用外文写字的时候好像有问题(法文...)

例如，如果我要求输入 std::string 或 char[] 像这样:

std::string s;
std::cin>>s;  //if we input the string "café"
std::cout<<s<<std::endl;  //outputs "café"

std::string s="café";
std::cout<<s<<std::endl; //outputs "cafÚ"

最佳答案

简而言之，如果要在 Windows 10(实际上是任何版本的 Windows)上向/从控制台传递/接收 unicode 文本，则需要使用宽字符串、IE、std::wstring。 Windows 本身不支持 UTF-8 编码。这是一个基本的操作系统限制。

控制台和文件系统访问等基于的整个 Win32 API 仅适用于 UTF-16 编码下的 unicode 字符，并且 Visual Studio 中提供的 C/C++ 运行时不提供任何类型的翻译层来制作这个API UTF-8 兼容。这并不意味着您不能在内部使用 UTF-8 编码，只是意味着当您使用 Win32 API 或使用它的 C/C++ 运行时功能时，您需要在 UTF-8 和 UTF 之间进行转换-16 编码。这很糟糕，但这正是我们现在所处的位置。

有些人可能会指导您使用一系列技巧，使控制台能够使用 UTF-8。不要走这条路，你会遇到很多问题。 Unicode 控制台访问仅正确支持宽字符串。

编辑 : 因为UTF-8/UTF-16 字符串转换很重要，而且C++ 中也没有提供太多帮助，这里是我之前准备的一些转换函数:

///////////////////////////////////////////////////////////////////////////////////////////////////
std::wstring UTF8ToUTF16(const std::string& stringUTF8)
{
    // Convert the encoding of the supplied string
    std::wstring stringUTF16;
    size_t sourceStringPos = 0;
    size_t sourceStringSize = stringUTF8.size();
    stringUTF16.reserve(sourceStringSize);
    while (sourceStringPos < sourceStringSize)
    {
        // Determine the number of code units required for the next character
        static const unsigned int codeUnitCountLookup[] = { 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 3, 4 };
        unsigned int codeUnitCount = codeUnitCountLookup[(unsigned char)stringUTF8[sourceStringPos] >> 4];

        // Ensure that the requested number of code units are left in the source string
        if ((sourceStringPos + codeUnitCount) > sourceStringSize)
        {
            break;
        }

        // Convert the encoding of this character
        switch (codeUnitCount)
        {
        case 1:
        {
            stringUTF16.push_back((wchar_t)stringUTF8[sourceStringPos]);
            break;
        }
        case 2:
        {
            unsigned int unicodeCodePoint = (((unsigned int)stringUTF8[sourceStringPos] & 0x1F) << 6) |
                                            ((unsigned int)stringUTF8[sourceStringPos + 1] & 0x3F);
            stringUTF16.push_back((wchar_t)unicodeCodePoint);
            break;
        }
        case 3:
        {
            unsigned int unicodeCodePoint = (((unsigned int)stringUTF8[sourceStringPos] & 0x0F) << 12) |
                                            (((unsigned int)stringUTF8[sourceStringPos + 1] & 0x3F) << 6) |
                                            ((unsigned int)stringUTF8[sourceStringPos + 2] & 0x3F);
            stringUTF16.push_back((wchar_t)unicodeCodePoint);
            break;
        }
        case 4:
        {
            unsigned int unicodeCodePoint = (((unsigned int)stringUTF8[sourceStringPos] & 0x07) << 18) |
                                            (((unsigned int)stringUTF8[sourceStringPos + 1] & 0x3F) << 12) |
                                            (((unsigned int)stringUTF8[sourceStringPos + 2] & 0x3F) << 6) |
                                            ((unsigned int)stringUTF8[sourceStringPos + 3] & 0x3F);
            wchar_t convertedCodeUnit1 = 0xD800 | (((unicodeCodePoint - 0x10000) >> 10) & 0x03FF);
            wchar_t convertedCodeUnit2 = 0xDC00 | ((unicodeCodePoint - 0x10000) & 0x03FF);
            stringUTF16.push_back(convertedCodeUnit1);
            stringUTF16.push_back(convertedCodeUnit2);
            break;
        }
        }

        // Advance past the converted code units
        sourceStringPos += codeUnitCount;
    }

    // Return the converted string to the caller
    return stringUTF16;
}

///////////////////////////////////////////////////////////////////////////////////////////////////
std::string UTF16ToUTF8(const std::wstring& stringUTF16)
{
    // Convert the encoding of the supplied string
    std::string stringUTF8;
    size_t sourceStringPos = 0;
    size_t sourceStringSize = stringUTF16.size();
    stringUTF8.reserve(sourceStringSize * 2);
    while (sourceStringPos < sourceStringSize)
    {
        // Check if a surrogate pair is used for this character
        bool usesSurrogatePair = (((unsigned int)stringUTF16[sourceStringPos] & 0xF800) == 0xD800);

        // Ensure that the requested number of code units are left in the source string
        if (usesSurrogatePair && ((sourceStringPos + 2) > sourceStringSize))
        {
            break;
        }

        // Decode the character from UTF-16 encoding
        unsigned int unicodeCodePoint;
        if (usesSurrogatePair)
        {
            unicodeCodePoint = 0x10000 + ((((unsigned int)stringUTF16[sourceStringPos] & 0x03FF) << 10) | ((unsigned int)stringUTF16[sourceStringPos + 1] & 0x03FF));
        }
        else
        {
            unicodeCodePoint = (unsigned int)stringUTF16[sourceStringPos];
        }

        // Encode the character into UTF-8 encoding
        if (unicodeCodePoint <= 0x7F)
        {
            stringUTF8.push_back((char)unicodeCodePoint);
        }
        else if (unicodeCodePoint <= 0x07FF)
        {
            char convertedCodeUnit1 = (char)(0xC0 | (unicodeCodePoint >> 6));
            char convertedCodeUnit2 = (char)(0x80 | (unicodeCodePoint & 0x3F));
            stringUTF8.push_back(convertedCodeUnit1);
            stringUTF8.push_back(convertedCodeUnit2);
        }
        else if (unicodeCodePoint <= 0xFFFF)
        {
            char convertedCodeUnit1 = (char)(0xE0 | (unicodeCodePoint >> 12));
            char convertedCodeUnit2 = (char)(0x80 | ((unicodeCodePoint >> 6) & 0x3F));
            char convertedCodeUnit3 = (char)(0x80 | (unicodeCodePoint & 0x3F));
            stringUTF8.push_back(convertedCodeUnit1);
            stringUTF8.push_back(convertedCodeUnit2);
            stringUTF8.push_back(convertedCodeUnit3);
        }
        else
        {
            char convertedCodeUnit1 = (char)(0xF0 | (unicodeCodePoint >> 18));
            char convertedCodeUnit2 = (char)(0x80 | ((unicodeCodePoint >> 12) & 0x3F));
            char convertedCodeUnit3 = (char)(0x80 | ((unicodeCodePoint >> 6) & 0x3F));
            char convertedCodeUnit4 = (char)(0x80 | (unicodeCodePoint & 0x3F));
            stringUTF8.push_back(convertedCodeUnit1);
            stringUTF8.push_back(convertedCodeUnit2);
            stringUTF8.push_back(convertedCodeUnit3);
            stringUTF8.push_back(convertedCodeUnit4);
        }

        // Advance past the converted code units
        sourceStringPos += (usesSurrogatePair) ? 2 : 1;
    }

    // Return the converted string to the caller
    return stringUTF8;
}

关于c++ - C++ 支持的字符，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/41810586/