使用C ++将越南语字符编码为USASCII，ISO88591，UTF8，UTF16BE，UTF16LE，UTF16

Question

我已经编辑了我的帖子。当前，我正在尝试对用户的输入字符串进行编码，然后将其转换为每种编码格式。我可以使用Unicode完美地做到这一点，而且我认为输入String的格式为UTF-8。如果我的inputString是“ Hello”。但是，当我尝试输入“Tôi”之类的字符串时，我不知道该怎么做。

    enum Encodings { USASCII, ISO88591, UTF8, UTF16BE, UTF16LE, UTF16, BIN, OCT, HEX };

    switch (Encodings)
        {
        case USASCII:
            ASCIIToHex(inputString, &ascii); //hello output 48656C6C6F
            return new ByteField(ascii.c_str());
        case ISO88591:
            ASCIIToHex(inputString, &ascii);//hello output 48656C6C6F
                                              //tôi output 54F469
            return new ByteField(ascii.c_str());
        case UTF8:
            ASCIIToHex(inputString, &ascii);//hello output 48656C6C6F
                                           //tôi output 54C3B469
            return new ByteField(ascii.c_str());
        case UTF16BE:
            ToUTF16(inputString, &ascii, Encodings);//hello output 00480065006C006C006F
                                                    //tôi output 005400F40069
            return new ByteField(ascii.c_str());
        case UTF16:
        ToUTF16(inputString, &ascii, Encodings);//hello output FEFF00480065006C006C006F
                                                //tôi output FEFF005400F40069
            return new ByteField(ascii.c_str());
        case UTF16LE:
            ToUTF16(inputString, &ascii, Encodings);//hello output 480065006C006C006F00
                                                    //tôi output 5400F4006900
            return new ByteField(ascii.c_str());
        }

void StringUtilLib::ASCIIToHex(std::string s, std::string * result)
{
    int n = s.length();
    for (int i = 0; i < n; i++)
    {
        unsigned char c = s[i];
        long val = long(c);
        std::string bin = "";
        while (val > 0)
        {
            (val % 2) ? bin.push_back('1') :
                bin.push_back('0');
            val /= 2;
        }
        reverse(bin.begin(), bin.end());
        result->append(ConvertBinToHex(bin));
    }
}

std::string ToUTF16(std::string s, std::string * result, int encodings) {
    int n = s.length();
    if (encodings == UTF16) {
        result->append("FEFF");
    }
    for (int i = 0; i < n; i++)
    {
        int val = int(s[i]);
        std::string bin = "";
        while (val > 0)
        {
            (val % 2) ? bin.push_back('1') :
                bin.push_back('0');
            val /= 2;
        }
        reverse(bin.begin(), bin.end());
        if (encodings == UTF16 || encodings == UTF16BE) {
            result->append("00" + ConvertBinToHex(bin));
        }
        if (encodings == UTF16LE) {
            result->append(ConvertBinToHex(bin) + "00");
        }

    }
}

std::string ConvertBinToHex(std::string str) {
    long long temp = atoll(str.c_str());
    int dec_value = 0;
    int base = 1;
    int i = 0;
    while (temp) {
        int last_digit = temp % 10;
        temp = temp / 10;
        dec_value += last_digit * base;
        base = base * 2;
    }
    char hexaDeciNum[10];
    while (dec_value != 0)
    {
        int temp = 0;
        temp = dec_value % 16;
        if (temp < 10)
        {
            hexaDeciNum[i] = temp + 48;
            i++;
        }
        else
        {
            hexaDeciNum[i] = temp + 55;
            i++;
        }
        dec_value = dec_value / 16;
    }
    str.clear();
    for (int j = i - 1; j >= 0; j--) {
        str = str + hexaDeciNum[j];
    }
    return str;
}

Answer 1

另一答案

使用C ++将越南语字符编码为USASCII，ISO88591，UTF8，UTF16BE，UTF16LE，UTF16

编辑：