Mirrors/fish-shell
2
0
Fork 0
mirror of https://github.com/fish-shell/fish-shell synced 2025-01-12 21:18:53 +00:00
Code Issues Projects Releases Packages Wiki Activity

Merge branch 'Integration_2.3.0'

Browse source 
Merge the pcre2 10.20 to 10.21 update.

Closes #2943.
This commit is contained in:
David Adam 2016-04-19 16:28:03 +08:00
commit 9aeed0dc06
122 changed files with 8599 additions and 5728 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
Makefile.in
View file

@ -62,7 +62,7 @@ extra_confdir = @extra_confdir@
#
PCRE2_WIDTH = @WCHAR_T_BITS@
PCRE2_DIR = pcre2-10.20
PCRE2_DIR = pcre2-10.21
PCRE2_LIBDIR = $(PCRE2_DIR)/.libs
PCRE2_LIB = $(PCRE2_LIBDIR)/libpcre2-$(PCRE2_WIDTH).a
PCRE2_H = $(PCRE2_DIR)/src/pcre2.h

6
build_tools/lint.fish
View file

@ -71,14 +71,14 @@ if set -q c_files[1]
oclint-xcodebuild xcodebuild.log > /dev/null
end
if test $all = yes
oclint-json-compilation-database -e '/pcre2-10.20/' -- -enable-global-analysis 2>& 1
oclint-json-compilation-database -e '/pcre2-10.21/' -- -enable-global-analysis 2>& 1
else
set i_files
for f in $c_files
set i_files $i_files -i $f
end
echo oclint-json-compilation-database -e '/pcre2-10.20/' $i_files
oclint-json-compilation-database -e '/pcre2-10.20/' $i_files 2>& 1
echo oclint-json-compilation-database -e '/pcre2-10.21/' $i_files
oclint-json-compilation-database -e '/pcre2-10.21/' $i_files 2>& 1
end
else
# Presumably we're on Linux or other platform not requiring special

2
configure.ac
View file

@ -849,7 +849,7 @@ if test "x$included_pcre2" = "xyes"; then
AC_MSG_NOTICE([using included PCRE2 library])
# unfortunately these get added to the global configuration
ac_configure_args="$ac_configure_args --disable-pcre2-8 --enable-pcre2-$WCHAR_T_BITS --disable-shared"
AC_CONFIG_SUBDIRS([pcre2-10.20])
AC_CONFIG_SUBDIRS([pcre2-10.21])
PCRE2_CXXFLAGS='-I$(PCRE2_DIR)/src'
PCRE2_LIBS='-L$(PCRE2_LIBDIR) -lpcre2-$(PCRE2_WIDTH)'

53
fish.xcodeproj/project.pbxproj
View file

@ -66,6 +66,7 @@
/* End PBXAggregateTarget section */
/* Begin PBXBuildFile section */
63A2C0E91CC60F3B00973404 /* pcre2_find_bracket.c in Sources */ = {isa = PBXBuildFile; fileRef = 63A2C0E81CC5F9FB00973404 /* pcre2_find_bracket.c */; };
D00769121990137800CA4627 /* autoload.cpp in Sources */ = {isa = PBXBuildFile; fileRef = D0C6FCC914CFA4B0004CE8AD /* autoload.cpp */; };
D00769131990137800CA4627 /* builtin_test.cpp in Sources */ = {isa = PBXBuildFile; fileRef = D0F3373A1506DE3C00ECEFC0 /* builtin_test.cpp */; };
D00769141990137800CA4627 /* color.cpp in Sources */ = {isa = PBXBuildFile; fileRef = D0B6B0FE14E88BA400AD6C10 /* color.cpp */; };
@ -448,6 +449,7 @@
/* Begin PBXFileReference section */
4E142D731B56B5D7008783C8 /* config.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; name = config.h; path = ../osx/config.h; sourceTree = "<group>"; };
63A2C0E81CC5F9FB00973404 /* pcre2_find_bracket.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_find_bracket.c; sourceTree = "<group>"; };
D00769421990137800CA4627 /* fish_tests */ = {isa = PBXFileReference; explicitFileType = "compiled.mach-o.executable"; includeInIndex = 0; path = fish_tests; sourceTree = BUILT_PRODUCTS_DIR; };
D00F63F019137E9D00FCCDEC /* fish_version.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = fish_version.cpp; sourceTree = "<group>"; };
D01A2D23169B730A00767098 /* man1 */ = {isa = PBXFileReference; lastKnownFileType = text; name = man1; path = pages_for_manpath/man1; sourceTree = BUILT_PRODUCTS_DIR; };
@ -459,30 +461,30 @@
D032388A1849D1980032CF2C /* pager.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = pager.h; sourceTree = "<group>"; };
D03EE83814DF88B200FC7150 /* lru.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; path = lru.h; sourceTree = "<group>"; };
D04F7F7B1BA4BF4000B0F227 /* builtin_string.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = builtin_string.cpp; sourceTree = "<group>"; };
D04F7F8D1BA4DCD900B0F227 /* pcre2_compile.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_compile.c; path = "pcre2-10.20/src/pcre2_compile.c"; sourceTree = SOURCE_ROOT; };
D04F7F901BA4DCE900B0F227 /* pcre2_config.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_config.c; path = "pcre2-10.20/src/pcre2_config.c"; sourceTree = SOURCE_ROOT; };
D04F7F931BA4DCFA00B0F227 /* pcre2_context.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_context.c; path = "pcre2-10.20/src/pcre2_context.c"; sourceTree = SOURCE_ROOT; };
D04F7F961BA4DD1100B0F227 /* pcre2_dfa_match.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_dfa_match.c; path = "pcre2-10.20/src/pcre2_dfa_match.c"; sourceTree = SOURCE_ROOT; };
D04F7F991BA4DD2000B0F227 /* pcre2_error.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_error.c; path = "pcre2-10.20/src/pcre2_error.c"; sourceTree = SOURCE_ROOT; };
D04F7F9C1BA4DD4A00B0F227 /* pcre2_maketables.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_maketables.c; path = "pcre2-10.20/src/pcre2_maketables.c"; sourceTree = SOURCE_ROOT; };
D04F7F9F1BA4DD5900B0F227 /* pcre2_match.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_match.c; path = "pcre2-10.20/src/pcre2_match.c"; sourceTree = SOURCE_ROOT; };
D04F7FA21BA4DD6900B0F227 /* pcre2_match_data.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_match_data.c; path = "pcre2-10.20/src/pcre2_match_data.c"; sourceTree = SOURCE_ROOT; };
D04F7FA51BA4DD7300B0F227 /* pcre2_newline.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_newline.c; path = "pcre2-10.20/src/pcre2_newline.c"; sourceTree = SOURCE_ROOT; };
D04F7FA81BA4DD8400B0F227 /* pcre2_ord2utf.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_ord2utf.c; path = "pcre2-10.20/src/pcre2_ord2utf.c"; sourceTree = SOURCE_ROOT; };
D04F7FAB1BA4DDA500B0F227 /* pcre2_pattern_info.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_pattern_info.c; path = "pcre2-10.20/src/pcre2_pattern_info.c"; sourceTree = SOURCE_ROOT; };
D04F7FAE1BA4DDB500B0F227 /* pcre2_serialize.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_serialize.c; path = "pcre2-10.20/src/pcre2_serialize.c"; sourceTree = SOURCE_ROOT; };
D04F7FB11BA4DDBF00B0F227 /* pcre2_string_utils.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_string_utils.c; path = "pcre2-10.20/src/pcre2_string_utils.c"; sourceTree = SOURCE_ROOT; };
D04F7FB41BA4DDC900B0F227 /* pcre2_study.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_study.c; path = "pcre2-10.20/src/pcre2_study.c"; sourceTree = SOURCE_ROOT; };
D04F7FB71BA4DDEB00B0F227 /* pcre2_substitute.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_substitute.c; path = "pcre2-10.20/src/pcre2_substitute.c"; sourceTree = SOURCE_ROOT; };
D04F7FB81BA4DDEB00B0F227 /* pcre2_substring.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_substring.c; path = "pcre2-10.20/src/pcre2_substring.c"; sourceTree = SOURCE_ROOT; };
D04F7FB91BA4DDEB00B0F227 /* pcre2_tables.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_tables.c; path = "pcre2-10.20/src/pcre2_tables.c"; sourceTree = SOURCE_ROOT; };
D04F7FBA1BA4DDEB00B0F227 /* pcre2_ucd.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_ucd.c; path = "pcre2-10.20/src/pcre2_ucd.c"; sourceTree = SOURCE_ROOT; };
D04F7FBB1BA4DDEB00B0F227 /* pcre2_valid_utf.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_valid_utf.c; path = "pcre2-10.20/src/pcre2_valid_utf.c"; sourceTree = SOURCE_ROOT; };
D04F7FBC1BA4DDEB00B0F227 /* pcre2_xclass.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_xclass.c; path = "pcre2-10.20/src/pcre2_xclass.c"; sourceTree = SOURCE_ROOT; };
D04F7FC91BA4DE3500B0F227 /* pcre2_jit_compile.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_jit_compile.c; path = "pcre2-10.20/src/pcre2_jit_compile.c"; sourceTree = SOURCE_ROOT; };
D04F7F8D1BA4DCD900B0F227 /* pcre2_compile.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_compile.c; sourceTree = "<group>"; };
D04F7F901BA4DCE900B0F227 /* pcre2_config.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_config.c; sourceTree = "<group>"; };
D04F7F931BA4DCFA00B0F227 /* pcre2_context.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_context.c; sourceTree = "<group>"; };
D04F7F961BA4DD1100B0F227 /* pcre2_dfa_match.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_dfa_match.c; sourceTree = "<group>"; };
D04F7F991BA4DD2000B0F227 /* pcre2_error.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_error.c; sourceTree = "<group>"; };
D04F7F9C1BA4DD4A00B0F227 /* pcre2_maketables.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_maketables.c; sourceTree = "<group>"; };
D04F7F9F1BA4DD5900B0F227 /* pcre2_match.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_match.c; sourceTree = "<group>"; };
D04F7FA21BA4DD6900B0F227 /* pcre2_match_data.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_match_data.c; sourceTree = "<group>"; };
D04F7FA51BA4DD7300B0F227 /* pcre2_newline.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_newline.c; sourceTree = "<group>"; };
D04F7FA81BA4DD8400B0F227 /* pcre2_ord2utf.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_ord2utf.c; sourceTree = "<group>"; };
D04F7FAB1BA4DDA500B0F227 /* pcre2_pattern_info.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_pattern_info.c; sourceTree = "<group>"; };
D04F7FAE1BA4DDB500B0F227 /* pcre2_serialize.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_serialize.c; sourceTree = "<group>"; };
D04F7FB11BA4DDBF00B0F227 /* pcre2_string_utils.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_string_utils.c; sourceTree = "<group>"; };
D04F7FB41BA4DDC900B0F227 /* pcre2_study.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_study.c; sourceTree = "<group>"; };
D04F7FB71BA4DDEB00B0F227 /* pcre2_substitute.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_substitute.c; sourceTree = "<group>"; };
D04F7FB81BA4DDEB00B0F227 /* pcre2_substring.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_substring.c; sourceTree = "<group>"; };
D04F7FB91BA4DDEB00B0F227 /* pcre2_tables.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_tables.c; sourceTree = "<group>"; };
D04F7FBA1BA4DDEB00B0F227 /* pcre2_ucd.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_ucd.c; sourceTree = "<group>"; };
D04F7FBB1BA4DDEB00B0F227 /* pcre2_valid_utf.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_valid_utf.c; sourceTree = "<group>"; };
D04F7FBC1BA4DDEB00B0F227 /* pcre2_xclass.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_xclass.c; sourceTree = "<group>"; };
D04F7FC91BA4DE3500B0F227 /* pcre2_jit_compile.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_jit_compile.c; sourceTree = "<group>"; };
D04F7FD01BA4E29300B0F227 /* libpcre2.a */ = {isa = PBXFileReference; explicitFileType = archive.ar; includeInIndex = 0; path = libpcre2.a; sourceTree = BUILT_PRODUCTS_DIR; };
D04F7FF31BA4E6F300B0F227 /* pcre2_auto_possess.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = pcre2_auto_possess.c; path = "pcre2-10.20/src/pcre2_auto_possess.c"; sourceTree = SOURCE_ROOT; };
D04F7FF71BA4E82C00B0F227 /* pcre2_chartables.c.dist */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = text; name = pcre2_chartables.c.dist; path = "pcre2-10.20/src/pcre2_chartables.c.dist"; sourceTree = SOURCE_ROOT; };
D04F7FF31BA4E6F300B0F227 /* pcre2_auto_possess.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; path = pcre2_auto_possess.c; sourceTree = "<group>"; };
D04F7FF71BA4E82C00B0F227 /* pcre2_chartables.c.dist */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = text; path = pcre2_chartables.c.dist; sourceTree = "<group>"; };
D052D8091868F7FC003ABCBD /* parse_execution.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = parse_execution.cpp; sourceTree = "<group>"; };
D052D80A1868F7FC003ABCBD /* parse_execution.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = parse_execution.h; sourceTree = "<group>"; };
D07B247215BCC15700D4ADB4 /* add-shell */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = text.script.sh; name = "add-shell"; path = "build_tools/osx_package_scripts/add-shell"; sourceTree = "<group>"; };
@ -663,6 +665,7 @@
D04F7F8B1BA4DC7600B0F227 /* pcre */ = {
isa = PBXGroup;
children = (
63A2C0E81CC5F9FB00973404 /* pcre2_find_bracket.c */,
D04F7FF31BA4E6F300B0F227 /* pcre2_auto_possess.c */,
D04F7F8D1BA4DCD900B0F227 /* pcre2_compile.c */,
D04F7F901BA4DCE900B0F227 /* pcre2_config.c */,
@ -688,7 +691,8 @@
D04F7FF71BA4E82C00B0F227 /* pcre2_chartables.c.dist */,
);
name = pcre;
sourceTree = "<group>";
path = "pcre2-10.21/src";
sourceTree = SOURCE_ROOT;
};
D08A328E17B4455100F3A533 /* fish_tests */ = {
isa = PBXGroup;
@ -1273,6 +1277,7 @@
D04F7FDE1BA4E3AC00B0F227 /* pcre2_newline.c in Sources */,
D04F7FDF1BA4E3AC00B0F227 /* pcre2_ord2utf.c in Sources */,
D04F7FE01BA4E3AC00B0F227 /* pcre2_pattern_info.c in Sources */,
63A2C0E91CC60F3B00973404 /* pcre2_find_bracket.c in Sources */,
D04F7FF41BA4E6F300B0F227 /* pcre2_auto_possess.c in Sources */,
D04F7FE11BA4E3AC00B0F227 /* pcre2_serialize.c in Sources */,
D04F7FE21BA4E3AC00B0F227 /* pcre2_string_utils.c in Sources */,

30
osx/shared_headers/pcre2.h
View file

@ -5,7 +5,7 @@
/* This is the public header file for the PCRE library, second API, to be
#included by applications that call PCRE2 functions.
Copyright (c) 2015 University of Cambridge
Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -42,9 +42,9 @@ POSSIBILITY OF SUCH DAMAGE.
/* The current PCRE version information. */
#define PCRE2_MAJOR 10
#define PCRE2_MINOR 20
#define PCRE2_MINOR 21
#define PCRE2_PRERELEASE
#define PCRE2_DATE 2015-06-30
#define PCRE2_DATE 2016-01-12
/* When an application links to a PCRE DLL in Windows, the symbols that are
imported have to be identified as such. When building PCRE2, the appropriate
@ -120,6 +120,8 @@ D is inspected during pcre2_dfa_match() execution
#define PCRE2_UTF 0x00080000u /* C J M D */
#define PCRE2_NEVER_BACKSLASH_C 0x00100000u /* C */
#define PCRE2_ALT_CIRCUMFLEX 0x00200000u /* J M D */
#define PCRE2_ALT_VERBNAMES 0x00400000u /* C */
#define PCRE2_USE_OFFSET_LIMIT 0x00800000u /* J M D */
/* These are for pcre2_jit_compile(). */
@ -144,9 +146,13 @@ sanity checks). */
#define PCRE2_DFA_RESTART 0x00000040u
#define PCRE2_DFA_SHORTEST 0x00000080u
/* This is an additional option for pcre2_substitute(). */
/* These are additional options for pcre2_substitute(). */
#define PCRE2_SUBSTITUTE_GLOBAL 0x00000100u
#define PCRE2_SUBSTITUTE_GLOBAL 0x00000100u
#define PCRE2_SUBSTITUTE_EXTENDED 0x00000200u
#define PCRE2_SUBSTITUTE_UNSET_EMPTY 0x00000400u
#define PCRE2_SUBSTITUTE_UNKNOWN_UNSET 0x00000800u
#define PCRE2_SUBSTITUTE_OVERFLOW_LENGTH 0x00001000u
/* Newline and \R settings, for use in compile contexts. The newline values
must be kept in step with values set in config.h and both sets must all be
@ -233,6 +239,12 @@ numbers must not be changed. */
#define PCRE2_ERROR_RECURSIONLIMIT (-53)
#define PCRE2_ERROR_UNAVAILABLE (-54)
#define PCRE2_ERROR_UNSET (-55)
#define PCRE2_ERROR_BADOFFSETLIMIT (-56)
#define PCRE2_ERROR_BADREPESCAPE (-57)
#define PCRE2_ERROR_REPMISSINGBRACE (-58)
#define PCRE2_ERROR_BADSUBSTITUTION (-59)
#define PCRE2_ERROR_BADSUBSPATTERN (-60)
#define PCRE2_ERROR_TOOMANYREPLACE (-61)
/* Request types for pcre2_pattern_info() */
@ -259,6 +271,7 @@ numbers must not be changed. */
#define PCRE2_INFO_NEWLINE 20
#define PCRE2_INFO_RECURSIONLIMIT 21
#define PCRE2_INFO_SIZE 22
#define PCRE2_INFO_HASBACKSLASHC 23
/* Request types for pcre2_config(). */
@ -291,6 +304,7 @@ define special values to indicate zero-terminated strings and unset offsets in
the offset vector (ovector). */
#define PCRE2_SIZE size_t
#define PCRE2_SIZE_MAX SIZE_MAX
#define PCRE2_ZERO_TERMINATED (~(PCRE2_SIZE)0)
#define PCRE2_UNSET (~(PCRE2_SIZE)0)
@ -388,6 +402,8 @@ PCRE2_EXP_DECL void pcre2_compile_context_free(pcre2_compile_context *); \
PCRE2_EXP_DECL int pcre2_set_bsr(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int pcre2_set_character_tables(pcre2_compile_context *, \
const unsigned char *); \
PCRE2_EXP_DECL int pcre2_set_max_pattern_length(pcre2_compile_context *, \
PCRE2_SIZE); \
PCRE2_EXP_DECL int pcre2_set_newline(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int pcre2_set_parens_nest_limit(pcre2_compile_context *, \
uint32_t); \
@ -405,6 +421,8 @@ PCRE2_EXP_DECL int pcre2_set_callout(pcre2_match_context *, \
int (*)(pcre2_callout_block *, void *), void *); \
PCRE2_EXP_DECL int pcre2_set_match_limit(pcre2_match_context *, \
uint32_t); \
PCRE2_EXP_DECL int pcre2_set_offset_limit(pcre2_match_context *, \
PCRE2_SIZE); \
PCRE2_EXP_DECL int pcre2_set_recursion_limit(pcre2_match_context *, \
uint32_t); \
PCRE2_EXP_DECL int pcre2_set_recursion_memory_management( \
@ -606,8 +624,10 @@ pcre2_compile are called by application code. */
#define pcre2_set_character_tables PCRE2_SUFFIX(pcre2_set_character_tables_)
#define pcre2_set_compile_recursion_guard PCRE2_SUFFIX(pcre2_set_compile_recursion_guard_)
#define pcre2_set_match_limit PCRE2_SUFFIX(pcre2_set_match_limit_)
#define pcre2_set_max_pattern_length PCRE2_SUFFIX(pcre2_set_max_pattern_length_)
#define pcre2_set_newline PCRE2_SUFFIX(pcre2_set_newline_)
#define pcre2_set_parens_nest_limit PCRE2_SUFFIX(pcre2_set_parens_nest_limit_)
#define pcre2_set_offset_limit PCRE2_SUFFIX(pcre2_set_offset_limit_)
#define pcre2_set_recursion_limit PCRE2_SUFFIX(pcre2_set_recursion_limit_)
#define pcre2_set_recursion_memory_management PCRE2_SUFFIX(pcre2_set_recursion_memory_management_)
#define pcre2_substitute PCRE2_SUFFIX(pcre2_substitute_)

674
pcre2-10.20/COPYING
View file

@ -1,674 +0,0 @@
GNU GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU General Public License is a free, copyleft license for
software and other kinds of works.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
the GNU General Public License is intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users. We, the Free Software Foundation, use the
GNU General Public License for most of our software; it applies also to
any other work released this way by its authors. You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
To protect your rights, we need to prevent others from denying you
these rights or asking you to surrender the rights. Therefore, you have
certain responsibilities if you distribute copies of the software, or if
you modify it: responsibilities to respect the freedom of others.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must pass on to the recipients the same
freedoms that you received. You must make sure that they, too, receive
or can get the source code. And you must show them these terms so they
know their rights.
Developers that use the GNU GPL protect your rights with two steps:
(1) assert copyright on the software, and (2) offer you this License
giving you legal permission to copy, distribute and/or modify it.
For the developers' and authors' protection, the GPL clearly explains
that there is no warranty for this free software. For both users' and
authors' sake, the GPL requires that modified versions be marked as
changed, so that their problems will not be attributed erroneously to
authors of previous versions.
Some devices are designed to deny users access to install or run
modified versions of the software inside them, although the manufacturer
can do so. This is fundamentally incompatible with the aim of
protecting users' freedom to change the software. The systematic
pattern of such abuse occurs in the area of products for individuals to
use, which is precisely where it is most unacceptable. Therefore, we
have designed this version of the GPL to prohibit the practice for those
products. If such problems arise substantially in other domains, we
stand ready to extend this provision to those domains in future versions
of the GPL, as needed to protect the freedom of users.
Finally, every program is threatened constantly by software patents.
States should not allow patents to restrict development and use of
software on general-purpose computers, but in those that do, we wish to
avoid the special danger that patents applied to a free program could
make it effectively proprietary. To prevent this, the GPL assures that
patents cannot be used to render the program non-free.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Use with the GNU Affero General Public License.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU Affero General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the special requirements of the GNU Affero General Public License,
section 13, concerning interaction through a network will apply to the
combination as such.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program 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 3 of the License, or
(at your option) any later version.
This program 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 <http://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If the program does terminal interaction, make it output a short
notice like this when it starts in an interactive mode:
<program> Copyright (C) <year> <name of author>
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, your program's commands
might be different; for a GUI interface, you would use an "about box".
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU GPL, see
<http://www.gnu.org/licenses/>.
The GNU General Public License does not permit incorporating your program
into proprietary programs. If your program is a subroutine library, you
may consider it more useful to permit linking proprietary applications with
the library. If this is what you want to do, use the GNU Lesser General
Public License instead of this License. But first, please read
<http://www.gnu.org/philosophy/why-not-lgpl.html>.

47
pcre2-10.20/NEWS
View file

@ -1,47 +0,0 @@
News about PCRE2 releases
-------------------------
Version 10.20 30-June-2015
--------------------------
1. Callouts with string arguments and the pcre2_callout_enumerate() function
have been implemented.
2. The PCRE2_NEVER_BACKSLASH_C option, which locks out the use of \C, is added.
3. The PCRE2_ALT_CIRCUMFLEX option lets ^ match after a newline at the end of a
subject in multiline mode.
4. The way named subpatterns are handled has been refactored. The previous
approach had several bugs.
5. The handling of \c in EBCDIC environments has been changed to conform to the
perlebcdic document. This is an incompatible change.
6. Bugs have been mended, many of them discovered by fuzzers.
Version 10.10 06-March-2015
---------------------------
1. Serialization and de-serialization functions have been added to the API,
making it possible to save and restore sets of compiled patterns, though
restoration must be done in the same environment that was used for compilation.
2. The (*NO_JIT) feature has been added; this makes it possible for a pattern
creator to specify that JIT is not to be used.
3. A number of bugs have been fixed. In particular, bugs that caused building
on Windows using CMake to fail have been mended.
Version 10.00 05-January-2015
-----------------------------
Version 10.00 is the first release of PCRE2, a revised API for the PCRE
library. Changes prior to 10.00 are logged in the ChangeLog file for the old
API, up to item 20 for release 8.36. New programs are recommended to use the
new library. Programs that use the original (PCRE1) API will need changing
before linking with the new library.
****

315
pcre2-10.20/src/pcre2_substitute.c
View file

@ -1,315 +0,0 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/*************************************************
* Match and substitute *
*************************************************/
/* This function applies a compiled re to a subject string and creates a new
string with substitutions. The first 7 arguments are the same as for
pcre2_match(). Either string length may be PCRE2_ZERO_TERMINATED.
Arguments:
code points to the compiled expression
subject points to the subject string
length length of subject string (may contain binary zeros)
start_offset where to start in the subject string
options option bits
match_data points to a match_data block, or is NULL
context points a PCRE2 context
replacement points to the replacement string
rlength length of replacement string
buffer where to put the substituted string
blength points to length of buffer; updated to length of string
Returns: >= 0 number of substitutions made
< 0 an error code
PCRE2_ERROR_BADREPLACEMENT means invalid use of $
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_substitute(const pcre2_code *code, PCRE2_SPTR subject, PCRE2_SIZE length,
PCRE2_SIZE start_offset, uint32_t options, pcre2_match_data *match_data,
pcre2_match_context *mcontext, PCRE2_SPTR replacement, PCRE2_SIZE rlength,
PCRE2_UCHAR *buffer, PCRE2_SIZE *blength)
{
int rc;
int subs;
uint32_t ovector_count;
uint32_t goptions = 0;
BOOL match_data_created = FALSE;
BOOL global = FALSE;
PCRE2_SIZE buff_offset, lengthleft, fraglength;
PCRE2_SIZE *ovector;
/* Partial matching is not valid. */
if ((options & (PCRE2_PARTIAL_HARD|PCRE2_PARTIAL_SOFT)) != 0)
return PCRE2_ERROR_BADOPTION;
/* If no match data block is provided, create one. */
if (match_data == NULL)
{
pcre2_general_context *gcontext = (mcontext == NULL)?
(pcre2_general_context *)code :
(pcre2_general_context *)mcontext;
match_data = pcre2_match_data_create_from_pattern(code, gcontext);
if (match_data == NULL) return PCRE2_ERROR_NOMEMORY;
match_data_created = TRUE;
}
ovector = pcre2_get_ovector_pointer(match_data);
ovector_count = pcre2_get_ovector_count(match_data);
/* Check UTF replacement string if necessary. */
#ifdef SUPPORT_UNICODE
if ((code->overall_options & PCRE2_UTF) != 0 &&
(options & PCRE2_NO_UTF_CHECK) == 0)
{
rc = PRIV(valid_utf)(replacement, rlength, &(match_data->rightchar));
if (rc != 0)
{
match_data->leftchar = 0;
goto EXIT;
}
}
#endif /* SUPPORT_UNICODE */
/* Notice the global option and remove it from the options that are passed to
pcre2_match(). */
if ((options & PCRE2_SUBSTITUTE_GLOBAL) != 0)
{
options &= ~PCRE2_SUBSTITUTE_GLOBAL;
global = TRUE;
}
/* Find lengths of zero-terminated strings. */
if (length == PCRE2_ZERO_TERMINATED) length = PRIV(strlen)(subject);
if (rlength == PCRE2_ZERO_TERMINATED) rlength = PRIV(strlen)(replacement);
/* Copy up to the start offset */
if (start_offset > *blength) goto NOROOM;
memcpy(buffer, subject, start_offset * (PCRE2_CODE_UNIT_WIDTH/8));
buff_offset = start_offset;
lengthleft = *blength - start_offset;
/* Loop for global substituting. */
subs = 0;
do
{
PCRE2_SIZE i;
rc = pcre2_match(code, subject, length, start_offset, options|goptions,
match_data, mcontext);
/* Any error other than no match returns the error code. No match when not
doing the special after-empty-match global rematch, or when at the end of the
subject, breaks the global loop. Otherwise, advance the starting point by one
character, copying it to the output, and try again. */
if (rc < 0)
{
PCRE2_SIZE save_start;
if (rc != PCRE2_ERROR_NOMATCH) goto EXIT;
if (goptions == 0 || start_offset >= length) break;
save_start = start_offset++;
if ((code->overall_options & PCRE2_UTF) != 0)
{
#if PCRE2_CODE_UNIT_WIDTH == 8
while (start_offset < length && (subject[start_offset] & 0xc0) == 0x80)
start_offset++;
#elif PCRE2_CODE_UNIT_WIDTH == 16
while (start_offset < length &&
(subject[start_offset] & 0xfc00) == 0xdc00)
start_offset++;
#endif
}
fraglength = start_offset - save_start;
if (lengthleft < fraglength) goto NOROOM;
memcpy(buffer + buff_offset, subject + save_start,
fraglength*(PCRE2_CODE_UNIT_WIDTH/8));
buff_offset += fraglength;
lengthleft -= fraglength;
goptions = 0;
continue;
}
/* Handle a successful match. */
subs++;
if (rc == 0) rc = ovector_count;
fraglength = ovector[0] - start_offset;
if (fraglength >= lengthleft) goto NOROOM;
memcpy(buffer + buff_offset, subject + start_offset,
fraglength*(PCRE2_CODE_UNIT_WIDTH/8));
buff_offset += fraglength;
lengthleft -= fraglength;
for (i = 0; i < rlength; i++)
{
if (replacement[i] == CHAR_DOLLAR_SIGN)
{
int group, n;
BOOL inparens;
PCRE2_SIZE sublength;
PCRE2_UCHAR next;
PCRE2_UCHAR name[33];
if (++i == rlength) goto BAD;
if ((next = replacement[i]) == CHAR_DOLLAR_SIGN) goto LITERAL;
group = -1;
n = 0;
inparens = FALSE;
if (next == CHAR_LEFT_CURLY_BRACKET)
{
if (++i == rlength) goto BAD;
next = replacement[i];
inparens = TRUE;
}
if (next >= CHAR_0 && next <= CHAR_9)
{
group = next - CHAR_0;
while (++i < rlength)
{
next = replacement[i];
if (next < CHAR_0 || next > CHAR_9) break;
group = group * 10 + next - CHAR_0;
}
}
else
{
const uint8_t *ctypes = code->tables + ctypes_offset;
while (MAX_255(next) && (ctypes[next] & ctype_word) != 0)
{
name[n++] = next;
if (n > 32) goto BAD;
if (i == rlength) break;
next = replacement[++i];
}
if (n == 0) goto BAD;
name[n] = 0;
}
if (inparens)
{
if (i == rlength || next != CHAR_RIGHT_CURLY_BRACKET) goto BAD;
}
else i--; /* Last code unit of name/number */
/* Have found a syntactically correct group number or name. */
sublength = lengthleft;
if (group < 0)
rc = pcre2_substring_copy_byname(match_data, name,
buffer + buff_offset, &sublength);
else
rc = pcre2_substring_copy_bynumber(match_data, group,
buffer + buff_offset, &sublength);
if (rc < 0) goto EXIT;
buff_offset += sublength;
lengthleft -= sublength;
}
/* Handle a literal code unit */
else
{
LITERAL:
if (lengthleft-- < 1) goto NOROOM;
buffer[buff_offset++] = replacement[i];
}
}
/* The replacement has been copied to the output. Update the start offset to
point to the rest of the subject string. If we matched an empty string,
do the magic for global matches. */
start_offset = ovector[1];
goptions = (ovector[0] != ovector[1])? 0 :
PCRE2_ANCHORED|PCRE2_NOTEMPTY_ATSTART;
} while (global); /* Repeat "do" loop */
/* Copy the rest of the subject and return the number of substitutions. */
rc = subs;
fraglength = length - start_offset;
if (fraglength + 1 > lengthleft) goto NOROOM;
memcpy(buffer + buff_offset, subject + start_offset,
fraglength*(PCRE2_CODE_UNIT_WIDTH/8));
buff_offset += fraglength;
buffer[buff_offset] = 0;
*blength = buff_offset;
EXIT:
if (match_data_created) pcre2_match_data_free(match_data);
else match_data->rc = rc;
return rc;
NOROOM:
rc = PCRE2_ERROR_NOMEMORY;
goto EXIT;
BAD:
rc = PCRE2_ERROR_BADREPLACEMENT;
goto EXIT;
}
/* End of pcre2_substitute.c */

2
pcre2-10.20/.gitignore → pcre2-10.21/.gitignore vendored
View file

@ -12,4 +12,4 @@ pcre2_chartables.c
pcre2-config
pcre2test
pcre2.h
stamp-h1
stamp-h1

2
pcre2-10.20/132html → pcre2-10.21/132html
View file

@ -148,7 +148,7 @@ while (<STDIN>)
printf("<li><a name=\"TOC%d\" href=\"#SEC%d\">$title</a>\n",
$ref, $ref);
printf TEMP ("<br><a name=\"SEC%d\" href=\"#TOC1\">$title</a><br>\n",
$ref, $ref);
$ref);
$ref++;
}
else

