Summery Summery
Detect XML encoding, as per XML 1.0 Appendix F.1
Syntax Syntax
Parameters Parameters
- $data
-
(Required) XML data
- $registry
-
(Required) Class registry
Return Return
(array) Possible encodings
Source Source
File: wp-includes/SimplePie/Misc.php
}
else
{
$return[urldecode($section)][] = null;
}
}
return $return;
}
/**
* Detect XML encoding, as per XML 1.0 Appendix F.1
*
* @todo Add support for EBCDIC
* @param string $data XML data
* @param SimplePie_Registry $registry Class registry
* @return array Possible encodings
*/
public static function xml_encoding($data, $registry)
{
// UTF-32 Big Endian BOM
if (substr($data, 0, 4) === "\x00\x00\xFE\xFF")
{
$encoding[] = 'UTF-32BE';
}
// UTF-32 Little Endian BOM
elseif (substr($data, 0, 4) === "\xFF\xFE\x00\x00")
{
$encoding[] = 'UTF-32LE';
}
// UTF-16 Big Endian BOM
elseif (substr($data, 0, 2) === "\xFE\xFF")
{
$encoding[] = 'UTF-16BE';
}
// UTF-16 Little Endian BOM
elseif (substr($data, 0, 2) === "\xFF\xFE")
{
$encoding[] = 'UTF-16LE';
}
// UTF-8 BOM
elseif (substr($data, 0, 3) === "\xEF\xBB\xBF")
{
$encoding[] = 'UTF-8';
}
// UTF-32 Big Endian Without BOM
elseif (substr($data, 0, 20) === "\x00\x00\x00\x3C\x00\x00\x00\x3F\x00\x00\x00\x78\x00\x00\x00\x6D\x00\x00\x00\x6C")
{
if ($pos = strpos($data, "\x00\x00\x00\x3F\x00\x00\x00\x3E"))
{
$parser = $registry->create('XML_Declaration_Parser', array(SimplePie_Misc::change_encoding(substr($data, 20, $pos - 20), 'UTF-32BE', 'UTF-8')));
if ($parser->parse())
{
$encoding[] = $parser->encoding;
}
}
$encoding[] = 'UTF-32BE';
}
// UTF-32 Little Endian Without BOM
elseif (substr($data, 0, 20) === "\x3C\x00\x00\x00\x3F\x00\x00\x00\x78\x00\x00\x00\x6D\x00\x00\x00\x6C\x00\x00\x00")
{
if ($pos = strpos($data, "\x3F\x00\x00\x00\x3E\x00\x00\x00"))
{
$parser = $registry->create('XML_Declaration_Parser', array(SimplePie_Misc::change_encoding(substr($data, 20, $pos - 20), 'UTF-32LE', 'UTF-8')));
if ($parser->parse())
{
$encoding[] = $parser->encoding;
}
}
$encoding[] = 'UTF-32LE';
}
// UTF-16 Big Endian Without BOM
elseif (substr($data, 0, 10) === "\x00\x3C\x00\x3F\x00\x78\x00\x6D\x00\x6C")
{
if ($pos = strpos($data, "\x00\x3F\x00\x3E"))
{
$parser = $registry->create('XML_Declaration_Parser', array(SimplePie_Misc::change_encoding(substr($data, 20, $pos - 10), 'UTF-16BE', 'UTF-8')));
if ($parser->parse())
{
$encoding[] = $parser->encoding;
}
}
$encoding[] = 'UTF-16BE';
}
// UTF-16 Little Endian Without BOM
elseif (substr($data, 0, 10) === "\x3C\x00\x3F\x00\x78\x00\x6D\x00\x6C\x00")
{
if ($pos = strpos($data, "\x3F\x00\x3E\x00"))
{
$parser = $registry->create('XML_Declaration_Parser', array(SimplePie_Misc::change_encoding(substr($data, 20, $pos - 10), 'UTF-16LE', 'UTF-8')));
if ($parser->parse())
{
$encoding[] = $parser->encoding;
}
}
$encoding[] = 'UTF-16LE';
}
// US-ASCII (or superset)
elseif (substr($data, 0, 5) === "\x3C\x3F\x78\x6D\x6C")