Files
FabledCurator/backend/app/services/artist_service.py
T
bvandeusen 7b2a2051e9
CI / lint (push) Failing after 2s
CI / frontend-build (push) Successful in 22s
CI / backend-lint-and-test (push) Successful in 35s
CI / integration (push) Successful in 3m19s
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>
2026-06-09 23:46:01 -04:00

304 lines
11 KiB
Python

"""Artist overview + paged images.
Images are linked to an artist through the provenance chain
Source(artist_id) -> ImageProvenance(source_id) -> ImageRecord. DISTINCT
guards against an image having several provenance rows for one artist.
Dates come from Post.post_date via ImageProvenance.post_id.
"""
from dataclasses import dataclass
from sqlalchemy import and_, case, func, or_, select
from sqlalchemy.dialects.postgresql import insert as pg_insert
from sqlalchemy.ext.asyncio import AsyncSession
from ..models import (
Artist,
ArtistVisit,
ImageProvenance,
ImageRecord,
Post,
Source,
Tag,
)
from ..models.tag import image_tag
from ..utils.slug import slugify
from .db_helpers import get_or_create
from .gallery_service import decode_cursor, encode_cursor, thumbnail_url
@dataclass(frozen=True)
class ArtistImagesPage:
images: list[dict]
next_cursor: str | None
class ArtistService:
def __init__(self, session: AsyncSession):
self.session = session
async def _artist_by_slug(self, slug: str) -> Artist | None:
return (
await self.session.execute(
select(Artist).where(Artist.slug == slug)
)
).scalar_one_or_none()
async def overview(self, slug: str) -> dict | None:
artist = await self._artist_by_slug(slug)
if artist is None:
return None
aid = artist.id
img_join = (
select(ImageRecord.id).where(ImageRecord.artist_id == aid)
)
image_count = (
await self.session.execute(
select(func.count(ImageRecord.id))
.where(ImageRecord.artist_id == aid)
)
).scalar_one()
# Posts under this artist that have at least one image attached.
# Use Post.artist_id (alembic 0030) for the artist filter; keep
# the ImageProvenance JOIN so date bounds reflect only image-
# bearing posts (matches the original semantic). NULL-source
# posts now surface too.
date_row = (
await self.session.execute(
select(func.min(Post.post_date), func.max(Post.post_date))
.select_from(Post)
.join(ImageProvenance, ImageProvenance.post_id == Post.id)
.where(Post.artist_id == aid)
)
).first()
dmin, dmax = date_row if date_row else (None, None)
cooccurring = (
await self.session.execute(
select(
Tag.id, Tag.name, Tag.kind,
func.count(image_tag.c.image_record_id).label("cnt"),
)
.select_from(Tag)
.join(image_tag, image_tag.c.tag_id == Tag.id)
.where(image_tag.c.image_record_id.in_(img_join))
.group_by(Tag.id, Tag.name, Tag.kind)
.order_by(func.count(image_tag.c.image_record_id).desc())
.limit(20)
)
).all()
sources = (
await self.session.execute(
select(
Source.id, Source.platform, Source.url,
func.count(func.distinct(ImageProvenance.image_record_id)).label("cnt"),
)
.select_from(Source)
.outerjoin(ImageProvenance, ImageProvenance.source_id == Source.id)
.where(Source.artist_id == aid)
.group_by(Source.id, Source.platform, Source.url)
.order_by(Source.id)
)
).all()
# Same Post.artist_id direct filter — counts NULL-source posts too.
month = func.date_trunc("month", Post.post_date).label("m")
activity = (
await self.session.execute(
select(month, func.count(func.distinct(ImageProvenance.image_record_id)))
.select_from(Post)
.join(ImageProvenance, ImageProvenance.post_id == Post.id)
.where(and_(Post.artist_id == aid, Post.post_date.isnot(None)))
.group_by(month)
.order_by(month)
)
).all()
post_count = (
await self.session.execute(
select(func.count(func.distinct(Post.id)))
.where(Post.artist_id == aid)
)
).scalar_one()
# Mark this artist as "visited now"; the returned count is what
# the operator should see in the banner ("N new since last
# visit"). Done LAST so the read aggregates above all see the
# pre-visit state (cosmetic — none depend on visit data).
unseen_at_visit = await self._mark_visited_returning_unseen(aid)
return {
"id": artist.id,
"name": artist.name,
"slug": artist.slug,
"is_subscription": bool(artist.is_subscription),
"image_count": int(image_count),
"post_count": int(post_count),
"unseen_count_at_visit": unseen_at_visit,
"date_range": {
"min": dmin.isoformat() if dmin else None,
"max": dmax.isoformat() if dmax else None,
},
"cooccurring_tags": [
{
"id": tid,
"name": name,
"kind": kind.value if hasattr(kind, "value") else kind,
"count": int(cnt),
}
for tid, name, kind, cnt in cooccurring
],
"sources": [
{
"id": sid,
"platform": platform,
"url": url,
"image_count": int(cnt),
}
for sid, platform, url, cnt in sources
],
"activity": [
{"month": m.isoformat(), "count": int(cnt)}
for m, cnt in activity
],
}
async def _mark_visited_returning_unseen(self, artist_id: int) -> int:
"""Read pre-visit `last_viewed_at`, count images added since,
then upsert `last_viewed_at = NOW()`. Returns the count BEFORE
the upsert so the banner has data to render.
