Files
FabledCurator/tests/test_source_service.py
T
bvandeusen 19aece1fc4
CI / lint (push) Successful in 3s
CI / backend-lint-and-test (push) Successful in 16s
CI / frontend-build (push) Successful in 27s
CI / intimp (push) Successful in 3m42s
CI / intapi (push) Successful in 7m38s
CI / intcore (push) Successful in 8m20s
feat(download): tick/backfill modes + partial-success classifier (plan #544)
Routine subscription polls walked the entire post history every tick
even when nothing had changed, because gallery-dl's default `skip: True`
continues iterating archived posts. A creator with ~550 archived posts
(Knuxy patreon) saturates the 870s wall-clock cap before completing,
even with zero downloads needed. Plus, a tier-limited run that
downloaded hundreds of files but ran out the clock should be a
warning, not an error.

Two coupled changes, both operator-flagged 2026-06-01:

* **Tick mode (default, cron polls).** New `TICK_SKIP_VALUE = "exit:20"`
  asks gallery-dl to exit after 20 contiguous archived items. Fresh
  subscriptions + new-content cases still walk normally; established
  subscription with zero new content exits in ~30s of HEAD requests
  instead of pegging the timeout. 20 (not 5) gives headroom against
  paywall warnings interleaving with archived items.
* **Backfill mode (explicit, operator-triggered).** Sticky for N runs
  via new `Source.backfill_runs_remaining` (alembic 0031). While > 0,
  downloads use `skip: True` + 1800s timeout. Auto-decrements per run
  with early-reset to 0 when a clean run finds zero files (queue
  drained). N defaults to 3 — multiple runs give the system enough
  budget to finish a deep walk across timeout boundaries. New
  `POST /api/sources/{id}/backfill` arms the source; "Deep scan"
  button on each SourceRow (chip shows remaining count) wires it.

Plus partial-success classifier: non-zero gallery-dl exit + ≥1 file
downloaded + no source-level error fires `ErrorType.PARTIAL`, which
download_service maps to `status=\"ok\"`. The run did real work; the
next tick continues via gallery-dl's archive. No more red events for
"timed out mid-walk after downloading 300 files."

Retires `SourceConfig.skip_existing` — skip value is now derived from
the source state and passed as a separate `skip_value` parameter
through download() / _build_config_for_source(). `GD_DEFAULTS` drops
the now-dead key (was inert data after this refactor).

Tests cover:
* tick + backfill skip-value emission in _build_config_for_source
* PARTIAL classifier branch + TIER_LIMITED-wins-over-PARTIAL ordering
* SourceService.set_backfill_runs validation + persistence
* /api/sources/{id}/backfill 200/400/404 paths
* download_service auto-decrement / auto-reset / tick-mode-no-touch
* PARTIAL → status=ok in the orchestrator (no consecutive_failures bump)
2026-06-01 18:23:28 -04:00

