php无损截取包括html标签的字符串

	composer @Ta
	2018-09-13 00:08

---

/**
 * 字符串切割+过滤+转换
 *
 * 功能：截取字符串（支持中文）
 * 如果截取的字符串中不包含html标签，则正常截取
 * 如果字符串中包括img标签，则先进行过去标签，截取后，将标签位置放回,截取的字符串则会保留完整的html标签
 *
 * @param string $string
 * @param unknown $length
 * @param string $replace
 * @return string
 */
function cutTab($string, $length='15', $dot = '…') {
    $_lenth = mb_strlen($string, "utf-8");
    $text_str = preg_replace("/<img.*?>/si","",$string);
    $text_lenth = mb_strlen($text_str, "utf-8") - 1;
    if($text_lenth <= $length) {
        return stripcslashes($string);
    }
    if(strpos($string, '<img') === false){
        $res = mb_substr($string, 0, $length, 'UTF-8');
        return stripcslashes($res).$dot;
    }
    //计算标签位置
    $html_start = ceil(strpos($string, '<img') / 3);
    $html_end = ceil(strpos($string, '/>') / 3);
    if($length < $html_start) {
        $res = mb_substr($string, 0, $length, 'UTF-8');
        return stripcslashes($res).$dot;
    }
    if($length > $html_start) {
        $res_html = mb_substr($text_str, 0, $length-1, 'UTF-8');
        preg_match('/<img[^>]*>/',$string,$result_html);
        $before = mb_substr($res_html, 0, $html_start, 'UTF-8');
        $after = mb_substr($res_html, $html_start, mb_strlen($res_html, "utf-8"), 'UTF-8');
        $res = $before.$result_html[0].$after;
        return stripcslashes($res).$dot;
    }
}

本站所有文章均为wangyongdong原创，转载请注明出处来自 https://www.wangyd.com/post/64

阅:2664

发表于2018-09-13 00:08

#php源码