代码之家 › 专栏 › 技术社区 › catphive

使用区域和流的MbSrtoCoS和WcSrRtBs的C++等价物

libstdc++ locale internationalization linux c++

4

catphive · 技术社区 · 14 年前

使用STD:C++和WSRSTOMBS类型的函数是否有C++等价的:

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具有的限制有点怀疑。

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,然后在不丢失信息的情况下返回。

我认为windows上的locale可能有一些限制,但我并不特别关心它们。只要答案在Linux上有效,并且除了libstdc++之外没有其他依赖项,也就是说没有boost依赖项,我就很高兴了。

背景资料链接欣赏。

注意:似乎有些混乱在utf-8中,多个字符可以表示单个字符,因此在从wchar_t转换为char时不考虑此问题的函数将不起作用。

2 回复 | 直到 14 年前

1

3

Community Neeleshkumar S 7 年前

locale 对于这项任务来说是过分了-utf-8和utf-16可以通过简单的二进制转换来回转换。这里有一些代码,基于我的 answer to an earlier question 是的。

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;
}

如果你的wchar是32位而不是16位,这里有一个版本(未测试)。

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;
}

2

1

wengseng 14 年前

你试过创建一些简单的函数吗?

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);
}