From 3279ee8a5057f915d12cf4a0693ecfa0449d3f93 Mon Sep 17 00:00:00 2001
From: Christian Schneider
Date: Thu, 5 Jul 2007 14:10:43 +0000
Subject: Handle XML files with BOM marker (Byte Order Mark)

---
 xml.class | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'xml.class')

diff --git a/xml.class b/xml.class
index 24a9f23..8cd386a 100644
--- a/xml.class
+++ b/xml.class
@@ -56,6 +56,7 @@ function from_xml($xmldata, $p)
 	xml_set_element_handler($parser, "start_element", "end_element");
 	xml_set_character_data_handler($parser, "character_data");
 	xml_parser_set_option($parser, XML_OPTION_CASE_FOLDING, 0);
+	xml_parser_set_option($parser, XML_OPTION_TARGET_ENCODING, $this->_p['encoding']);
 	
 	$result = true;
 
@@ -74,7 +75,9 @@ function from_xml($xmldata, $p)
 	}
 	else
 	{
-		if (!preg_match('/^<\?xml/', $xmldata))	# Prepend XML header for charset detection in PHP5
+		# Add header for charset detection (PHP5) if no header/BOM
+		# See http://www.w3.org/TR/2006/REC-xml-20060816/#sec-guessing
+		if (!preg_match('/^(<\?xml|\xEF\xBB\xBF|\xFE\xFF|\xFF\xFE|\x00\x00\xFE\xFF|\x00\x00\xFF\xFE)/', $xmldata))
 			$xmldata = '<?xml version="1.0" encoding="' . $this->_p['encoding'] . '"?>' . $xmldata;
 
 		$result = xml_parse($parser, $xmldata);
-- 
cgit v1.2.3