From 59c81169ef94c56493f04dd62bff20404af47d0e Mon Sep 17 00:00:00 2001
From: Rajesh Taneja <rajesh@moodle.com>
Date: Tue, 21 Feb 2012 16:31:20 +0800
Subject: [PATCH] MDL-22896 libraries: Updated regular expression in html2text,
 for replacing unknown/unhandled entities

---
 lib/html2text.php | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/html2text.php b/lib/html2text.php
index e360b2c47d2..0320433362a 100644
--- a/lib/html2text.php
+++ b/lib/html2text.php
@@ -470,7 +470,7 @@ class html2text
         $text = html_entity_decode($text, ENT_COMPAT, 'UTF-8');
 
         // Remove unknown/unhandled entities (this cannot be done in search-and-replace block)
-        $text = preg_replace('/&[^&;]+;/i', '', $text);
+        $text = preg_replace('/&([a-zA-Z0-9]{2,6}|#[0-9]{2,4});/', '', $text);
 
         // Strip any other HTML tags
         $text = strip_tags($text, $this->allowed_tags);
-- 
2.17.1