From a3a2744d033c41a0456d495f6a0fb5e8165224bf Mon Sep 17 00:00:00 2001
From: Brion Vibber <brion@users.mediawiki.org>
Date: Fri, 28 Dec 2007 21:34:49 +0000
Subject: [PATCH] * (bug 3097) Inconsistently usable titles containing HTML
 character entities   are now forbidden. A run of cleanupTitles.php will fix
 up existing pages.

---
 RELEASE-NOTES      |  2 ++
 includes/Title.php | 14 ++++++++++++--
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/RELEASE-NOTES b/RELEASE-NOTES
index 6a43665a5e..5e80096150 100644
--- a/RELEASE-NOTES
+++ b/RELEASE-NOTES
@@ -270,6 +270,8 @@ it from source control: http://www.mediawiki.org/wiki/Download_from_SVN
 * (bug 8066) Spaces can't be entered in special page aliases
 * Hide undo link if user can't edit article
 * (bug 12416) Fix password setting for createAndPromote.php
+* (bug 3097) Inconsistently usable titles containing HTML character entities
+  are now forbidden. A run of cleanupTitles.php will fix up existing pages.
 
 
 == Parser changes in 1.12 ==
diff --git a/includes/Title.php b/includes/Title.php
index 2225aa358e..c78870762c 100644
--- a/includes/Title.php
+++ b/includes/Title.php
@@ -1894,8 +1894,18 @@ class Title {
 		# Initialisation
 		static $rxTc = false;
 		if( !$rxTc ) {
-			# % is needed as well
-			$rxTc = '/[^' . Title::legalChars() . ']|%[0-9A-Fa-f]{2}/S';
+			# Matching titles will be held as illegal.
+			$rxTc = '/' .
+				# Any character not allowed is forbidden...
+				'[^' . Title::legalChars() . ']' .
+				# URL percent encoding sequences interfere with the ability
+				# to round-trip titles -- you can't link to them consistently.
+				'|%[0-9A-Fa-f]{2}' .
+				# XML/HTML character references produce similar issues.
+				'|&[A-Za-z0-9\x80-\xff]+;' .
+				'|&#[0-9]+;' .
+				'|&#x[0-9A-Fa-f]+;' .
+				'/S';
 		}
 
 		$this->mInterwiki = $this->mFragment = '';
-- 
2.20.1