siftlode/backend/tests/test_plex_tmdb.py

"""TMDB enrichment engine (E5 S2): the pure parser + persister, guid→tmdb-id resolution, and the
DB-lane batch/serve integration (enrich stamps the watermark + links people; serve_block resolves
recommendations to library rows; the whole thing no-ops without an API key).

The DB tests use the `db` fixture (real Postgres) — skipped when none is reachable."""

from datetime import datetime, timezone

import httpx
import pytest

from app.models import PlexItem, PlexLibrary, PlexPerson, PlexShow
from app.plex import tmdb

# A TMDB /movie/{id}?append_to_response=keywords,credits,recommendations,images,external_ids payload.
MOVIE_PAYLOAD = {
    "id": 238,
    "vote_average": 8.7,
    "vote_count": 20000,
    "budget": 6000000,
    "revenue": 245066411,
    "keywords": {"keywords": [{"id": 1, "name": "mafia"}, {"id": 2, "name": "crime family"}]},
    "credits": {
        "cast": [
            {
                "id": 3084,
                "name": "Marlon Brando",
                "character": "Vito",
                "profile_path": "/a.jpg",
                "order": 0,
            },
            {
                "id": 1158,
                "name": "Al Pacino",
                "character": "Michael",
                "profile_path": "/b.jpg",
                "order": 1,
            },
        ],
        "crew": [
            {
                "id": 1776,
                "name": "Francis Ford Coppola",
                "job": "Director",
                "profile_path": "/c.jpg",
            },
            {"id": 1776, "name": "Francis Ford Coppola", "job": "Writer", "profile_path": "/c.jpg"},
            {"id": 9, "name": "Some Gaffer", "job": "Gaffer"},  # not a key job → dropped
        ],
    },
    "production_companies": [{"name": "Paramount"}, {"name": "Alfran"}],
    "production_countries": [{"iso_3166_1": "US", "name": "United States of America"}],
    "recommendations": {
        "results": [
            {
                "id": 240,
                "title": "The Godfather Part II",
                "poster_path": "/p.jpg",
                "media_type": "movie",
            },
            {"id": 999, "title": "Not In Library", "poster_path": "/q.jpg", "media_type": "movie"},
        ]
    },
    "images": {"backdrops": [{"file_path": "/bd1.jpg"}, {"file_path": "/bd2.jpg"}]},
    "external_ids": {"imdb_id": "tt0068646"},
}

# A TMDB /tv payload: keywords under `results`, aggregate_credits with per-person `jobs`, no budget.
TV_PAYLOAD = {
    "id": 1396,
    "vote_average": 9.0,
    "vote_count": 12000,
    "created_by": [{"id": 66633, "name": "Vince Gilligan", "profile_path": "/vg.jpg"}],
    "keywords": {"results": [{"name": "drugs"}, {"name": "new mexico"}]},
    "aggregate_credits": {
        "cast": [{"id": 17419, "name": "Bryan Cranston"}],
        "crew": [
            {"id": 66633, "name": "Vince Gilligan", "jobs": [{"job": "Executive Producer"}]},
            {"id": 5, "name": "Someone", "jobs": [{"job": "Sound"}]},  # dropped
        ],
    },
    "production_companies": [{"name": "Sony Pictures Television"}],
    "production_countries": [{"name": "United States of America"}],
    "recommendations": {"results": []},
    "images": {"backdrops": []},
}


class FakeTmdb:
    """Stand-in for TmdbClient in the parse/batch tests — no network."""

    def __init__(self, payloads=None, find_map=None):
        self.payloads = payloads or {}  # (media_type, tmdb_id) -> payload
        self.find_map = find_map or {}  # external_id -> /find result

    def fetch(self, tmdb_id, media_type):
        return self.payloads.get((media_type, tmdb_id))

    def find(self, external_id, source):
        return self.find_map.get(external_id)


