archive/php-src
1
0
Fork 0
mirror of https://github.com/php/php-src.git synced 2025-08-16 05:58:45 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

PCRE: Only remember valid UTF-8 if start offset zero

Browse source 
PCRE only validates the string starting from the start offset
(minus maximum look-behind, but let's ignore that), so we can
only remember that the string is fully valid UTF-8 is the original
start offset is zero.
This commit is contained in:
Nikita Popov 2020-02-07 17:01:39 +01:00
parent c9e78e6d33
commit cd5591a28d
3 changed files with 19 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

1
NEWS
View file

@ -13,6 +13,7 @@ PHP NEWS
- PCRE: - PCRE:
. Fixed bug #79188 (Memory corruption in preg_replace/preg_replace_callback . Fixed bug #79188 (Memory corruption in preg_replace/preg_replace_callback
and unicode). (Nikita) and unicode). (Nikita)
. Fixed bug #79241 (Segmentation fault on preg_match()). (Nikita)
?? ??? ????, PHP 7.4.3 ?? ??? ????, PHP 7.4.3

11
ext/pcre/php_pcre.c
View file

@ -1167,7 +1167,7 @@ PHPAPI void php_pcre_match_impl(pcre_cache_entry *pce, zend_string *subject_str,
PCRE2_SPTR mark = NULL; /* Target for MARK name */ PCRE2_SPTR mark = NULL; /* Target for MARK name */
zval marks; /* Array of marks for PREG_PATTERN_ORDER */ zval marks; /* Array of marks for PREG_PATTERN_ORDER */
pcre2_match_data *match_data; pcre2_match_data *match_data;
PCRE2_SIZE start_offset2; PCRE2_SIZE start_offset2, orig_start_offset;
char *subject = ZSTR_VAL(subject_str); char *subject = ZSTR_VAL(subject_str);
size_t subject_len = ZSTR_LEN(subject_str); size_t subject_len = ZSTR_LEN(subject_str);
@ -1263,8 +1263,10 @@ PHPAPI void php_pcre_match_impl(pcre_cache_entry *pce, zend_string *subject_str,
} }
} }
options = (pce->compile_options & PCRE2_UTF) && !is_known_valid_utf8(subject_str, start_offset2) orig_start_offset = start_offset2;
? 0 : PCRE2_NO_UTF_CHECK; options =
(pce->compile_options & PCRE2_UTF) && !is_known_valid_utf8(subject_str, orig_start_offset)
? 0 : PCRE2_NO_UTF_CHECK;
/* Execute the regular expression. */ /* Execute the regular expression. */
#ifdef HAVE_PCRE_JIT_SUPPORT #ifdef HAVE_PCRE_JIT_SUPPORT
@ -1454,7 +1456,8 @@ error:
if (PCRE_G(error_code) == PHP_PCRE_NO_ERROR) { if (PCRE_G(error_code) == PHP_PCRE_NO_ERROR) {
/* If there was no error and we're in /u mode, remember that the string is valid UTF-8. */ /* If there was no error and we're in /u mode, remember that the string is valid UTF-8. */
if ((pce->compile_options & PCRE2_UTF) && !ZSTR_IS_INTERNED(subject_str)) { if ((pce->compile_options & PCRE2_UTF)
&& !ZSTR_IS_INTERNED(subject_str) && orig_start_offset == 0) {
GC_ADD_FLAGS(subject_str, IS_STR_VALID_UTF8); GC_ADD_FLAGS(subject_str, IS_STR_VALID_UTF8);
} }

11
ext/pcre/tests/bug79241.phpt
View file

@ -15,8 +15,19 @@ var_dump(preg_match($pattern, $text, $matches, 0, 0));
var_dump(preg_match($pattern, $text, $matches, 0, 1)); var_dump(preg_match($pattern, $text, $matches, 0, 1));
var_dump(preg_last_error() == PREG_BAD_UTF8_OFFSET_ERROR); var_dump(preg_last_error() == PREG_BAD_UTF8_OFFSET_ERROR);
echo "\n";
$text = "VA\xff"; $text .= "LID";
var_dump(preg_match($pattern, $text, $matches, 0, 4));
var_dump(preg_match($pattern, $text, $matches, 0, 0));
var_dump(preg_last_error() == PREG_BAD_UTF8_ERROR);
?> ?>
--EXPECT-- --EXPECT--
int(0) int(0)
bool(false) bool(false)
bool(true) bool(true)
int(1)
bool(false)
bool(true)