How to print Unicode character in C++?

This code works in Linux (C++11, geany, g++ 7.4.0):

#include <iostream>

using namespace std;


int utf8_to_unicode(string utf8_code);
string unicode_to_utf8(int unicode);


int main()
{
    cout << unicode_to_utf8(36) << '\t';
    cout << unicode_to_utf8(162) << '\t';
    cout << unicode_to_utf8(8364) << '\t';
    cout << unicode_to_utf8(128578) << endl;

    cout << unicode_to_utf8(0x24) << '\t';
    cout << unicode_to_utf8(0xa2) << '\t';
    cout << unicode_to_utf8(0x20ac) << '\t';
    cout << unicode_to_utf8(0x1f642) << endl;

    cout << utf8_to_unicode("$") << '\t';
    cout << utf8_to_unicode("¢") << '\t';
    cout << utf8_to_unicode("€") << '\t';
    cout << utf8_to_unicode("🙂") << endl;

    cout << utf8_to_unicode("\x24") << '\t';
    cout << utf8_to_unicode("\xc2\xa2") << '\t';
    cout << utf8_to_unicode("\xe2\x82\xac") << '\t';
    cout << utf8_to_unicode("\xf0\x9f\x99\x82") << endl;

    return 0;
}


int utf8_to_unicode(string utf8_code)
{
    unsigned utf8_size = utf8_code.length();
    int unicode = 0;

    for (unsigned p=0; p<utf8_size; ++p)
    {
        int bit_count = (p? 6: 8 - utf8_size - (utf8_size == 1? 0: 1)),
            shift = (p < utf8_size - 1? (6*(utf8_size - p - 1)): 0);

        for (int k=0; k<bit_count; ++k)
            unicode += ((utf8_code[p] & (1 << k)) << shift);
    }

    return unicode;
}


string unicode_to_utf8(int unicode)
{
    string s;

    if (unicode>=0 and unicode <= 0x7f)  // 7F(16) = 127(10)
    {
        s = static_cast<char>(unicode);

        return s;
    }
    else if (unicode <= 0x7ff)  // 7FF(16) = 2047(10)
    {
        unsigned char c1 = 192, c2 = 128;

        for (int k=0; k<11; ++k)
        {
            if (k < 6)  c2 |= (unicode % 64) & (1 << k);
            else c1 |= (unicode >> 6) & (1 << (k - 6));
        }

        s = c1;    s += c2;

        return s;
    }
    else if (unicode <= 0xffff)  // FFFF(16) = 65535(10)
    {
        unsigned char c1 = 224, c2 = 128, c3 = 128;

        for (int k=0; k<16; ++k)
        {
            if (k < 6)  c3 |= (unicode % 64) & (1 << k);
            else if (k < 12) c2 |= (unicode >> 6) & (1 << (k - 6));
            else c1 |= (unicode >> 12) & (1 << (k - 12));
        }

        s = c1;    s += c2;    s += c3;

        return s;
    }
    else if (unicode <= 0x1fffff)  // 1FFFFF(16) = 2097151(10)
    {
        unsigned char c1 = 240, c2 = 128, c3 = 128, c4 = 128;

        for (int k=0; k<21; ++k)
        {
            if (k < 6)  c4 |= (unicode % 64) & (1 << k);
            else if (k < 12) c3 |= (unicode >> 6) & (1 << (k - 6));
            else if (k < 18) c2 |= (unicode >> 12) & (1 << (k - 12));
            else c1 |= (unicode >> 18) & (1 << (k - 18));
        }

        s = c1;    s += c2;    s += c3;    s += c4;

        return s;
    }
    else if (unicode <= 0x3ffffff)  // 3FFFFFF(16) = 67108863(10)
    {
        ;  // actually, there are no 5-bytes unicodes
    }
    else if (unicode <= 0x7fffffff)  // 7FFFFFFF(16) = 2147483647(10)
    {
        ;  // actually, there are no 6-bytes unicodes
    }
    else  ;  // incorrect unicode (< 0 or > 2147483647)

    return "";
}

More:

• https://sites.google.com/view/technik-informatyk-nysa/porady/porady-c-cpp#h.p_lz0skneGFILy
• https://en.wikipedia.org/wiki/UTF-8

Ultimately, this is completely platform-dependent. Unicode-support is, unfortunately, very poor in Standard C++. For GCC, you will have to make it a narrow string, as they use UTF-8, and Windows wants a wide string, and you must output to wcout.

// GCC
std::cout << "ф";
// Windoze
wcout << L"ф";

When compiling with -std=c++11, one can simply

  const char *s  = u8"\u0444";
  cout << s << endl;

To represent the character you can use Universal Character Names (UCNs). The character 'ф' has the Unicode value U+0444 and so in C++ you could write it '\u0444' or '\U00000444'. Also if the source code encoding supports this character then you can just write it literally in your source code.

// both of these assume that the character can be represented with
// a single char in the execution encoding
char b = '\u0444';
char a = 'ф'; // this line additionally assumes that the source character encoding supports this character

Printing such characters out depends on what you're printing to. If you're printing to a Unix terminal emulator, the terminal emulator is using an encoding that supports this character, and that encoding matches the compiler's execution encoding, then you can do the following:

#include <iostream>

int main() {
    std::cout << "Hello, ф or \u0444!\n";
}

This program does not require that 'ф' can be represented in a single char. On OS X and most any modern Linux install this will work just fine, because the source, execution, and console encodings will all be UTF-8 (which supports all Unicode characters).

Things are harder with Windows and there are different possibilities with different tradeoffs.

Probably the best, if you don't need portable code (you'll be using wchar_t, which should really be avoided on every other platform), is to set the mode of the output file handle to take only UTF-16 data.

#include <iostream>
#include <io.h>
#include <fcntl.h>

int main() {
    _setmode(_fileno(stdout), _O_U16TEXT);
    std::wcout << L"Hello, \u0444!\n";
}

Portable code is more difficult.