Function unicode_cpt_from_utf8

external/llama_tokenizer/unicode.cpp:30–65

}

uint32_t unicode_cpt_from_utf8(const std::string & utf8, size_t & offset) {
    assert(offset < utf8.size());
    if (!(utf8[offset + 0] & 0x80)) {
        auto result = utf8[offset + 0];
        offset += 1;
        return result;
    }
    if (!(utf8[offset + 0] & 0x40)) {
        throw std::invalid_argument("invalid character");
    }
    if (!(utf8[offset + 0] & 0x20)) {
        if (offset + 1 >= utf8.size() || ! ((utf8[offset + 1] & 0xc0) == 0x80)) {
            throw std::invalid_argument("invalid character");
        }
        auto result = ((utf8[offset + 0] & 0x1f) << 6) | (utf8[offset + 1] & 0x3f);
        offset += 2;
        return result;
    }
    if (!(utf8[offset + 0] & 0x10)) {
        if (offset + 2 >= utf8.size() || ! ((utf8[offset + 1] & 0xc0) == 0x80) || ! ((utf8[offset + 2] & 0xc0) == 0x80)) {
            throw std::invalid_argument("invalid character");
        }
        auto result = ((utf8[offset + 0] & 0x0f) << 12) | ((utf8[offset + 1] & 0x3f) << 6) | (utf8[offset + 2] & 0x3f);
        offset += 3;
        return result;
    }
    if (!(utf8[offset + 0] & 0x08)) {
        if (offset + 3 >= utf8.size() || ! ((utf8[offset + 1] & 0xc0) == 0x80) || ! ((utf8[offset + 2] & 0xc0) == 0x80) || !((utf8[offset + 3] & 0xc0) == 0x80)) {
            throw std::invalid_argument("invalid character");
        }
        auto result = ((utf8[offset + 0] & 0x07) << 18) | ((utf8[offset + 1] & 0x3f) << 12) | ((utf8[offset + 2] & 0x3f) << 6) | (utf8[offset + 3] & 0x3f);
        offset += 4;
        return result;
    }
    throw std::invalid_argument("failed to convert utf8 to codepoint");
}

//static std::vector<uint16_t> unicode_cpt_to_utf16(uint32_t cpt) {
//    std::vector<uint16_t> result;