utf-8 与 utf-16 之间的问题
我基于这两个转换函数和 StackOverflow 上的答案,但来回转换不起作用:
std::wstring MultiByteToWideString(const char* szSrc)
{
unsigned int iSizeOfStr = MultiByteToWideChar(CP_ACP, 0, szSrc, -1, NULL, 0);
wchar_t* wszTgt = new wchar_t[iSizeOfStr];
if(!wszTgt) assert(0);
MultiByteToWideChar(CP_ACP, 0, szSrc, -1, wszTgt, iSizeOfStr);
std::wstring wstr(wszTgt);
delete(wszTgt);
return(wstr);
}
std::string WideStringToMultiByte(const wchar_t* wszSrc)
{
int iSizeOfStr = WideCharToMultiByte(CP_ACP, 0, wszSrc, -1, NULL, 0, NULL, NULL);
char* szTgt = new char[iSizeOfStr];
if(!szTgt) return(NULL);
WideCharToMultiByte(CP_ACP, 0, wszSrc, -1, szTgt, iSizeOfStr, NULL, NULL);
std::string str(szTgt);
delete(szTgt);
return(str);
}
[...]
// はてなブ in utf-16
wchar_t wTestUTF16[] = L"\u306f\u3066\u306a\u30d6\u306f\u306f";
// shows the text correctly
::MessageBoxW(NULL, wTestUTF16, L"Message", MB_OK);
// convert to UTF8, and back to UTF-16
std::string strUTF8 = WideStringToMultiByte(wTestUTF16);
std::wstring wstrUTF16 = MultiByteToWideString(strUTF8.c_str());
// this doesn't show the proper text. Should be same as first message box
::MessageBoxW(NULL, wstrUTF16.c_str(), L"Message", MB_OK);
I based these two conversion functions and an answer on StackOverflow, but converting back-and-forth doesn't work:
std::wstring MultiByteToWideString(const char* szSrc)
{
unsigned int iSizeOfStr = MultiByteToWideChar(CP_ACP, 0, szSrc, -1, NULL, 0);
wchar_t* wszTgt = new wchar_t[iSizeOfStr];
if(!wszTgt) assert(0);
MultiByteToWideChar(CP_ACP, 0, szSrc, -1, wszTgt, iSizeOfStr);
std::wstring wstr(wszTgt);
delete(wszTgt);
return(wstr);
}
std::string WideStringToMultiByte(const wchar_t* wszSrc)
{
int iSizeOfStr = WideCharToMultiByte(CP_ACP, 0, wszSrc, -1, NULL, 0, NULL, NULL);
char* szTgt = new char[iSizeOfStr];
if(!szTgt) return(NULL);
WideCharToMultiByte(CP_ACP, 0, wszSrc, -1, szTgt, iSizeOfStr, NULL, NULL);
std::string str(szTgt);
delete(szTgt);
return(str);
}
[...]
// はてなブ in utf-16
wchar_t wTestUTF16[] = L"\u306f\u3066\u306a\u30d6\u306f\u306f";
// shows the text correctly
::MessageBoxW(NULL, wTestUTF16, L"Message", MB_OK);
// convert to UTF8, and back to UTF-16
std::string strUTF8 = WideStringToMultiByte(wTestUTF16);
std::wstring wstrUTF16 = MultiByteToWideString(strUTF8.c_str());
// this doesn't show the proper text. Should be same as first message box
::MessageBoxW(NULL, wstrUTF16.c_str(), L"Message", MB_OK);
如果你对这篇内容有疑问,欢迎到本站社区发帖提问 参与讨论,获取更多帮助,或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱,如果其他用户或者作者回复了您的评论,将不能在第一时间通知您!
发布评论
评论(1)
检查 WideCharToMultiByte() 的文档。 CP_ACP 使用当前系统代码页进行转换。这是一件很亏的事。你想要CP_UTF8。
Check the docs for WideCharToMultiByte(). CP_ACP converts using the current system code page. That's a very lossy one. You want CP_UTF8.