彻底解决页面文字编码乱码问题-巨人网络通讯

彻底解决页面文字编码乱码问题

本文提供一种方法，通过将字符串编码成Unicode格式，保证数据在展示和传输过程中万无一失。无论客户端浏览器如何改变编码，页面上的编码都不会乱码。
对于HTML/XML,采用 # + 十位Unicode码 + ; 的形式格式化字符。
对于JS,采用 \u + 4位Unicode码来格式化字符串.
示例采用C#编写，使用了中文、俄文、韩文、日文来展示。对于PHP,文章末尾将会提到。
首先，有一个String的扩展类。

复制代码代码如下:

 
using System.Text.RegularExpressions; 
namespace XXOO 
{ 
/// summary> 
/// 扩展方法，提供Html编码 和 脚本编码 
/// /summary> 
public static class StringExtension 
{ 
private static string GetHtmlEncodedStr(Match m) 
{ 
string x = m.ToString(); 
return string.Format("#{0};", (int)x[0]); 
} 
/// summary> 
/// 将字符串转换为HTML编码格式 
/// /summary> 
/// param name="text">字符串/param> 
/// returns>输出形如：中文丰厚警/returns> 
public static string HtmlEncode( this string text ) 
{ 
return Regex.Replace(text 
, "([^\\000-\\127]||\\\"|\\|\\>|')" 
, new MatchEvaluator(GetHtmlEncodedStr) 
, RegexOptions.ECMAScript | RegexOptions.Compiled 
); 
} 
private static string GetScriptEncodedStr(Match m) 
{ 
string x = m.ToString(); 
return "\\u" + string.Format("{0:X}", (int)x[0]).PadLeft( 4, '0'); 
} 
/// summary> 
/// 将字符串编码成Unicode格式 如：\uXXXX 
/// /summary> 
/// param name="text">字符串/param> 
/// returns>输出形如：\u4E2D\u6587\u4E30\u539A\u8B66\u65B9/returns> 
public static string ScriptEncode( this string text ) 
{ 
return Regex.Replace(text 
, "([^\\000-\\127]||\\\"|'|\\|\\>|\\n|\\r|\\t)" 
, new MatchEvaluator(GetScriptEncodedStr) 
, RegexOptions.ECMAScript | RegexOptions.Compiled 
); 
} 
} 
} 

它提供了2个方法，给测试页面使用。
测试页面(ASP.Net)

复制代码代码如下:

 
%@ Page Language="C#" AutoEventWireup="true" CodeBehind="WebForm1.aspx.cs" Inherits="WebApplication1.WebForm1" %> 
!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 runat="server"> 
title>/title> 
/head> 
body> 
form id="form1" runat="server"> 
pre runat="Server" id="pre">/pre> 
asp:PlaceHolder runat="Server" ID="placeHolder">/asp:PlaceHolder> 
/form> 
/body> 
/html> 

测试页面代码：

复制代码代码如下:

 
using XXOO; 
namespace WebApplication1 
{ 
public partial class WebForm1 : System.Web.UI.Page 
{ 
protected void Page_Load(object sender, EventArgs e) 
{ 
var str = @"中文丰厚警方过后发达看见发的话该快发动机后购房贷款好 
Китайское посольство в Ираке и Багдаде отделение 
이라크에서 중국 대사관과 알의 바그다드 지사 - 만수르 호텔 
イラクでの大使館やアルのバグダッド支局-マンスールホテル 
1234567890!@#$%^*()>""'\|}{][:; 
"; 
pre.InnerHtml = str.HtmlEncode(); 
HtmlGenericControl control = new HtmlGenericControl("script"); 
control.Attributes["language"] = "javascript"; 
control.Attributes["type"] = "text/javascript"; 
control.InnerHtml = string.Format("alert(\"{0}\");", str.ScriptEncode()); 
placeHolder.Controls.Add(control); 
} 
} 
} 

运行后得到的HTML:

复制代码代码如下:

 
!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>title> 
/title>/head> 
body> 
form name="form1" method="post" action="WebForm1.aspx" id="form1"> 
pre id="pre">#20013;#25991;#20016;#21402;#35686;#26041;#36807;#21518;#21457;#36798;#30475;#35265;#21457;#30340;#35805;#35813;#24555;#21457;#21160;#26426;#21518;#36141;#25151;#36151;#27454;#22909; 
#1050;#1080;#1090;#1072;#1081;#1089;#1082;#1086;#1077; #1087;#1086;#1089;#1086;#1083;#1100;#1089;#1090;#1074;#1086; #1074; #1048;#1088;#1072;#1082;#1077; #1080; #1041;#1072;#1075;#1076;#1072;#1076;#1077; #1086;#1090;#1076;#1077;#1083;#1077;#1085;#1080;#1077; 
#51060;#46972;#53356;#50640;#49436; #51473;#44397; #45824;#49324;#44288;#44284; #50508;#51032; #48148;#44536;#45796;#46300; #51648;#49324; - #47564;#49688;#47476; #54840;#53588; 
#12452;#12521;#12463;#12391;#12398;#22823;#20351;#39208;#12420;#12450;#12523;#12398;#12496;#12464;#12480;#12483;#12489;#25903;#23616;-#12510;#12531;#12473;#12540;#12523;#12507;#12486;#12523; 
1234567890!@#$%#94;#38;*()#60;#62;#34;#39;#92;#124;#125;#123;#93;#91;:; 
/pre> 
script language="javascript" type="text/javascript">!-- 
alert("\u4E2D\u6587\u4E30\u539A\u8B66\u65B9\u8FC7\u540E\u53D1\u8FBE\u770B\u89C1\u53D1\u7684\u8BDD\u8BE5\u5FEB\u53D1\u52A8\u673A\u540E\u8D2D\u623F\u8D37\u6B3E\u597D\u000D\u000A\u041A\u0438\u0442\u0430\u0439\u0441\u043A\u043E\u0435 \u043F\u043E\u0441\u043E\u043B\u044C\u0441\u0442\u0432\u043E \u0432 \u0418\u0440\u0430\u043A\u0435 \u0438 \u0411\u0430\u0433\u0434\u0430\u0434\u0435 \u043E\u0442\u0434\u0435\u043B\u0435\u043D\u0438\u0435 \u000D\u000A\uC774\uB77C\uD06C\uC5D0\uC11C \uC911\uAD6D \uB300\uC0AC\uAD00\uACFC \uC54C\uC758 \uBC14\uADF8\uB2E4\uB4DC \uC9C0\uC0AC - \uB9CC\uC218\uB974 \uD638\uD154\u000D\u000A\u30A4\u30E9\u30AF\u3067\u306E\u5927\u4F7F\u9928\u3084\u30A2\u30EB\u306E\u30D0\u30B0\u30C0\u30C3\u30C9\u652F\u5C40-\u30DE\u30F3\u30B9\u30FC\u30EB\u30DB\u30C6\u30EB\u000D\u000A1234567890!@#$%\u005E\u0026*()\u003C\u003E\u0022\u0027\u005C\u007C\u007D\u007B\u005D\u005B:;\u000D\u000A"); 
// -->/script> 
/form> 
/body> 
/html> 
!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>title> 
/title>/head> 
body> 
form name="form1" method="post" action="WebForm1.aspx" id="form1"> 
pre id="pre">#20013;#25991;#20016;#21402;#35686;#26041;#36807;#21518;#21457;#36798;#30475;#35265;#21457;#30340;#35805;#35813;#24555;#21457;#21160;#26426;#21518;#36141;#25151;#36151;#27454;#22909; 
#1050;#1080;#1090;#1072;#1081;#1089;#1082;#1086;#1077; #1087;#1086;#1089;#1086;#1083;#1100;#1089;#1090;#1074;#1086; #1074; #1048;#1088;#1072;#1082;#1077; #1080; #1041;#1072;#1075;#1076;#1072;#1076;#1077; #1086;#1090;#1076;#1077;#1083;#1077;#1085;#1080;#1077; 
#51060;#46972;#53356;#50640;#49436; #51473;#44397; #45824;#49324;#44288;#44284; #50508;#51032; #48148;#44536;#45796;#46300; #51648;#49324; - #47564;#49688;#47476; #54840;#53588; 
#12452;#12521;#12463;#12391;#12398;#22823;#20351;#39208;#12420;#12450;#12523;#12398;#12496;#12464;#12480;#12483;#12489;#25903;#23616;-#12510;#12531;#12473;#12540;#12523;#12507;#12486;#12523; 
1234567890!@#$%#94;#38;*()#60;#62;#34;#39;#92;#124;#125;#123;#93;#91;:; 
/pre> 
script language="javascript" type="text/javascript">!-- 
alert("\u4E2D\u6587\u4E30\u539A\u8B66\u65B9\u8FC7\u540E\u53D1\u8FBE\u770B\u89C1\u53D1\u7684\u8BDD\u8BE5\u5FEB\u53D1\u52A8\u673A\u540E\u8D2D\u623F\u8D37\u6B3E\u597D\u000D\u000A\u041A\u0438\u0442\u0430\u0439\u0441\u043A\u043E\u0435 \u043F\u043E\u0441\u043E\u043B\u044C\u0441\u0442\u0432\u043E \u0432 \u0418\u0440\u0430\u043A\u0435 \u0438 \u0411\u0430\u0433\u0434\u0430\u0434\u0435 \u043E\u0442\u0434\u0435\u043B\u0435\u043D\u0438\u0435 \u000D\u000A\uC774\uB77C\uD06C\uC5D0\uC11C \uC911\uAD6D \uB300\uC0AC\uAD00\uACFC \uC54C\uC758 \uBC14\uADF8\uB2E4\uB4DC \uC9C0\uC0AC - \uB9CC\uC218\uB974 \uD638\uD154\u000D\u000A\u30A4\u30E9\u30AF\u3067\u306E\u5927\u4F7F\u9928\u3084\u30A2\u30EB\u306E\u30D0\u30B0\u30C0\u30C3\u30C9\u652F\u5C40-\u30DE\u30F3\u30B9\u30FC\u30EB\u30DB\u30C6\u30EB\u000D\u000A1234567890!@#$%\u005E\u0026*()\u003C\u003E\u0022\u0027\u005C\u007C\u007D\u007B\u005D\u005B:;\u000D\u000A"); 
// -->/script> 
/form> 
/body> 
/html> 

