From: Rajesh Taneja <rajesh@moodle.com>
Date: Tue, 21 Feb 2012 08:31:20 +0000 (+0800)
Subject: MDL-22896 libraries: Updated regular expression in html2text, for replacing unknown... 
X-Git-Tag: v2.3.0-beta~1129^2
X-Git-Url: http://git.moodle.org/gw?p=moodle.git;a=commitdiff_plain;h=59c81169ef94c56493f04dd62bff20404af47d0e

MDL-22896 libraries: Updated regular expression in html2text, for replacing unknown/unhandled entities
---

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);