6
pcre2-10.20/AUTHORS → pcre2-10.21/AUTHORS
View file

@ -8,7 +8,7 @@ Email domain: cam.ac.uk
University of Cambridge Computing Service,
Cambridge, England.
Copyright (c) 1997-2015 University of Cambridge
Copyright (c) 1997-2016 University of Cambridge
All rights reserved
@ -19,7 +19,7 @@ Written by: Zoltan Herczeg
Email local part: hzmester
Emain domain: freemail.hu
Copyright(c) 2010-2015 Zoltan Herczeg
Copyright(c) 2010-2016 Zoltan Herczeg
All rights reserved.
@ -30,7 +30,7 @@ Written by: Zoltan Herczeg
Email local part: hzmester
Emain domain: freemail.hu
Copyright(c) 2009-2015 Zoltan Herczeg
Copyright(c) 2009-2016 Zoltan Herczeg
All rights reserved.
####

16
pcre2-10.20/CMakeLists.txt → pcre2-10.21/CMakeLists.txt
View file

@ -67,7 +67,10 @@
# 2013-10-08 PH got rid of the "source" command, which is a bash-ism (use ".")
# 2013-11-05 PH added support for PARENS_NEST_LIMIT
# 2014-08-29 PH converted the file for PCRE2 (which has no C++).
# 2015-04024 PH added support for PCRE2_DEBUG
# 2015-04-24 PH added support for PCRE2_DEBUG
# 2015-07-16 PH updated for new pcre2_find_bracket source module
# 2015-08-24 PH correct C_FLAGS setting (patch from Roy Ivy III)
# 2015-10=16 PH added support for never-backslash-C
PROJECT(PCRE2 C)
@ -79,7 +82,7 @@ CMAKE_POLICY(SET CMP0026 OLD)
SET(CMAKE_MODULE_PATH ${PROJECT_SOURCE_DIR}/cmake) # for FindReadline.cmake
SET(CMAKE_C_FLAGS -I${PROJECT_SOURCE_DIR}/src)
SET(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -I${PROJECT_SOURCE_DIR}/src")
# external packages
FIND_PACKAGE( BZip2 )
@ -160,6 +163,9 @@ SET(PCRE2_SUPPORT_UNICODE ON CACHE BOOL
SET(PCRE2_SUPPORT_BSR_ANYCRLF OFF CACHE BOOL
"ON=Backslash-R matches only LF CR and CRLF, OFF=Backslash-R matches all Unicode Linebreaks")
SET(PCRE2_NEVER_BACKSLASH_C OFF CACHE BOOL
"If ON, backslash-C (upper case C) is locked out.")
SET(PCRE2_SUPPORT_VALGRIND OFF CACHE BOOL
"Enable Valgrind support.")
@ -250,6 +256,10 @@ IF(PCRE2_SUPPORT_BSR_ANYCRLF)
SET(BSR_ANYCRLF 1)
ENDIF(PCRE2_SUPPORT_BSR_ANYCRLF)
IF(PCRE2_NEVER_BACKSLASH_C)
SET(NEVER_BACKSLASH_C 1)
ENDIF(PCRE2_NEVER_BACKSLASH_C)
IF(PCRE2_SUPPORT_UNICODE)
SET(SUPPORT_UNICODE 1)
ENDIF(PCRE2_SUPPORT_UNICODE)
@ -390,6 +400,7 @@ SET(PCRE2_SOURCES
src/pcre2_context.c
src/pcre2_dfa_match.c
src/pcre2_error.c
src/pcre2_find_bracket.c
src/pcre2_jit_compile.c
src/pcre2_maketables.c
src/pcre2_match.c
@ -716,6 +727,7 @@ IF(PCRE2_SHOW_REPORT)
MESSAGE(STATUS " Enable Unicode support .......... : ${PCRE2_SUPPORT_UNICODE}")
MESSAGE(STATUS " Newline char/sequence ........... : ${PCRE2_NEWLINE}")
MESSAGE(STATUS " \\R matches only ANYCRLF ......... : ${PCRE2_SUPPORT_BSR_ANYCRLF}")
MESSAGE(STATUS " \\C is disabled .................. : ${PCRE2_NEVER_BACKSLASH_C}")
MESSAGE(STATUS " EBCDIC coding ................... : ${PCRE2_EBCDIC}")
MESSAGE(STATUS " EBCDIC coding with NL=0x25 ...... : ${PCRE2_EBCDIC_NL25}")
MESSAGE(STATUS " Rebuild char tables ............. : ${PCRE2_REBUILD_CHARTABLES}")

5
pcre2-10.21/COPYING Normal file
View file

@ -0,0 +1,5 @@
PCRE2 LICENCE
Please see the file LICENCE in the PCRE2 distribution for licensing details.
End

391
pcre2-10.20/ChangeLog → pcre2-10.21/ChangeLog
View file

@ -1,6 +1,397 @@
Change Log for PCRE2
--------------------
Version 10.21 12-January-2016
-----------------------------
1. Improve matching speed of patterns starting with + or * in JIT.
2. Use memchr() to find the first character in an unanchored match in 8-bit
mode in the interpreter. This gives a significant speed improvement.
3. Removed a redundant copy of the opcode_possessify table in the
pcre2_auto_possessify.c source.
4. Fix typos in dftables.c for z/OS.
5. Change 36 for 10.20 broke the handling of [[:>:]] and [[:<:]] in that
processing them could involve a buffer overflow if the following character was
an opening parenthesis.
6. Change 36 for 10.20 also introduced a bug in processing this pattern:
/((?x)(*:0))#(?'/. Specifically: if a setting of (?x) was followed by a (*MARK)
setting (which (*:0) is), then (?x) did not get unset at the end of its group
during the scan for named groups, and hence the external # was incorrectly
treated as a comment and the invalid (?' at the end of the pattern was not
diagnosed. This caused a buffer overflow during the real compile. This bug was
discovered by Karl Skomski with the LLVM fuzzer.
7. Moved the pcre2_find_bracket() function from src/pcre2_compile.c into its
own source module to avoid a circular dependency between src/pcre2_compile.c
and src/pcre2_study.c
8. A callout with a string argument containing an opening square bracket, for
example /(?C$[$)(?<]/, was incorrectly processed and could provoke a buffer
overflow. This bug was discovered by Karl Skomski with the LLVM fuzzer.
9. The handling of callouts during the pre-pass for named group identification
has been tightened up.
10. The quantifier {1} can be ignored, whether greedy, non-greedy, or
possessive. This is a very minor optimization.
11. A possessively repeated conditional group that could match an empty string,
for example, /(?(R))*+/, was incorrectly compiled.
12. The Unicode tables have been updated to Unicode 8.0.0 (thanks to Christian
Persch).
13. An empty comment (?#) in a pattern was incorrectly processed and could
provoke a buffer overflow. This bug was discovered by Karl Skomski with the
LLVM fuzzer.
14. Fix infinite recursion in the JIT compiler when certain patterns such as
/(?:|a|){100}x/ are analysed.
15. Some patterns with character classes involving [: and \\ were incorrectly
compiled and could cause reading from uninitialized memory or an incorrect
error diagnosis. Examples are: /[[:\\](?<[::]/ and /[[:\\](?'abc')[a:]. The
first of these bugs was discovered by Karl Skomski with the LLVM fuzzer.
16. Pathological patterns containing many nested occurrences of [: caused
pcre2_compile() to run for a very long time. This bug was found by the LLVM
fuzzer.
17. A missing closing parenthesis for a callout with a string argument was not
being diagnosed, possibly leading to a buffer overflow. This bug was found by
the LLVM fuzzer.
18. A conditional group with only one branch has an implicit empty alternative
branch and must therefore be treated as potentially matching an empty string.
19. If (?R was followed by - or + incorrect behaviour happened instead of a
diagnostic. This bug was discovered by Karl Skomski with the LLVM fuzzer.
20. Another bug that was introduced by change 36 for 10.20: conditional groups
whose condition was an assertion preceded by an explicit callout with a string
argument might be incorrectly processed, especially if the string contained \Q.
This bug was discovered by Karl Skomski with the LLVM fuzzer.
21. Compiling PCRE2 with the sanitize options of clang showed up a number of
very pedantic coding infelicities and a buffer overflow while checking a UTF-8
string if the final multi-byte UTF-8 character was truncated.
22. For Perl compatibility in EBCDIC environments, ranges such as a-z in a
class, where both values are literal letters in the same case, omit the
non-letter EBCDIC code points within the range.
23. Finding the minimum matching length of complex patterns with back
references and/or recursions can take a long time. There is now a cut-off that
gives up trying to find a minimum length when things get too complex.
24. An optimization has been added that speeds up finding the minimum matching
length for patterns containing repeated capturing groups or recursions.
25. If a pattern contained a back reference to a group whose number was
duplicated as a result of appearing in a (?|...) group, the computation of the
minimum matching length gave a wrong result, which could cause incorrect "no
match" errors. For such patterns, a minimum matching length cannot at present
be computed.
26. Added a check for integer overflow in conditions (?(<digits>) and
(?(R<digits>). This omission was discovered by Karl Skomski with the LLVM
fuzzer.
27. Fixed an issue when \p{Any} inside an xclass did not read the current
character.
28. If pcre2grep was given the -q option with -c or -l, or when handling a
binary file, it incorrectly wrote output to stdout.
29. The JIT compiler did not restore the control verb head in case of *THEN
control verbs. This issue was found by Karl Skomski with a custom LLVM fuzzer.
30. The way recursive references such as (?3) are compiled has been re-written
because the old way was the cause of many issues. Now, conversion of the group
number into a pattern offset does not happen until the pattern has been
completely compiled. This does mean that detection of all infinitely looping
recursions is postponed till match time. In the past, some easy ones were
detected at compile time. This re-writing was done in response to yet another
bug found by the LLVM fuzzer.
31. A test for a back reference to a non-existent group was missing for items
such as \987. This caused incorrect code to be compiled. This issue was found
by Karl Skomski with a custom LLVM fuzzer.
32. Error messages for syntax errors following \g and \k were giving inaccurate
offsets in the pattern.
33. Improve the performance of starting single character repetitions in JIT.
34. (*LIMIT_MATCH=) now gives an error instead of setting the value to 0.
35. Error messages for syntax errors in *LIMIT_MATCH and *LIMIT_RECURSION now
give the right offset instead of zero.
36. The JIT compiler should not check repeats after a {0,1} repeat byte code.
This issue was found by Karl Skomski with a custom LLVM fuzzer.
37. The JIT compiler should restore the control chain for empty possessive
repeats. This issue was found by Karl Skomski with a custom LLVM fuzzer.
38. A bug which was introduced by the single character repetition optimization
was fixed.
39. Match limit check added to recursion. This issue was found by Karl Skomski
with a custom LLVM fuzzer.
40. Arrange for the UTF check in pcre2_match() and pcre2_dfa_match() to look
only at the part of the subject that is relevant when the starting offset is
non-zero.
41. Improve first character match in JIT with SSE2 on x86.
42. Fix two assertion fails in JIT. These issues were found by Karl Skomski
with a custom LLVM fuzzer.
43. Correct the setting of CMAKE_C_FLAGS in CMakeLists.txt (patch from Roy Ivy
III).
44. Fix bug in RunTest.bat for new test 14, and adjust the script for the added
test (there are now 20 in total).
45. Fixed a corner case of range optimization in JIT.
46. Add the ${*MARK} facility to pcre2_substitute().
47. Modifier lists in pcre2test were splitting at spaces without the required
commas.
48. Implemented PCRE2_ALT_VERBNAMES.
49. Fixed two issues in JIT. These were found by Karl Skomski with a custom
LLVM fuzzer.
50. The pcre2test program has been extended by adding the #newline_default
command. This has made it possible to run the standard tests when PCRE2 is
compiled with either CR or CRLF as the default newline convention. As part of
this work, the new command was added to several test files and the testing
scripts were modified. The pcre2grep tests can now also be run when there is no
LF in the default newline convention.
51. The RunTest script has been modified so that, when JIT is used and valgrind
is specified, a valgrind suppressions file is set up to ignore "Invalid read of
size 16" errors because these are false positives when the hardware supports
the SSE2 instruction set.
52. It is now possible to have comment lines amid the subject strings in
pcre2test (and perltest.sh) input.
53. Implemented PCRE2_USE_OFFSET_LIMIT and pcre2_set_offset_limit().
54. Add the null_context modifier to pcre2test so that calling pcre2_compile()
and the matching functions with NULL contexts can be tested.
55. Implemented PCRE2_SUBSTITUTE_EXTENDED.
56. In a character class such as [\W\p{Any}] where both a negative-type escape
("not a word character") and a property escape were present, the property
escape was being ignored.
57. Fixed integer overflow for patterns whose minimum matching length is very,
very large.
58. Implemented --never-backslash-C.
59. Change 55 above introduced a bug by which certain patterns provoked the
erroneous error "\ at end of pattern".
60. The special sequences [[:<:]] and [[:>:]] gave rise to incorrect compiling
errors or other strange effects if compiled in UCP mode. Found with libFuzzer
and AddressSanitizer.
61. Whitespace at the end of a pcre2test pattern line caused a spurious error
message if there were only single-character modifiers. It should be ignored.
62. The use of PCRE2_NO_AUTO_CAPTURE could cause incorrect compilation results
or segmentation errors for some patterns. Found with libFuzzer and
AddressSanitizer.
63. Very long names in (*MARK) or (*THEN) etc. items could provoke a buffer
overflow.
64. Improve error message for overly-complicated patterns.
65. Implemented an optional replication feature for patterns in pcre2test, to
make it easier to test long repetitive patterns. The tests for 63 above are
converted to use the new feature.
66. In the POSIX wrapper, if regerror() was given too small a buffer, it could
misbehave.
67. In pcre2_substitute() in UTF mode, the UTF validity check on the
replacement string was happening before the length setting when the replacement
string was zero-terminated.
68. In pcre2_substitute() in UTF mode, PCRE2_NO_UTF_CHECK can be set for the
second and subsequent calls to pcre2_match().
69. There was no check for integer overflow for a replacement group number in
pcre2_substitute(). An added check for a number greater than the largest group
number in the pattern means this is not now needed.
70. The PCRE2-specific VERSION condition didn't work correctly if only one
digit was given after the decimal point, or if more than two digits were given.
It now works with one or two digits, and gives a compile time error if more are
given.
71. In pcre2_substitute() there was the possibility of reading one code unit
beyond the end of the replacement string.
72. The code for checking a subject's UTF-32 validity for a pattern with a
lookbehind involved an out-of-bounds pointer, which could potentially cause
trouble in some environments.
73. The maximum lookbehind length was incorrectly calculated for patterns such
as /(?<=(a)(?-1))x/ which have a recursion within a backreference.
74. Give an error if a lookbehind assertion is longer than 65535 code units.
75. Give an error in pcre2_substitute() if a match ends before it starts (as a
result of the use of \K).
76. Check the length of subpattern names and the names in (*MARK:xx) etc.
dynamically to avoid the possibility of integer overflow.
77. Implement pcre2_set_max_pattern_length() so that programs can restrict the
size of patterns that they are prepared to handle.
78. (*NO_AUTO_POSSESS) was not working.
79. Adding group information caching improves the speed of compiling when
checking whether a group has a fixed length and/or could match an empty string,
especially when recursion or subroutine calls are involved. However, this
cannot be used when (?| is present in the pattern because the same number may
be used for groups of different sizes. To catch runaway patterns in this
situation, counts have been introduced to the functions that scan for empty
branches or compute fixed lengths.
80. Allow for the possibility of the size of the nest_save structure not being
a factor of the size of the compiling workspace (it currently is).
81. Check for integer overflow in minimum length calculation and cap it at
65535.
82. Small optimizations in code for finding the minimum matching length.
83. Lock out configuring for EBCDIC with non-8-bit libraries.
84. Test for error code <= 0 in regerror().
85. Check for too many replacements (more than INT_MAX) in pcre2_substitute().
86. Avoid the possibility of computing with an out-of-bounds pointer (though
not dereferencing it) while handling lookbehind assertions.
87. Failure to get memory for the match data in regcomp() is now given as a
regcomp() error instead of waiting for regexec() to pick it up.
88. In pcre2_substitute(), ensure that CRLF is not split when it is a valid
newline sequence.
89. Paranoid check in regcomp() for bad error code from pcre2_compile().
90. Run test 8 (internal offsets and code sizes) for link sizes 3 and 4 as well
as for link size 2.
91. Document that JIT has a limit on pattern size, and give more information
about JIT compile failures in pcre2test.
92. Implement PCRE2_INFO_HASBACKSLASHC.
93. Re-arrange valgrind support code in pcre2test to avoid spurious reports
with JIT (possibly caused by SSE2?).
94. Support offset_limit in JIT.
95. A sequence such as [[:punct:]b] that is, a POSIX character class followed
by a single ASCII character in a class item, was incorrectly compiled in UCP
mode. The POSIX class got lost, but only if the single character followed it.
96. [:punct:] in UCP mode was matching some characters in the range 128-255
that should not have been matched.
97. If [:^ascii:] or [:^xdigit:] are present in a non-negated class, all
characters with code points greater than 255 are in the class. When a Unicode
property was also in the class (if PCRE2_UCP is set, escapes such as \w are
turned into Unicode properties), wide characters were not correctly handled,
and could fail to match.
98. In pcre2test, make the "startoffset" modifier a synonym of "offset",
because it sets the "startoffset" parameter for pcre2_match().
99. If PCRE2_AUTO_CALLOUT was set on a pattern that had a (?# comment between
an item and its qualifier (for example, A(?#comment)?B) pcre2_compile()
misbehaved. This bug was found by the LLVM fuzzer.
100. The error for an invalid UTF pattern string always gave the code unit
offset as zero instead of where the invalidity was found.
101. Further to 97 above, negated classes such as [^[:^ascii:]\d] were also not
working correctly in UCP mode.
102. Similar to 99 above, if an isolated \E was present between an item and its
qualifier when PCRE2_AUTO_CALLOUT was set, pcre2_compile() misbehaved. This bug
was found by the LLVM fuzzer.
103. The POSIX wrapper function regexec() crashed if the option REG_STARTEND
was set when the pmatch argument was NULL. It now returns REG_INVARG.
104. Allow for up to 32-bit numbers in the ordin() function in pcre2grep.
105. An empty \Q\E sequence between an item and its qualifier caused
pcre2_compile() to misbehave when auto callouts were enabled. This bug
was found by the LLVM fuzzer.
106. If both PCRE2_ALT_VERBNAMES and PCRE2_EXTENDED were set, and a (*MARK) or
other verb "name" ended with whitespace immediately before the closing
parenthesis, pcre2_compile() misbehaved. Example: /(*:abc )/, but only when
both those options were set.
107. In a number of places pcre2_compile() was not handling NULL characters
correctly, and pcre2test with the "bincode" modifier was not always correctly
displaying fields containing NULLS:
(a) Within /x extended #-comments
(b) Within the "name" part of (*MARK) and other *verbs
(c) Within the text argument of a callout
108. If a pattern that was compiled with PCRE2_EXTENDED started with white
space or a #-type comment that was followed by (?-x), which turns off
PCRE2_EXTENDED, and there was no subsequent (?x) to turn it on again,
pcre2_compile() assumed that (?-x) applied to the whole pattern and
consequently mis-compiled it. This bug was found by the LLVM fuzzer. The fix
for this bug means that a setting of any of the (?imsxU) options at the start
of a pattern is no longer transferred to the options that are returned by
PCRE2_INFO_ALLOPTIONS. In fact, this was an anachronism that should have
changed when the effects of those options were all moved to compile time.
109. An escaped closing parenthesis in the "name" part of a (*verb) when
PCRE2_ALT_VERBNAMES was set caused pcre2_compile() to malfunction. This bug
was found by the LLVM fuzzer.
110. Implemented PCRE2_SUBSTITUTE_UNSET_EMPTY, and updated pcre2test to make it
possible to test it.
111. "Harden" pcre2test against ridiculously large values in modifiers and
command line arguments.
112. Implemented PCRE2_SUBSTITUTE_UNKNOWN_UNSET and PCRE2_SUBSTITUTE_OVERFLOW_
LENGTH.
113. Fix printing of *MARK names that contain binary zeroes in pcre2test.
Version 10.20 30-June-2015
--------------------------

0
pcre2-10.20/CheckMan → pcre2-10.21/CheckMan
View file

0
pcre2-10.20/CleanTxt → pcre2-10.21/CleanTxt
View file

0
pcre2-10.20/Detrail → pcre2-10.21/Detrail
View file

0
pcre2-10.20/HACKING → pcre2-10.21/HACKING
View file

0
pcre2-10.20/INSTALL → pcre2-10.21/INSTALL
View file

6
pcre2-10.20/LICENCE → pcre2-10.21/LICENCE
View file

@ -25,7 +25,7 @@ Email domain: cam.ac.uk
University of Cambridge Computing Service,
Cambridge, England.
Copyright (c) 1997-2015 University of Cambridge
Copyright (c) 1997-2016 University of Cambridge
All rights reserved.
@ -36,7 +36,7 @@ Written by: Zoltan Herczeg
Email local part: hzmester
Emain domain: freemail.hu
Copyright(c) 2010-2015 Zoltan Herczeg
Copyright(c) 2010-2016 Zoltan Herczeg
All rights reserved.
@ -47,7 +47,7 @@ Written by: Zoltan Herczeg
Email local part: hzmester
Emain domain: freemail.hu
Copyright(c) 2009-2015 Zoltan Herczeg
Copyright(c) 2009-2016 Zoltan Herczeg
All rights reserved.

30
pcre2-10.20/Makefile.am → pcre2-10.21/Makefile.am
View file

@ -64,6 +64,7 @@ dist_html_DATA = \
doc/html/pcre2_set_character_tables.html \
doc/html/pcre2_set_compile_recursion_guard.html \
doc/html/pcre2_set_match_limit.html \
doc/html/pcre2_set_offset_limit.html \
doc/html/pcre2_set_newline.html \
doc/html/pcre2_set_parens_nest_limit.html \
doc/html/pcre2_set_recursion_limit.html \
@ -143,6 +144,7 @@ dist_man_MANS = \
doc/pcre2_set_character_tables.3 \
doc/pcre2_set_compile_recursion_guard.3 \
doc/pcre2_set_match_limit.3 \
doc/pcre2_set_offset_limit.3 \
doc/pcre2_set_newline.3 \
doc/pcre2_set_parens_nest_limit.3 \
doc/pcre2_set_recursion_limit.3 \
@ -319,6 +321,7 @@ COMMON_SOURCES = \
src/pcre2_context.c \
src/pcre2_dfa_match.c \
src/pcre2_error.c \
src/pcre2_find_bracket.c \
src/pcre2_internal.h \
src/pcre2_intmodedep.h \
src/pcre2_jit_compile.c \
@ -586,6 +589,10 @@ EXTRA_DIST += \
testdata/testinput17 \
testdata/testinput18 \
testdata/testinput19 \
testdata/testinput20 \
testdata/testinput21 \
testdata/testinput22 \
testdata/testinput23 \
testdata/testinputEBC \
testdata/testoutput1 \
testdata/testoutput2 \
@ -596,9 +603,15 @@ EXTRA_DIST += \
testdata/testoutput5 \
testdata/testoutput6 \
testdata/testoutput7 \
testdata/testoutput8-16 \
testdata/testoutput8-32 \
testdata/testoutput8-8 \
testdata/testoutput8-16-2 \
testdata/testoutput8-16-3 \
testdata/testoutput8-16-3 \
testdata/testoutput8-32-2 \
testdata/testoutput8-32-3 \
testdata/testoutput8-32-4 \
testdata/testoutput8-8-2 \
testdata/testoutput8-8-3 \
testdata/testoutput8-8-4 \
testdata/testoutput9 \
testdata/testoutput10 \
testdata/testoutput11-16 \
@ -606,13 +619,22 @@ EXTRA_DIST += \
testdata/testoutput12-16 \
testdata/testoutput12-32 \
testdata/testoutput13 \
testdata/testoutput14 \
testdata/testoutput14-16 \
testdata/testoutput14-32 \
testdata/testoutput14-8 \
testdata/testoutput15 \
testdata/testoutput16 \
testdata/testoutput17 \
testdata/testoutput18 \
testdata/testoutput19 \
testdata/testoutput20 \
testdata/testoutput21 \
testdata/testoutput22-16 \
testdata/testoutput22-32 \
testdata/testoutput22-8 \
testdata/testoutput23 \
testdata/testoutputEBC \
testdata/valgrind-jit.supp \
testdata/wintestinput3 \
testdata/wintestoutput3 \
perltest.sh

70
pcre2-10.20/Makefile.in → pcre2-10.21/Makefile.in
View file

@ -186,7 +186,8 @@ LTLIBRARIES = $(lib_LTLIBRARIES)
libpcre2_16_la_DEPENDENCIES =
am__libpcre2_16_la_SOURCES_DIST = 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_internal.h \
src/pcre2_dfa_match.c src/pcre2_error.c \
src/pcre2_find_bracket.c src/pcre2_internal.h \
src/pcre2_intmodedep.h src/pcre2_jit_compile.c \
src/pcre2_maketables.c src/pcre2_match.c \
src/pcre2_match_data.c src/pcre2_newline.c src/pcre2_ord2utf.c \
@ -202,6 +203,7 @@ am__objects_1 = src/libpcre2_16_la-pcre2_auto_possess.lo \
src/libpcre2_16_la-pcre2_context.lo \
src/libpcre2_16_la-pcre2_dfa_match.lo \
src/libpcre2_16_la-pcre2_error.lo \
src/libpcre2_16_la-pcre2_find_bracket.lo \
src/libpcre2_16_la-pcre2_jit_compile.lo \
src/libpcre2_16_la-pcre2_maketables.lo \
src/libpcre2_16_la-pcre2_match.lo \
@ -235,7 +237,8 @@ libpcre2_16_la_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC \
libpcre2_32_la_DEPENDENCIES =
am__libpcre2_32_la_SOURCES_DIST = 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_internal.h \
src/pcre2_dfa_match.c src/pcre2_error.c \
src/pcre2_find_bracket.c src/pcre2_internal.h \
src/pcre2_intmodedep.h src/pcre2_jit_compile.c \
src/pcre2_maketables.c src/pcre2_match.c \
src/pcre2_match_data.c src/pcre2_newline.c src/pcre2_ord2utf.c \
@ -250,6 +253,7 @@ am__objects_3 = src/libpcre2_32_la-pcre2_auto_possess.lo \
src/libpcre2_32_la-pcre2_context.lo \
src/libpcre2_32_la-pcre2_dfa_match.lo \
src/libpcre2_32_la-pcre2_error.lo \
src/libpcre2_32_la-pcre2_find_bracket.lo \
src/libpcre2_32_la-pcre2_jit_compile.lo \
src/libpcre2_32_la-pcre2_maketables.lo \
src/libpcre2_32_la-pcre2_match.lo \
@ -279,7 +283,8 @@ libpcre2_32_la_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC \
libpcre2_8_la_DEPENDENCIES =
am__libpcre2_8_la_SOURCES_DIST = 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_internal.h \
src/pcre2_dfa_match.c src/pcre2_error.c \
src/pcre2_find_bracket.c src/pcre2_internal.h \
src/pcre2_intmodedep.h src/pcre2_jit_compile.c \
src/pcre2_maketables.c src/pcre2_match.c \
src/pcre2_match_data.c src/pcre2_newline.c src/pcre2_ord2utf.c \
@ -294,6 +299,7 @@ am__objects_5 = src/libpcre2_8_la-pcre2_auto_possess.lo \
src/libpcre2_8_la-pcre2_context.lo \
src/libpcre2_8_la-pcre2_dfa_match.lo \
src/libpcre2_8_la-pcre2_error.lo \
src/libpcre2_8_la-pcre2_find_bracket.lo \
src/libpcre2_8_la-pcre2_jit_compile.lo \
src/libpcre2_8_la-pcre2_maketables.lo \
src/libpcre2_8_la-pcre2_match.lo \
@ -865,6 +871,7 @@ dist_html_DATA = \
doc/html/pcre2_set_character_tables.html \
doc/html/pcre2_set_compile_recursion_guard.html \
doc/html/pcre2_set_match_limit.html \
doc/html/pcre2_set_offset_limit.html \
doc/html/pcre2_set_newline.html \
doc/html/pcre2_set_parens_nest_limit.html \
doc/html/pcre2_set_recursion_limit.html \
@ -944,6 +951,7 @@ dist_man_MANS = \
doc/pcre2_set_character_tables.3 \
doc/pcre2_set_compile_recursion_guard.3 \
doc/pcre2_set_match_limit.3 \
doc/pcre2_set_offset_limit.3 \
doc/pcre2_set_newline.3 \
doc/pcre2_set_parens_nest_limit.3 \
doc/pcre2_set_recursion_limit.3 \
@ -1052,21 +1060,30 @@ EXTRA_DIST = m4/ax_pthread.m4 m4/pcre2_visibility.m4 \
testdata/testinput11 testdata/testinput12 testdata/testinput13 \
testdata/testinput14 testdata/testinput15 testdata/testinput16 \
testdata/testinput17 testdata/testinput18 testdata/testinput19 \
testdata/testinputEBC testdata/testoutput1 \
testdata/testoutput2 testdata/testoutput3 \
testdata/testinput20 testdata/testinput21 testdata/testinput22 \
testdata/testinput23 testdata/testinputEBC \
testdata/testoutput1 testdata/testoutput2 testdata/testoutput3 \
testdata/testoutput3A testdata/testoutput3B \
testdata/testoutput4 testdata/testoutput5 testdata/testoutput6 \
testdata/testoutput7 testdata/testoutput8-16 \
testdata/testoutput8-32 testdata/testoutput8-8 \
testdata/testoutput7 testdata/testoutput8-16-2 \
testdata/testoutput8-16-3 testdata/testoutput8-16-3 \
testdata/testoutput8-32-2 testdata/testoutput8-32-3 \
testdata/testoutput8-32-4 testdata/testoutput8-8-2 \
testdata/testoutput8-8-3 testdata/testoutput8-8-4 \
testdata/testoutput9 testdata/testoutput10 \
testdata/testoutput11-16 testdata/testoutput11-32 \
testdata/testoutput12-16 testdata/testoutput12-32 \
testdata/testoutput13 testdata/testoutput14 \
testdata/testoutput13 testdata/testoutput14-16 \
testdata/testoutput14-32 testdata/testoutput14-8 \
testdata/testoutput15 testdata/testoutput16 \
testdata/testoutput17 testdata/testoutput18 \
testdata/testoutput19 testdata/testoutputEBC \
testdata/wintestinput3 testdata/wintestoutput3 perltest.sh \
src/pcre2demo.c cmake/COPYING-CMAKE-SCRIPTS \
testdata/testoutput19 testdata/testoutput20 \
testdata/testoutput21 testdata/testoutput22-16 \
testdata/testoutput22-32 testdata/testoutput22-8 \
testdata/testoutput23 testdata/testoutputEBC \
testdata/valgrind-jit.supp testdata/wintestinput3 \
testdata/wintestoutput3 perltest.sh src/pcre2demo.c \
cmake/COPYING-CMAKE-SCRIPTS \
cmake/FindPackageHandleStandardArgs.cmake \
cmake/FindReadline.cmake cmake/FindEditline.cmake \
CMakeLists.txt config-cmake.h.in
@ -1088,6 +1105,7 @@ COMMON_SOURCES = \
src/pcre2_context.c \
src/pcre2_dfa_match.c \
src/pcre2_error.c \
src/pcre2_find_bracket.c \
src/pcre2_internal.h \
src/pcre2_intmodedep.h \
src/pcre2_jit_compile.c \
@ -1309,6 +1327,8 @@ src/libpcre2_16_la-pcre2_dfa_match.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_16_la-pcre2_error.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_16_la-pcre2_find_bracket.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_16_la-pcre2_jit_compile.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_16_la-pcre2_maketables.lo: src/$(am__dirstamp) \
@ -1358,6 +1378,8 @@ src/libpcre2_32_la-pcre2_dfa_match.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_32_la-pcre2_error.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_32_la-pcre2_find_bracket.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_32_la-pcre2_jit_compile.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_32_la-pcre2_maketables.lo: src/$(am__dirstamp) \
@ -1407,6 +1429,8 @@ src/libpcre2_8_la-pcre2_dfa_match.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_8_la-pcre2_error.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_8_la-pcre2_find_bracket.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_8_la-pcre2_jit_compile.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_8_la-pcre2_maketables.lo: src/$(am__dirstamp) \
@ -1583,6 +1607,7 @@ distclean-compile:
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_16_la-pcre2_context.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_16_la-pcre2_dfa_match.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_16_la-pcre2_error.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_16_la-pcre2_find_bracket.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_16_la-pcre2_jit_compile.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_16_la-pcre2_maketables.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_16_la-pcre2_match.Plo@am__quote@
@ -1606,6 +1631,7 @@ distclean-compile:
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_32_la-pcre2_context.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_32_la-pcre2_dfa_match.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_32_la-pcre2_error.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_32_la-pcre2_find_bracket.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_32_la-pcre2_jit_compile.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_32_la-pcre2_maketables.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_32_la-pcre2_match.Plo@am__quote@
@ -1629,6 +1655,7 @@ distclean-compile:
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_8_la-pcre2_context.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_8_la-pcre2_dfa_match.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_8_la-pcre2_error.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_8_la-pcre2_find_bracket.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_8_la-pcre2_jit_compile.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_8_la-pcre2_maketables.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_8_la-pcre2_match.Plo@am__quote@
@ -1716,6 +1743,13 @@ src/libpcre2_16_la-pcre2_error.lo: src/pcre2_error.c
@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libpcre2_16_la_CFLAGS) $(CFLAGS) -c -o src/libpcre2_16_la-pcre2_error.lo `test -f 'src/pcre2_error.c' || echo '$(srcdir)/'`src/pcre2_error.c
src/libpcre2_16_la-pcre2_find_bracket.lo: src/pcre2_find_bracket.c
@am__fastdepCC_TRUE@ $(AM_V_CC)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libpcre2_16_la_CFLAGS) $(CFLAGS) -MT src/libpcre2_16_la-pcre2_find_bracket.lo -MD -MP -MF src/$(DEPDIR)/libpcre2_16_la-pcre2_find_bracket.Tpo -c -o src/libpcre2_16_la-pcre2_find_bracket.lo `test -f 'src/pcre2_find_bracket.c' || echo '$(srcdir)/'`src/pcre2_find_bracket.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/libpcre2_16_la-pcre2_find_bracket.Tpo src/$(DEPDIR)/libpcre2_16_la-pcre2_find_bracket.Plo
@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='src/pcre2_find_bracket.c' object='src/libpcre2_16_la-pcre2_find_bracket.lo' libtool=yes @AMDEPBACKSLASH@
@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libpcre2_16_la_CFLAGS) $(CFLAGS) -c -o src/libpcre2_16_la-pcre2_find_bracket.lo `test -f 'src/pcre2_find_bracket.c' || echo '$(srcdir)/'`src/pcre2_find_bracket.c
src/libpcre2_16_la-pcre2_jit_compile.lo: src/pcre2_jit_compile.c
@am__fastdepCC_TRUE@ $(AM_V_CC)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libpcre2_16_la_CFLAGS) $(CFLAGS) -MT src/libpcre2_16_la-pcre2_jit_compile.lo -MD -MP -MF src/$(DEPDIR)/libpcre2_16_la-pcre2_jit_compile.Tpo -c -o src/libpcre2_16_la-pcre2_jit_compile.lo `test -f 'src/pcre2_jit_compile.c' || echo '$(srcdir)/'`src/pcre2_jit_compile.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/libpcre2_16_la-pcre2_jit_compile.Tpo src/$(DEPDIR)/libpcre2_16_la-pcre2_jit_compile.Plo
@ -1877,6 +1911,13 @@ src/libpcre2_32_la-pcre2_error.lo: src/pcre2_error.c
@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libpcre2_32_la_CFLAGS) $(CFLAGS) -c -o src/libpcre2_32_la-pcre2_error.lo `test -f 'src/pcre2_error.c' || echo '$(srcdir)/'`src/pcre2_error.c
src/libpcre2_32_la-pcre2_find_bracket.lo: src/pcre2_find_bracket.c
@am__fastdepCC_TRUE@ $(AM_V_CC)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libpcre2_32_la_CFLAGS) $(CFLAGS) -MT src/libpcre2_32_la-pcre2_find_bracket.lo -MD -MP -MF src/$(DEPDIR)/libpcre2_32_la-pcre2_find_bracket.Tpo -c -o src/libpcre2_32_la-pcre2_find_bracket.lo `test -f 'src/pcre2_find_bracket.c' || echo '$(srcdir)/'`src/pcre2_find_bracket.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/libpcre2_32_la-pcre2_find_bracket.Tpo src/$(DEPDIR)/libpcre2_32_la-pcre2_find_bracket.Plo
@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='src/pcre2_find_bracket.c' object='src/libpcre2_32_la-pcre2_find_bracket.lo' libtool=yes @AMDEPBACKSLASH@
@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libpcre2_32_la_CFLAGS) $(CFLAGS) -c -o src/libpcre2_32_la-pcre2_find_bracket.lo `test -f 'src/pcre2_find_bracket.c' || echo '$(srcdir)/'`src/pcre2_find_bracket.c
src/libpcre2_32_la-pcre2_jit_compile.lo: src/pcre2_jit_compile.c
@am__fastdepCC_TRUE@ $(AM_V_CC)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libpcre2_32_la_CFLAGS) $(CFLAGS) -MT src/libpcre2_32_la-pcre2_jit_compile.lo -MD -MP -MF src/$(DEPDIR)/libpcre2_32_la-pcre2_jit_compile.Tpo -c -o src/libpcre2_32_la-pcre2_jit_compile.lo `test -f 'src/pcre2_jit_compile.c' || echo '$(srcdir)/'`src/pcre2_jit_compile.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/libpcre2_32_la-pcre2_jit_compile.Tpo src/$(DEPDIR)/libpcre2_32_la-pcre2_jit_compile.Plo
@ -2038,6 +2079,13 @@ src/libpcre2_8_la-pcre2_error.lo: src/pcre2_error.c
@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libpcre2_8_la_CFLAGS) $(CFLAGS) -c -o src/libpcre2_8_la-pcre2_error.lo `test -f 'src/pcre2_error.c' || echo '$(srcdir)/'`src/pcre2_error.c
src/libpcre2_8_la-pcre2_find_bracket.lo: src/pcre2_find_bracket.c
@am__fastdepCC_TRUE@ $(AM_V_CC)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libpcre2_8_la_CFLAGS) $(CFLAGS) -MT src/libpcre2_8_la-pcre2_find_bracket.lo -MD -MP -MF src/$(DEPDIR)/libpcre2_8_la-pcre2_find_bracket.Tpo -c -o src/libpcre2_8_la-pcre2_find_bracket.lo `test -f 'src/pcre2_find_bracket.c' || echo '$(srcdir)/'`src/pcre2_find_bracket.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/libpcre2_8_la-pcre2_find_bracket.Tpo src/$(DEPDIR)/libpcre2_8_la-pcre2_find_bracket.Plo
@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='src/pcre2_find_bracket.c' object='src/libpcre2_8_la-pcre2_find_bracket.lo' libtool=yes @AMDEPBACKSLASH@
@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libpcre2_8_la_CFLAGS) $(CFLAGS) -c -o src/libpcre2_8_la-pcre2_find_bracket.lo `test -f 'src/pcre2_find_bracket.c' || echo '$(srcdir)/'`src/pcre2_find_bracket.c
src/libpcre2_8_la-pcre2_jit_compile.lo: src/pcre2_jit_compile.c
@am__fastdepCC_TRUE@ $(AM_V_CC)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libpcre2_8_la_CFLAGS) $(CFLAGS) -MT src/libpcre2_8_la-pcre2_jit_compile.lo -MD -MP -MF src/$(DEPDIR)/libpcre2_8_la-pcre2_jit_compile.Tpo -c -o src/libpcre2_8_la-pcre2_jit_compile.lo `test -f 'src/pcre2_jit_compile.c' || echo '$(srcdir)/'`src/pcre2_jit_compile.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/libpcre2_8_la-pcre2_jit_compile.Tpo src/$(DEPDIR)/libpcre2_8_la-pcre2_jit_compile.Plo

