PHP detect UTF8 && arabic encoding

utf8_arabic.php

<?php
function detect_utf_encoding($data) {

	$UTF32_BIG_ENDIAN_BOM    = chr(0x00) . chr(0x00) . chr(0xFE) . chr(0xFF);
	$UTF32_LITTLE_ENDIAN_BOM = chr(0xFF) . chr(0xFE) . chr(0x00) . chr(0x00);
	$UTF16_BIG_ENDIAN_BOM    = chr(0xFE) . chr(0xFF);
	$UTF16_LITTLE_ENDIAN_BOM = chr(0xFF) . chr(0xFE);
	$UTF8_BOM                = chr(0xEF) . chr(0xBB) . chr(0xBF);

    $first2 = substr($data, 0, 2);
    $first3 = substr($data, 0, 3);
    $first4 = substr($data, 0, 3);
   
    if ($first3 == $UTF8_BOM){
    	return 'UTF-8';
    }else if($first4 == $UTF32_BIG_ENDIAN_BOM){
    	return 'UTF-32BE';
    }else if($first4 == $UTF32_LITTLE_ENDIAN_BOM){
    	return 'UTF-32LE';
    }else if($first2 == $UTF16_BIG_ENDIAN_BOM){
    	return 'UTF-16BE';
    }else if($first2 == $UTF16_LITTLE_ENDIAN_BOM){
    	return 'UTF-16LE';
    }else{
    	return false;
    }
};



function is_arabic($str) {
    if(mb_detect_encoding($str) !== 'UTF-8') {
        $str = mb_convert_encoding($str,mb_detect_encoding($str),'UTF-8');
    }

    /*
    $str = str_split($str); <- this function is not mb safe, it splits by bytes, not characters. we cannot use it
    $str = preg_split('//u',$str); <- this function woulrd probably work fine but there was a bug reported in some php version so it pslits by bytes and not chars as well
    */
    preg_match_all('/.|\n/u', $str, $matches);
    $chars = $matches[0];
    $arabic_count = 0;
    $latin_count = 0;
    $total_count = 0;
    foreach($chars as $char) {
        //$pos = ord($char); we cant use that, its not binary safe 
        $pos = uniord($char);
        if($pos >= 1536 && $pos <= 1791) {
            $arabic_count++;
        } else if($pos > 123 && $pos < 123) {
            $latin_count++;
        }
        $total_count++;
    }
    if(($arabic_count/$total_count) > 0.6) {
        // 60% arabic chars, its probably arabic
        return true;
    }
    return false;
}
?>