rpms/pcre2
6
0
Fork 0
Code Issues Pull Requests Releases Activity

10.32 bump

Browse Source
This commit is contained in:
Petr Písař 2018-09-12 10:26:14 +02:00
parent 19a83faa12
commit cad8e83822
6 changed files with 7 additions and 489 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -12,3 +12,4 @@
/pcre2-10.31-RC1.tar.bz2
/pcre2-10.31.tar.bz2
/pcre2-10.32-RC1.tar.bz2
/pcre2-10.32.tar.bz2

79
pcre-10.32-RC1-Fix-bad-auto-possessification-of-certain-types-of-cl.patch
View File

@ -1,79 +0,0 @@
From 6f2408cec76565406fb17f2cd51e88f92d8dc0b3 Mon Sep 17 00:00:00 2001
From: ph10 <ph10@6239d852-aaf2-0410-a92c-79f79f948069>
Date: Fri, 17 Aug 2018 14:45:35 +0000
Subject: [PATCH] Fix bad auto-possessification of certain types of class.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
git-svn-id: svn://vcs.exim.org/pcre2/code/trunk@986 6239d852-aaf2-0410-a92c-79f79f948069
Petr Písař: Ported to 10.32-RC1.
---
src/pcre2_auto_possess.c | 4 ++--
testdata/testinput4 | 9 +++++++++
testdata/testoutput4 | 12 ++++++++++++
diff --git a/src/pcre2_auto_possess.c b/src/pcre2_auto_possess.c
index 82a43ae..2ce152e 100644
--- a/src/pcre2_auto_possess.c
+++ b/src/pcre2_auto_possess.c
@@ -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
@@ -730,7 +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;
}
diff --git a/testdata/testinput4 b/testdata/testinput4
index 3efb1ff..a27b6af 100644
--- a/testdata/testinput4
+++ b/testdata/testinput4
@@ -2309,4 +2309,13 @@
# -------
+/[^\x{100}-\x{ffff}]*[\x80-\xff]/utf
+ \x{99}\x{99}\x{99}
+
+/[^\x{100}-\x{ffff}ABC]*[\x80-\xff]/utf
+ \x{99}\x{99}\x{99}
+
+/[^\x{100}-\x{ffff}]*[\x80-\xff]/i,utf
+ \x{99}\x{99}\x{99}
+
# End of testinput4
diff --git a/testdata/testoutput4 b/testdata/testoutput4
index db474ef..ba3df37 100644
--- a/testdata/testoutput4
+++ b/testdata/testoutput4
@@ -3730,4 +3730,16 @@ No match
# -------
+/[^\x{100}-\x{ffff}]*[\x80-\xff]/utf
+ \x{99}\x{99}\x{99}
+ 0: \x{99}\x{99}\x{99}
+
+/[^\x{100}-\x{ffff}ABC]*[\x80-\xff]/utf
+ \x{99}\x{99}\x{99}
+ 0: \x{99}\x{99}\x{99}
+
+/[^\x{100}-\x{ffff}]*[\x80-\xff]/i,utf
+ \x{99}\x{99}\x{99}
+ 0: \x{99}\x{99}\x{99}
+
# End of testinput4
--
2.14.4

136
pcre2-10.32-RC1-Fix-anchoring-bug-in-conditionals-with-only-one-bran.patch
View File

