PHP 中英文截取无乱码

在学习MySql 字符集时，解决了PHP中英文截取无乱码的问题。这个方法的核心在于判断取多少个字节上。

<?php 
//PHP中英文截取无乱码
header("Content_type=text/php;charset=UTF-8");
$str = "浙江zju大学";
//关键在于判断往后截多少个字节上，这是这个函数的核心
//此函数是用客串来判断的，效率不高
//位运算效果会更好
//110x xxxx && 1110 0000 -> 1100 0000
//1110 xxxx && 1111 0000 -> 1110 0000
//位运算时不受英文字符最高位为0的影响，只是在转成字符串才受到影响
function utf8sub($str,$len){
	if($len<0){
		return "";
	}
	$res = "";
	$offset = 0;
	$chars = 0;
	$count = 0;
	$length = strlen($str);//待截取字符串的字节数
	while($chars<$len && $offset<$length){
		$high = decbin(ord(substr($str,$offset,1)));//先截取客串的一个字节，substr按字节进行截取
		//重要突破，已经能够判断高位字节
		if(strlen($high)<8){//英文字符ascii编码长度为7，通过长度小于8来判断
			$count = 1;
			// echo "hello,I am in","<br>";
		}elseif (substr($high,0,3) == "110") {
			$count = 2;	//取两个字节的长度
		}elseif (substr($high,0,4) == "1110") {
			$count = 3;	//取三个字节的长度
		}elseif (substr($high,0,5) == "11110") {
			$count = 4;

		}elseif (substr($high,0,6) == "111110") {
			$count = 5;
		}elseif(substr($high,0,7)=="1111110"){
			$count = 6;
		}
		$res .= substr($str,$offset,$count);
		$chars +=1;
		$offset += $count;
	}

	return $res;
}
echo utf8sub($str,5),"<br>";
echo utf8sub($str,10),"<br>";

?>