
+.sp
+Codepoints less than 256 can be specified in patterns by either braced or
+unbraced hexadecimal escape sequences (for example, \ex{b3} or \exb3). Larger
+values have to use braced sequences. Unbraced octal code points up to \e777 are
+also recognized; larger ones can be coded using \eo{...}.
+.P
+In UTF modes, repeat quantifiers apply to complete UTF characters, not to
+individual code units.
+.P
+In UTF modes, the dot metacharacter matches one UTF character instead of a
+single code unit.
+.P
+The escape sequence \eC can be used to match a single code unit, in a UTF mode,
+but its use can lead to some strange effects because it breaks up multi-unit
+characters (see the description of \eC in the
+.\" HREF
+\fBpcre2pattern\fP
+.\"
+documentation). The use of \eC is not supported in the alternative matching
+function \fBpcre2_dfa_match()\fP, nor is it supported in UTF mode by the JIT
+optimization. If JIT optimization is requested for a UTF pattern that contains
+\eC, it will not succeed, and so the matching will be carried out by the normal
+interpretive function.
+.P
+The character escapes \eb, \eB, \ed, \eD, \es, \eS, \ew, and \eW correctly test
+characters of any code value, but, by default, the characters that PCRE2
+recognizes as digits, spaces, or word characters remain the same set as in
+non-UTF mode, all with code points less than 256. This remains true even when
+PCRE2 is built to include Unicode support, because to do otherwise would slow
+down matching in many common cases. Note that this also applies to \eb
+and \eB, because they are defined in terms of \ew and \eW. If you want
+to test for a wider sense of, say, "digit", you can use explicit Unicode
+property tests such as \ep{Nd}. Alternatively, if you set the PCRE2_UCP option,
+the way that the character escapes work is changed so that Unicode properties
+are used to determine which characters match. There are more details in the
+section on
+.\" HTML 
+.\" 
+generic character types
+.\"
+in the
+.\" HREF
+\fBpcre2pattern\fP
+.\"
+documentation.
+.P
+Similarly, characters that match the POSIX named character classes are all
+low-valued characters, unless the PCRE2_UCP option is set.
+.P
+However, the special horizontal and vertical white space matching escapes (\eh,
+\eH, \ev, and \eV) do match all the appropriate Unicode characters, whether or
+not PCRE2_UCP is set.
+.P
+Case-insensitive matching in UTF mode makes use of Unicode properties. A few
+Unicode characters such as Greek sigma have more than two codepoints that are
+case-equivalent, and these are treated as such.
+.
+.
+.SH "VALIDITY OF UTF STRINGS"
+.rs
+.sp
+When the PCRE2_UTF option is set, the strings passed as patterns and subjects
+are (by default) checked for validity on entry to the relevant functions.
+If an invalid UTF string is passed, an negative error code is returned. The
+code unit offset to the offending character can be extracted from the match
+data block by calling \fBpcre2_get_startchar()\fP, which is used for this
+purpose after a UTF error.
+.P
+UTF-16 and UTF-32 strings can indicate their endianness by special code knows
+as a byte-order mark (BOM). The PCRE2 functions do not handle this, expecting
+strings to be in host byte order.
+.P
+The entire string is checked before any other processing takes place. In
+addition to checking the format of the string, there is a check to ensure that
+all code points lie in the range U+0 to U+10FFFF, excluding the surrogate area.
+The so-called "non-character" code points are not excluded because Unicode
+corrigendum #9 makes it clear that they should not be.
+.P
+Characters in the "Surrogate Area" of Unicode are reserved for use by UTF-16,
+where they are used in pairs to encode code points with values greater than
+0xFFFF. The code points that are encoded by UTF-16 pairs are available
+independently in the UTF-8 and UTF-32 encodings. (In other words, the whole
+surrogate thing is a fudge for UTF-16 which unfortunately messes up UTF-8 and
+UTF-32.)
+.P
+In some situations, you may already know that your strings are valid, and
+therefore want to skip these checks in order to improve performance, for
+example in the case of a long subject string that is being scanned repeatedly.