# ---- pure parse/persist --------------------------------------------------------------------------


def test_parse_movie_pulls_all_fields():
    d = tmdb.parse_tmdb(MOVIE_PAYLOAD, "movie")
    assert d["tmdb_id"] == 238
    assert d["tmdb_rating"] == 8.7
    assert d["tmdb_vote_count"] == 20000
    assert d["budget"] == 6000000
    assert d["revenue"] == 245066411
    assert d["keywords"] == ["mafia", "crime family"]
    assert d["crew"] == [
        {
            "name": "Francis Ford Coppola",
            "job": "Director",
            "tmdb_id": 1776,
            "profile_path": "/c.jpg",
        },
        {
            "name": "Francis Ford Coppola",
            "job": "Writer",
            "tmdb_id": 1776,
            "profile_path": "/c.jpg",
        },
    ]  # the Gaffer is filtered; the two Coppola jobs survive (dedup is by name+job)
    assert d["studios"] == ["Paramount", "Alfran"]
    # E30: the code beside the English name, so the client can name the country in the reader's language.
    assert d["production_countries"] == [{"code": "US", "name": "United States of America"}]
    assert [r["tmdb_id"] for r in d["recommendations"]] == [240, 999]
    assert d["backdrops"] == ["/bd1.jpg", "/bd2.jpg"]
    # cast + crew names → tmdb person ids for the plex_people foundation
    links = {(p["name"], p["tmdb_id"]) for p in d["people"]}
    assert ("Marlon Brando", 3084) in links
    assert ("Al Pacino", 1158) in links
    assert ("Francis Ford Coppola", 1776) in links


def test_parse_tv_uses_aggregate_credits_and_no_money():
    d = tmdb.parse_tmdb(TV_PAYLOAD, "tv")
    assert d["budget"] is None and d["revenue"] is None  # TV has neither
    assert d["keywords"] == ["drugs", "new mexico"]  # from keywords.results
    # The showrunner (created_by → Creator) leads; the aggregate-credits EP follows; the Sound person is
    # filtered; TV jobs are read from jobs[0]. Crew is display-priority ordered (Creator before EP).
    assert d["crew"] == [
        {"name": "Vince Gilligan", "job": "Creator", "tmdb_id": 66633, "profile_path": "/vg.jpg"},
        {
            "name": "Vince Gilligan",
            "job": "Executive Producer",
            "tmdb_id": 66633,
            "profile_path": None,
        },
    ]
    assert d["tmdb_rating"] == 9.0
    assert ("Bryan Cranston", 17419) in {(p["name"], p["tmdb_id"]) for p in d["people"]}


def test_parse_zero_votes_and_money_are_unknown():
    d = tmdb.parse_tmdb(
        {"id": 1, "vote_average": 0.0, "vote_count": 0, "budget": 0, "revenue": 0}, "movie"
    )
    assert d["tmdb_rating"] is None  # 0.0 with no votes is meaningless
    assert d["tmdb_vote_count"] is None
    assert d["budget"] is None and d["revenue"] is None


def test_apply_writes_row_fields_without_touching_plex_owned():
    it = PlexItem(
        rating_key="m1", kind="movie", title="The Godfather", imdb_rating=8.7, full_cast=[{"x": 1}]
    )
    tmdb.apply_tmdb_detail(it, tmdb.parse_tmdb(MOVIE_PAYLOAD, "movie"))
    assert it.tmdb_id == 238
    assert it.budget == 6000000
    assert it.keywords == ["mafia", "crime family"]
    assert it.imdb_rating == 8.7 and it.full_cast == [{"x": 1}]  # Plex-owned, untouched


def test_guid_to_tmdb_id_direct_find_and_bad():
    fake = FakeTmdb(find_map={"tt0068646": {"movie_results": [{"id": 238}], "tv_results": []}})
    assert tmdb.guid_to_tmdb_id("tmdb:238", "movie", fake) == 238
    assert tmdb.guid_to_tmdb_id("imdb:tt0068646", "movie", fake) == 238  # resolved via /find
    assert tmdb.guid_to_tmdb_id("imdb:tt0000000", "movie", fake) is None  # not in find_map
    assert tmdb.guid_to_tmdb_id("tmdb:notanumber", "movie", fake) is None
    assert tmdb.guid_to_tmdb_id(None, "movie", fake) is None
    assert tmdb.guid_to_tmdb_id("local://abc", "movie", fake) is None


