ZhuningOS/pcre2
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Initialize for pcre2

Browse source
This commit is contained in:
zyppe 2024-02-28 22:01:09 +08:00
commit c6d5f24b72
12 changed files with 2049 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
.gitignore vendored Normal file
View file

@ -0,0 +1 @@
pcre2-10.39.tar.bz2

1
.pcre2.metadata Normal file
View file

@ -0,0 +1 @@
ee4fb4e65033e8d7b1a23549cc8504b93a4f32d1750ba1cb3c7d5e104451699e pcre2-10.39.tar.bz2

4
baselibs.conf Normal file
View file

@ -0,0 +1,4 @@
libpcre2-8-0
libpcre2-16-0
libpcre2-32-0
libpcre2-posix2

34
pcre2-10.10-multilib.patch Normal file
View file

@ -0,0 +1,34 @@
From 1d5ce3e2e6341b01609aefab20786a8638fee17a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Petr=20P=C3=ADsa=C5=99?= <ppisar@redhat.com>
Date: Tue, 6 Dec 2011 18:44:11 +0100
Subject: [PATCH] Fix multilib
Do not set RPATH nor add explicit -L path to compiler.
---
pcre2-config.in | 12 ------------
1 file changed, 12 deletions(-)
Index: pcre2-10.10/pcre2-config.in
===================================================================
--- pcre2-10.10.orig/pcre2-config.in 2014-10-17 17:07:57.000000000 +0200
+++ pcre2-10.10/pcre2-config.in 2015-06-18 20:56:20.000000000 +0200
@@ -28,19 +28,7 @@ if test $# -eq 0; then
fi
libR=
-case `uname -s` in
- *SunOS*)
- libR=" -R@libdir@"
- ;;
- *BSD*)
- libR=" -Wl,-R@libdir@"
- ;;
-esac
-
libS=
-if test @libdir@ != /usr/lib ; then
- libS=-L@libdir@
-fi
while test $# -gt 0; do
case "$1" in

39
pcre2-10.39-bsc1199232-unicode-property-matching.patch Normal file
View file

@ -0,0 +1,39 @@
diff --git a/ChangeLog b/ChangeLog
index d27542d..cb7a0f2 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1081,6 +1081,9 @@ recursions. Iterators at the ends of capturing groups are no longer considered
for auto-possessification if the pattern contains any recursions. Fixes
Bugzilla #2232.
+23. Fixed a unicode properrty matching issue in JIT. The character was not
+fully read in caseless matching.
+
Version 10.30 14-August-2017
----------------------------
diff --git a/src/pcre2_jit_compile.c b/src/pcre2_jit_compile.c
index db2ce65..5fbee09 100644
--- a/src/pcre2_jit_compile.c
+++ b/src/pcre2_jit_compile.c
@@ -7473,7 +7473,7 @@ while (*cc != XCL_END)
{
SLJIT_ASSERT(*cc == XCL_PROP || *cc == XCL_NOTPROP);
cc++;
- if (*cc == PT_CLIST)
+ if (*cc == PT_CLIST && cc[-1] == XCL_PROP)
{
other_cases = PRIV(ucd_caseless_sets) + cc[1];
while (*other_cases != NOTACHAR)
diff --git a/src/pcre2_jit_test.c b/src/pcre2_jit_test.c
index 8dee16e..bf94c6d 100644
--- a/src/pcre2_jit_test.c
+++ b/src/pcre2_jit_test.c
@@ -412,6 +412,7 @@ static struct regression_test_case regression_test_cases[] = {
{ MUP, A, 0, 0 | F_PROPERTY, "[\\P{L&}]{2}[^\xc2\x85-\xc2\x89\\p{Ll}\\p{Lu}]{2}", "\xc3\xa9\xe6\x92\xad.a\xe6\x92\xad|\xc2\x8a#" },
{ PCRE2_UCP, 0, 0, 0 | F_PROPERTY, "[a-b\\s]{2,5}[^a]", "AB baaa" },
{ MUP, 0, 0, 0 | F_NOMATCH, "[^\\p{Hangul}\\p{Z}]", " " },
+ { CMUP, 0, 0, 0, "[^S]\\B", "\xe2\x80\x8a" },
/* Possible empty brackets. */
{ MU, A, 0, 0, "(?:|ab||bc|a)+d", "abcxabcabd" },

BIN
pcre2-10.39.tar.bz2.sig Normal file
View file

Binary file not shown.

73
pcre2-CVE-2022-41409.patch Normal file
View file

@ -0,0 +1,73 @@
From 94e1c001761373b7d9450768aa15d04c25547a35 Mon Sep 17 00:00:00 2001
From: Philip Hazel <Philip.Hazel@gmail.com>
Date: Tue, 16 Aug 2022 17:00:45 +0100
Subject: [PATCH] Diagnose negative repeat value in pcre2test subject line
---
ChangeLog | 3 +++
src/pcre2test.c | 4 ++--
testdata/testinput2 | 3 +++
testdata/testoutput2 | 4 ++++
4 files changed, 12 insertions(+), 2 deletions(-)
Index: pcre2-10.39/ChangeLog
===================================================================
--- pcre2-10.39.orig/ChangeLog
+++ pcre2-10.39/ChangeLog
@@ -1,6 +1,13 @@
Change Log for PCRE2
--------------------
+Version 10.41 06-December-2022
+------------------------------
+
+20. A negative repeat value in a pcre2test subject line was not being
+diagnosed, leading to infinite looping.
+
+
Version 10.39 29-October-2021
-----------------------------
Index: pcre2-10.39/src/pcre2test.c
===================================================================
--- pcre2-10.39.orig/src/pcre2test.c
+++ pcre2-10.39/src/pcre2test.c
@@ -6766,9 +6766,9 @@ while ((c = *p++) != 0)
}
i = (int32_t)li;
- if (i-- == 0)
+ if (i-- <= 0)
{
- fprintf(outfile, "** Zero repeat not allowed\n");
+ fprintf(outfile, "** Zero or negative repeat not allowed\n");
return PR_OK;
}
Index: pcre2-10.39/testdata/testinput2
===================================================================
--- pcre2-10.39.orig/testdata/testinput2
+++ pcre2-10.39/testdata/testinput2
@@ -5902,4 +5902,7 @@ a)"xI
# ---------
+--
+ \[X]{-10}
+
# End of testinput2
Index: pcre2-10.39/testdata/testoutput2
===================================================================
--- pcre2-10.39.orig/testdata/testoutput2
+++ pcre2-10.39/testdata/testoutput2
@@ -17674,6 +17674,10 @@ Failed: error 199 at offset 14: \K is no
# ---------
+--
+ \[X]{-10}
+** Zero or negative repeat not allowed
+
# End of testinput2
Error -70: PCRE2_ERROR_BADDATA (unknown error number)
Error -62: bad serialized data

