refactor(services): shared race-safe get_or_create helper (DRY backend sweep)
The find-or-create dance — SELECT, then a SAVEPOINT INSERT that recovers (not a full rollback) on IntegrityError when a concurrent worker inserted first — was hand-rolled identically in 4 async sites: ArtistService.find_or_create, TagService.find_or_create, ExtensionService._find_or_create_artist and ._find_or_create_source. Divergent copies of exactly this pattern are how the duplicate-row/race bugs in reference_scalar_one_or_none_duplicates crept in, so it now lives once in services/db_helpers.get_or_create (returns (row, created); factory adds+flushes+returns the row; caller owns the outer commit). Over-DRY guard: SourceService's IntegrityError sites RAISE DuplicateSourceError (reject-on-conflict, a different concept) — left alone. Importer._get_or_create is the lone SYNC consumer (already shared by 2 callers) — stays separate, can't cross the sync/async boundary. §8b: no hand-rolled async find-or-create remains. Test: get_or_create creates then returns existing without re-invoking the factory. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -11,11 +11,11 @@ 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 .db_helpers import get_or_create
|
||||
from .source_service import BACKFILL_MAX_CHUNKS
|
||||
|
||||
|
||||
@@ -169,24 +169,16 @@ class ExtensionService:
|
||||
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:
|
||||
|
||||
async def _create() -> Artist:
|
||||
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
|
||||
return artist
|
||||
|
||||
return await get_or_create(
|
||||
self.session, select(Artist).where(Artist.slug == slug), _create
|
||||
)
|
||||
|
||||
async def _find_or_create_source(
|
||||
self, *, artist_id: int, platform: str, url: str,
|
||||
@@ -194,17 +186,13 @@ class ExtensionService:
|
||||
"""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:
|
||||
select_existing = select(Source).where(
|
||||
Source.artist_id == artist_id,
|
||||
Source.platform == platform,
|
||||
Source.url == url,
|
||||
)
|
||||
|
||||
async def _create() -> Source:
|
||||
# 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
|
||||
@@ -219,16 +207,11 @@ class ExtensionService:
|
||||
)
|
||||
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
|
||||
return src
|
||||
|
||||
src, created = await get_or_create(
|
||||
self.session, select_existing, _create
|
||||
)
|
||||
if created:
|
||||
await self.session.commit()
|
||||
return src, created
|
||||
|
||||
Reference in New Issue
Block a user