From f90dd6f3d74646efdc33942933e43264cca1b46c Mon Sep 17 00:00:00 2001 From: Michael M Slusarz Date: Fri, 6 Aug 2010 12:54:50 -0600 Subject: [PATCH] Fix bad encoding when parsing HTML data --- framework/Text_Filter/lib/Horde/Text/Filter/Xss.php | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/framework/Text_Filter/lib/Horde/Text/Filter/Xss.php b/framework/Text_Filter/lib/Horde/Text/Filter/Xss.php index 0dc9d3c4e..456971817 100644 --- a/framework/Text_Filter/lib/Horde/Text/Filter/Xss.php +++ b/framework/Text_Filter/lib/Horde/Text/Filter/Xss.php @@ -106,6 +106,11 @@ class Horde_Text_Filter_Xss extends Horde_Text_Filter_Base $old_error = libxml_use_internal_errors(true); $doc = new DOMDocument(); $doc->loadHTML($text); + if (!$doc->encoding) { + /* If libxml can't auto-detect encoding, convert to ISO-8859-1 + * manually. */ + $doc->loadHTML(Horde_String::convertCharset($text, $this->_params['charset'], 'ISO-8859-1')); + } if ($old_error) { libxml_use_internal_errors(false); } -- 2.11.0