642
pcre2-bsc1199235-CVE-2022-1587.patch Normal file
View file

@ -0,0 +1,642 @@
diff --git a/ChangeLog b/ChangeLog
index cb7a0f2..2567c62 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -123,6 +123,9 @@ whenever a lookahead was processed, leading to some fuzzer-generated patterns
taking a very long time to compile when (?|) was present in the pattern,
because (?|) disables caching of group lengths.
+24. Fixed an issue affecting recursions in JIT caused by duplicated data
+transfers.
+
Version 10.37 26-May-2021
-------------------------
diff --git a/src/pcre2_jit_compile.c b/src/pcre2_jit_compile.c
index 5fbee09..6c42318 100644
--- a/src/pcre2_jit_compile.c
+++ b/src/pcre2_jit_compile.c
@@ -413,6 +413,9 @@ typedef struct compiler_common {
/* Locals used by fast fail optimization. */
sljit_s32 early_fail_start_ptr;
sljit_s32 early_fail_end_ptr;
+ /* Variables used by recursive call generator. */
+ sljit_s32 recurse_bitset_size;
+ uint8_t *recurse_bitset;
/* Flipped and lower case tables. */
const sljit_u8 *fcc;
@@ -2315,19 +2318,39 @@ for (i = 0; i < RECURSE_TMP_REG_COUNT; i++)
#undef RECURSE_TMP_REG_COUNT
+static BOOL recurse_check_bit(compiler_common *common, sljit_sw bit_index)
+{
+uint8_t *byte;
+uint8_t mask;
+
+SLJIT_ASSERT((bit_index & (sizeof(sljit_sw) - 1)) == 0);
+
+bit_index >>= SLJIT_WORD_SHIFT;
+
+mask = 1 << (bit_index & 0x7);
+byte = common->recurse_bitset + (bit_index >> 3);
+
+if (*byte & mask)
+ return FALSE;
+
+*byte |= mask;
+return TRUE;
+}
+
static int get_recurse_data_length(compiler_common *common, PCRE2_SPTR cc, PCRE2_SPTR ccend,
BOOL *needs_control_head, BOOL *has_quit, BOOL *has_accept)
{
int length = 1;
-int size;
+int size, offset;
PCRE2_SPTR alternative;
BOOL quit_found = FALSE;
BOOL accept_found = FALSE;
BOOL setsom_found = FALSE;
BOOL setmark_found = FALSE;
-BOOL capture_last_found = FALSE;
BOOL control_head_found = FALSE;
+memset(common->recurse_bitset, 0, common->recurse_bitset_size);
+
#if defined DEBUG_FORCE_CONTROL_HEAD && DEBUG_FORCE_CONTROL_HEAD
SLJIT_ASSERT(common->control_head_ptr != 0);
control_head_found = TRUE;
@@ -2350,15 +2373,17 @@ while (cc < ccend)
setsom_found = TRUE;
if (common->mark_ptr != 0)
setmark_found = TRUE;
- if (common->capture_last_ptr != 0)
- capture_last_found = TRUE;
+ if (common->capture_last_ptr != 0 && recurse_check_bit(common, common->capture_last_ptr))
+ length++;
cc += 1 + LINK_SIZE;
break;
case OP_KET:
- if (PRIVATE_DATA(cc) != 0)
+ offset = PRIVATE_DATA(cc);
+ if (offset != 0)
{
- length++;
+ if (recurse_check_bit(common, offset))
+ length++;
SLJIT_ASSERT(PRIVATE_DATA(cc + 1) != 0);
cc += PRIVATE_DATA(cc + 1);
}
@@ -2377,39 +2402,55 @@ while (cc < ccend)
case OP_SBRA:
case OP_SBRAPOS:
case OP_SCOND:
- length++;
SLJIT_ASSERT(PRIVATE_DATA(cc) != 0);
+ if (recurse_check_bit(common, PRIVATE_DATA(cc)))
+ length++;
cc += 1 + LINK_SIZE;
break;
case OP_CBRA:
case OP_SCBRA:
- length += 2;
- if (common->capture_last_ptr != 0)
- capture_last_found = TRUE;
- if (common->optimized_cbracket[GET2(cc, 1 + LINK_SIZE)] == 0)
+ offset = GET2(cc, 1 + LINK_SIZE);
+ if (recurse_check_bit(common, OVECTOR(offset << 1)))
+ {
+ SLJIT_ASSERT(recurse_check_bit(common, OVECTOR((offset << 1) + 1)));
+ length += 2;
+ }
+ if (common->optimized_cbracket[offset] == 0 && recurse_check_bit(common, OVECTOR_PRIV(offset)))
+ length++;
+ if (common->capture_last_ptr != 0 && recurse_check_bit(common, common->capture_last_ptr))
length++;
cc += 1 + LINK_SIZE + IMM2_SIZE;
break;
case OP_CBRAPOS:
case OP_SCBRAPOS:
- length += 2 + 2;
- if (common->capture_last_ptr != 0)
- capture_last_found = TRUE;
+ offset = GET2(cc, 1 + LINK_SIZE);
+ if (recurse_check_bit(common, OVECTOR(offset << 1)))
+ {
+ SLJIT_ASSERT(recurse_check_bit(common, OVECTOR((offset << 1) + 1)));
+ length += 2;
+ }
+ if (recurse_check_bit(common, OVECTOR_PRIV(offset)))
+ length++;
+ if (recurse_check_bit(common, PRIVATE_DATA(cc)))
+ length++;
+ if (common->capture_last_ptr != 0 && recurse_check_bit(common, common->capture_last_ptr))
+ length++;
cc += 1 + LINK_SIZE + IMM2_SIZE;
break;
case OP_COND:
/* Might be a hidden SCOND. */
alternative = cc + GET(cc, 1);
- if (*alternative == OP_KETRMAX || *alternative == OP_KETRMIN)
+ if ((*alternative == OP_KETRMAX || *alternative == OP_KETRMIN) && recurse_check_bit(common, PRIVATE_DATA(cc)))
length++;
cc += 1 + LINK_SIZE;
break;
CASE_ITERATOR_PRIVATE_DATA_1
- if (PRIVATE_DATA(cc) != 0)
+ offset = PRIVATE_DATA(cc);
+ if (offset != 0 && recurse_check_bit(common, offset))
length++;
cc += 2;
#ifdef SUPPORT_UNICODE
@@ -2418,8 +2459,12 @@ while (cc < ccend)
break;
CASE_ITERATOR_PRIVATE_DATA_2A
- if (PRIVATE_DATA(cc) != 0)
+ offset = PRIVATE_DATA(cc);
+ if (offset != 0 && recurse_check_bit(common, offset))
+ {
+ SLJIT_ASSERT(recurse_check_bit(common, offset + sizeof(sljit_sw)));
length += 2;
+ }
cc += 2;
#ifdef SUPPORT_UNICODE
if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]);
@@ -2427,8 +2472,12 @@ while (cc < ccend)
break;
CASE_ITERATOR_PRIVATE_DATA_2B
- if (PRIVATE_DATA(cc) != 0)
+ offset = PRIVATE_DATA(cc);
+ if (offset != 0 && recurse_check_bit(common, offset))
+ {
+ SLJIT_ASSERT(recurse_check_bit(common, offset + sizeof(sljit_sw)));
length += 2;
+ }
cc += 2 + IMM2_SIZE;
#ifdef SUPPORT_UNICODE
if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]);
@@ -2436,20 +2485,29 @@ while (cc < ccend)
break;
CASE_ITERATOR_TYPE_PRIVATE_DATA_1
- if (PRIVATE_DATA(cc) != 0)
+ offset = PRIVATE_DATA(cc);
+ if (offset != 0 && recurse_check_bit(common, offset))
length++;
cc += 1;
break;
CASE_ITERATOR_TYPE_PRIVATE_DATA_2A
- if (PRIVATE_DATA(cc) != 0)
+ offset = PRIVATE_DATA(cc);
+ if (offset != 0 && recurse_check_bit(common, offset))
+ {
+ SLJIT_ASSERT(recurse_check_bit(common, offset + sizeof(sljit_sw)));
length += 2;
+ }
cc += 1;
break;
CASE_ITERATOR_TYPE_PRIVATE_DATA_2B
- if (PRIVATE_DATA(cc) != 0)
+ offset = PRIVATE_DATA(cc);
+ if (offset != 0 && recurse_check_bit(common, offset))
+ {
+ SLJIT_ASSERT(recurse_check_bit(common, offset + sizeof(sljit_sw)));
length += 2;
+ }
cc += 1 + IMM2_SIZE;
break;
@@ -2461,7 +2519,9 @@ while (cc < ccend)
#else
size = 1 + 32 / (int)sizeof(PCRE2_UCHAR);
#endif
- if (PRIVATE_DATA(cc) != 0)
+
+ offset = PRIVATE_DATA(cc);
+ if (offset != 0 && recurse_check_bit(common, offset))
length += get_class_iterator_size(cc + size);
cc += size;
break;
@@ -2496,8 +2556,7 @@ while (cc < ccend)
case OP_THEN:
SLJIT_ASSERT(common->control_head_ptr != 0);
quit_found = TRUE;
- if (!control_head_found)
- control_head_found = TRUE;
+ control_head_found = TRUE;
cc++;
break;
@@ -2517,8 +2576,6 @@ SLJIT_ASSERT(cc == ccend);
if (control_head_found)
length++;
-if (capture_last_found)
- length++;
if (quit_found)
{
if (setsom_found)
@@ -2551,14 +2608,12 @@ sljit_sw shared_srcw[3];
sljit_sw kept_shared_srcw[2];
int private_count, shared_count, kept_shared_count;
int from_sp, base_reg, offset, i;
-BOOL setsom_found = FALSE;
-BOOL setmark_found = FALSE;
-BOOL capture_last_found = FALSE;
-BOOL control_head_found = FALSE;
+
+memset(common->recurse_bitset, 0, common->recurse_bitset_size);
#if defined DEBUG_FORCE_CONTROL_HEAD && DEBUG_FORCE_CONTROL_HEAD
SLJIT_ASSERT(common->control_head_ptr != 0);
-control_head_found = TRUE;
+recurse_check_bit(common, common->control_head_ptr);
#endif
switch (type)
@@ -2646,11 +2701,10 @@ while (cc < ccend)
{
case OP_SET_SOM:
SLJIT_ASSERT(common->has_set_som);
- if (has_quit && !setsom_found)
+ if (has_quit && recurse_check_bit(common, OVECTOR(0)))
{
kept_shared_srcw[0] = OVECTOR(0);
kept_shared_count = 1;
- setsom_found = TRUE;
}
cc += 1;
break;
@@ -2658,33 +2712,31 @@ while (cc < ccend)
case OP_RECURSE:
if (has_quit)
{
- if (common->has_set_som && !setsom_found)
+ if (common->has_set_som && recurse_check_bit(common, OVECTOR(0)))
{
kept_shared_srcw[0] = OVECTOR(0);
kept_shared_count = 1;
- setsom_found = TRUE;
}
- if (common->mark_ptr != 0 && !setmark_found)
+ if (common->mark_ptr != 0 && recurse_check_bit(common, common->mark_ptr))
{
kept_shared_srcw[kept_shared_count] = common->mark_ptr;
kept_shared_count++;
- setmark_found = TRUE;
}
}
- if (common->capture_last_ptr != 0 && !capture_last_found)
+ if (common->capture_last_ptr != 0 && recurse_check_bit(common, common->capture_last_ptr))
{
shared_srcw[0] = common->capture_last_ptr;
shared_count = 1;
- capture_last_found = TRUE;
}
cc += 1 + LINK_SIZE;
break;
case OP_KET:
- if (PRIVATE_DATA(cc) != 0)
+ private_srcw[0] = PRIVATE_DATA(cc);
+ if (private_srcw[0] != 0)
{
- private_count = 1;
- private_srcw[0] = PRIVATE_DATA(cc);
+ if (recurse_check_bit(common, private_srcw[0]))
+ private_count = 1;
SLJIT_ASSERT(PRIVATE_DATA(cc + 1) != 0);
cc += PRIVATE_DATA(cc + 1);
}
@@ -2703,50 +2755,66 @@ while (cc < ccend)
case OP_SBRA:
case OP_SBRAPOS:
case OP_SCOND:
- private_count = 1;
private_srcw[0] = PRIVATE_DATA(cc);
+ if (recurse_check_bit(common, private_srcw[0]))
+ private_count = 1;
cc += 1 + LINK_SIZE;
break;
case OP_CBRA:
case OP_SCBRA:
- offset = (GET2(cc, 1 + LINK_SIZE)) << 1;
- shared_srcw[0] = OVECTOR(offset);
- shared_srcw[1] = OVECTOR(offset + 1);
- shared_count = 2;
+ offset = GET2(cc, 1 + LINK_SIZE);
