sync community patchs

backport-Fix-an-invalid-match-of-ascii-word-classes-when-inva.patch

@@ -0,0 +1,41 @@
+From 2c08b619dc973beacc474dcb67cda8cd366200ce Mon Sep 17 00:00:00 2001
+From: Zoltan Herczeg <hzmester@freemail.hu>
+Date: Tue, 11 Apr 2023 12:42:11 +0000
+Subject: [PATCH] Fix an invalid match of ascii word classes when invalid utf
+ is enabled
+
+Fixes #224
+Conflict:delete changelog
+Reference:https://github.com/PCRE2Project/pcre2/commit/2c08b619dc973beacc474dcb67cda8cd366200ce
+---
+ src/pcre2_jit_compile.c | 1 +
+ src/pcre2_jit_test.c    | 1 +
+ 2 files changed, 2 insertions(+)
+
+diff --git a/src/pcre2_jit_compile.c b/src/pcre2_jit_compile.c
+index 75ba610..81b7a93 100644
+--- a/src/pcre2_jit_compile.c
++++ b/src/pcre2_jit_compile.c
+@@ -4132,6 +4132,7 @@ if (negated)
+ 
+   if (common->invalid_utf)
+     {
++    OP1(SLJIT_MOV, TMP1, 0, TMP2, 0);
+     add_jump(compiler, &common->utfreadchar_invalid, JUMP(SLJIT_FAST_CALL));
+     add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, INVALID_UTF_CHAR));
+     OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, 0);
+diff --git a/src/pcre2_jit_test.c b/src/pcre2_jit_test.c
+index e1f0bbc..1a1f6c5 100644
+--- a/src/pcre2_jit_test.c
++++ b/src/pcre2_jit_test.c
+@@ -1979,6 +1979,7 @@ static const struct invalid_utf8_regression_test_case invalid_utf8_regression_te
+ 	{ PCRE2_UTF, CI, 0, 0, 0, 7, 11, { "#\xc7\x85#", NULL }, "\x80\x80#\xc7\x80\x80\x80#\xc7\x85#" },
+ 
+ 	{ PCRE2_UTF | PCRE2_UCP, CI, 0, 0, 0, -1, -1, { "[\\s]", NULL }, "\xed\xa0\x80" },
++	{ PCRE2_UTF, CI, 0, 0, 0, 1, 4, { "[\\D]", NULL }, "@\xe0\xab\xaa@" },
+ 
+ 	/* These two are not invalid UTF tests, but this infrastructure fits better for them. */
+ 	{ 0, PCRE2_JIT_COMPLETE, 0, 0, 1, -1, -1, { "\\X{2}", NULL }, "\r\n\n" },
+-- 
+2.27.0
+

backport-fix-wrong-test.patch

@@ -0,0 +1,24 @@
+From a8558f252e8d8b3fd52d1dc8ea46ecefd991a187 Mon Sep 17 00:00:00 2001
+From: Zoltan Herczeg <hzmester@freemail.hu>
+Date: Tue, 11 Apr 2023 12:55:01 +0000
+Subject: [PATCH] Fix wrong test
+
+Conflict:NA
+Reference:https://github.com/PCRE2Project/pcre2/commit/a8558f252e8d8b3fd52d1dc8ea46ecefd991a187
+---
+ src/pcre2_jit_test.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/src/pcre2_jit_test.c b/src/pcre2_jit_test.c
+index 7a83bc02..331ed6d4 100644
+--- a/src/pcre2_jit_test.c
++++ b/src/pcre2_jit_test.c
+@@ -1981,7 +1981,7 @@ static const struct invalid_utf8_regression_test_case invalid_utf8_regression_te
+ 	{ PCRE2_UTF, CI, 0, 0, 0, 7, 11, { "#\xc7\x85#", NULL }, "\x80\x80#\xc7\x80\x80\x80#\xc7\x85#" },
+ 
+ 	{ PCRE2_UTF | PCRE2_UCP, CI, 0, 0, 0, -1, -1, { "[\\s]", NULL }, "\xed\xa0\x80" },
+-	{ PCRE2_UTF, CI, 0, 0, 0, 1, 4, { "[\\D]", NULL }, "@\xe0\xab\xaa@" },
++	{ PCRE2_UTF, CI, 0, 0, 0, 0, 3, { "[\\D]", NULL }, "\xe0\xab\xaa@" },
+ 
+ 	/* These two are not invalid UTF tests, but this infrastructure fits better for them. */
+ 	{ 0, PCRE2_JIT_COMPLETE, 0, 0, 1, -1, -1, { "\\X{2}", NULL }, "\r\n\n" },