88
pcre2-10.21/NEWS Normal file
View file

@ -0,0 +1,88 @@
News about PCRE2 releases
-------------------------
Version 10.21 12-January-2016
-----------------------------
1. Many bugs have been fixed. A large number of them were provoked only by very
strange pattern input, and were discovered by fuzzers. Some others were
discovered by code auditing. See ChangeLog for details.
2. The Unicode tables have been updated to Unicode version 8.0.0.
3. For Perl compatibility in EBCDIC environments, ranges such as a-z in a
class, where both values are literal letters in the same case, omit the
non-letter EBCDIC code points within the range.
4. There have been a number of enhancements to the pcre2_substitute() function,
giving more flexibility to replacement facilities. It is now also possible to
cause the function to return the needed buffer size if the one given is too
small.
5. The PCRE2_ALT_VERBNAMES option causes the "name" parts of special verbs such
as (*THEN:name) to be processed for backslashes and to take note of
PCRE2_EXTENDED.
6. PCRE2_INFO_HASBACKSLASHC makes it possible for a client to find out if a
pattern uses \C, and --never-backslash-C makes it possible to compile a version
PCRE2 in which the use of \C is always forbidden.
7. A limit to the length of pattern that can be handled can now be set by
calling pcre2_set_max_pattern_length().
8. When matching an unanchored pattern, a match can be required to begin within
a given number of code units after the start of the subject by calling
pcre2_set_offset_limit().
9. The pcre2test program has been extended to test new facilities, and it can
now run the tests when LF on its own is not a valid newline sequence.
10. The RunTest script has also been updated to enable more tests to be run.
11. There have been some minor performance enhancements.
Version 10.20 30-June-2015
--------------------------
1. Callouts with string arguments and the pcre2_callout_enumerate() function
have been implemented.
2. The PCRE2_NEVER_BACKSLASH_C option, which locks out the use of \C, is added.
3. The PCRE2_ALT_CIRCUMFLEX option lets ^ match after a newline at the end of a
subject in multiline mode.
4. The way named subpatterns are handled has been refactored. The previous
approach had several bugs.
5. The handling of \c in EBCDIC environments has been changed to conform to the
perlebcdic document. This is an incompatible change.
6. Bugs have been mended, many of them discovered by fuzzers.
Version 10.10 06-March-2015
---------------------------
1. Serialization and de-serialization functions have been added to the API,
making it possible to save and restore sets of compiled patterns, though
restoration must be done in the same environment that was used for compilation.
2. The (*NO_JIT) feature has been added; this makes it possible for a pattern
creator to specify that JIT is not to be used.
3. A number of bugs have been fixed. In particular, bugs that caused building
on Windows using CMake to fail have been mended.
Version 10.00 05-January-2015
-----------------------------
Version 10.00 is the first release of PCRE2, a revised API for the PCRE
library. Changes prior to 10.00 are logged in the ChangeLog file for the old
API, up to item 20 for release 8.36. New programs are recommended to use the
new library. Programs that use the original (PCRE1) API will need changing
before linking with the new library.
****

3
pcre2-10.20/NON-AUTOTOOLS-BUILD → pcre2-10.21/NON-AUTOTOOLS-BUILD
View file

@ -97,6 +97,7 @@ can skip ahead to the CMake section.
pcre2_context.c
pcre2_dfa_match.c
pcre2_error.c
pcre2_find_bracket.c
pcre2_jit_compile.c
pcre2_maketables.c
pcre2_match.c
@ -388,4 +389,4 @@ and executable, is in EBCDIC and native z/OS file formats and this is the
recommended download site.
=============================
Last Updated: 15 June 2015
Last Updated: 16 July 2015

12
pcre2-10.20/PrepareRelease → pcre2-10.21/PrepareRelease
View file

@ -65,13 +65,9 @@ End
echo "Making pcre2.txt"
for file in pcre2 pcre2api pcre2build pcre2callout pcre2compat pcre2jit \
pcre2limits pcre2matching pcre2partial pcre2unicode ; do
#for file in \
# pcre2syntax \
# pcre2precompile pcre2perform pcre2posix pcre2sample \
# pcre2stack ; do
pcre2limits pcre2matching pcre2partial pcre2pattern pcre2perform \
pcre2posix pcre2sample pcre2serialize pcre2stack pcre2syntax \
pcre2unicode ; do
echo " Processing $file.3"
nroff -c -man $file.3 >$file.rawtxt
perl ../CleanTxt <$file.rawtxt >>pcre2.txt
@ -153,7 +149,6 @@ for file in *.3 ; do
[ "$base" = "pcre2stack" ] || \
[ "$base" = "pcre2compat" ] || \
[ "$base" = "pcre2limits" ] || \
[ "$base" = "pcre2perform" ] || \
[ "$base" = "pcre2unicode" ] ; then
toc=""
fi
@ -204,6 +199,7 @@ files="\
src/pcre2_context.c \
src/pcre2_dfa_match.c \
src/pcre2_error.c \
src/pcre2_find_bracket.c \
src/pcre2_internal.h \
src/pcre2_intmodedep.h \
src/pcre2_jit_compile.c \

10
pcre2-10.20/README → pcre2-10.21/README
View file

@ -220,6 +220,13 @@ library. They are also documented in the pcre2build man page.
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").
. In a pattern, the escape sequence \C matches a single code unit, even in a
UTF mode. This can be dangerous because it breaks up multi-code-unit
characters. You can build PCRE2 with the use of \C permanently locked out by
adding --enable-never-backslash-C (note the upper case C) to the "configure"
command. When \C is allowed by the library, individual applications can lock
it out by calling pcre2_compile() with the PCRE2_NEVER_BACKSLASH_C option.
. 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
@ -724,6 +731,7 @@ The distribution should contain the files listed below.
src/pcre2_context.c )
src/pcre2_dfa_match.c )
src/pcre2_error.c )
src/pcre2_find_bracket.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
@ -832,4 +840,4 @@ The distribution should contain the files listed below.
Philip Hazel
Email local part: ph10
Email domain: cam.ac.uk
Last updated: 24 April 2015
Last updated: 16 October 2015

27
pcre2-10.20/RunGrepTest → pcre2-10.21/RunGrepTest
View file

@ -19,12 +19,18 @@ unset cp ls mv rm
builddir=`pwd`
pcre2grep=$builddir/pcre2grep
pcre2test=$builddir/pcre2test
if [ ! -x $pcre2grep ] ; then
echo "** $pcre2grep does not exist or is not execuatble."
exit 1
fi
if [ ! -x $pcre2test ] ; then
echo "** $pcre2test does not exist or is not execuatble."
exit 1
fi
valgrind=
while [ $# -gt 0 ] ; do
case $1 in
@ -34,7 +40,6 @@ while [ $# -gt 0 ] ; do
shift
done
echo " "
pcre2grep_version=`$pcre2grep -V`
if [ "$valgrind" = "" ] ; then
echo "Testing $pcre2grep_version"
@ -69,14 +74,22 @@ fi
# Check for the availability of UTF-8 support
./pcre2test -C unicode >/dev/null
$pcre2test -C unicode >/dev/null
utf8=$?
# Check default newline convention. If it does not include LF, force LF.
nl=`$pcre2test -C newline`
if [ "$nl" != "LF" -a "$nl" != "ANY" -a "$nl" != "ANYCRLF" ]; then
pcre2grep="$pcre2grep -N LF"
echo "Default newline setting forced to LF"
fi
# ------ Function to run and check a special pcre2grep arguments test -------
checkspecial()
{
$valgrind ./pcre2grep $1 >>testtrygrep 2>&1
$valgrind $pcre2grep $1 >>testtrygrep 2>&1
if [ $? -ne $2 ] ; then
echo "** pcre2grep $1 failed - check testtrygrep"
exit 1
@ -530,6 +543,14 @@ echo "aaaaa" >>testtemp1grep
(cd $srcdir; $valgrind $pcre2grep --line-offsets '(?<=\Ka)' $builddir/testtemp1grep) >>testtrygrep 2>&1
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 108 ------------------------------" >>testtrygrep
(cd $srcdir; $valgrind $pcre2grep -lq PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 109 -----------------------------" >>testtrygrep
(cd $srcdir; $valgrind $pcre2grep -cq lazy ./testdata/grepinput*) >>testtrygrep
echo "RC=$?" >>testtrygrep
# Now compare the results.
$cf $srcdir/testdata/grepoutput testtrygrep

217
pcre2-10.20/RunTest → pcre2-10.21/RunTest
View file

@ -33,6 +33,10 @@
# For backwards compatibility, -nojit, -valgrind, -valgrind-log, and -sim may
# be given without the leading "-" character.
#
# When PCRE2 is compiled by clang with -fsanitize arguments, some tests need
# very much more stack than normal. In environments where the stack can be
# set at runtime, -bigstack sets a gigantic stack.
#
# There are two special cases where only one argument is allowed:
#
# If the first and only argument is "ebcdic", the script runs the special
@ -64,13 +68,17 @@ title10="Test 10: Specials for the 8-bit library with UTF-8 and UCP support"
title11="Test 11: Specials for the basic 16-bit and 32-bit libraries"
title12="Test 12: Specials for the 16-bit and 32-bit libraries UTF and UCP support"
title13="Test 13: DFA specials for the basic 16-bit and 32-bit libraries"
title14="Test 14: Non-JIT limits and other non-JIT tests"
title15="Test 15: JIT-specific features when JIT is not available"
title16="Test 16: JIT-specific features when JIT is available"
title17="Test 17: Tests of the POSIX interface, excluding UTF/UCP"
title18="Test 18: Tests of the POSIX interface with UTF/UCP"
title19="Test 19: Serialization tests"
maxtest=18
title14="Test 14: DFA specials for UTF and UCP support"
title15="Test 15: Non-JIT limits and other non-JIT tests"
title16="Test 16: JIT-specific features when JIT is not available"
title17="Test 17: JIT-specific features when JIT is available"
title18="Test 18: Tests of the POSIX interface, excluding UTF/UCP"
title19="Test 19: Tests of the POSIX interface with UTF/UCP"
title20="Test 20: Serialization tests"
title21="Test 21: \C tests without UTF (supported for DFA matching)"
title22="Test 22: \C tests with UTF (not supported for DFA matching)"
title23="Test 23: \C disabled test"
maxtest=23
if [ $# -eq 1 -a "$1" = "list" ]; then
echo $title0
@ -93,6 +101,10 @@ if [ $# -eq 1 -a "$1" = "list" ]; then
echo $title17
echo $title18
echo $title19
echo $title20
echo $title21
echo $title22
echo $title23
exit 0
fi
@ -151,7 +163,7 @@ checkresult()
checkspecial()
{
$valgrind ./pcre2test $1 >>testtry
$valgrind $vjs ./pcre2test $1 >>testtry
if [ $? -ne 0 ] ; then
echo "** pcre2test $1 failed - check testtry"
exit 1
@ -184,9 +196,11 @@ arg8=
arg16=
arg32=
nojit=
bigstack=
sim=
skip=
valgrind=
vjs=
# This is in case the caller has set aliases (as I do - PH)
unset cp ls mv rm
@ -214,6 +228,10 @@ do16=no
do17=no
do18=no
do19=no
do20=no
do21=no
do22=no
do23=no
while [ $# -gt 0 ] ; do
case $1 in
@ -237,9 +255,14 @@ while [ $# -gt 0 ] ; do
17) do17=yes;;
18) do18=yes;;
19) do19=yes;;
20) do20=yes;;
21) do21=yes;;
22) do22=yes;;
23) do23=yes;;
-8) arg8=yes;;
-16) arg16=yes;;
-32) arg32=yes;;
bigstack|-bigstack) bigstack=yes;;
nojit|-nojit) nojit=yes;;
sim|-sim) shift; sim=$1;;
valgrind|-valgrind) valgrind="valgrind --tool=memcheck -q --smc-check=all";;
@ -287,13 +310,22 @@ fi
# If it is possible to set the system stack size, arrange to set a value for
# test 2, which needs more than the even the Linux default when PCRE2 has been
# compiled with -fsanitize=address.
# compiled by gcc with -fsanitize=address. When the compiler is clang, sanitize
# options require an even bigger stack for test 2, and an increased stack for
# some of the other tests.
$sim ./pcre2test -S 1 /dev/null /dev/null
if [ $? -eq 0 ] ; then
test2stack="-S 16"
if [ "$bigstack" = "" ] ; then
test2stack="-S 16"
defaultstack=""
else
test2stack="-S 1024"
defaultstack="-S 64"
fi
else
test2stack=""
defaultstack=""
fi
# All of 8-bit, 16-bit, and 32-bit character strings may be supported, but only
@ -306,6 +338,11 @@ support16=$?
$sim ./pcre2test -C pcre2-32 >/dev/null
support32=$?
# \C may be disabled
$sim ./pcre2test -C backslash-C >/dev/null
supportBSC=$?
# Initialize all bitsizes skipped
test8=skip
@ -358,11 +395,18 @@ fi
$sim ./pcre2test -C unicode >/dev/null
utf=$?
# When JIT is used with valgrind, we need to set up valgrind suppressions as
# otherwise there are a lot of false positive valgrind reports when the
# the hardware supports SSE2.
jitopt=
$sim ./pcre2test -C jit >/dev/null
jit=$?
if [ $jit -ne 0 -a "$nojit" != "yes" ] ; then
jitopt=-jit
if [ "$valgrind" != "" ] ; then
vjs="--suppressions=$testdata/valgrind-jit.supp"
fi
fi
# If no specific tests were requested, select all. Those that are not
@ -372,7 +416,8 @@ if [ $do0 = no -a $do1 = no -a $do2 = no -a $do3 = no -a \
$do4 = no -a $do5 = no -a $do6 = no -a $do7 = no -a \
$do8 = no -a $do9 = no -a $do10 = no -a $do11 = no -a \
$do12 = no -a $do13 = no -a $do14 = no -a $do15 = no -a \
$do16 = no -a $do17 = no -a $do18 = no -a $do19 = no \
$do16 = no -a $do17 = no -a $do18 = no -a $do19 = no -a \
$do20 = no -a $do21 = no -a $do22 = no -a $do23 = no \
]; then
do0=yes
do1=yes
@ -394,6 +439,10 @@ if [ $do0 = no -a $do1 = no -a $do2 = no -a $do3 = no -a \
do17=yes
do18=yes
do19=yes
do20=yes
do21=yes
do22=yes
do23=yes
fi
# Handle any explicit skips at this stage, so that an argument list may consist
@ -438,7 +487,7 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ $do1 = yes ] ; then
echo $title1
for opt in "" $jitopt; do
$sim $valgrind ./pcre2test -q $bmode $opt $testdata/testinput1 testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput1 testtry
checkresult $? 1 "$opt"
done
fi
@ -448,7 +497,7 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ $do2 = yes ] ; then
echo $title2 "(excluding UTF-$bits)"
for opt in "" $jitopt; do
$sim $valgrind ./pcre2test -q $test2stack $bmode $opt $testdata/testinput2 testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $test2stack $bmode $opt $testdata/testinput2 testtry
if [ $? = 0 ] ; then
checkresult $? 2 "$opt"
else
@ -508,7 +557,7 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ "$locale" != "" ] ; then
echo $title3 "(using '$locale' locale)"
for opt in "" $jitopt; do
$sim $valgrind ./pcre2test -q $bmode $opt $infile testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $infile testtry
if [ $? = 0 ] ; then
case "$opt" in
-jit) with=" with JIT";;
@ -545,7 +594,7 @@ for bmode in "$test8" "$test16" "$test32"; do
echo " Skipped because UTF-$bits support is not available"
else
for opt in "" $jitopt; do
$sim $valgrind ./pcre2test -q $bmode $opt $testdata/testinput4 testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput4 testtry
checkresult $? 4 "$opt"
done
fi
@ -557,7 +606,7 @@ for bmode in "$test8" "$test16" "$test32"; do
echo " Skipped because UTF-$bits support is not available"
else
for opt in "" $jitopt; do
$sim $valgrind ./pcre2test -q $bmode $opt $testdata/testinput5 testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput5 testtry
checkresult $? 5 "$opt"
done
fi
@ -567,7 +616,7 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ $do6 = yes ] ; then
echo $title6
$sim $valgrind ./pcre2test -q $bmode $testdata/testinput6 testtry
$sim $valgrind ./pcre2test -q $defaultstack $bmode $testdata/testinput6 testtry
checkresult $? 6 ""
fi
@ -576,28 +625,26 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
$sim $valgrind ./pcre2test -q $bmode $opt $testdata/testinput7 testtry
$sim $valgrind ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput7 testtry
checkresult $? 7 ""
fi
fi
# Test of internal offsets and code sizes. This test is run only when there
# is UTF/UCP support and the link size is 2. The actual tests are
# mostly the same as in some of the above, but in this test we inspect some
# offsets and sizes that require a known link size. This is a doublecheck for
# the maintainer, just in case something changes unexpectely. The output from
# this test is different in 8-bit, 16-bit, and 32-bit modes, so there are
# mode-specific output files.
# is UTF/UCP support. The actual tests are mostly the same as in some of the
# above, but in this test we inspect some offsets and sizes. This is a
# doublecheck for the maintainer, just in case something changes unexpectely.
# The output from this test is different in 8-bit, 16-bit, and 32-bit modes
# and for different link sizes, so there are different output files for each
# mode and link size.
if [ $do8 = yes ] ; then
echo $title8
if [ $link_size -ne 2 ] ; then
echo " Skipped because link size is not 2"
elif [ $utf -eq 0 ] ; then
if [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
$sim $valgrind ./pcre2test -q $bmode $testdata/testinput8 testtry
checkresult $? 8-$bits ""
$sim $valgrind ./pcre2test -q $defaultstack $bmode $testdata/testinput8 testtry
checkresult $? 8-$bits-$link_size ""
fi
fi
@ -609,7 +656,7 @@ for bmode in "$test8" "$test16" "$test32"; do
echo " Skipped when running 16/32-bit tests"
else
for opt in "" $jitopt; do
$sim $valgrind ./pcre2test -q $bmode $opt $testdata/testinput9 testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput9 testtry
checkresult $? 9 "$opt"
done
fi
@ -625,7 +672,7 @@ for bmode in "$test8" "$test16" "$test32"; do
echo " Skipped because UTF-$bits support is not available"
else
for opt in "" $jitopt; do
$sim $valgrind ./pcre2test -q $bmode $opt $testdata/testinput10 testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput10 testtry
checkresult $? 10 "$opt"
done
fi
@ -639,7 +686,7 @@ for bmode in "$test8" "$test16" "$test32"; do
echo " Skipped when running 8-bit tests"
else
for opt in "" $jitopt; do
$sim $valgrind ./pcre2test -q $bmode $opt $testdata/testinput11 testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput11 testtry
checkresult $? 11-$bits "$opt"
done
fi
@ -656,7 +703,7 @@ for bmode in "$test8" "$test16" "$test32"; do
echo " Skipped because UTF-$bits support is not available"
else
for opt in "" $jitopt; do
$sim $valgrind ./pcre2test -q $bmode $opt $testdata/testinput12 testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput12 testtry
checkresult $? 12-$bits "$opt"
done
fi
@ -669,75 +716,129 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ "$bits" = "8" ] ; then
echo " Skipped when running 8-bit tests"
else
$sim $valgrind ./pcre2test -q $bmode $testdata/testinput13 testtry
$sim $valgrind ./pcre2test -q $defaultstack $bmode $testdata/testinput13 testtry
checkresult $? 13 ""
fi
fi
# Tests for DFA UTF and UCP features. Output is different for the different widths.
if [ $do14 = yes ] ; then
echo $title14
if [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
$sim $valgrind ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput14 testtry
checkresult $? 14-$bits ""
fi
fi
# Test non-JIT match and recursion limits
if [ $do14 = yes ] ; then
echo $title14
$sim $valgrind ./pcre2test -q $bmode $testdata/testinput14 testtry
checkresult $? 14 ""
if [ $do15 = yes ] ; then
echo $title15
$sim $valgrind ./pcre2test -q $defaultstack $bmode $testdata/testinput15 testtry
checkresult $? 15 ""
fi
# Test JIT-specific features when JIT is not available
if [ $do15 = yes ] ; then
echo $title15
if [ $do16 = yes ] ; then
echo $title16
if [ $jit -ne 0 ] ; then
echo " Skipped because JIT is available"
else
$sim $valgrind ./pcre2test -q $bmode $testdata/testinput15 testtry
checkresult $? 15 ""
$sim $valgrind ./pcre2test -q $defaultstack $bmode $testdata/testinput16 testtry
checkresult $? 16 ""
fi
fi
# Test JIT-specific features when JIT is available
if [ $do16 = yes ] ; then
echo $title16
if [ $do17 = yes ] ; then
echo $title17
if [ $jit -eq 0 -o "$nojit" = "yes" ] ; then
echo " Skipped because JIT is not available or nojit was specified"
else
$sim $valgrind ./pcre2test -q $bmode $testdata/testinput16 testtry
checkresult $? 16 ""
$sim $valgrind $vjs ./pcre2test -q $defaultstack $bmode $testdata/testinput17 testtry
checkresult $? 17 ""
fi
fi
# Tests for the POSIX interface without UTF/UCP (8-bit only)
if [ $do17 = yes ] ; then
echo $title17
if [ $do18 = yes ] ; then
echo $title18
if [ "$bits" = "16" -o "$bits" = "32" ] ; then
echo " Skipped when running 16/32-bit tests"
else
$sim $valgrind ./pcre2test -q $bmode $testdata/testinput17 testtry
checkresult $? 17 ""
$sim $valgrind ./pcre2test -q $defaultstack $bmode $testdata/testinput18 testtry
checkresult $? 18 ""
fi
fi
# Tests for the POSIX interface with UTF/UCP (8-bit only)
if [ $do18 = yes ] ; then
echo $title18
if [ $do19 = yes ] ; then
echo $title19
if [ "$bits" = "16" -o "$bits" = "32" ] ; then
echo " Skipped when running 16/32-bit tests"
elif [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
$sim $valgrind ./pcre2test -q $bmode $testdata/testinput18 testtry
checkresult $? 18 ""
$sim $valgrind ./pcre2test -q $defaultstack $bmode $testdata/testinput19 testtry
checkresult $? 19 ""
fi
fi
# Serialization tests
if [ $do19 = yes ] ; then
echo $title19
$sim $valgrind ./pcre2test -q $bmode $testdata/testinput19 testtry
checkresult $? 19 ""
if [ $do20 = yes ] ; then
echo $title20
$sim $valgrind ./pcre2test -q $defaultstack $bmode $testdata/testinput20 testtry
checkresult $? 20 ""
fi
# \C tests without UTF - DFA matching is supported
if [ "$do21" = yes ] ; then
echo $title21
if [ $supportBSC -eq 0 ] ; then
echo " Skipped because \C is disabled"
else
for opt in "" $jitopt -dfa; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput21 testtry
checkresult $? 21 "$opt"
done
fi
fi
# \C tests with UTF - DFA matching is not supported for \C in UTF mode
if [ "$do22" = yes ] ; then
echo $title22
if [ $supportBSC -eq 0 ] ; then
echo " Skipped because \C is disabled"
elif [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput22 testtry
checkresult $? 22-$bits "$opt"
done
fi
fi
# Test when \C is disabled
if [ "$do23" = yes ] ; then
echo $title23
if [ $supportBSC -ne 0 ] ; then
echo " Skipped because \C is not disabled"
else
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput23 testtry
checkresult $? 23 ""
fi
fi
# End of loop for 8/16/32-bit tests

119
pcre2-10.20/RunTest.bat → pcre2-10.21/RunTest.bat
View file

@ -13,17 +13,18 @@
@rem line. Added argument validation and added error reporting.
@rem
@rem Sheri Pierce added logic to skip feature dependent tests
@rem tests 4 5 9 15 and 18 require utf support
@rem tests 6 7 10 16 and 19 require ucp support
@rem 11 requires ucp and link size 2
@rem 12 requires presence of jit support
@rem 13 requires absence of jit support
@rem tests 4 5 7 10 12 14 19 and 22 require Unicode support
@rem 8 requires Unicode and link size 2
@rem 16 requires absence of jit support
@rem 17 requires presence of jit support
@rem Sheri P also added override tests for study and jit testing
@rem Zoltan Herczeg added libpcre16 support
@rem Zoltan Herczeg added libpcre32 support
@rem -------------------------------------------------------------------
@rem
@rem The file was converted for PCRE2 by PH, February 2015.
@rem Updated for new test 14 (moving others up a number), August 2015.
@rem Tidied and updated for new tests 21, 22, 23 by PH, October 2015.
setlocal enabledelayedexpansion
@ -64,6 +65,8 @@ set support32=%ERRORLEVEL%
set unicode=%ERRORLEVEL%
%pcre2test% -C jit >NUL
set jit=%ERRORLEVEL%
%pcre2test% -C backslash-C >NUL
set supportBSC=%ERRORLEVEL%
if %support8% EQU 1 (
if not exist testout8 md testout8
@ -99,18 +102,22 @@ set do16=no
set do17=no
set do18=no
set do19=no
set do20=no
set do21=no
set do22=no
set do23=no
set all=yes
for %%a in (%*) do (
set valid=no
for %%v in (1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19) do if %%v == %%a set valid=yes
for %%v in (1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23) do if %%v == %%a set valid=yes
if "!valid!" == "yes" (
set do%%a=yes
set all=no
) else (
echo Invalid test number - %%a!
echo Usage %0 [ test_number ] ...
echo Where test_number is one or more optional test numbers 1 through 19, default is all tests.
echo Where test_number is one or more optional test numbers 1 through 23, default is all tests.
exit /b 1
)
)
@ -136,6 +143,10 @@ if "%all%" == "yes" (
set do17=yes
set do18=yes
set do19=yes
set do20=yes
set do21=yes
set do22=yes
set do23=yes
)
@echo RunTest.bat's pcre2test output is written to newly created subfolders
@ -183,6 +194,10 @@ if "%do16%" == "yes" call :do16
if "%do17%" == "yes" call :do17
if "%do18%" == "yes" call :do18
if "%do19%" == "yes" call :do19
if "%do20%" == "yes" call :do20
if "%do21%" == "yes" call :do21
if "%do22%" == "yes" call :do22
if "%do23%" == "yes" call :do23
:modeSkip
if "%mode%" == "" (
set mode=-16
@ -253,6 +268,9 @@ if [%1]==[11] (
if [%1]==[12] (
set type=-%bits%
)
if [%1]==[14] (
set type=-%bits%
)
fc /n %srcdir%\testdata\%testoutput%%type% %2%bits%\%testoutput% >NUL
@ -316,7 +334,7 @@ if %unicode% EQU 0 (
goto :eof
:do6
call :runsub 6 testout "DFA matching main non-UTF, non-UCP functionality" -q -dfa
call :runsub 6 testout "DFA matching main non-UTF, non-UCP functionality" -q
goto :eof
:do7
@ -324,7 +342,7 @@ if %unicode% EQU 0 (
echo Test 7 Skipped due to absence of Unicode support.
goto :eof
)
call :runsub 7 testout "DFA matching with UTF-%bits% and Unicode property support" -q -dfa
call :runsub 7 testout "DFA matching with UTF-%bits% and Unicode property support" -q
goto :eof
:do8
@ -388,39 +406,35 @@ if %bits% EQU 8 (
echo Test 13 Skipped when running 8-bit tests.
goto :eof
)
call :runsub 13 testout "DFA specials for the basic 16/32-bit library" -q -dfa
call :runsub 13 testout "DFA specials for the basic 16/32-bit library" -q
goto :eof
:do14
call :runsub 14 testout "Non-JIT limits and other non_JIT tests" -q
goto :eof
:do15
if %jit% EQU 1 (
echo Test 15 Skipped due to presence of JIT support.
if %unicode% EQU 0 (
echo Test 14 Skipped due to absence of Unicode support.
goto :eof
)
call :runsub 15 testout "JIT-specific features when JIT is not available" -q
call :runsub 14 testout "DFA specials for UTF and UCP support" -q
goto :eof
:do15
call :runsub 15 testout "Non-JIT limits and other non_JIT tests" -q
goto :eof
:do16
if %jit% EQU 0 (
echo Test 16 Skipped due to absence of JIT support.
if %jit% EQU 1 (
echo Test 16 Skipped due to presence of JIT support.
goto :eof
)
call :runsub 16 testout "JIT-specific features when JIT is available" -q
call :runsub 16 testout "JIT-specific features when JIT is not available" -q
goto :eof
:do17
if %bits% EQU 16 (
echo Test 17 Skipped when running 16-bit tests.
if %jit% EQU 0 (
echo Test 17 Skipped due to absence of JIT support.
goto :eof
)
if %bits% EQU 32 (
echo Test 17 Skipped when running 32-bit tests.
goto :eof
)
call :runsub 17 testout "POSIX interface, excluding UTF-8 and UCP" -q
call :runsub 17 testout "JIT-specific features when JIT is available" -q
goto :eof
:do18
@ -432,11 +446,58 @@ if %bits% EQU 32 (
echo Test 18 Skipped when running 32-bit tests.
goto :eof
)
call :runsub 1 testout "POSIX interface with UTF-8 and UCP" -q
call :runsub 18 testout "POSIX interface, excluding UTF-8 and UCP" -q
goto :eof
:do19
call :runsub 1 testout "Serialization tests" -q
if %bits% EQU 16 (
echo Test 19 Skipped when running 16-bit tests.
goto :eof
)
if %bits% EQU 32 (
echo Test 19 Skipped when running 32-bit tests.
goto :eof
)
if %unicode% EQU 0 (
echo Test 19 Skipped due to absence of Unicode support.
goto :eof
)
call :runsub 19 testout "POSIX interface with UTF-8 and UCP" -q
goto :eof
:do20
call :runsub 20 testout "Serialization tests" -q
goto :eof
:do21
if %supportBSC% EQU 0 (
echo Test 21 Skipped due to absence of backslash-C support.
goto :eof
)
call :runsub 21 testout "Backslash-C tests without UTF" -q
call :runsub 21 testout "Backslash-C tests without UTF (DFA)" -q -dfa
if %jit% EQU 1 call :runsub 21 testoutjit "Test with JIT Override" -q -jit
goto :eof
:do22
if %supportBSC% EQU 0 (
echo Test 22 Skipped due to absence of backslash-C support.
goto :eof
)
if %unicode% EQU 0 (
echo Test 22 Skipped due to absence of Unicode support.
goto :eof
)
call :runsub 22 testout "Backslash-C tests with UTF" -q
if %jit% EQU 1 call :runsub 22 testoutjit "Test with JIT Override" -q -jit
goto :eof
:do23
if %supportBSC% EQU 1 (
echo Test 23 Skipped due to presence of backslash-C support.
goto :eof
)
call :runsub 23 testout "Backslash-C disabled test" -q
goto :eof
:conferror

209
pcre2-10.20/aclocal.m4 → pcre2-10.21/aclocal.m4 vendored
View file

@ -20,32 +20,63 @@ You have another version of autoconf. It may work, but is not guaranteed to.
If you have problems, you may need to regenerate the build system entirely.
To do so, use the procedure documented by the package, typically 'autoreconf'.])])
# pkg.m4 - Macros to locate and utilise pkg-config. -*- Autoconf -*-
# serial 1 (pkg-config-0.24)
#
# Copyright © 2004 Scott James Remnant <scott@netsplit.com>.
#
# This program 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 the License, or
# (at your option) any later version.
#
# This program 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, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
#
# As a special exception to the GNU General Public License, if you
# distribute this file as part of a program that contains a
# configuration script generated by Autoconf, you may include it under
# the same distribution terms that you use for the rest of that program.
dnl pkg.m4 - Macros to locate and utilise pkg-config. -*- Autoconf -*-
dnl serial 11 (pkg-config-0.29)
dnl
dnl Copyright © 2004 Scott James Remnant <scott@netsplit.com>.
dnl Copyright © 2012-2015 Dan Nicholson <dbn.lists@gmail.com>
dnl
dnl This program is free software; you can redistribute it and/or modify
dnl it under the terms of the GNU General Public License as published by
dnl the Free Software Foundation; either version 2 of the License, or
dnl (at your option) any later version.
dnl
dnl This program is distributed in the hope that it will be useful, but
dnl WITHOUT ANY WARRANTY; without even the implied warranty of
dnl MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
dnl General Public License for more details.
dnl
dnl You should have received a copy of the GNU General Public License
dnl along with this program; if not, write to the Free Software
dnl Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
dnl 02111-1307, USA.
dnl
dnl As a special exception to the GNU General Public License, if you
dnl distribute this file as part of a program that contains a
dnl configuration script generated by Autoconf, you may include it under
dnl the same distribution terms that you use for the rest of that
dnl program.
# PKG_PROG_PKG_CONFIG([MIN-VERSION])
# ----------------------------------
dnl PKG_PREREQ(MIN-VERSION)
dnl -----------------------
dnl Since: 0.29
dnl
dnl Verify that the version of the pkg-config macros are at least
dnl MIN-VERSION. Unlike PKG_PROG_PKG_CONFIG, which checks the user's
dnl installed version of pkg-config, this checks the developer's version
dnl of pkg.m4 when generating configure.
dnl
dnl To ensure that this macro is defined, also add:
dnl m4_ifndef([PKG_PREREQ],
dnl [m4_fatal([must install pkg-config 0.29 or later before running autoconf/autogen])])
dnl
dnl See the "Since" comment for each macro you use to see what version
dnl of the macros you require.
m4_defun([PKG_PREREQ],
[m4_define([PKG_MACROS_VERSION], [0.29])
m4_if(m4_version_compare(PKG_MACROS_VERSION, [$1]), -1,
[m4_fatal([pkg.m4 version $1 or higher is required but ]PKG_MACROS_VERSION[ found])])
])dnl PKG_PREREQ
dnl PKG_PROG_PKG_CONFIG([MIN-VERSION])
dnl ----------------------------------
dnl Since: 0.16
dnl
dnl Search for the pkg-config tool and set the PKG_CONFIG variable to
dnl first found in the path. Checks that the version of pkg-config found
dnl is at least MIN-VERSION. If MIN-VERSION is not specified, 0.9.0 is
dnl used since that's the first version where most current features of
dnl pkg-config existed.
AC_DEFUN([PKG_PROG_PKG_CONFIG],
[m4_pattern_forbid([^_?PKG_[A-Z_]+$])
m4_pattern_allow([^PKG_CONFIG(_(PATH|LIBDIR|SYSROOT_DIR|ALLOW_SYSTEM_(CFLAGS|LIBS)))?$])
@ -67,18 +98,19 @@ if test -n "$PKG_CONFIG"; then
PKG_CONFIG=""
fi
fi[]dnl
])# PKG_PROG_PKG_CONFIG
])dnl PKG_PROG_PKG_CONFIG
# PKG_CHECK_EXISTS(MODULES, [ACTION-IF-FOUND], [ACTION-IF-NOT-FOUND])
#
# Check to see whether a particular set of modules exists. Similar
# to PKG_CHECK_MODULES(), but does not set variables or print errors.
#
# Please remember that m4 expands AC_REQUIRE([PKG_PROG_PKG_CONFIG])
# only at the first occurence in configure.ac, so if the first place
# it's called might be skipped (such as if it is within an "if", you
# have to call PKG_CHECK_EXISTS manually
# --------------------------------------------------------------
dnl PKG_CHECK_EXISTS(MODULES, [ACTION-IF-FOUND], [ACTION-IF-NOT-FOUND])
dnl -------------------------------------------------------------------
dnl Since: 0.18
dnl
dnl Check to see whether a particular set of modules exists. Similar to
dnl PKG_CHECK_MODULES(), but does not set variables or print errors.
dnl
dnl Please remember that m4 expands AC_REQUIRE([PKG_PROG_PKG_CONFIG])
dnl only at the first occurence in configure.ac, so if the first place
dnl it's called might be skipped (such as if it is within an "if", you
dnl have to call PKG_CHECK_EXISTS manually
AC_DEFUN([PKG_CHECK_EXISTS],
[AC_REQUIRE([PKG_PROG_PKG_CONFIG])dnl
if test -n "$PKG_CONFIG" && \
@ -88,8 +120,10 @@ m4_ifvaln([$3], [else
$3])dnl
fi])
# _PKG_CONFIG([VARIABLE], [COMMAND], [MODULES])
# ---------------------------------------------
dnl _PKG_CONFIG([VARIABLE], [COMMAND], [MODULES])
dnl ---------------------------------------------
dnl Internal wrapper calling pkg-config via PKG_CONFIG and setting
dnl pkg_failed based on the result.
m4_define([_PKG_CONFIG],
[if test -n "$$1"; then
pkg_cv_[]$1="$$1"
@ -101,10 +135,11 @@ m4_define([_PKG_CONFIG],
else
pkg_failed=untried
fi[]dnl
])# _PKG_CONFIG
])dnl _PKG_CONFIG
# _PKG_SHORT_ERRORS_SUPPORTED
# -----------------------------
dnl _PKG_SHORT_ERRORS_SUPPORTED
dnl ---------------------------
dnl Internal check to see if pkg-config supports short errors.
AC_DEFUN([_PKG_SHORT_ERRORS_SUPPORTED],
[AC_REQUIRE([PKG_PROG_PKG_CONFIG])
if $PKG_CONFIG --atleast-pkgconfig-version 0.20; then
@ -112,19 +147,17 @@ if $PKG_CONFIG --atleast-pkgconfig-version 0.20; then
else
_pkg_short_errors_supported=no
fi[]dnl
])# _PKG_SHORT_ERRORS_SUPPORTED
])dnl _PKG_SHORT_ERRORS_SUPPORTED
# PKG_CHECK_MODULES(VARIABLE-PREFIX, MODULES, [ACTION-IF-FOUND],
# [ACTION-IF-NOT-FOUND])
#
#
# Note that if there is a possibility the first call to
# PKG_CHECK_MODULES might not happen, you should be sure to include an
# explicit call to PKG_PROG_PKG_CONFIG in your configure.ac
#
#
# --------------------------------------------------------------
dnl PKG_CHECK_MODULES(VARIABLE-PREFIX, MODULES, [ACTION-IF-FOUND],
dnl [ACTION-IF-NOT-FOUND])
dnl --------------------------------------------------------------
dnl Since: 0.4.0
dnl
dnl Note that if there is a possibility the first call to
dnl PKG_CHECK_MODULES might not happen, you should be sure to include an
dnl explicit call to PKG_PROG_PKG_CONFIG in your configure.ac
AC_DEFUN([PKG_CHECK_MODULES],
[AC_REQUIRE([PKG_PROG_PKG_CONFIG])dnl
AC_ARG_VAR([$1][_CFLAGS], [C compiler flags for $1, overriding pkg-config])dnl
@ -178,16 +211,40 @@ else
AC_MSG_RESULT([yes])
$3
fi[]dnl
])# PKG_CHECK_MODULES
])dnl PKG_CHECK_MODULES
# PKG_INSTALLDIR(DIRECTORY)
# -------------------------
# Substitutes the variable pkgconfigdir as the location where a module
# should install pkg-config .pc files. By default the directory is
# $libdir/pkgconfig, but the default can be changed by passing
# DIRECTORY. The user can override through the --with-pkgconfigdir
# parameter.
dnl PKG_CHECK_MODULES_STATIC(VARIABLE-PREFIX, MODULES, [ACTION-IF-FOUND],
dnl [ACTION-IF-NOT-FOUND])
dnl ---------------------------------------------------------------------
dnl Since: 0.29
dnl
dnl Checks for existence of MODULES and gathers its build flags with
dnl static libraries enabled. Sets VARIABLE-PREFIX_CFLAGS from --cflags
dnl and VARIABLE-PREFIX_LIBS from --libs.
dnl
dnl Note that if there is a possibility the first call to
dnl PKG_CHECK_MODULES_STATIC might not happen, you should be sure to
dnl include an explicit call to PKG_PROG_PKG_CONFIG in your
dnl configure.ac.
AC_DEFUN([PKG_CHECK_MODULES_STATIC],
[AC_REQUIRE([PKG_PROG_PKG_CONFIG])dnl
_save_PKG_CONFIG=$PKG_CONFIG
PKG_CONFIG="$PKG_CONFIG --static"
PKG_CHECK_MODULES($@)
PKG_CONFIG=$_save_PKG_CONFIG[]dnl
])dnl PKG_CHECK_MODULES_STATIC
dnl PKG_INSTALLDIR([DIRECTORY])
dnl -------------------------
dnl Since: 0.27
dnl
dnl Substitutes the variable pkgconfigdir as the location where a module
dnl should install pkg-config .pc files. By default the directory is
dnl $libdir/pkgconfig, but the default can be changed by passing
dnl DIRECTORY. The user can override through the --with-pkgconfigdir
dnl parameter.
AC_DEFUN([PKG_INSTALLDIR],
[m4_pushdef([pkg_default], [m4_default([$1], ['${libdir}/pkgconfig'])])
m4_pushdef([pkg_description],
@ -198,16 +255,18 @@ AC_ARG_WITH([pkgconfigdir],
AC_SUBST([pkgconfigdir], [$with_pkgconfigdir])
m4_popdef([pkg_default])
m4_popdef([pkg_description])
]) dnl PKG_INSTALLDIR
])dnl PKG_INSTALLDIR
# PKG_NOARCH_INSTALLDIR(DIRECTORY)
# -------------------------
# Substitutes the variable noarch_pkgconfigdir as the location where a
# module should install arch-independent pkg-config .pc files. By
# default the directory is $datadir/pkgconfig, but the default can be
# changed by passing DIRECTORY. The user can override through the
# --with-noarch-pkgconfigdir parameter.
dnl PKG_NOARCH_INSTALLDIR([DIRECTORY])
dnl --------------------------------
dnl Since: 0.27
dnl
dnl Substitutes the variable noarch_pkgconfigdir as the location where a
dnl module should install arch-independent pkg-config .pc files. By
dnl default the directory is $datadir/pkgconfig, but the default can be
dnl changed by passing DIRECTORY. The user can override through the
dnl --with-noarch-pkgconfigdir parameter.
AC_DEFUN([PKG_NOARCH_INSTALLDIR],
[m4_pushdef([pkg_default], [m4_default([$1], ['${datadir}/pkgconfig'])])
m4_pushdef([pkg_description],
@ -218,13 +277,15 @@ AC_ARG_WITH([noarch-pkgconfigdir],
AC_SUBST([noarch_pkgconfigdir], [$with_noarch_pkgconfigdir])
m4_popdef([pkg_default])
m4_popdef([pkg_description])
]) dnl PKG_NOARCH_INSTALLDIR
])dnl PKG_NOARCH_INSTALLDIR
# PKG_CHECK_VAR(VARIABLE, MODULE, CONFIG-VARIABLE,
# [ACTION-IF-FOUND], [ACTION-IF-NOT-FOUND])
# -------------------------------------------
# Retrieves the value of the pkg-config variable for the given module.
dnl PKG_CHECK_VAR(VARIABLE, MODULE, CONFIG-VARIABLE,
dnl [ACTION-IF-FOUND], [ACTION-IF-NOT-FOUND])
dnl -------------------------------------------
dnl Since: 0.28
dnl
dnl Retrieves the value of the pkg-config variable for the given module.
AC_DEFUN([PKG_CHECK_VAR],
[AC_REQUIRE([PKG_PROG_PKG_CONFIG])dnl
AC_ARG_VAR([$1], [value of $3 for $2, overriding pkg-config])dnl
@ -233,7 +294,7 @@ _PKG_CONFIG([$1], [variable="][$3]["], [$2])
AS_VAR_COPY([$1], [pkg_cv_][$1])
AS_VAR_IF([$1], [""], [$5], [$4])dnl
])# PKG_CHECK_VAR
])dnl PKG_CHECK_VAR
# Copyright (C) 2002-2014 Free Software Foundation, Inc.
#

0
pcre2-10.20/ar-lib → pcre2-10.21/ar-lib
View file

0
pcre2-10.20/cmake/COPYING-CMAKE-SCRIPTS → pcre2-10.21/cmake/COPYING-CMAKE-SCRIPTS
View file

0
pcre2-10.20/cmake/FindEditline.cmake → pcre2-10.21/cmake/FindEditline.cmake
View file

0
pcre2-10.20/cmake/FindPackageHandleStandardArgs.cmake → pcre2-10.21/cmake/FindPackageHandleStandardArgs.cmake
View file

0
pcre2-10.20/cmake/FindReadline.cmake → pcre2-10.21/cmake/FindReadline.cmake
View file

0
pcre2-10.20/compile → pcre2-10.21/compile
View file

1
pcre2-10.20/config-cmake.h.in → pcre2-10.21/config-cmake.h.in
View file

@ -33,6 +33,7 @@
#cmakedefine EBCDIC 1
#cmakedefine EBCDIC_NL25 1
#cmakedefine HEAP_MATCH_RECURSE 1
#cmakedefine NEVER_BACKSLASH_C 1
#define LINK_SIZE @PCRE2_LINK_SIZE@
#define MATCH_LIMIT @PCRE2_MATCH_LIMIT@

0
pcre2-10.20/config.guess → pcre2-10.21/config.guess vendored
View file

0
pcre2-10.20/config.sub → pcre2-10.21/config.sub vendored
View file

58
pcre2-10.20/configure → pcre2-10.21/configure vendored
View file

@ -1,6 +1,6 @@
#! /bin/sh
# Guess values for system-dependent variables and create Makefiles.
# Generated by GNU Autoconf 2.69 for PCRE2 10.20.
# Generated by GNU Autoconf 2.69 for PCRE2 10.21.
#
#
# Copyright (C) 1992-1996, 1998-2012 Free Software Foundation, Inc.
@ -587,8 +587,8 @@ MAKEFLAGS=
# Identity of this package.
PACKAGE_NAME='PCRE2'
PACKAGE_TARNAME='pcre2'
PACKAGE_VERSION='10.20'
PACKAGE_STRING='PCRE2 10.20'
PACKAGE_VERSION='10.21'
PACKAGE_STRING='PCRE2 10.21'
PACKAGE_BUGREPORT=''
PACKAGE_URL=''
@ -833,6 +833,7 @@ enable_newline_is_crlf
enable_newline_is_anycrlf
enable_newline_is_any
enable_bsr_anycrlf
enable_never_backslash_C
enable_ebcdic
enable_ebcdic_nl25
enable_stack_for_recursion
@ -1405,7 +1406,7 @@ 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.
\`configure' configures PCRE2 10.21 to adapt to many kinds of systems.
Usage: $0 [OPTION]... [VAR=VALUE]...
@ -1475,7 +1476,7 @@ fi
if test -n "$ac_init_help"; then
case $ac_init_help in
short | recursive ) echo "Configuration of PCRE2 10.20:";;
short | recursive ) echo "Configuration of PCRE2 10.21:";;
esac
cat <<\_ACEOF
@ -1515,6 +1516,8 @@ Optional Features:
use CR, LF, or CRLF as newline sequence
--enable-newline-is-any use any valid Unicode newline sequence
--enable-bsr-anycrlf \R matches only CR, LF, CRLF by default
--enable-never-backslash-C
use of \C causes an error
--enable-ebcdic assume EBCDIC coding rather than ASCII; incompatible
with --enable-utf; use only in (uncommon) EBCDIC
environments; it implies --enable-rebuild-chartables
@ -1642,7 +1645,7 @@ fi
test -n "$ac_init_help" && exit $ac_status
if $ac_init_version; then
cat <<\_ACEOF
PCRE2 configure 10.20
PCRE2 configure 10.21
generated by GNU Autoconf 2.69
Copyright (C) 2012 Free Software Foundation, Inc.
@ -2137,7 +2140,7 @@ 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
It was created by PCRE2 $as_me 10.21, which was
generated by GNU Autoconf 2.69. Invocation command line was
$ $0 $@
@ -3001,7 +3004,7 @@ fi
# Define the identity of the package.
PACKAGE='pcre2'
VERSION='10.20'
VERSION='10.21'
cat >>confdefs.h <<_ACEOF
@ -3162,6 +3165,7 @@ fi
MAINT=$MAINTAINER_MODE_TRUE
# END FISH PATCH
# This is a new thing required to stop a warning from automake 1.12
DEPDIR="${am__leading_dot}deps"
@ -13624,9 +13628,9 @@ _ACEOF
# Versioning
PCRE2_MAJOR="10"
PCRE2_MINOR="20"
PCRE2_MINOR="21"
PCRE2_PRERELEASE=""
PCRE2_DATE="2015-06-30"
PCRE2_DATE="2016-01-12"
if test "$PCRE2_MINOR" = "08" -o "$PCRE2_MINOR" = "09"
then
@ -13790,6 +13794,15 @@ else
fi
# Handle --enable-never-backslash-C
# Check whether --enable-never-backslash-C was given.
if test "${enable_never_backslash_C+set}" = set; then :
enableval=$enable_never_backslash_C;
else
enable_never_backslash_C=no
fi
# Handle --enable-ebcdic
# Check whether --enable-ebcdic was given.
if test "${enable_ebcdic+set}" = set; then :
@ -13980,13 +13993,17 @@ 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.
# character constants depending on the mode. Also, EBCDIC cannot be used with
# 16-bit and 32-bit libraries.
#
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
if test "x$enable_pcre2_16" = "xyes" -o "x$enable_pcre2_32" = "xyes"; then
as_fn_error $? "EBCDIC support is available only for the 8-bit library" "$LINENO" 5
fi
fi
# Check argument to --with-link-size
@ -15321,6 +15338,12 @@ $as_echo "#define BSR_ANYCRLF /**/" >>confdefs.h
fi
if test "$enable_never_backslash_C" = "yes"; then
$as_echo "#define NEVER_BACKSLASH_C /**/" >>confdefs.h
fi
cat >>confdefs.h <<_ACEOF
#define LINK_SIZE $with_link_size
@ -15395,16 +15418,16 @@ esac
# are m4 variables, assigned above.
EXTRA_LIBPCRE2_8_LDFLAGS="$EXTRA_LIBPCRE2_8_LDFLAGS \
$NO_UNDEFINED -version-info 2:0:2"
$NO_UNDEFINED -version-info 3:0:3"
EXTRA_LIBPCRE2_16_LDFLAGS="$EXTRA_LIBPCRE2_16_LDFLAGS \
$NO_UNDEFINED -version-info 2:0:2"
$NO_UNDEFINED -version-info 3:0:3"
EXTRA_LIBPCRE2_32_LDFLAGS="$EXTRA_LIBPCRE2_32_LDFLAGS \
$NO_UNDEFINED -version-info 2:0:2"
$NO_UNDEFINED -version-info 3:0:3"
EXTRA_LIBPCRE2_POSIX_LDFLAGS="$EXTRA_LIBPCRE2_POSIX_LDFLAGS \
$NO_UNDEFINED -version-info 0:0:0"
$NO_UNDEFINED -version-info 0:1:0"
@ -16451,7 +16474,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
# 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
This file was extended by PCRE2 $as_me 10.21, which was
generated by GNU Autoconf 2.69. Invocation command line was
CONFIG_FILES = $CONFIG_FILES
@ -16517,7 +16540,7 @@ _ACEOF
cat >>$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
PCRE2 config.status 10.21
configured by $0, generated by GNU Autoconf 2.69,
with options \\"\$ac_cs_config\\"
@ -18249,6 +18272,7 @@ $PACKAGE-$VERSION configuration summary:
Enable Unicode support .......... : ${enable_unicode}
Newline char/sequence ........... : ${enable_newline}
\R matches only ANYCRLF ......... : ${enable_bsr_anycrlf}
\C is disabled .................. : ${enable_never_backslash_C}
EBCDIC coding ................... : ${enable_ebcdic}
EBCDIC code for NL .............. : ${ebcdic_nl_code}
Rebuild char tables ............. : ${enable_rebuild_chartables}

31
pcre2-10.20/configure.ac → pcre2-10.21/configure.ac
View file

@ -9,18 +9,18 @@ dnl The PCRE2_PRERELEASE feature is for identifying release candidates. It might
dnl be defined as -RC2, for example. For real releases, it should be empty.
m4_define(pcre2_major, [10])
m4_define(pcre2_minor, [20])
m4_define(pcre2_minor, [21])
m4_define(pcre2_prerelease, [])
m4_define(pcre2_date, [2015-06-30])
m4_define(pcre2_date, [2016-01-12])
# NOTE: The CMakeLists.txt file searches for the above variables in the first
# 50 lines of this file. Please update that if the variables above are moved.
# Libtool shared library interface versions (current:revision:age)
m4_define(libpcre2_8_version, [2:0:2])
m4_define(libpcre2_16_version, [2:0:2])
m4_define(libpcre2_32_version, [2:0:2])
m4_define(libpcre2_posix_version, [0:0:0])
m4_define(libpcre2_8_version, [3:0:3])
m4_define(libpcre2_16_version, [3:0:3])
m4_define(libpcre2_32_version, [3:0:3])
m4_define(libpcre2_posix_version, [0:1:0])
AC_PREREQ(2.57)
AC_INIT(PCRE2, pcre2_major.pcre2_minor[]pcre2_prerelease, , pcre2)
@ -33,6 +33,7 @@ AC_CONFIG_HEADERS(src/config.h)
# Enable maintainer mode to avoid spurious rebuilds due to timestamps in git
# not being stored. Discussion in https://github.com/fish-shell/fish-shell/issues/2469
AM_MAINTAINER_MODE
# END FISH PATCH
# This is a new thing required to stop a warning from automake 1.12
m4_ifdef([AM_PROG_AR], [AM_PROG_AR])
@ -195,6 +196,12 @@ AC_ARG_ENABLE(bsr-anycrlf,
[\R matches only CR, LF, CRLF by default]),
, enable_bsr_anycrlf=no)
# Handle --enable-never-backslash-C
AC_ARG_ENABLE(never-backslash-C,
AS_HELP_STRING([--enable-never-backslash-C],
[use of \C causes an error]),
, enable_never_backslash_C=no)
# Handle --enable-ebcdic
AC_ARG_ENABLE(ebcdic,
AS_HELP_STRING([--enable-ebcdic],
@ -338,13 +345,17 @@ 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.
# character constants depending on the mode. Also, EBCDIC cannot be used with
# 16-bit and 32-bit libraries.
#
if test "x$enable_ebcdic" = "xyes"; then
enable_rebuild_chartables=yes
if test "x$enable_unicode" = "xyes"; then
AC_MSG_ERROR([support for EBCDIC and Unicode cannot be enabled at the same time])
fi
if test "x$enable_pcre2_16" = "xyes" -o "x$enable_pcre2_32" = "xyes"; then
AC_MSG_ERROR([EBCDIC support is available only for the 8-bit library])
fi
fi
# Check argument to --with-link-size
@ -609,6 +620,11 @@ if test "$enable_bsr_anycrlf" = "yes"; then
The build-time default can be overridden by the user of PCRE2 at runtime.])
fi
if test "$enable_never_backslash_C" = "yes"; then
AC_DEFINE([NEVER_BACKSLASH_C], [], [
Defining NEVER_BACKSLASH_C locks out the use of \C in all patterns.])
fi
AC_DEFINE_UNQUOTED([LINK_SIZE], [$with_link_size], [
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
@ -886,6 +902,7 @@ $PACKAGE-$VERSION configuration summary:
Enable Unicode support .......... : ${enable_unicode}
Newline char/sequence ........... : ${enable_newline}
\R matches only ANYCRLF ......... : ${enable_bsr_anycrlf}
\C is disabled .................. : ${enable_never_backslash_C}
EBCDIC coding ................... : ${enable_ebcdic}
EBCDIC code for NL .............. : ${ebcdic_nl_code}
Rebuild char tables ............. : ${enable_rebuild_chartables}

0
pcre2-10.20/depcomp → pcre2-10.21/depcomp
View file

0
pcre2-10.20/install-sh → pcre2-10.21/install-sh
View file

0
pcre2-10.20/libpcre2-16.pc.in → pcre2-10.21/libpcre2-16.pc.in
View file

0
pcre2-10.20/libpcre2-32.pc.in → pcre2-10.21/libpcre2-32.pc.in
View file

0
pcre2-10.20/libpcre2-8.pc.in → pcre2-10.21/libpcre2-8.pc.in
View file

0
pcre2-10.20/libpcre2-posix.pc.in → pcre2-10.21/libpcre2-posix.pc.in
View file

0
pcre2-10.20/ltmain.sh → pcre2-10.21/ltmain.sh
View file

0
pcre2-10.20/m4/ax_pthread.m4 → pcre2-10.21/m4/ax_pthread.m4
View file

0
pcre2-10.20/m4/libtool.m4 → pcre2-10.21/m4/libtool.m4 vendored
View file

0
pcre2-10.20/m4/ltoptions.m4 → pcre2-10.21/m4/ltoptions.m4 vendored
View file

0
pcre2-10.20/m4/ltsugar.m4 → pcre2-10.21/m4/ltsugar.m4 vendored
View file

0
pcre2-10.20/m4/ltversion.m4 → pcre2-10.21/m4/ltversion.m4 vendored
View file

0
pcre2-10.20/m4/lt~obsolete.m4 → pcre2-10.21/m4/lt~obsolete.m4 vendored
View file

0
pcre2-10.20/m4/pcre2_visibility.m4 → pcre2-10.21/m4/pcre2_visibility.m4
View file

0
pcre2-10.20/missing → pcre2-10.21/missing
View file

0
pcre2-10.20/pcre2-config.in → pcre2-10.21/pcre2-config.in
View file

4
pcre2-10.20/perltest.sh → pcre2-10.21/perltest.sh
View file

@ -204,12 +204,14 @@ for (;;)
printf "data> " if $interact;
last NEXT_RE if ! ($_ = <$infile>);
chomp;
printf $outfile "$_\n" if ! $interact;
printf $outfile "%s", "$_\n" if ! $interact;
s/\s+$//; # Remove trailing space
s/^\s+//; # Remove leading space
last if ($_ eq "");
next if $_ =~ /^\\=(?:\s|$)/; # Comment line
$x = eval "\"$_\""; # To get escapes processed
# Empty array for holding results, ensure $REGERROR and $REGMARK are

9
pcre2-10.20/src/config.h.generic → pcre2-10.21/src/config.h.generic
View file

@ -182,6 +182,9 @@ sure both macros are undefined; an emulation function will then be used. */
#define MAX_NAME_SIZE 32
#endif
/* Defining NEVER_BACKSLASH_C locks out the use of \C in all patterns. */
/* #undef NEVER_BACKSLASH_C */
/* 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
@ -200,7 +203,7 @@ sure both macros are undefined; an emulation function will then be used. */
#define PACKAGE_NAME "PCRE2"
/* Define to the full name and version of this package. */
#define PACKAGE_STRING "PCRE2 10.20"
#define PACKAGE_STRING "PCRE2 10.21"
/* Define to the one symbol short name of this package. */
#define PACKAGE_TARNAME "pcre2"
@ -209,7 +212,7 @@ sure both macros are undefined; an emulation function will then be used. */
#define PACKAGE_URL ""
/* Define to the version of this package. */
#define PACKAGE_VERSION "10.20"
#define PACKAGE_VERSION "10.21"
/* 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
@ -290,7 +293,7 @@ sure both macros are undefined; an emulation function will then be used. */
/* #undef SUPPORT_VALGRIND */
/* Version number of package */
#define VERSION "10.20"
#define VERSION "10.21"
/* Define to empty if `const' does not conform to ANSI C. */
/* #undef const */

3
pcre2-10.20/src/config.h.in → pcre2-10.21/src/config.h.in
View file

@ -169,6 +169,9 @@ sure both macros are undefined; an emulation function will then be used. */
overflow caused by enormously large patterns. */
#undef MAX_NAME_SIZE
/* Defining NEVER_BACKSLASH_C locks out the use of \C in all patterns. */
#undef NEVER_BACKSLASH_C
/* 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

