"""The four sample texts used by show_numbers.py, compare_tiktoken.py and the widget's presets.

None of them appears in corpus.txt, so the toy tokenizer has never seen them. The Korean sample
was written for this lesson and has not been reviewed by a native speaker.
"""
SAMPLES = {
    "English": (
        "The ferry leaves at nine, so we should pack the bags tonight and walk down to the harbour "
        "early. If the weather turns, the keeper at the hut will know before we do. Tell him we are "
        "coming, and ask whether the bridge is open."
    ),
    "Code": (
        "def average(values):\n"
        "    if not values:\n"
        "        return 0.0\n"
        "    total = 0.0\n"
        "    for value in values:\n"
        "        total += value\n"
        "    return total / len(values)\n"
        "\n"
        "\n"
        "print(average([3, 5, 8]))\n"
    ),
    "Numbers": (
        "Invoice 20260418: 3 items, 1,250.75 total, due 2026-05-02. Readings: 7.25 8.5 9.125 "
        "10.0625 11.03125. Powers of two: 4096 8192 16384 32768 65536. Id 9047215."
    ),
    "Korean": (
        "내일 아침에는 기차를 타고 바닷가에 가서 친구들과 함께 맛있는 생선 요리를 먹을 계획입니다. "
        "날씨가 좋으면 해변을 따라 걷고 저녁에는 시장에서 과일을 사 오겠습니다."
    ),
}