PHP utf-8中文截取無亂碼(字符串判斷版本)

/*E4 B8 AD E5 9B BD   中國
1110 0100    10111000   10101101
1110 0101    1001101110111101

61  a
0011 1101


0xxx xxxx ,1個字節
110xx xxxx , 2個字節
1110 xxxx, 3
1111 0xxxx 4...
*/<pre name="code" class="php">$str = '中華人aaa民共b和國,c萬歲';

function utf8sub($str,$len){
	if($len <=0) return '';
	$length = strlen($str);
	$offset=0;
	$chars=0;
	$res='';
	while($chars<$len && $offset<$length){
		$heigh = decbin(ord(substr($str, $offset,1)));
		echo $heigh ,'</br>';
		if(strlen($heigh)<8){
			$count=1;
		}else if(substr($heigh,0,3) == '110'){
			$count=2;
		}else if(substr($heigh,0,4) == '1110'){
			$count=3;
		}else if(substr($heigh,0,5) == '11110'){
			$count=4;
		}else if(substr($heigh,0,6) == '111110'){
			$count=5;
		}else if(substr($heigh,0,7) == '1111110'){
			$count=6;
		}
		$res .= substr($str, $offset,$count);
		$chars += 1;
		$offset += $count;
	}
	return $res;
}

echo utf8sub($str,10);




發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章