C + + convert Unicode utf-8 gb2312 encoding

The conversion method for Unicode, Utf-8, gb2312 Three encoding formats using vc++6.0 in the Windows Development environment:

[CPP]View Plaincopy

2. #include <iostream>
4. #include <string>
6. #include <Windows.h>
8. Using namespace std;
12. void UnicodeToUTF8 (const wstring &SRC, string& result)
14. {
16. int n = widechartomultibyte (Cp_utf8, 0, Src.c_str (),-1, 0, 0, 0, 0);
18. Result.resize (n);
20. :: WideCharToMultiByte (Cp_utf8, 0, Src.c_str (),-1, (char*) result.c_str (), Result.length (), 0, 0);
22. }
26. void unicodeToGB2312 (const wstring& WSTR, string& result)
28. {
30. int n = widechartomultibyte (CP_ACP, 0, Wstr.c_str (),-1, 0, 0, 0, 0);
32. Result.resize (n);
34. :: WideCharToMultiByte (CP_ACP, 0, Wstr.c_str (),-1, (char*) result.c_str (), n, 0, 0);
36. }
40. void Utf8tounicode (const string& SRC, wstring& result)
42. {
44. int n = MultiByteToWideChar (Cp_utf8, 0, Src.c_str (),-1, NULL, 0);
46. Result.resize (n);
48. :: MultiByteToWideChar (Cp_utf8, 0, Src.c_str (),-1, (lpwstr) result.c_str (), result.length ());
50. }
54. void Gb2312tounicode (const string& SRC, wstring& result)
56. {
58. int n = MultiByteToWideChar (CP_ACP, 0, Src.c_str (),-1, NULL, 0);
60. Result.resize (n);
62. :: MultiByteToWideChar (CP_ACP, 0, Src.c_str (),-1, (lpwstr) result.c_str (), result.length ());
64. }
68. void Printbyte (String str)
70. {
72. int i=0;
74. For (i=0; i<str.length (); i++)
76. {
78. printf ("%x", (unsigned char) str.at (i));
80. }
82. printf ("\ n");
84. }
88. void Wprintbyte (wstring str)
90. {
92. int i=0;
94. For (i=0; I<str.length () *sizeof (wchar_t); i++)
96. {
98. printf ("%x", * ((unsigned char*) str.c_str () +i));
100. }
102. printf ("\ n");
104. }
108. int main ()
110. {
112. String strText = "ab kanji";
114. String strUTF8;
116. Wstring Wstrunicode;
118. String strGB2312;
122. Gb2312tounicode (StrText, Wstrunicode);
124. printf ("unicode=");
126. Wprintbyte (Wstrunicode);
130. UnicodeToUTF8 (Wstrunicode, strUTF8);
132. printf ("UTF-8 =");
134. Printbyte (STRUTF8);
138. Utf8tounicode (Strutf8,wstrunicode);
140. printf ("unicode=");
142. Wprintbyte (Wstrunicode);
146. unicodeToGB2312 (wstrunicode,strgb2312);
148. printf ("GB2312 =");
150. Printbyte (strGB2312);
154. return 0;
156. }

This is a string of "ab Kanji" for testing, and its ASCII code is a BA ba D7 D6
Output Result: