siftlode/backend/tests/test_plex_lang.py

"""E5 S6: HU-overlay language serving. When ?lang=hu, the unified library, facets, genre filter and
detail endpoints serve the Hungarian `*_hu` columns (falling back to EN where a row has no HU twin);
?lang=en (the default) serves English. Also covers the imdb_rating IMDb-only / audience-score split.
DB lane (`db` fixture) — skipped without Postgres.
"""

from datetime import datetime, timezone

from fastapi.testclient import TestClient

import app.state as state
from app.auth import current_user
from app.db import get_db
from app.main import app
from app.models import PlexItem, PlexLibrary, User


def _seed(db):
    """One EN movie library with a single movie that has both EN and HU metadata, plus a second movie
    that is EN-only (no HU twin) to prove the coalesce fallback."""
    lib = PlexLibrary(plex_key="1", title="Movies", kind="movie", enabled=True)
    db.add(lib)
    db.flush()
    m1 = PlexItem(
        rating_key="m1",
        library_id=lib.id,
        kind="movie",
        title="English Title",
        title_hu="Magyar Cím",
        summary="English summary.",
        summary_hu="Magyar összefoglaló.",
        genres=["Drama"],
        genres_hu=["Dráma"],
        rating=6.5,
        imdb_rating=None,
        year=2001,
        added_at=datetime(2024, 1, 1, tzinfo=timezone.utc),
        people_enriched_at=datetime(
            2024, 1, 1, tzinfo=timezone.utc
        ),  # serve from row, skip live enrich
    )
    m2 = PlexItem(
        rating_key="m2",
        library_id=lib.id,
        kind="movie",
        title="EN Only",
        genres=["Comedy"],  # no HU twin
        year=2002,
        added_at=datetime(2024, 1, 2, tzinfo=timezone.utc),
        people_enriched_at=datetime(2024, 1, 2, tzinfo=timezone.utc),
    )
    db.add_all([m1, m2])
    user = User(email="plexlang@example.com")
    db.add(user)
    db.commit()
    return user


def _get(db, user, monkeypatch, override_dep, path):
    monkeypatch.setattr(
        state, "_configured_cache", True
    )  # the request gate 503s an unconfigured app
    override_dep(get_db, lambda: db)
    override_dep(current_user, lambda: user)
    client = TestClient(app)  # no context manager: skip lifespan
    return client.get(path)


def _titles(resp):
    return {i["title"] for i in resp.json()["items"]}


def test_library_serves_active_language_titles(db, monkeypatch, override_dep):
    user = _seed(db)
    hu = _get(db, user, monkeypatch, override_dep, "/api/plex/library?scope=movie&lang=hu")
    en = _get(db, user, monkeypatch, override_dep, "/api/plex/library?scope=movie&lang=en")
    # HU serves the twin's Hungarian title; the EN-only row falls back to its English title.
    assert _titles(hu) == {"Magyar Cím", "EN Only"}
    assert _titles(en) == {"English Title", "EN Only"}


def test_facets_vocabulary_is_language_specific(db, monkeypatch, override_dep):
    user = _seed(db)
    hu = _get(db, user, monkeypatch, override_dep, "/api/plex/facets?scope=movie&lang=hu")
    en = _get(db, user, monkeypatch, override_dep, "/api/plex/facets?scope=movie&lang=en")
    hu_genres = {g["value"] for g in hu.json()["genres"]}
    en_genres = {g["value"] for g in en.json()["genres"]}
    assert "Dráma" in hu_genres and "Drama" not in hu_genres
    assert "Drama" in en_genres and "Dráma" not in en_genres


def test_genre_filter_matches_active_language_vocabulary(db, monkeypatch, override_dep):
    user = _seed(db)
    # The HU genre chip filters the HU column; the same string against the EN column matches nothing.
    hit = _get(
        db, user, monkeypatch, override_dep, "/api/plex/library?scope=movie&lang=hu&genres=Dráma"
    )
    miss = _get(
        db, user, monkeypatch, override_dep, "/api/plex/library?scope=movie&lang=en&genres=Dráma"
    )
    assert _titles(hit) == {"Magyar Cím"}
    assert miss.json()["items"] == []


def test_item_detail_language_and_rating_split(db, monkeypatch, override_dep):
    user = _seed(db)
    resp = _get(db, user, monkeypatch, override_dep, "/api/plex/item/m1?lang=hu")
    body = resp.json()
    assert body["title"] == "Magyar Cím"
    assert body["summary"] == "Magyar összefoglaló."
    # imdb_rating is IMDb-only (None here); the audience score is served separately as `rating`.
    assert body["imdb_rating"] is None
    assert body["rating"] == 6.5


def test_hu_search_still_finds_en_only_titles(db, monkeypatch, override_dep):
    user = _seed(db)
    # m2 ("EN Only") has no HU twin, so search_vector_hu carries no title tokens for it. HU-mode search
    # must still match it via the EN vector (vector_match's union) — findable by its English title.
    resp = _get(db, user, monkeypatch, override_dep, "/api/plex/library?scope=movie&lang=hu&q=Only")
    assert "EN Only" in _titles(resp)


def test_rating_filter_prefers_imdb_over_audience(db, monkeypatch, override_dep):
    lib = PlexLibrary(plex_key="1", title="Movies", kind="movie", enabled=True)
    db.add(lib)
    db.flush()
    # imdb 8.0 but audience 4.0 → a rating_min of 7 must MATCH (filter the displayed best score,
    # IMDb preferred), where filtering the raw audience column (4.0) would wrongly exclude it.
    db.add(
        PlexItem(
            rating_key="r1",
            library_id=lib.id,
            kind="movie",
            title="High IMDb",
            imdb_rating=8.0,
            rating=4.0,
            year=2001,
            added_at=datetime(2024, 1, 1, tzinfo=timezone.utc),
            people_enriched_at=datetime(2024, 1, 1, tzinfo=timezone.utc),
        )
    )
    user = User(email="rating@example.com")
    db.add(user)
    db.commit()
    hit = _get(db, user, monkeypatch, override_dep, "/api/plex/library?scope=movie&rating_min=7")
    assert "High IMDb" in _titles(hit)
    miss = _get(db, user, monkeypatch, override_dep, "/api/plex/library?scope=movie&rating_min=9")
    assert "High IMDb" not in _titles(miss)