def test_guid_to_tmdb_id_tvdb_source_and_tv_media_type():
    # A tvdb guid for a TV item goes through /find and must pick the tv_results list (not movie_results),
    # and a tvdb source maps to the tvdb_id external_source. The media_type branch is the whole point.
    fake = FakeTmdb(find_map={"81189": {"movie_results": [], "tv_results": [{"id": 1396}]}})
    assert tmdb.guid_to_tmdb_id("tvdb:81189", "tv", fake) == 1396
    # The SAME /find result, asked for a movie, reads the (empty) movie_results → None.
    assert tmdb.guid_to_tmdb_id("tvdb:81189", "movie", fake) is None
    # A direct tmdb guid for a tv item is just the int (no /find).
    assert tmdb.guid_to_tmdb_id("tmdb:1396", "tv", fake) == 1396
    # An unknown provider (only imdb/tvdb are /find sources) is unresolvable.
    assert tmdb.guid_to_tmdb_id("plex:abc", "tv", fake) is None


# ---- DB-lane: batch enrich + serve --------------------------------------------------------------


def _lib(db, key="1", kind="movie"):
    lib = PlexLibrary(plex_key=key, title="L", kind=kind, enabled=True)
    db.add(lib)
    db.flush()
    return lib


def test_enrich_batch_persists_stamps_and_links_people(db):
    lib = _lib(db)
    mv = PlexItem(
        rating_key="m1", library_id=lib.id, kind="movie", title="The Godfather", guid="tmdb:238"
    )
    unmatched = PlexItem(
        rating_key="m2", library_id=lib.id, kind="movie", title="Nope", guid="tmdb:777"
    )
    db.add_all([mv, unmatched])
    db.commit()

    fake = FakeTmdb(
        payloads={("movie", 238): MOVIE_PAYLOAD}
    )  # 777 has no payload → definitive no-match
    n = tmdb.enrich_batch(db, fake, 50)
    assert n == 2  # both processed (one matched, one definitively unmatched)

    db.refresh(mv)
    assert mv.tmdb_id == 238
    assert mv.keywords == ["mafia", "crime family"]
    assert mv.revenue == 245066411
    assert mv.tmdb_enriched_at is not None

    db.refresh(unmatched)
    assert unmatched.tmdb_enriched_at is not None  # stamped so it isn't re-fetched every run
    assert unmatched.tmdb_id is None  # but nothing stored

    brando = (
        db.execute(PlexPerson.__table__.select().where(PlexPerson.name == "Marlon Brando"))
        .mappings()
        .first()
    )
    assert brando is not None and brando["tmdb_person_id"] == 3084


def test_serve_block_none_until_enriched_and_resolves_recs(db):
    lib = _lib(db)
    # A recommendation target that IS in our library (guid tmdb:240) → deep-linkable.
    sequel = PlexItem(
        rating_key="m240", library_id=lib.id, kind="movie", title="Part II", guid="tmdb:240"
    )
    fresh = PlexItem(
        rating_key="m1", library_id=lib.id, kind="movie", title="The Godfather", guid="tmdb:238"
    )
    db.add_all([sequel, fresh])
    db.commit()

    assert tmdb.serve_block(db, fresh, lang="en") is None  # not enriched yet

    tmdb.apply_tmdb_detail(fresh, tmdb.parse_tmdb(MOVIE_PAYLOAD, "movie"))
    fresh.tmdb_enriched_at = datetime.now(timezone.utc)
    db.commit()

    block = tmdb.serve_block(db, fresh, lang="en")
    assert block is not None
    assert block["budget"] == 6000000
    assert block["keywords"] == ["mafia", "crime family"]
    recs = {r["tmdb_id"]: r for r in block["recommendations"]}
    assert recs[240]["in_library"] is True and recs[240]["rating_key"] == "m240"
    assert recs[999]["in_library"] is False and recs[999]["rating_key"] is None


def test_get_never_leaks_api_key_in_error_messages(monkeypatch):
    # The api_key rides in the request URL query string, so an error message built from the httpx
    # exception (which embeds that URL) would leak the secret to logs (enrich_batch logs it). Both the
    # HTTP-status and the network error paths must report status/path only — never the key.
    monkeypatch.setattr(
        tmdb.sysconfig, "get_str", lambda d, k: "SECRETKEY" if k == "tmdb_api_key" else "en-US"
    )
    client = tmdb.TmdbClient(None)
    req = httpx.Request(
        "GET", "https://api.themoviedb.org/3/movie/1?api_key=SECRETKEY&language=en-US"
    )

