Revert "Strip Unicode 6.3.0 directional formatting characters from title"

[lhc/web/wiklou.git] / includes / title / MediaWikiTitleCodec.php

diff --git a/includes/title/MediaWikiTitleCodec.php b/includes/title/MediaWikiTitleCodec.php
index efc0fd4..655884b 100644 (file)
--- a/includes/title/MediaWikiTitleCodec.php
+++ b/includes/title/MediaWikiTitleCodec.php
@@ -1,6 +1,6 @@
 <?php
 /**
- * A codec for %MediaWiki page titles.
+ * A codec for MediaWiki page titles.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -18,7 +18,6 @@
  * http://www.gnu.org/copyleft/gpl.html
  *
  * @file
- * @license GPL 2+
  * @author Daniel Kinzler
  */
 use MediaWiki\Interwiki\InterwikiLookup;
@@ -26,7 +25,7 @@ use MediaWiki\MediaWikiServices;
 use MediaWiki\Linker\LinkTarget;
 
 /**
- * A codec for %MediaWiki page titles.
+ * A codec for MediaWiki page titles.
  *
  * @note Normalization and validation is applied while parsing, not when formatting.
  * It's possible to construct a TitleValue with an invalid title, and use MediaWikiTitleCodec
@@ -276,10 +275,11 @@ class MediaWikiTitleCodec implements TitleFormatter, TitleParser {
                        'user_case_dbkey' => $dbkey,
                ];
 
-               # Strip Unicode bidi override characters.
+               # Strip soft hyphens (U+00AD) and Unicode bidi override characters
+               # (U+200E, U+200F, U+202A. U+202B, U+202C, U+202D, U+202E).
                # Sometimes they slip into cut-n-pasted page titles, where the
-               # override chars get included in list displays.
-               $dbkey = preg_replace( '/\xE2\x80[\x8E\x8F\xAA-\xAE]/S', '', $dbkey );
+               # soft hyphens or override chars get included in list displays.
+               $dbkey = preg_replace( '/\xC2\xAD|\xE2\x80[\x8E\x8F\xAA-\xAE]/S', '', $dbkey );
 
                # Clean up whitespace
                # Note: use of the /u option on preg_replace here will cause