@ -1,136 +0,0 @@
From c2d378421fedba48cb02b6b3dc4a74d2a24b2dd4 Mon Sep 17 00:00:00 2001
From: ph10 <ph10@6239d852-aaf2-0410-a92c-79f79f948069>
Date: Sun, 2 Sep 2018 16:53:29 +0000
Subject: [PATCH] Fix anchoring bug in conditionals with only one branch.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
git-svn-id: svn://vcs.exim.org/pcre2/code/trunk@995 6239d852-aaf2-0410-a92c-79f79f948069
Petr Písař: Ported to 10.32-RC1.
---
src/pcre2_compile.c | 11 ++++++-----
testdata/testinput2 | 15 +++++++++++++++
testdata/testoutput2 | 40 ++++++++++++++++++++++++++++++++++++++++
diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c
index f6a7e99..3df55e9 100644
--- a/src/pcre2_compile.c
+++ b/src/pcre2_compile.c
@@ -1454,8 +1454,8 @@ else if ((i = escapes[c - ESCAPES_FIRST]) != 0)
/* \N{U+ can be handled by the \x{ code. However, this construction is
not valid in EBCDIC environments because it specifies a Unicode
character, not a codepoint in the local code. For example \N{U+0041}
- must be "A" in all environments. Also, in Perl, \N{U+ forces Unicode
- casing semantics for the entire pattern, so allow it only in UTF (i.e.
+ must be "A" in all environments. Also, in Perl, \N{U+ forces Unicode
+ casing semantics for the entire pattern, so allow it only in UTF (i.e.
Unicode) mode. */
if (ptrend - p > 1 && *p == CHAR_U && p[1] == CHAR_PLUS)
@@ -1464,12 +1464,12 @@ else if ((i = escapes[c - ESCAPES_FIRST]) != 0)
*errorcodeptr = ERR93;
#else
if (utf)
- {
+ {
ptr = p + 1;
escape = 0; /* Not a fancy escape after all */
goto COME_FROM_NU;
}
- else *errorcodeptr = ERR93;
+ else *errorcodeptr = ERR93;
#endif
}
@@ -7864,10 +7864,11 @@ do {
if (!is_anchored(scode, bracket_map, cb, atomcount, TRUE)) return FALSE;
}
- /* Condition */
+ /* Condition. If there is no second branch, it can't be anchored. */
else if (op == OP_COND)
{
+ if (scode[GET(scode,1)] != OP_ALT) return FALSE;
if (!is_anchored(scode, bracket_map, cb, atomcount, inassert))
return FALSE;
}
diff --git a/testdata/testinput2 b/testdata/testinput2
index 9b59b3e..c0f4292 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -5459,4 +5459,19 @@ a)"xI
/(?x-i-i)/
+/(?(?=^))b/I
+ abc
+
+/(?(?=^)|)b/I
+ abc
+
+/(?(?=^)|^)b/I
+ bbc
+\= Expect no match
+ abc
+
+/(?(1)^|^())/I
+
+/(?(1)^())b/I
+
# End of testinput2
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index d629771..6f0dd12 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -16631,6 +16631,46 @@ Failed: error 194 at offset 3: invalid hyphen in option setting
/(?x-i-i)/
Failed: error 194 at offset 5: invalid hyphen in option setting
+/(?(?=^))b/I
+Capturing subpattern count = 0
+Last code unit = 'b'
+Subject length lower bound = 1
+ abc
+ 0: b
+
+/(?(?=^)|)b/I
+Capturing subpattern count = 0
+First code unit = 'b'
+Subject length lower bound = 1
+ abc
+ 0: b
+
+/(?(?=^)|^)b/I
+Capturing subpattern count = 0
+Compile options: <none>
+Overall options: anchored
+First code unit = 'b'
+Subject length lower bound = 1
+ bbc
+ 0: b
+\= Expect no match
+ abc
+No match
+
+/(?(1)^|^())/I
+Capturing subpattern count = 1
+Max back reference = 1
+May match empty string
+Compile options: <none>
+Overall options: anchored
+Subject length lower bound = 0
+
+/(?(1)^())b/I
+Capturing subpattern count = 1
+Max back reference = 1
+Last code unit = 'b'
+Subject length lower bound = 1
+
# End of testinput2
Error -70: PCRE2_ERROR_BADDATA (unknown error number)
Error -62: bad serialized data
--
2.14.4

258
pcre2-10.32-RC1-Lock-out-N-U-hhhh-in-non-UTF-non-Unicode-modes.patch
View File

