pcre2: move to PCRE2 10.32

Closes #5353.
This commit is contained in:
David Adam 2018-12-29 21:33:00 +08:00
parent 742fde0dd6
commit b60a9d8c4a
131 changed files with 44615 additions and 33524 deletions

4
.gitattributes vendored
View file

@ -20,8 +20,8 @@
/.github/* export-ignore
# for linguist; let github identify our project as C++ instead of C due to pcre2
/pcre2-10.22/ linguist-vendored
/pcre2-10.22/* linguist-vendored
/pcre2-10.32/ linguist-vendored
/pcre2-10.32/* linguist-vendored
/muparser-2.2.5/ linguist-vendored
/muparser-2.2.5/* linguist-vendored
angular.js linguist-vendored

View file

@ -71,7 +71,7 @@ extra_confdir = @extra_confdir@
# pcre2
#
PCRE2_WIDTH = @WCHAR_T_BITS@
PCRE2_DIR = pcre2-10.22
PCRE2_DIR = pcre2-10.32
PCRE2_LIBDIR = $(PCRE2_DIR)/.libs
PCRE2_LIB = $(PCRE2_LIBDIR)/libpcre2-$(PCRE2_WIDTH).a
PCRE2_H = $(PCRE2_DIR)/src/pcre2.h

View file

@ -134,14 +134,14 @@ if set -q c_files[1]
oclint-xcodebuild xcodebuild.log >/dev/null
end
if test $all = yes
oclint-json-compilation-database -e '/pcre2-10.22/' -- -enable-global-analysis 2>&1
oclint-json-compilation-database -e '/pcre2-10.32/' -- -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 '/pcre2-10.22/' $i_files
oclint-json-compilation-database -e '/pcre2-10.22/' $i_files 2>&1
echo oclint-json-compilation-database -e '/pcre2-10.32/' $i_files
oclint-json-compilation-database -e '/pcre2-10.32/' $i_files 2>&1
end
else
# Presumably we're on Linux or other platform not requiring special

View file

@ -13,8 +13,8 @@ IF (PCRE2_LIB AND PCRE2_INCLUDE_DIR)
MESSAGE(STATUS "Found system PCRE2 library ${PCRE2_INCLUDE_DIR}")
ELSE()
MESSAGE(STATUS "Using bundled PCRE2 library")
ADD_SUBDIRECTORY(pcre2-10.22 EXCLUDE_FROM_ALL)
SET(PCRE2_INCLUDE_DIR ${CMAKE_BINARY_DIR}/pcre2-10.22/)
ADD_SUBDIRECTORY(pcre2-10.32 EXCLUDE_FROM_ALL)
SET(PCRE2_INCLUDE_DIR ${CMAKE_BINARY_DIR}/pcre2-10.32/)
SET(PCRE2_LIB pcre2-${PCRE2_WIDTH})
endif(PCRE2_LIB AND PCRE2_INCLUDE_DIR)
INCLUDE_DIRECTORIES(${PCRE2_INCLUDE_DIR})

View file

@ -686,7 +686,7 @@ 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-$WCHAR_T_BITS --disable-shared"
AC_CONFIG_SUBDIRS([pcre2-10.22])
AC_CONFIG_SUBDIRS([pcre2-10.32])
PCRE2_CXXFLAGS='-I$(PCRE2_DIR)/src'
PCRE2_LIBS='-L$(PCRE2_LIBDIR) -lpcre2-$(PCRE2_WIDTH)'

View file

@ -986,7 +986,7 @@
D04F7FF71BA4E82C00B0F227 /* pcre2_chartables.c.dist */,
);
name = pcre;
path = "pcre2-10.22/src";
path = "pcre2-10.32/src";
sourceTree = SOURCE_ROOT;
};
D08A328E17B4455100F3A533 /* fish_tests */ = {

View file

@ -1,15 +0,0 @@
!config.h.in
!configure
!doc/
.deps
.dirstamp
.libs/
*.la
*.lo
*.pc
libtool
pcre2_chartables.c
pcre2-config
pcre2test
pcre2.h
stamp-h1

View file

@ -1,934 +0,0 @@
Change Log for PCRE2
--------------------
Version 10.22 29-July-2016
--------------------------
1. Applied Jason Hood's patches to RunTest.bat and testdata/wintestoutput3
to fix problems with running the tests under Windows.
2. Implemented a facility for quoting literal characters within hexadecimal
patterns in pcre2test, to make it easier to create patterns with just a few
non-printing characters.
3. Binary zeros are not supported in pcre2test input files. It now detects them
and gives an error.
4. Updated the valgrind parameters in RunTest: (a) changed smc-check=all to
smc-check=all-non-file; (b) changed obj:* in the suppression file to obj:??? so
that it matches only unknown objects.
5. Updated the maintenance script maint/ManyConfigTests to make it easier to
select individual groups of tests.
6. When the POSIX wrapper function regcomp() is called, the REG_NOSUB option
used to set PCRE2_NO_AUTO_CAPTURE when calling pcre2_compile(). However, this
disables the use of back references (and subroutine calls), which are supported
by other implementations of regcomp() with RE_NOSUB. Therefore, REG_NOSUB no
longer causes PCRE2_NO_AUTO_CAPTURE to be set, though it still ignores nmatch
and pmatch when regexec() is called.
7. Because of 6 above, pcre2test has been modified with a new modifier called
posix_nosub, to call regcomp() with REG_NOSUB. Previously the no_auto_capture
modifier had this effect. That option is now ignored when the POSIX API is in
use.
8. Minor tidies to the pcre2demo.c sample program, including more comments
about its 8-bit-ness.
9. Detect unmatched closing parentheses and give the error in the pre-scan
instead of later. Previously the pre-scan carried on and could give a
misleading incorrect error message. For example, /(?J)(?'a'))(?'a')/ gave a
message about invalid duplicate group names.
10. It has happened that pcre2test was accidentally linked with another POSIX
regex library instead of libpcre2-posix. In this situation, a call to regcomp()
(in the other library) may succeed, returning zero, but of course putting its
own data into the regex_t block. In one example the re_pcre2_code field was
left as NULL, which made pcre2test think it had not got a compiled POSIX regex,
so it treated the next line as another pattern line, resulting in a confusing
error message. A check has been added to pcre2test to see if the data returned
from a successful call of regcomp() are valid for PCRE2's regcomp(). If they
are not, an error message is output and the pcre2test run is abandoned. The
message points out the possibility of a mis-linking. Hopefully this will avoid
some head-scratching the next time this happens.
11. A pattern such as /(?<=((?C)0))/, which has a callout inside a lookbehind
assertion, caused pcre2test to output a very large number of spaces when the
callout was taken, making the program appearing to loop.
12. A pattern that included (*ACCEPT) in the middle of a sufficiently deeply
nested set of parentheses of sufficient size caused an overflow of the
compiling workspace (which was diagnosed, but of course is not desirable).
13. Detect missing closing parentheses during the pre-pass for group
identification.
14. Changed some integer variable types and put in a number of casts, following
a report of compiler warnings from Visual Studio 2013 and a few tests with
gcc's -Wconversion (which still throws up a lot).
15. Implemented pcre2_code_copy(), and added pushcopy and #popcopy to pcre2test
for testing it.
16. Change 66 for 10.21 introduced the use of snprintf() in PCRE2's version of
regerror(). When the error buffer is too small, my version of snprintf() puts a
binary zero in the final byte. Bug #1801 seems to show that other versions do
not do this, leading to bad output from pcre2test when it was checking for
buffer overflow. It no longer assumes a binary zero at the end of a too-small
regerror() buffer.
17. Fixed typo ("&&" for "&") in pcre2_study(). Fortunately, this could not
actually affect anything, by sheer luck.
18. Two minor fixes for MSVC compilation: (a) removal of apparently incorrect
"const" qualifiers in pcre2test and (b) defining snprintf as _snprintf for
older MSVC compilers. This has been done both in src/pcre2_internal.h for most
of the library, and also in src/pcre2posix.c, which no longer includes
pcre2_internal.h (see 24 below).
19. Applied Chris Wilson's patch (Bugzilla #1681) to CMakeLists.txt for MSVC
static compilation. Subsequently applied Chris Wilson's second patch, putting
the first patch under a new option instead of being unconditional when
PCRE_STATIC is set.
20. Updated pcre2grep to set stdout as binary when run under Windows, so as not
to convert \r\n at the ends of reflected lines into \r\r\n. This required
ensuring that other output that is written to stdout (e.g. file names) uses the
appropriate line terminator: \r\n for Windows, \n otherwise.
21. When a line is too long for pcre2grep's internal buffer, show the maximum
length in the error message.
22. Added support for string callouts to pcre2grep (Zoltan's patch with PH
additions).
23. RunTest.bat was missing a "set type" line for test 22.
24. The pcre2posix.c file was including pcre2_internal.h, and using some
"private" knowledge of the data structures. This is unnecessary; the code has
been re-factored and no longer includes pcre2_internal.h.
25. A racing condition is fixed in JIT reported by Mozilla.
26. Minor code refactor to avoid "array subscript is below array bounds"
compiler warning.
27. Minor code refactor to avoid "left shift of negative number" warning.
28. Add a bit more sanity checking to pcre2_serialize_decode() and document
that it expects trusted data.
29. Fix typo in pcre2_jit_test.c
30. Due to an oversight, pcre2grep was not making use of JIT when available.
This is now fixed.
31. The RunGrepTest script is updated to use the valgrind suppressions file
when testing with JIT under valgrind (compare 10.21/51 below). The suppressions
file is updated so that is now the same as for PCRE1: it suppresses the
Memcheck warnings Addr16 and Cond in unknown objects (that is, JIT-compiled
code). Also changed smc-check=all to smc-check=all-non-file as was done for
RunTest (see 4 above).
32. Implemented the PCRE2_NO_JIT option for pcre2_match().
33. Fix typo that gave a compiler error when JIT not supported.
34. Fix comment describing the returns from find_fixedlength().
35. Fix potential negative index in pcre2test.
36. Calls to pcre2_get_error_message() with error numbers that are never
returned by PCRE2 functions were returning empty strings. Now the error code
PCRE2_ERROR_BADDATA is returned. A facility has been added to pcre2test to
show the texts for given error numbers (i.e. to call pcre2_get_error_message()
and display what it returns) and a few representative error codes are now
checked in RunTest.
37. Added "&& !defined(__INTEL_COMPILER)" to the test for __GNUC__ in
pcre2_match.c, in anticipation that this is needed for the same reason it was
recently added to pcrecpp.cc in PCRE1.
38. Using -o with -M in pcre2grep could cause unnecessary repeated output when
the match extended over a line boundary, as it tried to find more matches "on
the same line" - but it was already over the end.
39. Allow \C in lookbehinds and DFA matching in UTF-32 mode (by converting it
to the same code as '.' when PCRE2_DOTALL is set).
40. Fix two clang compiler warnings in pcre2test when only one code unit width
is supported.
41. Upgrade RunTest to automatically re-run test 2 with a large (64M) stack if
it fails when running the interpreter with a 16M stack (and if changing the
stack size via pcre2test is possible). This avoids having to manually set a
large stack size when testing with clang.
42. Fix register overwite in JIT when SSE2 acceleration is enabled.
43. Detect integer overflow in pcre2test pattern and data repetition counts.
44. In pcre2test, ignore "allcaptures" after DFA matching.
45. Fix unaligned accesses on x86. Patch by Marc Mutz.
46. Fix some more clang compiler warnings.
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 (?imsxJU) 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
--------------------------
1. Callouts with string arguments have been added.
2. Assertion code generator in JIT has been optimized.
3. The invalid pattern (?(?C) has a missing assertion condition at the end. The
pcre2_compile() function read past the end of the input before diagnosing an
error. This bug was discovered by the LLVM fuzzer.
4. Implemented pcre2_callout_enumerate().
5. Fix JIT compilation of conditional blocks whose assertion is converted to
(*FAIL). E.g: /(?(?!))/.
6. The pattern /(?(?!)^)/ caused references to random memory. This bug was
discovered by the LLVM fuzzer.
7. The assertion (?!) is optimized to (*FAIL). This was not handled correctly
when this assertion was used as a condition, for example (?(?!)a|b). In
pcre2_match() it worked by luck; in pcre2_dfa_match() it gave an incorrect
error about an unsupported item.
8. For some types of pattern, for example /Z*(|d*){216}/, the auto-
possessification code could take exponential time to complete. A recursion
depth limit of 1000 has been imposed to limit the resources used by this
optimization. This infelicity was discovered by the LLVM fuzzer.
9. A pattern such as /(*UTF)[\S\V\H]/, which contains a negated special class
such as \S in non-UCP mode, explicit wide characters (> 255) can be ignored
because \S ensures they are all in the class. The code for doing this was
interacting badly with the code for computing the amount of space needed to
compile the pattern, leading to a buffer overflow. This bug was discovered by
the LLVM fuzzer.
10. A pattern such as /((?2)+)((?1))/ which has mutual recursion nested inside
other kinds of group caused stack overflow at compile time. This bug was
discovered by the LLVM fuzzer.
11. A pattern such as /(?1)(?#?'){8}(a)/ which had a parenthesized comment
between a subroutine call and its quantifier was incorrectly compiled, leading
to buffer overflow or other errors. This bug was discovered by the LLVM fuzzer.
12. The illegal pattern /(?(?<E>.*!.*)?)/ was not being diagnosed as missing an
assertion after (?(. The code was failing to check the character after (?(?<
for the ! or = that would indicate a lookbehind assertion. This bug was
discovered by the LLVM fuzzer.
13. A pattern such as /X((?2)()*+){2}+/ which has a possessive quantifier with
a fixed maximum following a group that contains a subroutine reference was
incorrectly compiled and could trigger buffer overflow. This bug was discovered
by the LLVM fuzzer.
14. Negative relative recursive references such as (?-7) to non-existent
subpatterns were not being diagnosed and could lead to unpredictable behaviour.
This bug was discovered by the LLVM fuzzer.
15. The bug fixed in 14 was due to an integer variable that was unsigned when
it should have been signed. Some other "int" variables, having been checked,
have either been changed to uint32_t or commented as "must be signed".
16. A mutual recursion within a lookbehind assertion such as (?<=((?2))((?1)))
caused a stack overflow instead of the diagnosis of a non-fixed length
lookbehind assertion. This bug was discovered by the LLVM fuzzer.
17. The use of \K in a positive lookbehind assertion in a non-anchored pattern
(e.g. /(?<=\Ka)/) could make pcre2grep loop.
18. There was a similar problem to 17 in pcre2test for global matches, though
the code there did catch the loop.
19. If a greedy quantified \X was preceded by \C in UTF mode (e.g. \C\X*),
and a subsequent item in the pattern caused a non-match, backtracking over the
repeated \X did not stop, but carried on past the start of the subject, causing
reference to random memory and/or a segfault. There were also some other cases
where backtracking after \C could crash. This set of bugs was discovered by the
LLVM fuzzer.
20. The function for finding the minimum length of a matching string could take
a very long time if mutual recursion was present many times in a pattern, for
example, /((?2){73}(?2))((?1))/. A better mutual recursion detection method has
been implemented. This infelicity was discovered by the LLVM fuzzer.
21. Implemented PCRE2_NEVER_BACKSLASH_C.
22. The feature for string replication in pcre2test could read from freed
memory if the replication required a buffer to be extended, and it was not
working properly in 16-bit and 32-bit modes. This issue was discovered by a
fuzzer: see http://lcamtuf.coredump.cx/afl/.
23. Added the PCRE2_ALT_CIRCUMFLEX option.
24. Adjust the treatment of \8 and \9 to be the same as the current Perl
behaviour.
25. Static linking against the PCRE2 library using the pkg-config module was
failing on missing pthread symbols.
26. If a group that contained a recursive back reference also contained a
forward reference subroutine call followed by a non-forward-reference
subroutine call, for example /.((?2)(?R)\1)()/, pcre2_compile() failed to
compile correct code, leading to undefined behaviour or an internally detected
error. This bug was discovered by the LLVM fuzzer.
27. Quantification of certain items (e.g. atomic back references) could cause
incorrect code to be compiled when recursive forward references were involved.
For example, in this pattern: /(?1)()((((((\1++))\x85)+)|))/. This bug was
discovered by the LLVM fuzzer.
28. A repeated conditional group whose condition was a reference by name caused
a buffer overflow if there was more than one group with the given name. This
bug was discovered by the LLVM fuzzer.
29. A recursive back reference by name within a group that had the same name as
another group caused a buffer overflow. For example: /(?J)(?'d'(?'d'\g{d}))/.
This bug was discovered by the LLVM fuzzer.
30. A forward reference by name to a group whose number is the same as the
current group, for example in this pattern: /(?|(\k'Pm')|(?'Pm'))/, caused a
buffer overflow at compile time. This bug was discovered by the LLVM fuzzer.
31. Fix -fsanitize=undefined warnings for left shifts of 1 by 31 (it treats 1
as an int; fixed by writing it as 1u).
32. Fix pcre2grep compile when -std=c99 is used with gcc, though it still gives
a warning for "fileno" unless -std=gnu99 us used.
33. A lookbehind assertion within a set of mutually recursive subpatterns could
provoke a buffer overflow. This bug was discovered by the LLVM fuzzer.
34. Give an error for an empty subpattern name such as (?'').
35. Make pcre2test give an error if a pattern that follows #forbud_utf contains
\P, \p, or \X.
36. The way named subpatterns are handled has been refactored. There is now a
pre-pass over the regex which does nothing other than identify named
subpatterns and count the total captures. This means that information about
named patterns is known before the rest of the compile. In particular, it means
that forward references can be checked as they are encountered. Previously, the
code for handling forward references was contorted and led to several errors in
computing the memory requirements for some patterns, leading to buffer
overflows.
37. There was no check for integer overflow in subroutine calls such as (?123).
38. The table entry for \l in EBCDIC environments was incorrect, leading to its
being treated as a literal 'l' instead of causing an error.
39. If a non-capturing group containing a conditional group that could match
an empty string was repeated, it was not identified as matching an empty string
itself. For example: /^(?:(?(1)x|)+)+$()/.
40. In an EBCDIC environment, pcretest was mishandling the escape sequences
\a and \e in test subject lines.
41. In an EBCDIC environment, \a in a pattern was converted to the ASCII
instead of the EBCDIC value.
42. The handling of \c in an EBCDIC environment has been revised so that it is
now compatible with the specification in Perl's perlebcdic page.
43. Single character repetition in JIT has been improved. 20-30% speedup
was achieved on certain patterns.
44. The EBCDIC character 0x41 is a non-breaking space, equivalent to 0xa0 in
ASCII/Unicode. This has now been added to the list of characters that are
recognized as white space in EBCDIC.
45. When PCRE2 was compiled without Unicode support, the use of \p and \P gave
an error (correctly) when used outside a class, but did not give an error
within a class.
46. \h within a class was incorrectly compiled in EBCDIC environments.
47. JIT should return with error when the compiled pattern requires
more stack space than the maximum.
48. Fixed a memory leak in pcre2grep when a locale is set.
Version 10.10 06-March-2015
---------------------------
1. When a pattern is compiled, it remembers the highest back reference so that
when matching, if the ovector is too small, extra memory can be obtained to
use instead. A conditional subpattern whose condition is a check on a capture
having happened, such as, for example in the pattern /^(?:(a)|b)(?(1)A|B)/, is
another kind of back reference, but it was not setting the highest
backreference number. This mattered only if pcre2_match() was called with an
ovector that was too small to hold the capture, and there was no other kind of
back reference (a situation which is probably quite rare). The effect of the
bug was that the condition was always treated as FALSE when the capture could
not be consulted, leading to a incorrect behaviour by pcre2_match(). This bug
has been fixed.
2. Functions for serialization and deserialization of sets of compiled patterns
have been added.
3. The value that is returned by PCRE2_INFO_SIZE has been corrected to remove
excess code units at the end of the data block that may occasionally occur if
the code for calculating the size over-estimates. This change stops the
serialization code copying uninitialized data, to which valgrind objects. The
documentation of PCRE2_INFO_SIZE was incorrect in stating that the size did not
include the general overhead. This has been corrected.
4. All code units in every slot in the table of group names are now set, again
in order to avoid accessing uninitialized data when serializing.
5. The (*NO_JIT) feature is implemented.
6. If a bug that caused pcre2_compile() to use more memory than allocated was
triggered when using valgrind, the code in (3) above passed a stupidly large
value to valgrind. This caused a crash instead of an "internal error" return.
7. A reference to a duplicated named group (either a back reference or a test
for being set in a conditional) that occurred in a part of the pattern where
PCRE2_DUPNAMES was not set caused the amount of memory needed for the pattern
to be incorrectly calculated, leading to overwriting.
8. A mutually recursive set of back references such as (\2)(\1) caused a
segfault at compile time (while trying to find the minimum matching length).
The infinite loop is now broken (with the minimum length unset, that is, zero).
9. If an assertion that was used as a condition was quantified with a minimum
of zero, matching went wrong. In particular, if the whole group had unlimited
repetition and could match an empty string, a segfault was likely. The pattern
(?(?=0)?)+ is an example that caused this. Perl allows assertions to be
quantified, but not if they are being used as conditions, so the above pattern
is faulted by Perl. PCRE2 has now been changed so that it also rejects such
patterns.
10. The error message for an invalid quantifier has been changed from "nothing
to repeat" to "quantifier does not follow a repeatable item".
11. If a bad UTF string is compiled with NO_UTF_CHECK, it may succeed, but
scanning the compiled pattern in subsequent auto-possessification can get out
of step and lead to an unknown opcode. Previously this could have caused an
infinite loop. Now it generates an "internal error" error. This is a tidyup,
not a bug fix; passing bad UTF with NO_UTF_CHECK is documented as having an
undefined outcome.
12. A UTF pattern containing a "not" match of a non-ASCII character and a
subroutine reference could loop at compile time. Example: /[^\xff]((?1))/.
13. The locale test (RunTest 3) has been upgraded. It now checks that a locale
that is found in the output of "locale -a" can actually be set by pcre2test
before it is accepted. Previously, in an environment where a locale was listed
but would not set (an example does exist), the test would "pass" without
actually doing anything. Also the fr_CA locale has been added to the list of
locales that can be used.
14. Fixed a bug in pcre2_substitute(). If a replacement string ended in a
capturing group number without parentheses, the last character was incorrectly
literally included at the end of the replacement string.
15. A possessive capturing group such as (a)*+ with a minimum repeat of zero
failed to allow the zero-repeat case if pcre2_match() was called with an
ovector too small to capture the group.
16. Improved error message in pcre2test when setting the stack size (-S) fails.
17. Fixed two bugs in CMakeLists.txt: (1) Some lines had got lost in the
transfer from PCRE1, meaning that CMake configuration failed if "build tests"
was selected. (2) The file src/pcre2_serialize.c had not been added to the list
of PCRE2 sources, which caused a failure to build pcre2test.
18. Fixed typo in pcre2_serialize.c (DECL instead of DEFN) that causes problems
only on Windows.
19. Use binary input when reading back saved serialized patterns in pcre2test.
20. Added RunTest.bat for running the tests under Windows.
21. "make distclean" was not removing config.h, a file that may be created for
use with CMake.
22. A pattern such as "((?2){0,1999}())?", which has a group containing a
forward reference repeated a large (but limited) number of times within a
repeated outer group that has a zero minimum quantifier, caused incorrect code
to be compiled, leading to the error "internal error: previously-checked
referenced subpattern not found" when an incorrect memory address was read.
This bug was reported as "heap overflow", discovered by Kai Lu of Fortinet's
FortiGuard Labs. (Added 24-March-2015: CVE-2015-2325 was given to this.)
23. A pattern such as "((?+1)(\1))/" containing a forward reference subroutine
call within a group that also contained a recursive back reference caused
incorrect code to be compiled. This bug was reported as "heap overflow",
discovered by Kai Lu of Fortinet's FortiGuard Labs. (Added 24-March-2015:
CVE-2015-2326 was given to this.)
24. Computing the size of the JIT read-only data in advance has been a source
of various issues, and new ones are still appear unfortunately. To fix
existing and future issues, size computation is eliminated from the code,
and replaced by on-demand memory allocation.
25. A pattern such as /(?i)[A-`]/, where characters in the other case are
adjacent to the end of the range, and the range contained characters with more
than one other case, caused incorrect behaviour when compiled in UTF mode. In
that example, the range a-j was left out of the class.
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.
The code of the library was heavily revised as part of the new API
implementation. Details of each and every modification were not individually
logged. In addition to the API changes, the following changes were made. They
are either new functionality, or bug fixes and other noticeable changes of
behaviour that were implemented after the code had been forked.
1. Including Unicode support at build time is now enabled by default, but it
can optionally be disabled. It is not enabled by default at run time (no
change).
2. The test program, now called pcre2test, was re-specified and almost
completely re-written. Its input is not compatible with input for pcretest.
3. Patterns may start with (*NOTEMPTY) or (*NOTEMPTY_ATSTART) to set the
PCRE2_NOTEMPTY or PCRE2_NOTEMPTY_ATSTART options for every subject line that is
matched by that pattern.
4. For the benefit of those who use PCRE2 via some other application, that is,
not writing the function calls themselves, it is possible to check the PCRE2
version by matching a pattern such as /(?(VERSION>=10)yes|no)/ against a
string such as "yesno".
5. There are case-equivalent Unicode characters whose encodings use different
numbers of code units in UTF-8. U+023A and U+2C65 are one example. (It is
theoretically possible for this to happen in UTF-16 too.) If a backreference to
a group containing one of these characters was greedily repeated, and during
the match a backtrack occurred, the subject might be backtracked by the wrong
number of code units. For example, if /^(\x{23a})\1*(.)/ is matched caselessly
(and in UTF-8 mode) against "\x{23a}\x{2c65}\x{2c65}\x{2c65}", group 2 should
capture the final character, which is the three bytes E2, B1, and A5 in UTF-8.
Incorrect backtracking meant that group 2 captured only the last two bytes.
This bug has been fixed; the new code is slower, but it is used only when the
strings matched by the repetition are not all the same length.
6. A pattern such as /()a/ was not setting the "first character must be 'a'"
information. This applied to any pattern with a group that matched no
characters, for example: /(?:(?=.)|(?<!x))a/.
7. When an (*ACCEPT) is triggered inside capturing parentheses, it arranges for
those parentheses to be closed with whatever has been captured so far. However,
it was failing to mark any other groups between the highest capture so far and
the currrent group as "unset". Thus, the ovector for those groups contained
whatever was previously there. An example is the pattern /(x)|((*ACCEPT))/ when
matched against "abcd".
8. The pcre2_substitute() function has been implemented.
9. If an assertion used as a condition was quantified with a minimum of zero
(an odd thing to do, but it happened), SIGSEGV or other misbehaviour could
occur.
10. The PCRE2_NO_DOTSTAR_ANCHOR option has been implemented.
****

View file

@ -1,370 +0,0 @@
Installation Instructions
*************************
Copyright (C) 1994-1996, 1999-2002, 2004-2013 Free Software Foundation,
Inc.
Copying and distribution of this file, with or without modification,
are permitted in any medium without royalty provided the copyright
notice and this notice are preserved. This file is offered as-is,
without warranty of any kind.
Basic Installation
==================
Briefly, the shell command `./configure && make && make install'
should configure, build, and install this package. The following
more-detailed instructions are generic; see the `README' file for
instructions specific to this package. Some packages provide this
`INSTALL' file but do not implement all of the features documented
below. The lack of an optional feature in a given package is not
necessarily a bug. More recommendations for GNU packages can be found
in *note Makefile Conventions: (standards)Makefile Conventions.
The `configure' shell script attempts to guess correct values for
various system-dependent variables used during compilation. It uses
those values to create a `Makefile' in each directory of the package.
It may also create one or more `.h' files containing system-dependent
definitions. Finally, it creates a shell script `config.status' that
you can run in the future to recreate the current configuration, and a
file `config.log' containing compiler output (useful mainly for
debugging `configure').
It can also use an optional file (typically called `config.cache'
and enabled with `--cache-file=config.cache' or simply `-C') that saves
the results of its tests to speed up reconfiguring. Caching is
disabled by default to prevent problems with accidental use of stale
cache files.
If you need to do unusual things to compile the package, please try
to figure out how `configure' could check whether to do them, and mail
diffs or instructions to the address given in the `README' so they can
be considered for the next release. If you are using the cache, and at
some point `config.cache' contains results you don't want to keep, you
may remove or edit it.
The file `configure.ac' (or `configure.in') is used to create
`configure' by a program called `autoconf'. You need `configure.ac' if
you want to change it or regenerate `configure' using a newer version
of `autoconf'.
The simplest way to compile this package is:
1. `cd' to the directory containing the package's source code and type
`./configure' to configure the package for your system.
Running `configure' might take a while. While running, it prints
some messages telling which features it is checking for.
2. Type `make' to compile the package.
3. Optionally, type `make check' to run any self-tests that come with
the package, generally using the just-built uninstalled binaries.
4. Type `make install' to install the programs and any data files and
documentation. When installing into a prefix owned by root, it is
recommended that the package be configured and built as a regular
user, and only the `make install' phase executed with root
privileges.
5. Optionally, type `make installcheck' to repeat any self-tests, but
this time using the binaries in their final installed location.
This target does not install anything. Running this target as a
regular user, particularly if the prior `make install' required
root privileges, verifies that the installation completed
correctly.
6. You can remove the program binaries and object files from the
source code directory by typing `make clean'. To also remove the
files that `configure' created (so you can compile the package for
a different kind of computer), type `make distclean'. There is
also a `make maintainer-clean' target, but that is intended mainly
for the package's developers. If you use it, you may have to get
all sorts of other programs in order to regenerate files that came
with the distribution.
7. Often, you can also type `make uninstall' to remove the installed
files again. In practice, not all packages have tested that
uninstallation works correctly, even though it is required by the
GNU Coding Standards.
8. Some packages, particularly those that use Automake, provide `make
distcheck', which can by used by developers to test that all other
targets like `make install' and `make uninstall' work correctly.
This target is generally not run by end users.
Compilers and Options
=====================
Some systems require unusual options for compilation or linking that
the `configure' script does not know about. Run `./configure --help'
for details on some of the pertinent environment variables.
You can give `configure' initial values for configuration parameters
by setting variables in the command line or in the environment. Here
is an example:
./configure CC=c99 CFLAGS=-g LIBS=-lposix
*Note Defining Variables::, for more details.
Compiling For Multiple Architectures
====================================
You can compile the package for more than one kind of computer at the
same time, by placing the object files for each architecture in their
own directory. To do this, you can use GNU `make'. `cd' to the
directory where you want the object files and executables to go and run
the `configure' script. `configure' automatically checks for the
source code in the directory that `configure' is in and in `..'. This
is known as a "VPATH" build.
With a non-GNU `make', it is safer to compile the package for one
architecture at a time in the source code directory. After you have
installed the package for one architecture, use `make distclean' before
reconfiguring for another architecture.
On MacOS X 10.5 and later systems, you can create libraries and
executables that work on multiple system types--known as "fat" or
"universal" binaries--by specifying multiple `-arch' options to the
compiler but only a single `-arch' option to the preprocessor. Like
this:
./configure CC="gcc -arch i386 -arch x86_64 -arch ppc -arch ppc64" \
CXX="g++ -arch i386 -arch x86_64 -arch ppc -arch ppc64" \
CPP="gcc -E" CXXCPP="g++ -E"
This is not guaranteed to produce working output in all cases, you
may have to build one architecture at a time and combine the results
using the `lipo' tool if you have problems.
Installation Names
==================
By default, `make install' installs the package's commands under
`/usr/local/bin', include files under `/usr/local/include', etc. You
can specify an installation prefix other than `/usr/local' by giving
`configure' the option `--prefix=PREFIX', where PREFIX must be an
absolute file name.
You can specify separate installation prefixes for
architecture-specific files and architecture-independent files. If you
pass the option `--exec-prefix=PREFIX' to `configure', the package uses
PREFIX as the prefix for installing programs and libraries.
Documentation and other data files still use the regular prefix.
In addition, if you use an unusual directory layout you can give
options like `--bindir=DIR' to specify different values for particular
kinds of files. Run `configure --help' for a list of the directories
you can set and what kinds of files go in them. In general, the
default for these options is expressed in terms of `${prefix}', so that
specifying just `--prefix' will affect all of the other directory
specifications that were not explicitly provided.
The most portable way to affect installation locations is to pass the
correct locations to `configure'; however, many packages provide one or
both of the following shortcuts of passing variable assignments to the
`make install' command line to change installation locations without
having to reconfigure or recompile.
The first method involves providing an override variable for each
affected directory. For example, `make install
prefix=/alternate/directory' will choose an alternate location for all
directory configuration variables that were expressed in terms of
`${prefix}'. Any directories that were specified during `configure',
but not in terms of `${prefix}', must each be overridden at install
time for the entire installation to be relocated. The approach of
makefile variable overrides for each directory variable is required by
the GNU Coding Standards, and ideally causes no recompilation.
However, some platforms have known limitations with the semantics of
shared libraries that end up requiring recompilation when using this
method, particularly noticeable in packages that use GNU Libtool.
The second method involves providing the `DESTDIR' variable. For
example, `make install DESTDIR=/alternate/directory' will prepend
`/alternate/directory' before all installation names. The approach of
`DESTDIR' overrides is not required by the GNU Coding Standards, and
does not work on platforms that have drive letters. On the other hand,
it does better at avoiding recompilation issues, and works well even
when some directory options were not specified in terms of `${prefix}'
at `configure' time.
Optional Features
=================
If the package supports it, you can cause programs to be installed
with an extra prefix or suffix on their names by giving `configure' the
option `--program-prefix=PREFIX' or `--program-suffix=SUFFIX'.
Some packages pay attention to `--enable-FEATURE' options to
`configure', where FEATURE indicates an optional part of the package.
They may also pay attention to `--with-PACKAGE' options, where PACKAGE
is something like `gnu-as' or `x' (for the X Window System). The
`README' should mention any `--enable-' and `--with-' options that the
package recognizes.
For packages that use the X Window System, `configure' can usually
find the X include and library files automatically, but if it doesn't,
you can use the `configure' options `--x-includes=DIR' and
`--x-libraries=DIR' to specify their locations.
Some packages offer the ability to configure how verbose the
execution of `make' will be. For these packages, running `./configure
--enable-silent-rules' sets the default to minimal output, which can be
overridden with `make V=1'; while running `./configure
--disable-silent-rules' sets the default to verbose, which can be
overridden with `make V=0'.
Particular systems
==================
On HP-UX, the default C compiler is not ANSI C compatible. If GNU
CC is not installed, it is recommended to use the following options in
order to use an ANSI C compiler:
./configure CC="cc -Ae -D_XOPEN_SOURCE=500"
and if that doesn't work, install pre-built binaries of GCC for HP-UX.
HP-UX `make' updates targets which have the same time stamps as
their prerequisites, which makes it generally unusable when shipped
generated files such as `configure' are involved. Use GNU `make'
instead.
On OSF/1 a.k.a. Tru64, some versions of the default C compiler cannot
parse its `<wchar.h>' header file. The option `-nodtk' can be used as
a workaround. If GNU CC is not installed, it is therefore recommended
to try
./configure CC="cc"
and if that doesn't work, try
./configure CC="cc -nodtk"
On Solaris, don't put `/usr/ucb' early in your `PATH'. This
directory contains several dysfunctional programs; working variants of
these programs are available in `/usr/bin'. So, if you need `/usr/ucb'
in your `PATH', put it _after_ `/usr/bin'.
On Haiku, software installed for all users goes in `/boot/common',
not `/usr/local'. It is recommended to use the following options:
./configure --prefix=/boot/common
Specifying the System Type
==========================
There may be some features `configure' cannot figure out
automatically, but needs to determine by the type of machine the package
will run on. Usually, assuming the package is built to be run on the
_same_ architectures, `configure' can figure that out, but if it prints
a message saying it cannot guess the machine type, give it the
`--build=TYPE' option. TYPE can either be a short name for the system
type, such as `sun4', or a canonical name which has the form:
CPU-COMPANY-SYSTEM
where SYSTEM can have one of these forms:
OS
KERNEL-OS
See the file `config.sub' for the possible values of each field. If
`config.sub' isn't included in this package, then this package doesn't
need to know the machine type.
If you are _building_ compiler tools for cross-compiling, you should
use the option `--target=TYPE' to select the type of system they will
produce code for.
If you want to _use_ a cross compiler, that generates code for a
platform different from the build platform, you should specify the
"host" platform (i.e., that on which the generated programs will
eventually be run) with `--host=TYPE'.
Sharing Defaults
================
If you want to set default values for `configure' scripts to share,
you can create a site shell script called `config.site' that gives
default values for variables like `CC', `cache_file', and `prefix'.
`configure' looks for `PREFIX/share/config.site' if it exists, then
`PREFIX/etc/config.site' if it exists. Or, you can set the
`CONFIG_SITE' environment variable to the location of the site script.
A warning: not all `configure' scripts look for a site script.
Defining Variables
==================
Variables not defined in a site shell script can be set in the
environment passed to `configure'. However, some packages may run
configure again during the build, and the customized values of these
variables may be lost. In order to avoid this problem, you should set
them in the `configure' command line, using `VAR=value'. For example:
./configure CC=/usr/local2/bin/gcc
causes the specified `gcc' to be used as the C compiler (unless it is
overridden in the site shell script).
Unfortunately, this technique does not work for `CONFIG_SHELL' due to
an Autoconf limitation. Until the limitation is lifted, you can use
this workaround:
CONFIG_SHELL=/bin/bash ./configure CONFIG_SHELL=/bin/bash
`configure' Invocation
======================
`configure' recognizes the following options to control how it
operates.
`--help'
`-h'
Print a summary of all of the options to `configure', and exit.
`--help=short'
`--help=recursive'
Print a summary of the options unique to this package's
`configure', and exit. The `short' variant lists options used
only in the top level, while the `recursive' variant lists options
also present in any nested packages.
`--version'
`-V'
Print the version of Autoconf used to generate the `configure'
script, and exit.
`--cache-file=FILE'
Enable the cache: use and save the results of the tests in FILE,
traditionally `config.cache'. FILE defaults to `/dev/null' to
disable caching.
`--config-cache'
`-C'
Alias for `--cache-file=config.cache'.
`--quiet'
`--silent'
`-q'
Do not print messages saying which checks are being made. To
suppress all normal output, redirect it to `/dev/null' (any error
messages will still be shown).
`--srcdir=DIR'
Look for the package's source code in directory DIR. Usually
`configure' can determine that directory automatically.
`--prefix=DIR'
Use DIR as the installation prefix. *note Installation Names::
for more details, including other options available for fine-tuning
the installation locations.
`--no-create'
`-n'
Run the configure checks, but stop before creating any output
files.
`configure' also accepts some other, not widely useful, options. Run
`configure --help' for more details.

View file

@ -1,110 +0,0 @@
News about PCRE2 releases
-------------------------
Version 10.22 29-July-2016
--------------------------
1. ChangeLog has the details of a number of bug fixes.
2. The POSIX wrapper function regcomp() did not used to support back references
and subroutine calls if called with the REG_NOSUB option. It now does.
3. A new function, pcre2_code_copy(), is added, to make a copy of a compiled
pattern.
4. Support for string callouts is added to pcre2grep.
5. Added the PCRE2_NO_JIT option to pcre2_match().
6. The pcre2_get_error_message() function now returns with a negative error
code if the error number it is given is unknown.
7. Several updates have been made to pcre2test and test scripts (see
ChangeLog).
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.
****

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

View file

@ -1,366 +0,0 @@
/*
* Stack-less Just-In-Time compiler
*
* Copyright 2009-2012 Zoltan Herczeg (hzmester@freemail.hu). All rights reserved.
*
* Redistribution and use in source and binary forms, with or without modification, are
* permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright notice, this list of
* conditions and the following disclaimer.
*
* 2. 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.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDER(S) 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 HOLDER(S) 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.
*/
/* mips 32-bit arch dependent functions. */
static sljit_s32 load_immediate(struct sljit_compiler *compiler, sljit_s32 dst_ar, sljit_sw imm)
{
if (!(imm & ~0xffff))
return push_inst(compiler, ORI | SA(0) | TA(dst_ar) | IMM(imm), dst_ar);
if (imm < 0 && imm >= SIMM_MIN)
return push_inst(compiler, ADDIU | SA(0) | TA(dst_ar) | IMM(imm), dst_ar);
FAIL_IF(push_inst(compiler, LUI | TA(dst_ar) | IMM(imm >> 16), dst_ar));
return (imm & 0xffff) ? push_inst(compiler, ORI | SA(dst_ar) | TA(dst_ar) | IMM(imm), dst_ar) : SLJIT_SUCCESS;
}
#define EMIT_LOGICAL(op_imm, op_norm) \
if (flags & SRC2_IMM) { \
if (op & SLJIT_SET_E) \
FAIL_IF(push_inst(compiler, op_imm | S(src1) | TA(EQUAL_FLAG) | IMM(src2), EQUAL_FLAG)); \
if (CHECK_FLAGS(SLJIT_SET_E)) \
FAIL_IF(push_inst(compiler, op_imm | S(src1) | T(dst) | IMM(src2), DR(dst))); \
} \
else { \
if (op & SLJIT_SET_E) \
FAIL_IF(push_inst(compiler, op_norm | S(src1) | T(src2) | DA(EQUAL_FLAG), EQUAL_FLAG)); \
if (CHECK_FLAGS(SLJIT_SET_E)) \
FAIL_IF(push_inst(compiler, op_norm | S(src1) | T(src2) | D(dst), DR(dst))); \
}
#define EMIT_SHIFT(op_imm, op_v) \
if (flags & SRC2_IMM) { \
if (op & SLJIT_SET_E) \
FAIL_IF(push_inst(compiler, op_imm | T(src1) | DA(EQUAL_FLAG) | SH_IMM(src2), EQUAL_FLAG)); \
if (CHECK_FLAGS(SLJIT_SET_E)) \
FAIL_IF(push_inst(compiler, op_imm | T(src1) | D(dst) | SH_IMM(src2), DR(dst))); \
} \
else { \
if (op & SLJIT_SET_E) \
FAIL_IF(push_inst(compiler, op_v | S(src2) | T(src1) | DA(EQUAL_FLAG), EQUAL_FLAG)); \
if (CHECK_FLAGS(SLJIT_SET_E)) \
FAIL_IF(push_inst(compiler, op_v | S(src2) | T(src1) | D(dst), DR(dst))); \
}
static SLJIT_INLINE sljit_s32 emit_single_op(struct sljit_compiler *compiler, sljit_s32 op, sljit_s32 flags,
sljit_s32 dst, sljit_s32 src1, sljit_sw src2)
{
switch (GET_OPCODE(op)) {
case SLJIT_MOV:
case SLJIT_MOV_U32:
case SLJIT_MOV_S32:
case SLJIT_MOV_P:
SLJIT_ASSERT(src1 == TMP_REG1 && !(flags & SRC2_IMM));
if (dst != src2)
return push_inst(compiler, ADDU | S(src2) | TA(0) | D(dst), DR(dst));
return SLJIT_SUCCESS;
case SLJIT_MOV_U8:
case SLJIT_MOV_S8:
SLJIT_ASSERT(src1 == TMP_REG1 && !(flags & SRC2_IMM));
if ((flags & (REG_DEST | REG2_SOURCE)) == (REG_DEST | REG2_SOURCE)) {
if (op == SLJIT_MOV_S8) {
#if (defined SLJIT_MIPS_R1 && SLJIT_MIPS_R1)
return push_inst(compiler, SEB | T(src2) | D(dst), DR(dst));
#else
FAIL_IF(push_inst(compiler, SLL | T(src2) | D(dst) | SH_IMM(24), DR(dst)));
return push_inst(compiler, SRA | T(dst) | D(dst) | SH_IMM(24), DR(dst));
#endif
}
return push_inst(compiler, ANDI | S(src2) | T(dst) | IMM(0xff), DR(dst));
}
else if (dst != src2)
SLJIT_ASSERT_STOP();
return SLJIT_SUCCESS;
case SLJIT_MOV_U16:
case SLJIT_MOV_S16:
SLJIT_ASSERT(src1 == TMP_REG1 && !(flags & SRC2_IMM));
if ((flags & (REG_DEST | REG2_SOURCE)) == (REG_DEST | REG2_SOURCE)) {
if (op == SLJIT_MOV_S16) {
#if (defined SLJIT_MIPS_R1 && SLJIT_MIPS_R1)
return push_inst(compiler, SEH | T(src2) | D(dst), DR(dst));
#else
FAIL_IF(push_inst(compiler, SLL | T(src2) | D(dst) | SH_IMM(16), DR(dst)));
return push_inst(compiler, SRA | T(dst) | D(dst) | SH_IMM(16), DR(dst));
#endif
}
return push_inst(compiler, ANDI | S(src2) | T(dst) | IMM(0xffff), DR(dst));
}
else if (dst != src2)
SLJIT_ASSERT_STOP();
return SLJIT_SUCCESS;
case SLJIT_NOT:
SLJIT_ASSERT(src1 == TMP_REG1 && !(flags & SRC2_IMM));
if (op & SLJIT_SET_E)
FAIL_IF(push_inst(compiler, NOR | S(src2) | T(src2) | DA(EQUAL_FLAG), EQUAL_FLAG));
if (CHECK_FLAGS(SLJIT_SET_E))
FAIL_IF(push_inst(compiler, NOR | S(src2) | T(src2) | D(dst), DR(dst)));
return SLJIT_SUCCESS;
case SLJIT_CLZ:
SLJIT_ASSERT(src1 == TMP_REG1 && !(flags & SRC2_IMM));
#if (defined SLJIT_MIPS_R1 && SLJIT_MIPS_R1)
if (op & SLJIT_SET_E)
FAIL_IF(push_inst(compiler, CLZ | S(src2) | TA(EQUAL_FLAG) | DA(EQUAL_FLAG), EQUAL_FLAG));
if (CHECK_FLAGS(SLJIT_SET_E))
FAIL_IF(push_inst(compiler, CLZ | S(src2) | T(dst) | D(dst), DR(dst)));
#else
if (SLJIT_UNLIKELY(flags & UNUSED_DEST)) {
FAIL_IF(push_inst(compiler, SRL | T(src2) | DA(EQUAL_FLAG) | SH_IMM(31), EQUAL_FLAG));
return push_inst(compiler, XORI | SA(EQUAL_FLAG) | TA(EQUAL_FLAG) | IMM(1), EQUAL_FLAG);
}
/* Nearly all instructions are unmovable in the following sequence. */
FAIL_IF(push_inst(compiler, ADDU | S(src2) | TA(0) | D(TMP_REG1), DR(TMP_REG1)));
/* Check zero. */
FAIL_IF(push_inst(compiler, BEQ | S(TMP_REG1) | TA(0) | IMM(5), UNMOVABLE_INS));
FAIL_IF(push_inst(compiler, ORI | SA(0) | T(dst) | IMM(32), UNMOVABLE_INS));
FAIL_IF(push_inst(compiler, ADDIU | SA(0) | T(dst) | IMM(-1), DR(dst)));
/* Loop for searching the highest bit. */
FAIL_IF(push_inst(compiler, ADDIU | S(dst) | T(dst) | IMM(1), DR(dst)));
FAIL_IF(push_inst(compiler, BGEZ | S(TMP_REG1) | IMM(-2), UNMOVABLE_INS));
FAIL_IF(push_inst(compiler, SLL | T(TMP_REG1) | D(TMP_REG1) | SH_IMM(1), UNMOVABLE_INS));
if (op & SLJIT_SET_E)
return push_inst(compiler, ADDU | S(dst) | TA(0) | DA(EQUAL_FLAG), EQUAL_FLAG);
#endif
return SLJIT_SUCCESS;
case SLJIT_ADD:
if (flags & SRC2_IMM) {
if (op & SLJIT_SET_O) {
if (src2 >= 0)
FAIL_IF(push_inst(compiler, OR | S(src1) | T(src1) | DA(OVERFLOW_FLAG), OVERFLOW_FLAG));
else
FAIL_IF(push_inst(compiler, NOR | S(src1) | T(src1) | DA(OVERFLOW_FLAG), OVERFLOW_FLAG));
}
if (op & SLJIT_SET_E)
FAIL_IF(push_inst(compiler, ADDIU | S(src1) | TA(EQUAL_FLAG) | IMM(src2), EQUAL_FLAG));
if (op & (SLJIT_SET_C | SLJIT_SET_O)) {
if (src2 >= 0)
FAIL_IF(push_inst(compiler, ORI | S(src1) | TA(ULESS_FLAG) | IMM(src2), ULESS_FLAG));
else {
FAIL_IF(push_inst(compiler, ADDIU | SA(0) | TA(ULESS_FLAG) | IMM(src2), ULESS_FLAG));
FAIL_IF(push_inst(compiler, OR | S(src1) | TA(ULESS_FLAG) | DA(ULESS_FLAG), ULESS_FLAG));
}
}
/* dst may be the same as src1 or src2. */
if (CHECK_FLAGS(SLJIT_SET_E))
FAIL_IF(push_inst(compiler, ADDIU | S(src1) | T(dst) | IMM(src2), DR(dst)));
}
else {
if (op & SLJIT_SET_O)
FAIL_IF(push_inst(compiler, XOR | S(src1) | T(src2) | DA(OVERFLOW_FLAG), OVERFLOW_FLAG));
if (op & SLJIT_SET_E)
FAIL_IF(push_inst(compiler, ADDU | S(src1) | T(src2) | DA(EQUAL_FLAG), EQUAL_FLAG));
if (op & (SLJIT_SET_C | SLJIT_SET_O))
FAIL_IF(push_inst(compiler, OR | S(src1) | T(src2) | DA(ULESS_FLAG), ULESS_FLAG));
/* dst may be the same as src1 or src2. */
if (CHECK_FLAGS(SLJIT_SET_E))
FAIL_IF(push_inst(compiler, ADDU | S(src1) | T(src2) | D(dst), DR(dst)));
}
/* a + b >= a | b (otherwise, the carry should be set to 1). */
if (op & (SLJIT_SET_C | SLJIT_SET_O))
FAIL_IF(push_inst(compiler, SLTU | S(dst) | TA(ULESS_FLAG) | DA(ULESS_FLAG), ULESS_FLAG));
if (!(op & SLJIT_SET_O))
return SLJIT_SUCCESS;
FAIL_IF(push_inst(compiler, SLL | TA(ULESS_FLAG) | D(TMP_REG1) | SH_IMM(31), DR(TMP_REG1)));
FAIL_IF(push_inst(compiler, XOR | S(TMP_REG1) | TA(OVERFLOW_FLAG) | DA(OVERFLOW_FLAG), OVERFLOW_FLAG));
FAIL_IF(push_inst(compiler, XOR | S(dst) | TA(OVERFLOW_FLAG) | DA(OVERFLOW_FLAG), OVERFLOW_FLAG));
return push_inst(compiler, SLL | TA(OVERFLOW_FLAG) | DA(OVERFLOW_FLAG) | SH_IMM(31), OVERFLOW_FLAG);
case SLJIT_ADDC:
if (flags & SRC2_IMM) {
if (op & SLJIT_SET_C) {
if (src2 >= 0)
FAIL_IF(push_inst(compiler, ORI | S(src1) | TA(OVERFLOW_FLAG) | IMM(src2), OVERFLOW_FLAG));
else {
FAIL_IF(push_inst(compiler, ADDIU | SA(0) | TA(OVERFLOW_FLAG) | IMM(src2), OVERFLOW_FLAG));
FAIL_IF(push_inst(compiler, OR | S(src1) | TA(OVERFLOW_FLAG) | DA(OVERFLOW_FLAG), OVERFLOW_FLAG));
}
}
FAIL_IF(push_inst(compiler, ADDIU | S(src1) | T(dst) | IMM(src2), DR(dst)));
} else {
if (op & SLJIT_SET_C)
FAIL_IF(push_inst(compiler, OR | S(src1) | T(src2) | DA(OVERFLOW_FLAG), OVERFLOW_FLAG));
/* dst may be the same as src1 or src2. */
FAIL_IF(push_inst(compiler, ADDU | S(src1) | T(src2) | D(dst), DR(dst)));
}
if (op & SLJIT_SET_C)
FAIL_IF(push_inst(compiler, SLTU | S(dst) | TA(OVERFLOW_FLAG) | DA(OVERFLOW_FLAG), OVERFLOW_FLAG));
FAIL_IF(push_inst(compiler, ADDU | S(dst) | TA(ULESS_FLAG) | D(dst), DR(dst)));
if (!(op & SLJIT_SET_C))
return SLJIT_SUCCESS;
/* Set ULESS_FLAG (dst == 0) && (ULESS_FLAG == 1). */
FAIL_IF(push_inst(compiler, SLTU | S(dst) | TA(ULESS_FLAG) | DA(ULESS_FLAG), ULESS_FLAG));
/* Set carry flag. */
return push_inst(compiler, OR | SA(ULESS_FLAG) | TA(OVERFLOW_FLAG) | DA(ULESS_FLAG), ULESS_FLAG);
case SLJIT_SUB:
if ((flags & SRC2_IMM) && ((op & (SLJIT_SET_U | SLJIT_SET_S)) || src2 == SIMM_MIN)) {
FAIL_IF(push_inst(compiler, ADDIU | SA(0) | T(TMP_REG2) | IMM(src2), DR(TMP_REG2)));
src2 = TMP_REG2;
flags &= ~SRC2_IMM;
}
if (flags & SRC2_IMM) {
if (op & SLJIT_SET_O) {
if (src2 >= 0)
FAIL_IF(push_inst(compiler, OR | S(src1) | T(src1) | DA(OVERFLOW_FLAG), OVERFLOW_FLAG));
else
FAIL_IF(push_inst(compiler, NOR | S(src1) | T(src1) | DA(OVERFLOW_FLAG), OVERFLOW_FLAG));
}
if (op & SLJIT_SET_E)
FAIL_IF(push_inst(compiler, ADDIU | S(src1) | TA(EQUAL_FLAG) | IMM(-src2), EQUAL_FLAG));
if (op & (SLJIT_SET_C | SLJIT_SET_O))
FAIL_IF(push_inst(compiler, SLTIU | S(src1) | TA(ULESS_FLAG) | IMM(src2), ULESS_FLAG));
/* dst may be the same as src1 or src2. */
if (CHECK_FLAGS(SLJIT_SET_E))
FAIL_IF(push_inst(compiler, ADDIU | S(src1) | T(dst) | IMM(-src2), DR(dst)));
}
else {
if (op & SLJIT_SET_O)
FAIL_IF(push_inst(compiler, XOR | S(src1) | T(src2) | DA(OVERFLOW_FLAG), OVERFLOW_FLAG));
if (op & SLJIT_SET_E)
FAIL_IF(push_inst(compiler, SUBU | S(src1) | T(src2) | DA(EQUAL_FLAG), EQUAL_FLAG));
if (op & (SLJIT_SET_U | SLJIT_SET_C | SLJIT_SET_O))
FAIL_IF(push_inst(compiler, SLTU | S(src1) | T(src2) | DA(ULESS_FLAG), ULESS_FLAG));
if (op & SLJIT_SET_U)
FAIL_IF(push_inst(compiler, SLTU | S(src2) | T(src1) | DA(UGREATER_FLAG), UGREATER_FLAG));
if (op & SLJIT_SET_S) {
FAIL_IF(push_inst(compiler, SLT | S(src1) | T(src2) | DA(LESS_FLAG), LESS_FLAG));
FAIL_IF(push_inst(compiler, SLT | S(src2) | T(src1) | DA(GREATER_FLAG), GREATER_FLAG));
}
/* dst may be the same as src1 or src2. */
if (CHECK_FLAGS(SLJIT_SET_E | SLJIT_SET_U | SLJIT_SET_S | SLJIT_SET_C))
FAIL_IF(push_inst(compiler, SUBU | S(src1) | T(src2) | D(dst), DR(dst)));
}
if (!(op & SLJIT_SET_O))
return SLJIT_SUCCESS;
FAIL_IF(push_inst(compiler, SLL | TA(ULESS_FLAG) | D(TMP_REG1) | SH_IMM(31), DR(TMP_REG1)));
FAIL_IF(push_inst(compiler, XOR | S(TMP_REG1) | TA(OVERFLOW_FLAG) | DA(OVERFLOW_FLAG), OVERFLOW_FLAG));
FAIL_IF(push_inst(compiler, XOR | S(dst) | TA(OVERFLOW_FLAG) | DA(OVERFLOW_FLAG), OVERFLOW_FLAG));
return push_inst(compiler, SRL | TA(OVERFLOW_FLAG) | DA(OVERFLOW_FLAG) | SH_IMM(31), OVERFLOW_FLAG);
case SLJIT_SUBC:
if ((flags & SRC2_IMM) && src2 == SIMM_MIN) {
FAIL_IF(push_inst(compiler, ADDIU | SA(0) | T(TMP_REG2) | IMM(src2), DR(TMP_REG2)));
src2 = TMP_REG2;
flags &= ~SRC2_IMM;
}
if (flags & SRC2_IMM) {
if (op & SLJIT_SET_C)
FAIL_IF(push_inst(compiler, SLTIU | S(src1) | TA(OVERFLOW_FLAG) | IMM(src2), OVERFLOW_FLAG));
/* dst may be the same as src1 or src2. */
FAIL_IF(push_inst(compiler, ADDIU | S(src1) | T(dst) | IMM(-src2), DR(dst)));
}
else {
if (op & SLJIT_SET_C)
FAIL_IF(push_inst(compiler, SLTU | S(src1) | T(src2) | DA(OVERFLOW_FLAG), OVERFLOW_FLAG));
/* dst may be the same as src1 or src2. */
FAIL_IF(push_inst(compiler, SUBU | S(src1) | T(src2) | D(dst), DR(dst)));
}
if (op & SLJIT_SET_C)
FAIL_IF(push_inst(compiler, SLTU | S(dst) | TA(ULESS_FLAG) | DA(LESS_FLAG), LESS_FLAG));
FAIL_IF(push_inst(compiler, SUBU | S(dst) | TA(ULESS_FLAG) | D(dst), DR(dst)));
return (op & SLJIT_SET_C) ? push_inst(compiler, OR | SA(OVERFLOW_FLAG) | TA(LESS_FLAG) | DA(ULESS_FLAG), ULESS_FLAG) : SLJIT_SUCCESS;
case SLJIT_MUL:
SLJIT_ASSERT(!(flags & SRC2_IMM));
if (!(op & SLJIT_SET_O)) {
#if (defined SLJIT_MIPS_R1 && SLJIT_MIPS_R1)
return push_inst(compiler, MUL | S(src1) | T(src2) | D(dst), DR(dst));
#else
FAIL_IF(push_inst(compiler, MULT | S(src1) | T(src2), MOVABLE_INS));
return push_inst(compiler, MFLO | D(dst), DR(dst));
#endif
}
FAIL_IF(push_inst(compiler, MULT | S(src1) | T(src2), MOVABLE_INS));
FAIL_IF(push_inst(compiler, MFHI | DA(ULESS_FLAG), ULESS_FLAG));
FAIL_IF(push_inst(compiler, MFLO | D(dst), DR(dst)));
FAIL_IF(push_inst(compiler, SRA | T(dst) | DA(UGREATER_FLAG) | SH_IMM(31), UGREATER_FLAG));
return push_inst(compiler, SUBU | SA(ULESS_FLAG) | TA(UGREATER_FLAG) | DA(OVERFLOW_FLAG), OVERFLOW_FLAG);
case SLJIT_AND:
EMIT_LOGICAL(ANDI, AND);
return SLJIT_SUCCESS;
case SLJIT_OR:
EMIT_LOGICAL(ORI, OR);
return SLJIT_SUCCESS;
case SLJIT_XOR:
EMIT_LOGICAL(XORI, XOR);
return SLJIT_SUCCESS;
case SLJIT_SHL:
EMIT_SHIFT(SLL, SLLV);
return SLJIT_SUCCESS;
case SLJIT_LSHR:
EMIT_SHIFT(SRL, SRLV);
return SLJIT_SUCCESS;
case SLJIT_ASHR:
EMIT_SHIFT(SRA, SRAV);
return SLJIT_SUCCESS;
}
SLJIT_ASSERT_STOP();
return SLJIT_SUCCESS;
}
static SLJIT_INLINE sljit_s32 emit_const(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw init_value)
{
FAIL_IF(push_inst(compiler, LUI | T(dst) | IMM(init_value >> 16), DR(dst)));
return push_inst(compiler, ORI | S(dst) | T(dst) | IMM(init_value), DR(dst));
}
SLJIT_API_FUNC_ATTRIBUTE void sljit_set_jump_addr(sljit_uw addr, sljit_uw new_addr)
{
sljit_ins *inst = (sljit_ins*)addr;
inst[0] = (inst[0] & 0xffff0000) | ((new_addr >> 16) & 0xffff);
inst[1] = (inst[1] & 0xffff0000) | (new_addr & 0xffff);
SLJIT_CACHE_FLUSH(inst, inst + 2);
}
SLJIT_API_FUNC_ATTRIBUTE void sljit_set_const(sljit_uw addr, sljit_sw new_constant)
{
sljit_ins *inst = (sljit_ins*)addr;
inst[0] = (inst[0] & 0xffff0000) | ((new_constant >> 16) & 0xffff);
inst[1] = (inst[1] & 0xffff0000) | (new_constant & 0xffff);
SLJIT_CACHE_FLUSH(inst, inst + 2);
}

View file

@ -1,550 +0,0 @@
/*
* Stack-less Just-In-Time compiler
*
* Copyright 2009-2012 Zoltan Herczeg (hzmester@freemail.hu). All rights reserved.
*
* Redistribution and use in source and binary forms, with or without modification, are
* permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright notice, this list of
* conditions and the following disclaimer.
*
* 2. 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.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDER(S) 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 HOLDER(S) 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.
*/
/* x86 32-bit arch dependent functions. */
static sljit_s32 emit_do_imm(struct sljit_compiler *compiler, sljit_u8 opcode, sljit_sw imm)
{
sljit_u8 *inst;
inst = (sljit_u8*)ensure_buf(compiler, 1 + 1 + sizeof(sljit_sw));
FAIL_IF(!inst);
INC_SIZE(1 + sizeof(sljit_sw));
*inst++ = opcode;
sljit_unaligned_store_sw(inst, imm);
return SLJIT_SUCCESS;
}
static sljit_u8* generate_far_jump_code(struct sljit_jump *jump, sljit_u8 *code_ptr, sljit_s32 type)
{
if (type == SLJIT_JUMP) {
*code_ptr++ = JMP_i32;
jump->addr++;
}
else if (type >= SLJIT_FAST_CALL) {
*code_ptr++ = CALL_i32;
jump->addr++;
}
else {
*code_ptr++ = GROUP_0F;
*code_ptr++ = get_jump_code(type);
jump->addr += 2;
}
if (jump->flags & JUMP_LABEL)
jump->flags |= PATCH_MW;
else
sljit_unaligned_store_sw(code_ptr, jump->u.target - (jump->addr + 4));
code_ptr += 4;
return code_ptr;
}
SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_enter(struct sljit_compiler *compiler,
sljit_s32 options, sljit_s32 args, sljit_s32 scratches, sljit_s32 saveds,
sljit_s32 fscratches, sljit_s32 fsaveds, sljit_s32 local_size)
{
sljit_s32 size;
sljit_u8 *inst;
CHECK_ERROR();
CHECK(check_sljit_emit_enter(compiler, options, args, scratches, saveds, fscratches, fsaveds, local_size));
set_emit_enter(compiler, options, args, scratches, saveds, fscratches, fsaveds, local_size);
compiler->args = args;
compiler->flags_saved = 0;
size = 1 + (scratches > 7 ? (scratches - 7) : 0) + (saveds <= 3 ? saveds : 3);
#if (defined SLJIT_X86_32_FASTCALL && SLJIT_X86_32_FASTCALL)
size += (args > 0 ? (args * 2) : 0) + (args > 2 ? 2 : 0);
#else
size += (args > 0 ? (2 + args * 3) : 0);
#endif
inst = (sljit_u8*)ensure_buf(compiler, 1 + size);
FAIL_IF(!inst);
INC_SIZE(size);
PUSH_REG(reg_map[TMP_REG1]);
#if !(defined SLJIT_X86_32_FASTCALL && SLJIT_X86_32_FASTCALL)
if (args > 0) {
*inst++ = MOV_r_rm;
*inst++ = MOD_REG | (reg_map[TMP_REG1] << 3) | 0x4 /* esp */;
}
#endif
if (saveds > 2 || scratches > 7)
PUSH_REG(reg_map[SLJIT_S2]);
if (saveds > 1 || scratches > 8)
PUSH_REG(reg_map[SLJIT_S1]);
if (saveds > 0 || scratches > 9)
PUSH_REG(reg_map[SLJIT_S0]);
#if (defined SLJIT_X86_32_FASTCALL && SLJIT_X86_32_FASTCALL)
if (args > 0) {
*inst++ = MOV_r_rm;
*inst++ = MOD_REG | (reg_map[SLJIT_S0] << 3) | reg_map[SLJIT_R2];
}
if (args > 1) {
*inst++ = MOV_r_rm;
*inst++ = MOD_REG | (reg_map[SLJIT_S1] << 3) | reg_map[SLJIT_R1];
}
if (args > 2) {
*inst++ = MOV_r_rm;
*inst++ = MOD_DISP8 | (reg_map[SLJIT_S2] << 3) | 0x4 /* esp */;
*inst++ = 0x24;
*inst++ = sizeof(sljit_sw) * (3 + 2); /* saveds >= 3 as well. */
}
#else
if (args > 0) {
*inst++ = MOV_r_rm;
*inst++ = MOD_DISP8 | (reg_map[SLJIT_S0] << 3) | reg_map[TMP_REG1];
*inst++ = sizeof(sljit_sw) * 2;
}
if (args > 1) {
*inst++ = MOV_r_rm;
*inst++ = MOD_DISP8 | (reg_map[SLJIT_S1] << 3) | reg_map[TMP_REG1];
*inst++ = sizeof(sljit_sw) * 3;
}
if (args > 2) {
*inst++ = MOV_r_rm;
*inst++ = MOD_DISP8 | (reg_map[SLJIT_S2] << 3) | reg_map[TMP_REG1];
*inst++ = sizeof(sljit_sw) * 4;
}
#endif
SLJIT_COMPILE_ASSERT(SLJIT_LOCALS_OFFSET >= (2 + 4) * sizeof(sljit_uw), require_at_least_two_words);
#if defined(__APPLE__)
/* Ignore pushed registers and SLJIT_LOCALS_OFFSET when computing the aligned local size. */
saveds = (2 + (scratches > 7 ? (scratches - 7) : 0) + (saveds <= 3 ? saveds : 3)) * sizeof(sljit_uw);
local_size = ((SLJIT_LOCALS_OFFSET + saveds + local_size + 15) & ~15) - saveds;
#else
if (options & SLJIT_DOUBLE_ALIGNMENT) {
local_size = SLJIT_LOCALS_OFFSET + ((local_size + 7) & ~7);
inst = (sljit_u8*)ensure_buf(compiler, 1 + 17);
FAIL_IF(!inst);
INC_SIZE(17);
inst[0] = MOV_r_rm;
inst[1] = MOD_REG | (reg_map[TMP_REG1] << 3) | reg_map[SLJIT_SP];
inst[2] = GROUP_F7;
inst[3] = MOD_REG | (0 << 3) | reg_map[SLJIT_SP];
sljit_unaligned_store_sw(inst + 4, 0x4);
inst[8] = JNE_i8;
inst[9] = 6;
inst[10] = GROUP_BINARY_81;
inst[11] = MOD_REG | (5 << 3) | reg_map[SLJIT_SP];
sljit_unaligned_store_sw(inst + 12, 0x4);
inst[16] = PUSH_r + reg_map[TMP_REG1];
}
else
local_size = SLJIT_LOCALS_OFFSET + ((local_size + 3) & ~3);
#endif
compiler->local_size = local_size;
#ifdef _WIN32
if (local_size > 1024) {
#if (defined SLJIT_X86_32_FASTCALL && SLJIT_X86_32_FASTCALL)
FAIL_IF(emit_do_imm(compiler, MOV_r_i32 + reg_map[SLJIT_R0], local_size));
#else
local_size -= SLJIT_LOCALS_OFFSET;
FAIL_IF(emit_do_imm(compiler, MOV_r_i32 + reg_map[SLJIT_R0], local_size));
FAIL_IF(emit_non_cum_binary(compiler, SUB_r_rm, SUB_rm_r, SUB, SUB_EAX_i32,
SLJIT_SP, 0, SLJIT_SP, 0, SLJIT_IMM, SLJIT_LOCALS_OFFSET));
#endif
FAIL_IF(sljit_emit_ijump(compiler, SLJIT_CALL1, SLJIT_IMM, SLJIT_FUNC_OFFSET(sljit_grow_stack)));
}
#endif
SLJIT_ASSERT(local_size > 0);
return emit_non_cum_binary(compiler, SUB_r_rm, SUB_rm_r, SUB, SUB_EAX_i32,
SLJIT_SP, 0, SLJIT_SP, 0, SLJIT_IMM, local_size);
}
SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_set_context(struct sljit_compiler *compiler,
sljit_s32 options, sljit_s32 args, sljit_s32 scratches, sljit_s32 saveds,
sljit_s32 fscratches, sljit_s32 fsaveds, sljit_s32 local_size)
{
CHECK_ERROR();
CHECK(check_sljit_set_context(compiler, options, args, scratches, saveds, fscratches, fsaveds, local_size));
set_set_context(compiler, options, args, scratches, saveds, fscratches, fsaveds, local_size);
compiler->args = args;
#if defined(__APPLE__)
saveds = (2 + (scratches > 7 ? (scratches - 7) : 0) + (saveds <= 3 ? saveds : 3)) * sizeof(sljit_uw);
compiler->local_size = ((SLJIT_LOCALS_OFFSET + saveds + local_size + 15) & ~15) - saveds;
#else
if (options & SLJIT_DOUBLE_ALIGNMENT)
compiler->local_size = SLJIT_LOCALS_OFFSET + ((local_size + 7) & ~7);
else
compiler->local_size = SLJIT_LOCALS_OFFSET + ((local_size + 3) & ~3);
#endif
return SLJIT_SUCCESS;
}
SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_return(struct sljit_compiler *compiler, sljit_s32 op, sljit_s32 src, sljit_sw srcw)
{
sljit_s32 size;
sljit_u8 *inst;
CHECK_ERROR();
CHECK(check_sljit_emit_return(compiler, op, src, srcw));
SLJIT_ASSERT(compiler->args >= 0);
compiler->flags_saved = 0;
FAIL_IF(emit_mov_before_return(compiler, op, src, srcw));
SLJIT_ASSERT(compiler->local_size > 0);
FAIL_IF(emit_cum_binary(compiler, ADD_r_rm, ADD_rm_r, ADD, ADD_EAX_i32,
SLJIT_SP, 0, SLJIT_SP, 0, SLJIT_IMM, compiler->local_size));
#if !defined(__APPLE__)
if (compiler->options & SLJIT_DOUBLE_ALIGNMENT) {
inst = (sljit_u8*)ensure_buf(compiler, 1 + 3);
FAIL_IF(!inst);
INC_SIZE(3);
inst[0] = MOV_r_rm;
inst[1] = (reg_map[SLJIT_SP] << 3) | 0x4 /* SIB */;
inst[2] = (4 << 3) | reg_map[SLJIT_SP];
}
#endif
size = 2 + (compiler->scratches > 7 ? (compiler->scratches - 7) : 0) +
(compiler->saveds <= 3 ? compiler->saveds : 3);
#if (defined SLJIT_X86_32_FASTCALL && SLJIT_X86_32_FASTCALL)
if (compiler->args > 2)
size += 2;
#else
if (compiler->args > 0)
size += 2;
#endif
inst = (sljit_u8*)ensure_buf(compiler, 1 + size);
FAIL_IF(!inst);
INC_SIZE(size);
if (compiler->saveds > 0 || compiler->scratches > 9)
POP_REG(reg_map[SLJIT_S0]);
if (compiler->saveds > 1 || compiler->scratches > 8)
POP_REG(reg_map[SLJIT_S1]);
if (compiler->saveds > 2 || compiler->scratches > 7)
POP_REG(reg_map[SLJIT_S2]);
POP_REG(reg_map[TMP_REG1]);
#if (defined SLJIT_X86_32_FASTCALL && SLJIT_X86_32_FASTCALL)
if (compiler->args > 2)
RET_I16(sizeof(sljit_sw));
else
RET();
#else
RET();
#endif
return SLJIT_SUCCESS;
}
/* --------------------------------------------------------------------- */
/* Operators */
/* --------------------------------------------------------------------- */
/* Size contains the flags as well. */
static sljit_u8* emit_x86_instruction(struct sljit_compiler *compiler, sljit_s32 size,
/* The register or immediate operand. */
sljit_s32 a, sljit_sw imma,
/* The general operand (not immediate). */
sljit_s32 b, sljit_sw immb)
{
sljit_u8 *inst;
sljit_u8 *buf_ptr;
sljit_s32 flags = size & ~0xf;
sljit_s32 inst_size;
/* Both cannot be switched on. */
SLJIT_ASSERT((flags & (EX86_BIN_INS | EX86_SHIFT_INS)) != (EX86_BIN_INS | EX86_SHIFT_INS));
/* Size flags not allowed for typed instructions. */
SLJIT_ASSERT(!(flags & (EX86_BIN_INS | EX86_SHIFT_INS)) || (flags & (EX86_BYTE_ARG | EX86_HALF_ARG)) == 0);
/* Both size flags cannot be switched on. */
SLJIT_ASSERT((flags & (EX86_BYTE_ARG | EX86_HALF_ARG)) != (EX86_BYTE_ARG | EX86_HALF_ARG));
/* SSE2 and immediate is not possible. */
SLJIT_ASSERT(!(a & SLJIT_IMM) || !(flags & EX86_SSE2));
SLJIT_ASSERT((flags & (EX86_PREF_F2 | EX86_PREF_F3)) != (EX86_PREF_F2 | EX86_PREF_F3)
&& (flags & (EX86_PREF_F2 | EX86_PREF_66)) != (EX86_PREF_F2 | EX86_PREF_66)
&& (flags & (EX86_PREF_F3 | EX86_PREF_66)) != (EX86_PREF_F3 | EX86_PREF_66));
size &= 0xf;
inst_size = size;
if (flags & (EX86_PREF_F2 | EX86_PREF_F3))
inst_size++;
if (flags & EX86_PREF_66)
inst_size++;
/* Calculate size of b. */
inst_size += 1; /* mod r/m byte. */
if (b & SLJIT_MEM) {
if ((b & REG_MASK) == SLJIT_UNUSED)
inst_size += sizeof(sljit_sw);
else if (immb != 0 && !(b & OFFS_REG_MASK)) {
/* Immediate operand. */
if (immb <= 127 && immb >= -128)
inst_size += sizeof(sljit_s8);
else
inst_size += sizeof(sljit_sw);
}
if ((b & REG_MASK) == SLJIT_SP && !(b & OFFS_REG_MASK))
b |= TO_OFFS_REG(SLJIT_SP);
if ((b & OFFS_REG_MASK) != SLJIT_UNUSED)
inst_size += 1; /* SIB byte. */
}
/* Calculate size of a. */
if (a & SLJIT_IMM) {
if (flags & EX86_BIN_INS) {
if (imma <= 127 && imma >= -128) {
inst_size += 1;
flags |= EX86_BYTE_ARG;
} else
inst_size += 4;
}
else if (flags & EX86_SHIFT_INS) {
imma &= 0x1f;
if (imma != 1) {
inst_size ++;
flags |= EX86_BYTE_ARG;
}
} else if (flags & EX86_BYTE_ARG)
inst_size++;
else if (flags & EX86_HALF_ARG)
inst_size += sizeof(short);
else
inst_size += sizeof(sljit_sw);
}
else
SLJIT_ASSERT(!(flags & EX86_SHIFT_INS) || a == SLJIT_PREF_SHIFT_REG);
inst = (sljit_u8*)ensure_buf(compiler, 1 + inst_size);
PTR_FAIL_IF(!inst);
/* Encoding the byte. */
INC_SIZE(inst_size);
if (flags & EX86_PREF_F2)
*inst++ = 0xf2;
if (flags & EX86_PREF_F3)
*inst++ = 0xf3;
if (flags & EX86_PREF_66)
*inst++ = 0x66;
buf_ptr = inst + size;
/* Encode mod/rm byte. */
if (!(flags & EX86_SHIFT_INS)) {
if ((flags & EX86_BIN_INS) && (a & SLJIT_IMM))
*inst = (flags & EX86_BYTE_ARG) ? GROUP_BINARY_83 : GROUP_BINARY_81;
if ((a & SLJIT_IMM) || (a == 0))
*buf_ptr = 0;
else if (!(flags & EX86_SSE2_OP1))
*buf_ptr = reg_map[a] << 3;
else
*buf_ptr = a << 3;
}
else {
if (a & SLJIT_IMM) {
if (imma == 1)
*inst = GROUP_SHIFT_1;
else
*inst = GROUP_SHIFT_N;
} else
*inst = GROUP_SHIFT_CL;
*buf_ptr = 0;
}
if (!(b & SLJIT_MEM))
*buf_ptr++ |= MOD_REG + ((!(flags & EX86_SSE2_OP2)) ? reg_map[b] : b);
else if ((b & REG_MASK) != SLJIT_UNUSED) {
if ((b & OFFS_REG_MASK) == SLJIT_UNUSED || (b & OFFS_REG_MASK) == TO_OFFS_REG(SLJIT_SP)) {
if (immb != 0) {
if (immb <= 127 && immb >= -128)
*buf_ptr |= 0x40;
else
*buf_ptr |= 0x80;
}
if ((b & OFFS_REG_MASK) == SLJIT_UNUSED)
*buf_ptr++ |= reg_map[b & REG_MASK];
else {
*buf_ptr++ |= 0x04;
*buf_ptr++ = reg_map[b & REG_MASK] | (reg_map[OFFS_REG(b)] << 3);
}
if (immb != 0) {
if (immb <= 127 && immb >= -128)
*buf_ptr++ = immb; /* 8 bit displacement. */
else {
sljit_unaligned_store_sw(buf_ptr, immb); /* 32 bit displacement. */
buf_ptr += sizeof(sljit_sw);
}
}
}
else {
*buf_ptr++ |= 0x04;
*buf_ptr++ = reg_map[b & REG_MASK] | (reg_map[OFFS_REG(b)] << 3) | (immb << 6);
}
}
else {
*buf_ptr++ |= 0x05;
sljit_unaligned_store_sw(buf_ptr, immb); /* 32 bit displacement. */
buf_ptr += sizeof(sljit_sw);
}
if (a & SLJIT_IMM) {
if (flags & EX86_BYTE_ARG)
*buf_ptr = imma;
else if (flags & EX86_HALF_ARG)
sljit_unaligned_store_s16(buf_ptr, imma);
else if (!(flags & EX86_SHIFT_INS))
sljit_unaligned_store_sw(buf_ptr, imma);
}
return !(flags & EX86_SHIFT_INS) ? inst : (inst + 1);
}
/* --------------------------------------------------------------------- */
/* Call / return instructions */
/* --------------------------------------------------------------------- */
static SLJIT_INLINE sljit_s32 call_with_args(struct sljit_compiler *compiler, sljit_s32 type)
{
sljit_u8 *inst;
#if (defined SLJIT_X86_32_FASTCALL && SLJIT_X86_32_FASTCALL)
inst = (sljit_u8*)ensure_buf(compiler, type >= SLJIT_CALL3 ? 1 + 2 + 1 : 1 + 2);
FAIL_IF(!inst);
INC_SIZE(type >= SLJIT_CALL3 ? 2 + 1 : 2);
if (type >= SLJIT_CALL3)
PUSH_REG(reg_map[SLJIT_R2]);
*inst++ = MOV_r_rm;
*inst++ = MOD_REG | (reg_map[SLJIT_R2] << 3) | reg_map[SLJIT_R0];
#else
inst = (sljit_u8*)ensure_buf(compiler, 1 + 4 * (type - SLJIT_CALL0));
FAIL_IF(!inst);
INC_SIZE(4 * (type - SLJIT_CALL0));
*inst++ = MOV_rm_r;
*inst++ = MOD_DISP8 | (reg_map[SLJIT_R0] << 3) | 0x4 /* SIB */;
*inst++ = (0x4 /* none*/ << 3) | reg_map[SLJIT_SP];
*inst++ = 0;
if (type >= SLJIT_CALL2) {
*inst++ = MOV_rm_r;
*inst++ = MOD_DISP8 | (reg_map[SLJIT_R1] << 3) | 0x4 /* SIB */;
*inst++ = (0x4 /* none*/ << 3) | reg_map[SLJIT_SP];
*inst++ = sizeof(sljit_sw);
}
if (type >= SLJIT_CALL3) {
*inst++ = MOV_rm_r;
*inst++ = MOD_DISP8 | (reg_map[SLJIT_R2] << 3) | 0x4 /* SIB */;
*inst++ = (0x4 /* none*/ << 3) | reg_map[SLJIT_SP];
*inst++ = 2 * sizeof(sljit_sw);
}
#endif
return SLJIT_SUCCESS;
}
SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_fast_enter(struct sljit_compiler *compiler, sljit_s32 dst, sljit_sw dstw)
{
sljit_u8 *inst;
CHECK_ERROR();
CHECK(check_sljit_emit_fast_enter(compiler, dst, dstw));
ADJUST_LOCAL_OFFSET(dst, dstw);
CHECK_EXTRA_REGS(dst, dstw, (void)0);
/* For UNUSED dst. Uncommon, but possible. */
if (dst == SLJIT_UNUSED)
dst = TMP_REG1;
if (FAST_IS_REG(dst)) {
/* Unused dest is possible here. */
inst = (sljit_u8*)ensure_buf(compiler, 1 + 1);
FAIL_IF(!inst);
INC_SIZE(1);
POP_REG(reg_map[dst]);
return SLJIT_SUCCESS;
}
/* Memory. */
inst = emit_x86_instruction(compiler, 1, 0, 0, dst, dstw);
FAIL_IF(!inst);
*inst++ = POP_rm;
return SLJIT_SUCCESS;
}
SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_fast_return(struct sljit_compiler *compiler, sljit_s32 src, sljit_sw srcw)
{
sljit_u8 *inst;
CHECK_ERROR();
CHECK(check_sljit_emit_fast_return(compiler, src, srcw));
ADJUST_LOCAL_OFFSET(src, srcw);
CHECK_EXTRA_REGS(src, srcw, (void)0);
if (FAST_IS_REG(src)) {
inst = (sljit_u8*)ensure_buf(compiler, 1 + 1 + 1);
FAIL_IF(!inst);
INC_SIZE(1 + 1);
PUSH_REG(reg_map[src]);
}
else if (src & SLJIT_MEM) {
inst = emit_x86_instruction(compiler, 1, 0, 0, src, srcw);
FAIL_IF(!inst);
*inst++ = GROUP_FF;
*inst |= PUSH_rm;
inst = (sljit_u8*)ensure_buf(compiler, 1 + 1);
FAIL_IF(!inst);
INC_SIZE(1);
}
else {
/* SLJIT_IMM. */
inst = (sljit_u8*)ensure_buf(compiler, 1 + 5 + 1);
FAIL_IF(!inst);
INC_SIZE(5 + 1);
*inst++ = PUSH_i32;
sljit_unaligned_store_sw(inst, srcw);
inst += sizeof(sljit_sw);
}
RET();
return SLJIT_SUCCESS;
}

