SHARE

PHP have function ord to find ASCII value of character. But PHP don’t support a function to find this value of unicode character. Now, we provider some method:

<?php

/**
 * @author www.Tutorialspots.com
 * @copyright 2015
 */

function unicodeord($c) { 
    $t = mb_convert_encoding($c, 'UCS-2LE', 'UTF-8'); 
    return (ord($t{1}) << 8) + ord($t{0}); 
} 

function unicodeord2($c)
{
    $ord0 = ord($c{0}); if ($ord0>=0 && $ord0<=127) return $ord0;
    $ord1 = ord($c{1}); if ($ord0>=192 && $ord0<=223) return ($ord0-192)*64 + ($ord1-128);
    $ord2 = ord($c{2}); if ($ord0>=224 && $ord0<=239) return ($ord0-224)*4096 + ($ord1-128)*64 + ($ord2-128);
    $ord3 = ord($c{3}); if ($ord0>=240 && $ord0<=247) return ($ord0-240)*262144 + ($ord1-128)*4096 + ($ord2-128)*64 + ($ord3-128);
    return false;
}

function unicodeord3($u) { 
    $k = mb_convert_encoding($u, 'UCS-2LE', 'UTF-8'); 
    $k1 = ord(substr($k, 0, 1)); 
    $k2 = ord(substr($k, 1, 1)); 
    return $k2 * 256 + $k1; 
} 

function unicodeord4($string, &$offset=0) {
    $code = ord(substr($string, $offset,1));
    if ($code >= 128) {        //otherwise 0xxxxxxx
        if ($code < 224) $bytesnumber = 2;                //110xxxxx
        else if ($code < 240) $bytesnumber = 3;        //1110xxxx
        else if ($code < 248) $bytesnumber = 4;    //11110xxx
        $codetemp = $code - 192 - ($bytesnumber > 2 ? 32 : 0) - ($bytesnumber > 3 ? 16 : 0);
        for ($i = 2; $i <= $bytesnumber; $i++) {
            $offset ++;
            $code2 = ord(substr($string, $offset, 1)) - 128;        //10xxxxxx
            $codetemp = $codetemp*64 + $code2;
        }
        $code = $codetemp;
    }
    $offset += 1;
    if ($offset >= strlen($string)) $offset = -1;
    return $code;
}

function unicodeord5($c)
{
    $ud = 0;
	if (ord($c{0})>=0 && ord($c{0})<=127) $ud = ord($c{0});
	if (ord($c{0})>=192 && ord($c{0})<=223) $ud = (ord($c{0})-192)*64 + (ord($c{1})-128);
	if (ord($c{0})>=224 && ord($c{0})<=239) $ud = (ord($c{0})-224)*4096 + (ord($c{1})-128)*64 + (ord($c{2})-128);
	if (ord($c{0})>=240 && ord($c{0})<=247) $ud = (ord($c{0})-240)*262144 + (ord($c{1})-128)*4096 + (ord($c{2})-128)*64 + (ord($c{3})-128);
	if (ord($c{0})>=248 && ord($c{0})<=251) $ud = (ord($c{0})-248)*16777216 + (ord($c{1})-128)*262144 + (ord($c{2})-128)*4096 + (ord($c{3})-128)*64 + (ord($c{4})-128);
	if (ord($c{0})>=252 && ord($c{0})<=253) $ud = (ord($c{0})-252)*1073741824 + (ord($c{1})-128)*16777216 + (ord($c{2})-128)*262144 + (ord($c{3})-128)*4096 + (ord($c{4})-128)*64 + (ord($c{5})-128);
	//error
	if (ord($c{0})>=254 && ord($c{0})<=255)	$ud = false;
    return $ud;
}

Examples:

echo unicodeord("♥"); //9829
echo "<br />";
echo unicodeord2("❤"); //10084
echo "<br />";
echo unicodeord3("❥"); //10085
echo "<br />";
echo unicodeord4("❦"); //10086
echo "<br />";
echo unicodeord5("❧"); //10087

NO COMMENTS