"""learner 子包测试：StudyDataBuilder 与各生成器。"""
import pytest

from pl_japanese.learner.builder import StudyDataBuilder
from pl_japanese.learner import generators


# 小型样本词表：覆盖单字多音、熟字训、空拼音等情况
SAMPLE = """\
中|国:ちゅう|ごく:zhong|guo
中|国|人:ちゅう|ごく|じん:zhong|guo|ren
生:せい:sheng
生:なま:sheng
学|生:がく|せい:xue|sheng
今日:きょう:jinri
一|人:ひと|り:yi|ren
"""


@pytest.fixture
def sample_vocab(tmp_path):
    p = tmp_path / "vocab.txt"
    p.write_text(SAMPLE, encoding="utf-8", newline="\n")
    return p


@pytest.fixture
def builder(sample_vocab):
    return StudyDataBuilder(str(sample_vocab))


def test_builder_loads(builder):
    st = builder.stats()
    assert st["loaded"] > 0
    assert st["skipped"] == 0


def test_pinyin_reverse_lookup(builder):
    # 单字 中 读 ちゅう，拼音应为 zhong
    assert builder.pinyin_for("中", "ちゅう") == "zhong"
    assert builder.pinyin_for("生", "せい") == "sheng"
    assert builder.pinyin_for("生", "なま") == "sheng"


def test_single_only_excludes_multichar(builder):
    single = builder.kanji_readings(single_only=True)
    # 熟字训 今日 不应出现在单字里
    assert "今日" not in single
    assert "中" in single
    assert "生" in single


def test_jukujikun_captures_multichar(builder):
    juku = builder.jukujikun()
    assert "今日" in juku
    assert "きょう" in juku["今日"]
    # 单字不应出现在熟字训里
    assert "中" not in juku


def test_multi_reading_kanji(builder):
    single = builder.kanji_readings(single_only=True)
    # 生 有两种读音 せい / なま
    assert set(single["生"].keys()) == {"せい", "なま"}


def test_all_generators_produce_files(builder, tmp_path):
    out = tmp_path / "out"
    out.mkdir()
    for name, (func, _desc) in generators.GENERATORS.items():
        path = func(builder, out)
        assert path.exists(), f"{name} 未生成文件"
        assert path.stat().st_size > 0, f"{name} 生成了空文件"


def test_anki_deck_is_tsv(builder, tmp_path):
    out = tmp_path / "out"
    out.mkdir()
    path = generators.gen_anki_deck(builder, out)
    lines = path.read_text(encoding="utf-8").strip().split("\n")
    assert len(lines) > 0
    for line in lines:
        assert "\t" in line, "Anki 卡片应为 TAB 分隔"
        front, back = line.split("\t", 1)
        assert front  # 正面非空


def test_missing_vocab_raises(tmp_path):
    with pytest.raises(FileNotFoundError):
        StudyDataBuilder(str(tmp_path / "nonexistent.txt"))