View file

@ -109,8 +109,9 @@ while (<STDIN>)
# Handling .sp is subtle. If it is inside a literal section, do nothing if
# the next line is a non literal text line; similarly, if not inside a
# literal section, do nothing if a literal follows, unless we are inside
# a .nf/.ne section. The point being that the <pre> and </pre> that delimit
# literal sections will do the spacing. Always skip if no previous output.
# a .nf/.fi section or about to enter one. The point being that the <pre>
# and </pre> that delimit literal sections will do the spacing. Always skip
# if no previous output.
elsif (/^\.sp/)
{
@ -123,7 +124,7 @@ while (<STDIN>)
}
else
{
print TEMP "<br>\n<br>\n" if ($innf || !/^[\s.]/);
print TEMP "<br>\n<br>\n" if ($innf || /^\.nf/ || !/^[\s.]/);
}
redo; # Now process the lookahead line we just read
}

View file

@ -8,7 +8,7 @@ Email domain: cam.ac.uk
University of Cambridge Computing Service,
Cambridge, England.
Copyright (c) 1997-2016 University of Cambridge
Copyright (c) 1997-2018 University of Cambridge
All rights reserved
@ -19,7 +19,7 @@ Written by: Zoltan Herczeg
Email local part: hzmester
Emain domain: freemail.hu
Copyright(c) 2010-2016 Zoltan Herczeg
Copyright(c) 2010-2018 Zoltan Herczeg
All rights reserved.
@ -30,7 +30,7 @@ Written by: Zoltan Herczeg
Email local part: hzmester
Emain domain: freemail.hu
Copyright(c) 2009-2016 Zoltan Herczeg
Copyright(c) 2009-2018 Zoltan Herczeg
All rights reserved.
####

View file

@ -74,6 +74,14 @@
# 2016-03-01 PH applied Chris Wilson's patch for MSVC static
# 2016-06-24 PH applied Chris Wilson's second patch, putting the first under
# a new option instead of being unconditional.
# 2016-10-05 PH fixed a typo (PCRE should be PCRE2) in above patch
# fix by David Gaussmann
# 2016-10-07 PH added PCREGREP_MAX_BUFSIZE
# 2017-03-11 PH turned HEAP_MATCH_RECURSE into a NO-OP for 10.30
# 2017-04-08 PH added HEAP_LIMIT
# 2017-06-15 ZH added SUPPORT_JIT_SEALLOC support
# 2018-06-19 PH added checks for stdint.h and inttypes.h
# 2018-06-27 PH added Daniel's patch to increase the stack for MSVC
PROJECT(PCRE2 C)
@ -107,6 +115,18 @@ CHECK_INCLUDE_FILE(sys/types.h HAVE_SYS_TYPES_H)
CHECK_INCLUDE_FILE(unistd.h HAVE_UNISTD_H)
CHECK_INCLUDE_FILE(windows.h HAVE_WINDOWS_H)
IF(HAVE_INTTYPES_H)
SET(PCRE2_HAVE_INTTYPES_H 1)
ELSE(HAVE_INTTYPES_H)
SET(PCRE2_HAVE_INTTYPES_H 0)
ENDIF(HAVE_INTTYPES_H)
IF(HAVE_STDINT_H)
SET(PCRE2_HAVE_STDINT_H 1)
ELSE(HAVE_STDINT_H)
SET(PCRE2_HAVE_STDINT_H 0)
ENDIF(HAVE_STDINT_H)
CHECK_FUNCTION_EXISTS(bcopy HAVE_BCOPY)
CHECK_FUNCTION_EXISTS(memmove HAVE_MEMMOVE)
CHECK_FUNCTION_EXISTS(strerror HAVE_STRERROR)
@ -139,24 +159,33 @@ SET(PCRE2_LINK_SIZE "2" CACHE STRING
SET(PCRE2_PARENS_NEST_LIMIT "250" CACHE STRING
"Default nested parentheses limit. See PARENS_NEST_LIMIT in config.h.in for details.")
SET(PCRE2_HEAP_LIMIT "20000000" CACHE STRING
"Default limit on heap memory (kibibytes). See HEAP_LIMIT in config.h.in for details.")
SET(PCRE2_MATCH_LIMIT "10000000" CACHE STRING
"Default limit on internal looping. See MATCH_LIMIT in config.h.in for details.")
SET(PCRE2_MATCH_LIMIT_RECURSION "MATCH_LIMIT" CACHE STRING
"Default limit on internal recursion. See MATCH_LIMIT_RECURSION in config.h.in for details.")
SET(PCRE2_MATCH_LIMIT_DEPTH "MATCH_LIMIT" CACHE STRING
"Default limit on internal depth of search. See MATCH_LIMIT_DEPTH in config.h.in for details.")
SET(PCRE2GREP_BUFSIZE "20480" CACHE STRING
"Buffer size parameter for pcre2grep. See PCRE2GREP_BUFSIZE in config.h.in for details.")
"Buffer starting size parameter for pcre2grep. See PCRE2GREP_BUFSIZE in config.h.in for details.")
SET(PCRE2GREP_MAX_BUFSIZE "1048576" CACHE STRING
"Buffer maximum size parameter for pcre2grep. See PCRE2GREP_MAX_BUFSIZE in config.h.in for details.")
SET(PCRE2_NEWLINE "LF" CACHE STRING
"What to recognize as a newline (one of CR, LF, CRLF, ANY, ANYCRLF).")
"What to recognize as a newline (one of CR, LF, CRLF, ANY, ANYCRLF, NUL).")
SET(PCRE2_HEAP_MATCH_RECURSE OFF CACHE BOOL
"If ON, then don't use stack recursion when matching. See HEAP_MATCH_RECURSE in config.h.in for details.")
"Obsolete option: do not use")
SET(PCRE2_SUPPORT_JIT OFF CACHE BOOL
"Enable support for Just-in-time compiling.")
SET(PCRE2_SUPPORT_JIT_SEALLOC OFF CACHE BOOL
"Enable SELinux compatible execmem allocator in JIT.")
SET(PCRE2_SUPPORT_PCRE2GREP_JIT ON CACHE BOOL
"Enable use of Just-in-time compiling in pcre2grep.")
@ -190,7 +219,7 @@ IF (MINGW)
ENDIF(MINGW)
IF(MSVC)
OPTION(PCRE_STATIC_RUNTIME
OPTION(PCRE2_STATIC_RUNTIME
"ON=Compile against the static runtime (/MT)."
OFF)
OPTION(INSTALL_MSVC_PDB
@ -277,6 +306,10 @@ IF(PCRE2_SUPPORT_JIT)
SET(SUPPORT_JIT 1)
ENDIF(PCRE2_SUPPORT_JIT)
IF(PCRE2_SUPPORT_JIT_SEALLOC)
SET(SLJIT_PROT_EXECUTABLE_ALLOCATOR 1)
ENDIF(PCRE2_SUPPORT_JIT_SEALLOC)
IF(PCRE2_SUPPORT_PCRE2GREP_JIT)
SET(SUPPORT_PCRE2GREP_JIT 1)
ENDIF(PCRE2_SUPPORT_PCRE2GREP_JIT)
@ -333,6 +366,9 @@ ENDIF(PCRE2_NEWLINE STREQUAL "ANY")
IF(PCRE2_NEWLINE STREQUAL "ANYCRLF")
SET(NEWLINE_DEFAULT "5")
ENDIF(PCRE2_NEWLINE STREQUAL "ANYCRLF")
IF(PCRE2_NEWLINE STREQUAL "NUL")
SET(NEWLINE_DEFAULT "6")
ENDIF(PCRE2_NEWLINE STREQUAL "NUL")
IF(NEWLINE_DEFAULT STREQUAL "")
MESSAGE(FATAL_ERROR "The PCRE2_NEWLINE variable must be set to one of the following values: \"LF\", \"CR\", \"CRLF\", \"ANY\", \"ANYCRLF\".")
@ -347,10 +383,6 @@ IF(PCRE2_EBCDIC_NL25)
SET(EBCDIC_NL25 1)
ENDIF(PCRE2_EBCDIC_NL25)
IF(PCRE2_HEAP_MATCH_RECURSE)
SET(HEAP_MATCH_RECURSE 1)
ENDIF(PCRE2_HEAP_MATCH_RECURSE)
# Output files
CONFIGURE_FILE(config-cmake.h.in
@ -411,8 +443,10 @@ SET(PCRE2_SOURCES
src/pcre2_compile.c
src/pcre2_config.c
src/pcre2_context.c
src/pcre2_convert.c
src/pcre2_dfa_match.c
src/pcre2_error.c
src/pcre2_extuni.c
src/pcre2_find_bracket.c
src/pcre2_jit_compile.c
src/pcre2_maketables.c
@ -505,18 +539,18 @@ ADD_LIBRARY(pcre2-8 ${PCRE2_HEADERS} ${PCRE2_SOURCES} ${PROJECT_BINARY_DIR}/conf
SET_PROPERTY(TARGET pcre2-8
PROPERTY COMPILE_DEFINITIONS PCRE2_CODE_UNIT_WIDTH=8)
SET(targets ${targets} pcre2-8)
ADD_LIBRARY(pcre2posix ${PCRE2POSIX_HEADERS} ${PCRE2POSIX_SOURCES})
SET_PROPERTY(TARGET pcre2posix
ADD_LIBRARY(pcre2-posix ${PCRE2POSIX_HEADERS} ${PCRE2POSIX_SOURCES})
SET_PROPERTY(TARGET pcre2-posix
PROPERTY COMPILE_DEFINITIONS PCRE2_CODE_UNIT_WIDTH=8)
SET(targets ${targets} pcre2posix)
TARGET_LINK_LIBRARIES(pcre2posix pcre2-8)
SET(targets ${targets} pcre2-posix)
TARGET_LINK_LIBRARIES(pcre2-posix pcre2-8)
IF(MINGW AND NOT PCRE2_STATIC)
IF(NON_STANDARD_LIB_PREFIX)
SET_TARGET_PROPERTIES(pcre2-8 pcre2posix PROPERTIES PREFIX "")
SET_TARGET_PROPERTIES(pcre2-8 pcre2-posix PROPERTIES PREFIX "")
ENDIF(NON_STANDARD_LIB_PREFIX)
IF(NON_STANDARD_LIB_SUFFIX)
SET_TARGET_PROPERTIES(pcre2-8 pcre2posix PROPERTIES SUFFIX "-0.dll")
SET_TARGET_PROPERTIES(pcre2-8 pcre2-posix PROPERTIES SUFFIX "-0.dll")
ENDIF(NON_STANDARD_LIB_SUFFIX)
ENDIF(MINGW AND NOT PCRE2_STATIC)
ENDIF(PCRE2_BUILD_PCRE2_8)
@ -564,7 +598,7 @@ IF(PCRE2_BUILD_PCRE2GREP)
SET_PROPERTY(TARGET pcre2grep
PROPERTY COMPILE_DEFINITIONS PCRE2_CODE_UNIT_WIDTH=8)
SET(targets ${targets} pcre2grep)
TARGET_LINK_LIBRARIES(pcre2grep pcre2posix ${PCRE2GREP_LIBS})
TARGET_LINK_LIBRARIES(pcre2grep pcre2-posix ${PCRE2GREP_LIBS})
ENDIF(PCRE2_BUILD_PCRE2GREP)
# Testing
@ -574,10 +608,17 @@ IF(PCRE2_BUILD_TESTS)
SET(PCRE2TEST_SOURCES src/pcre2test.c)
IF(MSVC)
# This is needed to avoid a stack overflow error in the standard tests. The
# flag should be indicated with a forward-slash instead of a hyphen, but
# then CMake treats it as a file path.
SET(PCRE2TEST_LINKER_FLAGS -STACK:2500000)
ENDIF(MSVC)
ADD_EXECUTABLE(pcre2test ${PCRE2TEST_SOURCES})
SET(targets ${targets} pcre2test)
IF(PCRE2_BUILD_PCRE2_8)
LIST(APPEND PCRE2TEST_LIBS pcre2posix pcre2-8)
LIST(APPEND PCRE2TEST_LIBS pcre2-posix pcre2-8)
ENDIF(PCRE2_BUILD_PCRE2_8)
IF(PCRE2_BUILD_PCRE2_16)
LIST(APPEND PCRE2TEST_LIBS pcre2-16)
@ -585,7 +626,7 @@ IF(PCRE2_BUILD_TESTS)
IF(PCRE2_BUILD_PCRE2_32)
LIST(APPEND PCRE2TEST_LIBS pcre2-32)
ENDIF(PCRE2_BUILD_PCRE2_32)
TARGET_LINK_LIBRARIES(pcre2test ${PCRE2TEST_LIBS})
TARGET_LINK_LIBRARIES(pcre2test ${PCRE2TEST_LIBS} ${PCRE2TEST_LINKER_FLAGS})
IF(PCRE2_SUPPORT_JIT)
ADD_EXECUTABLE(pcre2_jit_test src/pcre2_jit_test.c)
@ -732,6 +773,10 @@ ELSE(BUILD_SHARED_LIBS)
SET(BUILD_STATIC_LIBS ON)
ENDIF(BUILD_SHARED_LIBS)
IF(PCRE2_HEAP_MATCH_RECURSE)
MESSAGE(WARNING "HEAP_MATCH_RECURSE is obsolete and does nothing.")
ENDIF(PCRE2_HEAP_MATCH_RECURSE)
IF(PCRE2_SHOW_REPORT)
STRING(TOUPPER "${CMAKE_BUILD_TYPE}" buildtype)
IF (CMAKE_C_FLAGS)
@ -749,6 +794,7 @@ IF(PCRE2_SHOW_REPORT)
MESSAGE(STATUS " Build 16 bit PCRE2 library ...... : ${PCRE2_BUILD_PCRE2_16}")
MESSAGE(STATUS " Build 32 bit PCRE2 library ...... : ${PCRE2_BUILD_PCRE2_32}")
MESSAGE(STATUS " Enable JIT compiling support .... : ${PCRE2_SUPPORT_JIT}")
MESSAGE(STATUS " Use SELinux allocator in JIT .... : ${PCRE2_SUPPORT_JIT_SEALLOC}")
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}")
@ -756,11 +802,11 @@ IF(PCRE2_SHOW_REPORT)
MESSAGE(STATUS " EBCDIC coding ................... : ${PCRE2_EBCDIC}")
MESSAGE(STATUS " EBCDIC coding with NL=0x25 ...... : ${PCRE2_EBCDIC_NL25}")
MESSAGE(STATUS " Rebuild char tables ............. : ${PCRE2_REBUILD_CHARTABLES}")
MESSAGE(STATUS " Use heap recursion .............. : ${PCRE2_HEAP_MATCH_RECURSE}")
MESSAGE(STATUS " Internal link size .............. : ${PCRE2_LINK_SIZE}")
MESSAGE(STATUS " Parentheses nest limit .......... : ${PCRE2_PARENS_NEST_LIMIT}")
MESSAGE(STATUS " Heap limit ...................... : ${PCRE2_HEAP_LIMIT}")
MESSAGE(STATUS " Match limit ..................... : ${PCRE2_MATCH_LIMIT}")
MESSAGE(STATUS " Match limit recursion ........... : ${PCRE2_MATCH_LIMIT_RECURSION}")
MESSAGE(STATUS " Match depth limit ............... : ${PCRE2_MATCH_LIMIT_DEPTH}")
MESSAGE(STATUS " Build shared libs ............... : ${BUILD_SHARED_LIBS}")
MESSAGE(STATUS " Build static libs ............... : ${BUILD_STATIC_LIBS}")
MESSAGE(STATUS " Build pcre2grep ................. : ${PCRE2_BUILD_PCRE2GREP}")

1867
pcre2-10.32/ChangeLog vendored Normal file

File diff suppressed because it is too large Load diff

View file

@ -7,8 +7,8 @@ but with a revised (and incompatible) API. To avoid confusion, the original
library is referred to as PCRE1 below. For information about testing PCRE2, see
the pcre2test documentation and the comment at the head of the RunTest file.
PCRE1 releases were up to 8.3x when PCRE2 was developed. The 8.xx series will
continue for bugfixes if necessary. PCRE2 releases started at 10.00 to avoid
PCRE1 releases were up to 8.3x when PCRE2 was developed, and later bug fix
releases remain in the 8.xx series. PCRE2 releases started at 10.00 to avoid
confusion with PCRE1.
@ -16,19 +16,20 @@ Historical note 1
-----------------
Many years ago I implemented some regular expression functions to an algorithm
suggested by Martin Richards. These were not Unix-like in form, and were quite
restricted in what they could do by comparison with Perl. The interesting part
about the algorithm was that the amount of space required to hold the compiled
form of an expression was known in advance. The code to apply an expression did
not operate by backtracking, as the original Henry Spencer code and current
PCRE2 and Perl code does, but instead checked all possibilities simultaneously
by keeping a list of current states and checking all of them as it advanced
through the subject string. In the terminology of Jeffrey Friedl's book, it was
a "DFA algorithm", though it was not a traditional Finite State Machine (FSM).
When the pattern was all used up, all remaining states were possible matches,
and the one matching the longest subset of the subject string was chosen. This
did not necessarily maximize the individual wild portions of the pattern, as is
expected in Unix and Perl-style regular expressions.
suggested by Martin Richards. The rather simple patterns were not Unix-like in
form, and were quite restricted in what they could do by comparison with Perl.
The interesting part about the algorithm was that the amount of space required
to hold the compiled form of an expression was known in advance. The code to
apply an expression did not operate by backtracking, as the original Henry
Spencer code and current PCRE2 and Perl code does, but instead checked all
possibilities simultaneously by keeping a list of current states and checking
all of them as it advanced through the subject string. In the terminology of
Jeffrey Friedl's book, it was a "DFA algorithm", though it was not a
traditional Finite State Machine (FSM). When the pattern was all used up, all
remaining states were possible matches, and the one matching the longest subset
of the subject string was chosen. This did not necessarily maximize the
individual wild portions of the pattern, as is expected in Unix and Perl-style
regular expressions.
Historical note 2
@ -47,18 +48,20 @@ Friedl's terminology.
OK, here's the real stuff
-------------------------
For the set of functions that formed the original PCRE1 library (which are
unrelated to those mentioned above), I tried at first to invent an algorithm
that used an amount of store bounded by a multiple of the number of characters
in the pattern, to save on compiling time. However, because of the greater
complexity in Perl regular expressions, I couldn't do this. In any case, a
first pass through the pattern is helpful for other reasons.
For the set of functions that formed the original PCRE1 library in 1997 (which
are unrelated to those mentioned above), I tried at first to invent an
algorithm that used an amount of store bounded by a multiple of the number of
characters in the pattern, to save on compiling time. However, because of the
greater complexity in Perl regular expressions, I couldn't do this, even though
the then current Perl 5.004 patterns were much simpler than those supported
nowadays. In any case, a first pass through the pattern is helpful for other
reasons.
Support for 16-bit and 32-bit data strings
-------------------------------------------
The library can be compiled in any combination of 8-bit, 16-bit or 32-bit
The PCRE2 library can be compiled in any combination of 8-bit, 16-bit or 32-bit
modes, creating up to three different libraries. In the description that
follows, the word "short" is used for a 16-bit data quantity, and the phrase
"code unit" is used for a quantity that is a byte in 8-bit mode, a short in
@ -85,12 +88,12 @@ had become very complicated and hard to maintain. Indeed one of the early
things I did for 6.8 was to fix Yet Another Bug in the memory computation. Then
I had a flash of inspiration as to how I could run the real compile function in
a "fake" mode that enables it to compute how much memory it would need, while
actually only ever using a few hundred bytes of working memory, and without too
in most cases only ever using a small amount of working memory, and without too
many tests of the mode that might slow it down. So I refactored the compiling
functions to work this way. This got rid of about 600 lines of source. It
should make future maintenance and development easier. As this was such a major
change, I never released 6.8, instead upping the number to 7.0 (other quite
major changes were also present in the 7.0 release).
functions to work this way. This got rid of about 600 lines of source and made
further maintenance and development easier. As this was such a major change, I
never released 6.8, instead upping the number to 7.0 (other quite major changes
were also present in the 7.0 release).
A side effect of this work was that the previous limit of 200 on the nesting
depth of parentheses was removed. However, there was a downside: compiling ran
@ -104,20 +107,209 @@ system stack used by the compile function, which uses recursive function calls
for nested parenthesized groups. This is a safety feature for environments with
small stacks where the patterns are provided by users.
History repeated itself for release 10.20. A number of bugs relating to named
subpatterns had been discovered by fuzzers. Most of these were related to the
handling of forward references when it was not known if the named pattern was
Yet another pattern scan
------------------------
History repeated itself for PCRE2 release 10.20. A number of bugs relating to
named subpatterns had been discovered by fuzzers. Most of these were related to
the handling of forward references when it was not known if the named group was
unique. (References to non-unique names use a different opcode and more
memory.) The use of duplicate group numbers (the (?| facility) also caused
issues.
issues.
To get around these problems I adopted a new approach by adding a third pass,
really a "pre-pass", over the pattern, which does nothing other than identify
all the named subpatterns and their corresponding group numbers. This means
that the actual compile (both pre-pass and real compile) have full knowledge of
group names and numbers throughout. Several dozen lines of messy code were
eliminated, though the new pre-pass is not short (skipping over [] classes is
complicated).
To get around these problems I adopted a new approach by adding a third pass
over the pattern (really a "pre-pass"), which did nothing other than identify
all the named subpatterns and their corresponding group numbers. This means
that the actual compile (both the memory-computing dummy run and the real
compile) has full knowledge of group names and numbers throughout. Several
dozen lines of messy code were eliminated, though the new pre-pass was not
short. In particular, parsing and skipping over [] classes is complicated.
While working on 10.22 I realized that I could simplify yet again by moving
more of the parsing into the pre-pass, thus avoiding doing it in two places, so
after 10.22 was released, the code underwent yet another big refactoring. This
is how it is from 10.23 onwards:
The function called parse_regex() scans the pattern characters, parsing them
into literal data and meta characters. It converts escapes such as \x{123}
into literals, handles \Q...\E, and skips over comments and non-significant
white space. The result of the scanning is put into a vector of 32-bit unsigned
integers. Values less than 0x80000000 are literal data. Higher values represent
meta-characters. The top 16-bits of such values identify the meta-character,
and these are given names such as META_CAPTURE. The lower 16-bits are available
for data, for example, the capturing group number. The only situation in which
literal data values greater than 0x7fffffff can appear is when the 32-bit
library is running in non-UTF mode. This is handled by having a special
meta-character that is followed by the 32-bit data value.
The size of the parsed pattern vector, when auto-callouts are not enabled, is
bounded by the length of the pattern (with one exception). The code is written
so that each item in the pattern uses no more vector elements than the number
of code units in the item itself. The exception is the aforementioned large
32-bit number handling. For this reason, 32-bit non-UTF patterns are scanned in
advance to check for such values. When auto-callouts are enabled, the generous
assumption is made that there will be a callout for each pattern code unit
(which of course is only actually true if all code units are literals) plus one
at the end. There is a default parsed pattern vector on the system stack, but
if this is not big enough, heap memory is used.
As before, the actual compiling function is run twice, the first time to
determine the amount of memory needed for the final compiled pattern. It
now processes the parsed pattern vector, not the pattern itself, although some
of the parsed items refer to strings in the pattern - for example, group
names. As escapes and comments have already been processed, the code is a bit
simpler than before.
Most errors can be diagnosed during the parsing scan. For those that cannot
(for example, "lookbehind assertion is not fixed length"), the parsed code
contains offsets into the pattern so that the actual compiling code can
report where errors are.
The elements of the parsed pattern vector
-----------------------------------------
The word "offset" below means a code unit offset into the pattern. When
PCRE2_SIZE (which is usually size_t) is no bigger than uint32_t, an offset is
stored in a single parsed pattern element. Otherwise (typically on 64-bit
systems) it occupies two elements. The following meta items occupy just one
element, with no data:
META_ACCEPT (*ACCEPT)
META_ASTERISK *
META_ASTERISK_PLUS *+
META_ASTERISK_QUERY *?
META_ATOMIC (?> start of atomic group
META_CIRCUMFLEX ^ metacharacter
META_CLASS [ start of non-empty class
META_CLASS_EMPTY [] empty class - only with PCRE2_ALLOW_EMPTY_CLASS
META_CLASS_EMPTY_NOT [^] negative empty class - ditto
META_CLASS_END ] end of non-empty class
META_CLASS_NOT [^ start non-empty negative class
META_COMMIT (*COMMIT)
META_COND_ASSERT (?(?assertion)
META_DOLLAR $ metacharacter
META_DOT . metacharacter
META_END End of pattern (this value is 0x80000000)
META_FAIL (*FAIL)
META_KET ) closing parenthesis
META_LOOKAHEAD (?= start of lookahead
META_LOOKAHEADNOT (?! start of negative lookahead
META_NOCAPTURE (?: no capture parens
META_PLUS +
META_PLUS_PLUS ++
META_PLUS_QUERY +?
META_PRUNE (*PRUNE) - no argument
META_QUERY ?
META_QUERY_PLUS ?+
META_QUERY_QUERY ??
META_RANGE_ESCAPED hyphen in class range with at least one escape
META_RANGE_LITERAL hyphen in class range defined literally
META_SKIP (*SKIP) - no argument
META_THEN (*THEN) - no argument
The two RANGE values occur only in character classes. They are positioned
between two literals that define the start and end of the range. In an EBCDIC
evironment it is necessary to know whether either of the range values was
specified as an escape. In an ASCII/Unicode environment the distinction is not
relevant.
The following have data in the lower 16 bits, and may be followed by other data
elements:
META_ALT | alternation
META_BACKREF back reference
META_CAPTURE start of capturing group
META_ESCAPE non-literal escape sequence
META_RECURSE recursion call
If the data for META_ALT is non-zero, it is inside a lookbehind, and the data
is the length of its branch, for which OP_REVERSE must be generated.
META_BACKREF, META_CAPTURE, and META_RECURSE have the capture group number as
their data in the lower 16 bits of the element.
META_BACKREF is followed by an offset if the back reference group number is 10
or more. The offsets of the first ocurrences of references to groups whose
numbers are less than 10 are put in cb->small_ref_offset[] (only the first
occurrence is useful). On 64-bit systems this avoids using more than two parsed
pattern elements for items such as \3. The offset is used when an error occurs
because the reference is to a non-existent group.
META_RECURSE is always followed by an offset, for use in error messages.
META_ESCAPE has an ESC_xxx value as its data. For ESC_P and ESC_p, the next
element contains the 16-bit type and data property values, packed together.
ESC_g and ESC_k are used only for named references - numerical ones are turned
into META_RECURSE or META_BACKREF as appropriate. ESC_g and ESC_k are followed
by a length and an offset into the pattern to specify the name.
The following have one data item that follows in the next vector element:
META_BIGVALUE Next is a literal >= META_END
META_OPTIONS (?i) and friends (data is new option bits)
META_POSIX POSIX class item (data identifies the class)
META_POSIX_NEG negative POSIX class item (ditto)
The following are followed by a length element, then a number of character code
values (which should match with the length):
META_MARK (*MARK:xxxx)
META_COMMIT_ARG )*COMMIT:xxxx)
META_PRUNE_ARG (*PRUNE:xxx)
META_SKIP_ARG (*SKIP:xxxx)
META_THEN_ARG (*THEN:xxxx)
The following are followed by a length element, then an offset in the pattern
that identifies the name:
META_COND_NAME (?(<name>) or (?('name') or (?(name)
META_COND_RNAME (?(R&name)
META_COND_RNUMBER (?(Rdigits)
META_RECURSE_BYNAME (?&name)
META_BACKREF_BYNAME \k'name'
META_COND_RNUMBER is used for names that start with R and continue with digits,
because this is an ambiguous case. It could be a back reference to a group with
that name, or it could be a recursion test on a numbered group.
This one is followed by an offset, for use in error messages, then a number:
META_COND_NUMBER (?([+-]digits)
The following is followed just by an offset, for use in error messages:
META_COND_DEFINE (?(DEFINE)
The following are also followed just by an offset, but also the lower 16 bits
of the main word contain the length of the first branch of the lookbehind
group; this is used when generating OP_REVERSE for that branch.
META_LOOKBEHIND (?<=
META_LOOKBEHINDNOT (?<!
The following are followed by two elements, the minimum and maximum. Repeat
values are limited to 65535 (MAX_REPEAT). A maximum value of "unlimited" is
represented by UNLIMITED_REPEAT, which is bigger than MAX_REPEAT:
META_MINMAX {n,m} repeat
META_MINMAX_PLUS {n,m}+ repeat
META_MINMAX_QUERY {n,m}? repeat
This one is followed by three elements. The first is 0 for '>' and 1 for '>=';
the next two are the major and minor numbers:
META_COND_VERSION (?(VERSION<op>x.y)
Callouts are converted into one of two items:
META_CALLOUT_NUMBER (?C with numerical argument
META_CALLOUT_STRING (?C with string argument
In both cases, the next two elements contain the offset and length of the next
item in the pattern. Then there is either one callout number, or a length and
an offset for the string argument. The length includes both delimiters.
Traditional matching function
@ -154,9 +346,14 @@ Changeable options
------------------
The /i, /m, or /s options (PCRE2_CASELESS, PCRE2_MULTILINE, PCRE2_DOTALL, and
some others) may change in the middle of patterns. Their processing is handled
entirely at compile time by generating different opcodes for the different
settings. The runtime functions do not need to keep track of an options state.
others) may be changed in the middle of patterns by items such as (?i). Their
processing is handled entirely at compile time by generating different opcodes
for the different settings. The runtime functions do not need to keep track of
an option's state.
PCRE2_DUPNAMES, PCRE2_EXTENDED, PCRE2_EXTENDED_MORE, and PCRE2_NO_AUTO_CAPTURE
are tracked and processed during the parsing pre-pass. The others are handled
from META_OPTIONS items during the main compile phase.
Format of compiled patterns
@ -174,19 +371,19 @@ default value for LINK_SIZE is 2, except for the 32-bit library, where it can
only be 4. The 8-bit library can be compiled to used 3-byte or 4-byte values,
and the 16-bit library can be compiled to use 4-byte values, though this
impairs performance. Specifing a LINK_SIZE larger than 2 for these libraries is
necessary only when patterns whose compiled length is greater than 64K code
necessary only when patterns whose compiled length is greater than 65535 code
units are going to be processed. When a LINK_SIZE value uses more than one code
unit, the most significant unit is first.
In this description, we assume the "normal" compilation options. Data values
that are counts (e.g. quantifiers) are always two bytes long in 8-bit mode
(most significant byte first), or one code unit in 16-bit and 32-bit modes.
(most significant byte first), and one code unit in 16-bit and 32-bit modes.
Opcodes with no following data
------------------------------
These items are all just one unit long
These items are all just one unit long:
OP_END end of pattern
OP_ANY match any one character other than newline
@ -220,42 +417,58 @@ These items are all just one unit long
OP_ACCEPT ) These are Perl 5.10's "backtracking control
OP_COMMIT ) verbs". If OP_ACCEPT is inside capturing
OP_FAIL ) parentheses, it may be preceded by one or more
OP_PRUNE ) OP_CLOSE, each followed by a count that
OP_PRUNE ) OP_CLOSE, each followed by a number that
OP_SKIP ) indicates which parentheses must be closed.
OP_THEN )
OP_ASSERT_ACCEPT is used when (*ACCEPT) is encountered within an assertion.
This ends the assertion, not the entire pattern match. The assertion (?!) is
This ends the assertion, not the entire pattern match. The assertion (?!) is
always optimized to OP_FAIL.
OP_ALLANY is used for '.' when PCRE2_DOTALL is set. It is also used for \C in
non-UTF modes and in UTF-32 mode (since one code unit still equals one
non-UTF modes and in UTF-32 mode (since one code unit still equals one
character). Another use is for [^] when empty classes are permitted
(PCRE2_ALLOW_EMPTY_CLASS is set).
Backtracking control verbs with optional data
---------------------------------------------
Backtracking control verbs
--------------------------
(*THEN) without an argument generates the opcode OP_THEN and no following data.
OP_MARK is followed by the mark name, preceded by a length in one code unit,
and followed by a binary zero. For (*PRUNE), (*SKIP), and (*THEN) with
arguments, the opcodes OP_PRUNE_ARG, OP_SKIP_ARG, and OP_THEN_ARG are used,
with the name following in the same format as OP_MARK.
Verbs with no arguments generate opcodes with no following data (as listed
in the section above).
(*MARK:NAME) generates OP_MARK followed by the mark name, preceded by a
length in one code unit, and followed by a binary zero. The name length is
limited by the size of the code unit.
(*ACCEPT:NAME) and (*FAIL:NAME) are compiled as (*MARK:NAME)(*ACCEPT) and
(*MARK:NAME)(*FAIL) respectively.
For (*COMMIT:NAME), (*PRUNE:NAME), (*SKIP:NAME), and (*THEN:NAME), the opcodes
OP_COMMIT_ARG, OP_PRUNE_ARG, OP_SKIP_ARG, and OP_THEN_ARG are used, with the
name following in the same format as for OP_MARK.
Matching literal characters
---------------------------
The OP_CHAR opcode is followed by a single character that is to be matched
casefully. For caseless matching, OP_CHARI is used. In UTF-8 or UTF-16 modes,
the character may be more than one code unit long. In UTF-32 mode, characters
are always exactly one code unit long.
casefully. For caseless matching of characters that have at most two
case-equivalent code points, OP_CHARI is used. In UTF-8 or UTF-16 modes, the
character may be more than one code unit long. In UTF-32 mode, characters are
always exactly one code unit long.
If there is only one character in a character class, OP_CHAR or OP_CHARI is
used for a positive class, and OP_NOT or OP_NOTI for a negative one (that is,
for something like [^a]).
Caseless matching (positive or negative) of characters that have more than two
case-equivalent code points (which is possible only in UTF mode) is handled by
compiling a Unicode property item (see below), with the pseudo-property
PT_CLIST. The value of this property is an offset in a vector called
"ucd_caseless_sets" which identifies the start of a short list of equivalent
characters, terminated by the value NOTACHAR (0xffffffff).
Repeating single characters
---------------------------
@ -331,7 +544,8 @@ Each is followed by two code units that encode the desired property as a type
and a value. The types are a set of #defines of the form PT_xxx, and the values
are enumerations of the form ucp_xx, defined in the pcre2_ucp.h source file.
The value is relevant only for PT_GC (General Category), PT_PC (Particular
Category), and PT_SC (Script).
Category), PT_SC (Script), and the pseudo-property PT_CLIST, which is used to
identify a list of case-equivalent characters when there are three or more.
Repeats of these items use the OP_TYPESTAR etc. set of opcodes, followed by
three code units: OP_PROP or OP_NOTPROP, and then the desired property type and
@ -343,7 +557,10 @@ Character classes
If there is only one character in a class, OP_CHAR or OP_CHARI is used for a
positive class, and OP_NOT or OP_NOTI for a negative one (that is, for
something like [^a]).
something like [^a]), except when caselessly matching a character that has more
than two case-equivalent code points (which can happen only in UTF mode). In
this case a Unicode property item is used, as described above in "Matching
literal characters".
A set of repeating opcodes (called OP_NOTSTAR etc.) are used for repeated,
negated, single-character classes. The normal single-character opcodes
@ -364,8 +581,8 @@ do.
For classes containing characters with values greater than 255 or that contain
\p or \P, OP_XCLASS is used. It optionally uses a bit map if any acceptable
code points are less than 256, followed by a list of pairs (for a range) and/or
single characters and/or properties. In caseless mode, both cases are
explicitly listed.
single characters and/or properties. In caseless mode, all equivalent
characters are explicitly listed.
OP_XCLASS is followed by a LINK_SIZE value containing the total length of the
opcode and its data. This is followed by a code unit containing flag bits:
@ -422,8 +639,8 @@ opcode to see if it is one of these:
OP_CRMINRANGE
OP_CRPOSRANGE
All but the last three are single-code-unit items, with no data. The others are
followed by the minimum and maximum repeat counts.
All but the last three are single-code-unit items, with no data. The range
opcodes are followed by the minimum and maximum repeat counts.
Brackets and alternation
@ -438,16 +655,17 @@ myself, can be round, square, curly, or pointy. Hence this usage rather than
Non-capturing brackets use the opcode OP_BRA, capturing brackets use OP_CBRA. A
bracket opcode is followed by a LINK_SIZE value which gives the offset to the
next alternative OP_ALT or, if there aren't any branches, to the matching
OP_KET opcode. Each OP_ALT is followed by a LINK_SIZE value giving the offset
to the next one, or to the OP_KET opcode. For capturing brackets, the bracket
number is a count that immediately follows the offset.
next alternative OP_ALT or, if there aren't any branches, to the terminating
opcode. Each OP_ALT is followed by a LINK_SIZE value giving the offset to the
next one, or to the final opcode. For capturing brackets, the bracket number is
a count that immediately follows the offset.
OP_KET is used for subpatterns that do not repeat indefinitely, and OP_KETRMIN
and OP_KETRMAX are used for indefinite repetitions, minimally or maximally
respectively (see below for possessive repetitions). All three are followed by
a LINK_SIZE value giving (as a positive number) the offset back to the matching
bracket opcode.
There are several opcodes that mark the end of a subpattern group. OP_KET is
used for subpatterns that do not repeat indefinitely, OP_KETRMIN and
OP_KETRMAX are used for indefinite repetitions, minimally or maximally
respectively, and OP_KETRPOS for possessive repetitions (see below for more
details). All four are followed by a LINK_SIZE value giving (as a positive
number) the offset back to the matching bracket opcode.
If a subpattern is quantified such that it is permitted to match zero times, it
is preceded by one of OP_BRAZERO, OP_BRAMINZERO, or OP_SKIPZERO. These are
@ -488,17 +706,9 @@ repetition is zero, the group is preceded by OP_BRAPOSZERO.
Once-only (atomic) groups
-------------------------
These are just like other subpatterns, but they start with the opcode
OP_ONCE or OP_ONCE_NC. The former is used when there are no capturing brackets
within the atomic group; the latter when there are. The distinction is needed
for when there is a backtrack to before the group - any captures within the
group must be reset, so it is necessary to retain backtracking points inside
the group, even after it is complete, in order to do this. When there are no
captures in an atomic group, all the backtracking can be discarded when it is
complete. This is more efficient, and also uses less stack.
These are just like other subpatterns, but they start with the opcode OP_ONCE.
The check for matching an empty string in an unbounded repeat is handled
entirely at runtime, so there are just these two opcodes for atomic groups.
entirely at runtime, so there is just this one opcode for atomic groups.
Assertions
@ -544,14 +754,14 @@ tests the PCRE2 version number. This compiles into one of the opcodes OP_TRUE
or OP_FALSE.
If a condition is not a back reference, recursion test, DEFINE, or VERSION, it
must start with an assertion, whose opcode normally immediately follows OP_COND
or OP_SCOND. However, if automatic callouts are enabled, a callout is inserted
immediately before the assertion. It is also possible to insert a manual
callout at this point. Only assertion conditions may have callouts preceding
the condition.
must start with a parenthesized assertion, whose opcode normally immediately
follows OP_COND or OP_SCOND. However, if automatic callouts are enabled, a
callout is inserted immediately before the assertion. It is also possible to
insert a manual callout at this point. Only assertion conditions may have
callouts preceding the condition.
A condition that is the negative assertion (?!) is optimized to OP_FAIL in all
parts of the pattern, so this is another opcode that may appear as a condition.
A condition that is the negative assertion (?!) is optimized to OP_FAIL in all
parts of the pattern, so this is another opcode that may appear as a condition.
It is treated the same as OP_FALSE.
@ -561,21 +771,28 @@ Recursion
Recursion either matches the current pattern, or some subexpression. The opcode
OP_RECURSE is followed by a LINK_SIZE value that is the offset to the starting
bracket from the start of the whole pattern. OP_RECURSE is also used for
"subroutine" calls, even though they are not strictly a recursion. Repeated
recursions are automatically wrapped inside OP_ONCE brackets, because otherwise
some patterns broke them. A non-repeated recursion is not wrapped in OP_ONCE
brackets, but it is nevertheless still treated as an atomic group.
"subroutine" calls, even though they are not strictly a recursion. Up till
release 10.30 recursions were treated as atomic groups, making them
incompatible with Perl (but PCRE had them well before Perl did). From 10.30,
backtracking into recursions is supported.
Repeated recursions used to be wrapped inside OP_ONCE brackets, which not only
forced no backtracking, but also allowed repetition to be handled as for other
bracketed groups. From 10.30 onwards, repeated recursions are duplicated for
their minimum repetitions, and then wrapped in non-capturing brackets for the
remainder. For example, (?1){3} is treated as (?1)(?1)(?1), and (?1){2,4} is
treated as (?1)(?1)(?:(?1)){0,2}.
Callout
-------
Callouts
--------
A callout can nowadays have either a numerical argument or a string argument.
These use OP_CALLOUT or OP_CALLOUT_STR, respectively. In each case these are
followed by two LINK_SIZE values giving the offset in the pattern string to the
start of the following item, and another count giving the length of this item.
These values make it possible for pcre2test to output useful tracing
information using callouts.
A callout may have either a numerical argument or a string argument. These use
OP_CALLOUT or OP_CALLOUT_STR, respectively. In each case these are followed by
two LINK_SIZE values giving the offset in the pattern string to the start of
the following item, and another count giving the length of this item. These
values make it possible for pcre2test to output useful tracing information
using callouts.
In the case of a numeric callout, after these two values there is a single code
unit containing the callout number, in the range 0-255, with 255 being used for
@ -593,17 +810,17 @@ the actual string is passed, but the delimiter can be accessed as string[-1] if
the application needs it. In the 8-bit library, the callout in /X(?C'abc')Y/ is
compiled as the following bytes (decimal numbers represent binary values):
[OP_CALLOUT] [0] [10] [0] [1] [0] [14] [0] [5] ['] [a] [b] [c] [0]
-------- ------- -------- -------
| | | |
------- LINK_SIZE items ------
[OP_CALLOUT_STR] [0] [10] [0] [1] [0] [14] [0] [5] ['] [a] [b] [c] [0]
-------- ------- -------- -------
| | | |
------- LINK_SIZE items ------
Opcode table checking
---------------------
The last opcode that is defined in pcre2_internal.h is OP_TABLE_LENGTH. This is
not a real opcode, but is used to check that tables indexed by opcode are the
correct length, in order to catch updating errors.
not a real opcode, but is used to check at compile time that tables indexed by
opcode are the correct length, in order to catch updating errors.
Philip Hazel
June 2016
20 July 2018

368
pcre2-10.32/INSTALL vendored Normal file
View file

@ -0,0 +1,368 @@
Installation Instructions
*************************
Copyright (C) 1994-1996, 1999-2002, 2004-2016 Free Software
Foundation, Inc.
Copying and distribution of this file, with or without modification,
are permitted in any medium without royalty provided the copyright
notice and this notice are preserved. This file is offered as-is,
without warranty of any kind.
Basic Installation
==================
Briefly, the shell command './configure && make && make install'
should configure, build, and install this package. The following
more-detailed instructions are generic; see the 'README' file for
instructions specific to this package. Some packages provide this
'INSTALL' file but do not implement all of the features documented
below. The lack of an optional feature in a given package is not
necessarily a bug. More recommendations for GNU packages can be found
in *note Makefile Conventions: (standards)Makefile Conventions.
The 'configure' shell script attempts to guess correct values for
various system-dependent variables used during compilation. It uses
those values to create a 'Makefile' in each directory of the package.
It may also create one or more '.h' files containing system-dependent
definitions. Finally, it creates a shell script 'config.status' that
you can run in the future to recreate the current configuration, and a
file 'config.log' containing compiler output (useful mainly for
debugging 'configure').
It can also use an optional file (typically called 'config.cache' and
enabled with '--cache-file=config.cache' or simply '-C') that saves the
results of its tests to speed up reconfiguring. Caching is disabled by
default to prevent problems with accidental use of stale cache files.
If you need to do unusual things to compile the package, please try
to figure out how 'configure' could check whether to do them, and mail
diffs or instructions to the address given in the 'README' so they can
be considered for the next release. If you are using the cache, and at
some point 'config.cache' contains results you don't want to keep, you
may remove or edit it.
The file 'configure.ac' (or 'configure.in') is used to create
'configure' by a program called 'autoconf'. You need 'configure.ac' if
you want to change it or regenerate 'configure' using a newer version of
'autoconf'.
The simplest way to compile this package is:
1. 'cd' to the directory containing the package's source code and type
'./configure' to configure the package for your system.
Running 'configure' might take a while. While running, it prints
some messages telling which features it is checking for.
2. Type 'make' to compile the package.
3. Optionally, type 'make check' to run any self-tests that come with
the package, generally using the just-built uninstalled binaries.
4. Type 'make install' to install the programs and any data files and
documentation. When installing into a prefix owned by root, it is
recommended that the package be configured and built as a regular
user, and only the 'make install' phase executed with root
privileges.
5. Optionally, type 'make installcheck' to repeat any self-tests, but
this time using the binaries in their final installed location.
This target does not install anything. Running this target as a
regular user, particularly if the prior 'make install' required
root privileges, verifies that the installation completed
correctly.
6. You can remove the program binaries and object files from the
source code directory by typing 'make clean'. To also remove the
files that 'configure' created (so you can compile the package for
a different kind of computer), type 'make distclean'. There is
also a 'make maintainer-clean' target, but that is intended mainly
for the package's developers. If you use it, you may have to get
all sorts of other programs in order to regenerate files that came
with the distribution.
7. Often, you can also type 'make uninstall' to remove the installed
files again. In practice, not all packages have tested that
uninstallation works correctly, even though it is required by the
GNU Coding Standards.
8. Some packages, particularly those that use Automake, provide 'make
distcheck', which can by used by developers to test that all other
targets like 'make install' and 'make uninstall' work correctly.
This target is generally not run by end users.
Compilers and Options
=====================
Some systems require unusual options for compilation or linking that
the 'configure' script does not know about. Run './configure --help'
for details on some of the pertinent environment variables.
You can give 'configure' initial values for configuration parameters
by setting variables in the command line or in the environment. Here is
an example:
./configure CC=c99 CFLAGS=-g LIBS=-lposix
*Note Defining Variables::, for more details.
Compiling For Multiple Architectures
====================================
You can compile the package for more than one kind of computer at the
same time, by placing the object files for each architecture in their
own directory. To do this, you can use GNU 'make'. 'cd' to the
directory where you want the object files and executables to go and run
the 'configure' script. 'configure' automatically checks for the source
code in the directory that 'configure' is in and in '..'. This is known
as a "VPATH" build.
With a non-GNU 'make', it is safer to compile the package for one
architecture at a time in the source code directory. After you have
installed the package for one architecture, use 'make distclean' before
reconfiguring for another architecture.
On MacOS X 10.5 and later systems, you can create libraries and
executables that work on multiple system types--known as "fat" or
"universal" binaries--by specifying multiple '-arch' options to the
compiler but only a single '-arch' option to the preprocessor. Like
this:
./configure CC="gcc -arch i386 -arch x86_64 -arch ppc -arch ppc64" \
CXX="g++ -arch i386 -arch x86_64 -arch ppc -arch ppc64" \
CPP="gcc -E" CXXCPP="g++ -E"
This is not guaranteed to produce working output in all cases, you
may have to build one architecture at a time and combine the results
using the 'lipo' tool if you have problems.
Installation Names
==================
By default, 'make install' installs the package's commands under
'/usr/local/bin', include files under '/usr/local/include', etc. You
can specify an installation prefix other than '/usr/local' by giving
'configure' the option '--prefix=PREFIX', where PREFIX must be an
absolute file name.
You can specify separate installation prefixes for
architecture-specific files and architecture-independent files. If you
pass the option '--exec-prefix=PREFIX' to 'configure', the package uses
PREFIX as the prefix for installing programs and libraries.
Documentation and other data files still use the regular prefix.
In addition, if you use an unusual directory layout you can give
options like '--bindir=DIR' to specify different values for particular
kinds of files. Run 'configure --help' for a list of the directories
you can set and what kinds of files go in them. In general, the default
for these options is expressed in terms of '${prefix}', so that
specifying just '--prefix' will affect all of the other directory
specifications that were not explicitly provided.
The most portable way to affect installation locations is to pass the
correct locations to 'configure'; however, many packages provide one or
both of the following shortcuts of passing variable assignments to the
'make install' command line to change installation locations without
having to reconfigure or recompile.
The first method involves providing an override variable for each
affected directory. For example, 'make install
prefix=/alternate/directory' will choose an alternate location for all
directory configuration variables that were expressed in terms of
'${prefix}'. Any directories that were specified during 'configure',
but not in terms of '${prefix}', must each be overridden at install time
for the entire installation to be relocated. The approach of makefile
variable overrides for each directory variable is required by the GNU
Coding Standards, and ideally causes no recompilation. However, some
platforms have known limitations with the semantics of shared libraries
that end up requiring recompilation when using this method, particularly
noticeable in packages that use GNU Libtool.
The second method involves providing the 'DESTDIR' variable. For
example, 'make install DESTDIR=/alternate/directory' will prepend
'/alternate/directory' before all installation names. The approach of
'DESTDIR' overrides is not required by the GNU Coding Standards, and
does not work on platforms that have drive letters. On the other hand,
it does better at avoiding recompilation issues, and works well even
when some directory options were not specified in terms of '${prefix}'
at 'configure' time.
Optional Features
=================
If the package supports it, you can cause programs to be installed
with an extra prefix or suffix on their names by giving 'configure' the
option '--program-prefix=PREFIX' or '--program-suffix=SUFFIX'.
Some packages pay attention to '--enable-FEATURE' options to
'configure', where FEATURE indicates an optional part of the package.
They may also pay attention to '--with-PACKAGE' options, where PACKAGE
is something like 'gnu-as' or 'x' (for the X Window System). The
'README' should mention any '--enable-' and '--with-' options that the
package recognizes.
For packages that use the X Window System, 'configure' can usually
find the X include and library files automatically, but if it doesn't,
you can use the 'configure' options '--x-includes=DIR' and
'--x-libraries=DIR' to specify their locations.
Some packages offer the ability to configure how verbose the
execution of 'make' will be. For these packages, running './configure
--enable-silent-rules' sets the default to minimal output, which can be
overridden with 'make V=1'; while running './configure
--disable-silent-rules' sets the default to verbose, which can be
overridden with 'make V=0'.
Particular systems
==================
On HP-UX, the default C compiler is not ANSI C compatible. If GNU CC
is not installed, it is recommended to use the following options in
order to use an ANSI C compiler:
./configure CC="cc -Ae -D_XOPEN_SOURCE=500"
and if that doesn't work, install pre-built binaries of GCC for HP-UX.
HP-UX 'make' updates targets which have the same time stamps as their
prerequisites, which makes it generally unusable when shipped generated
files such as 'configure' are involved. Use GNU 'make' instead.
On OSF/1 a.k.a. Tru64, some versions of the default C compiler cannot
parse its '<wchar.h>' header file. The option '-nodtk' can be used as a
workaround. If GNU CC is not installed, it is therefore recommended to
try
./configure CC="cc"
and if that doesn't work, try
./configure CC="cc -nodtk"
On Solaris, don't put '/usr/ucb' early in your 'PATH'. This
directory contains several dysfunctional programs; working variants of
these programs are available in '/usr/bin'. So, if you need '/usr/ucb'
in your 'PATH', put it _after_ '/usr/bin'.
On Haiku, software installed for all users goes in '/boot/common',
not '/usr/local'. It is recommended to use the following options:
./configure --prefix=/boot/common
Specifying the System Type
==========================
There may be some features 'configure' cannot figure out
automatically, but needs to determine by the type of machine the package
will run on. Usually, assuming the package is built to be run on the
_same_ architectures, 'configure' can figure that out, but if it prints
a message saying it cannot guess the machine type, give it the
'--build=TYPE' option. TYPE can either be a short name for the system
type, such as 'sun4', or a canonical name which has the form:
CPU-COMPANY-SYSTEM
where SYSTEM can have one of these forms:
OS
KERNEL-OS
See the file 'config.sub' for the possible values of each field. If
'config.sub' isn't included in this package, then this package doesn't
need to know the machine type.
If you are _building_ compiler tools for cross-compiling, you should
use the option '--target=TYPE' to select the type of system they will
produce code for.
If you want to _use_ a cross compiler, that generates code for a
platform different from the build platform, you should specify the
"host" platform (i.e., that on which the generated programs will
eventually be run) with '--host=TYPE'.
Sharing Defaults
================
If you want to set default values for 'configure' scripts to share,
you can create a site shell script called 'config.site' that gives
default values for variables like 'CC', 'cache_file', and 'prefix'.
'configure' looks for 'PREFIX/share/config.site' if it exists, then
'PREFIX/etc/config.site' if it exists. Or, you can set the
'CONFIG_SITE' environment variable to the location of the site script.
A warning: not all 'configure' scripts look for a site script.
Defining Variables
==================
Variables not defined in a site shell script can be set in the
environment passed to 'configure'. However, some packages may run
configure again during the build, and the customized values of these
variables may be lost. In order to avoid this problem, you should set
them in the 'configure' command line, using 'VAR=value'. For example:
./configure CC=/usr/local2/bin/gcc
causes the specified 'gcc' to be used as the C compiler (unless it is
overridden in the site shell script).
Unfortunately, this technique does not work for 'CONFIG_SHELL' due to an
Autoconf limitation. Until the limitation is lifted, you can use this
workaround:
CONFIG_SHELL=/bin/bash ./configure CONFIG_SHELL=/bin/bash
'configure' Invocation
======================
'configure' recognizes the following options to control how it
operates.
'--help'
'-h'
Print a summary of all of the options to 'configure', and exit.
'--help=short'
'--help=recursive'
Print a summary of the options unique to this package's
'configure', and exit. The 'short' variant lists options used only
in the top level, while the 'recursive' variant lists options also
present in any nested packages.
'--version'
'-V'
Print the version of Autoconf used to generate the 'configure'
script, and exit.
'--cache-file=FILE'
Enable the cache: use and save the results of the tests in FILE,
traditionally 'config.cache'. FILE defaults to '/dev/null' to
disable caching.
'--config-cache'
'-C'
Alias for '--cache-file=config.cache'.
'--quiet'
'--silent'
'-q'
Do not print messages saying which checks are being made. To
suppress all normal output, redirect it to '/dev/null' (any error
messages will still be shown).
'--srcdir=DIR'
Look for the package's source code in directory DIR. Usually
'configure' can determine that directory automatically.
'--prefix=DIR'
Use DIR as the installation prefix. *note Installation Names:: for
more details, including other options available for fine-tuning the
installation locations.
'--no-create'
'-n'
Run the configure checks, but stop before creating any output
files.
'configure' also accepts some other, not widely useful, options. Run
'configure --help' for more details.

View file

@ -4,10 +4,11 @@ PCRE2 LICENCE
PCRE2 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.
Release 10 of PCRE2 is distributed under the terms of the "BSD" licence, as
specified below. The documentation for PCRE2, supplied in the "doc"
directory, is distributed under the same terms as the software itself. The data
in the testdata directory is not copyrighted and is in the public domain.
Releases 10.00 and above of PCRE2 are distributed under the terms of the "BSD"
licence, as specified below, with one exemption for certain binary
redistributions. The documentation for PCRE2, supplied in the "doc" directory,
is distributed under the same terms as the software itself. The data in the
testdata directory is not copyrighted and is in the public domain.
The basic library functions are written in C and are freestanding. Also
included in the distribution is a just-in-time compiler that can be used to
@ -25,7 +26,7 @@ Email domain: cam.ac.uk
University of Cambridge Computing Service,
Cambridge, England.
Copyright (c) 1997-2016 University of Cambridge
Copyright (c) 1997-2018 University of Cambridge
All rights reserved.
@ -34,9 +35,9 @@ PCRE2 JUST-IN-TIME COMPILATION SUPPORT
Written by: Zoltan Herczeg
Email local part: hzmester
Emain domain: freemail.hu
Email domain: freemail.hu
Copyright(c) 2010-2016 Zoltan Herczeg
Copyright(c) 2010-2018 Zoltan Herczeg
All rights reserved.
@ -45,9 +46,9 @@ STACK-LESS JUST-IN-TIME COMPILER
Written by: Zoltan Herczeg
Email local part: hzmester
Emain domain: freemail.hu
Email domain: freemail.hu
Copyright(c) 2009-2016 Zoltan Herczeg
Copyright(c) 2009-2018 Zoltan Herczeg
All rights reserved.
@ -57,11 +58,11 @@ THE "BSD" LICENCE
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,
* Redistributions of source code must retain the above copyright notices,
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
notices, 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 any
@ -80,4 +81,14 @@ 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.
EXEMPTION FOR BINARY LIBRARY-LIKE PACKAGES
------------------------------------------
The second condition in the BSD licence (covering binary redistributions) does
not apply all the way down a chain of software. If binary package A includes
PCRE2, it must respect the condition, but if package B is software that
includes package A, the condition is not imposed on package B unless it uses
PCRE2 independently.
End

View file

@ -2,7 +2,10 @@
AUTOMAKE_OPTIONS = subdir-objects
ACLOCAL_AMFLAGS = -I m4
AM_CPPFLAGS = -I$(builddir)/src -I$(srcdir)/src
## This seems to have become necessary for building in non-source directory.
AM_CPPFLAGS="-I$(srcdir)/src"
## Specify the documentation files that are distributed.
@ -26,12 +29,17 @@ dist_html_DATA = \
doc/html/pcre2.html \
doc/html/pcre2_callout_enumerate.html \
doc/html/pcre2_code_copy.html \
doc/html/pcre2_code_copy_with_tables.html \
doc/html/pcre2_code_free.html \
doc/html/pcre2_compile.html \
doc/html/pcre2_compile_context_copy.html \
doc/html/pcre2_compile_context_create.html \
doc/html/pcre2_compile_context_free.html \
doc/html/pcre2_config.html \
doc/html/pcre2_convert_context_copy.html \
doc/html/pcre2_convert_context_create.html \
doc/html/pcre2_convert_context_free.html \
doc/html/pcre2_converted_pattern_free.html \
doc/html/pcre2_dfa_match.html \
doc/html/pcre2_general_context_copy.html \
doc/html/pcre2_general_context_create.html \
@ -55,6 +63,7 @@ dist_html_DATA = \
doc/html/pcre2_match_data_create.html \
doc/html/pcre2_match_data_create_from_pattern.html \
doc/html/pcre2_match_data_free.html \
doc/html/pcre2_pattern_convert.html \
doc/html/pcre2_pattern_info.html \
doc/html/pcre2_serialize_decode.html \
doc/html/pcre2_serialize_encode.html \
@ -63,8 +72,14 @@ dist_html_DATA = \
doc/html/pcre2_set_bsr.html \
doc/html/pcre2_set_callout.html \
doc/html/pcre2_set_character_tables.html \
doc/html/pcre2_set_compile_extra_options.html \
doc/html/pcre2_set_compile_recursion_guard.html \
doc/html/pcre2_set_depth_limit.html \
doc/html/pcre2_set_glob_escape.html \
doc/html/pcre2_set_glob_separator.html \
doc/html/pcre2_set_heap_limit.html \
doc/html/pcre2_set_match_limit.html \
doc/html/pcre2_set_max_pattern_length.html \
doc/html/pcre2_set_offset_limit.html \
doc/html/pcre2_set_newline.html \
doc/html/pcre2_set_parens_nest_limit.html \
@ -86,6 +101,7 @@ dist_html_DATA = \
doc/html/pcre2build.html \
doc/html/pcre2callout.html \
doc/html/pcre2compat.html \
doc/html/pcre2convert.html \
doc/html/pcre2demo.html \
doc/html/pcre2grep.html \
doc/html/pcre2jit.html \
@ -97,7 +113,6 @@ dist_html_DATA = \
doc/html/pcre2posix.html \
doc/html/pcre2sample.html \
doc/html/pcre2serialize.html \
doc/html/pcre2stack.html \
doc/html/pcre2syntax.html \
doc/html/pcre2test.html \
doc/html/pcre2unicode.html
@ -107,12 +122,17 @@ dist_man_MANS = \
doc/pcre2.3 \
doc/pcre2_callout_enumerate.3 \
doc/pcre2_code_copy.3 \
doc/pcre2_code_copy_with_tables.3 \
doc/pcre2_code_free.3 \
doc/pcre2_compile.3 \
doc/pcre2_compile_context_copy.3 \
doc/pcre2_compile_context_create.3 \
doc/pcre2_compile_context_free.3 \
doc/pcre2_config.3 \
doc/pcre2_convert_context_copy.3 \
doc/pcre2_convert_context_create.3 \
doc/pcre2_convert_context_free.3 \
doc/pcre2_converted_pattern_free.3 \
doc/pcre2_dfa_match.3 \
doc/pcre2_general_context_copy.3 \
doc/pcre2_general_context_create.3 \
@ -136,6 +156,7 @@ dist_man_MANS = \
doc/pcre2_match_data_create.3 \
doc/pcre2_match_data_create_from_pattern.3 \
doc/pcre2_match_data_free.3 \
doc/pcre2_pattern_convert.3 \
doc/pcre2_pattern_info.3 \
doc/pcre2_serialize_decode.3 \
doc/pcre2_serialize_encode.3 \
@ -144,8 +165,14 @@ dist_man_MANS = \
doc/pcre2_set_bsr.3 \
doc/pcre2_set_callout.3 \
doc/pcre2_set_character_tables.3 \
doc/pcre2_set_compile_extra_options.3 \
doc/pcre2_set_compile_recursion_guard.3 \
doc/pcre2_set_depth_limit.3 \
doc/pcre2_set_glob_escape.3 \
doc/pcre2_set_glob_separator.3 \
doc/pcre2_set_heap_limit.3 \
doc/pcre2_set_match_limit.3 \
doc/pcre2_set_max_pattern_length.3 \
doc/pcre2_set_offset_limit.3 \
doc/pcre2_set_newline.3 \
doc/pcre2_set_parens_nest_limit.3 \
@ -167,6 +194,7 @@ dist_man_MANS = \
doc/pcre2build.3 \
doc/pcre2callout.3 \
doc/pcre2compat.3 \
doc/pcre2convert.3 \
doc/pcre2demo.3 \
doc/pcre2grep.1 \
doc/pcre2jit.3 \
@ -178,7 +206,6 @@ dist_man_MANS = \
doc/pcre2posix.3 \
doc/pcre2sample.3 \
doc/pcre2serialize.3 \
doc/pcre2stack.3 \
doc/pcre2syntax.3 \
doc/pcre2test.1 \
doc/pcre2unicode.3
@ -204,7 +231,7 @@ noinst_PROGRAMS =
# and 'make maintainer-clean'.
CLEANFILES =
DISTCLEANFILES = src/config.h.in~ config.h
DISTCLEANFILES = src/config.h.in~ config.h pcre2.h.generic
MAINTAINERCLEANFILES =
# Additional files to bundle with the distribution, over and above what
@ -321,8 +348,10 @@ COMMON_SOURCES = \
src/pcre2_compile.c \
src/pcre2_config.c \
src/pcre2_context.c \
src/pcre2_convert.c \
src/pcre2_dfa_match.c \
src/pcre2_error.c \
src/pcre2_extuni.c \
src/pcre2_find_bracket.c \
src/pcre2_internal.h \
src/pcre2_intmodedep.h \
@ -414,6 +443,7 @@ EXTRA_DIST += \
src/sljit/sljitNativeX86_32.c \
src/sljit/sljitNativeX86_64.c \
src/sljit/sljitNativeX86_common.c \
src/sljit/sljitProtExecAllocator.c \
src/sljit/sljitUtils.c
# Some of the JIT sources are also in separate files that are #included.
@ -471,7 +501,7 @@ libpcre2_posix_la_CFLAGS += $(GCOV_CFLAGS)
endif # WITH_GCOV
endif # WITH_PCRE2_8
## Build pcre2grep if the 8-bit library is enabled
## Build pcre2grep and optional fuzzer stuff if the 8-bit library is enabled
if WITH_PCRE2_8
bin_PROGRAMS += pcre2grep
@ -483,6 +513,22 @@ if WITH_GCOV
pcre2grep_CFLAGS += $(GCOV_CFLAGS)
pcre2grep_LDADD += $(GCOV_LIBS)
endif # WITH_GCOV
## If fuzzer support is enabled, build a non-distributed library containing the
## fuzzing function. Also build the standalone checking binary from the same
## source but using -DSTANDALONE.
if WITH_FUZZ_SUPPORT
noinst_LIBRARIES = .libs/libpcre2-fuzzsupport.a
_libs_libpcre2_fuzzsupport_a_SOURCES = src/pcre2_fuzzsupport.c
_libs_libpcre2_fuzzsupport_a_CFLAGS = $(AM_CFLAGS)
_libs_libpcre2_fuzzsupport_a_LIBADD =
noinst_PROGRAMS += pcre2fuzzcheck
pcre2fuzzcheck_SOURCES = src/pcre2_fuzzsupport.c
pcre2fuzzcheck_CFLAGS = -DSTANDALONE $(AM_CFLAGS)
pcre2fuzzcheck_LDADD = libpcre2-8.la
endif # WITH FUZZ_SUPPORT
endif # WITH_PCRE2_8
## -------- Testing ----------
@ -543,17 +589,17 @@ endif # WITH_GCOV
## The main library tests. Each test is a binary plus a script that runs that
## binary in various ways. We install these test binaries in case folks find it
## helpful.
## helpful. The two .bat files are for running the tests under Windows.
TESTS += RunTest
dist_noinst_SCRIPTS += RunTest
EXTRA_DIST += RunTest.bat
dist_noinst_SCRIPTS += RunTest
## When the 8-bit library is configured, pcre2grep will have been built.
if WITH_PCRE2_8
TESTS += RunGrepTest
EXTRA_DIST += RunGrepTest.bat
dist_noinst_SCRIPTS += RunGrepTest
endif # WITH_PCRE2_8
@ -565,6 +611,7 @@ EXTRA_DIST += \
testdata/grepinput \
testdata/grepinput3 \
testdata/grepinput8 \
testdata/grepinputM \
testdata/grepinputv \
testdata/grepinputx \
testdata/greplist \
@ -596,6 +643,8 @@ EXTRA_DIST += \
testdata/testinput21 \
testdata/testinput22 \
testdata/testinput23 \
testdata/testinput24 \
testdata/testinput25 \
testdata/testinputEBC \
testdata/testoutput1 \
testdata/testoutput2 \
@ -608,7 +657,7 @@ EXTRA_DIST += \
testdata/testoutput7 \
testdata/testoutput8-16-2 \
testdata/testoutput8-16-3 \
testdata/testoutput8-16-3 \
testdata/testoutput8-16-4 \
testdata/testoutput8-32-2 \
testdata/testoutput8-32-3 \
testdata/testoutput8-32-4 \
@ -636,6 +685,8 @@ EXTRA_DIST += \
testdata/testoutput22-32 \
testdata/testoutput22-8 \
testdata/testoutput23 \
testdata/testoutput24 \
testdata/testoutput25 \
testdata/testoutputEBC \
testdata/valgrind-jit.supp \
testdata/wintestinput3 \

