php的汉字转换: Unicode(UTF8)->GBK

类别:编程语言 点击:0 评论:0 推荐:

秋水无恨 GBK Unicode UTF8 汉字 转换

php的汉字转换一直是比较麻烦的事

该类内置了四个过滤"&#[dec];","&#x[hex];","%u[hex]","utf8转换"
方便用户的使用,同时也可自定义过滤进行自己喜欢的操作


qswhU.php 从这里下载
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;
 }
 
 


使用范例

$qswh=new qswhU("qswhU.php");//如果文件名是qswhU.php,可省参数
echo "<xmp>不带参数(默认过滤为:&#[num];):";
echo "\n".$qswh->decode("&#x4E2D;&#x6587;&#x41;&#x62;&#x63;");
echo "\n".$qswh->decode("&#20013;&#25991;&#65;&#98;&#99;");
echo "\n调用内置过滤(UTF转码):".$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调用内置过滤unescape(%u[num]):".$qswh->decode("%u4E2D%u6587Abc",2);
echo "\n自定义过滤([x+num]):".$qswh->decode("[x4E2D][x6587][x41][x62][x63]","/\[(\w+)\]/");

效果如下:
不带参数(默认过滤为:&#[num];):
中文Abc
中文Abc
调用内置过滤(UTF转码):中文 !"#$%&'()*+,/:;<=>?@[]^`{|}~%Abc
调用内置过滤unescape(%u[num]):中文Abc
自定义过滤([x+num]):中文Abc


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。

本文地址:http://com.8s8s.com/it/it29549.htm