+ shared_srcw[0] = OVECTOR(offset << 1);
+ if (recurse_check_bit(common, shared_srcw[0]))
+ {
+ shared_srcw[1] = shared_srcw[0] + sizeof(sljit_sw);
+ SLJIT_ASSERT(recurse_check_bit(common, shared_srcw[1]));
+ shared_count = 2;
+ }
- if (common->capture_last_ptr != 0 && !capture_last_found)
+ if (common->capture_last_ptr != 0 && recurse_check_bit(common, common->capture_last_ptr))
{
- shared_srcw[2] = common->capture_last_ptr;
- shared_count = 3;
- capture_last_found = TRUE;
+ shared_srcw[shared_count] = common->capture_last_ptr;
+ shared_count++;
}
- if (common->optimized_cbracket[GET2(cc, 1 + LINK_SIZE)] == 0)
+ if (common->optimized_cbracket[offset] == 0)
{
- private_count = 1;
- private_srcw[0] = OVECTOR_PRIV(GET2(cc, 1 + LINK_SIZE));
+ private_srcw[0] = OVECTOR_PRIV(offset);
+ if (recurse_check_bit(common, private_srcw[0]))
+ private_count = 1;
}
+
cc += 1 + LINK_SIZE + IMM2_SIZE;
break;
case OP_CBRAPOS:
case OP_SCBRAPOS:
- offset = (GET2(cc, 1 + LINK_SIZE)) << 1;
- shared_srcw[0] = OVECTOR(offset);
- shared_srcw[1] = OVECTOR(offset + 1);
- shared_count = 2;
+ offset = GET2(cc, 1 + LINK_SIZE);
+ shared_srcw[0] = OVECTOR(offset << 1);
+ if (recurse_check_bit(common, shared_srcw[0]))
+ {
+ shared_srcw[1] = shared_srcw[0] + sizeof(sljit_sw);
+ SLJIT_ASSERT(recurse_check_bit(common, shared_srcw[1]));
+ shared_count = 2;
+ }
- if (common->capture_last_ptr != 0 && !capture_last_found)
+ if (common->capture_last_ptr != 0 && recurse_check_bit(common, common->capture_last_ptr))
{
- shared_srcw[2] = common->capture_last_ptr;
- shared_count = 3;
- capture_last_found = TRUE;
+ shared_srcw[shared_count] = common->capture_last_ptr;
+ shared_count++;
}
- private_count = 2;
private_srcw[0] = PRIVATE_DATA(cc);
- private_srcw[1] = OVECTOR_PRIV(GET2(cc, 1 + LINK_SIZE));
+ if (recurse_check_bit(common, private_srcw[0]))
+ private_count = 1;
+
+ offset = OVECTOR_PRIV(offset);
+ if (recurse_check_bit(common, offset))
+ {
+ private_srcw[private_count] = offset;
+ private_count++;
+ }
cc += 1 + LINK_SIZE + IMM2_SIZE;
break;
@@ -2755,18 +2823,17 @@ while (cc < ccend)
alternative = cc + GET(cc, 1);
if (*alternative == OP_KETRMAX || *alternative == OP_KETRMIN)
{
- private_count = 1;
private_srcw[0] = PRIVATE_DATA(cc);
+ if (recurse_check_bit(common, private_srcw[0]))
+ private_count = 1;
}
cc += 1 + LINK_SIZE;
break;
CASE_ITERATOR_PRIVATE_DATA_1
- if (PRIVATE_DATA(cc))
- {
+ private_srcw[0] = PRIVATE_DATA(cc);
+ if (private_srcw[0] != 0 && recurse_check_bit(common, private_srcw[0]))
private_count = 1;
- private_srcw[0] = PRIVATE_DATA(cc);
- }
cc += 2;
#ifdef SUPPORT_UNICODE
if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]);
@@ -2774,11 +2841,12 @@ while (cc < ccend)
break;
CASE_ITERATOR_PRIVATE_DATA_2A
- if (PRIVATE_DATA(cc))
+ private_srcw[0] = PRIVATE_DATA(cc);
+ if (private_srcw[0] != 0 && recurse_check_bit(common, private_srcw[0]))
{
private_count = 2;
- private_srcw[0] = PRIVATE_DATA(cc);
- private_srcw[1] = PRIVATE_DATA(cc) + sizeof(sljit_sw);
+ private_srcw[1] = private_srcw[0] + sizeof(sljit_sw);
+ SLJIT_ASSERT(recurse_check_bit(common, private_srcw[1]));
}
cc += 2;
#ifdef SUPPORT_UNICODE
@@ -2787,11 +2855,12 @@ while (cc < ccend)
break;
CASE_ITERATOR_PRIVATE_DATA_2B
- if (PRIVATE_DATA(cc))
+ private_srcw[0] = PRIVATE_DATA(cc);
+ if (private_srcw[0] != 0 && recurse_check_bit(common, private_srcw[0]))
{
private_count = 2;
- private_srcw[0] = PRIVATE_DATA(cc);
- private_srcw[1] = PRIVATE_DATA(cc) + sizeof(sljit_sw);
+ private_srcw[1] = private_srcw[0] + sizeof(sljit_sw);
+ SLJIT_ASSERT(recurse_check_bit(common, private_srcw[1]));
}
cc += 2 + IMM2_SIZE;
#ifdef SUPPORT_UNICODE
@@ -2800,30 +2869,30 @@ while (cc < ccend)
break;
CASE_ITERATOR_TYPE_PRIVATE_DATA_1
- if (PRIVATE_DATA(cc))
- {
+ private_srcw[0] = PRIVATE_DATA(cc);
+ if (private_srcw[0] != 0 && recurse_check_bit(common, private_srcw[0]))
private_count = 1;
- private_srcw[0] = PRIVATE_DATA(cc);
- }
cc += 1;
break;
CASE_ITERATOR_TYPE_PRIVATE_DATA_2A
- if (PRIVATE_DATA(cc))
+ private_srcw[0] = PRIVATE_DATA(cc);
+ if (private_srcw[0] != 0 && recurse_check_bit(common, private_srcw[0]))
{
private_count = 2;
- private_srcw[0] = PRIVATE_DATA(cc);
private_srcw[1] = private_srcw[0] + sizeof(sljit_sw);
+ SLJIT_ASSERT(recurse_check_bit(common, private_srcw[1]));
}
cc += 1;
break;
CASE_ITERATOR_TYPE_PRIVATE_DATA_2B
- if (PRIVATE_DATA(cc))
+ private_srcw[0] = PRIVATE_DATA(cc);
+ if (private_srcw[0] != 0 && recurse_check_bit(common, private_srcw[0]))
{
private_count = 2;
- private_srcw[0] = PRIVATE_DATA(cc);
private_srcw[1] = private_srcw[0] + sizeof(sljit_sw);
+ SLJIT_ASSERT(recurse_check_bit(common, private_srcw[1]));
}
cc += 1 + IMM2_SIZE;
break;
@@ -2840,14 +2909,17 @@ while (cc < ccend)
switch(get_class_iterator_size(cc + i))
{
case 1:
- private_count = 1;
private_srcw[0] = PRIVATE_DATA(cc);
break;
case 2:
- private_count = 2;
private_srcw[0] = PRIVATE_DATA(cc);
- private_srcw[1] = private_srcw[0] + sizeof(sljit_sw);
+ if (recurse_check_bit(common, private_srcw[0]))
+ {
+ private_count = 2;
+ private_srcw[1] = private_srcw[0] + sizeof(sljit_sw);
+ SLJIT_ASSERT(recurse_check_bit(common, private_srcw[1]));
+ }
break;
default:
@@ -2862,28 +2934,25 @@ while (cc < ccend)
case OP_PRUNE_ARG:
case OP_THEN_ARG:
SLJIT_ASSERT(common->mark_ptr != 0);
- if (has_quit && !setmark_found)
+ if (has_quit && recurse_check_bit(common, common->mark_ptr))
{
kept_shared_srcw[0] = common->mark_ptr;
kept_shared_count = 1;
- setmark_found = TRUE;
}
- if (common->control_head_ptr != 0 && !control_head_found)
+ if (common->control_head_ptr != 0 && recurse_check_bit(common, common->control_head_ptr))
{
private_srcw[0] = common->control_head_ptr;
private_count = 1;
- control_head_found = TRUE;
}
cc += 1 + 2 + cc[1];
break;
case OP_THEN:
SLJIT_ASSERT(common->control_head_ptr != 0);
- if (!control_head_found)
+ if (recurse_check_bit(common, common->control_head_ptr))
{
private_srcw[0] = common->control_head_ptr;
private_count = 1;
- control_head_found = TRUE;
}
cc++;
break;
@@ -2891,7 +2960,7 @@ while (cc < ccend)
default:
cc = next_opcode(common, cc);
SLJIT_ASSERT(cc != NULL);
- break;
+ continue;
}
if (type != recurse_copy_shared_to_global && type != recurse_copy_kept_shared_to_global)
@@ -13652,7 +13721,7 @@ SLJIT_ASSERT(!(common->req_char_ptr != 0 && common->start_used_ptr != 0));
common->cbra_ptr = OVECTOR_START + (re->top_bracket + 1) * 2 * sizeof(sljit_sw);
total_length = ccend - common->start;
-common->private_data_ptrs = (sljit_s32 *)SLJIT_MALLOC(total_length * (sizeof(sljit_s32) + (common->has_then ? 1 : 0)), allocator_data);
+common->private_data_ptrs = (sljit_s32*)SLJIT_MALLOC(total_length * (sizeof(sljit_s32) + (common->has_then ? 1 : 0)), allocator_data);
if (!common->private_data_ptrs)
{
SLJIT_FREE(common->optimized_cbracket, allocator_data);
@@ -13693,6 +13762,7 @@ if (!compiler)
common->compiler = compiler;
/* Main pcre_jit_exec entry. */
+SLJIT_ASSERT((private_data_size & (sizeof(sljit_sw) - 1)) == 0);
sljit_emit_enter(compiler, 0, SLJIT_ARG1(SW), 5, 5, 0, 0, private_data_size);
/* Register init. */
@@ -13915,20 +13985,40 @@ common->early_fail_end_ptr = 0;
common->currententry = common->entries;
common->local_quit_available = TRUE;
quit_label = common->quit_label;
-while (common->currententry != NULL)
+if (common->currententry != NULL)
{
- /* Might add new entries. */
- compile_recurse(common);
- if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler)))
+ /* A free bit for each private data. */
+ common->recurse_bitset_size = ((private_data_size / (int)sizeof(sljit_sw)) + 7) >> 3;
+ SLJIT_ASSERT(common->recurse_bitset_size > 0);
+ common->recurse_bitset = (sljit_u8*)SLJIT_MALLOC(common->recurse_bitset_size, allocator_data);;
+
+ if (common->recurse_bitset != NULL)
+ {
+ do
+ {
+ /* Might add new entries. */
+ compile_recurse(common);
+ if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler)))
+ break;
+ flush_stubs(common);
+ common->currententry = common->currententry->next;
+ }
+ while (common->currententry != NULL);
+
+ SLJIT_FREE(common->recurse_bitset, allocator_data);
+ }
+
+ if (common->currententry != NULL)
{
+ /* The common->recurse_bitset has been freed. */
+ SLJIT_ASSERT(sljit_get_compiler_error(compiler) || common->recurse_bitset == NULL);
+
sljit_free_compiler(compiler);
SLJIT_FREE(common->optimized_cbracket, allocator_data);
SLJIT_FREE(common->private_data_ptrs, allocator_data);
PRIV(jit_free_rodata)(common->read_only_data_head, allocator_data);
return PCRE2_ERROR_NOMEMORY;
}
- flush_stubs(common);
- common->currententry = common->currententry->next;
}
common->local_quit_available = FALSE;
common->quit_label = quit_label;
diff --git a/src/pcre2_jit_test.c b/src/pcre2_jit_test.c
index bf94c6d..26de6c7 100644
--- a/src/pcre2_jit_test.c
+++ b/src/pcre2_jit_test.c
@@ -748,6 +748,7 @@ static struct regression_test_case regression_test_cases[] = {
{ 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#" },
+ { MU, A, 0, 0 | F_NOMATCH, "(?1)$((.|\\2xx){1,2})", "abc" },
/* 16 bit specific tests. */
{ CM, A, 0, 0 | F_FORCECONV, "\xc3\xa1", "\xc3\x81\xc3\xa1" },

