php的漢字轉換： Unicode(UTF8)->GBK

漢字|轉換

秋水無恨 GBK Unicode UTF8 漢字 轉換

php的漢字轉換一直是比較麻煩的事

該類內建了四個過濾"&#[dec];","&#x[hex];","%u[hex]","utf8轉換"
方便使用者的使用，同時也可自訂過濾進行自己喜歡的操作

qswhU.php 從這裡下載
http://www.blueidea.com/user/qswh/qswhU.zip

class qswhU{
 var $qswhData;
 function qswhU($filename="qswhU.php"){
  $this->qswhData=file($filename);
 }
 
 function decode($str,$pattern=0){
  $arr=array("/&#(\w+);/iU","/((%\w\w)+)/i","/%u(\w{4,5})/iU");
  if(is_integer($pattern)){
    if($pattern>=count($arr))die("Invalid Function");
    $pattern=$arr[$pattern];
  }
  return preg_replace_callback($pattern,array($this,"u2gb"),$str);
 }
 
 function u2gb($arr){
  /******(qiushuiwuhen 2002-8-15)******/
  $ret="";$str=$arr[1];
  if(preg_match_all("/%\w{2}/",$str,$matches)){
   for($i=0;$i<count($matches[0]);$i++){
    $chr1=hexdec(substr($matches[0][$i],1));
    $arr=array("f0","e0","c0","0");
    for($j=0;$j<count($arr);$j++)if($chr1>hexdec($arr[$j]))break;
    $chr=hexdec(substr($matches[0][$i],1))-hexdec($arr[$j]);
    while(++$j<count($arr))$chr=$chr*0x40+(hexdec(substr($matches[0][++$i],1))-0x80);
    $str=dechex($chr);
    if(strlen($str)==4){
     $p=hexdec(substr($str,0,2))-0x4d;
     $q=hexdec(substr($str,2))*4;
     $ret.=chr(hexdec(substr($this->qswhData[$p],$q,2)));
     $ret.=chr(hexdec(substr($this->qswhData[$p],$q+2,2)));
    }else
     $ret.=chr(hexdec($str));
   }
  }
  else{
   if(strtolower($str[0])=="x")
    $str=substr($str,1);
   else
    if(strlen($str)!=4)$str=dechex($str);
   
   if(strlen($str)==4){
    $p=hexdec(substr($str,0,2))-0x4d;
    $q=hexdec(substr($str,2))*4;
    $ret.=chr(hexdec(substr($this->qswhData[$p],$q,2)));
    $ret.=chr(hexdec(substr($this->qswhData[$p],$q+2,2)));
   }else
    $ret.=chr(hexdec($str));
  }
  return $ret;
 }
 
 
}

使用範例

$qswh=new qswhU("qswhU.php");//如果檔案名稱是qswhU.php,可省參數
echo "<xmp>不帶參數(預設過濾為：&#[num];):";
echo "\n".$qswh->decode("中文Abc");
echo "\n".$qswh->decode("中文Abc");
echo "\n調用內建過濾(UTF轉碼):".$qswh->decode("%E4%B8%AD%E6%96%87%20!%22%23%24%25%26'()*%2B%2C%2F%3A%3B%3C%3D%3E%3F%40%5B%5D%5E%60%7B%7C%7D~%25Abc",1);
echo "\n調用內建過濾unescape(%u[num]):".$qswh->decode("%u4E2D%u6587Abc",2);
echo "\n自訂過濾([x+num]):".$qswh->decode("[x4E2D][x6587][x41][x62][x63]","/\[(\w+)\]/");

效果如下：
不帶參數(預設過濾為：&#[num];):
中文Abc
中文Abc
調用內建過濾(UTF轉碼):中文 !"#$%&'()*+,/:;<=>?@[]^`{|}~%Abc
調用內建過濾unescape(%u[num]):中文Abc
自訂過濾([x+num]):中文Abc