Last active
October 8, 2015 16:49
-
-
Save lifo101/3361046 to your computer and use it in GitHub Desktop.
htmlentities() replacement that converts all entities in a string into character entities (suitable for XML documents)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
/** | |
* Works like htmlentities() but only encodes entities as numeric codes | |
* instead of names (for use in XML). | |
*/ | |
function xmlentities($str, $encoding = 'UTF-8', $asList = false) | |
{ | |
$list = array(); | |
$ent = ''; | |
$chars = preg_split('//u', $str, -1, PREG_SPLIT_NO_EMPTY); | |
foreach ($chars as $chr) { | |
// FYI: 'UCS-4BE' encodes all characters as a 4 byte 32bit int | |
$str = mb_convert_encoding($chr, 'UCS-4BE', $encoding); | |
$len = mb_strlen($str, 'UCS-4BE'); | |
for ($i = 0; $i < $len; $i++){ | |
$s = mb_substr($str, $i, 1, 'UCS-4BE'); | |
list(, $val) = unpack('N', $s); | |
if ($val < 128) { | |
$list[] = chr($val); | |
$ent .= htmlspecialchars(chr($val), ENT_QUOTES, $encoding); | |
} else { | |
$list[] = $val; | |
$ent .= '&#' . $val . ';'; | |
} | |
} | |
} | |
return $asList ? $list : $ent; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment