使用 C++ 将 UTF-8 字符转换为最接近的等效 ASCII 字符（不带 winapi）

Question

有没有人有一个代码片段可以转换至少最常见的欧洲语言字符？例如：

测试

作为 UTF-8 编码的字符串（即十六进制字节：74 65 73 74 c3 a1 c3 a9 6e 0）

到

睾丸

（我想使用 c/c++ 和 std，或小的跨平台库）

Answer 1

这是处理将字符从 ISO-8859-1 范围转换为 ascii 的代码。替换字符用于 ascii 之外的所有其他内容。

#include <codecvt>
#include <array>
#include <string>

#include <iostream>

constexpr char const *rc = "?"; // replacement_char

// table mapping ISO-8859-1 characters to similar ASCII characters
std::array<char const *,96> conversions = {{
   " ",  "!","c","L", rc,"Y", "|","S", rc,"C","a","<<",   rc,  "-",  "R", "-",
    rc,"+/-","2","3","'","u", "P",".",",","1","o",">>","1/4","1/2","3/4", "?", 
   "A",  "A","A","A","A","A","AE","C","E","E","E", "E",  "I",  "I",  "I", "I",
   "D",  "N","O","O","O","O", "O","*","0","U","U", "U",  "U",  "Y",  "P","ss",
   "a",  "a","a","a","a","a","ae","c","e","e","e", "e",  "i",  "i",  "i", "i",
   "d",  "n","o","o","o","o", "o","/","0","u","u", "u",  "u",  "y",  "p", "y"    
}};

template <class Facet>
class usable_facet : public Facet {
public:
    using Facet::Facet;
    ~usable_facet() {}
};

std::string to_ascii(std::string const &utf8) {
    std::wstring_convert<usable_facet<std::codecvt<char32_t,char,std::mbstate_t>>,
                         char32_t> convert;
    std::u32string utf32 = convert.from_bytes(utf8);

    std::string ascii;
    for (char32_t c : utf32) {
        if (c<=U'\u007F')
            ascii.push_back(static_cast<char>(c));
        else if (U'\u00A0'<=c && c<=U'\u00FF')
            ascii.append(conversions[c - U'\u00A0']);
        else
            ascii.append(rc);
    }
    return ascii;
}

int main() {
    std::cout << to_ascii(u8"testáén\n");
}