6
pcre2-10.20/src/dftables.c → pcre2-10.21/src/dftables.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -102,7 +102,7 @@ fprintf(f,
"/* This file was automatically written by the dftables auxiliary\n"
"program. It contains character tables that are used when no external\n"
"tables are passed to PCRE2 by the application that calls it. The tables\n"
"are used only for characters whose code values are less than 256.\n\n");
"are used only for characters whose code values are less than 256. */\n\n");
/* Force config.h in z/OS */
@ -115,7 +115,7 @@ fprintf(f,
#endif
fprintf(f,
"The following #includes are present because without them gcc 4.x may remove\n"
"/* The following #includes are present because without them gcc 4.x may remove\n"
"the array definition from the final binary if PCRE2 is built into a static\n"
"library and dead code stripping is activated. This leads to link errors.\n"
"Pulling in the header ensures that the array gets flagged as \"someone\n"

30
pcre2-10.20/src/pcre2.h.generic → pcre2-10.21/src/pcre2.h.generic
View file

@ -5,7 +5,7 @@
/* This is the public header file for the PCRE library, second API, to be
#included by applications that call PCRE2 functions.
Copyright (c) 2015 University of Cambridge
Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -42,9 +42,9 @@ POSSIBILITY OF SUCH DAMAGE.
/* The current PCRE version information. */
#define PCRE2_MAJOR 10
#define PCRE2_MINOR 20
#define PCRE2_MINOR 21
#define PCRE2_PRERELEASE
#define PCRE2_DATE 2015-06-30
#define PCRE2_DATE 2016-01-12
/* When an application links to a PCRE DLL in Windows, the symbols that are
imported have to be identified as such. When building PCRE2, the appropriate
@ -120,6 +120,8 @@ D is inspected during pcre2_dfa_match() execution
#define PCRE2_UTF 0x00080000u /* C J M D */
#define PCRE2_NEVER_BACKSLASH_C 0x00100000u /* C */
#define PCRE2_ALT_CIRCUMFLEX 0x00200000u /* J M D */
#define PCRE2_ALT_VERBNAMES 0x00400000u /* C */
#define PCRE2_USE_OFFSET_LIMIT 0x00800000u /* J M D */
/* These are for pcre2_jit_compile(). */
@ -144,9 +146,13 @@ sanity checks). */
#define PCRE2_DFA_RESTART 0x00000040u
#define PCRE2_DFA_SHORTEST 0x00000080u
/* This is an additional option for pcre2_substitute(). */
/* These are additional options for pcre2_substitute(). */
#define PCRE2_SUBSTITUTE_GLOBAL 0x00000100u
#define PCRE2_SUBSTITUTE_GLOBAL 0x00000100u
#define PCRE2_SUBSTITUTE_EXTENDED 0x00000200u
#define PCRE2_SUBSTITUTE_UNSET_EMPTY 0x00000400u
#define PCRE2_SUBSTITUTE_UNKNOWN_UNSET 0x00000800u
#define PCRE2_SUBSTITUTE_OVERFLOW_LENGTH 0x00001000u
/* Newline and \R settings, for use in compile contexts. The newline values
must be kept in step with values set in config.h and both sets must all be
@ -233,6 +239,12 @@ numbers must not be changed. */
#define PCRE2_ERROR_RECURSIONLIMIT (-53)
#define PCRE2_ERROR_UNAVAILABLE (-54)
#define PCRE2_ERROR_UNSET (-55)
#define PCRE2_ERROR_BADOFFSETLIMIT (-56)
#define PCRE2_ERROR_BADREPESCAPE (-57)
#define PCRE2_ERROR_REPMISSINGBRACE (-58)
#define PCRE2_ERROR_BADSUBSTITUTION (-59)
#define PCRE2_ERROR_BADSUBSPATTERN (-60)
#define PCRE2_ERROR_TOOMANYREPLACE (-61)
/* Request types for pcre2_pattern_info() */
@ -259,6 +271,7 @@ numbers must not be changed. */
#define PCRE2_INFO_NEWLINE 20
#define PCRE2_INFO_RECURSIONLIMIT 21
#define PCRE2_INFO_SIZE 22
#define PCRE2_INFO_HASBACKSLASHC 23
/* Request types for pcre2_config(). */
@ -291,6 +304,7 @@ define special values to indicate zero-terminated strings and unset offsets in
the offset vector (ovector). */
#define PCRE2_SIZE size_t
#define PCRE2_SIZE_MAX SIZE_MAX
#define PCRE2_ZERO_TERMINATED (~(PCRE2_SIZE)0)
#define PCRE2_UNSET (~(PCRE2_SIZE)0)
@ -388,6 +402,8 @@ PCRE2_EXP_DECL void pcre2_compile_context_free(pcre2_compile_context *); \
PCRE2_EXP_DECL int pcre2_set_bsr(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int pcre2_set_character_tables(pcre2_compile_context *, \
const unsigned char *); \
PCRE2_EXP_DECL int pcre2_set_max_pattern_length(pcre2_compile_context *, \
PCRE2_SIZE); \
PCRE2_EXP_DECL int pcre2_set_newline(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int pcre2_set_parens_nest_limit(pcre2_compile_context *, \
uint32_t); \
@ -405,6 +421,8 @@ PCRE2_EXP_DECL int pcre2_set_callout(pcre2_match_context *, \
int (*)(pcre2_callout_block *, void *), void *); \
PCRE2_EXP_DECL int pcre2_set_match_limit(pcre2_match_context *, \
uint32_t); \
PCRE2_EXP_DECL int pcre2_set_offset_limit(pcre2_match_context *, \
PCRE2_SIZE); \
PCRE2_EXP_DECL int pcre2_set_recursion_limit(pcre2_match_context *, \
uint32_t); \
PCRE2_EXP_DECL int pcre2_set_recursion_memory_management( \
@ -606,8 +624,10 @@ pcre2_compile are called by application code. */
#define pcre2_set_character_tables PCRE2_SUFFIX(pcre2_set_character_tables_)
#define pcre2_set_compile_recursion_guard PCRE2_SUFFIX(pcre2_set_compile_recursion_guard_)
#define pcre2_set_match_limit PCRE2_SUFFIX(pcre2_set_match_limit_)
#define pcre2_set_max_pattern_length PCRE2_SUFFIX(pcre2_set_max_pattern_length_)
#define pcre2_set_newline PCRE2_SUFFIX(pcre2_set_newline_)
#define pcre2_set_parens_nest_limit PCRE2_SUFFIX(pcre2_set_parens_nest_limit_)
#define pcre2_set_offset_limit PCRE2_SUFFIX(pcre2_set_offset_limit_)
#define pcre2_set_recursion_limit PCRE2_SUFFIX(pcre2_set_recursion_limit_)
#define pcre2_set_recursion_memory_management PCRE2_SUFFIX(pcre2_set_recursion_memory_management_)
#define pcre2_substitute PCRE2_SUFFIX(pcre2_substitute_)

26
pcre2-10.20/src/pcre2.h.in → pcre2-10.21/src/pcre2.h.in
View file

@ -5,7 +5,7 @@
/* This is the public header file for the PCRE library, second API, to be
#included by applications that call PCRE2 functions.
Copyright (c) 2015 University of Cambridge
Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -120,6 +120,8 @@ D is inspected during pcre2_dfa_match() execution
#define PCRE2_UTF 0x00080000u /* C J M D */
#define PCRE2_NEVER_BACKSLASH_C 0x00100000u /* C */
#define PCRE2_ALT_CIRCUMFLEX 0x00200000u /* J M D */
#define PCRE2_ALT_VERBNAMES 0x00400000u /* C */
#define PCRE2_USE_OFFSET_LIMIT 0x00800000u /* J M D */
/* These are for pcre2_jit_compile(). */
@ -144,9 +146,13 @@ sanity checks). */
#define PCRE2_DFA_RESTART 0x00000040u
#define PCRE2_DFA_SHORTEST 0x00000080u
/* This is an additional option for pcre2_substitute(). */
/* These are additional options for pcre2_substitute(). */
#define PCRE2_SUBSTITUTE_GLOBAL 0x00000100u
#define PCRE2_SUBSTITUTE_GLOBAL 0x00000100u
#define PCRE2_SUBSTITUTE_EXTENDED 0x00000200u
#define PCRE2_SUBSTITUTE_UNSET_EMPTY 0x00000400u
#define PCRE2_SUBSTITUTE_UNKNOWN_UNSET 0x00000800u
#define PCRE2_SUBSTITUTE_OVERFLOW_LENGTH 0x00001000u
/* Newline and \R settings, for use in compile contexts. The newline values
must be kept in step with values set in config.h and both sets must all be
@ -233,6 +239,12 @@ numbers must not be changed. */
#define PCRE2_ERROR_RECURSIONLIMIT (-53)
#define PCRE2_ERROR_UNAVAILABLE (-54)
#define PCRE2_ERROR_UNSET (-55)
#define PCRE2_ERROR_BADOFFSETLIMIT (-56)
#define PCRE2_ERROR_BADREPESCAPE (-57)
#define PCRE2_ERROR_REPMISSINGBRACE (-58)
#define PCRE2_ERROR_BADSUBSTITUTION (-59)
#define PCRE2_ERROR_BADSUBSPATTERN (-60)
#define PCRE2_ERROR_TOOMANYREPLACE (-61)
/* Request types for pcre2_pattern_info() */
@ -259,6 +271,7 @@ numbers must not be changed. */
#define PCRE2_INFO_NEWLINE 20
#define PCRE2_INFO_RECURSIONLIMIT 21
#define PCRE2_INFO_SIZE 22
#define PCRE2_INFO_HASBACKSLASHC 23
/* Request types for pcre2_config(). */
@ -291,6 +304,7 @@ define special values to indicate zero-terminated strings and unset offsets in
the offset vector (ovector). */
#define PCRE2_SIZE size_t
#define PCRE2_SIZE_MAX SIZE_MAX
#define PCRE2_ZERO_TERMINATED (~(PCRE2_SIZE)0)
#define PCRE2_UNSET (~(PCRE2_SIZE)0)
@ -388,6 +402,8 @@ PCRE2_EXP_DECL void pcre2_compile_context_free(pcre2_compile_context *); \
PCRE2_EXP_DECL int pcre2_set_bsr(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int pcre2_set_character_tables(pcre2_compile_context *, \
const unsigned char *); \
PCRE2_EXP_DECL int pcre2_set_max_pattern_length(pcre2_compile_context *, \
PCRE2_SIZE); \
PCRE2_EXP_DECL int pcre2_set_newline(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int pcre2_set_parens_nest_limit(pcre2_compile_context *, \
uint32_t); \
@ -405,6 +421,8 @@ PCRE2_EXP_DECL int pcre2_set_callout(pcre2_match_context *, \
int (*)(pcre2_callout_block *, void *), void *); \
PCRE2_EXP_DECL int pcre2_set_match_limit(pcre2_match_context *, \
uint32_t); \
PCRE2_EXP_DECL int pcre2_set_offset_limit(pcre2_match_context *, \
PCRE2_SIZE); \
PCRE2_EXP_DECL int pcre2_set_recursion_limit(pcre2_match_context *, \
uint32_t); \
PCRE2_EXP_DECL int pcre2_set_recursion_memory_management( \
@ -606,8 +624,10 @@ pcre2_compile are called by application code. */
#define pcre2_set_character_tables PCRE2_SUFFIX(pcre2_set_character_tables_)
#define pcre2_set_compile_recursion_guard PCRE2_SUFFIX(pcre2_set_compile_recursion_guard_)
#define pcre2_set_match_limit PCRE2_SUFFIX(pcre2_set_match_limit_)
#define pcre2_set_max_pattern_length PCRE2_SUFFIX(pcre2_set_max_pattern_length_)
#define pcre2_set_newline PCRE2_SUFFIX(pcre2_set_newline_)
#define pcre2_set_parens_nest_limit PCRE2_SUFFIX(pcre2_set_parens_nest_limit_)
#define pcre2_set_offset_limit PCRE2_SUFFIX(pcre2_set_offset_limit_)
#define pcre2_set_recursion_limit PCRE2_SUFFIX(pcre2_set_recursion_limit_)
#define pcre2_set_recursion_memory_management PCRE2_SUFFIX(pcre2_set_recursion_memory_management_)
#define pcre2_substitute PCRE2_SUFFIX(pcre2_substitute_)

60
pcre2-10.20/src/pcre2_auto_possess.c → pcre2-10.21/src/pcre2_auto_possess.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -171,64 +171,6 @@ static const uint8_t posspropstab[3][4] = {
{ ucp_L, ucp_N, ucp_P, ucp_Po } /* WORD */
};
/* This table is used when converting repeating opcodes into possessified
versions as a result of an explicit possessive quantifier such as ++. A zero
value means there is no possessified version - in those cases the item in
question must be wrapped in ONCE brackets. The table is truncated at OP_CALLOUT
because all relevant opcodes are less than that. */
static const uint8_t opcode_possessify[] = {
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0 - 15 */
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 16 - 31 */
0, /* NOTI */
OP_POSSTAR, 0, /* STAR, MINSTAR */
OP_POSPLUS, 0, /* PLUS, MINPLUS */
OP_POSQUERY, 0, /* QUERY, MINQUERY */
OP_POSUPTO, 0, /* UPTO, MINUPTO */
0, /* EXACT */
0, 0, 0, 0, /* POS{STAR,PLUS,QUERY,UPTO} */
OP_POSSTARI, 0, /* STARI, MINSTARI */
OP_POSPLUSI, 0, /* PLUSI, MINPLUSI */
OP_POSQUERYI, 0, /* QUERYI, MINQUERYI */
OP_POSUPTOI, 0, /* UPTOI, MINUPTOI */
0, /* EXACTI */
0, 0, 0, 0, /* POS{STARI,PLUSI,QUERYI,UPTOI} */
OP_NOTPOSSTAR, 0, /* NOTSTAR, NOTMINSTAR */
OP_NOTPOSPLUS, 0, /* NOTPLUS, NOTMINPLUS */
OP_NOTPOSQUERY, 0, /* NOTQUERY, NOTMINQUERY */
OP_NOTPOSUPTO, 0, /* NOTUPTO, NOTMINUPTO */
0, /* NOTEXACT */
0, 0, 0, 0, /* NOTPOS{STAR,PLUS,QUERY,UPTO} */
OP_NOTPOSSTARI, 0, /* NOTSTARI, NOTMINSTARI */
OP_NOTPOSPLUSI, 0, /* NOTPLUSI, NOTMINPLUSI */
OP_NOTPOSQUERYI, 0, /* NOTQUERYI, NOTMINQUERYI */
OP_NOTPOSUPTOI, 0, /* NOTUPTOI, NOTMINUPTOI */
0, /* NOTEXACTI */
0, 0, 0, 0, /* NOTPOS{STARI,PLUSI,QUERYI,UPTOI} */
OP_TYPEPOSSTAR, 0, /* TYPESTAR, TYPEMINSTAR */
OP_TYPEPOSPLUS, 0, /* TYPEPLUS, TYPEMINPLUS */
OP_TYPEPOSQUERY, 0, /* TYPEQUERY, TYPEMINQUERY */
OP_TYPEPOSUPTO, 0, /* TYPEUPTO, TYPEMINUPTO */
0, /* TYPEEXACT */
0, 0, 0, 0, /* TYPEPOS{STAR,PLUS,QUERY,UPTO} */
OP_CRPOSSTAR, 0, /* CRSTAR, CRMINSTAR */
OP_CRPOSPLUS, 0, /* CRPLUS, CRMINPLUS */
OP_CRPOSQUERY, 0, /* CRQUERY, CRMINQUERY */
OP_CRPOSRANGE, 0, /* CRRANGE, CRMINRANGE */
0, 0, 0, 0, /* CRPOS{STAR,PLUS,QUERY,RANGE} */
0, 0, 0, /* CLASS, NCLASS, XCLASS */
0, 0, /* REF, REFI */
0, 0, /* DNREF, DNREFI */
0, 0 /* RECURSE, CALLOUT */
};
#ifdef SUPPORT_UNICODE

0
pcre2-10.20/src/pcre2_chartables.c.dist → pcre2-10.21/src/pcre2_chartables.c.dist
View file

2128
pcre2-10.20/src/pcre2_compile.c → pcre2-10.21/src/pcre2_compile.c
View file

File diff suppressed because it is too large Load diff

2
pcre2-10.20/src/pcre2_config.c → pcre2-10.21/src/pcre2_config.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without

32
pcre2-10.20/src/pcre2_context.c → pcre2-10.21/src/pcre2_context.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -131,13 +131,14 @@ return gcontext;
when no context is supplied to the compile function. */
const pcre2_compile_context PRIV(default_compile_context) = {
{ default_malloc, default_free, NULL },
NULL,
NULL,
PRIV(default_tables),
BSR_DEFAULT,
NEWLINE_DEFAULT,
PARENS_NEST_LIMIT };
{ default_malloc, default_free, NULL }, /* Default memory handling */
NULL, /* Stack guard */
NULL, /* Stack guard data */
PRIV(default_tables), /* Character tables */
PCRE2_UNSET, /* Max pattern length */
BSR_DEFAULT, /* Backslash R default */
NEWLINE_DEFAULT, /* Newline convention */
PARENS_NEST_LIMIT }; /* As it says */
/* The create function copies the default into the new memory, but must
override the default memory handling functions if a gcontext was provided. */
@ -169,6 +170,7 @@ const pcre2_match_context PRIV(default_match_context) = {
#endif
NULL,
NULL,
PCRE2_UNSET, /* Offset limit */
MATCH_LIMIT,
MATCH_LIMIT_RECURSION };
@ -294,6 +296,13 @@ switch(value)
}
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_max_pattern_length(pcre2_compile_context *ccontext, PCRE2_SIZE length)
{
ccontext->max_pattern_length = length;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_newline(pcre2_compile_context *ccontext, uint32_t newline)
{
@ -347,6 +356,13 @@ mcontext->match_limit = limit;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_offset_limit(pcre2_match_context *mcontext, PCRE2_SIZE limit)
{
mcontext->offset_limit = limit;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_recursion_limit(pcre2_match_context *mcontext, uint32_t limit)
{

87
pcre2-10.20/src/pcre2_dfa_match.c → pcre2-10.21/src/pcre2_dfa_match.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -433,13 +433,13 @@ move back, and set up each alternative appropriately. */
if (*first_op == OP_REVERSE)
{
int max_back = 0;
int gone_back;
size_t max_back = 0;
size_t gone_back;
end_code = this_start_code;
do
{
int back = GET(end_code, 2+LINK_SIZE);
size_t back = GET(end_code, 2+LINK_SIZE);
if (back > max_back) max_back = back;
end_code += GET(end_code, 1);
}
@ -466,8 +466,8 @@ if (*first_op == OP_REVERSE)
/* In byte-mode we can do this quickly. */
{
gone_back = (current_subject - max_back < start_subject)?
(int)(current_subject - start_subject) : max_back;
size_t current_offset = (size_t)(current_subject - start_subject);
gone_back = (current_offset < max_back)? current_offset : max_back;
current_subject -= gone_back;
}
@ -481,7 +481,7 @@ if (*first_op == OP_REVERSE)
end_code = this_start_code;
do
{
int back = GET(end_code, 2+LINK_SIZE);
size_t back = GET(end_code, 2+LINK_SIZE);
if (back <= gone_back)
{
int bstate = (int)(end_code - start_code + 2 + 2*LINK_SIZE);
@ -2774,7 +2774,7 @@ for (;;)
{
PCRE2_SPTR p = start_subject + local_offsets[rc];
PCRE2_SPTR pp = start_subject + local_offsets[rc+1];
while (p < pp) if (NOT_FIRSTCHAR(*p++)) charcount--;
while (p < pp) if (NOT_FIRSTCU(*p++)) charcount--;
}
#endif
if (charcount > 0)
@ -2874,7 +2874,7 @@ for (;;)
PCRE2_SPTR pp = local_ptr;
charcount = (int)(pp - p);
#if defined SUPPORT_UNICODE && PCRE2_CODE_UNIT_WIDTH != 32
if (utf) while (p < pp) if (NOT_FIRSTCHAR(*p++)) charcount--;
if (utf) while (p < pp) if (NOT_FIRSTCU(*p++)) charcount--;
#endif
ADD_NEW_DATA(-next_state_offset, 0, (charcount - 1));
}
@ -2960,7 +2960,7 @@ for (;;)
{
PCRE2_SPTR p = start_subject + local_offsets[0];
PCRE2_SPTR pp = start_subject + local_offsets[1];
while (p < pp) if (NOT_FIRSTCHAR(*p++)) charcount--;
while (p < pp) if (NOT_FIRSTCU(*p++)) charcount--;
}
#endif
ADD_NEW_DATA(-next_state_offset, 0, (charcount - 1));
@ -3116,6 +3116,7 @@ const pcre2_real_code *re = (const pcre2_real_code *)code;
PCRE2_SPTR start_match;
PCRE2_SPTR end_subject;
PCRE2_SPTR bumpalong_limit;
PCRE2_SPTR req_cu_ptr;
BOOL utf, anchored, startline, firstline;
@ -3172,15 +3173,10 @@ occur. */
#define FF (PCRE2_NOTEMPTY_SET|PCRE2_NE_ATST_SET)
#define OO (PCRE2_NOTEMPTY|PCRE2_NOTEMPTY_ATSTART)
options |= (re->flags & FF) / ((FF & -FF) / (OO & -OO));
options |= (re->flags & FF) / ((FF & (~FF+1)) / (OO & (~OO+1)));
#undef FF
#undef OO
/* A NULL match context means "use a default context" */
if (mcontext == NULL)
mcontext = (pcre2_match_context *)(&PRIV(default_match_context));
/* If restarting after a partial match, do some sanity checks on the contents
of the workspace. */
@ -3205,8 +3201,11 @@ where to start. */
startline = (re->flags & PCRE2_STARTLINE) != 0;
firstline = (re->overall_options & PCRE2_FIRSTLINE) != 0;
bumpalong_limit = end_subject;
/* Fill in the fields in the match block. */
/* Get data from the match context, if present, and fill in the fields in the
match block. It is an error to set an offset limit without setting the flag at
compile time. */
if (mcontext == NULL)
{
@ -3215,6 +3214,12 @@ if (mcontext == NULL)
}
else
{
if (mcontext->offset_limit != PCRE2_UNSET)
{
if ((re->overall_options & PCRE2_USE_OFFSET_LIMIT) == 0)
return PCRE2_ERROR_BADOFFSETLIMIT;
bumpalong_limit = subject + mcontext->offset_limit;
}
mb->callout = mcontext->callout;
mb->callout_data = mcontext->callout_data;
mb->memctl = mcontext->memctl;
@ -3264,18 +3269,50 @@ switch(re->newline_convention)
/* Check a UTF string for validity if required. For 8-bit and 16-bit strings,
we must also check that a starting offset does not point into the middle of a
multiunit character. */
multiunit character. We check only the portion of the subject that is going to
be inspected during matching - from the offset minus the maximum back reference
to the given length. This saves time when a small part of a large subject is
being matched by the use of a starting offset. Note that the maximum lookbehind
is a number of characters, not code units. */
#ifdef SUPPORT_UNICODE
if (utf && (options & PCRE2_NO_UTF_CHECK) == 0)
{
match_data->rc = PRIV(valid_utf)(subject, length, &(match_data->startchar));
if (match_data->rc != 0) return match_data->rc;
PCRE2_SPTR check_subject = start_match; /* start_match includes offset */
if (start_offset > 0)
{
#if PCRE2_CODE_UNIT_WIDTH != 32
if (start_offset > 0 && start_offset < length &&
NOT_FIRSTCHAR(subject[start_offset]))
return PCRE2_ERROR_BADUTFOFFSET;
unsigned int i;
if (start_match < end_subject && NOT_FIRSTCU(*start_match))
return PCRE2_ERROR_BADUTFOFFSET;
for (i = re->max_lookbehind; i > 0 && check_subject > subject; i--)
{
check_subject--;
while (check_subject > subject &&
#if PCRE2_CODE_UNIT_WIDTH == 8
(*check_subject & 0xc0) == 0x80)
#else /* 16-bit */
(*check_subject & 0xfc00) == 0xdc00)
#endif /* PCRE2_CODE_UNIT_WIDTH == 8 */
check_subject--;
}
#else /* In the 32-bit library, one code unit equals one character. */
check_subject -= re->max_lookbehind;
if (check_subject < subject) check_subject = subject;
#endif /* PCRE2_CODE_UNIT_WIDTH != 32 */
}
/* Validate the relevant portion of the subject. After an error, adjust the
offset to be an absolute offset in the whole string. */
match_data->rc = PRIV(valid_utf)(check_subject,
length - (check_subject - subject), &(match_data->startchar));
if (match_data->rc != 0)
{
match_data->startchar += check_subject - subject;
return match_data->rc;
}
}
#endif /* SUPPORT_UNICODE */
@ -3507,6 +3544,10 @@ for (;;)
/* ------------ End of start of match optimizations ------------ */
/* Give no match if we have passed the bumpalong limit. */
if (start_match > bumpalong_limit) break;
/* OK, now we can do the business */
mb->start_used_ptr = start_match;

32
pcre2-10.20/src/pcre2_error.c → pcre2-10.21/src/pcre2_error.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2015 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -51,11 +51,10 @@ POSSIBILITY OF SUCH DAMAGE.
/* The texts of compile-time error messages. Compile-time error numbers start
at COMPILE_ERROR_BASE (100).
Do not ever re-use any error number, because they are documented. Always add a
new error instead. This used to be a table of strings, but in order to reduce
the number of relocations needed when a shared library is loaded dynamically,
it is now one long string. We cannot use a table of offsets, because the
lengths of inserts such as XSTRING(MAX_NAME_SIZE) are not known. Instead,
This used to be a table of strings, but in order to reduce the number of
relocations needed when a shared library is loaded dynamically, it is now one
long string. We cannot use a table of offsets, because the lengths of inserts
such as XSTRING(MAX_NAME_SIZE) are not known. Instead,
pcre2_get_error_message() counts through to the one it wants - this isn't a
performance issue because these strings are used only when there is an error.
@ -92,7 +91,7 @@ static const char compile_error_texts[] =
"failed to allocate heap memory\0"
"unmatched closing parenthesis\0"
"internal error: code overflow\0"
"unrecognized character after (?<\0"
"letter or underscore expected after (?< or (?'\0"
/* 25 */
"lookbehind assertion is not fixed length\0"
"malformed number or name after (?(\0"
@ -112,7 +111,7 @@ static const char compile_error_texts[] =
"number after (?C is greater than 255\0"
"closing parenthesis for (?C expected\0"
/* 40 */
"recursion could loop indefinitely\0"
"invalid escape sequence in (*VERB) name\0"
"unrecognized character after (?P\0"
"syntax error in subpattern name (missing terminator)\0"
"two named subpatterns have the same name (PCRE2_DUPNAMES not set)\0"
@ -154,7 +153,7 @@ static const char compile_error_texts[] =
/* 70 */
"internal error: unknown opcode in find_fixedlength()\0"
"\\N is not supported in a class\0"
"too many forward references\0"
"SPARE ERROR\0"
"disallowed Unicode code point (>= 0xd800 && <= 0xdfff)\0"
"using UTF is disabled by the application\0"
/* 75 */
@ -169,6 +168,11 @@ static const char compile_error_texts[] =
"unrecognized string delimiter follows (?C\0"
"using \\C is disabled by the application\0"
"(?| and/or (?J: or (?x: parentheses are too deeply nested\0"
/* 85 */
"using \\C is disabled in this PCRE2 library\0"
"regular expression is too complicated\0"
"lookbehind assertion is too long\0"
"pattern string is longer than the limit set by the application\0"
;
/* Match-time and UTF error texts are in the same format. */
@ -200,7 +204,7 @@ static const char match_error_texts[] =
/* 20 */
"UTF-8 error: overlong 5-byte sequence\0"
"UTF-8 error: overlong 6-byte sequence\0"
"UTF-8 error: isolated 0x80 byte\0"
"UTF-8 error: isolated byte with 0x80 bit set\0"
"UTF-8 error: illegal byte (0xfe or 0xff)\0"
"UTF-16 error: missing low surrogate at end\0"
/* 25 */
@ -239,7 +243,15 @@ static const char match_error_texts[] =
"nested recursion at the same subject position\0"
"recursion limit exceeded\0"
"requested value is not available\0"
/* 55 */
"requested value is not set\0"
"offset limit set without PCRE2_USE_OFFSET_LIMIT\0"
"bad escape sequence in replacement string\0"
"expected closing curly bracket in replacement string\0"
"bad substitution in replacement string\0"
/* 60 */
"match with end before start is not supported\0"
"too many replacements (more than INT_MAX)\0"
;

218
pcre2-10.21/src/pcre2_find_bracket.c Normal file
View file

@ -0,0 +1,218 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains a single function that scans through a compiled pattern
until it finds a capturing bracket with the given number, or, if the number is
negative, an instance of OP_REVERSE for a lookbehind. The function is called
from pcre2_compile.c and also from pcre2_study.c when finding the minimum
matching length. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/*************************************************
* Scan compiled regex for specific bracket *
*************************************************/
/*
Arguments:
code points to start of expression
utf TRUE in UTF mode
number the required bracket number or negative to find a lookbehind
Returns: pointer to the opcode for the bracket, or NULL if not found
*/
PCRE2_SPTR
PRIV(find_bracket)(PCRE2_SPTR code, BOOL utf, int number)
{
for (;;)
{
register PCRE2_UCHAR c = *code;
if (c == OP_END) return NULL;
/* XCLASS is used for classes that cannot be represented just by a bit map.
This includes negated single high-valued characters. CALLOUT_STR is used for
callouts with string arguments. In both cases the length in the table is
zero; the actual length is stored in the compiled code. */
if (c == OP_XCLASS) code += GET(code, 1);
else if (c == OP_CALLOUT_STR) code += GET(code, 1 + 2*LINK_SIZE);
/* Handle lookbehind */
else if (c == OP_REVERSE)
{
if (number < 0) return (PCRE2_UCHAR *)code;
code += PRIV(OP_lengths)[c];
}
/* Handle capturing bracket */
else if (c == OP_CBRA || c == OP_SCBRA ||
c == OP_CBRAPOS || c == OP_SCBRAPOS)
{
int n = (int)GET2(code, 1+LINK_SIZE);
if (n == number) return (PCRE2_UCHAR *)code;
code += PRIV(OP_lengths)[c];
}
/* Otherwise, we can get the item's length from the table, except that for
repeated character types, we have to test for \p and \P, which have an extra
two bytes of parameters, and for MARK/PRUNE/SKIP/THEN with an argument, we
must add in its length. */
else
{
switch(c)
{
case OP_TYPESTAR:
case OP_TYPEMINSTAR:
case OP_TYPEPLUS:
case OP_TYPEMINPLUS:
case OP_TYPEQUERY:
case OP_TYPEMINQUERY:
case OP_TYPEPOSSTAR:
case OP_TYPEPOSPLUS:
case OP_TYPEPOSQUERY:
if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2;
break;
case OP_TYPEUPTO:
case OP_TYPEMINUPTO:
case OP_TYPEEXACT:
case OP_TYPEPOSUPTO:
if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP)
code += 2;
break;
case OP_MARK:
case OP_PRUNE_ARG:
case OP_SKIP_ARG:
case OP_THEN_ARG:
code += code[1];
break;
}
/* Add in the fixed length from the table */
code += PRIV(OP_lengths)[c];
/* In UTF-8 and UTF-16 modes, opcodes that are followed by a character may be
followed by a multi-byte character. The length in the table is a minimum, so
we have to arrange to skip the extra bytes. */
#ifdef MAYBE_UTF_MULTI
if (utf) switch(c)
{
case OP_CHAR:
case OP_CHARI:
case OP_NOT:
case OP_NOTI:
case OP_EXACT:
case OP_EXACTI:
case OP_NOTEXACT:
case OP_NOTEXACTI:
case OP_UPTO:
case OP_UPTOI:
case OP_NOTUPTO:
case OP_NOTUPTOI:
case OP_MINUPTO:
case OP_MINUPTOI:
case OP_NOTMINUPTO:
case OP_NOTMINUPTOI:
case OP_POSUPTO:
case OP_POSUPTOI:
case OP_NOTPOSUPTO:
case OP_NOTPOSUPTOI:
case OP_STAR:
case OP_STARI:
case OP_NOTSTAR:
case OP_NOTSTARI:
case OP_MINSTAR:
case OP_MINSTARI:
case OP_NOTMINSTAR:
case OP_NOTMINSTARI:
case OP_POSSTAR:
case OP_POSSTARI:
case OP_NOTPOSSTAR:
case OP_NOTPOSSTARI:
case OP_PLUS:
case OP_PLUSI:
case OP_NOTPLUS:
case OP_NOTPLUSI:
case OP_MINPLUS:
case OP_MINPLUSI:
case OP_NOTMINPLUS:
case OP_NOTMINPLUSI:
case OP_POSPLUS:
case OP_POSPLUSI:
case OP_NOTPOSPLUS:
case OP_NOTPOSPLUSI:
case OP_QUERY:
case OP_QUERYI:
case OP_NOTQUERY:
case OP_NOTQUERYI:
case OP_MINQUERY:
case OP_MINQUERYI:
case OP_NOTMINQUERY:
case OP_NOTMINQUERYI:
case OP_POSQUERY:
case OP_POSQUERYI:
case OP_NOTPOSQUERY:
case OP_NOTPOSQUERYI:
if (HAS_EXTRALEN(code[-1])) code += GET_EXTRALEN(code[-1]);
break;
}
#else
(void)(utf); /* Keep compiler happy by referencing function argument */
#endif /* MAYBE_UTF_MULTI */
}
}
}
/* End of pcre2_find_bracket.c */

