- Fixed bug #49687 (utf8_decode vulnerabilities and deficiencies in the number

  of reported malformed sequences). (Gustavo)
#Made a public interface for get_next_char/utf-8 in trunk to use in utf8_decode.
#In PHP 5.3, trunk's get_next_char was copied to xml.c because 5.3's
#get_next_char is different and is not prepared to recover appropriately from
#errors.

2 files changed, 34 insertions, 30 deletions

diff --git a/ext/xml/tests/bug49687.phpt b/ext/xml/tests/bug49687.phpt
new file mode 100644
index 0000000000..3ff19cee7e
--- /dev/null
+++ b/ext/xml/tests/bug49687.phpt
@@ -0,0 +1,24 @@
+--TEST--

+Bug #49687 Several utf8_decode deficiencies and vulnerabilities

+--SKIPIF--

+<?php

+require_once("skipif.inc");

+if (!extension_loaded('xml')) die ("skip xml extension not available");

+?>

+--FILE--

+<?php

+

+$tests = array(

+    "\x41\xC2\x3E\x42",

+    "\xE3\x80\x22",

+    "\x41\x98\xBA\x42\xE2\x98\x43\xE2\x98\xBA\xE2\x98",

+);

+foreach ($tests as $t) {

+    echo bin2hex(utf8_decode($t)), "\n";

+}

+echo "Done.\n";

+--EXPECT--

+413f3e42

+3f22

+413f3f423f433f3f

+Done.

diff --git a/ext/xml/xml.c b/ext/xml/xml.c
index 72729d6de5..54e03d5e63 100644
--- a/ext/xml/xml.c
+++ b/ext/xml/xml.c
@@ -32,6 +32,7 @@
 #include "zend_variables.h"
 #include "ext/standard/php_string.h"
 #include "ext/standard/info.h"
+#include "ext/standard/html.h"
 
 #if HAVE_XML
 
@@ -662,7 +663,7 @@ PHPAPI char *xml_utf8_encode(const char *s, int len, int *newlen, const XML_Char
 /* {{{ xml_utf8_decode */
 PHPAPI char *xml_utf8_decode(const XML_Char *s, int len, int *newlen, const XML_Char *encoding)
 {
-	int pos = len;
+	size_t pos = 0;
 	char *newbuf = emalloc(len + 1);
 	unsigned int c;
 	char (*decoder)(unsigned short) = NULL;
@@ -681,36 +682,15 @@ PHPAPI char *xml_utf8_decode(const XML_Char *s, int len, int *newlen, const XML_
 		newbuf[*newlen] = '\0';
 		return newbuf;
 	}
-	while (pos > 0) {
-		c = (unsigned char)(*s);
-		if (c >= 0xf0) { /* four bytes encoded, 21 bits */
-			if(pos-4 >= 0) {
-				c = ((s[0]&7)<<18) | ((s[1]&63)<<12) | ((s[2]&63)<<6) | (s[3]&63);
-			} else {
-				c = '?';	
-			}
-			s += 4;
-			pos -= 4;
-		} else if (c >= 0xe0) { /* three bytes encoded, 16 bits */
-			if(pos-3 >= 0) {
-				c = ((s[0]&63)<<12) | ((s[1]&63)<<6) | (s[2]&63);
-			} else {
-				c = '?';
-			}
-			s += 3;
-			pos -= 3;
-		} else if (c >= 0xc0) { /* two bytes encoded, 11 bits */
-			if(pos-2 >= 0) {
-				c = ((s[0]&63)<<6) | (s[1]&63);
-			} else {
-				c = '?';
-			}
-			s += 2;
-			pos -= 2;
-		} else {
-			s++;
-			pos--;
+
+	while (pos < (size_t)len) {
+		int status = FAILURE;
+		c = php_next_utf8_char((const unsigned char*)s, (size_t) len, &pos, &status);
+
+		if (status == FAILURE || c > 0xFFU) {
+			c = '?';
 		}
+
 		newbuf[*newlen] = decoder ? decoder(c) : c;
 		++*newlen;
 	}