unicode字符和多字节字符的相互转换接口

作者：朱金灿

来源：http://blog.csdn.net/clever101

发现开源代码的可利用资源真多，从sqlite3的源码中抠出了几个字符转换接口，稍微改造下了发现还挺好用的。下面是实现代码：

/*
** Convert a UTF-8 string to microsoft unicode (UTF-16?).
**
** Space to 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.  Space 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.
**
** Space to 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.
**
** Space to 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.  Space 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.  Space 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;
}

要测试这些接口，为此我写了一个测试工程，是读取一个xml文件把里面的字符进行转换的，测试工程的代码下载地址如下：

unicode字符和多字节字符的相互转换接口及测试工程