View file

@ -1,7 +1,7 @@
# Makefile.in generated by automake 1.15 from Makefile.am.
# Makefile.in generated by automake 1.15.1 from Makefile.am.
# @configure_input@
# Copyright (C) 1994-2014 Free Software Foundation, Inc.
# Copyright (C) 1994-2017 Free Software Foundation, Inc.
# This Makefile.in is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -18,6 +18,7 @@
VPATH = @srcdir@
am__is_gnu_make = { \
if test -z '$(MAKELEVEL)'; then \
@ -92,9 +93,9 @@ PRE_UNINSTALL = :
POST_UNINSTALL = :
build_triplet = @build@
host_triplet = @host@
TESTS = $(am__EXEEXT_3) RunTest $(am__append_29)
TESTS = $(am__EXEEXT_4) RunTest $(am__append_30)
bin_PROGRAMS = $(am__EXEEXT_1) pcre2test$(EXEEXT)
noinst_PROGRAMS = $(am__EXEEXT_2) $(am__EXEEXT_3)
noinst_PROGRAMS = $(am__EXEEXT_2) $(am__EXEEXT_3) $(am__EXEEXT_4)
@WITH_REBUILD_CHARTABLES_TRUE@am__append_1 = dftables
@WITH_PCRE2_8_TRUE@am__append_2 = libpcre2-8.la
@WITH_PCRE2_16_TRUE@am__append_3 = libpcre2-16.la
@ -110,25 +111,27 @@ noinst_PROGRAMS = $(am__EXEEXT_2) $(am__EXEEXT_3)
@WITH_PCRE2_8_TRUE@am__append_13 = pcre2grep
@WITH_GCOV_TRUE@@WITH_PCRE2_8_TRUE@am__append_14 = $(GCOV_CFLAGS)
@WITH_GCOV_TRUE@@WITH_PCRE2_8_TRUE@am__append_15 = $(GCOV_LIBS)
@WITH_JIT_TRUE@am__append_16 = pcre2_jit_test
@WITH_FUZZ_SUPPORT_TRUE@@WITH_PCRE2_8_TRUE@am__append_16 = pcre2fuzzcheck
@WITH_JIT_TRUE@am__append_17 = pcre2_jit_test
@WITH_JIT_TRUE@@WITH_PCRE2_8_TRUE@am__append_18 = libpcre2-8.la
@WITH_JIT_TRUE@@WITH_PCRE2_16_TRUE@am__append_19 = libpcre2-16.la
@WITH_JIT_TRUE@@WITH_PCRE2_32_TRUE@am__append_20 = libpcre2-32.la
@WITH_GCOV_TRUE@@WITH_JIT_TRUE@am__append_21 = $(GCOV_CFLAGS)
@WITH_GCOV_TRUE@@WITH_JIT_TRUE@am__append_22 = $(GCOV_LIBS)
@WITH_PCRE2_8_TRUE@am__append_23 = libpcre2-8.la libpcre2-posix.la
@WITH_PCRE2_16_TRUE@am__append_24 = libpcre2-16.la
@WITH_PCRE2_32_TRUE@am__append_25 = libpcre2-32.la
@WITH_VALGRIND_TRUE@am__append_26 = $(VALGRIND_CFLAGS)
@WITH_GCOV_TRUE@am__append_27 = $(GCOV_CFLAGS)
@WITH_GCOV_TRUE@am__append_28 = $(GCOV_LIBS)
@WITH_PCRE2_8_TRUE@am__append_29 = RunGrepTest
@WITH_JIT_TRUE@am__append_18 = pcre2_jit_test
@WITH_JIT_TRUE@@WITH_PCRE2_8_TRUE@am__append_19 = libpcre2-8.la
@WITH_JIT_TRUE@@WITH_PCRE2_16_TRUE@am__append_20 = libpcre2-16.la
@WITH_JIT_TRUE@@WITH_PCRE2_32_TRUE@am__append_21 = libpcre2-32.la
@WITH_GCOV_TRUE@@WITH_JIT_TRUE@am__append_22 = $(GCOV_CFLAGS)
@WITH_GCOV_TRUE@@WITH_JIT_TRUE@am__append_23 = $(GCOV_LIBS)
@WITH_PCRE2_8_TRUE@am__append_24 = libpcre2-8.la libpcre2-posix.la
@WITH_PCRE2_16_TRUE@am__append_25 = libpcre2-16.la
@WITH_PCRE2_32_TRUE@am__append_26 = libpcre2-32.la
@WITH_VALGRIND_TRUE@am__append_27 = $(VALGRIND_CFLAGS)
@WITH_GCOV_TRUE@am__append_28 = $(GCOV_CFLAGS)
@WITH_GCOV_TRUE@am__append_29 = $(GCOV_LIBS)
@WITH_PCRE2_8_TRUE@am__append_30 = RunGrepTest
@WITH_PCRE2_8_TRUE@am__append_31 = libpcre2-8.pc libpcre2-posix.pc
@WITH_PCRE2_16_TRUE@am__append_32 = libpcre2-16.pc
@WITH_PCRE2_32_TRUE@am__append_33 = libpcre2-32.pc
@WITH_GCOV_FALSE@am__append_34 = src/*.gcda src/*.gcno
@WITH_PCRE2_8_TRUE@am__append_31 = RunGrepTest.bat
@WITH_PCRE2_8_TRUE@am__append_32 = RunGrepTest
@WITH_PCRE2_8_TRUE@am__append_33 = libpcre2-8.pc libpcre2-posix.pc
@WITH_PCRE2_16_TRUE@am__append_34 = libpcre2-16.pc
@WITH_PCRE2_32_TRUE@am__append_35 = libpcre2-32.pc
@WITH_GCOV_FALSE@am__append_36 = src/*.gcda src/*.gcno
subdir = .
ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
am__aclocal_m4_deps = $(top_srcdir)/m4/ax_pthread.m4 \
@ -150,6 +153,20 @@ CONFIG_HEADER = $(top_builddir)/src/config.h
CONFIG_CLEAN_FILES = libpcre2-8.pc libpcre2-16.pc libpcre2-32.pc \
libpcre2-posix.pc pcre2-config src/pcre2.h
CONFIG_CLEAN_VPATH_FILES =
LIBRARIES = $(noinst_LIBRARIES)
ARFLAGS = cru
AM_V_AR = $(am__v_AR_@AM_V@)
am__v_AR_ = $(am__v_AR_@AM_DEFAULT_V@)
am__v_AR_0 = @echo " AR " $@;
am__v_AR_1 =
_libs_libpcre2_fuzzsupport_a_AR = $(AR) $(ARFLAGS)
_libs_libpcre2_fuzzsupport_a_DEPENDENCIES =
am___libs_libpcre2_fuzzsupport_a_SOURCES_DIST = \
src/pcre2_fuzzsupport.c
am__dirstamp = $(am__leading_dot)dirstamp
@WITH_FUZZ_SUPPORT_TRUE@@WITH_PCRE2_8_TRUE@am__libs_libpcre2_fuzzsupport_a_OBJECTS = src/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.$(OBJEXT)
_libs_libpcre2_fuzzsupport_a_OBJECTS = \
$(am__libs_libpcre2_fuzzsupport_a_OBJECTS)
am__vpath_adj_setup = srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`;
am__vpath_adj = case $$p in \
$(srcdir)/*) f=`echo "$$p" | sed "s|^$$srcdirstrip/||"`;; \
@ -186,23 +203,24 @@ 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_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 \
src/pcre2_pattern_info.c src/pcre2_serialize.c \
src/pcre2_string_utils.c src/pcre2_study.c \
src/pcre2_substitute.c src/pcre2_substring.c \
src/pcre2_convert.c src/pcre2_dfa_match.c src/pcre2_error.c \
src/pcre2_extuni.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 src/pcre2_pattern_info.c \
src/pcre2_serialize.c src/pcre2_string_utils.c \
src/pcre2_study.c src/pcre2_substitute.c src/pcre2_substring.c \
src/pcre2_tables.c src/pcre2_ucd.c src/pcre2_ucp.h \
src/pcre2_valid_utf.c src/pcre2_xclass.c
am__dirstamp = $(am__leading_dot)dirstamp
am__objects_1 = src/libpcre2_16_la-pcre2_auto_possess.lo \
src/libpcre2_16_la-pcre2_compile.lo \
src/libpcre2_16_la-pcre2_config.lo \
src/libpcre2_16_la-pcre2_context.lo \
src/libpcre2_16_la-pcre2_convert.lo \
src/libpcre2_16_la-pcre2_dfa_match.lo \
src/libpcre2_16_la-pcre2_error.lo \
src/libpcre2_16_la-pcre2_extuni.lo \
src/libpcre2_16_la-pcre2_find_bracket.lo \
src/libpcre2_16_la-pcre2_jit_compile.lo \
src/libpcre2_16_la-pcre2_maketables.lo \
@ -237,22 +255,24 @@ 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_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 \
src/pcre2_pattern_info.c src/pcre2_serialize.c \
src/pcre2_string_utils.c src/pcre2_study.c \
src/pcre2_substitute.c src/pcre2_substring.c \
src/pcre2_convert.c src/pcre2_dfa_match.c src/pcre2_error.c \
src/pcre2_extuni.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 src/pcre2_pattern_info.c \
src/pcre2_serialize.c src/pcre2_string_utils.c \
src/pcre2_study.c src/pcre2_substitute.c src/pcre2_substring.c \
src/pcre2_tables.c src/pcre2_ucd.c src/pcre2_ucp.h \
src/pcre2_valid_utf.c src/pcre2_xclass.c
am__objects_3 = src/libpcre2_32_la-pcre2_auto_possess.lo \
src/libpcre2_32_la-pcre2_compile.lo \
src/libpcre2_32_la-pcre2_config.lo \
src/libpcre2_32_la-pcre2_context.lo \
src/libpcre2_32_la-pcre2_convert.lo \
src/libpcre2_32_la-pcre2_dfa_match.lo \
src/libpcre2_32_la-pcre2_error.lo \
src/libpcre2_32_la-pcre2_extuni.lo \
src/libpcre2_32_la-pcre2_find_bracket.lo \
src/libpcre2_32_la-pcre2_jit_compile.lo \
src/libpcre2_32_la-pcre2_maketables.lo \
@ -283,22 +303,24 @@ 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_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 \
src/pcre2_pattern_info.c src/pcre2_serialize.c \
src/pcre2_string_utils.c src/pcre2_study.c \
src/pcre2_substitute.c src/pcre2_substring.c \
src/pcre2_convert.c src/pcre2_dfa_match.c src/pcre2_error.c \
src/pcre2_extuni.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 src/pcre2_pattern_info.c \
src/pcre2_serialize.c src/pcre2_string_utils.c \
src/pcre2_study.c src/pcre2_substitute.c src/pcre2_substring.c \
src/pcre2_tables.c src/pcre2_ucd.c src/pcre2_ucp.h \
src/pcre2_valid_utf.c src/pcre2_xclass.c
am__objects_5 = src/libpcre2_8_la-pcre2_auto_possess.lo \
src/libpcre2_8_la-pcre2_compile.lo \
src/libpcre2_8_la-pcre2_config.lo \
src/libpcre2_8_la-pcre2_context.lo \
src/libpcre2_8_la-pcre2_convert.lo \
src/libpcre2_8_la-pcre2_dfa_match.lo \
src/libpcre2_8_la-pcre2_error.lo \
src/libpcre2_8_la-pcre2_extuni.lo \
src/libpcre2_8_la-pcre2_find_bracket.lo \
src/libpcre2_8_la-pcre2_jit_compile.lo \
src/libpcre2_8_la-pcre2_maketables.lo \
@ -337,7 +359,8 @@ libpcre2_posix_la_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC \
@WITH_PCRE2_8_TRUE@am_libpcre2_posix_la_rpath = -rpath $(libdir)
@WITH_PCRE2_8_TRUE@am__EXEEXT_1 = pcre2grep$(EXEEXT)
@WITH_REBUILD_CHARTABLES_TRUE@am__EXEEXT_2 = dftables$(EXEEXT)
@WITH_JIT_TRUE@am__EXEEXT_3 = pcre2_jit_test$(EXEEXT)
@WITH_FUZZ_SUPPORT_TRUE@@WITH_PCRE2_8_TRUE@am__EXEEXT_3 = pcre2fuzzcheck$(EXEEXT)
@WITH_JIT_TRUE@am__EXEEXT_4 = pcre2_jit_test$(EXEEXT)
PROGRAMS = $(bin_PROGRAMS) $(noinst_PROGRAMS)
am__dftables_SOURCES_DIST = src/dftables.c
@WITH_REBUILD_CHARTABLES_TRUE@am_dftables_OBJECTS = \
@ -351,13 +374,22 @@ pcre2_jit_test_OBJECTS = $(am_pcre2_jit_test_OBJECTS)
am__DEPENDENCIES_1 =
@WITH_GCOV_TRUE@@WITH_JIT_TRUE@am__DEPENDENCIES_2 = \
@WITH_GCOV_TRUE@@WITH_JIT_TRUE@ $(am__DEPENDENCIES_1)
@WITH_JIT_TRUE@pcre2_jit_test_DEPENDENCIES = $(am__append_18) \
@WITH_JIT_TRUE@ $(am__append_19) $(am__append_20) \
@WITH_JIT_TRUE@pcre2_jit_test_DEPENDENCIES = $(am__append_19) \
@WITH_JIT_TRUE@ $(am__append_20) $(am__append_21) \
@WITH_JIT_TRUE@ $(am__DEPENDENCIES_2)
pcre2_jit_test_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC \
$(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=link $(CCLD) \
$(pcre2_jit_test_CFLAGS) $(CFLAGS) $(AM_LDFLAGS) $(LDFLAGS) -o \
$@
am__pcre2fuzzcheck_SOURCES_DIST = src/pcre2_fuzzsupport.c
@WITH_FUZZ_SUPPORT_TRUE@@WITH_PCRE2_8_TRUE@am_pcre2fuzzcheck_OBJECTS = src/pcre2fuzzcheck-pcre2_fuzzsupport.$(OBJEXT)
pcre2fuzzcheck_OBJECTS = $(am_pcre2fuzzcheck_OBJECTS)
@WITH_FUZZ_SUPPORT_TRUE@@WITH_PCRE2_8_TRUE@pcre2fuzzcheck_DEPENDENCIES = \
@WITH_FUZZ_SUPPORT_TRUE@@WITH_PCRE2_8_TRUE@ libpcre2-8.la
pcre2fuzzcheck_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC \
$(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=link $(CCLD) \
$(pcre2fuzzcheck_CFLAGS) $(CFLAGS) $(AM_LDFLAGS) $(LDFLAGS) -o \
$@
am__pcre2grep_SOURCES_DIST = src/pcre2grep.c
@WITH_PCRE2_8_TRUE@am_pcre2grep_OBJECTS = \
@WITH_PCRE2_8_TRUE@ src/pcre2grep-pcre2grep.$(OBJEXT)
@ -373,8 +405,8 @@ pcre2grep_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) \
am_pcre2test_OBJECTS = src/pcre2test-pcre2test.$(OBJEXT)
pcre2test_OBJECTS = $(am_pcre2test_OBJECTS)
@WITH_GCOV_TRUE@am__DEPENDENCIES_4 = $(am__DEPENDENCIES_1)
pcre2test_DEPENDENCIES = $(am__DEPENDENCIES_1) $(am__append_23) \
$(am__append_24) $(am__append_25) $(am__DEPENDENCIES_4)
pcre2test_DEPENDENCIES = $(am__DEPENDENCIES_1) $(am__append_24) \
$(am__append_25) $(am__append_26) $(am__DEPENDENCIES_4)
pcre2test_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) \
$(LIBTOOLFLAGS) --mode=link $(CCLD) $(pcre2test_CFLAGS) \
$(CFLAGS) $(AM_LDFLAGS) $(LDFLAGS) -o $@
@ -414,18 +446,21 @@ AM_V_CCLD = $(am__v_CCLD_@AM_V@)
am__v_CCLD_ = $(am__v_CCLD_@AM_DEFAULT_V@)
am__v_CCLD_0 = @echo " CCLD " $@;
am__v_CCLD_1 =
SOURCES = $(libpcre2_16_la_SOURCES) $(nodist_libpcre2_16_la_SOURCES) \
SOURCES = $(_libs_libpcre2_fuzzsupport_a_SOURCES) \
$(libpcre2_16_la_SOURCES) $(nodist_libpcre2_16_la_SOURCES) \
$(libpcre2_32_la_SOURCES) $(nodist_libpcre2_32_la_SOURCES) \
$(libpcre2_8_la_SOURCES) $(nodist_libpcre2_8_la_SOURCES) \
$(libpcre2_posix_la_SOURCES) $(dftables_SOURCES) \
$(pcre2_jit_test_SOURCES) $(pcre2grep_SOURCES) \
$(pcre2test_SOURCES)
DIST_SOURCES = $(am__libpcre2_16_la_SOURCES_DIST) \
$(pcre2_jit_test_SOURCES) $(pcre2fuzzcheck_SOURCES) \
$(pcre2grep_SOURCES) $(pcre2test_SOURCES)
DIST_SOURCES = $(am___libs_libpcre2_fuzzsupport_a_SOURCES_DIST) \
$(am__libpcre2_16_la_SOURCES_DIST) \
$(am__libpcre2_32_la_SOURCES_DIST) \
$(am__libpcre2_8_la_SOURCES_DIST) \
$(am__libpcre2_posix_la_SOURCES_DIST) \
$(am__dftables_SOURCES_DIST) \
$(am__pcre2_jit_test_SOURCES_DIST) \
$(am__pcre2fuzzcheck_SOURCES_DIST) \
$(am__pcre2grep_SOURCES_DIST) $(pcre2test_SOURCES)
am__can_run_installinfo = \
case $$AM_UPDATE_INFO_DIR in \
@ -714,7 +749,6 @@ LIPO = @LIPO@
LN_S = @LN_S@
LTLIBOBJS = @LTLIBOBJS@
LT_SYS_LIBRARY_PATH = @LT_SYS_LIBRARY_PATH@
MAINT = @MAINT@
MAKEINFO = @MAKEINFO@
MANIFEST_TOOL = @MANIFEST_TOOL@
MKDIR_P = @MKDIR_P@
@ -733,6 +767,8 @@ PACKAGE_URL = @PACKAGE_URL@
PACKAGE_VERSION = @PACKAGE_VERSION@
PATH_SEPARATOR = @PATH_SEPARATOR@
PCRE2_DATE = @PCRE2_DATE@
PCRE2_HAVE_INTTYPES_H = @PCRE2_HAVE_INTTYPES_H@
PCRE2_HAVE_STDINT_H = @PCRE2_HAVE_STDINT_H@
PCRE2_MAJOR = @PCRE2_MAJOR@
PCRE2_MINOR = @PCRE2_MINOR@
PCRE2_PRERELEASE = @PCRE2_PRERELEASE@
@ -812,7 +848,7 @@ top_builddir = @top_builddir@
top_srcdir = @top_srcdir@
AUTOMAKE_OPTIONS = subdir-objects
ACLOCAL_AMFLAGS = -I m4
AM_CPPFLAGS = -I$(builddir)/src -I$(srcdir)/src
AM_CPPFLAGS = "-I$(srcdir)/src"
dist_doc_DATA = \
AUTHORS \
COPYING \
@ -833,12 +869,17 @@ dist_html_DATA = \
doc/html/pcre2.html \
doc/html/pcre2_callout_enumerate.html \
doc/html/pcre2_code_copy.html \
doc/html/pcre2_code_copy_with_tables.html \
doc/html/pcre2_code_free.html \
doc/html/pcre2_compile.html \
doc/html/pcre2_compile_context_copy.html \
doc/html/pcre2_compile_context_create.html \
doc/html/pcre2_compile_context_free.html \
doc/html/pcre2_config.html \
doc/html/pcre2_convert_context_copy.html \
doc/html/pcre2_convert_context_create.html \
doc/html/pcre2_convert_context_free.html \
doc/html/pcre2_converted_pattern_free.html \
doc/html/pcre2_dfa_match.html \
doc/html/pcre2_general_context_copy.html \
doc/html/pcre2_general_context_create.html \
@ -862,6 +903,7 @@ dist_html_DATA = \
doc/html/pcre2_match_data_create.html \
doc/html/pcre2_match_data_create_from_pattern.html \
doc/html/pcre2_match_data_free.html \
doc/html/pcre2_pattern_convert.html \
doc/html/pcre2_pattern_info.html \
doc/html/pcre2_serialize_decode.html \
doc/html/pcre2_serialize_encode.html \
@ -870,8 +912,14 @@ dist_html_DATA = \
doc/html/pcre2_set_bsr.html \
doc/html/pcre2_set_callout.html \
doc/html/pcre2_set_character_tables.html \
doc/html/pcre2_set_compile_extra_options.html \
doc/html/pcre2_set_compile_recursion_guard.html \
doc/html/pcre2_set_depth_limit.html \
doc/html/pcre2_set_glob_escape.html \
doc/html/pcre2_set_glob_separator.html \
doc/html/pcre2_set_heap_limit.html \
doc/html/pcre2_set_match_limit.html \
doc/html/pcre2_set_max_pattern_length.html \
doc/html/pcre2_set_offset_limit.html \
doc/html/pcre2_set_newline.html \
doc/html/pcre2_set_parens_nest_limit.html \
@ -893,6 +941,7 @@ dist_html_DATA = \
doc/html/pcre2build.html \
doc/html/pcre2callout.html \
doc/html/pcre2compat.html \
doc/html/pcre2convert.html \
doc/html/pcre2demo.html \
doc/html/pcre2grep.html \
doc/html/pcre2jit.html \
@ -904,7 +953,6 @@ dist_html_DATA = \
doc/html/pcre2posix.html \
doc/html/pcre2sample.html \
doc/html/pcre2serialize.html \
doc/html/pcre2stack.html \
doc/html/pcre2syntax.html \
doc/html/pcre2test.html \
doc/html/pcre2unicode.html
@ -914,12 +962,17 @@ dist_man_MANS = \
doc/pcre2.3 \
doc/pcre2_callout_enumerate.3 \
doc/pcre2_code_copy.3 \
doc/pcre2_code_copy_with_tables.3 \
doc/pcre2_code_free.3 \
doc/pcre2_compile.3 \
doc/pcre2_compile_context_copy.3 \
doc/pcre2_compile_context_create.3 \
doc/pcre2_compile_context_free.3 \
doc/pcre2_config.3 \
doc/pcre2_convert_context_copy.3 \
doc/pcre2_convert_context_create.3 \
doc/pcre2_convert_context_free.3 \
doc/pcre2_converted_pattern_free.3 \
doc/pcre2_dfa_match.3 \
doc/pcre2_general_context_copy.3 \
doc/pcre2_general_context_create.3 \
@ -943,6 +996,7 @@ dist_man_MANS = \
doc/pcre2_match_data_create.3 \
doc/pcre2_match_data_create_from_pattern.3 \
doc/pcre2_match_data_free.3 \
doc/pcre2_pattern_convert.3 \
doc/pcre2_pattern_info.3 \
doc/pcre2_serialize_decode.3 \
doc/pcre2_serialize_encode.3 \
@ -951,8 +1005,14 @@ dist_man_MANS = \
doc/pcre2_set_bsr.3 \
doc/pcre2_set_callout.3 \
doc/pcre2_set_character_tables.3 \
doc/pcre2_set_compile_extra_options.3 \
doc/pcre2_set_compile_recursion_guard.3 \
doc/pcre2_set_depth_limit.3 \
doc/pcre2_set_glob_escape.3 \
doc/pcre2_set_glob_separator.3 \
doc/pcre2_set_heap_limit.3 \
doc/pcre2_set_match_limit.3 \
doc/pcre2_set_max_pattern_length.3 \
doc/pcre2_set_offset_limit.3 \
doc/pcre2_set_newline.3 \
doc/pcre2_set_parens_nest_limit.3 \
@ -974,6 +1034,7 @@ dist_man_MANS = \
doc/pcre2build.3 \
doc/pcre2callout.3 \
doc/pcre2compat.3 \
doc/pcre2convert.3 \
doc/pcre2demo.3 \
doc/pcre2grep.1 \
doc/pcre2jit.3 \
@ -985,7 +1046,6 @@ dist_man_MANS = \
doc/pcre2posix.3 \
doc/pcre2sample.3 \
doc/pcre2serialize.3 \
doc/pcre2stack.3 \
doc/pcre2syntax.3 \
doc/pcre2test.1 \
doc/pcre2unicode.3
@ -995,7 +1055,7 @@ dist_man_MANS = \
lib_LTLIBRARIES = $(am__append_2) $(am__append_3) $(am__append_4) \
$(am__append_11)
check_SCRIPTS =
dist_noinst_SCRIPTS = RunTest $(am__append_30)
dist_noinst_SCRIPTS = RunTest $(am__append_32)
# Additional files to delete on 'make clean', 'make distclean',
# and 'make maintainer-clean'.
@ -1006,7 +1066,8 @@ CLEANFILES = src/pcre2_chartables.c testSinput test3input test3output \
test3outputA test3outputB testtry teststdout teststderr \
teststderrgrep testtemp1grep testtemp2grep testtrygrep \
testNinputgrep
DISTCLEANFILES = src/config.h.in~ config.h $(am__append_34)
DISTCLEANFILES = src/config.h.in~ config.h pcre2.h.generic \
$(am__append_36)
MAINTAINERCLEANFILES = src/pcre2.h.generic src/config.h.generic
# Additional files to bundle with the distribution, over and above what
@ -1049,27 +1110,29 @@ EXTRA_DIST = m4/ax_pthread.m4 m4/pcre2_visibility.m4 \
src/sljit/sljitNativeTILEGX-encoder.c \
src/sljit/sljitNativeTILEGX_64.c src/sljit/sljitNativeX86_32.c \
src/sljit/sljitNativeX86_64.c \
src/sljit/sljitNativeX86_common.c src/sljit/sljitUtils.c \
src/sljit/sljitNativeX86_common.c \
src/sljit/sljitProtExecAllocator.c src/sljit/sljitUtils.c \
src/pcre2_jit_match.c src/pcre2_jit_misc.c \
src/pcre2_printint.c RunTest.bat testdata/grepbinary \
testdata/grepfilelist testdata/grepinput testdata/grepinput3 \
testdata/grepinput8 testdata/grepinputv testdata/grepinputx \
testdata/greplist testdata/grepoutput testdata/grepoutput8 \
testdata/grepoutputC testdata/grepoutputN testdata/greppatN4 \
testdata/testinput1 testdata/testinput2 testdata/testinput3 \
testdata/testinput4 testdata/testinput5 testdata/testinput6 \
testdata/testinput7 testdata/testinput8 testdata/testinput9 \
testdata/testinput10 testdata/testinput11 testdata/testinput12 \
testdata/testinput13 testdata/testinput14 testdata/testinput15 \
testdata/testinput16 testdata/testinput17 testdata/testinput18 \
testdata/testinput19 testdata/testinput20 testdata/testinput21 \
testdata/testinput22 testdata/testinput23 \
src/pcre2_printint.c RunTest.bat $(am__append_31) \
testdata/grepbinary testdata/grepfilelist testdata/grepinput \
testdata/grepinput3 testdata/grepinput8 testdata/grepinputM \
testdata/grepinputv testdata/grepinputx testdata/greplist \
testdata/grepoutput testdata/grepoutput8 testdata/grepoutputC \
testdata/grepoutputN testdata/greppatN4 testdata/testinput1 \
testdata/testinput2 testdata/testinput3 testdata/testinput4 \
testdata/testinput5 testdata/testinput6 testdata/testinput7 \
testdata/testinput8 testdata/testinput9 testdata/testinput10 \
testdata/testinput11 testdata/testinput12 testdata/testinput13 \
testdata/testinput14 testdata/testinput15 testdata/testinput16 \
testdata/testinput17 testdata/testinput18 testdata/testinput19 \
testdata/testinput20 testdata/testinput21 testdata/testinput22 \
testdata/testinput23 testdata/testinput24 testdata/testinput25 \
testdata/testinputEBC testdata/testoutput1 \
testdata/testoutput2 testdata/testoutput3 \
testdata/testoutput3A testdata/testoutput3B \
testdata/testoutput4 testdata/testoutput5 testdata/testoutput6 \
testdata/testoutput7 testdata/testoutput8-16-2 \
testdata/testoutput8-16-3 testdata/testoutput8-16-3 \
testdata/testoutput8-16-3 testdata/testoutput8-16-4 \
testdata/testoutput8-32-2 testdata/testoutput8-32-3 \
testdata/testoutput8-32-4 testdata/testoutput8-8-2 \
testdata/testoutput8-8-3 testdata/testoutput8-8-4 \
@ -1083,7 +1146,8 @@ EXTRA_DIST = m4/ax_pthread.m4 m4/pcre2_visibility.m4 \
testdata/testoutput19 testdata/testoutput20 \
testdata/testoutput21 testdata/testoutput22-16 \
testdata/testoutput22-32 testdata/testoutput22-8 \
testdata/testoutput23 testdata/testoutputEBC \
testdata/testoutput23 testdata/testoutput24 \
testdata/testoutput25 testdata/testoutputEBC \
testdata/valgrind-jit.supp testdata/wintestinput3 \
testdata/wintestoutput3 perltest.sh src/pcre2demo.c \
cmake/COPYING-CMAKE-SCRIPTS \
@ -1106,8 +1170,10 @@ COMMON_SOURCES = \
src/pcre2_compile.c \
src/pcre2_config.c \
src/pcre2_context.c \
src/pcre2_convert.c \
src/pcre2_dfa_match.c \
src/pcre2_error.c \
src/pcre2_extuni.c \
src/pcre2_find_bracket.c \
src/pcre2_internal.h \
src/pcre2_intmodedep.h \
@ -1175,19 +1241,26 @@ COMMON_SOURCES = \
@WITH_PCRE2_8_TRUE@pcre2grep_CFLAGS = $(AM_CFLAGS) $(am__append_14)
@WITH_PCRE2_8_TRUE@pcre2grep_LDADD = $(LIBZ) $(LIBBZ2) libpcre2-8.la \
@WITH_PCRE2_8_TRUE@ $(am__append_15)
@WITH_FUZZ_SUPPORT_TRUE@@WITH_PCRE2_8_TRUE@noinst_LIBRARIES = .libs/libpcre2-fuzzsupport.a
@WITH_FUZZ_SUPPORT_TRUE@@WITH_PCRE2_8_TRUE@_libs_libpcre2_fuzzsupport_a_SOURCES = src/pcre2_fuzzsupport.c
@WITH_FUZZ_SUPPORT_TRUE@@WITH_PCRE2_8_TRUE@_libs_libpcre2_fuzzsupport_a_CFLAGS = $(AM_CFLAGS)
@WITH_FUZZ_SUPPORT_TRUE@@WITH_PCRE2_8_TRUE@_libs_libpcre2_fuzzsupport_a_LIBADD =
@WITH_FUZZ_SUPPORT_TRUE@@WITH_PCRE2_8_TRUE@pcre2fuzzcheck_SOURCES = src/pcre2_fuzzsupport.c
@WITH_FUZZ_SUPPORT_TRUE@@WITH_PCRE2_8_TRUE@pcre2fuzzcheck_CFLAGS = -DSTANDALONE $(AM_CFLAGS)
@WITH_FUZZ_SUPPORT_TRUE@@WITH_PCRE2_8_TRUE@pcre2fuzzcheck_LDADD = libpcre2-8.la
@WITH_JIT_TRUE@pcre2_jit_test_SOURCES = src/pcre2_jit_test.c
@WITH_JIT_TRUE@pcre2_jit_test_CFLAGS = $(AM_CFLAGS) $(am__append_21)
@WITH_JIT_TRUE@pcre2_jit_test_LDADD = $(am__append_18) \
@WITH_JIT_TRUE@ $(am__append_19) $(am__append_20) \
@WITH_JIT_TRUE@ $(am__append_22)
@WITH_JIT_TRUE@pcre2_jit_test_CFLAGS = $(AM_CFLAGS) $(am__append_22)
@WITH_JIT_TRUE@pcre2_jit_test_LDADD = $(am__append_19) \
@WITH_JIT_TRUE@ $(am__append_20) $(am__append_21) \
@WITH_JIT_TRUE@ $(am__append_23)
pcre2test_SOURCES = src/pcre2test.c
pcre2test_CFLAGS = $(AM_CFLAGS) $(am__append_26) $(am__append_27)
pcre2test_LDADD = $(LIBREADLINE) $(am__append_23) $(am__append_24) \
$(am__append_25) $(am__append_28)
pcre2test_CFLAGS = $(AM_CFLAGS) $(am__append_27) $(am__append_28)
pcre2test_LDADD = $(LIBREADLINE) $(am__append_24) $(am__append_25) \
$(am__append_26) $(am__append_29)
# We have .pc files for pkg-config users.
pkgconfigdir = $(libdir)/pkgconfig
pkgconfig_DATA = $(am__append_31) $(am__append_32) $(am__append_33)
pkgconfig_DATA = $(am__append_33) $(am__append_34) $(am__append_35)
# gcov/lcov code coverage reporting
#
@ -1219,7 +1292,7 @@ all: $(BUILT_SOURCES)
.SUFFIXES: .c .lo .log .o .obj .test .test$(EXEEXT) .trs
am--refresh: Makefile
@:
$(srcdir)/Makefile.in: @MAINTAINER_MODE_TRUE@ $(srcdir)/Makefile.am $(am__configure_deps)
$(srcdir)/Makefile.in: $(srcdir)/Makefile.am $(am__configure_deps)
@for dep in $?; do \
case '$(am__configure_deps)' in \
*$$dep*) \
@ -1245,9 +1318,9 @@ Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status
$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES)
$(SHELL) ./config.status --recheck
$(top_srcdir)/configure: @MAINTAINER_MODE_TRUE@ $(am__configure_deps)
$(top_srcdir)/configure: $(am__configure_deps)
$(am__cd) $(srcdir) && $(AUTOCONF)
$(ACLOCAL_M4): @MAINTAINER_MODE_TRUE@ $(am__aclocal_m4_deps)
$(ACLOCAL_M4): $(am__aclocal_m4_deps)
$(am__cd) $(srcdir) && $(ACLOCAL) $(ACLOCAL_AMFLAGS)
$(am__aclocal_m4_deps):
@ -1258,7 +1331,7 @@ src/config.h: src/stamp-h1
src/stamp-h1: $(top_srcdir)/src/config.h.in $(top_builddir)/config.status
@rm -f src/stamp-h1
cd $(top_builddir) && $(SHELL) ./config.status src/config.h
$(top_srcdir)/src/config.h.in: @MAINTAINER_MODE_TRUE@ $(am__configure_deps)
$(top_srcdir)/src/config.h.in: $(am__configure_deps)
($(am__cd) $(top_srcdir) && $(AUTOHEADER))
rm -f src/stamp-h1
touch $@
@ -1278,6 +1351,25 @@ pcre2-config: $(top_builddir)/config.status $(srcdir)/pcre2-config.in
src/pcre2.h: $(top_builddir)/config.status $(top_srcdir)/src/pcre2.h.in
cd $(top_builddir) && $(SHELL) ./config.status $@
clean-noinstLIBRARIES:
-test -z "$(noinst_LIBRARIES)" || rm -f $(noinst_LIBRARIES)
src/$(am__dirstamp):
@$(MKDIR_P) src
@: > src/$(am__dirstamp)
src/$(DEPDIR)/$(am__dirstamp):
@$(MKDIR_P) src/$(DEPDIR)
@: > src/$(DEPDIR)/$(am__dirstamp)
src/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.$(OBJEXT): \
src/$(am__dirstamp) src/$(DEPDIR)/$(am__dirstamp)
.libs/$(am__dirstamp):
@$(MKDIR_P) .libs
@: > .libs/$(am__dirstamp)
.libs/libpcre2-fuzzsupport.a: $(_libs_libpcre2_fuzzsupport_a_OBJECTS) $(_libs_libpcre2_fuzzsupport_a_DEPENDENCIES) $(EXTRA__libs_libpcre2_fuzzsupport_a_DEPENDENCIES) .libs/$(am__dirstamp)
$(AM_V_at)-rm -f .libs/libpcre2-fuzzsupport.a
$(AM_V_AR)$(_libs_libpcre2_fuzzsupport_a_AR) .libs/libpcre2-fuzzsupport.a $(_libs_libpcre2_fuzzsupport_a_OBJECTS) $(_libs_libpcre2_fuzzsupport_a_LIBADD)
$(AM_V_at)$(RANLIB) .libs/libpcre2-fuzzsupport.a
install-libLTLIBRARIES: $(lib_LTLIBRARIES)
@$(NORMAL_INSTALL)
@list='$(lib_LTLIBRARIES)'; test -n "$(libdir)" || list=; \
@ -1312,12 +1404,6 @@ clean-libLTLIBRARIES:
echo rm -f $${locs}; \
rm -f $${locs}; \
}
src/$(am__dirstamp):
@$(MKDIR_P) src
@: > src/$(am__dirstamp)
src/$(DEPDIR)/$(am__dirstamp):
@$(MKDIR_P) src/$(DEPDIR)
@: > src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_16_la-pcre2_auto_possess.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_16_la-pcre2_compile.lo: src/$(am__dirstamp) \
@ -1326,10 +1412,14 @@ src/libpcre2_16_la-pcre2_config.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_16_la-pcre2_context.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_16_la-pcre2_convert.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
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_extuni.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) \
@ -1377,10 +1467,14 @@ src/libpcre2_32_la-pcre2_config.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_32_la-pcre2_context.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_32_la-pcre2_convert.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
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_extuni.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) \
@ -1428,10 +1522,14 @@ src/libpcre2_8_la-pcre2_config.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_8_la-pcre2_context.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
src/libpcre2_8_la-pcre2_convert.lo: src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
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_extuni.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) \
@ -1546,6 +1644,12 @@ src/pcre2_jit_test-pcre2_jit_test.$(OBJEXT): src/$(am__dirstamp) \
pcre2_jit_test$(EXEEXT): $(pcre2_jit_test_OBJECTS) $(pcre2_jit_test_DEPENDENCIES) $(EXTRA_pcre2_jit_test_DEPENDENCIES)
@rm -f pcre2_jit_test$(EXEEXT)
$(AM_V_CCLD)$(pcre2_jit_test_LINK) $(pcre2_jit_test_OBJECTS) $(pcre2_jit_test_LDADD) $(LIBS)
src/pcre2fuzzcheck-pcre2_fuzzsupport.$(OBJEXT): src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
pcre2fuzzcheck$(EXEEXT): $(pcre2fuzzcheck_OBJECTS) $(pcre2fuzzcheck_DEPENDENCIES) $(EXTRA_pcre2fuzzcheck_DEPENDENCIES)
@rm -f pcre2fuzzcheck$(EXEEXT)
$(AM_V_CCLD)$(pcre2fuzzcheck_LINK) $(pcre2fuzzcheck_OBJECTS) $(pcre2fuzzcheck_LDADD) $(LIBS)
src/pcre2grep-pcre2grep.$(OBJEXT): src/$(am__dirstamp) \
src/$(DEPDIR)/$(am__dirstamp)
@ -1602,14 +1706,17 @@ mostlyclean-compile:
distclean-compile:
-rm -f *.tab.c
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.Po@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/dftables.Po@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_16_la-pcre2_auto_possess.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_16_la-pcre2_chartables.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_16_la-pcre2_compile.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_16_la-pcre2_config.Plo@am__quote@
@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_convert.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_extuni.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@
@ -1632,8 +1739,10 @@ distclean-compile:
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_32_la-pcre2_compile.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_32_la-pcre2_config.Plo@am__quote@
@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_convert.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_extuni.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@
@ -1656,8 +1765,10 @@ distclean-compile:
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_8_la-pcre2_compile.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_8_la-pcre2_config.Plo@am__quote@
@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_convert.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_extuni.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@
@ -1677,6 +1788,7 @@ distclean-compile:
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_8_la-pcre2_xclass.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/libpcre2_posix_la-pcre2posix.Plo@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/pcre2_jit_test-pcre2_jit_test.Po@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/pcre2fuzzcheck-pcre2_fuzzsupport.Po@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/pcre2grep-pcre2grep.Po@am__quote@
@AMDEP_TRUE@@am__include@ @am__quote@src/$(DEPDIR)/pcre2test-pcre2test.Po@am__quote@
@ -1704,6 +1816,20 @@ distclean-compile:
@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(LTCOMPILE) -c -o $@ $<
src/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.o: src/pcre2_fuzzsupport.c
@am__fastdepCC_TRUE@ $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(_libs_libpcre2_fuzzsupport_a_CFLAGS) $(CFLAGS) -MT src/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.o -MD -MP -MF src/$(DEPDIR)/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.Tpo -c -o src/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.o `test -f 'src/pcre2_fuzzsupport.c' || echo '$(srcdir)/'`src/pcre2_fuzzsupport.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.Tpo src/$(DEPDIR)/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.Po
@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='src/pcre2_fuzzsupport.c' object='src/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.o' libtool=no @AMDEPBACKSLASH@
@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(_libs_libpcre2_fuzzsupport_a_CFLAGS) $(CFLAGS) -c -o src/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.o `test -f 'src/pcre2_fuzzsupport.c' || echo '$(srcdir)/'`src/pcre2_fuzzsupport.c
src/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.obj: src/pcre2_fuzzsupport.c
@am__fastdepCC_TRUE@ $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(_libs_libpcre2_fuzzsupport_a_CFLAGS) $(CFLAGS) -MT src/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.obj -MD -MP -MF src/$(DEPDIR)/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.Tpo -c -o src/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.obj `if test -f 'src/pcre2_fuzzsupport.c'; then $(CYGPATH_W) 'src/pcre2_fuzzsupport.c'; else $(CYGPATH_W) '$(srcdir)/src/pcre2_fuzzsupport.c'; fi`
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.Tpo src/$(DEPDIR)/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.Po
@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='src/pcre2_fuzzsupport.c' object='src/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.obj' libtool=no @AMDEPBACKSLASH@
@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(_libs_libpcre2_fuzzsupport_a_CFLAGS) $(CFLAGS) -c -o src/_libs_libpcre2_fuzzsupport_a-pcre2_fuzzsupport.obj `if test -f 'src/pcre2_fuzzsupport.c'; then $(CYGPATH_W) 'src/pcre2_fuzzsupport.c'; else $(CYGPATH_W) '$(srcdir)/src/pcre2_fuzzsupport.c'; fi`
src/libpcre2_16_la-pcre2_auto_possess.lo: src/pcre2_auto_possess.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_auto_possess.lo -MD -MP -MF src/$(DEPDIR)/libpcre2_16_la-pcre2_auto_possess.Tpo -c -o src/libpcre2_16_la-pcre2_auto_possess.lo `test -f 'src/pcre2_auto_possess.c' || echo '$(srcdir)/'`src/pcre2_auto_possess.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/libpcre2_16_la-pcre2_auto_possess.Tpo src/$(DEPDIR)/libpcre2_16_la-pcre2_auto_possess.Plo
@ -1732,6 +1858,13 @@ src/libpcre2_16_la-pcre2_context.lo: src/pcre2_context.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_context.lo `test -f 'src/pcre2_context.c' || echo '$(srcdir)/'`src/pcre2_context.c
src/libpcre2_16_la-pcre2_convert.lo: src/pcre2_convert.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_convert.lo -MD -MP -MF src/$(DEPDIR)/libpcre2_16_la-pcre2_convert.Tpo -c -o src/libpcre2_16_la-pcre2_convert.lo `test -f 'src/pcre2_convert.c' || echo '$(srcdir)/'`src/pcre2_convert.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/libpcre2_16_la-pcre2_convert.Tpo src/$(DEPDIR)/libpcre2_16_la-pcre2_convert.Plo
@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='src/pcre2_convert.c' object='src/libpcre2_16_la-pcre2_convert.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_convert.lo `test -f 'src/pcre2_convert.c' || echo '$(srcdir)/'`src/pcre2_convert.c
src/libpcre2_16_la-pcre2_dfa_match.lo: src/pcre2_dfa_match.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_dfa_match.lo -MD -MP -MF src/$(DEPDIR)/libpcre2_16_la-pcre2_dfa_match.Tpo -c -o src/libpcre2_16_la-pcre2_dfa_match.lo `test -f 'src/pcre2_dfa_match.c' || echo '$(srcdir)/'`src/pcre2_dfa_match.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/libpcre2_16_la-pcre2_dfa_match.Tpo src/$(DEPDIR)/libpcre2_16_la-pcre2_dfa_match.Plo
@ -1746,6 +1879,13 @@ 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_extuni.lo: src/pcre2_extuni.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_extuni.lo -MD -MP -MF src/$(DEPDIR)/libpcre2_16_la-pcre2_extuni.Tpo -c -o src/libpcre2_16_la-pcre2_extuni.lo `test -f 'src/pcre2_extuni.c' || echo '$(srcdir)/'`src/pcre2_extuni.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/libpcre2_16_la-pcre2_extuni.Tpo src/$(DEPDIR)/libpcre2_16_la-pcre2_extuni.Plo
@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='src/pcre2_extuni.c' object='src/libpcre2_16_la-pcre2_extuni.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_extuni.lo `test -f 'src/pcre2_extuni.c' || echo '$(srcdir)/'`src/pcre2_extuni.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
@ -1900,6 +2040,13 @@ src/libpcre2_32_la-pcre2_context.lo: src/pcre2_context.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_context.lo `test -f 'src/pcre2_context.c' || echo '$(srcdir)/'`src/pcre2_context.c
src/libpcre2_32_la-pcre2_convert.lo: src/pcre2_convert.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_convert.lo -MD -MP -MF src/$(DEPDIR)/libpcre2_32_la-pcre2_convert.Tpo -c -o src/libpcre2_32_la-pcre2_convert.lo `test -f 'src/pcre2_convert.c' || echo '$(srcdir)/'`src/pcre2_convert.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/libpcre2_32_la-pcre2_convert.Tpo src/$(DEPDIR)/libpcre2_32_la-pcre2_convert.Plo
@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='src/pcre2_convert.c' object='src/libpcre2_32_la-pcre2_convert.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_convert.lo `test -f 'src/pcre2_convert.c' || echo '$(srcdir)/'`src/pcre2_convert.c
src/libpcre2_32_la-pcre2_dfa_match.lo: src/pcre2_dfa_match.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_dfa_match.lo -MD -MP -MF src/$(DEPDIR)/libpcre2_32_la-pcre2_dfa_match.Tpo -c -o src/libpcre2_32_la-pcre2_dfa_match.lo `test -f 'src/pcre2_dfa_match.c' || echo '$(srcdir)/'`src/pcre2_dfa_match.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/libpcre2_32_la-pcre2_dfa_match.Tpo src/$(DEPDIR)/libpcre2_32_la-pcre2_dfa_match.Plo
@ -1914,6 +2061,13 @@ 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_extuni.lo: src/pcre2_extuni.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_extuni.lo -MD -MP -MF src/$(DEPDIR)/libpcre2_32_la-pcre2_extuni.Tpo -c -o src/libpcre2_32_la-pcre2_extuni.lo `test -f 'src/pcre2_extuni.c' || echo '$(srcdir)/'`src/pcre2_extuni.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/libpcre2_32_la-pcre2_extuni.Tpo src/$(DEPDIR)/libpcre2_32_la-pcre2_extuni.Plo
@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='src/pcre2_extuni.c' object='src/libpcre2_32_la-pcre2_extuni.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_extuni.lo `test -f 'src/pcre2_extuni.c' || echo '$(srcdir)/'`src/pcre2_extuni.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
@ -2068,6 +2222,13 @@ src/libpcre2_8_la-pcre2_context.lo: src/pcre2_context.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_context.lo `test -f 'src/pcre2_context.c' || echo '$(srcdir)/'`src/pcre2_context.c
src/libpcre2_8_la-pcre2_convert.lo: src/pcre2_convert.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_convert.lo -MD -MP -MF src/$(DEPDIR)/libpcre2_8_la-pcre2_convert.Tpo -c -o src/libpcre2_8_la-pcre2_convert.lo `test -f 'src/pcre2_convert.c' || echo '$(srcdir)/'`src/pcre2_convert.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/libpcre2_8_la-pcre2_convert.Tpo src/$(DEPDIR)/libpcre2_8_la-pcre2_convert.Plo
@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='src/pcre2_convert.c' object='src/libpcre2_8_la-pcre2_convert.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_convert.lo `test -f 'src/pcre2_convert.c' || echo '$(srcdir)/'`src/pcre2_convert.c
src/libpcre2_8_la-pcre2_dfa_match.lo: src/pcre2_dfa_match.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_dfa_match.lo -MD -MP -MF src/$(DEPDIR)/libpcre2_8_la-pcre2_dfa_match.Tpo -c -o src/libpcre2_8_la-pcre2_dfa_match.lo `test -f 'src/pcre2_dfa_match.c' || echo '$(srcdir)/'`src/pcre2_dfa_match.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/libpcre2_8_la-pcre2_dfa_match.Tpo src/$(DEPDIR)/libpcre2_8_la-pcre2_dfa_match.Plo
@ -2082,6 +2243,13 @@ 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_extuni.lo: src/pcre2_extuni.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_extuni.lo -MD -MP -MF src/$(DEPDIR)/libpcre2_8_la-pcre2_extuni.Tpo -c -o src/libpcre2_8_la-pcre2_extuni.lo `test -f 'src/pcre2_extuni.c' || echo '$(srcdir)/'`src/pcre2_extuni.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/libpcre2_8_la-pcre2_extuni.Tpo src/$(DEPDIR)/libpcre2_8_la-pcre2_extuni.Plo
@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='src/pcre2_extuni.c' object='src/libpcre2_8_la-pcre2_extuni.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_extuni.lo `test -f 'src/pcre2_extuni.c' || echo '$(srcdir)/'`src/pcre2_extuni.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
@ -2229,6 +2397,20 @@ src/pcre2_jit_test-pcre2_jit_test.obj: src/pcre2_jit_test.c
@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(pcre2_jit_test_CFLAGS) $(CFLAGS) -c -o src/pcre2_jit_test-pcre2_jit_test.obj `if test -f 'src/pcre2_jit_test.c'; then $(CYGPATH_W) 'src/pcre2_jit_test.c'; else $(CYGPATH_W) '$(srcdir)/src/pcre2_jit_test.c'; fi`
src/pcre2fuzzcheck-pcre2_fuzzsupport.o: src/pcre2_fuzzsupport.c
@am__fastdepCC_TRUE@ $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(pcre2fuzzcheck_CFLAGS) $(CFLAGS) -MT src/pcre2fuzzcheck-pcre2_fuzzsupport.o -MD -MP -MF src/$(DEPDIR)/pcre2fuzzcheck-pcre2_fuzzsupport.Tpo -c -o src/pcre2fuzzcheck-pcre2_fuzzsupport.o `test -f 'src/pcre2_fuzzsupport.c' || echo '$(srcdir)/'`src/pcre2_fuzzsupport.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/pcre2fuzzcheck-pcre2_fuzzsupport.Tpo src/$(DEPDIR)/pcre2fuzzcheck-pcre2_fuzzsupport.Po
@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='src/pcre2_fuzzsupport.c' object='src/pcre2fuzzcheck-pcre2_fuzzsupport.o' libtool=no @AMDEPBACKSLASH@
@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(pcre2fuzzcheck_CFLAGS) $(CFLAGS) -c -o src/pcre2fuzzcheck-pcre2_fuzzsupport.o `test -f 'src/pcre2_fuzzsupport.c' || echo '$(srcdir)/'`src/pcre2_fuzzsupport.c
src/pcre2fuzzcheck-pcre2_fuzzsupport.obj: src/pcre2_fuzzsupport.c
@am__fastdepCC_TRUE@ $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(pcre2fuzzcheck_CFLAGS) $(CFLAGS) -MT src/pcre2fuzzcheck-pcre2_fuzzsupport.obj -MD -MP -MF src/$(DEPDIR)/pcre2fuzzcheck-pcre2_fuzzsupport.Tpo -c -o src/pcre2fuzzcheck-pcre2_fuzzsupport.obj `if test -f 'src/pcre2_fuzzsupport.c'; then $(CYGPATH_W) 'src/pcre2_fuzzsupport.c'; else $(CYGPATH_W) '$(srcdir)/src/pcre2_fuzzsupport.c'; fi`
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/pcre2fuzzcheck-pcre2_fuzzsupport.Tpo src/$(DEPDIR)/pcre2fuzzcheck-pcre2_fuzzsupport.Po
@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='src/pcre2_fuzzsupport.c' object='src/pcre2fuzzcheck-pcre2_fuzzsupport.obj' libtool=no @AMDEPBACKSLASH@
@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(pcre2fuzzcheck_CFLAGS) $(CFLAGS) -c -o src/pcre2fuzzcheck-pcre2_fuzzsupport.obj `if test -f 'src/pcre2_fuzzsupport.c'; then $(CYGPATH_W) 'src/pcre2_fuzzsupport.c'; else $(CYGPATH_W) '$(srcdir)/src/pcre2_fuzzsupport.c'; fi`
src/pcre2grep-pcre2grep.o: src/pcre2grep.c
@am__fastdepCC_TRUE@ $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(pcre2grep_CFLAGS) $(CFLAGS) -MT src/pcre2grep-pcre2grep.o -MD -MP -MF src/$(DEPDIR)/pcre2grep-pcre2grep.Tpo -c -o src/pcre2grep-pcre2grep.o `test -f 'src/pcre2grep.c' || echo '$(srcdir)/'`src/pcre2grep.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) src/$(DEPDIR)/pcre2grep-pcre2grep.Tpo src/$(DEPDIR)/pcre2grep-pcre2grep.Po
@ -2734,7 +2916,7 @@ distdir: $(DISTFILES)
! -type d ! -perm -444 -exec $(install_sh) -c -m a+r {} {} \; \
|| chmod -R a+r "$(distdir)"
dist-gzip: distdir
tardir=$(distdir) && $(am__tar) | GZIP=$(GZIP_ENV) gzip -c >$(distdir).tar.gz
tardir=$(distdir) && $(am__tar) | eval GZIP= gzip $(GZIP_ENV) -c >$(distdir).tar.gz
$(am__post_remove_distdir)
dist-bzip2: distdir
tardir=$(distdir) && $(am__tar) | BZIP2=$${BZIP2--9} bzip2 -c >$(distdir).tar.bz2
@ -2759,7 +2941,7 @@ dist-shar: distdir
@echo WARNING: "Support for shar distribution archives is" \
"deprecated." >&2
@echo WARNING: "It will be removed altogether in Automake 2.0" >&2
shar $(distdir) | GZIP=$(GZIP_ENV) gzip -c >$(distdir).shar.gz
shar $(distdir) | eval GZIP= gzip $(GZIP_ENV) -c >$(distdir).shar.gz
$(am__post_remove_distdir)
dist-zip: distdir
-rm -f $(distdir).zip
@ -2776,7 +2958,7 @@ dist dist-all:
distcheck: dist
case '$(DIST_ARCHIVES)' in \
*.tar.gz*) \
GZIP=$(GZIP_ENV) gzip -dc $(distdir).tar.gz | $(am__untar) ;;\
eval GZIP= gzip $(GZIP_ENV) -dc $(distdir).tar.gz | $(am__untar) ;;\
*.tar.bz2*) \
bzip2 -dc $(distdir).tar.bz2 | $(am__untar) ;;\
*.tar.lz*) \
@ -2786,7 +2968,7 @@ distcheck: dist
*.tar.Z*) \
uncompress -c $(distdir).tar.Z | $(am__untar) ;;\
*.shar.gz*) \
GZIP=$(GZIP_ENV) gzip -dc $(distdir).shar.gz | unshar ;;\
eval GZIP= gzip $(GZIP_ENV) -dc $(distdir).shar.gz | unshar ;;\
*.zip*) \
unzip $(distdir).zip ;;\
esac
@ -2860,8 +3042,8 @@ check-am: all-am
$(MAKE) $(AM_MAKEFLAGS) check-TESTS
check: $(BUILT_SOURCES)
$(MAKE) $(AM_MAKEFLAGS) check-am
all-am: Makefile $(LTLIBRARIES) $(PROGRAMS) $(SCRIPTS) $(MANS) $(DATA) \
$(HEADERS)
all-am: Makefile $(LIBRARIES) $(LTLIBRARIES) $(PROGRAMS) $(SCRIPTS) \
$(MANS) $(DATA) $(HEADERS)
install-binPROGRAMS: install-libLTLIBRARIES
installdirs:
@ -2899,6 +3081,7 @@ clean-generic:
distclean-generic:
-test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES)
-test . = "$(srcdir)" || test -z "$(CONFIG_CLEAN_VPATH_FILES)" || rm -f $(CONFIG_CLEAN_VPATH_FILES)
-rm -f .libs/$(am__dirstamp)
-rm -f src/$(DEPDIR)/$(am__dirstamp)
-rm -f src/$(am__dirstamp)
-test -z "$(DISTCLEANFILES)" || rm -f $(DISTCLEANFILES)
@ -2912,7 +3095,8 @@ maintainer-clean-generic:
clean: clean-am
clean-am: clean-binPROGRAMS clean-generic clean-libLTLIBRARIES \
clean-libtool clean-local clean-noinstPROGRAMS mostlyclean-am
clean-libtool clean-local clean-noinstLIBRARIES \
clean-noinstPROGRAMS mostlyclean-am
distclean: distclean-am
-rm -f $(am__CONFIG_DISTCLEAN_FILES)
@ -2997,29 +3181,30 @@ uninstall-man: uninstall-man1 uninstall-man3
.PHONY: CTAGS GTAGS TAGS all all-am am--refresh check check-TESTS \
check-am clean clean-binPROGRAMS clean-cscope clean-generic \
clean-libLTLIBRARIES clean-libtool clean-local \
clean-noinstPROGRAMS cscope cscopelist-am ctags ctags-am dist \
dist-all dist-bzip2 dist-gzip dist-lzip dist-shar dist-tarZ \
dist-xz dist-zip distcheck distclean distclean-compile \
distclean-generic distclean-hdr distclean-libtool \
distclean-local distclean-tags distcleancheck distdir \
distuninstallcheck dvi dvi-am html html-am info info-am \
install install-am install-binPROGRAMS install-binSCRIPTS \
install-data install-data-am install-dist_docDATA \
install-dist_htmlDATA install-dvi install-dvi-am install-exec \
install-exec-am install-html install-html-am \
install-includeHEADERS install-info install-info-am \
install-libLTLIBRARIES install-man install-man1 install-man3 \
install-nodist_includeHEADERS install-pdf install-pdf-am \
install-pkgconfigDATA install-ps install-ps-am install-strip \
installcheck installcheck-am installdirs maintainer-clean \
maintainer-clean-generic mostlyclean mostlyclean-compile \
mostlyclean-generic mostlyclean-libtool pdf pdf-am ps ps-am \
recheck tags tags-am uninstall uninstall-am \
uninstall-binPROGRAMS uninstall-binSCRIPTS \
uninstall-dist_docDATA uninstall-dist_htmlDATA \
uninstall-includeHEADERS uninstall-libLTLIBRARIES \
uninstall-man uninstall-man1 uninstall-man3 \
uninstall-nodist_includeHEADERS uninstall-pkgconfigDATA
clean-noinstLIBRARIES clean-noinstPROGRAMS cscope \
cscopelist-am ctags ctags-am dist dist-all dist-bzip2 \
dist-gzip dist-lzip dist-shar dist-tarZ dist-xz dist-zip \
distcheck distclean distclean-compile distclean-generic \
distclean-hdr distclean-libtool distclean-local distclean-tags \
distcleancheck distdir distuninstallcheck dvi dvi-am html \
html-am info info-am install install-am install-binPROGRAMS \
install-binSCRIPTS install-data install-data-am \
install-dist_docDATA install-dist_htmlDATA install-dvi \
install-dvi-am install-exec install-exec-am install-html \
install-html-am install-includeHEADERS install-info \
install-info-am install-libLTLIBRARIES install-man \
install-man1 install-man3 install-nodist_includeHEADERS \
install-pdf install-pdf-am install-pkgconfigDATA install-ps \
install-ps-am install-strip installcheck installcheck-am \
installdirs maintainer-clean maintainer-clean-generic \
mostlyclean mostlyclean-compile mostlyclean-generic \
mostlyclean-libtool pdf pdf-am ps ps-am recheck tags tags-am \
uninstall uninstall-am uninstall-binPROGRAMS \
uninstall-binSCRIPTS uninstall-dist_docDATA \
uninstall-dist_htmlDATA uninstall-includeHEADERS \
uninstall-libLTLIBRARIES uninstall-man uninstall-man1 \
uninstall-man3 uninstall-nodist_includeHEADERS \
uninstall-pkgconfigDATA
.PRECIOUS: Makefile

248
pcre2-10.32/NEWS vendored Normal file
View file

@ -0,0 +1,248 @@
News about PCRE2 releases
-------------------------
Version 10.32 10-September-2018
-------------------------------
This is another mainly bugfix and tidying release with a few minor
enhancements. These are the main ones:
1. pcre2grep now supports the inclusion of binary zeros in patterns that are
read from files via the -f option.
2. ./configure now supports --enable-jit=auto, which automatically enables JIT
if the hardware supports it.
3. In pcre2_dfa_match(), internal recursive calls no longer use the stack for
local workspace and local ovectors. Instead, an initial block of stack is
reserved, but if this is insufficient, heap memory is used. The heap limit
parameter now applies to pcre2_dfa_match().
4. Updated to Unicode version 11.0.0.
5. (*ACCEPT:ARG), (*FAIL:ARG), and (*COMMIT:ARG) are now supported.
6. Added support for \N{U+dddd}, but only in Unicode mode.
7. Added support for (?^) to unset all imnsx options.
Version 10.31 12-February-2018
------------------------------
This is mainly a bugfix and tidying release (see ChangeLog for full details).
However, there are some minor enhancements.
1. New pcre2_config() options: PCRE2_CONFIG_NEVER_BACKSLASH_C and
PCRE2_CONFIG_COMPILED_WIDTHS.
2. New pcre2_pattern_info() option PCRE2_INFO_EXTRAOPTIONS to retrieve the
extra compile time options.
3. There are now public names for all the pcre2_compile() error numbers.
4. Added PCRE2_CALLOUT_STARTMATCH and PCRE2_CALLOUT_BACKTRACK bits to a new
field callout_flags in callout blocks.
Version 10.30 14-August-2017
----------------------------
The full list of changes that includes bugfixes and tidies is, as always, in
ChangeLog. These are the most important new features:
1. The main interpreter, pcre2_match(), has been refactored into a new version
that does not use recursive function calls (and therefore the system stack) for
remembering backtracking positions. This makes --disable-stack-for-recursion a
NOOP. The new implementation allows backtracking into recursive group calls in
patterns, making it more compatible with Perl, and also fixes some other
previously hard-to-do issues. For patterns that have a lot of backtracking, the
heap is now used, and there is an explicit limit on the amount, settable by
pcre2_set_heap_limit() or (*LIMIT_HEAP=xxx). The "recursion limit" is retained,
but is renamed as "depth limit" (though the old names remain for
compatibility).
There is also a change in the way callouts from pcre2_match() are handled. The
offset_vector field in the callout block is no longer a pointer to the
actual ovector that was passed to the matching function in the match data
block. Instead it points to an internal ovector of a size large enough to hold
all possible captured substrings in the pattern.
2. The new option PCRE2_ENDANCHORED insists that a pattern match must end at
the end of the subject.
3. The new option PCRE2_EXTENDED_MORE implements Perl's /xx feature, and
pcre2test is upgraded to support it. Setting within the pattern by (?xx) is
also supported.
4. (?n) can be used to set PCRE2_NO_AUTO_CAPTURE, because Perl now has this.
5. Additional compile options in the compile context are now available, and the
first two are: PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES and
PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL.
6. The newline type PCRE2_NEWLINE_NUL is now available.
7. The match limit value now also applies to pcre2_dfa_match() as there are
patterns that can use up a lot of resources without necessarily recursing very
deeply.
8. The option REG_PEND (a GNU extension) is now available for the POSIX
wrapper. Also there is a new option PCRE2_LITERAL which is used to support
REG_NOSPEC.
9. PCRE2_EXTRA_MATCH_LINE and PCRE2_EXTRA_MATCH_WORD are implemented for the
benefit of pcre2grep, and pcre2grep's -F, -w, and -x options are re-implemented
using PCRE2_LITERAL, PCRE2_EXTRA_MATCH_WORD, and PCRE2_EXTRA_MATCH_LINE. This
is tidier and also fixes some bugs.
10. The Unicode tables are upgraded from Unicode 8.0.0 to Unicode 10.0.0.
11. There are some experimental functions for converting foreign patterns
(globs and POSIX patterns) into PCRE2 patterns.
Version 10.23 14-February-2017
------------------------------
1. ChangeLog has the details of a lot of bug fixes and tidies.
2. There has been a major re-factoring of the pcre2_compile.c file. Most syntax
checking is now done in the pre-pass that identifies capturing groups. This has
reduced the amount of duplication and made the code tidier. While doing this,
some minor bugs and Perl incompatibilities were fixed (see ChangeLog for
details.)
3. Back references are now permitted in lookbehind assertions when there are
no duplicated group numbers (that is, (?| has not been used), and, if the
reference is by name, there is only one group of that name. The referenced
group must, of course be of fixed length.
4. \g{+<number>} (e.g. \g{+2} ) is now supported. It is a "forward back
reference" and can be useful in repetitions (compare \g{-<number>} ). Perl does
not recognize this syntax.
5. pcre2grep now automatically expands its buffer up to a maximum set by
--max-buffer-size.
6. The -t option (grand total) has been added to pcre2grep.
7. A new function called pcre2_code_copy_with_tables() exists to copy a
compiled pattern along with a private copy of the character tables that is
uses.
8. A user supplied a number of patches to upgrade pcre2grep under Windows and
tidy the code.
9. Several updates have been made to pcre2test and test scripts (see
ChangeLog).
Version 10.22 29-July-2016
--------------------------
1. ChangeLog has the details of a number of bug fixes.
2. The POSIX wrapper function regcomp() did not used to support back references
and subroutine calls if called with the REG_NOSUB option. It now does.
3. A new function, pcre2_code_copy(), is added, to make a copy of a compiled
pattern.
4. Support for string callouts is added to pcre2grep.
5. Added the PCRE2_NO_JIT option to pcre2_match().
6. The pcre2_get_error_message() function now returns with a negative error
code if the error number it is given is unknown.
7. Several updates have been made to pcre2test and test scripts (see
ChangeLog).
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.
****

View file

@ -1,10 +1,6 @@
Building PCRE2 without using autotools
--------------------------------------
This document has been converted from the PCRE1 document. I have removed a
number of sections about building in various environments, as they applied only
to PCRE1 and are probably out of date.
This document contains the following sections:
General
@ -14,6 +10,7 @@ This document contains the following sections:
Calling conventions in Windows environments
Comments about Win32 builds
Building PCRE2 on Windows with CMake
Building PCRE2 on Windows with Visual Studio
Testing with RunTest.bat
Building PCRE2 on native z/OS and z/VM
@ -49,7 +46,7 @@ can skip ahead to the CMake section.
macro settings that it contains to whatever is appropriate for your
environment. In particular, you can alter the definition of the NEWLINE
macro to specify what character(s) you want to be interpreted as line
terminators.
terminators by default.
When you compile any of the PCRE2 modules, you must specify
-DHAVE_CONFIG_H to your compiler so that src/config.h is included in the
@ -95,8 +92,10 @@ can skip ahead to the CMake section.
pcre2_compile.c
pcre2_config.c
pcre2_context.c
pcre2_convert.c
pcre2_dfa_match.c
pcre2_error.c
pcre2_extuni.c
pcre2_find_bracket.c
pcre2_jit_compile.c
pcre2_maketables.c
@ -123,10 +122,14 @@ can skip ahead to the CMake section.
Note that you must compile pcre2_jit_compile.c, even if you have not
defined SUPPORT_JIT in src/config.h, because when JIT support is not
configured, dummy functions are compiled. When JIT support IS configured,
pcre2_compile.c #includes other files from the sljit subdirectory, where
there should be 16 files, all of whose names begin with "sljit". It also
#includes src/pcre2_jit_match.c and src/pcre2_jit_misc.c, so you should
not compile these yourself.
pcre2_jit_compile.c #includes other files from the sljit subdirectory,
all of whose names begin with "sljit". It also #includes
src/pcre2_jit_match.c and src/pcre2_jit_misc.c, so you should not compile
these yourself.
Note also that the pcre2_fuzzsupport.c file contains special code that is
useful to those who want to run fuzzing tests on the PCRE2 library. Unless
you are doing that, you can ignore it.
(5) Now link all the compiled code into an object library in whichever form
your system keeps such libraries. This is the basic PCRE2 C 8-bit library.
@ -174,26 +177,18 @@ can skip ahead to the CMake section.
(11) If you want to use the pcre2grep command, compile and link
src/pcre2grep.c; it uses only the basic 8-bit PCRE2 library (it does not
need the pcre2posix library).
need the pcre2posix library). If you have built the PCRE2 library with JIT
support by defining SUPPORT_JIT in src/config.h, you can also define
SUPPORT_PCRE2GREP_JIT, which causes pcre2grep to make use of JIT (unless
it is run with --no-jit). If you define SUPPORT_PCRE2GREP_JIT without
defining SUPPORT_JIT, pcre2grep does not try to make use of JIT.
STACK SIZE IN WINDOWS ENVIRONMENTS
The default processor stack size of 1Mb in some Windows environments is too
small for matching patterns that need much recursion. In particular, test 2 may
fail because of this. Normally, running out of stack causes a crash, but there
have been cases where the test program has just died silently. See your linker
documentation for how to increase stack size if you experience problems. If you
are using CMake (see "BUILDING PCRE2 ON WINDOWS WITH CMAKE" below) and the gcc
compiler, you can increase the stack size for pcre2test and pcre2grep by
setting the CMAKE_EXE_LINKER_FLAGS variable to "-Wl,--stack,8388608" (for
example). The Linux default of 8Mb is a reasonable choice for the stack, though
even that can be too small for some pattern/subject combinations.
PCRE2 has a compile configuration option to disable the use of stack for
recursion so that heap is used instead. However, pattern matching is
significantly slower when this is done. There is more about stack usage in the
"pcre2stack" documentation.
Prior to release 10.30 the default system stack size of 1MiB in some Windows
environments caused issues with some tests. This should no longer be the case
for 10.30 and later releases.
LINKING PROGRAMS IN WINDOWS ENVIRONMENTS
@ -336,6 +331,18 @@ cache can be deleted by selecting "File > Delete Cache".
available for review in Testing\Temporary under your build dir.
BUILDING PCRE2 ON WINDOWS WITH VISUAL STUDIO
The code currently cannot be compiled without a stdint.h header, which is
available only in relatively recent versions of Visual Studio. However, this
portable and permissively-licensed implementation of the header worked without
issue:
http://www.azillionmonkeys.com/qed/pstdint.h
Just rename it and drop it into the top level of the build tree.
TESTING WITH RUNTEST.BAT
If configured with CMake, building the test project ("make test" or building
@ -375,18 +382,19 @@ BUILDING PCRE2 ON NATIVE Z/OS AND Z/VM
z/OS and z/VM are operating systems for mainframe computers, produced by IBM.
The character code used is EBCDIC, not ASCII or Unicode. In z/OS, UNIX APIs and
applications can be supported through UNIX System Services, and in such an
environment PCRE2 can be built in the same way as in other systems. However, in
native z/OS (without UNIX System Services) and in z/VM, special ports are
required. For details, please see this web site:
environment it should be possible to build PCRE2 in the same way as in other
systems, with the EBCDIC related configuration settings, but it is not known if
anybody has tried this.
http://www.zaconsultants.net
In native z/OS (without UNIX System Services) and in z/VM, special ports are
required. For details, please see file 939 on this web site:
The site currently has ports for PCRE1 releases, but PCRE2 should follow in due
course.
http://www.cbttape.org
You may also download PCRE1 from WWW.CBTTAPE.ORG, file 882. Everything, source
and executable, is in EBCDIC and native z/OS file formats and this is the
recommended download site.
Everything in that location, source and executable, is in EBCDIC and native
z/OS file formats. The port provides an API for LE languages such as COBOL and
for the z/OS and z/VM versions of the Rexx languages.
=============================
Last Updated: 16 July 2015
===========================
Last Updated: 19 April 2018
===========================

View file

@ -66,7 +66,7 @@ End
echo "Making pcre2.txt"
for file in pcre2 pcre2api pcre2build pcre2callout pcre2compat pcre2jit \
pcre2limits pcre2matching pcre2partial pcre2pattern pcre2perform \
pcre2posix pcre2sample pcre2serialize pcre2stack pcre2syntax \
pcre2posix pcre2sample pcre2serialize pcre2syntax \
pcre2unicode ; do
echo " Processing $file.3"
nroff -c -man $file.3 >$file.rawtxt
@ -146,7 +146,6 @@ for file in *.3 ; do
toc=-toc
if [ `expr $base : '.*_'` -ne 0 ] ; then toc="" ; fi
if [ "$base" = "pcre2sample" ] || \
[ "$base" = "pcre2stack" ] || \
[ "$base" = "pcre2compat" ] || \
[ "$base" = "pcre2limits" ] || \
[ "$base" = "pcre2unicode" ] ; then
@ -197,8 +196,10 @@ files="\
src/pcre2_compile.c \
src/pcre2_config.c \
src/pcre2_context.c \
src/pcre2_convert.c \
src/pcre2_dfa_match.c \
src/pcre2_error.c \
src/pcre2_extuni.c \
src/pcre2_find_bracket.c \
src/pcre2_internal.h \
src/pcre2_intmodedep.h \

View file

@ -15,8 +15,8 @@ subscribe or manage your subscription here:
https://lists.exim.org/mailman/listinfo/pcre-dev
Please read the NEWS file if you are upgrading from a previous release.
The contents of this README file are:
Please read the NEWS file if you are upgrading from a previous release. The
contents of this README file are:
The PCRE2 APIs
Documentation for PCRE2
@ -44,8 +44,8 @@ wrappers.
The distribution does contain a set of C wrapper functions for the 8-bit
library that are based on the POSIX regular expression API (see the pcre2posix
man page). These can be found in a library called libpcre2posix. Note that this
just provides a POSIX calling interface to PCRE2; the regular expressions
man page). These can be found in a library called libpcre2-posix. Note that
this just provides a POSIX calling interface to PCRE2; the regular expressions
themselves still follow Perl syntax and semantics. The POSIX API is restricted,
and does not give full access to all of PCRE2's facilities.
@ -58,8 +58,8 @@ renamed or pointed at by a link.
If you are using the POSIX interface to PCRE2 and there is already a POSIX
regex library installed on your system, as well as worrying about the regex.h
header file (as mentioned above), you must also take care when linking programs
to ensure that they link with PCRE2's libpcre2posix library. Otherwise they may
pick up the POSIX functions of the same name from the other library.
to ensure that they link with PCRE2's libpcre2-posix library. Otherwise they
may pick up the POSIX functions of the same name from the other library.
One way of avoiding this confusion is to compile PCRE2 with the addition of
-Dregcomp=PCRE2regcomp (and similarly for the other POSIX functions) to the
@ -95,10 +95,9 @@ PCRE2 documentation is supplied in two other forms:
Building PCRE2 on non-Unix-like systems
---------------------------------------
For a non-Unix-like system, please read the comments in the file
NON-AUTOTOOLS-BUILD, though if your system supports the use of "configure" and
"make" you may be able to build PCRE2 using autotools in the same way as for
many Unix-like systems.
For a non-Unix-like system, please read the file NON-AUTOTOOLS-BUILD, though if
your system supports the use of "configure" and "make" you may be able to build
PCRE2 using autotools in the same way as for many Unix-like systems.
PCRE2 can also be configured using CMake, which can be run in various ways
(command line, GUI, etc). This creates Makefiles, solution files, etc. The file
@ -172,21 +171,26 @@ library. They are also documented in the pcre2build man page.
give large performance improvements on certain platforms, add --enable-jit to
the "configure" command. This support is available only for certain hardware
architectures. If you try to enable it on an unsupported architecture, there
will be a compile time error.
will be a compile time error. If in doubt, use --enable-jit=auto, which
enables JIT only if the current hardware is supported.
. If you do not want to make use of the support for UTF-8 Unicode character
strings in the 8-bit library, UTF-16 Unicode character strings in the 16-bit
library, or UTF-32 Unicode character strings in the 32-bit library, you can
add --disable-unicode to the "configure" command. This reduces the size of
the libraries. It is not possible to configure one library with Unicode
support, and another without, in the same configuration.
. If you are enabling JIT under SELinux you may also want to add
--enable-jit-sealloc, which enables the use of an execmem allocator in JIT
that is compatible with SELinux. This has no effect if JIT is not enabled.
. If you do not want to make use of the default support for UTF-8 Unicode
character strings in the 8-bit library, UTF-16 Unicode character strings in
the 16-bit library, or UTF-32 Unicode character strings in the 32-bit
library, you can add --disable-unicode to the "configure" command. This
reduces the size of the libraries. It is not possible to configure one
library with Unicode support, and another without, in the same configuration.
It is also not possible to use --enable-ebcdic (see below) with Unicode
support, so if this option is set, you must also use --disable-unicode.
When Unicode support is available, the use of a UTF encoding still has to be
enabled by setting the PCRE2_UTF option at run time or starting a pattern
with (*UTF). When PCRE2 is compiled with Unicode support, its input can only
either be ASCII or UTF-8/16/32, even when running on EBCDIC platforms. It is
not possible to use both --enable-unicode and --enable-ebcdic at the same
time.
either be ASCII or UTF-8/16/32, even when running on EBCDIC platforms.
As well as supporting UTF strings, Unicode support includes support for the
\P, \p, and \X sequences that recognize Unicode character properties.
@ -196,20 +200,14 @@ library. They are also documented in the pcre2build man page.
or starting a pattern with (*UCP).
. You can build PCRE2 to recognize either CR or LF or the sequence CRLF, or any
of the preceding, or any of the Unicode newline sequences, as indicating the
end of a line. Whatever you specify at build time is the default; the caller
of PCRE2 can change the selection at run time. The default newline indicator
is a single LF character (the Unix standard). You can specify the default
newline indicator by adding --enable-newline-is-cr, --enable-newline-is-lf,
--enable-newline-is-crlf, --enable-newline-is-anycrlf, or
--enable-newline-is-any to the "configure" command, respectively.
If you specify --enable-newline-is-cr or --enable-newline-is-crlf, some of
the standard tests will fail, because the lines in the test files end with
LF. Even if the files are edited to change the line endings, there are likely
to be some failures. With --enable-newline-is-anycrlf or
--enable-newline-is-any, many tests should succeed, but there may be some
failures.
of the preceding, or any of the Unicode newline sequences, or the NUL (zero)
character as indicating the end of a line. Whatever you specify at build time
is the default; the caller of PCRE2 can change the selection at run time. The
default newline indicator is a single LF character (the Unix standard). You
can specify the default newline indicator by adding --enable-newline-is-cr,
--enable-newline-is-lf, --enable-newline-is-crlf,
--enable-newline-is-anycrlf, --enable-newline-is-any, or
--enable-newline-is-nul to the "configure" command, respectively.
. By default, the sequence \R in a pattern matches any Unicode line ending
sequence. This is independent of the option specifying what PCRE2 considers
@ -231,49 +229,47 @@ library. They are also documented in the pcre2build man page.
--with-parens-nest-limit=500
. PCRE2 has a counter that can be set to limit the amount of resources it uses
when matching a pattern. If the limit is exceeded during a match, the match
fails. The default is ten million. You can change the default by setting, for
example,
. PCRE2 has a counter that can be set to limit the amount of computing resource
it uses when matching a pattern. If the limit is exceeded during a match, the
match fails. The default is ten million. You can change the default by
setting, for example,
--with-match-limit=500000
on the "configure" command. This is just the default; individual calls to
pcre2_match() can supply their own value. There is more discussion on the
pcre2api man page.
pcre2_match() or pcre2_dfa_match() can supply their own value. There is more
discussion in the pcre2api man page (search for pcre2_set_match_limit).
. There is a separate counter that limits the depth of recursive function calls
during a matching process. This also has a default of ten million, which is
essentially "unlimited". You can change the default by setting, for example,
. There is a separate counter that limits the depth of nested backtracking
(pcre2_match()) or nested function calls (pcre2_dfa_match()) during a
matching process, which indirectly limits the amount of heap memory that is
used, and in the case of pcre2_dfa_match() the amount of stack as well. This
counter also has a default of ten million, which is essentially "unlimited".
You can change the default by setting, for example,
--with-match-limit-recursion=500000
--with-match-limit-depth=5000
Recursive function calls use up the runtime stack; running out of stack can
cause programs to crash in strange ways. There is a discussion about stack
sizes in the pcre2stack man page.
There is more discussion in the pcre2api man page (search for
pcre2_set_depth_limit).
. You can also set an explicit limit on the amount of heap memory used by
the pcre2_match() and pcre2_dfa_match() interpreters:
--with-heap-limit=500
The units are kibibytes (units of 1024 bytes). This limit does not apply when
the JIT optimization (which has its own memory control features) is used.
There is more discussion on the pcre2api man page (search for
pcre2_set_heap_limit).
. In the 8-bit library, the default maximum compiled pattern size is around
64K. You can increase this by adding --with-link-size=3 to the "configure"
command. PCRE2 then uses three bytes instead of two for offsets to different
parts of the compiled pattern. In the 16-bit library, --with-link-size=3 is
the same as --with-link-size=4, which (in both libraries) uses four-byte
offsets. Increasing the internal link size reduces performance in the 8-bit
and 16-bit libraries. In the 32-bit library, the link size setting is
ignored, as 4-byte offsets are always used.
. You can build PCRE2 so that its internal match() function that is called from
pcre2_match() does not call itself recursively. Instead, it uses memory
blocks obtained from the heap to save data that would otherwise be saved on
the stack. To build PCRE2 like this, use
--disable-stack-for-recursion
on the "configure" command. PCRE2 runs more slowly in this mode, but it may
be necessary in environments with limited stack sizes. This applies only to
the normal execution of the pcre2_match() function; if JIT support is being
successfully used, it is not relevant. Equally, it does not apply to
pcre2_dfa_match(), which does not use deeply nested recursion. There is a
discussion about stack sizes in the pcre2stack man page.
64 kibibytes. You can increase this by adding --with-link-size=3 to the
"configure" command. PCRE2 then uses three bytes instead of two for offsets
to different parts of the compiled pattern. In the 16-bit library,
--with-link-size=3 is the same as --with-link-size=4, which (in both
libraries) uses four-byte offsets. Increasing the internal link size reduces
performance in the 8-bit and 16-bit libraries. In the 32-bit library, the
link size setting is ignored, as 4-byte offsets are always used.
. For speed, PCRE2 uses four tables for manipulating and identifying characters
whose code point values are less than 256. By default, it uses a set of
@ -324,10 +320,10 @@ library. They are also documented in the pcre2build man page.
. When JIT support is enabled, pcre2grep automatically makes use of it, unless
you add --disable-pcre2grep-jit to the "configure" command.
. On non-Windows sytems there is support for calling external scripts during
matching in the pcre2grep command via PCRE2's callout facility with string
arguments. This support can be disabled by adding --disable-pcre2grep-callout
to the "configure" command.
. There is support for calling external programs during matching in the
pcre2grep command, using PCRE2's callout facility with string arguments. This
support can be disabled by adding --disable-pcre2grep-callout to the
"configure" command.
. The pcre2grep program currently supports only 8-bit data files, and so
requires the 8-bit PCRE2 library. It is possible to compile pcre2grep to use
@ -339,12 +335,23 @@ library. They are also documented in the pcre2build man page.
Of course, the relevant libraries must be installed on your system.
. The default size (in bytes) of the internal buffer used by pcre2grep can be
set by, for example:
. The default starting size (in bytes) of the internal buffer used by pcre2grep
can be set by, for example:
--with-pcre2grep-bufsize=51200
The value must be a plain integer. The default is 20480.
The value must be a plain integer. The default is 20480. The amount of memory
used by pcre2grep is actually three times this number, to allow for "before"
and "after" lines. If very long lines are encountered, the buffer is
automatically enlarged, up to a fixed maximum size.
. The default maximum size of pcre2grep's internal buffer can be set by, for
example:
--with-pcre2grep-max-bufsize=2097152
The default is either 1048576 or the value of --with-pcre2grep-bufsize,
whichever is the larger.
. It is possible to compile pcre2test so that it links with the libreadline
or libedit libraries, by specifying, respectively,
@ -369,6 +376,29 @@ library. They are also documented in the pcre2build man page.
tgetflag, or tgoto, this is the problem, and linking with the ncurses library
should fix it.
. There is a special option called --enable-fuzz-support for use by people who
want to run fuzzing tests on PCRE2. At present this applies only to the 8-bit
library. If set, it causes an extra library called libpcre2-fuzzsupport.a to
be built, but not installed. This contains a single function called
LLVMFuzzerTestOneInput() whose arguments are a pointer to a string and the
length of the string. When called, this function tries to compile the string
as a pattern, and if that succeeds, to match it. This is done both with no
options and with some random options bits that are generated from the string.
Setting --enable-fuzz-support also causes a binary called pcre2fuzzcheck to
be created. This is normally run under valgrind or used when PCRE2 is
compiled with address sanitizing enabled. It calls the fuzzing function and
outputs information about it is doing. The input strings are specified by
arguments: if an argument starts with "=" the rest of it is a literal input
string. Otherwise, it is assumed to be a file name, and the contents of the
file are the test string.
. Releases before 10.30 could be compiled with --disable-stack-for-recursion,
which caused pcre2_match() to use individual blocks on the heap for
backtracking instead of recursive function calls (which use the stack). This
is now obsolete since pcre2_match() was refactored always to use the heap (in
a much more efficient way than before). This option is retained for backwards
compatibility, but has no effect other than to output a warning.
The "configure" script builds the following files for the basic C library:
. Makefile the makefile that builds the library
@ -543,7 +573,7 @@ script creates the .txt and HTML forms of the documentation from the man pages.
Testing PCRE2
------------
-------------
To test the basic PCRE2 library on a Unix-like system, run the RunTest script.
There is another script called RunGrepTest that tests the pcre2grep command.
@ -635,32 +665,43 @@ with the perltest.sh script, and test 5 checking PCRE2-specific things.
Tests 6 and 7 check the pcre2_dfa_match() alternative matching function, in
non-UTF mode and UTF-mode with Unicode property support, respectively.
Test 8 checks some internal offsets and code size features; it is run only when
the default "link size" of 2 is set (in other cases the sizes change) and when
Unicode support is enabled.
Test 8 checks some internal offsets and code size features, but it is run only
when Unicode support is enabled. The output 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.
Tests 9 and 10 are run only in 8-bit mode, and tests 11 and 12 are run only in
16-bit and 32-bit modes. These are tests that generate different output in
8-bit mode. Each pair are for general cases and Unicode support, respectively.
Test 13 checks the handling of non-UTF characters greater than 255 by
pcre2_dfa_match() in 16-bit and 32-bit modes.
Test 14 contains a number of tests that must not be run with JIT. They check,
Test 14 contains some special UTF and UCP tests that give different output for
different code unit widths.
Test 15 contains a number of tests that must not be run with JIT. They check,
among other non-JIT things, the match-limiting features of the intepretive
matcher.
Test 15 is run only when JIT support is not available. It checks that an
Test 16 is run only when JIT support is not available. It checks that an
attempt to use JIT has the expected behaviour.
Test 16 is run only when JIT support is available. It checks JIT complete and
Test 17 is run only when JIT support is available. It checks JIT complete and
partial modes, match-limiting under JIT, and other JIT-specific features.
Tests 17 and 18 are run only in 8-bit mode. They check the POSIX interface to
Tests 18 and 19 are run only in 8-bit mode. They check the POSIX interface to
the 8-bit library, without and with Unicode support, respectively.
Test 19 checks the serialization functions by writing a set of compiled
Test 20 checks the serialization functions by writing a set of compiled
patterns to a file, and then reloading and checking them.
Tests 21 and 22 test \C support when the use of \C is not locked out, without
and with UTF support, respectively. Test 23 tests \C when it is locked out.
Tests 24 and 25 test the experimental pattern conversion functions, without and
with UTF support, respectively.
Character tables
----------------
@ -679,7 +720,7 @@ specified for ./configure, a different version of pcre2_chartables.c is built
by the program dftables (compiled from dftables.c), which uses the ANSI C
character handling functions such as isalnum(), isalpha(), isupper(),
islower(), etc. to build the table sources. This means that the default C
locale which is set for your system will control the contents of these default
locale that is set for your system will control the contents of these default
tables. You can change the default tables by editing pcre2_chartables.c and
then re-building PCRE2. If you do this, you should take care to ensure that the
file does not get automatically re-generated. The best way to do this is to
@ -734,8 +775,10 @@ The distribution should contain the files listed below.
src/pcre2_compile.c )
src/pcre2_config.c )
src/pcre2_context.c )
src/pcre2_convert.c )
src/pcre2_dfa_match.c )
src/pcre2_error.c )
src/pcre2_extuni.c )
src/pcre2_find_bracket.c )
src/pcre2_jit_compile.c )
src/pcre2_jit_match.c ) sources for the functions in the library,
@ -757,6 +800,7 @@ The distribution should contain the files listed below.
src/pcre2_xclass.c )
src/pcre2_printint.c debugging function that is used by pcre2test,
src/pcre2_fuzzsupport.c function for (optional) fuzzing support
src/config.h.in template for config.h, when built by "configure"
src/pcre2.h.in template for pcre2.h when built by "configure"
@ -772,7 +816,6 @@ The distribution should contain the files listed below.
src/pcre2demo.c simple demonstration of coding calls to PCRE2
src/pcre2grep.c source of a grep utility that uses PCRE2
src/pcre2test.c comprehensive test program
src/pcre2_printint.c part of pcre2test
src/pcre2_jit_test.c JIT test program
(C) Auxiliary files:
@ -814,7 +857,7 @@ The distribution should contain the files listed below.
libpcre2-8.pc.in template for libpcre2-8.pc for pkg-config
libpcre2-16.pc.in template for libpcre2-16.pc for pkg-config
libpcre2-32.pc.in template for libpcre2-32.pc for pkg-config
libpcre2posix.pc.in template for libpcre2posix.pc for pkg-config
libpcre2-posix.pc.in template for libpcre2-posix.pc for pkg-config
ltmain.sh file used to build a libtool script
missing ) common stub for a few missing GNU programs while
) installing, generated by automake
@ -837,12 +880,12 @@ The distribution should contain the files listed below.
(E) Auxiliary files for building PCRE2 "by hand"
pcre2.h.generic ) a version of the public PCRE2 header file
src/pcre2.h.generic ) a version of the public PCRE2 header file
) for use in non-"configure" environments
config.h.generic ) a version of config.h for use in non-"configure"
src/config.h.generic ) a version of config.h for use in non-"configure"
) environments
Philip Hazel
Email local part: ph10
Email domain: cam.ac.uk
Last updated: 01 April 2016
Last updated: 17 June 2018

View file

@ -4,6 +4,12 @@
# itself. What we are checking here is the file handling and options that are
# supported by pcre2grep. This script must be run in the build directory.
# CODING CONVENTIONS:
# * Put printf arguments in single, not double quotes to avoid unwanted
# escaping.
# * Use \0 for binary zero in printf, not \x0, for the benefit of older
# versions.
# Set the C locale, so that sort(1) behaves predictably.
LC_ALL=C
@ -11,7 +17,8 @@ export LC_ALL
# Remove any non-default colouring and aliases that the caller may have set.
unset PCRE2GREP_COLOUR PCRE2GREP_COLOR
unset PCRE2GREP_COLOUR PCRE2GREP_COLOR PCREGREP_COLOUR PCREGREP_COLOR
unset GREP_COLOR GREP_COLORS
unset cp ls mv rm
# Remember the current (build) directory, set the program to be tested, and
@ -22,12 +29,12 @@ pcre2grep=$builddir/pcre2grep
pcre2test=$builddir/pcre2test
if [ ! -x $pcre2grep ] ; then
echo "** $pcre2grep does not exist or is not execuatble."
echo "** $pcre2grep does not exist or is not executable."
exit 1
fi
if [ ! -x $pcre2test ] ; then
echo "** $pcre2test does not exist or is not execuatble."
echo "** $pcre2test does not exist or is not executable."
exit 1
fi
@ -247,7 +254,7 @@ echo "---------------------------- Test 35 -----------------------------" >>test
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 36 -----------------------------" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -L -r --include=grepinput --exclude 'grepinput$' --exclude=grepinput8 --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -L -r --include=grepinput --exclude 'grepinput$' --exclude=grepinput8 --exclude=grepinputM --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 37 -----------------------------" >>testtrygrep
@ -390,6 +397,12 @@ echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 70 -----------------------------" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep --color=always -M "triple:\t.*\n\n" ./testdata/grepinput3) >>testtrygrep
echo "RC=$?" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep --color=always -M -n "triple:\t.*\n\n" ./testdata/grepinput3) >>testtrygrep
echo "RC=$?" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -M "triple:\t.*\n\n" ./testdata/grepinput3) >>testtrygrep
echo "RC=$?" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -M -n "triple:\t.*\n\n" ./testdata/grepinput3) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 71 -----------------------------" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -o "^01|^02|^03" ./testdata/grepinput) >>testtrygrep
@ -440,7 +453,7 @@ echo "---------------------------- Test 82 -----------------------------" >>test
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 83 -----------------------------" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep --buffer-size=100 "^a" ./testdata/grepinput3) >>testtrygrep 2>&1
(cd $srcdir; $valgrind $vjs $pcre2grep --buffer-size=10 --max-buffer-size=100 "^a" ./testdata/grepinput3) >>testtrygrep 2>&1
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 84 -----------------------------" >>testtrygrep
@ -493,25 +506,25 @@ echo "---------------------------- Test 95 -----------------------------" >>test
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 96 -----------------------------" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -L -r --include-dir=testdata --exclude '^(?!grepinput)' 'fox' ./test* | sort) >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -L -r --include-dir=testdata --exclude '^(?!grepinput)' --exclude=grepinputM 'fox' ./test* | sort) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 97 -----------------------------" >>testtrygrep
echo "grepinput$" >testtemp1grep
echo "grepinput8" >>testtemp1grep
(cd $srcdir; $valgrind $vjs $pcre2grep -L -r --include=grepinput --exclude-from $builddir/testtemp1grep --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -L -r --include=grepinput --exclude=grepinputM --exclude-from $builddir/testtemp1grep --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 98 -----------------------------" >>testtrygrep
echo "grepinput$" >testtemp1grep
echo "grepinput8" >>testtemp1grep
(cd $srcdir; $valgrind $vjs $pcre2grep -L -r --exclude=grepinput3 --include=grepinput --exclude-from $builddir/testtemp1grep --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -L -r --exclude=grepinput3 --exclude=grepinputM --include=grepinput --exclude-from $builddir/testtemp1grep --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 99 -----------------------------" >>testtrygrep
echo "grepinput$" >testtemp1grep
echo "grepinput8" >testtemp2grep
(cd $srcdir; $valgrind $vjs $pcre2grep -L -r --include grepinput --exclude-from $builddir/testtemp1grep --exclude-from=$builddir/testtemp2grep --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -L -r --include grepinput --exclude=grepinputM --exclude-from $builddir/testtemp1grep --exclude-from=$builddir/testtemp2grep --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 100 ------------------------------" >>testtrygrep
@ -568,6 +581,79 @@ echo "---------------------------- Test 112 -----------------------------" >>tes
(cd $srcdir; $valgrind $vjs $pcre2grep --file-offsets -M 'match (\d+):\n (.)\n' testdata/grepinput) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 113 -----------------------------" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep --total-count 'the' testdata/grepinput*) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 114 -----------------------------" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -tc 'the' testdata/grepinput*) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 115 -----------------------------" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -tlc 'the' testdata/grepinput*) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 116 -----------------------------" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep --exclude=grepinputM -th 'the' testdata/grepinput*) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 117 -----------------------------" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -tch 'the' testdata/grepinput*) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 118 -----------------------------" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -tL 'the' testdata/grepinput*) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 119 -----------------------------" >>testtrygrep
printf '123\n456\n789\n---abc\ndef\nxyz\n---\n' >testNinputgrep
$valgrind $vjs $pcre2grep -Mo '(\n|[^-])*---' testNinputgrep >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 120 ------------------------------" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -HO '$0:$2$1$3' '(\w+) binary (\w+)(\.)?' ./testdata/grepinput) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 121 -----------------------------" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -F '\E and (regex)' testdata/grepinputv) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 122 -----------------------------" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -w 'cat|dog' testdata/grepinputv) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 123 -----------------------------" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -w 'dog|cat' testdata/grepinputv) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 124 -----------------------------" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -Mn --colour=always 'start[\s]+end' testdata/grepinputM) >>testtrygrep
echo "RC=$?" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -Mn --colour=always -A2 'start[\s]+end' testdata/grepinputM) >>testtrygrep
echo "RC=$?" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -Mn 'start[\s]+end' testdata/grepinputM) >>testtrygrep
echo "RC=$?" >>testtrygrep
(cd $srcdir; $valgrind $vjs $pcre2grep -Mn -A2 'start[\s]+end' testdata/grepinputM) >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 125 -----------------------------" >>testtrygrep
printf 'abcd\n' >testNinputgrep
$valgrind $vjs $pcre2grep --colour=always '(?<=\K.)' testNinputgrep >>testtrygrep
echo "RC=$?" >>testtrygrep
$valgrind $vjs $pcre2grep --colour=always '(?=.\K)' testNinputgrep >>testtrygrep
echo "RC=$?" >>testtrygrep
$valgrind $vjs $pcre2grep --colour=always '(?<=\K[ac])' testNinputgrep >>testtrygrep
echo "RC=$?" >>testtrygrep
$valgrind $vjs $pcre2grep --colour=always '(?=[ac]\K)' testNinputgrep >>testtrygrep
echo "RC=$?" >>testtrygrep
echo "---------------------------- Test 126 -----------------------------" >>testtrygrep
printf 'Next line pattern has binary zero\nABC\0XYZ\n' >testtemp1grep
printf 'ABC\0XYZ\nABCDEF\nDEFABC\n' >testtemp2grep
$valgrind $vjs $pcre2grep -a -f testtemp1grep testtemp2grep >>testtrygrep
echo "RC=$?" >>testtrygrep
# Now compare the results.
$cf $srcdir/testdata/grepoutput testtrygrep
@ -607,27 +693,42 @@ fi
# starts with a hyphen. These tests are run in the build directory.
echo "Testing pcre2grep newline settings"
printf "abc\rdef\r\nghi\njkl" >testNinputgrep
printf 'abc\rdef\r\nghi\njkl' >testNinputgrep
printf "%c--------------------------- Test N1 ------------------------------\r\n" - >testtrygrep
printf '%c--------------------------- Test N1 ------------------------------\r\n' - >testtrygrep
$valgrind $vjs $pcre2grep -n -N CR "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep
printf "%c--------------------------- Test N2 ------------------------------\r\n" - >>testtrygrep
printf '%c--------------------------- Test N2 ------------------------------\r\n' - >>testtrygrep
$valgrind $vjs $pcre2grep -n --newline=crlf "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep
printf "%c--------------------------- Test N3 ------------------------------\r\n" - >>testtrygrep
printf '%c--------------------------- Test N3 ------------------------------\r\n' - >>testtrygrep
pattern=`printf 'def\rjkl'`
$valgrind $vjs $pcre2grep -n --newline=cr -F "$pattern" testNinputgrep >>testtrygrep
printf "%c--------------------------- Test N4 ------------------------------\r\n" - >>testtrygrep
printf '%c--------------------------- Test N4 ------------------------------\r\n' - >>testtrygrep
$valgrind $vjs $pcre2grep -n --newline=crlf -F -f $srcdir/testdata/greppatN4 testNinputgrep >>testtrygrep
printf "%c--------------------------- Test N5 ------------------------------\r\n" - >>testtrygrep
printf '%c--------------------------- Test N5 ------------------------------\r\n' - >>testtrygrep
$valgrind $vjs $pcre2grep -n --newline=any "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep
printf "%c--------------------------- Test N6 ------------------------------\r\n" - >>testtrygrep
printf '%c--------------------------- Test N6 ------------------------------\r\n' - >>testtrygrep
$valgrind $vjs $pcre2grep -n --newline=anycrlf "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep
# It seems impossible to handle NUL characters easily in Solaris (aka SunOS).
# The version of sed explicitly doesn't like them. For the moment, we just
# don't run this test under SunOS. Fudge the output so that the comparison
# works. A similar problem has also been reported for MacOS (Darwin).
printf '%c--------------------------- Test N7 ------------------------------\r\n' - >>testtrygrep
uname=`uname`
if [ "$uname" != "SunOS" -a "$uname" != "Darwin" ] ; then
printf 'abc\0def' >testNinputgrep
$valgrind $vjs $pcre2grep -na --newline=nul "^(abc|def)" testNinputgrep | sed 's/\x00/ZERO/' >>testtrygrep
echo "" >>testtrygrep
else
echo '1:abcZERO2:def' >>testtrygrep
fi
$cf $srcdir/testdata/grepoutputN testtrygrep
if [ $? != 0 ] ; then exit 1; fi
@ -637,6 +738,9 @@ if $valgrind $vjs $pcre2grep --help | $valgrind $vjs $pcre2grep -q 'Callout scri
echo "Testing pcre2grep script callouts"
$valgrind $vjs $pcre2grep '(T)(..(.))(?C"/bin/echo|Arg1: [$1] [$2] [$3]|Arg2: $|${1}$| ($4) ($14) ($0)")()' $srcdir/testdata/grepinputv >testtrygrep
$valgrind $vjs $pcre2grep '(T)(..(.))()()()()()()()(..)(?C"/bin/echo|Arg1: [$11] [${11}]")' $srcdir/testdata/grepinputv >>testtrygrep
$valgrind $vjs $pcre2grep '(T)(?C"|$0:$1$n")' $srcdir/testdata/grepinputv >>testtrygrep
$valgrind $vjs $pcre2grep '(T)(?C"|$1$n")(*F)' $srcdir/testdata/grepinputv >>testtrygrep
# The above has no newline, which 'diff -ub' ignores, so add one.
$cf $srcdir/testdata/grepoutputC testtrygrep
if [ $? != 0 ] ; then exit 1; fi
else

View file

@ -78,7 +78,9 @@ title20="Test 20: Serialization and code copy 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
title24="Test 24: Non-UTF pattern conversion tests"
title25="Test 25: UTF pattern conversion tests"
maxtest=25
if [ $# -eq 1 -a "$1" = "list" ]; then
echo $title0
@ -105,6 +107,8 @@ if [ $# -eq 1 -a "$1" = "list" ]; then
echo $title21
echo $title22
echo $title23
echo $title24
echo $title25
exit 0
fi
@ -232,6 +236,8 @@ do20=no
do21=no
do22=no
do23=no
do24=no
do25=no
while [ $# -gt 0 ] ; do
case $1 in
@ -259,6 +265,8 @@ while [ $# -gt 0 ] ; do
21) do21=yes;;
22) do22=yes;;
23) do23=yes;;
24) do24=yes;;
25) do25=yes;;
-8) arg8=yes;;
-16) arg16=yes;;
-32) arg32=yes;;
@ -308,27 +316,14 @@ if [ $link_size -gt 4 ] ; then
exit 1
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 by gcc with -fsanitize=address. If "bigstack" is on the command
# line, set even bigger numbers. 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. Test 2 now has code to automatically try again with a 64M
# stack if it crashes when test2stack is "-S 16" when matching with the
# interpreter.
# If it is possible to set the system stack size and -bigstack was given,
# set up a large stack.
$sim ./pcre2test -S 1 /dev/null /dev/null
if [ $? -eq 0 ] ; then
if [ "$bigstack" = "" ] ; then
test2stack="-S 16"
defaultstack=""
else
test2stack="-S 1024"
defaultstack="-S 64"
fi
if [ $? -eq 0 -a "$bigstack" != "" ] ; then
setstack="-S 64"
else
test2stack=""
defaultstack=""
setstack=""
fi
# All of 8-bit, 16-bit, and 32-bit character strings may be supported, but only
@ -420,7 +415,8 @@ if [ $do0 = no -a $do1 = no -a $do2 = no -a $do3 = 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 -a \
$do20 = no -a $do21 = no -a $do22 = no -a $do23 = no \
$do20 = no -a $do21 = no -a $do22 = no -a $do23 = no -a \
$do24 = no -a $do25 = no \
]; then
do0=yes
do1=yes
@ -446,6 +442,8 @@ if [ $do0 = no -a $do1 = no -a $do2 = no -a $do3 = no -a \
do21=yes
do22=yes
do23=yes
do24=yes
do25=yes
fi
# Handle any explicit skips at this stage, so that an argument list may consist
@ -476,7 +474,7 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ $do0 = yes ] ; then
echo $title0
echo '/abc/jit,memory' >testSinput
echo '/abc/jit,memory,framesize' >testSinput
echo ' abc' >>testSinput
echo '' >testtry
checkspecial '-C'
@ -490,7 +488,7 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ $do1 = yes ] ; then
echo $title1
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput1 testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput1 testtry
checkresult $? 1 "$opt"
done
fi
@ -500,34 +498,10 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ $do2 = yes ] ; then
echo $title2 "(excluding UTF-$bits)"
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $test2stack $bmode $opt $testdata/testinput2 testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput2 testtry
if [ $? = 0 ] ; then
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $bmode $opt -error -63,-62,-2,-1,0,100,188,189 >>testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $bmode $opt -error -70,-62,-2,-1,0,100,101,191,200 >>testtry
checkresult $? 2 "$opt"
else
echo " "
echo "** Test 2, when run under the interpreter, requires a lot of stack."
echo "** If it has crashed with a segmentation fault, it may be that you"
echo "** do not have enough stack available by default. Please see the"
echo "** 'pcre2stack' man page for a discussion of PCRE2's stack usage."
if [ "$test2stack" != "-S 16" -o "$opt" != "" ]; then
echo " "
exit 1
fi
echo " "
echo "** Trying again with an increased stack size."
echo " "
echo $title2 "(excluding UTF-$bits) (64M stack)"
$sim $valgrind ${opt:+$vjs} ./pcre2test -q -S 64 $bmode $opt $testdata/testinput2 testtry
if [ $? = 0 ] ; then
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $bmode $opt -error -63,-62,-2,-1,0,100,188,189 >>testtry
checkresult $? 2 "$opt"
else
echo " "
echo "** Failed with an increased stack size. Tests abandoned."
echo " "
exit 1
fi
fi
done
fi
@ -577,7 +551,7 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ "$locale" != "" ] ; then
echo $title3 "(using '$locale' locale)"
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $infile testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $infile testtry
if [ $? = 0 ] ; then
case "$opt" in
-jit) with=" with JIT";;
@ -614,7 +588,7 @@ for bmode in "$test8" "$test16" "$test32"; do
echo " Skipped because UTF-$bits support is not available"
else
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput4 testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput4 testtry
checkresult $? 4 "$opt"
done
fi
@ -626,7 +600,7 @@ for bmode in "$test8" "$test16" "$test32"; do
echo " Skipped because UTF-$bits support is not available"
else
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput5 testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput5 testtry
checkresult $? 5 "$opt"
done
fi
@ -636,7 +610,7 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ $do6 = yes ] ; then
echo $title6
$sim $valgrind ./pcre2test -q $defaultstack $bmode $testdata/testinput6 testtry
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput6 testtry
checkresult $? 6 ""
fi
@ -645,7 +619,7 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
$sim $valgrind ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput7 testtry
$sim $valgrind ./pcre2test -q $setstack $bmode $opt $testdata/testinput7 testtry
checkresult $? 7 ""
fi
fi
@ -663,7 +637,7 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
$sim $valgrind ./pcre2test -q $defaultstack $bmode $testdata/testinput8 testtry
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput8 testtry
checkresult $? 8-$bits-$link_size ""
fi
fi
@ -676,7 +650,7 @@ for bmode in "$test8" "$test16" "$test32"; do
echo " Skipped when running 16/32-bit tests"
else
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput9 testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput9 testtry
checkresult $? 9 "$opt"
done
fi
@ -692,7 +666,7 @@ for bmode in "$test8" "$test16" "$test32"; do
echo " Skipped because UTF-$bits support is not available"
else
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput10 testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput10 testtry
checkresult $? 10 "$opt"
done
fi
@ -706,7 +680,7 @@ for bmode in "$test8" "$test16" "$test32"; do
echo " Skipped when running 8-bit tests"
else
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput11 testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput11 testtry
checkresult $? 11-$bits "$opt"
done
fi
@ -723,7 +697,7 @@ for bmode in "$test8" "$test16" "$test32"; do
echo " Skipped because UTF-$bits support is not available"
else
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput12 testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput12 testtry
checkresult $? 12-$bits "$opt"
done
fi
@ -736,7 +710,7 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ "$bits" = "8" ] ; then
echo " Skipped when running 8-bit tests"
else
$sim $valgrind ./pcre2test -q $defaultstack $bmode $testdata/testinput13 testtry
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput13 testtry
checkresult $? 13 ""
fi
fi
@ -748,7 +722,7 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
$sim $valgrind ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput14 testtry
$sim $valgrind ./pcre2test -q $setstack $bmode $opt $testdata/testinput14 testtry
checkresult $? 14-$bits ""
fi
fi
@ -757,7 +731,7 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ $do15 = yes ] ; then
echo $title15
$sim $valgrind ./pcre2test -q $defaultstack $bmode $testdata/testinput15 testtry
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput15 testtry
checkresult $? 15 ""
fi
@ -768,7 +742,7 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ $jit -ne 0 ] ; then
echo " Skipped because JIT is available"
else
$sim $valgrind ./pcre2test -q $defaultstack $bmode $testdata/testinput16 testtry
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput16 testtry
checkresult $? 16 ""
fi
fi
@ -780,7 +754,7 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ $jit -eq 0 -o "$nojit" = "yes" ] ; then
echo " Skipped because JIT is not available or nojit was specified"
else
$sim $valgrind $vjs ./pcre2test -q $defaultstack $bmode $testdata/testinput17 testtry
$sim $valgrind $vjs ./pcre2test -q $setstack $bmode $testdata/testinput17 testtry
checkresult $? 17 ""
fi
fi
@ -792,7 +766,7 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ "$bits" = "16" -o "$bits" = "32" ] ; then
echo " Skipped when running 16/32-bit tests"
else
$sim $valgrind ./pcre2test -q $defaultstack $bmode $testdata/testinput18 testtry
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput18 testtry
checkresult $? 18 ""
fi
fi
@ -806,7 +780,7 @@ for bmode in "$test8" "$test16" "$test32"; do
elif [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
$sim $valgrind ./pcre2test -q $defaultstack $bmode $testdata/testinput19 testtry
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput19 testtry
checkresult $? 19 ""
fi
fi
@ -815,7 +789,7 @@ for bmode in "$test8" "$test16" "$test32"; do
if [ $do20 = yes ] ; then
echo $title20
$sim $valgrind ./pcre2test -q $defaultstack $bmode $testdata/testinput20 testtry
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput20 testtry
checkresult $? 20 ""
fi
@ -827,7 +801,7 @@ for bmode in "$test8" "$test16" "$test32"; do
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
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput21 testtry
checkresult $? 21 "$opt"
done
fi
@ -843,7 +817,7 @@ for bmode in "$test8" "$test16" "$test32"; do
echo " Skipped because UTF-$bits support is not available"
else
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput22 testtry
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput22 testtry
checkresult $? 22-$bits "$opt"
done
fi
@ -856,11 +830,31 @@ for bmode in "$test8" "$test16" "$test32"; do
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
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput23 testtry
checkresult $? 23 ""
fi
fi
# Non-UTF pattern conversion tests
if [ "$do24" = yes ] ; then
echo $title24
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput24 testtry
checkresult $? 24 ""
fi
# UTF pattern conversion tests
if [ "$do25" = yes ] ; then
echo $title25
if [ $utf -eq 0 ] ; then
echo " Skipped because UTF-$bits support is not available"
else
$sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput25 testtry
checkresult $? 25 ""
fi
fi
# End of loop for 8/16/32-bit tests
done

View file

@ -1,6 +1,6 @@
# generated automatically by aclocal 1.15 -*- Autoconf -*-
# generated automatically by aclocal 1.15.1 -*- Autoconf -*-
# Copyright (C) 1996-2014 Free Software Foundation, Inc.
# Copyright (C) 1996-2017 Free Software Foundation, Inc.
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -20,9 +20,9 @@ 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'.])])
dnl pkg.m4 - Macros to locate and utilise pkg-config. -*- Autoconf -*-
dnl serial 11 (pkg-config-0.29.1)
dnl
# pkg.m4 - Macros to locate and utilise pkg-config. -*- Autoconf -*-
# serial 11 (pkg-config-0.29.1)
dnl Copyright © 2004 Scott James Remnant <scott@netsplit.com>.
dnl Copyright © 2012-2015 Dan Nicholson <dbn.lists@gmail.com>
dnl
@ -296,7 +296,75 @@ AS_VAR_COPY([$1], [pkg_cv_][$1])
AS_VAR_IF([$1], [""], [$5], [$4])dnl
])dnl PKG_CHECK_VAR
# Copyright (C) 2002-2014 Free Software Foundation, Inc.
dnl PKG_WITH_MODULES(VARIABLE-PREFIX, MODULES,
dnl [ACTION-IF-FOUND],[ACTION-IF-NOT-FOUND],
dnl [DESCRIPTION], [DEFAULT])
dnl ------------------------------------------
dnl
dnl Prepare a "--with-" configure option using the lowercase
dnl [VARIABLE-PREFIX] name, merging the behaviour of AC_ARG_WITH and
dnl PKG_CHECK_MODULES in a single macro.
AC_DEFUN([PKG_WITH_MODULES],
[
m4_pushdef([with_arg], m4_tolower([$1]))
m4_pushdef([description],
[m4_default([$5], [build with ]with_arg[ support])])
m4_pushdef([def_arg], [m4_default([$6], [auto])])
m4_pushdef([def_action_if_found], [AS_TR_SH([with_]with_arg)=yes])
m4_pushdef([def_action_if_not_found], [AS_TR_SH([with_]with_arg)=no])
m4_case(def_arg,
[yes],[m4_pushdef([with_without], [--without-]with_arg)],
[m4_pushdef([with_without],[--with-]with_arg)])
AC_ARG_WITH(with_arg,
AS_HELP_STRING(with_without, description[ @<:@default=]def_arg[@:>@]),,
[AS_TR_SH([with_]with_arg)=def_arg])
AS_CASE([$AS_TR_SH([with_]with_arg)],
[yes],[PKG_CHECK_MODULES([$1],[$2],$3,$4)],
[auto],[PKG_CHECK_MODULES([$1],[$2],
[m4_n([def_action_if_found]) $3],
[m4_n([def_action_if_not_found]) $4])])
m4_popdef([with_arg])
m4_popdef([description])
m4_popdef([def_arg])
])dnl PKG_WITH_MODULES
dnl PKG_HAVE_WITH_MODULES(VARIABLE-PREFIX, MODULES,
dnl [DESCRIPTION], [DEFAULT])
dnl -----------------------------------------------
dnl
dnl Convenience macro to trigger AM_CONDITIONAL after PKG_WITH_MODULES
dnl check._[VARIABLE-PREFIX] is exported as make variable.
AC_DEFUN([PKG_HAVE_WITH_MODULES],
[
PKG_WITH_MODULES([$1],[$2],,,[$3],[$4])
AM_CONDITIONAL([HAVE_][$1],
[test "$AS_TR_SH([with_]m4_tolower([$1]))" = "yes"])
])dnl PKG_HAVE_WITH_MODULES
dnl PKG_HAVE_DEFINE_WITH_MODULES(VARIABLE-PREFIX, MODULES,
dnl [DESCRIPTION], [DEFAULT])
dnl ------------------------------------------------------
dnl
dnl Convenience macro to run AM_CONDITIONAL and AC_DEFINE after
dnl PKG_WITH_MODULES check. HAVE_[VARIABLE-PREFIX] is exported as make
dnl and preprocessor variable.
AC_DEFUN([PKG_HAVE_DEFINE_WITH_MODULES],
[
PKG_HAVE_WITH_MODULES([$1],[$2],[$3],[$4])
AS_IF([test "$AS_TR_SH([with_]m4_tolower([$1]))" = "yes"],
[AC_DEFINE([HAVE_][$1], 1, [Enable ]m4_tolower([$1])[ support])])
])dnl PKG_HAVE_DEFINE_WITH_MODULES
# Copyright (C) 2002-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -311,7 +379,7 @@ AC_DEFUN([AM_AUTOMAKE_VERSION],
[am__api_version='1.15'
dnl Some users find AM_AUTOMAKE_VERSION and mistake it for a way to
dnl require some minimum version. Point them to the right macro.
m4_if([$1], [1.15], [],
m4_if([$1], [1.15.1], [],
[AC_FATAL([Do not call $0, use AM_INIT_AUTOMAKE([$1]).])])dnl
])
@ -327,12 +395,12 @@ m4_define([_AM_AUTOCONF_VERSION], [])
# Call AM_AUTOMAKE_VERSION and AM_AUTOMAKE_VERSION so they can be traced.
# This function is AC_REQUIREd by AM_INIT_AUTOMAKE.
AC_DEFUN([AM_SET_CURRENT_AUTOMAKE_VERSION],
[AM_AUTOMAKE_VERSION([1.15])dnl
[AM_AUTOMAKE_VERSION([1.15.1])dnl
m4_ifndef([AC_AUTOCONF_VERSION],
[m4_copy([m4_PACKAGE_VERSION], [AC_AUTOCONF_VERSION])])dnl
_AM_AUTOCONF_VERSION(m4_defn([AC_AUTOCONF_VERSION]))])
# Copyright (C) 2011-2014 Free Software Foundation, Inc.
# Copyright (C) 2011-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -394,7 +462,7 @@ AC_SUBST([AR])dnl
# AM_AUX_DIR_EXPAND -*- Autoconf -*-
# Copyright (C) 2001-2014 Free Software Foundation, Inc.
# Copyright (C) 2001-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -446,7 +514,7 @@ am_aux_dir=`cd "$ac_aux_dir" && pwd`
# AM_CONDITIONAL -*- Autoconf -*-
# Copyright (C) 1997-2014 Free Software Foundation, Inc.
# Copyright (C) 1997-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -477,7 +545,7 @@ AC_CONFIG_COMMANDS_PRE(
Usually this means the macro was only invoked conditionally.]])
fi])])
# Copyright (C) 1999-2014 Free Software Foundation, Inc.
# Copyright (C) 1999-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -668,7 +736,7 @@ _AM_SUBST_NOTMAKE([am__nodep])dnl
# Generate code to set up dependency tracking. -*- Autoconf -*-
# Copyright (C) 1999-2014 Free Software Foundation, Inc.
# Copyright (C) 1999-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -744,7 +812,7 @@ AC_DEFUN([AM_OUTPUT_DEPENDENCY_COMMANDS],
# Do all the work for Automake. -*- Autoconf -*-
# Copyright (C) 1996-2014 Free Software Foundation, Inc.
# Copyright (C) 1996-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -941,7 +1009,7 @@ for _am_header in $config_headers :; do
done
echo "timestamp for $_am_arg" >`AS_DIRNAME(["$_am_arg"])`/stamp-h[]$_am_stamp_count])
# Copyright (C) 2001-2014 Free Software Foundation, Inc.
# Copyright (C) 2001-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -962,7 +1030,7 @@ if test x"${install_sh+set}" != xset; then
fi
AC_SUBST([install_sh])])
# Copyright (C) 2003-2014 Free Software Foundation, Inc.
# Copyright (C) 2003-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -981,45 +1049,9 @@ fi
rmdir .tst 2>/dev/null
AC_SUBST([am__leading_dot])])
# Add --enable-maintainer-mode option to configure. -*- Autoconf -*-
# From Jim Meyering
# Copyright (C) 1996-2014 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
# with or without modifications, as long as this notice is preserved.
# AM_MAINTAINER_MODE([DEFAULT-MODE])
# ----------------------------------
# Control maintainer-specific portions of Makefiles.
# Default is to disable them, unless 'enable' is passed literally.
# For symmetry, 'disable' may be passed as well. Anyway, the user
# can override the default with the --enable/--disable switch.
AC_DEFUN([AM_MAINTAINER_MODE],
[m4_case(m4_default([$1], [disable]),
[enable], [m4_define([am_maintainer_other], [disable])],
[disable], [m4_define([am_maintainer_other], [enable])],
[m4_define([am_maintainer_other], [enable])
m4_warn([syntax], [unexpected argument to AM@&t@_MAINTAINER_MODE: $1])])
AC_MSG_CHECKING([whether to enable maintainer-specific portions of Makefiles])
dnl maintainer-mode's default is 'disable' unless 'enable' is passed
AC_ARG_ENABLE([maintainer-mode],
[AS_HELP_STRING([--]am_maintainer_other[-maintainer-mode],
am_maintainer_other[ make rules and dependencies not useful
(and sometimes confusing) to the casual installer])],
[USE_MAINTAINER_MODE=$enableval],
[USE_MAINTAINER_MODE=]m4_if(am_maintainer_other, [enable], [no], [yes]))
AC_MSG_RESULT([$USE_MAINTAINER_MODE])
AM_CONDITIONAL([MAINTAINER_MODE], [test $USE_MAINTAINER_MODE = yes])
MAINT=$MAINTAINER_MODE_TRUE
AC_SUBST([MAINT])dnl
]
)
# Check to see how 'make' treats includes. -*- Autoconf -*-
# Copyright (C) 2001-2014 Free Software Foundation, Inc.
# Copyright (C) 2001-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -1069,7 +1101,7 @@ rm -f confinc confmf
# Fake the existence of programs that GNU maintainers use. -*- Autoconf -*-
# Copyright (C) 1997-2014 Free Software Foundation, Inc.
# Copyright (C) 1997-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -1108,7 +1140,7 @@ fi
# Helper functions for option handling. -*- Autoconf -*-
# Copyright (C) 2001-2014 Free Software Foundation, Inc.
# Copyright (C) 2001-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -1137,7 +1169,7 @@ AC_DEFUN([_AM_SET_OPTIONS],
AC_DEFUN([_AM_IF_OPTION],
[m4_ifset(_AM_MANGLE_OPTION([$1]), [$2], [$3])])
# Copyright (C) 1999-2014 Free Software Foundation, Inc.
# Copyright (C) 1999-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -1184,7 +1216,7 @@ AC_LANG_POP([C])])
# For backward compatibility.
AC_DEFUN_ONCE([AM_PROG_CC_C_O], [AC_REQUIRE([AC_PROG_CC])])
# Copyright (C) 2001-2014 Free Software Foundation, Inc.
# Copyright (C) 2001-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -1203,7 +1235,7 @@ AC_DEFUN([AM_RUN_LOG],
# Check to make sure that the build environment is sane. -*- Autoconf -*-
# Copyright (C) 1996-2014 Free Software Foundation, Inc.
# Copyright (C) 1996-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -1284,7 +1316,7 @@ AC_CONFIG_COMMANDS_PRE(
rm -f conftest.file
])
# Copyright (C) 2009-2014 Free Software Foundation, Inc.
# Copyright (C) 2009-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -1344,7 +1376,7 @@ AC_SUBST([AM_BACKSLASH])dnl
_AM_SUBST_NOTMAKE([AM_BACKSLASH])dnl
])
# Copyright (C) 2001-2014 Free Software Foundation, Inc.
# Copyright (C) 2001-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -1372,7 +1404,7 @@ fi
INSTALL_STRIP_PROGRAM="\$(install_sh) -c -s"
AC_SUBST([INSTALL_STRIP_PROGRAM])])
# Copyright (C) 2006-2014 Free Software Foundation, Inc.
# Copyright (C) 2006-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@ -1391,7 +1423,7 @@ AC_DEFUN([AM_SUBST_NOTMAKE], [_AM_SUBST_NOTMAKE($@)])
# Check how to create a tarball. -*- Autoconf -*-
# Copyright (C) 2004-2014 Free Software Foundation, Inc.
# Copyright (C) 2004-2017 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,

View file

@ -4,7 +4,7 @@
me=ar-lib
scriptversion=2012-03-01.08; # UTC
# Copyright (C) 2010-2014 Free Software Foundation, Inc.
# Copyright (C) 2010-2017 Free Software Foundation, Inc.
# Written by Peter Rosin <peda@lysator.liu.se>.
#
# This program is free software; you can redistribute it and/or modify

View file

@ -1,9 +1,9 @@
#! /bin/sh
# Wrapper for compilers which do not understand '-c -o'.
scriptversion=2012-10-14.11; # UTC
scriptversion=2016-01-11.22; # UTC
# Copyright (C) 1999-2014 Free Software Foundation, Inc.
# Copyright (C) 1999-2017 Free Software Foundation, Inc.
# Written by Tom Tromey <tromey@cygnus.com>.
#
# This program is free software; you can redistribute it and/or modify
@ -255,7 +255,8 @@ EOF
echo "compile $scriptversion"
exit $?
;;
cl | *[/\\]cl | cl.exe | *[/\\]cl.exe )
cl | *[/\\]cl | cl.exe | *[/\\]cl.exe | \
icl | *[/\\]icl | icl.exe | *[/\\]icl.exe )
func_cl_wrapper "$@" # Doesn't return...
;;
esac
@ -342,6 +343,6 @@ exit $ret
# eval: (add-hook 'write-file-hooks 'time-stamp)
# time-stamp-start: "scriptversion="
# time-stamp-format: "%:y-%02m-%02d.%02H"
# time-stamp-time-zone: "UTC"
# time-stamp-time-zone: "UTC0"
# time-stamp-end: "; # UTC"
# End:

View file

@ -25,6 +25,7 @@
#cmakedefine SUPPORT_LIBZ 1
#cmakedefine SUPPORT_JIT 1
#cmakedefine SLJIT_PROT_EXECUTABLE_ALLOCATOR 1
#cmakedefine SUPPORT_PCRE2GREP_JIT 1
#cmakedefine SUPPORT_UNICODE 1
#cmakedefine SUPPORT_VALGRIND 1
@ -36,11 +37,13 @@
#cmakedefine NEVER_BACKSLASH_C 1
#define LINK_SIZE @PCRE2_LINK_SIZE@
#define HEAP_LIMIT @PCRE2_HEAP_LIMIT@
#define MATCH_LIMIT @PCRE2_MATCH_LIMIT@
#define MATCH_LIMIT_RECURSION @PCRE2_MATCH_LIMIT_RECURSION@
#define MATCH_LIMIT_DEPTH @PCRE2_MATCH_LIMIT_DEPTH@
#define NEWLINE_DEFAULT @NEWLINE_DEFAULT@
#define PARENS_NEST_LIMIT @PCRE2_PARENS_NEST_LIMIT@
#define PCRE2GREP_BUFSIZE @PCRE2GREP_BUFSIZE@
#define PCRE2GREP_MAX_BUFSIZE @PCRE2GREP_MAX_BUFSIZE@
#define MAX_NAME_SIZE 32
#define MAX_NAME_COUNT 10000

View file

@ -1,8 +1,8 @@
#! /bin/sh
# Attempt to guess a canonical system name.
# Copyright 1992-2014 Free Software Foundation, Inc.
# Copyright 1992-2017 Free Software Foundation, Inc.
timestamp='2014-11-04'
timestamp='2017-05-27'
# This file is free software; you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by
@ -27,7 +27,7 @@ timestamp='2014-11-04'
# Originally written by Per Bothner; maintained since 2000 by Ben Elliston.
#
# You can get the latest version of this script from:
# http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.guess;hb=HEAD
# http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.guess
#
# Please send patches to <config-patches@gnu.org>.
@ -50,7 +50,7 @@ version="\
GNU config.guess ($timestamp)
Originally written by Per Bothner.
Copyright 1992-2014 Free Software Foundation, Inc.
Copyright 1992-2017 Free Software Foundation, Inc.
This is free software; see the source for copying conditions. There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE."
@ -168,19 +168,29 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
# Note: NetBSD doesn't particularly care about the vendor
# portion of the name. We always set it to "unknown".
sysctl="sysctl -n hw.machine_arch"
UNAME_MACHINE_ARCH=`(/sbin/$sysctl 2>/dev/null || \
/usr/sbin/$sysctl 2>/dev/null || echo unknown)`
UNAME_MACHINE_ARCH=`(uname -p 2>/dev/null || \
/sbin/$sysctl 2>/dev/null || \
/usr/sbin/$sysctl 2>/dev/null || \
echo unknown)`
case "${UNAME_MACHINE_ARCH}" in
armeb) machine=armeb-unknown ;;
arm*) machine=arm-unknown ;;
sh3el) machine=shl-unknown ;;
sh3eb) machine=sh-unknown ;;
sh5el) machine=sh5le-unknown ;;
earmv*)
arch=`echo ${UNAME_MACHINE_ARCH} | sed -e 's,^e\(armv[0-9]\).*$,\1,'`
endian=`echo ${UNAME_MACHINE_ARCH} | sed -ne 's,^.*\(eb\)$,\1,p'`
machine=${arch}${endian}-unknown
;;
*) machine=${UNAME_MACHINE_ARCH}-unknown ;;
esac
# The Operating System including object format, if it has switched
# to ELF recently, or will in the future.
# to ELF recently (or will in the future) and ABI.
case "${UNAME_MACHINE_ARCH}" in
earm*)
os=netbsdelf
;;
arm*|i386|m68k|ns32k|sh3*|sparc|vax)
eval $set_cc_for_build
if echo __ELF__ | $CC_FOR_BUILD -E - 2>/dev/null \
@ -197,6 +207,13 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
os=netbsd
;;
esac
# Determine ABI tags.
case "${UNAME_MACHINE_ARCH}" in
earm*)
expr='s/^earmv[0-9]/-eabi/;s/eb$//'
abi=`echo ${UNAME_MACHINE_ARCH} | sed -e "$expr"`
;;
esac
# The OS release
# Debian GNU/NetBSD machines have a different userland, and
# thus, need a distinct triplet. However, they do not need
@ -207,13 +224,13 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
release='-gnu'
;;
*)
release=`echo ${UNAME_RELEASE}|sed -e 's/[-_].*/\./'`
release=`echo ${UNAME_RELEASE} | sed -e 's/[-_].*//' | cut -d. -f1,2`
;;
esac
# Since CPU_TYPE-MANUFACTURER-KERNEL-OPERATING_SYSTEM:
# contains redundant information, the shorter form:
# CPU_TYPE-MANUFACTURER-OPERATING_SYSTEM is used.
echo "${machine}-${os}${release}"
echo "${machine}-${os}${release}${abi}"
exit ;;
*:Bitrig:*:*)
UNAME_MACHINE_ARCH=`arch | sed 's/Bitrig.//'`
@ -223,6 +240,10 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
UNAME_MACHINE_ARCH=`arch | sed 's/OpenBSD.//'`
echo ${UNAME_MACHINE_ARCH}-unknown-openbsd${UNAME_RELEASE}
exit ;;
*:LibertyBSD:*:*)
UNAME_MACHINE_ARCH=`arch | sed 's/^.*BSD\.//'`
echo ${UNAME_MACHINE_ARCH}-unknown-libertybsd${UNAME_RELEASE}
exit ;;
*:ekkoBSD:*:*)
echo ${UNAME_MACHINE}-unknown-ekkobsd${UNAME_RELEASE}
exit ;;
@ -235,6 +256,9 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
*:MirBSD:*:*)
echo ${UNAME_MACHINE}-unknown-mirbsd${UNAME_RELEASE}
exit ;;
*:Sortix:*:*)
echo ${UNAME_MACHINE}-unknown-sortix
exit ;;
alpha:OSF1:*:*)
case $UNAME_RELEASE in
*4.0)
@ -251,42 +275,42 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
ALPHA_CPU_TYPE=`/usr/sbin/psrinfo -v | sed -n -e 's/^ The alpha \(.*\) processor.*$/\1/p' | head -n 1`
case "$ALPHA_CPU_TYPE" in
"EV4 (21064)")
UNAME_MACHINE="alpha" ;;
UNAME_MACHINE=alpha ;;
"EV4.5 (21064)")
UNAME_MACHINE="alpha" ;;
UNAME_MACHINE=alpha ;;
"LCA4 (21066/21068)")
UNAME_MACHINE="alpha" ;;
UNAME_MACHINE=alpha ;;
"EV5 (21164)")
UNAME_MACHINE="alphaev5" ;;
UNAME_MACHINE=alphaev5 ;;
"EV5.6 (21164A)")
UNAME_MACHINE="alphaev56" ;;
UNAME_MACHINE=alphaev56 ;;
"EV5.6 (21164PC)")
UNAME_MACHINE="alphapca56" ;;
UNAME_MACHINE=alphapca56 ;;
"EV5.7 (21164PC)")
UNAME_MACHINE="alphapca57" ;;
UNAME_MACHINE=alphapca57 ;;
"EV6 (21264)")
UNAME_MACHINE="alphaev6" ;;
UNAME_MACHINE=alphaev6 ;;
"EV6.7 (21264A)")
UNAME_MACHINE="alphaev67" ;;
UNAME_MACHINE=alphaev67 ;;
"EV6.8CB (21264C)")
UNAME_MACHINE="alphaev68" ;;
UNAME_MACHINE=alphaev68 ;;
"EV6.8AL (21264B)")
UNAME_MACHINE="alphaev68" ;;
UNAME_MACHINE=alphaev68 ;;
"EV6.8CX (21264D)")
UNAME_MACHINE="alphaev68" ;;
UNAME_MACHINE=alphaev68 ;;
"EV6.9A (21264/EV69A)")
UNAME_MACHINE="alphaev69" ;;
UNAME_MACHINE=alphaev69 ;;
"EV7 (21364)")
UNAME_MACHINE="alphaev7" ;;
UNAME_MACHINE=alphaev7 ;;
"EV7.9 (21364A)")
UNAME_MACHINE="alphaev79" ;;
UNAME_MACHINE=alphaev79 ;;
esac
# A Pn.n version is a patched version.
# A Vn.n version is a released version.
# A Tn.n version is a released field test version.
# A Xn.n version is an unreleased experimental baselevel.
# 1.2 uses "1.2" for uname -r.
echo ${UNAME_MACHINE}-dec-osf`echo ${UNAME_RELEASE} | sed -e 's/^[PVTX]//' | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz'`
echo ${UNAME_MACHINE}-dec-osf`echo ${UNAME_RELEASE} | sed -e 's/^[PVTX]//' | tr ABCDEFGHIJKLMNOPQRSTUVWXYZ abcdefghijklmnopqrstuvwxyz`
# Reset EXIT trap before exiting to avoid spurious non-zero exit code.
exitcode=$?
trap '' 0
@ -359,16 +383,16 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
exit ;;
i86pc:SunOS:5.*:* | i86xen:SunOS:5.*:*)
eval $set_cc_for_build
SUN_ARCH="i386"
SUN_ARCH=i386
# If there is a compiler, see if it is configured for 64-bit objects.
# Note that the Sun cc does not turn __LP64__ into 1 like gcc does.
# This test works for both compilers.
if [ "$CC_FOR_BUILD" != 'no_compiler_found' ]; then
if [ "$CC_FOR_BUILD" != no_compiler_found ]; then
if (echo '#ifdef __amd64'; echo IS_64BIT_ARCH; echo '#endif') | \
(CCOPTS= $CC_FOR_BUILD -E - 2>/dev/null) | \
(CCOPTS="" $CC_FOR_BUILD -E - 2>/dev/null) | \
grep IS_64BIT_ARCH >/dev/null
then
SUN_ARCH="x86_64"
SUN_ARCH=x86_64
fi
fi
echo ${SUN_ARCH}-pc-solaris2`echo ${UNAME_RELEASE}|sed -e 's/[^.]*//'`
@ -393,7 +417,7 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
exit ;;
sun*:*:4.2BSD:*)
UNAME_RELEASE=`(sed 1q /etc/motd | awk '{print substr($5,1,3)}') 2>/dev/null`
test "x${UNAME_RELEASE}" = "x" && UNAME_RELEASE=3
test "x${UNAME_RELEASE}" = x && UNAME_RELEASE=3
case "`/bin/arch`" in
sun3)
echo m68k-sun-sunos${UNAME_RELEASE}
@ -618,13 +642,13 @@ EOF
sc_cpu_version=`/usr/bin/getconf SC_CPU_VERSION 2>/dev/null`
sc_kernel_bits=`/usr/bin/getconf SC_KERNEL_BITS 2>/dev/null`
case "${sc_cpu_version}" in
523) HP_ARCH="hppa1.0" ;; # CPU_PA_RISC1_0
528) HP_ARCH="hppa1.1" ;; # CPU_PA_RISC1_1
523) HP_ARCH=hppa1.0 ;; # CPU_PA_RISC1_0
528) HP_ARCH=hppa1.1 ;; # CPU_PA_RISC1_1
532) # CPU_PA_RISC2_0
case "${sc_kernel_bits}" in
32) HP_ARCH="hppa2.0n" ;;
64) HP_ARCH="hppa2.0w" ;;
'') HP_ARCH="hppa2.0" ;; # HP-UX 10.20
32) HP_ARCH=hppa2.0n ;;
64) HP_ARCH=hppa2.0w ;;
'') HP_ARCH=hppa2.0 ;; # HP-UX 10.20
esac ;;
esac
fi
@ -663,11 +687,11 @@ EOF
exit (0);
}
EOF
(CCOPTS= $CC_FOR_BUILD -o $dummy $dummy.c 2>/dev/null) && HP_ARCH=`$dummy`
(CCOPTS="" $CC_FOR_BUILD -o $dummy $dummy.c 2>/dev/null) && HP_ARCH=`$dummy`
test -z "$HP_ARCH" && HP_ARCH=hppa
fi ;;
esac
if [ ${HP_ARCH} = "hppa2.0w" ]
if [ ${HP_ARCH} = hppa2.0w ]
then
eval $set_cc_for_build
@ -680,12 +704,12 @@ EOF
# $ CC_FOR_BUILD="cc +DA2.0w" ./config.guess
# => hppa64-hp-hpux11.23
if echo __LP64__ | (CCOPTS= $CC_FOR_BUILD -E - 2>/dev/null) |
if echo __LP64__ | (CCOPTS="" $CC_FOR_BUILD -E - 2>/dev/null) |
grep -q __LP64__
then
HP_ARCH="hppa2.0w"
HP_ARCH=hppa2.0w
else
HP_ARCH="hppa64"
HP_ARCH=hppa64
fi
fi
echo ${HP_ARCH}-hp-hpux${HPUX_REV}
@ -790,14 +814,14 @@ EOF
echo craynv-cray-unicosmp${UNAME_RELEASE} | sed -e 's/\.[^.]*$/.X/'
exit ;;
F30[01]:UNIX_System_V:*:* | F700:UNIX_System_V:*:*)
FUJITSU_PROC=`uname -m | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz'`
FUJITSU_SYS=`uname -p | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' | sed -e 's/\///'`
FUJITSU_PROC=`uname -m | tr ABCDEFGHIJKLMNOPQRSTUVWXYZ abcdefghijklmnopqrstuvwxyz`
FUJITSU_SYS=`uname -p | tr ABCDEFGHIJKLMNOPQRSTUVWXYZ abcdefghijklmnopqrstuvwxyz | sed -e 's/\///'`
FUJITSU_REL=`echo ${UNAME_RELEASE} | sed -e 's/ /_/'`
echo "${FUJITSU_PROC}-fujitsu-${FUJITSU_SYS}${FUJITSU_REL}"
exit ;;
5000:UNIX_System_V:4.*:*)
FUJITSU_SYS=`uname -p | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' | sed -e 's/\///'`
FUJITSU_REL=`echo ${UNAME_RELEASE} | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' | sed -e 's/ /_/'`
FUJITSU_SYS=`uname -p | tr ABCDEFGHIJKLMNOPQRSTUVWXYZ abcdefghijklmnopqrstuvwxyz | sed -e 's/\///'`
FUJITSU_REL=`echo ${UNAME_RELEASE} | tr ABCDEFGHIJKLMNOPQRSTUVWXYZ abcdefghijklmnopqrstuvwxyz | sed -e 's/ /_/'`
echo "sparc-fujitsu-${FUJITSU_SYS}${FUJITSU_REL}"
exit ;;
i*86:BSD/386:*:* | i*86:BSD/OS:*:* | *:Ascend\ Embedded/OS:*:*)
@ -813,10 +837,11 @@ EOF
UNAME_PROCESSOR=`/usr/bin/uname -p`
case ${UNAME_PROCESSOR} in
amd64)
echo x86_64-unknown-freebsd`echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'` ;;
*)
echo ${UNAME_PROCESSOR}-unknown-freebsd`echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'` ;;
UNAME_PROCESSOR=x86_64 ;;
i386)
UNAME_PROCESSOR=i586 ;;
esac
echo ${UNAME_PROCESSOR}-unknown-freebsd`echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'`
exit ;;
i*:CYGWIN*:*)
echo ${UNAME_MACHINE}-pc-cygwin
@ -879,7 +904,7 @@ EOF
exit ;;
*:GNU/*:*:*)
# other systems with GNU libc and userland
echo ${UNAME_MACHINE}-unknown-`echo ${UNAME_SYSTEM} | sed 's,^[^/]*/,,' | tr '[A-Z]' '[a-z]'``echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'`-${LIBC}
echo ${UNAME_MACHINE}-unknown-`echo ${UNAME_SYSTEM} | sed 's,^[^/]*/,,' | tr "[:upper:]" "[:lower:]"``echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'`-${LIBC}
exit ;;
i*86:Minix:*:*)
echo ${UNAME_MACHINE}-pc-minix
@ -902,7 +927,7 @@ EOF
EV68*) UNAME_MACHINE=alphaev68 ;;
esac
objdump --private-headers /bin/sh | grep -q ld.so.1
if test "$?" = 0 ; then LIBC="gnulibc1" ; fi
if test "$?" = 0 ; then LIBC=gnulibc1 ; fi
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
exit ;;
arc:Linux:*:* | arceb:Linux:*:*)
@ -933,6 +958,9 @@ EOF
crisv32:Linux:*:*)
echo ${UNAME_MACHINE}-axis-linux-${LIBC}
exit ;;
e2k:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
exit ;;
frv:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
exit ;;
@ -945,6 +973,9 @@ EOF
ia64:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
exit ;;
k1om:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
exit ;;
m32r*:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
exit ;;
@ -970,6 +1001,9 @@ EOF
eval `$CC_FOR_BUILD -E $dummy.c 2>/dev/null | grep '^CPU'`
test x"${CPU}" != x && { echo "${CPU}-unknown-linux-${LIBC}"; exit; }
;;
mips64el:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
exit ;;
openrisc*:Linux:*:*)
echo or1k-unknown-linux-${LIBC}
exit ;;
@ -1002,6 +1036,9 @@ EOF
ppcle:Linux:*:*)
echo powerpcle-unknown-linux-${LIBC}
exit ;;
riscv32:Linux:*:* | riscv64:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
exit ;;
s390:Linux:*:* | s390x:Linux:*:*)
echo ${UNAME_MACHINE}-ibm-linux-${LIBC}
exit ;;
@ -1021,7 +1058,7 @@ EOF
echo ${UNAME_MACHINE}-dec-linux-${LIBC}
exit ;;
x86_64:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
echo ${UNAME_MACHINE}-pc-linux-${LIBC}
exit ;;
xtensa*:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
@ -1100,7 +1137,7 @@ EOF
# uname -m prints for DJGPP always 'pc', but it prints nothing about
# the processor, so we play safe by assuming i586.
# Note: whatever this is, it MUST be the same as what config.sub
# prints for the "djgpp" host, or else GDB configury will decide that
# prints for the "djgpp" host, or else GDB configure will decide that
# this is a cross-build.
echo i586-pc-msdosdjgpp
exit ;;
@ -1249,6 +1286,9 @@ EOF
SX-8R:SUPER-UX:*:*)
echo sx8r-nec-superux${UNAME_RELEASE}
exit ;;
SX-ACE:SUPER-UX:*:*)
echo sxace-nec-superux${UNAME_RELEASE}
exit ;;
Power*:Rhapsody:*:*)
echo powerpc-apple-rhapsody${UNAME_RELEASE}
exit ;;
@ -1262,16 +1302,23 @@ EOF
UNAME_PROCESSOR=powerpc
fi
if test `echo "$UNAME_RELEASE" | sed -e 's/\..*//'` -le 10 ; then
if [ "$CC_FOR_BUILD" != 'no_compiler_found' ]; then
if [ "$CC_FOR_BUILD" != no_compiler_found ]; then
if (echo '#ifdef __LP64__'; echo IS_64BIT_ARCH; echo '#endif') | \
(CCOPTS= $CC_FOR_BUILD -E - 2>/dev/null) | \
grep IS_64BIT_ARCH >/dev/null
(CCOPTS="" $CC_FOR_BUILD -E - 2>/dev/null) | \
grep IS_64BIT_ARCH >/dev/null
then
case $UNAME_PROCESSOR in
i386) UNAME_PROCESSOR=x86_64 ;;
powerpc) UNAME_PROCESSOR=powerpc64 ;;
esac
fi
# On 10.4-10.6 one might compile for PowerPC via gcc -arch ppc
if (echo '#ifdef __POWERPC__'; echo IS_PPC; echo '#endif') | \
(CCOPTS="" $CC_FOR_BUILD -E - 2>/dev/null) | \
grep IS_PPC >/dev/null
then
UNAME_PROCESSOR=powerpc
fi
fi
elif test "$UNAME_PROCESSOR" = i386 ; then
# Avoid executing cc on OS X 10.9, as it ships with a stub
@ -1286,7 +1333,7 @@ EOF
exit ;;
*:procnto*:*:* | *:QNX:[0123456789]*:*)
UNAME_PROCESSOR=`uname -p`
if test "$UNAME_PROCESSOR" = "x86"; then
if test "$UNAME_PROCESSOR" = x86; then
UNAME_PROCESSOR=i386
UNAME_MACHINE=pc
fi
@ -1295,15 +1342,18 @@ EOF
*:QNX:*:4*)
echo i386-pc-qnx
exit ;;
NEO-?:NONSTOP_KERNEL:*:*)
NEO-*:NONSTOP_KERNEL:*:*)
echo neo-tandem-nsk${UNAME_RELEASE}
exit ;;
NSE-*:NONSTOP_KERNEL:*:*)
echo nse-tandem-nsk${UNAME_RELEASE}
exit ;;
NSR-?:NONSTOP_KERNEL:*:*)
NSR-*:NONSTOP_KERNEL:*:*)
echo nsr-tandem-nsk${UNAME_RELEASE}
exit ;;
NSX-*:NONSTOP_KERNEL:*:*)
echo nsx-tandem-nsk${UNAME_RELEASE}
exit ;;
*:NonStop-UX:*:*)
echo mips-compaq-nonstopux
exit ;;
@ -1317,7 +1367,7 @@ EOF
# "uname -m" is not consistent, so use $cputype instead. 386
# is converted to i386 for consistency with other x86
# operating systems.
if test "$cputype" = "386"; then
if test "$cputype" = 386; then
UNAME_MACHINE=i386
else
UNAME_MACHINE="$cputype"
@ -1359,7 +1409,7 @@ EOF
echo i386-pc-xenix
exit ;;
i*86:skyos:*:*)
echo ${UNAME_MACHINE}-pc-skyos`echo ${UNAME_RELEASE}` | sed -e 's/ .*$//'
echo ${UNAME_MACHINE}-pc-skyos`echo ${UNAME_RELEASE} | sed -e 's/ .*$//'`
exit ;;
i*86:rdos:*:*)
echo ${UNAME_MACHINE}-pc-rdos
@ -1370,23 +1420,25 @@ EOF
x86_64:VMkernel:*:*)
echo ${UNAME_MACHINE}-unknown-esx
exit ;;
amd64:Isilon\ OneFS:*:*)
echo x86_64-unknown-onefs
exit ;;
esac
cat >&2 <<EOF
$0: unable to guess system type
This script, last modified $timestamp, has failed to recognize
the operating system you are using. It is advised that you
download the most up to date version of the config scripts from
This script (version $timestamp), has failed to recognize the
operating system you are using. If your script is old, overwrite
config.guess and config.sub with the latest versions from:
http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.guess;hb=HEAD
http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.guess
and
http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.sub;hb=HEAD
http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.sub
If the version you run ($0) is already up to date, please
send the following data and any information you think might be
pertinent to <config-patches@gnu.org> in order to provide the needed
information to handle your system.
If $0 has already been updated, send the following data and any
information you think might be pertinent to config-patches@gnu.org to
provide the necessary information to handle your system.
config.guess timestamp = $timestamp

View file

@ -1,8 +1,8 @@
#! /bin/sh
# Configuration validation subroutine script.
# Copyright 1992-2014 Free Software Foundation, Inc.
# Copyright 1992-2017 Free Software Foundation, Inc.
timestamp='2014-12-03'
timestamp='2017-04-02'
# This file is free software; you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by
@ -33,7 +33,7 @@ timestamp='2014-12-03'
# Otherwise, we print the canonical config type on stdout and succeed.
# You can get the latest version of this script from:
# http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.sub;hb=HEAD
# http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.sub
# This file is supposed to be the same for all GNU packages
# and recognize all the CPU types, system types and aliases
@ -53,8 +53,7 @@ timestamp='2014-12-03'
me=`echo "$0" | sed -e 's,.*/,,'`
usage="\
Usage: $0 [OPTION] CPU-MFR-OPSYS
$0 [OPTION] ALIAS
Usage: $0 [OPTION] CPU-MFR-OPSYS or ALIAS
Canonicalize a configuration name.
@ -68,7 +67,7 @@ Report bugs and patches to <config-patches@gnu.org>."
version="\
GNU config.sub ($timestamp)
Copyright 1992-2014 Free Software Foundation, Inc.
Copyright 1992-2017 Free Software Foundation, Inc.
This is free software; see the source for copying conditions. There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE."
@ -117,8 +116,8 @@ maybe_os=`echo $1 | sed 's/^\(.*\)-\([^-]*-[^-]*\)$/\2/'`
case $maybe_os in
nto-qnx* | linux-gnu* | linux-android* | linux-dietlibc | linux-newlib* | \
linux-musl* | linux-uclibc* | uclinux-uclibc* | uclinux-gnu* | kfreebsd*-gnu* | \
knetbsd*-gnu* | netbsd*-gnu* | \
kopensolaris*-gnu* | \
knetbsd*-gnu* | netbsd*-gnu* | netbsd*-eabi* | \
kopensolaris*-gnu* | cloudabi*-eabi* | \
storm-chaos* | os2-emx* | rtmk-nova*)
os=-$maybe_os
basic_machine=`echo $1 | sed 's/^\(.*\)-\([^-]*-[^-]*\)$/\1/'`
@ -255,15 +254,16 @@ case $basic_machine in
| arc | arceb \
| arm | arm[bl]e | arme[lb] | armv[2-8] | armv[3-8][lb] | armv7[arm] \
| avr | avr32 \
| ba \
| be32 | be64 \
| bfin \
| c4x | c8051 | clipper \
| d10v | d30v | dlx | dsp16xx \
| epiphany \
| fido | fr30 | frv \
| e2k | epiphany \
| fido | fr30 | frv | ft32 \
| h8300 | h8500 | hppa | hppa1.[01] | hppa2.0 | hppa2.0[nw] | hppa64 \
| hexagon \
| i370 | i860 | i960 | ia64 \
| i370 | i860 | i960 | ia16 | ia64 \
| ip2k | iq2000 \
| k1om \
| le32 | le64 \
@ -301,11 +301,12 @@ case $basic_machine in
| open8 | or1k | or1knd | or32 \
| pdp10 | pdp11 | pj | pjl \
| powerpc | powerpc64 | powerpc64le | powerpcle \
| pru \
| pyramid \
| riscv32 | riscv64 \
| rl78 | rx \
| score \
| sh | sh[1234] | sh[24]a | sh[24]aeb | sh[23]e | sh[34]eb | sheb | shbe | shle | sh[1234]le | sh3ele \
| sh | sh[1234] | sh[24]a | sh[24]aeb | sh[23]e | sh[234]eb | sheb | shbe | shle | sh[1234]le | sh3ele \
| sh64 | sh64le \
| sparc | sparc64 | sparc64b | sparc64v | sparc86x | sparclet | sparclite \
| sparcv8 | sparcv9 | sparcv9b | sparcv9v \
@ -314,6 +315,7 @@ case $basic_machine in
| ubicom32 \
| v850 | v850e | v850e1 | v850e2 | v850es | v850e2v3 \
| visium \
| wasm32 \
| we32k \
| x86 | xc16x | xstormy16 | xtensa \
| z8k | z80)
@ -376,17 +378,18 @@ case $basic_machine in
| alphapca5[67]-* | alpha64pca5[67]-* | arc-* | arceb-* \
| arm-* | armbe-* | armle-* | armeb-* | armv*-* \
| avr-* | avr32-* \
| ba-* \
| be32-* | be64-* \
| bfin-* | bs2000-* \
| c[123]* | c30-* | [cjt]90-* | c4x-* \
| c8051-* | clipper-* | craynv-* | cydra-* \
| d10v-* | d30v-* | dlx-* \
| elxsi-* \
| e2k-* | elxsi-* \
| f30[01]-* | f700-* | fido-* | fr30-* | frv-* | fx80-* \
| h8300-* | h8500-* \
| hppa-* | hppa1.[01]-* | hppa2.0-* | hppa2.0[nw]-* | hppa64-* \
| hexagon-* \
| i*86-* | i860-* | i960-* | ia64-* \
| i*86-* | i860-* | i960-* | ia16-* | ia64-* \
| ip2k-* | iq2000-* \
| k1om-* \
| le32-* | le64-* \
@ -427,13 +430,15 @@ case $basic_machine in
| orion-* \
| pdp10-* | pdp11-* | pj-* | pjl-* | pn-* | power-* \
| powerpc-* | powerpc64-* | powerpc64le-* | powerpcle-* \
| pru-* \
| pyramid-* \
| riscv32-* | riscv64-* \
| rl78-* | romp-* | rs6000-* | rx-* \
| sh-* | sh[1234]-* | sh[24]a-* | sh[24]aeb-* | sh[23]e-* | sh[34]eb-* | sheb-* | shbe-* \
| shle-* | sh[1234]le-* | sh3ele-* | sh64-* | sh64le-* \
| sparc-* | sparc64-* | sparc64b-* | sparc64v-* | sparc86x-* | sparclet-* \
| sparclite-* \
| sparcv8-* | sparcv9-* | sparcv9b-* | sparcv9v-* | sv1-* | sx?-* \
| sparcv8-* | sparcv9-* | sparcv9b-* | sparcv9v-* | sv1-* | sx*-* \
| tahoe-* \
| tic30-* | tic4x-* | tic54x-* | tic55x-* | tic6x-* | tic80-* \
| tile*-* \
@ -442,6 +447,7 @@ case $basic_machine in
| v850-* | v850e-* | v850e1-* | v850es-* | v850e2-* | v850e2v3-* \
| vax-* \
| visium-* \
| wasm32-* \
| we32k-* \
| x86-* | x86_64-* | xc16x-* | xps100-* \
| xstormy16-* | xtensa*-* \
@ -518,6 +524,9 @@ case $basic_machine in
basic_machine=i386-pc
os=-aros
;;
asmjs)
basic_machine=asmjs-unknown
;;
aux)
basic_machine=m68k-apple
os=-aux
@ -638,6 +647,14 @@ case $basic_machine in
basic_machine=m68k-bull
os=-sysv3
;;
e500v[12])
basic_machine=powerpc-unknown
os=$os"spe"
;;
e500v[12]-*)
basic_machine=powerpc-`echo $basic_machine | sed 's/^[^-]*-//'`
os=$os"spe"
;;
ebmon29k)
basic_machine=a29k-amd
os=-ebmon
@ -933,6 +950,9 @@ case $basic_machine in
nsr-tandem)
basic_machine=nsr-tandem
;;
nsx-tandem)
basic_machine=nsx-tandem
;;
op50n-* | op60c-*)
basic_machine=hppa1.1-oki
os=-proelf
@ -1017,7 +1037,7 @@ case $basic_machine in
ppc-* | ppcbe-*)
basic_machine=powerpc-`echo $basic_machine | sed 's/^[^-]*-//'`
;;
ppcle | powerpclittle | ppc-le | powerpc-little)
ppcle | powerpclittle)
basic_machine=powerpcle-unknown
;;
ppcle-* | powerpclittle-*)
@ -1027,7 +1047,7 @@ case $basic_machine in
;;
ppc64-*) basic_machine=powerpc64-`echo $basic_machine | sed 's/^[^-]*-//'`
;;
ppc64le | powerpc64little | ppc64-le | powerpc64-little)
ppc64le | powerpc64little)
basic_machine=powerpc64le-unknown
;;
ppc64le-* | powerpc64little-*)
@ -1228,6 +1248,9 @@ case $basic_machine in
basic_machine=a29k-wrs
os=-vxworks
;;
wasm32)
basic_machine=wasm32-unknown
;;
w65*)
basic_machine=w65-wdc
os=-none
@ -1373,18 +1396,18 @@ case $os in
| -hpux* | -unos* | -osf* | -luna* | -dgux* | -auroraux* | -solaris* \
| -sym* | -kopensolaris* | -plan9* \
| -amigaos* | -amigados* | -msdos* | -newsos* | -unicos* | -aof* \
| -aos* | -aros* \
| -aos* | -aros* | -cloudabi* | -sortix* \
| -nindy* | -vxsim* | -vxworks* | -ebmon* | -hms* | -mvs* \
| -clix* | -riscos* | -uniplus* | -iris* | -rtu* | -xenix* \
| -hiux* | -386bsd* | -knetbsd* | -mirbsd* | -netbsd* \
| -bitrig* | -openbsd* | -solidbsd* \
| -bitrig* | -openbsd* | -solidbsd* | -libertybsd* \
| -ekkobsd* | -kfreebsd* | -freebsd* | -riscix* | -lynxos* \
| -bosx* | -nextstep* | -cxux* | -aout* | -elf* | -oabi* \
| -ptx* | -coff* | -ecoff* | -winnt* | -domain* | -vsta* \
| -udi* | -eabi* | -lites* | -ieee* | -go32* | -aux* \
| -chorusos* | -chorusrdb* | -cegcc* \
| -chorusos* | -chorusrdb* | -cegcc* | -glidix* \
| -cygwin* | -msys* | -pe* | -psos* | -moss* | -proelf* | -rtems* \
| -mingw32* | -mingw64* | -linux-gnu* | -linux-android* \
| -midipix* | -mingw32* | -mingw64* | -linux-gnu* | -linux-android* \
| -linux-newlib* | -linux-musl* | -linux-uclibc* \
| -uxpv* | -beos* | -mpeix* | -udk* | -moxiebox* \
| -interix* | -uwin* | -mks* | -rhapsody* | -darwin* | -opened* \
@ -1393,7 +1416,8 @@ case $os in
| -os2* | -vos* | -palmos* | -uclinux* | -nucleus* \
| -morphos* | -superux* | -rtmk* | -rtmk-nova* | -windiss* \
| -powermax* | -dnix* | -nx6 | -nx7 | -sei* | -dragonfly* \
| -skyos* | -haiku* | -rdos* | -toppers* | -drops* | -es* | -tirtos*)
| -skyos* | -haiku* | -rdos* | -toppers* | -drops* | -es* \
| -onefs* | -tirtos* | -phoenix* | -fuchsia* | -redox*)
# Remember, each alternative MUST END IN *, to match a version number.
;;
-qnx*)
@ -1525,6 +1549,8 @@ case $os in
;;
-nacl*)
;;
-ios)
;;
-none)
;;
*)
@ -1620,6 +1646,9 @@ case $basic_machine in
sparc-* | *-sun)
os=-sunos4.1.1
;;
pru-*)
os=-elf
;;
*-be)
os=-beos
;;

