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

8.40-RC1 bump

Browse Source
This commit is contained in:
Petr Písař 2016-12-12 14:56:30 +01:00
parent acfd08086a
commit 4949309617
12 changed files with 8 additions and 900 deletions

1
.gitignore vendored
View File

@ -26,3 +26,4 @@ pcre-8.10.tar.bz2
/pcre-8.38.tar.bz2
/pcre-8.39-RC1.tar.bz2
/pcre-8.39.tar.bz2
/pcre-8.40-RC1.tar.bz2

49
pcre-8.39-Document-assertion-capture-limitation.patch
View File

@ -1,49 +0,0 @@
From ee124b6b235a560fc5bfc18cc27e280af7e021d2 Mon Sep 17 00:00:00 2001
From: ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15>
Date: Sun, 23 Oct 2016 15:44:15 +0000
Subject: [PATCH] Document assertion capture limitation.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1671 2f5784b3-3f2a-0410-8824-cb99058d5e15
Signed-off-by: Petr Písař <ppisar@redhat.com>
---
doc/pcrepattern.3 | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/doc/pcrepattern.3 b/doc/pcrepattern.3
index 1e25371..c221682 100644
--- a/doc/pcrepattern.3
+++ b/doc/pcrepattern.3
@@ -1,4 +1,4 @@
-.TH PCREPATTERN 3 "14 October 2016" "PCRE 8.40"
+.TH PCREPATTERN 3 "23 October 2016" "PCRE 8.40"
.SH NAME
PCRE - Perl-compatible regular expressions
.SH "PCRE REGULAR EXPRESSION DETAILS"
@@ -2167,6 +2167,13 @@ numbering the capturing subpatterns in the whole pattern. However, substring
capturing is carried out only for positive assertions. (Perl sometimes, but not
always, does do capturing in negative assertions.)
.P
+WARNING: If a positive assertion containing one or more capturing subpatterns
+succeeds, but failure to match later in the pattern causes backtracking over
+this assertion, the captures within the assertion are reset only if no higher
+numbered captures are already set. This is, unfortunately, a fundamental
+limitation of the current implementation, and as PCRE1 is now in
+maintenance-only status, it is unlikely ever to change.
+.P
For compatibility with Perl, assertion subpatterns may be repeated; though
it makes no sense to assert the same thing several times, the side effect of
capturing parentheses may occasionally be useful. In practice, there only three
@@ -3292,6 +3299,6 @@ Cambridge CB2 3QH, England.
.rs
.sp
.nf
-Last updated: 14 October 2016
+Last updated: 23 October 2016
Copyright (c) 1997-2016 University of Cambridge.
.fi
--
2.7.4

80
pcre-8.39-Fix-bad-conditional-recursion-test-bug-when-a-group-.patch
View File

@ -1,80 +0,0 @@
From a2d87770aebc2ba13d6943ff1fcfae0fc26a3134 Mon Sep 17 00:00:00 2001
From: ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15>
Date: Thu, 13 Oct 2016 16:00:48 +0000
Subject: [PATCH] Fix bad conditional recursion test bug when a group with name
starting "R" exists.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1667 2f5784b3-3f2a-0410-8824-cb99058d5e15
Petr Písař: Ported to 8.39.
diff --git a/pcre_compile.c b/pcre_compile.c
index fb80ed1..67c74e8 100644
--- a/pcre_compile.c
+++ b/pcre_compile.c
@@ -6951,7 +6951,8 @@ for (;; ptr++)
slot = cd->name_table;
for (i = 0; i < cd->names_found; i++)
{
- if (STRNCMP_UC_UC(name, slot+IMM2_SIZE, namelen) == 0) break;
+ if (STRNCMP_UC_UC(name, slot+IMM2_SIZE, namelen) == 0 &&
+ slot[IMM2_SIZE+namelen] == 0) break;
slot += cd->name_entry_size;
}
diff --git a/testdata/testinput2 b/testdata/testinput2
index 75e402e..38346ef 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -4243,4 +4243,8 @@ backtracking verbs. --/
/\N(?(?C)0?!.)*/
+/(?<RA>abc)(?(R)xyz)/BZ
+
+/(?<R>abc)(?(R)xyz)/BZ
+
/-- End of testinput2 --/
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index 5e88d1a..216bff8 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -14670,4 +14670,32 @@ No match
/\N(?(?C)0?!.)*/
Failed: assertion expected after (?( or (?(?C) at offset 4
+/(?<RA>abc)(?(R)xyz)/BZ
+------------------------------------------------------------------
+ Bra
+ CBra 1
+ abc
+ Ket
+ Cond
+ Cond recurse any
+ xyz
+ Ket
+ Ket
+ End
+------------------------------------------------------------------
+
+/(?<R>abc)(?(R)xyz)/BZ
+------------------------------------------------------------------
+ Bra
+ CBra 1
+ abc
+ Ket
+ Cond
+ 1 Cond ref
+ xyz
+ Ket
+ Ket
+ End
+------------------------------------------------------------------
+
/-- End of testinput2 --/
--
2.7.4

