字符串编码之间的转换（GB2312<->UTF8<->Unicode）及URLEncoding

最新推荐文章于 2018-09-19 21:14:30 发布

原创最新推荐文章于 2018-09-19 21:14:30 发布 · 5.2k 阅读

28 ·

CC 4.0 BY-SA版权

VC/MFC Development 专栏收录该内容

67 篇文章

订阅专栏

本文介绍了一种实现不同字符集（如GB2312、UTF-8和Unicode）间相互转换的方法，并提供了具体的C/C++代码示例。通过这些函数可以进行字符串编码的转换，例如从GB2312到UTF-8或者相反。此外还展示了如何将字符串转换为适用于网页显示的转义格式。

LPWSTR GB2312ToUnicode(LPCSTR lpszInBuf)
{
	if (NULL == lpszInBuf)
	{
		return NULL;
	}
	WCHAR* pBuf = NULL;
	int nLen = MultiByteToWideChar(CP_ACP, 0, lpszInBuf, -1, pBuf, 0);
	pBuf = new WCHAR[nLen];
	memset(pBuf, 0, sizeof(WCHAR) * nLen);
	MultiByteToWideChar(CP_ACP, 0, lpszInBuf, -1, pBuf, nLen);
	return pBuf;
}

LPSTR UnicodeToGB2312(LPCWSTR lpszInBuf)
{
	if (NULL == lpszInBuf)
	{
		return NULL;
	}
	CHAR* pBuf = NULL;
	int nLen = WideCharToMultiByte(CP_ACP, 0, lpszInBuf, -1, pBuf, 0, NULL, NULL);
	pBuf = new CHAR[nLen];
	memset(pBuf, 0, sizeof(CHAR) * nLen);
	WideCharToMultiByte(CP_ACP, 0, lpszInBuf, -1, pBuf, nLen, NULL, NULL);
	return pBuf;
}

LPWSTR UTF8ToUnicode(LPCSTR lpszInBuf)
{
	if (NULL == lpszInBuf)
	{
		return NULL;
	}
	WCHAR* pBuf = NULL;
	int nLen = MultiByteToWideChar(CP_UTF8, 0, lpszInBuf, -1, pBuf, 0);
	pBuf = new WCHAR[nLen];
	memset(pBuf, 0, sizeof(WCHAR) * nLen);
	MultiByteToWideChar(CP_UTF8, 0, lpszInBuf, -1, pBuf, nLen);
	return pBuf;
}

LPSTR UnicodeToUTF8(LPCWSTR lpszInBuf)
{
	if (NULL == lpszInBuf)
	{
		return NULL;
	}
	CHAR* pBuf = NULL;
	int nLen = WideCharToMultiByte(CP_UTF8, 0, lpszInBuf, -1, pBuf, 0, NULL, NULL);
	pBuf = new CHAR[nLen];
	memset(pBuf, 0, sizeof(CHAR) * nLen);
	WideCharToMultiByte(CP_UTF8, 0, lpszInBuf, -1, pBuf, nLen, NULL, NULL);
	return pBuf;
}

LPSTR GB2312ToUTF8(LPCSTR lpszInBuf)
{
	if (NULL == lpszInBuf)
	{
		return NULL;
	}
	LPWSTR lpszTmp = GB2312ToUnicode(lpszInBuf);
	LPSTR lpszBuf = UnicodeToUTF8(lpszTmp);
	delete[] lpszTmp;
	lpszTmp = NULL;
	return lpszBuf;
}

LPSTR UTF8ToGB2312(LPCSTR lpszInBuf)
{
	if (NULL == lpszInBuf)
	{
		return NULL;
	}
	LPWSTR lpszTmp = UTF8ToUnicode(lpszInBuf);
	LPSTR lpszBuf = UnicodeToGB2312(lpszTmp);
	delete[] lpszTmp;
	lpszTmp = NULL;
	return lpszBuf;
}

LPSTR GB2312Encoding(LPCSTR lpszInBuf)
{
	if (NULL == lpszInBuf)
	{
		return NULL;
	}
	const int nLen = strlen(lpszInBuf) * 3 + 1;
	CHAR* pBuf = new CHAR[nLen];
	memset(pBuf, 0, sizeof(CHAR) * nLen);
	CHAR szTmp[4] = { 0 };
	for (int i = 0; i != strlen(lpszInBuf); ++i)
	{
		if (IsDBCSLeadByte(lpszInBuf[i]))
		{
			sprintf_s(szTmp, _countof(szTmp), "%%%02X", lpszInBuf[i] & 0xFF);
		}
		else
		{
			sprintf_s(szTmp, _countof(szTmp), "%c", lpszInBuf[i]);
		}
		sprintf_s(pBuf + strlen(pBuf), nLen - strlen(pBuf), "%s", szTmp);
	}
	return pBuf;
}

LPSTR UTF8Encoding(LPCSTR lpszInBuf)
{
	if (NULL == lpszInBuf)
	{
		return NULL;
	}

	CHAR* pBuffer = GB2312ToUTF8(lpszInBuf);

	const int nLen = strlen(pBuffer) * 3 + 1;
	CHAR* pBuf = new CHAR[nLen];
	memset(pBuf, 0, sizeof(CHAR) * nLen);
	CHAR szTmp[4] = { 0 };
	for (int i = 0; i != strlen(pBuffer); ++i)
	{
		if (IsDBCSLeadByte(pBuffer[i]))
		{
			sprintf_s(szTmp, _countof(szTmp), "%%%02X", pBuffer[i] & 0xFF);
		}
		else
		{
			sprintf_s(szTmp, _countof(szTmp), "%c", pBuffer[i]);
		}
		sprintf_s(pBuf + strlen(pBuf), nLen - strlen(pBuf), "%s", szTmp);
	}
	if (NULL != pBuffer) { delete[] pBuffer; pBuffer = NULL; }
	return pBuf;
}


int main()
{
	CHAR szText[] = "百度Hi";
	CHAR* pBuf = UTF8Encoding(szText);
	MessageBoxA(NULL, pBuf, NULL, 0);
	delete[] pBuf;
	pBuf = NULL;

    return 0;
}