#pragma once

#include <cstdint>
#include <string>

namespace roro::utf8 {

inline bool isContinuation(unsigned char c) { return (c & 0xC0) == 0x80; }

inline std::string encode(uint32_t cp) {
    std::string out;
    if (cp < 0x80) {
        out += static_cast<char>(cp);
    } else if (cp < 0x800) {
        out += static_cast<char>(0xC0 | (cp >> 6));
        out += static_cast<char>(0x80 | (cp & 0x3F));
    } else if (cp < 0x10000) {
        out += static_cast<char>(0xE0 | (cp >> 12));
        out += static_cast<char>(0x80 | ((cp >> 6) & 0x3F));
        out += static_cast<char>(0x80 | (cp & 0x3F));
    } else {
        out += static_cast<char>(0xF0 | (cp >> 18));
        out += static_cast<char>(0x80 | ((cp >> 12) & 0x3F));
        out += static_cast<char>(0x80 | ((cp >> 6) & 0x3F));
        out += static_cast<char>(0x80 | (cp & 0x3F));
    }
    return out;
}

// Byte index of the character start before / after `pos`.
inline size_t previous(const std::string& s, size_t pos) {
    if (pos == 0) return 0;
    do pos--;
    while (pos > 0 && isContinuation(static_cast<unsigned char>(s[pos])));
    return pos;
}

inline size_t next(const std::string& s, size_t pos) {
    if (pos >= s.size()) return s.size();
    do pos++;
    while (pos < s.size() && isContinuation(static_cast<unsigned char>(s[pos])));
    return pos;
}

// Longest prefix of at most `maxBytes` that doesn't cut a character.
inline size_t clampToBoundary(const std::string& s, size_t maxBytes) {
    if (s.size() <= maxBytes) return s.size();
    size_t pos = maxBytes;
    while (pos > 0 && isContinuation(static_cast<unsigned char>(s[pos]))) pos--;
    return pos;
}

}  // namespace roro::utf8