C++ 中文乱码的问题
乱码的根本原因就是字符串编码的方式也字符串解码方式不一致导致的, 而在我们平常用的编码编码方式一般都是utf-8以gbk之间的相互转换, 下面给出编码方式的转换代码
string UtfToString(string strValue) { int nwLen = ::MultiByteToWideChar(CP_ACP, 0, strValue.c_str(), -1, NULL, 0); wchar_t * pwBuf = new wchar_t[nwLen + 1];//加上末尾'\0' ZeroMemory(pwBuf, nwLen * 2 + 2); ::MultiByteToWideChar(CP_ACP, 0, strValue.c_str(), strValue.length(), pwBuf, nwLen); int nLen = ::WideCharToMultiByte(CP_UTF8, 0, pwBuf, -1, NULL, NULL, NULL, NULL); char * pBuf = new char[nLen + 1]; ZeroMemory(pBuf, nLen + 1); ::WideCharToMultiByte(CP_UTF8, 0, pwBuf, nwLen, pBuf, nLen, NULL, NULL); std::string retStr(pBuf); delete []pwBuf; delete []pBuf; pwBuf = NULL; pBuf = NULL; return retStr; } string StringToUtf(string strValue) { int nwLen = MultiByteToWideChar(CP_UTF8, 0, strValue.c_str(), -1, NULL, 0); wchar_t * pwBuf = new wchar_t[nwLen + 1];//加上末尾'\0' memset(pwBuf, 0, nwLen * 2 + 2); MultiByteToWideChar(CP_UTF8, 0, strValue.c_str(), strValue.length(), pwBuf, nwLen); int nLen = WideCharToMultiByte(CP_ACP, 0, pwBuf, -1, NULL, NULL, NULL, NULL); char * pBuf = new char[nLen + 1]; memset(pBuf, 0, nLen + 1); WideCharToMultiByte(CP_ACP, 0, pwBuf, nwLen, pBuf, nLen, NULL, NULL); std::string retStr = pBuf; delete []pBuf; delete []pwBuf; return retStr; }
string UtfToGbk(string strValue)
{
int len = MultiByteToWideChar(CP_UTF8, 0, strValue.c_str(), -1, NULL, 0);
wchar_t* wstr = new wchar_t[len+1];
memset(wstr, 0, len+1);
MultiByteToWideChar(CP_UTF8, 0, strValue.c_str(), -1, wstr, len);
len = WideCharToMultiByte(CP_ACP, 0, wstr, -1, NULL, 0, NULL, NULL);
char* str = new char[len+1];
memset(str, 0, len+1);
WideCharToMultiByte(CP_ACP, 0, wstr, -1, str, len, NULL, NULL);
if(wstr) delete[] wstr;
return string(str);
}