33
pcre-8.39-Fix-bad-interaction-between-o-and-M-in-pcregrep.patch
View File

@ -1,33 +0,0 @@
From 664df44c7eb62edbce95ab6dbdedcba7f07fed02 Mon Sep 17 00:00:00 2001
From: ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15>
Date: Fri, 17 Jun 2016 17:28:14 +0000
Subject: [PATCH] Fix bad interaction between -o and -M in pcregrep.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1658 2f5784b3-3f2a-0410-8824-cb99058d5e15
Petr Písař <ppisar@redhat.com>: Ported to 8.39.
diff --git a/pcregrep.c b/pcregrep.c
index cd53c64..fd2a676 100644
--- a/pcregrep.c
+++ b/pcregrep.c
@@ -1803,6 +1803,12 @@ while (ptr < endptr)
match = FALSE;
if (line_buffered) fflush(stdout);
rc = 0; /* Had some success */
+
+ /* If the current match ended past the end of the line (only possible
+ in multiline mode), we are done with this line. */
+
+ if ((unsigned int)offsets[1] > linelength) goto END_ONE_MATCH;
+
startoffset = offsets[1]; /* Restart after the match */
if (startoffset <= oldstartoffset)
{
--
2.5.5

269
pcre-8.39-Fix-character-class-bug-when-a-Unicode-property-was-.patch
View File