+If you set the PCRE2_NO_UTF_CHECK option at compile time or at match time,
+PCRE2 assumes that the pattern or subject it is given (respectively) contains
+only valid UTF code unit sequences.
+.P
+Passing PCRE2_NO_UTF_CHECK to \fBpcre2_compile()\fP just disables the check for
+the pattern; it does not also apply to subject strings. If you want to disable
+the check for a subject string you must pass this option to \fBpcre2_match()\fP
+or \fBpcre2_dfa_match()\fP.
+.P
+If you pass an invalid UTF string when PCRE2_NO_UTF_CHECK is set, the result
+is undefined and your program may crash or loop indefinitely.
+.
+.
+.\" HTML 
+.SS "Errors in UTF-8 strings"
+.rs
+.sp
+The following negative error codes are given for invalid UTF-8 strings:
+.sp
+  PCRE2_ERROR_UTF8_ERR1
+  PCRE2_ERROR_UTF8_ERR2
+  PCRE2_ERROR_UTF8_ERR3
+  PCRE2_ERROR_UTF8_ERR4
+  PCRE2_ERROR_UTF8_ERR5
+.sp
+The string ends with a truncated UTF-8 character; the code specifies how many
+bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 characters to be
+no longer than 4 bytes, the encoding scheme (originally defined by RFC 2279)
+allows for up to 6 bytes, and this is checked first; hence the possibility of
+4 or 5 missing bytes.
+.sp
+  PCRE2_ERROR_UTF8_ERR6
+  PCRE2_ERROR_UTF8_ERR7
+  PCRE2_ERROR_UTF8_ERR8
+  PCRE2_ERROR_UTF8_ERR9
+  PCRE2_ERROR_UTF8_ERR10
+.sp
+The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of the
+character do not have the binary value 0b10 (that is, either the most
+significant bit is 0, or the next bit is 1).
+.sp
+  PCRE2_ERROR_UTF8_ERR11
+  PCRE2_ERROR_UTF8_ERR12
+.sp
+A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long;
+these code points are excluded by RFC 3629.
+.sp
+  PCRE2_ERROR_UTF8_ERR13
+.sp
+A 4-byte character has a value greater than 0x10fff; these code points are
+excluded by RFC 3629.
+.sp
+  PCRE2_ERROR_UTF8_ERR14
+.sp
+A 3-byte character has a value in the range 0xd800 to 0xdfff; this range of
+code points are reserved by RFC 3629 for use with UTF-16, and so are excluded
+from UTF-8.
+.sp
+  PCRE2_ERROR_UTF8_ERR15
+  PCRE2_ERROR_UTF8_ERR16
+  PCRE2_ERROR_UTF8_ERR17
+  PCRE2_ERROR_UTF8_ERR18
+  PCRE2_ERROR_UTF8_ERR19
+.sp
+A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes for a
+value that can be represented by fewer bytes, which is invalid. For example,
+the two bytes 0xc0, 0xae give the value 0x2e, whose correct coding uses just
+one byte.
+.sp
+  PCRE2_ERROR_UTF8_ERR20
+.sp
+The two most significant bits of the first byte of a character have the binary
+value 0b10 (that is, the most significant bit is 1 and the second is 0). Such a
+byte can only validly occur as the second or subsequent byte of a multi-byte
+character.
+.sp
+  PCRE2_ERROR_UTF8_ERR21
+.sp
+The first byte of a character has the value 0xfe or 0xff. These values can
+never occur in a valid UTF-8 string.
+.
+.
+.\" HTML 
+.SS "Errors in UTF-16 strings"
+.rs
+.sp
+The following negative error codes are given for invalid UTF-16 strings:
+.sp
+  PCRE_UTF16_ERR1  Missing low surrogate at end of string
+  PCRE_UTF16_ERR2  Invalid low surrogate follows high surrogate
+  PCRE_UTF16_ERR3  Isolated low surrogate
+.sp
+.
