How can I cin and cout some unicode text?
I had a similar problem in the past, in my case imbue
and sync_with_stdio
did the trick. Try this:
#include <iostream>
#include <locale>
#include <string>
using namespace std;
int main() {
ios_base::sync_with_stdio(false);
wcin.imbue(locale("en_US.UTF-8"));
wcout.imbue(locale("en_US.UTF-8"));
wstring s;
wstring t(L" la Polynésie française");
wcin >> s;
wcout << s << t << endl;
return 0;
}
Depending on what type unicode you mean. I assume you mean you are just working with std::wstring
though. In that case use std::wcin
and std::wcout
.
For conversion between encodings you can use your OS functions like for Win32: WideCharToMultiByte
, MultiByteToWideChar
or you can use a library like libiconv
Here is an example that shows four different methods, of which only the third (C conio
) and the fourth (native Windows API) work (but only if stdin/stdout aren't redirected). Note that you still need a font that contains the character you want to show (Lucida Console supports at least Greek and Cyrillic). Note that everything here is completely non-portable, there is just no portable way to input/output Unicode strings on the terminal.
#ifndef UNICODE
#define UNICODE
#endif
#ifndef _UNICODE
#define _UNICODE
#endif
#define STRICT
#define NOMINMAX
#define WIN32_LEAN_AND_MEAN
#include <iostream>
#include <string>
#include <cstdlib>
#include <cstdio>
#include <conio.h>
#include <windows.h>
void testIostream();
void testStdio();
void testConio();
void testWindows();
int wmain() {
testIostream();
testStdio();
testConio();
testWindows();
std::system("pause");
}
void testIostream() {
std::wstring first, second;
std::getline(std::wcin, first);
if (!std::wcin.good()) return;
std::getline(std::wcin, second);
if (!std::wcin.good()) return;
std::wcout << first << second << std::endl;
}
void testStdio() {
wchar_t buffer[0x1000];
if (!_getws_s(buffer)) return;
const std::wstring first = buffer;
if (!_getws_s(buffer)) return;
const std::wstring second = buffer;
const std::wstring result = first + second;
_putws(result.c_str());
}
void testConio() {
wchar_t buffer[0x1000];
std::size_t numRead = 0;
if (_cgetws_s(buffer, &numRead)) return;
const std::wstring first(buffer, numRead);
if (_cgetws_s(buffer, &numRead)) return;
const std::wstring second(buffer, numRead);
const std::wstring result = first + second + L'\n';
_cputws(result.c_str());
}
void testWindows() {
const HANDLE stdIn = GetStdHandle(STD_INPUT_HANDLE);
WCHAR buffer[0x1000];
DWORD numRead = 0;
if (!ReadConsoleW(stdIn, buffer, sizeof buffer, &numRead, NULL)) return;
const std::wstring first(buffer, numRead - 2);
if (!ReadConsoleW(stdIn, buffer, sizeof buffer, &numRead, NULL)) return;
const std::wstring second(buffer, numRead);
const std::wstring result = first + second;
const HANDLE stdOut = GetStdHandle(STD_OUTPUT_HANDLE);
DWORD numWritten = 0;
WriteConsoleW(stdOut, result.c_str(), result.size(), &numWritten, NULL);
}
-
Edit 1: I've added a method based on
conio
. -
Edit 2: I've messed around with
_O_U16TEXT
a bit as described in Michael Kaplan's blog, but that seemingly only hadwgets
interpret the (8-bit) data fromReadFile
as UTF-16. I'll investigate this a bit further during the weekend.