note 45561 modified in function.utf8-decode by aidan

big thanks to wielspm and mittag for the function to convert wide utf to html. I have altered your function to output decimal html entities which i hear are more widely supported. Also I've optimized it, it is now twice as fast. <?php 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 * 100 + $c2) . ";"; // this is the fastest string concatenation $last = $i+1; } } return $ret . substr($str, $last, $i); // append the last batch of regular characters } ?> --was-- big thanks to wielspm and mittag for the function to convert wide utf to html. I have altered your function to output decimal html entities which i hear are more widely supported. Also I've optimized it, it is now twice as fast. function utf2html ($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 * 100 + $c2) . ";"; // this is the fastest string concatenation $last = $i+1; } } return $ret . substr($str, $last, $i); // append the last batch of regular characters } http://php.net/manual/en/function.utf8-decode.php