Javascript url 解码算法(utf-8) by shawl.qiu

最新推荐文章于 2022-03-10 12:10:46 发布

btbtd

最新推荐文章于 2022-03-10 12:10:46 发布

阅读量3.8k

点赞数

文章标签： javascript 算法 url string function join

本文链接：https://blog.csdn.net/btbtd/article/details/1799280

版权

Me Script 同时被 3 个专栏收录

88 篇文章 0 订阅

订阅专栏

Me Script function library

34 篇文章 0 订阅

订阅专栏

MS JScript

31 篇文章 0 订阅

订阅专栏

Javascript url 解码算法(utf-8) by shawl.qiu

注:
上一篇相关文章:
javascript utf-8 url 编码之纯算法解码 by shawl.qiu 2007-9-24
http://blog.csdn.net/btbtd/archive/2007/09/24/1797805.aspx

由于理解不全, 内容作废.

说明:
写这个大部分原因是想了解编码集, 至于这个东西的用处嘛...基本没用.

现在明白, UTF-8 中的编码分为四个分区,
一, 二, 三分区是常用区, 第四部分是极少用的部分也是待扩展的部分...
解码 URL 编码时, 得先识别分区

第一区是一字节, 对应编码是 %xx
第二分区是二字节, 对应编码是 %xx%xx
....

以此类推.
至于分区边界, 请查看相关 RFC 档...

值得一提的是, 我在测试时使用第四区的字符, 但是UTF-8 是使用三字节编码方式.

shawl.qiu
2007-09-25
http://blog.csdn.net/btbtd

下载:
http://files.myopera.com/btbtd/javascript/function/fDecodingPEUtf8.7z

演示:
http://files.myopera.com/btbtd/javascript/function/fDecodingPEUtf8(Fix).htm

内容:

<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<title>shawl.qiu template</title>
<style type="text/css">
/* <![CDATA[ */

/* ]]> */
</style>
<script type="text/javascript">
/*<![CDATA[*/
if (navigator.appName=="Microsoft Internet Explorer")
{
  //最大化窗口
  self.moveTo(-5,-5)
  self.resizeTo(screen.availWidth +8,screen.availHeight+8)
  //这个脚本定义的宽度其实比原窗口还要大那么一点.
}
/*]]*/
</script>
</head>
<body>
<script type="text/javascript">
/*<![CDATA[*/
var IWrite = document;

  var str = fGeneratingBoundStr(65, 100);
  var pe = encodeURI(str);
  var d = fDecodingPEUtf8(pe);

  IWrite.write("<p/>str: "+str);
  IWrite.write("<p/> pe: "+pe);
  IWrite.write("<p/>  d: "+d);

  IWrite.write("<hr/>");

  //-----------------------------------------------

// PE = percent encoding
function fDecodingPEUtf8(sUtf8PE) // %xx[,%xx]
{ // shawl.qiu code, return string; Func: fGetPEUtf8, fGetPEUtf8Bound
  if(sUtf8PE.indexOf("%")===-1) return sUtf8PE;
  var iLBound = 0x7f;
  sUtf8PE = sUtf8PE.replace(//+/g, " ");

  for(var i=0, j=sUtf8PE.length; i<j; i++)
  {
   var iIndex = sUtf8PE.indexOf("%", i);
   if(iIndex===-1) break;
   i=iIndex+1;

   var sHex = sUtf8PE.slice(i, i+2);
   var iCode = parseInt(sHex, 16);
   var sPE = sUtf8PE.slice(i, i+2);
   var iBound = fGetPEUtf8Bound(sUtf8PE.slice(i, i+2));
   switch(iBound)
   {
    case 1:
     var sHexExt = sUtf8PE.slice(i, i+2);
     TempStr = String.fromCharCode(parseInt(sHexExt, 16));
     sUtf8PE = [sUtf8PE.slice(0, i-1), TempStr, sUtf8PE.slice(i+2)].join("");
     i-=1;
     break;

    case 2:
     var sHexExt = sUtf8PE.slice(i+2, i+5);
     if(/%../.test(sHexExt))
     {
      var TempStr = sUtf8PE.slice(i-1, i+5);
      TempStr = fGetPEUtf8(TempStr);
      sUtf8PE = [sUtf8PE.slice(0, i-1), TempStr, sUtf8PE.slice(i+5)].join("");
      i-=1;
     }
     break;

