From: Brion Vibber <brion@users.mediawiki.org>
Date: Fri, 9 Mar 2007 16:22:24 +0000 (+0000)
Subject: * Fix fallback implementation of mb_strlen so it works and isn't insanely
X-Git-Tag: 1.31.0-rc.0~53828
X-Git-Url: http://git.cyclocoop.org/%22.%28%24lien.?a=commitdiff_plain;h=2c9cb9dcbd5fad07049e91a7ba59613f30106c52;p=lhc%2Fweb%2Fwiklou.git

* Fix fallback implementation of mb_strlen so it works and isn't insanely
  slow for large strings, since it's used for page edit lengths
---

diff --git a/RELEASE-NOTES b/RELEASE-NOTES
index 151c57824d..33f896ab0c 100644
--- a/RELEASE-NOTES
+++ b/RELEASE-NOTES
@@ -259,6 +259,9 @@ lighter making things easier to read.
 * (bug 6997) Link from Special:log/block to unblock form
 * (bug 9117) Link from Special:log/delete to undelete form
 * Link from Special:log/protect to change protection form
+* Fix fallback implementation of mb_strlen so it works and isn't insanely
+  slow for large strings, since it's used for page edit lengths
+
 
 == Languages updated ==
 
diff --git a/includes/GlobalFunctions.php b/includes/GlobalFunctions.php
index 61b930d458..19eb4be087 100644
--- a/includes/GlobalFunctions.php
+++ b/includes/GlobalFunctions.php
@@ -62,9 +62,26 @@ if ( !function_exists( 'mb_substr' ) ) {
 }
 
 if ( !function_exists( 'mb_strlen' ) ) {
-	function mb_strlen( $str, $enc = "" ) {
-		preg_match_all( '/./us', $str, $matches );
-		return count($matches);
+	/**
+	 * Fallback implementation of mb_strlen, hardcoded to UTF-8.
+	 * @param string $str
+	 * @param string $enc optional encoding; ignored
+	 * @return int
+	 */
+	function new_mb_strlen( $str, $enc="" ) {
+		$counts = count_chars( $str );
+		$total = 0;
+
+		// Count ASCII bytes
+		for( $i = 0; $i < 0x80; $i++ ) {
+			$total += $counts[$i];
+		}
+
+		// Count multibyte sequence heads
+		for( $i = 0xc0; $i < 0xff; $i++ ) {
+			$total += $counts[$i];
+		}
+		return $total;
 	}
 }