Function sam3_init_byte_encoder

sam3.cpp:1144–1168

Maps each byte 0-255 to a unique unicode character (as UTF-8 string). Printable bytes map to themselves; non-printable bytes map to U+0100..U+0143.

// Maps each byte 0-255 to a unique unicode character (as UTF-8 string).
// Printable bytes map to themselves; non-printable bytes map to U+0100..U+0143.
static void sam3_init_byte_encoder(std::unordered_map<uint8_t, std::string>& enc) {
    // Collect printable byte values
    std::vector<int> bs;
    for (int i = 33; i <= 126; ++i) bs.push_back(i);
    for (int i = 161; i <= 172; ++i) bs.push_back(i);
    for (int i = 174; i <= 255; ++i) bs.push_back(i);

    // Corresponding codepoints (printable → identity)
    std::vector<int> cs(bs.begin(), bs.end());

    // Non-printable bytes get codepoints starting at 256
    int n = 0;
    for (int b = 0; b < 256; ++b) {
        if (std::find(bs.begin(), bs.end(), b) == bs.end()) {
            bs.push_back(b);
            cs.push_back(256 + n);
            n++;
        }
    }

    enc.clear();
    for (size_t i = 0; i < bs.size(); ++i) {
        enc[(uint8_t)bs[i]] = sam3_codepoint_to_utf8(cs[i]);
    }
}

/*
** ── Merge key helper ─────────────────────────────────────────────────────────