有不少php初学者截取字符都会使用substr()函数或者mb_substr()函数来截取了,第一个中文肯定乱码了,第二个性能不好,下面我总结了几个自定的中文字串截取无乱码实例.
例1代码如下:
- function msubstr($str, $start=0, $length, $charset="utf-8", $suffix=true)
- {
- if(function_exists("mb_substr"))
- return mb_substr($str, $start, $length, $charset);
- elseif(function_exists('iconv_substr')) {
- return iconv_substr($str,$start,$length,$charset);
- }
- $re['utf-8'] = "/[x01-x7f]|[xc2-xdf][x80-xbf]|[xe0-xef][x80-xbf]{2}|[xf0-xff][x80-xbf]{3}/";
- $re['gb2312'] = "/[x01-x7f]|[xb0-xf7][xa0-xfe]/";
- $re['gbk'] = "/[x01-x7f]|[x81-xfe][x40-xfe]/";
- $re['big5'] = "/[x01-x7f]|[x81-xfe]([x40-x7e]|xa1-xfe])/";
- preg_match_all($re[$charset], $str, $match);
- $slice = join("",array_slice($match[0], $start, $length));
- if($suffix) return $slice."…";
- return $slice;
- }
例2代码如下:
- <?php
-
- function substr2($string, $start, $length)
- {
- $len = strlen($string);
- if($len > $length)
- {
- $str = '';
- $len1 = $start + $length;
- for($i=$start; $i<$len1; $i++)
- {
- if(ord(substr($string, $i, 2)) > 0xa0)
- {
- $str.=substr($string, $i, 2);
- $i++;
- }
- else
- {
- $str.=substr($string, $i, 1);
- }
- }
- return $str.'...';
- }
- else
- {
- return $string;
- }
- }
-
- ?>
例3代码如下:
- <?php
- function chinesesubstr($str, $start, $len){
- $strlen = $start + $len;
- for($i=0; $i<$strlen; $i++){
- if(ord(substr($str, $i, 1)) > 0xa0){
- $tmpstr .= substr($str, $i, 2);
- $i++;
- }else{
- $tmpstr .= substr($str, $i, 1);
- }
- }
- return $tmpstr;
- }
- $str = "waiting for you 等wait你back";
- echo chinesesubstr($str, 0, 19)
- ?>
|