PHP截取字符串长度（中英文混合字符串）

<?
echo substr("abcdef", 1, 3);  // 返回 "bcd"
echo substr("abcdef", -2);    // 返回 "ef"
echo substr("abcdef", -3, 1); // 返回 "d"
echo substr("abcdef", 1, -1); // 返回 "bcde"
?>

< ?php 
 //截取中文字符串
 function mysubstr($str, $start, $len) {
     $tmpstr = "";
     $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;
 }
 ?>

< ?php
 //截取utf8字符串
 function utf8Substr($str, $from, $len)
 {
     return preg_replace('#^(?:[x00-x7F]|[xC0-xFF][x80-xBF]+){0,'.$from.'}'.
                        '((?:[x00-x7F]|[xC0-xFF][x80-xBF]+){0,'.$len.'}).*#s',
                        '$1',$str);
 }
 ?>

   function utf8_substr( $str , $start , $length=null ){
       
        // 先正常截取一遍.
        $res = substr( $str , $start , $length );
        $strlen = strlen( $str );
       
        /* 接着判断头尾各6字节是否完整(不残缺) */

        // 如果参数start是正数
        if ( $start >= 0 ){
            // 往前再截取大约6字节
            $next_start = $start + $length; // 初始位置
            $next_len = $next_start + 6 <= $strlen ? 6 : $strlen - $next_start;
            $next_segm = substr( $str , $next_start , $next_len );

            // 如果第1字节就不是 完整字符的首字节, 再往后截取大约6字节
            $prev_start = $start - 6 > 0 ? $start - 6 : 0;
            $prev_segm = substr( $str , $prev_start , $start - $prev_start );
        }
        // start是负数
        else{
            // 往前再截取大约6字节
            $next_start = $strlen + $start + $length; // 初始位置
            $next_len = $next_start + 6 <= $strlen ? 6 : $strlen - $next_start;
            $next_segm = substr( $str , $next_start , $next_len );
           
            // 如果第1字节就不是 完整字符的首字节, 再往后截取大约6字节.
            $start = $strlen + $start;
            $prev_start = $start - 6 > 0 ? $start - 6 : 0;
            $prev_segm = substr( $str , $prev_start , $start - $prev_start );
        }

        // 判断前6字节是否符合utf8规则
        if ( preg_match( '@^([x80-xBF]{0,5})[xC0-xFD]?@' , $next_segm , $bytes ) ){
            if ( !empty( $bytes[1] ) ){
                $bytes = $bytes[1];
                $res .= $bytes;
            }
        }

        // 判断后6字节是否符合utf8规则
        $ord0 = ord( $res[0] );
        if ( 128 <= $ord0 && 191 >= $ord0 ){
            // 往后截取 , 并加在res的前面.
            if ( preg_match( '@[xC0-xFD][x80-xBF]{0,5}$@' , $prev_segm , $bytes ) ){
                if ( !empty( $bytes[0] ) ){
                    $bytes = $bytes[0];
                    $res = $bytes . $res;
                }
            }
        }

        return $res;
    }

function MooCutstr($string, $length, $dot = ' ...') {
 global $charset;

 if(strlen($string) <= $length) {
  return $string;
 }
 $string = str_replace(array('&amp;', '&quot;', '&lt;', '&gt;'), 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];
  }
 }
 //$strcut = str_replace(array('&', '"', '<', '>'), array('&amp;', '&quot;', '&lt;', '&gt;'), $strcut);

 return $strcut.$dot;
}