23
pcre2-10.20/src/pcre2_internal.h → pcre2-10.21/src/pcre2_internal.h
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2015 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -39,7 +39,10 @@ POSSIBILITY OF SUCH DAMAGE.
*/
/* We do not support both EBCDIC and Unicode at the same time. The "configure"
script prevents both being selected, but not everybody uses "configure". */
script prevents both being selected, but not everybody uses "configure". EBCDIC
is only supported for the 8-bit library, but the check for this has to be later
in this file, because the first part is not width-dependent, and is included by
pcre2test.c with CODE_UNIT_WIDTH == 0. */
#if defined EBCDIC && defined SUPPORT_UNICODE
#error The use of both EBCDIC and SUPPORT_UNICODE is not supported.
@ -524,9 +527,11 @@ bytes in a code unit in that mode. */
#define PCRE2_NL_SET 0x00008000 /* newline was set in the pattern */
#define PCRE2_NOTEMPTY_SET 0x00010000 /* (*NOTEMPTY) used ) keep */
#define PCRE2_NE_ATST_SET 0x00020000 /* (*NOTEMPTY_ATSTART) used) together */
#define PCRE2_DEREF_TABLES 0x00040000 /* Release character tables. */
#define PCRE2_DEREF_TABLES 0x00040000 /* release character tables */
#define PCRE2_NOJIT 0x00080000 /* (*NOJIT) used */
#define PCRE2_HASBKPORX 0x00100000 /* contains \P, \p, or \X */
#define PCRE2_DUPCAPUSED 0x00200000 /* contains (?| */
#define PCRE2_HASBKC 0x00400000 /* contains \C */
#define PCRE2_MODE_MASK (PCRE2_MODE8 | PCRE2_MODE16 | PCRE2_MODE32)
@ -917,6 +922,7 @@ a positive value. */
#define STRING_NOTEMPTY_ATSTART_RIGHTPAR "NOTEMPTY_ATSTART)"
#define STRING_LIMIT_MATCH_EQ "LIMIT_MATCH="
#define STRING_LIMIT_RECURSION_EQ "LIMIT_RECURSION="
#define STRING_MARK "MARK"
#else /* SUPPORT_UNICODE */
@ -1189,6 +1195,7 @@ only. */
#define STRING_NOTEMPTY_ATSTART_RIGHTPAR STR_N STR_O STR_T STR_E STR_M STR_P STR_T STR_Y STR_UNDERSCORE STR_A STR_T STR_S STR_T STR_A STR_R STR_T STR_RIGHT_PARENTHESIS
#define STRING_LIMIT_MATCH_EQ STR_L STR_I STR_M STR_I STR_T STR_UNDERSCORE STR_M STR_A STR_T STR_C STR_H STR_EQUALS_SIGN
#define STRING_LIMIT_RECURSION_EQ STR_L STR_I STR_M STR_I STR_T STR_UNDERSCORE STR_R STR_E STR_C STR_U STR_R STR_S STR_I STR_O STR_N STR_EQUALS_SIGN
#define STRING_MARK STR_M STR_A STR_R STR_K
#endif /* SUPPORT_UNICODE */
@ -1800,11 +1807,16 @@ typedef struct pcre2_serialized_data {
#if defined PCRE2_CODE_UNIT_WIDTH && PCRE2_CODE_UNIT_WIDTH != 0
/* EBCDIC is supported only for the 8-bit library. */
#if defined EBCDIC && PCRE2_CODE_UNIT_WIDTH != 8
#error EBCDIC is not supported for the 16-bit or 32-bit libraries
#endif
/* This is the largest non-UTF code point. */
#define MAX_NON_UTF_CHAR (0xffffffffU >> (32 - PCRE2_CODE_UNIT_WIDTH))
/* Internal shared data tables and variables. These are used by more than one
of the exported public functions. They have to be "external" in the C sense,
but are not part of the PCRE2 public API. Although the data for some of them is
@ -1883,6 +1895,7 @@ not referenced from pcre2test, and must not be defined when no code unit width
is available. */
#define _pcre2_auto_possessify PCRE2_SUFFIX(_pcre2_auto_possessify_)
#define _pcre2_check_escape PCRE2_SUFFIX(_pcre2_check_escape_)
#define _pcre2_find_bracket PCRE2_SUFFIX(_pcre2_find_bracket_)
#define _pcre2_is_newline PCRE2_SUFFIX(_pcre2_is_newline_)
#define _pcre2_jit_free_rodata PCRE2_SUFFIX(_pcre2_jit_free_rodata_)
@ -1904,6 +1917,8 @@ is available. */
extern int _pcre2_auto_possessify(PCRE2_UCHAR *, BOOL,
const compile_block *);
extern int _pcre2_check_escape(PCRE2_SPTR *, PCRE2_SPTR, uint32_t *,
int *, uint32_t, BOOL, compile_block *);
extern PCRE2_SPTR _pcre2_find_bracket(PCRE2_SPTR, BOOL, int);
extern BOOL _pcre2_is_newline(PCRE2_SPTR, uint32_t, PCRE2_SPTR,
uint32_t *, BOOL);

41
pcre2-10.20/src/pcre2_intmodedep.h → pcre2-10.21/src/pcre2_intmodedep.h
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -72,7 +72,7 @@ just to undefine them all. */
#undef MAX_MARK
#undef MAX_PATTERN_SIZE
#undef MAX_UTF_SINGLE_CU
#undef NOT_FIRSTCHAR
#undef NOT_FIRSTCU
#undef PUT
#undef PUT2
#undef PUT2INC
@ -252,7 +252,7 @@ UTF support is omitted, we don't even define them. */
/* #define MAX_UTF_SINGLE_CU */
/* #define HAS_EXTRALEN(c) */
/* #define GET_EXTRALEN(c) */
/* #define NOT_FIRSTCHAR(c) */
/* #define NOT_FIRSTCU(c) */
#define GETCHAR(c, eptr) c = *eptr;
#define GETCHARTEST(c, eptr) c = *eptr;
#define GETCHARINC(c, eptr) c = *eptr++;
@ -285,10 +285,10 @@ Otherwise it has an undefined behaviour. */
#define GET_EXTRALEN(c) (PRIV(utf8_table4)[(c) & 0x3f])
/* Returns TRUE, if the given character is not the first character
of a UTF sequence. */
/* Returns TRUE, if the given value is not the first code unit of a UTF
sequence. */
#define NOT_FIRSTCHAR(c) (((c) & 0xc0) == 0x80)
#define NOT_FIRSTCU(c) (((c) & 0xc0) == 0x80)
/* Get the next UTF-8 character, not advancing the pointer. This is called when
we know we are in UTF-8 mode. */
@ -371,10 +371,10 @@ Otherwise it has an undefined behaviour. */
#define GET_EXTRALEN(c) 1
/* Returns TRUE, if the given character is not the first character
of a UTF sequence. */
/* Returns TRUE, if the given value is not the first code unit of a UTF
sequence. */
#define NOT_FIRSTCHAR(c) (((c) & 0xfc00) == 0xdc00)
#define NOT_FIRSTCU(c) (((c) & 0xfc00) == 0xdc00)
/* Base macro to pick up the low surrogate of a UTF-16 character, not
advancing the pointer. */
@ -469,7 +469,7 @@ into one PCRE2_UCHAR unit. */
#define MAX_UTF_SINGLE_CU (0x10ffffu)
#define HAS_EXTRALEN(c) (0)
#define GET_EXTRALEN(c) (0)
#define NOT_FIRSTCHAR(c) (0)
#define NOT_FIRSTCU(c) (0)
/* Get the next UTF-32 character, not advancing the pointer. This is called when
we know we are in UTF-32 mode. */
@ -562,6 +562,7 @@ typedef struct pcre2_real_compile_context {
int (*stack_guard)(uint32_t, void *);
void *stack_guard_data;
const uint8_t *tables;
PCRE2_SIZE max_pattern_length;
uint16_t bsr_convention;
uint16_t newline_convention;
uint32_t parens_nest_limit;
@ -580,6 +581,7 @@ typedef struct pcre2_real_match_context {
#endif
int (*callout)(pcre2_callout_block *, void *);
void *callout_data;
PCRE2_SIZE offset_limit;
uint32_t match_limit;
uint32_t recursion_limit;
} pcre2_real_match_context;
@ -588,11 +590,17 @@ typedef struct pcre2_real_match_context {
defined specially because it is required in pcre2_serialize_decode() when
copying the size from possibly unaligned memory into a variable of the same
type. Use a macro rather than a typedef to avoid compiler warnings when this
file is included multiple times by pcre2test. */
file is included multiple times by pcre2test. LOOKBEHIND_MAX specifies the
largest lookbehind that is supported. (OP_REVERSE in a pattern has a 16-bit
argument in 8-bit and 16-bit modes, so we need no more than a 16-bit field
here.) */
#undef CODE_BLOCKSIZE_TYPE
#define CODE_BLOCKSIZE_TYPE size_t
#undef LOOKBEHIND_MAX
#define LOOKBEHIND_MAX UINT16_MAX
typedef struct pcre2_real_code {
pcre2_memctl memctl; /* Memory control fields */
const uint8_t *tables; /* The character tables */
@ -647,6 +655,13 @@ typedef struct recurse_check {
PCRE2_SPTR group;
} recurse_check;
/* Structure for building a cache when filling in recursion offsets. */
typedef struct recurse_cache {
PCRE2_SPTR group;
int recno;
} recurse_cache;
/* Structure for maintaining a chain of pointers to the currently incomplete
branches, for testing for left recursion while compiling. */
@ -678,7 +693,7 @@ typedef struct compile_block {
PCRE2_SPTR start_code; /* The start of the compiled code */
PCRE2_SPTR start_pattern; /* The start of the pattern */
PCRE2_SPTR end_pattern; /* The end of the pattern */
PCRE2_UCHAR *hwm; /* High watermark of workspace */
PCRE2_SPTR nestptr[2]; /* Pointer(s) saved for string substitution */
PCRE2_UCHAR *name_table; /* The name/number table */
size_t workspace_size; /* Size of workspace */
uint16_t names_found; /* Number of entries so far */
@ -690,6 +705,7 @@ typedef struct compile_block {
uint32_t external_flags; /* External flag bits to be set */
uint32_t bracount; /* Count of capturing parens as we compile */
uint32_t final_bracount; /* Saved value after first pass */
uint32_t *groupinfo; /* Group info vector */
uint32_t top_backref; /* Maximum back reference */
uint32_t backref_map; /* Bitmap of low back refs */
uint32_t nltype; /* Newline type */
@ -701,6 +717,7 @@ typedef struct compile_block {
int req_varyopt; /* "After variable item" flag for reqbyte */
BOOL had_accept; /* (*ACCEPT) encountered */
BOOL had_pruneorskip; /* (*PRUNE) or (*SKIP) encountered */
BOOL had_recurse; /* Had a recursion or subroutine call */
BOOL check_lookbehind; /* Lookbehinds need later checking */
BOOL dupnames; /* Duplicate names exist */
BOOL iscondassert; /* Next assert is a condition */

1422
pcre2-10.20/src/pcre2_jit_compile.c → pcre2-10.21/src/pcre2_jit_compile.c
View file

File diff suppressed because it is too large Load diff

5
pcre2-10.20/src/pcre2_jit_match.c → pcre2-10.21/src/pcre2_jit_match.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -129,10 +129,12 @@ arguments.match_data = match_data;
arguments.startchar_ptr = subject;
arguments.mark_ptr = NULL;
arguments.options = options;
if (mcontext != NULL)
{
arguments.callout = mcontext->callout;
arguments.callout_data = mcontext->callout_data;
arguments.offset_limit = mcontext->offset_limit;
arguments.limit_match = (mcontext->match_limit < re->limit_match)?
mcontext->match_limit : re->limit_match;
if (mcontext->jit_callback != NULL)
@ -144,6 +146,7 @@ else
{
arguments.callout = NULL;
arguments.callout_data = NULL;
arguments.offset_limit = PCRE2_UNSET;
arguments.limit_match = (MATCH_LIMIT < re->limit_match)?
MATCH_LIMIT : re->limit_match;
jit_stack = NULL;

2
pcre2-10.20/src/pcre2_jit_misc.c → pcre2-10.21/src/pcre2_jit_misc.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without

21
pcre2-10.20/src/pcre2_jit_test.c → pcre2-10.21/src/pcre2_jit_test.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -188,6 +188,7 @@ static struct regression_test_case regression_test_cases[] = {
{ CMUP, A, 0, 0, "\xf0\x90\x90\x80{2}", "\xf0\x90\x90\x80#\xf0\x90\x90\xa8\xf0\x90\x90\x80" },
{ CMUP, A, 0, 0, "\xf0\x90\x90\xa8{2}", "\xf0\x90\x90\x80#\xf0\x90\x90\xa8\xf0\x90\x90\x80" },
{ CMUP, A, 0, 0, "\xe1\xbd\xb8\xe1\xbf\xb8", "\xe1\xbf\xb8\xe1\xbd\xb8" },
{ M, A, 0, 0, "[3-57-9]", "5" },
/* Assertions. */
{ MU, A, 0, 0, "\\b[^A]", "A_B#" },
@ -247,13 +248,17 @@ static struct regression_test_case regression_test_cases[] = {
{ M, A, 0, 0, "a\\z", "aaa" },
{ M, A, 0, 0 | F_NOMATCH, "a\\z", "aab" },
/* Brackets. */
/* Brackets and alternatives. */
{ MU, A, 0, 0, "(ab|bb|cd)", "bacde" },
{ MU, A, 0, 0, "(?:ab|a)(bc|c)", "ababc" },
{ MU, A, 0, 0, "((ab|(cc))|(bb)|(?:cd|efg))", "abac" },
{ CMU, A, 0, 0, "((aB|(Cc))|(bB)|(?:cd|EFg))", "AcCe" },
{ MU, A, 0, 0, "((ab|(cc))|(bb)|(?:cd|ebg))", "acebebg" },
{ MU, A, 0, 0, "(?:(a)|(?:b))(cc|(?:d|e))(a|b)k", "accabdbbccbk" },
{ MU, A, 0, 0, "\xc7\x82|\xc6\x82", "\xf1\x83\x82\x82\xc7\x82\xc7\x83" },
{ MU, A, 0, 0, "=\xc7\x82|#\xc6\x82", "\xf1\x83\x82\x82=\xc7\x82\xc7\x83" },
{ MU, A, 0, 0, "\xc7\x82\xc7\x83|\xc6\x82\xc6\x82", "\xf1\x83\x82\x82\xc7\x82\xc7\x83" },
{ MU, A, 0, 0, "\xc6\x82\xc6\x82|\xc7\x83\xc7\x83|\xc8\x84\xc8\x84", "\xf1\x83\x82\x82\xc8\x84\xc8\x84" },
/* Greedy and non-greedy ? operators. */
{ MU, A, 0, 0, "(?:a)?a", "laab" },
@ -323,6 +328,14 @@ static struct regression_test_case regression_test_cases[] = {
{ CMU, A, 0, 0, "[^\xe1\xbd\xb8][^\xc3\xa9]", "\xe1\xbd\xb8\xe1\xbf\xb8\xc3\xa9\xc3\x89#" },
{ MU, A, 0, 0, "[^\xe1\xbd\xb8][^\xc3\xa9]", "\xe1\xbd\xb8\xe1\xbf\xb8\xc3\xa9\xc3\x89#" },
{ MU, A, 0, 0, "[^\xe1\xbd\xb8]{3,}?", "##\xe1\xbd\xb8#\xe1\xbd\xb8#\xc3\x89#\xe1\xbd\xb8" },
{ MU, A, 0, 0, "\\d+123", "987654321,01234" },
{ MU, A, 0, 0, "abcd*|\\w+xy", "aaaaa,abxyz" },
{ MU, A, 0, 0, "(?:abc|((?:amc|\\b\\w*xy)))", "aaaaa,abxyz" },
{ MU, A, 0, 0, "a(?R)|([a-z]++)#", ".abcd.abcd#."},
{ MU, A, 0, 0, "a(?R)|([a-z]++)#", ".abcd.mbcd#."},
{ MU, A, 0, 0, ".[ab]*.", "xx" },
{ MU, A, 0, 0, ".[ab]*a", "xxa" },
{ MU, A, 0, 0, ".[ab]?.", "xx" },
/* Bracket repeats with limit. */
{ MU, A, 0, 0, "(?:(ab){2}){5}M", "abababababababababababM" },
@ -679,6 +692,7 @@ static struct regression_test_case regression_test_cases[] = {
{ MU | PCRE2_FIRSTLINE, PCRE2_NEWLINE_CRLF, 0, 1, ".", "\r\n" },
{ PCRE2_FIRSTLINE | PCRE2_DOTALL, PCRE2_NEWLINE_LF, 0, 0 | F_NOMATCH, "ab.", "ab" },
{ MU | PCRE2_FIRSTLINE, A, 0, 1 | F_NOMATCH, "^[a-d0-9]", "\nxx\nd" },
{ PCRE2_FIRSTLINE | PCRE2_DOTALL, PCRE2_NEWLINE_ANY, 0, 0, "....a", "012\n0a" },
/* Recurse. */
{ MU, A, 0, 0, "(a)(?1)", "aa" },
@ -813,6 +827,9 @@ static struct regression_test_case regression_test_cases[] = {
/* (*SKIP) verb. */
{ MU, A, 0, 0 | F_NOMATCH, "(?=a(*SKIP)b)ab|ad", "ad" },
{ MU, A, 0, 0, "(\\w+(*SKIP)#)", "abcd,xyz#," },
{ MU, A, 0, 0, "\\w+(*SKIP)#|mm", "abcd,xyz#," },
{ MU, A, 0, 0 | F_NOMATCH, "b+(?<=(*SKIP)#c)|b+", "#bbb" },
/* (*THEN) verb. */
{ MU, A, 0, 0, "((?:a(*THEN)|aab)(*THEN)c|a+)+m", "aabcaabcaabcaabcnacm" },

2
pcre2-10.20/src/pcre2_maketables.c → pcre2-10.21/src/pcre2_maketables.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without

132
pcre2-10.20/src/pcre2_match.c → pcre2-10.21/src/pcre2_match.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -194,7 +194,7 @@ if (caseless)
GETCHARINC(c, eptr);
GETCHARINC(d, p);
ur = GET_UCD(d);
if (c != d && c != d + ur->other_case)
if (c != d && c != (uint32_t)((int)d + ur->other_case))
{
const uint32_t *pp = PRIV(ucd_caseless_sets) + ur->caseset;
for (;;)
@ -211,7 +211,7 @@ if (caseless)
/* Not in UTF mode */
{
while (length-- > 0)
for (; length > 0; length--)
{
uint32_t cc, cp;
if (eptr >= mb->end_subject) return 1; /* Partial match */
@ -226,11 +226,11 @@ if (caseless)
}
/* In the caseful case, we can just compare the code units, whether or not we
are in UT mode. */
are in UTF mode. */
else
{
while (length-- > 0)
for (; length > 0; length--)
{
if (eptr >= mb->end_subject) return 1; /* Partial match */
if (UCHAR21INCTEST(p) != UCHAR21INCTEST(eptr)) return -1; /*No match */
@ -1704,14 +1704,14 @@ for (;;)
back a number of characters, not bytes. */
case OP_REVERSE:
i = GET(ecode, 1);
#ifdef SUPPORT_UNICODE
if (utf)
{
i = GET(ecode, 1);
while (i-- > 0)
{
if (eptr <= mb->start_subject) RRETURN(MATCH_NOMATCH);
eptr--;
if (eptr < mb->start_subject) RRETURN(MATCH_NOMATCH);
BACKCHAR(eptr);
}
}
@ -1721,8 +1721,8 @@ for (;;)
/* No UTF-8 support, or not in UTF-8 mode: count is byte count */
{
eptr -= GET(ecode, 1);
if (eptr < mb->start_subject) RRETURN(MATCH_NOMATCH);
if (i > eptr - mb->start_subject) RRETURN(MATCH_NOMATCH);
eptr -= i;
}
/* Save the earliest consulted character, then skip to next op code */
@ -2408,8 +2408,9 @@ for (;;)
ecode++;
break;
/* Match a single byte, even in UTF-8 mode. This opcode really does match
any byte, even newline, independent of the setting of PCRE2_DOTALL. */
/* Match a single code unit, even in UTF-8 mode. This opcode really does
match any code unit, even newline. (It really should be called ANYCODEUNIT,
of course - the byte name is from pre-16 bit days.) */
case OP_ANYBYTE:
if (eptr >= mb->end_subject) /* DO NOT merge the eptr++ here; it must */
@ -3342,7 +3343,10 @@ for (;;)
CHECK_PARTIAL(); /* Not SCHECK_PARTIAL() */
RRETURN(MATCH_NOMATCH);
}
while (length-- > 0) if (*ecode++ != UCHAR21INC(eptr)) RRETURN(MATCH_NOMATCH);
for (; length > 0; length--)
{
if (*ecode++ != UCHAR21INC(eptr)) RRETURN(MATCH_NOMATCH);
}
}
else
#endif
@ -6459,6 +6463,7 @@ PCRE2_UCHAR first_cu2 = 0;
PCRE2_UCHAR req_cu = 0;
PCRE2_UCHAR req_cu2 = 0;
PCRE2_SPTR bumpalong_limit;
PCRE2_SPTR end_subject;
PCRE2_SPTR start_match = subject + start_offset;
PCRE2_SPTR req_cu_ptr = start_match - 1;
@ -6482,6 +6487,7 @@ mb->match_frames_base = &frame_zero;
subject string. */
if (length == PCRE2_ZERO_TERMINATED) length = PRIV(strlen)(subject);
end_subject = subject + length;
/* Plausibility checks */
@ -6513,7 +6519,7 @@ occur. */
#define FF (PCRE2_NOTEMPTY_SET|PCRE2_NE_ATST_SET)
#define OO (PCRE2_NOTEMPTY|PCRE2_NOTEMPTY_ATSTART)
options |= (re->flags & FF) / ((FF & -FF) / (OO & -OO));
options |= (re->flags & FF) / ((FF & (~FF+1)) / (OO & (~OO+1)));
#undef FF
#undef OO
@ -6533,21 +6539,66 @@ mb->partial = ((options & PCRE2_PARTIAL_HARD) != 0)? 2 :
/* Check a UTF string for validity if required. For 8-bit and 16-bit strings,
we must also check that a starting offset does not point into the middle of a
multiunit character. */
multiunit character. We check only the portion of the subject that is going to
be inspected during matching - from the offset minus the maximum back reference
to the given length. This saves time when a small part of a large subject is
being matched by the use of a starting offset. Note that the maximum lookbehind
is a number of characters, not code units. */
#ifdef SUPPORT_UNICODE
if (utf && (options & PCRE2_NO_UTF_CHECK) == 0)
{
match_data->rc = PRIV(valid_utf)(subject, length, &(match_data->startchar));
if (match_data->rc != 0) return match_data->rc;
PCRE2_SPTR check_subject = start_match; /* start_match includes offset */
if (start_offset > 0)
{
#if PCRE2_CODE_UNIT_WIDTH != 32
if (start_offset > 0 && start_offset < length &&
NOT_FIRSTCHAR(subject[start_offset]))
return PCRE2_ERROR_BADUTFOFFSET;
unsigned int i;
if (start_match < end_subject && NOT_FIRSTCU(*start_match))
return PCRE2_ERROR_BADUTFOFFSET;
for (i = re->max_lookbehind; i > 0 && check_subject > subject; i--)
{
check_subject--;
while (check_subject > subject &&
#if PCRE2_CODE_UNIT_WIDTH == 8
(*check_subject & 0xc0) == 0x80)
#else /* 16-bit */
(*check_subject & 0xfc00) == 0xdc00)
#endif /* PCRE2_CODE_UNIT_WIDTH == 8 */
check_subject--;
}
#else
/* In the 32-bit library, one code unit equals one character. However,
we cannot just subtract the lookbehind and then compare pointers, because
a very large lookbehind could create an invalid pointer. */
if (start_offset >= re->max_lookbehind)
check_subject -= re->max_lookbehind;
else
check_subject = subject;
#endif /* PCRE2_CODE_UNIT_WIDTH != 32 */
}
/* Validate the relevant portion of the subject. After an error, adjust the
offset to be an absolute offset in the whole string. */
match_data->rc = PRIV(valid_utf)(check_subject,
length - (check_subject - subject), &(match_data->startchar));
if (match_data->rc != 0)
{
match_data->startchar += check_subject - subject;
return match_data->rc;
}
}
#endif /* SUPPORT_UNICODE */
/* It is an error to set an offset limit without setting the flag at compile
time. */
if (mcontext->offset_limit != PCRE2_UNSET &&
(re->overall_options & PCRE2_USE_OFFSET_LIMIT) == 0)
return PCRE2_ERROR_BADOFFSETLIMIT;
/* If the pattern was successfully studied with JIT support, run the JIT
executable instead of the rest of this function. Most options must be set at
compile time for the JIT code to be usable. Fallback to the normal code path if
@ -6568,30 +6619,21 @@ if (re->executable_jit != NULL && (options & ~PUBLIC_JIT_MATCH_OPTIONS) == 0)
anchored = ((re->overall_options | options) & PCRE2_ANCHORED) != 0;
firstline = (re->overall_options & PCRE2_FIRSTLINE) != 0;
startline = (re->flags & PCRE2_STARTLINE) != 0;
bumpalong_limit = (mcontext->offset_limit == PCRE2_UNSET)?
end_subject : subject + mcontext->offset_limit;
/* Fill in the fields in the match block. */
if (mcontext == NULL)
{
mb->callout = NULL;
mb->memctl = re->memctl;
mb->callout = mcontext->callout;
mb->callout_data = mcontext->callout_data;
mb->memctl = mcontext->memctl;
#ifdef HEAP_MATCH_RECURSE
mb->stack_memctl = re->memctl;
mb->stack_memctl = mcontext->stack_memctl;
#endif
}
else
{
mb->callout = mcontext->callout;
mb->callout_data = mcontext->callout_data;
mb->memctl = mcontext->memctl;
#ifdef HEAP_MATCH_RECURSE
mb->stack_memctl = mcontext->stack_memctl;
#endif
}
mb->start_subject = subject;
mb->start_offset = start_offset;
mb->end_subject = end_subject = mb->start_subject + length;
mb->end_subject = end_subject;
mb->hasthen = (re->flags & PCRE2_HASTHEN) != 0;
mb->moptions = options; /* Match options */
@ -6783,7 +6825,8 @@ for(;;)
end_subject = t;
}
/* Advance to a unique first code unit if there is one. */
/* Advance to a unique first code unit if there is one. In 8-bit mode, the
use of memchr() gives a big speed up. */
if (has_first_cu)
{
@ -6793,8 +6836,15 @@ for(;;)
(smc = UCHAR21TEST(start_match)) != first_cu && smc != first_cu2)
start_match++;
else
{
#if PCRE2_CODE_UNIT_WIDTH != 8
while (start_match < end_subject && UCHAR21TEST(start_match) != first_cu)
start_match++;
#else
start_match = memchr(start_match, first_cu, end_subject - start_match);
if (start_match == NULL) start_match = end_subject;
#endif
}
}
/* Or to just after a linebreak for a multiline match */
@ -6926,6 +6976,14 @@ for(;;)
/* ------------ End of start of match optimizations ------------ */
/* Give no match if we have passed the bumpalong limit. */
if (start_match > bumpalong_limit)
{
rc = MATCH_NOMATCH;
break;
}
/* OK, we can now run the match. If "hitend" is set afterwards, remember the
first starting point for which a partial match was found. */
@ -7044,7 +7102,7 @@ for(;;)
(2) The pattern is anchored or the match was failed by (*COMMIT);
(3) We are past the end of the subject;
(3) We are past the end of the subject or the bumpalong limit;
(4) PCRE2_FIRSTLINE is set and we have failed to match at a newline, because
this option requests that a match occur at or before the first newline in

2
pcre2-10.20/src/pcre2_match_data.c → pcre2-10.21/src/pcre2_match_data.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without

2
pcre2-10.20/src/pcre2_newline.c → pcre2-10.21/src/pcre2_newline.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without

2
pcre2-10.20/src/pcre2_ord2utf.c → pcre2-10.21/src/pcre2_ord2utf.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without

7
pcre2-10.20/src/pcre2_pattern_info.c → pcre2-10.21/src/pcre2_pattern_info.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -77,6 +77,7 @@ if (where == NULL) /* Requests field length */
case PCRE2_INFO_CAPTURECOUNT:
case PCRE2_INFO_FIRSTCODETYPE:
case PCRE2_INFO_FIRSTCODEUNIT:
case PCRE2_INFO_HASBACKSLASHC:
case PCRE2_INFO_HASCRORLF:
case PCRE2_INFO_JCHANGED:
case PCRE2_INFO_LASTCODETYPE:
@ -151,6 +152,10 @@ switch(what)
&(re->start_bitmap[0]) : NULL;
break;
case PCRE2_INFO_HASBACKSLASHC:
*((uint32_t *)where) = (re->flags & PCRE2_HASBKC) != 0;
break;
case PCRE2_INFO_HASCRORLF:
*((uint32_t *)where) = (re->flags & PCRE2_HASCRORLF) != 0;
break;

35
pcre2-10.20/src/pcre2_printint.c → pcre2-10.21/src/pcre2_printint.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -58,12 +58,13 @@ static const char *OP_names[] = { OP_NAME_LIST };
/* The functions and tables herein must all have mode-dependent names. */
#define OP_lengths PCRE2_SUFFIX(OP_lengths_)
#define get_ucpname PCRE2_SUFFIX(get_ucpname_)
#define pcre2_printint PCRE2_SUFFIX(pcre2_printint_)
#define print_char PCRE2_SUFFIX(print_char_)
#define print_custring PCRE2_SUFFIX(print_custring_)
#define print_prop PCRE2_SUFFIX(print_prop_)
#define OP_lengths PCRE2_SUFFIX(OP_lengths_)
#define get_ucpname PCRE2_SUFFIX(get_ucpname_)
#define pcre2_printint PCRE2_SUFFIX(pcre2_printint_)
#define print_char PCRE2_SUFFIX(print_char_)
#define print_custring PCRE2_SUFFIX(print_custring_)
#define print_custring_bylen PCRE2_SUFFIX(print_custring_bylen_)
#define print_prop PCRE2_SUFFIX(print_prop_)
/* Table of sizes for the fixed-length opcodes. It's defined in a macro so that
the definition is next to the definition of the opcodes in pcre2_internal.h.
@ -188,12 +189,14 @@ return 0;
* Print string as a list of code units *
*************************************************/
/* This takes no account of UTF as it always prints each individual code unit.
The string is zero-terminated.
/* These take no account of UTF as they always print each individual code unit.
The string is zero-terminated for print_custring(); the length is given for
print_custring_bylen().
Arguments:
f file to write to
ptr point to the string
len length for print_custring_bylen()
Returns: nothing
*/
@ -208,6 +211,16 @@ while (*ptr != '\0')
}
}
static void
print_custring_bylen(FILE *f, PCRE2_SPTR ptr, PCRE2_UCHAR len)
{
while (len-- > 0)
{
register uint32_t c = *ptr++;
if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x{%x}", c);
}
}
/*************************************************
@ -603,7 +616,7 @@ for(;;)
c = code[1 + 4*LINK_SIZE];
fprintf(f, " %s %c", OP_names[*code], c);
extra = GET(code, 1 + 2*LINK_SIZE);
print_custring(f, code + 2 + 4*LINK_SIZE);
print_custring_bylen(f, code + 2 + 4*LINK_SIZE, extra - 3 - 4*LINK_SIZE);
for (i = 0; PRIV(callout_start_delims)[i] != 0; i++)
if (c == PRIV(callout_start_delims)[i])
{
@ -791,7 +804,7 @@ for(;;)
case OP_SKIP_ARG:
case OP_THEN_ARG:
fprintf(f, " %s ", OP_names[*code]);
print_custring(f, code + 2);
print_custring_bylen(f, code + 2, code[1]);
extra += code[1];
break;

20
pcre2-10.20/src/pcre2_serialize.c → pcre2-10.21/src/pcre2_serialize.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2015 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -104,7 +104,7 @@ for (i = 0; i < number_of_codes; i++)
return PCRE2_ERROR_MIXEDTABLES;
total_size += re->blocksize;
}
/* Initialize the byte stream. */
bytes = memctl->malloc(total_size + sizeof(pcre2_memctl), memctl->memory_data);
if (bytes == NULL) return PCRE2_ERROR_NOMEMORY;
@ -167,7 +167,7 @@ if (number_of_codes > data->number_of_codes)
src_bytes = bytes + sizeof(pcre2_serialized_data);
/* Decode tables. The reference count for the tables is stored immediately
/* Decode tables. The reference count for the tables is stored immediately
following them. */
tables = memctl->malloc(tables_length + sizeof(PCRE2_SIZE), memctl->memory_data);
@ -179,8 +179,8 @@ src_bytes += tables_length;
/* Decode the byte stream. We must not try to read the size from the compiled
code block in the stream, because it might be unaligned, which causes errors on
hardware such as Sparc-64 that doesn't like unaligned memory accesses. The type
of the blocksize field is given its own name to ensure that it is the same here
hardware such as Sparc-64 that doesn't like unaligned memory accesses. The type
of the blocksize field is given its own name to ensure that it is the same here
as in the block. */
for (i = 0; i < number_of_codes; i++)
@ -190,8 +190,8 @@ for (i = 0; i < number_of_codes; i++)
sizeof(CODE_BLOCKSIZE_TYPE));
/* The allocator provided by gcontext replaces the original one. */
dst_re = (pcre2_real_code *)PRIV(memctl_malloc)(blocksize,
dst_re = (pcre2_real_code *)PRIV(memctl_malloc)(blocksize,
(pcre2_memctl *)gcontext);
if (dst_re == NULL)
{
@ -205,12 +205,12 @@ for (i = 0; i < number_of_codes; i++)
}
/* The new allocator must be preserved. */
memcpy(((uint8_t *)dst_re) + sizeof(pcre2_memctl),
src_bytes + sizeof(pcre2_memctl), blocksize - sizeof(pcre2_memctl));
/* At the moment only one table is supported. */
dst_re->tables = tables;
dst_re->executable_jit = NULL;
dst_re->flags |= PCRE2_DEREF_TABLES;
@ -252,7 +252,7 @@ if (bytes != NULL)
{
pcre2_memctl *memctl = (pcre2_memctl *)(bytes - sizeof(pcre2_memctl));
memctl->free(memctl, memctl->memory_data);
}
}
}
/* End of pcre2_serialize.c */

