日期:2014-05-17  浏览次数:20488 次

php 中英字符串截取,支持utf8 和gbk

?

今天在遇到了一个中英字符串截取的问题,在gbk里中文里每个字占两字节,如果全是中文的话,用substr()函数就可以实现了,但中英都有的话就麻烦了,在以前收藏的代码里找到了一个不错的函数,很好的实现了截取的功能

?

function get_word($string, $length, $dot = '..',$charset='gbk') {
    
    if(strlen($string) <= $length) {
        return $string;
    }

    $string = str_replace(array(' ',' ', '&', '"', '<', '>'), array('','','&', '"', '<', '>'), $string);

    $strcut = '';
    if(strtolower($charset) == 'utf-8') {

        $n = $tn = $noc = 0;
        while($n < strlen($string)) {

            $t = ord($string[$n]);
            if($t == 9 || $t == 10 || (32 <= $t && $t <= 126)) {
                $tn = 1; $n++; $noc++;
            } elseif(194 <= $t && $t <= 223) {
                $tn = 2; $n += 2; $noc += 2;
            } elseif(224 <= $t && $t < 239) {
                $tn = 3; $n += 3; $noc += 2;
            } elseif(240 <= $t && $t <= 247) {
                $tn = 4; $n += 4; $noc += 2;
            } elseif(248 <= $t && $t <= 251) {
                $tn = 5; $n += 5; $noc += 2;
            } elseif($t == 252 || $t == 253) {
                $tn = 6; $n += 6; $noc += 2;
            } else {
                $n++;
            }

            if($noc >= $length) {
                break;
            }

        }
        if($noc > $length) {
            $n -= $tn;
        }

        $strcut = substr($string, 0, $n);

    } else {
        for($i = 0; $i < $length; $i++) {
            $strcut .= ord($string[$i]) > 127 ? $string[$i].$string[++$i] : $string[$i];
        }
    }

    
    return $strcut.$dot;
}
?