Ticket #29717: 29717.4.patch

formatting.php

@@ -695 +695 @@
 /**
  * Checks for invalid UTF8 in a string.
  *
+ * Could change the ini_setting mbstring.substitute_character to 'none' without restoring.
+ *
  * @since 2.8.0
  *
  * @param string $string The text which is to be checked.
  * @param boolean $strip Optional. Whether to attempt to strip out invalid UTF8. Default is false.
- * @return string The checked text.
+ * @return string If the string is valid UTF-8 or the blog_charset is not UTF-8, the string is returned unmodified. Otherwise, an empty string is returned, or optionally the string stripped of invalid chars.
  */
 function wp_check_invalid_utf8( $string, $strip = false ) {
         $string = (string) $string;
 
-        if ( 0 === strlen( $string ) ) {
+        // if string length is 0 (faster than strlen) return empty
+        if ( ! isset( $string[0] ) ) {
                 return '';
         }
 
-        // Store the site charset as a static to avoid multiple calls to get_option()
+        // Store the site charset
         static $is_utf8;
-        if ( !isset( $is_utf8 ) ) {
-                $is_utf8 = in_array( get_option( 'blog_charset' ), array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) );
+
+        // if first time this function is called, save boolean if utf-8 enabled or not static
+        if ( ! isset( $is_utf8 ) ) {
+                $is_utf8 = ( in_array( get_option( 'blog_charset' ), array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) ) );
         }
-        if ( !$is_utf8 ) {
+
+        // if utf not used return the string
+        if ( ! $is_utf8 ) {
                 return $string;
         }
 
+        // Whether pcre is enabled, and whether pcre needs to use the (*UTF8) trick
+        static $pcre_utf8;
+
         // Check for support for utf8 in the installed PCRE library once and store the result in a static
-        static $utf8_pcre;
-        if ( !isset( $utf8_pcre ) ) {
-                $utf8_pcre = @preg_match( '/^./u', 'a' );
+        if ( ! isset( $pcre_utf8 ) ) {
+                $pcre_utf8 = ( @preg_match( '//u', '' ) !== false );
         }
-        // We can't demand utf8 in the PCRE installation, so just return the string in those cases
-        if ( !$utf8_pcre ) {
+
+        // If pcre_utf /u modifier allowed and the utf is valid, return string
+        if ( $pcre_utf8 && @preg_match( '//u', $string ) !== false ) {
                 return $string;
         }
 
-        // preg_match fails when it encounters invalid UTF8 in $string
-        if ( 1 === @preg_match( '/^./us', $string ) ) {
-                return $string;
+        // just means that the /u modifier is disallowed, so try the pattern option
+        if ( ! $pcre_utf8 ) {
+
+                // Use the pattern option for pcre and return string if valid.  Else use the regex
+                if ( @preg_match( '/(*UTF8)/', $string ) !== false ) {
+                        return $string;
+                } else {
+
+                        // pcre was compiled explicitly to forbid the support of UTF.  So use a regex to check (third times the charm)
+                        $pattern = '/(
+                                [\xC0-\xC1] # Invalid UTF-8 Bytes
+                                | [\xF5-\xFF] # Invalid UTF-8 Bytes
+                                | \xE0[\x80-\x9F] # Overlong encoding of prior code point
+                                | \xF0[\x80-\x8F] # Overlong encoding of prior code point
+                                | [\xC2-\xDF](?![\x80-\xBF]) # Invalid UTF-8 Sequence Start
+                                | [\xE0-\xEF](?![\x80-\xBF]{2}) # Invalid UTF-8 Sequence Start
+                                | [\xF0-\xF4](?![\x80-\xBF]{3}) # Invalid UTF-8 Sequence Start
+                                | (?<=[\x0-\x7F\xF5-\xFF])[\x80-\xBF] # Invalid UTF-8 Sequence Middle
+                                | (?<![\xC2-\xDF]|[\xE0-\xEF]|[\xE0-\xEF][\x80-\xBF]|[\xF0-\xF4]|[\xF0-\xF4][\x80-\xBF]|[\xF0-\xF4][\x80-\xBF]{2})[\x80-\xBF] # Overlong Sequence
+                                | (?<=[\xE0-\xEF])[\x80-\xBF](?![\x80-\xBF]) # Short 3 byte sequence
+                                | (?<=[\xF0-\xF4])[\x80-\xBF](?![\x80-\xBF]{2}) # Short 4 byte sequence
+                                | (?<=[\xF0-\xF4][\x80-\xBF])[\x80-\xBF](?![\x80-\xBF]) # Short 4 byte sequence (2)
+                        )/x';
+
+                        // if the utf is valid return the string
+                        if ( @preg_match( $pattern , $string ) === 1 ) {
+                                return $string;
+                        }
+                }
         }
 
         // Attempt to strip the bad chars if requested (not recommended)
-        if ( $strip && function_exists( 'iconv' ) ) {
-                return iconv( 'utf-8', 'utf-8', $string );
+        if ( $strip ) {
+                // Whether inconv is available
+                static $iconv;
+
+                // Check once for support for iconv and save statically, if not set the mbstring.substitute_character ini
+                if ( ! isset( $iconv ) ) {
+                        $iconv = function_exists( 'iconv' );
+
+                        if ( ! $iconv ) {
+                                // only create a static var if $iconv is not available since only then will the final if ( $mb_convert ) check utilize this var
+                                static $mb_convert;
+
+                                // if mb_convert_encoding is available, set the ini_setting once                        
+                                @ini_set( 'mbstring.substitute_character', 'none' );
+                                $mb_convert = ( function_exists( 'mb_convert_encoding' ) && @ini_get( 'mbstring.substitute_character' ) === 'none' );
+                        }
+                }
+
+                // use iconv if exists
+                if ( $iconv ) {
+                        return @iconv( 'utf-8', 'utf-8//ignore', $string );
+                }
+
+                // otherwise try to use mb_convert_encoding, setting the substitue_character to none to mimic strip
+                if ( $mb_convert ) {
+                        return @mb_convert_encoding( $string, 'utf-8', 'utf-8' );
+                }
         }
 
+        // default to returning empty string, meaning invalid utf was found
         return '';
 }