6
pcre2-10.20/src/pcre2_string_utils.c → pcre2-10.21/src/pcre2_string_utils.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -121,7 +121,7 @@ int
PRIV(strncmp)(PCRE2_SPTR str1, PCRE2_SPTR str2, size_t len)
{
PCRE2_UCHAR c1, c2;
while (len-- > 0)
for (; len > 0; len--)
{
c1 = *str1++;
c2 = *str2++;
@ -150,7 +150,7 @@ int
PRIV(strncmp_c8)(PCRE2_SPTR str1, const char *str2, size_t len)
{
PCRE2_UCHAR c1, c2;
while (len-- > 0)
for (; len > 0; len--)
{
c1 = *str1++;
c2 = *str2++;

186
pcre2-10.20/src/pcre2_study.c → pcre2-10.21/src/pcre2_study.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -59,15 +59,17 @@ collecting data (e.g. minimum matching length). */
enum { SSB_FAIL, SSB_DONE, SSB_CONTINUE, SSB_UNKNOWN };
/*************************************************
* Find the minimum subject length for a group *
*************************************************/
/* Scan a parenthesized group and compute the minimum length of subject that
is needed to match it. This is a lower bound; it does not mean there is a
string of that length that matches. In UTF8 mode, the result is in characters
rather than bytes.
string of that length that matches. In UTF mode, the result is in characters
rather than code units. The field in a compiled pattern for storing the minimum
length is 16-bits long (on the grounds that anything longer than that is
pathological), so we give up when we reach that amount. This also means that
integer overflow for really crazy patterns cannot happen.
Arguments:
re compiled pattern block
@ -75,36 +77,57 @@ Arguments:
startcode pointer to start of the whole pattern's code
utf UTF flag
recurses chain of recurse_check to catch mutual recursion
countptr pointer to call count (to catch over complexity)
Returns: the minimum length
-1 \C in UTF-8 mode
or (*ACCEPT)
or pattern too complicated
or back reference to duplicate name/number
-2 internal error (missing capturing bracket)
-3 internal error (opcode not listed)
*/
static int
find_minlength(const pcre2_real_code *re, PCRE2_SPTR code,
PCRE2_SPTR startcode, BOOL utf, recurse_check *recurses)
PCRE2_SPTR startcode, BOOL utf, recurse_check *recurses, int *countptr)
{
int length = -1;
int prev_cap_recno = -1;
int prev_cap_d = 0;
int prev_recurse_recno = -1;
int prev_recurse_d = 0;
uint32_t once_fudge = 0;
BOOL had_recurse = FALSE;
BOOL dupcapused = (re->flags & PCRE2_DUPCAPUSED) != 0;
recurse_check this_recurse;
register int branchlength = 0;
register PCRE2_UCHAR *cc = (PCRE2_UCHAR *)code + 1 + LINK_SIZE;
if (*code == OP_CBRA || *code == OP_SCBRA ||
*code == OP_CBRAPOS || *code == OP_SCBRAPOS) cc += IMM2_SIZE;
/* If this is a "could be empty" group, its minimum length is 0. */
/* Scan along the opcodes for this branch. If we get to the end of the
branch, check the length against that of the other branches. */
if (*code >= OP_SBRA && *code <= OP_SCOND) return 0;
/* Skip over capturing bracket number */
if (*code == OP_CBRA || *code == OP_CBRAPOS) cc += IMM2_SIZE;
/* A large and/or complex regex can take too long to process. */
if ((*countptr)++ > 1000) return -1;
/* Scan along the opcodes for this branch. If we get to the end of the branch,
check the length against that of the other branches. If the accumulated length
passes 16-bits, stop. */
for (;;)
{
int d, min;
int d, min, recno;
PCRE2_UCHAR *cs, *ce;
register PCRE2_UCHAR op = *cc;
if (branchlength >= UINT16_MAX) return UINT16_MAX;
switch (op)
{
case OP_COND:
@ -112,7 +135,8 @@ for (;;)
/* If there is only one branch in a condition, the implied branch has zero
length, so we don't add anything. This covers the DEFINE "condition"
automatically. */
automatically. If there are two branches we can treat it the same as any
other non-capturing subpattern. */
cs = cc + GET(cc, 1);
if (*cs != OP_ALT)
@ -120,23 +144,52 @@ for (;;)
cc = cs + 1 + LINK_SIZE;
break;
}
goto PROCESS_NON_CAPTURE;
/* Otherwise we can fall through and treat it the same as any other
subpattern. */
/* There's a special case of OP_ONCE, when it is wrapped round an
OP_RECURSE. We'd like to process the latter at this level so that
remembering the value works for repeated cases. So we do nothing, but
set a fudge value to skip over the OP_KET after the recurse. */
case OP_ONCE:
if (cc[1+LINK_SIZE] == OP_RECURSE && cc[2*(1+LINK_SIZE)] == OP_KET)
{
once_fudge = 1 + LINK_SIZE;
cc += 1 + LINK_SIZE;
break;
}
/* Fall through */
case OP_ONCE_NC:
case OP_BRA:
case OP_SBRA:
case OP_BRAPOS:
case OP_SBRAPOS:
PROCESS_NON_CAPTURE:
d = find_minlength(re, cc, startcode, utf, recurses, countptr);
if (d < 0) return d;
branchlength += d;
do cc += GET(cc, 1); while (*cc == OP_ALT);
cc += 1 + LINK_SIZE;
break;
/* To save time for repeated capturing subpatterns, we remember the
length of the previous one. Unfortunately we can't do the same for
the unnumbered ones above. Nor can we do this if (?| is present in the
pattern because captures with the same number are not then identical. */
case OP_CBRA:
case OP_SCBRA:
case OP_BRA:
case OP_SBRA:
case OP_CBRAPOS:
case OP_SCBRAPOS:
case OP_BRAPOS:
case OP_SBRAPOS:
case OP_ONCE:
case OP_ONCE_NC:
d = find_minlength(re, cc, startcode, utf, recurses);
if (d < 0) return d;
branchlength += d;
recno = dupcapused? prev_cap_recno - 1 : (int)GET2(cc, 1+LINK_SIZE);
if (recno != prev_cap_recno)
{
prev_cap_recno = recno;
prev_cap_d = find_minlength(re, cc, startcode, utf, recurses, countptr);
if (prev_cap_d < 0) return prev_cap_d;
}
branchlength += prev_cap_d;
do cc += GET(cc, 1); while (*cc == OP_ALT);
cc += 1 + LINK_SIZE;
break;
@ -388,8 +441,12 @@ for (;;)
matches an empty string (by default it causes a matching failure), so in
that case we must set the minimum length to zero. */
case OP_DNREF: /* Duplicate named pattern back reference */
/* Duplicate named pattern back reference. We cannot reliably find a length
for this if duplicate numbers are present in the pattern. */
case OP_DNREF:
case OP_DNREFI:
if (dupcapused) return -1;
if ((re->overall_options & PCRE2_MATCH_UNSET_BACKREF) == 0)
{
int count = GET2(cc, 1+IMM2_SIZE);
@ -427,7 +484,7 @@ for (;;)
int dd;
this_recurse.prev = recurses;
this_recurse.group = cs;
dd = find_minlength(re, cs, startcode, utf, &this_recurse);
dd = find_minlength(re, cs, startcode, utf, &this_recurse, countptr);
if (dd < d) d = dd;
}
}
@ -438,8 +495,12 @@ for (;;)
cc += 1 + 2*IMM2_SIZE;
goto REPEAT_BACK_REFERENCE;
case OP_REF: /* Single back reference */
/* Single back reference. We cannot find a length for this if duplicate
numbers are present in the pattern. */
case OP_REF:
case OP_REFI:
if (dupcapused) return -1;
if ((re->overall_options & PCRE2_MATCH_UNSET_BACKREF) == 0)
{
ce = cs = (PCRE2_UCHAR *)PRIV(find_bracket)(startcode, utf, GET2(cc, 1));
@ -463,7 +524,7 @@ for (;;)
{
this_recurse.prev = recurses;
this_recurse.group = cs;
d = find_minlength(re, cs, startcode, utf, &this_recurse);
d = find_minlength(re, cs, startcode, utf, &this_recurse, countptr);
}
}
}
@ -504,28 +565,51 @@ for (;;)
break;
}
branchlength += min * d;
/* Take care not to overflow: (1) min and d are ints, so check that their
product is not greater than INT_MAX. (2) branchlength is limited to
UINT16_MAX (checked at the top of the loop). */
if ((d > 0 && (INT_MAX/d) < min) || UINT16_MAX - branchlength < min*d)
branchlength = UINT16_MAX;
else branchlength += min * d;
break;
/* Recursion always refers to the first occurrence of a subpattern with a
given number. Therefore, we can always make use of caching, even when the
pattern contains multiple subpatterns with the same number. */
case OP_RECURSE:
cs = ce = (PCRE2_UCHAR *)startcode + GET(cc, 1);
do ce += GET(ce, 1); while (*ce == OP_ALT);
if (cc > cs && cc < ce) /* Simple recursion */
had_recurse = TRUE;
recno = GET2(cs, 1+LINK_SIZE);
if (recno == prev_recurse_recno)
{
branchlength += prev_recurse_d;
}
else
{
recurse_check *r = recurses;
for (r = recurses; r != NULL; r = r->prev) if (r->group == cs) break;
if (r != NULL) /* Mutual recursion */
do ce += GET(ce, 1); while (*ce == OP_ALT);
if (cc > cs && cc < ce) /* Simple recursion */
had_recurse = TRUE;
else
{
this_recurse.prev = recurses;
this_recurse.group = cs;
branchlength += find_minlength(re, cs, startcode, utf, &this_recurse);
recurse_check *r = recurses;
for (r = recurses; r != NULL; r = r->prev) if (r->group == cs) break;
if (r != NULL) /* Mutual recursion */
had_recurse = TRUE;
else
{
this_recurse.prev = recurses;
this_recurse.group = cs;
prev_recurse_d = find_minlength(re, cs, startcode, utf, &this_recurse,
countptr);
if (prev_recurse_d < 0) return prev_recurse_d;
prev_recurse_recno = recno;
branchlength += prev_recurse_d;
}
}
}
cc += 1 + LINK_SIZE;
cc += 1 + LINK_SIZE + once_fudge;
once_fudge = 0;
break;
/* Anything else does not or need not match a character. We can get the
@ -1441,6 +1525,7 @@ int
PRIV(study)(pcre2_real_code *re)
{
int min;
int count = 0;
PCRE2_UCHAR *code;
BOOL utf = (re->overall_options & PCRE2_UTF) != 0;
@ -1461,22 +1546,27 @@ if ((re->overall_options & PCRE2_ANCHORED) == 0 &&
if (rc == SSB_DONE) re->flags |= PCRE2_FIRSTMAPSET;
}
/* Find the minimum length of subject string. */
/* Find the minimum length of subject string. If it can match an empty string,
the minimum length is already known. */
switch(min = find_minlength(re, code, code, utf, NULL))
if ((re->flags & PCRE2_MATCH_EMPTY) == 0)
{
case -1: /* \C in UTF mode or (*ACCEPT) */
break; /* Leave minlength unchanged (will be zero) */
switch(min = find_minlength(re, code, code, utf, NULL, &count))
{
case -1: /* \C in UTF mode or (*ACCEPT) or over-complex regex */
break; /* Leave minlength unchanged (will be zero) */
case -2:
return 2; /* missing capturing bracket */
case -2:
return 2; /* missing capturing bracket */
case -3:
return 3; /* unrecognized opcode */
case -3:
return 3; /* unrecognized opcode */
default:
re->minlength = min;
break;
default:
if (min > UINT16_MAX) min = UINT16_MAX;
re->minlength = min;
break;
}
}
return 0;

850
pcre2-10.21/src/pcre2_substitute.c Normal file
View file

@ -0,0 +1,850 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
#define PTR_STACK_SIZE 20
#define SUBSTITUTE_OPTIONS \
(PCRE2_SUBSTITUTE_EXTENDED|PCRE2_SUBSTITUTE_GLOBAL| \
PCRE2_SUBSTITUTE_OVERFLOW_LENGTH|PCRE2_SUBSTITUTE_UNKNOWN_UNSET| \
PCRE2_SUBSTITUTE_UNSET_EMPTY)
/*************************************************
* Find end of substitute text *
*************************************************/
/* In extended mode, we recognize ${name:+set text:unset text} and similar
constructions. This requires the identification of unescaped : and }
characters. This function scans for such. It must deal with nested ${
constructions. The pointer to the text is updated, either to the required end
character, or to where an error was detected.
Arguments:
code points to the compiled expression (for options)
ptrptr points to the pointer to the start of the text (updated)
ptrend end of the whole string
last TRUE if the last expected string (only } recognized)
Returns: 0 on success
negative error code on failure
*/
static int
find_text_end(const pcre2_code *code, PCRE2_SPTR *ptrptr, PCRE2_SPTR ptrend,
BOOL last)
{
int rc = 0;
uint32_t nestlevel = 0;
BOOL literal = FALSE;
PCRE2_SPTR ptr = *ptrptr;
for (; ptr < ptrend; ptr++)
{
if (literal)
{
if (ptr[0] == CHAR_BACKSLASH && ptr < ptrend - 1 && ptr[1] == CHAR_E)
{
literal = FALSE;
ptr += 1;
}
}
else if (*ptr == CHAR_RIGHT_CURLY_BRACKET)
{
if (nestlevel == 0) goto EXIT;
nestlevel--;
}
else if (*ptr == CHAR_COLON && !last && nestlevel == 0) goto EXIT;
else if (*ptr == CHAR_DOLLAR_SIGN)
{
if (ptr < ptrend - 1 && ptr[1] == CHAR_LEFT_CURLY_BRACKET)
{
nestlevel++;
ptr += 1;
}
}
else if (*ptr == CHAR_BACKSLASH)
{
int erc;
int errorcode = 0;
uint32_t ch;
if (ptr < ptrend - 1) switch (ptr[1])
{
case CHAR_L:
case CHAR_l:
case CHAR_U:
case CHAR_u:
ptr += 1;
continue;
}
erc = PRIV(check_escape)(&ptr, ptrend, &ch, &errorcode,
code->overall_options, FALSE, NULL);
if (errorcode != 0)
{
rc = errorcode;
goto EXIT;
}
switch(erc)
{
case 0: /* Data character */
case ESC_E: /* Isolated \E is ignored */
break;
case ESC_Q:
literal = TRUE;
break;
default:
rc = PCRE2_ERROR_BADREPESCAPE;
goto EXIT;
}
}
}
rc = PCRE2_ERROR_REPMISSINGBRACE; /* Terminator not found */
EXIT:
*ptrptr = ptr;
return rc;
}
/*************************************************
* Match and substitute *
*************************************************/
/* This function applies a compiled re to a subject string and creates a new
string with substitutions. The first 7 arguments are the same as for
pcre2_match(). Either string length may be PCRE2_ZERO_TERMINATED.
Arguments:
code points to the compiled expression
subject points to the subject string
length length of subject string (may contain binary zeros)
start_offset where to start in the subject string
options option bits
match_data points to a match_data block, or is NULL
context points a PCRE2 context
replacement points to the replacement string
rlength length of replacement string
buffer where to put the substituted string
blength points to length of buffer; updated to length of string
Returns: >= 0 number of substitutions made
< 0 an error code
PCRE2_ERROR_BADREPLACEMENT means invalid use of $
*/
/* This macro checks for space in the buffer before copying into it. On
overflow, either give an error immediately, or keep on, accumulating the
length. */
#define CHECKMEMCPY(from,length) \
if (!overflowed && lengthleft < length) \
{ \
if ((suboptions & PCRE2_SUBSTITUTE_OVERFLOW_LENGTH) == 0) goto NOROOM; \
overflowed = TRUE; \
extra_needed = length - lengthleft; \
} \
else if (overflowed) \
{ \
extra_needed += length; \
} \
else \
{ \
memcpy(buffer + buff_offset, from, CU2BYTES(length)); \
buff_offset += length; \
lengthleft -= length; \
}
/* Here's the function */
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_substitute(const pcre2_code *code, PCRE2_SPTR subject, PCRE2_SIZE length,
PCRE2_SIZE start_offset, uint32_t options, pcre2_match_data *match_data,
pcre2_match_context *mcontext, PCRE2_SPTR replacement, PCRE2_SIZE rlength,
PCRE2_UCHAR *buffer, PCRE2_SIZE *blength)
{
int rc;
int subs;
int forcecase = 0;
int forcecasereset = 0;
uint32_t ovector_count;
uint32_t goptions = 0;
uint32_t suboptions;
BOOL match_data_created = FALSE;
BOOL literal = FALSE;
BOOL overflowed = FALSE;
#ifdef SUPPORT_UNICODE
BOOL utf = (code->overall_options & PCRE2_UTF) != 0;
#endif
PCRE2_UCHAR temp[6];
PCRE2_SPTR ptr;
PCRE2_SPTR repend;
PCRE2_SIZE extra_needed = 0;
PCRE2_SIZE buff_offset, buff_length, lengthleft, fraglength;
PCRE2_SIZE *ovector;
buff_offset = 0;
lengthleft = buff_length = *blength;
*blength = PCRE2_UNSET;
/* Partial matching is not valid. */
if ((options & (PCRE2_PARTIAL_HARD|PCRE2_PARTIAL_SOFT)) != 0)
return PCRE2_ERROR_BADOPTION;
/* If no match data block is provided, create one. */
if (match_data == NULL)
{
pcre2_general_context *gcontext = (mcontext == NULL)?
(pcre2_general_context *)code :
(pcre2_general_context *)mcontext;
match_data = pcre2_match_data_create_from_pattern(code, gcontext);
if (match_data == NULL) return PCRE2_ERROR_NOMEMORY;
match_data_created = TRUE;
}
ovector = pcre2_get_ovector_pointer(match_data);
ovector_count = pcre2_get_ovector_count(match_data);
/* Find lengths of zero-terminated strings and the end of the replacement. */
if (length == PCRE2_ZERO_TERMINATED) length = PRIV(strlen)(subject);
if (rlength == PCRE2_ZERO_TERMINATED) rlength = PRIV(strlen)(replacement);
repend = replacement + rlength;
/* Check UTF replacement string if necessary. */
#ifdef SUPPORT_UNICODE
if (utf && (options & PCRE2_NO_UTF_CHECK) == 0)
{
rc = PRIV(valid_utf)(replacement, rlength, &(match_data->rightchar));
if (rc != 0)
{
match_data->leftchar = 0;
goto EXIT;
}
}
#endif /* SUPPORT_UNICODE */
/* Save the substitute options and remove them from the match options. */
suboptions = options & SUBSTITUTE_OPTIONS;
options &= ~SUBSTITUTE_OPTIONS;
/* Copy up to the start offset */
CHECKMEMCPY(subject, start_offset);
/* Loop for global substituting. */
subs = 0;
do
{
PCRE2_SPTR ptrstack[PTR_STACK_SIZE];
uint32_t ptrstackptr = 0;
rc = pcre2_match(code, subject, length, start_offset, options|goptions,
match_data, mcontext);
#ifdef SUPPORT_UNICODE
if (utf) options |= PCRE2_NO_UTF_CHECK; /* Only need to check once */
#endif
/* Any error other than no match returns the error code. No match when not
doing the special after-empty-match global rematch, or when at the end of the
subject, breaks the global loop. Otherwise, advance the starting point by one
character, copying it to the output, and try again. */
if (rc < 0)
{
PCRE2_SIZE save_start;
if (rc != PCRE2_ERROR_NOMATCH) goto EXIT;
if (goptions == 0 || start_offset >= length) break;
/* Advance by one code point. Then, if CRLF is a valid newline sequence and
we have advanced into the middle of it, advance one more code point. In
other words, do not start in the middle of CRLF, even if CR and LF on their
own are valid newlines. */
save_start = start_offset++;
if (subject[start_offset-1] == CHAR_CR &&
code->newline_convention != PCRE2_NEWLINE_CR &&
code->newline_convention != PCRE2_NEWLINE_LF &&
start_offset < length &&
subject[start_offset] == CHAR_LF)
start_offset++;
/* Otherwise, in UTF mode, advance past any secondary code points. */
else if ((code->overall_options & PCRE2_UTF) != 0)
{
#if PCRE2_CODE_UNIT_WIDTH == 8
while (start_offset < length && (subject[start_offset] & 0xc0) == 0x80)
start_offset++;
#elif PCRE2_CODE_UNIT_WIDTH == 16
while (start_offset < length &&
(subject[start_offset] & 0xfc00) == 0xdc00)
start_offset++;
#endif
}
/* Copy what we have advanced past, reset the special global options, and
continue to the next match. */
fraglength = start_offset - save_start;
CHECKMEMCPY(subject + save_start, fraglength);
goptions = 0;
continue;
}
/* Handle a successful match. Matches that use \K to end before they start
are not supported. */
if (ovector[1] < ovector[0])
{
rc = PCRE2_ERROR_BADSUBSPATTERN;
goto EXIT;
}
/* Count substitutions with a paranoid check for integer overflow; surely no
real call to this function would ever hit this! */
if (subs == INT_MAX)
{
rc = PCRE2_ERROR_TOOMANYREPLACE;
goto EXIT;
}
subs++;
/* Copy the text leading up to the match. */
if (rc == 0) rc = ovector_count;
fraglength = ovector[0] - start_offset;
CHECKMEMCPY(subject + start_offset, fraglength);
/* Process the replacement string. Literal mode is set by \Q, but only in
extended mode when backslashes are being interpreted. In extended mode we
must handle nested substrings that are to be reprocessed. */
ptr = replacement;
for (;;)
{
uint32_t ch;
unsigned int chlen;
/* If at the end of a nested substring, pop the stack. */
if (ptr >= repend)
{
if (ptrstackptr <= 0) break; /* End of replacement string */
repend = ptrstack[--ptrstackptr];
ptr = ptrstack[--ptrstackptr];
continue;
}
/* Handle the next character */
if (literal)
{
if (ptr[0] == CHAR_BACKSLASH && ptr < repend - 1 && ptr[1] == CHAR_E)
{
literal = FALSE;
ptr += 2;
continue;
}
goto LOADLITERAL;
}
/* Not in literal mode. */
if (*ptr == CHAR_DOLLAR_SIGN)
{
int group, n;
uint32_t special = 0;
BOOL inparens;
BOOL star;
PCRE2_SIZE sublength;
PCRE2_SPTR text1_start = NULL;
PCRE2_SPTR text1_end = NULL;
PCRE2_SPTR text2_start = NULL;
PCRE2_SPTR text2_end = NULL;
PCRE2_UCHAR next;
PCRE2_UCHAR name[33];
if (++ptr >= repend) goto BAD;
if ((next = *ptr) == CHAR_DOLLAR_SIGN) goto LOADLITERAL;
group = -1;
n = 0;
inparens = FALSE;
star = FALSE;
if (next == CHAR_LEFT_CURLY_BRACKET)
{
if (++ptr >= repend) goto BAD;
next = *ptr;
inparens = TRUE;
}
if (next == CHAR_ASTERISK)
{
if (++ptr >= repend) goto BAD;
next = *ptr;
star = TRUE;
}
if (!star && next >= CHAR_0 && next <= CHAR_9)
{
group = next - CHAR_0;
while (++ptr < repend)
{
next = *ptr;
if (next < CHAR_0 || next > CHAR_9) break;
group = group * 10 + next - CHAR_0;
/* A check for a number greater than the hightest captured group
is sufficient here; no need for a separate overflow check. If unknown
groups are to be treated as unset, just skip over any remaining
digits and carry on. */
if (group > code->top_bracket)
{
if ((suboptions & PCRE2_SUBSTITUTE_UNKNOWN_UNSET) != 0)
{
while (++ptr < repend && *ptr >= CHAR_0 && *ptr <= CHAR_9);
break;
}
else
{
rc = PCRE2_ERROR_NOSUBSTRING;
goto PTREXIT;
}
}
}
}
else
{
const uint8_t *ctypes = code->tables + ctypes_offset;
while (MAX_255(next) && (ctypes[next] & ctype_word) != 0)
{
name[n++] = next;
if (n > 32) goto BAD;
if (++ptr >= repend) break;
next = *ptr;
}
if (n == 0) goto BAD;
name[n] = 0;
}
/* In extended mode we recognize ${name:+set text:unset text} and
${name:-default text}. */
if (inparens)
{
if ((suboptions & PCRE2_SUBSTITUTE_EXTENDED) != 0 &&
!star && ptr < repend - 2 && next == CHAR_COLON)
{
special = *(++ptr);
if (special != CHAR_PLUS && special != CHAR_MINUS)
{
rc = PCRE2_ERROR_BADSUBSTITUTION;
goto PTREXIT;
}
text1_start = ++ptr;
rc = find_text_end(code, &ptr, repend, special == CHAR_MINUS);
if (rc != 0) goto PTREXIT;
text1_end = ptr;
if (special == CHAR_PLUS && *ptr == CHAR_COLON)
{
text2_start = ++ptr;
rc = find_text_end(code, &ptr, repend, TRUE);
if (rc != 0) goto PTREXIT;
text2_end = ptr;
}
}
else
{
if (ptr >= repend || *ptr != CHAR_RIGHT_CURLY_BRACKET)
{
rc = PCRE2_ERROR_REPMISSINGBRACE;
goto PTREXIT;
}
}
ptr++;
}
/* Have found a syntactically correct group number or name, or *name.
Only *MARK is currently recognized. */
if (star)
{
if (PRIV(strcmp_c8)(name, STRING_MARK) == 0)
{
PCRE2_SPTR mark = pcre2_get_mark(match_data);
if (mark != NULL)
{
PCRE2_SPTR mark_start = mark;
while (*mark != 0) mark++;
fraglength = mark - mark_start;
CHECKMEMCPY(mark_start, fraglength);
}
}
else goto BAD;
}
/* Substitute the contents of a group. We don't use substring_copy
functions any more, in order to support case forcing. */
else
{
PCRE2_SPTR subptr, subptrend;
/* Find a number for a named group. In case there are duplicate names,
search for the first one that is set. If the name is not found when
PCRE2_SUBSTITUTE_UNKNOWN_EMPTY is set, set the group number to a
non-existent group. */
if (group < 0)
{
PCRE2_SPTR first, last, entry;
rc = pcre2_substring_nametable_scan(code, name, &first, &last);
if (rc == PCRE2_ERROR_NOSUBSTRING &&
(suboptions & PCRE2_SUBSTITUTE_UNKNOWN_UNSET) != 0)
{
group = code->top_bracket + 1;
}
else
{
if (rc < 0) goto PTREXIT;
for (entry = first; entry <= last; entry += rc)
{
uint32_t ng = GET2(entry, 0);
if (ng < ovector_count)
{
if (group < 0) group = ng; /* First in ovector */
if (ovector[ng*2] != PCRE2_UNSET)
{
group = ng; /* First that is set */
break;
}
}
}
/* If group is still negative, it means we did not find a group
that is in the ovector. Just set the first group. */
if (group < 0) group = GET2(first, 0);
}
}
/* We now have a group that is identified by number. Find the length of
the captured string. If a group in a non-special substitution is unset
when PCRE2_SUBSTITUTE_UNSET_EMPTY is set, substitute nothing. */
rc = pcre2_substring_length_bynumber(match_data, group, &sublength);
if (rc < 0)
{
if (rc == PCRE2_ERROR_NOSUBSTRING &&
(suboptions & PCRE2_SUBSTITUTE_UNKNOWN_UNSET) != 0)
{
rc = PCRE2_ERROR_UNSET;
}
if (rc != PCRE2_ERROR_UNSET) goto PTREXIT; /* Non-unset errors */
if (special == 0) /* Plain substitution */
{
if ((suboptions & PCRE2_SUBSTITUTE_UNSET_EMPTY) != 0) continue;
goto PTREXIT; /* Else error */
}
}
/* If special is '+' we have a 'set' and possibly an 'unset' text,
both of which are reprocessed when used. If special is '-' we have a
default text for when the group is unset; it must be reprocessed. */
if (special != 0)
{
if (special == CHAR_MINUS)
{
if (rc == 0) goto LITERAL_SUBSTITUTE;
text2_start = text1_start;
text2_end = text1_end;
}
if (ptrstackptr >= PTR_STACK_SIZE) goto BAD;
ptrstack[ptrstackptr++] = ptr;
ptrstack[ptrstackptr++] = repend;
if (rc == 0)
{
ptr = text1_start;
repend = text1_end;
}
else
{
ptr = text2_start;
repend = text2_end;
}
continue;
}
/* Otherwise we have a literal substitution of a group's contents. */
LITERAL_SUBSTITUTE:
subptr = subject + ovector[group*2];
subptrend = subject + ovector[group*2 + 1];
/* Substitute a literal string, possibly forcing alphabetic case. */
while (subptr < subptrend)
{
GETCHARINCTEST(ch, subptr);
if (forcecase != 0)
{
#ifdef SUPPORT_UNICODE
if (utf)
{
uint32_t type = UCD_CHARTYPE(ch);
if (PRIV(ucp_gentype)[type] == ucp_L &&
type != ((forcecase > 0)? ucp_Lu : ucp_Ll))
ch = UCD_OTHERCASE(ch);
}
else
#endif
{
if (((code->tables + cbits_offset +
((forcecase > 0)? cbit_upper:cbit_lower)
)[ch/8] & (1 << (ch%8))) == 0)
ch = (code->tables + fcc_offset)[ch];
}
forcecase = forcecasereset;
}
#ifdef SUPPORT_UNICODE
if (utf) chlen = PRIV(ord2utf)(ch, temp); else
#endif
{
temp[0] = ch;
chlen = 1;
}
CHECKMEMCPY(temp, chlen);
}
}
}
/* Handle an escape sequence in extended mode. We can use check_escape()
to process \Q, \E, \c, \o, \x and \ followed by non-alphanumerics, but
the case-forcing escapes are not supported in pcre2_compile() so must be
recognized here. */
else if ((suboptions & PCRE2_SUBSTITUTE_EXTENDED) != 0 &&
*ptr == CHAR_BACKSLASH)
{
int errorcode = 0;
if (ptr < repend - 1) switch (ptr[1])
{
case CHAR_L:
forcecase = forcecasereset = -1;
ptr += 2;
continue;
case CHAR_l:
forcecase = -1;
forcecasereset = 0;
ptr += 2;
continue;
case CHAR_U:
forcecase = forcecasereset = 1;
ptr += 2;
continue;
case CHAR_u:
forcecase = 1;
forcecasereset = 0;
ptr += 2;
continue;
default:
break;
}
rc = PRIV(check_escape)(&ptr, repend, &ch, &errorcode,
code->overall_options, FALSE, NULL);
if (errorcode != 0) goto BADESCAPE;
ptr++;
switch(rc)
{
case ESC_E:
forcecase = forcecasereset = 0;
continue;
case ESC_Q:
literal = TRUE;
continue;
case 0: /* Data character */
goto LITERAL;
default:
goto BADESCAPE;
}
}
/* Handle a literal code unit */
else
{
LOADLITERAL:
GETCHARINCTEST(ch, ptr); /* Get character value, increment pointer */
LITERAL:
if (forcecase != 0)
{
#ifdef SUPPORT_UNICODE
if (utf)
{
uint32_t type = UCD_CHARTYPE(ch);
if (PRIV(ucp_gentype)[type] == ucp_L &&
type != ((forcecase > 0)? ucp_Lu : ucp_Ll))
ch = UCD_OTHERCASE(ch);
}
else
#endif
{
if (((code->tables + cbits_offset +
((forcecase > 0)? cbit_upper:cbit_lower)
)[ch/8] & (1 << (ch%8))) == 0)
ch = (code->tables + fcc_offset)[ch];
}
forcecase = forcecasereset;
}
#ifdef SUPPORT_UNICODE
if (utf) chlen = PRIV(ord2utf)(ch, temp); else
#endif
{
temp[0] = ch;
chlen = 1;
}
CHECKMEMCPY(temp, chlen);
} /* End handling a literal code unit */
} /* End of loop for scanning the replacement. */
/* The replacement has been copied to the output. Update the start offset to
point to the rest of the subject string. If we matched an empty string,
do the magic for global matches. */
start_offset = ovector[1];
goptions = (ovector[0] != ovector[1])? 0 :
PCRE2_ANCHORED|PCRE2_NOTEMPTY_ATSTART;
} while ((suboptions & PCRE2_SUBSTITUTE_GLOBAL) != 0); /* Repeat "do" loop */
/* Copy the rest of the subject. */
fraglength = length - start_offset;
CHECKMEMCPY(subject + start_offset, fraglength);
temp[0] = 0;
CHECKMEMCPY(temp , 1);
/* If overflowed is set it means the PCRE2_SUBSTITUTE_OVERFLOW_LENGTH is set,
and matching has carried on after a full buffer, in order to compute the length
needed. Otherwise, an overflow generates an immediate error return. */
if (overflowed)
{
rc = PCRE2_ERROR_NOMEMORY;
*blength = buff_length + extra_needed;
}
/* After a successful execution, return the number of substitutions and set the
length of buffer used, excluding the trailing zero. */
else
{
rc = subs;
*blength = buff_offset - 1;
}
EXIT:
if (match_data_created) pcre2_match_data_free(match_data);
else match_data->rc = rc;
return rc;
NOROOM:
rc = PCRE2_ERROR_NOMEMORY;
goto EXIT;
BAD:
rc = PCRE2_ERROR_BADREPLACEMENT;
goto PTREXIT;
BADESCAPE:
rc = PCRE2_ERROR_BADREPESCAPE;
PTREXIT:
*blength = (PCRE2_SIZE)(ptr - replacement);
goto EXIT;
}
/* End of pcre2_substitute.c */