38
pcre2-readd-wrappers-POSIX.patch Normal file
View file

@ -0,0 +1,38 @@
Index: pcre2-10.39/src/pcre2posix.c
===================================================================
--- pcre2-10.39.orig/src/pcre2posix.c 2021-08-31 18:12:05.000000000 +0200
+++ pcre2-10.39/src/pcre2posix.c 2022-03-15 17:46:34.705052429 +0100
@@ -176,19 +176,7 @@ static const char *const pstring[] = {
-#if 0 /* REMOVE THIS CODE */
-
-The code below was created for 10.33 (see ChangeLog 10.33 #4) when the
-POSIX functions were given pcre2_... names instead of the traditional POSIX
-names. However, it has proved to be more troublesome than useful. There have
-been at least two cases where a program links with two others, one of which
-uses the POSIX library and the other uses the PCRE2 POSIX functions, thus
-causing two instances of the POSIX runctions to exist, leading to trouble. For
-10.37 this code is commented out. In due course it can be removed if there are
-no issues. The only small worry is the comment below about languages that do
-not include pcre2posix.h. If there are any such cases, they will have to use
-the PCRE2 names.
-
+#if 1
/*************************************************
* Wrappers with traditional POSIX names *
Index: pcre2-10.39/configure.ac
===================================================================
--- pcre2-10.39.orig/configure.ac 2021-10-29 17:30:33.000000000 +0200
+++ pcre2-10.39/configure.ac 2022-03-15 17:46:47.681128564 +0100
@@ -17,7 +17,7 @@ m4_define(pcre2_date, [2021-10-29])
m4_define(libpcre2_8_version, [10:4:10])
m4_define(libpcre2_16_version, [10:4:10])
m4_define(libpcre2_32_version, [10:4:10])
-m4_define(libpcre2_posix_version, [3:1:0])
+m4_define(libpcre2_posix_version, [2:4:0])
# 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.

