diff options
author | Christian Weber | 2012-03-23 15:28:10 +0000 |
---|---|---|
committer | Christian Weber | 2012-03-23 15:28:10 +0000 |
commit | 6c6828a8f0904110a67fe89031f9d4eaedf29213 (patch) | |
tree | 3269f6c18dac1eef3bf125e81072b334d27048be /it_xml.class | |
parent | b7e99acb4b7f53799751c07ac9aae3de5fabd99e (diff) | |
download | itools-6c6828a8f0904110a67fe89031f9d4eaedf29213.tar.gz itools-6c6828a8f0904110a67fe89031f9d4eaedf29213.tar.bz2 itools-6c6828a8f0904110a67fe89031f9d4eaedf29213.zip |
it_xml uses correct target encoding by default, adapt tests to utf-8 deafult
Diffstat (limited to 'it_xml.class')
-rw-r--r-- | it_xml.class | 11 |
1 files changed, 5 insertions, 6 deletions
diff --git a/it_xml.class b/it_xml.class index 0679c69..f854682 100644 --- a/it_xml.class +++ b/it_xml.class @@ -29,7 +29,7 @@ class it_xml * @param $p associative array * @param $p['forcearray'] xml tags to ALWAYS return as array * @param $p['safety'] 2 causes program abort with invalid xml, 1 (default) causes error report, 0 just returns false - * @param $p['encoding'] Output character encoding (e.g. UTF-8, default: ISO-8859-1) + * @param $p['encoding'] Output character encoding (utf-8, iso-8859-1 or us-ascii, default: ini_get('default_charset') * @param $p['prefix'] Optional prefix for class names * @param $p['lowercase'] Lowercase all tag and attribute names * @return XML object tree or null on failure @@ -49,23 +49,22 @@ function it_xml($xmldata = "", $p = array()) function create($xmldata, $p = array()) { $xml = new it_xml; - return $xml->from_xml($xmldata, array('factory' => true) + $p) ? $xml->_root : null; } function from_xml($xmldata, $p) { - $this->_p = $p + array('encoding' => "ISO-8859-1", 'safety' => 1); + $this->_p = $p + array('encoding' => ini_get('default_charset'), 'safety' => 1); $this->_arrayforce = array_flip((array)$this->_p['forcearray']); $this->_stack = array(); unset($this->error); - $parser = xml_parser_create($this->_p['encoding']); + $parser = xml_parser_create(); xml_set_object($parser, $this); xml_set_element_handler($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']); - + $result = true; if (is_resource($xmldata)) @@ -123,7 +122,7 @@ function _sanitize($xmldata, $isutf8 = null) 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; - $isutf8 = (!preg_match('/^<\?xml[^>]* encoding=/i', $xmldata) || preg_match('/^<\?xml[^>]* encoding=.UTF-8/i', $xmldata)); + $isutf8 = (!preg_match('/^<\?xml[^>]* encoding=/i', $xmldata) || preg_match('/^<\?xml[^>]* encoding=.utf-8/i', $xmldata)); } # Decode illegal entities but protect semantically important ones |