如何在C++中打印Unicode字符？

Question

我正在尝试打印俄语"ф"(U + 0444 CYRILLIC SMALL LETTER EF)字符,其代码为十进制1092.使用C++,我该如何打印出这个角色？我会想到下面的内容会起作用,但......

int main (){
   wchar_t f = '1060';
   cout << f << endl;
}

Answer 1

要表示字符,您可以使用通用字符名称(UCN).字符'ф'的Unicode值为U + 0444,因此在C++中您可以将其写为'\ u0444'或'\ U00000444'.此外,如果源代码编码支持此字符,那么您可以直接在源代码中编写它.

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

打印此类字符取决于您要打印的内容.如果您要打印到Unix终端仿真器,终端仿真器正在使用支持该字符的编码,并且该编码与编译器的执行编码匹配,那么您可以执行以下操作:

#include <iostream>

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

该程序不要求'ф'可以用单个字符表示.在OS X和大多数现代Linux安装上,这都可以正常工作,因为源代码,执行代码和控制台编码都是UTF-8(支持所有Unicode字符).

Windows的情况比较困难,不同的权衡方式有不同的可能性.

可能是最好的,如果你不需要可移植代码(你将使用wchar_t,这应该在每个其他平台上都应该避免),就是将输出文件句柄的模式设置为仅采用UTF-16数据.

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

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

便携代码更难.

Answer 2

最终,这完全取决于平台.遗憾的是,在标准C++中,Unicode支持非常差.对于GCC,你必须使它成为一个窄字符串,因为它们使用UTF-8,而Windows需要一个宽字符串,你必须输出到wcout.

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

Answer 3

编译时-std=c++11,可以简单地进行编译

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

Answer 4

如果您使用Windows(注意,我们使用的是printf(),而不是cout):

//Save As UTF8 without signature
#include <stdio.h>
#include<windows.h>
int main (){
    SetConsoleOutputCP(65001); 
    printf("?\n");
}

不是Unicode而是工作 - 1251而不是UTF8:

//Save As Windows 1251
#include <iostream>
#include<windows.h>
using namespace std;
int main (){
    SetConsoleOutputCP(1251); 
    cout << "?" << endl;
}

Answer 5

此代码适用于 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 "";
}

更多的：

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