Postgres UPSERT (`ON CONFLICT DO UPDATE`) keeps the write
atomic — no SELECT-then-INSERT race per
`reference_scalar_one_or_none_duplicates`.
"""
prev = (
await self.session.execute(
select(ArtistVisit.last_viewed_at).where(
ArtistVisit.artist_id == artist_id
)
)
).scalar_one_or_none()
count_stmt = select(func.count(ImageRecord.id)).where(
ImageRecord.artist_id == artist_id
)
if prev is not None:
count_stmt = count_stmt.where(ImageRecord.created_at > prev)
unseen = (await self.session.execute(count_stmt)).scalar_one()
upsert = pg_insert(ArtistVisit.__table__).values(artist_id=artist_id)
upsert = upsert.on_conflict_do_update(
index_elements=["artist_id"],
set_={"last_viewed_at": func.now()},
)
await self.session.execute(upsert)
await self.session.commit()
return int(unseen)
async def images(
self, slug: str, cursor: str | None, limit: int = 60
) -> ArtistImagesPage | None:
if limit < 1 or limit > 200:
raise ValueError("limit must be between 1 and 200")
artist = await self._artist_by_slug(slug)
if artist is None:
return None
# Dedupe via IN-subquery rather than JOIN + DISTINCT: an image can
# have several provenance rows for one artist, and SELECT DISTINCT
# over ImageRecord fails in Postgres because its json columns have
# no equality operator.
stmt = select(ImageRecord).where(
ImageRecord.artist_id == artist.id
)
if cursor:
cur_ts, cur_id = decode_cursor(cursor)
stmt = stmt.where(
or_(
ImageRecord.created_at < cur_ts,
and_(ImageRecord.created_at == cur_ts, ImageRecord.id < cur_id),
)
)
stmt = stmt.order_by(
ImageRecord.created_at.desc(), ImageRecord.id.desc()
).limit(limit + 1)
rows = (await self.session.execute(stmt)).scalars().all()
next_cursor = None
if len(rows) > limit:
last = rows[limit - 1]
next_cursor = encode_cursor(last.created_at, last.id)
rows = rows[:limit]
return ArtistImagesPage(
images=[
{
"id": r.id,
"sha256": r.sha256,
"mime": r.mime,
"width": r.width,
"height": r.height,
"thumbnail_url": thumbnail_url(r.thumbnail_path, r.sha256, r.mime),
}
for r in rows
],
next_cursor=next_cursor,
)
async def find_or_create(self, name: str) -> tuple[Artist, bool]:
"""Return (artist, created). Slug-keyed; idempotent under races via the
shared race-safe db_helpers.get_or_create (savepoint + IntegrityError
recovery). A new artist also seeds an ArtistVisit so the directory's
`+N new` badge starts at 0.
"""
cleaned = (name or "").strip()
if not cleaned:
raise ValueError("artist name must not be empty")
slug = slugify(cleaned)
select_existing = select(Artist).where(Artist.slug == slug)
async def _create() -> Artist:
artist = Artist(name=cleaned, slug=slug)
self.session.add(artist)
await self.session.flush()
# New artist starts "caught up" — seed ArtistVisit so the
# directory's `+N new` badge stays at 0 until real new
# content arrives. Without this, the unseen-count query
# treats NULL last_viewed_at as "never visited" and would
# count every image imported in the same session.
self.session.add(ArtistVisit(artist_id=artist.id))
await self.session.flush()
return artist
artist, created = await get_or_create(
self.session, select_existing, _create
)
if created:
await self.session.commit()
return artist, created
async def autocomplete(self, prefix: str, limit: int = 20) -> list[Artist]:
cleaned = (prefix or "").strip()
if not cleaned:
return []
like = f"%{cleaned.lower()}%"
prefix_like = f"{cleaned.lower()}%"
# Rank: exact (0) < prefix (1) < substring (2).
rank = case(
(func.lower(Artist.name) == cleaned.lower(), 0),
(func.lower(Artist.name).like(prefix_like), 1),
else_=2,
).label("rank")
rows = (await self.session.execute(
select(Artist, rank)
.where(func.lower(Artist.name).like(like))
.order_by(rank, Artist.name.asc())
.limit(limit)
)).all()
return [a for a, _ in rows]