216 lines
6.8 KiB
Python

import pytest
from sqlalchemy import select
from backend.app.models import Artist, Source
from backend.app.services.source_service import (
KNOWN_PLATFORMS,
ArtistNotFoundError,
DuplicateSourceError,
EmptyUrlError,
InvalidConfigError,
SourceService,
UnknownPlatformError,
)
pytestmark = pytest.mark.integration
async def _artist(db, name="Alice"):
a = Artist(name=name, slug=name.lower())
db.add(a)
await db.flush()
return a
@pytest.mark.asyncio
async def test_known_platforms_is_gs_six(db):
assert KNOWN_PLATFORMS == frozenset({
"patreon", "subscribestar", "hentaifoundry",
"discord", "pixiv", "deviantart",
})
assert "fanbox" not in KNOWN_PLATFORMS
@pytest.mark.asyncio
async def test_create_flips_is_subscription_on_first_source(db):
artist = await _artist(db)
svc = SourceService(db)
rec = await svc.create(
artist_id=artist.id, platform="patreon", url="https://patreon.com/alice",
)
assert rec.id is not None
is_sub = (await db.execute(
select(Artist.is_subscription).where(Artist.id == artist.id)
)).scalar_one()
assert is_sub is True
@pytest.mark.asyncio
async def test_delete_last_source_flips_is_subscription_off(db):
artist = await _artist(db)
svc = SourceService(db)
rec = await svc.create(
artist_id=artist.id, platform="patreon", url="https://patreon.com/alice",
)
await svc.delete(rec.id)
is_sub = (await db.execute(
select(Artist.is_subscription).where(Artist.id == artist.id)
)).scalar_one()
assert is_sub is False
@pytest.mark.asyncio
async def test_create_rejects_unknown_platform(db):
artist = await _artist(db)
svc = SourceService(db)
with pytest.raises(UnknownPlatformError):
await svc.create(
artist_id=artist.id, platform="myspace", url="https://m/x",
)
@pytest.mark.asyncio
async def test_create_rejects_non_dict_config(db):
artist = await _artist(db)
svc = SourceService(db)
with pytest.raises(InvalidConfigError):
await svc.create(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice", config_overrides=[1, 2, 3],
)
@pytest.mark.asyncio
async def test_create_rejects_empty_url(db):
artist = await _artist(db)
svc = SourceService(db)
with pytest.raises(EmptyUrlError):
await svc.create(artist_id=artist.id, platform="patreon", url=" ")
@pytest.mark.asyncio
async def test_create_rejects_unknown_artist(db):
svc = SourceService(db)
with pytest.raises(ArtistNotFoundError):
await svc.create(artist_id=99999, platform="patreon", url="https://x/y")
@pytest.mark.asyncio
async def test_create_duplicate_raises_with_existing_id(db):
artist = await _artist(db)
svc = SourceService(db)
first = await svc.create(
artist_id=artist.id, platform="patreon", url="https://patreon.com/alice",
)
with pytest.raises(DuplicateSourceError) as exc:
await svc.create(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice",
)
assert exc.value.existing_id == first.id
@pytest.mark.asyncio
async def test_list_filters_by_artist(db):
a = await _artist(db, "Alice")
b = await _artist(db, "Bob")
svc = SourceService(db)
await svc.create(artist_id=a.id, platform="patreon", url="https://patreon.com/a")
await svc.create(artist_id=b.id, platform="patreon", url="https://patreon.com/b")
only_a = await svc.list(artist_id=a.id)
assert [s.artist_id for s in only_a] == [a.id]
all_rows = await svc.list()
assert len(all_rows) == 2
@pytest.mark.asyncio
async def test_update_changes_fields(db):
artist = await _artist(db)
svc = SourceService(db)
rec = await svc.create(
artist_id=artist.id, platform="patreon", url="https://patreon.com/a",
)
updated = await svc.update(rec.id, enabled=False, config_overrides={"videos": False})
assert updated.enabled is False
assert updated.config_overrides == {"videos": False}
@pytest.mark.asyncio
async def test_list_hides_sidecar_synthetic_anchors(db):
"""Filesystem-import synthetic Sources (url='sidecar:<platform>:<slug>',
enabled=False — historical pre-alembic-0030 artifact) used to leak into the
Subscriptions UI as phantom subscriptions because list() didn't filter
them. They aren't pollable feeds; hide by default."""
artist = await _artist(db, "Alice")
real = Source(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice", enabled=True, config_overrides={},
)
synthetic = Source(
artist_id=artist.id, platform="patreon",
url="sidecar:patreon:alice", enabled=False, config_overrides={},
)
db.add_all([real, synthetic])
await db.commit()
svc = SourceService(db)
visible = await svc.list()
visible_urls = {s.url for s in visible}
assert "https://patreon.com/alice" in visible_urls
assert "sidecar:patreon:alice" not in visible_urls
# Same filter applies to the artist-scoped list path (the artist detail
# page hits /api/sources?artist_id=N).
artist_scoped = await svc.list(artist_id=artist.id)
assert {s.url for s in artist_scoped} == {"https://patreon.com/alice"}
# include_synthetic=True opts back in for admin tooling.
everything = await svc.list(include_synthetic=True)
assert {s.url for s in everything} >= {
"https://patreon.com/alice", "sidecar:patreon:alice",
}
# --- Plan #544: backfill counter -------------------------------------------
@pytest.mark.asyncio
async def test_set_backfill_runs_arms_source(db):
"""The service method sets backfill_runs_remaining and returns the
updated record so the API can echo it back."""
artist = await _artist(db, "Alice")
svc = SourceService(db)
rec = await svc.create(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice",
)
assert rec.backfill_runs_remaining == 0
updated = await svc.set_backfill_runs(rec.id, 5)
assert updated.backfill_runs_remaining == 5
db_value = (await db.execute(
select(Source.backfill_runs_remaining).where(Source.id == rec.id)
)).scalar_one()
assert db_value == 5
@pytest.mark.asyncio
async def test_set_backfill_runs_rejects_out_of_range(db):
artist = await _artist(db, "Alice")
svc = SourceService(db)
rec = await svc.create(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice",
)
with pytest.raises(ValueError):
await svc.set_backfill_runs(rec.id, 0)
with pytest.raises(ValueError):
await svc.set_backfill_runs(rec.id, 11)
@pytest.mark.asyncio
async def test_set_backfill_runs_raises_when_source_missing(db):
svc = SourceService(db)
with pytest.raises(LookupError):
await svc.set_backfill_runs(99999, 3)