这样，不管浏览器采用何种编码，页面都不会出现乱码。
==============================================
PHP
PHP的情况就复杂一点，需要考虑mysql的编码。这些姑且不论。
下面给出一点示例，将GBK进行HTML编码。仅作参考：

复制代码代码如下:

 
function htmlEncode($text) 
{ 
$encoded = ""; 
for( $index = 0; $index  strlen($text); $index++) 
{ 
if( ord($text[$index]) = 127 ) 
{ 
switch(ord($text[$index])) 
{ 
case 34: 
case 38: 
case 39: 
case 60: 
case 62: 
$encoded .= "#" .ord($text[$index]).";"; 
break; 
default: 
$encoded .= $text[$index]; 
} 
} 
else 
{ 
$char = $text[$index] . $text[$index+1]; 
$char = mb_convert_encoding( $char, "utf-16", "gbk"); 
$encoded .= "#" . (ord($char[0])*256 + ord($char[1])) . ";"; 
$index++; 
} 
} 
return $encoded; 
} 
function htmlEncode($text) 
{ 
$encoded = ""; 
for( $index = 0; $index  strlen($text); $index++) 
{ 
if( ord($text[$index]) = 127 ) 
{ 
switch(ord($text[$index])) 
{ 
case 34: 
case 38: 
case 39: 
case 60: 
case 62: 
$encoded .= "#" .ord($text[$index]).";"; 
break; 
default: 
$encoded .= $text[$index]; 
} 
} 
else 
{ 
$char = $text[$index] . $text[$index+1]; 
$char = mb_convert_encoding( $char, "utf-16", "gbk"); 
$encoded .= "#" . (ord($char[0])*256 + ord($char[1])) . ";"; 
$index++; 
} 
} 
return $encoded; 
} 

然后通过XML返回，这样就能够彻底杜绝乱码。

复制代码代码如下:

 
echo "?xml version=\"1.0\" encoding=\"utf-8\"?>\n"; 
echo "result>"; 
echo "success>". ($success ? 1 : 0) ."/success>"; 
echo "message>" . htmlEncode($message) . "/message>"; 
if( $success ) 
{ 
echo "nickname>" . htmlEncode($nickname) . "/nickname>"; 
echo "userId>".$userId."/userId>"; 
echo "siteId>".$siteId."/siteId>"; 
echo "isTeacher>". ($isTeacher ? 1 : 0) ."/isTeacher>"; 
echo "ipAddress>" . htmlEncode($ipAddress) . "/ipAddress>"; 
} 
echo "/result>"; 

本文来自CSDN博客，转载请标明出处：http://blog.csdn.net/wangjia184/archive/2009/10/26/4728318.aspx

上一篇：alt键 chr码值对应列表查看方法
下一篇：数据类型和Json格式分析小结