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

关注

原创最新推荐文章于 2026-04-28 14:39:34 发布 5.2k 阅读 AI 写同款· GEO 优化 ›

stm32单片机平台上ASCII(GBK,GB2312)转unicode转UTF-8 问题来源用stm32单片机接收APP发下来的汉字，并显示此汉字。 APP发下来的是UTF-8，转到服务器，因为mdk里面输入的汉字是ASCII(GBK,GB2312)，所以需要服务器将UTF-8转成ASCII(GBK,GB2312)。现在升级STM32单片机程序，发现需要UTF-8编码，APP和服务器最好不动，不然修改太大。所以就出现了ASCII(GBK,GB2312)转unicode转UTF-8需求以下ASCII(GBK,GB2312)，统称为GBK，因为ASCII是GB2312子集，G 阅读详情

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;
}

收录于