字符编码转换（内附字符串类似string.Format的具体实现）

下面的代码用来测试字符编码转换。

 

 1 namespace CA_Encoding
 2 {
 3     using System;
 4     using System.Text;
 5 
 6     class Program
 7     {
 8         static void Main(string[] args)
 9         {
10             // 1.Declare the encoding sets.
11             System.Text.Encoding[] encodings = { 
12                                                 Encoding.Unicode,
13                                                 Encoding.UTF8,
14                                                 Encoding.UTF7,
15                                                 Encoding.UTF32,
16                                                 Encoding.ASCII,
17                                                 Encoding.BigEndianUnicode,
18                                                 Encoding.Default
19                                                };
20             // 2.Declare a stard word.
21             // string text = "我是一棵小草, I am a Grass, Unë jam një Gras(阿尔巴尼亚语), 私は、グラス午前。";
22             string text = "我是一棵小草（I am a Grass）";
23 
24             // 3.Output the text.
25             ConsoleColor defaultColor = Console.ForegroundColor;
26             Console.ForegroundColor = ConsoleColor.Blue;
27             Console.WriteLine("The text is : {0}", text);
28             Console.ForegroundColor = defaultColor;
29 
30             // 4.For each to encoding or decoding.
31             for (int i = 0, length = encodings.Length; i < length; ++i)
32             {
33                 Console.ForegroundColor = ConsoleColor.Cyan;
34                 Console.WriteLine("{0}", encodings[i].EncodingName);
35 
36                 byte[] textBytes = encodings[i].GetBytes(text);
37                 for (int j = 0; j < length; ++j)
38                 {
39                     Console.ForegroundColor = ConsoleColor.Yellow;
40                     Console.Write("\t-> {0}:", encodings[j].EncodingName);
41                     Console.ForegroundColor = defaultColor;
42                     string decodingText = encodings[j].GetString(textBytes);
43                     Console.WriteLine("{0}", decodingText);
44                 }
45             }
46         }
47     }
48 }
49 

 

 下面则是以上代码的输出：

结论：

只要是编码不匹配的，或多或少都会出现问题。

另：

调用Windows API，可以查看当前系统语言设置。

下面的设置将影响代码的输出结果：

C++代码：

 

 1 // Encoding.cpp : Defines the entry point for the console application.
 2 //
 3 
 4 #include "stdafx.h"
 5 #include <iostream>
 6 #include "windows.h"
 7 #include <string>
 8 // #include "mlang.h"
 9 
10 using namespace std;
11 int _tmain(int argc, _TCHAR* argv[])
12 {
13     LANGID langId = :: GetSystemDefaultLangID();
14     string displayName;
15     string defaultCharSet;
16     // http://msdn.microsoft.com/zh-cn/library/ms776260(en-us,VS.85).aspx
17     // http://msdn.microsoft.com/en-us/library/bb165625(VS.80).aspx
18     cout<<langId<<endl;
19     switch(langId){
20         case 0x804:
21             displayName = "Chinese (Simplified)";
22             defaultCharSet = "GB2312";
23             break;
24     }
25 
26     cout << "DisplayName = " << displayName << ";" << endl << "Default CharSet = " << defaultCharSet << endl;
27     return 0;
28 }
29 
30 

最后，我们更换我们的C#代码，然后输出全部的Encoding（下载附件）

因为在命令行输出比较大，可能会死机，这里我改造代码，并将其写入到文本文件中。

 