@ -1,269 +0,0 @@
From 1767e8be04f300ad10f2b358c281a23f0759e3d3 Mon Sep 17 00:00:00 2001
From: ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15>
Date: Thu, 4 Aug 2016 17:15:38 +0000
Subject: [PATCH] Fix character class bug when a Unicode property was present
with \D etc in a non-ucp character class in a wide character mode.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1664 2f5784b3-3f2a-0410-8824-cb99058d5e15
Petr Písař: Ported to 8.39.
diff --git a/pcre_compile.c b/pcre_compile.c
index 7cd3950..fb80ed1 100644
--- a/pcre_compile.c
+++ b/pcre_compile.c
@@ -5579,6 +5579,34 @@ for (;; ptr++)
#endif
#if defined SUPPORT_UTF || !defined COMPILE_PCRE8
{
+ /* For non-UCP wide characters, in a non-negative class containing \S or
+ similar (should_flip_negation is set), all characters greater than 255
+ must be in the class. */
+
+ if (
+#if defined COMPILE_PCRE8
+ utf &&
+#endif
+ should_flip_negation && !negate_class && (options & PCRE_UCP) == 0)
+ {
+ *class_uchardata++ = XCL_RANGE;
+ if (utf) /* Will always be utf in the 8-bit library */
+ {
+ class_uchardata += PRIV(ord2utf)(0x100, class_uchardata);
+ class_uchardata += PRIV(ord2utf)(0x10ffff, class_uchardata);
+ }
+ else /* Can only happen for the 16-bit & 32-bit libraries */
+ {
+#if defined COMPILE_PCRE16
+ *class_uchardata++ = 0x100;
+ *class_uchardata++ = 0xffffu;
+#elif defined COMPILE_PCRE32
+ *class_uchardata++ = 0x100;
+ *class_uchardata++ = 0xffffffffu;
+#endif
+ }
+ }
+
*class_uchardata++ = XCL_END; /* Marks the end of extra data */
*code++ = OP_XCLASS;
code += LINK_SIZE;
diff --git a/testdata/testinput16 b/testdata/testinput16
index 15419e6..7ccde0a 100644
--- a/testdata/testinput16
+++ b/testdata/testinput16
@@ -38,4 +38,30 @@
/s+/i8SI
SSss\x{17f}
+/[\W\p{Any}]/BZ
+ abc
+ 123
+
+/[\W\pL]/BZ
+ abc
+ ** Failers
+ 123
+
+/[\D]/8
+ \x{1d7cf}
+
+/[\D\P{Nd}]/8
+ \x{1d7cf}
+
+/[^\D]/8
+ a9b
+ ** Failers
+ \x{1d7cf}
+
+/[^\D\P{Nd}]/8
+ a9b
+ \x{1d7cf}
+ ** Failers
+ \x{10000}
+
/-- End of testinput16 --/
diff --git a/testdata/testinput19 b/testdata/testinput19
index ce45afc..dfe8c7b 100644
--- a/testdata/testinput19
+++ b/testdata/testinput19
@@ -25,4 +25,21 @@
/s+/i8SI
SSss\x{17f}
+/[\D]/8
+ \x{1d7cf}
+
+/[\D\P{Nd}]/8
+ \x{1d7cf}
+
+/[^\D]/8
+ a9b
+ ** Failers
+ \x{1d7cf}
+
+/[^\D\P{Nd}]/8
+ a9b
+ \x{1d7cf}
+ ** Failers
+ \x{10000}
+
/-- End of testinput19 --/
diff --git a/testdata/testinput7 b/testdata/testinput7
index 00b9738..f44a810 100644
--- a/testdata/testinput7
+++ b/testdata/testinput7
@@ -838,15 +838,6 @@ of case for anything other than the ASCII letters. --/
/^s?c/mi8I
scat
-/[\W\p{Any}]/BZ
- abc
- 123
-
-/[\W\pL]/BZ
- abc
- ** Failers
- 123
-
/a[[:punct:]b]/WBZ
/a[[:punct:]b]/8WBZ
diff --git a/testdata/testoutput16 b/testdata/testoutput16
index fd184cd..e6ba26a 100644
--- a/testdata/testoutput16
+++ b/testdata/testoutput16
@@ -138,4 +138,56 @@ Starting chars: S s \xc5
SSss\x{17f}
0: SSss\x{17f}
+/[\W\p{Any}]/BZ
+------------------------------------------------------------------
+ Bra
+ [\x00-/:-@[-^`{-\xff\p{Any}]
+ Ket
+ End
+------------------------------------------------------------------
+ abc
+ 0: a
+ 123
+ 0: 1
+
+/[\W\pL]/BZ
+------------------------------------------------------------------
+ Bra
+ [\x00-/:-@[-^`{-\xff\p{L}]
+ Ket
+ End
+------------------------------------------------------------------
+ abc
+ 0: a
+ ** Failers
+ 0: *
+ 123
+No match
+
+/[\D]/8
+ \x{1d7cf}
+ 0: \x{1d7cf}
+
+/[\D\P{Nd}]/8
+ \x{1d7cf}
+ 0: \x{1d7cf}
+
+/[^\D]/8
+ a9b
+ 0: 9
+ ** Failers
+No match
+ \x{1d7cf}
+No match
+
+/[^\D\P{Nd}]/8
+ a9b
+ 0: 9
+ \x{1d7cf}
+ 0: \x{1d7cf}
+ ** Failers
+No match
+ \x{10000}
+No match
+
/-- End of testinput16 --/
diff --git a/testdata/testoutput19 b/testdata/testoutput19
index eb8a8f6..982bea4 100644
--- a/testdata/testoutput19
+++ b/testdata/testoutput19
@@ -105,4 +105,30 @@ Starting chars: S s \xff
SSss\x{17f}
0: SSss\x{17f}
+/[\D]/8
+ \x{1d7cf}
+ 0: \x{1d7cf}
+
+/[\D\P{Nd}]/8
+ \x{1d7cf}
+ 0: \x{1d7cf}
+
+/[^\D]/8
+ a9b
+ 0: 9
+ ** Failers
+No match
+ \x{1d7cf}
+No match
+
+/[^\D\P{Nd}]/8
+ a9b
+ 0: 9
+ \x{1d7cf}
+ 0: \x{1d7cf}
+ ** Failers
+No match
+ \x{10000}
+No match
+
/-- End of testinput19 --/
diff --git a/testdata/testoutput7 b/testdata/testoutput7
index fdfff64..2b167b2 100644
--- a/testdata/testoutput7
+++ b/testdata/testoutput7
@@ -2295,32 +2295,6 @@ Need char = 'c' (caseless)
scat
0: sc
-/[\W\p{Any}]/BZ
-------------------------------------------------------------------
- Bra
- [\x00-/:-@[-^`{-\xff\p{Any}]
- Ket
- End
-------------------------------------------------------------------
- abc
- 0: a
- 123
- 0: 1
-
-/[\W\pL]/BZ
-------------------------------------------------------------------
- Bra
- [\x00-/:-@[-^`{-\xff\p{L}]
- Ket
- End
-------------------------------------------------------------------
- abc
- 0: a
- ** Failers
- 0: *
- 123
-No match
-
/a[[:punct:]b]/WBZ
------------------------------------------------------------------
Bra
--
2.5.5