@ -1,258 +0,0 @@
From 11ad23b7e6f2b3b81bc7e1e605e34416b5b900ff Mon Sep 17 00:00:00 2001
From: ph10 <ph10@6239d852-aaf2-0410-a92c-79f79f948069>
Date: Sun, 2 Sep 2018 16:03:27 +0000
Subject: [PATCH] Lock out \N{U+hhhh} in non-UTF (non-Unicode) modes.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
git-svn-id: svn://vcs.exim.org/pcre2/code/trunk@994 6239d852-aaf2-0410-a92c-79f79f948069
Signed-off-by: Petr Písař <ppisar@redhat.com>
---
ChangeLog | 2 +-
doc/pcre2api.3 | 5 +++--
doc/pcre2pattern.3 | 16 +++++++++-------
doc/pcre2syntax.3 | 6 +++---
doc/pcre2unicode.3 | 13 +++++++++----
src/pcre2.h.in | 2 +-
src/pcre2_compile.c | 14 ++++++++++----
src/pcre2_error.c | 2 +-
testdata/testinput5 | 2 ++
testdata/testoutput5 | 3 +++
10 files changed, 42 insertions(+), 23 deletions(-)
diff --git a/ChangeLog b/ChangeLog
index 264bfae..4b55639 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -130,7 +130,7 @@ present.
28. A (*MARK) name was not being passed back for positive assertions that were
terminated by (*ACCEPT).
-29. Add support for \N{U+dddd}, but not in EBCDIC environments.
+29. Add support for \N{U+dddd}, but only in Unicode mode.
30. Add support for (?^) for unsetting all imnsx options.
diff --git a/doc/pcre2api.3 b/doc/pcre2api.3
index 5a97739..fff4fcc 100644
--- a/doc/pcre2api.3
+++ b/doc/pcre2api.3
@@ -1,4 +1,4 @@
-.TH PCRE2API 3 "03 August 2018" "PCRE2 10.32"
+.TH PCRE2API 3 "02 September 2018" "PCRE2 10.32"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.sp
@@ -1756,7 +1756,8 @@ behaviour of PCRE2 are given in the
.\" HREF
\fBpcre2unicode\fP
.\"
-page.
+page. In particular, note that it changes the way PCRE2_CASELESS handles
+characters with code points greater than 127.
.
.
.\" HTML <a name="extracompileoptions"></a>
diff --git a/doc/pcre2pattern.3 b/doc/pcre2pattern.3
index aa0d652..fd086b4 100644
--- a/doc/pcre2pattern.3
+++ b/doc/pcre2pattern.3
@@ -1,4 +1,4 @@
-.TH PCRE2PATTERN 3 "03 August 2018" "PCRE2 10.32"
+.TH PCRE2PATTERN 3 "02 September 2018" "PCRE2 10.32"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.SH "PCRE2 REGULAR EXPRESSION DETAILS"
@@ -376,14 +376,15 @@ these escapes are as follows:
\eddd character with octal code ddd, or backreference
\eo{ddd..} character with octal code ddd..
\exhh character with hex code hh
- \ex{hhh..} character with hex code hhh.. (default mode)
- \eN{U+hhh..} character with Unicode code point hhh..
+ \ex{hhh..} character with hex code hhh..
+ \eN{U+hhh..} character with Unicode hex code point hhh..
\euhhhh character with hex code hhhh (when PCRE2_ALT_BSUX is set)
.sp
+The \eN{U+hhh..} escape sequence is recognized only when the PCRE2_UTF option
+is set, that is, when PCRE2 is operating in a Unicode mode. Perl also uses
+\eN{name} to specify characters by Unicode name; PCRE2 does not support this.
Note that when \eN is not followed by an opening brace (curly bracket) it has
an entirely different meaning, matching any character that is not a newline.
-Perl also uses \eN{name} to specify characters by Unicode name; PCRE2 does not
-support this.
.P
The precise effect of \ecx on ASCII characters is as follows: if x is a lower
case letter, it is converted to upper case. Then bit 6 of the character (hex
@@ -509,7 +510,8 @@ limited to certain values, as follows:
Invalid Unicode code points are all those in the range 0xd800 to 0xdfff (the
so-called "surrogate" code points). The check for these can be disabled by the
caller of \fBpcre2_compile()\fP by setting the option
-PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES.
+PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES. However, this is possible only in UTF-8
+and UTF-32 modes, because these values are not representable in UTF-16.
.
.
.SS "Escape sequences in character classes"
@@ -3650,6 +3652,6 @@ Cambridge, England.
.rs
.sp
.nf
-Last updated: 03 August 2018
+Last updated: 02 September 2018
Copyright (c) 1997-2018 University of Cambridge.
.fi
diff --git a/doc/pcre2syntax.3 b/doc/pcre2syntax.3
index e5ace25..c392bfb 100644
--- a/doc/pcre2syntax.3
+++ b/doc/pcre2syntax.3
@@ -1,4 +1,4 @@
-.TH PCRE2SYNTAX 3 "01 August 2018" "PCRE2 10.32"
+.TH PCRE2SYNTAX 3 "02 September 2018" "PCRE2 10.32"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.SH "PCRE2 REGULAR EXPRESSION SYNTAX SUMMARY"
@@ -35,7 +35,7 @@ This table applies to ASCII and Unicode environments.
\eddd character with octal code ddd, or backreference
\eo{ddd..} character with octal code ddd..
