fix(importer): Source = one per (artist, platform), not one per post — filesystem importer's sidecar paths now reuse the artist's existing subscription Source (or create one synthetic anchor with enabled=False) instead of fabricating a new Source per post URL. Alembic 0022 consolidates existing per-post Sources to canonical (prefers campaign URL; falls back to sidecar:<platform>:<slug>) and re-parents Posts + ImageProvenance, merging Post collisions.

Operator-flagged 2026-05-26: Atole artist detail page showed 406 Sources where 1 was right.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-26 14:19:29 -04:00
parent 397021dcbd
commit 0bc5767a2b
3 changed files with 307 additions and 6 deletions
+65
View File
@@ -145,3 +145,68 @@ def test_find_or_create_source_recovers_from_integrity_error(
artist_id=artist_row.id, platform="patreon", url=canonical_url,
)
assert recovered.id == pre_existing.id
def test_source_for_sidecar_reuses_existing_subscription(
importer, artist_row, db_sync,
):
"""The filesystem-import sidecar resolver should attach to whatever
Source already exists for (artist, platform) — the canonical subscription
Source — regardless of its URL. Without this, every imported post
spawned its own Source row.
"""
canonical = Source(
artist_id=artist_row.id, platform="patreon",
url="https://www.patreon.com/cw/testartist", enabled=True,
)
db_sync.add(canonical)
db_sync.flush()
resolved = importer._source_for_sidecar(
artist_id=artist_row.id, platform="patreon",
artist_slug=artist_row.slug,
)
assert resolved.id == canonical.id
def test_source_for_sidecar_creates_synthetic_anchor_when_none_exists(
importer, artist_row, db_sync,
):
"""No subscription Source for this (artist, platform) yet. The helper
creates one synthetic anchor (enabled=False, url='sidecar:<plat>:<slug>')
so subsequent imports reuse it instead of spawning per-post Sources.
"""
resolved = importer._source_for_sidecar(
artist_id=artist_row.id, platform="pixiv",
artist_slug=artist_row.slug,
)
assert resolved.url == f"sidecar:pixiv:{artist_row.slug}"
assert resolved.enabled is False
assert resolved.artist_id == artist_row.id
assert resolved.platform == "pixiv"
# Second call returns the same row (no new Source spawned).
again = importer._source_for_sidecar(
artist_id=artist_row.id, platform="pixiv",
artist_slug=artist_row.slug,
)
assert again.id == resolved.id
def test_source_for_sidecar_distinct_platforms_distinct_anchors(
importer, artist_row, db_sync,
):
"""One synthetic anchor per (artist, platform). Different platforms get
different anchors even when no campaign Source exists for either.
"""
p = importer._source_for_sidecar(
artist_id=artist_row.id, platform="patreon",
artist_slug=artist_row.slug,
)
x = importer._source_for_sidecar(
artist_id=artist_row.id, platform="pixiv",
artist_slug=artist_row.slug,
)
assert p.id != x.id
assert p.platform == "patreon"
assert x.platform == "pixiv"