NixReaperandClaude Sonnet 5
fef914db36
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
Section 10: every image API responses reference has pointed straight at TMDb's CDN since day one -- Aurora never actually downloaded or served artwork itself, despite storing dimensions/checksum/local_path columns for exactly that. Closes the gap: - is_primary was declared on the Artwork model but never actually set anywhere -- every row defaulted to False. Now the normalizer marks the one image each provider designates as *the* image for an entity (TMDb's poster_path/backdrop_path/profile_path) as primary, distinct from the dozens of alternates also ingested, including correctly marking an existing row primary (not inserting a duplicate) when that image already appears in the alternates list. - app/services/artwork/: an ArtworkStorage interface with a LocalDiskStorage implementation (checksum-named files, single-host deployment via a Docker volume shared between api and worker -- see docs/architecture.md for the S3/R2 upgrade path), and a download pipeline with content-type validation, a size cap, and path-traversal protection. - After movie/series/person ingestion succeeds, tasks.py cascades one download_artwork_task per primary artwork id via arq's ctx['redis'] (same fan-out pattern as the season cascade) -- fire-and-forget, not tracked in ingestion_jobs, since a failed image cache is a known-safe fallback to the provider URL, not a user-facing failure. - app/main.py serves MEDIA_ROOT at MEDIA_URL_PREFIX; local_path is preferred over original_url once set (already-existing fallback logic in app/services/common.py:artwork_url, now actually exercised). Also fixes a real interaction bug this surfaced: every ingestion pipeline deleted and recreated all of an entity's Artwork rows on each re-sync, which would have silently wiped local_path/checksum on every re-ingestion, forcing a full re-download every time and defeating the point of caching locally at all. app/repositories/polymorphic.py's new sync_artwork upserts by provider_asset_id (TMDb's stable per-image path) instead, preserving downloaded copies across re-sync, and replaces three near-identical delete+recreate helpers that used to live separately in movie_ingestion.py, series_ingestion.py, and person_ingestion.py. Co-Authored-By: Claude Sonnet 5 <[email protected]>
104 lines
3.3 KiB
Python
104 lines
3.3 KiB
Python
"""Person ingestion pipeline (section 15).
|
|
|
|
Movie/series ingestion already creates a stub `Person` row (name + gender)
|
|
for each cast/crew credit via `get_or_create_person`. This module fetches
|
|
and upserts a *full* profile (biography, birthday, images, ...) for one
|
|
person, either standalone (admin-triggered) or as a follow-up job.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import uuid
|
|
|
|
from sqlalchemy.ext.asyncio import AsyncSession
|
|
|
|
from app.core.logging import get_logger
|
|
from app.models.enums import MatchConfidence
|
|
from app.models.person import Person
|
|
from app.providers.base import MetadataProvider
|
|
from app.repositories import polymorphic
|
|
from app.repositories import reference_repository as refs
|
|
from app.repositories.provider_repository import get_or_create_provider, upsert_provider_record
|
|
from app.services.metadata.matcher import match_entity
|
|
from app.services.metadata.normalizer import normalize_person
|
|
|
|
logger = get_logger(__name__)
|
|
|
|
|
|
async def ingest_person(
|
|
session: AsyncSession,
|
|
provider: MetadataProvider,
|
|
external_id: str,
|
|
*,
|
|
ingestion_job_id: uuid.UUID | None = None,
|
|
) -> uuid.UUID:
|
|
tmdb_provider = await get_or_create_provider(session, provider.slug, provider.name)
|
|
|
|
aurora_id_existing, confidence = await match_entity(
|
|
session, provider_id=tmdb_provider.id, entity_type="person", external_id=external_id
|
|
)
|
|
|
|
raw = await provider.get_person(external_id)
|
|
normalized = normalize_person(raw)
|
|
|
|
person: Person | None = None
|
|
if aurora_id_existing is not None:
|
|
person = await session.get(Person, aurora_id_existing)
|
|
|
|
if person is None:
|
|
person = Person(name=normalized.name)
|
|
session.add(person)
|
|
await session.flush()
|
|
aurora_id_existing = None
|
|
|
|
person.name = normalized.name
|
|
person.biography = normalized.biography
|
|
person.birthday = normalized.birthday
|
|
person.deathday = normalized.deathday
|
|
person.birthplace = normalized.birthplace
|
|
person.gender = normalized.gender
|
|
person.known_for_department = normalized.known_for_department
|
|
person.popularity = normalized.popularity
|
|
person.aliases = normalized.aliases
|
|
|
|
await session.flush()
|
|
|
|
await polymorphic.sync_artwork(
|
|
session,
|
|
entity_type="person",
|
|
entity_id=person.id,
|
|
provider_id=tmdb_provider.id,
|
|
artwork_list=normalized.artwork,
|
|
)
|
|
|
|
await refs.link_external_id(
|
|
session,
|
|
entity_type="person",
|
|
entity_id=person.id,
|
|
provider_id=tmdb_provider.id,
|
|
external_id=external_id,
|
|
)
|
|
for slug, ext_id in normalized.external_ids.items():
|
|
ext_provider = await get_or_create_provider(session, slug, slug.upper())
|
|
await refs.link_external_id(
|
|
session,
|
|
entity_type="person",
|
|
entity_id=person.id,
|
|
provider_id=ext_provider.id,
|
|
external_id=ext_id,
|
|
)
|
|
|
|
await upsert_provider_record(
|
|
session,
|
|
provider_id=tmdb_provider.id,
|
|
entity_type="person",
|
|
external_id=external_id,
|
|
raw_data=raw,
|
|
aurora_entity_id=person.id,
|
|
match_confidence=confidence if aurora_id_existing else MatchConfidence.NEW,
|
|
ingestion_job_id=ingestion_job_id,
|
|
)
|
|
|
|
logger.info("person_ingested", person_id=str(person.id), external_id=external_id)
|
|
return person.id
|