mariri le larili

#include <iostream>
#include <string>
#include <vector>

// Convertit un codepoint Unicode → UTF-8
std::string utf8_from_codepoint(uint32_t cp) {
    std::string out;

    if (cp <= 0x7F) {
        out.push_back(cp);
    } 
    else if (cp <= 0x7FF) {
        out.push_back(0xC0 | (cp >> 6));
        out.push_back(0x80 | (cp & 0x3F));
    }
    else if (cp <= 0xFFFF) {
        out.push_back(0xE0 | (cp >> 12));
        out.push_back(0x80 | ((cp >> 6) & 0x3F));
        out.push_back(0x80 | (cp & 0x3F));
    }
    else {
        out.push_back(0xF0 | (cp >> 18));
        out.push_back(0x80 | ((cp >> 12) & 0x3F));
        out.push_back(0x80 | ((cp >> 6) & 0x3F));
        out.push_back(0x80 | (cp & 0x3F));
    }

    return out;
}

int main() {
    std::vector<uint32_t> codepoints;

    // Remplir la liste de tous les codepoints Unicode valides
    for (uint32_t cp = 0; cp <= 0x10FFFF; cp++) {
        // sauter les surrogates UTF-16 (non-caractères)
        if (cp >= 0xD800 && cp <= 0xDFFF) continue;
        codepoints.push_back(cp);
    }

    std::cout << "Total de codepoints valides: " << codepoints.size() << "\n";

    // Exemple: accéder à un index
    size_t index = 5000;
    if (index < codepoints.size()) {
        uint32_t cp = codepoints[index];
        std::string utf8 = utf8_from_codepoint(cp);

        std::cout << "Index = " << index << "\n";
        std::cout << "Codepoint = U+"
                  << std::hex << cp << std::dec << "\n";
        std::cout << "UTF-8 = \"" << utf8 << "\"\n";
    }

    return 0;
}
Créé il y a 1 mois.