Files
FabledCurator/backend/app/services/refetch_service.py
T
bvandeusen dcfe55d731 feat(import-resilience L2): one-shot re-download for corrupt downloaded files
Layer 2 — remediate a corrupt file by re-fetching a fresh copy from its
source, bounded to a single attempt. Operator-requested 2026-05-28.

New backend/app/services/refetch_service.py:
- resolve_refetch_source: parse the failed file's sidecar → platform,
  derive the artist from the import path, find an ENABLED Source with a
  real feed URL for (artist, platform). Returns None for filesystem-only
  imports, missing sidecars, or `sidecar:<platform>:<slug>` synthetic
  anchors (not pollable).
- attempt_refetch: if not already refetched AND a Source resolves,
  delete the corrupt file (so gallery-dl's skip_existing re-fetches it),
  set ImportTask.refetched=True, and trigger ONE download_source
  re-check. Bounded by `refetched` so source-side corruption can't loop.

Wiring:
- Manual endpoint POST /api/import/tasks/<id>/refetch (only on 'failed'
  tasks). Returns refetch_queued / no_source / already_refetched /
  not_found / not_failed.
- Auto path in recover_interrupted_tasks: for each poison-pill row, if
  env FC_AUTO_REFETCH_CORRUPT=1, attempt_refetch (default OFF — the
  manual button is the primary path; auto is opt-in since re-fetch
  deletes a file + re-runs the downloader).
- Frontend: a cloud-refresh icon button on failed rows in ImportTaskList
  → stores.import.refetchTask → toast keyed on the result status.

Filesystem imports with no upstream return no_source — the operator's
only remediation there is replacing the file on disk, surfaced clearly
in the toast.

Tests: 404 unknown task, 400 non-failed task, no_source when
unresolvable, and the full resolvable-source path (file deleted,
refetched flag set, one download_source dispatched, second call is a
no-op). The resolvable test repoints the migration-seeded
import_settings(id=1) scan path rather than inserting a conflicting row.
2026-05-28 00:08:03 -04:00

107 lines
3.5 KiB
Python

"""Layer-2 one-shot re-download remediation for corrupt imported files.
When an import fails on a file that came from a known, pollable
subscription Source, deleting the bad copy and re-running the source's
downloader can fetch a fresh, unblemished copy. This only helps when:
- the corruption is in transit / on disk (not at the source), AND
- the file resolves to an ENABLED Source with a real feed URL
(a `sidecar:<platform>:<slug>` synthetic anchor is not pollable),
AND
- we haven't already re-fetched this task once (bounded by
ImportTask.refetched so source-side corruption can't loop).
Filesystem-only imports with no resolvable Source return 'no_source' —
the operator's only remediation there is to replace the file on disk.
Operator-requested 2026-05-28 (Layer 2).
"""
import json
import logging
from pathlib import Path
from sqlalchemy import select
from sqlalchemy.orm import Session
from ..models import Artist, ImportTask, Source
from ..utils.paths import derive_top_level_artist
from ..utils.sidecar import find_sidecar, parse_sidecar
from ..utils.slug import slugify
log = logging.getLogger(__name__)
def resolve_refetch_source(
session: Session, source_path: str, import_root: Path,
) -> Source | None:
"""Find an enabled, real-URL Source for the file's (artist, platform),
or None when nothing re-pollable resolves."""
path = Path(source_path)
sc = find_sidecar(path)
if sc is None:
return None
try:
data = json.loads(sc.read_text("utf-8"))
except (OSError, json.JSONDecodeError):
return None
if not isinstance(data, dict):
return None
sd = parse_sidecar(data)
if not sd.platform:
return None
artist_name = derive_top_level_artist(path, import_root)
if not artist_name:
return None
artist = session.execute(
select(Artist).where(Artist.slug == slugify(artist_name))
).scalar_one_or_none()
if artist is None:
return None
src = session.execute(
select(Source)
.where(
Source.artist_id == artist.id,
Source.platform == sd.platform,
Source.enabled.is_(True),
)
.order_by(Source.id.asc())
).scalars().first()
if src is None:
return None
if (src.url or "").startswith("sidecar:"):
return None # synthetic anchor — not a pollable feed
return src
def attempt_refetch(
session: Session, task: ImportTask, import_root: Path,
) -> dict:
"""Delete the corrupt file, mark the task refetched, and trigger ONE
source re-check. Idempotent/bounded: a task already refetched (or
with no resolvable Source) is a no-op. Commits."""
if task.refetched:
return {"status": "already_refetched"}
src = resolve_refetch_source(session, task.source_path, import_root)
if src is None:
return {"status": "no_source"}
# Remove the bad copy so gallery-dl (skip_existing) re-fetches it on
# the source re-check instead of skipping the still-present corrupt
# file.
try:
Path(task.source_path).unlink(missing_ok=True)
except OSError as exc:
log.warning("refetch unlink failed for %s: %s", task.source_path, exc)
task.refetched = True
session.add(task)
session.commit()
# Lazy import to avoid a tasks→services→tasks import cycle at module
# load. download_source.delay() is sync-safe in any context.
from ..tasks.download import download_source
download_source.delay(src.id)
return {"status": "refetch_queued", "source_id": src.id}