\eU "U" if PCRE2_ALT_BSUX is set (otherwise is an error)
- \eN{U+hh..} character with Unicode code point hh..
+ \eN{U+hh..} character with Unicode code point hh.. (Unicode mode only)
\euhhhh character with hex code hhhh (if PCRE2_ALT_BSUX is set)
\exhh character with hex code hh
\ex{hh..} character with hex code hh..
@@ -621,6 +621,6 @@ Cambridge, England.
.rs
.sp
.nf
-Last updated: 01 August 2018
+Last updated: 02 September 2018
Copyright (c) 1997-2018 University of Cambridge.
.fi
diff --git a/doc/pcre2unicode.3 b/doc/pcre2unicode.3
index fdaddc4..edd8dcd 100644
--- a/doc/pcre2unicode.3
+++ b/doc/pcre2unicode.3
@@ -1,4 +1,4 @@
-.TH PCRE2UNICODE 3 "17 May 2017" "PCRE2 10.30"
+.TH PCRE2UNICODE 3 "02 September 2018" "PCRE2 10.32"
.SH NAME
PCRE - Perl-compatible regular expressions (revised API)
.SH "UNICODE AND UTF SUPPORT"
@@ -16,7 +16,8 @@ you must call
with the PCRE2_UTF option flag, or the pattern must start with the sequence
(*UTF). When either of these is the case, both the pattern and any subject
strings that are matched against it are treated as UTF strings instead of
-strings of individual one-code-unit characters.
+strings of individual one-code-unit characters. There are also some other
+changes to the way characters are handled, as documented below.
.P
If you do not need Unicode support you can build PCRE2 without it, in which
case the library will be smaller.
@@ -51,6 +52,10 @@ unbraced hexadecimal escape sequences (for example, \ex{b3} or \exb3). Larger
values have to use braced sequences. Unbraced octal code points up to \e777 are
also recognized; larger ones can be coded using \eo{...}.
.P
+The escape sequence \eN{U+<hex digits>} is recognized as another way of
+specifying a Unicode character by code point in a UTF mode. It is not allowed
+in non-UTF modes.
+.P
In UTF modes, repeat quantifiers apply to complete UTF characters, not to
individual code units.
.P
@@ -280,6 +285,6 @@ Cambridge, England.
.rs
.sp
.nf
-Last updated: 17 May 2017
-Copyright (c) 1997-2017 University of Cambridge.
+Last updated: 02 September 2018
+Copyright (c) 1997-2018 University of Cambridge.
.fi
diff --git a/src/pcre2.h.in b/src/pcre2.h.in
index 4c7c674..a9396e0 100644
--- a/src/pcre2.h.in
+++ b/src/pcre2.h.in
@@ -316,7 +316,7 @@ pcre2_pattern_convert(). */
#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_NOT_SUPPORTED_IN_EBCDIC 193
+#define PCRE2_ERROR_SUPPORTED_ONLY_IN_UNICODE 193
#define PCRE2_ERROR_INVALID_HYPHEN_IN_OPTIONS 194
diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c
index 8c30064..f6a7e99 100644
--- a/src/pcre2_compile.c
+++ b/src/pcre2_compile.c
@@ -1454,16 +1454,22 @@ else if ((i = escapes[c - ESCAPES_FIRST]) != 0)
/* \N{U+ can be handled by the \x{ code. However, this construction is
not valid in EBCDIC environments because it specifies a Unicode
character, not a codepoint in the local code. For example \N{U+0041}
- must be "A" in all environments. */
+ must be "A" in all environments. Also, in Perl, \N{U+ forces Unicode
+ casing semantics for the entire pattern, so allow it only in UTF (i.e.
+ Unicode) mode. */
if (ptrend - p > 1 && *p == CHAR_U && p[1] == CHAR_PLUS)
{
#ifdef EBCDIC
*errorcodeptr = ERR93;
#else
- ptr = p + 1;
- escape = 0; /* Not a fancy escape after all */
- goto COME_FROM_NU;
+ if (utf)
+ {
+ ptr = p + 1;
+ escape = 0; /* Not a fancy escape after all */
+ goto COME_FROM_NU;
+ }
+ else *errorcodeptr = ERR93;
#endif
}
diff --git a/src/pcre2_error.c b/src/pcre2_error.c
index 64ab5d9..4b3b3f1 100644
--- a/src/pcre2_error.c
+++ b/src/pcre2_error.c
@@ -179,7 +179,7 @@ static const unsigned char compile_error_texts[] =
"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 not supported in EBCDIC mode\0"
+ "\\N{U+dddd} is supported only in Unicode (UTF) mode\0"
"invalid hyphen in option setting\0"
;
diff --git a/testdata/testinput5 b/testdata/testinput5
index e339808..687de32 100644
--- a/testdata/testinput5
+++ b/testdata/testinput5
@@ -2089,6 +2089,8 @@
/\N{U+}/
+/\N{U+}/utf
+
/\N{U}/
# This tests the non-UTF Unicode NEL pattern whitespace character, only
diff --git a/testdata/testoutput5 b/testdata/testoutput5
index a9552f4..51caa18 100644
--- a/testdata/testoutput5
+++ b/testdata/testoutput5
@@ -4751,6 +4751,9 @@ No match
0: \x{1d1aa}
/\N{U+}/
+Failed: error 193 at offset 2: \N{U+dddd} is supported only in Unicode (UTF) mode
+
+/\N{U+}/utf
Failed: error 178 at offset 5: digits missing in \x{} or \o{} or \N{U+}
/\N{U}/
--
2.14.4