2
pcre2-10.20/src/pcre2_substring.c → pcre2-10.21/src/pcre2_substring.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without

358
pcre2-10.20/src/pcre2_tables.c → pcre2-10.21/src/pcre2_tables.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -227,6 +227,8 @@ version. Like all other character and string literals that are compared against
the regular expression pattern, we must use STR_ macros instead of literal
strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Ahom0 STR_A STR_h STR_o STR_m "\0"
#define STRING_Anatolian_Hieroglyphs0 STR_A STR_n STR_a STR_t STR_o STR_l STR_i STR_a STR_n STR_UNDERSCORE STR_H STR_i STR_e STR_r STR_o STR_g STR_l STR_y STR_p STR_h STR_s "\0"
#define STRING_Any0 STR_A STR_n STR_y "\0"
#define STRING_Arabic0 STR_A STR_r STR_a STR_b STR_i STR_c "\0"
#define STRING_Armenian0 STR_A STR_r STR_m STR_e STR_n STR_i STR_a STR_n "\0"
@ -274,6 +276,7 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Han0 STR_H STR_a STR_n "\0"
#define STRING_Hangul0 STR_H STR_a STR_n STR_g STR_u STR_l "\0"
#define STRING_Hanunoo0 STR_H STR_a STR_n STR_u STR_n STR_o STR_o "\0"
#define STRING_Hatran0 STR_H STR_a STR_t STR_r STR_a STR_n "\0"
#define STRING_Hebrew0 STR_H STR_e STR_b STR_r STR_e STR_w "\0"
#define STRING_Hiragana0 STR_H STR_i STR_r STR_a STR_g STR_a STR_n STR_a "\0"
#define STRING_Imperial_Aramaic0 STR_I STR_m STR_p STR_e STR_r STR_i STR_a STR_l STR_UNDERSCORE STR_A STR_r STR_a STR_m STR_a STR_i STR_c "\0"
@ -321,6 +324,7 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Modi0 STR_M STR_o STR_d STR_i "\0"
#define STRING_Mongolian0 STR_M STR_o STR_n STR_g STR_o STR_l STR_i STR_a STR_n "\0"
#define STRING_Mro0 STR_M STR_r STR_o "\0"
#define STRING_Multani0 STR_M STR_u STR_l STR_t STR_a STR_n STR_i "\0"
#define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0"
#define STRING_N0 STR_N "\0"
#define STRING_Nabataean0 STR_N STR_a STR_b STR_a STR_t STR_a STR_e STR_a STR_n "\0"
@ -331,6 +335,7 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_No0 STR_N STR_o "\0"
#define STRING_Ogham0 STR_O STR_g STR_h STR_a STR_m "\0"
#define STRING_Ol_Chiki0 STR_O STR_l STR_UNDERSCORE STR_C STR_h STR_i STR_k STR_i "\0"
#define STRING_Old_Hungarian0 STR_O STR_l STR_d STR_UNDERSCORE STR_H STR_u STR_n STR_g STR_a STR_r STR_i STR_a STR_n "\0"
#define STRING_Old_Italic0 STR_O STR_l STR_d STR_UNDERSCORE STR_I STR_t STR_a STR_l STR_i STR_c "\0"
#define STRING_Old_North_Arabian0 STR_O STR_l STR_d STR_UNDERSCORE STR_N STR_o STR_r STR_t STR_h STR_UNDERSCORE STR_A STR_r STR_a STR_b STR_i STR_a STR_n "\0"
#define STRING_Old_Permic0 STR_O STR_l STR_d STR_UNDERSCORE STR_P STR_e STR_r STR_m STR_i STR_c "\0"
@ -362,6 +367,7 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Sharada0 STR_S STR_h STR_a STR_r STR_a STR_d STR_a "\0"
#define STRING_Shavian0 STR_S STR_h STR_a STR_v STR_i STR_a STR_n "\0"
#define STRING_Siddham0 STR_S STR_i STR_d STR_d STR_h STR_a STR_m "\0"
#define STRING_SignWriting0 STR_S STR_i STR_g STR_n STR_W STR_r STR_i STR_t STR_i STR_n STR_g "\0"
#define STRING_Sinhala0 STR_S STR_i STR_n STR_h STR_a STR_l STR_a "\0"
#define STRING_Sk0 STR_S STR_k "\0"
#define STRING_Sm0 STR_S STR_m "\0"
@ -398,6 +404,8 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Zs0 STR_Z STR_s "\0"
const char PRIV(utt_names)[] =
STRING_Ahom0
STRING_Anatolian_Hieroglyphs0
STRING_Any0
STRING_Arabic0
STRING_Armenian0
@ -445,6 +453,7 @@ const char PRIV(utt_names)[] =
STRING_Han0
STRING_Hangul0
STRING_Hanunoo0
STRING_Hatran0
STRING_Hebrew0
STRING_Hiragana0
STRING_Imperial_Aramaic0
@ -492,6 +501,7 @@ const char PRIV(utt_names)[] =
STRING_Modi0
STRING_Mongolian0
STRING_Mro0
STRING_Multani0
STRING_Myanmar0
STRING_N0
STRING_Nabataean0
@ -502,6 +512,7 @@ const char PRIV(utt_names)[] =
STRING_No0
STRING_Ogham0
STRING_Ol_Chiki0
STRING_Old_Hungarian0
STRING_Old_Italic0
STRING_Old_North_Arabian0
STRING_Old_Permic0
@ -533,6 +544,7 @@ const char PRIV(utt_names)[] =
STRING_Sharada0
STRING_Shavian0
STRING_Siddham0
STRING_SignWriting0
STRING_Sinhala0
STRING_Sk0
STRING_Sm0
@ -569,175 +581,181 @@ const char PRIV(utt_names)[] =
STRING_Zs0;
const ucp_type_table PRIV(utt)[] = {
{ 0, PT_ANY, 0 },
{ 4, PT_SC, ucp_Arabic },
{ 11, PT_SC, ucp_Armenian },
{ 20, PT_SC, ucp_Avestan },
{ 28, PT_SC, ucp_Balinese },
{ 37, PT_SC, ucp_Bamum },
{ 43, PT_SC, ucp_Bassa_Vah },
{ 53, PT_SC, ucp_Batak },
{ 59, PT_SC, ucp_Bengali },
{ 67, PT_SC, ucp_Bopomofo },
{ 76, PT_SC, ucp_Brahmi },
{ 83, PT_SC, ucp_Braille },
{ 91, PT_SC, ucp_Buginese },
{ 100, PT_SC, ucp_Buhid },
{ 106, PT_GC, ucp_C },
{ 108, PT_SC, ucp_Canadian_Aboriginal },
{ 128, PT_SC, ucp_Carian },
{ 135, PT_SC, ucp_Caucasian_Albanian },
{ 154, PT_PC, ucp_Cc },
{ 157, PT_PC, ucp_Cf },
{ 160, PT_SC, ucp_Chakma },
{ 167, PT_SC, ucp_Cham },
{ 172, PT_SC, ucp_Cherokee },
{ 181, PT_PC, ucp_Cn },
{ 184, PT_PC, ucp_Co },
{ 187, PT_SC, ucp_Common },
{ 194, PT_SC, ucp_Coptic },
{ 201, PT_PC, ucp_Cs },
{ 204, PT_SC, ucp_Cuneiform },
{ 214, PT_SC, ucp_Cypriot },
{ 222, PT_SC, ucp_Cyrillic },
{ 231, PT_SC, ucp_Deseret },
{ 239, PT_SC, ucp_Devanagari },
{ 250, PT_SC, ucp_Duployan },
{ 259, PT_SC, ucp_Egyptian_Hieroglyphs },
{ 280, PT_SC, ucp_Elbasan },
{ 288, PT_SC, ucp_Ethiopic },
{ 297, PT_SC, ucp_Georgian },
{ 306, PT_SC, ucp_Glagolitic },
{ 317, PT_SC, ucp_Gothic },
{ 324, PT_SC, ucp_Grantha },
{ 332, PT_SC, ucp_Greek },
{ 338, PT_SC, ucp_Gujarati },
{ 347, PT_SC, ucp_Gurmukhi },
{ 356, PT_SC, ucp_Han },
{ 360, PT_SC, ucp_Hangul },
{ 367, PT_SC, ucp_Hanunoo },
{ 375, PT_SC, ucp_Hebrew },
{ 382, PT_SC, ucp_Hiragana },
{ 391, PT_SC, ucp_Imperial_Aramaic },
{ 408, PT_SC, ucp_Inherited },
{ 418, PT_SC, ucp_Inscriptional_Pahlavi },
{ 440, PT_SC, ucp_Inscriptional_Parthian },
{ 463, PT_SC, ucp_Javanese },
{ 472, PT_SC, ucp_Kaithi },
{ 479, PT_SC, ucp_Kannada },
{ 487, PT_SC, ucp_Katakana },
{ 496, PT_SC, ucp_Kayah_Li },
{ 505, PT_SC, ucp_Kharoshthi },
{ 516, PT_SC, ucp_Khmer },
{ 522, PT_SC, ucp_Khojki },
{ 529, PT_SC, ucp_Khudawadi },
{ 539, PT_GC, ucp_L },
{ 541, PT_LAMP, 0 },
{ 544, PT_SC, ucp_Lao },
{ 548, PT_SC, ucp_Latin },
{ 554, PT_SC, ucp_Lepcha },
{ 561, PT_SC, ucp_Limbu },
{ 567, PT_SC, ucp_Linear_A },
{ 576, PT_SC, ucp_Linear_B },
{ 585, PT_SC, ucp_Lisu },
{ 590, PT_PC, ucp_Ll },
{ 593, PT_PC, ucp_Lm },
{ 596, PT_PC, ucp_Lo },
{ 599, PT_PC, ucp_Lt },
{ 602, PT_PC, ucp_Lu },
{ 605, PT_SC, ucp_Lycian },
{ 612, PT_SC, ucp_Lydian },
{ 619, PT_GC, ucp_M },
{ 621, PT_SC, ucp_Mahajani },
{ 630, PT_SC, ucp_Malayalam },
{ 640, PT_SC, ucp_Mandaic },
{ 648, PT_SC, ucp_Manichaean },
{ 659, PT_PC, ucp_Mc },
{ 662, PT_PC, ucp_Me },
{ 665, PT_SC, ucp_Meetei_Mayek },
{ 678, PT_SC, ucp_Mende_Kikakui },
{ 692, PT_SC, ucp_Meroitic_Cursive },
{ 709, PT_SC, ucp_Meroitic_Hieroglyphs },
{ 730, PT_SC, ucp_Miao },
{ 735, PT_PC, ucp_Mn },
{ 738, PT_SC, ucp_Modi },
{ 743, PT_SC, ucp_Mongolian },
{ 753, PT_SC, ucp_Mro },
{ 757, PT_SC, ucp_Myanmar },
{ 765, PT_GC, ucp_N },
{ 767, PT_SC, ucp_Nabataean },
{ 777, PT_PC, ucp_Nd },
{ 780, PT_SC, ucp_New_Tai_Lue },
{ 792, PT_SC, ucp_Nko },
{ 796, PT_PC, ucp_Nl },
{ 799, PT_PC, ucp_No },
{ 802, PT_SC, ucp_Ogham },
{ 808, PT_SC, ucp_Ol_Chiki },
{ 817, PT_SC, ucp_Old_Italic },
{ 828, PT_SC, ucp_Old_North_Arabian },
{ 846, PT_SC, ucp_Old_Permic },
{ 857, PT_SC, ucp_Old_Persian },
{ 869, PT_SC, ucp_Old_South_Arabian },
{ 887, PT_SC, ucp_Old_Turkic },
{ 898, PT_SC, ucp_Oriya },
{ 904, PT_SC, ucp_Osmanya },
{ 912, PT_GC, ucp_P },
{ 914, PT_SC, ucp_Pahawh_Hmong },
{ 927, PT_SC, ucp_Palmyrene },
{ 937, PT_SC, ucp_Pau_Cin_Hau },
{ 949, PT_PC, ucp_Pc },
{ 952, PT_PC, ucp_Pd },
{ 955, PT_PC, ucp_Pe },
{ 958, PT_PC, ucp_Pf },
{ 961, PT_SC, ucp_Phags_Pa },
{ 970, PT_SC, ucp_Phoenician },
{ 981, PT_PC, ucp_Pi },
{ 984, PT_PC, ucp_Po },
{ 987, PT_PC, ucp_Ps },
{ 990, PT_SC, ucp_Psalter_Pahlavi },
{ 1006, PT_SC, ucp_Rejang },
{ 1013, PT_SC, ucp_Runic },
{ 1019, PT_GC, ucp_S },
{ 1021, PT_SC, ucp_Samaritan },
{ 1031, PT_SC, ucp_Saurashtra },
{ 1042, PT_PC, ucp_Sc },
{ 1045, PT_SC, ucp_Sharada },
{ 1053, PT_SC, ucp_Shavian },
{ 1061, PT_SC, ucp_Siddham },
{ 1069, PT_SC, ucp_Sinhala },
{ 1077, PT_PC, ucp_Sk },
{ 1080, PT_PC, ucp_Sm },
{ 1083, PT_PC, ucp_So },
{ 1086, PT_SC, ucp_Sora_Sompeng },
{ 1099, PT_SC, ucp_Sundanese },
{ 1109, PT_SC, ucp_Syloti_Nagri },
{ 1122, PT_SC, ucp_Syriac },
{ 1129, PT_SC, ucp_Tagalog },
{ 1137, PT_SC, ucp_Tagbanwa },
{ 1146, PT_SC, ucp_Tai_Le },
{ 1153, PT_SC, ucp_Tai_Tham },
{ 1162, PT_SC, ucp_Tai_Viet },
{ 1171, PT_SC, ucp_Takri },
{ 1177, PT_SC, ucp_Tamil },
{ 1183, PT_SC, ucp_Telugu },
{ 1190, PT_SC, ucp_Thaana },
{ 1197, PT_SC, ucp_Thai },
{ 1202, PT_SC, ucp_Tibetan },
{ 1210, PT_SC, ucp_Tifinagh },
{ 1219, PT_SC, ucp_Tirhuta },
{ 1227, PT_SC, ucp_Ugaritic },
{ 1236, PT_SC, ucp_Vai },
{ 1240, PT_SC, ucp_Warang_Citi },
{ 1252, PT_ALNUM, 0 },
{ 1256, PT_PXSPACE, 0 },
{ 1260, PT_SPACE, 0 },
{ 1264, PT_UCNC, 0 },
{ 1268, PT_WORD, 0 },
{ 1272, PT_SC, ucp_Yi },
{ 1275, PT_GC, ucp_Z },
{ 1277, PT_PC, ucp_Zl },
{ 1280, PT_PC, ucp_Zp },
{ 1283, PT_PC, ucp_Zs }
{ 0, PT_SC, ucp_Ahom },
{ 5, PT_SC, ucp_Anatolian_Hieroglyphs },
{ 27, PT_ANY, 0 },
{ 31, PT_SC, ucp_Arabic },
{ 38, PT_SC, ucp_Armenian },
{ 47, PT_SC, ucp_Avestan },
{ 55, PT_SC, ucp_Balinese },
{ 64, PT_SC, ucp_Bamum },
{ 70, PT_SC, ucp_Bassa_Vah },
{ 80, PT_SC, ucp_Batak },
{ 86, PT_SC, ucp_Bengali },
{ 94, PT_SC, ucp_Bopomofo },
{ 103, PT_SC, ucp_Brahmi },
{ 110, PT_SC, ucp_Braille },
{ 118, PT_SC, ucp_Buginese },
{ 127, PT_SC, ucp_Buhid },
{ 133, PT_GC, ucp_C },
{ 135, PT_SC, ucp_Canadian_Aboriginal },
{ 155, PT_SC, ucp_Carian },
{ 162, PT_SC, ucp_Caucasian_Albanian },
{ 181, PT_PC, ucp_Cc },
{ 184, PT_PC, ucp_Cf },
{ 187, PT_SC, ucp_Chakma },
{ 194, PT_SC, ucp_Cham },
{ 199, PT_SC, ucp_Cherokee },
{ 208, PT_PC, ucp_Cn },
{ 211, PT_PC, ucp_Co },
{ 214, PT_SC, ucp_Common },
{ 221, PT_SC, ucp_Coptic },
{ 228, PT_PC, ucp_Cs },
{ 231, PT_SC, ucp_Cuneiform },
{ 241, PT_SC, ucp_Cypriot },
{ 249, PT_SC, ucp_Cyrillic },
{ 258, PT_SC, ucp_Deseret },
{ 266, PT_SC, ucp_Devanagari },
{ 277, PT_SC, ucp_Duployan },
{ 286, PT_SC, ucp_Egyptian_Hieroglyphs },
{ 307, PT_SC, ucp_Elbasan },
{ 315, PT_SC, ucp_Ethiopic },
{ 324, PT_SC, ucp_Georgian },
{ 333, PT_SC, ucp_Glagolitic },
{ 344, PT_SC, ucp_Gothic },
{ 351, PT_SC, ucp_Grantha },
{ 359, PT_SC, ucp_Greek },
{ 365, PT_SC, ucp_Gujarati },
{ 374, PT_SC, ucp_Gurmukhi },
{ 383, PT_SC, ucp_Han },
{ 387, PT_SC, ucp_Hangul },
{ 394, PT_SC, ucp_Hanunoo },
{ 402, PT_SC, ucp_Hatran },
{ 409, PT_SC, ucp_Hebrew },
{ 416, PT_SC, ucp_Hiragana },
{ 425, PT_SC, ucp_Imperial_Aramaic },
{ 442, PT_SC, ucp_Inherited },
{ 452, PT_SC, ucp_Inscriptional_Pahlavi },
{ 474, PT_SC, ucp_Inscriptional_Parthian },
{ 497, PT_SC, ucp_Javanese },
{ 506, PT_SC, ucp_Kaithi },
{ 513, PT_SC, ucp_Kannada },
{ 521, PT_SC, ucp_Katakana },
{ 530, PT_SC, ucp_Kayah_Li },
{ 539, PT_SC, ucp_Kharoshthi },
{ 550, PT_SC, ucp_Khmer },
{ 556, PT_SC, ucp_Khojki },
{ 563, PT_SC, ucp_Khudawadi },
{ 573, PT_GC, ucp_L },
{ 575, PT_LAMP, 0 },
{ 578, PT_SC, ucp_Lao },
{ 582, PT_SC, ucp_Latin },
{ 588, PT_SC, ucp_Lepcha },
{ 595, PT_SC, ucp_Limbu },
{ 601, PT_SC, ucp_Linear_A },
{ 610, PT_SC, ucp_Linear_B },
{ 619, PT_SC, ucp_Lisu },
{ 624, PT_PC, ucp_Ll },
{ 627, PT_PC, ucp_Lm },
{ 630, PT_PC, ucp_Lo },
{ 633, PT_PC, ucp_Lt },
{ 636, PT_PC, ucp_Lu },
{ 639, PT_SC, ucp_Lycian },
{ 646, PT_SC, ucp_Lydian },
{ 653, PT_GC, ucp_M },
{ 655, PT_SC, ucp_Mahajani },
{ 664, PT_SC, ucp_Malayalam },
{ 674, PT_SC, ucp_Mandaic },
{ 682, PT_SC, ucp_Manichaean },
{ 693, PT_PC, ucp_Mc },
{ 696, PT_PC, ucp_Me },
{ 699, PT_SC, ucp_Meetei_Mayek },
{ 712, PT_SC, ucp_Mende_Kikakui },
{ 726, PT_SC, ucp_Meroitic_Cursive },
{ 743, PT_SC, ucp_Meroitic_Hieroglyphs },
{ 764, PT_SC, ucp_Miao },
{ 769, PT_PC, ucp_Mn },
{ 772, PT_SC, ucp_Modi },
{ 777, PT_SC, ucp_Mongolian },
{ 787, PT_SC, ucp_Mro },
{ 791, PT_SC, ucp_Multani },
{ 799, PT_SC, ucp_Myanmar },
{ 807, PT_GC, ucp_N },
{ 809, PT_SC, ucp_Nabataean },
{ 819, PT_PC, ucp_Nd },
{ 822, PT_SC, ucp_New_Tai_Lue },
{ 834, PT_SC, ucp_Nko },
{ 838, PT_PC, ucp_Nl },
{ 841, PT_PC, ucp_No },
{ 844, PT_SC, ucp_Ogham },
{ 850, PT_SC, ucp_Ol_Chiki },
{ 859, PT_SC, ucp_Old_Hungarian },
{ 873, PT_SC, ucp_Old_Italic },
{ 884, PT_SC, ucp_Old_North_Arabian },
{ 902, PT_SC, ucp_Old_Permic },
{ 913, PT_SC, ucp_Old_Persian },
{ 925, PT_SC, ucp_Old_South_Arabian },
{ 943, PT_SC, ucp_Old_Turkic },
{ 954, PT_SC, ucp_Oriya },
{ 960, PT_SC, ucp_Osmanya },
{ 968, PT_GC, ucp_P },
{ 970, PT_SC, ucp_Pahawh_Hmong },
{ 983, PT_SC, ucp_Palmyrene },
{ 993, PT_SC, ucp_Pau_Cin_Hau },
{ 1005, PT_PC, ucp_Pc },
{ 1008, PT_PC, ucp_Pd },
{ 1011, PT_PC, ucp_Pe },
{ 1014, PT_PC, ucp_Pf },
{ 1017, PT_SC, ucp_Phags_Pa },
{ 1026, PT_SC, ucp_Phoenician },
{ 1037, PT_PC, ucp_Pi },
{ 1040, PT_PC, ucp_Po },
{ 1043, PT_PC, ucp_Ps },
{ 1046, PT_SC, ucp_Psalter_Pahlavi },
{ 1062, PT_SC, ucp_Rejang },
{ 1069, PT_SC, ucp_Runic },
{ 1075, PT_GC, ucp_S },
{ 1077, PT_SC, ucp_Samaritan },
{ 1087, PT_SC, ucp_Saurashtra },
{ 1098, PT_PC, ucp_Sc },
{ 1101, PT_SC, ucp_Sharada },
{ 1109, PT_SC, ucp_Shavian },
{ 1117, PT_SC, ucp_Siddham },
{ 1125, PT_SC, ucp_SignWriting },
{ 1137, PT_SC, ucp_Sinhala },
{ 1145, PT_PC, ucp_Sk },
{ 1148, PT_PC, ucp_Sm },
{ 1151, PT_PC, ucp_So },
{ 1154, PT_SC, ucp_Sora_Sompeng },
{ 1167, PT_SC, ucp_Sundanese },
{ 1177, PT_SC, ucp_Syloti_Nagri },
{ 1190, PT_SC, ucp_Syriac },
{ 1197, PT_SC, ucp_Tagalog },
{ 1205, PT_SC, ucp_Tagbanwa },
{ 1214, PT_SC, ucp_Tai_Le },
{ 1221, PT_SC, ucp_Tai_Tham },
{ 1230, PT_SC, ucp_Tai_Viet },
{ 1239, PT_SC, ucp_Takri },
{ 1245, PT_SC, ucp_Tamil },
{ 1251, PT_SC, ucp_Telugu },
{ 1258, PT_SC, ucp_Thaana },
{ 1265, PT_SC, ucp_Thai },
{ 1270, PT_SC, ucp_Tibetan },
{ 1278, PT_SC, ucp_Tifinagh },
{ 1287, PT_SC, ucp_Tirhuta },
{ 1295, PT_SC, ucp_Ugaritic },
{ 1304, PT_SC, ucp_Vai },
{ 1308, PT_SC, ucp_Warang_Citi },
{ 1320, PT_ALNUM, 0 },
{ 1324, PT_PXSPACE, 0 },
{ 1328, PT_SPACE, 0 },
{ 1332, PT_UCNC, 0 },
{ 1336, PT_WORD, 0 },
{ 1340, PT_SC, ucp_Yi },
{ 1343, PT_GC, ucp_Z },
{ 1345, PT_PC, ucp_Zl },
{ 1348, PT_PC, ucp_Zp },
{ 1351, PT_PC, ucp_Zs }
};
const size_t PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table);

4520
pcre2-10.20/src/pcre2_ucd.c → pcre2-10.21/src/pcre2_ucd.c
View file

File diff suppressed because it is too large Load diff

11
pcre2-10.20/src/pcre2_ucp.h → pcre2-10.21/src/pcre2_ucp.h
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -253,7 +253,14 @@ enum {
ucp_Pau_Cin_Hau,
ucp_Siddham,
ucp_Tirhuta,
ucp_Warang_Citi
ucp_Warang_Citi,
/* New for Unicode 8.0.0: */
ucp_Ahom,
ucp_Anatolian_Hieroglyphs,
ucp_Hatran,
ucp_Multani,
ucp_Old_Hungarian,
ucp_SignWriting
};
#endif

11
pcre2-10.20/src/pcre2_valid_utf.c → pcre2-10.21/src/pcre2_valid_utf.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -131,11 +131,13 @@ PCRE2_ERROR_UTF8_ERR20 Isolated 0x80 byte (not within UTF-8 character)
PCRE2_ERROR_UTF8_ERR21 Byte with the illegal value 0xfe or 0xff
*/
for (p = string; length-- > 0; p++)
for (p = string; length > 0; p++)
{
register uint32_t ab, d;
c = *p;
length--;
if (c < 128) continue; /* ASCII character */
if (c < 0xc0) /* Isolated 10xx xxxx byte */
@ -324,9 +326,10 @@ PCRE2_ERROR_UTF16_ERR2 Invalid low surrogate
PCRE2_ERROR_UTF16_ERR3 Isolated low surrogate
*/
for (p = string; length-- > 0; p++)
for (p = string; length > 0; p++)
{
c = *p;
length--;
if ((c & 0xf800) != 0xd800)
{
@ -368,7 +371,7 @@ PCRE2_ERROR_UTF32_ERR1 Surrogate character
PCRE2_ERROR_UTF32_ERR2 Character > 0x10ffff
*/
for (p = string; length-- > 0; p++)
for (p = string; length > 0; length--, p++)
{
c = *p;
if ((c & 0xfffff800u) != 0xd800u)

4
pcre2-10.20/src/pcre2_xclass.c → pcre2-10.21/src/pcre2_xclass.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -247,7 +247,7 @@ while ((t = *data++) != XCL_END)
case PT_PXPUNCT:
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_P ||
(c < 256 && PRIV(ucp_gentype)[prop->chartype] == ucp_S)) == isprop)
(c < 128 && PRIV(ucp_gentype)[prop->chartype] == ucp_S)) == isprop)
return !negated;
break;

0
pcre2-10.20/src/pcre2demo.c → pcre2-10.21/src/pcre2demo.c
View file

20
pcre2-10.20/src/pcre2grep.c → pcre2-10.21/src/pcre2grep.c
View file

@ -13,7 +13,7 @@ distribution because other apparatus is needed to compile pcre2grep for z/OS.
The header can be found in the special z/OS distribution, which is available
from www.zaconsultants.net or from www.cbttape.org.
Copyright (c) 1997-2014 University of Cambridge
Copyright (c) 1997-2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -1691,9 +1691,13 @@ while (ptr < endptr)
if (filenames == FN_NOMATCH_ONLY) return 1;
/* If all we want is a yes/no answer, we can return immediately. */
if (quiet) return 0;
/* Just count if just counting is wanted. */
if (count_only) count++;
else if (count_only) count++;
/* When handling a binary file and binary-files==binary, the "binary"
variable will be set true (it's false in all other cases). In this
@ -1705,8 +1709,8 @@ while (ptr < endptr)
return 0;
}
/* If all we want is a file name, there is no need to scan any more lines
in the file. */
/* Likewise, if all we want is a file name, there is no need to scan any
more lines in the file. */
else if (filenames == FN_MATCH_ONLY)
{
@ -1714,10 +1718,6 @@ while (ptr < endptr)
return 0;
}
/* Likewise, if all we want is a yes/no answer. */
else if (quiet) return 0;
/* The --only-matching option prints just the substring that matched,
and/or one or more captured portions of it, as long as these strings are
not empty. The --file-offsets and --line-offsets options output offsets for
@ -2069,7 +2069,7 @@ if (filenames == FN_NOMATCH_ONLY)
/* Print the match count if wanted */
if (count_only)
if (count_only && !quiet)
{
if (count > 0 || !omit_zero_count)
{
@ -2421,7 +2421,7 @@ return options;
static char *
ordin(int n)
{
static char buffer[8];
static char buffer[14];
char *p = buffer;
sprintf(p, "%d", n);
while (*p != 0) p++;

47
pcre2-10.20/src/pcre2posix.c → pcre2-10.21/src/pcre2posix.c
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -106,7 +106,7 @@ static const int eint1[] = {
static const int eint2[] = {
30, REG_ECTYPE, /* unknown POSIX class name */
32, REG_INVARG, /* this version of PCRE does not have UTF or UCP support */
32, REG_INVARG, /* this version of PCRE2 does not have Unicode support */
37, REG_EESCAPE, /* PCRE2 does not support \L, \l, \N{name}, \U, or \u */
56, REG_INVARG, /* internal error: unknown newline setting */
};
@ -144,29 +144,23 @@ static const char *const pstring[] = {
PCRE2POSIX_EXP_DEFN size_t PCRE2_CALL_CONVENTION
regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size)
{
const char *message, *addmessage;
size_t length, addlength;
int used;
const char *message;
message = (errcode >= (int)(sizeof(pstring)/sizeof(char *)))?
message = (errcode <= 0 || errcode >= (int)(sizeof(pstring)/sizeof(char *)))?
"unknown error code" : pstring[errcode];
length = strlen(message) + 1;
addmessage = " at offset ";
addlength = (preg != NULL && (int)preg->re_erroffset != -1)?
strlen(addmessage) + 6 : 0;
if (errbuf_size > 0)
if (preg != NULL && (int)preg->re_erroffset != -1)
{
if (addlength > 0 && errbuf_size >= length + addlength)
sprintf(errbuf, "%s%s%-6d", message, addmessage, (int)preg->re_erroffset);
else
{
strncpy(errbuf, message, errbuf_size - 1);
errbuf[errbuf_size-1] = 0;
}
used = snprintf(errbuf, errbuf_size, "%s at offset %-6d", message,
(int)preg->re_erroffset);
}
else
{
used = snprintf(errbuf, errbuf_size, "%s", message);
}
return length + addlength;
return used + 1;
}
@ -223,8 +217,13 @@ preg->re_erroffset = erroffset;
if (preg->re_pcre2_code == NULL)
{
unsigned int i;
if (errorcode < 0) return REG_BADPAT; /* UTF error */
/* A negative value is a UTF error; otherwise all error codes are greater
than COMPILE_ERROR_BASE, but check, just in case. */
if (errorcode < COMPILE_ERROR_BASE) return REG_BADPAT;
errorcode -= COMPILE_ERROR_BASE;
if (errorcode < (int)(sizeof(eint1)/sizeof(const int)))
return eint1[errorcode];
for (i = 0; i < sizeof(eint2)/(2*sizeof(const int)); i += 2)
@ -237,6 +236,13 @@ if (preg->re_pcre2_code == NULL)
preg->re_nsub = (size_t)re_nsub;
if ((options & PCRE2_NO_AUTO_CAPTURE) != 0) re_nsub = -1;
preg->re_match_data = pcre2_match_data_create(re_nsub + 1, NULL);
if (preg->re_match_data == NULL)
{
pcre2_code_free(preg->re_pcre2_code);
return REG_ESPACE;
}
return 0;
}
@ -279,6 +285,7 @@ start location rather than being passed as a PCRE2 "starting offset". */
if ((eflags & REG_STARTEND) != 0)
{
if (pmatch == NULL) return REG_INVARG;
so = pmatch[0].rm_so;
eo = pmatch[0].rm_eo;
}

2
pcre2-10.20/src/pcre2posix.h → pcre2-10.21/src/pcre2posix.h
View file

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without

1050
pcre2-10.20/src/pcre2test.c → pcre2-10.21/src/pcre2test.c
View file

File diff suppressed because it is too large Load diff

0
pcre2-10.20/src/sljit/sljitConfig.h → pcre2-10.21/src/sljit/sljitConfig.h
View file

Some files were not shown because too many files have changed in this diff Show more