Aurora-Core/tests/integration/test_trending.py

"""Integration tests for trending (section 17, additive): Aurora mirrors
TMDb's own /trending/{media_type}/{time_window} ranking rather than
computing its own from popularity deltas (see app/models/trending.py) --
refresh_trending ingests/refreshes each item and replaces the window's
ranked snapshot.

refresh_trending manages its own per-item session_scope() (so one failing
item doesn't roll back others already committed -- see its docstring),
so these tests read back through session_scope() too rather than the
db_session fixture, same convention as test_ingestion_retry.py: db_session
is accepted only to trigger the Postgres-reachability skip, real reads and
writes all go through session_scope() to stay on a connection that
actually sees committed data."""

from __future__ import annotations

from typing import Any

import pytest
from sqlalchemy.ext.asyncio import AsyncSession

from app.core.database import session_scope
from app.providers.base import MetadataProvider
from app.repositories.trending_repository import get_trending_entity_ids, replace_trending
from app.services import movie_service, tv_service
from app.services.ingestion.trending_ingestion import refresh_trending
from tests.unit.test_normalizer import FAKE_MOVIE, FAKE_SERIES


class FakeTrendingProvider(MetadataProvider):
    slug = "tmdb"
    name = "The Movie Database (TMDb)"

    def __init__(self, movie_ids: list[int], series_ids: list[int]) -> None:
        self._movie_ids = movie_ids
        self._series_ids = series_ids

    async def get_movie(self, external_id: str) -> dict[str, Any]:
        # FAKE_MOVIE's embedded video id and imdb_id are fixed identifiers
        # meant to be globally unique per real TMDb movie -- reusing them
        # unmodified across multiple synthetic movies here would collide
        # on uq_video_provider_source / uq_external_id_source. Unlike
        # every other test file (db_session rolls back per test),
        # refresh_trending's session_scope() commits are never rolled
        # back, so that collision would otherwise permanently poison the
        # shared test database for every later test in the same run that
        # also ingests FAKE_MOVIE unmodified (see test_watch_providers.py).
        return {
            **FAKE_MOVIE,
            "id": int(external_id),
            "title": f"Movie {external_id}",
            "videos": {"results": []},
            "imdb_id": None,
            "external_ids": {},
        }

    async def get_series(self, external_id: str) -> dict[str, Any]:
        # Same reasoning as get_movie above, for FAKE_SERIES's imdb_id/tvdb_id.
        return {
            **FAKE_SERIES,
            "id": int(external_id),
            "name": f"Series {external_id}",
            "external_ids": {},
        }

    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

    async def get_trending(self, media_type: str, time_window: str) -> list[dict[str, Any]]:
        ids = self._movie_ids if media_type == "movie" else self._series_ids
        return [{"id": i} for i in ids]


@pytest.mark.asyncio
async def test_refresh_trending_ingests_and_ranks_movies(db_session: AsyncSession):
    provider = FakeTrendingProvider(movie_ids=[901, 902, 903], series_ids=[])

    count = await refresh_trending(provider, "movie", "day")
    assert count == 3

    async with session_scope() as session:
        ids = await get_trending_entity_ids(session, entity_type="movie", time_window="day")
    assert len(ids) == 3


@pytest.mark.asyncio
async def test_refresh_trending_preserves_tmdb_rank_order(db_session: AsyncSession):
    provider = FakeTrendingProvider(movie_ids=[901, 902, 903], series_ids=[])
    await refresh_trending(provider, "movie", "day")

    async with session_scope() as session:
        out = await movie_service.list_trending(session, time_window="day", page=1, page_size=20)

    assert [m.title for m in out.results] == ["Movie 901", "Movie 902", "Movie 903"]


@pytest.mark.asyncio
async def test_refresh_trending_is_scoped_per_window(db_session: AsyncSession):
    """A "week" refresh must not appear in "day" results, and vice versa."""

    day_provider = FakeTrendingProvider(movie_ids=[901], series_ids=[])
    week_provider = FakeTrendingProvider(movie_ids=[902], series_ids=[])
    await refresh_trending(day_provider, "movie", "day")
    await refresh_trending(week_provider, "movie", "week")

    async with session_scope() as session:
        day_out = await movie_service.list_trending(session, time_window="day", page=1, page_size=20)
        week_out = await movie_service.list_trending(session, time_window="week", page=1, page_size=20)

    assert [m.title for m in day_out.results] == ["Movie 901"]
    assert [m.title for m in week_out.results] == ["Movie 902"]


@pytest.mark.asyncio
async def test_refresh_trending_replaces_stale_entries(db_session: AsyncSession):
    """A movie that falls off trending must not linger from a prior
    refresh -- this is a wholesale replace, not an accumulate."""

    provider = FakeTrendingProvider(movie_ids=[901, 902], series_ids=[])
    await refresh_trending(provider, "movie", "day")

    provider_v2 = FakeTrendingProvider(movie_ids=[903], series_ids=[])
    await refresh_trending(provider_v2, "movie", "day")

    async with session_scope() as session:
        out = await movie_service.list_trending(session, time_window="day", page=1, page_size=20)
    assert [m.title for m in out.results] == ["Movie 903"]


@pytest.mark.asyncio
async def test_refresh_trending_ingests_series(db_session: AsyncSession):
    provider = FakeTrendingProvider(movie_ids=[], series_ids=[1901, 1902])
    count = await refresh_trending(provider, "tv", "day")
    assert count == 2

    async with session_scope() as session:
        out = await tv_service.list_trending(session, time_window="day", page=1, page_size=20)
    assert [s.title for s in out.results] == ["Series 1901", "Series 1902"]


@pytest.mark.asyncio
async def test_list_trending_paginates(db_session: AsyncSession):
    provider = FakeTrendingProvider(movie_ids=[901, 902, 903, 904], series_ids=[])
    await refresh_trending(provider, "movie", "day")

    async with session_scope() as session:
        page1 = await movie_service.list_trending(session, time_window="day", page=1, page_size=2)
        page2 = await movie_service.list_trending(session, time_window="day", page=2, page_size=2)

    assert page1.total_results == 4
    assert page1.total_pages == 2
    assert [m.title for m in page1.results] == ["Movie 901", "Movie 902"]
    assert [m.title for m in page2.results] == ["Movie 903", "Movie 904"]


@pytest.mark.asyncio
async def test_list_trending_rejects_unknown_window(db_session: AsyncSession):
    async with session_scope() as session:
        with pytest.raises(movie_service.InvalidMovieFilterError):
            await movie_service.list_trending(session, time_window="month", page=1, page_size=20)


@pytest.mark.asyncio
async def test_list_trending_returns_empty_when_never_refreshed(db_session: AsyncSession):
    # Unlike the other tests here, this one's precondition is "no trending
    # data exists yet" -- every other test calls refresh_trending, which
    # always wipes its own (entity_type, time_window) scope before writing,
    # making the prior state irrelevant. This one has no such call, so it
    # must clear the scope itself rather than assume a clean slate (these
    # tests commit for real via session_scope(), unlike db_session's
    # per-test rollback, so a prior test's rows would otherwise leak in).
    async with session_scope() as session:
        await replace_trending(session, entity_type="movie", time_window="day", entity_ids=[])

    async with session_scope() as session:
        out = await movie_service.list_trending(session, time_window="day", page=1, page_size=20)
    assert out.results == []
    assert out.total_results == 0