backport-no-partial-match-if-trailing-data-is-invalid-utf-238.patch

@@ -0,0 +1,205 @@
+From 1bb1ef67eff000fe4aa8c1c45289938188e11e48 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Carlo=20Marcelo=20Arenas=20Bel=C3=B3n?= <carenas@gmail.com>
+Date: Fri, 21 Apr 2023 01:12:45 -0700
+Subject: [PATCH] no partial match if trailing data is invalid utf (#238)
+
+Avoid returning a partial match if one was found but followed by invalid
+UTF, making the result consistent with JIT and unlike:
+
+  PCRE2 version 10.34 2019-11-21
+    re> /.a/match_invalid_utf,allvector,jit
+  data> b\xb1\=ph,ovector=1
+  No match
+   0: <unchanged>
+  data> b\xb1\=ph,ovector=1,no_jit
+  Partial match: b\x{b1}
+  ** ovector[1] is not equal to the subject length: 1 != 2
+   0: 0 1
+
+Conflict:NA
+Reference:https://github.com/PCRE2Project/pcre2/commit/1bb1ef67eff000fe4aa8c1c45289938188e11e48
+---
+ src/pcre2_match.c        |  1 +
+ testdata/testinput10     | 19 +++++++++++++++++++
+ testdata/testinput12     | 14 ++++++++++++++
+ testdata/testoutput10    | 32 ++++++++++++++++++++++++++++++++
+ testdata/testoutput12-16 | 22 ++++++++++++++++++++++
+ testdata/testoutput12-32 | 22 ++++++++++++++++++++++
+ 6 files changed, 110 insertions(+)
+
+diff --git a/src/pcre2_match.c b/src/pcre2_match.c
+index ea98af3c..afe3036b 100644
+--- a/src/pcre2_match.c
++++ b/src/pcre2_match.c
+@@ -7454,6 +7454,7 @@ if (utf && end_subject != true_end_subject &&
+     if (start_match >= true_end_subject)
+       {
+       rc = MATCH_NOMATCH;  /* In case it was partial */
++      match_partial = NULL;
+       break;
+       }
+ 
+diff --git a/testdata/testinput10 b/testdata/testinput10
+index 53e37cbc..27321e37 100644
+--- a/testdata/testinput10
++++ b/testdata/testinput10
+@@ -506,6 +506,25 @@
+ \= Expect no match
+     ab\x80cdef\=ph
+ 
++/.a/match_invalid_utf
++    ab\=ph
++    ab\=ps
++    b\xf0\x91\x88b\=ph
++    b\xf0\x91\x88b\=ps
++    b\xf0\x91\x88\xb4a
++\= Expect no match
++    b\x80\=ph
++    b\x80\=ps
++    b\xf0\x91\x88\=ph
++    b\xf0\x91\x88\=ps
++
++/.a$/match_invalid_utf
++    ab\=ph
++    ab\=ps
++\= Expect no match
++    b\xf0\x91\x98\=ph
++    b\xf0\x91\x98\=ps
++
+ /ab$/match_invalid_utf
+     ab\x80cdeab
+ \= Expect no match
+diff --git a/testdata/testinput12 b/testdata/testinput12
+index 9b4f8d34..7a85eb57 100644
+--- a/testdata/testinput12
++++ b/testdata/testinput12
+@@ -413,6 +413,20 @@
+ \= Expect no match
+     ab\x{df00}cdef\=ph