51
pcre-8.39-Fix-documentation-error.patch
View File

@ -1,51 +0,0 @@
From bad0d0347aa4ab37d2b3e906193725d68a5d98bf Mon Sep 17 00:00:00 2001
From: ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15>
Date: Fri, 14 Oct 2016 17:06:22 +0000
Subject: [PATCH] Fix documentation error.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1668 2f5784b3-3f2a-0410-8824-cb99058d5e15
Signed-off-by: Petr Písař <ppisar@redhat.com>
---
doc/pcrepattern.3 | 14 +++++---------
1 file changed, 5 insertions(+), 9 deletions(-)
diff --git a/doc/pcrepattern.3 b/doc/pcrepattern.3
index 952451f..1e25371 100644
--- a/doc/pcrepattern.3
+++ b/doc/pcrepattern.3
@@ -1,4 +1,4 @@
-.TH PCREPATTERN 3 "14 June 2015" "PCRE 8.38"
+.TH PCREPATTERN 3 "14 October 2016" "PCRE 8.40"
.SH NAME
PCRE - Perl-compatible regular expressions
.SH "PCRE REGULAR EXPRESSION DETAILS"
@@ -1511,12 +1511,8 @@ J, U and X respectively.
.P
When one of these option changes occurs at top level (that is, not inside
subpattern parentheses), the change applies to the remainder of the pattern
-that follows. If the change is placed right at the start of a pattern, PCRE
-extracts it into the global options (and it will therefore show up in data
-extracted by the \fBpcre_fullinfo()\fP function).
-.P
-An option change within a subpattern (see below for a description of
-subpatterns) affects only that part of the subpattern that follows it, so
+that follows. An option change within a subpattern (see below for a description
+of subpatterns) affects only that part of the subpattern that follows it, so
.sp
(a(?i)b)c
.sp
@@ -3296,6 +3292,6 @@ Cambridge CB2 3QH, England.
.rs
.sp
.nf
-Last updated: 14 June 2015
-Copyright (c) 1997-2015 University of Cambridge.
+Last updated: 14 October 2016
+Copyright (c) 1997-2016 University of Cambridge.
.fi
--
2.7.4

242
pcre-8.39-Fix-optimization-bugs-for-patterns-starting-with-loo.patch
View File

