ansi与unicode字符串转换

在windows程序中使用MultiByteToWideChar和WideCharToMultiByte实现多字节字符与宽字符的转换

以下是部分Unicode字符集的截图，在其中选取几个文字测试转换

int main()
{
	const char* ansiString = "A一丐东";
	int strLength = strlen(ansiString);

	//ANSI转UNICODE
	int unicodeLen = ::MultiByteToWideChar(CP_ACP, 0, ansiString, strLength, NULL, 0);//计算需要的长度
	wchar_t* pUnicode = new wchar_t[unicodeLen + 1]; //加1让字符串以‘0’结束
	memset(pUnicode, 0, (unicodeLen + 1) * sizeof(wchar_t));
	MultiByteToWideChar(CP_ACP, 0, ansiString, strLength, pUnicode, unicodeLen);

	printf("unicode: ");
	for (int i = 0; i < unicodeLen; i++)
	{
		printf("%X ", (unsigned short)pUnicode[i]);
	}
	printf("\n");


	//UNICODE转ANSI
	int ansiLen = WideCharToMultiByte(CP_ACP, 0, pUnicode, unicodeLen, NULL, 0, NULL, NULL);
	char* pAnsi = new char[ansiLen + 1];
	memset(pAnsi, 0, (ansiLen + 1) * sizeof(char));
	WideCharToMultiByte(CP_ACP, 0, pUnicode, unicodeLen, pAnsi, ansiLen, NULL, NULL);

	printf("ansi: ");
	for (int i = 0; i < ansiLen; i++)
	{
		printf("%X ", (unsigned char)pAnsi[i]);
	}
	printf("\n");


	//UNICODE转UTF8
	int utf8Len = WideCharToMultiByte(CP_UTF8, 0, pUnicode, unicodeLen, NULL, 0, NULL, NULL);
	char* pUtf8 = new char[utf8Len + 1];
	memset(pUtf8, 0, (utf8Len + 1) * sizeof(char));
	WideCharToMultiByte(CP_UTF8, 0, pUnicode, unicodeLen, pUtf8, utf8Len, NULL, NULL);

	printf("utf8: ");
	for (int i = 0; i < utf8Len; i++)
	{
		printf("%X ", (unsigned char)pUtf8[i]);
	}
	printf("\n");


	//UTF8转UNICODE
	int unicodeLen2 = ::MultiByteToWideChar(CP_UTF8, 0, pUtf8, utf8Len, NULL, 0);
	wchar_t* pUnicode2 = new wchar_t[unicodeLen2 + 1];
	memset(pUnicode2, 0, (unicodeLen2 + 1) * sizeof(wchar_t));
	MultiByteToWideChar(CP_UTF8, 0, pUtf8, utf8Len, pUnicode2, unicodeLen2);

	printf("unicode2: ");
	for (int i = 0; i < unicodeLen2; i++)
	{
		printf("%X ", (unsigned short)pUnicode2[i]);
	}
	printf("\n");

	delete[] pUnicode;
	delete[] pAnsi;
	delete[] pUtf8;
	delete[] pUnicode2;
	system("pause");
	return 0;
}

运行结果

代码页CP_ACP实现ANSI字符和Unicode字符之间的转换，CP_UTF8实现Unicode字符和utf8编码之间的转换， utf8是Unicode字符集的一种编码方式，如果要将ansi字符转utf8编码，先要转为Unicode字符，然后通过CP_UTF8代码页转为utf8编码，中文字符的utf8编码一般占用3个字节，英文字符占用一个字节，上面的Unicode字符都占用两个字节，所以UTF8编码英文字符时可以节省内存。