File diff suppressed because it is too large Load diff

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, [22])
m4_define(pcre2_minor, [32])
m4_define(pcre2_prerelease, [])
m4_define(pcre2_date, [2016-07-29])
m4_define(pcre2_date, [2018-09-10])
# 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, [4:0:4])
m4_define(libpcre2_16_version, [4:0:4])
m4_define(libpcre2_32_version, [4:0:4])
m4_define(libpcre2_posix_version, [1:0:0])
m4_define(libpcre2_8_version, [7:1:7])
m4_define(libpcre2_16_version, [7:1:7])
m4_define(libpcre2_32_version, [7:1:7])
m4_define(libpcre2_posix_version, [2:1:0])
AC_PREREQ(2.57)
AC_INIT(PCRE2, pcre2_major.pcre2_minor[]pcre2_prerelease, , pcre2)
@ -29,15 +29,6 @@ AM_INIT_AUTOMAKE([dist-bzip2 dist-zip])
m4_ifdef([AM_SILENT_RULES], [AM_SILENT_RULES([yes])])
AC_CONFIG_HEADERS(src/config.h)
# FISH PATCH
# 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])
# This was added at the suggestion of libtoolize (03-Jan-10)
AC_CONFIG_MACRO_DIR([m4])
@ -53,6 +44,7 @@ remember_set_CFLAGS="$CFLAGS"
AC_PROG_CC
AM_PROG_CC_C_O
AC_USE_SYSTEM_EXTENSIONS
if test "x$remember_set_CFLAGS" = "x"
then
@ -65,6 +57,9 @@ then
fi
fi
# This is a new thing required to stop a warning from automake 1.12
m4_ifdef([AM_PROG_AR], [AM_PROG_AR])
# Check for a 64-bit integer type
AC_TYPE_INT64_T
@ -148,22 +143,35 @@ AC_ARG_ENABLE(jit,
[enable Just-In-Time compiling support]),
, enable_jit=no)
# This code enables JIT if the hardware supports it.
if test "$enable_jit" = "auto"; then
AC_LANG(C)
AC_COMPILE_IFELSE([AC_LANG_SOURCE([[
#define SLJIT_CONFIG_AUTO 1
#include "src/sljit/sljitConfigInternal.h"
#if (defined SLJIT_CONFIG_UNSUPPORTED && SLJIT_CONFIG_UNSUPPORTED)
#error unsupported
#endif]])], enable_jit=yes, enable_jit=no)
echo checking for JIT support on this hardware... $enable_jit
fi
# Handle --enable-jit-sealloc (disabled by default)
AC_ARG_ENABLE(jit-sealloc,
AS_HELP_STRING([--enable-jit-sealloc],
[enable SELinux compatible execmem allocator in JIT]),
, enable_jit_sealloc=no)
# Handle --disable-pcre2grep-jit (enabled by default)
AC_ARG_ENABLE(pcre2grep-jit,
AS_HELP_STRING([--disable-pcre2grep-jit],
[disable JIT support in pcre2grep]),
, enable_pcre2grep_jit=yes)
# Handle --disable-pcre2grep-callout (enabled by default) but not supported
# for Windows.
if test "$HAVE_WINDOWS_H" != "1"; then
AC_ARG_ENABLE(pcre2grep-callout,
AS_HELP_STRING([--disable-pcre2grep-callout],
[disable callout script support in pcre2grep]),
, enable_pcre2grep_callout=yes)
else
enable_pcre2grep_callout=no
fi
# Handle --disable-pcre2grep-callout (enabled by default)
AC_ARG_ENABLE(pcre2grep-callout,
AS_HELP_STRING([--disable-pcre2grep-callout],
[disable callout script support in pcre2grep]),
, enable_pcre2grep_callout=yes)
# Handle --enable-rebuild-chartables
AC_ARG_ENABLE(rebuild-chartables,
@ -199,6 +207,10 @@ AC_ARG_ENABLE(newline-is-any,
AS_HELP_STRING([--enable-newline-is-any],
[use any valid Unicode newline sequence]),
ac_pcre2_newline=any)
AC_ARG_ENABLE(newline-is-nul,
AS_HELP_STRING([--enable-newline-is-nul],
[use NUL (binary zero) as newline character]),
ac_pcre2_newline=nul)
enable_newline="$ac_pcre2_newline"
# Handle --enable-bsr-anycrlf
@ -225,12 +237,6 @@ AC_ARG_ENABLE(ebcdic-nl25,
[set EBCDIC code for NL to 0x25 instead of 0x15; it implies --enable-ebcdic]),
, enable_ebcdic_nl25=no)
# Handle --disable-stack-for-recursion
AC_ARG_ENABLE(stack-for-recursion,
AS_HELP_STRING([--disable-stack-for-recursion],
[don't use stack recursion when matching]),
, enable_stack_for_recursion=yes)
# Handle --enable-pcre2grep-libz
AC_ARG_ENABLE(pcre2grep-libz,
AS_HELP_STRING([--enable-pcre2grep-libz],
@ -246,9 +252,15 @@ AC_ARG_ENABLE(pcre2grep-libbz2,
# Handle --with-pcre2grep-bufsize=N
AC_ARG_WITH(pcre2grep-bufsize,
AS_HELP_STRING([--with-pcre2grep-bufsize=N],
[pcre2grep buffer size (default=20480, minimum=8192)]),
[pcre2grep initial buffer size (default=20480, minimum=8192)]),
, with_pcre2grep_bufsize=20480)
# Handle --with-pcre2grep-max-bufsize=N
AC_ARG_WITH(pcre2grep-max-bufsize,
AS_HELP_STRING([--with-pcre2grep-max-bufsize=N],
[pcre2grep maximum buffer size (default=1048576, minimum=8192)]),
, with_pcre2grep_max_bufsize=1048576)
# Handle --enable-pcre2test-libedit
AC_ARG_ENABLE(pcre2test-libedit,
AS_HELP_STRING([--enable-pcre2test-libedit],
@ -273,29 +285,39 @@ AC_ARG_WITH(parens-nest-limit,
[nested parentheses limit (default=250)]),
, with_parens_nest_limit=250)
# Handle --with-heap-limit
AC_ARG_WITH(heap-limit,
AS_HELP_STRING([--with-heap-limit=N],
[default limit on heap memory (kibibytes, default=20000000)]),
, with_heap_limit=20000000)
# Handle --with-match-limit=N
AC_ARG_WITH(match-limit,
AS_HELP_STRING([--with-match-limit=N],
[default limit on internal looping (default=10000000)]),
, with_match_limit=10000000)
# Handle --with-match-limit_recursion=N
# Handle --with-match-limit-depth=N
# Recognize old synonym --with-match-limit-recursion
#
# Note: In config.h, the default is to define MATCH_LIMIT_RECURSION
# symbolically as MATCH_LIMIT, which in turn is defined to be some numeric
# value (e.g. 10000000). MATCH_LIMIT_RECURSION can otherwise be set to some
# different numeric value (or even the same numeric value as MATCH_LIMIT,
# though no longer defined in terms of the latter).
# Note: In config.h, the default is to define MATCH_LIMIT_DEPTH symbolically as
# MATCH_LIMIT, which in turn is defined to be some numeric value (e.g.
# 10000000). MATCH_LIMIT_DEPTH can otherwise be set to some different numeric
# value (or even the same numeric value as MATCH_LIMIT, though no longer
# defined in terms of the latter).
#
AC_ARG_WITH(match-limit-recursion,
AS_HELP_STRING([--with-match-limit-recursion=N],
[default limit on internal recursion (default=MATCH_LIMIT)]),
, with_match_limit_recursion=MATCH_LIMIT)
AC_ARG_WITH(match-limit-depth,
AS_HELP_STRING([--with-match-limit-depth=N],
[default limit on match tree depth (default=MATCH_LIMIT)]),
, with_match_limit_depth=MATCH_LIMIT)
AC_ARG_WITH(match-limit-recursion,,
, with_match_limit_recursion=UNSET)
# Handle --enable-valgrind
AC_ARG_ENABLE(valgrind,
AS_HELP_STRING([--enable-valgrind],
[valgrind support]),
[enable valgrind support]),
, enable_valgrind=no)
# Enable code coverage reports using gcov
@ -304,6 +326,23 @@ AC_ARG_ENABLE(coverage,
[enable code coverage reports using gcov]),
, enable_coverage=no)
# Handle --enable-fuzz-support
AC_ARG_ENABLE(fuzz_support,
AS_HELP_STRING([--enable-fuzz-support],
[enable fuzzer support]),
, enable_fuzz_support=no)
# Handle --disable-stack-for-recursion
# This option became obsolete at release 10.30.
AC_ARG_ENABLE(stack-for-recursion,,
, enable_stack_for_recursion=yes)
# Original code
# AC_ARG_ENABLE(stack-for-recursion,
# AS_HELP_STRING([--disable-stack-for-recursion],
# [don't use stack recursion when matching]),
# , enable_stack_for_recursion=yes)
# Set the default value for pcre2-8
if test "x$enable_pcre2_8" = "xunset"
then
@ -343,6 +382,7 @@ case "$enable_newline" in
crlf) ac_pcre2_newline_value=3 ;;
any) ac_pcre2_newline_value=4 ;;
anycrlf) ac_pcre2_newline_value=5 ;;
nul) ac_pcre2_newline_value=6 ;;
*)
AC_MSG_ERROR([invalid argument \"$enable_newline\" to --enable-newline option])
;;
@ -395,10 +435,10 @@ to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H,
but if you do, default values will be taken from config.h for non-boolean
macros that are not defined on the command line.
Boolean macros such as HAVE_STDLIB_H and SUPPORT_PCRE2_8 should either be defined
(conventionally to 1) for TRUE, and not defined at all for FALSE. All such
macros are listed as a commented #undef in config.h.generic. Macros such as
MATCH_LIMIT, whose actual value is relevant, have defaults defined, but are
Boolean macros such as HAVE_STDLIB_H and SUPPORT_PCRE2_8 should either be
defined (conventionally to 1) for TRUE, and not defined at all for FALSE. All
such macros are listed as a commented #undef in config.h.generic. Macros such
as MATCH_LIMIT, whose actual value is relevant, have defaults defined, but are
surrounded by #ifndef/#endif lines so that the value can be overridden by -D.
PCRE2 uses memmove() if HAVE_MEMMOVE is defined; otherwise it uses bcopy() if
@ -411,6 +451,11 @@ AC_CHECK_HEADERS(limits.h sys/types.h sys/stat.h dirent.h)
AC_CHECK_HEADERS([windows.h], [HAVE_WINDOWS_H=1])
AC_CHECK_HEADERS([sys/wait.h], [HAVE_SYS_WAIT_H=1])
AC_CHECK_HEADERS([stdint.h], [PCRE2_HAVE_STDINT_H=1], [PCRE2_HAVE_STDINT_H=0])
AC_CHECK_HEADERS([inttypes.h], [PCRE2_HAVE_INTTYPES_H=1], [PCRE2_HAVE_INTTYPES_H=0])
AC_SUBST([PCRE2_HAVE_STDINT_H])
AC_SUBST([PCRE2_HAVE_INTTYPES_H])
# Conditional compilation
AM_CONDITIONAL(WITH_PCRE2_8, test "x$enable_pcre2_8" = "xyes")
AM_CONDITIONAL(WITH_PCRE2_16, test "x$enable_pcre2_16" = "xyes")
@ -420,6 +465,12 @@ AM_CONDITIONAL(WITH_REBUILD_CHARTABLES, test "x$enable_rebuild_chartables" = "xy
AM_CONDITIONAL(WITH_JIT, test "x$enable_jit" = "xyes")
AM_CONDITIONAL(WITH_UNICODE, test "x$enable_unicode" = "xyes")
AM_CONDITIONAL(WITH_VALGRIND, test "x$enable_valgrind" = "xyes")
AM_CONDITIONAL(WITH_FUZZ_SUPPORT, test "x$enable_fuzz_support" = "xyes")
if test "$enable_fuzz_support" = "yes" -a "$enable_pcre2_8" = "no"; then
echo "** ERROR: Fuzzer support requires the 8-bit library"
exit 1
fi
# Checks for typedefs, structures, and compiler characteristics.
@ -428,7 +479,7 @@ AC_TYPE_SIZE_T
# Checks for library functions.
AC_CHECK_FUNCS(bcopy memmove strerror)
AC_CHECK_FUNCS(bcopy memmove strerror mkostemp secure_getenv)
# Check for the availability of libz (aka zlib)
@ -511,9 +562,6 @@ if test "$enable_pcre2test_libedit" = "yes"; then
AC_CHECK_LIB([edit], [readline], [LIBEDIT="-ledit"])
fi
# This facilitates -ansi builds under Linux
dnl AC_DEFINE([_GNU_SOURCE], [], [Enable GNU extensions in glibc])
PCRE2_STATIC_CFLAG=""
if test "x$enable_shared" = "xno" ; then
AC_DEFINE([PCRE2_STATIC], [1], [
@ -559,24 +607,27 @@ else
enable_pcre2grep_jit="no"
fi
if test "$enable_pcre2grep_jit" = "yes"; then
AC_DEFINE([SUPPORT_PCRE2GREP_JIT], [], [
Define to any value to enable JIT support in pcre2grep.])
if test "$enable_jit_sealloc" = "yes"; then
AC_DEFINE([SLJIT_PROT_EXECUTABLE_ALLOCATOR], [1], [
Define to any non-zero number to enable support for SELinux
compatible executable memory allocator in JIT. Note that this
will have no effect unless SUPPORT_JIT is also defined.])
fi
# Currently pcre2grep callout string is not supported under Windows.
if test "$enable_pcre2grep_jit" = "yes"; then
AC_DEFINE([SUPPORT_PCRE2GREP_JIT], [], [
Define to any value to enable JIT support in pcre2grep. Note that this will
have no effect unless SUPPORT_JIT is also defined.])
fi
if test "$enable_pcre2grep_callout" = "yes"; then
if test "$HAVE_WINDOWS_H" != "1"; then
if test "$HAVE_SYS_WAIT_H" != "1"; then
AC_MSG_ERROR([Callout script support needs sys/wait.h.])
fi
AC_DEFINE([SUPPORT_PCRE2GREP_CALLOUT], [], [
Define to any value to enable callout script support in pcre2grep.])
else
AC_MSG_WARN([Callout script support is not available for Windows: disabled])
enable_pcre2grep_callout=no
fi
AC_DEFINE([SUPPORT_PCRE2GREP_CALLOUT], [], [
Define to any value to enable callout script support in pcre2grep.])
fi
if test "$enable_unicode" = "yes"; then
@ -587,16 +638,6 @@ if test "$enable_unicode" = "yes"; then
code *or* ASCII/Unicode, but not both at once.])
fi
if test "$enable_stack_for_recursion" = "no"; then
AC_DEFINE([HEAP_MATCH_RECURSE], [], [
PCRE2 uses recursive function calls to handle backtracking while
matching. This can sometimes be a problem on systems that have
stacks of limited size. Define HEAP_MATCH_RECURSE to any value to get a
version that doesn't use recursion in the match() function; instead
it creates its own stack by steam using memory from the heap. For more
detail, see the comments and other stuff just above the match() function.])
fi
if test "$enable_pcre2grep_libz" = "yes"; then
AC_DEFINE([SUPPORT_LIBZ], [], [
Define to any value to allow pcre2grep to be linked with libz, so that it is
@ -614,15 +655,30 @@ if test $with_pcre2grep_bufsize -lt 8192 ; then
with_pcre2grep_bufsize="8192"
else
if test $? -gt 1 ; then
AC_MSG_ERROR([Bad value for --with-pcre2grep-bufsize])
AC_MSG_ERROR([Bad value for --with-pcre2grep-bufsize])
fi
fi
if test $with_pcre2grep_max_bufsize -lt $with_pcre2grep_bufsize ; then
with_pcre2grep_max_bufsize="$with_pcre2grep_bufsize"
else
if test $? -gt 1 ; then
AC_MSG_ERROR([Bad value for --with-pcre2grep-max-bufsize])
fi
fi
AC_DEFINE_UNQUOTED([PCRE2GREP_BUFSIZE], [$with_pcre2grep_bufsize], [
The value of PCRE2GREP_BUFSIZE determines the size of buffer used by pcre2grep
to hold parts of the file it is searching. This is also the minimum value.
The actual amount of memory used by pcre2grep is three times this number,
because it allows for the buffering of "before" and "after" lines.])
The value of PCRE2GREP_BUFSIZE is the starting size of the buffer used by
pcre2grep to hold parts of the file it is searching. The buffer will be
expanded up to PCRE2GREP_MAX_BUFSIZE if necessary, for files containing very
long lines. The actual amount of memory used by pcre2grep is three times this
number, because it allows for the buffering of "before" and "after" lines.])
AC_DEFINE_UNQUOTED([PCRE2GREP_MAX_BUFSIZE], [$with_pcre2grep_max_bufsize], [
The value of PCRE2GREP_MAX_BUFSIZE specifies the maximum size of the buffer
used by pcre2grep to hold parts of the file it is searching. The actual
amount of memory used by pcre2grep is three times this number, because it
allows for the buffering of "before" and "after" lines.])
if test "$enable_pcre2test_libedit" = "yes"; then
AC_DEFINE([SUPPORT_LIBEDIT], [], [
@ -637,7 +693,7 @@ AC_DEFINE_UNQUOTED([NEWLINE_DEFAULT], [$ac_pcre2_newline_value], [
The value of NEWLINE_DEFAULT determines the default newline character
sequence. PCRE2 client programs can override this by selecting other values
at run time. The valid values are 1 (CR), 2 (LF), 3 (CRLF), 4 (ANY),
and 5 (ANYCRLF).])
5 (ANYCRLF), and 6 (NUL).])
if test "$enable_bsr_anycrlf" = "yes"; then
AC_DEFINE([BSR_ANYCRLF], [], [
@ -655,8 +711,8 @@ fi
AC_DEFINE_UNQUOTED([LINK_SIZE], [$with_link_size], [
The value of LINK_SIZE determines the number of bytes used to store
links as offsets within the compiled regex. The default is 2, which
allows for compiled patterns up to 64K long. This covers the vast
majority of cases. However, PCRE2 can also be compiled to use 3 or 4
allows for compiled patterns up to 65535 code units long. This covers the
vast majority of cases. However, PCRE2 can also be compiled to use 3 or 4
bytes instead. This allows for longer patterns in extreme cases.])
AC_DEFINE_UNQUOTED([PARENS_NEST_LIMIT], [$with_parens_nest_limit], [
@ -666,23 +722,44 @@ AC_DEFINE_UNQUOTED([PARENS_NEST_LIMIT], [$with_parens_nest_limit], [
AC_DEFINE_UNQUOTED([MATCH_LIMIT], [$with_match_limit], [
The value of MATCH_LIMIT determines the default number of times the
internal match() function can be called during a single execution of
pcre2_match(). There is a runtime interface for setting a different
limit. The limit exists in order to catch runaway regular
expressions that take for ever to determine that they do not match.
The default is set very large so that it does not accidentally catch
legitimate cases.])
pcre2_match() function can record a backtrack position during a single
matching attempt. The value is also used to limit a loop counter in
pcre2_dfa_match(). There is a runtime interface for setting a different
limit. The limit exists in order to catch runaway regular expressions that
take for ever to determine that they do not match. The default is set very
large so that it does not accidentally catch legitimate cases.])
AC_DEFINE_UNQUOTED([MATCH_LIMIT_RECURSION], [$with_match_limit_recursion], [
The above limit applies to all calls of match(), whether or not they
increase the recursion depth. In some environments it is desirable
to limit the depth of recursive calls of match() more strictly, in
order to restrict the maximum amount of stack (or heap, if
HEAP_MATCH_RECURSE is defined) that is used. The value of
MATCH_LIMIT_RECURSION applies only to recursive calls of match(). To
have any useful effect, it must be less than the value of
MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT.
There is a runtime method for setting a different limit.])
# --with-match-limit-recursion is an obsolete synonym for --with-match-limit-depth
if test "$with_match_limit_recursion" != "UNSET"; then
cat <<EOF
WARNING: --with-match-limit-recursion is an obsolete option. Please use
--with-match-limit-depth in future. If both are set, --with-match-limit-depth
will be used. See also --with-heap-limit.
EOF
if test "$with_match_limit_depth" = "MATCH_LIMIT"; then
with_match_limit_depth=$with_match_limit_recursion
fi
fi
AC_DEFINE_UNQUOTED([MATCH_LIMIT_DEPTH], [$with_match_limit_depth], [
The above limit applies to all backtracks, whether or not they are nested. In
some environments it is desirable to limit the nesting of backtracking (that
is, the depth of tree that is searched) more strictly, in order to restrict
the maximum amount of heap memory that is used. The value of
MATCH_LIMIT_DEPTH provides this facility. To have any useful effect, it must
be less than the value of MATCH_LIMIT. The default is to use the same value
as MATCH_LIMIT. There is a runtime method for setting a different limit. In
the case of pcre2_dfa_match(), this limit controls the depth of the internal
nested function calls that are used for pattern recursions, lookarounds, and
atomic groups.])
AC_DEFINE_UNQUOTED([HEAP_LIMIT], [$with_heap_limit], [
This limits the amount of memory that may be used while matching
a pattern. It applies to both pcre2_match() and pcre2_dfa_match(). It does
not apply to JIT matching. The value is in kibibytes (units of 1024 bytes).])
AC_DEFINE([MAX_NAME_SIZE], [32], [
This limit is parameterized just in case anybody ever wants to
@ -762,7 +839,7 @@ AC_SUBST(EXTRA_LIBPCRE2_POSIX_LDFLAGS)
# When we run 'make distcheck', use these arguments. Turning off compiler
# optimization makes it run faster.
DISTCHECK_CONFIGURE_FLAGS="CFLAGS='' CXXFLAGS='' --enable-pcre2-16 --enable-pcre2-32 --enable-jit --enable-utf"
DISTCHECK_CONFIGURE_FLAGS="CFLAGS='' CXXFLAGS='' --enable-pcre2-16 --enable-pcre2-32 --enable-jit"
AC_SUBST(DISTCHECK_CONFIGURE_FLAGS)
# Check that, if --enable-pcre2grep-libz or --enable-pcre2grep-libbz2 is
@ -898,6 +975,15 @@ AC_CONFIG_COMMANDS([delete-old-chartables], [rm -f pcre2_chartables.c])
AC_OUTPUT
# --disable-stack-for-recursion is obsolete and has no effect.
if test "$enable_stack_for_recursion" = "no"; then
cat <<EOF
WARNING: --disable-stack-for-recursion is obsolete and has no effect.
EOF
fi
# Print out a nice little message after configure is run displaying the
# chosen options.
@ -912,43 +998,46 @@ cat <<EOF
$PACKAGE-$VERSION configuration summary:
Install prefix .................. : ${prefix}
C preprocessor .................. : ${CPP}
C compiler ...................... : ${CC}
Linker .......................... : ${LD}
C preprocessor flags ............ : ${CPPFLAGS}
C compiler flags ................ : ${CFLAGS} ${VISIBILITY_CFLAGS}
Linker flags .................... : ${LDFLAGS}
Extra libraries ................. : ${LIBS}
Install prefix ..................... : ${prefix}
C preprocessor ..................... : ${CPP}
C compiler ......................... : ${CC}
Linker ............................. : ${LD}
C preprocessor flags ............... : ${CPPFLAGS}
C compiler flags ................... : ${CFLAGS} ${VISIBILITY_CFLAGS}
Linker flags ....................... : ${LDFLAGS}
Extra libraries .................... : ${LIBS}
Build 8-bit pcre2 library ....... : ${enable_pcre2_8}
Build 16-bit pcre2 library ...... : ${enable_pcre2_16}
Build 32-bit pcre2 library ...... : ${enable_pcre2_32}
Include debugging code .......... : ${enable_debug}
Enable JIT compiling support .... : ${enable_jit}
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}
Use stack recursion ............. : ${enable_stack_for_recursion}
Internal link size .............. : ${with_link_size}
Nested parentheses limit ........ : ${with_parens_nest_limit}
Match limit ..................... : ${with_match_limit}
Match limit recursion ........... : ${with_match_limit_recursion}
Build shared libs ............... : ${enable_shared}
Build static libs ............... : ${enable_static}
Use JIT in pcre2grep ............ : ${enable_pcre2grep_jit}
Enable callouts in pcre2grep .... : ${enable_pcre2grep_callout}
Buffer size for pcre2grep ....... : ${with_pcre2grep_bufsize}
Link pcre2grep with libz ........ : ${enable_pcre2grep_libz}
Link pcre2grep with libbz2 ...... : ${enable_pcre2grep_libbz2}
Link pcre2test with libedit ..... : ${enable_pcre2test_libedit}
Link pcre2test with libreadline . : ${enable_pcre2test_libreadline}
Valgrind support ................ : ${enable_valgrind}
Code coverage ................... : ${enable_coverage}
Build 8-bit pcre2 library .......... : ${enable_pcre2_8}
Build 16-bit pcre2 library ......... : ${enable_pcre2_16}
Build 32-bit pcre2 library ......... : ${enable_pcre2_32}
Include debugging code ............. : ${enable_debug}
Enable JIT compiling support ....... : ${enable_jit}
Use SELinux allocator in JIT ....... : ${enable_jit_sealloc}
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}
Internal link size ................. : ${with_link_size}
Nested parentheses limit ........... : ${with_parens_nest_limit}
Heap limit ......................... : ${with_heap_limit} kibibytes
Match limit ........................ : ${with_match_limit}
Match depth limit .................. : ${with_match_limit_depth}
Build shared libs .................. : ${enable_shared}
Build static libs .................. : ${enable_static}
Use JIT in pcre2grep ............... : ${enable_pcre2grep_jit}
Enable callouts in pcre2grep ....... : ${enable_pcre2grep_callout}
Initial buffer size for pcre2grep .. : ${with_pcre2grep_bufsize}
Maximum buffer size for pcre2grep .. : ${with_pcre2grep_max_bufsize}
Link pcre2grep with libz ........... : ${enable_pcre2grep_libz}
Link pcre2grep with libbz2 ......... : ${enable_pcre2grep_libbz2}
Link pcre2test with libedit ........ : ${enable_pcre2test_libedit}
Link pcre2test with libreadline .... : ${enable_pcre2test_libreadline}
Valgrind support ................... : ${enable_valgrind}
Code coverage ...................... : ${enable_coverage}
Fuzzer support ..................... : ${enable_fuzz_support}
EOF

View file

@ -1,9 +1,9 @@
#! /bin/sh
# depcomp - compile a program generating dependencies as side-effects
scriptversion=2013-05-30.07; # UTC
scriptversion=2016-01-11.22; # UTC
# Copyright (C) 1999-2014 Free Software Foundation, Inc.
# Copyright (C) 1999-2017 Free Software Foundation, Inc.
# 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
@ -786,6 +786,6 @@ exit 0
# eval: (add-hook 'write-file-hooks 'time-stamp)
# time-stamp-start: "scriptversion="
# time-stamp-format: "%:y-%02m-%02d.%02H"
# time-stamp-time-zone: "UTC"
# time-stamp-time-zone: "UTC0"
# time-stamp-end: "; # UTC"
# End:

View file

@ -1,7 +1,7 @@
#!/bin/sh
# install - install a program, script, or datafile
scriptversion=2013-12-25.23; # UTC
scriptversion=2016-01-11.22; # UTC
# This originates from X11R5 (mit/util/scripts/install.sh), which was
# later released in X11R6 (xc/config/util/install.sh) with the
@ -496,6 +496,6 @@ done
# eval: (add-hook 'write-file-hooks 'time-stamp)
# time-stamp-start: "scriptversion="
# time-stamp-format: "%:y-%02m-%02d.%02H"
# time-stamp-time-zone: "UTC"
# time-stamp-time-zone: "UTC0"
# time-stamp-end: "; # UTC"
# End:

File diff suppressed because it is too large Load diff

View file

@ -1,6 +1,6 @@
# libtool.m4 - Configure libtool for the host system. -*-Autoconf-*-
#
# Copyright (C) 1996-2001, 2003-2015 Free Software Foundation, Inc.
# Copyright (C) 1996-2001, 2003-2017 Free Software Foundation, Inc.
# Written by Gordon Matzigkeit, 1996
#
# This file is free software; the Free Software Foundation gives
@ -1042,8 +1042,8 @@ int forced_loaded() { return 2;}
_LT_EOF
echo "$LTCC $LTCFLAGS -c -o conftest.o conftest.c" >&AS_MESSAGE_LOG_FD
$LTCC $LTCFLAGS -c -o conftest.o conftest.c 2>&AS_MESSAGE_LOG_FD
echo "$AR cru libconftest.a conftest.o" >&AS_MESSAGE_LOG_FD
$AR cru libconftest.a conftest.o 2>&AS_MESSAGE_LOG_FD
echo "$AR $AR_FLAGS libconftest.a conftest.o" >&AS_MESSAGE_LOG_FD
$AR $AR_FLAGS libconftest.a conftest.o 2>&AS_MESSAGE_LOG_FD
echo "$RANLIB libconftest.a" >&AS_MESSAGE_LOG_FD
$RANLIB libconftest.a 2>&AS_MESSAGE_LOG_FD
cat > conftest.c << _LT_EOF
@ -1493,9 +1493,22 @@ need_locks=$enable_libtool_lock
m4_defun([_LT_PROG_AR],
[AC_CHECK_TOOLS(AR, [ar], false)
: ${AR=ar}
: ${AR_FLAGS=cru}
_LT_DECL([], [AR], [1], [The archiver])
_LT_DECL([], [AR_FLAGS], [1], [Flags to create an archive])
# Use ARFLAGS variable as AR's operation code to sync the variable naming with
# Automake. If both AR_FLAGS and ARFLAGS are specified, AR_FLAGS should have
# higher priority because thats what people were doing historically (setting
# ARFLAGS for automake and AR_FLAGS for libtool). FIXME: Make the AR_FLAGS
# variable obsoleted/removed.
test ${AR_FLAGS+y} || AR_FLAGS=${ARFLAGS-cr}
lt_ar_flags=$AR_FLAGS
_LT_DECL([], [lt_ar_flags], [0], [Flags to create an archive (by configure)])
# Make AR_FLAGS overridable by 'make ARFLAGS='. Don't try to run-time override
# by AR_FLAGS because that was never working and AR_FLAGS is about to die.
_LT_DECL([], [AR_FLAGS], [\@S|@{ARFLAGS-"\@S|@lt_ar_flags"}],
[Flags to create an archive])
AC_CACHE_CHECK([for archiver @FILE support], [lt_cv_ar_at_file],
[lt_cv_ar_at_file=no
@ -2207,26 +2220,35 @@ m4_defun([_LT_CMD_STRIPLIB],
striplib=
old_striplib=
AC_MSG_CHECKING([whether stripping libraries is possible])
if test -n "$STRIP" && $STRIP -V 2>&1 | $GREP "GNU strip" >/dev/null; then
test -z "$old_striplib" && old_striplib="$STRIP --strip-debug"
test -z "$striplib" && striplib="$STRIP --strip-unneeded"
AC_MSG_RESULT([yes])
if test -z "$STRIP"; then
AC_MSG_RESULT([no])
else
# FIXME - insert some real tests, host_os isn't really good enough
case $host_os in
darwin*)
if test -n "$STRIP"; then
if $STRIP -V 2>&1 | $GREP "GNU strip" >/dev/null; then
old_striplib="$STRIP --strip-debug"
striplib="$STRIP --strip-unneeded"
AC_MSG_RESULT([yes])
else
case $host_os in
darwin*)
# FIXME - insert some real tests, host_os isn't really good enough
striplib="$STRIP -x"
old_striplib="$STRIP -S"
AC_MSG_RESULT([yes])
else
;;
freebsd*)
if $STRIP -V 2>&1 | $GREP "elftoolchain" >/dev/null; then
old_striplib="$STRIP --strip-debug"
striplib="$STRIP --strip-unneeded"
AC_MSG_RESULT([yes])
else
AC_MSG_RESULT([no])
fi
;;
*)
AC_MSG_RESULT([no])
fi
;;
*)
AC_MSG_RESULT([no])
;;
esac
;;
esac
fi
fi
_LT_DECL([], [old_striplib], [1], [Commands to strip libraries])
_LT_DECL([], [striplib], [1])
@ -4919,7 +4941,7 @@ m4_if([$1], [CXX], [
if $NM -V 2>&1 | $GREP 'GNU' > /dev/null; then
_LT_TAGVAR(export_symbols_cmds, $1)='$NM -Bpg $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "W")) && ([substr](\$ 3,1,1) != ".")) { if (\$ 2 == "W") { print \$ 3 " weak" } else { print \$ 3 } } }'\'' | sort -u > $export_symbols'
else
_LT_TAGVAR(export_symbols_cmds, $1)='`func_echo_all $NM | $SED -e '\''s/B\([[^B]]*\)$/P\1/'\''` -PCpgl $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) && ([substr](\$ 1,1,1) != ".")) { if ((\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) { print \$ 1 " weak" } else { print \$ 1 } } }'\'' | sort -u > $export_symbols'
_LT_TAGVAR(export_symbols_cmds, $1)='`func_echo_all $NM | $SED -e '\''s/B\([[^B]]*\)$/P\1/'\''` -PCpgl $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "L") || (\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) && ([substr](\$ 1,1,1) != ".")) { if ((\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) { print \$ 1 " weak" } else { print \$ 1 } } }'\'' | sort -u > $export_symbols'
fi
;;
pw32*)
@ -5156,6 +5178,7 @@ _LT_EOF
emximp -o $lib $output_objdir/$libname.def'
_LT_TAGVAR(old_archive_From_new_cmds, $1)='emximp -o $output_objdir/${libname}_dll.a $output_objdir/$libname.def'
_LT_TAGVAR(enable_shared_with_static_runtimes, $1)=yes
_LT_TAGVAR(file_list_spec, $1)='@'
;;
interix[[3-9]]*)
@ -5373,7 +5396,7 @@ _LT_EOF
if $NM -V 2>&1 | $GREP 'GNU' > /dev/null; then
_LT_TAGVAR(export_symbols_cmds, $1)='$NM -Bpg $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "W")) && ([substr](\$ 3,1,1) != ".")) { if (\$ 2 == "W") { print \$ 3 " weak" } else { print \$ 3 } } }'\'' | sort -u > $export_symbols'
else
_LT_TAGVAR(export_symbols_cmds, $1)='`func_echo_all $NM | $SED -e '\''s/B\([[^B]]*\)$/P\1/'\''` -PCpgl $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) && ([substr](\$ 1,1,1) != ".")) { if ((\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) { print \$ 1 " weak" } else { print \$ 1 } } }'\'' | sort -u > $export_symbols'
_LT_TAGVAR(export_symbols_cmds, $1)='`func_echo_all $NM | $SED -e '\''s/B\([[^B]]*\)$/P\1/'\''` -PCpgl $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "L") || (\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) && ([substr](\$ 1,1,1) != ".")) { if ((\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) { print \$ 1 " weak" } else { print \$ 1 } } }'\'' | sort -u > $export_symbols'
fi
aix_use_runtimelinking=no
@ -5861,6 +5884,7 @@ _LT_EOF
emximp -o $lib $output_objdir/$libname.def'
_LT_TAGVAR(old_archive_From_new_cmds, $1)='emximp -o $output_objdir/${libname}_dll.a $output_objdir/$libname.def'
_LT_TAGVAR(enable_shared_with_static_runtimes, $1)=yes
_LT_TAGVAR(file_list_spec, $1)='@'
;;
osf3*)
@ -6730,6 +6754,7 @@ if test yes != "$_lt_caught_CXX_error"; then
emximp -o $lib $output_objdir/$libname.def'
_LT_TAGVAR(old_archive_From_new_cmds, $1)='emximp -o $output_objdir/${libname}_dll.a $output_objdir/$libname.def'
_LT_TAGVAR(enable_shared_with_static_runtimes, $1)=yes
_LT_TAGVAR(file_list_spec, $1)='@'
;;
dgux*)

View file

@ -1,6 +1,6 @@
# Helper functions for option handling. -*- Autoconf -*-
#
# Copyright (C) 2004-2005, 2007-2009, 2011-2015 Free Software
# Copyright (C) 2004-2005, 2007-2009, 2011-2017 Free Software
# Foundation, Inc.
# Written by Gary V. Vaughan, 2004
#

View file

@ -1,6 +1,6 @@
# ltsugar.m4 -- libtool m4 base layer. -*-Autoconf-*-
#
# Copyright (C) 2004-2005, 2007-2008, 2011-2015 Free Software
# Copyright (C) 2004-2005, 2007-2008, 2011-2017 Free Software
# Foundation, Inc.
# Written by Gary V. Vaughan, 2004
#

View file

@ -1,6 +1,6 @@
# ltversion.m4 -- version numbers -*- Autoconf -*-
#
# Copyright (C) 2004, 2011-2015 Free Software Foundation, Inc.
# Copyright (C) 2004, 2011-2017 Free Software Foundation, Inc.
# Written by Scott James Remnant, 2004
#
# This file is free software; the Free Software Foundation gives
@ -9,15 +9,15 @@
# @configure_input@
# serial 4179 ltversion.m4
# serial 4219 ltversion.m4
# This file is part of GNU Libtool
m4_define([LT_PACKAGE_VERSION], [2.4.6])
m4_define([LT_PACKAGE_REVISION], [2.4.6])
m4_define([LT_PACKAGE_VERSION], [2.4.6.40-6ca5-dirty])
m4_define([LT_PACKAGE_REVISION], [2.4.6.40])
AC_DEFUN([LTVERSION_VERSION],
[macro_version='2.4.6'
macro_revision='2.4.6'
[macro_version='2.4.6.40-6ca5-dirty'
macro_revision='2.4.6.40'
_LT_DECL(, macro_version, 0, [Which release of libtool.m4 was used?])
_LT_DECL(, macro_revision, 0)
])

View file

@ -1,6 +1,6 @@
# lt~obsolete.m4 -- aclocal satisfying obsolete definitions. -*-Autoconf-*-
#
# Copyright (C) 2004-2005, 2007, 2009, 2011-2015 Free Software
# Copyright (C) 2004-2005, 2007, 2009, 2011-2017 Free Software
# Foundation, Inc.
# Written by Scott James Remnant, 2004.
#

View file

@ -1,9 +1,9 @@
#! /bin/sh
# Common wrapper for a few potentially missing GNU programs.
scriptversion=2013-10-28.13; # UTC
scriptversion=2016-01-11.22; # UTC
# Copyright (C) 1996-2014 Free Software Foundation, Inc.
# Copyright (C) 1996-2017 Free Software Foundation, Inc.
# Originally written by Fran,cois Pinard <pinard@iro.umontreal.ca>, 1996.
# This program is free software; you can redistribute it and/or modify
@ -210,6 +210,6 @@ exit $st
# eval: (add-hook 'write-file-hooks 'time-stamp)
# time-stamp-start: "scriptversion="
# time-stamp-format: "%:y-%02m-%02d.%02H"
# time-stamp-time-zone: "UTC"
# time-stamp-time-zone: "UTC0"
# time-stamp-end: "; # UTC"
# End:

View file

@ -86,7 +86,7 @@ while test $# -gt 0; do
;;
--libs-posix)
if test @enable_pcre2_8@ = yes ; then
echo $libS$libR -lpcre2posix -lpcre2-8
echo $libS$libR -lpcre2-posix -lpcre2-8
else
echo "${usage}" 1>&2
fi

View file

@ -1,14 +1,17 @@
#! /bin/sh
# Script for testing regular expressions with perl to check that PCRE2 handles
# them the same. The Perl code has to have "use utf8" and "require Encode" at
# the start when running UTF-8 tests, but *not* for non-utf8 tests. (The
# "require" would actually be OK for non-utf8-tests, but is not always
# installed, so this way the script will always run for these tests.)
# them the same. If the first argument to this script is "-w", Perl is also
# called with "-w", which turns on its warning mode.
#
# The Perl code has to have "use utf8" and "require Encode" at the start when
# running UTF-8 tests, but *not* for non-utf8 tests. (The "require" would
# actually be OK for non-utf8-tests, but is not always installed, so this way
# the script will always run for these tests.)
#
# The desired effect is achieved by making this a shell script that passes the
# Perl script to Perl through a pipe. If the first argument is "-utf8", a
# suitable prefix is set up.
# Perl script to Perl through a pipe. If the first argument (possibly after
# removing "-w") is "-utf8", a suitable prefix is set up.
#
# The remaining arguments, if any, are passed to Perl. They are an input file
# and an output file. If there is one argument, the output is written to
@ -17,7 +20,14 @@
# of the contorted piping input.)
perl=perl
perlarg=''
prefix=''
if [ $# -gt 0 -a "$1" = "-w" ] ; then
perlarg="-w"
shift
fi
if [ $# -gt 0 -a "$1" = "-utf8" ] ; then
prefix="use utf8; require Encode;"
shift
@ -32,13 +42,26 @@ fi
# aftertext interpreted as "print $' afterwards"
# afteralltext ignored
# dupnames ignored (Perl always allows)
# mark ignored
# jitstack ignored
# mark show mark information
# no_auto_possess ignored
# no_start_optimize ignored
# no_start_optimize insert (??{""}) at pattern start (disables optimizing)
# -no_start_optimize ignored
# subject_literal does not process subjects for escapes
# ucp sets Perl's /u modifier
# utf invoke UTF-8 functionality
#
# The data lines must not have any pcre2test modifiers. They are processed as
# Comment lines are ignored. The #pattern command can be used to set modifiers
# that will be added to each subsequent pattern, after any modifiers it may
# already have. NOTE: this is different to pcre2test where #pattern sets
# defaults which can be overridden on individual patterns. The #subject command
# may be used to set or unset a default "mark" modifier for data lines. This is
# the only use of #subject that is supported. The #perltest, #forbid_utf, and
# #newline_default commands, which are needed in the relevant pcre2test files,
# are ignored. Any other #-command is ignored, with a warning message.
#
# The data lines must not have any pcre2test modifiers. Unless
# "subject_literal" is on the pattern, data lines are processed as
# Perl double-quoted strings, so if they contain " $ or @ characters, these
# have to be escaped. For this reason, all such characters in the
# Perl-compatible testinput1 and testinput4 files are escaped so that they can
@ -114,7 +137,42 @@ for (;;)
printf " re> " if $interact;
last if ! ($_ = <$infile>);
printf $outfile "$_" if ! $interact;
next if ($_ =~ /^\s*$/ || $_ =~ /^#/);
next if ($_ =~ /^\s*$/ || $_ =~ /^#[\s!]/);
# A few of pcre2test's #-commands are supported, or just ignored. Any others
# cause an error.
if ($_ =~ /^#pattern(.*)/)
{
$extra_modifiers = $1;
chomp($extra_modifiers);
$extra_modifiers =~ s/\s+$//;
next;
}
elsif ($_ =~ /^#subject(.*)/)
{
$mod = $1;
chomp($mod);
$mod =~ s/\s+$//;
if ($mod =~ s/(-?)mark,?//)
{
$minus = $1;
$default_show_mark = ($minus =~ /^$/);
}
if ($mod !~ /^\s*$/)
{
printf $outfile "** Warning: \"$mod\" in #subject ignored\n";
}
next;
}
elsif ($_ =~ /^#/)
{
if ($_ !~ /^#newline_default|^#perltest|^#forbid_utf/)
{
printf $outfile "** Warning: #-command ignored: %s", $_;
}
next;
}
$pattern = $_;
@ -133,12 +191,18 @@ for (;;)
$pattern =~ /^\s*((.).*\2)(.*)$/s;
$pat = $1;
$mod = $3;
$del = $2;
$mod = "$3,$extra_modifiers";
$mod =~ s/^,\s*//;
# The private "aftertext" modifier means "print $' afterwards".
$showrest = ($mod =~ s/aftertext,?//);
# The "subject_literal" modifer disables escapes in subjects.
$subject_literal = ($mod =~ s/subject_literal,?//);
# "allaftertext" is used by pcre2test to print remainders after captures
$mod =~ s/allaftertext,?//;
@ -151,18 +215,28 @@ for (;;)
$mod =~ s/dupnames,?//;
# Remove "mark" (asks pcre2test to check MARK data) */
# Remove "jitstack".
$mod =~ s/mark,?//;
$mod =~ s/jitstack=\d+,?//;
# The "mark" modifier requests checking of MARK data */
$show_mark = $default_show_mark | ($mod =~ s/mark,?//);
# "ucp" asks pcre2test to set PCRE2_UCP; change this to /u for Perl
$mod =~ s/ucp,?/u/;
# Remove "no_auto_possess" and "no_start_optimize" (disable PCRE2 optimizations)
# Remove "no_auto_possess".
$mod =~ s/no_auto_possess,?//;
$mod =~ s/no_start_optimize,?//;
# Use no_start_optimize (disable PCRE2 start-up optimization) to disable Perl
# optimization by inserting (??{""}) at the start of the pattern. We may
# also encounter -no_start_optimize from a #pattern setting.
$mod =~ s/-no_start_optimize,?//;
if ($mod =~ s/no_start_optimize,?//) { $pat =~ s/$del/$del(??{""})/; }
# Add back retained modifiers and check that the pattern is valid.
@ -212,7 +286,14 @@ for (;;)
last if ($_ eq "");
next if $_ =~ /^\\=(?:\s|$)/; # Comment line
$x = eval "\"$_\""; # To get escapes processed
if ($subject_literal)
{
$x = $_;
}
else
{
$x = eval "\"$_\""; # To get escapes processed
}
# Empty array for holding results, ensure $REGERROR and $REGMARK are
# unset, then do the matching.
@ -251,7 +332,7 @@ for (;;)
elsif (scalar(@subs) == 0)
{
printf $outfile "No match";
if (defined $REGERROR && $REGERROR != 1)
if ($show_mark && defined $REGERROR && $REGERROR != 1)
{ printf $outfile (", mark = %s", &pchars($REGERROR)); }
printf $outfile "\n";
}
@ -279,7 +360,7 @@ for (;;)
# set and the input pattern was a UTF-8 string. We can, however, force
# it to be so marked.
if (defined $REGMARK && $REGMARK != 1)
if ($show_mark && defined $REGMARK && $REGMARK != 1)
{
$xx = $REGMARK;
$xx = Encode::decode_utf8($xx) if $utf8;
@ -292,6 +373,6 @@ for (;;)
# printf $outfile "\n";
PERLEND
) | $perl - $@
) | $perl $perlarg - $@
# End

View file

@ -18,10 +18,10 @@ to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H,
but if you do, default values will be taken from config.h for non-boolean
macros that are not defined on the command line.
Boolean macros such as HAVE_STDLIB_H and SUPPORT_PCRE2_8 should either be defined
(conventionally to 1) for TRUE, and not defined at all for FALSE. All such
macros are listed as a commented #undef in config.h.generic. Macros such as
MATCH_LIMIT, whose actual value is relevant, have defaults defined, but are
Boolean macros such as HAVE_STDLIB_H and SUPPORT_PCRE2_8 should either be
defined (conventionally to 1) for TRUE, and not defined at all for FALSE. All
such macros are listed as a commented #undef in config.h.generic. Macros such
as MATCH_LIMIT, whose actual value is relevant, have defaults defined, but are
surrounded by #ifndef/#endif lines so that the value can be overridden by -D.
PCRE2 uses memmove() if HAVE_MEMMOVE is defined; otherwise it uses bcopy() if
@ -78,6 +78,9 @@ sure both macros are undefined; an emulation function will then be used. */
/* Define to 1 if you have the <memory.h> header file. */
/* #undef HAVE_MEMORY_H */
/* Define to 1 if you have the `mkostemp' function. */
/* #undef HAVE_MKOSTEMP */
/* Define if you have POSIX threads libraries and header files. */
/* #undef HAVE_PTHREAD */
@ -90,6 +93,9 @@ sure both macros are undefined; an emulation function will then be used. */
/* Define to 1 if you have the <readline/readline.h> header file. */
/* #undef HAVE_READLINE_READLINE_H */
/* Define to 1 if you have the `secure_getenv' function. */
/* #undef HAVE_SECURE_GETENV */
/* Define to 1 if you have the <stdint.h> header file. */
/* #undef HAVE_STDINT_H */
@ -126,19 +132,18 @@ sure both macros are undefined; an emulation function will then be used. */
/* Define to 1 if you have the <zlib.h> header file. */
/* #undef HAVE_ZLIB_H */
/* PCRE2 uses recursive function calls to handle backtracking while matching.
This can sometimes be a problem on systems that have stacks of limited
size. Define HEAP_MATCH_RECURSE to any value to get a version that doesn't
use recursion in the match() function; instead it creates its own stack by
steam using memory from the heap. For more detail, see the comments and
other stuff just above the match() function. */
/* #undef HEAP_MATCH_RECURSE */
/* This limits the amount of memory that may be used while matching a pattern.
It applies to both pcre2_match() and pcre2_dfa_match(). It does not apply
to JIT matching. The value is in kibibytes (units of 1024 bytes). */
#ifndef HEAP_LIMIT
#define HEAP_LIMIT 20000000
#endif
/* The value of LINK_SIZE determines the number of bytes used to store links
as offsets within the compiled regex. The default is 2, which allows for
compiled patterns up to 64K long. This covers the vast majority of cases.
However, PCRE2 can also be compiled to use 3 or 4 bytes instead. This
allows for longer patterns in extreme cases. */
compiled patterns up to 65535 code units long. This covers the vast
majority of cases. However, PCRE2 can also be compiled to use 3 or 4 bytes
instead. This allows for longer patterns in extreme cases. */
#ifndef LINK_SIZE
#define LINK_SIZE 2
#endif
@ -150,25 +155,28 @@ sure both macros are undefined; an emulation function will then be used. */
#endif
/* The value of MATCH_LIMIT determines the default number of times the
internal match() function can be called during a single execution of
pcre2_match(). There is a runtime interface for setting a different limit.
The limit exists in order to catch runaway regular expressions that take
for ever to determine that they do not match. The default is set very large
so that it does not accidentally catch legitimate cases. */
pcre2_match() function can record a backtrack position during a single
matching attempt. The value is also used to limit a loop counter in
pcre2_dfa_match(). There is a runtime interface for setting a different
limit. The limit exists in order to catch runaway regular expressions that
take for ever to determine that they do not match. The default is set very
large so that it does not accidentally catch legitimate cases. */
#ifndef MATCH_LIMIT
#define MATCH_LIMIT 10000000
#endif
/* The above limit applies to all calls of match(), whether or not they
increase the recursion depth. In some environments it is desirable to limit
the depth of recursive calls of match() more strictly, in order to restrict
the maximum amount of stack (or heap, if HEAP_MATCH_RECURSE is defined)
that is used. The value of MATCH_LIMIT_RECURSION applies only to recursive
calls of match(). To have any useful effect, it must be less than the value
of MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT. There
is a runtime method for setting a different limit. */
#ifndef MATCH_LIMIT_RECURSION
#define MATCH_LIMIT_RECURSION MATCH_LIMIT
/* The above limit applies to all backtracks, whether or not they are nested.
In some environments it is desirable to limit the nesting of backtracking
(that is, the depth of tree that is searched) more strictly, in order to
restrict the maximum amount of heap memory that is used. The value of
MATCH_LIMIT_DEPTH provides this facility. To have any useful effect, it
must be less than the value of MATCH_LIMIT. The default is to use the same
value as MATCH_LIMIT. There is a runtime method for setting a different
limit. In the case of pcre2_dfa_match(), this limit controls the depth of
the internal nested function calls that are used for pattern recursions,
lookarounds, and atomic groups. */
#ifndef MATCH_LIMIT_DEPTH
#define MATCH_LIMIT_DEPTH MATCH_LIMIT
#endif
/* This limit is parameterized just in case anybody ever wants to change it.
@ -190,8 +198,8 @@ sure both macros are undefined; an emulation function will then be used. */
/* The value of NEWLINE_DEFAULT determines the default newline character
sequence. PCRE2 client programs can override this by selecting other values
at run time. The valid values are 1 (CR), 2 (LF), 3 (CRLF), 4 (ANY), and 5
(ANYCRLF). */
at run time. The valid values are 1 (CR), 2 (LF), 3 (CRLF), 4 (ANY), 5
(ANYCRLF), and 6 (NUL). */
#ifndef NEWLINE_DEFAULT
#define NEWLINE_DEFAULT 2
#endif
@ -206,7 +214,7 @@ 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 10.22"
#define PACKAGE_STRING "PCRE2 10.32"
/* Define to the one symbol short name of this package. */
#define PACKAGE_TARNAME "pcre2"
@ -215,7 +223,7 @@ 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 "10.22"
#define PACKAGE_VERSION "10.32"
/* 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
@ -224,15 +232,24 @@ sure both macros are undefined; an emulation function will then be used. */
#define PARENS_NEST_LIMIT 250
#endif
/* The value of PCRE2GREP_BUFSIZE determines the size of buffer used by
pcre2grep to hold parts of the file it is searching. This is also the
minimum value. The actual amount of memory used by pcre2grep is three times
this number, because it allows for the buffering of "before" and "after"
lines. */
/* The value of PCRE2GREP_BUFSIZE is the starting size of the buffer used by
pcre2grep to hold parts of the file it is searching. The buffer will be
expanded up to PCRE2GREP_MAX_BUFSIZE if necessary, for files containing
very long lines. The actual amount of memory used by pcre2grep is three
times this number, because it allows for the buffering of "before" and
"after" lines. */
#ifndef PCRE2GREP_BUFSIZE
#define PCRE2GREP_BUFSIZE 20480
#endif
/* The value of PCRE2GREP_MAX_BUFSIZE specifies the maximum size of the buffer
used by pcre2grep to hold parts of the file it is searching. The actual
amount of memory used by pcre2grep is three times this number, because it
allows for the buffering of "before" and "after" lines. */
#ifndef PCRE2GREP_MAX_BUFSIZE
#define PCRE2GREP_MAX_BUFSIZE 1048576
#endif
/* Define to any value to include debugging code. */
/* #undef PCRE2_DEBUG */
@ -254,6 +271,11 @@ sure both macros are undefined; an emulation function will then be used. */
your system. */
/* #undef PTHREAD_CREATE_JOINABLE */
/* Define to any non-zero number to enable support for SELinux compatible
executable memory allocator in JIT. Note that this will have no effect
unless SUPPORT_JIT is also defined. */
/* #undef SLJIT_PROT_EXECUTABLE_ALLOCATOR */
/* Define to 1 if you have the ANSI C header files. */
/* #undef STDC_HEADERS */
@ -277,7 +299,8 @@ sure both macros are undefined; an emulation function will then be used. */
/* Define to any value to enable callout script support in pcre2grep. */
/* #undef SUPPORT_PCRE2GREP_CALLOUT */
/* Define to any value to enable JIT support in pcre2grep. */
/* Define to any value to enable JIT support in pcre2grep. Note that this will
have no effect unless SUPPORT_JIT is also defined. */
/* #undef SUPPORT_PCRE2GREP_JIT */
/* Define to any value to enable the 16 bit PCRE2 library. */
@ -298,8 +321,39 @@ sure both macros are undefined; an emulation function will then be used. */
/* Define to any value for valgrind support to find invalid memory reads. */
/* #undef SUPPORT_VALGRIND */
/* Enable extensions on AIX 3, Interix. */
#ifndef _ALL_SOURCE
# define _ALL_SOURCE 1
#endif
/* Enable GNU extensions on systems that have them. */
#ifndef _GNU_SOURCE
# define _GNU_SOURCE 1
#endif
/* Enable threading extensions on Solaris. */
#ifndef _POSIX_PTHREAD_SEMANTICS
# define _POSIX_PTHREAD_SEMANTICS 1
#endif
/* Enable extensions on HP NonStop. */
#ifndef _TANDEM_SOURCE
# define _TANDEM_SOURCE 1
#endif
/* Enable general extensions on Solaris. */
#ifndef __EXTENSIONS__
# define __EXTENSIONS__ 1
#endif
/* Version number of package */
#define VERSION "10.22"
#define VERSION "10.32"
/* Define to 1 if on MINIX. */
/* #undef _MINIX */
/* Define to 2 if the system does not provide POSIX.1 features except with
this defined. */
/* #undef _POSIX_1_SOURCE */
/* Define to 1 if you need to in order for `stat' and other things to work. */
/* #undef _POSIX_SOURCE */
/* Define to empty if `const' does not conform to ANSI C. */
/* #undef const */

View file

@ -18,10 +18,10 @@ to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H,
but if you do, default values will be taken from config.h for non-boolean
macros that are not defined on the command line.
Boolean macros such as HAVE_STDLIB_H and SUPPORT_PCRE2_8 should either be defined
(conventionally to 1) for TRUE, and not defined at all for FALSE. All such
macros are listed as a commented #undef in config.h.generic. Macros such as
MATCH_LIMIT, whose actual value is relevant, have defaults defined, but are
Boolean macros such as HAVE_STDLIB_H and SUPPORT_PCRE2_8 should either be
defined (conventionally to 1) for TRUE, and not defined at all for FALSE. All
such macros are listed as a commented #undef in config.h.generic. Macros such
as MATCH_LIMIT, whose actual value is relevant, have defaults defined, but are
surrounded by #ifndef/#endif lines so that the value can be overridden by -D.
PCRE2 uses memmove() if HAVE_MEMMOVE is defined; otherwise it uses bcopy() if
@ -78,6 +78,9 @@ sure both macros are undefined; an emulation function will then be used. */
/* Define to 1 if you have the <memory.h> header file. */
#undef HAVE_MEMORY_H
/* Define to 1 if you have the `mkostemp' function. */
#undef HAVE_MKOSTEMP
/* Define if you have POSIX threads libraries and header files. */
#undef HAVE_PTHREAD
@ -90,6 +93,9 @@ sure both macros are undefined; an emulation function will then be used. */
/* Define to 1 if you have the <readline/readline.h> header file. */
#undef HAVE_READLINE_READLINE_H
/* Define to 1 if you have the `secure_getenv' function. */
#undef HAVE_SECURE_GETENV
/* Define to 1 if you have the <stdint.h> header file. */
#undef HAVE_STDINT_H
@ -126,41 +132,41 @@ sure both macros are undefined; an emulation function will then be used. */
/* Define to 1 if you have the <zlib.h> header file. */
#undef HAVE_ZLIB_H
/* PCRE2 uses recursive function calls to handle backtracking while matching.
This can sometimes be a problem on systems that have stacks of limited
size. Define HEAP_MATCH_RECURSE to any value to get a version that doesn't
use recursion in the match() function; instead it creates its own stack by
steam using memory from the heap. For more detail, see the comments and
other stuff just above the match() function. */
#undef HEAP_MATCH_RECURSE
/* This limits the amount of memory that may be used while matching a pattern.
It applies to both pcre2_match() and pcre2_dfa_match(). It does not apply
to JIT matching. The value is in kibibytes (units of 1024 bytes). */
#undef HEAP_LIMIT
/* The value of LINK_SIZE determines the number of bytes used to store links
as offsets within the compiled regex. The default is 2, which allows for
compiled patterns up to 64K long. This covers the vast majority of cases.
However, PCRE2 can also be compiled to use 3 or 4 bytes instead. This
allows for longer patterns in extreme cases. */
compiled patterns up to 65535 code units long. This covers the vast
majority of cases. However, PCRE2 can also be compiled to use 3 or 4 bytes
instead. This allows for longer patterns in extreme cases. */
#undef LINK_SIZE
/* Define to the sub-directory where libtool stores uninstalled libraries. */
#undef LT_OBJDIR
/* The value of MATCH_LIMIT determines the default number of times the
internal match() function can be called during a single execution of
pcre2_match(). There is a runtime interface for setting a different limit.
The limit exists in order to catch runaway regular expressions that take
for ever to determine that they do not match. The default is set very large
so that it does not accidentally catch legitimate cases. */
pcre2_match() function can record a backtrack position during a single
matching attempt. The value is also used to limit a loop counter in
pcre2_dfa_match(). There is a runtime interface for setting a different
limit. The limit exists in order to catch runaway regular expressions that
take for ever to determine that they do not match. The default is set very
large so that it does not accidentally catch legitimate cases. */
#undef MATCH_LIMIT
/* The above limit applies to all calls of match(), whether or not they
increase the recursion depth. In some environments it is desirable to limit
the depth of recursive calls of match() more strictly, in order to restrict
the maximum amount of stack (or heap, if HEAP_MATCH_RECURSE is defined)
that is used. The value of MATCH_LIMIT_RECURSION applies only to recursive
calls of match(). To have any useful effect, it must be less than the value
of MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT. There
is a runtime method for setting a different limit. */
#undef MATCH_LIMIT_RECURSION
/* The above limit applies to all backtracks, whether or not they are nested.
In some environments it is desirable to limit the nesting of backtracking
(that is, the depth of tree that is searched) more strictly, in order to
restrict the maximum amount of heap memory that is used. The value of
MATCH_LIMIT_DEPTH provides this facility. To have any useful effect, it
must be less than the value of MATCH_LIMIT. The default is to use the same
value as MATCH_LIMIT. There is a runtime method for setting a different
limit. In the case of pcre2_dfa_match(), this limit controls the depth of
the internal nested function calls that are used for pattern recursions,
lookarounds, and atomic groups. */
#undef MATCH_LIMIT_DEPTH
/* This limit is parameterized just in case anybody ever wants to change it.
Care must be taken if it is increased, because it guards against integer
@ -177,8 +183,8 @@ sure both macros are undefined; an emulation function will then be used. */
/* The value of NEWLINE_DEFAULT determines the default newline character
sequence. PCRE2 client programs can override this by selecting other values
at run time. The valid values are 1 (CR), 2 (LF), 3 (CRLF), 4 (ANY), and 5
(ANYCRLF). */
at run time. The valid values are 1 (CR), 2 (LF), 3 (CRLF), 4 (ANY), 5
(ANYCRLF), and 6 (NUL). */
#undef NEWLINE_DEFAULT
/* Name of package */
@ -207,13 +213,20 @@ sure both macros are undefined; an emulation function will then be used. */
stack that is used while compiling a pattern. */
#undef PARENS_NEST_LIMIT
/* The value of PCRE2GREP_BUFSIZE determines the size of buffer used by
pcre2grep to hold parts of the file it is searching. This is also the
minimum value. The actual amount of memory used by pcre2grep is three times
this number, because it allows for the buffering of "before" and "after"
lines. */
/* The value of PCRE2GREP_BUFSIZE is the starting size of the buffer used by
pcre2grep to hold parts of the file it is searching. The buffer will be
expanded up to PCRE2GREP_MAX_BUFSIZE if necessary, for files containing
very long lines. The actual amount of memory used by pcre2grep is three
times this number, because it allows for the buffering of "before" and
"after" lines. */
#undef PCRE2GREP_BUFSIZE
/* The value of PCRE2GREP_MAX_BUFSIZE specifies the maximum size of the buffer
used by pcre2grep to hold parts of the file it is searching. The actual
amount of memory used by pcre2grep is three times this number, because it
allows for the buffering of "before" and "after" lines. */
#undef PCRE2GREP_MAX_BUFSIZE
/* to make a symbol visible */
#undef PCRE2POSIX_EXP_DECL
@ -245,6 +258,11 @@ sure both macros are undefined; an emulation function will then be used. */
your system. */
#undef PTHREAD_CREATE_JOINABLE
/* Define to any non-zero number to enable support for SELinux compatible
executable memory allocator in JIT. Note that this will have no effect
unless SUPPORT_JIT is also defined. */
#undef SLJIT_PROT_EXECUTABLE_ALLOCATOR
/* Define to 1 if you have the ANSI C header files. */
#undef STDC_HEADERS
@ -268,7 +286,8 @@ sure both macros are undefined; an emulation function will then be used. */
/* Define to any value to enable callout script support in pcre2grep. */
#undef SUPPORT_PCRE2GREP_CALLOUT
/* Define to any value to enable JIT support in pcre2grep. */
/* Define to any value to enable JIT support in pcre2grep. Note that this will
have no effect unless SUPPORT_JIT is also defined. */
#undef SUPPORT_PCRE2GREP_JIT
/* Define to any value to enable the 16 bit PCRE2 library. */
@ -289,9 +308,41 @@ sure both macros are undefined; an emulation function will then be used. */
/* Define to any value for valgrind support to find invalid memory reads. */
#undef SUPPORT_VALGRIND
/* Enable extensions on AIX 3, Interix. */
#ifndef _ALL_SOURCE
# undef _ALL_SOURCE
#endif
/* Enable GNU extensions on systems that have them. */
#ifndef _GNU_SOURCE
# undef _GNU_SOURCE
#endif
/* Enable threading extensions on Solaris. */
#ifndef _POSIX_PTHREAD_SEMANTICS
# undef _POSIX_PTHREAD_SEMANTICS
#endif
/* Enable extensions on HP NonStop. */
#ifndef _TANDEM_SOURCE
# undef _TANDEM_SOURCE
#endif
/* Enable general extensions on Solaris. */
#ifndef __EXTENSIONS__
# undef __EXTENSIONS__
#endif
/* Version number of package */
#undef VERSION
/* Define to 1 if on MINIX. */
#undef _MINIX
/* Define to 2 if the system does not provide POSIX.1 features except with
this defined. */
#undef _POSIX_1_SOURCE
/* Define to 1 if you need to in order for `stat' and other things to work. */
#undef _POSIX_SOURCE
/* Define to empty if `const' does not conform to ANSI C. */
#undef const

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) 2016 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -104,6 +104,14 @@ fprintf(f,
"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");
fprintf(f,
"/*The dftables program (which is distributed with PCRE2) can be used to\n"
"build alternative versions of this file. This is necessary if you are\n"
"running in an EBCDIC environment, or if you want to default to a different\n"
"encoding, for example ISO-8859-1. When dftables is run, it creates these\n"
"tables in the current locale. This happens automatically if PCRE2 is\n"
"configured with --enable-rebuild-chartables. */\n\n");
/* Force config.h in z/OS */
#if defined NATIVE_ZOS
@ -115,7 +123,7 @@ fprintf(f,
#endif
fprintf(f,
"/* The following #includes are present because without them gcc 4.x may remove\n"
"/* The following #include is present because without it 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"
@ -153,11 +161,10 @@ for (i = 0; i < 256; i++)
fprintf(f, ",\n\n");
fprintf(f,
"/* This table contains bit maps for various character classes.\n"
"Each map is 32 bytes long and the bits run from the least\n"
"significant end of each byte. The classes that have their own\n"
"maps are: space, xdigit, digit, upper, lower, word, graph\n"
"print, punct, and cntrl. Other classes are built from combinations. */\n\n");
"/* This table contains bit maps for various character classes. Each map is 32\n"
"bytes long and the bits run from the least significant end of each byte. The\n"
"classes that have their own maps are: space, xdigit, digit, upper, lower, word,\n"
"graph print, punct, and cntrl. Other classes are built from combinations. */\n\n");
fprintf(f, " ");
for (i = 0; i < cbit_length; i++)
@ -178,10 +185,8 @@ fprintf(f,
" 0x%02x letter\n"
" 0x%02x decimal digit\n"
" 0x%02x hexadecimal digit\n"
" 0x%02x alphanumeric or '_'\n"
" 0x%02x regular expression metacharacter or binary zero\n*/\n\n",
ctype_space, ctype_letter, ctype_digit, ctype_xdigit, ctype_word,
ctype_meta);
" 0x%02x alphanumeric or '_'\n*/\n\n",
ctype_space, ctype_letter, ctype_digit, ctype_xdigit, ctype_word);
fprintf(f, " ");
for (i = 0; i < 256; i++)