    class _StatusHttp:
        def get(self, url, params=None):
            return httpx.Response(401, request=req)  # non-404 → raise_for_status → HTTPStatusError

        def close(self):
            pass

    client._http = _StatusHttp()
    with pytest.raises(tmdb.TmdbError) as ei:
        client._get("/movie/1")
    assert "SECRETKEY" not in str(ei.value) and "401" in str(ei.value)

    class _NetHttp:
        def get(self, url, params=None):
            raise httpx.ConnectError("connect failed", request=req)

        def close(self):
            pass

    client._http = _NetHttp()
    with pytest.raises(tmdb.TmdbError) as ei2:
        client._get("/movie/1")
    assert "SECRETKEY" not in str(ei2.value)
    client.close()


def test_run_enrich_noops_without_key(db):
    # No tmdb_api_key configured (default "") → clean no-op, never an error.
    out = tmdb.run_enrich(db)
    assert out["enriched"] == 0 and "skipped" in out


class _RaisingTmdb:
    """A client whose fetch raises a transient TmdbError (e.g. a 429), to exercise the retry path."""

    def find(self, external_id, source):
        return None

    def fetch(self, tmdb_id, media_type):
        raise tmdb.TmdbError("429 rate limited")


def test_enrich_batch_transient_error_leaves_watermark_null(db):
    # A transient TmdbError mid-batch must leave the row's tmdb_enriched_at NULL so the next run retries
    # it (unlike a definitive no-match, which stamps the watermark). The row is NOT counted as processed.
    lib = _lib(db)
    mv = PlexItem(
        rating_key="m1", library_id=lib.id, kind="movie", title="Godfather", guid="tmdb:238"
    )
    db.add(mv)
    db.commit()

    n = tmdb.enrich_batch(db, _RaisingTmdb(), 50)
    assert n == 0  # the transient failure is skipped, not processed
    db.refresh(mv)
    assert mv.tmdb_enriched_at is None  # left NULL → retried next run
    assert mv.tmdb_id is None


def test_enrich_batch_skips_shows_without_guid(db):
    lib = _lib(db, key="2", kind="show")
    sh = PlexShow(
        rating_key="s1", library_id=lib.id, title="No Guid Show"
    )  # guid None → not selected
    db.add(sh)
    db.commit()
    assert tmdb.enrich_batch(db, FakeTmdb(), 50) == 0
    db.refresh(sh)
    assert sh.tmdb_enriched_at is None


def test_resolve_library_guids_scopes_to_given_libraries(db):
    # The scoped path (person page) must keep a credit that lives in a NON-scoped library (disabled or an
    # HU-overlay twin) OUT of the result; the unscoped path (detail recs) matches across all libraries;
    # and an explicit empty list skips that media side entirely (distinct from None = match all).
    lib_on = _lib(db, key="on", kind="movie")
    lib_off = _lib(db, key="off", kind="movie")
    m_on = PlexItem(
        rating_key="on1", library_id=lib_on.id, kind="movie", title="In Scope", guid="tmdb:100"
    )
    m_off = PlexItem(
        rating_key="off1", library_id=lib_off.id, kind="movie", title="Out", guid="tmdb:200"
    )
    db.add_all([m_on, m_off])
    db.commit()
    entries = [{"tmdb_id": 100, "media_type": "movie"}, {"tmdb_id": 200, "media_type": "movie"}]

    # Scoped to lib_on: the row in lib_off is excluded.
    movies, shows = tmdb.resolve_library_guids(
        db, entries, movie_lib_ids=[lib_on.id], show_lib_ids=[]
    )
    assert set(movies) == {"tmdb:100"}
    assert shows == {}

    # Unscoped (None defaults): matches across all libraries.
    movies_all, _ = tmdb.resolve_library_guids(db, entries)
    assert set(movies_all) == {"tmdb:100", "tmdb:200"}

