Conversion interface between Unicode characters and multibyte characters

Author: Zhu Jinchan

Source: http://blog.csdn.net/clever101

Found open source code of the available resources are really many, from the source of the sqlite3 to pull out a few characters to transform the interface, a little transformation of the discovery is quite good to use. Here is the implementation code:

* * * * * Convert a UTF-8 string to Microsoft Unicode (UTF-16?).
* * * * * * Hold the returned string is obtained from malloc.
	*/Static WCHAR *utf8tounicode (const char *zfilename) {int nChar;

	WCHAR *zwidefilename;
	NChar = MultiByteToWideChar (Cp_utf8, 0, Zfilename,-1, NULL, 0);
	Zwidefilename = Static_cast<wchar *> (malloc (nchar*sizeof (zwidefilename[0)));

	if (zwidefilename==0) {return 0;
	} NChar = MultiByteToWideChar (Cp_utf8, 0, Zfilename,-1, Zwidefilename, NChar);
		if (nchar==0) {free (zwidefilename);

	Zwidefilename = 0;

return zwidefilename;  /* * * * Convert Microsoft Unicode to UTF-8.
Spaces to hold the returned string is * * obtained from malloc ().
	*/Static char *unicodetoutf8 (const WCHAR *zwidefilename) {int nbyte;

	Char *zfilename;
	Nbyte = WideCharToMultiByte (Cp_utf8, 0, Zwidefilename,-1, 0, 0, 0, 0);
	Zfilename = static_cast<char*> (malloc (nbyte));

	if (zfilename==0) {return 0; } nbyte = WideCharToMultiByte (Cp_utf8, 0, ZwidefilenAme,-1, Zfilename, nbyte, 0, 0);
		if (Nbyte = = 0) {free (zfilename);
	Zfilename = 0;

return zfilename;
/* * * * Convert an ANSI string to Microsoft Unicode, based on the * * Current codepage settings for file APIs.
* * * * * * Hold the returned string is obtained * * from malloc.
	*/Static WCHAR *mbcstounicode (const char *zfilename) {int nbyte;
	WCHAR *zmbcsfilename; int codepage = Arefileapisansi ()?

	CP_ACP:CP_OEMCP;
	Nbyte = MultiByteToWideChar (codepage, 0, Zfilename,-1, null,0) *sizeof (WCHAR);
	Zmbcsfilename = static_cast<wchar*> (malloc (nbyte*sizeof (zmbcsfilename[0)));

	if (zmbcsfilename==0) {return 0;
	} Nbyte = MultiByteToWideChar (codepage, 0, Zfilename,-1, Zmbcsfilename, nbyte);
		if (nbyte==0) {free (zmbcsfilename);
	Zmbcsfilename = 0;

return zmbcsfilename;
}/* * * * Convert Microsoft Unicode to multibyte character string, based on the * * user's Ansi codepage.
* * * * * * Hold the returned string is obtained from * * malloc (). * * STATIC char* Unicodetombcs (const wchar* zwidefilename) {int nbyte;
	Char *zfilename; int codepage = Arefileapisansi ()?

	CP_ACP:CP_OEMCP;
	Nbyte = WideCharToMultiByte (codepage, 0, Zwidefilename,-1, 0, 0, 0, 0);
	Zfilename = static_cast<char*> (malloc (nbyte));

	if (zfilename==0) {return 0;
	Nbyte = WideCharToMultiByte (codepage, 0, Zwidefilename,-1, Zfilename, nbyte, 0, 0);
		if (Nbyte = = 0) {free (zfilename);
	Zfilename = 0;

return zfilename;  } * * * * Convert multibyte character string to UTF-8.
Spaces to hold the * * returned string is obtained from malloc ().
	*/Static char* MbcsToUtf8 (const char *zfilename) {char *zfilenameutf8;

	WCHAR *ztmpwide;
	Ztmpwide = Mbcstounicode (zfilename);

	if (ztmpwide==0) {return 0;
	} ZFilenameUtf8 = UnicodeToUtf8 (ztmpwide);
	Free (ztmpwide);
return ZFilenameUtf8;  } * * * * Convert UTF-8 to multibyte character string.
Spaces to hold the * * returned string is obtained from malloc (). */Static char* Utf8tombcs (const char *zfilename) {char *zfilenamembcs;

	wchar* Ztmpwide;
	Ztmpwide = Utf8tounicode (zfilename);

	if (ztmpwide==0) {return 0;
	} Zfilenamembcs = Unicodetombcs (ztmpwide);
	Free (ztmpwide);
return ZFILENAMEMBCS;
	} std::string MbcsToUtf8 (const char* PSZMBCS) {std::string str;
	WCHAR *pwchar=0;
	CHAR *pchar=0;
	int len=0; int codepage = Arefileapisansi ()?
	CP_ACP:CP_OEMCP;
	Len=multibytetowidechar (codepage, 0, Pszmbcs,-1, null,0);
	Pwchar=new Wchar[len];
		if (pwchar!=0) {len = MultiByteToWideChar (codepage, 0, Pszmbcs,-1, Pwchar, Len);
			if (len!=0) {len = WideCharToMultiByte (Cp_utf8, 0, Pwchar,-1, 0, 0, 0, 0);
			Pchar=new Char[len];
				if (pchar!=0) {len = WideCharToMultiByte (Cp_utf8, 0, Pwchar,-1, Pchar, len,0, 0);                   
				if (len!=0) {str = Pchar;
			} Delete Pchar;
		} Delete Pwchar;
} return str; }

To test these interfaces, I wrote a test project that reads an XML file to convert the characters inside, and the code for the test project downloads the following address:

The interface between Unicode character and multibyte character and test engineering