从 UTF-8 转换为 unicode C++

2022-01-07 00:00:00 character-encoding c++

如何在 c++ 应用程序中转换 ú，其中应用程序接收字符为 UTF-8 编码 %C3%BA 并将其存储为 unicode 等效 %FA.我只想知道我将如何编写代码来执行此编码过程

How do I convert ú within a c++ application where the application receives the character as UTF-8 encoding %C3%BA and store it as the unicode equivalent %FA. I just want to know how I would go about writing code to perform this encoding process

推荐答案

我昨天刚刚写了一些代码来做到这一点...

I just wrote some code to do this yesterday...

我并不是说这是做到这一点的完美"方式，但它似乎适用于我运行过的所有测试用例(我为此编写了两个方向).

I'm not saying this is the "perfect" way to do this, but it appears to work for all testcases I've run through it (I wrote both directions for that purpose).

我会让你把 "%NN" 转换成一个整数值.

I'll leave it to you to translate "%NN" to an integer value.

#include <iostream>
#include <deque>

std::deque<int> unicode_to_utf8(int charcode)
{
    std::deque<int> d;
    if (charcode < 128)
    {
        d.push_back(charcode);
    }
    else
    {
        int first_bits = 6; 
        const int other_bits = 6;
        int first_val = 0xC0;
        int t = 0;
        while (charcode >= (1 << first_bits))
        {
            {
                t = 128 | (charcode & ((1 << other_bits)-1));
                charcode >>= other_bits;
                first_val |= 1 << (first_bits);
                first_bits--;
            }
            d.push_front(t);
        }
        t = first_val | charcode;
        d.push_front(t);
    }
    return d;
}


int utf8_to_unicode(std::deque<int> &coded)
{
    int charcode = 0;
    int t = coded.front();
    coded.pop_front();
    if (t < 128)
    {
        return t;
    }
    int high_bit_mask = (1 << 6) -1;
    int high_bit_shift = 0;
    int total_bits = 0;
    const int other_bits = 6;
    while((t & 0xC0) == 0xC0)
    {
        t <<= 1;
        t &= 0xff;
        total_bits += 6;
        high_bit_mask >>= 1; 
        high_bit_shift++;
        charcode <<= other_bits;
        charcode |= coded.front() & ((1 << other_bits)-1);
        coded.pop_front();
    } 
    charcode |= ((t >> high_bit_shift) & high_bit_mask) << total_bits;
    return charcode;
}

int main()
{
    int charcode; 

    for(;;)
    {
        std::cout << "Enter unicode value:" << std::endl;
        std::cin >> charcode; 
        auto x = unicode_to_utf8(charcode);
        for(auto c : x)
        {
            std::cout << "\x" << std::hex << c << " ";
        }
        std::cout << std::endl;
        int c = utf8_to_unicode(x);
        std::cout << "reversed:" << std::dec << c << std::hex << " in hex:" << c << std::endl;
    }
}

相关文章