C/C++,字符串的UTF-8与GBK(或GB2312)编码转换

时间:2023-01-06 21:20:35

写代码时经常会遇到各种编码转换问题,因此记录下来以便日后对各种平台下不同编码转换作整理。


C/C++:

GBK(或GB2312)转UTF-8实现:

string GBKToUTF8(const char* strGBK)
{
int len = MultiByteToWideChar(CP_ACP, 0, strGBK, -1, NULL, 0);
wchar_t* wstr = new wchar_t[len+1];
memset(wstr, 0, len+1);
MultiByteToWideChar(CP_ACP, 0, strGBK, -1, wstr, len);
len = WideCharToMultiByte(CP_UTF8, 0, wstr, -1, NULL, 0, NULL, NULL);
char* str = new char[len+1];
memset(str, 0, len+1);
WideCharToMultiByte(CP_UTF8, 0, wstr, -1, str, len, NULL, NULL);
string strTemp = str;
if(wstr) delete[] wstr;
if(str) delete[] str;
return strTemp;
}

UTF-8转GBK(或GB2312)实现:

string UTF8ToGBK(const char* strUTF8)
{
int len = MultiByteToWideChar(CP_UTF8, 0, strUTF8, -1, NULL, 0);
wchar_t* wszGBK = new wchar_t[len+1];
memset(wszGBK, 0, len*2+2);
MultiByteToWideChar(CP_UTF8, 0, strUTF8, -1, wszGBK, len);
len = WideCharToMultiByte(CP_ACP, 0, wszGBK, -1, NULL, 0, NULL, NULL);
char* szGBK = new char[len+1];
memset(szGBK, 0, len+1);
WideCharToMultiByte(CP_ACP, 0, wszGBK, -1, szGBK, len, NULL, NULL);
string strTemp(szGBK);
if(wszGBK) delete[] wszGBK;
if(szGBK) delete[] szGBK;
return strTemp;
}