919
pcre2.changes Normal file
View file

@ -0,0 +1,919 @@
* Fri Jul 21 2023 pmonreal@suse.com
- Security fix: [bsc#1213514, CVE-2022-41409]
* Integer overflow vulnerability in pcre2test before 10.41
allows attackers to cause a denial of service or other
unspecified impacts via negative input.
* Add pcre2-CVE-2022-41409.patch
* Wed Jul 20 2022 jsikes@suse.com
- Added pcre2-bsc1199235-CVE-2022-1587.patch
* CVE-2022-1587 / bsc#1199235
* Fix out-of-bounds read due to bug in recursions
* Sourced from:
- https://github.com/PCRE2Project/pcre2/commit/03654e751e7f0700693526b67dfcadda6b42c9d0
* Thu Jun 16 2022 jsikes@suse.com
- Added pcre2-10.39-bsc1199232-unicode-property-matching.patch
* bsc#1199232
* CVE-2022-1586
* Fixes unicode property matching issue
* Thu May 5 2022 pgajdos@suse.com
- do not enable jit-sealloc [bsc#1182864] [bsc#1199208]
* Thu May 5 2022 pgajdos@suse.com
- enable jit for s390x [bsc#1199196]
* Mon Mar 14 2022 pgajdos@suse.com
- version update to 10.39
* Fix incorrect detection of alternatives in first character
search in JIT
* Update to Unicode 14.0.0
- 0001-Fixed-atomic-group-backtracking-bug.patch released for 15:Update
due to bsc#1187937 is already upstreamed
https://bugzilla.suse.com/show_bug.cgi?id=1187937#c7
* Thu Nov 11 2021 pgajdos@suse.com
- added patches
fix revert https://github.com/PhilipHazel/pcre2/commit/080d7789eba00b570181dfe28809b01aa88c01f8
+ pcre2-readd-wrappers-POSIX.patch
* Sun Oct 24 2021 andreas.stieger@gmx.de
- pcre2 10.38:
* Following Perl's lead, \K is now locked out in lookaround
assertions by default, but an option is provided to re-enable
the previous behaviour
* Thu May 27 2021 andreas.stieger@gmx.de
- pcre2 10.37:
* removal of the actual POSIX names regcomp etc. from the POSIX
wrapper library because these have caused issues for some
applications, replacing pcre2-symbol-clash.patch
* fix a hypothetical NULL dereference
* fix two bugs related to over-large numbers so the behaviour is
now the same as Perl
* Fix propagation of \K back from the full pattern recursion
* Restore single character repetition optimization in JIT
* Wed Apr 14 2021 jengelh@inai.de
- Remove regcomp, regexec etc. from libpcre2-posix.
(Add pcre2-symbol-clash.patch)
* Sat Dec 5 2020 andreas.stieger@gmx.de
- pcre2 10.36:
* add GNU grep's -m (aka --max-count) option to pcre2grep
* unify the handling of substitution strings for both -O and
callouts in pcre2grep, with the addition of $x{...} and
$o{...} to allow for characters whose code points are greater
than 255 in Unicode mode
* Wed May 13 2020 ilya@ilya.pp.ua
- Refresh spec-file via spec-cleaner.
* Add %%make_build and %%license macros.
- Update to 10.35
* https://www.pcre.org/changelog.txt
* Use PCRE2_MATCH_EMPTY flag to detect empty matches in JIT.
* A JIT bug is fixed which allowed to read the fields
of the compiled pattern before its existence is checked.
* Added PCRE2_SUBSTITUTE_LITERAL.
* Avoid some VS compiler warnings.
* Added PCRE2_SUBSTITUTE_MATCHED.
* Added (?* and (?<* as synonms for (*napla: and (*naplb:
to match another regex engine.
* Fix *THEN verbs in lookahead assertions in JIT.
* Added PCRE2_SUBSTITUTE_REPLACEMENT_ONLY.
* The JIT stack should be freed when the low-level stack
allocation fails.
* Changed setting of CMAKE_MODULE_PATH in CMakeLists.txt from SET
to LIST(APPEND...) to allow a setting from the command line
to be included.
* Updated to Unicode 13.0.0.
* CMake build now checks for secure_getenv() and strerror().
* Restrict the configuration setting for the SELinux compatible
execmem allocator (change 10.30/44) to Linux and NetBSD.
* Fri Mar 27 2020 mcalabkova@suse.com
- Resubmit the package (bsc#1167890, jsc#SLE-11608)
* Tue Nov 26 2019 schwab@suse.de
- Enable JIT on aarch64
* Fri Nov 22 2019 andreas.stieger@gmx.de
- pcre2 10.34:
* implement the documented maximum number of capturing
subpatterns of 65535
* Improve the invalid utf32 support of the JIT compiler
* Add support for matching in invalid UTF strings to the pcre2_match()
* Give more error detail for invalid UTF-8 when detected in pcre2grep
* support for invalid UTF-8 to pcre2grep.
* Adjust the limit for "must have" code unit searching, in particular,
* increase it substantially for non-anchored patterns.
* Allow (*ACCEPT) to be quantified, because an ungreedy quantifier
with a zero minimum is potentially useful.
* Some changes to the way the minimum subject length is handled
* Check for integer overflow when computing lookbehind lengths
* Implement non-atomic positive lookaround assertions
* Upgraded to Unicode 12.1.0
* Make pcre2test -C show if libreadline or libedit is supported
* Various bug fixes and improvements
* Thu May 2 2019 jsikes@suse.de
- Update to 10.33-RC1 to fix issue with LTO (boo#1133274).
* Callouts from pcre2_substitute() are now available.
* The POSIX functions are now all called pcre2_regcomp() etc., with wrapper
functions that use the standard POSIX names. However, in pcre2posix.h the POSIX
names are defined as macros. This should help avoid linking with the wrong
library in some environments, while still exporting the POSIX names for
pre-existing programs that use them.
* Some new options:
(a) PCRE2_EXTRA_ESCAPED_CR_IS_LF makes \r behave as \n.
(b) PCRE2_EXTRA_ALT_BSUX enables support for ECMAScript 6's \u{hh...}
construct.
(c) PCRE2_COPY_MATCHED_SUBJECT causes a copy of a matched subject to be
made, instead of just remembering a pointer.
* Some new Perl features:
(a) Perl 5.28's experimental alphabetic names for atomic groups and
lookaround assertions, for example, (*pla:...) and (*atomic:...).
(b) The new Perl "script run" features (*script_run:...) and
(*atomic_script_run:...) aka (*sr:...) and (*asr:...).
(c) When PCRE2_UTF is set, allow non-ASCII letters and decimal digits in
capture group names.
* --disable-percent-zt disables the use of %%zu and %%td in formatting strings
in pcre2test. They were already automatically disabled for VC and older C
compilers.
* Some changes related to callouts in pcre2grep:
(a) Support for running an external program under VMS has been added, in
addition to Windows and fork() support.
(b) --disable-pcre2grep-callout-fork restricts the callout support in
to the inbuilt echo facility.
* Wed Apr 24 2019 mliska@suse.cz
- Disable LTO (boo#1133274).
* Wed Jan 23 2019 bwiedemann@suse.com
- Do not run profiling in parallel for reproducible builds (boo#1040589)
* Mon Jan 14 2019 kukuk@suse.de
- Mark all license files as %%license
* Tue Dec 11 2018 crrodriguez@opensuse.org
- Build with --enable-jit-sealloc option, otherwise when
selinux is enabled or systemd memory protections are on,
programs will fail to work with execmem violations.
* Thu Oct 25 2018 astieger@suse.com
- pcre2 10.32:
* pcre2grep now supports the inclusion of binary zeros in
patterns that are read from files via the -f option.
* In pcre2_dfa_match(), internal recursive calls no longer use
the stack for local workspace and local ovectors
* Updated to Unicode version 11.0.0.
* (*ACCEPT:ARG), (*FAIL:ARG), and (*COMMIT:ARG) are now supported.
* Add support for \N{U+dddd}, but only in Unicode mode.
* Addesupport for (?^) to unset all imnsx options
* Fri Jul 20 2018 mpluskal@suse.com
- Drop conditions for old distributions
- Do profile guided build
* Sun Feb 18 2018 avindra@opensuse.org
- Update to new upstream release 10.31
* New pcre2_config() options: PCRE2_CONFIG_NEVER_BACKSLASH_C and
PCRE2_CONFIG_COMPILED_WIDTHS.
* New pcre2_pattern_info() option PCRE2_INFO_EXTRAOPTIONS to
retrieve the extra compile time options.
* Public names for all pcre2_compile() error numbers.
* Added PCRE2_CALLOUT_STARTMATCH and PCRE2_CALLOUT_BACKTRACK
bits to a new field callout_flags in callout blocks.
- use https for main site
- cleanup with spec-cleaner
* Mon Sep 11 2017 jengelh@inai.de
- Update to new upstream release 10.30
* The main interpreter, pcre2_match(), has been refactored into
a new version that does not use recursive function calls for
remembering backtracking positions. The new implementation
allows backtracking into recursive group calls in patterns,
making it more compatible with Perl. For patterns that have a
lot of backtracking, the heap is now used, and there is
explicit limit on the amount, settable by
pcre2_set_heap_limit(). The "recursion limit" is retained,
but is renamed as "depth limit".
* The new option PCRE2_ENDANCHORED insists that a pattern match
must end at the end of the subject.
* 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.
* (?n) can be used to set PCRE2_NO_AUTO_CAPTURE, because Perl
now has this.
* Additional pattern compile options in the compile context are
now available: PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES and
PCRE2_EXTRA_BAD_ESCAPE_IS LITERAL.
* The newline type PCRE2_NEWLINE_NUL is now available.
* 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.
* Various minor security fixes found by fuzzers:
+ bsc#1037165: crash for forward reference in lookbehind with
PCRE2_ANCHORED
+ CVE-2017-8786: heap-based buffer overflow write in pcre2test
(bsc#1036942)
+ CVE-2017-7186: DoS by triggering an invalid Unicode property
lookup (bsc#1030066)
- Switch source URLs to use HTTP.
* Sat Aug 5 2017 astieger@suse.com
- fix SLE 11 build
* Tue May 2 2017 astieger@suse.com
- pcre2grep can now read .gz and .bz2 files directly
- pcre2test is now built to support line editing
* Thu Feb 16 2017 astieger@suse.com
- pcre2 10.23:
* major re-factoring of the pcre2_compile.c file
* 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.
* \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.
* pcre2grep now automatically expands its buffer up to a maximum
set by --max-buffer-size.
* The -t option (grand total) has been added to pcre2grep.
* 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.
* Tue Feb 7 2017 dimstar@opensuse.org
- Explicitly package %%{_docdir}/%%{name} to fix build with RPM 4.13.
* Mon Aug 1 2016 astieger@suse.com
- pcre2 10.22:
* 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.
* A new function, pcre2_code_copy(), is added, to make a copy of a
compiled pattern.
* Support for string callouts is added to pcre2grep.
* Added the PCRE2_NO_JIT option to pcre2_match().
* The pcre2_get_error_message() function now returns with a
negative error code if the error number it is given is unknown.
* Several updates have been made to pcre2test and test scripts
* Fix CVE-2016-3191: workspace overflow for (*ACCEPT) with deeply
nested parentheses (boo#971741)
* Sun Jan 17 2016 jengelh@inai.de
- Update to new upstream release 10.21
* Improve JIT matching speed of patterns starting with + or *.
* Use memchr() to find the first character in an unanchored match
in 8-bit mode in the interpreter. This gives a significant speed
improvement.
* 10.20 broke the handling of [[:>:]] and [[:<:]] in that
processing them could involve a buffer overflow if the
following character was an opening parenthesis.
* 10.20 also introduced a bug in processing this pattern:
/((?x)(*:0))#(?'/, which was fixed.
* A callout with a string argument containing an opening square
bracket, for example /(?C$[$)(?<]/, was incorrectly processed and
could provoke a buffer overflow.
* A possessively repeated conditional group that could match an empty
string, for example, /(?(R))*+/, was incorrectly compiled.
* The Unicode tables have been updated to Unicode 8.0.0.
* An empty comment (?#) in a pattern was incorrectly processed and
could provoke a buffer overflow.
* Fix infinite recursion in the JIT compiler when certain patterns
/such as (?:|a|){100}x/ are analysed.
* 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:].
* A missing closing parenthesis for a callout with a string argument
was not being diagnosed, possibly leading to a buffer overflow.
* If (?R was followed by - or + incorrect behaviour happened instead
of a diagnostic.
* Fixed an issue when \p{Any} inside an xclass did not read the current
character.
* About 80 more fixes, which you can read about in the ChangeLog
shipped with the libpcre2-8-0 package.
* Tue Jul 14 2015 astieger@suse.com
- PCRE2 10.20:
* Callouts with string arguments and the
pcre2_callout_enumerate() function have been implemented.
* The PCRE2_NEVER_BACKSLASH_C option, which locks out the use of
\C, is added.
* The PCRE2_ALT_CIRCUMFLEX option lets ^ match after a newline at
the end of a subject in multiline mode.
* The way named subpatterns are handled has been refactored. The
previous approach had several bugs.
* The handling of \c in EBCDIC environments has been changed to
conform to the perlebcdic document. (Incompatible change)
* Bugs have been mended, many of them discovered by fuzzers.
* Thu Jun 18 2015 astieger@suse.com
- PCRE2, a re-working of the original PCRE library to provide an
entirely new API, version 10.10. Not source compatible.
- copy of the pcre package, with the following adjustments:
* required name changes
* adjust pcre-8.21-multilib.patch to pcre2-10.10-multilib.patch
* drop upstreamed pcre-8.32-visibility.patch
* --enable-{utf8,unicode-properties} became --enable-unicode
* drop cpp subpackage
* make test -> check
* enable 32 bit character support
* Thu Apr 30 2015 astieger@suse.com
- pcre 8.37:
* CVE-2015-2325: Patterns with certain groups specifying a zero
minimum quantifier caused incorrect code to be compiled,
leading to an incorrect memory read. [boo#924960]
* CVE-2015-2326: Specific patterns containing a forward reference
with subroutine calls caused incorrect code to be compiled
[boo#924961]
* CVE-2014-8964: If an assertion condition was quantified with a
minimum of zero, SIGSEGV or other misbehaviour could occur.
[boo#906574]
* further bug fixes as listed in ChangeLog
* Mon Mar 9 2015 p.drouand@gmail.com
- Update to version 3.16
* This is primarily a bug-fix release.
* The Unicode data tables have been updated to Unicode 7.0.0.
- Remove pcre-commit1472.patch; fixed on upstream release
- Remove obsolete "Obsoletes" tag
* Tue Sep 2 2014 jengelh@inai.de
- Improve on RPM group classification
- Remove defunct %%gpg_verify (replaced by source validators),
defunct freecode link
* Thu Aug 28 2014 crrodriguez@opensuse.org
- Harden build with full RELRO as this libraries end linked
to at least one setuid root executable.
* Mon Jun 16 2014 dvaleev@suse.com
- Enable JIT on ppc64le as well
* Sat May 3 2014 coolo@suse.com
- update to 0.35:
There have been performance improvements for classes containing non-ASCII
characters and the "auto-possessification" feature has been extended. Other
minor improvements have been implemented and bugs fixed. There is a new callout
feature to enable applications to do detailed stack checks at compile time, to
avoid running out of stack for deeply nested parentheses. The JIT compiler has
been extended with experimental support for ARM-64, MIPS-64, and PPC-LE.
- add pcre-commit1472.patch from SVN to work with gcc49, see
http://bugs.exim.org/show_bug.cgi?id=1463
* Sun Mar 23 2014 tchvatal@suse.com