+.
+.\" HTML 
+.SS "Errors in UTF-32 strings"
+.rs
+.sp
+The following negative error codes are given for invalid UTF-32 strings:
+.sp
+  PCRE_UTF32_ERR1  Surrogate character (range from 0xd800 to 0xdfff)
+  PCRE_UTF32_ERR2  Code point is greater than 0x10ffff
+.sp
+.
+.
+.SH AUTHOR
+.rs
+.sp
+.nf
+Philip Hazel
+University Computing Service
+Cambridge, England.
+.fi
+.
+.
+.SH REVISION
+.rs
+.sp
+.nf
+Last updated: 23 November 2014
+Copyright (c) 1997-2014 University of Cambridge.
+.fi
diff --git a/pcre2-10.20/src/config.h.in b/pcre2-10.20/src/config.h.in
new file mode 100644
index 000000000..e3ef2fddc
--- /dev/null
+++ b/pcre2-10.20/src/config.h.in
@@ -0,0 +1,294 @@
+/* src/config.h.in.  Generated from configure.ac by autoheader.  */
+
+
+/* PCRE2 is written in Standard C, but there are a few non-standard things it
+can cope with, allowing it to run on SunOS4 and other "close to standard"
+systems.
+
+In environments that support the GNU autotools, config.h.in is converted into
+config.h by the "configure" script. In environments that use CMake,
+config-cmake.in is converted into config.h. If you are going to build PCRE2 "by
+hand" without using "configure" or CMake, you should copy the distributed
+config.h.generic to config.h, and edit the macro definitions to be the way you
+need them. You must then add -DHAVE_CONFIG_H to all of your compile commands,
+so that config.h is included at the start of every source.
+
+Alternatively, you can avoid editing by using -D on the compiler command line
+to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H,
+but if you do, default values will be taken from config.h for non-boolean
+macros that are not defined on the command line.
+
+Boolean macros such as HAVE_STDLIB_H and SUPPORT_PCRE2_8 should either be defined
+(conventionally to 1) for TRUE, and not defined at all for FALSE. All such
+macros are listed as a commented #undef in config.h.generic. Macros such as
+MATCH_LIMIT, whose actual value is relevant, have defaults defined, but are
+surrounded by #ifndef/#endif lines so that the value can be overridden by -D.
+
+PCRE2 uses memmove() if HAVE_MEMMOVE is defined; otherwise it uses bcopy() if
+HAVE_BCOPY is defined. If your system has neither bcopy() nor memmove(), make
+sure both macros are undefined; an emulation function will then be used. */
+
+/* By default, the \R escape sequence matches any Unicode line ending
+   character or sequence of characters. If BSR_ANYCRLF is defined (to any
+   value), this is changed so that backslash-R matches only CR, LF, or CRLF.
+   The build-time default can be overridden by the user of PCRE2 at runtime.
+   */
+#undef BSR_ANYCRLF
+
+/* If you are compiling for a system that uses EBCDIC instead of ASCII
+   character codes, define this macro to any value. When EBCDIC is set, PCRE2
+   assumes that all input strings are in EBCDIC. If you do not define this
+   macro, PCRE2 will assume input strings are ASCII or UTF-8/16/32 Unicode. It
+   is not possible to build a version of PCRE2 that supports both EBCDIC and
+   UTF-8/16/32. */
+#undef EBCDIC
+
+/* In an EBCDIC environment, define this macro to any value to arrange for the
+   NL character to be 0x25 instead of the default 0x15. NL plays the role that
+   LF does in an ASCII/Unicode environment. */
+#undef EBCDIC_NL25
+
+/* Define to 1 if you have the `bcopy' function. */
+#undef HAVE_BCOPY
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_BZLIB_H
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_DIRENT_H
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_DLFCN_H
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_EDITLINE_READLINE_H
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_EDIT_READLINE_READLINE_H
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_INTTYPES_H
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_LIMITS_H
+
+/* Define to 1 if you have the `memmove' function. */
+#undef HAVE_MEMMOVE
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_MEMORY_H
+
+/* Define if you have POSIX threads libraries and header files. */
+#undef HAVE_PTHREAD
+
+/* Have PTHREAD_PRIO_INHERIT. */
+#undef HAVE_PTHREAD_PRIO_INHERIT
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_READLINE_HISTORY_H
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_READLINE_READLINE_H
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_STDINT_H
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_STDLIB_H
+
+/* Define to 1 if you have the `strerror' function. */
+#undef HAVE_STRERROR
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_STRINGS_H
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_STRING_H
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_SYS_STAT_H
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_SYS_TYPES_H
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_UNISTD_H
+
+/* Define to 1 if the compiler supports simple visibility declarations. */
+#undef HAVE_VISIBILITY
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_WINDOWS_H
+
+/* Define to 1 if you have the  header file. */
+#undef HAVE_ZLIB_H
+
+/* PCRE2 uses recursive function calls to handle backtracking while matching.