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) 2016 University of Cambridge
Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -36,15 +36,21 @@ POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifndef _PCRE2_H
#define _PCRE2_H
#ifndef PCRE2_H_IDEMPOTENT_GUARD
#define PCRE2_H_IDEMPOTENT_GUARD
/* The current PCRE version information. */
#define PCRE2_MAJOR 10
#define PCRE2_MINOR 22
#define PCRE2_PRERELEASE
#define PCRE2_DATE 2016-07-29
#define PCRE2_MAJOR 10
#define PCRE2_MINOR 32
#define PCRE2_PRERELEASE
#define PCRE2_DATE 2018-09-10
/* For the benefit of systems without stdint.h, an alternative is to use
inttypes.h. The existence of these headers is checked by configure or CMake. */
#define PCRE2_HAVE_STDINT_H 1
#define PCRE2_HAVE_INTTYPES_H 1
/* 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
@ -67,12 +73,32 @@ don't change existing definitions of PCRE2_EXP_DECL. */
# endif
#endif
/* Have to include limits.h, stdlib.h and stdint.h to ensure that size_t and
uint8_t, UCHAR_MAX, etc are defined. */
/* When compiling with the MSVC compiler, it is sometimes necessary to include
a "calling convention" before exported function names. (This is secondhand
information; I know nothing about MSVC myself). For example, something like
void __cdecl function(....)
might be needed. In order so make this easy, all the exported functions have
PCRE2_CALL_CONVENTION just before their names. It is rarely needed; if not
set, we ensure here that it has no effect. */
#ifndef PCRE2_CALL_CONVENTION
#define PCRE2_CALL_CONVENTION
#endif
/* Have to include limits.h, stdlib.h and stdint.h (or inttypes.h) to ensure
that size_t and uint8_t, UCHAR_MAX, etc are defined. If the system has neither
header, the relevant values must be provided by some other means. */
#include <limits.h>
#include <stdlib.h>
#if PCRE2_HAVE_STDINT_H
#include <stdint.h>
#elif PCRE2_HAVE_INTTYPES_H
#include <inttypes.h>
#endif
/* Allow for C++ users compiling this directly. */
@ -87,6 +113,7 @@ others can be added next to them */
#define PCRE2_ANCHORED 0x80000000u
#define PCRE2_NO_UTF_CHECK 0x40000000u
#define PCRE2_ENDANCHORED 0x20000000u
/* The following option bits can be passed only to pcre2_compile(). However,
they may affect compilation, JIT compilation, and/or interpretive execution.
@ -122,6 +149,15 @@ D is inspected during pcre2_dfa_match() execution
#define PCRE2_ALT_CIRCUMFLEX 0x00200000u /* J M D */
#define PCRE2_ALT_VERBNAMES 0x00400000u /* C */
#define PCRE2_USE_OFFSET_LIMIT 0x00800000u /* J M D */
#define PCRE2_EXTENDED_MORE 0x01000000u /* C */
#define PCRE2_LITERAL 0x02000000u /* C */
/* An additional compile options word is available in the compile context. */
#define PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES 0x00000001u /* C */
#define PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL 0x00000002u /* C */
#define PCRE2_EXTRA_MATCH_WORD 0x00000004u /* C */
#define PCRE2_EXTRA_MATCH_LINE 0x00000008u /* C */
/* These are for pcre2_jit_compile(). */
@ -160,6 +196,16 @@ ignored for pcre2_jit_match(). */
#define PCRE2_NO_JIT 0x00002000u
/* Options for pcre2_pattern_convert(). */
#define PCRE2_CONVERT_UTF 0x00000001u
#define PCRE2_CONVERT_NO_UTF_CHECK 0x00000002u
#define PCRE2_CONVERT_POSIX_BASIC 0x00000004u
#define PCRE2_CONVERT_POSIX_EXTENDED 0x00000008u
#define PCRE2_CONVERT_GLOB 0x00000010u
#define PCRE2_CONVERT_GLOB_NO_WILD_SEPARATOR 0x00000030u
#define PCRE2_CONVERT_GLOB_NO_STARSTAR 0x00000050u
/* 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
greater than zero. */
@ -169,11 +215,112 @@ greater than zero. */
#define PCRE2_NEWLINE_CRLF 3
#define PCRE2_NEWLINE_ANY 4
#define PCRE2_NEWLINE_ANYCRLF 5
#define PCRE2_NEWLINE_NUL 6
#define PCRE2_BSR_UNICODE 1
#define PCRE2_BSR_ANYCRLF 2
/* Error codes: no match and partial match are "expected" errors. */
/* Error codes for pcre2_compile(). Some of these are also used by
pcre2_pattern_convert(). */
#define PCRE2_ERROR_END_BACKSLASH 101
#define PCRE2_ERROR_END_BACKSLASH_C 102
#define PCRE2_ERROR_UNKNOWN_ESCAPE 103
#define PCRE2_ERROR_QUANTIFIER_OUT_OF_ORDER 104
#define PCRE2_ERROR_QUANTIFIER_TOO_BIG 105
#define PCRE2_ERROR_MISSING_SQUARE_BRACKET 106
#define PCRE2_ERROR_ESCAPE_INVALID_IN_CLASS 107
#define PCRE2_ERROR_CLASS_RANGE_ORDER 108
#define PCRE2_ERROR_QUANTIFIER_INVALID 109
#define PCRE2_ERROR_INTERNAL_UNEXPECTED_REPEAT 110
#define PCRE2_ERROR_INVALID_AFTER_PARENS_QUERY 111
#define PCRE2_ERROR_POSIX_CLASS_NOT_IN_CLASS 112
#define PCRE2_ERROR_POSIX_NO_SUPPORT_COLLATING 113
#define PCRE2_ERROR_MISSING_CLOSING_PARENTHESIS 114
#define PCRE2_ERROR_BAD_SUBPATTERN_REFERENCE 115
#define PCRE2_ERROR_NULL_PATTERN 116
#define PCRE2_ERROR_BAD_OPTIONS 117
#define PCRE2_ERROR_MISSING_COMMENT_CLOSING 118
#define PCRE2_ERROR_PARENTHESES_NEST_TOO_DEEP 119
#define PCRE2_ERROR_PATTERN_TOO_LARGE 120
#define PCRE2_ERROR_HEAP_FAILED 121
#define PCRE2_ERROR_UNMATCHED_CLOSING_PARENTHESIS 122
#define PCRE2_ERROR_INTERNAL_CODE_OVERFLOW 123
#define PCRE2_ERROR_MISSING_CONDITION_CLOSING 124
#define PCRE2_ERROR_LOOKBEHIND_NOT_FIXED_LENGTH 125
#define PCRE2_ERROR_ZERO_RELATIVE_REFERENCE 126
#define PCRE2_ERROR_TOO_MANY_CONDITION_BRANCHES 127
#define PCRE2_ERROR_CONDITION_ASSERTION_EXPECTED 128
#define PCRE2_ERROR_BAD_RELATIVE_REFERENCE 129
#define PCRE2_ERROR_UNKNOWN_POSIX_CLASS 130
#define PCRE2_ERROR_INTERNAL_STUDY_ERROR 131
#define PCRE2_ERROR_UNICODE_NOT_SUPPORTED 132
#define PCRE2_ERROR_PARENTHESES_STACK_CHECK 133
#define PCRE2_ERROR_CODE_POINT_TOO_BIG 134
#define PCRE2_ERROR_LOOKBEHIND_TOO_COMPLICATED 135
#define PCRE2_ERROR_LOOKBEHIND_INVALID_BACKSLASH_C 136
#define PCRE2_ERROR_UNSUPPORTED_ESCAPE_SEQUENCE 137
#define PCRE2_ERROR_CALLOUT_NUMBER_TOO_BIG 138
#define PCRE2_ERROR_MISSING_CALLOUT_CLOSING 139
#define PCRE2_ERROR_ESCAPE_INVALID_IN_VERB 140
#define PCRE2_ERROR_UNRECOGNIZED_AFTER_QUERY_P 141
#define PCRE2_ERROR_MISSING_NAME_TERMINATOR 142
#define PCRE2_ERROR_DUPLICATE_SUBPATTERN_NAME 143
#define PCRE2_ERROR_INVALID_SUBPATTERN_NAME 144
#define PCRE2_ERROR_UNICODE_PROPERTIES_UNAVAILABLE 145
#define PCRE2_ERROR_MALFORMED_UNICODE_PROPERTY 146
#define PCRE2_ERROR_UNKNOWN_UNICODE_PROPERTY 147
#define PCRE2_ERROR_SUBPATTERN_NAME_TOO_LONG 148
#define PCRE2_ERROR_TOO_MANY_NAMED_SUBPATTERNS 149
#define PCRE2_ERROR_CLASS_INVALID_RANGE 150
#define PCRE2_ERROR_OCTAL_BYTE_TOO_BIG 151
#define PCRE2_ERROR_INTERNAL_OVERRAN_WORKSPACE 152
#define PCRE2_ERROR_INTERNAL_MISSING_SUBPATTERN 153
#define PCRE2_ERROR_DEFINE_TOO_MANY_BRANCHES 154
#define PCRE2_ERROR_BACKSLASH_O_MISSING_BRACE 155
#define PCRE2_ERROR_INTERNAL_UNKNOWN_NEWLINE 156
#define PCRE2_ERROR_BACKSLASH_G_SYNTAX 157
#define PCRE2_ERROR_PARENS_QUERY_R_MISSING_CLOSING 158
/* Error 159 is obsolete and should now never occur */
#define PCRE2_ERROR_VERB_ARGUMENT_NOT_ALLOWED 159
#define PCRE2_ERROR_VERB_UNKNOWN 160
#define PCRE2_ERROR_SUBPATTERN_NUMBER_TOO_BIG 161
#define PCRE2_ERROR_SUBPATTERN_NAME_EXPECTED 162
#define PCRE2_ERROR_INTERNAL_PARSED_OVERFLOW 163
#define PCRE2_ERROR_INVALID_OCTAL 164
#define PCRE2_ERROR_SUBPATTERN_NAMES_MISMATCH 165
#define PCRE2_ERROR_MARK_MISSING_ARGUMENT 166
#define PCRE2_ERROR_INVALID_HEXADECIMAL 167
#define PCRE2_ERROR_BACKSLASH_C_SYNTAX 168
#define PCRE2_ERROR_BACKSLASH_K_SYNTAX 169
#define PCRE2_ERROR_INTERNAL_BAD_CODE_LOOKBEHINDS 170
#define PCRE2_ERROR_BACKSLASH_N_IN_CLASS 171
#define PCRE2_ERROR_CALLOUT_STRING_TOO_LONG 172
#define PCRE2_ERROR_UNICODE_DISALLOWED_CODE_POINT 173
#define PCRE2_ERROR_UTF_IS_DISABLED 174
#define PCRE2_ERROR_UCP_IS_DISABLED 175
#define PCRE2_ERROR_VERB_NAME_TOO_LONG 176
#define PCRE2_ERROR_BACKSLASH_U_CODE_POINT_TOO_BIG 177
#define PCRE2_ERROR_MISSING_OCTAL_OR_HEX_DIGITS 178
#define PCRE2_ERROR_VERSION_CONDITION_SYNTAX 179
#define PCRE2_ERROR_INTERNAL_BAD_CODE_AUTO_POSSESS 180
#define PCRE2_ERROR_CALLOUT_NO_STRING_DELIMITER 181
#define PCRE2_ERROR_CALLOUT_BAD_STRING_DELIMITER 182
#define PCRE2_ERROR_BACKSLASH_C_CALLER_DISABLED 183
#define PCRE2_ERROR_QUERY_BARJX_NEST_TOO_DEEP 184
#define PCRE2_ERROR_BACKSLASH_C_LIBRARY_DISABLED 185
#define PCRE2_ERROR_PATTERN_TOO_COMPLICATED 186
#define PCRE2_ERROR_LOOKBEHIND_TOO_LONG 187
#define PCRE2_ERROR_PATTERN_STRING_TOO_LONG 188
#define PCRE2_ERROR_INTERNAL_BAD_CODE 189
#define PCRE2_ERROR_INTERNAL_BAD_CODE_IN_SKIP 190
#define PCRE2_ERROR_NO_SURROGATES_IN_UTF16 191
#define PCRE2_ERROR_BAD_LITERAL_OPTIONS 192
#define PCRE2_ERROR_SUPPORTED_ONLY_IN_UNICODE 193
#define PCRE2_ERROR_INVALID_HYPHEN_IN_OPTIONS 194
/* "Expected" matching error codes: no match and partial match. */
#define PCRE2_ERROR_NOMATCH (-1)
#define PCRE2_ERROR_PARTIAL (-2)
@ -213,10 +360,10 @@ greater than zero. */
#define PCRE2_ERROR_UTF32_ERR1 (-27)
#define PCRE2_ERROR_UTF32_ERR2 (-28)
/* Error codes for pcre2[_dfa]_match(), substring extraction functions, context
functions, and serializing functions. They are in numerical order. Originally
they were in alphabetical order too, but now that PCRE2 is released, the
numbers must not be changed. */
/* Miscellaneous error codes for pcre2[_dfa]_match(), substring extraction
functions, context functions, and serializing functions. They are in numerical
order. Originally they were in alphabetical order too, but now that PCRE2 is
released, the numbers must not be changed. */
#define PCRE2_ERROR_BADDATA (-29)
#define PCRE2_ERROR_MIXEDTABLES (-30) /* Name was changed */
@ -242,7 +389,8 @@ numbers must not be changed. */
#define PCRE2_ERROR_NOUNIQUESUBSTRING (-50)
#define PCRE2_ERROR_NULL (-51)
#define PCRE2_ERROR_RECURSELOOP (-52)
#define PCRE2_ERROR_RECURSIONLIMIT (-53)
#define PCRE2_ERROR_DEPTHLIMIT (-53)
#define PCRE2_ERROR_RECURSIONLIMIT (-53) /* Obsolete synonym */
#define PCRE2_ERROR_UNAVAILABLE (-54)
#define PCRE2_ERROR_UNSET (-55)
#define PCRE2_ERROR_BADOFFSETLIMIT (-56)
@ -252,6 +400,10 @@ numbers must not be changed. */
#define PCRE2_ERROR_BADSUBSPATTERN (-60)
#define PCRE2_ERROR_TOOMANYREPLACE (-61)
#define PCRE2_ERROR_BADSERIALIZEDDATA (-62)
#define PCRE2_ERROR_HEAPLIMIT (-63)
#define PCRE2_ERROR_CONVERT_SYNTAX (-64)
#define PCRE2_ERROR_INTERNAL_DUPMATCH (-65)
/* Request types for pcre2_pattern_info() */
@ -276,9 +428,13 @@ numbers must not be changed. */
#define PCRE2_INFO_NAMEENTRYSIZE 18
#define PCRE2_INFO_NAMETABLE 19
#define PCRE2_INFO_NEWLINE 20
#define PCRE2_INFO_RECURSIONLIMIT 21
#define PCRE2_INFO_DEPTHLIMIT 21
#define PCRE2_INFO_RECURSIONLIMIT 21 /* Obsolete synonym */
#define PCRE2_INFO_SIZE 22
#define PCRE2_INFO_HASBACKSLASHC 23
#define PCRE2_INFO_FRAMESIZE 24
#define PCRE2_INFO_HEAPLIMIT 25
#define PCRE2_INFO_EXTRAOPTIONS 26
/* Request types for pcre2_config(). */
@ -289,11 +445,16 @@ numbers must not be changed. */
#define PCRE2_CONFIG_MATCHLIMIT 4
#define PCRE2_CONFIG_NEWLINE 5
#define PCRE2_CONFIG_PARENSLIMIT 6
#define PCRE2_CONFIG_RECURSIONLIMIT 7
#define PCRE2_CONFIG_STACKRECURSE 8
#define PCRE2_CONFIG_DEPTHLIMIT 7
#define PCRE2_CONFIG_RECURSIONLIMIT 7 /* Obsolete synonym */
#define PCRE2_CONFIG_STACKRECURSE 8 /* Obsolete */
#define PCRE2_CONFIG_UNICODE 9
#define PCRE2_CONFIG_UNICODE_VERSION 10
#define PCRE2_CONFIG_VERSION 11
#define PCRE2_CONFIG_HEAPLIMIT 12
#define PCRE2_CONFIG_NEVER_BACKSLASH_C 13
#define PCRE2_CONFIG_COMPILED_WIDTHS 14
/* Types for code units in patterns and subject strings. */
@ -328,6 +489,9 @@ typedef struct pcre2_real_compile_context pcre2_compile_context; \
struct pcre2_real_match_context; \
typedef struct pcre2_real_match_context pcre2_match_context; \
\
struct pcre2_real_convert_context; \
typedef struct pcre2_real_convert_context pcre2_convert_context; \
\
struct pcre2_real_code; \
typedef struct pcre2_real_code pcre2_code; \
\
@ -346,6 +510,11 @@ without changing the API of the function, thereby allowing old clients to work
without modification. Define the generic version in a macro; the width-specific
versions are generated from this macro below. */
/* Flags for the callout_flags field. These are cleared after a callout. */
#define PCRE2_CALLOUT_STARTMATCH 0x00000001u /* Set for each bumpalong */
#define PCRE2_CALLOUT_BACKTRACK 0x00000002u /* Set after a backtrack */
#define PCRE2_STRUCTURE_LIST \
typedef struct pcre2_callout_block { \
uint32_t version; /* Identifies version of block */ \
@ -365,6 +534,8 @@ typedef struct pcre2_callout_block { \
PCRE2_SIZE callout_string_offset; /* Offset to string within pattern */ \
PCRE2_SIZE callout_string_length; /* Length of string compiled into pattern */ \
PCRE2_SPTR callout_string; /* String compiled into pattern */ \
/* ------------------- Added for Version 2 -------------------------- */ \
uint32_t callout_flags; /* See above for list */ \
/* ------------------------------------------------------------------ */ \
} pcre2_callout_block; \
\
@ -386,170 +557,220 @@ expanded for each width below. Start with functions that give general
information. */
#define PCRE2_GENERAL_INFO_FUNCTIONS \
PCRE2_EXP_DECL int pcre2_config(uint32_t, void *);
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION pcre2_config(uint32_t, void *);
/* Functions for manipulating contexts. */
#define PCRE2_GENERAL_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL \
pcre2_general_context *pcre2_general_context_copy(pcre2_general_context *); \
PCRE2_EXP_DECL \
pcre2_general_context *pcre2_general_context_create( \
void *(*)(PCRE2_SIZE, void *), \
void (*)(void *, void *), void *); \
PCRE2_EXP_DECL void pcre2_general_context_free(pcre2_general_context *);
PCRE2_EXP_DECL pcre2_general_context PCRE2_CALL_CONVENTION \
*pcre2_general_context_copy(pcre2_general_context *); \
PCRE2_EXP_DECL pcre2_general_context PCRE2_CALL_CONVENTION \
*pcre2_general_context_create(void *(*)(PCRE2_SIZE, void *), \
void (*)(void *, void *), void *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_general_context_free(pcre2_general_context *);
#define PCRE2_COMPILE_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL \
pcre2_compile_context *pcre2_compile_context_copy(pcre2_compile_context *); \
PCRE2_EXP_DECL \
pcre2_compile_context *pcre2_compile_context_create(pcre2_general_context *);\
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); \
PCRE2_EXP_DECL int pcre2_set_compile_recursion_guard(\
pcre2_compile_context *, int (*)(uint32_t, void *), \
void *);
PCRE2_EXP_DECL pcre2_compile_context PCRE2_CALL_CONVENTION \
*pcre2_compile_context_copy(pcre2_compile_context *); \
PCRE2_EXP_DECL pcre2_compile_context PCRE2_CALL_CONVENTION \
*pcre2_compile_context_create(pcre2_general_context *);\
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_compile_context_free(pcre2_compile_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_bsr(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_character_tables(pcre2_compile_context *, const unsigned char *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_compile_extra_options(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_max_pattern_length(pcre2_compile_context *, PCRE2_SIZE); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_newline(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_parens_nest_limit(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_compile_recursion_guard(pcre2_compile_context *, \
int (*)(uint32_t, void *), void *);
#define PCRE2_MATCH_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL \
pcre2_match_context *pcre2_match_context_copy(pcre2_match_context *); \
PCRE2_EXP_DECL \
pcre2_match_context *pcre2_match_context_create(pcre2_general_context *); \
PCRE2_EXP_DECL void pcre2_match_context_free(pcre2_match_context *); \
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( \
pcre2_match_context *, void *(*)(PCRE2_SIZE, void *), \
void (*)(void *, void *), void *);
PCRE2_EXP_DECL pcre2_match_context PCRE2_CALL_CONVENTION \
*pcre2_match_context_copy(pcre2_match_context *); \
PCRE2_EXP_DECL pcre2_match_context PCRE2_CALL_CONVENTION \
*pcre2_match_context_create(pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_match_context_free(pcre2_match_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_callout(pcre2_match_context *, \
int (*)(pcre2_callout_block *, void *), void *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_depth_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_heap_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_match_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_offset_limit(pcre2_match_context *, PCRE2_SIZE); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_recursion_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_recursion_memory_management(pcre2_match_context *, \
void *(*)(PCRE2_SIZE, void *), void (*)(void *, void *), void *);
#define PCRE2_CONVERT_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL pcre2_convert_context PCRE2_CALL_CONVENTION \
*pcre2_convert_context_copy(pcre2_convert_context *); \
PCRE2_EXP_DECL pcre2_convert_context PCRE2_CALL_CONVENTION \
*pcre2_convert_context_create(pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_convert_context_free(pcre2_convert_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_glob_escape(pcre2_convert_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_glob_separator(pcre2_convert_context *, uint32_t);
/* Functions concerned with compiling a pattern to PCRE internal code. */
#define PCRE2_COMPILE_FUNCTIONS \
PCRE2_EXP_DECL \
pcre2_code *pcre2_compile(PCRE2_SPTR, PCRE2_SIZE, uint32_t, \
int *, PCRE2_SIZE *, pcre2_compile_context *); \
PCRE2_EXP_DECL void pcre2_code_free(pcre2_code *); \
PCRE2_EXP_DECL \
pcre2_code *pcre2_code_copy(const pcre2_code *);
PCRE2_EXP_DECL pcre2_code PCRE2_CALL_CONVENTION \
*pcre2_compile(PCRE2_SPTR, PCRE2_SIZE, uint32_t, int *, PCRE2_SIZE *, \
pcre2_compile_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_code_free(pcre2_code *); \
PCRE2_EXP_DECL pcre2_code PCRE2_CALL_CONVENTION \
*pcre2_code_copy(const pcre2_code *); \
PCRE2_EXP_DECL pcre2_code PCRE2_CALL_CONVENTION \
*pcre2_code_copy_with_tables(const pcre2_code *);
/* Functions that give information about a compiled pattern. */
#define PCRE2_PATTERN_INFO_FUNCTIONS \
PCRE2_EXP_DECL int pcre2_pattern_info(const pcre2_code *, uint32_t, \
void *); \
PCRE2_EXP_DECL int pcre2_callout_enumerate(const pcre2_code *, \
int (*)(pcre2_callout_enumerate_block *, void *), \
void *);
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_pattern_info(const pcre2_code *, uint32_t, void *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_callout_enumerate(const pcre2_code *, \
int (*)(pcre2_callout_enumerate_block *, void *), void *);
/* Functions for running a match and inspecting the result. */
#define PCRE2_MATCH_FUNCTIONS \
PCRE2_EXP_DECL \
pcre2_match_data *pcre2_match_data_create(uint32_t, \
pcre2_general_context *); \
PCRE2_EXP_DECL \
pcre2_match_data *pcre2_match_data_create_from_pattern(\
const pcre2_code *, \
pcre2_general_context *); \
PCRE2_EXP_DECL int pcre2_dfa_match(const pcre2_code *, PCRE2_SPTR, \
PCRE2_SIZE, PCRE2_SIZE, uint32_t, \
pcre2_match_data *, pcre2_match_context *, int *, \
PCRE2_SIZE); \
PCRE2_EXP_DECL int pcre2_match(const pcre2_code *, \
PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, uint32_t, \
pcre2_match_data *, pcre2_match_context *); \
PCRE2_EXP_DECL void pcre2_match_data_free(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SPTR pcre2_get_mark(pcre2_match_data *); \
PCRE2_EXP_DECL uint32_t pcre2_get_ovector_count(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *);
PCRE2_EXP_DECL pcre2_match_data PCRE2_CALL_CONVENTION \
*pcre2_match_data_create(uint32_t, pcre2_general_context *); \
PCRE2_EXP_DECL pcre2_match_data PCRE2_CALL_CONVENTION \
*pcre2_match_data_create_from_pattern(const pcre2_code *, \
pcre2_general_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_dfa_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *, int *, PCRE2_SIZE); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_match_data_free(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SPTR PCRE2_CALL_CONVENTION \
pcre2_get_mark(pcre2_match_data *); \
PCRE2_EXP_DECL uint32_t PCRE2_CALL_CONVENTION \
pcre2_get_ovector_count(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
*pcre2_get_ovector_pointer(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
pcre2_get_startchar(pcre2_match_data *);
/* Convenience functions for handling matched substrings. */
#define PCRE2_SUBSTRING_FUNCTIONS \
PCRE2_EXP_DECL int pcre2_substring_copy_byname(pcre2_match_data *, \
PCRE2_SPTR, PCRE2_UCHAR *, PCRE2_SIZE *); \
PCRE2_EXP_DECL int pcre2_substring_copy_bynumber(pcre2_match_data *, \
uint32_t, PCRE2_UCHAR *, PCRE2_SIZE *); \
PCRE2_EXP_DECL void pcre2_substring_free(PCRE2_UCHAR *); \
PCRE2_EXP_DECL int pcre2_substring_get_byname(pcre2_match_data *, \
PCRE2_SPTR, PCRE2_UCHAR **, PCRE2_SIZE *); \
PCRE2_EXP_DECL int pcre2_substring_get_bynumber(pcre2_match_data *, \
uint32_t, PCRE2_UCHAR **, PCRE2_SIZE *); \
PCRE2_EXP_DECL int pcre2_substring_length_byname(pcre2_match_data *, \
PCRE2_SPTR, PCRE2_SIZE *); \
PCRE2_EXP_DECL int pcre2_substring_length_bynumber(pcre2_match_data *, \
uint32_t, PCRE2_SIZE *); \
PCRE2_EXP_DECL int pcre2_substring_nametable_scan(const pcre2_code *, \
PCRE2_SPTR, PCRE2_SPTR *, PCRE2_SPTR *); \
PCRE2_EXP_DECL int pcre2_substring_number_from_name(\
const pcre2_code *, PCRE2_SPTR); \
PCRE2_EXP_DECL void pcre2_substring_list_free(PCRE2_SPTR *); \
PCRE2_EXP_DECL int pcre2_substring_list_get(pcre2_match_data *, \
PCRE2_UCHAR ***, PCRE2_SIZE **);
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_copy_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_UCHAR *, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_copy_bynumber(pcre2_match_data *, uint32_t, PCRE2_UCHAR *, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_substring_free(PCRE2_UCHAR *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_get_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_UCHAR **, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_get_bynumber(pcre2_match_data *, uint32_t, PCRE2_UCHAR **, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_length_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_length_bynumber(pcre2_match_data *, uint32_t, PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_nametable_scan(const pcre2_code *, PCRE2_SPTR, PCRE2_SPTR *, \
PCRE2_SPTR *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_number_from_name(const pcre2_code *, PCRE2_SPTR); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_substring_list_free(PCRE2_SPTR *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_list_get(pcre2_match_data *, PCRE2_UCHAR ***, PCRE2_SIZE **);
/* Functions for serializing / deserializing compiled patterns. */
#define PCRE2_SERIALIZE_FUNCTIONS \
PCRE2_EXP_DECL int32_t pcre2_serialize_encode(const pcre2_code **, \
int32_t, uint8_t **, PCRE2_SIZE *, \
pcre2_general_context *); \
PCRE2_EXP_DECL int32_t pcre2_serialize_decode(pcre2_code **, int32_t, \
const uint8_t *, pcre2_general_context *); \
PCRE2_EXP_DECL int32_t pcre2_serialize_get_number_of_codes(const uint8_t *); \
PCRE2_EXP_DECL void pcre2_serialize_free(uint8_t *);
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
pcre2_serialize_encode(const pcre2_code **, int32_t, uint8_t **, \
PCRE2_SIZE *, pcre2_general_context *); \
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
pcre2_serialize_decode(pcre2_code **, int32_t, const uint8_t *, \
pcre2_general_context *); \
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
pcre2_serialize_get_number_of_codes(const uint8_t *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_serialize_free(uint8_t *);
/* Convenience function for match + substitute. */
#define PCRE2_SUBSTITUTE_FUNCTION \
PCRE2_EXP_DECL int pcre2_substitute(const pcre2_code *, \
PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, uint32_t, \
pcre2_match_data *, pcre2_match_context *, \
PCRE2_SPTR, PCRE2_SIZE, PCRE2_UCHAR *, \
PCRE2_SIZE *);
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substitute(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *, PCRE2_SPTR, \
PCRE2_SIZE, PCRE2_UCHAR *, PCRE2_SIZE *);
/* Functions for converting pattern source strings. */
#define PCRE2_CONVERT_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_pattern_convert(PCRE2_SPTR, PCRE2_SIZE, uint32_t, PCRE2_UCHAR **, \
PCRE2_SIZE *, pcre2_convert_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_converted_pattern_free(PCRE2_UCHAR *);
/* Functions for JIT processing */
#define PCRE2_JIT_FUNCTIONS \
PCRE2_EXP_DECL int pcre2_jit_compile(pcre2_code *, uint32_t); \
PCRE2_EXP_DECL int pcre2_jit_match(const pcre2_code *, \
PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, uint32_t, \
pcre2_match_data *, pcre2_match_context *); \
PCRE2_EXP_DECL void pcre2_jit_free_unused_memory(pcre2_general_context *); \
PCRE2_EXP_DECL \
pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE, PCRE2_SIZE, \
pcre2_general_context *); \
PCRE2_EXP_DECL void pcre2_jit_stack_assign(pcre2_match_context *, \
pcre2_jit_callback, void *); \
PCRE2_EXP_DECL void pcre2_jit_stack_free(pcre2_jit_stack *);
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_jit_compile(pcre2_code *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_jit_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_jit_free_unused_memory(pcre2_general_context *); \
PCRE2_EXP_DECL pcre2_jit_stack PCRE2_CALL_CONVENTION \
*pcre2_jit_stack_create(PCRE2_SIZE, PCRE2_SIZE, pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_jit_stack_assign(pcre2_match_context *, pcre2_jit_callback, void *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_jit_stack_free(pcre2_jit_stack *);
/* Other miscellaneous functions. */
#define PCRE2_OTHER_FUNCTIONS \
PCRE2_EXP_DECL int pcre2_get_error_message(int, PCRE2_UCHAR *, PCRE2_SIZE); \
PCRE2_EXP_DECL \
const uint8_t *pcre2_maketables(pcre2_general_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_get_error_message(int, PCRE2_UCHAR *, PCRE2_SIZE); \
PCRE2_EXP_DECL const uint8_t PCRE2_CALL_CONVENTION \
*pcre2_maketables(pcre2_general_context *); \
/* Define macros that generate width-specific names from generic versions. The
@ -576,6 +797,7 @@ pcre2_compile are called by application code. */
#define pcre2_real_code PCRE2_SUFFIX(pcre2_real_code_)
#define pcre2_real_general_context PCRE2_SUFFIX(pcre2_real_general_context_)
#define pcre2_real_compile_context PCRE2_SUFFIX(pcre2_real_compile_context_)
#define pcre2_real_convert_context PCRE2_SUFFIX(pcre2_real_convert_context_)
#define pcre2_real_match_context PCRE2_SUFFIX(pcre2_real_match_context_)
#define pcre2_real_jit_stack PCRE2_SUFFIX(pcre2_real_jit_stack_)
#define pcre2_real_match_data PCRE2_SUFFIX(pcre2_real_match_data_)
@ -587,6 +809,7 @@ pcre2_compile are called by application code. */
#define pcre2_callout_enumerate_block PCRE2_SUFFIX(pcre2_callout_enumerate_block_)
#define pcre2_general_context PCRE2_SUFFIX(pcre2_general_context_)
#define pcre2_compile_context PCRE2_SUFFIX(pcre2_compile_context_)
#define pcre2_convert_context PCRE2_SUFFIX(pcre2_convert_context_)
#define pcre2_match_context PCRE2_SUFFIX(pcre2_match_context_)
#define pcre2_match_data PCRE2_SUFFIX(pcre2_match_data_)
@ -595,12 +818,17 @@ pcre2_compile are called by application code. */
#define pcre2_callout_enumerate PCRE2_SUFFIX(pcre2_callout_enumerate_)
#define pcre2_code_copy PCRE2_SUFFIX(pcre2_code_copy_)
#define pcre2_code_copy_with_tables PCRE2_SUFFIX(pcre2_code_copy_with_tables_)
#define pcre2_code_free PCRE2_SUFFIX(pcre2_code_free_)
#define pcre2_compile PCRE2_SUFFIX(pcre2_compile_)
#define pcre2_compile_context_copy PCRE2_SUFFIX(pcre2_compile_context_copy_)
#define pcre2_compile_context_create PCRE2_SUFFIX(pcre2_compile_context_create_)
#define pcre2_compile_context_free PCRE2_SUFFIX(pcre2_compile_context_free_)
#define pcre2_config PCRE2_SUFFIX(pcre2_config_)
#define pcre2_convert_context_copy PCRE2_SUFFIX(pcre2_convert_context_copy_)
#define pcre2_convert_context_create PCRE2_SUFFIX(pcre2_convert_context_create_)
#define pcre2_convert_context_free PCRE2_SUFFIX(pcre2_convert_context_free_)
#define pcre2_converted_pattern_free PCRE2_SUFFIX(pcre2_converted_pattern_free_)
#define pcre2_dfa_match PCRE2_SUFFIX(pcre2_dfa_match_)
#define pcre2_general_context_copy PCRE2_SUFFIX(pcre2_general_context_copy_)
#define pcre2_general_context_create PCRE2_SUFFIX(pcre2_general_context_create_)
@ -624,6 +852,7 @@ pcre2_compile are called by application code. */
#define pcre2_match_data_create PCRE2_SUFFIX(pcre2_match_data_create_)
#define pcre2_match_data_create_from_pattern PCRE2_SUFFIX(pcre2_match_data_create_from_pattern_)
#define pcre2_match_data_free PCRE2_SUFFIX(pcre2_match_data_free_)
#define pcre2_pattern_convert PCRE2_SUFFIX(pcre2_pattern_convert_)
#define pcre2_pattern_info PCRE2_SUFFIX(pcre2_pattern_info_)
#define pcre2_serialize_decode PCRE2_SUFFIX(pcre2_serialize_decode_)
#define pcre2_serialize_encode PCRE2_SUFFIX(pcre2_serialize_encode_)
@ -632,14 +861,17 @@ pcre2_compile are called by application code. */
#define pcre2_set_bsr PCRE2_SUFFIX(pcre2_set_bsr_)
#define pcre2_set_callout PCRE2_SUFFIX(pcre2_set_callout_)
#define pcre2_set_character_tables PCRE2_SUFFIX(pcre2_set_character_tables_)
#define pcre2_set_compile_extra_options PCRE2_SUFFIX(pcre2_set_compile_extra_options_)
#define pcre2_set_compile_recursion_guard PCRE2_SUFFIX(pcre2_set_compile_recursion_guard_)
#define pcre2_set_depth_limit PCRE2_SUFFIX(pcre2_set_depth_limit_)
#define pcre2_set_glob_escape PCRE2_SUFFIX(pcre2_set_glob_escape_)
#define pcre2_set_glob_separator PCRE2_SUFFIX(pcre2_set_glob_separator_)
#define pcre2_set_heap_limit PCRE2_SUFFIX(pcre2_set_heap_limit_)
#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_)
#define pcre2_substring_copy_byname PCRE2_SUFFIX(pcre2_substring_copy_byname_)
#define pcre2_substring_copy_bynumber PCRE2_SUFFIX(pcre2_substring_copy_bynumber_)
@ -653,6 +885,11 @@ pcre2_compile are called by application code. */
#define pcre2_substring_nametable_scan PCRE2_SUFFIX(pcre2_substring_nametable_scan_)
#define pcre2_substring_number_from_name PCRE2_SUFFIX(pcre2_substring_number_from_name_)
/* Keep this old function name for backwards compatibility */
#define pcre2_set_recursion_limit PCRE2_SUFFIX(pcre2_set_recursion_limit_)
/* Keep this obsolete function for backwards compatibility: it is now a noop. */
#define pcre2_set_recursion_memory_management PCRE2_SUFFIX(pcre2_set_recursion_memory_management_)
/* Now generate all three sets of width-specific structures and function
prototypes. */
@ -663,6 +900,8 @@ PCRE2_STRUCTURE_LIST \
PCRE2_GENERAL_INFO_FUNCTIONS \
PCRE2_GENERAL_CONTEXT_FUNCTIONS \
PCRE2_COMPILE_CONTEXT_FUNCTIONS \
PCRE2_CONVERT_CONTEXT_FUNCTIONS \
PCRE2_CONVERT_FUNCTIONS \
PCRE2_MATCH_CONTEXT_FUNCTIONS \
PCRE2_COMPILE_FUNCTIONS \
PCRE2_PATTERN_INFO_FUNCTIONS \
@ -692,6 +931,7 @@ PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
#undef PCRE2_GENERAL_INFO_FUNCTIONS
#undef PCRE2_GENERAL_CONTEXT_FUNCTIONS
#undef PCRE2_COMPILE_CONTEXT_FUNCTIONS
#undef PCRE2_CONVERT_CONTEXT_FUNCTIONS
#undef PCRE2_MATCH_CONTEXT_FUNCTIONS
#undef PCRE2_COMPILE_FUNCTIONS
#undef PCRE2_PATTERN_INFO_FUNCTIONS
@ -729,4 +969,6 @@ PCRE2_SUFFIX a no-op. Otherwise, generate an error. */
} /* extern "C" */
#endif
#endif /* End of pcre2.h */
#endif /* PCRE2_H_IDEMPOTENT_GUARD */
/* End of 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) 2016 University of Cambridge
Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -36,15 +36,21 @@ POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifndef _PCRE2_H
#define _PCRE2_H
#ifndef PCRE2_H_IDEMPOTENT_GUARD
#define PCRE2_H_IDEMPOTENT_GUARD
/* The current PCRE version information. */
#define PCRE2_MAJOR @PCRE2_MAJOR@
#define PCRE2_MINOR @PCRE2_MINOR@
#define PCRE2_PRERELEASE @PCRE2_PRERELEASE@
#define PCRE2_DATE @PCRE2_DATE@
#define PCRE2_MAJOR @PCRE2_MAJOR@
#define PCRE2_MINOR @PCRE2_MINOR@
#define PCRE2_PRERELEASE @PCRE2_PRERELEASE@
#define PCRE2_DATE @PCRE2_DATE@
/* For the benefit of systems without stdint.h, an alternative is to use
inttypes.h. The existence of these headers is checked by configure or CMake. */
#define PCRE2_HAVE_STDINT_H @PCRE2_HAVE_STDINT_H@
#define PCRE2_HAVE_INTTYPES_H @PCRE2_HAVE_INTTYPES_H@
/* 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
@ -67,12 +73,32 @@ don't change existing definitions of PCRE2_EXP_DECL. */
# endif
#endif
/* Have to include limits.h, stdlib.h and stdint.h to ensure that size_t and
uint8_t, UCHAR_MAX, etc are defined. */
/* When compiling with the MSVC compiler, it is sometimes necessary to include
a "calling convention" before exported function names. (This is secondhand
information; I know nothing about MSVC myself). For example, something like
void __cdecl function(....)
might be needed. In order so make this easy, all the exported functions have
PCRE2_CALL_CONVENTION just before their names. It is rarely needed; if not
set, we ensure here that it has no effect. */
#ifndef PCRE2_CALL_CONVENTION
#define PCRE2_CALL_CONVENTION
#endif
/* Have to include limits.h, stdlib.h and stdint.h (or inttypes.h) to ensure
that size_t and uint8_t, UCHAR_MAX, etc are defined. If the system has neither
header, the relevant values must be provided by some other means. */
#include <limits.h>
#include <stdlib.h>
#if PCRE2_HAVE_STDINT_H
#include <stdint.h>
#elif PCRE2_HAVE_INTTYPES_H
#include <inttypes.h>
#endif
/* Allow for C++ users compiling this directly. */
@ -87,6 +113,7 @@ others can be added next to them */
#define PCRE2_ANCHORED 0x80000000u
#define PCRE2_NO_UTF_CHECK 0x40000000u
#define PCRE2_ENDANCHORED 0x20000000u
/* The following option bits can be passed only to pcre2_compile(). However,
they may affect compilation, JIT compilation, and/or interpretive execution.
@ -122,6 +149,15 @@ D is inspected during pcre2_dfa_match() execution
#define PCRE2_ALT_CIRCUMFLEX 0x00200000u /* J M D */
#define PCRE2_ALT_VERBNAMES 0x00400000u /* C */
#define PCRE2_USE_OFFSET_LIMIT 0x00800000u /* J M D */
#define PCRE2_EXTENDED_MORE 0x01000000u /* C */
#define PCRE2_LITERAL 0x02000000u /* C */
/* An additional compile options word is available in the compile context. */
#define PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES 0x00000001u /* C */
#define PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL 0x00000002u /* C */
#define PCRE2_EXTRA_MATCH_WORD 0x00000004u /* C */
#define PCRE2_EXTRA_MATCH_LINE 0x00000008u /* C */
/* These are for pcre2_jit_compile(). */
@ -160,6 +196,16 @@ ignored for pcre2_jit_match(). */
#define PCRE2_NO_JIT 0x00002000u
/* Options for pcre2_pattern_convert(). */
#define PCRE2_CONVERT_UTF 0x00000001u
#define PCRE2_CONVERT_NO_UTF_CHECK 0x00000002u
#define PCRE2_CONVERT_POSIX_BASIC 0x00000004u
#define PCRE2_CONVERT_POSIX_EXTENDED 0x00000008u
#define PCRE2_CONVERT_GLOB 0x00000010u
#define PCRE2_CONVERT_GLOB_NO_WILD_SEPARATOR 0x00000030u
#define PCRE2_CONVERT_GLOB_NO_STARSTAR 0x00000050u
/* 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
greater than zero. */
@ -169,11 +215,112 @@ greater than zero. */
#define PCRE2_NEWLINE_CRLF 3
#define PCRE2_NEWLINE_ANY 4
#define PCRE2_NEWLINE_ANYCRLF 5
#define PCRE2_NEWLINE_NUL 6
#define PCRE2_BSR_UNICODE 1
#define PCRE2_BSR_ANYCRLF 2
/* Error codes: no match and partial match are "expected" errors. */
/* Error codes for pcre2_compile(). Some of these are also used by
pcre2_pattern_convert(). */
#define PCRE2_ERROR_END_BACKSLASH 101
#define PCRE2_ERROR_END_BACKSLASH_C 102
#define PCRE2_ERROR_UNKNOWN_ESCAPE 103
#define PCRE2_ERROR_QUANTIFIER_OUT_OF_ORDER 104
#define PCRE2_ERROR_QUANTIFIER_TOO_BIG 105
#define PCRE2_ERROR_MISSING_SQUARE_BRACKET 106
#define PCRE2_ERROR_ESCAPE_INVALID_IN_CLASS 107
#define PCRE2_ERROR_CLASS_RANGE_ORDER 108
#define PCRE2_ERROR_QUANTIFIER_INVALID 109
#define PCRE2_ERROR_INTERNAL_UNEXPECTED_REPEAT 110
#define PCRE2_ERROR_INVALID_AFTER_PARENS_QUERY 111
#define PCRE2_ERROR_POSIX_CLASS_NOT_IN_CLASS 112
#define PCRE2_ERROR_POSIX_NO_SUPPORT_COLLATING 113
#define PCRE2_ERROR_MISSING_CLOSING_PARENTHESIS 114
#define PCRE2_ERROR_BAD_SUBPATTERN_REFERENCE 115
#define PCRE2_ERROR_NULL_PATTERN 116
#define PCRE2_ERROR_BAD_OPTIONS 117
#define PCRE2_ERROR_MISSING_COMMENT_CLOSING 118
#define PCRE2_ERROR_PARENTHESES_NEST_TOO_DEEP 119
#define PCRE2_ERROR_PATTERN_TOO_LARGE 120
#define PCRE2_ERROR_HEAP_FAILED 121
#define PCRE2_ERROR_UNMATCHED_CLOSING_PARENTHESIS 122
#define PCRE2_ERROR_INTERNAL_CODE_OVERFLOW 123
#define PCRE2_ERROR_MISSING_CONDITION_CLOSING 124
#define PCRE2_ERROR_LOOKBEHIND_NOT_FIXED_LENGTH 125
#define PCRE2_ERROR_ZERO_RELATIVE_REFERENCE 126
#define PCRE2_ERROR_TOO_MANY_CONDITION_BRANCHES 127
#define PCRE2_ERROR_CONDITION_ASSERTION_EXPECTED 128
#define PCRE2_ERROR_BAD_RELATIVE_REFERENCE 129
#define PCRE2_ERROR_UNKNOWN_POSIX_CLASS 130
#define PCRE2_ERROR_INTERNAL_STUDY_ERROR 131
#define PCRE2_ERROR_UNICODE_NOT_SUPPORTED 132
#define PCRE2_ERROR_PARENTHESES_STACK_CHECK 133
#define PCRE2_ERROR_CODE_POINT_TOO_BIG 134
#define PCRE2_ERROR_LOOKBEHIND_TOO_COMPLICATED 135
#define PCRE2_ERROR_LOOKBEHIND_INVALID_BACKSLASH_C 136
#define PCRE2_ERROR_UNSUPPORTED_ESCAPE_SEQUENCE 137
#define PCRE2_ERROR_CALLOUT_NUMBER_TOO_BIG 138
#define PCRE2_ERROR_MISSING_CALLOUT_CLOSING 139
#define PCRE2_ERROR_ESCAPE_INVALID_IN_VERB 140
#define PCRE2_ERROR_UNRECOGNIZED_AFTER_QUERY_P 141
#define PCRE2_ERROR_MISSING_NAME_TERMINATOR 142
#define PCRE2_ERROR_DUPLICATE_SUBPATTERN_NAME 143
#define PCRE2_ERROR_INVALID_SUBPATTERN_NAME 144
#define PCRE2_ERROR_UNICODE_PROPERTIES_UNAVAILABLE 145
#define PCRE2_ERROR_MALFORMED_UNICODE_PROPERTY 146
#define PCRE2_ERROR_UNKNOWN_UNICODE_PROPERTY 147
#define PCRE2_ERROR_SUBPATTERN_NAME_TOO_LONG 148
#define PCRE2_ERROR_TOO_MANY_NAMED_SUBPATTERNS 149
#define PCRE2_ERROR_CLASS_INVALID_RANGE 150
#define PCRE2_ERROR_OCTAL_BYTE_TOO_BIG 151
#define PCRE2_ERROR_INTERNAL_OVERRAN_WORKSPACE 152
#define PCRE2_ERROR_INTERNAL_MISSING_SUBPATTERN 153
#define PCRE2_ERROR_DEFINE_TOO_MANY_BRANCHES 154
#define PCRE2_ERROR_BACKSLASH_O_MISSING_BRACE 155
#define PCRE2_ERROR_INTERNAL_UNKNOWN_NEWLINE 156
#define PCRE2_ERROR_BACKSLASH_G_SYNTAX 157
#define PCRE2_ERROR_PARENS_QUERY_R_MISSING_CLOSING 158
/* Error 159 is obsolete and should now never occur */
#define PCRE2_ERROR_VERB_ARGUMENT_NOT_ALLOWED 159
#define PCRE2_ERROR_VERB_UNKNOWN 160
#define PCRE2_ERROR_SUBPATTERN_NUMBER_TOO_BIG 161
#define PCRE2_ERROR_SUBPATTERN_NAME_EXPECTED 162
#define PCRE2_ERROR_INTERNAL_PARSED_OVERFLOW 163
#define PCRE2_ERROR_INVALID_OCTAL 164
#define PCRE2_ERROR_SUBPATTERN_NAMES_MISMATCH 165
#define PCRE2_ERROR_MARK_MISSING_ARGUMENT 166
#define PCRE2_ERROR_INVALID_HEXADECIMAL 167
#define PCRE2_ERROR_BACKSLASH_C_SYNTAX 168
#define PCRE2_ERROR_BACKSLASH_K_SYNTAX 169
#define PCRE2_ERROR_INTERNAL_BAD_CODE_LOOKBEHINDS 170
#define PCRE2_ERROR_BACKSLASH_N_IN_CLASS 171
#define PCRE2_ERROR_CALLOUT_STRING_TOO_LONG 172
#define PCRE2_ERROR_UNICODE_DISALLOWED_CODE_POINT 173
#define PCRE2_ERROR_UTF_IS_DISABLED 174
#define PCRE2_ERROR_UCP_IS_DISABLED 175
#define PCRE2_ERROR_VERB_NAME_TOO_LONG 176
#define PCRE2_ERROR_BACKSLASH_U_CODE_POINT_TOO_BIG 177
#define PCRE2_ERROR_MISSING_OCTAL_OR_HEX_DIGITS 178
#define PCRE2_ERROR_VERSION_CONDITION_SYNTAX 179
#define PCRE2_ERROR_INTERNAL_BAD_CODE_AUTO_POSSESS 180
#define PCRE2_ERROR_CALLOUT_NO_STRING_DELIMITER 181
#define PCRE2_ERROR_CALLOUT_BAD_STRING_DELIMITER 182
#define PCRE2_ERROR_BACKSLASH_C_CALLER_DISABLED 183
#define PCRE2_ERROR_QUERY_BARJX_NEST_TOO_DEEP 184
#define PCRE2_ERROR_BACKSLASH_C_LIBRARY_DISABLED 185
#define PCRE2_ERROR_PATTERN_TOO_COMPLICATED 186
#define PCRE2_ERROR_LOOKBEHIND_TOO_LONG 187
#define PCRE2_ERROR_PATTERN_STRING_TOO_LONG 188
#define PCRE2_ERROR_INTERNAL_BAD_CODE 189
#define PCRE2_ERROR_INTERNAL_BAD_CODE_IN_SKIP 190
#define PCRE2_ERROR_NO_SURROGATES_IN_UTF16 191
#define PCRE2_ERROR_BAD_LITERAL_OPTIONS 192
#define PCRE2_ERROR_SUPPORTED_ONLY_IN_UNICODE 193
#define PCRE2_ERROR_INVALID_HYPHEN_IN_OPTIONS 194
/* "Expected" matching error codes: no match and partial match. */
#define PCRE2_ERROR_NOMATCH (-1)
#define PCRE2_ERROR_PARTIAL (-2)
@ -213,10 +360,10 @@ greater than zero. */
#define PCRE2_ERROR_UTF32_ERR1 (-27)
#define PCRE2_ERROR_UTF32_ERR2 (-28)
/* Error codes for pcre2[_dfa]_match(), substring extraction functions, context
functions, and serializing functions. They are in numerical order. Originally
they were in alphabetical order too, but now that PCRE2 is released, the
numbers must not be changed. */
/* Miscellaneous error codes for pcre2[_dfa]_match(), substring extraction
functions, context functions, and serializing functions. They are in numerical
order. Originally they were in alphabetical order too, but now that PCRE2 is
released, the numbers must not be changed. */
#define PCRE2_ERROR_BADDATA (-29)
#define PCRE2_ERROR_MIXEDTABLES (-30) /* Name was changed */
@ -242,7 +389,8 @@ numbers must not be changed. */
#define PCRE2_ERROR_NOUNIQUESUBSTRING (-50)
#define PCRE2_ERROR_NULL (-51)
#define PCRE2_ERROR_RECURSELOOP (-52)
#define PCRE2_ERROR_RECURSIONLIMIT (-53)
#define PCRE2_ERROR_DEPTHLIMIT (-53)
#define PCRE2_ERROR_RECURSIONLIMIT (-53) /* Obsolete synonym */
#define PCRE2_ERROR_UNAVAILABLE (-54)
#define PCRE2_ERROR_UNSET (-55)
#define PCRE2_ERROR_BADOFFSETLIMIT (-56)
@ -252,6 +400,10 @@ numbers must not be changed. */
#define PCRE2_ERROR_BADSUBSPATTERN (-60)
#define PCRE2_ERROR_TOOMANYREPLACE (-61)
#define PCRE2_ERROR_BADSERIALIZEDDATA (-62)
#define PCRE2_ERROR_HEAPLIMIT (-63)
#define PCRE2_ERROR_CONVERT_SYNTAX (-64)
#define PCRE2_ERROR_INTERNAL_DUPMATCH (-65)
/* Request types for pcre2_pattern_info() */
@ -276,9 +428,13 @@ numbers must not be changed. */
#define PCRE2_INFO_NAMEENTRYSIZE 18
#define PCRE2_INFO_NAMETABLE 19
#define PCRE2_INFO_NEWLINE 20
#define PCRE2_INFO_RECURSIONLIMIT 21
#define PCRE2_INFO_DEPTHLIMIT 21
#define PCRE2_INFO_RECURSIONLIMIT 21 /* Obsolete synonym */
#define PCRE2_INFO_SIZE 22
#define PCRE2_INFO_HASBACKSLASHC 23
#define PCRE2_INFO_FRAMESIZE 24
#define PCRE2_INFO_HEAPLIMIT 25
#define PCRE2_INFO_EXTRAOPTIONS 26
/* Request types for pcre2_config(). */
@ -289,11 +445,16 @@ numbers must not be changed. */
#define PCRE2_CONFIG_MATCHLIMIT 4
#define PCRE2_CONFIG_NEWLINE 5
#define PCRE2_CONFIG_PARENSLIMIT 6
#define PCRE2_CONFIG_RECURSIONLIMIT 7
#define PCRE2_CONFIG_STACKRECURSE 8
#define PCRE2_CONFIG_DEPTHLIMIT 7
#define PCRE2_CONFIG_RECURSIONLIMIT 7 /* Obsolete synonym */
#define PCRE2_CONFIG_STACKRECURSE 8 /* Obsolete */
#define PCRE2_CONFIG_UNICODE 9
#define PCRE2_CONFIG_UNICODE_VERSION 10
#define PCRE2_CONFIG_VERSION 11
#define PCRE2_CONFIG_HEAPLIMIT 12
#define PCRE2_CONFIG_NEVER_BACKSLASH_C 13
#define PCRE2_CONFIG_COMPILED_WIDTHS 14
/* Types for code units in patterns and subject strings. */
@ -328,6 +489,9 @@ typedef struct pcre2_real_compile_context pcre2_compile_context; \
struct pcre2_real_match_context; \
typedef struct pcre2_real_match_context pcre2_match_context; \
\
struct pcre2_real_convert_context; \
typedef struct pcre2_real_convert_context pcre2_convert_context; \
\
struct pcre2_real_code; \
typedef struct pcre2_real_code pcre2_code; \
\
@ -346,6 +510,11 @@ without changing the API of the function, thereby allowing old clients to work
without modification. Define the generic version in a macro; the width-specific
versions are generated from this macro below. */
/* Flags for the callout_flags field. These are cleared after a callout. */
#define PCRE2_CALLOUT_STARTMATCH 0x00000001u /* Set for each bumpalong */
#define PCRE2_CALLOUT_BACKTRACK 0x00000002u /* Set after a backtrack */
#define PCRE2_STRUCTURE_LIST \
typedef struct pcre2_callout_block { \
uint32_t version; /* Identifies version of block */ \
@ -365,6 +534,8 @@ typedef struct pcre2_callout_block { \
PCRE2_SIZE callout_string_offset; /* Offset to string within pattern */ \
PCRE2_SIZE callout_string_length; /* Length of string compiled into pattern */ \
PCRE2_SPTR callout_string; /* String compiled into pattern */ \
/* ------------------- Added for Version 2 -------------------------- */ \
uint32_t callout_flags; /* See above for list */ \
/* ------------------------------------------------------------------ */ \
} pcre2_callout_block; \
\
@ -386,170 +557,220 @@ expanded for each width below. Start with functions that give general
information. */
#define PCRE2_GENERAL_INFO_FUNCTIONS \
PCRE2_EXP_DECL int pcre2_config(uint32_t, void *);
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION pcre2_config(uint32_t, void *);
/* Functions for manipulating contexts. */
#define PCRE2_GENERAL_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL \
pcre2_general_context *pcre2_general_context_copy(pcre2_general_context *); \
PCRE2_EXP_DECL \
pcre2_general_context *pcre2_general_context_create( \
void *(*)(PCRE2_SIZE, void *), \
void (*)(void *, void *), void *); \
PCRE2_EXP_DECL void pcre2_general_context_free(pcre2_general_context *);
PCRE2_EXP_DECL pcre2_general_context PCRE2_CALL_CONVENTION \
*pcre2_general_context_copy(pcre2_general_context *); \
PCRE2_EXP_DECL pcre2_general_context PCRE2_CALL_CONVENTION \
*pcre2_general_context_create(void *(*)(PCRE2_SIZE, void *), \
void (*)(void *, void *), void *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_general_context_free(pcre2_general_context *);
#define PCRE2_COMPILE_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL \
pcre2_compile_context *pcre2_compile_context_copy(pcre2_compile_context *); \
PCRE2_EXP_DECL \
pcre2_compile_context *pcre2_compile_context_create(pcre2_general_context *);\
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); \
PCRE2_EXP_DECL int pcre2_set_compile_recursion_guard(\
pcre2_compile_context *, int (*)(uint32_t, void *), \
void *);
PCRE2_EXP_DECL pcre2_compile_context PCRE2_CALL_CONVENTION \
*pcre2_compile_context_copy(pcre2_compile_context *); \
PCRE2_EXP_DECL pcre2_compile_context PCRE2_CALL_CONVENTION \
*pcre2_compile_context_create(pcre2_general_context *);\
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_compile_context_free(pcre2_compile_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_bsr(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_character_tables(pcre2_compile_context *, const unsigned char *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_compile_extra_options(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_max_pattern_length(pcre2_compile_context *, PCRE2_SIZE); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_newline(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_parens_nest_limit(pcre2_compile_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_compile_recursion_guard(pcre2_compile_context *, \
int (*)(uint32_t, void *), void *);
#define PCRE2_MATCH_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL \
pcre2_match_context *pcre2_match_context_copy(pcre2_match_context *); \
PCRE2_EXP_DECL \
pcre2_match_context *pcre2_match_context_create(pcre2_general_context *); \
PCRE2_EXP_DECL void pcre2_match_context_free(pcre2_match_context *); \
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( \
pcre2_match_context *, void *(*)(PCRE2_SIZE, void *), \
void (*)(void *, void *), void *);
PCRE2_EXP_DECL pcre2_match_context PCRE2_CALL_CONVENTION \
*pcre2_match_context_copy(pcre2_match_context *); \
PCRE2_EXP_DECL pcre2_match_context PCRE2_CALL_CONVENTION \
*pcre2_match_context_create(pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_match_context_free(pcre2_match_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_callout(pcre2_match_context *, \
int (*)(pcre2_callout_block *, void *), void *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_depth_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_heap_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_match_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_offset_limit(pcre2_match_context *, PCRE2_SIZE); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_recursion_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_recursion_memory_management(pcre2_match_context *, \
void *(*)(PCRE2_SIZE, void *), void (*)(void *, void *), void *);
#define PCRE2_CONVERT_CONTEXT_FUNCTIONS \
PCRE2_EXP_DECL pcre2_convert_context PCRE2_CALL_CONVENTION \
*pcre2_convert_context_copy(pcre2_convert_context *); \
PCRE2_EXP_DECL pcre2_convert_context PCRE2_CALL_CONVENTION \
*pcre2_convert_context_create(pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_convert_context_free(pcre2_convert_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_glob_escape(pcre2_convert_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_glob_separator(pcre2_convert_context *, uint32_t);
/* Functions concerned with compiling a pattern to PCRE internal code. */
#define PCRE2_COMPILE_FUNCTIONS \
PCRE2_EXP_DECL \
pcre2_code *pcre2_compile(PCRE2_SPTR, PCRE2_SIZE, uint32_t, \
int *, PCRE2_SIZE *, pcre2_compile_context *); \
PCRE2_EXP_DECL void pcre2_code_free(pcre2_code *); \
PCRE2_EXP_DECL \
pcre2_code *pcre2_code_copy(const pcre2_code *);
PCRE2_EXP_DECL pcre2_code PCRE2_CALL_CONVENTION \
*pcre2_compile(PCRE2_SPTR, PCRE2_SIZE, uint32_t, int *, PCRE2_SIZE *, \
pcre2_compile_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_code_free(pcre2_code *); \
PCRE2_EXP_DECL pcre2_code PCRE2_CALL_CONVENTION \
*pcre2_code_copy(const pcre2_code *); \
PCRE2_EXP_DECL pcre2_code PCRE2_CALL_CONVENTION \
*pcre2_code_copy_with_tables(const pcre2_code *);
/* Functions that give information about a compiled pattern. */
#define PCRE2_PATTERN_INFO_FUNCTIONS \
PCRE2_EXP_DECL int pcre2_pattern_info(const pcre2_code *, uint32_t, \
void *); \
PCRE2_EXP_DECL int pcre2_callout_enumerate(const pcre2_code *, \
int (*)(pcre2_callout_enumerate_block *, void *), \
void *);
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_pattern_info(const pcre2_code *, uint32_t, void *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_callout_enumerate(const pcre2_code *, \
int (*)(pcre2_callout_enumerate_block *, void *), void *);
/* Functions for running a match and inspecting the result. */
#define PCRE2_MATCH_FUNCTIONS \
PCRE2_EXP_DECL \
pcre2_match_data *pcre2_match_data_create(uint32_t, \
pcre2_general_context *); \
PCRE2_EXP_DECL \
pcre2_match_data *pcre2_match_data_create_from_pattern(\
const pcre2_code *, \
pcre2_general_context *); \
PCRE2_EXP_DECL int pcre2_dfa_match(const pcre2_code *, PCRE2_SPTR, \
PCRE2_SIZE, PCRE2_SIZE, uint32_t, \
pcre2_match_data *, pcre2_match_context *, int *, \
PCRE2_SIZE); \
PCRE2_EXP_DECL int pcre2_match(const pcre2_code *, \
PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, uint32_t, \
pcre2_match_data *, pcre2_match_context *); \
PCRE2_EXP_DECL void pcre2_match_data_free(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SPTR pcre2_get_mark(pcre2_match_data *); \
PCRE2_EXP_DECL uint32_t pcre2_get_ovector_count(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *);
PCRE2_EXP_DECL pcre2_match_data PCRE2_CALL_CONVENTION \
*pcre2_match_data_create(uint32_t, pcre2_general_context *); \
PCRE2_EXP_DECL pcre2_match_data PCRE2_CALL_CONVENTION \
*pcre2_match_data_create_from_pattern(const pcre2_code *, \
pcre2_general_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_dfa_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *, int *, PCRE2_SIZE); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_match_data_free(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SPTR PCRE2_CALL_CONVENTION \
pcre2_get_mark(pcre2_match_data *); \
PCRE2_EXP_DECL uint32_t PCRE2_CALL_CONVENTION \
pcre2_get_ovector_count(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
*pcre2_get_ovector_pointer(pcre2_match_data *); \
PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
pcre2_get_startchar(pcre2_match_data *);
/* Convenience functions for handling matched substrings. */
#define PCRE2_SUBSTRING_FUNCTIONS \
PCRE2_EXP_DECL int pcre2_substring_copy_byname(pcre2_match_data *, \
PCRE2_SPTR, PCRE2_UCHAR *, PCRE2_SIZE *); \
PCRE2_EXP_DECL int pcre2_substring_copy_bynumber(pcre2_match_data *, \
uint32_t, PCRE2_UCHAR *, PCRE2_SIZE *); \
PCRE2_EXP_DECL void pcre2_substring_free(PCRE2_UCHAR *); \
PCRE2_EXP_DECL int pcre2_substring_get_byname(pcre2_match_data *, \
PCRE2_SPTR, PCRE2_UCHAR **, PCRE2_SIZE *); \
PCRE2_EXP_DECL int pcre2_substring_get_bynumber(pcre2_match_data *, \
uint32_t, PCRE2_UCHAR **, PCRE2_SIZE *); \
PCRE2_EXP_DECL int pcre2_substring_length_byname(pcre2_match_data *, \
PCRE2_SPTR, PCRE2_SIZE *); \
PCRE2_EXP_DECL int pcre2_substring_length_bynumber(pcre2_match_data *, \
uint32_t, PCRE2_SIZE *); \
PCRE2_EXP_DECL int pcre2_substring_nametable_scan(const pcre2_code *, \
PCRE2_SPTR, PCRE2_SPTR *, PCRE2_SPTR *); \
PCRE2_EXP_DECL int pcre2_substring_number_from_name(\
const pcre2_code *, PCRE2_SPTR); \
PCRE2_EXP_DECL void pcre2_substring_list_free(PCRE2_SPTR *); \
PCRE2_EXP_DECL int pcre2_substring_list_get(pcre2_match_data *, \
PCRE2_UCHAR ***, PCRE2_SIZE **);
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_copy_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_UCHAR *, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_copy_bynumber(pcre2_match_data *, uint32_t, PCRE2_UCHAR *, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_substring_free(PCRE2_UCHAR *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_get_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_UCHAR **, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_get_bynumber(pcre2_match_data *, uint32_t, PCRE2_UCHAR **, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_length_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_length_bynumber(pcre2_match_data *, uint32_t, PCRE2_SIZE *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_nametable_scan(const pcre2_code *, PCRE2_SPTR, PCRE2_SPTR *, \
PCRE2_SPTR *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_number_from_name(const pcre2_code *, PCRE2_SPTR); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_substring_list_free(PCRE2_SPTR *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substring_list_get(pcre2_match_data *, PCRE2_UCHAR ***, PCRE2_SIZE **);
/* Functions for serializing / deserializing compiled patterns. */
#define PCRE2_SERIALIZE_FUNCTIONS \
PCRE2_EXP_DECL int32_t pcre2_serialize_encode(const pcre2_code **, \
int32_t, uint8_t **, PCRE2_SIZE *, \
pcre2_general_context *); \
PCRE2_EXP_DECL int32_t pcre2_serialize_decode(pcre2_code **, int32_t, \
const uint8_t *, pcre2_general_context *); \
PCRE2_EXP_DECL int32_t pcre2_serialize_get_number_of_codes(const uint8_t *); \
PCRE2_EXP_DECL void pcre2_serialize_free(uint8_t *);
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
pcre2_serialize_encode(const pcre2_code **, int32_t, uint8_t **, \
PCRE2_SIZE *, pcre2_general_context *); \
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
pcre2_serialize_decode(pcre2_code **, int32_t, const uint8_t *, \
pcre2_general_context *); \
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
pcre2_serialize_get_number_of_codes(const uint8_t *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_serialize_free(uint8_t *);
/* Convenience function for match + substitute. */
#define PCRE2_SUBSTITUTE_FUNCTION \
PCRE2_EXP_DECL int pcre2_substitute(const pcre2_code *, \
PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, uint32_t, \
pcre2_match_data *, pcre2_match_context *, \
PCRE2_SPTR, PCRE2_SIZE, PCRE2_UCHAR *, \
PCRE2_SIZE *);
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_substitute(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *, PCRE2_SPTR, \
PCRE2_SIZE, PCRE2_UCHAR *, PCRE2_SIZE *);
/* Functions for converting pattern source strings. */
#define PCRE2_CONVERT_FUNCTIONS \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_pattern_convert(PCRE2_SPTR, PCRE2_SIZE, uint32_t, PCRE2_UCHAR **, \
PCRE2_SIZE *, pcre2_convert_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_converted_pattern_free(PCRE2_UCHAR *);
/* Functions for JIT processing */
#define PCRE2_JIT_FUNCTIONS \
PCRE2_EXP_DECL int pcre2_jit_compile(pcre2_code *, uint32_t); \
PCRE2_EXP_DECL int pcre2_jit_match(const pcre2_code *, \
PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, uint32_t, \
pcre2_match_data *, pcre2_match_context *); \
PCRE2_EXP_DECL void pcre2_jit_free_unused_memory(pcre2_general_context *); \
PCRE2_EXP_DECL \
pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE, PCRE2_SIZE, \
pcre2_general_context *); \
PCRE2_EXP_DECL void pcre2_jit_stack_assign(pcre2_match_context *, \
pcre2_jit_callback, void *); \
PCRE2_EXP_DECL void pcre2_jit_stack_free(pcre2_jit_stack *);
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_jit_compile(pcre2_code *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_jit_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
uint32_t, pcre2_match_data *, pcre2_match_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_jit_free_unused_memory(pcre2_general_context *); \
PCRE2_EXP_DECL pcre2_jit_stack PCRE2_CALL_CONVENTION \
*pcre2_jit_stack_create(PCRE2_SIZE, PCRE2_SIZE, pcre2_general_context *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_jit_stack_assign(pcre2_match_context *, pcre2_jit_callback, void *); \
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_jit_stack_free(pcre2_jit_stack *);
/* Other miscellaneous functions. */
#define PCRE2_OTHER_FUNCTIONS \
PCRE2_EXP_DECL int pcre2_get_error_message(int, PCRE2_UCHAR *, PCRE2_SIZE); \
PCRE2_EXP_DECL \
const uint8_t *pcre2_maketables(pcre2_general_context *); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_get_error_message(int, PCRE2_UCHAR *, PCRE2_SIZE); \
PCRE2_EXP_DECL const uint8_t PCRE2_CALL_CONVENTION \
*pcre2_maketables(pcre2_general_context *); \
/* Define macros that generate width-specific names from generic versions. The
@ -576,6 +797,7 @@ pcre2_compile are called by application code. */
#define pcre2_real_code PCRE2_SUFFIX(pcre2_real_code_)
#define pcre2_real_general_context PCRE2_SUFFIX(pcre2_real_general_context_)
#define pcre2_real_compile_context PCRE2_SUFFIX(pcre2_real_compile_context_)
#define pcre2_real_convert_context PCRE2_SUFFIX(pcre2_real_convert_context_)
#define pcre2_real_match_context PCRE2_SUFFIX(pcre2_real_match_context_)
#define pcre2_real_jit_stack PCRE2_SUFFIX(pcre2_real_jit_stack_)
#define pcre2_real_match_data PCRE2_SUFFIX(pcre2_real_match_data_)
@ -587,6 +809,7 @@ pcre2_compile are called by application code. */
#define pcre2_callout_enumerate_block PCRE2_SUFFIX(pcre2_callout_enumerate_block_)
#define pcre2_general_context PCRE2_SUFFIX(pcre2_general_context_)
#define pcre2_compile_context PCRE2_SUFFIX(pcre2_compile_context_)
#define pcre2_convert_context PCRE2_SUFFIX(pcre2_convert_context_)
#define pcre2_match_context PCRE2_SUFFIX(pcre2_match_context_)
#define pcre2_match_data PCRE2_SUFFIX(pcre2_match_data_)
@ -595,12 +818,17 @@ pcre2_compile are called by application code. */
#define pcre2_callout_enumerate PCRE2_SUFFIX(pcre2_callout_enumerate_)
#define pcre2_code_copy PCRE2_SUFFIX(pcre2_code_copy_)
#define pcre2_code_copy_with_tables PCRE2_SUFFIX(pcre2_code_copy_with_tables_)
#define pcre2_code_free PCRE2_SUFFIX(pcre2_code_free_)
#define pcre2_compile PCRE2_SUFFIX(pcre2_compile_)
#define pcre2_compile_context_copy PCRE2_SUFFIX(pcre2_compile_context_copy_)
#define pcre2_compile_context_create PCRE2_SUFFIX(pcre2_compile_context_create_)
#define pcre2_compile_context_free PCRE2_SUFFIX(pcre2_compile_context_free_)
#define pcre2_config PCRE2_SUFFIX(pcre2_config_)
#define pcre2_convert_context_copy PCRE2_SUFFIX(pcre2_convert_context_copy_)
#define pcre2_convert_context_create PCRE2_SUFFIX(pcre2_convert_context_create_)
#define pcre2_convert_context_free PCRE2_SUFFIX(pcre2_convert_context_free_)
#define pcre2_converted_pattern_free PCRE2_SUFFIX(pcre2_converted_pattern_free_)
#define pcre2_dfa_match PCRE2_SUFFIX(pcre2_dfa_match_)
#define pcre2_general_context_copy PCRE2_SUFFIX(pcre2_general_context_copy_)
#define pcre2_general_context_create PCRE2_SUFFIX(pcre2_general_context_create_)
@ -624,6 +852,7 @@ pcre2_compile are called by application code. */
#define pcre2_match_data_create PCRE2_SUFFIX(pcre2_match_data_create_)
#define pcre2_match_data_create_from_pattern PCRE2_SUFFIX(pcre2_match_data_create_from_pattern_)
#define pcre2_match_data_free PCRE2_SUFFIX(pcre2_match_data_free_)
#define pcre2_pattern_convert PCRE2_SUFFIX(pcre2_pattern_convert_)
#define pcre2_pattern_info PCRE2_SUFFIX(pcre2_pattern_info_)
#define pcre2_serialize_decode PCRE2_SUFFIX(pcre2_serialize_decode_)
#define pcre2_serialize_encode PCRE2_SUFFIX(pcre2_serialize_encode_)
@ -632,14 +861,17 @@ pcre2_compile are called by application code. */
#define pcre2_set_bsr PCRE2_SUFFIX(pcre2_set_bsr_)
#define pcre2_set_callout PCRE2_SUFFIX(pcre2_set_callout_)
#define pcre2_set_character_tables PCRE2_SUFFIX(pcre2_set_character_tables_)
#define pcre2_set_compile_extra_options PCRE2_SUFFIX(pcre2_set_compile_extra_options_)
#define pcre2_set_compile_recursion_guard PCRE2_SUFFIX(pcre2_set_compile_recursion_guard_)
#define pcre2_set_depth_limit PCRE2_SUFFIX(pcre2_set_depth_limit_)
#define pcre2_set_glob_escape PCRE2_SUFFIX(pcre2_set_glob_escape_)
#define pcre2_set_glob_separator PCRE2_SUFFIX(pcre2_set_glob_separator_)
#define pcre2_set_heap_limit PCRE2_SUFFIX(pcre2_set_heap_limit_)
#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_)
#define pcre2_substring_copy_byname PCRE2_SUFFIX(pcre2_substring_copy_byname_)
#define pcre2_substring_copy_bynumber PCRE2_SUFFIX(pcre2_substring_copy_bynumber_)
@ -653,6 +885,11 @@ pcre2_compile are called by application code. */
#define pcre2_substring_nametable_scan PCRE2_SUFFIX(pcre2_substring_nametable_scan_)
#define pcre2_substring_number_from_name PCRE2_SUFFIX(pcre2_substring_number_from_name_)
/* Keep this old function name for backwards compatibility */
#define pcre2_set_recursion_limit PCRE2_SUFFIX(pcre2_set_recursion_limit_)
/* Keep this obsolete function for backwards compatibility: it is now a noop. */
#define pcre2_set_recursion_memory_management PCRE2_SUFFIX(pcre2_set_recursion_memory_management_)
/* Now generate all three sets of width-specific structures and function
prototypes. */
@ -663,6 +900,8 @@ PCRE2_STRUCTURE_LIST \
PCRE2_GENERAL_INFO_FUNCTIONS \
PCRE2_GENERAL_CONTEXT_FUNCTIONS \
PCRE2_COMPILE_CONTEXT_FUNCTIONS \
PCRE2_CONVERT_CONTEXT_FUNCTIONS \
PCRE2_CONVERT_FUNCTIONS \
PCRE2_MATCH_CONTEXT_FUNCTIONS \
PCRE2_COMPILE_FUNCTIONS \
PCRE2_PATTERN_INFO_FUNCTIONS \
@ -692,6 +931,7 @@ PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
#undef PCRE2_GENERAL_INFO_FUNCTIONS
#undef PCRE2_GENERAL_CONTEXT_FUNCTIONS
#undef PCRE2_COMPILE_CONTEXT_FUNCTIONS
#undef PCRE2_CONVERT_CONTEXT_FUNCTIONS
#undef PCRE2_MATCH_CONTEXT_FUNCTIONS
#undef PCRE2_COMPILE_FUNCTIONS
#undef PCRE2_PATTERN_INFO_FUNCTIONS
@ -729,4 +969,6 @@ PCRE2_SUFFIX a no-op. Otherwise, generate an error. */
} /* extern "C" */
#endif
#endif /* End of pcre2.h */
#endif /* PCRE2_H_IDEMPOTENT_GUARD */
/* End of pcre2.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) 2016 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -505,7 +505,7 @@ Arguments:
utf TRUE in UTF mode
cb compile data block
base_list the data list of the base opcode
base_end the end of the data list
base_end the end of the base opcode
rec_limit points to recursion depth counter
Returns: TRUE if the auto-possessification is possible
@ -558,54 +558,82 @@ for(;;)
continue;
}
/* At the end of a branch, skip to the end of the group. */
if (c == OP_ALT)
{
do code += GET(code, 1); while (*code == OP_ALT);
c = *code;
}
/* Inspect the next opcode. */
switch(c)
{
case OP_END:
case OP_KETRPOS:
/* TRUE only in greedy case. The non-greedy case could be replaced by
an OP_EXACT, but it is probably not worth it. (And note that OP_EXACT
uses more memory, which we cannot get at this stage.) */
/* We can always possessify a greedy iterator at the end of the pattern,
which is reached after skipping over the final OP_KET. A non-greedy
iterator must never be possessified. */
case OP_END:
return base_list[1] != 0;
/* When an iterator is at the end of certain kinds of group we can inspect
what follows the group by skipping over the closing ket. Note that this
does not apply to OP_KETRMAX or OP_KETRMIN because what follows any given
iteration is variable (could be another iteration or could be the next
item). As these two opcodes are not listed in the next switch, they will
end up as the next code to inspect, and return FALSE by virtue of being
unsupported. */
case OP_KET:
/* If the bracket is capturing, and referenced by an OP_RECURSE, or
it is an atomic sub-pattern (assert, once, etc.) the non-greedy case
cannot be converted to a possessive form. */
case OP_KETRPOS:
/* The non-greedy case cannot be converted to a possessive form. */
if (base_list[1] == 0) return FALSE;
/* If the bracket is capturing it might be referenced by an OP_RECURSE
so its last iterator can never be possessified if the pattern contains
recursions. (This could be improved by keeping a list of group numbers that
are called by recursion.) */
switch(*(code - GET(code, 1)))
{
case OP_CBRA:
case OP_SCBRA:
case OP_CBRAPOS:
case OP_SCBRAPOS:
if (cb->had_recurse) return FALSE;
break;
/* Atomic sub-patterns and assertions can always auto-possessify their
last iterator. However, if the group was entered as a result of checking
a previous iterator, this is not possible. */
case OP_ASSERT:
case OP_ASSERT_NOT:
case OP_ASSERTBACK:
case OP_ASSERTBACK_NOT:
case OP_ONCE:
case OP_ONCE_NC:
/* Atomic sub-patterns and assertions can always auto-possessify their
last iterator. However, if the group was entered as a result of checking
a previous iterator, this is not possible. */
return !entered_a_group;
}
/* Skip over the bracket and inspect what comes next. */
code += PRIV(OP_lengths)[c];
continue;
/* Handle cases where the next item is a group. */
case OP_ONCE:
case OP_ONCE_NC:
case OP_BRA:
case OP_CBRA:
next_code = code + GET(code, 1);
code += PRIV(OP_lengths)[c];
/* Check each branch. We have to recurse a level for all but the last
branch. */
while (*next_code == OP_ALT)
{
if (!compare_opcodes(code, utf, cb, base_list, base_end, rec_limit))
@ -621,8 +649,8 @@ for(;;)
case OP_BRAMINZERO:
next_code = code + 1;
if (*next_code != OP_BRA && *next_code != OP_CBRA
&& *next_code != OP_ONCE && *next_code != OP_ONCE_NC) return FALSE;
if (*next_code != OP_BRA && *next_code != OP_CBRA &&
*next_code != OP_ONCE) return FALSE;
do next_code += GET(next_code, 1); while (*next_code == OP_ALT);
@ -635,11 +663,15 @@ for(;;)
code += PRIV(OP_lengths)[c];
continue;
/* The next opcode does not need special handling; fall through and use it
to see if the base can be possessified. */
default:
break;
}
/* Check for a supported opcode, and load its properties. */
/* We now have the next appropriate opcode to compare with the base. Check
for a supported opcode, and load its properties. */
code = get_chr_property_list(code, utf, cb->fcc, list);
if (code == NULL) return FALSE; /* Unsupported */
@ -698,7 +730,7 @@ for(;;)
if ((*xclass_flags & XCL_MAP) == 0)
{
/* No bits are set for characters < 256. */
if (list[1] == 0) return TRUE;
if (list[1] == 0) return (*xclass_flags & XCL_NOT) == 0;
/* Might be an empty repeat. */
continue;
}
@ -1046,8 +1078,10 @@ but some compilers complain about an unreachable statement. */
/* Replaces single character iterations with their possessive alternatives
if appropriate. This function modifies the compiled opcode! Hitting a
non-existant opcode may indicate a bug in PCRE2, but it can also be caused if a
bad UTF string was compiled with PCRE2_NO_UTF_CHECK.
non-existent opcode may indicate a bug in PCRE2, but it can also be caused if a
bad UTF string was compiled with PCRE2_NO_UTF_CHECK. The rec_limit catches
overly complicated or large patterns. In these cases, the check just stops,
leaving the remainder of the pattern unpossessified.
Arguments:
code points to start of the byte code
@ -1061,17 +1095,17 @@ Returns: 0 for success
int
PRIV(auto_possessify)(PCRE2_UCHAR *code, BOOL utf, const compile_block *cb)
{
register PCRE2_UCHAR c;
PCRE2_UCHAR c;
PCRE2_SPTR end;
PCRE2_UCHAR *repeat_opcode;
uint32_t list[8];
int rec_limit;
int rec_limit = 1000; /* Was 10,000 but clang+ASAN uses a lot of stack. */
for (;;)
{
c = *code;
if (c > OP_TABLE_LENGTH) return -1; /* Something gone wrong */
if (c >= OP_TABLE_LENGTH) return -1; /* Something gone wrong */
if (c >= OP_STAR && c <= OP_TYPEPOSUPTO)
{
@ -1080,7 +1114,6 @@ for (;;)
get_chr_property_list(code, utf, cb->fcc, list) : NULL;
list[1] = c == OP_STAR || c == OP_PLUS || c == OP_QUERY || c == OP_UPTO;
rec_limit = 1000;
if (end != NULL && compare_opcodes(end, utf, cb, list, end, &rec_limit))
{
switch(c)
@ -1137,7 +1170,6 @@ for (;;)
list[1] = (c & 1) == 0;
rec_limit = 1000;
if (compare_opcodes(end, utf, cb, list, end, &rec_limit))
{
switch (c)
@ -1203,6 +1235,7 @@ for (;;)
#endif
case OP_MARK:
case OP_COMMIT_ARG:
case OP_PRUNE_ARG:
case OP_SKIP_ARG:
case OP_THEN_ARG:

