5

是否有使用 std::locale 和 C++ 流功能的 mbsrtowcs 和 wcsrtombs 类型函数的 C++ 等效项？

我试图找出使用标准库在 std::string 和 std::wstring 之间来回转换的最佳方法。似乎 std::locale 几乎可以做到这一点，但我对一些细节或它可能有什么限制有点不确定。

一些细节：我在 Linux 上，它使用 utf-8 作为本机编码。我想从 utf-8 std::string 转到 std::wstring 并返回而不会丢失信息。

我认为 Windows 上的语言环境可能存在一些限制，但我并不特别担心它们。只要答案适用于 Linux 并且除了 libstdc++ 之外没有依赖项，即没有提升依赖项，我很高兴。

链接到背景信息表示赞赏。

注意：似乎有些混乱。多个 char 可以表示 UTF-8 中的单个字符，因此在从 wchar_t 转换为 char 时不考虑这一点的函数将不起作用。

4

2 回答 2

3

locale对这项任务来说太过分了——UTF-8 和 UTF-16 可以通过简单的二进制转换来回转换。这是一些代码，基于我对之前问题的回答。

std::string UTF16to8(const wchar_t * in)
{
    std::string out;
    if (in == NULL)
        return out;

    unsigned int codepoint = 0;
    for (in;  *in != 0;  ++in)
    {
        if (*in >= 0xd800 && *in <= 0xdbff)
            codepoint = ((*in - 0xd800) << 10) + 0x10000;
        else
        {
            if (*in >= 0xdc00 && *in <= 0xdfff)
                codepoint |= *in - 0xdc00;
            else
                codepoint = *in;

            if (codepoint <= 0x7f)
                out.append(1, static_cast<char>(codepoint));
            else if (codepoint <= 0x7ff)
            {
                out.append(1, static_cast<char>(0xc0 | ((codepoint >> 6) & 0x1f)));
                out.append(1, static_cast<char>(0x80 | (codepoint & 0x3f)));
            }
            else if (codepoint <= 0xffff)
            {
                out.append(1, static_cast<char>(0xe0 | ((codepoint >> 12) & 0x0f)));
                out.append(1, static_cast<char>(0x80 | ((codepoint >> 6) & 0x3f)));
                out.append(1, static_cast<char>(0x80 | (codepoint & 0x3f)));
            }
            else
            {
                out.append(1, static_cast<char>(0xf0 | ((codepoint >> 18) & 0x07)));
                out.append(1, static_cast<char>(0x80 | ((codepoint >> 12) & 0x3f)));
                out.append(1, static_cast<char>(0x80 | ((codepoint >> 6) & 0x3f)));
                out.append(1, static_cast<char>(0x80 | (codepoint & 0x3f)));
            }
            codepoint = 0;
        }
    }
    return out;
}

std::wstring UTF8to16(const char * in)
{
    std::wstring out;
    if (in == NULL)
        return out;

    unsigned int codepoint = 0;
    int following = 0;
    for (in;  *in != 0;  ++in)
    {
        unsigned char ch = *in;
        if (ch <= 0x7f)
        {
            codepoint = ch;
            following = 0;
        }
        else if (ch <= 0xbf)
        {
            if (following > 0)
            {
                codepoint = (codepoint << 6) | (ch & 0x3f);
                --following;
            }
        }
        else if (ch <= 0xdf)
        {
            codepoint = ch & 0x1f;
            following = 1;
        }
        else if (ch <= 0xef)
        {
            codepoint = ch & 0x0f;
            following = 2;
        }
        else
        {
            codepoint = ch & 0x07;
            following = 3;
        }
        if (following == 0)
        {
            if (codepoint > 0xffff)
            {
                out.append(1, static_cast<wchar_t>(0xd800 + (codepoint >> 10)));
                out.append(1, static_cast<wchar_t>(0xdc00 + (codepoint & 0x03ff)));
            }
            else
                out.append(1, static_cast<wchar_t>(codepoint));
            codepoint = 0;
        }
    }
    return out;
}

如果您的 wchar_t 是 32 位而不是 16 位，这是一个版本（未经测试）。

std::string UTF32to8(const wchar_t * in)
{
    assert(sizeof(wchar_t) >= 4);
    std::string out;
    if (in == NULL)
        return out;

    for (in;  *in != 0;  ++in)
    {
        unsigned int codepoint = *in;

        if (codepoint <= 0x7f)
            out.append(1, static_cast<char>(codepoint));
        else if (codepoint <= 0x7ff)
        {
            out.append(1, static_cast<char>(0xc0 | ((codepoint >> 6) & 0x1f)));
            out.append(1, static_cast<char>(0x80 | (codepoint & 0x3f)));
        }
        else if (codepoint <= 0xffff)
        {
            out.append(1, static_cast<char>(0xe0 | ((codepoint >> 12) & 0x0f)));
            out.append(1, static_cast<char>(0x80 | ((codepoint >> 6) & 0x3f)));
            out.append(1, static_cast<char>(0x80 | (codepoint & 0x3f)));
        }
        else
        {
            out.append(1, static_cast<char>(0xf0 | ((codepoint >> 18) & 0x07)));
            out.append(1, static_cast<char>(0x80 | ((codepoint >> 12) & 0x3f)));
            out.append(1, static_cast<char>(0x80 | ((codepoint >> 6) & 0x3f)));
            out.append(1, static_cast<char>(0x80 | (codepoint & 0x3f)));
        }
    }
    return out;
}

std::wstring UTF8to32(const char * in)
{
    assert(sizeof(wchar_t) >= 4);
    std::wstring out;
    if (in == NULL)
        return out;

    wchar_t codepoint = 0;
    int following = 0;
    for (in;  *in != 0;  ++in)
    {
        unsigned char ch = *in;
        if (ch <= 0x7f)
        {
            codepoint = ch;
            following = 0;
        }
        else if (ch <= 0xbf)
        {
            if (following > 0)
            {
                codepoint = (codepoint << 6) | (ch & 0x3f);
                --following;
            }
        }
        else if (ch <= 0xdf)
        {
            codepoint = ch & 0x1f;
            following = 1;
        }
        else if (ch <= 0xef)
        {
            codepoint = ch & 0x0f;
            following = 2;
        }
        else
        {
            codepoint = ch & 0x07;
            following = 3;
        }
        if (following == 0)
        {
            out.append(1, codepoint);
            codepoint = 0;
        }
    }
    return out;
}
于 2010-09-28T01:13:28.977 回答
1

您是否尝试过创建一些简单的功能？

std::wstring StringToWString(const std::string& src)
{
 std::wstring str(src.length(),L' ');
 std::copy(src.begin(), src.end(), str.begin());
 return str; 
}


std::string WStringToString(const std::wstring& src)
{
 std::string str(src.length(), ' ');
 std::copy(src.begin(), src.end(), str.begin());
 return str; 
}

void main()
{
 string s1 = "Hello World!";
 wstring s2 = StringToWString(s1);
 s1 = WStringToString(s2);
}
于 2010-09-28T00:56:52.403 回答