Ticket #5998: 5998-interrim.patch

wp-includes/formatting.php

@@ -246 +246 @@
 /**
  * Checks to see if a string is utf8 encoded.
  *
- * NOTE: This function checks for 5-Byte sequences, UTF8
+ * NOTE: This function checks for 6-Byte sequences, UTF8
  *       has Bytes Sequences with a maximum length of 4.
  *
  * @author bmorel at ssi dot fr (modified)
@@ -255 +255 @@
  * @param string $str The string to be checked
  * @return bool True if $str fits a UTF-8 model, false otherwise.
  */
-function seems_utf8($str) {
-        $length = strlen($str);
-        for ($i=0; $i < $length; $i++) {
-                $c = ord($str[$i]);
-                if ($c < 0x80) $n = 0; # 0bbbbbbb
-                elseif (($c & 0xE0) == 0xC0) $n=1; # 110bbbbb
-                elseif (($c & 0xF0) == 0xE0) $n=2; # 1110bbbb
-                elseif (($c & 0xF8) == 0xF0) $n=3; # 11110bbb
-                elseif (($c & 0xFC) == 0xF8) $n=4; # 111110bb
-                elseif (($c & 0xFE) == 0xFC) $n=5; # 1111110b
+function seems_utf8( $str ) {
+        $str    = (string) $str;
+        $length = strlen( $str );
+        for ( $i = 0; $i < $length; $i++ ) {
+                $c = ord( $str[$i] );
+                if ( $c < 0x80 ) $n = 0;               # 0bbbbbbb
+                elseif ( ($c & 0xE0) == 0xC0 ) $n = 1; # 110bbbbb
+                elseif ( ($c & 0xF0) == 0xE0 ) $n = 2; # 1110bbbb
+                elseif ( ($c & 0xF8) == 0xF0 ) $n = 3; # 11110bbb
+                elseif ( ($c & 0xFC) == 0xF8 ) $n = 4; # 111110bb // invalid UTF-8, in here 
+                elseif ( ($c & 0xFE) == 0xFC ) $n = 5; # 1111110b // for backcompat reasons 
                 else return false; # Does not match any model
-                for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
-                        if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80))
+                for ( $j = 0; $j < $n; $j++ ) { # n bytes matching 10bbbbbb follow ?
+                        if ( (++$i == $length) || ( (ord( $str[$i] ) & 0xC0) != 0x80) )
                                 return false;
                 }
         }