开源软件构建与测试

Changes of Revision 2

_service:tar_scm:pcre2.spec Changed

@@ -1,6 +1,6 @@
 Name:        pcre2
 Version:     10.42
-Release:     7
+Release:     9
 Summary:     Perl Compatible Regular Expressions
 License:     BSD
 URL:         http://www.pcre.org/
@@ -29,6 +29,8 @@
 Patch6018:     backport-Sanity-checks-for-ctype-functions-342.patch
 Patch6019:     backport-Fix-incorrect-class-character-matches-in-JIT.patch
 Patch6020:     backport-Fixing-an-issue-using-empty-character-sets-in-jit.patch
+Patch6021:     backport-pcre2grep-document-better-possible-multiline-matchin.patch
+Patch6022:     backport-Remove-incorrect-optimization-in-DFA-matching-when-p.patch
 
 BuildRequires:  autoconf libtool automake coreutils gcc make readline-devel
 Obsoletes:      pcre2-utf16 pcre2-utf32 pcre2-tools
@@ -146,6 +148,12 @@
 %{_pkgdocdir}/html/
 
 %changelog
+* Tue Sep 03 2024 dongyuzhen <dongyuzhen@h-partners.com> - 10.42-9
+- DESC:Remove incorrect optimization in DFA matching when partial matching and (*F) are involved
+
+* Tue Jul 23 2024 fuanan <fuanan3@h-partners.com> - 10.42-8
+- DESC:document better possible multiline matching misses
+
 * Tue May 07 2024 xujing <xujing125@huawei.com> - 10.42-7
 - DESC:Fixing an issue using empty character sets in jit

_service:tar_scm:backport-Remove-incorrect-optimization-in-DFA-matching-when-p.patch Added

@@ -0,0 +1,118 @@
+From 674b6640e702705e8e90125f972197fae3aa364d Mon Sep 17 00:00:00 2001
+From: Philip Hazel <Philip.Hazel@gmail.com>
+Date: Sat, 3 Aug 2024 17:18:56 +0100
+Subject: PATCH Remove incorrect optimization in DFA matching when partial
+ matching and (*F) are involved
+ 
+Conflict:don't modify ChangeLog; adapt context
+Reference:https://github.com/PCRE2Project/pcre2/commit/674b6640e702705e8e90125f972197fae3aa364d
+
+---
+ src/pcre2_dfa_match.c | 10 +---------
+ testdata/testinput6   |  9 +++++++++
+ testdata/testoutput6  | 13 +++++++++++++
+ 3 files changed, 23 insertions(+), 9 deletions(-)
+
+diff --git a/src/pcre2_dfa_match.c b/src/pcre2_dfa_match.c
+index 60f6b4f..1c4495f 100644
+--- a/src/pcre2_dfa_match.c
++++ b/src/pcre2_dfa_match.c
+@@ -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) 2016-2022 University of Cambridge
++          New API code Copyright (c) 2016-2024 University of Cambridge
+ 
+ -----------------------------------------------------------------------------
+ Redistribution and use in source and binary forms, with or without
+@@ -693,7 +693,6 @@ for (;;)
+   int i, j;
+   int clen, dlen;
+   uint32_t c, d;
+-  int forced_fail = 0;
+   BOOL partial_newline = FALSE;
+   BOOL could_continue = reset_could_continue;
+   reset_could_continue = FALSE;
+@@ -2765,7 +2764,6 @@ for (;;)
+       though the other "backtracking verbs" are not supported. */
+ 
+       case OP_FAIL:
+-      forced_fail++;    /* Count FAILs for multiple states */
+       break;
+ 
+       case OP_ASSERT:
+@@ -3247,18 +3245,12 @@ for (;;)
+   matches that we are going to find. If partial matching has been requested,
+   check for appropriate conditions.
+ 
+-  The "forced_ fail" variable counts the number of (*F) encountered for the
+-  character. If it is equal to the original active_count (saved in
+-  workspace1) it means that (*F) was found on every active state. In this
+-  case we don't want to give a partial match.
+-
+   The "could_continue" variable is true if a state could have continued but
+   for the fact that the end of the subject was reached. */
+ 
+   if (new_count <= 0)
+     {
+     if (could_continue &&                            /* Some could go on, and */
+-        forced_fail != workspace1 &&               /* Not all forced fail & */
+         (                                            /* either... */
+         (mb->moptions & PCRE2_PARTIAL_HARD) != 0      /* Hard partial */
+         ||                                           /* or... */
+diff --git a/testdata/testinput6 b/testdata/testinput6
+index 0ca0d23..b71a69c 100644
+--- a/testdata/testinput6
++++ b/testdata/testinput6
+@@ -4392,9 +4392,18 @@
+ 
+ /Z(*F)Q|ZXY/
+     Z\=ps
++    XY\=dfa_restart 
+ \= Expect no match 
+     ZA\=ps
+     X\=ps
++    
++/Z(?:(*F)Q|XY)/
++    Z\=ps
++    XY\=dfa_restart 
++    
++/Z(*F)Q|Z(*F)XY/
++\= Expect no match
++    Z\=ps
+ 
+ /\bthe cat\b/
+     the cat\=ps
+diff --git a/testdata/testoutput6 b/testdata/testoutput6
+index 607b572..38c653e 100644
+--- a/testdata/testoutput6
++++ b/testdata/testoutput6
+@@ -6769,11 +6769,24 @@ Partial match: dogs
+ /Z(*F)Q|ZXY/
+     Z\=ps
+ Partial match: Z
++    XY\=dfa_restart 
++ 0: XY
+ \= Expect no match 
+     ZA\=ps
+ No match
+     X\=ps
+ No match
++    
++/Z(?:(*F)Q|XY)/
++    Z\=ps
++Partial match: Z
++    XY\=dfa_restart 
++ 0: XY
++    
++/Z(*F)Q|Z(*F)XY/
++\= Expect no match
++    Z\=ps
++No match
+ 
+ /\bthe cat\b/
+     the cat\=ps
+-- 
+2.43.0
+

_service:tar_scm:backport-pcre2grep-document-better-possible-multiline-matchin.patch Added

@@ -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:don't modify ucptest.c because ucptest.c doesn't exist in current version.
+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
+@@ -1856,7 +1856,7 @@ if (slen > 200)
+ 
+ for (int i = 1; p != NULL; p = p->next, i++)
+   {
+-  int rc = pcre2_match(p->compiled, (PCRE2_SPTR)matchptr, (int)length,
++  int rc = pcre2_match(p->compiled, (PCRE2_SPTR)matchptr, length,
+     startoffset, options, match_data, match_context);
+   if (rc == PCRE2_ERROR_NOMATCH) continue;
+ 
+-- 
+2.27.0
+