Add opt-in season cascade to series ingestion
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
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
Ingesting a series only ever produced season stubs -- getting actual episodes meant calling POST /admin/ingest/season once per season by hand, which is exactly what manual end-to-end testing kept requiring for every multi-season show. POST /api/v1/admin/ingest/series now takes include_seasons (default false, since a show can have dozens of seasons and that's dozens of TMDb calls fired from one request). When true, ingest_series_task fans out one ingest_season job per season once the series succeeds, using arq's own ctx['redis'] connection for the job (the same pattern arq's docs recommend for job chaining) rather than a second unrelated connection. Each fanned-out season job still goes through get_or_create_ingestion_job, so re-running a cascaded series ingestion reuses the same season job rows instead of creating duplicates. Co-Authored-By: Claude Sonnet 5 <[email protected]>
This commit is contained in:
co-authored by
Claude Sonnet 5
parent
ec6b5bdd7d
commit
b4d1e8f755
@@ -0,0 +1,99 @@
|
||||
"""Tests for the series -> season ingestion cascade
|
||||
(app/workers/tasks.py:ingest_series_task, include_seasons=True).
|
||||
|
||||
run_series_ingestion and get_series_season_numbers are monkeypatched so this
|
||||
doesn't need a real TMDbProvider/network call — the thing actually at risk
|
||||
here is the fan-out wiring itself (does it enqueue the right task with the
|
||||
right arguments for every season), not the ingestion pipeline, which
|
||||
test_series_ingestion.py already covers.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import uuid
|
||||
|
||||
import pytest
|
||||
|
||||
from app.workers import tasks
|
||||
|
||||
|
||||
class _FakeArqRedis:
|
||||
def __init__(self) -> None:
|
||||
self.enqueued: list[tuple[str, tuple]] = []
|
||||
|
||||
async def enqueue_job(self, task_name: str, *args):
|
||||
self.enqueued.append((task_name, args))
|
||||
return object() # stand-in for arq's Job — callers don't use it here
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_series_task_does_not_cascade_by_default(monkeypatch):
|
||||
fake_series_id = uuid.uuid4()
|
||||
|
||||
async def fake_run_series_ingestion(job_id, external_id):
|
||||
return fake_series_id
|
||||
|
||||
monkeypatch.setattr(tasks, "run_series_ingestion", fake_run_series_ingestion)
|
||||
|
||||
redis = _FakeArqRedis()
|
||||
result = await tasks.ingest_series_task({"redis": redis}, str(uuid.uuid4()), "1396")
|
||||
|
||||
assert result == str(fake_series_id)
|
||||
assert redis.enqueued == []
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_series_task_cascades_one_season_job_per_season(monkeypatch, db_session):
|
||||
fake_series_id = uuid.uuid4()
|
||||
|
||||
async def fake_run_series_ingestion(job_id, external_id):
|
||||
return fake_series_id
|
||||
|
||||
async def fake_get_series_season_numbers(series_id):
|
||||
assert series_id == fake_series_id
|
||||
return [0, 1, 2]
|
||||
|
||||
monkeypatch.setattr(tasks, "run_series_ingestion", fake_run_series_ingestion)
|
||||
monkeypatch.setattr(tasks, "get_series_season_numbers", fake_get_series_season_numbers)
|
||||
|
||||
redis = _FakeArqRedis()
|
||||
result = await tasks.ingest_series_task(
|
||||
{"redis": redis}, str(uuid.uuid4()), "1396", include_seasons=True
|
||||
)
|
||||
|
||||
assert result == str(fake_series_id)
|
||||
assert len(redis.enqueued) == 3
|
||||
for task_name, args in redis.enqueued:
|
||||
assert task_name == "ingest_season_task"
|
||||
job_id_arg, external_id_arg, season_number_arg = args
|
||||
assert external_id_arg == "1396"
|
||||
uuid.UUID(job_id_arg) # must be a real, parseable job id
|
||||
|
||||
seasons_enqueued = sorted(args[2] for _, args in redis.enqueued)
|
||||
assert seasons_enqueued == [0, 1, 2]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_series_task_cascade_reuses_job_on_repeat_enqueue(monkeypatch, db_session):
|
||||
"""Re-cascading the same series (e.g. a retried job) must reuse the same
|
||||
season IngestionJob rows, not create duplicates — get_or_create_ingestion_job
|
||||
is idempotency-keyed by (entity_type, external_id)."""
|
||||
|
||||
fake_series_id = uuid.uuid4()
|
||||
|
||||
async def fake_run_series_ingestion(job_id, external_id):
|
||||
return fake_series_id
|
||||
|
||||
async def fake_get_series_season_numbers(series_id):
|
||||
return [1]
|
||||
|
||||
monkeypatch.setattr(tasks, "run_series_ingestion", fake_run_series_ingestion)
|
||||
monkeypatch.setattr(tasks, "get_series_season_numbers", fake_get_series_season_numbers)
|
||||
|
||||
redis = _FakeArqRedis()
|
||||
await tasks.ingest_series_task({"redis": redis}, str(uuid.uuid4()), "9999", include_seasons=True)
|
||||
await tasks.ingest_series_task({"redis": redis}, str(uuid.uuid4()), "9999", include_seasons=True)
|
||||
|
||||
first_job_id = redis.enqueued[0][1][0]
|
||||
second_job_id = redis.enqueued[1][1][0]
|
||||
assert first_job_id == second_job_id
|
||||
Reference in New Issue
Block a user