C++中GB2312、UTF-8、unicode 之间转换

最新推荐文章于 2021-05-18 05:43:23 发布

LearnLHC

最新推荐文章于 2021-05-18 05:43:23 发布

阅读量2.5k

点赞数 2

分类专栏：编码格式

编码格式专栏收录该内容

3 篇文章

订阅专栏

本文详细介绍了几种常见字符编码之间的转换方法，包括GB2312到UTF-8、UTF-8到GB2312、GB2312到Unicode、Unicode到GB2312、UTF-8到Unicode及Unicode到UTF-8的具体实现。通过Windows API函数MultiByteToWideChar和WideCharToMultiByte完成各种编码间的相互转换。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

包含头文件 #include <windows.h>

//GB2312到UTF-8的转换
static int GB2312ToUtf8(const char* gb2312, char* utf8)
{
	int len = MultiByteToWideChar(CP_ACP, 0, gb2312, -1, NULL, 0);
	wchar_t* wstr = new wchar_t[len+1];
	memset(wstr, 0, len+1);
	MultiByteToWideChar(CP_ACP, 0, gb2312, -1, wstr, len);
	len = WideCharToMultiByte(CP_UTF8, 0, wstr, -1, NULL, 0, NULL, NULL);
	WideCharToMultiByte(CP_UTF8, 0, wstr, -1, utf8, len, NULL, NULL);
	if(wstr) delete[] wstr;
	return len;
}

//UTF-8到GB2312的转换
static int Utf8ToGB2312(const char* utf8, char* gb2312)
{
	int len = MultiByteToWideChar(CP_UTF8, 0, utf8, -1, NULL, 0);
	wchar_t* wstr = new wchar_t[len+1];
	memset(wstr, 0, len+1);
	MultiByteToWideChar(CP_UTF8, 0, utf8, -1, wstr, len);
	len = WideCharToMultiByte(CP_ACP, 0, wstr, -1, NULL, 0, NULL, NULL);
	WideCharToMultiByte(CP_ACP, 0, wstr, -1, gb2312, len, NULL, NULL);
	if(wstr) delete[] wstr;
	return len;
}

--------------------------------------------------------------------------------------------------------------------------------------

//GB2312到Unicode的转换
static int GB2312ToUnicode(const char* gb2312, char* unicode)
{
	UINT nCodePage = 936; //GB2312
	int len = MultiByteToWideChar(nCodePage, 0, gb2312, -1, NULL, 0);
	wchar_t* wstr = new wchar_t[len+1];
	memset(wstr, 0, len+1);
	MultiByteToWideChar(nCodePage, 0, gb2312, -1, wstr, len);
	len = len*sizeof(wchar_t);
	memcpy(unicode, wstr, len);
	if(wstr) delete[] wstr;
	return len;
}

//Unicode到GB2312的转换
static int UnicodeToGB2312(const char* unicode, int size, char*gb2312)
{
	UINT nCodePage = 936; //GB2312
	wchar_t* wstr = new wchar_t[size/2+1];
	memcpy(wstr, unicode, size);
	int len = WideCharToMultiByte(nCodePage, 0, wstr, -1, NULL, 0, NULL, NULL);
	WideCharToMultiByte(nCodePage, 0, wstr, -1, gb2312, len, NULL, NULL);
	if(wstr) delete[] wstr;
	return len;
}

------------------------------------------------------------------------------------------------------

//UTF-8到Unicode的转换
static int Utf8ToUnicode(const char* utf8, char*unicode)
{
	int len = MultiByteToWideChar(CP_UTF8, 0, utf8, -1, NULL, 0);
	wchar_t* wstr = new wchar_t[len+1];
	memset(wstr, 0, len+1);
	MultiByteToWideChar(CP_UTF8, 0, utf8, -1, wstr, len);
	memcpy(unicode, wstr, len);
	if(wstr) delete[] wstr;
	return len;
}

//Unicode到UTF-8的转换
static int UnicodeToUtf8(const char* unicode, int size, char* utf8)
{
	wchar_t* wstr = new wchar_t[size/2+1];
	memcpy(wstr, unicode, size);
	int len = WideCharToMultiByte(CP_UTF8, 0, wstr, -1, NULL, 0, NULL, NULL);
	WideCharToMultiByte(CP_UTF8, 0, wstr, -1, utf8, len, NULL, NULL);
	if(wstr) delete[] wstr;
	return len;
}