@ -1,242 +0,0 @@
From d6d45d15235fc6f010cfb193db8fb672a152e41c Mon Sep 17 00:00:00 2001
From: ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15>
Date: Tue, 18 Oct 2016 15:10:09 +0000
Subject: [PATCH] Fix optimization bugs for patterns starting with lookaheads.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1669 2f5784b3-3f2a-0410-8824-cb99058d5e15
Petr Písař: Ported to 8.39.
diff --git a/pcre_compile.c b/pcre_compile.c
index 67c74e8..de92313 100644
--- a/pcre_compile.c
+++ b/pcre_compile.c
@@ -7918,15 +7918,17 @@ for (;; ptr++)
}
}
- /* For a forward assertion, we take the reqchar, if set. This can be
- helpful if the pattern that follows the assertion doesn't set a different
- char. For example, it's useful for /(?=abcde).+/. We can't set firstchar
- for an assertion, however because it leads to incorrect effect for patterns
- such as /(?=a)a.+/ when the "real" "a" would then become a reqchar instead
- of a firstchar. This is overcome by a scan at the end if there's no
- firstchar, looking for an asserted first char. */
-
- else if (bravalue == OP_ASSERT && subreqcharflags >= 0)
+ /* For a forward assertion, we take the reqchar, if set, provided that the
+ group has also set a first char. This can be helpful if the pattern that
+ follows the assertion doesn't set a different char. For example, it's
+ useful for /(?=abcde).+/. We can't set firstchar for an assertion, however
+ because it leads to incorrect effect for patterns such as /(?=a)a.+/ when
+ the "real" "a" would then become a reqchar instead of a firstchar. This is
+ overcome by a scan at the end if there's no firstchar, looking for an
+ asserted first char. */
+
+ else if (bravalue == OP_ASSERT && subreqcharflags >= 0 &&
+ subfirstcharflags >= 0)
{
reqchar = subreqchar;
reqcharflags = subreqcharflags;
@@ -8715,8 +8717,8 @@ matching and for non-DOTALL patterns that start with .* (which must start at
the beginning or after \n). As in the case of is_anchored() (see above), we
have to take account of back references to capturing brackets that contain .*
because in that case we can't make the assumption. Also, the appearance of .*
-inside atomic brackets or in a pattern that contains *PRUNE or *SKIP does not
-count, because once again the assumption no longer holds.
+inside atomic brackets or in an assertion, or in a pattern that contains *PRUNE
+or *SKIP does not count, because once again the assumption no longer holds.
Arguments:
code points to start of expression (the bracket)
@@ -8725,13 +8727,14 @@ Arguments:
the less precise approach
cd points to the compile data
atomcount atomic group level
+ inassert TRUE if in an assertion
Returns: TRUE or FALSE
*/
static BOOL
is_startline(const pcre_uchar *code, unsigned int bracket_map,
- compile_data *cd, int atomcount)
+ compile_data *cd, int atomcount, BOOL inassert)
{
do {
const pcre_uchar *scode = first_significant_code(
@@ -8758,7 +8761,7 @@ do {
return FALSE;
default: /* Assertion */
- if (!is_startline(scode, bracket_map, cd, atomcount)) return FALSE;
+ if (!is_startline(scode, bracket_map, cd, atomcount, TRUE)) return FALSE;
do scode += GET(scode, 1); while (*scode == OP_ALT);
scode += 1 + LINK_SIZE;
break;
@@ -8772,7 +8775,7 @@ do {
if (op == OP_BRA || op == OP_BRAPOS ||
op == OP_SBRA || op == OP_SBRAPOS)
{
- if (!is_startline(scode, bracket_map, cd, atomcount)) return FALSE;
+ if (!is_startline(scode, bracket_map, cd, atomcount, inassert)) return FALSE;
}
/* Capturing brackets */
@@ -8782,33 +8785,33 @@ do {
{
int n = GET2(scode, 1+LINK_SIZE);
int new_map = bracket_map | ((n < 32)? (1 << n) : 1);
- if (!is_startline(scode, new_map, cd, atomcount)) return FALSE;
+ if (!is_startline(scode, new_map, cd, atomcount, inassert)) return FALSE;
}
/* Positive forward assertions */
else if (op == OP_ASSERT)
{
- if (!is_startline(scode, bracket_map, cd, atomcount)) return FALSE;
+ if (!is_startline(scode, bracket_map, cd, atomcount, TRUE)) return FALSE;
}
/* Atomic brackets */
else if (op == OP_ONCE || op == OP_ONCE_NC)
{
- if (!is_startline(scode, bracket_map, cd, atomcount + 1)) return FALSE;
+ if (!is_startline(scode, bracket_map, cd, atomcount + 1, inassert)) return FALSE;
}
/* .* means "start at start or after \n" if it isn't in atomic brackets or
- brackets that may be referenced, as long as the pattern does not contain
- *PRUNE or *SKIP, because these break the feature. Consider, for example,
- /.*?a(*PRUNE)b/ with the subject "aab", which matches "ab", i.e. not at the
- start of a line. */
+ brackets that may be referenced or an assertion, as long as the pattern does
+ not contain *PRUNE or *SKIP, because these break the feature. Consider, for
+ example, /.*?a(*PRUNE)b/ with the subject "aab", which matches "ab", i.e.
+ not at the start of a line. */
else if (op == OP_TYPESTAR || op == OP_TYPEMINSTAR || op == OP_TYPEPOSSTAR)
{
if (scode[1] != OP_ANY || (bracket_map & cd->backref_map) != 0 ||
- atomcount > 0 || cd->had_pruneorskip)
+ atomcount > 0 || cd->had_pruneorskip || inassert)
return FALSE;
}
@@ -9663,7 +9666,7 @@ if ((re->options & PCRE_ANCHORED) == 0)
re->flags |= PCRE_FIRSTSET;
}
- else if (is_startline(codestart, 0, cd, 0)) re->flags |= PCRE_STARTLINE;
+ else if (is_startline(codestart, 0, cd, 0, FALSE)) re->flags |= PCRE_STARTLINE;
}
}
diff --git a/testdata/testinput1 b/testdata/testinput1
index 8379ce0..93abab3 100644
--- a/testdata/testinput1
+++ b/testdata/testinput1
@@ -5733,4 +5733,10 @@ AbcdCBefgBhiBqz
"(?|(\k'Pm')|(?'Pm'))"
abcd
+/(?=.*[A-Z])(?=.*[a-z])(?=.*[0-9])(?=.*[,;:])(?=.{8,16})(?!.*[\s])/
+ \ Fred:099
+
+/(?=.*X)X$/
+ \ X
+
/-- End of testinput1 --/
diff --git a/testdata/testinput2 b/testdata/testinput2
index 38346ef..08c6f39 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -4247,4 +4247,6 @@ backtracking verbs. --/
/(?<R>abc)(?(R)xyz)/BZ
+/(?=.*[A-Z])/I
+
/-- End of testinput2 --/
diff --git a/testdata/testinput6 b/testdata/testinput6
index a178d3d..22ed1e6 100644
--- a/testdata/testinput6
+++ b/testdata/testinput6
@@ -1562,4 +1562,10 @@
\x{389}
\x{20ac}
+/(?=.*b)\pL/
+ 11bb
+
+/(?(?=.*b)(?=.*b)\pL|.*c)/
+ 11bb
+
/-- End of testinput6 --/
diff --git a/testdata/testoutput1 b/testdata/testoutput1
index e852ab9..a2b3cff 100644
--- a/testdata/testoutput1
+++ b/testdata/testoutput1
@@ -9434,4 +9434,12 @@ No match
0:
1:
+/(?=.*[A-Z])(?=.*[a-z])(?=.*[0-9])(?=.*[,;:])(?=.{8,16})(?!.*[\s])/
+ \ Fred:099
+ 0:
+
+/(?=.*X)X$/
+ \ X
+ 0: X
+
/-- End of testinput1 --/
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index 216bff8..811bbef 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -9380,7 +9380,7 @@ No need char
/(?(?=.*b).*b|^d)/I
Capturing subpattern count = 0
No options
-First char at start or follows newline
+No first char
No need char
/xyz/C
@@ -14698,4 +14698,11 @@ Failed: assertion expected after (?( or (?(?C) at offset 4
End
------------------------------------------------------------------
+/(?=.*[A-Z])/I
+Capturing subpattern count = 0
+May match empty string
+No options
+No first char
+No need char
+
/-- End of testinput2 --/
diff --git a/testdata/testoutput6 b/testdata/testoutput6
index b64dc0d..422d383 100644
--- a/testdata/testoutput6
+++ b/testdata/testoutput6
@@ -2573,4 +2573,12 @@ No match
\x{20ac}
No match
+/(?=.*b)\pL/
+ 11bb
+ 0: b
+
+/(?(?=.*b)(?=.*b)\pL|.*c)/
+ 11bb
+ 0: b
+
/-- End of testinput6 --/
--
2.7.4

