在C++中从UTF-8转换到in 8859-15

Question

我想在C/C++中完成从UTF-8到ISO 8859-15的转换，而不包括额外的库。

我怎样才能做到这一点？

我已经找到了适用于ISO 8859-1的以下代码，但我不知道如何处理ISO 8859-15和ISO 8859-1 (8859-15)之间的差异：

std::string UTF8toISO8859_1(const char * in) {
    std::string out;
    if (in == NULL)
        return out;

    unsigned int codepoint;
    while (*in != 0) {
        unsigned char ch = static_cast<unsigned char>(*in);
        if (ch <= 0x7f)
            codepoint = ch;
        else if (ch <= 0xbf)
            codepoint = (codepoint << 6) | (ch & 0x3f);
        else if (ch <= 0xdf)
            codepoint = ch & 0x1f;
        else if (ch <= 0xef)
            codepoint = ch & 0x0f;
        else
            codepoint = ch & 0x07;
        ++in;
        if (((*in & 0xc0) != 0x80) && (codepoint <= 0x10ffff)) {
            if (codepoint <= 255) {
                out.append(1, static_cast<char>(codepoint));
            }
            else {
                out.append("?");
            }
        }
    }
    return out;
}

Answer 1

我喜欢这个密码。它太短了。大部分代码只处理将多字节序列解码为编码点的问题。一旦解码了代码点，转换到ISO-8859-1非常简单：

• 如果它小于等于255，它也是一个有效的ISO-8859-1字符：out.append(1, static_cast<char>(codepoint));
• 如果没有，则不能用ISO-8859-1表示，而代之以问号：out.append("?");。

因此，为了使其适用于ISO8859-15，需要更多的代码来处理在引入ISO-8859-15时被替换的字符(请参阅比较ISO-8859-1和ISO-8859-15)。不幸的是，它大大增加了代码大小。

下面的代码应该很容易理解。如果这是一个主要问题的话，它可以被优化以获得更好的性能。

std::string UTF8toISO8859_1(const char * in) {
    std::string out;
    if (in == NULL)
        return out;

    unsigned int codepoint;
    while (*in != 0) {
        unsigned char ch = static_cast<unsigned char>(*in);
        if (ch <= 0x7f)
            codepoint = ch;
        else if (ch <= 0xbf)
            codepoint = (codepoint << 6) | (ch & 0x3f);
        else if (ch <= 0xdf)
            codepoint = ch & 0x1f;
        else if (ch <= 0xef)
            codepoint = ch & 0x0f;
        else
            codepoint = ch & 0x07;
        ++in;

        if (((*in & 0xc0) != 0x80) && (codepoint <= 0x10ffff)) {
            // a valid codepoint has been decoded; convert it to ISO-8859-15               
            char outc;
            if (codepoint <= 255) {
                // codepoints up to 255 can be directly converted wit a few exceptions
                if (codepoint != 0xa4 && codepoint != 0xa6 && codepoint != 0xa8
                        && codepoint != 0xb4 && codepoint != 0xb8 && codepoint != 0xbc
                        && codepoint != 0xbd && codepoint != 0xbe) {
                    outc = static_cast<char>(codepoint);
                }
                else {
                    outc = '?';
                }
            }
            else {
                // With a few exceptions, codepoints above 255 cannot be converted
                if (codepoint == 0x20AC) {
                    outc = 0xa4;
                }
                else if (codepoint == 0x0160) {
                    outc = 0xa6;
                }
                else if (codepoint == 0x0161) {
                    outc = 0xa8;
                }
                else if (codepoint == 0x017d) {
                    outc = 0xb4;
                }
                else if (codepoint == 0x017e) {
                    outc = 0xb8;
                }
                else if (codepoint == 0x0152) {
                    outc = 0xbc;
                }
                else if (codepoint == 0x0153) {
                    outc = 0xbd;
                }
                else if (codepoint == 0x0178) {
                    outc = 0xbe;
                }
                else {
                    outc = '?';
                }
            }
            out.append(1, outc);
        }
    }
    return out;
}