Files
FabledCurator/backend/app/services/extension_service.py
T
bvandeusen 96fffaff64
CI / lint (push) Successful in 2s
CI / backend-lint-and-test (push) Successful in 11s
CI / frontend-build (push) Successful in 17s
CI / integration (push) Successful in 2m58s
feat(download): smarter backfill — time-boxed chunks, run-until-done (backend)
Plan #693. Large-catalog backfill (Anduo) no longer sprints to the timeout
wall and dies as an error each run. Builds on the cursor checkpoint (#689).

- Time-boxed chunks: BACKFILL_TIMEOUT_SECONDS(1170)→BACKFILL_CHUNK_SECONDS(600),
  far under the 1350 soft limit. Hitting it = normal chunk boundary (the
  TimeoutExpired path already captures partial output + the cursor), not a
  near-wall death.
- Run-until-done state machine driven by config_overrides[_backfill_state]
  (running/complete/stalled). A running backfill auto-continues in chunks
  across ticks until gallery-dl exits cleanly (rc=0 = reached the bottom →
  'complete'); a safety-cap (BACKFILL_MAX_CHUNKS=200) + the #689 stall-guard
  pause a pathological walk as 'stalled'. Replaces the N-runs counter
  (backfill_runs_remaining repurposed as the cap countdown).
- Progress, not error: a chunk that timed out but advanced (cursor moved
  and/or files written) is reclassified TIMEOUT→PARTIAL (status 'ok').
- Retry storm tamed: gallery-dl retries 3→2, downloader timeout 120→60s, so
  one stuck CDN file fails in ~1-2 min not ~10 (Anduo #40838).
- API: POST /sources/{id}/backfill now takes {action: start|stop}; service
  start_backfill/stop_backfill; new enabled sources auto-arm run-until-done;
  source dict exposes backfill_state + backfill_chunks.

Frontend (Start/Stop control + state badge) lands in the next push.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-05 15:02:46 -04:00