- Add automake and autoconf as explicit deps as we run autoreconf
* Sun Mar 23 2014 tchvatal@suse.com
- Add patch pcre-8.21-multilib.patch to fix RPATH issues.
* The patch is taken from RedHat.
* Sun Mar 23 2014 tchvatal@suse.com
- Clean up with the spec cleaner. Use -j1 in tests as it is not
really thread safe
* Sun Mar 23 2014 tchvatal@suse.com
- Version bump to 8.34:
* warning fixes
* perl fixes
* unocode6.3.0 support
* gconv support
* Wed Nov 13 2013 sweet_f_a@gmx.de
- enable tests for all archs
- --enable-jit for sparc
* Thu Jun 13 2013 jengelh@inai.de
- Update to new upstream release 8.33
* The Just-In-Time compiler (JIT) now supports all pattern
features, including callouts and the backtracking verbs. In
addition, some bugs are fixed and there are minor performance
enhancements.
- More robust make install call. Provide signature verification
files (avoid depending on gpg-offline due to bootstrap cycle).
* Sat Jun 8 2013 crrodriguez@opensuse.org
- Ensure the PCRE library and tools are built with large file
support in 32 bit archs.
* Sun Jan 6 2013 p.drouand@gmail.com
- Update to 8.32 version:
* There is now support for 32-bit character strings and UTF-32. Like the
16-bit support, this is done by compiling a separate 32-bit library.
* \X now matches a Unicode extended grapheme cluster.
* Case-independent matching of Unicode characters that have more than one
"other case" now makes all three (or more) characters equivalent. This
applies, for example, to Greek Sigma, which has two lowercase versions.
* Unicode character properties are updated to Unicode 6.2.0.
* The EBCDIC support, which had decayed, has had a spring clean.
* A number of JIT optimizations have been added, which give faster JIT
execution speed. In addition, a new direct interface to JIT execution is
available. This bypasses some of the sanity checks of pcre_exec() to give a
noticeable speed-up.
* A number of issues in pcregrep have been fixed, making it more compatible
with GNU grep. In particular, --exclude and --include (and variants) apply
to all files now, not just those obtained from scanning a directory
recursively. In Windows environments, the default action for directories is
now "skip" instead of "read" (which provokes an error).
* If the --only-matching (-o) option in pcregrep is specified multiple
times, each one causes appropriate output. For example, -o1 -o2 outputs the
substrings matched by the 1st and 2nd capturing parentheses. A separating
string can be specified by --om-separator (default empty).
* When PCRE is built via Autotools using a version of gcc that has the
"visibility" feature, it is used to hide internal library functions that are
not part of the public API.
- updated and versionned pcre-visibility.patch to svn trunk
* Modifications on configure.ac and makefile have been merged on upstream release
* Fri Nov 23 2012 jengelh@inai.de
- Update package descriptions about the differences between the
PCRE library subpackages.
* Wed Nov 7 2012 cgiboudeaux@gmx.com
- Use the --enable-pcre16 configure flag.
This switch enables 16 bit character support that will be required by Qt5
* Fri Aug 17 2012 dimstar@opensuse.org
- Upate to version 8.31:
+ The JIT compiler now supports partial matching and the (*MARK)
and (*COMMIT) verbs
+ PCRE_INFO_MAXLOOKBEHIND can be used to find the longest
lookbehing in a pattern.
+ There should be a performance improvement when using the heap
instead of the stack for recursion
+ pcregrep can now be linked with libedit as an alternative to
libreadline
+ pcregrep now has a --file-list option where the list of files
to scan is given as a file
+ pcregrep now recognizes binary files and there are related
options
+ The Unicode tables have been updated to 6.1.0
- Rebase pcre-visibility.patch.
* Thu Jul 19 2012 jengelh@inai.de
- Only use --enable-jit on supported architectures; the build will
otherwise fail (e.g. on sparc).
* Thu May 10 2012 afaerber@suse.de
- Add devel-static package
* Tue Feb 7 2012 crrodriguez@opensuse.org
- fix baselibs
* Tue Feb 7 2012 crrodriguez@opensuse.org
- Update to PCRE 8.30, upstream SONAME bump, libpcre1
- Drop no longer needed ppc patch.
- move library back to %%{_libdir}
* Wed Feb 1 2012 dvaleev@suse.com
- Fix cache-flush on PPC
* Wed Nov 16 2011 coolo@suse.com
- add libtool as buildrequire to avoid implicit dependency
* Tue Nov 1 2011 crrodriguez@opensuse.org
- Update to version 8.20
* too many fixes to list here, see included ChangeLog
* replace pcre-visibility patch with the one I submitted to
upstream for inclusion.
* Tue Oct 11 2011 dmueller@suse.de
- udpate to 8.13:
* too many fixes to list here, see included ChangeLog
* the Unicode data tables have been updated to Unicode 6.0.0.
* Mon Sep 19 2011 coolo@suse.com
- remove fragile _service
* Wed Mar 9 2011 coolo@novell.com
- Update to version 8.12
* This release fixes some bugs in pcregrep, one of which caused the tests to fail
on 64-bit big-endian systems. There are no changes to the code of the library.
- Update to version 8.11
* A number of bugs in the library and in pcregrep have been fixed. As always, see
ChangeLog for details. The following are the non-bug-fix changes:
Added --match-limit and --recursion-limit to pcregrep.
Added an optional parentheses number to the -o and --only-matching options
of pcregrep.
Changed the way PCRE_PARTIAL_HARD affects the matching of $, \z, \Z, \b, and
\B.
Added PCRE_ERROR_SHORTUTF8 to make it possible to distinguish between a
bad UTF-8 sequence and one that is incomplete when using PCRE_PARTIAL_HARD.
Recognize (*NO_START_OPT) at the start of a pattern to set the PCRE_NO_
START_OPTIMIZE option, which is now allowed at compile time
* Sat Oct 30 2010 cristian.rodriguez@opensuse.org
- Support GCC visibility, symbol clashes no more.
* Sun Sep 19 2010 vuntz@opensuse.org
- Update to version 8.10:
+ Major additions:
- support for (*MARK) and friends
- PCRE_UCP option, which changes the behaviour of \b, \d, \s,
and \w (and their opposites) so that they make use of Unicode
properties
+ Other additions:
- support for \N, which always matches any character other than
newline
- added --line-buffered to pcregrep
+ Several small new features and bugfixes
- Changes from version 8.02:
+ Update Unicode data tables to Unicode 5.2.0
+ Update the licensing terms in the pcregexp.pas file
+ Several bug fixes
- Changes from version 8.01:
+ Several bug fixes and build system improvements
- Changes from version 8.00:
+ Enhancements:
- remove restrictions on patterns used for partial matching
- give extra information for partial matches
- improve the partial matching process
- add option to make a partial match override a full match
- enhance "study" process by finding a lower bound matching
length
- groups with duplicate numbers may now have duplicated names
without the use of PCRE_DUPNAMES, but they may not have
different names
- add REG_UNGREEDY to the pcreposix interface, which maps to
PCRE_UNGREEDY.
+ Several bug fixes
- Drop pcre-7.9.patch: fixed upstream.
- Rearrange spec file to have all the %%files sections together, as
well as all the scriptlets together.
- Kill the main package that only included doc files like AUTHORS,
NEWS, and license, and put those files in libpcre0: this really
makes more sense. Therefore, make libpcre0 Provides/Obsoletes
libpcre0.
- We can also remove the other dependencies on the main package,
since everything already depends on libpcre0.
- Remove AutoReqProv: it's default now.
- Remove references to perl 5.005 in descriptons: it's not
mentioned anywhere anymore upstream.
* Mon Jun 28 2010 jengelh@medozas.de
- use %%_smp_mflags
* Sat Apr 24 2010 coolo@novell.com
- buildrequire pkg-config to fix provides
* Thu Feb 25 2010 prusnak@suse.cz
- build noarch docs only for >= 11.2
* Wed Feb 10 2010 ms@suse.de
- fixed license statement according to the conversation
and permissions granted in (bnc #578724)
* Sat Dec 12 2009 jengelh@medozas.de
- add baselibs.conf as a source
- package documentation as noarch
* Wed Oct 7 2009 coolo@novell.com
- add obsolete/provides for pcre-32bit (bnc#539543)
* Wed Jun 10 2009 coolo@novell.com
- split package into tools, docs and libraries
* Fri Jun 5 2009 crrodriguez@suse.de
- disable static libraries, shouldn't be used now
* Sat May 30 2009 dmueller@suse.de
- fix symlinks to libpcre and libpcreposix to fix the build
* Wed May 27 2009 ms@suse.de
- moved libpcre and libpcreposix to %%{_lib} (bnc #507449)
* Tue May 5 2009 ms@suse.de
- Release 7.9 11-Apr-09 (bnc #500734)
Mostly bugfixes and tidies with just a couple of minor
functional additions.
* Wed Jan 7 2009 olh@suse.de
- obsolete old -XXbit packages (bnc#437293)
* Thu Sep 11 2008 crrodriguez@suse.de
- update to PCRE 7.8
* More bug fixes, plus a performance improvement
in Unicode character property lookup.
see complete changelog at http://www.pcre.org/changelog.txt
* Thu Apr 10 2008 ro@suse.de
- added baselibs.conf file to build xxbit packages
for multilib support
* Fri Feb 1 2008 crrodriguez@suse.de
- update to version 7.6
- The main reason for having this release so soon after 7.5
is because it fixes a potential buffer overflow problem in pcre_compile()
when run in UTF-8 mode. In addition, the CMake configuration files have been brought up to date.
* Sun Jan 13 2008 crrodriguez@suse.de
- update version 7.5
1. Applied a patch from Craig: "This patch makes it possible to 'ignore'
values in parens when parsing an RE using the C++ wrapper."
2. Negative specials like \S did not work in character classes in UTF-8 mode.
Characters greater than 255 were excluded from the class instead of being
included.
3. The same bug as (2) above applied to negated POSIX classes such as
[:^space:].
4. PCRECPP_STATIC was referenced in pcrecpp_internal.h, but nowhere was it
defined or documented. It seems to have been a typo for PCRE_STATIC, so
I have changed it.
5. The construct (?&) was not diagnosed as a syntax error (it referenced the
first named subpattern) and a construct such as (?&a) would reference the
first named subpattern whose name started with "a" (in other words, the
length check was missing). Both these problems are fixed. "Subpattern name
expected" is now given for (?&) (a zero-length name), and this patch also
makes it give the same error for \k'' (previously it complained that that
was a reference to a non-existent subpattern).
6. The erroneous patterns (?+-a) and (?-+a) give different error messages;
this is right because (?- can be followed by option settings as well as by
digits. I have, however, made the messages clearer.
7. Patterns such as (?(1)a|b) (a pattern that contains fewer subpatterns
than the number used in the conditional) now cause a compile-time error.
This is actually not compatible with Perl, which accepts such patterns, but
treats the conditional as always being FALSE (as PCRE used to), but it
seems to me that giving a diagnostic is better.
8. Change "alphameric" to the more common word "alphanumeric" in comments
and messages.
9. Fix two occurrences of "backslash" in comments that should have been
"backspace".
10. Remove two redundant lines of code that can never be obeyed (their function
was moved elsewhere).
11. The program that makes PCRE's Unicode character property table had a bug
which caused it to generate incorrect table entries for sequences of
characters that have the same character type, but are in different scripts.
It amalgamated them into a single range, with the script of the first of
them. In other words, some characters were in the wrong script. There were
thirteen such cases, affecting characters in the following ranges:
U+002b0 - U+002c1
U+0060c - U+0060d
U+0061e - U+00612
U+0064b - U+0065e
U+0074d - U+0076d
U+01800 - U+01805
U+01d00 - U+01d77
U+01d9b - U+01dbf
U+0200b - U+0200f
U+030fc - U+030fe
U+03260 - U+0327f
U+0fb46 - U+0fbb1
U+10450 - U+1049d
12. The -o option (show only the matching part of a line) for pcregrep was not
compatible with GNU grep in that, if there was more than one match in a
line, it showed only the first of them. It now behaves in the same way as
GNU grep.
13. If the -o and -v options were combined for pcregrep, it printed a blank
line for every non-matching line. GNU grep prints nothing, and pcregrep now
does the same. The return code can be used to tell if there were any
non-matching lines.
14. Added --file-offsets and --line-offsets to pcregrep.
15. The pattern (?=something)(?R) was not being diagnosed as a potentially
infinitely looping recursion. The bug was that positive lookaheads were not
being skipped when checking for a possible empty match (negative lookaheads
and both kinds of lookbehind were skipped).
16. Fixed two typos in the Windows-only code in pcregrep.c, and moved the
inclusion of <windows.h> to before rather than after the definition of
INVALID_FILE_ATTRIBUTES (patch from David Byron).
17. Specifying a possessive quantifier with a specific limit for a Unicode
character property caused pcre_compile() to compile bad code, which led at
runtime to PCRE_ERROR_INTERNAL (-14). Examples of patterns that caused this
are: /\p{Zl}{2,3}+/8 and /\p{Cc}{2}+/8. It was the possessive "+" that
caused the error; without that there was no problem.
18. Added --enable-pcregrep-libz and --enable-pcregrep-libbz2.
19. Added --enable-pcretest-libreadline.
20. In pcrecpp.cc, the variable 'count' was incremented twice in
RE::GlobalReplace(). As a result, the number of replacements returned was
double what it should be. I removed one of the increments, but Craig sent a
later patch that removed the other one (the right fix) and added unit tests
that check the return values (which was not done before).
21. Several CMake things:
(1) Arranged that, when cmake is used on Unix, the libraries end up with
the names libpcre and libpcreposix, not just pcre and pcreposix.
(2) The above change means that pcretest and pcregrep are now correctly
linked with the newly-built libraries, not previously installed ones.
(3) Added PCRE_SUPPORT_LIBREADLINE, PCRE_SUPPORT_LIBZ, PCRE_SUPPORT_LIBBZ2.
22. In UTF-8 mode, with newline set to "any", a pattern such as .*a.*=.b.*
crashed when matching a string such as a\x{2029}b (note that \x{2029} is a
UTF-8 newline character). The key issue is that the pattern starts .*;
this means that the match must be either at the beginning, or after a
newline. The bug was in the code for advancing after a failed match and
checking that the new position followed a newline. It was not taking
account of UTF-8 characters correctly.
23. PCRE was behaving differently from Perl in the way it recognized POSIX
character classes. PCRE was not treating the sequence [:...:] as a
character class unless the ... were all letters. Perl, however, seems to
allow any characters between [: and :], though of course it rejects as
unknown any "names" that contain non-letters, because all the known class
names consist only of letters. Thus, Perl gives an error for [[:1234:]],