  1 namespace CA_Encoding
  2 {
  3     using System;
  4     using System.Text;
  5     using System.IO;
  6 
  7     class Program
  8     {
  9         static void Main(string[] args)
 10         {
 11             // 1.Declare the encoding sets.
 12             System.Text.Encoding[] encodings = { 
 13                                                 Encoding.Unicode,
 14                                                 Encoding.UTF8,
 15                                                 Encoding.UTF7,
 16                                                 Encoding.UTF32,
 17                                                 Encoding.ASCII,
 18                                                 Encoding.BigEndianUnicode,
 19                                                 Encoding.Default
 20                                                };
 21             EncodingInfo[] encodingInfos = Encoding.GetEncodings();
 22 
 23             // 2.Declare a stard word.
 24             // string text = "我是一棵小草, I am a Grass, Unë jam një Gras(阿尔巴尼亚语), 私は、グラス午前。";
 25             string text = "我是一棵小草（I am a Grass）";
 26 
 27             // 3.Output the text.
 28             WriteMeLine("The text is : {0}", text);
 29 
 30             // 4.For each to encoding or decoding.
 31             for (int i = 0, length = encodingInfos.Length; i < length; ++i)
 32             {
 33                 WriteMeLine("{0},{1},{2},{3}", encodingInfos[i].GetEncoding().EncodingName,
 34                     encodingInfos[i].CodePage,
 35                     encodingInfos[i].DisplayName,
 36                     encodingInfos[i].Name
 37                     );
 38 
 39                 byte[] textBytes = encodingInfos[i].GetEncoding().GetBytes(text);
 40                 for (int j = 0; j < length; ++j)
 41                 {
 42                     WriteMe("\t-> {0}:", encodingInfos[j].GetEncoding().EncodingName);
 43                     string decodingText = encodingInfos[j].GetEncoding().GetString(textBytes);
 44                     WriteMeLine("{0}", decodingText);
 45                 }
 46             }
 47         }
 48 
 49         static void WriteMeLine(string format, params object[] args)
 50         {
 51             WriteMe(format + "\r\n", args);
 52         }
 53         static void WriteMe(string format, params object[] args)
 54         {
 55             StringBuilder sb = new StringBuilder();
 56             if (args != null && args.Length > 0)
 57             {
 58                 for (int i = 0, length = format.Length; i < length; ++i)
 59                 {
 60                     if (format[i] == '{')
 61                     {
 62                         int j = i + 1;
 63                         while (SafeArrayIndex(ref format, j) && format[j] != '}')
 64                             ++j;
 65                         if (j != length)
 66                         {
 67                             string between = FetchBetween(ref format, i + 1, j);
 68                             int betweenInt = -1;
 69                             if (int.TryParse(between, out betweenInt) && betweenInt < args.Length)
 70                             {
 71                                 sb.Append(string.Format("{0}", args[betweenInt]));
 72                             }
 73                             else
 74                             {
 75                                 sb.Append(FetchBetween(ref format, i, j + 1));
 76                             }
 77                             i = j;
 78                         }
 79                         else
 80                         {
 81                             sb.Append(FetchBetween(ref format, i, j + 1));
 82                         }
 83                     }
 84                     else
 85                     {
 86                         sb.Append(format[i]);
 87                     }
 88                 }
 89             }
 90             WriteLog(sb.ToString());
 91         }
 92 
 93         static bool SafeArrayIndex(ref string format, int index)
 94         {
 95             if (index >= 0 && index < format.Length)
 96                 return true;
 97             else
 98                 return false;
 99         }
100 
101         static string FetchBetween(ref string format, int begin, int end)
102         {
103             string result = null;
104             if (SafeArrayIndex(ref format, begin) && SafeArrayIndex(ref format, end - 1))
105             {
106                 while (begin != end)
107                 {
108                     result += format[begin++];
109                 }
110             }
111             return result;
112         }
113 
114         static string logFile = null;
115         static void WriteLog(string msg)
116         {
117             FileStream fs = null;
118             try
119             {
120                 //msg = string.Format("[{0}] {1}\r\n", System.DateTime.Now.ToString("yyyyMMdd HH:mm:ss.fff"), msg);
121 
122                 if (string.IsNullOrEmpty(logFile))
123                 {
124                     string path = string.Format("log{0}.txt", System.DateTime.Now.ToString("yyyyMMdd"));
125                     if (!File.Exists(path))
126                     {
127                         fs = File.Create(path);
128                     }
129                     else
130                     {
131                         fs = File.Open(path, FileMode.Append);
132                     }
133                     logFile = path;
134                 }
135                 else
136                 {
137                     fs = File.Open(logFile, FileMode.Append);
138                 }
139                 if (fs != null && fs.CanWrite)
140                 {
141                     byte[] msgBytes = System.Text.Encoding.Default.GetBytes(msg);
142 
143                     fs.Write(msgBytes, 0, msgBytes.Length);
144                 }
145             }
146             catch (Exception ex)
147             {
148                 //
149             }
150             finally
151             {
152                 if (fs != null)
153                     fs.Close();
154             }
155         }
156     }
157 }
158 

 

See also：

1、《Language Identifier Constants and Strings》http://msdn.microsoft.com/zh-cn/library/dd318693(en-us,VS.85).aspx

2、《如何取得 charset》http://topic.csdn.net/u/20091129/05/a897fdb7-6792-41a1-b703-81e408fb430b.html

3、《Locale Identifier Constants and Strings》http://msdn.microsoft.com/zh-cn/library/ms776260(en-us,VS.85).aspx

 

Download：

 /Files/volnet/encoding-output.7z