36
pcre-8.39-Fix-pcretest-callout-display-bug.patch
View File

@ -1,36 +0,0 @@
From 74599ddaf3dfb11277401eb6279dd32371f54e18 Mon Sep 17 00:00:00 2001
From: ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15>
Date: Thu, 6 Oct 2016 16:32:46 +0000
Subject: [PATCH] Fix pcretest callout display bug
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1665 2f5784b3-3f2a-0410-8824-cb99058d5e15
Petr Písař: Ported to 8.39.
diff --git a/pcretest.c b/pcretest.c
index 5748c55..5b73a91 100644
--- a/pcretest.c
+++ b/pcretest.c
@@ -1982,6 +1982,7 @@ return(result);
static int pchar(pcre_uint32 c, FILE *f)
{
int n = 0;
+char tempbuffer[16];
if (PRINTOK(c))
{
if (f != NULL) fprintf(f, "%c", c);
@@ -2003,6 +2004,8 @@ if (c < 0x100)
}
if (f != NULL) n = fprintf(f, "\\x{%02x}", c);
+ else n = sprintf(tempbuffer, "\\x{%02x}", c);
+
return n >= 0 ? n : 0;
}
--
2.7.4

47
pcre-8.39-Fix-register-overwite-in-JIT-when-SSE2-acceleration-.patch
View File