for example, whereas PCRE did not - it did not recognize a POSIX character
class. This seemed a bit dangerous, so the code has been changed to be
closer to Perl. The behaviour is not identical to Perl, because PCRE will
diagnose an unknown class for, for example, [[:l\ower:]] where Perl will
treat it as [[:lower:]]. However, PCRE does now give "unknown" errors where
Perl does, and where it didn't before.
24. Rewrite so as to remove the single use of %%n from pcregrep because in some
Windows environments %%n is disabled by default.
* Tue Nov 6 2007 crrodriguez@suse.de
- update to version 7.4, since version 7.2, more than 40 bugs were fixed
including multiple vulnerabilities [#325921] . The list of changes is too long
to mention here, see changelog.txt for details.
* Wed Aug 8 2007 ms@suse.de
- added fix to run ldconfig for libpcre*, Thanks to
Cristian Rodriguez <crrodriguez@novell.com> who provided
the patch (#298291)
* Mon Jul 23 2007 ms@suse.de
- update to version 7.2, fixes bug: (#293752)
- Changes from 7.1 to 7.2
1. If the fr_FR locale cannot be found for test 3, try the "french" locale,
which is apparently normally available under Windows.
2. Re-jig the pcregrep tests with different newline settings in an attempt
to make them independent of the local environment's newline setting.
3. Add code to configure.ac to remove -g from the CFLAGS default settings.
4. Some of the "internals" tests were previously cut out when the link size
was not 2, because the output contained actual offsets. The recent new
"Z" feature of pcretest means that these can be cut out, making the tests
usable with all link sizes.
5. Implemented Stan Switzer's goto replacement for longjmp() when not using
stack recursion. This gives a massive performance boost under BSD, but just
a small improvement under Linux. However, it saves one field in the frame
in all cases.
6. Added more features from the forthcoming Perl 5.10:
(a) (?-n) (where n is a string of digits) is a relative subroutine or
recursion call. It refers to the nth most recently opened parentheses.
(b) (?+n) is also a relative subroutine call; it refers to the nth next
to be opened parentheses.
(c) Conditions that refer to capturing parentheses can be specified
relatively, for example, (?(-2)... or (?(+3)...
(d) \K resets the start of the current match so that everything before
is not part of it.
(e) \k{name} is synonymous with \k<name> and \k'name' (.NET compatible).
(f) \g{name} is another synonym - part of Perl 5.10's unification of
reference syntax.
(g) (?| introduces a group in which the numbering of parentheses in each
alternative starts with the same number.
(h) \h, \H, \v, and \V match horizontal and vertical whitespace.
7. Added two new calls to pcre_fullinfo(): PCRE_INFO_OKPARTIAL and
PCRE_INFO_JCHANGED.
8. A pattern such as (.*(.)?)* caused pcre_exec() to fail by either not
terminating or by crashing. Diagnosed by Viktor Griph; it was in the code
for detecting groups that can match an empty string.
9. A pattern with a very large number of alternatives (more than several
hundred) was running out of internal workspace during the pre-compile
phase, where pcre_compile() figures out how much memory will be needed. A
bit of new cunning has reduced the workspace needed for groups with
alternatives. The 1000-alternative test pattern now uses 12 bytes of
workspace instead of running out of the 4096 that are available.
10. Inserted some missing (unsigned int) casts to get rid of compiler warnings.
11. Applied patch from Google to remove an optimization that didn't quite work.
The report of the bug said:
pcrecpp::RE("a*").FullMatch("aaa") matches, while
pcrecpp::RE("a*?").FullMatch("aaa") does not, and
pcrecpp::RE("a*?\\z").FullMatch("aaa") does again.
12. If \p or \P was used in non-UTF-8 mode on a character greater than 127
it matched the wrong number of bytes.
* Tue May 1 2007 ms@suse.de
- added --enable-unicode-properties configure option to support
UTF-8 character strings in \P, \p, and \X (#269749)
* Mon Apr 30 2007 trenn@suse.de
- corrected assert compile error
* Wed Apr 25 2007 ms@suse.de
- update to pcre 7.1
1. Applied Bob Rossi and Daniel G's patches to convert the build system to one
that is more "standard", making use of automake and other Autotools. There
is some re-arrangement of the files and adjustment of comments consequent
on this.
2. Part of the patch fixed a problem with the pcregrep tests. The test of -r
for recursive directory scanning broke on some systems because the files
are not scanned in any specific order and on different systems the order
was different. A call to "sort" has been inserted into RunGrepTest for the
approprate test as a short-term fix. In the longer term there may be an
alternative.
3. I had an email from Eric Raymond about problems translating some of PCRE's
man pages to HTML (despite the fact that I distribute HTML pages, some
people do their own conversions for various reasons). The problems
concerned the use of low-level troff macros .br and .in. I have therefore
removed all such uses from the man pages (some were redundant, some could
be replaced by .nf/.fi pairs). The 132html script that I use to generate
HTML has been updated to handle .nf/.fi and to complain if it encounters
.br or .in.
4. Updated comments in configure.ac that get placed in config.h.in and also
arranged for config.h to be included in the distribution, with the name
config.h.generic, for the benefit of those who have to compile without
Autotools (compare pcre.h, which is now distributed as pcre.h.generic).
5. Updated the support (such as it is) for Virtual Pascal, thanks to Stefan
Weber: (1) pcre_internal.h was missing some function renames; (2) updated
makevp.bat for the current PCRE, using the additional files
makevp_c.txt, makevp_l.txt, and pcregexp.pas.
6. A Windows user reported a minor discrepancy with test 2, which turned out
to be caused by a trailing space on an input line that had got lost in his
copy. The trailing space was an accident, so I've just removed it.
7. Add -Wl,-R... flags in pcre-config.in for *BSD* systems, as I'm told
that is needed.
8. Mark ucp_table (in ucptable.h) and ucp_gentype (in pcre_ucp_searchfuncs.c)
as "const" (a) because they are and (b) because it helps the PHP
maintainers who have recently made a script to detect big data structures
in the php code that should be moved to the .rodata section. I remembered
to update Builducptable as well, so it won't revert if ucptable.h is ever
re-created.
9. Added some extra #ifdef SUPPORT_UTF8 conditionals into pcretest.c,
pcre_printint.src, pcre_compile.c, pcre_study.c, and pcre_tables.c, in
order to be able to cut out the UTF-8 tables in the latter when UTF-8
support is not required. This saves 1.5-2K of code, which is important in
some applications.
Later: more #ifdefs are needed in pcre_ord2utf8.c and pcre_valid_utf8.c
so as not to refer to the tables, even though these functions will never be
called when UTF-8 support is disabled. Otherwise there are problems with a
shared library.
10. Fixed two bugs in the emulated memmove() function in pcre_internal.h:
(a) It was defining its arguments as char * instead of void *.
(b) It was assuming that all moves were upwards in memory; this was true
a long time ago when I wrote it, but is no longer the case.
The emulated memove() is provided for those environments that have neither
memmove() nor bcopy(). I didn't think anyone used it these days, but that
is clearly not the case, as these two bugs were recently reported.
11. The script PrepareRelease is now distributed: it calls 132html, CleanTxt,
and Detrail to create the HTML documentation, the .txt form of the man
pages, and it removes trailing spaces from listed files. It also creates
pcre.h.generic and config.h.generic from pcre.h and config.h. In the latter
case, it wraps all the #defines with #ifndefs. This script should be run
before "make dist".
12. Fixed two fairly obscure bugs concerned with quantified caseless matching
with Unicode property support.
(a) For a maximizing quantifier, if the two different cases of the
character were of different lengths in their UTF-8 codings (there are
some cases like this - I found 11), and the matching function had to
back up over a mixture of the two cases, it incorrectly assumed they
were both the same length.
(b) When PCRE was configured to use the heap rather than the stack for
recursion during matching, it was not correctly preserving the data for
the other case of a UTF-8 character when checking ahead for a match
while processing a minimizing repeat. If the check also involved
matching a wide character, but failed, corruption could cause an
erroneous result when trying to check for a repeat of the original
character.
13. Some tidying changes to the testing mechanism:
(a) The RunTest script now detects the internal link size and whether there
is UTF-8 and UCP support by running ./pcretest -C instead of relying on
values substituted by "configure". (The RunGrepTest script already did
this for UTF-8.) The configure.ac script no longer substitutes the
relevant variables.
(b) The debugging options /B and /D in pcretest show the compiled bytecode
with length and offset values. This means that the output is different
for different internal link sizes. Test 2 is skipped for link sizes
other than 2 because of this, bypassing the problem. Unfortunately,
there was also a test in test 3 (the locale tests) that used /B and
failed for link sizes other than 2. Rather than cut the whole test out,
I have added a new /Z option to pcretest that replaces the length and
offset values with spaces. This is now used to make test 3 independent
of link size. (Test 2 will be tidied up later.)
14. If erroroffset was passed as NULL to pcre_compile, it provoked a
segmentation fault instead of returning the appropriate error message.
15. In multiline mode when the newline sequence was set to "any", the pattern
^$ would give a match between the \r and \n of a subject such as "A\r\nB".
This doesn't seem right; it now treats the CRLF combination as the line
ending, and so does not match in that case. It's only a pattern such as ^$
that would hit this one: something like ^ABC$ would have failed after \r
and then tried again after \r\n.
16. Changed the comparison command for RunGrepTest from "diff -u" to "diff -ub"
in an attempt to make files that differ only in their line terminators
compare equal. This works on Linux.
17. Under certain error circumstances pcregrep might try to free random memory
as it exited. This is now fixed, thanks to valgrind.
19. In pcretest, if the pattern /(?m)^$/g<any> was matched against the string
"abc\r\n\r\n", it found an unwanted second match after the second \r. This
was because its rules for how to advance for /g after matching an empty
string at the end of a line did not allow for this case. They now check for
it specially.
20. pcretest is supposed to handle patterns and data of any length, by
extending its buffers when necessary. It was getting this wrong when the
buffer for a data line had to be extended.
21. Added PCRE_NEWLINE_ANYCRLF which is like ANY, but matches only CR, LF, or
CRLF as a newline sequence.
22. Code for handling Unicode properties in pcre_dfa_exec() wasn't being cut
out by #ifdef SUPPORT_UCP. This did no harm, as it could never be used, but
I have nevertheless tidied it up.
23. Added some casts to kill warnings from HP-UX ia64 compiler.
24. Added a man page for pcre-config.
* Fri Feb 9 2007 ms@suse.de
- fixed wrong usage of assert() call
* Tue Jan 9 2007 ms@suse.de
- fixed build for all architectures
* Mon Jan 8 2007 ms@suse.de
- update to new version 7.0
Changes: As well as a number of bugfixes, there has been a major
refactoring of the compiling code, which makes it easier to add new
features, including some new optimizations. A QuoteMeta function has been
added to the C++ wrapper. There is now a mode in which all Unicode newline
sequences are recognized. Support for the Perl 5.10 syntax for features
that were previously in PCRE but not in Perl (named groups, possessive
quantifiers) has been added.
* Sat Oct 28 2006 meissner@suse.de
- CXXFLAGS needs RPM_OPT_FLAGS too.
* Mon Jul 10 2006 ms@suse.de
- update to new version 6.7
- finally removed evil configure patch
- When UTF-8 mode was not set, PCRE looped when compiling certain patterns
containing an extended class (one that cannot be represented by a bitmap
because it contains high-valued characters or Unicode property items, e.g.
[\pZ]). Almost always one would set UTF-8 mode when processing such a
pattern, but PCRE should not loop if you do not (it no longer does).
[Detail: two cases were found: (a) a repeated subpattern containing an
extended class; (b) a recursive reference to a subpattern that followed a
previous extended class. It wasn't skipping over the extended class
correctly when UTF-8 mode was not set.]
- Applied a patch from the folks at Google to pcrecpp.cc, to fix "another
instance of the 'standard' template library not being so standard".
* Wed Jan 25 2006 mls@suse.de
- converted neededforbuild to BuildRequires
* Thu Jan 12 2006 mmj@suse.de
- build with -fstack-protector
* Thu Dec 1 2005 ro@suse.de
- hack libtool core in configure script
since configure.in is too broken for a autoreconf ...
* Mon Sep 19 2005 mmj@suse.de
- update to the latest version v6.4
* Tue Aug 2 2005 mmj@suse.de
- update to the latest version v6.2
* Thu Jun 23 2005 mmj@suse.de
- update to latest version v6.1
* Mon Jun 13 2005 mmj@suse.de
- add gcc-c++ to #nfb as well
* Wed Jun 8 2005 mmj@suse.de
- update to latest version v6.0
* Mon May 23 2005 mmj@suse.de
- use --enable-utf8
- use $RPM_OPT_FLAGS
* Thu Mar 31 2005 uli@suse.de
- ignore test suite errors on ARM
* Mon Nov 22 2004 choeger@suse.de
- update to latest version v5.0
* Mon Jun 7 2004 choeger@suse.de
- update to latest version v4.5
* Mon Jan 5 2004 schwab@suse.de
- Move pcre-config to pcre-devel.
* Fri Oct 31 2003 choeger@suse.de
- Don't build as root
* Thu Aug 21 2003 choeger@suse.de
- update to v4.4
* Fri Aug 1 2003 choeger@suse.de
- disabled Test2, because it is not 64bit arch clean
(contacted author, he knows about that problem)
* Wed Jul 30 2003 choeger@suse.de
- update to most recent version v4.3
- splitted into -devel subpackage
* Fri Dec 6 2002 coolo@suse.de
- removed undefined symbols in libpcreposix
* Tue Sep 17 2002 ro@suse.de
- removed bogus self-provides
* Fri Apr 5 2002 coolo@suse.de
- fixing autoheader usage
- forward ported %%libdir changes from sles7-s390x
* Tue Jan 22 2002 choeger@suse.de
- update to version 3.9
- added BuildRoot
* Mon Aug 20 2001 mge@suse.de
- pcre 3.5
* Wed Apr 11 2001 froh@suse.de
- suse_update_config
* Mon Dec 4 2000 mge@suse.de
- pcre 3.4
* Tue Jun 27 2000 mge@suse.de
- pcre 3.2
* Thu Mar 2 2000 mge@suse.de
- fixed manpath
* Sun Feb 13 2000 mge@suse.de
- update to 3.1
- group tag
* Mon Oct 25 1999 mge@suse.de
- initial SuSE-RPM: changed Makefile to install into /usr

