php的汉字转换： GBK->Unicode(UTF8)

php的汉字转换一直是比较麻烦的事

该类内置了四个函数"htmlHex","htmlDec","escape","u2utf8"
方便用户的使用，同时也可自定义函数进行自己喜欢的操作

qswhGBK.php 从这里下载
http://www.blueidea.com/user/qswh/qswhGBK.zip

<?
class qswhGBK{
 var $qswhData;
 function qswhGBK($filename="qswhGBK.php"){
  $this->qswhData=file($filename);
 }
 function gb2u($gb,$callback=""){
  /******(qiushuiwuhen 2002-8-15)******/
  $ret="";
  for($i=0;$i<strlen($gb);$i++){
   if(($p=ord(substr($gb,$i,1)))>127){
    
    $q=ord(substr($gb,++$i,1));
    $q=($q-($q>128?65:64))*4;
    $q=substr($this->qswhData[$p-128],$q,4);
   }
   else
    $q=dechex($p);
   if(empty($callback))
    $ret.=$q;
   else {
    $arr=array("htmlHex","htmlDec","escape","u2utf8");
    if(is_integer($callback)){
     if($callback>count($arr))die("Invalid Function");
     $ret.=$this->$arr[$callback-1]($q);
    }else
     $ret.=$callback($q);
   }
  }
  return $ret;
 }
 
 function htmlHex($str){
  return "&#x".$str.";";
 }
 
 function htmlDec($str){
  return "&#".hexdec($str).";";
 }
 
 function escape($str){
  return hexdec($str)<256?chr(hexdec($str)):"%u".$str;
 }
 
 function u2utf8($str){
  /******(qiushuiwuhen 2002-8-15)******/
  $sp="!'()*-.0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz~";
  $dec=hexdec($str);
  $bin=decbin($dec);
  $len=strlen($bin);
  $arr=array("c0","e0","f0");
  if($dec>0x7f){
   $ret="";
   for($i=$len,$j=-1;$i>=0;$i-=6,$j++){
    if($i>6)
     $ret="%".dechex(0x80+bindec(substr($bin,$i-6,6))).$ret;
    else
     $ret="%".dechex(hexdec($arr[$j])+bindec(substr($bin,0,6-$i))).$ret;
   }
  }else{
   if(strpos($sp,chr($dec)))
    $ret=chr($dec);
   else
    $ret="%".strtolower($str);
  }
  return $ret;
 }
}

使用范例
$words="中文Abc";
function ex($str){return "[".$str."]";}

$qswh=new qswhGBK("qswhGBK.php");//如果文件名是qswhGBK.php,可省参数

echo("<xmp>不带参数:".$qswh->gb2u($words));
echo("/n调用内置函数htmlHex:".$qswh->gb2u($words,1));
echo("/n调用内置函数htmlDec:".$qswh->gb2u($words,2));
echo("/n调用内置函数escape:".$qswh->gb2u($words,3));
echo("/n调用内置函数u2utf8:".$qswh->gb2u($words,4));
echo("/n调用自定义函数:".$qswh->gb2u($words,ex));

效果如下：

  不带参数:4E2D6587416263 调用内置函数htmlHex:中文Abc 调用内置函数htmlDec:中文Abc 调用内置函数escape:%u4E2D%u6587Abc 调用内置函数u2utf8:%e4%b8%ad%e6%96%87Abc 调用自定义函数:[4E2D][6587][41][62][63] 

ps.该文章现仅限在csdn文档中心，如要转载，请和作者联系，否则后果自负。