php实现中文字符截取防乱码方法汇总

/** 
 * 支持中文字符串截取 
 */ 
function msubstr($str, $start=0, $length, $charset="utf-8", $suffix=true){ 
  switch($charset){ 
    case 'utf-8':$char_len=3;break; 
    case 'UTF8':$char_len=3;break; 
    default:$char_len=2; 
  } 
  //小于指定长度，直接返回 
  if(strlen($str)<=($length*$char_len)){   
    return $str; 
  } 
  if(function_exists("mb_substr")){  
    $slice= mb_substr($str, $start, $length, $charset); 
  }else if(function_exists('iconv_substr')){ 
    $slice=iconv_substr($str,$start,$length,$charset); 
  }else{ 
    $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; 
} 

string mb_substr ( string $str , int $start [, int $length [, string $encoding ]] ) 
<?php 
 function substr_unicode($str, $s, $l = null) { 
   return join("", array_slice( 
     preg_split("//u", $str, -1, PREG_SPLIT_NO_EMPTY), $s, $l)); 
 } 
 
$str = "Büyük"; 
 $s = 0; // start from "0" (nth) char 
 $l = 3; // get "3" chars 
 echo substr($str, $s, $l) ."\n";  
 echo mb_substr($str, $s, $l) ."\n"; 
 echo substr_unicode($str, $s, $l); 
 ?>