+   This can sometimes be a problem on systems that have stacks of limited
+   size. Define HEAP_MATCH_RECURSE to any value to get a version that doesn't
+   use recursion in the match() function; instead it creates its own stack by
+   steam using memory from the heap. For more detail, see the comments and
+   other stuff just above the match() function. */
+#undef HEAP_MATCH_RECURSE
+
+/* The value of LINK_SIZE determines the number of bytes used to store links
+   as offsets within the compiled regex. The default is 2, which allows for
+   compiled patterns up to 64K long. This covers the vast majority of cases.
+   However, PCRE2 can also be compiled to use 3 or 4 bytes instead. This
+   allows for longer patterns in extreme cases. */
+#undef LINK_SIZE
+
+/* Define to the sub-directory where libtool stores uninstalled libraries. */
+#undef LT_OBJDIR
+
+/* The value of MATCH_LIMIT determines the default number of times the
+   internal match() function can be called during a single execution of
+   pcre2_match(). There is a runtime interface for setting a different limit.
+   The limit exists in order to catch runaway regular expressions that take
+   for ever to determine that they do not match. The default is set very large
+   so that it does not accidentally catch legitimate cases. */
+#undef MATCH_LIMIT
+
+/* The above limit applies to all calls of match(), whether or not they
+   increase the recursion depth. In some environments it is desirable to limit
+   the depth of recursive calls of match() more strictly, in order to restrict
+   the maximum amount of stack (or heap, if HEAP_MATCH_RECURSE is defined)
+   that is used. The value of MATCH_LIMIT_RECURSION applies only to recursive
+   calls of match(). To have any useful effect, it must be less than the value
+   of MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT. There
+   is a runtime method for setting a different limit. */
+#undef MATCH_LIMIT_RECURSION
+
+/* This limit is parameterized just in case anybody ever wants to change it.
+   Care must be taken if it is increased, because it guards against integer
+   overflow caused by enormously large patterns. */
+#undef MAX_NAME_COUNT
+
+/* This limit is parameterized just in case anybody ever wants to change it.