@ -1,47 +0,0 @@
From 575b84a7bcbd63f54d933804ea5036642b93c0f7 Mon Sep 17 00:00:00 2001
From: zherczeg <zherczeg@2f5784b3-3f2a-0410-8824-cb99058d5e15>
Date: Fri, 1 Jul 2016 09:06:38 +0000
Subject: [PATCH] Fix register overwite in JIT when SSE2 acceleration is
enabled.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1660 2f5784b3-3f2a-0410-8824-cb99058d5e15
Petr Písař: Ported to 8.39.
diff --git a/pcre_jit_compile.c b/pcre_jit_compile.c
index 4f15a27..46ce6c6 100644
--- a/pcre_jit_compile.c
+++ b/pcre_jit_compile.c
@@ -4004,12 +4004,12 @@ sljit_emit_op_custom(compiler, instruction, 4);
if (load_twice)
{
- OP1(SLJIT_MOV, TMP3, 0, TMP2, 0);
+ OP1(SLJIT_MOV, RETURN_ADDR, 0, TMP2, 0);
instruction[3] = 0xc0 | (tmp2_ind << 3) | 1;
sljit_emit_op_custom(compiler, instruction, 4);
OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0);
- OP1(SLJIT_MOV, TMP2, 0, TMP3, 0);
+ OP1(SLJIT_MOV, TMP2, 0, RETURN_ADDR, 0);
}
OP2(SLJIT_ASHR, TMP1, 0, TMP1, 0, TMP2, 0);
diff --git a/pcre_jit_test.c b/pcre_jit_test.c
index 9b61ec0..034cb52 100644
--- a/pcre_jit_test.c
+++ b/pcre_jit_test.c
@@ -687,6 +687,7 @@ static struct regression_test_case regression_test_cases[] = {
{ PCRE_FIRSTLINE | PCRE_NEWLINE_LF | PCRE_DOTALL, 0 | F_NOMATCH, "ab.", "ab" },
{ MUA | PCRE_FIRSTLINE, 1 | F_NOMATCH, "^[a-d0-9]", "\nxx\nd" },
{ PCRE_NEWLINE_ANY | PCRE_FIRSTLINE | PCRE_DOTALL, 0, "....a", "012\n0a" },
+ { MUA | PCRE_FIRSTLINE, 0, "[aC]", "a" },
/* Recurse. */
{ MUA, 0, "(a)(?1)", "aa" },
--
2.5.5

52
pcre-8.39-Fix-typos-in-documentation.patch
View File

@ -1,52 +0,0 @@
From c53d4af2465bf11a8aefceb67bf7f7ae19b08ac5 Mon Sep 17 00:00:00 2001
From: ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15>
Date: Thu, 6 Oct 2016 17:49:48 +0000
Subject: [PATCH] Fix typos in documentation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1666 2f5784b3-3f2a-0410-8824-cb99058d5e15
Signed-off-by: Petr Písař <ppisar@redhat.com>
---
doc/pcrepattern.3 | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/doc/pcrepattern.3 b/doc/pcrepattern.3
index 3b8c639..952451f 100644
--- a/doc/pcrepattern.3
+++ b/doc/pcrepattern.3
@@ -336,22 +336,22 @@ When PCRE is compiled in EBCDIC mode, \ea, \ee, \ef, \en, \er, and \et
generate the appropriate EBCDIC code values. The \ec escape is processed
as specified for Perl in the \fBperlebcdic\fP document. The only characters
that are allowed after \ec are A-Z, a-z, or one of @, [, \e, ], ^, _, or ?. Any
-other character provokes a compile-time error. The sequence \e@ encodes
-character code 0; the letters (in either case) encode characters 1-26 (hex 01
-to hex 1A); [, \e, ], ^, and _ encode characters 27-31 (hex 1B to hex 1F), and
-\e? becomes either 255 (hex FF) or 95 (hex 5F).
+other character provokes a compile-time error. The sequence \ec@ encodes
+character code 0; after \ec the letters (in either case) encode characters 1-26
+(hex 01 to hex 1A); [, \e, ], ^, and _ encode characters 27-31 (hex 1B to hex
+1F), and \ec? becomes either 255 (hex FF) or 95 (hex 5F).
.P
-Thus, apart from \e?, these escapes generate the same character code values as
+Thus, apart from \ec?, these escapes generate the same character code values as
they do in an ASCII environment, though the meanings of the values mostly
-differ. For example, \eG always generates code value 7, which is BEL in ASCII
+differ. For example, \ecG always generates code value 7, which is BEL in ASCII
but DEL in EBCDIC.
.P
-The sequence \e? generates DEL (127, hex 7F) in an ASCII environment, but
+The sequence \ec? generates DEL (127, hex 7F) in an ASCII environment, but
because 127 is not a control character in EBCDIC, Perl makes it generate the
APC character. Unfortunately, there are several variants of EBCDIC. In most of
them the APC character has the value 255 (hex FF), but in the one Perl calls
POSIX-BC its value is 95 (hex 5F). If certain other characters have POSIX-BC
-values, PCRE makes \e? generate 95; otherwise it generates 255.
+values, PCRE makes \ec? generate 95; otherwise it generates 255.
.P
After \e0 up to two further octal digits are read. If there are fewer than two
digits, just those that are present are used. Thus the sequence \e0\ex\e015
--
2.7.4