+ 
++/.a/match_invalid_utf
++    ab\=ph
++    ab\=ps
++\= Expect no match
++    b\x{df00}\=ph
++    b\x{df00}\=ps
++
++/.a$/match_invalid_utf
++    ab\=ph
++    ab\=ps
++\= Expect no match
++    b\x{df00}\=ph
++    b\x{df00}\=ps
++
+ /ab$/match_invalid_utf
+     ab\x{df00}cdeab
+ \= Expect no match
+diff --git a/testdata/testoutput10 b/testdata/testoutput10
+index d4085106..1f4c876b 100644
+--- a/testdata/testoutput10
++++ b/testdata/testoutput10
+@@ -1646,6 +1646,38 @@ Partial match: ab
+     ab\x80cdef\=ph
+ No match
+ 
++/.a/match_invalid_utf
++    ab\=ph
++Partial match: b
++    ab\=ps
++Partial match: b
++    b\xf0\x91\x88b\=ph
++Partial match: b
++    b\xf0\x91\x88b\=ps
++Partial match: b
++    b\xf0\x91\x88\xb4a
++ 0: \x{11234}a
++\= Expect no match
++    b\x80\=ph
++No match
++    b\x80\=ps
++No match
++    b\xf0\x91\x88\=ph
++No match
++    b\xf0\x91\x88\=ps
++No match
++
++/.a$/match_invalid_utf
++    ab\=ph
++Partial match: b
++    ab\=ps
++Partial match: b
++\= Expect no match
++    b\xf0\x91\x98\=ph
++No match
++    b\xf0\x91\x98\=ps
++No match
++
+ /ab$/match_invalid_utf
+     ab\x80cdeab
+  0: ab
+diff --git a/testdata/testoutput12-16 b/testdata/testoutput12-16
+index 84c48581..98676324 100644
+--- a/testdata/testoutput12-16
++++ b/testdata/testoutput12-16
+@@ -1522,6 +1522,28 @@ Partial match: ab
+     ab\x{df00}cdef\=ph
+ No match
+ 
++/.a/match_invalid_utf
++    ab\=ph
++Partial match: b
++    ab\=ps
++Partial match: b
++\= Expect no match
++    b\x{df00}\=ph
++No match
++    b\x{df00}\=ps
++No match
++
++/.a$/match_invalid_utf
++    ab\=ph
++Partial match: b
++    ab\=ps
++Partial match: b
++\= Expect no match
++    b\x{df00}\=ph
++No match
++    b\x{df00}\=ps
++No match
++
+ /ab$/match_invalid_utf
+     ab\x{df00}cdeab
+  0: ab
+diff --git a/testdata/testoutput12-32 b/testdata/testoutput12-32
+index 03b6e394..3a20dd4b 100644
+--- a/testdata/testoutput12-32
++++ b/testdata/testoutput12-32
+@@ -1520,6 +1520,28 @@ Partial match: ab
+     ab\x{df00}cdef\=ph
+ No match
+ 
++/.a/match_invalid_utf
++    ab\=ph
++Partial match: b
++    ab\=ps
++Partial match: b
++\= Expect no match
++    b\x{df00}\=ph
++No match
++    b\x{df00}\=ps
++No match
++
++/.a$/match_invalid_utf
++    ab\=ph
++Partial match: b
++    ab\=ps
++Partial match: b
++\= Expect no match
++    b\x{df00}\=ph
++No match
++    b\x{df00}\=ps
++No match
++
+ /ab$/match_invalid_utf
+     ab\x{df00}cdeab
+  0: ab