View file

@ -2,23 +2,24 @@
* Perl-Compatible Regular Expressions *
*************************************************/
/* This file contains character tables that are used when no external tables
are passed to PCRE2 by the application that calls it. The tables are used only
for characters whose code values are less than 256.
/* This file was automatically written by the dftables auxiliary
program. It contains character tables that are used when no external
tables are passed to PCRE2 by the application that calls it. The tables
are used only for characters whose code values are less than 256. */
This is a default version of the tables that assumes ASCII encoding. A program
called dftables (which is distributed with PCRE2) can be used to build
alternative versions of this file. This is necessary if you are running in an
EBCDIC environment, or if you want to default to a different encoding, for
example ISO-8859-1. When dftables is run, it creates these tables in the
current locale. If PCRE2 is configured with --enable-rebuild-chartables, this
happens automatically.
/*The dftables program (which is distributed with PCRE2) can be used to
build alternative versions of this file. This is necessary if you are
running in an EBCDIC environment, or if you want to default to a different
encoding, for example ISO-8859-1. When dftables is run, it creates these
tables in the current locale. This happens automatically if PCRE2 is
configured with --enable-rebuild-chartables. */
The following #includes are present because without them gcc 4.x may remove the
array definition from the final binary if PCRE2 is built into a static library
and dead code stripping is activated. This leads to link errors. Pulling in the
header ensures that the array gets flagged as "someone outside this compilation
unit might reference this" and so it will always be supplied to the linker. */
/* The following #include is present because without it gcc 4.x may remove
the array definition from the final binary if PCRE2 is built into a static
library and dead code stripping is activated. This leads to link errors.
Pulling in the header ensures that the array gets flagged as "someone
outside this compilation unit might reference this" and so it will always
be supplied to the linker. */
#ifdef HAVE_CONFIG_H
#include "config.h"
@ -101,7 +102,7 @@ const uint8_t PRIV(default_tables)[] = {
/* This table contains bit maps for various character classes. Each map is 32
bytes long and the bits run from the least significant end of each byte. The
classes that have their own maps are: space, xdigit, digit, upper, lower, word,
graph, print, punct, and cntrl. Other classes are built from combinations. */
graph print, punct, and cntrl. Other classes are built from combinations. */
0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
@ -159,25 +160,24 @@ graph, print, punct, and cntrl. Other classes are built from combinations. */
0x04 decimal digit
0x08 hexadecimal digit
0x10 alphanumeric or '_'
0x80 regular expression metacharacter or binary zero
*/
0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */
0x00,0x01,0x01,0x01,0x01,0x01,0x00,0x00, /* 8- 15 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */
0x01,0x00,0x00,0x00,0x80,0x00,0x00,0x00, /* - ' */
0x80,0x80,0x80,0x80,0x00,0x00,0x80,0x00, /* ( - / */
0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - ' */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ( - / */
0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */
0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x80, /* 8 - ? */
0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x00, /* 8 - ? */
0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* @ - G */
0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* H - O */
0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* P - W */
0x12,0x12,0x12,0x80,0x80,0x00,0x80,0x10, /* X - _ */
0x12,0x12,0x12,0x00,0x00,0x00,0x00,0x10, /* X - _ */
0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* ` - g */
0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* h - o */
0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* p - w */
0x12,0x12,0x12,0x80,0x80,0x00,0x00,0x00, /* x -127 */
0x12,0x12,0x12,0x00,0x00,0x00,0x00,0x00, /* x -127 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */

File diff suppressed because it is too large Load diff

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) 2016 University of Cambridge
New API code Copyright (c) 2016-2017 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -84,13 +84,16 @@ if (where == NULL) /* Requests a length */
return PCRE2_ERROR_BADOPTION;
case PCRE2_CONFIG_BSR:
case PCRE2_CONFIG_COMPILED_WIDTHS:
case PCRE2_CONFIG_DEPTHLIMIT:
case PCRE2_CONFIG_HEAPLIMIT:
case PCRE2_CONFIG_JIT:
case PCRE2_CONFIG_LINKSIZE:
case PCRE2_CONFIG_MATCHLIMIT:
case PCRE2_CONFIG_NEVER_BACKSLASH_C:
case PCRE2_CONFIG_NEWLINE:
case PCRE2_CONFIG_PARENSLIMIT:
case PCRE2_CONFIG_RECURSIONLIMIT:
case PCRE2_CONFIG_STACKRECURSE:
case PCRE2_CONFIG_STACKRECURSE: /* Obsolete */
case PCRE2_CONFIG_UNICODE:
return sizeof(uint32_t);
@ -116,6 +119,28 @@ switch (what)
#endif
break;
case PCRE2_CONFIG_COMPILED_WIDTHS:
*((uint32_t *)where) = 0
#ifdef SUPPORT_PCRE2_8
+ 1
#endif
#ifdef SUPPORT_PCRE2_16
+ 2
#endif
#ifdef SUPPORT_PCRE2_32
+ 4
#endif
;
break;
case PCRE2_CONFIG_DEPTHLIMIT:
*((uint32_t *)where) = MATCH_LIMIT_DEPTH;
break;
case PCRE2_CONFIG_HEAPLIMIT:
*((uint32_t *)where) = HEAP_LIMIT;
break;
case PCRE2_CONFIG_JIT:
#ifdef SUPPORT_JIT
*((uint32_t *)where) = 1;
@ -147,20 +172,23 @@ switch (what)
*((uint32_t *)where) = NEWLINE_DEFAULT;
break;
case PCRE2_CONFIG_NEVER_BACKSLASH_C:
#ifdef NEVER_BACKSLASH_C
*((uint32_t *)where) = 1;
#else
*((uint32_t *)where) = 0;
#endif
break;
case PCRE2_CONFIG_PARENSLIMIT:
*((uint32_t *)where) = PARENS_NEST_LIMIT;
break;
case PCRE2_CONFIG_RECURSIONLIMIT:
*((uint32_t *)where) = MATCH_LIMIT_RECURSION;
break;
/* This is now obsolete. The stack is no longer used via recursion for
handling backtracking in pcre2_match(). */
case PCRE2_CONFIG_STACKRECURSE:
#ifdef HEAP_MATCH_RECURSE
*((uint32_t *)where) = 0;
#else
*((uint32_t *)where) = 1;
#endif
break;
case PCRE2_CONFIG_UNICODE_VERSION:

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) 2016 University of Cambridge
New API code Copyright (c) 2016-2017 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -138,7 +138,8 @@ const pcre2_compile_context PRIV(default_compile_context) = {
PCRE2_UNSET, /* Max pattern length */
BSR_DEFAULT, /* Backslash R default */
NEWLINE_DEFAULT, /* Newline convention */
PARENS_NEST_LIMIT }; /* As it says */
PARENS_NEST_LIMIT, /* As it says */
0 }; /* Extra options */
/* The create function copies the default into the new memory, but must
override the default memory handling functions if a gcontext was provided. */
@ -161,9 +162,6 @@ when no context is supplied to a match function. */
const pcre2_match_context PRIV(default_match_context) = {
{ default_malloc, default_free, NULL },
#ifdef HEAP_MATCH_RECURSE
{ default_malloc, default_free, NULL },
#endif
#ifdef SUPPORT_JIT
NULL,
NULL,
@ -171,8 +169,9 @@ const pcre2_match_context PRIV(default_match_context) = {
NULL,
NULL,
PCRE2_UNSET, /* Offset limit */
HEAP_LIMIT,
MATCH_LIMIT,
MATCH_LIMIT_RECURSION };
MATCH_LIMIT_DEPTH };
/* The create function copies the default into the new memory, but must
override the default memory handling functions if a gcontext was provided. */
@ -190,6 +189,36 @@ return mcontext;
}
/* A default convert context is set up to save having to initialize at run time
when no context is supplied to the convert function. */
const pcre2_convert_context PRIV(default_convert_context) = {
{ default_malloc, default_free, NULL }, /* Default memory handling */
#ifdef _WIN32
CHAR_BACKSLASH, /* Default path separator */
CHAR_GRAVE_ACCENT /* Default escape character */
#else /* Not Windows */
CHAR_SLASH, /* Default path separator */
CHAR_BACKSLASH /* Default escape character */
#endif
};
/* The create function copies the default into the new memory, but must
override the default memory handling functions if a gcontext was provided. */
PCRE2_EXP_DEFN pcre2_convert_context * PCRE2_CALL_CONVENTION
pcre2_convert_context_create(pcre2_general_context *gcontext)
{
pcre2_convert_context *ccontext = PRIV(memctl_malloc)(
sizeof(pcre2_real_convert_context), (pcre2_memctl *)gcontext);
if (ccontext == NULL) return NULL;
*ccontext = PRIV(default_convert_context);
if (gcontext != NULL)
*((pcre2_memctl *)ccontext) = *((pcre2_memctl *)gcontext);
return ccontext;
}
/*************************************************
* Context copy functions *
*************************************************/
@ -231,11 +260,22 @@ return new;
PCRE2_EXP_DEFN pcre2_convert_context * PCRE2_CALL_CONVENTION
pcre2_convert_context_copy(pcre2_convert_context *ccontext)
{
pcre2_convert_context *new =
ccontext->memctl.malloc(sizeof(pcre2_real_convert_context),
ccontext->memctl.memory_data);
if (new == NULL) return NULL;
memcpy(new, ccontext, sizeof(pcre2_real_convert_context));
return new;
}
/*************************************************
* Context free functions *
*************************************************/
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_general_context_free(pcre2_general_context *gcontext)
{
@ -260,6 +300,12 @@ if (mcontext != NULL)
}
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_convert_context_free(pcre2_convert_context *ccontext)
{
if (ccontext != NULL)
ccontext->memctl.free(ccontext, ccontext->memctl.memory_data);
}
/*************************************************
@ -271,7 +317,7 @@ data is given. Only some of the functions are able to test the validity of the
data. */
/* ------------ Compile contexts ------------ */
/* ------------ Compile context ------------ */
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_character_tables(pcre2_compile_context *ccontext,
@ -313,6 +359,7 @@ switch(newline)
case PCRE2_NEWLINE_CRLF:
case PCRE2_NEWLINE_ANY:
case PCRE2_NEWLINE_ANYCRLF:
case PCRE2_NEWLINE_NUL:
ccontext->newline_convention = newline;
return 0;
@ -328,6 +375,13 @@ ccontext->parens_nest_limit = limit;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_compile_extra_options(pcre2_compile_context *ccontext, uint32_t options)
{
ccontext->extra_options = options;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_compile_recursion_guard(pcre2_compile_context *ccontext,
int (*guard)(uint32_t, void *), void *user_data)
@ -338,7 +392,7 @@ return 0;
}
/* ------------ Match contexts ------------ */
/* ------------ Match context ------------ */
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_callout(pcre2_match_context *mcontext,
@ -349,6 +403,13 @@ mcontext->callout_data = callout_data;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_heap_limit(pcre2_match_context *mcontext, uint32_t limit)
{
mcontext->heap_limit = limit;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_match_limit(pcre2_match_context *mcontext, uint32_t limit)
{
@ -356,6 +417,13 @@ mcontext->match_limit = limit;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_depth_limit(pcre2_match_context *mcontext, uint32_t limit)
{
mcontext->depth_limit = limit;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_offset_limit(pcre2_match_context *mcontext, PCRE2_SIZE limit)
{
@ -363,11 +431,13 @@ mcontext->offset_limit = limit;
return 0;
}
/* This function became obsolete at release 10.30. It is kept as a synonym for
backwards compatibility. */
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_recursion_limit(pcre2_match_context *mcontext, uint32_t limit)
{
mcontext->recursion_limit = limit;
return 0;
return pcre2_set_depth_limit(mcontext, limit);
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
@ -375,17 +445,32 @@ pcre2_set_recursion_memory_management(pcre2_match_context *mcontext,
void *(*mymalloc)(size_t, void *), void (*myfree)(void *, void *),
void *mydata)
{
#ifdef HEAP_MATCH_RECURSE
mcontext->stack_memctl.malloc = mymalloc;
mcontext->stack_memctl.free = myfree;
mcontext->stack_memctl.memory_data = mydata;
#else
(void)mcontext;
(void)mymalloc;
(void)myfree;
(void)mydata;
#endif
return 0;
}
/* ------------ Convert context ------------ */
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_glob_separator(pcre2_convert_context *ccontext, uint32_t separator)
{
if (separator != CHAR_SLASH && separator != CHAR_BACKSLASH &&
separator != CHAR_DOT) return PCRE2_ERROR_BADDATA;
ccontext->glob_separator = separator;
return 0;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_glob_escape(pcre2_convert_context *ccontext, uint32_t escape)
{
if (escape > 255 || (escape != 0 && !ispunct(escape)))
return PCRE2_ERROR_BADDATA;
ccontext->glob_escape = escape;
return 0;
}
/* End of pcre2_context.c */

File diff suppressed because it is too large Load diff

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) 2016 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -91,13 +91,13 @@ static const unsigned char compile_error_texts[] =
"failed to allocate heap memory\0"
"unmatched closing parenthesis\0"
"internal error: code overflow\0"
"letter or underscore expected after (?< or (?'\0"
"missing closing parenthesis for condition\0"
/* 25 */
"lookbehind assertion is not fixed length\0"
"malformed number or name after (?(\0"
"a relative value of zero is not allowed\0"
"conditional group contains more than two branches\0"
"assertion expected after (?( or (?(?C)\0"
"(?R or (?[+-]digits must be followed by )\0"
"digit expected after (?+ or (?-\0"
/* 30 */
"unknown POSIX class name\0"
"internal error in pcre2_study(): should not occur\0"
@ -105,9 +105,9 @@ static const unsigned char compile_error_texts[] =
"parentheses are too deeply nested (stack check)\0"
"character code point value in \\x{} or \\o{} is too large\0"
/* 35 */
"invalid condition (?(0)\0"
"lookbehind is too complicated\0"
"\\C is not allowed in a lookbehind assertion in UTF-" XSTRING(PCRE2_CODE_UNIT_WIDTH) " mode\0"
"PCRE does not support \\L, \\l, \\N{name}, \\U, or \\u\0"
"PCRE2 does not support \\F, \\L, \\l, \\N{name}, \\U, or \\u\0"
"number after (?C is greater than 255\0"
"closing parenthesis for (?C expected\0"
/* 40 */
@ -132,13 +132,14 @@ static const unsigned char compile_error_texts[] =
"missing opening brace after \\o\0"
"internal error: unknown newline setting\0"
"\\g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number\0"
"a numbered reference must not be zero\0"
"an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)\0"
"(?R (recursive pattern call) must be followed by a closing parenthesis\0"
/* "an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)\0" */
"obsolete error (should not occur)\0" /* Was the above */
/* 60 */
"(*VERB) not recognized or malformed\0"
"number is too big\0"
"group number is too big\0"
"subpattern name expected\0"
"digit expected after (?+\0"
"internal error: parsed pattern overflow\0"
"non-octal character in \\o{} (closing brace missing?)\0"
/* 65 */
"different names for subpatterns of the same number are not allowed\0"
@ -151,17 +152,17 @@ static const unsigned char compile_error_texts[] =
#endif
"\\k is not followed by a braced, angle-bracketed, or quoted name\0"
/* 70 */
"internal error: unknown opcode in find_fixedlength()\0"
"internal error: unknown meta code in check_lookbehinds()\0"
"\\N is not supported in a class\0"
"SPARE ERROR\0"
"callout string is too long\0"
"disallowed Unicode code point (>= 0xd800 && <= 0xdfff)\0"
"using UTF is disabled by the application\0"
/* 75 */
"using UCP is disabled by the application\0"
"name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)\0"
"character code point value in \\u.... sequence is too large\0"
"digits missing in \\x{} or \\o{}\0"
"syntax error in (?(VERSION condition\0"
"digits missing in \\x{} or \\o{} or \\N{U+}\0"
"syntax error or number too big in (?(VERSION condition\0"
/* 80 */
"internal error: unknown opcode in auto_possessify()\0"
"missing terminating delimiter for callout with string argument\0"
@ -173,6 +174,13 @@ static const unsigned char compile_error_texts[] =
"regular expression is too complicated\0"
"lookbehind assertion is too long\0"
"pattern string is longer than the limit set by the application\0"
"internal error: unknown code in parsed pattern\0"
/* 90 */
"internal error: bad code value in parsed_skip()\0"
"PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES is not allowed in UTF-16 mode\0"
"invalid option bits with PCRE2_LITERAL\0"
"\\N{U+dddd} is supported only in Unicode (UTF) mode\0"
"invalid hyphen in option setting\0"
;
/* Match-time and UTF error texts are in the same format. */
@ -241,7 +249,7 @@ static const unsigned char match_error_texts[] =
"non-unique substring name\0"
"NULL argument passed\0"
"nested recursion at the same subject position\0"
"recursion limit exceeded\0"
"matching depth limit exceeded\0"
"requested value is not available\0"
/* 55 */
"requested value is not set\0"
@ -250,9 +258,13 @@ static const unsigned char match_error_texts[] =
"expected closing curly bracket in replacement string\0"
"bad substitution in replacement string\0"
/* 60 */
"match with end before start is not supported\0"
"match with end before start or start moved backwards is not supported\0"
"too many replacements (more than INT_MAX)\0"
"bad serialized data\0"
"heap limit exceeded\0"
"invalid syntax\0"
/* 65 */
"internal error - duplicate substitution match\0"
;
@ -268,17 +280,17 @@ distinct.
Arguments:
enumber error number
buffer where to put the message (zero terminated)
size size of the buffer
size size of the buffer in code units
Returns: length of message if all is well
negative on error
*/
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_get_error_message(int enumber, PCRE2_UCHAR *buffer, size_t size)
pcre2_get_error_message(int enumber, PCRE2_UCHAR *buffer, PCRE2_SIZE size)
{
const unsigned char *message;
size_t i;
PCRE2_SIZE i;
int n;
if (size == 0) return PCRE2_ERROR_NOMEMORY;
@ -301,8 +313,8 @@ else /* Invalid error number */
for (; n > 0; n--)
{
while (*message++ != CHAR_NULL) {};
if (*message == CHAR_NULL) return PCRE2_ERROR_BADDATA;
while (*message++ != CHAR_NUL) {};
if (*message == CHAR_NUL) return PCRE2_ERROR_BADDATA;
}
for (i = 0; *message != 0; i++)

View file

@ -0,0 +1,148 @@
/*************************************************
* 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) 2016-2018 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 an internal function that is used to match a Unicode
extended grapheme sequence. It is used by both pcre2_match() and
pcre2_def_match(). However, it is called only when Unicode support is being
compiled. Nevertheless, we provide a dummy function when there is no Unicode
support, because some compilers do not like functionless source files. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/* Dummy function */
#ifndef SUPPORT_UNICODE
PCRE2_SPTR
PRIV(extuni)(uint32_t c, PCRE2_SPTR eptr, PCRE2_SPTR start_subject,
PCRE2_SPTR end_subject, BOOL utf, int *xcount)
{
(void)c;
(void)eptr;
(void)start_subject;
(void)end_subject;
(void)utf;
(void)xcount;
return NULL;
}
#else
/*************************************************
* Match an extended grapheme sequence *
*************************************************/
/*
Arguments:
c the first character
eptr pointer to next character
start_subject pointer to start of subject
end_subject pointer to end of subject
utf TRUE if in UTF mode
xcount pointer to count of additional characters,
or NULL if count not needed
Returns: pointer after the end of the sequence
*/
PCRE2_SPTR
PRIV(extuni)(uint32_t c, PCRE2_SPTR eptr, PCRE2_SPTR start_subject,
PCRE2_SPTR end_subject, BOOL utf, int *xcount)
{
int lgb = UCD_GRAPHBREAK(c);
while (eptr < end_subject)
{
int rgb;
int len = 1;
if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); }
rgb = UCD_GRAPHBREAK(c);
if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break;
/* Not breaking between Regional Indicators is allowed only if there
are an even number of preceding RIs. */
if (lgb == ucp_gbRegionalIndicator && rgb == ucp_gbRegionalIndicator)
{
int ricount = 0;
PCRE2_SPTR bptr = eptr - 1;
if (utf) BACKCHAR(bptr);
/* bptr is pointing to the left-hand character */
while (bptr > start_subject)
{
bptr--;
if (utf)
{
BACKCHAR(bptr);
GETCHAR(c, bptr);
}
else
c = *bptr;
if (UCD_GRAPHBREAK(c) != ucp_gbRegionalIndicator) break;
ricount++;
}
if ((ricount & 1) != 0) break; /* Grapheme break required */
}
/* If Extend or ZWJ follows Extended_Pictographic, do not update lgb; this
allows any number of them before a following Extended_Pictographic. */
if ((rgb != ucp_gbExtend && rgb != ucp_gbZWJ) ||
lgb != ucp_gbExtended_Pictographic)
lgb = rgb;
eptr += len;
if (xcount != NULL) *xcount += 1;
}
return eptr;
}
#endif /* SUPPORT_UNICODE */
/* End of pcre2_extuni.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) 2016 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -71,7 +71,7 @@ PRIV(find_bracket)(PCRE2_SPTR code, BOOL utf, int number)
{
for (;;)
{
register PCRE2_UCHAR c = *code;
PCRE2_UCHAR c = *code;
if (c == OP_END) return NULL;
@ -131,6 +131,7 @@ for (;;)
break;
case OP_MARK:
case OP_COMMIT_ARG:
case OP_PRUNE_ARG:
case OP_SKIP_ARG:
case OP_THEN_ARG:

View file

@ -0,0 +1,365 @@
/***************************************************************************
Fuzzer driver for PCRE2. Given an arbitrary string of bytes and a length, it
tries to compile and match it, deriving options from the string itself. If
STANDALONE is defined, a main program that calls the driver with the contents
of specified files is compiled, and commentary on what is happening is output.
If an argument starts with '=' the rest of it it is taken as a literal string
rather than a file name. This allows easy testing of short strings.
Written by Philip Hazel, October 2016
***************************************************************************/
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define PCRE2_CODE_UNIT_WIDTH 8
#include "pcre2.h"
#define MAX_MATCH_SIZE 1000
#define DFA_WORKSPACE_COUNT 100
#define ALLOWED_COMPILE_OPTIONS \
(PCRE2_ANCHORED|PCRE2_ALLOW_EMPTY_CLASS|PCRE2_ALT_BSUX|PCRE2_ALT_CIRCUMFLEX| \
PCRE2_ALT_VERBNAMES|PCRE2_AUTO_CALLOUT|PCRE2_CASELESS|PCRE2_DOLLAR_ENDONLY| \
PCRE2_DOTALL|PCRE2_DUPNAMES|PCRE2_ENDANCHORED|PCRE2_EXTENDED|PCRE2_FIRSTLINE| \
PCRE2_MATCH_UNSET_BACKREF|PCRE2_MULTILINE|PCRE2_NEVER_BACKSLASH_C| \
PCRE2_NO_AUTO_CAPTURE| \
PCRE2_NO_AUTO_POSSESS|PCRE2_NO_DOTSTAR_ANCHOR|PCRE2_NO_START_OPTIMIZE| \
PCRE2_UCP|PCRE2_UNGREEDY|PCRE2_USE_OFFSET_LIMIT| \
PCRE2_UTF)
#define ALLOWED_MATCH_OPTIONS \
(PCRE2_ANCHORED|PCRE2_ENDANCHORED|PCRE2_NOTBOL|PCRE2_NOTEOL|PCRE2_NOTEMPTY| \
PCRE2_NOTEMPTY_ATSTART|PCRE2_PARTIAL_HARD| \
PCRE2_PARTIAL_SOFT|PCRE2_NO_JIT)
/* This is the callout function. Its only purpose is to halt matching if there
are more than 100 callouts, as one way of stopping too much time being spent on
fruitless matches. The callout data is a pointer to the counter. */
static int callout_function(pcre2_callout_block *cb, void *callout_data)
{
(void)cb; /* Avoid unused parameter warning */
*((uint32_t *)callout_data) += 1;
return (*((uint32_t *)callout_data) > 100)? PCRE2_ERROR_CALLOUT : 0;
}
/* Putting in this apparently unnecessary prototype prevents gcc from giving a
"no previous prototype" warning when compiling at high warning level. */
int LLVMFuzzerTestOneInput(const unsigned char *, size_t);
/* Here's the driving function. */
int LLVMFuzzerTestOneInput(const unsigned char *data, size_t size)
{
uint32_t compile_options;
uint32_t match_options;
pcre2_match_data *match_data = NULL;
pcre2_match_context *match_context = NULL;
size_t match_size;
int dfa_workspace[DFA_WORKSPACE_COUNT];
int r1, r2;
int i;
if (size < 1) return 0;
/* Limiting the length of the subject for matching stops fruitless searches
in large trees taking too much time. */
match_size = (size > MAX_MATCH_SIZE)? MAX_MATCH_SIZE : size;
/* Figure out some options to use. Initialize the random number to ensure
repeatability. Ensure that we get a 32-bit unsigned random number for testing
options. (RAND_MAX is required to be at least 32767, but is commonly
2147483647, which excludes the top bit.) */
srand((unsigned int)(data[size/2]));
r1 = rand();
r2 = rand();
/* Ensure that all undefined option bits are zero (waste of time trying them)
and also that PCRE2_NO_UTF_CHECK is unset, as there is no guarantee that the
input is UTF-8. Also unset PCRE2_NEVER_UTF and PCRE2_NEVER_UCP as there is no
reason to disallow UTF and UCP. Force PCRE2_NEVER_BACKSLASH_C to be set because
\C in random patterns is highly likely to cause a crash. */
compile_options =
((((uint32_t)r1 << 16) | ((uint32_t)r2 & 0xffff)) & ALLOWED_COMPILE_OPTIONS) |
PCRE2_NEVER_BACKSLASH_C;
match_options =
((((uint32_t)r1 << 16) | ((uint32_t)r2 & 0xffff)) & ALLOWED_MATCH_OPTIONS);
/* Discard partial matching if PCRE2_ENDANCHORED is set, because they are not
allowed together and just give an immediate error return. */
if (((compile_options|match_options) & PCRE2_ENDANCHORED) != 0)
match_options &= ~(PCRE2_PARTIAL_HARD|PCRE2_PARTIAL_SOFT);
/* Do the compile with and without the options, and after a successful compile,
likewise do the match with and without the options. */
for (i = 0; i < 2; i++)
{
uint32_t callout_count;
int errorcode;
PCRE2_SIZE erroroffset;
pcre2_code *code;
#ifdef STANDALONE
printf("Compile options %.8x never_backslash_c", compile_options);
printf("%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n",
((compile_options & PCRE2_ALT_BSUX) != 0)? ",alt_bsux" : "",
((compile_options & PCRE2_ALT_CIRCUMFLEX) != 0)? ",alt_circumflex" : "",
((compile_options & PCRE2_ALT_VERBNAMES) != 0)? ",alt_verbnames" : "",
((compile_options & PCRE2_ALLOW_EMPTY_CLASS) != 0)? ",allow_empty_class" : "",
((compile_options & PCRE2_ANCHORED) != 0)? ",anchored" : "",
((compile_options & PCRE2_AUTO_CALLOUT) != 0)? ",auto_callout" : "",
((compile_options & PCRE2_CASELESS) != 0)? ",caseless" : "",
((compile_options & PCRE2_DOLLAR_ENDONLY) != 0)? ",dollar_endonly" : "",
((compile_options & PCRE2_DOTALL) != 0)? ",dotall" : "",
((compile_options & PCRE2_DUPNAMES) != 0)? ",dupnames" : "",
((compile_options & PCRE2_ENDANCHORED) != 0)? ",endanchored" : "",
((compile_options & PCRE2_EXTENDED) != 0)? ",extended" : "",
((compile_options & PCRE2_FIRSTLINE) != 0)? ",firstline" : "",
((compile_options & PCRE2_MATCH_UNSET_BACKREF) != 0)? ",match_unset_backref" : "",
((compile_options & PCRE2_MULTILINE) != 0)? ",multiline" : "",
((compile_options & PCRE2_NEVER_UCP) != 0)? ",never_ucp" : "",
((compile_options & PCRE2_NEVER_UTF) != 0)? ",never_utf" : "",
((compile_options & PCRE2_NO_AUTO_CAPTURE) != 0)? ",no_auto_capture" : "",
((compile_options & PCRE2_NO_AUTO_POSSESS) != 0)? ",no_auto_possess" : "",
((compile_options & PCRE2_NO_DOTSTAR_ANCHOR) != 0)? ",no_dotstar_anchor" : "",
((compile_options & PCRE2_NO_UTF_CHECK) != 0)? ",no_utf_check" : "",
((compile_options & PCRE2_NO_START_OPTIMIZE) != 0)? ",no_start_optimize" : "",
((compile_options & PCRE2_UCP) != 0)? ",ucp" : "",
((compile_options & PCRE2_UNGREEDY) != 0)? ",ungreedy" : "",
((compile_options & PCRE2_USE_OFFSET_LIMIT) != 0)? ",use_offset_limit" : "",
((compile_options & PCRE2_UTF) != 0)? ",utf" : "");
#endif
code = pcre2_compile((PCRE2_SPTR)data, (PCRE2_SIZE)size, compile_options,
&errorcode, &erroroffset, NULL);
/* Compilation succeeded */
if (code != NULL)
{
int j;
uint32_t save_match_options = match_options;
/* Create match data and context blocks only when we first need them. Set
low match and depth limits to avoid wasting too much searching large
pattern trees. Almost all matches are going to fail. */
if (match_data == NULL)
{
match_data = pcre2_match_data_create(32, NULL);
if (match_data == NULL)
{
#ifdef STANDALONE
printf("** Failed to create match data block\n");
#endif
return 0;
}
}
if (match_context == NULL)
{
match_context = pcre2_match_context_create(NULL);
if (match_context == NULL)
{
#ifdef STANDALONE
printf("** Failed to create match context block\n");
#endif
return 0;
}
(void)pcre2_set_match_limit(match_context, 100);
(void)pcre2_set_depth_limit(match_context, 100);
(void)pcre2_set_callout(match_context, callout_function, &callout_count);
}
/* Match twice, with and without options. */
for (j = 0; j < 2; j++)
{
#ifdef STANDALONE
printf("Match options %.8x", match_options);
printf("%s%s%s%s%s%s%s%s%s%s\n",
((match_options & PCRE2_ANCHORED) != 0)? ",anchored" : "",
((match_options & PCRE2_ENDANCHORED) != 0)? ",endanchored" : "",
((match_options & PCRE2_NO_JIT) != 0)? ",no_jit" : "",
((match_options & PCRE2_NO_UTF_CHECK) != 0)? ",no_utf_check" : "",
((match_options & PCRE2_NOTBOL) != 0)? ",notbol" : "",
((match_options & PCRE2_NOTEMPTY) != 0)? ",notempty" : "",
((match_options & PCRE2_NOTEMPTY_ATSTART) != 0)? ",notempty_atstart" : "",
((match_options & PCRE2_NOTEOL) != 0)? ",noteol" : "",
((match_options & PCRE2_PARTIAL_HARD) != 0)? ",partial_hard" : "",
((match_options & PCRE2_PARTIAL_SOFT) != 0)? ",partial_soft" : "");
#endif
callout_count = 0;
errorcode = pcre2_match(code, (PCRE2_SPTR)data, (PCRE2_SIZE)match_size, 0,
match_options, match_data, match_context);
#ifdef STANDALONE
if (errorcode >= 0) printf("Match returned %d\n", errorcode); else
{
unsigned char buffer[256];
pcre2_get_error_message(errorcode, buffer, 256);
printf("Match failed: error %d: %s\n", errorcode, buffer);
}
#endif
match_options = 0; /* For second time */
}
/* Match with DFA twice, with and without options. */
match_options = save_match_options & ~PCRE2_NO_JIT; /* Not valid for DFA */
for (j = 0; j < 2; j++)
{
#ifdef STANDALONE
printf("DFA match options %.8x", match_options);
printf("%s%s%s%s%s%s%s%s%s\n",
((match_options & PCRE2_ANCHORED) != 0)? ",anchored" : "",
((match_options & PCRE2_ENDANCHORED) != 0)? ",endanchored" : "",
((match_options & PCRE2_NO_UTF_CHECK) != 0)? ",no_utf_check" : "",
((match_options & PCRE2_NOTBOL) != 0)? ",notbol" : "",
((match_options & PCRE2_NOTEMPTY) != 0)? ",notempty" : "",
((match_options & PCRE2_NOTEMPTY_ATSTART) != 0)? ",notempty_atstart" : "",
((match_options & PCRE2_NOTEOL) != 0)? ",noteol" : "",
((match_options & PCRE2_PARTIAL_HARD) != 0)? ",partial_hard" : "",
((match_options & PCRE2_PARTIAL_SOFT) != 0)? ",partial_soft" : "");
#endif
callout_count = 0;
errorcode = pcre2_dfa_match(code, (PCRE2_SPTR)data,
(PCRE2_SIZE)match_size, 0, match_options, match_data, match_context,
dfa_workspace, DFA_WORKSPACE_COUNT);
#ifdef STANDALONE
if (errorcode >= 0) printf("Match returned %d\n", errorcode); else
{
unsigned char buffer[256];
pcre2_get_error_message(errorcode, buffer, 256);
printf("Match failed: error %d: %s\n", errorcode, buffer);
}
#endif
match_options = 0; /* For second time */
}
match_options = save_match_options; /* Reset for the second compile */
pcre2_code_free(code);
}
/* Compilation failed */
else
{
unsigned char buffer[256];
pcre2_get_error_message(errorcode, buffer, 256);
#ifdef STANDALONE
printf("Error %d at offset %lu: %s\n", errorcode, erroroffset, buffer);
#else
if (strstr((const char *)buffer, "internal error") != NULL) abort();
#endif
}
compile_options = PCRE2_NEVER_BACKSLASH_C; /* For second time */
}
if (match_data != NULL) pcre2_match_data_free(match_data);
if (match_context != NULL) pcre2_match_context_free(match_context);
return 0;
}
/* Optional main program. */
#ifdef STANDALONE
int main(int argc, char **argv)
{
int i;
if (argc < 2)
{
printf("** No arguments given\n");
return 0;
}
for (i = 1; i < argc; i++)
{
size_t filelen;
size_t readsize;
unsigned char *buffer;
FILE *f;
/* Handle a literal string. Copy to an exact size buffer so that checks for
overrunning work. */
if (argv[i][0] == '=')
{
readsize = strlen(argv[i]) - 1;
printf("------ <Literal> ------\n");
printf("Length = %lu\n", readsize);
printf("%.*s\n", (int)readsize, argv[i]+1);
buffer = (unsigned char *)malloc(readsize);
if (buffer == NULL)
printf("** Failed to allocate %lu bytes of memory\n", readsize);
else
{
memcpy(buffer, argv[i]+1, readsize);
LLVMFuzzerTestOneInput(buffer, readsize);
free(buffer);
}
continue;
}
/* Handle a string given in a file */
f = fopen(argv[i], "rb");
if (f == NULL)
{
printf("** Failed to open %s: %s\n", argv[i], strerror(errno));
continue;
}
printf("------ %s ------\n", argv[i]);
fseek(f, 0, SEEK_END);
filelen = ftell(f);
fseek(f, 0, SEEK_SET);
buffer = (unsigned char *)malloc(filelen);
if (buffer == NULL)
{
printf("** Failed to allocate %lu bytes of memory\n", filelen);
fclose(f);
continue;
}
readsize = fread(buffer, 1, filelen, f);
fclose(f);
if (readsize != filelen)
printf("** File size is %lu but fread() returned %lu\n", filelen, readsize);
else
{
printf("Length = %lu\n", filelen);
LLVMFuzzerTestOneInput(buffer, filelen);
}
free(buffer);
}
return 0;
}
#endif /* STANDALONE */
/* End */

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) 2016 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -38,6 +38,9 @@ POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifndef PCRE2_INTERNAL_H_IDEMPOTENT_GUARD
#define PCRE2_INTERNAL_H_IDEMPOTENT_GUARD
/* We do not support both EBCDIC and Unicode at the same time. The "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
@ -142,20 +145,6 @@ pcre2_match() because of the way it backtracks. */
#define PCRE2_SPTR CUSTOM_SUBJECT_PTR
#endif
/* When compiling with the MSVC compiler, it is sometimes necessary to include
a "calling convention" before exported function names. (This is secondhand
information; I know nothing about MSVC myself). For example, something like
void __cdecl function(....)
might be needed. In order so make this easy, all the exported functions have
PCRE2_CALL_CONVENTION just before their names. It is rarely needed; if not
set, we ensure here that it has no effect. */
#ifndef PCRE2_CALL_CONVENTION
#define PCRE2_CALL_CONVENTION
#endif
/* When checking for integer overflow in pcre2_compile(), we need to handle
large integers. If a 64-bit integer type is available, we can use that.
Otherwise we have to cast to double, which of course requires floating point
@ -176,6 +165,16 @@ by "configure". */
#define INT64_OR_DOUBLE double
#endif
/* External (in the C sense) functions and tables that are private to the
libraries are always referenced using the PRIV macro. This makes it possible
for pcre2test.c to include some of the source files from the libraries using a
different PRIV definition to avoid name clashes. It also makes it clear in the
code that a non-static object is being referenced. */
#ifndef PRIV
#define PRIV(name) _pcre2_##name
#endif
/* When compiling for use with the Virtual Pascal compiler, these functions
need to have their names changed. PCRE2 must be compiled with the -DVPCOMPAT
option on the command line. */
@ -189,50 +188,15 @@ option on the command line. */
#define memset(s,c,n) _memset(s,c,n)
#else /* VPCOMPAT */
/* To cope with SunOS4 and other systems that lack memmove() but have bcopy(),
define a macro for memmove() if HAVE_MEMMOVE is false, provided that HAVE_BCOPY
is set. Otherwise, include an emulating function for those systems that have
neither (there some non-Unix environments where this is the case). */
/* Otherwise, to cope with SunOS4 and other systems that lack memmove(), define
a macro that calls an emulating function. */
#ifndef HAVE_MEMMOVE
#undef memmove /* some systems may have a macro */
#ifdef HAVE_BCOPY
#define memmove(a, b, c) bcopy(b, a, c)
#else /* HAVE_BCOPY */
static void *
pcre2_memmove(void *d, const void *s, size_t n)
{
size_t i;
unsigned char *dest = (unsigned char *)d;
const unsigned char *src = (const unsigned char *)s;
if (dest > src)
{
dest += n;
src += n;
for (i = 0; i < n; ++i) *(--dest) = *(--src);
return (void *)dest;
}
else
{
for (i = 0; i < n; ++i) *dest++ = *src++;
return (void *)(dest - n);
}
}
#define memmove(a, b, c) pcre2_memmove(a, b, c)
#endif /* not HAVE_BCOPY */
#undef memmove /* Some systems may have a macro */
#define memmove(a, b, c) PRIV(memmove)(a, b, c)
#endif /* not HAVE_MEMMOVE */
#endif /* not VPCOMPAT */
/* External (in the C sense) functions and tables that are private to the
libraries are always referenced using the PRIV macro. This makes it possible
for pcre2test.c to include some of the source files from the libraries using a
different PRIV definition to avoid name clashes. It also makes it clear in the
code that a non-static object is being referenced. */
#ifndef PRIV
#define PRIV(name) _pcre2_##name
#endif
/* This is an unsigned int value that no UTF character can ever have, as
Unicode doesn't go beyond 0x0010ffff. */
@ -254,6 +218,21 @@ not rely on this. */
#define COMPILE_ERROR_BASE 100
/* The initial frames vector for remembering backtracking points in
pcre2_match() is allocated on the system stack, of this size (bytes). The size
must be a multiple of sizeof(PCRE2_SPTR) in all environments, so making it a
multiple of 8 is best. Typical frame sizes are a few hundred bytes (it depends
on the number of capturing parentheses) so 20KiB handles quite a few frames. A
larger vector on the heap is obtained for patterns that need more frames. The
maximum size of this can be limited. */
#define START_FRAMES_SIZE 20480
/* Similarly, for DFA matching, an initial internal workspace vector is
allocated on the stack. */
#define DFA_START_RWS_SIZE 30720
/* Define the default BSR convention. */
#ifdef BSR_ANYCRLF
@ -561,9 +540,14 @@ enum { PCRE2_MATCHEDBY_INTERPRETER, /* pcre2_match() */
#define MAGIC_NUMBER 0x50435245UL /* 'PCRE' */
/* The maximum remaining length of subject we are prepared to search for a
req_unit match. */
req_unit match. In 8-bit mode, memchr() is used and is much faster than the
search loop that has to be used in 16-bit and 32-bit modes. */
#if PCRE2_CODE_UNIT_WIDTH == 8
#define REQ_CU_MAX 2000
#else
#define REQ_CU_MAX 1000
#endif
/* Offsets for the bitmap tables in the cbits set of tables. Each table
contains a set of bits for a class map. Some classes are built by combining
@ -581,14 +565,15 @@ these tables. */
#define cbit_cntrl 288 /* [:cntrl:] */
#define cbit_length 320 /* Length of the cbits table */
/* Bit definitions for entries in the ctypes table. */
/* Bit definitions for entries in the ctypes table. Do not change these values
without checking pcre2_jit_compile.c, which has an assertion to ensure that
ctype_word has the value 16. */
#define ctype_space 0x01
#define ctype_letter 0x02
#define ctype_digit 0x04
#define ctype_xdigit 0x08
#define ctype_xdigit 0x08 /* not actually used any more */
#define ctype_word 0x10 /* alphanumeric or '_' */
#define ctype_meta 0x80 /* regexp meta char or zero (end pattern) */
/* Offsets of the various tables from the base tables pointer, and
total length of the tables. */
@ -682,7 +667,7 @@ a positive value. */
/* The remaining definitions work in both environments. */
#define CHAR_NULL '\0'
#define CHAR_NUL '\0'
#define CHAR_HT '\t'
#define CHAR_VT '\v'
#define CHAR_FF '\f'
@ -923,6 +908,7 @@ a positive value. */
#define STRING_CRLF_RIGHTPAR "CRLF)"
#define STRING_ANY_RIGHTPAR "ANY)"
#define STRING_ANYCRLF_RIGHTPAR "ANYCRLF)"
#define STRING_NUL_RIGHTPAR "NUL)"
#define STRING_BSR_ANYCRLF_RIGHTPAR "BSR_ANYCRLF)"
#define STRING_BSR_UNICODE_RIGHTPAR "BSR_UNICODE)"
#define STRING_UTF8_RIGHTPAR "UTF8)"
@ -936,7 +922,9 @@ a positive value. */
#define STRING_NO_START_OPT_RIGHTPAR "NO_START_OPT)"
#define STRING_NOTEMPTY_RIGHTPAR "NOTEMPTY)"
#define STRING_NOTEMPTY_ATSTART_RIGHTPAR "NOTEMPTY_ATSTART)"
#define STRING_LIMIT_HEAP_EQ "LIMIT_HEAP="
#define STRING_LIMIT_MATCH_EQ "LIMIT_MATCH="
#define STRING_LIMIT_DEPTH_EQ "LIMIT_DEPTH="
#define STRING_LIMIT_RECURSION_EQ "LIMIT_RECURSION="
#define STRING_MARK "MARK"
@ -958,7 +946,7 @@ only. */
#define CHAR_ESC '\033'
#define CHAR_DEL '\177'
#define CHAR_NULL '\0'
#define CHAR_NUL '\0'
#define CHAR_SPACE '\040'
#define CHAR_EXCLAMATION_MARK '\041'
#define CHAR_QUOTATION_MARK '\042'
@ -1196,6 +1184,7 @@ only. */
#define STRING_CRLF_RIGHTPAR STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS
#define STRING_ANY_RIGHTPAR STR_A STR_N STR_Y STR_RIGHT_PARENTHESIS
#define STRING_ANYCRLF_RIGHTPAR STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS
#define STRING_NUL_RIGHTPAR STR_N STR_U STR_L STR_RIGHT_PARENTHESIS
#define STRING_BSR_ANYCRLF_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS
#define STRING_BSR_UNICODE_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_U STR_N STR_I STR_C STR_O STR_D STR_E STR_RIGHT_PARENTHESIS
#define STRING_UTF8_RIGHTPAR STR_U STR_T STR_F STR_8 STR_RIGHT_PARENTHESIS
@ -1209,7 +1198,9 @@ only. */
#define STRING_NO_START_OPT_RIGHTPAR STR_N STR_O STR_UNDERSCORE STR_S STR_T STR_A STR_R STR_T STR_UNDERSCORE STR_O STR_P STR_T STR_RIGHT_PARENTHESIS
#define STRING_NOTEMPTY_RIGHTPAR STR_N STR_O STR_T STR_E STR_M STR_P STR_T STR_Y STR_RIGHT_PARENTHESIS
#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_HEAP_EQ STR_L STR_I STR_M STR_I STR_T STR_UNDERSCORE STR_H STR_E STR_A STR_P STR_EQUALS_SIGN
#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_DEPTH_EQ STR_L STR_I STR_M STR_I STR_T STR_UNDERSCORE STR_D STR_E STR_P STR_T 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
@ -1257,36 +1248,6 @@ contain characters with values greater than 255. */
#define XCL_PROP 3 /* Unicode property (2-byte property code follows) */
#define XCL_NOTPROP 4 /* Unicode inverted property (ditto) */
/* Escape items that are just an encoding of a particular data value. These
appear in the escapes[] table in pcre2_compile.c as positive numbers. */
#ifndef ESC_a
#define ESC_a CHAR_BEL
#endif
#ifndef ESC_e
#define ESC_e CHAR_ESC
#endif
#ifndef ESC_f
#define ESC_f CHAR_FF
#endif
#ifndef ESC_n
#define ESC_n CHAR_LF
#endif
#ifndef ESC_r
#define ESC_r CHAR_CR
#endif
/* We can't officially use ESC_t because it is a POSIX reserved identifier
(presumably because of all the others like size_t). */
#ifndef ESC_tee
#define ESC_tee CHAR_HT
#endif
/* These are escaped items that aren't just an encoding of a particular data
value such as \n. They must have non-zero values, as check_escape() returns 0
for a data character. In the escapes[] table in pcre2_compile.c their values
@ -1298,23 +1259,16 @@ mode rather than an escape sequence. It is also used for [^] in JavaScript
compatibility mode, and for \C in non-utf mode. In non-DOTALL mode, "." behaves
like \N.
The special values ESC_DU, ESC_du, etc. are used instead of ESC_D, ESC_d, etc.
when PCRE2_UCP is set and replacement of \d etc by \p sequences is required.
They must be contiguous, and remain in order so that the replacements can be
looked up from a table.
Negative numbers are used to encode a backreference (\1, \2, \3, etc.) in
check_escape(). There are two tests in the code for an escape
greater than ESC_b and less than ESC_Z to detect the types that may be
repeated. These are the types that consume characters. If any new escapes are
put in between that don't consume a character, that code will have to change.
*/
check_escape(). There are tests in the code for an escape greater than ESC_b
and less than ESC_Z to detect the types that may be repeated. These are the
types that consume characters. If any new escapes are put in between that don't
consume a character, that code will have to change. */
enum { ESC_A = 1, ESC_G, ESC_K, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s,
ESC_W, ESC_w, ESC_N, ESC_dum, ESC_C, ESC_P, ESC_p, ESC_R, ESC_H,
ESC_h, ESC_V, ESC_v, ESC_X, ESC_Z, ESC_z,
ESC_E, ESC_Q, ESC_g, ESC_k,
ESC_DU, ESC_du, ESC_SU, ESC_su, ESC_WU, ESC_wu };
ESC_E, ESC_Q, ESC_g, ESC_k };
/********************** Opcode definitions ******************/
@ -1380,7 +1334,8 @@ enum {
OP_CIRC, /* 27 Start of line - not multiline */
OP_CIRCM, /* 28 Start of line - multiline */
/* Single characters; caseful must precede the caseless ones */
/* Single characters; caseful must precede the caseless ones, and these
must remain in this order, and adjacent. */
OP_CHAR, /* 29 Match one character, casefully */
OP_CHARI, /* 30 Match one character, caselessly */
@ -1530,53 +1485,55 @@ enum {
OP_ASSERTBACK, /* 128 Positive lookbehind */
OP_ASSERTBACK_NOT, /* 129 Negative lookbehind */
/* ONCE, ONCE_NC, BRA, BRAPOS, CBRA, CBRAPOS, and COND must come immediately
after the assertions, with ONCE first, as there's a test for >= ONCE for a
subpattern that isn't an assertion. The POS versions must immediately follow
the non-POS versions in each case. */
/* ONCE, BRA, BRAPOS, CBRA, CBRAPOS, and COND must come immediately after the
assertions, with ONCE first, as there's a test for >= ONCE for a subpattern
that isn't an assertion. The POS versions must immediately follow the non-POS
versions in each case. */
OP_ONCE, /* 130 Atomic group, contains captures */
OP_ONCE_NC, /* 131 Atomic group containing no captures */
OP_BRA, /* 132 Start of non-capturing bracket */
OP_BRAPOS, /* 133 Ditto, with unlimited, possessive repeat */
OP_CBRA, /* 134 Start of capturing bracket */
OP_CBRAPOS, /* 135 Ditto, with unlimited, possessive repeat */
OP_COND, /* 136 Conditional group */
OP_BRA, /* 131 Start of non-capturing bracket */
OP_BRAPOS, /* 132 Ditto, with unlimited, possessive repeat */
OP_CBRA, /* 133 Start of capturing bracket */
OP_CBRAPOS, /* 134 Ditto, with unlimited, possessive repeat */
OP_COND, /* 135 Conditional group */
/* These five must follow the previous five, in the same order. There's a
check for >= SBRA to distinguish the two sets. */
OP_SBRA, /* 137 Start of non-capturing bracket, check empty */
OP_SBRAPOS, /* 138 Ditto, with unlimited, possessive repeat */
OP_SCBRA, /* 139 Start of capturing bracket, check empty */
OP_SCBRAPOS, /* 140 Ditto, with unlimited, possessive repeat */
OP_SCOND, /* 141 Conditional group, check empty */
OP_SBRA, /* 136 Start of non-capturing bracket, check empty */
OP_SBRAPOS, /* 137 Ditto, with unlimited, possessive repeat */
OP_SCBRA, /* 138 Start of capturing bracket, check empty */
OP_SCBRAPOS, /* 139 Ditto, with unlimited, possessive repeat */
OP_SCOND, /* 140 Conditional group, check empty */
/* The next two pairs must (respectively) be kept together. */
OP_CREF, /* 142 Used to hold a capture number as condition */
OP_DNCREF, /* 143 Used to point to duplicate names as a condition */
OP_RREF, /* 144 Used to hold a recursion number as condition */
OP_DNRREF, /* 145 Used to point to duplicate names as a condition */
OP_FALSE, /* 146 Always false (used by DEFINE and VERSION) */
OP_TRUE, /* 147 Always true (used by VERSION) */
OP_CREF, /* 141 Used to hold a capture number as condition */
OP_DNCREF, /* 142 Used to point to duplicate names as a condition */
OP_RREF, /* 143 Used to hold a recursion number as condition */
OP_DNRREF, /* 144 Used to point to duplicate names as a condition */
OP_FALSE, /* 145 Always false (used by DEFINE and VERSION) */
OP_TRUE, /* 146 Always true (used by VERSION) */
OP_BRAZERO, /* 148 These two must remain together and in this */
OP_BRAMINZERO, /* 149 order. */
OP_BRAPOSZERO, /* 150 */
OP_BRAZERO, /* 147 These two must remain together and in this */
OP_BRAMINZERO, /* 148 order. */
OP_BRAPOSZERO, /* 149 */
/* These are backtracking control verbs */
OP_MARK, /* 151 always has an argument */
OP_PRUNE, /* 152 */
OP_PRUNE_ARG, /* 153 same, but with argument */
OP_SKIP, /* 154 */
OP_SKIP_ARG, /* 155 same, but with argument */
OP_THEN, /* 156 */
OP_THEN_ARG, /* 157 same, but with argument */
OP_COMMIT, /* 158 */
OP_MARK, /* 150 always has an argument */
OP_PRUNE, /* 151 */
OP_PRUNE_ARG, /* 152 same, but with argument */
OP_SKIP, /* 153 */
OP_SKIP_ARG, /* 154 same, but with argument */
OP_THEN, /* 155 */
OP_THEN_ARG, /* 156 same, but with argument */
OP_COMMIT, /* 157 */
OP_COMMIT_ARG, /* 158 same, but with argument */
/* These are forced failure and success verbs */
/* These are forced failure and success verbs. FAIL and ACCEPT do accept an
argument, but these cases can be compiled as, for example, (*MARK:X)(*FAIL)
without the need for a special opcode. */
OP_FAIL, /* 159 */
OP_ACCEPT, /* 160 */
@ -1638,7 +1595,7 @@ some cases doesn't actually use these names at all). */
"Recurse", "Callout", "CalloutStr", \
"Alt", "Ket", "KetRmax", "KetRmin", "KetRpos", \
"Reverse", "Assert", "Assert not", "AssertB", "AssertB not", \
"Once", "Once_NC", \
"Once", \
"Bra", "BraPos", "CBra", "CBraPos", \
"Cond", \
"SBra", "SBraPos", "SCBra", "SCBraPos", \
@ -1647,7 +1604,7 @@ some cases doesn't actually use these names at all). */
"Cond false", "Cond true", \
"Brazero", "Braminzero", "Braposzero", \
"*MARK", "*PRUNE", "*PRUNE", "*SKIP", "*SKIP", \
"*THEN", "*THEN", "*COMMIT", "*FAIL", \
"*THEN", "*THEN", "*COMMIT", "*COMMIT", "*FAIL", \
"*ACCEPT", "*ASSERT_ACCEPT", \
"Close", "Skip zero", "Define"
@ -1722,7 +1679,6 @@ in UTF-8 mode. The code that uses this table must know about such things. */
1+LINK_SIZE, /* Assert behind */ \
1+LINK_SIZE, /* Assert behind not */ \
1+LINK_SIZE, /* ONCE */ \
1+LINK_SIZE, /* ONCE_NC */ \
1+LINK_SIZE, /* BRA */ \
1+LINK_SIZE, /* BRAPOS */ \
1+LINK_SIZE+IMM2_SIZE, /* CBRA */ \
@ -1740,7 +1696,8 @@ in UTF-8 mode. The code that uses this table must know about such things. */
3, 1, 3, /* MARK, PRUNE, PRUNE_ARG */ \
1, 3, /* SKIP, SKIP_ARG */ \
1, 3, /* THEN, THEN_ARG */ \
1, 1, 1, 1, /* COMMIT, FAIL, ACCEPT, ASSERT_ACCEPT */ \
1, 3, /* COMMIT, COMMIT_ARG */ \
1, 1, 1, /* FAIL, ACCEPT, ASSERT_ACCEPT */ \
1+IMM2_SIZE, 1, /* CLOSE, SKIPZERO */ \
1 /* DEFINE */
@ -1768,6 +1725,7 @@ typedef struct open_capitem {
struct open_capitem *next; /* Chain link */
uint16_t number; /* Capture number */
uint16_t flag; /* Set TRUE if recursive back ref */
uint16_t assert_depth; /* Assertion depth when opened */
} open_capitem;
/* Layout of the UCP type table that translates property names into types and
@ -1794,10 +1752,17 @@ typedef struct {
/* UCD access macros */
#define UCD_BLOCK_SIZE 128
#define GET_UCD(ch) (PRIV(ucd_records) + \
#define REAL_GET_UCD(ch) (PRIV(ucd_records) + \
PRIV(ucd_stage2)[PRIV(ucd_stage1)[(int)(ch) / UCD_BLOCK_SIZE] * \
UCD_BLOCK_SIZE + (int)(ch) % UCD_BLOCK_SIZE])
#if PCRE2_CODE_UNIT_WIDTH == 32
#define GET_UCD(ch) ((ch > MAX_UTF_CODE_POINT)? \
PRIV(dummy_ucd_record) : REAL_GET_UCD(ch))
#else
#define GET_UCD(ch) REAL_GET_UCD(ch)
#endif
#define UCD_CHARTYPE(ch) GET_UCD(ch)->chartype
#define UCD_SCRIPT(ch) GET_UCD(ch)->script
#define UCD_CATEGORY(ch) PRIV(ucp_gentype)[UCD_CHARTYPE(ch)]
@ -1852,8 +1817,12 @@ extern const uint8_t PRIV(utf8_table4)[];
#define _pcre2_callout_end_delims PCRE2_SUFFIX(_pcre2_callout_end_delims_)
#define _pcre2_callout_start_delims PCRE2_SUFFIX(_pcre2_callout_start_delims_)
#define _pcre2_default_compile_context PCRE2_SUFFIX(_pcre2_default_compile_context_)
#define _pcre2_default_convert_context PCRE2_SUFFIX(_pcre2_default_convert_context_)
#define _pcre2_default_match_context PCRE2_SUFFIX(_pcre2_default_match_context_)
#define _pcre2_default_tables PCRE2_SUFFIX(_pcre2_default_tables_)
#if PCRE2_CODE_UNIT_WIDTH == 32
#define _pcre2_dummy_ucd_record PCRE2_SUFFIX(_pcre2_dummy_ucd_record_)
#endif
#define _pcre2_hspace_list PCRE2_SUFFIX(_pcre2_hspace_list_)
#define _pcre2_vspace_list PCRE2_SUFFIX(_pcre2_vspace_list_)
#define _pcre2_ucd_caseless_sets PCRE2_SUFFIX(_pcre2_ucd_caseless_sets_)
@ -1872,13 +1841,17 @@ extern const uint8_t PRIV(OP_lengths)[];
extern const uint32_t PRIV(callout_end_delims)[];
extern const uint32_t PRIV(callout_start_delims)[];
extern const pcre2_compile_context PRIV(default_compile_context);
extern const pcre2_convert_context PRIV(default_convert_context);
extern const pcre2_match_context PRIV(default_match_context);
extern const uint8_t PRIV(default_tables)[];
extern const uint32_t PRIV(hspace_list)[];
extern const uint32_t PRIV(vspace_list)[];
extern const uint32_t PRIV(ucd_caseless_sets)[];
extern const ucd_record PRIV(ucd_records)[];
extern const uint8_t PRIV(ucd_stage1)[];
#if PCRE2_CODE_UNIT_WIDTH == 32
extern const ucd_record PRIV(dummy_ucd_record)[];
#endif
extern const uint16_t PRIV(ucd_stage1)[];
extern const uint16_t PRIV(ucd_stage2)[];
extern const uint32_t PRIV(ucp_gbtable)[];
extern const uint32_t PRIV(ucp_gentype)[];
@ -1912,6 +1885,7 @@ is available. */
#define _pcre2_auto_possessify PCRE2_SUFFIX(_pcre2_auto_possessify_)
#define _pcre2_check_escape PCRE2_SUFFIX(_pcre2_check_escape_)
#define _pcre2_extuni PCRE2_SUFFIX(_pcre2_extuni_)
#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_)
@ -1935,6 +1909,8 @@ 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_extuni(uint32_t, PCRE2_SPTR, PCRE2_SPTR, PCRE2_SPTR,
BOOL, int *);
extern PCRE2_SPTR _pcre2_find_bracket(PCRE2_SPTR, BOOL, int);
extern BOOL _pcre2_is_newline(PCRE2_SPTR, uint32_t, PCRE2_SPTR,
uint32_t *, BOOL);
@ -1955,6 +1931,15 @@ extern int _pcre2_valid_utf(PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE *);
extern BOOL _pcre2_was_newline(PCRE2_SPTR, uint32_t, PCRE2_SPTR,
uint32_t *, BOOL);
extern BOOL _pcre2_xclass(uint32_t, PCRE2_SPTR, BOOL);
/* This function is needed only when memmove() is not available. */
#if !defined(VPCOMPAT) && !defined(HAVE_MEMMOVE)
#define _pcre2_memmove PCRE2_SUFFIX(_pcre2_memmove)
extern void * _pcre2_memmove(void *, const void *, size_t);
#endif
#endif /* PCRE2_CODE_UNIT_WIDTH */
#endif /* PCRE2_INTERNAL_H_IDEMPOTENT_GUARD */
/* End of 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) 2016 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -54,6 +54,7 @@ just to undefine them all. */
#undef ACROSSCHAR
#undef BACKCHAR
#undef BYTES2CU
#undef CHMAX_255
#undef CU2BYTES
#undef FORWARDCHAR
#undef FORWARDCHARTEST
@ -140,7 +141,7 @@ values of 3 or 4 are also supported. */
#undef LINK_SIZE
#define LINK_SIZE 1
#define PUT(a,n,d) \
(a[n] = (d))
(a[n] = (PCRE2_UCHAR)(d))
#define GET(a,n) \
(a[n])
#define MAX_PATTERN_SIZE (1 << 16)
@ -200,21 +201,26 @@ arithmetic results in a signed value. Hence the cast. */
#endif
/* Other macros that are different for 8-bit mode. The MAX_255 macro checks
whether its argument is less than 256. The maximum length of a MARK name must
fit in one code unit; currently it is set to 255 or 65535. The TABLE_GET macro
is used to access elements of tables containing exactly 256 items. When code
points can be greater than 255, a check is needed before accessing these
tables. */
whether its argument, which is assumed to be one code unit, is less than 256.
The CHMAX_255 macro does not assume one code unit. The maximum length of a MARK
name must fit in one code unit; currently it is set to 255 or 65535. The
TABLE_GET macro is used to access elements of tables containing exactly 256
items. When code points can be greater than 255, a check is needed before
accessing these tables. */
#if PCRE2_CODE_UNIT_WIDTH == 8
#define MAX_255(c) TRUE
#define MAX_MARK ((1u << 8) - 1)
#ifdef SUPPORT_UNICODE
#define SUPPORT_WIDE_CHARS
#define CHMAX_255(c) ((c) <= 255u)
#else
#define CHMAX_255(c) TRUE
#endif /* SUPPORT_UNICODE */
#define TABLE_GET(c, table, default) ((table)[c])
#else /* Code units are 16 or 32 bits */
#define CHMAX_255(c) ((c) <= 255u)
#define MAX_255(c) ((c) <= 255u)
#define MAX_MARK ((1u << 16) - 1)
#define SUPPORT_WIDE_CHARS
@ -345,7 +351,7 @@ because almost all calls are already within a block of UTF-8 only code. */
/* Same as above, but it allows a fully customizable form. */
#define ACROSSCHAR(condition, eptr, action) \
while((condition) && ((eptr) & 0xc0u) == 0x80u) action
while((condition) && ((*eptr) & 0xc0u) == 0x80u) action
/* Deposit a character into memory, returning the number of code units. */
@ -451,7 +457,7 @@ code. */
/* Same as above, but it allows a fully customizable form. */
#define ACROSSCHAR(condition, eptr, action) \
if ((condition) && ((eptr) & 0xfc00u) == 0xdc00u) action
if ((condition) && ((*eptr) & 0xfc00u) == 0xdc00u) action
/* Deposit a character into memory, returning the number of code units. */
@ -566,15 +572,13 @@ typedef struct pcre2_real_compile_context {
uint16_t bsr_convention;
uint16_t newline_convention;
uint32_t parens_nest_limit;
uint32_t extra_options;
} pcre2_real_compile_context;
/* The real match context structure. */
typedef struct pcre2_real_match_context {
pcre2_memctl memctl;
#ifdef HEAP_MATCH_RECURSE
pcre2_memctl stack_memctl;
#endif
#ifdef SUPPORT_JIT
pcre2_jit_callback jit_callback;
void *jit_callback_data;
@ -582,10 +586,19 @@ typedef struct pcre2_real_match_context {
int (*callout)(pcre2_callout_block *, void *);
void *callout_data;
PCRE2_SIZE offset_limit;
uint32_t heap_limit;
uint32_t match_limit;
uint32_t recursion_limit;
uint32_t depth_limit;
} pcre2_real_match_context;
/* The real convert context structure. */
typedef struct pcre2_real_convert_context {
pcre2_memctl memctl;
uint32_t glob_separator;
uint32_t glob_escape;
} pcre2_real_convert_context;
/* The real compiled code structure. The type for the blocksize field is
defined specially because it is required in pcre2_serialize_decode() when
copying the size from possibly unaligned memory into a variable of the same
@ -610,9 +623,11 @@ typedef struct pcre2_real_code {
uint32_t magic_number; /* Paranoid and endianness check */
uint32_t compile_options; /* Options passed to pcre2_compile() */
uint32_t overall_options; /* Options after processing the pattern */
uint32_t extra_options; /* Taken from compile_context */
uint32_t flags; /* Various state flags */
uint32_t limit_heap; /* Limit set in the pattern */
uint32_t limit_match; /* Limit set in the pattern */
uint32_t limit_recursion; /* Limit set in the pattern */
uint32_t limit_depth; /* Limit set in the pattern */
uint32_t first_codeunit; /* Starting code unit */
uint32_t last_codeunit; /* This codeunit must be seen */
uint16_t bsr_convention; /* What \R matches */
@ -625,7 +640,13 @@ typedef struct pcre2_real_code {
uint16_t name_count; /* Number of name entries in the table */
} pcre2_real_code;
/* The real match data structure. */
/* The real match data structure. Define ovector as large as it can ever
actually be so that array bound checkers don't grumble. Memory for this
structure is obtained by calling pcre2_match_data_create(), which sets the size
as the offset of ovector plus a pair of elements for each capturable string, so
the size varies from call to call. As the maximum number of capturing
subpatterns is 65535 we must allow for 65536 strings to include the overall
match. (See also the heapframe structure below.) */
typedef struct pcre2_real_match_data {
pcre2_memctl memctl;
@ -638,7 +659,7 @@ typedef struct pcre2_real_match_data {
uint16_t matchedby; /* Type of match (normal, JIT, DFA) */
uint16_t oveccount; /* Number of pairs */
int rc; /* The return code from the match */
PCRE2_SIZE ovector[1]; /* The first field */
PCRE2_SIZE ovector[131072]; /* Must be last in the structure */
} pcre2_real_match_data;
@ -648,18 +669,24 @@ typedef struct pcre2_real_match_data {
#ifndef PCRE2_PCRE2TEST
/* Structure for checking for mutual recursion when scanning compiled code. */
/* Structures for checking for mutual recursion when scanning compiled or
parsed code. */
typedef struct recurse_check {
struct recurse_check *prev;
PCRE2_SPTR group;
} recurse_check;
typedef struct parsed_recurse_check {
struct parsed_recurse_check *prev;
uint32_t *groupptr;
} parsed_recurse_check;
/* Structure for building a cache when filling in recursion offsets. */
typedef struct recurse_cache {
PCRE2_SPTR group;
int recno;
int groupnumber;
} recurse_cache;
/* Structure for maintaining a chain of pointers to the currently incomplete
@ -693,34 +720,37 @@ 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_SPTR nestptr[2]; /* Pointer(s) saved for string substitution */
PCRE2_UCHAR *name_table; /* The name/number table */
size_t workspace_size; /* Size of workspace */
PCRE2_SIZE workspace_size; /* Size of workspace */
PCRE2_SIZE small_ref_offset[10]; /* Offsets for \1 to \9 */
PCRE2_SIZE erroroffset; /* Offset of error in pattern */
uint16_t names_found; /* Number of entries so far */
uint16_t name_entry_size; /* Size of each entry */
uint16_t parens_depth; /* Depth of nested parentheses */
uint16_t assert_depth; /* Depth of nested assertions */
open_capitem *open_caps; /* Chain of open capture items */
named_group *named_groups; /* Points to vector in pre-compile */
uint32_t named_group_list_size; /* Number of entries in the list */
uint32_t external_options; /* External (initial) options */
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 bracount; /* Count of capturing parentheses */
uint32_t lastcapture; /* Last capture encountered */
uint32_t *parsed_pattern; /* Parsed pattern buffer */
uint32_t *parsed_pattern_end; /* Parsed pattern should not get here */
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 */
uint32_t nllen; /* Newline string length */
uint32_t class_range_start; /* Overall class range start */
uint32_t class_range_end; /* Overall class range end */
PCRE2_UCHAR nl[4]; /* Newline string when fixed length */
int max_lookbehind; /* Maximum lookbehind (characters) */
int parens_depth; /* Depth of nested parentheses */
int assert_depth; /* Depth of nested assertions */
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 */
} compile_block;
/* Structure for keeping the properties of the in-memory stack used
@ -731,27 +761,8 @@ typedef struct pcre2_real_jit_stack {
void* stack;
} pcre2_real_jit_stack;
/* Structure for keeping a chain of heap blocks used for saving ovectors
during pattern recursion when the ovector is larger than can be saved on
the system stack. */
typedef struct ovecsave_frame {
struct ovecsave_frame *next; /* Next frame on free chain */
PCRE2_SIZE saved_ovec[1]; /* First vector element */
} ovecsave_frame;
/* Structure for items in a linked list that represents an explicit recursive
call within the pattern; used by pcre_match(). */
typedef struct recursion_info {
struct recursion_info *prevrec; /* Previous recursion record (or NULL) */
unsigned int group_num; /* Number of group that was called */
PCRE2_SIZE *ovec_save; /* Pointer to saved ovector frame */
uint32_t saved_capture_last; /* Last capture number */
PCRE2_SPTR subject_position; /* Position at start of recursion */
} recursion_info;
/* A similar structure for pcre_dfa_match(). */
call within the pattern when running pcre_dfa_match(). */
typedef struct dfa_recursion_info {
struct dfa_recursion_info *prevrec;
@ -759,35 +770,90 @@ typedef struct dfa_recursion_info {
uint32_t group_num;
} dfa_recursion_info;
/* Structure for building a chain of data for holding the values of the subject
pointer at the start of each subpattern, so as to detect when an empty string
has been matched by a subpattern - to break infinite loops; used by
pcre2_match(). */
/* Structure for "stack" frames that are used for remembering backtracking
positions during matching. As these are used in a vector, with the ovector item
being extended, the size of the structure must be a multiple of PCRE2_SIZE. The
only way to check this at compile time is to force an error by generating an
array with a negative size. By putting this in a typedef (which is never used),
we don't generate any code when all is well. */
typedef struct eptrblock {
struct eptrblock *epb_prev;
PCRE2_SPTR epb_saved_eptr;
} eptrblock;
typedef struct heapframe {
/* The first set of fields are variables that have to be preserved over calls
to RRMATCH(), but which do not need to be copied to new frames. */
PCRE2_SPTR ecode; /* The current position in the pattern */
PCRE2_SPTR temp_sptr[2]; /* Used for short-term PCRE_SPTR values */
PCRE2_SIZE length; /* Used for character, string, or code lengths */
PCRE2_SIZE back_frame; /* Amount to subtract on RRETURN */
PCRE2_SIZE temp_size; /* Used for short-term PCRE2_SIZE values */
uint32_t rdepth; /* "Recursion" depth */
uint32_t group_frame_type; /* Type information for group frames */
uint32_t temp_32[4]; /* Used for short-term 32-bit or BOOL values */
uint8_t return_id; /* Where to go on in internal "return" */
uint8_t op; /* Processing opcode */
/* At this point, the structure is 16-bit aligned. On most architectures
the alignment requirement for a pointer will ensure that the eptr field below
is 32-bit or 64-bit aligned. However, on m68k it is fine to have a pointer
that is 16-bit aligned. We must therefore ensure that what comes between here
and eptr is an odd multiple of 16 bits so as to get back into 32-bit
alignment. This happens naturally when PCRE2_UCHAR is 8 bits wide, but needs
fudges in the other cases. In the 32-bit case the padding comes first so that
the occu field itself is 32-bit aligned. Without the padding, this structure
is no longer a multiple of PCRE2_SIZE on m68k, and the check below fails. */
#if PCRE2_CODE_UNIT_WIDTH == 8
PCRE2_UCHAR occu[6]; /* Used for other case code units */
#elif PCRE2_CODE_UNIT_WIDTH == 16
PCRE2_UCHAR occu[2]; /* Used for other case code units */
uint8_t unused[2]; /* Ensure 32-bit alignment (see above) */
#else
uint8_t unused[2]; /* Ensure 32-bit alignment (see above) */
PCRE2_UCHAR occu[1]; /* Used for other case code units */
#endif
/* The rest have to be copied from the previous frame whenever a new frame
becomes current. The final field is specified as a large vector so that
runtime array bound checks don't catch references to it. However, for any
specific call to pcre2_match() the memory allocated for each frame structure
allows for exactly the right size ovector for the number of capturing
parentheses. (See also the comment for pcre2_real_match_data above.) */
PCRE2_SPTR eptr; /* MUST BE FIRST */
PCRE2_SPTR start_match; /* Can be adjusted by \K */
PCRE2_SPTR mark; /* Most recent mark on the success path */
uint32_t current_recurse; /* Current (deepest) recursion number */
uint32_t capture_last; /* Most recent capture */
PCRE2_SIZE last_group_offset; /* Saved offset to most recent group frame */
PCRE2_SIZE offset_top; /* Offset after highest capture */
PCRE2_SIZE ovector[131072]; /* Must be last in the structure */
} heapframe;
/* This typedef is a check that the size of the heapframe structure is a
multiple of PCRE2_SIZE. See various comments above. */
typedef char check_heapframe_size[
((sizeof(heapframe) % sizeof(PCRE2_SIZE)) == 0)? (+1):(-1)];
/* Structure for passing "static" information around between the functions
doing traditional NFA matching (pcre2_match() and friends). */
typedef struct match_block {
pcre2_memctl memctl; /* For general use */
#ifdef HEAP_MATCH_RECURSE
pcre2_memctl stack_memctl; /* For "stack" frames */
#endif
uint32_t match_call_count; /* As it says */
PCRE2_SIZE frame_vector_size; /* Size of a backtracking frame */
heapframe *match_frames; /* Points to vector of frames */
heapframe *match_frames_top; /* Points after the end of the vector */
heapframe *stack_frames; /* The original vector on the stack */
PCRE2_SIZE heap_limit; /* As it says */
uint32_t match_limit; /* As it says */
uint32_t match_limit_recursion; /* As it says */
uint32_t match_limit_depth; /* As it says */
uint32_t match_call_count; /* Number of times a new frame is created */
BOOL hitend; /* Hit the end of the subject at some point */
BOOL hasthen; /* Pattern contains (*THEN) */
const uint8_t *lcc; /* Points to lower casing table */
const uint8_t *fcc; /* Points to case-flipping table */
const uint8_t *ctypes; /* Points to table of type maps */
PCRE2_SIZE *ovector; /* Pointer to the offset vector */
PCRE2_SIZE offset_end; /* One past the end */
PCRE2_SIZE offset_max; /* The maximum usable for return data */
PCRE2_SIZE start_offset; /* The start offset value */
PCRE2_SIZE end_offset_top; /* Highwater mark at end of match */
uint16_t partial; /* PARTIAL options */
@ -798,30 +864,24 @@ typedef struct match_block {
PCRE2_SPTR start_code; /* For use when recursing */
PCRE2_SPTR start_subject; /* Start of the subject string */
PCRE2_SPTR end_subject; /* End of the subject string */
PCRE2_SPTR start_match_ptr; /* Start of matched string */
PCRE2_SPTR end_match_ptr; /* Subject position at end match */
PCRE2_SPTR start_used_ptr; /* Earliest consulted character */
PCRE2_SPTR last_used_ptr; /* Latest consulted character */
PCRE2_SPTR mark; /* Mark pointer to pass back on success */
PCRE2_SPTR nomatch_mark; /* Mark pointer to pass back on failure */
PCRE2_SPTR once_target; /* Where to back up to for atomic groups */
PCRE2_SPTR verb_ecode_ptr; /* For passing back info */
PCRE2_SPTR verb_skip_ptr; /* For passing back a (*SKIP) name */
uint32_t verb_current_recurse; /* Current recurse when (*VERB) happens */
uint32_t moptions; /* Match options */
uint32_t poptions; /* Pattern options */
uint32_t capture_last; /* Most recent capture number + overflow flag */
uint32_t skip_arg_count; /* For counting SKIP_ARGs */
uint32_t ignore_skip_arg; /* For re-run when SKIP arg name not found */
uint32_t match_function_type; /* Set for certain special calls of match() */
uint32_t nltype; /* Newline type */
uint32_t nllen; /* Newline string length */
PCRE2_UCHAR nl[4]; /* Newline string when fixed */
eptrblock *eptrchain; /* Chain of eptrblocks for tail recursions */
recursion_info *recursive; /* Linked list of recursion data */
ovecsave_frame *ovecsave_chain; /* Linked list of free ovecsave blocks */
pcre2_callout_block *cb; /* Points to a callout block */
void *callout_data; /* To pass back to callouts */
int (*callout)(pcre2_callout_block *,void *); /* Callout function or NULL */
#ifdef HEAP_MATCH_RECURSE
void *match_frames_base; /* For remembering malloc'd frames */
#endif
} match_block;
/* A similar structure is used for the same purpose by the DFA matching
@ -836,12 +896,18 @@ typedef struct dfa_match_block {
PCRE2_SPTR last_used_ptr; /* Latest consulted character */
const uint8_t *tables; /* Character tables */
PCRE2_SIZE start_offset; /* The start offset value */
PCRE2_SIZE heap_limit; /* As it says */
PCRE2_SIZE heap_used; /* As it says */
uint32_t match_limit; /* As it says */
uint32_t match_limit_depth; /* As it says */
uint32_t match_call_count; /* Number of calls of internal function */
uint32_t moptions; /* Match options */
uint32_t poptions; /* Pattern options */
uint32_t nltype; /* Newline type */
uint32_t nllen; /* Newline string length */
PCRE2_UCHAR nl[4]; /* Newline string when fixed */
uint16_t bsr_convention; /* \R interpretation */
pcre2_callout_block *cb; /* Points to a callout block */
void *callout_data; /* To pass back to callouts */
int (*callout)(pcre2_callout_block *,void *); /* Callout function or NULL */
dfa_recursion_info *recursive; /* Linked list of recursion data */

