bvandeusen
a497104661
Existing PostAttachments that are actually archives (filed opaquely before the magic-byte gate) need extracting retroactively. cleanup_service. reextract_archive_attachments scans PostAttachments, magic-detects the archives, and for each reconstructs the post's sidecar from the DB + re-runs attach_in_place in a temp dir — so the members extract and re-link to the SAME post via find_or_create_post (source_id + external_post_id). Idempotent (members dedupe by sha256). Enqueues thumbnail+ML for new members. Wired as a maintenance-queue Celery task (tasks/admin) + POST /api/admin/maintenance/reextract-archives (202) + a "Re-extract archive attachments" card in Settings → Maintenance. Test: a zip stored under a mangled extension-less name extracts + links its member to the post via ImageProvenance, and a second run is a no-op (idempotent). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
76 lines
2.7 KiB
Python
76 lines
2.7 KiB
Python
"""FC-3k: admin destructive Celery tasks.
|
|
|
|
Two long-running ops on the maintenance queue. task_run lifecycle is
|
|
captured automatically by FC-3i signals — these tasks just return
|
|
their summary dict so it lands in task_run.metadata (via Celery's
|
|
result backend) for the dashboard to surface.
|
|
|
|
Soft/hard time limits inherit the FC-3i recovery sweep: a runaway
|
|
task gets killed and flipped to status='timeout' by
|
|
recover_stalled_task_runs.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
from pathlib import Path
|
|
|
|
from sqlalchemy.exc import DBAPIError, OperationalError
|
|
|
|
from ..celery_app import celery
|
|
from ..services import cleanup_service
|
|
from ._sync_engine import sync_session_factory as _sync_session_factory
|
|
|
|
log = logging.getLogger(__name__)
|
|
IMAGES_ROOT = Path("/images")
|
|
|
|
|
|
@celery.task(
|
|
name="backend.app.tasks.admin.delete_artist_cascade_task",
|
|
bind=True,
|
|
autoretry_for=(OperationalError, DBAPIError),
|
|
retry_backoff=15, retry_backoff_max=180, max_retries=1,
|
|
soft_time_limit=1800, time_limit=2400, # 30 min / 40 min
|
|
)
|
|
def delete_artist_cascade_task(self, *, artist_id: int) -> dict:
|
|
"""Wraps cleanup_service.delete_artist_cascade. Returns the
|
|
service's summary dict for FC-3i task_run.metadata capture."""
|
|
SessionLocal = _sync_session_factory()
|
|
with SessionLocal() as session:
|
|
return cleanup_service.delete_artist_cascade(
|
|
session, artist_id=artist_id, images_root=IMAGES_ROOT,
|
|
)
|
|
|
|
|
|
@celery.task(
|
|
name="backend.app.tasks.admin.bulk_delete_images_task",
|
|
bind=True,
|
|
autoretry_for=(OperationalError, DBAPIError),
|
|
retry_backoff=15, retry_backoff_max=180, max_retries=1,
|
|
soft_time_limit=900, time_limit=1200, # 15 min / 20 min
|
|
)
|
|
def bulk_delete_images_task(self, *, image_ids: list[int]) -> dict:
|
|
"""Wraps cleanup_service.delete_images."""
|
|
SessionLocal = _sync_session_factory()
|
|
with SessionLocal() as session:
|
|
return cleanup_service.delete_images(
|
|
session, image_ids=image_ids, images_root=IMAGES_ROOT,
|
|
)
|
|
|
|
|
|
@celery.task(
|
|
name="backend.app.tasks.admin.reextract_archive_attachments_task",
|
|
bind=True,
|
|
autoretry_for=(OperationalError, DBAPIError),
|
|
retry_backoff=15, retry_backoff_max=180, max_retries=1,
|
|
soft_time_limit=1800, time_limit=2400, # 30 min / 40 min
|
|
)
|
|
def reextract_archive_attachments_task(self) -> dict:
|
|
"""Wraps cleanup_service.reextract_archive_attachments (#713 part 2):
|
|
re-extract PostAttachments that are actually archives but were filed
|
|
opaquely before the magic-byte gate, and link their members to the post."""
|
|
SessionLocal = _sync_session_factory()
|
|
with SessionLocal() as session:
|
|
return cleanup_service.reextract_archive_attachments(
|
|
session, images_root=IMAGES_ROOT,
|
|
)
|