20
pcre2.spec
View File

@ -6,10 +6,10 @@
%bcond_with pcre2_enables_sealloc
# This is stable release:
%global rcversion RC1
#%%global rcversion RC1
Name: pcre2
Version: 10.32
Release: %{?rcversion:0.}3%{?rcversion:.%rcversion}%{?dist}
Release: %{?rcversion:0.}1%{?rcversion:.%rcversion}%{?dist}
%global myversion %{version}%{?rcversion:-%rcversion}
Summary: Perl-compatible regular expression library
# the library: BSD with exceptions
@ -49,16 +49,6 @@ URL: http://www.pcre.org/
Source: ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/%{?rcversion:Testing/}%{name}-%{myversion}.tar.bz2
# Do no set RPATH if libdir is not /usr/lib
Patch0: pcre2-10.10-Fix-multilib.patch
# Fix autopossessifying a repeated negative class with no characters less than
# 256 that is followed by a positive class with only characters less than 256,
# upstream bug #2300, in upstream after 10.32-RC1
Patch1: pcre-10.32-RC1-Fix-bad-auto-possessification-of-certain-types-of-cl.patch
# Accept \N{U+hhhh} only in UTF mode, upstream bug #2305,
# in upstream after 10.32-RC1
Patch2: pcre2-10.32-RC1-Lock-out-N-U-hhhh-in-non-UTF-non-Unicode-modes.patch
# Fix anchoring in conditionals with only one branch, upstream bug #2307,
# in upstream after 10.32-RC1
Patch3: pcre2-10.32-RC1-Fix-anchoring-bug-in-conditionals-with-only-one-bran.patch
BuildRequires: autoconf
BuildRequires: automake
BuildRequires: coreutils
@ -135,9 +125,6 @@ Utilities demonstrating PCRE2 capabilities like pcre2grep or pcre2test.
%prep
%setup -q -n %{name}-%{myversion}
%patch0 -p1
%patch1 -p1
%patch2 -p1
%patch3 -p1
# Because of multilib patch
libtoolize --copy --force
autoreconf -vif
@ -240,6 +227,9 @@ make %{?_smp_mflags} check VERBOSE=yes
%{_mandir}/man1/pcre2test.*
%changelog
* Wed Sep 12 2018 Petr Pisar <ppisar@redhat.com> - 10.32-1
- 10.32 bump
* Mon Sep 03 2018 Petr Pisar <ppisar@redhat.com> - 10.32-0.3.RC1
- Accept \N{U+hhhh} only in UTF mode (upstream bug #2305)
- Fix anchoring in conditionals with only one branch (upstream bug #2307)

2
sources
View File

@ -1 +1 @@
SHA512 (pcre2-10.32-RC1.tar.bz2) = 387d9060eef3553d254b48d510859f028eed0f6fbdc7b5067b7d84ec81ed9356972defdb97dce5f28e6188421336f77052700eb530caf8c6e245b079b8258558
SHA512 (pcre2-10.32.tar.bz2) = 3d712e7d6afbaef227952680ded69fadbdec0b1abdfcac17cf071415c3c93edd152d6d268dec80570aedf24f82ba954f74f5f9e62c9b9991be75080a3d6ab5fe