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 7c2d393..655884b 100644 (file)
--- a/includes/title/MediaWikiTitleCodec.php
+++ b/includes/title/MediaWikiTitleCodec.php
@@ -275,15 +275,11 @@ class MediaWikiTitleCodec implements TitleFormatter, TitleParser {
                        'user_case_dbkey' => $dbkey,
                ];
 
-               # Strip soft hyphens (U+00AD) and Unicode directional formatting characters (U+061C, U+200E,
-               # U+200F, U+202A. U+202B, U+202C, U+202D, U+202E, U+2066, U+2067, U+2068, U+2069).
+               # 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
                # soft hyphens or override chars get included in list displays.
-               $dbkey = preg_replace(
-                       '/\xC2\xAD|\xD8\x9C|\xE2\x80[\x8E\x8F\xAA-\xAE]|\xE2\x81[\xA6-\xA9]/S',
-                       '',
-                       $dbkey
-               );
+               $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