Add series/season/episode ingestion pipeline
CI / lint (push) Canceled after 0s
CI / typecheck (push) Canceled after 0s
CI / unit-tests (push) Canceled after 0s
CI / integration-tests (push) Canceled after 0s
CI / container-build (push) Canceled after 0s
CI / dependency-audit (push) Canceled after 0s

Movie and person ingestion existed, but the series/season/episode API
endpoints had no way to actually populate them from TMDb -- the
biggest remaining gap in Core 0.1's television scope.

- normalize_series/normalize_season in the metadata normalizer,
  including two TMDb quirks that would otherwise silently produce
  empty data: /tv nests keywords and alternative_titles under
  "results" (not "keywords"/"titles" like /movie), and series-level
  creators come from a separate created_by array, not the credits
  cast/crew lists.
- ingest_series upserts the Series row plus season *stubs* (number,
  title, air date, poster -- everything TMDb inlines on /tv/{id});
  ingest_season fetches and upserts one season's full episode list,
  and requires the series to already exist (TMDb has no single
  endpoint for a whole series' episodes, so this has to be a separate
  per-season call).
- Wired through the same job-lifecycle path as movie/person ingestion
  (runner.py, arq tasks, admin endpoints), with the shared boilerplate
  between them factored into runner._run_ingestion and
  admin.py:_enqueue rather than copy-pasted a third and fourth time.
- Unit tests for both normalizers (runnable without a DB) and
  integration tests for the full ingest_series -> ingest_season flow,
  including the series-must-exist-first error and idempotency on
  re-ingestion.

Co-Authored-By: Claude Sonnet 5 <[email protected]>
This commit is contained in:
NixReaper
2026-09-04 19:43:56 -05:00
co-authored by Claude Sonnet 5
parent 669034896a
commit 3f6332559a
11 changed files with 1288 additions and 49 deletions
+121
View File
@@ -0,0 +1,121 @@
"""Integration tests for the series/season 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
from typing import Any
import pytest
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession
from app.models.tv import Episode, Season, Series
from app.providers.base import MetadataProvider, ProviderNotFoundError
from app.services.ingestion.series_ingestion import ingest_season, ingest_series
from tests.unit.test_normalizer import FAKE_SEASON, FAKE_SERIES
class FakeTMDbSeriesProvider(MetadataProvider):
slug = "tmdb"
name = "The Movie Database (TMDb)"
def __init__(self, series_payload: dict[str, Any], season_payload: dict[str, Any]) -> None:
self._series_payload = series_payload
self._season_payload = season_payload
async def get_movie(self, external_id: str) -> dict[str, Any]:
raise NotImplementedError
async def get_series(self, external_id: str) -> dict[str, Any]:
return self._series_payload
async def get_season(self, series_external_id: str, season_number: int) -> dict[str, Any]:
return self._season_payload
async def get_person(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_series_creates_series_and_season_stubs(db_session: AsyncSession):
provider = FakeTMDbSeriesProvider(FAKE_SERIES, FAKE_SEASON)
series_id = await ingest_series(db_session, provider, "1396")
await db_session.commit()
series = await db_session.get(Series, series_id)
assert series is not None
assert series.title == "Ozymandias"
assert series.status.value == "ended"
seasons = (
(await db_session.execute(select(Season).where(Season.series_id == series_id)))
.scalars()
.all()
)
season_numbers = sorted(s.season_number for s in seasons)
assert season_numbers == [0, 1]
# Season stubs have no episodes yet — that's ingest_season's job.
assert all(
(await db_session.execute(select(Episode).where(Episode.season_id == s.id)))
.scalars()
.first()
is None
for s in seasons
)
@pytest.mark.asyncio
async def test_ingest_season_requires_series_ingested_first(db_session: AsyncSession):
provider = FakeTMDbSeriesProvider(FAKE_SERIES, FAKE_SEASON)
with pytest.raises(ProviderNotFoundError):
await ingest_season(db_session, provider, "1396", 1)
@pytest.mark.asyncio
async def test_ingest_season_creates_episodes_with_credits_and_stills(db_session: AsyncSession):
provider = FakeTMDbSeriesProvider(FAKE_SERIES, FAKE_SEASON)
await ingest_series(db_session, provider, "1396")
await db_session.flush()
season_id = await ingest_season(db_session, provider, "1396", 1)
await db_session.commit()
episodes = (
(await db_session.execute(select(Episode).where(Episode.season_id == season_id)))
.scalars()
.all()
)
assert len(episodes) == 2
pilot = next(e for e in episodes if e.episode_number == 1)
assert pilot.title == "Pilot"
assert pilot.runtime_minutes == 58
@pytest.mark.asyncio
async def test_ingest_season_is_idempotent(db_session: AsyncSession):
provider = FakeTMDbSeriesProvider(FAKE_SERIES, FAKE_SEASON)
await ingest_series(db_session, provider, "1396")
await db_session.flush()
first_season_id = await ingest_season(db_session, provider, "1396", 1)
await db_session.flush()
second_season_id = await ingest_season(db_session, provider, "1396", 1)
await db_session.commit()
assert first_season_id == second_season_id
episodes = (
(await db_session.execute(select(Episode).where(Episode.season_id == first_season_id)))
.scalars()
.all()
)
# Re-running must not duplicate episode rows.
assert len(episodes) == 2