+   Care must be taken if it is increased, because it guards against integer
+   overflow caused by enormously large patterns. */
+#undef MAX_NAME_SIZE
+
+/* The value of NEWLINE_DEFAULT determines the default newline character
+   sequence. PCRE2 client programs can override this by selecting other values
+   at run time. The valid values are 1 (CR), 2 (LF), 3 (CRLF), 4 (ANY), and 5
+   (ANYCRLF). */
+#undef NEWLINE_DEFAULT
+
+/* Name of package */
+#undef PACKAGE
+
+/* Define to the address where bug reports for this package should be sent. */
+#undef PACKAGE_BUGREPORT
+
+/* Define to the full name of this package. */
+#undef PACKAGE_NAME
+
+/* Define to the full name and version of this package. */
+#undef PACKAGE_STRING
+
+/* Define to the one symbol short name of this package. */
+#undef PACKAGE_TARNAME
+
+/* Define to the home page for this package. */
+#undef PACKAGE_URL
+
+/* Define to the version of this package. */
+#undef PACKAGE_VERSION
+
+/* The value of PARENS_NEST_LIMIT specifies the maximum depth of nested
+   parentheses (of any kind) in a pattern. This limits the amount of system
+   stack that is used while compiling a pattern. */
+#undef PARENS_NEST_LIMIT
+
+/* The value of PCRE2GREP_BUFSIZE determines the size of buffer used by
+   pcre2grep to hold parts of the file it is searching. This is also the
+   minimum value. The actual amount of memory used by pcre2grep is three times
+   this number, because it allows for the buffering of "before" and "after"
+   lines. */
+#undef PCRE2GREP_BUFSIZE
+
+/* to make a symbol visible */
+#undef PCRE2POSIX_EXP_DECL
+
+/* to make a symbol visible */
+#undef PCRE2POSIX_EXP_DEFN
+
+/* Define to any value to include debugging code. */
+#undef PCRE2_DEBUG
+
+/* to make a symbol visible */
+#undef PCRE2_EXP_DECL
+
+
+/* If you are compiling for a system other than a Unix-like system or
+   Win32, and it needs some magic to be inserted before the definition
+   of a function that is exported by the library, define this macro to
+   contain the relevant magic. If you do not define this macro, a suitable
+    __declspec value is used for Windows systems; in other environments
+   "extern" is used for a C compiler and "extern C" for a C++ compiler.
+   This macro apears at the start of every exported function that is part
+   of the external API. It does not appear on functions that are "external"
+   in the C sense, but which are internal to the library. */
+#undef PCRE2_EXP_DEFN
+
+/* Define to any value if linking statically (TODO: make nice with Libtool) */
+#undef PCRE2_STATIC
+
+/* Define to necessary symbol if this constant uses a non-standard name on
+   your system. */
+#undef PTHREAD_CREATE_JOINABLE
+
+/* Define to 1 if you have the ANSI C header files. */
+#undef STDC_HEADERS
+
+/* Define to any value to enable support for Just-In-Time compiling. */
+#undef SUPPORT_JIT
+
+/* Define to any value to allow pcre2grep to be linked with libbz2, so that it
+   is able to handle .bz2 files. */
+#undef SUPPORT_LIBBZ2
+
+/* Define to any value to allow pcre2test to be linked with libedit. */
+#undef SUPPORT_LIBEDIT
+
+/* Define to any value to allow pcre2test to be linked with libreadline. */
+#undef SUPPORT_LIBREADLINE
+
+/* Define to any value to allow pcre2grep to be linked with libz, so that it
+   is able to handle .gz files. */
+#undef SUPPORT_LIBZ
+
+/* Define to any value to enable JIT support in pcre2grep. */
+#undef SUPPORT_PCRE2GREP_JIT
+
+/* Define to any value to enable the 16 bit PCRE2 library. */
+#undef SUPPORT_PCRE2_16
+
+/* Define to any value to enable the 32 bit PCRE2 library. */
+#undef SUPPORT_PCRE2_32
+
+/* Define to any value to enable the 8 bit PCRE2 library. */
+#undef SUPPORT_PCRE2_8
+
+/* Define to any value to enable support for Unicode and UTF encoding. This
+   will work even in an EBCDIC environment, but it is incompatible with the
+   EBCDIC macro. That is, PCRE2 can support *either* EBCDIC code *or*
+   ASCII/Unicode, but not both at once. */
+#undef SUPPORT_UNICODE
+
+/* Define to any value for valgrind support to find invalid memory reads. */
+#undef SUPPORT_VALGRIND
+
+/* Version number of package */
+#undef VERSION
+
+/* Define to empty if `const' does not conform to ANSI C. */
+#undef const
+
+/* Define to the type of a signed integer type of width exactly 64 bits if
+   such a type exists and the standard includes do not define it. */
+#undef int64_t
+
+/* Define to `unsigned int' if  does not define. */
+#undef size_t