"""Integration tests for the movie ingestion pipeline (section 15): a fake provider stands in for TMDb so these run without network access, while still exercising the real normalize -> match -> upsert -> provenance path against PostgreSQL.""" from __future__ import annotations import uuid from typing import Any import pytest from sqlalchemy import select from sqlalchemy.ext.asyncio import AsyncSession from app.core.ids import aurora_id from app.models.artwork import Artwork from app.models.company import Company from app.models.credit import Credit from app.models.genre import Genre from app.models.movie import Movie from app.models.provider import ProviderRecord from app.providers.base import MetadataProvider from app.services import movie_service from app.services.ingestion.collection_ingestion import ingest_collection from app.services.ingestion.movie_ingestion import ingest_movie from tests.integration.test_collection_ingestion import FakeTMDbCollectionProvider from tests.unit.test_normalizer import FAKE_COLLECTION, FAKE_MOVIE class FakeTMDbProvider(MetadataProvider): slug = "tmdb" name = "The Movie Database (TMDb)" def __init__(self, payload: dict[str, Any]) -> None: self._payload = payload async def get_movie(self, external_id: str) -> dict[str, Any]: return self._payload async def get_series(self, external_id: str) -> dict[str, Any]: raise NotImplementedError async def get_season(self, series_external_id: str, season_number: int) -> dict[str, Any]: raise NotImplementedError async def get_person(self, external_id: str) -> dict[str, Any]: raise NotImplementedError async def get_collection(self, external_id: str) -> dict[str, Any]: raise NotImplementedError async def search_movie(self, query: str) -> list[dict[str, Any]]: raise NotImplementedError @pytest.mark.asyncio async def test_ingest_movie_creates_normalized_record(db_session: AsyncSession): provider = FakeTMDbProvider(FAKE_MOVIE) movie_id = await ingest_movie(db_session, provider, "603") await db_session.commit() movie = await db_session.get(Movie, movie_id) assert movie is not None assert movie.title == "The Matrix" assert movie.runtime_minutes == 136 genres = (await db_session.execute(select(Genre.name))).scalars().all() assert "Action" in genres credits_ = ( (await db_session.execute(select(Credit).where(Credit.entity_id == movie_id))) .scalars() .all() ) assert any(c.character == "Neo" for c in credits_) record = ( await db_session.execute( select(ProviderRecord).where(ProviderRecord.external_id == "603") ) ).scalar_one() assert record.aurora_entity_id == movie_id assert record.match_confidence.value == "new" @pytest.mark.asyncio async def test_ingest_movie_is_idempotent(db_session: AsyncSession): """Re-running ingestion for the same provider + external_id must update the same Aurora movie, never create a duplicate (section 2: zero duplicate ingestion records).""" provider = FakeTMDbProvider(FAKE_MOVIE) first_id = await ingest_movie(db_session, provider, "603") await db_session.commit() updated_payload = {**FAKE_MOVIE, "title": "The Matrix (Updated Title)"} second_provider = FakeTMDbProvider(updated_payload) second_id = await ingest_movie(db_session, second_provider, "603") await db_session.commit() assert first_id == second_id all_movies = (await db_session.execute(select(Movie))).scalars().all() assert len(all_movies) == 1 assert all_movies[0].title == "The Matrix (Updated Title)" credits_ = ( (await db_session.execute(select(Credit).where(Credit.entity_id == first_id))) .scalars() .all() ) # Credits are replaced wholesale on re-sync, not duplicated. assert len(credits_) == 2 # 1 cast + 1 crew from FAKE_MOVIE @pytest.mark.asyncio async def test_ingest_movie_ingests_company_logo(db_session: AsyncSession): provider = FakeTMDbProvider(FAKE_MOVIE) await ingest_movie(db_session, provider, "603") await db_session.commit() company = ( await db_session.execute( select(Company).where(Company.name == "Village Roadshow Pictures") ) ).scalar_one() logo = ( await db_session.execute( select(Artwork).where(Artwork.entity_type == "company", Artwork.entity_id == company.id) ) ).scalar_one() assert logo.artwork_type.value == "logo" assert logo.is_primary is True assert logo.original_url.endswith("/village-roadshow-logo.png") @pytest.mark.asyncio async def test_movie_detail_surfaces_company_logo_path(db_session: AsyncSession): """The ingested logo must actually reach the API response -- movie_service used to hardcode companies[].logo_path = None instead of looking up the company's artwork, so ingestion could succeed while the API still showed logo_path: None for every company.""" provider = FakeTMDbProvider(FAKE_MOVIE) movie_id = await ingest_movie(db_session, provider, "603") await db_session.commit() detail = await movie_service.get_movie_detail(db_session, aurora_id("movie", str(movie_id))) roadshow = next(c for c in detail.companies if c.name == "Village Roadshow Pictures") assert roadshow.logo_path is not None assert roadshow.logo_path.endswith("/village-roadshow-logo.png") @pytest.mark.asyncio async def test_movie_detail_surfaces_collection_poster_path(db_session: AsyncSession): """Same class of bug as company logo_path: movie_service built the embedded collection field without ever looking up its poster artwork, so poster_path stayed None even after a full ingest_collection run populated one. The bare belongs_to_collection stub created by ingest_movie alone has no poster -- only ingest_collection provides it.""" provider = FakeTMDbCollectionProvider( movie_payloads={"603": FAKE_MOVIE}, collection_payload=FAKE_COLLECTION ) movie_id = await ingest_movie(db_session, provider, "603") await db_session.flush() await ingest_collection(db_session, provider, "2344") await db_session.commit() detail = await movie_service.get_movie_detail(db_session, aurora_id("movie", str(movie_id))) assert detail.collection is not None assert detail.collection.poster_path is not None assert detail.collection.poster_path.endswith("/collection-poster.jpg") @pytest.mark.asyncio async def test_movie_recommendations_only_include_already_ingested_movies( db_session: AsyncSession, ): """TMDb's recommendations list can reference movies Aurora hasn't ingested yet; ingest_movie must link only the ones it can resolve by external id (section 15: never fabricate a stub for an unseen entity), and GET .../recommendations must return them in TMDb's ranked order.""" # videos and imdb_id overridden: FAKE_MOVIE's embedded video and imdb_id # are both fixed identifiers, and two different movies both ingesting # them unmodified would collide on the real uq_video_provider_source / # uq_external_id_source unique constraints -- each belongs to exactly # one entity, unlike genres/companies which are legitimately shared. sequel_payload = { **FAKE_MOVIE, "id": 604, "title": "The Matrix Reloaded", "videos": {"results": []}, "imdb_id": "tt0234215", } await ingest_movie(db_session, FakeTMDbProvider(sequel_payload), "604") await db_session.flush() movie_with_recs = { **FAKE_MOVIE, "recommendations": {"results": [{"id": 604}, {"id": 999999}]}, } movie_id = await ingest_movie(db_session, FakeTMDbProvider(movie_with_recs), "603") await db_session.commit() recs = await movie_service.get_movie_recommendations( db_session, aurora_id("movie", str(movie_id)) ) assert [r.title for r in recs.recommendations] == ["The Matrix Reloaded"] @pytest.mark.asyncio async def test_movie_recommendations_not_found_for_unknown_movie(db_session: AsyncSession): with pytest.raises(movie_service.MovieNotFoundError): await movie_service.get_movie_recommendations( db_session, aurora_id("movie", str(uuid.uuid4())) )