backport-pcre2grep-document-better-possible-multiline-matchin.patch

@@ -0,0 +1,84 @@
+From 1bc34ffa64c33381d793fb5cdddf3f484e603d23 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Carlo=20Marcelo=20Arenas=20Bel=C3=B3n?= <carenas@gmail.com>
+Date: Fri, 12 May 2023 07:54:02 -0700
+Subject: [PATCH] pcre2grep: document better possible multiline matching misses
+ (#252)
+
+While at it, remove a misplaced cast that would cause problems for
+subjects over 2GB and a few typos.
+
+Conflict:adapt context
+Reference:https://github.com/PCRE2Project/pcre2/commit/1bc34ffa64c33381d793fb5cdddf3f484e603d23
+---
+ doc/pcre2grep.1     | 11 ++++++++---
+ src/pcre2_compile.c |  4 ++--
+ src/pcre2grep.c     |  2 +-
+ 3 files changed, 11 insertions(+), 6 deletions(-)
+
+diff --git a/doc/pcre2grep.1 b/doc/pcre2grep.1
+index 1081591..5077304 100644
+--- a/doc/pcre2grep.1
++++ b/doc/pcre2grep.1
+@@ -66,6 +66,9 @@ The block of memory that is actually used is three times the "buffer size", to
+ allow for buffering "before" and "after" lines. If the buffer size is too
+ small, fewer than requested "before" and "after" lines may be output.
+ .P
++When matching with a multiline pattern, the size of the buffer must be at least
++half of the maximum match expected or the pattern might fail to match.
++.P
+ Patterns can be no longer than 8KiB or BUFSIZ bytes, whichever is the greater.
+ BUFSIZ is defined in \fB<stdio.h>\fP. When there is more than one pattern
+ (specified by the use of \fB-e\fP and/or \fB-f\fP), each pattern is applied to
+@@ -201,7 +204,7 @@ exactly the same as the number of lines that would have been output, but if the
+ \fB-M\fP (multiline) option is used (without \fB-v\fP), there may be more
+ suppressed lines than the count (that is, the number of matches).
+ .sp
+-If no lines are selected, the number zero is output. If several files are are
++If no lines are selected, the number zero is output. If several files are
+ being scanned, a count is output for each of them and the \fB-t\fP option can
+ be used to cause a total to be output at the end. However, if the
+ \fB--files-with-matches\fP option is also used, only those files whose counts
+@@ -490,8 +493,10 @@ well as possibly handling a two-character newline sequence.
+ .sp
+ There is a limit to the number of lines that can be matched, imposed by the way
+ that \fBpcre2grep\fP buffers the input file as it scans it. With a sufficiently
+-large processing buffer, this should not be a problem, but the \fB-M\fP option
+-does not work when input is read line by line (see \fB--line-buffered\fP.)
++large processing buffer, this should not be a problem.
++.sp
++The \fB-M\fP option does not work when input is read line by line (see
++\fB--line-buffered\fP.)
+ .TP
+ \fB-m\fP \fInumber\fP, \fB--max-count\fP=\fInumber\fP
+ Stop processing after finding \fInumber\fP matching lines, or non-matching
+diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c
+index b906dc0..c6d4c60 100644
+--- a/src/pcre2_compile.c
++++ b/src/pcre2_compile.c
+@@ -5549,8 +5549,8 @@ for (;; pptr++)
+ 
+     If the class contains characters outside the 0-255 range, a different
+     opcode is compiled. It may optionally have a bit map for characters < 256,
+-    but those above are are explicitly listed afterwards. A flag code unit
+-    tells whether the bitmap is present, and whether this is a negated class or
++    but those above are explicitly listed afterwards. A flag code unit tells
++    whether the bitmap is present, and whether this is a negated class or
+     not. */
+ 
+     case META_CLASS_NOT:
+diff --git a/src/pcre2grep.c b/src/pcre2grep.c
+index 1484d67..d2ab620 100644
+--- a/src/pcre2grep.c
++++ b/src/pcre2grep.c
+@@ -1843,7 +1843,7 @@ if (slen > 200)
+ 
+ for (i = 1; p != NULL; p = p->next, i++)
+   {
+-  *mrc = pcre2_match(p->compiled, (PCRE2_SPTR)matchptr, (int)length,
++  *mrc = pcre2_match(p->compiled, (PCRE2_SPTR)matchptr, length,
+     startoffset, options, match_data, match_context);
+   if (*mrc >= 0) return TRUE;
+   if (*mrc == PCRE2_ERROR_NOMATCH) continue;
+-- 
+2.27.0
+

pcre2.spec

@@ -1,6 +1,6 @@
 Name:        pcre2
 Version:     10.40
-Release:     3
+Release:     4
 Summary:     Perl Compatible Regular Expressions
 License:     BSD
 URL:         http://www.pcre.org/
@@ -16,6 +16,10 @@ Patch6014:     backport-Add-an-ifdef-to-avoid-the-need-even-to-link-with-pcr.pat
 Patch6015:     backport-Fixed-an-issue-in-the-backtracking-optimization-of-c.patch
 Patch6016:     backport-jit-fail-early-in-ffcps_-if-subject-shorter-than-off.patch
 Patch6017:     backport-jit-fix-pcre2_jit_free_unused_memory-if-sljit-not-us.patch
+Patch6018:     backport-pcre2grep-document-better-possible-multiline-matchin.patch
+Patch6019:     backport-no-partial-match-if-trailing-data-is-invalid-utf-238.patch
+Patch6020:     backport-Fix-an-invalid-match-of-ascii-word-classes-when-inva.patch
+Patch6021:     backport-fix-wrong-test.patch
 
 BuildRequires:  autoconf libtool automake coreutils gcc make readline-devel
 Obsoletes:      pcre2-utf16 pcre2-utf32 pcre2-tools
@@ -132,6 +136,9 @@ make check
 %{_pkgdocdir}/html/
 
 %changelog
+* Mon Jun 26 2023 yangmingtai <yangmingtai@huawei.com> - 10.40-4
+- DESC:sync community patches
+
 * Thu Mar 16 2023 yangmingtai <yangmingtai@huawei.com> - 10.40-3
 - DESC:sync community patches