Commit 1b091dcf375 for php.net
commit 1b091dcf37544e3f871db57e97e224371d85ec8d
Author: Arnaud Le Blanc <365207+arnaud-lb@users.noreply.github.com>
Date: Mon Jul 27 18:01:34 2026 +0200
Forbid \C in UTF-8 patterns (#21139)
Fixes GH-21134
diff --git a/NEWS b/NEWS
index 0aa44c4d500..1dc666e361b 100644
--- a/NEWS
+++ b/NEWS
@@ -16,6 +16,10 @@ PHP NEWS
. Fixed bug GH-22779 (mb_strrpos() returns the wrong position for a negative
offset in a non-UTF-8 encoding). (Eyüp Can Akman)
+- PCRE:
+ . Fixed bug GH-21134 (Crash with \C + UTF-8). Using \C in UTF-8 patterns is
+ now forbidden. (Arnaud)
+
- Sockets:
. Fixed various memory related issues in ext/sockets. (David Carlier)
diff --git a/ext/pcre/php_pcre.c b/ext/pcre/php_pcre.c
index 43cee3b6b57..6a24691a170 100644
--- a/ext/pcre/php_pcre.c
+++ b/ext/pcre/php_pcre.c
@@ -734,6 +734,8 @@ PHPAPI pcre_cache_entry* pcre_get_compiled_regex_cache_ex(zend_string *regex, bo
#ifdef PCRE2_UCP
coptions |= PCRE2_UCP;
#endif
+ /* The \C escape sequence is unsafe in PCRE2_UTF mode */
+ coptions |= PCRE2_NEVER_BACKSLASH_C;
break;
case 'J': coptions |= PCRE2_DUPNAMES; break;
@@ -787,8 +789,13 @@ PHPAPI pcre_cache_entry* pcre_get_compiled_regex_cache_ex(zend_string *regex, bo
if (key != regex) {
zend_string_release_ex(key, 0);
}
- pcre2_get_error_message(errnumber, error, sizeof(error));
- php_error_docref(NULL,E_WARNING, "Compilation failed: %s at offset %zu", error, erroffset);
+ const char *err_msg = (const char*) error;
+ if (errnumber == PCRE2_ERROR_BACKSLASH_C_CALLER_DISABLED) {
+ err_msg = "using \\C is incompatible with the 'u' modifier";
+ } else {
+ pcre2_get_error_message(errnumber, error, sizeof(error));
+ }
+ php_error_docref(NULL,E_WARNING, "Compilation failed: %s at offset %zu", err_msg, erroffset);
pcre_handle_exec_error(PCRE2_ERROR_INTERNAL);
efree(pattern);
return NULL;
diff --git a/ext/pcre/tests/gh21134.phpt b/ext/pcre/tests/gh21134.phpt
new file mode 100644
index 00000000000..ddcf19a6e7a
--- /dev/null
+++ b/ext/pcre/tests/gh21134.phpt
@@ -0,0 +1,15 @@
+--TEST--
+GH-21134: ASan negative-size-param in preg_match_all() with \C + UTF-8 multibyte input
+--CREDITS--
+vi3tL0u1s
+--FILE--
+<?php
+
+$r = preg_match_all("/(.*)\\C/u", "à", $m);
+var_dump($r, $m);
+
+?>
+--EXPECTF--
+Warning: preg_match_all(): Compilation failed: using \C is incompatible with the 'u' modifier at offset 6 in %s on line %d
+bool(false)
+NULL