    case 3:
     var sHexExt = sUtf8PE.slice(i+2, i+8);
     if(//%../%/.test(sHexExt))
     {
      var TempStr = sUtf8PE.slice(i-1, i+8);
      TempStr = fGetPEUtf8(TempStr);
      sUtf8PE = [sUtf8PE.slice(0, i-1), TempStr, sUtf8PE.slice(i+8)].join("");
      i-=1;
     }
     break;
   }
  } // end for(var i=0, j=sUtf8PE.length; i<j; i++)

  return sUtf8PE;
} // end function fDecodingPEUtf8(sUtf8PE)

// PE = percent encoding
function fGetPEUtf8(sUtf8PE) // %xx[,%xx]
{ // shawl.qiu code, return string
  sUtf8PE = sUtf8PE.replace(/%/, "");
  //IWrite.write("<br/>sUtfPE: "+sUtf8PE);
  var Ar = sUtf8PE.split("%");
  for(var i=0, j=Ar.length; i<j; i++)
  {
   Ar[i] = parseInt(Ar[i], 16).toString(2);
   var iZeroIndex = Ar[i].indexOf("0");
   Ar[i] = Ar[i].slice(iZeroIndex+1);
  }
  var sBin = Ar.join("");
  var iCode = parseInt(sBin, 2);
  return String.fromCharCode(iCode);
} // end function fGetPEUtf8(sUtf8PE)

// PE = percent encoding
function fGetPEUtf8Bound(cUtf8PE) // %xx
{ // shawl.qiu code, return integer
  cUtf8PE = cUtf8PE.replace(/%/, "");
  var iCharCode = parseInt(cUtf8PE, 16);
  var iLBound = iUBound = 0;
  //00-7F
  iLBound = 0; iUBound = 0x7f;
  if(iCharCode>=iLBound&&iCharCode<=iUBound) return 1;
  //C2-DF
  iLBound = 0xC2; iUBound = 0xDF;
  if(iCharCode>=iLBound&&iCharCode<=iUBound) return 2;
  //E0-EF
  iLBound = 0xE0; iUBound = 0xEF;
  if(iCharCode>=iLBound&&iCharCode<=iUBound) return 3;
  //F0-F4
  iLBound = 0xF0; iUBound = 0xF4;
  if(iCharCode>=iLBound&&iCharCode<=iUBound) return 4;

  return 0;
} // end function fGetPEUtf8Bound(cUtf8PE)

function fGeneratingBoundStr(iPadBegin, iLen)
{
  if(!iPadBegin) iPadBegin = 0;
  if(!iLen) iLen = 10;
  var Ar = [];
  var iLBound = iUBound = 0;

  iLBound = 0+iPadBegin; iUBound = iLBound+iLen;
  for(;iLBound<iUBound; iLBound++ )
  {
   Ar.push(String.fromCharCode(iLBound));
  }

  iLBound = 0x000080+iPadBegin; iUBound = iLBound+iLen;
  //IWrite.write("<br/>iLBound: "+iLBound);
  for(;iLBound<iUBound; iLBound++ )
  {
   Ar.push(String.fromCharCode(iLBound));
  }

  iLBound = 0x000800+19000+iPadBegin; iUBound = iLBound+iLen;
  //IWrite.write("<br/>iLBound: "+iLBound);
  for(;iLBound<iUBound; iLBound++ )
  {
   Ar.push(String.fromCharCode(iLBound));
  }

  iLBound = 0x010000+iPadBegin; iUBound = iLBound+iLen;
  //IWrite.write("<br/>iLBound: "+iLBound);
  for(;iLBound<iUBound; iLBound++ )
  {
   Ar.push(String.fromCharCode(iLBound));
  }

  return Ar;
}
/*]]*/
</script>
</body>
</html>

原仓野智能马桶

btbtd

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
Javascript url 解码算法(utf-8) by shawl.qiu

Javascript url 解码算法(utf-8) by shawl.qiu注: 上一篇相关文章: javascript utf-8 url 编码之纯算法解码 by shawl.qiu 2007-9-24http://blog.csdn.net/btbtd/archive/2007/09/24/1797805.aspx由于理解不全, 内容作废. 说明:写这个大部分原因是想了解编码集...
复制链接

扫一扫