    # Empty list for a media side skips its bucket even with candidates present (vs None = match all).
    _, shows_empty = tmdb.resolve_library_guids(
        db, [{"tmdb_id": 100, "media_type": "tv"}], show_lib_ids=[]
    )
    assert shows_empty == {}


def test_resolve_recs_matches_by_media_type_not_bare_id(db):
    # TMDB movie ids and tv ids are independent, so tmdb:500 can be BOTH a show (in our library) and a
    # movie recommendation. The match must respect media_type — a bare-id match would deep-link the movie
    # rec to the unrelated show (and vice-versa).
    mlib = _lib(db, key="10", kind="movie")
    slib = _lib(db, key="11", kind="show")
    show500 = PlexShow(rating_key="s500", library_id=slib.id, title="Show 500", guid="tmdb:500")
    movie900 = PlexItem(
        rating_key="m900", library_id=mlib.id, kind="movie", title="Movie 900", guid="tmdb:900"
    )
    db.add_all([show500, movie900])
    db.commit()

    # A movie rec for id 500 must NOT match show s500; a tv rec for id 900 must NOT match movie m900.
    miss = {
        r["tmdb_id"]: r
        for r in tmdb.resolve_recs(
            db,
            [
                {"tmdb_id": 500, "title": "Movie 500", "media_type": "movie"},
                {"tmdb_id": 900, "title": "Show 900", "media_type": "tv"},
            ],
            lang="en",
        )
    }
    assert miss[500]["in_library"] is False and miss[500]["rating_key"] is None
    assert miss[900]["in_library"] is False and miss[900]["rating_key"] is None

    # The right media_type DOES resolve to the right row.
    hit = {
        r["tmdb_id"]: r
        for r in tmdb.resolve_recs(
            db,
            [
                {"tmdb_id": 900, "media_type": "movie"},
                {"tmdb_id": 500, "media_type": "tv"},
            ],
            lang="en",
        )
    }
    assert hit[900]["in_library"] is True and hit[900]["rating_key"] == "m900"
    assert hit[500]["in_library"] is True and hit[500]["rating_key"] == "s500"


# ---- E30: countries by ISO code -----------------------------------------------------------------


class FakeCountries(FakeTmdb):
    """TMDB's /configuration/countries, counting the requests."""

    def __init__(self):
        super().__init__()
        self.calls = 0

    def countries(self):
        self.calls += 1
        return [
            {"iso_3166_1": "US", "english_name": "United States of America"},
            {"iso_3166_1": "YU", "english_name": "Yugoslavia"},
        ]


def test_countries_stored_before_codes_get_them_from_tmdbs_list(db):
    lib = _lib(db)
    old = PlexItem(
        rating_key="m1",
        library_id=lib.id,
        kind="movie",
        title="Old",
        production_countries=["Yugoslavia", "Atlantis"],
        tmdb_enriched_at=datetime.now(timezone.utc),
    )
    show_lib = _lib(db, key="2", kind="show")
    show = PlexShow(
        rating_key="s1",
        library_id=show_lib.id,
        title="Show",
        production_countries=["United States of America"],
    )
    new = PlexItem(
        rating_key="m2",
        library_id=lib.id,
        kind="movie",
        title="New",
        production_countries=[{"code": "US", "name": "United States of America"}],
    )
    db.add_all([old, show, new])
    db.commit()

    # Served before the backfill: the bare name, with no code — never a crash on the old shape.
    assert tmdb.serve_block(db, old, lang="hu")["production_countries"] == [
        {"code": None, "name": "Yugoslavia"},
        {"code": None, "name": "Atlantis"},
    ]

    fake = FakeCountries()
    assert tmdb.backfill_country_codes(db, fake) == 2
    db.refresh(old)
    db.refresh(show)
    assert old.production_countries == [
        {"code": "YU", "name": "Yugoslavia"},
        {"code": None, "name": "Atlantis"},  # not in TMDB's list → no code, the name kept
    ]
    assert show.production_countries == [{"code": "US", "name": "United States of America"}]

    # Nothing left to code: no request at all.
    assert tmdb.backfill_country_codes(db, fake) == 0
    assert fake.calls == 1