46
pcre.spec
View File

@ -1,8 +1,8 @@
# Is this a stable/testing release:
#%%global rcversion RC1
%global rcversion RC1
Name: pcre
Version: 8.39
Release: %{?rcversion:0.}6%{?rcversion:.%rcversion}%{?dist}
Version: 8.40
Release: %{?rcversion:0.}1%{?rcversion:.%rcversion}%{?dist}
%global myversion %{version}%{?rcversion:-%rcversion}
Summary: Perl-compatible regular expression library
Group: System Environment/Libraries
@ -34,34 +34,6 @@ Source: ftp://ftp.csx.cam.ac.uk/pub/software/programming/%{name}/%{?rcversio
Patch0: pcre-8.21-multilib.patch
# Refused by upstream, bug #675477
Patch1: pcre-8.32-refused_spelling_terminated.patch
# Fix repeated pcregrep output if -o with -M options were used and the match
# extended over a line boundary, upstream bug #1848, fixed in upstream after
# 8.39
Patch2: pcre-8.39-Fix-bad-interaction-between-o-and-M-in-pcregrep.patch
# Fix register overwite in JIT when SSE2 acceleration is enabled,
# in upstream after 8.39
Patch3: pcre-8.39-Fix-register-overwite-in-JIT-when-SSE2-acceleration-.patch
# Fix matching characters above 255 when a negative character type was used
# without enabled UCP in a positive class, in upstream after 8.39,
# upstream bug #1866
Patch4: pcre-8.39-Fix-character-class-bug-when-a-Unicode-property-was-.patch
# Fix displaying position in pcretest callout with an escape sequence greater
# than \x{ff}, in upstream after 8.39
Patch5: pcre-8.39-Fix-pcretest-callout-display-bug.patch
# Fix pcrepattern(3) documentation, in upstream after 8.39
Patch6: pcre-8.39-Fix-typos-in-documentation.patch
# Fix miscopmilation of conditionals when a group name start with "R",
# in upstream after 8.39, upstream bug #1873
Patch7: pcre-8.39-Fix-bad-conditional-recursion-test-bug-when-a-group-.patch
# Fix internal option documentation in pcrepattern(3), in upstream after 8.39,
# upstream bug #1875
Patch8: pcre-8.39-Fix-documentation-error.patch
# Fix optimization bugs for patterns starting with lookaheads,
# in upstream after 8.39, upstream bug #1882
Patch9: pcre-8.39-Fix-optimization-bugs-for-patterns-starting-with-loo.patch
# Document assert capture limitation, in upstream after 8.39,
# upstream bug #1887
Patch10: pcre-8.39-Document-assertion-capture-limitation.patch
BuildRequires: readline-devel
BuildRequires: autoconf
BuildRequires: automake
@ -151,15 +123,6 @@ Utilities demonstrating PCRE capabilities like pcregrep or pcretest.
# Get rid of rpath
%patch0 -p1
%patch1 -p1
%patch2 -p1
%patch3 -p1
%patch4 -p1
%patch5 -p1
%patch6 -p1
%patch7 -p1
%patch8 -p1
%patch9 -p1
%patch10 -p1
# Because of rpath patch
libtoolize --copy --force
autoreconf -vif
@ -256,6 +219,9 @@ make %{?_smp_mflags} check VERBOSE=yes
%{_mandir}/man1/pcretest.*
%changelog
* Mon Dec 12 2016 Petr Pisar <ppisar@redhat.com> - 8.40-0.1.RC1
- 8.40-RC1 bump
* Mon Oct 24 2016 Petr Pisar <ppisar@redhat.com> - 8.39-6
- Document assert capture limitation (upstream bug #1887)

2
sources
View File

@ -1 +1 @@
e3fca7650a0556a2647821679d81f585 pcre-8.39.tar.bz2
SHA512 (pcre-8.40-RC1.tar.bz2) = cc68c1e603dec3e60bf899841a24dc6f162784849520d6dc4e77bba0b8eda152b23de4f192bb893d44c6e77af169959a0070e8ae2dbd1e7a670fcb11bbc1cc8f