235 lines
8.7 KiB
Python

"""FC-3g: backend support for the Firefox extension.
`ExtensionService.quick_add_source(url)` derives platform + artist
slug from a URL using regex patterns mirrored from
extension/lib/platforms.js, then find-or-creates Artist + Source rows
and returns a JSON-shaped dict for the API layer.
"""
from __future__ import annotations
import re
from sqlalchemy import select
from sqlalchemy.exc import IntegrityError
from sqlalchemy.ext.asyncio import AsyncSession
from ..models import Artist, Source
from ..utils.slug import slugify
from .source_service import BACKFILL_MAX_CHUNKS
class UnknownPlatformError(Exception):
"""URL didn't match any platform pattern."""
class InvalidUrlError(Exception):
"""URL was empty or missing a scheme."""
# Mirrored byte-for-byte from extension/lib/platforms.js
# PLATFORM_ARTIST_PATTERNS. Keep these two copies in sync by hand —
# reviewers catch drift.
_PLATFORM_PATTERNS: list[tuple[str, re.Pattern[str]]] = [
("patreon", re.compile(
r"^https?://(?:www\.)?patreon\.com/"
r"(?!home$|search\b|messages\b|notifications\b|library\b|settings\b|posts\b|c/)"
r"(?P<slug>[^/?#]+)/?$",
re.IGNORECASE,
)),
("subscribestar", re.compile(
r"^https?://(?:www\.)?subscribestar\.(?:com|adult)/"
r"(?!feed$|messages$|library$)"
r"(?P<slug>[^/?#]+)/?$",
re.IGNORECASE,
)),
("hentaifoundry", re.compile(
r"^https?://(?:www\.)?hentai-foundry\.com/user/(?P<slug>[^/?#]+)",
re.IGNORECASE,
)),
("deviantart", re.compile(
r"^https?://(?:www\.)?deviantart\.com/"
r"(?!home$|watch\b|tag\b|browse\b)"
r"(?P<slug>[^/?#]+)/?$",
re.IGNORECASE,
)),
("pixiv", re.compile(
r"^https?://(?:www\.)?pixiv\.net/(?:en/)?users/(?P<slug>\d+)",
re.IGNORECASE,
)),
]
class ExtensionService:
def __init__(self, session: AsyncSession) -> None:
self.session = session
async def quick_add_source(self, url: str) -> dict:
platform, raw_slug = self._derive(url)
artist, created_artist = await self._find_or_create_artist(raw_slug)
source, created_source = await self._find_or_create_source(
artist_id=artist.id, platform=platform, url=url,
)
return {
"source": {
"id": source.id,
"artist_id": source.artist_id,
"platform": source.platform,
"url": source.url,
"enabled": source.enabled,
},
"artist": {
"id": artist.id,
"name": artist.name,
"slug": artist.slug,
},
"created_source": created_source,
"created_artist": created_artist,
}
async def probe(self, url: str) -> dict:
"""Read-only resolution of a creator-page URL against the FC DB.
Returns one of:
- {state: 'unknown_platform'} — URL didn't match any
platform's strict artist-page pattern
- {state: 'new', platform, slug} — would create both
artist and source on quick-add
- {state: 'artist_match', platform, slug, artist}
— artist exists, this
exact URL isn't a Source yet (collapses the sidecar-synthetic
case too — the synthetic anchor counts as an existing artist
row but not as a pollable Source for this URL)
- {state: 'source_match', platform, slug, artist, source}
— exact (artist, platform,
url) Source already exists
Side-effect-free: two SELECTs at most.
"""
try:
platform, raw_slug = self._derive(url)
except (UnknownPlatformError, InvalidUrlError):
return {"state": "unknown_platform"}
slug = slugify(raw_slug)
artist = (await self.session.execute(
select(Artist).where(Artist.slug == slug)
)).scalar_one_or_none()
if artist is None:
return {"state": "new", "platform": platform, "slug": slug}
artist_payload = {"id": artist.id, "name": artist.name, "slug": artist.slug}
source = (await self.session.execute(
select(Source).where(
Source.artist_id == artist.id,
Source.platform == platform,
Source.url == url,
)
)).scalar_one_or_none()
if source is None:
return {
"state": "artist_match",
"platform": platform,
"slug": slug,
"artist": artist_payload,
}
return {
"state": "source_match",
"platform": platform,
"slug": slug,
"artist": artist_payload,
"source": {
"id": source.id,
"artist_id": source.artist_id,
"platform": source.platform,
"url": source.url,
"enabled": source.enabled,
},
}
def _derive(self, url: str) -> tuple[str, str]:
if not isinstance(url, str) or not url.strip():
raise InvalidUrlError("url is empty")
if not url.startswith(("http://", "https://")):
raise InvalidUrlError(f"url must include http:// or https:// scheme: {url!r}")
for platform, pattern in _PLATFORM_PATTERNS:
m = pattern.match(url)
if m:
return platform, m.group("slug")
raise UnknownPlatformError(f"no platform pattern matched {url!r}")
async def _find_or_create_artist(self, raw_name: str) -> tuple[Artist, bool]:
"""Race-safe find-or-create on Artist by slug. Mirrors the
savepoint + IntegrityError recovery pattern used in
Importer._find_or_create_source/post (see
reference_scalar_one_or_none_duplicates memory). Without this,
two concurrent quick-add-source calls hitting the same artist
would both miss the existence check and the second INSERT would
500 against uq_artist_slug.
"""
slug = slugify(raw_name)
existing = (await self.session.execute(
select(Artist).where(Artist.slug == slug)
)).scalar_one_or_none()
if existing is not None:
return existing, False
sp = await self.session.begin_nested()
try:
artist = Artist(name=raw_name, slug=slug, is_subscription=True)
self.session.add(artist)
await self.session.flush()
await sp.commit()
return artist, True
except IntegrityError:
await sp.rollback()
recovered = (await self.session.execute(
select(Artist).where(Artist.slug == slug)
)).scalar_one()
return recovered, False
async def _find_or_create_source(
self, *, artist_id: int, platform: str, url: str,
) -> tuple[Source, bool]:
"""Race-safe — same pattern as _find_or_create_artist above. The
uq_source_artist_platform_url constraint catches the duplicate
insert; we roll the savepoint back and re-select."""
existing = (await self.session.execute(
select(Source).where(
Source.artist_id == artist_id,
Source.platform == platform,
Source.url == url,
)
)).scalar_one_or_none()
if existing is not None:
return existing, False
sp = await self.session.begin_nested()
try:
# New subscription sources arm run-until-done backfill (plan #693)
# so the first ticks walk the full history (otherwise gallery-dl's
# exit:20 short-circuits before the archive is built). Mirrors
# SourceService.create — without it, Firefox quick-add on a creator
# with >20 unsynced posts would surface as "check failed" with no
# diagnosis. Audit 2026-06-02.
src = Source(
artist_id=artist_id, platform=platform,
url=url, enabled=True,
config_overrides={"_backfill_state": "running"},
backfill_runs_remaining=BACKFILL_MAX_CHUNKS,
)
self.session.add(src)
await self.session.flush()
await sp.commit()
except IntegrityError:
await sp.rollback()
recovered = (await self.session.execute(
select(Source).where(
Source.artist_id == artist_id,
Source.platform == platform,
Source.url == url,
)
)).scalar_one()
return recovered, False
await self.session.commit()
return src, True