I noticed that the utf-8 to html functions below are only for 2 byte long codes. Well I wanted 3 byte support (sorry haven't done 4, 5 or 6). Also I noticed the concatination of the character codes did have the hex prefix 0x and so failed with the large 2 byte codes)
<?
public function utf2html (&$str) {
$ret = "";
$max = strlen($str);
$last = 0; // keeps the index of the last regular character
for ($i=0; $i<$max; $i++) {
$c = $str{$i};
$c1 = ord($c);
if ($c1>>5 == 6) { // 110x xxxx, 110 prefix for 2 bytes unicode
$ret .= substr($str, $last, $i-$last); // append all the regular characters we've passed
$c1 &= 31; // remove the 3 bit two bytes prefix
$c2 = ord($str{++$i}); // the next byte
$c2 &= 63; // remove the 2 bit trailing byte prefix
$c2 |= (($c1 & 3) << 6); // last 2 bits of c1 become first 2 of c2
$c1 >>= 2; // c1 shifts 2 to the right
$ret .= "&#" . ($c1 * 0x100 + $c2) . ";"; // this is the fastest string concatenation
$last = $i+1;
}
elseif ($c1>>4 == 14) { // 1110 xxxx, 110 prefix for 3 bytes unicode
$ret .= substr($str, $last, $i-$last); // append all the regular characters we've passed
$c2 = ord($str{++$i}); // the next byte
$c3 = ord($str{++$i}); // the third byte
$c1 &= 15; // remove the 4 bit three bytes prefix
$c2 &= 63; // remove the 2 bit trailing byte prefix
$c3 &= 63; // remove the 2 bit trailing byte prefix
$c3 |= (($c2 & 3) << 6); // last 2 bits of c2 become first 2 of c3
$c2 >>=2; //c2 shifts 2 to the right
$c2 |= (($c1 & 15) << 4); // last 4 bits of c1 become first 4 of c2
$c1 >>= 4; // c1 shifts 4 to the right
$ret .= '&#' . (($c1 * 0x10000) + ($c2 * 0x100) + $c3) . ';'; // this is the fastest string concatenation
$last = $i+1;
}
}
$str=$ret . substr($str, $last, $i); // append the last batch of regular characters
}
?>