39
pcre2.keyring Normal file
View file

@ -0,0 +1,39 @@
This is Philip Hazel's public GPG key.
-----BEGIN PGP PUBLIC KEY BLOCK-----
Version: GnuPG v1.2.0 (SunOS)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=EHsz
-----END PGP PUBLIC KEY BLOCK-----

259
pcre2.spec Normal file
View file

@ -0,0 +1,259 @@
#
# spec file for package pcre2
#
# Copyright (c) 2022-2023 ZhuningOS
#
%global _lto_cflags %{_lto_cflags} -ffat-lto-objects
Name: pcre2
Version: 10.39
Release: 150400.4.9.1
Summary: A library for Perl-compatible regular expressions
License: BSD-3-Clause
Group: Development/Libraries/C and C++
URL: https://www.pcre.org
Source0: https://github.com/PhilipHazel/pcre2/releases/download/%{name}-%{version}/%{name}-%{version}.tar.bz2
Source2: https://github.com/PhilipHazel/pcre2/releases/download/%{name}-%{version}/%{name}-%{version}.tar.bz2.sig
Source3: %{name}.keyring
Source4: baselibs.conf
#PATCH-FIX-OPENSUSE tchvatal@suse.cz upstream thinks it is good idea to use rpath, taken from RH
Patch1: pcre2-10.10-multilib.patch
# revert https://github.com/PhilipHazel/pcre2/commit/080d7789eba00b570181dfe28809b01aa88c01f8
Patch2: pcre2-readd-wrappers-POSIX.patch
Patch3: pcre2-10.39-bsc1199232-unicode-property-matching.patch
Patch4: pcre2-bsc1199235-CVE-2022-1587.patch
#PATCH-FIX-UPSTREAM bsc#1213514 CVE-2022-41409 Integer overflow vulnerability
Patch5: pcre2-CVE-2022-41409.patch
BuildRequires: autoconf
BuildRequires: automake
BuildRequires: gcc-c++
BuildRequires: libbz2-devel
BuildRequires: libedit-devel
BuildRequires: libtool
BuildRequires: pkgconfig
BuildRequires: zlib-devel
%description
The PCRE2 library is a set of functions that implement regular
expression pattern matching using the same syntax and semantics
as Perl 5.
PCRE2 is a re-working of the original PCRE library to provide an entirely new
API.
%package devel
Summary: A library for Perl-compatible regular expressions
Group: Development/Libraries/C and C++
Requires: libpcre2-16-0 = %{version}
Requires: libpcre2-32-0 = %{version}
Requires: libpcre2-8-0 = %{version}
Requires: libpcre2-posix2 = %{version}
Requires: libstdc++-devel
%description devel
The PCRE2 library is a set of functions that implement regular
expression pattern matching using the same syntax and semantics
as Perl 5.
PCRE2 is a re-working of the original PCRE library to provide an entirely new
API.
%package devel-static
Summary: A library for Perl-compatible regular expressions
Group: Development/Libraries/C and C++
Requires: pcre2-devel = %{version}
%description devel-static
The PCRE2 library is a set of functions that implement regular
expression pattern matching using the same syntax and semantics
as Perl 5.
PCRE2 is a re-working of the original PCRE library to provide an entirely new
API.
This package contains static versions of the PCRE2 libraries.
%package -n libpcre2-8-0
Summary: A library for Perl-compatible regular expressions
Group: System/Libraries
%description -n libpcre2-8-0
The PCRE2 library is a set of functions that implement regular
expression pattern matching using the same syntax and semantics
as Perl 5.
PCRE2 is a re-working of the original PCRE library to provide an entirely new
API.
This PCRE2 library variant supports 8-bit and UTF-8 strings.
(See also libpcre2-16 and libpcre2-32)
%package -n libpcre2-16-0
Summary: A library for Perl-compatible regular expressions
Group: System/Libraries
%description -n libpcre2-16-0
The PCRE2 library is a set of functions that implement regular
expression pattern matching using the same syntax and semantics
as Perl 5.
PCRE2 is a re-working of the original PCRE library to provide an entirely new
API.
libpcre2-16 supports 16-bit and UTF-16 strings.
%package -n libpcre2-32-0
Summary: A library for Perl-compatible regular expressions
Group: System/Libraries
%description -n libpcre2-32-0
The PCRE2 library is a set of functions that implement regular
expression pattern matching using the same syntax and semantics
as Perl 5.
PCRE2 is a re-working of the original PCRE library to provide an entirely new
API.
libpcre2-32 supports 32-bit and UTF-32 strings.
%package -n libpcre2-posix2
Summary: A library for Perl-compatible regular expressions
Group: System/Libraries
%description -n libpcre2-posix2
The PCRE2 library is a set of functions that implement regular
expression pattern matching using the same syntax and semantics
as Perl 5.
PCRE2 is a re-working of the original PCRE library to provide an entirely new
API.
pcre2-posix provides a POSIX-compatible API to the PCRE2 engine.
%package doc
Summary: A library for Perl-compatible regular expressions
Group: Documentation/HTML
BuildArch: noarch
%description doc
The PCRE2 library is a set of functions that implement regular
expression pattern matching using the same syntax and semantics
as Perl 5.
PCRE2 is a re-working of the original PCRE library to provide an entirely new
API.
%package tools
Summary: A library for Perl-compatible regular expressions
Group: Productivity/Text/Utilities
Recommends: %{name}-doc
%description tools
The PCRE2 library is a set of functions that implement regular
expression pattern matching using the same syntax and semantics
as Perl 5.
PCRE2 is a re-working of the original PCRE library to provide an entirely new
API.
%prep
%autosetup -p1
%build
%define _lto_cflags %{nil}
# Available JIT archs see sljit/sljitConfig.h
autoreconf -fiv
export LDFLAGS="-Wl,-z,relro,-z,now"
%configure \
%ifarch %{ix86} x86_64 aarch64 %{arm} ppc ppc64 ppc64le mips sparc s390x
--enable-jit \
%endif
--enable-static \
--with-link-size=2 \
--with-match-limit=10000000 \
--enable-newline-is-lf \
--enable-pcre2-16 \
--enable-pcre2-32 \
--enable-pcre2grep-libz \
--enable-pcre2grep-libbz2 \
--enable-pcre2test-libedit \
--enable-unicode
%if 0%{?do_profiling}
%make_build CFLAGS="%{optflags} %{cflags_profile_generate}"
export LANG=POSIX
# do not run profiling in parallel for reproducible builds (boo#1040589 boo#1102408)
%make_build CFLAGS="%{optflags} %{cflags_profile_generate}" check
%make_build clean
%make_build CFLAGS="%{optflags} %{cflags_profile_feedback}"
%else
%make_build CFLAGS="%{optflags}"
%endif
%install
%make_install
mkdir -p %{buildroot}/%{_defaultdocdir}
mv %{buildroot}%{_datadir}/doc/pcre2 %{buildroot}/%{_defaultdocdir}/pcre2-doc
#empty dependecy_libs
find %{buildroot} -type f -name "*.la" -delete -print
%check
export LANG=POSIX
%make_build check -j1
%post -n libpcre2-8-0 -p /sbin/ldconfig
%postun -n libpcre2-8-0 -p /sbin/ldconfig
%post -n libpcre2-16-0 -p /sbin/ldconfig
%postun -n libpcre2-16-0 -p /sbin/ldconfig
%post -n libpcre2-32-0 -p /sbin/ldconfig
%postun -n libpcre2-32-0 -p /sbin/ldconfig
%post -n libpcre2-posix2 -p /sbin/ldconfig
%postun -n libpcre2-posix2 -p /sbin/ldconfig
%files -n libpcre2-8-0
%license COPYING LICENCE
%doc AUTHORS ChangeLog NEWS README
%{_libdir}/libpcre2-8.so.*
%files -n libpcre2-16-0
%license LICENCE
%{_libdir}/libpcre2-16.so.*
%files -n libpcre2-32-0
%license LICENCE
%{_libdir}/libpcre2-32.so.*
%files -n libpcre2-posix2
%license LICENCE
%{_libdir}/libpcre2-posix.so.*
%files tools
%license LICENCE
%{_bindir}/pcre2grep
%{_bindir}/pcre2test
%{_mandir}/man1/pcre2grep.1%{?ext_man}
%{_mandir}/man1/pcre2test.1%{?ext_man}
%files doc
%license COPYING LICENCE
%doc AUTHORS ChangeLog NEWS README
%doc doc/html doc/*.txt
%doc %{_defaultdocdir}/pcre2-doc
%files devel
%license LICENCE
%{_bindir}/pcre2-config
%{_includedir}/*
%{_libdir}/*.so
%{_libdir}/pkgconfig/libpcre2-8.pc
%{_libdir}/pkgconfig/libpcre2-16.pc
%{_libdir}/pkgconfig/libpcre2-32.pc
%{_libdir}/pkgconfig/libpcre2-posix.pc
%{_mandir}/man1/pcre2-config.1%{?ext_man}
%{_mandir}/man3/*%{ext_man}
%files devel-static
%{_libdir}/*.a
%changelog