View file

@ -49,10 +49,10 @@ static SLJIT_NOINLINE int jit_machine_stack_exec(jit_arguments *arguments, jit_f
sljit_u8 local_space[MACHINE_STACK_SIZE];
struct sljit_stack local_stack;
local_stack.top = (sljit_sw)&local_space;
local_stack.base = local_stack.top;
local_stack.limit = local_stack.base + MACHINE_STACK_SIZE;
local_stack.max_limit = local_stack.limit;
local_stack.min_start = local_space;
local_stack.start = local_space;
local_stack.end = local_space + MACHINE_STACK_SIZE;
local_stack.top = local_space + MACHINE_STACK_SIZE;
arguments->stack = &local_stack;
return executable_func(arguments);
}
@ -118,7 +118,7 @@ if ((options & PCRE2_PARTIAL_HARD) != 0)
else if ((options & PCRE2_PARTIAL_SOFT) != 0)
index = 1;
if (functions->executable_funcs[index] == NULL)
if (functions == NULL || functions->executable_funcs[index] == NULL)
return PCRE2_ERROR_JIT_BADOPTION;
/* Sanity checks should be handled by pcre_exec. */

View file

@ -179,10 +179,12 @@ static struct regression_test_case regression_test_cases[] = {
{ PCRE2_CASELESS, 0, 0, 0, "\xff#a", "\xff#\xff\xfe##\xff#A" },
{ PCRE2_CASELESS, 0, 0, 0, "\xfe", "\xff\xfc#\xfe\xfe" },
{ PCRE2_CASELESS, 0, 0, 0, "a1", "Aa1" },
#ifndef NEVER_BACKSLASH_C
{ M, A, 0, 0, "\\Ca", "cda" },
{ CM, A, 0, 0, "\\Ca", "CDA" },
{ M, A, 0, 0 | F_NOMATCH, "\\Cx", "cda" },
{ CM, A, 0, 0 | F_NOMATCH, "\\Cx", "CDA" },
#endif
{ CMUP, A, 0, 0, "\xf0\x90\x90\x80\xf0\x90\x90\xa8", "\xf0\x90\x90\xa8\xf0\x90\x90\x80" },
{ 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" },
@ -258,6 +260,8 @@ static struct regression_test_case regression_test_cases[] = {
{ 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" },
{ U, A, 0, 0, "\xe1\x81\x80|\xe2\x82\x80|\xe4\x84\x80", "\xdf\xbf\xc2\x80\xe4\x84\x80" },
{ U, A, 0, 0, "(?:\xe1\x81\x80|\xe2\x82\x80|\xe4\x84\x80)#", "\xdf\xbf\xc2\x80#\xe4\x84\x80#" },
/* Greedy and non-greedy ? operators. */
{ MU, A, 0, 0, "(?:a)?a", "laab" },
@ -707,7 +711,7 @@ static struct regression_test_case regression_test_cases[] = {
{ MU, A, 0, 0, "(?1)(((a(*ACCEPT)))b)", "axaa" },
{ MU, A, 0, 0, "(?1)(?(DEFINE) (((ac(*ACCEPT)))b) )", "akaac" },
{ MU, A, 0, 0, "(a+)b(?1)b\\1", "abaaabaaaaa" },
{ MU, A, 0, 0 | F_NOMATCH, "(?(DEFINE)(aa|a))(?1)ab", "aab" },
{ MU, A, 0, 0, "(?(DEFINE)(aa|a))(?1)ab", "aab" },
{ MU, A, 0, 0, "(?(DEFINE)(a\\Kb))(?1)+ababc", "abababxabababc" },
{ MU, A, 0, 0, "(a\\Kb)(?1)+ababc", "abababxababababc" },
{ MU, A, 0, 0 | F_NOMATCH, "(a\\Kb)(?1)+ababc", "abababxababababxc" },
@ -724,6 +728,8 @@ static struct regression_test_case regression_test_cases[] = {
{ MU, A, 0, 0, "((?:(?(R)a|(?1))){3})", "XaaaaaaaaaX" },
{ MU, A, 0, 0, "((?(R)a|(?1)){1,3})aaaaaa", "aaaaaaaaXaaaaaaaaa" },
{ MU, A, 0, 0, "((?(R)a|(?1)){1,3}?)M", "aaaM" },
{ MU, A, 0, 0, "((.)(?:.|\\2(?1))){0}#(?1)#", "#aabbccdde# #aabbccddee#" },
{ MU, A, 0, 0, "((.)(?:\\2|\\2{4}b)){0}#(?:(?1))+#", "#aaaab# #aaaaab#" },
/* 16 bit specific tests. */
{ CM, A, 0, 0 | F_FORCECONV, "\xc3\xa1", "\xc3\x81\xc3\xa1" },
@ -842,13 +848,23 @@ static struct regression_test_case regression_test_cases[] = {
{ MU, A, 0, 0 | F_NOMATCH, "(?(?=a)a(*THEN)b|ad)", "ad" },
{ MU, A, 0, 0, "(?!(?(?=a)ab|b(*THEN)d))bn|bnn", "bnn" },
/* Recurse and control verbs. */
{ MU, A, 0, 0, "(a(*ACCEPT)b){0}a(?1)b", "aacaabb" },
{ MU, A, 0, 0, "((a)\\2(*ACCEPT)b){0}a(?1)b", "aaacaaabb" },
{ MU, A, 0, 0, "((ab|a(*ACCEPT)x)+|ababababax){0}_(?1)_", "_ababababax_ _ababababa_" },
{ MU, A, 0, 0, "((.)(?:A(*ACCEPT)|(?1)\\2)){0}_(?1)_", "_bcdaAdcb_bcdaAdcb_" },
{ MU, A, 0, 0, "((*MARK:m)(?:a|a(*COMMIT)b|aa)){0}_(?1)_", "_ab_" },
{ MU, A, 0, 0, "((*MARK:m)(?:a|a(*COMMIT)b|aa)){0}_(?1)_|(_aa_)", "_aa_" },
{ MU, A, 0, 0, "(a(*COMMIT)(?:b|bb)|c(*ACCEPT)d|dd){0}_(?1)+_", "_ax_ _cd_ _abbb_ _abcd_ _abbcdd_" },
{ MU, A, 0, 0, "((.)(?:.|(*COMMIT)\\2{3}(*ACCEPT).*|.*)){0}_(?1){0,4}_", "_aaaabbbbccccddd_ _aaaabbbbccccdddd_" },
/* Deep recursion. */
{ MU, A, 0, 0, "((((?:(?:(?:\\w)+)?)*|(?>\\w)+?)+|(?>\\w)?\?)*)?\\s", "aaaaa+ " },
{ MU, A, 0, 0, "(?:((?:(?:(?:\\w*?)+)??|(?>\\w)?|\\w*+)*)+)+?\\s", "aa+ " },
{ MU, A, 0, 0, "((a?)+)+b", "aaaaaaaaaaaa b" },
/* Deep recursion: Stack limit reached. */
{ M, A, 0, 0 | F_NOMATCH, "a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?aaaaaaaaaaaaaaaaaaaaaaa", "aaaaaaaaaaaaaaaaaaaaaaa" },
{ M, A, 0, 0 | F_NOMATCH, "a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?aaaaaaaaaaaaaaaaaaaaaaa", "aaaaaaaaaaaaaaaaaaaaaaa" },
{ M, A, 0, 0 | F_NOMATCH, "(?:a+)+b", "aaaaaaaaaaaaaaaaaaaaaaaa b" },
{ M, A, 0, 0 | F_NOMATCH, "(?:a+?)+?b", "aaaaaaaaaaaaaaaaaaaaaaaa b" },
{ M, A, 0, 0 | F_NOMATCH, "(?:a*)*b", "aaaaaaaaaaaaaaaaaaaaaaaa b" },
@ -1309,14 +1325,15 @@ static int regression_tests(void)
} else {
ovector8_1 = pcre2_get_ovector_pointer_8(mdata8_1);
ovector8_2 = pcre2_get_ovector_pointer_8(mdata8_2);
for (i = 0; i < OVECTOR_SIZE * 3; ++i)
for (i = 0; i < OVECTOR_SIZE * 2; ++i)
ovector8_1[i] = -2;
for (i = 0; i < OVECTOR_SIZE * 3; ++i)
for (i = 0; i < OVECTOR_SIZE * 2; ++i)
ovector8_2[i] = -2;
}
if (re8) {
(void)pcre2_set_match_limit_8(mcontext8, 10000000);
return_value8[1] = pcre2_match_8(re8, (PCRE2_SPTR8)current->input, strlen(current->input),
current->start_offset & OFFSET_MASK, current->match_options, mdata8_2, NULL);
current->start_offset & OFFSET_MASK, current->match_options, mdata8_2, mcontext8);
if (pcre2_jit_compile_8(re8, jit_compile_mode)) {
printf("\n8 bit: JIT compiler does not support \"%s\"\n", current->pattern);
@ -1348,9 +1365,9 @@ static int regression_tests(void)
} else {
ovector16_1 = pcre2_get_ovector_pointer_16(mdata16_1);
ovector16_2 = pcre2_get_ovector_pointer_16(mdata16_2);
for (i = 0; i < OVECTOR_SIZE * 3; ++i)
for (i = 0; i < OVECTOR_SIZE * 2; ++i)
ovector16_1[i] = -2;
for (i = 0; i < OVECTOR_SIZE * 3; ++i)
for (i = 0; i < OVECTOR_SIZE * 2; ++i)
ovector16_2[i] = -2;
}
if (re16) {
@ -1359,8 +1376,9 @@ static int regression_tests(void)
else
length16 = copy_char8_to_char16((PCRE2_SPTR8)current->input, regtest_buf16, REGTEST_MAX_LENGTH16);
(void)pcre2_set_match_limit_16(mcontext16, 10000000);
return_value16[1] = pcre2_match_16(re16, regtest_buf16, length16,
current->start_offset & OFFSET_MASK, current->match_options, mdata16_2, NULL);
current->start_offset & OFFSET_MASK, current->match_options, mdata16_2, mcontext16);
if (pcre2_jit_compile_16(re16, jit_compile_mode)) {
printf("\n16 bit: JIT compiler does not support \"%s\"\n", current->pattern);
@ -1392,9 +1410,9 @@ static int regression_tests(void)
} else {
ovector32_1 = pcre2_get_ovector_pointer_32(mdata32_1);
ovector32_2 = pcre2_get_ovector_pointer_32(mdata32_2);
for (i = 0; i < OVECTOR_SIZE * 3; ++i)
for (i = 0; i < OVECTOR_SIZE * 2; ++i)
ovector32_1[i] = -2;
for (i = 0; i < OVECTOR_SIZE * 3; ++i)
for (i = 0; i < OVECTOR_SIZE * 2; ++i)
ovector32_2[i] = -2;
}
if (re32) {
@ -1403,8 +1421,9 @@ static int regression_tests(void)
else
length32 = copy_char8_to_char32((PCRE2_SPTR8)current->input, regtest_buf32, REGTEST_MAX_LENGTH32);
(void)pcre2_set_match_limit_32(mcontext32, 10000000);
return_value32[1] = pcre2_match_32(re32, regtest_buf32, length32,
current->start_offset & OFFSET_MASK, current->match_options, mdata32_2, NULL);
current->start_offset & OFFSET_MASK, current->match_options, mdata32_2, mcontext32);
if (pcre2_jit_compile_32(re32, jit_compile_mode)) {
printf("\n32 bit: JIT compiler does not support \"%s\"\n", current->pattern);

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) 2016 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -141,13 +141,6 @@ for (i = 0; i < 256; i++)
if (isdigit(i)) x += ctype_digit;
if (isxdigit(i)) x += ctype_xdigit;
if (isalnum(i) || i == '_') x += ctype_word;
/* Note: strchr includes the terminating zero in the characters it considers.
In this instance, that is ok because we want binary zero to be flagged as a
meta-character, which in this sense is any character that terminates a run
of data characters. */
if (strchr("\\*+?{^.$|()[", i) != 0) x += ctype_meta;
*p++ = x;
}

File diff suppressed because it is too large Load diff

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) 2016 University of Cambridge
New API code Copyright (c) 2016-2017 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -51,7 +51,7 @@ POSSIBILITY OF SUCH DAMAGE.
* Create a match data block given ovector size *
*************************************************/
/* A minimum of 1 is imposed on the number of ovector triplets. */
/* A minimum of 1 is imposed on the number of ovector pairs. */
PCRE2_EXP_DEFN pcre2_match_data * PCRE2_CALL_CONVENTION
pcre2_match_data_create(uint32_t oveccount, pcre2_general_context *gcontext)
@ -59,7 +59,7 @@ pcre2_match_data_create(uint32_t oveccount, pcre2_general_context *gcontext)
pcre2_match_data *yield;
if (oveccount < 1) oveccount = 1;
yield = PRIV(memctl_malloc)(
sizeof(pcre2_match_data) + 3*oveccount*sizeof(PCRE2_SIZE),
offsetof(pcre2_match_data, ovector) + 2*oveccount*sizeof(PCRE2_SIZE),
(pcre2_memctl *)gcontext);
if (yield == NULL) return NULL;
yield->oveccount = oveccount;

View file

@ -83,7 +83,7 @@ PRIV(ord2utf)(uint32_t cvalue, PCRE2_UCHAR *buffer)
/* Convert to UTF-8 */
#if PCRE2_CODE_UNIT_WIDTH == 8
register int i, j;
int i, j;
for (i = 0; i < PRIV(utf8_table1_size); i++)
if ((int)cvalue <= PRIV(utf8_table1)[i]) break;
buffer += i;

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) 2016 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -75,10 +75,13 @@ if (where == NULL) /* Requests field length */
case PCRE2_INFO_BACKREFMAX:
case PCRE2_INFO_BSR:
case PCRE2_INFO_CAPTURECOUNT:
case PCRE2_INFO_DEPTHLIMIT:
case PCRE2_INFO_EXTRAOPTIONS:
case PCRE2_INFO_FIRSTCODETYPE:
case PCRE2_INFO_FIRSTCODEUNIT:
case PCRE2_INFO_HASBACKSLASHC:
case PCRE2_INFO_HASCRORLF:
case PCRE2_INFO_HEAPLIMIT:
case PCRE2_INFO_JCHANGED:
case PCRE2_INFO_LASTCODETYPE:
case PCRE2_INFO_LASTCODEUNIT:
@ -89,7 +92,6 @@ if (where == NULL) /* Requests field length */
case PCRE2_INFO_NAMEENTRYSIZE:
case PCRE2_INFO_NAMECOUNT:
case PCRE2_INFO_NEWLINE:
case PCRE2_INFO_RECURSIONLIMIT:
return sizeof(uint32_t);
case PCRE2_INFO_FIRSTBITMAP:
@ -97,6 +99,7 @@ if (where == NULL) /* Requests field length */
case PCRE2_INFO_JITSIZE:
case PCRE2_INFO_SIZE:
case PCRE2_INFO_FRAMESIZE:
return sizeof(size_t);
case PCRE2_INFO_NAMETABLE:
@ -137,6 +140,15 @@ switch(what)
*((uint32_t *)where) = re->top_bracket;
break;
case PCRE2_INFO_DEPTHLIMIT:
*((uint32_t *)where) = re->limit_depth;
if (re->limit_depth == UINT32_MAX) return PCRE2_ERROR_UNSET;
break;
case PCRE2_INFO_EXTRAOPTIONS:
*((uint32_t *)where) = re->extra_options;
break;
case PCRE2_INFO_FIRSTCODETYPE:
*((uint32_t *)where) = ((re->flags & PCRE2_FIRSTSET) != 0)? 1 :
((re->flags & PCRE2_STARTLINE) != 0)? 2 : 0;
@ -152,6 +164,11 @@ switch(what)
&(re->start_bitmap[0]) : NULL;
break;
case PCRE2_INFO_FRAMESIZE:
*((size_t *)where) = offsetof(heapframe, ovector) +
re->top_bracket * 2 * sizeof(PCRE2_SIZE);
break;
case PCRE2_INFO_HASBACKSLASHC:
*((uint32_t *)where) = (re->flags & PCRE2_HASBKC) != 0;
break;
@ -160,6 +177,11 @@ switch(what)
*((uint32_t *)where) = (re->flags & PCRE2_HASCRORLF) != 0;
break;
case PCRE2_INFO_HEAPLIMIT:
*((uint32_t *)where) = re->limit_heap;
if (re->limit_heap == UINT32_MAX) return PCRE2_ERROR_UNSET;
break;
case PCRE2_INFO_JCHANGED:
*((uint32_t *)where) = (re->flags & PCRE2_JCHANGED) != 0;
break;
@ -215,11 +237,6 @@ switch(what)
*((uint32_t *)where) = re->newline_convention;
break;
case PCRE2_INFO_RECURSIONLIMIT:
*((uint32_t *)where) = re->limit_recursion;
if (re->limit_recursion == UINT32_MAX) return PCRE2_ERROR_UNSET;
break;
case PCRE2_INFO_SIZE:
*((size_t *)where) = re->blocksize;
break;
@ -255,11 +272,15 @@ pcre2_real_code *re = (pcre2_real_code *)code;
pcre2_callout_enumerate_block cb;
PCRE2_SPTR cc;
#ifdef SUPPORT_UNICODE
BOOL utf = (re->overall_options & PCRE2_UTF) != 0;
BOOL utf;
#endif
if (re == NULL) return PCRE2_ERROR_NULL;
#ifdef SUPPORT_UNICODE
utf = (re->overall_options & PCRE2_UTF) != 0;
#endif
/* Check that the first field in the block is the magic number. If it is not,
return with PCRE2_ERROR_BADMAGIC. */
@ -369,6 +390,7 @@ while (TRUE)
#endif
case OP_MARK:
case OP_COMMIT_ARG:
case OP_PRUNE_ARG:
case OP_SKIP_ARG:
case OP_THEN_ARG:

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) 2016 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -206,7 +206,7 @@ print_custring(FILE *f, PCRE2_SPTR ptr)
{
while (*ptr != '\0')
{
register uint32_t c = *ptr++;
uint32_t c = *ptr++;
if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x{%x}", c);
}
}
@ -216,7 +216,7 @@ print_custring_bylen(FILE *f, PCRE2_SPTR ptr, PCRE2_UCHAR len)
{
for (; len > 0; len--)
{
register uint32_t c = *ptr++;
uint32_t c = *ptr++;
if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x{%x}", c);
}
}
@ -340,7 +340,7 @@ for(;;)
case OP_TABLE_LENGTH +
((sizeof(OP_names)/sizeof(const char *) == OP_TABLE_LENGTH) &&
(sizeof(OP_lengths) == OP_TABLE_LENGTH)):
break;
return;
/* ========================================================================== */
case OP_END:
@ -393,7 +393,6 @@ for(;;)
case OP_ASSERTBACK:
case OP_ASSERTBACK_NOT:
case OP_ONCE:
case OP_ONCE_NC:
case OP_COND:
case OP_SCOND:
case OP_REVERSE:
@ -800,6 +799,7 @@ for(;;)
break;
case OP_MARK:
case OP_COMMIT_ARG:
case OP_PRUNE_ARG:
case OP_SKIP_ARG:
case OP_THEN_ARG:

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) 2016 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -127,7 +127,25 @@ dst_bytes += tables_length;
for (i = 0; i < number_of_codes; i++)
{
re = (const pcre2_real_code *)(codes[i]);
memcpy(dst_bytes, (char *)re, re->blocksize);
(void)memcpy(dst_bytes, (char *)re, re->blocksize);
/* Certain fields in the compiled code block are re-set during
deserialization. In order to ensure that the serialized data stream is always
the same for the same pattern, set them to zero here. We can't assume the
copy of the pattern is correctly aligned for accessing the fields as part of
a structure. Note the use of sizeof(void *) in the second of these, to
specify the size of a pointer. If sizeof(uint8_t *) is used (tables is a
pointer to uint8_t), gcc gives a warning because the first argument is also a
pointer to uint8_t. Casting the first argument to (void *) can stop this, but
it didn't stop Coverity giving the same complaint. */
(void)memset(dst_bytes + offsetof(pcre2_real_code, memctl), 0,
sizeof(pcre2_memctl));
(void)memset(dst_bytes + offsetof(pcre2_real_code, tables), 0,
sizeof(void *));
(void)memset(dst_bytes + offsetof(pcre2_real_code, executable_jit), 0,
sizeof(void *));
dst_bytes += re->blocksize;
}
@ -214,7 +232,10 @@ for (i = 0; i < number_of_codes; i++)
if (dst_re->magic_number != MAGIC_NUMBER ||
dst_re->name_entry_size > MAX_NAME_SIZE + IMM2_SIZE + 1 ||
dst_re->name_count > MAX_NAME_COUNT)
{
memctl->free(dst_re, memctl->memory_data);
return PCRE2_ERROR_BADSERIALIZEDDATA;
}
/* At the moment only one table is supported. */

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) 2016 University of Cambridge
New API code Copyright (c) 2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -50,6 +50,42 @@ functions work only on 8-bit data. */
#include "pcre2_internal.h"
/*************************************************
* Emulated memmove() for systems without it *
*************************************************/
/* This function can make use of bcopy() if it is available. Otherwise do it by
steam, as there some non-Unix environments that lack both memmove() and
bcopy(). */
#if !defined(VPCOMPAT) && !defined(HAVE_MEMMOVE)
void *
PRIV(memmove)(void *d, const void *s, size_t n)
{
#ifdef HAVE_BCOPY
bcopy(s, d, n);
return d;
#else
size_t i;
unsigned char *dest = (unsigned char *)d;
const unsigned char *src = (const unsigned char *)s;
if (dest > src)
{
dest += n;
src += n;
for (i = 0; i < n; ++i) *(--dest) = *(--src);
return (void *)dest;
}
else
{
for (i = 0; i < n; ++i) *dest++ = *src++;
return (void *)(dest - n);
}
#endif /* not HAVE_BCOPY */
}
#endif /* not VPCOMPAT && not HAVE_MEMMOVE */
/*************************************************
* Compare two zero-terminated PCRE2 strings *
*************************************************/

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) 2016 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -46,9 +46,11 @@ collecting data (e.g. minimum matching length). */
#include "config.h"
#endif
#include "pcre2_internal.h"
/* The maximum remembered capturing brackets minimum. */
#define MAX_CACHE_BACKREF 128
/* Set a bit in the starting code unit bit map. */
@ -71,6 +73,12 @@ 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.
Backreference minimum lengths are cached to speed up multiple references. This
function is called only when the highest back reference in the pattern is less
than or equal to MAX_CACHE_BACKREF, which is one less than the size of the
caching vector. The zeroth element contains the number of the highest set
value.
Arguments:
re compiled pattern block
code pointer to start of group (the bracket)
@ -78,6 +86,7 @@ Arguments:
utf UTF flag
recurses chain of recurse_check to catch mutual recursion
countptr pointer to call count (to catch over complexity)
backref_cache vector for caching back references.
Returns: the minimum length
-1 \C in UTF-8 mode
@ -90,7 +99,8 @@ Returns: the minimum length
static int
find_minlength(const pcre2_real_code *re, PCRE2_SPTR code,
PCRE2_SPTR startcode, BOOL utf, recurse_check *recurses, int *countptr)
PCRE2_SPTR startcode, BOOL utf, recurse_check *recurses, int *countptr,
int *backref_cache)
{
int length = -1;
int prev_cap_recno = -1;
@ -101,8 +111,8 @@ 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;
int branchlength = 0;
PCRE2_UCHAR *cc = (PCRE2_UCHAR *)code + 1 + LINK_SIZE;
/* If this is a "could be empty" group, its minimum length is 0. */
@ -124,7 +134,7 @@ for (;;)
{
int d, min, recno;
PCRE2_UCHAR *cs, *ce;
register PCRE2_UCHAR op = *cc;
PCRE2_UCHAR op = *cc;
if (branchlength >= UINT16_MAX) return UINT16_MAX;
@ -146,12 +156,12 @@ for (;;)
}
goto PROCESS_NON_CAPTURE;
/* There's a special case of OP_ONCE, when it is wrapped round an
case OP_BRA:
/* There's a special case of OP_BRA, when it is wrapped round a repeated
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;
@ -160,13 +170,13 @@ for (;;)
}
/* Fall through */
case OP_ONCE_NC:
case OP_BRA:
case OP_ONCE:
case OP_SBRA:
case OP_BRAPOS:
case OP_SBRAPOS:
PROCESS_NON_CAPTURE:
d = find_minlength(re, cc, startcode, utf, recurses, countptr);
d = find_minlength(re, cc, startcode, utf, recurses, countptr,
backref_cache);
if (d < 0) return d;
branchlength += d;
do cc += GET(cc, 1); while (*cc == OP_ALT);
@ -182,11 +192,12 @@ for (;;)
case OP_SCBRA:
case OP_CBRAPOS:
case OP_SCBRAPOS:
recno = dupcapused? prev_cap_recno - 1 : (int)GET2(cc, 1+LINK_SIZE);
if (recno != prev_cap_recno)
recno = (int)GET2(cc, 1+LINK_SIZE);
if (dupcapused || recno != prev_cap_recno)
{
prev_cap_recno = recno;
prev_cap_d = find_minlength(re, cc, startcode, utf, recurses, countptr);
prev_cap_d = find_minlength(re, cc, startcode, utf, recurses, countptr,
backref_cache);
if (prev_cap_d < 0) return prev_cap_d;
}
branchlength += prev_cap_d;
@ -456,38 +467,52 @@ for (;;)
d = INT_MAX;
/* Scan all groups with the same name */
/* Scan all groups with the same name; find the shortest. */
while (count-- > 0)
{
ce = cs = (PCRE2_UCHAR *)PRIV(find_bracket)(startcode, utf, GET2(slot, 0));
if (cs == NULL) return -2;
do ce += GET(ce, 1); while (*ce == OP_ALT);
if (cc > cs && cc < ce) /* Simple recursion */
{
d = 0;
had_recurse = TRUE;
break;
}
int dd, i;
recno = GET2(slot, 0);
if (recno <= backref_cache[0] && backref_cache[recno] >= 0)
dd = backref_cache[recno];
else
{
recurse_check *r = recurses;
for (r = recurses; r != NULL; r = r->prev) if (r->group == cs) break;
if (r != NULL) /* Mutual recursion */
ce = cs = (PCRE2_UCHAR *)PRIV(find_bracket)(startcode, utf, recno);
if (cs == NULL) return -2;
do ce += GET(ce, 1); while (*ce == OP_ALT);
if (cc > cs && cc < ce) /* Simple recursion */
{
d = 0;
dd = 0;
had_recurse = TRUE;
break;
}
else
{
int dd;
this_recurse.prev = recurses;
this_recurse.group = cs;
dd = find_minlength(re, cs, startcode, utf, &this_recurse, countptr);
if (dd < d) d = dd;
recurse_check *r = recurses;
for (r = recurses; r != NULL; r = r->prev)
if (r->group == cs) break;
if (r != NULL) /* Mutual recursion */
{
dd = 0;
had_recurse = TRUE;
}
else
{
this_recurse.prev = recurses;
this_recurse.group = cs;
dd = find_minlength(re, cs, startcode, utf, &this_recurse,
countptr, backref_cache);
if (dd < 0) return dd;
}
}
backref_cache[recno] = dd;
for (i = backref_cache[0] + 1; i < recno; i++) backref_cache[i] = -1;
backref_cache[0] = recno;
}
if (dd < d) d = dd;
if (d <= 0) break; /* No point looking at any more */
slot += re->name_entry_size;
}
}
@ -501,34 +526,48 @@ for (;;)
case OP_REF:
case OP_REFI:
if (dupcapused) return -1;
if ((re->overall_options & PCRE2_MATCH_UNSET_BACKREF) == 0)
recno = GET2(cc, 1);
if (recno <= backref_cache[0] && backref_cache[recno] >= 0)
d = backref_cache[recno];
else
{
ce = cs = (PCRE2_UCHAR *)PRIV(find_bracket)(startcode, utf, GET2(cc, 1));
if (cs == NULL) return -2;
do ce += GET(ce, 1); while (*ce == OP_ALT);
if (cc > cs && cc < ce) /* Simple recursion */
int i;
if ((re->overall_options & PCRE2_MATCH_UNSET_BACKREF) == 0)
{
d = 0;
had_recurse = TRUE;
}
else
{
recurse_check *r = recurses;
for (r = recurses; r != NULL; r = r->prev) if (r->group == cs) break;
if (r != NULL) /* Mutual recursion */
ce = cs = (PCRE2_UCHAR *)PRIV(find_bracket)(startcode, utf, recno);
if (cs == NULL) return -2;
do ce += GET(ce, 1); while (*ce == OP_ALT);
if (cc > cs && cc < ce) /* Simple recursion */
{
d = 0;
had_recurse = TRUE;
}
else
{
this_recurse.prev = recurses;
this_recurse.group = cs;
d = find_minlength(re, cs, startcode, utf, &this_recurse, countptr);
recurse_check *r = recurses;
for (r = recurses; r != NULL; r = r->prev) if (r->group == cs) break;
if (r != NULL) /* Mutual recursion */
{
d = 0;
had_recurse = TRUE;
}
else
{
this_recurse.prev = recurses;
this_recurse.group = cs;
d = find_minlength(re, cs, startcode, utf, &this_recurse, countptr,
backref_cache);
if (d < 0) return d;
}
}
}
else d = 0;
backref_cache[recno] = d;
for (i = backref_cache[0] + 1; i < recno; i++) backref_cache[i] = -1;
backref_cache[0] = recno;
}
else d = 0;
cc += 1 + IMM2_SIZE;
/* Handle repeated back references */
@ -601,7 +640,7 @@ for (;;)
this_recurse.prev = recurses;
this_recurse.group = cs;
prev_recurse_d = find_minlength(re, cs, startcode, utf, &this_recurse,
countptr);
countptr, backref_cache);
if (prev_recurse_d < 0) return prev_recurse_d;
prev_recurse_recno = recno;
branchlength += prev_recurse_d;
@ -668,6 +707,7 @@ for (;;)
/* Skip these, but we need to add in the name length. */
case OP_MARK:
case OP_COMMIT_ARG:
case OP_PRUNE_ARG:
case OP_SKIP_ARG:
case OP_THEN_ARG:
@ -747,6 +787,7 @@ if (utf)
if (caseless)
{
#ifdef SUPPORT_UNICODE
if (utf)
{
#if PCRE2_CODE_UNIT_WIDTH == 8
@ -759,10 +800,12 @@ if (caseless)
if (c > 0xff) SET_BIT(0xff); else SET_BIT(c);
#endif
}
else
#endif /* SUPPORT_UNICODE */
/* Not UTF */
else if (MAX_255(c)) SET_BIT(re->tables[fcc_offset + c]);
if (MAX_255(c)) SET_BIT(re->tables[fcc_offset + c]);
}
return p;
@ -792,7 +835,7 @@ Returns: nothing
static void
set_type_bits(pcre2_real_code *re, int cbit_type, unsigned int table_limit)
{
register uint32_t c;
uint32_t c;
for (c = 0; c < table_limit; c++)
re->start_bitmap[c] |= re->tables[c+cbits_offset+cbit_type];
#if defined SUPPORT_UNICODE && PCRE2_CODE_UNIT_WIDTH == 8
@ -833,7 +876,7 @@ Returns: nothing
static void
set_nottype_bits(pcre2_real_code *re, int cbit_type, unsigned int table_limit)
{
register uint32_t c;
uint32_t c;
for (c = 0; c < table_limit; c++)
re->start_bitmap[c] |= ~(re->tables[c+cbits_offset+cbit_type]);
#if defined SUPPORT_UNICODE && PCRE2_CODE_UNIT_WIDTH == 8
@ -873,7 +916,7 @@ Returns: SSB_FAIL => Failed to find any starting code units
static int
set_start_bits(pcre2_real_code *re, PCRE2_SPTR code, BOOL utf)
{
register uint32_t c;
uint32_t c;
int yield = SSB_DONE;
#if defined SUPPORT_UNICODE && PCRE2_CODE_UNIT_WIDTH == 8
@ -911,10 +954,10 @@ do
case OP_ALLANY:
case OP_ANY:
case OP_ANYBYTE:
case OP_CIRC:
case OP_CIRCM:
case OP_CLOSE:
case OP_COMMIT:
case OP_COMMIT_ARG:
case OP_COND:
case OP_CREF:
case OP_FALSE:
@ -979,6 +1022,13 @@ do
case OP_THEN_ARG:
return SSB_FAIL;
/* OP_CIRC happens only at the start of an anchored branch (multiline ^
uses OP_CIRCM). Skip over it. */
case OP_CIRC:
tcode += PRIV(OP_lengths)[OP_CIRC];
break;
/* A "real" property test implies no starting bits, but the fake property
PT_CLIST identifies a list of characters. These lists are short, as they
are used for characters with more than one "other case", so there is no
@ -1025,7 +1075,6 @@ do
case OP_CBRAPOS:
case OP_SCBRAPOS:
case OP_ONCE:
case OP_ONCE_NC:
case OP_ASSERT:
rc = set_start_bits(re, tcode, utf);
if (rc == SSB_FAIL || rc == SSB_UNKNOWN) return rc;
@ -1227,7 +1276,7 @@ do
break;
/* Single character types set the bits and stop. Note that if PCRE2_UCP
is set, we do not see these op codes because \d etc are converted to
is set, we do not see these opcodes because \d etc are converted to
properties. Therefore, these apply in the case when only characters less
than 256 are recognized to match the types. */
@ -1407,6 +1456,10 @@ do
classmap = ((tcode[1 + LINK_SIZE] & XCL_MAP) == 0)? NULL :
(uint8_t *)(tcode + 1 + LINK_SIZE + 1);
#endif
/* It seems that the fall through comment must be outside the #ifdef if
it is to avoid the gcc compiler warning. */
/* Fall through */
/* Enter here for a negative non-XCLASS. In the 8-bit library, if we are
in UTF mode, any byte with a value >= 0xc4 is a potentially valid starter
@ -1534,24 +1587,31 @@ BOOL utf = (re->overall_options & PCRE2_UTF) != 0;
code = (PCRE2_UCHAR *)((uint8_t *)re + sizeof(pcre2_real_code)) +
re->name_entry_size * re->name_count;
/* For an anchored pattern, or an unanchored pattern that has a first code
unit, or a multiline pattern that matches only at "line start", there is no
point in seeking a list of starting code units. */
/* For a pattern that has a first code unit, or a multiline pattern that
matches only at "line start", there is no point in seeking a list of starting
code units. */
if ((re->overall_options & PCRE2_ANCHORED) == 0 &&
(re->flags & (PCRE2_FIRSTSET|PCRE2_STARTLINE)) == 0)
if ((re->flags & (PCRE2_FIRSTSET|PCRE2_STARTLINE)) == 0)
{
int rc = set_start_bits(re, code, utf);
if (rc == SSB_UNKNOWN) return 1;
if (rc == SSB_DONE) re->flags |= PCRE2_FIRSTMAPSET;
}
/* Find the minimum length of subject string. If it can match an empty string,
the minimum length is already known. */
/* Find the minimum length of subject string. If the pattern can match an empty
string, the minimum length is already known. If there are more back references
than the size of the vector we are going to cache them in, do nothing. A
pattern that complicated will probably take a long time to analyze and may in
any case turn out to be too complicated. Note that back reference minima are
held as 16-bit numbers. */
if ((re->flags & PCRE2_MATCH_EMPTY) == 0)
if ((re->flags & PCRE2_MATCH_EMPTY) == 0 &&
re->top_backref <= MAX_CACHE_BACKREF)
{
switch(min = find_minlength(re, code, code, utf, NULL, &count))
int backref_cache[MAX_CACHE_BACKREF+1];
backref_cache[0] = 0; /* Highest one that is set */
min = find_minlength(re, code, code, utf, NULL, &count, backref_cache);
switch(min)
{
case -1: /* \C in UTF mode or (*ACCEPT) or over-complex regex */
break; /* Leave minlength unchanged (will be zero) */

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) 2016 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -114,7 +114,7 @@ for (; ptr < ptrend; ptr++)
else if (*ptr == CHAR_BACKSLASH)
{
int erc;
int errorcode = 0;
int errorcode;
uint32_t ch;
if (ptr < ptrend - 1) switch (ptr[1])
@ -127,8 +127,10 @@ for (; ptr < ptrend; ptr++)
continue;
}
ptr += 1; /* Must point after \ */
erc = PRIV(check_escape)(&ptr, ptrend, &ch, &errorcode,
code->overall_options, FALSE, NULL);
ptr -= 1; /* Back to last code unit of escape */
if (errorcode != 0)
{
rc = errorcode;
@ -236,10 +238,12 @@ PCRE2_SPTR repend;
PCRE2_SIZE extra_needed = 0;
PCRE2_SIZE buff_offset, buff_length, lengthleft, fraglength;
PCRE2_SIZE *ovector;
PCRE2_SIZE ovecsave[3];
buff_offset = 0;
lengthleft = buff_length = *blength;
*blength = PCRE2_UNSET;
ovecsave[0] = ovecsave[1] = ovecsave[2] = PCRE2_UNSET;
/* Partial matching is not valid. */
@ -287,6 +291,12 @@ options &= ~SUBSTITUTE_OPTIONS;
/* Copy up to the start offset */
if (start_offset > length)
{
match_data->leftchar = 0;
rc = PCRE2_ERROR_BADOFFSET;
goto EXIT;
}
CHECKMEMCPY(subject, start_offset);
/* Loop for global substituting. */
@ -353,13 +363,33 @@ do
}
/* Handle a successful match. Matches that use \K to end before they start
are not supported. */
if (ovector[1] < ovector[0])
or start before the current point in the subject are not supported. */
if (ovector[1] < ovector[0] || ovector[0] < start_offset)
{
rc = PCRE2_ERROR_BADSUBSPATTERN;
goto EXIT;
}
/* Check for the same match as previous. This is legitimate after matching an
empty string that starts after the initial match offset. We have tried again
at the match point in case the pattern is one like /(?<=\G.)/ which can never
match at its starting point, so running the match achieves the bumpalong. If
we do get the same (null) match at the original match point, it isn't such a
pattern, so we now do the empty string magic. In all other cases, a repeat
match should never occur. */
if (ovecsave[0] == ovector[0] && ovecsave[1] == ovector[1])
{
if (ovector[0] == ovector[1] && ovecsave[2] != start_offset)
{
goptions = PCRE2_NOTEMPTY_ATSTART | PCRE2_ANCHORED;
ovecsave[2] = start_offset;
continue; /* Back to the top of the loop */
}
rc = PCRE2_ERROR_INTERNAL_DUPMATCH;
goto EXIT;
}
/* Count substitutions with a paranoid check for integer overflow; surely no
real call to this function would ever hit this! */
@ -698,7 +728,7 @@ do
else if ((suboptions & PCRE2_SUBSTITUTE_EXTENDED) != 0 &&
*ptr == CHAR_BACKSLASH)
{
int errorcode = 0;
int errorcode;
if (ptr < repend - 1) switch (ptr[1])
{
@ -728,10 +758,10 @@ do
break;
}
ptr++; /* Point after \ */
rc = PRIV(check_escape)(&ptr, repend, &ch, &errorcode,
code->overall_options, FALSE, NULL);
if (errorcode != 0) goto BADESCAPE;
ptr++;
switch(rc)
{
@ -791,13 +821,18 @@ do
} /* 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 :
/* The replacement has been copied to the output. Save the details of this
match. See above for how this data is used. If we matched an empty string, do
the magic for global matches. Finally, update the start offset to point to
the rest of the subject string. */
ovecsave[0] = ovector[0];
ovecsave[1] = ovector[1];
ovecsave[2] = start_offset;
goptions = (ovector[0] != ovector[1] || ovector[0] > start_offset)? 0 :
PCRE2_ANCHORED|PCRE2_NOTEMPTY_ATSTART;
start_offset = ovector[1];
} while ((suboptions & PCRE2_SUBSTITUTE_GLOBAL) != 0); /* Repeat "do" loop */
/* Copy the rest of the subject. */

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) 2016 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -414,7 +414,12 @@ else
for (i = 0; i < count2; i += 2)
{
size = (ovector[i+1] > ovector[i])? (ovector[i+1] - ovector[i]) : 0;
memcpy(sp, match_data->subject + ovector[i], CU2BYTES(size));
/* Size == 0 includes the case when the capture is unset. Avoid adding
PCRE2_UNSET to match_data->subject because it overflows, even though with
zero size calling memcpy() is harmless. */
if (size != 0) memcpy(sp, match_data->subject + ovector[i], CU2BYTES(size));
*listp++ = sp;
if (lensp != NULL) *lensp++ = size;
sp += size;

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) 2016 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -39,7 +39,7 @@ POSSIBILITY OF SUCH DAMAGE.
*/
/* This module contains some fixed tables that are used by more than one of the
PCRE code modules. The tables are also #included by the pcre2test program,
PCRE2 code modules. The tables are also #included by the pcre2test program,
which uses macros to change their names from _pcre2_xxx to xxxx, thereby
avoiding name clashes with the library. In this case, PCRE2_PCRE2TEST is
defined. */
@ -137,9 +137,10 @@ const uint32_t PRIV(ucp_gentype)[] = {
/* This table encodes the rules for finding the end of an extended grapheme
cluster. Every code point has a grapheme break property which is one of the
ucp_gbXX values defined in pcre2_ucp.h. The 2-dimensional table is indexed by
the properties of two adjacent code points. The left property selects a word
from the table, and the right property selects a bit from that word like this:
ucp_gbXX values defined in pcre2_ucp.h. These changed between Unicode versions
10 and 11. The 2-dimensional table is indexed by the properties of two adjacent
code points. The left property selects a word from the table, and the right
property selects a bit from that word like this:
PRIV(ucp_gbtable)[left-property] & (1 << right-property)
@ -148,7 +149,7 @@ two code points. The breaking rules are as follows:
1. Break at the start and end of text (pretty obviously).
2. Do not break between a CR and LF; otherwise, break before and after
2. Do not break between a CR and LF; otherwise, break before and after
controls.
3. Do not break Hangul syllable sequences, the rules for which are:
@ -157,44 +158,54 @@ two code points. The breaking rules are as follows:
LV or V may be followed by V or T
LVT or T may be followed by T
4. Do not break before extending characters.
4. Do not break before extending characters or zero-width-joiner (ZWJ).
The next two rules are only for extended grapheme clusters (but that's what we
The following rules are only for extended grapheme clusters (but that's what we
are implementing).
5. Do not break before SpacingMarks.
6. Do not break after Prepend characters.
7. Otherwise, break everywhere.
7. Do not break within emoji modifier sequences or emoji zwj sequences. That
is, do not break between characters with the Extended_Pictographic property.
Extend and ZWJ characters are allowed between the characters; this cannot be
represented in this table, the code has to deal with it.
8. Do not break within emoji flag sequences. That is, do not break between
regional indicator (RI) symbols if there are an odd number of RI characters
before the break point. This table encodes "join RI characters"; the code
has to deal with checking for previous adjoining RIs.
9. Otherwise, break everywhere.
*/
#define ESZ (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbZWJ)
const uint32_t PRIV(ucp_gbtable)[] = {
(1<<ucp_gbLF), /* 0 CR */
0, /* 1 LF */
0, /* 2 Control */
(1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark), /* 3 Extend */
(1<<ucp_gbExtend)|(1<<ucp_gbPrepend)| /* 4 Prepend */
(1<<ucp_gbSpacingMark)|(1<<ucp_gbL)|
(1<<ucp_gbV)|(1<<ucp_gbT)|(1<<ucp_gbLV)|
(1<<ucp_gbLVT)|(1<<ucp_gbOther),
(1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark), /* 5 SpacingMark */
(1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbL)| /* 6 L */
(1<<ucp_gbL)|(1<<ucp_gbV)|(1<<ucp_gbLV)|(1<<ucp_gbLVT),
(1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)| /* 7 V */
(1<<ucp_gbT),
(1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT), /* 8 T */
(1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)| /* 9 LV */
(1<<ucp_gbT),
(1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT), /* 10 LVT */
(1<<ucp_gbRegionalIndicator), /* 11 RegionalIndicator */
(1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark) /* 12 Other */
(1<<ucp_gbLF), /* 0 CR */
0, /* 1 LF */
0, /* 2 Control */
ESZ, /* 3 Extend */
ESZ|(1<<ucp_gbPrepend)| /* 4 Prepend */
(1<<ucp_gbL)|(1<<ucp_gbV)|(1<<ucp_gbT)|
(1<<ucp_gbLV)|(1<<ucp_gbLVT)|(1<<ucp_gbOther)|
(1<<ucp_gbRegionalIndicator),
ESZ, /* 5 SpacingMark */
ESZ|(1<<ucp_gbL)|(1<<ucp_gbV)|(1<<ucp_gbLV)| /* 6 L */
(1<<ucp_gbLVT),
ESZ|(1<<ucp_gbV)|(1<<ucp_gbT), /* 7 V */
ESZ|(1<<ucp_gbT), /* 8 T */
ESZ|(1<<ucp_gbV)|(1<<ucp_gbT), /* 9 LV */
ESZ|(1<<ucp_gbT), /* 10 LVT */
(1<<ucp_gbRegionalIndicator), /* 11 RegionalIndicator */
ESZ, /* 12 Other */
ESZ, /* 13 ZWJ */
ESZ|(1<<ucp_gbExtended_Pictographic) /* 14 Extended Pictographic */
};
#undef ESZ
#ifdef SUPPORT_JIT
/* This table reverses PRIV(ucp_gentype). We can save the cost
of a memory load. */
@ -227,6 +238,7 @@ 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_Adlam0 STR_A STR_d STR_l STR_a STR_m "\0"
#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"
@ -238,6 +250,7 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Bassa_Vah0 STR_B STR_a STR_s STR_s STR_a STR_UNDERSCORE STR_V STR_a STR_h "\0"
#define STRING_Batak0 STR_B STR_a STR_t STR_a STR_k "\0"
#define STRING_Bengali0 STR_B STR_e STR_n STR_g STR_a STR_l STR_i "\0"
#define STRING_Bhaiksuki0 STR_B STR_h STR_a STR_i STR_k STR_s STR_u STR_k STR_i "\0"
#define STRING_Bopomofo0 STR_B STR_o STR_p STR_o STR_m STR_o STR_f STR_o "\0"
#define STRING_Brahmi0 STR_B STR_r STR_a STR_h STR_m STR_i "\0"
#define STRING_Braille0 STR_B STR_r STR_a STR_i STR_l STR_l STR_e "\0"
@ -262,6 +275,7 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Cyrillic0 STR_C STR_y STR_r STR_i STR_l STR_l STR_i STR_c "\0"
#define STRING_Deseret0 STR_D STR_e STR_s STR_e STR_r STR_e STR_t "\0"
#define STRING_Devanagari0 STR_D STR_e STR_v STR_a STR_n STR_a STR_g STR_a STR_r STR_i "\0"
#define STRING_Dogra0 STR_D STR_o STR_g STR_r STR_a "\0"
#define STRING_Duployan0 STR_D STR_u STR_p STR_l STR_o STR_y STR_a STR_n "\0"
#define STRING_Egyptian_Hieroglyphs0 STR_E STR_g STR_y STR_p STR_t 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_Elbasan0 STR_E STR_l STR_b STR_a STR_s STR_a STR_n "\0"
@ -272,9 +286,11 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Grantha0 STR_G STR_r STR_a STR_n STR_t STR_h STR_a "\0"
#define STRING_Greek0 STR_G STR_r STR_e STR_e STR_k "\0"
#define STRING_Gujarati0 STR_G STR_u STR_j STR_a STR_r STR_a STR_t STR_i "\0"
#define STRING_Gunjala_Gondi0 STR_G STR_u STR_n STR_j STR_a STR_l STR_a STR_UNDERSCORE STR_G STR_o STR_n STR_d STR_i "\0"
#define STRING_Gurmukhi0 STR_G STR_u STR_r STR_m STR_u STR_k STR_h STR_i "\0"
#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_Hanifi_Rohingya0 STR_H STR_a STR_n STR_i STR_f STR_i STR_UNDERSCORE STR_R STR_o STR_h STR_i STR_n STR_g STR_y STR_a "\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"
@ -310,11 +326,15 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Lydian0 STR_L STR_y STR_d STR_i STR_a STR_n "\0"
#define STRING_M0 STR_M "\0"
#define STRING_Mahajani0 STR_M STR_a STR_h STR_a STR_j STR_a STR_n STR_i "\0"
#define STRING_Makasar0 STR_M STR_a STR_k STR_a STR_s STR_a STR_r "\0"
#define STRING_Malayalam0 STR_M STR_a STR_l STR_a STR_y STR_a STR_l STR_a STR_m "\0"
#define STRING_Mandaic0 STR_M STR_a STR_n STR_d STR_a STR_i STR_c "\0"
#define STRING_Manichaean0 STR_M STR_a STR_n STR_i STR_c STR_h STR_a STR_e STR_a STR_n "\0"
#define STRING_Marchen0 STR_M STR_a STR_r STR_c STR_h STR_e STR_n "\0"
#define STRING_Masaram_Gondi0 STR_M STR_a STR_s STR_a STR_r STR_a STR_m STR_UNDERSCORE STR_G STR_o STR_n STR_d STR_i "\0"
#define STRING_Mc0 STR_M STR_c "\0"
#define STRING_Me0 STR_M STR_e "\0"
#define STRING_Medefaidrin0 STR_M STR_e STR_d STR_e STR_f STR_a STR_i STR_d STR_r STR_i STR_n "\0"
#define STRING_Meetei_Mayek0 STR_M STR_e STR_e STR_t STR_e STR_i STR_UNDERSCORE STR_M STR_a STR_y STR_e STR_k "\0"
#define STRING_Mende_Kikakui0 STR_M STR_e STR_n STR_d STR_e STR_UNDERSCORE STR_K STR_i STR_k STR_a STR_k STR_u STR_i "\0"
#define STRING_Meroitic_Cursive0 STR_M STR_e STR_r STR_o STR_i STR_t STR_i STR_c STR_UNDERSCORE STR_C STR_u STR_r STR_s STR_i STR_v STR_e "\0"
@ -330,9 +350,11 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Nabataean0 STR_N STR_a STR_b STR_a STR_t STR_a STR_e STR_a STR_n "\0"
#define STRING_Nd0 STR_N STR_d "\0"
#define STRING_New_Tai_Lue0 STR_N STR_e STR_w STR_UNDERSCORE STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_u STR_e "\0"
#define STRING_Newa0 STR_N STR_e STR_w STR_a "\0"
#define STRING_Nko0 STR_N STR_k STR_o "\0"
#define STRING_Nl0 STR_N STR_l "\0"
#define STRING_No0 STR_N STR_o "\0"
#define STRING_Nushu0 STR_N STR_u STR_s STR_h STR_u "\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"
@ -340,9 +362,11 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#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"
#define STRING_Old_Persian0 STR_O STR_l STR_d STR_UNDERSCORE STR_P STR_e STR_r STR_s STR_i STR_a STR_n "\0"
#define STRING_Old_Sogdian0 STR_O STR_l STR_d STR_UNDERSCORE STR_S STR_o STR_g STR_d STR_i STR_a STR_n "\0"
#define STRING_Old_South_Arabian0 STR_O STR_l STR_d STR_UNDERSCORE STR_S STR_o STR_u STR_t STR_h STR_UNDERSCORE STR_A STR_r STR_a STR_b STR_i STR_a STR_n "\0"
#define STRING_Old_Turkic0 STR_O STR_l STR_d STR_UNDERSCORE STR_T STR_u STR_r STR_k STR_i STR_c "\0"
#define STRING_Oriya0 STR_O STR_r STR_i STR_y STR_a "\0"
#define STRING_Osage0 STR_O STR_s STR_a STR_g STR_e "\0"
#define STRING_Osmanya0 STR_O STR_s STR_m STR_a STR_n STR_y STR_a "\0"
#define STRING_P0 STR_P "\0"
#define STRING_Pahawh_Hmong0 STR_P STR_a STR_h STR_a STR_w STR_h STR_UNDERSCORE STR_H STR_m STR_o STR_n STR_g "\0"
@ -372,7 +396,9 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Sk0 STR_S STR_k "\0"
#define STRING_Sm0 STR_S STR_m "\0"
#define STRING_So0 STR_S STR_o "\0"
#define STRING_Sogdian0 STR_S STR_o STR_g STR_d STR_i STR_a STR_n "\0"
#define STRING_Sora_Sompeng0 STR_S STR_o STR_r STR_a STR_UNDERSCORE STR_S STR_o STR_m STR_p STR_e STR_n STR_g "\0"
#define STRING_Soyombo0 STR_S STR_o STR_y STR_o STR_m STR_b STR_o "\0"
#define STRING_Sundanese0 STR_S STR_u STR_n STR_d STR_a STR_n STR_e STR_s STR_e "\0"
#define STRING_Syloti_Nagri0 STR_S STR_y STR_l STR_o STR_t STR_i STR_UNDERSCORE STR_N STR_a STR_g STR_r STR_i "\0"
#define STRING_Syriac0 STR_S STR_y STR_r STR_i STR_a STR_c "\0"
@ -383,6 +409,7 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Tai_Viet0 STR_T STR_a STR_i STR_UNDERSCORE STR_V STR_i STR_e STR_t "\0"
#define STRING_Takri0 STR_T STR_a STR_k STR_r STR_i "\0"
#define STRING_Tamil0 STR_T STR_a STR_m STR_i STR_l "\0"
#define STRING_Tangut0 STR_T STR_a STR_n STR_g STR_u STR_t "\0"
#define STRING_Telugu0 STR_T STR_e STR_l STR_u STR_g STR_u "\0"
#define STRING_Thaana0 STR_T STR_h STR_a STR_a STR_n STR_a "\0"
#define STRING_Thai0 STR_T STR_h STR_a STR_i "\0"
@ -399,11 +426,13 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Xwd0 STR_X STR_w STR_d "\0"
#define STRING_Yi0 STR_Y STR_i "\0"
#define STRING_Z0 STR_Z "\0"
#define STRING_Zanabazar_Square0 STR_Z STR_a STR_n STR_a STR_b STR_a STR_z STR_a STR_r STR_UNDERSCORE STR_S STR_q STR_u STR_a STR_r STR_e "\0"
#define STRING_Zl0 STR_Z STR_l "\0"
#define STRING_Zp0 STR_Z STR_p "\0"
#define STRING_Zs0 STR_Z STR_s "\0"
const char PRIV(utt_names)[] =
STRING_Adlam0
STRING_Ahom0
STRING_Anatolian_Hieroglyphs0
STRING_Any0
@ -415,6 +444,7 @@ const char PRIV(utt_names)[] =
STRING_Bassa_Vah0
STRING_Batak0
STRING_Bengali0
STRING_Bhaiksuki0
STRING_Bopomofo0
STRING_Brahmi0
STRING_Braille0
@ -439,6 +469,7 @@ const char PRIV(utt_names)[] =
STRING_Cyrillic0
STRING_Deseret0
STRING_Devanagari0
STRING_Dogra0
STRING_Duployan0
STRING_Egyptian_Hieroglyphs0
STRING_Elbasan0
@ -449,9 +480,11 @@ const char PRIV(utt_names)[] =
STRING_Grantha0
STRING_Greek0
STRING_Gujarati0
STRING_Gunjala_Gondi0
STRING_Gurmukhi0
STRING_Han0
STRING_Hangul0
STRING_Hanifi_Rohingya0
STRING_Hanunoo0
STRING_Hatran0
STRING_Hebrew0
@ -487,11 +520,15 @@ const char PRIV(utt_names)[] =
STRING_Lydian0
STRING_M0
STRING_Mahajani0
STRING_Makasar0
STRING_Malayalam0
STRING_Mandaic0
STRING_Manichaean0
STRING_Marchen0
STRING_Masaram_Gondi0
STRING_Mc0
STRING_Me0
STRING_Medefaidrin0
STRING_Meetei_Mayek0
STRING_Mende_Kikakui0
STRING_Meroitic_Cursive0
@ -507,9 +544,11 @@ const char PRIV(utt_names)[] =
STRING_Nabataean0
STRING_Nd0
STRING_New_Tai_Lue0
STRING_Newa0
STRING_Nko0
STRING_Nl0
STRING_No0
STRING_Nushu0
STRING_Ogham0
STRING_Ol_Chiki0
STRING_Old_Hungarian0
@ -517,9 +556,11 @@ const char PRIV(utt_names)[] =
STRING_Old_North_Arabian0
STRING_Old_Permic0
STRING_Old_Persian0
STRING_Old_Sogdian0
STRING_Old_South_Arabian0
STRING_Old_Turkic0
STRING_Oriya0
STRING_Osage0
STRING_Osmanya0
STRING_P0
STRING_Pahawh_Hmong0
@ -549,7 +590,9 @@ const char PRIV(utt_names)[] =
STRING_Sk0
STRING_Sm0
STRING_So0
STRING_Sogdian0
STRING_Sora_Sompeng0
STRING_Soyombo0
STRING_Sundanese0
STRING_Syloti_Nagri0
STRING_Syriac0
@ -560,6 +603,7 @@ const char PRIV(utt_names)[] =
STRING_Tai_Viet0
STRING_Takri0
STRING_Tamil0
STRING_Tangut0
STRING_Telugu0
STRING_Thaana0
STRING_Thai0
@ -576,186 +620,204 @@ const char PRIV(utt_names)[] =
STRING_Xwd0
STRING_Yi0
STRING_Z0
STRING_Zanabazar_Square0
STRING_Zl0
STRING_Zp0
STRING_Zs0;
const ucp_type_table PRIV(utt)[] = {
{ 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 }
{ 0, PT_SC, ucp_Adlam },
{ 6, PT_SC, ucp_Ahom },
{ 11, PT_SC, ucp_Anatolian_Hieroglyphs },
{ 33, PT_ANY, 0 },
{ 37, PT_SC, ucp_Arabic },
{ 44, PT_SC, ucp_Armenian },
{ 53, PT_SC, ucp_Avestan },
{ 61, PT_SC, ucp_Balinese },
{ 70, PT_SC, ucp_Bamum },
{ 76, PT_SC, ucp_Bassa_Vah },
{ 86, PT_SC, ucp_Batak },
{ 92, PT_SC, ucp_Bengali },
{ 100, PT_SC, ucp_Bhaiksuki },
{ 110, PT_SC, ucp_Bopomofo },
{ 119, PT_SC, ucp_Brahmi },
{ 126, PT_SC, ucp_Braille },
{ 134, PT_SC, ucp_Buginese },
{ 143, PT_SC, ucp_Buhid },
{ 149, PT_GC, ucp_C },
{ 151, PT_SC, ucp_Canadian_Aboriginal },
{ 171, PT_SC, ucp_Carian },
{ 178, PT_SC, ucp_Caucasian_Albanian },
{ 197, PT_PC, ucp_Cc },
{ 200, PT_PC, ucp_Cf },
{ 203, PT_SC, ucp_Chakma },
{ 210, PT_SC, ucp_Cham },
{ 215, PT_SC, ucp_Cherokee },
{ 224, PT_PC, ucp_Cn },
{ 227, PT_PC, ucp_Co },
{ 230, PT_SC, ucp_Common },
{ 237, PT_SC, ucp_Coptic },
{ 244, PT_PC, ucp_Cs },
{ 247, PT_SC, ucp_Cuneiform },
{ 257, PT_SC, ucp_Cypriot },
{ 265, PT_SC, ucp_Cyrillic },
{ 274, PT_SC, ucp_Deseret },
{ 282, PT_SC, ucp_Devanagari },
{ 293, PT_SC, ucp_Dogra },
{ 299, PT_SC, ucp_Duployan },
{ 308, PT_SC, ucp_Egyptian_Hieroglyphs },
{ 329, PT_SC, ucp_Elbasan },
{ 337, PT_SC, ucp_Ethiopic },
{ 346, PT_SC, ucp_Georgian },
{ 355, PT_SC, ucp_Glagolitic },
{ 366, PT_SC, ucp_Gothic },
{ 373, PT_SC, ucp_Grantha },
{ 381, PT_SC, ucp_Greek },
{ 387, PT_SC, ucp_Gujarati },
{ 396, PT_SC, ucp_Gunjala_Gondi },
{ 410, PT_SC, ucp_Gurmukhi },
{ 419, PT_SC, ucp_Han },
{ 423, PT_SC, ucp_Hangul },
{ 430, PT_SC, ucp_Hanifi_Rohingya },
{ 446, PT_SC, ucp_Hanunoo },
{ 454, PT_SC, ucp_Hatran },
{ 461, PT_SC, ucp_Hebrew },
{ 468, PT_SC, ucp_Hiragana },
{ 477, PT_SC, ucp_Imperial_Aramaic },
{ 494, PT_SC, ucp_Inherited },
{ 504, PT_SC, ucp_Inscriptional_Pahlavi },
{ 526, PT_SC, ucp_Inscriptional_Parthian },
{ 549, PT_SC, ucp_Javanese },
{ 558, PT_SC, ucp_Kaithi },
{ 565, PT_SC, ucp_Kannada },
{ 573, PT_SC, ucp_Katakana },
{ 582, PT_SC, ucp_Kayah_Li },
{ 591, PT_SC, ucp_Kharoshthi },
{ 602, PT_SC, ucp_Khmer },
{ 608, PT_SC, ucp_Khojki },
{ 615, PT_SC, ucp_Khudawadi },
{ 625, PT_GC, ucp_L },
{ 627, PT_LAMP, 0 },
{ 630, PT_SC, ucp_Lao },
{ 634, PT_SC, ucp_Latin },
{ 640, PT_SC, ucp_Lepcha },
{ 647, PT_SC, ucp_Limbu },
{ 653, PT_SC, ucp_Linear_A },
{ 662, PT_SC, ucp_Linear_B },
{ 671, PT_SC, ucp_Lisu },
{ 676, PT_PC, ucp_Ll },
{ 679, PT_PC, ucp_Lm },
{ 682, PT_PC, ucp_Lo },
{ 685, PT_PC, ucp_Lt },
{ 688, PT_PC, ucp_Lu },
{ 691, PT_SC, ucp_Lycian },
{ 698, PT_SC, ucp_Lydian },
{ 705, PT_GC, ucp_M },
{ 707, PT_SC, ucp_Mahajani },
{ 716, PT_SC, ucp_Makasar },
{ 724, PT_SC, ucp_Malayalam },
{ 734, PT_SC, ucp_Mandaic },
{ 742, PT_SC, ucp_Manichaean },
{ 753, PT_SC, ucp_Marchen },
{ 761, PT_SC, ucp_Masaram_Gondi },
{ 775, PT_PC, ucp_Mc },
{ 778, PT_PC, ucp_Me },
{ 781, PT_SC, ucp_Medefaidrin },
{ 793, PT_SC, ucp_Meetei_Mayek },
{ 806, PT_SC, ucp_Mende_Kikakui },
{ 820, PT_SC, ucp_Meroitic_Cursive },
{ 837, PT_SC, ucp_Meroitic_Hieroglyphs },
{ 858, PT_SC, ucp_Miao },
{ 863, PT_PC, ucp_Mn },
{ 866, PT_SC, ucp_Modi },
{ 871, PT_SC, ucp_Mongolian },
{ 881, PT_SC, ucp_Mro },
{ 885, PT_SC, ucp_Multani },
{ 893, PT_SC, ucp_Myanmar },
{ 901, PT_GC, ucp_N },
{ 903, PT_SC, ucp_Nabataean },
{ 913, PT_PC, ucp_Nd },
{ 916, PT_SC, ucp_New_Tai_Lue },
{ 928, PT_SC, ucp_Newa },
{ 933, PT_SC, ucp_Nko },
{ 937, PT_PC, ucp_Nl },
{ 940, PT_PC, ucp_No },
{ 943, PT_SC, ucp_Nushu },
{ 949, PT_SC, ucp_Ogham },
{ 955, PT_SC, ucp_Ol_Chiki },
{ 964, PT_SC, ucp_Old_Hungarian },
{ 978, PT_SC, ucp_Old_Italic },
{ 989, PT_SC, ucp_Old_North_Arabian },
{ 1007, PT_SC, ucp_Old_Permic },
{ 1018, PT_SC, ucp_Old_Persian },
{ 1030, PT_SC, ucp_Old_Sogdian },
{ 1042, PT_SC, ucp_Old_South_Arabian },
{ 1060, PT_SC, ucp_Old_Turkic },
{ 1071, PT_SC, ucp_Oriya },
{ 1077, PT_SC, ucp_Osage },
{ 1083, PT_SC, ucp_Osmanya },
{ 1091, PT_GC, ucp_P },
{ 1093, PT_SC, ucp_Pahawh_Hmong },
{ 1106, PT_SC, ucp_Palmyrene },
{ 1116, PT_SC, ucp_Pau_Cin_Hau },
{ 1128, PT_PC, ucp_Pc },
{ 1131, PT_PC, ucp_Pd },
{ 1134, PT_PC, ucp_Pe },
{ 1137, PT_PC, ucp_Pf },
{ 1140, PT_SC, ucp_Phags_Pa },
{ 1149, PT_SC, ucp_Phoenician },
{ 1160, PT_PC, ucp_Pi },
{ 1163, PT_PC, ucp_Po },
{ 1166, PT_PC, ucp_Ps },
{ 1169, PT_SC, ucp_Psalter_Pahlavi },
{ 1185, PT_SC, ucp_Rejang },
{ 1192, PT_SC, ucp_Runic },
{ 1198, PT_GC, ucp_S },
{ 1200, PT_SC, ucp_Samaritan },
{ 1210, PT_SC, ucp_Saurashtra },
{ 1221, PT_PC, ucp_Sc },
{ 1224, PT_SC, ucp_Sharada },
{ 1232, PT_SC, ucp_Shavian },
{ 1240, PT_SC, ucp_Siddham },
{ 1248, PT_SC, ucp_SignWriting },
{ 1260, PT_SC, ucp_Sinhala },
{ 1268, PT_PC, ucp_Sk },
{ 1271, PT_PC, ucp_Sm },
{ 1274, PT_PC, ucp_So },
{ 1277, PT_SC, ucp_Sogdian },
{ 1285, PT_SC, ucp_Sora_Sompeng },
{ 1298, PT_SC, ucp_Soyombo },
{ 1306, PT_SC, ucp_Sundanese },
{ 1316, PT_SC, ucp_Syloti_Nagri },
{ 1329, PT_SC, ucp_Syriac },
{ 1336, PT_SC, ucp_Tagalog },
{ 1344, PT_SC, ucp_Tagbanwa },
{ 1353, PT_SC, ucp_Tai_Le },
{ 1360, PT_SC, ucp_Tai_Tham },
{ 1369, PT_SC, ucp_Tai_Viet },
{ 1378, PT_SC, ucp_Takri },
{ 1384, PT_SC, ucp_Tamil },
{ 1390, PT_SC, ucp_Tangut },
{ 1397, PT_SC, ucp_Telugu },
{ 1404, PT_SC, ucp_Thaana },
{ 1411, PT_SC, ucp_Thai },
{ 1416, PT_SC, ucp_Tibetan },
{ 1424, PT_SC, ucp_Tifinagh },
{ 1433, PT_SC, ucp_Tirhuta },
{ 1441, PT_SC, ucp_Ugaritic },
{ 1450, PT_SC, ucp_Vai },
{ 1454, PT_SC, ucp_Warang_Citi },
{ 1466, PT_ALNUM, 0 },
{ 1470, PT_PXSPACE, 0 },
{ 1474, PT_SPACE, 0 },
{ 1478, PT_UCNC, 0 },
{ 1482, PT_WORD, 0 },
{ 1486, PT_SC, ucp_Yi },
{ 1489, PT_GC, ucp_Z },
{ 1491, PT_SC, ucp_Zanabazar_Square },
{ 1508, PT_PC, ucp_Zl },
{ 1511, PT_PC, ucp_Zp },
{ 1514, PT_PC, ucp_Zs }
};
const size_t PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table);

4189
pcre2-10.32/src/pcre2_ucd.c Normal file

File diff suppressed because it is too large Load diff

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) 2016 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -39,8 +39,8 @@ POSSIBILITY OF SUCH DAMAGE.
*/
#ifndef _PCRE2_UCP_H
#define _PCRE2_UCP_H
#ifndef PCRE2_UCP_H_IDEMPOTENT_GUARD
#define PCRE2_UCP_H_IDEMPOTENT_GUARD
/* This file contains definitions of the property values that are returned by
the UCD access macros. New values that are added for new releases of Unicode
@ -100,24 +100,25 @@ enum {
ucp_Zs /* Space separator */
};
/* These are grapheme break properties. Note that the code for processing them
assumes that the values are less than 16. If more values are added that take
the number to 16 or more, the code will have to be rewritten. */
/* These are grapheme break properties. The Extended Pictographic property
comes from the emoji-data.txt file. */
enum {
ucp_gbCR, /* 0 */
ucp_gbLF, /* 1 */
ucp_gbControl, /* 2 */
ucp_gbExtend, /* 3 */
ucp_gbPrepend, /* 4 */
ucp_gbSpacingMark, /* 5 */
ucp_gbL, /* 6 Hangul syllable type L */
ucp_gbV, /* 7 Hangul syllable type V */
ucp_gbT, /* 8 Hangul syllable type T */
ucp_gbLV, /* 9 Hangul syllable type LV */
ucp_gbLVT, /* 10 Hangul syllable type LVT */
ucp_gbRegionalIndicator, /* 11 */
ucp_gbOther /* 12 */
ucp_gbCR, /* 0 */
ucp_gbLF, /* 1 */
ucp_gbControl, /* 2 */
ucp_gbExtend, /* 3 */
ucp_gbPrepend, /* 4 */
ucp_gbSpacingMark, /* 5 */
ucp_gbL, /* 6 Hangul syllable type L */
ucp_gbV, /* 7 Hangul syllable type V */
ucp_gbT, /* 8 Hangul syllable type T */
ucp_gbLV, /* 9 Hangul syllable type LV */
ucp_gbLVT, /* 10 Hangul syllable type LVT */
ucp_gbRegionalIndicator, /* 11 */
ucp_gbOther, /* 12 */
ucp_gbZWJ, /* 13 */
ucp_gbExtended_Pictographic /* 14 */
};
/* These are the script identifications. */
@ -184,13 +185,13 @@ enum {
ucp_Tifinagh,
ucp_Ugaritic,
ucp_Yi,
/* New for Unicode 5.0: */
/* New for Unicode 5.0 */
ucp_Balinese,
ucp_Cuneiform,
ucp_Nko,
ucp_Phags_Pa,
ucp_Phoenician,
/* New for Unicode 5.1: */
/* New for Unicode 5.1 */
ucp_Carian,
ucp_Cham,
ucp_Kayah_Li,
@ -202,7 +203,7 @@ enum {
ucp_Saurashtra,
ucp_Sundanese,
ucp_Vai,
/* New for Unicode 5.2: */
/* New for Unicode 5.2 */
ucp_Avestan,
ucp_Bamum,
ucp_Egyptian_Hieroglyphs,
@ -218,11 +219,11 @@ enum {
ucp_Samaritan,
ucp_Tai_Tham,
ucp_Tai_Viet,
/* New for Unicode 6.0.0: */
/* New for Unicode 6.0.0 */
ucp_Batak,
ucp_Brahmi,
ucp_Mandaic,
/* New for Unicode 6.1.0: */
/* New for Unicode 6.1.0 */
ucp_Chakma,
ucp_Meroitic_Cursive,
ucp_Meroitic_Hieroglyphs,
@ -230,7 +231,7 @@ enum {
ucp_Sharada,
ucp_Sora_Sompeng,
ucp_Takri,
/* New for Unicode 7.0.0: */
/* New for Unicode 7.0.0 */
ucp_Bassa_Vah,
ucp_Caucasian_Albanian,
ucp_Duployan,
@ -254,15 +255,34 @@ enum {
ucp_Siddham,
ucp_Tirhuta,
ucp_Warang_Citi,
/* New for Unicode 8.0.0: */
/* New for Unicode 8.0.0 */
ucp_Ahom,
ucp_Anatolian_Hieroglyphs,
ucp_Hatran,
ucp_Multani,
ucp_Old_Hungarian,
ucp_SignWriting
ucp_SignWriting,
/* New for Unicode 10.0.0 (no update since 8.0.0) */
ucp_Adlam,
ucp_Bhaiksuki,
ucp_Marchen,
ucp_Newa,
ucp_Osage,
ucp_Tangut,
ucp_Masaram_Gondi,
ucp_Nushu,
ucp_Soyombo,
ucp_Zanabazar_Square,
/* New for Unicode 11.0.0 */
ucp_Dogra,
ucp_Gunjala_Gondi,
ucp_Hanifi_Rohingya,
ucp_Makasar,
ucp_Medefaidrin,
ucp_Old_Sogdian,
ucp_Sogdian
};
#endif
#endif /* PCRE2_UCP_H_IDEMPOTENT_GUARD */
/* End of pcre2_ucp.h */

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