"""Integration tests for the FastAPI app."""
import pytest
from fastapi.testclient import TestClient

from extractor import set_person_matcher
from person_matcher import PersonMatcher

_TEST_PERSONS = [
    ("Clara", "Cram"),
    ("Herbert", "Cram"),
    ("Eugenie", "de Gruyter"),
    ("Walter", "de Gruyter"),
    ("Marie", "Cram"),
    ("Anita", "Wöhler"),
]


@pytest.fixture(scope="session")
def client():
    # Pre-seed the matcher so the lifespan doesn't overwrite it with an empty one.
    m = PersonMatcher()
    m.load(_TEST_PERSONS)
    set_person_matcher(m)
    from main import app
    with TestClient(app) as c:
        yield c


def test_health(client):
    r = client.get("/health")
    assert r.status_code == 200
    assert r.json()["status"] == "ok"
    assert r.json()["persons_loaded"] > 0


def test_parse_returns_200_with_all_fields(client):
    r = client.post("/parse", json={"query": "Briefe vor 1920", "lang": "de"})
    assert r.status_code == 200
    d = r.json()
    assert "personNames" in d
    assert d["personRole"] in ("sender", "receiver", "any")
    assert "dateFrom" in d
    assert "dateTo" in d
    assert "keywords" in d
    assert d["rawQuery"] == "Briefe vor 1920"
    assert d["dateTo"] == "1920-12-31"


def test_parse_person_with_date(client):
    r = client.post(
        "/parse",
        json={"query": "Briefe von Clara Cram an Walter de Gruyter im Jahr 1920", "lang": "de"},
    )
    assert r.status_code == 200
    d = r.json()
    assert "Clara Cram" in d["personNames"]
    assert "Walter de Gruyter" in d["personNames"]
    assert d["dateFrom"] == "1920-01-01"
    assert d["dateTo"] == "1920-12-31"


def test_parse_unknown_lang_returns_422(client):
    r = client.post("/parse", json={"query": "test", "lang": "fr"})
    assert r.status_code == 422


def test_parse_missing_query_returns_422(client):
    r = client.post("/parse", json={"lang": "de"})
    assert r.status_code == 422


def test_parse_all_languages(client):
    cases = [
        ("de", "Briefe vor 1920"),
        ("en", "letters before 1920"),
        ("es", "cartas antes de 1920"),
    ]
    for lang, query in cases:
        r = client.post("/parse", json={"query": query, "lang": lang})
        assert r.status_code == 200, f"Failed for lang={lang}"
        assert r.json()["dateTo"] == "1920-12-31", f"Wrong dateTo for lang={lang}"


def test_fuzzy_threshold_valid_range():
    from main import _parse_fuzzy_threshold
    assert _parse_fuzzy_threshold("80") == 80
    assert _parse_fuzzy_threshold("0") == 0
    assert _parse_fuzzy_threshold("100") == 100


def test_fuzzy_threshold_out_of_range_raises():
    from main import _parse_fuzzy_threshold
    with pytest.raises(ValueError):
        _parse_fuzzy_threshold("101")
    with pytest.raises(ValueError):
        _parse_fuzzy_threshold("-1")
    with pytest.raises(ValueError):
        _parse_fuzzy_threshold("abc")


def test_parse_exceeds_max_length_returns_422(client):
    r = client.post("/parse", json={"query": "a" * 501, "lang": "de"})
    assert r.status_code == 422


def test_parse_internal_exception_does_not_leak_detail(client, monkeypatch):
    """500 errors must return generic message — never expose internal details."""
    import main as main_module

    def _boom(query, lang):
        raise RuntimeError("postgresql://archive_user:s3cr3t@db:5432/family_archive_db")

    monkeypatch.setattr(main_module, "extract", _boom)
    r = client.post("/parse", json={"query": "test", "lang": "de"})
    assert r.status_code == 500
    assert "s3cr3t" not in r.text
    assert r.json()["detail"] == "internal error"