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
+75 -16
View File
@@ -34,6 +34,15 @@ class IngestPersonRequest(BaseModel):
tmdb_id: str
class IngestSeriesRequest(BaseModel):
tmdb_id: str
class IngestSeasonRequest(BaseModel):
tmdb_id: str
season_number: int
class IngestionEnqueuedOut(BaseModel):
job_id: str
arq_job_id: str
@@ -51,16 +60,21 @@ class IngestionJobOut(BaseModel):
result_aurora_id: str | None
@router.post("/ingest/movie", response_model=IngestionEnqueuedOut)
async def enqueue_movie_ingestion(
body: IngestMovieRequest, queue: ArqRedis = Depends(get_queue)
async def _enqueue(
queue: ArqRedis,
*,
job_type: str,
entity_type: str,
external_id: str,
task_name: str,
task_args: tuple = (),
) -> IngestionEnqueuedOut:
# Created synchronously (and idempotently — same tmdb_id reuses the same
# row) so the response's job_id is immediately valid against
# GET /ingest/jobs/{job_id}. arq's own job id is a separate, unrelated
# identifier used only for queue bookkeeping.
job_id = await get_or_create_ingestion_job("movie_sync", "movie", body.tmdb_id)
arq_job = await queue.enqueue_job("ingest_movie_task", str(job_id), body.tmdb_id)
# The IngestionJob row is created synchronously (and idempotently — the
# same external_id reuses the same row) so the response's job_id is
# immediately valid against GET /ingest/jobs/{job_id}. arq's own job id
# is a separate, unrelated identifier used only for queue bookkeeping.
job_id = await get_or_create_ingestion_job(job_type, entity_type, external_id)
arq_job = await queue.enqueue_job(task_name, str(job_id), *task_args)
if arq_job is None:
raise HTTPException(
status.HTTP_503_SERVICE_UNAVAILABLE, "Could not enqueue ingestion job (queue busy)."
@@ -68,17 +82,62 @@ async def enqueue_movie_ingestion(
return IngestionEnqueuedOut(job_id=str(job_id), arq_job_id=arq_job.job_id)
@router.post("/ingest/movie", response_model=IngestionEnqueuedOut)
async def enqueue_movie_ingestion(
body: IngestMovieRequest, queue: ArqRedis = Depends(get_queue)
) -> IngestionEnqueuedOut:
return await _enqueue(
queue,
job_type="movie_sync",
entity_type="movie",
external_id=body.tmdb_id,
task_name="ingest_movie_task",
task_args=(body.tmdb_id,),
)
@router.post("/ingest/person", response_model=IngestionEnqueuedOut)
async def enqueue_person_ingestion(
body: IngestPersonRequest, queue: ArqRedis = Depends(get_queue)
) -> IngestionEnqueuedOut:
job_id = await get_or_create_ingestion_job("person_sync", "person", body.tmdb_id)
arq_job = await queue.enqueue_job("ingest_person_task", str(job_id), body.tmdb_id)
if arq_job is None:
raise HTTPException(
status.HTTP_503_SERVICE_UNAVAILABLE, "Could not enqueue ingestion job (queue busy)."
)
return IngestionEnqueuedOut(job_id=str(job_id), arq_job_id=arq_job.job_id)
return await _enqueue(
queue,
job_type="person_sync",
entity_type="person",
external_id=body.tmdb_id,
task_name="ingest_person_task",
task_args=(body.tmdb_id,),
)
@router.post("/ingest/series", response_model=IngestionEnqueuedOut)
async def enqueue_series_ingestion(
body: IngestSeriesRequest, queue: ArqRedis = Depends(get_queue)
) -> IngestionEnqueuedOut:
return await _enqueue(
queue,
job_type="series_sync",
entity_type="series",
external_id=body.tmdb_id,
task_name="ingest_series_task",
task_args=(body.tmdb_id,),
)
@router.post("/ingest/season", response_model=IngestionEnqueuedOut)
async def enqueue_season_ingestion(
body: IngestSeasonRequest, queue: ArqRedis = Depends(get_queue)
) -> IngestionEnqueuedOut:
# Season ingestion requires the series to already be ingested — see
# app/services/ingestion/series_ingestion.py:ingest_season.
return await _enqueue(
queue,
job_type="season_sync",
entity_type="season",
external_id=f"{body.tmdb_id}:{body.season_number}",
task_name="ingest_season_task",
task_args=(body.tmdb_id, body.season_number),
)
@router.get("/ingest/jobs/{job_id}", response_model=IngestionJobOut)