From 848507ccffdaf1d7de395d210869eb7684bf4394 Mon Sep 17 00:00:00 2001
From: Ryan Boren <ryan@git.wordpress.org>
Date: Wed, 20 May 2009 21:13:14 +0000
Subject: [PATCH] seems_utf8() cleanup. Props hakre. fixes #9692

git-svn-id: https://develop.svn.wordpress.org/trunk@11414 602fd350-edb4-49c9-b593-d223f7449a82
---
 wp-includes/formatting.php | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/wp-includes/formatting.php b/wp-includes/formatting.php
index 9b44ec5772..f69dc4f0c4 100644
--- a/wp-includes/formatting.php
+++ b/wp-includes/formatting.php
@@ -172,26 +172,29 @@ function wpautop($pee, $br = 1) {
 /**
  * Checks to see if a string is utf8 encoded.
  *
- * @author bmorel at ssi dot fr
+ * NOTE: This function checks for 5-Byte sequences, UTF8 
+ *       has Bytes Sequences with a maximum length of 4.
  *
+ * @author bmorel at ssi dot fr (modified)
  * @since 1.2.1
  *
- * @param string $Str The string to be checked
- * @return bool True if $Str fits a UTF-8 model, false otherwise.
+ * @param string $str The string to be checked
+ * @return bool True if $str fits a UTF-8 model, false otherwise.
  */
-function seems_utf8($Str) { # by bmorel at ssi dot fr
-	$length = strlen($Str);
+function seems_utf8(&$str) {
+	$length = strlen($str);
 	for ($i=0; $i < $length; $i++) {
-		if (ord($Str[$i]) < 0x80) continue; # 0bbbbbbb
-		elseif ((ord($Str[$i]) & 0xE0) == 0xC0) $n=1; # 110bbbbb
-		elseif ((ord($Str[$i]) & 0xF0) == 0xE0) $n=2; # 1110bbbb
-		elseif ((ord($Str[$i]) & 0xF8) == 0xF0) $n=3; # 11110bbb
-		elseif ((ord($Str[$i]) & 0xFC) == 0xF8) $n=4; # 111110bb
-		elseif ((ord($Str[$i]) & 0xFE) == 0xFC) $n=5; # 1111110b
+		$c = ord($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) $n=5; # 1111110b
 		else return false; # Does not match any model
 		for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
-			if ((++$i == $length) || ((ord($Str[$i]) & 0xC0) != 0x80))
-			return false;
+			if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80))
+				return false;
 		}
 	}
 	return true;