What is the optimal multiplatform way of dealing with Unicode strings under C++?
Same as Adam Rosenfield answer (+1), but I use UTFCPP instead.
I would strongly recommend using UTF-8 internally in your application, using regular old char*
or std::string
for data storage. For interfacing with APIs that use a different encoding (ASCII, UTF-16, etc.), I'd recommend using libiconv, which is licensed under the LGPL.
Example usage:
class TempWstring
{
public:
TempWstring(const char *str)
{
assert(sUTF8toUTF16 != (iconv_t)-1);
size_t inBytesLeft = strlen(str);
size_t outBytesLeft = 2 * (inBytesLeft + 1); // worst case
mStr = new char[outBytesLeft];
char *outBuf = mStr;
int result = iconv(sUTF8toUTF16, &str, &inBytesLeft, &outBuf, &outBytesLeft);
assert(result == 0 && inBytesLeft == 0);
}
~TempWstring()
{
delete [] mStr;
}
const wchar_t *Str() const { return (wchar_t *)mStr; }
static void Init()
{
sUTF8toUTF16 = iconv_open("UTF-16LE", "UTF-8");
assert(sUTF8toUTF16 != (iconv_t)-1);
}
static void Shutdown()
{
int err = iconv_close(sUTF8toUTF16);
assert(err == 0);
}
private:
char *mStr;
static iconv_t sUTF8toUTF16;
};
iconv_t TempWstring::sUTF8toUTF16 = (iconv_t)-1;
// At program startup:
TempWstring::Init();
// At program termination:
TempWstring::Shutdown();
// Now, to convert a UTF-8 string to a UTF-16 string, just do this:
TempWstring x("Entr\xc3\xa9""e"); // "Entrée"
const wchar_t *ws = x.Str(); // valid until x goes out of scope
// A less contrived example:
HWND hwnd = CreateWindowW(L"class name",
TempWstring("UTF-8 window title").Str(),
dwStyle, x, y, width, height, parent, menu, hInstance, lpParam);