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

2012-02-24 10:10:08 +08:00
parent d1c12af76e
commit cd1a0a72a5
1 changed files with 1 additions and 1 deletions
@@ -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);