bvandeusen/FabledCurator
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases 35 Wiki Activity

fix(migration-0022): pre-merge ALL duplicate-external_post_id Posts across the (canonical+others) group, not just canonical-vs-others — operator's v26.05.26.2 deploy still tripped uq_post_source_external_id because two non-canonical Sources both had Posts with epid=6166997. Bulk UPDATE moved the first cleanly then collided on the second. New pre-merge groups all Posts in the (artist, platform) by external_post_id; for any group with count>1, picks the keep (prefer one under canonical; else lowest id) and merges the rest before the bulk reparent.

Browse Source 
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Bryan Van Deusen
2026-05-26 17:52:29 -04:00
parent 1803a09306
commit 7a64730bd2
1 changed files with 60 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files
alembic/versions/0022_source_per_artist_platform.py
+60 -45
View File
@@ -83,55 +83,70 @@ def upgrade() -> None:
if not other_ids: if not other_ids:
continue continue
# STEP 2: PRE-merge colliding Posts BEFORE the bulk reparent. # STEP 2: PRE-merge ALL Posts with duplicate external_post_id
# Find pairs (keep, drop) where: # across the entire (canonical + others) group, BEFORE the bulk
# keep = a Post under the canonical source # reparent. Two cases must both be handled:
# drop = a Post under one of the non-canonical sources whose # (A) canonical has Post X with epid=N; an "other" source has
# external_post_id equals keep.external_post_id # Post Y with epid=N → after bulk UPDATE, (canonical, N)
# If we let the bulk UPDATE try to repoint drop onto canonical, # collides with itself.
# uq_post_source_external_id fires row-by-row and aborts the # (B) two different "other" sources each have a Post with
# whole migration. # epid=N; canonical has none → after bulk UPDATE, both
colliding = conn.execute( # are repointed to (canonical, N) and the second collides.
# The earlier version of this migration only handled (A); the
# operator's deploy 2026-05-26 tripped (B) at line 139.
# Fix: group ALL Posts in the (artist, platform) by epid; for
# any group with count>1, pick the keep (prefer one already
# under canonical; else lowest id) and merge the rest into it.
all_posts = conn.execute(
text(""" text("""
SELECT keep.id AS keep_id, drop_.id AS drop_id SELECT external_post_id, id, source_id
FROM post AS keep FROM post
JOIN post AS drop_ WHERE source_id = :canonical OR source_id = ANY(:others)
ON drop_.external_post_id = keep.external_post_id ORDER BY external_post_id, id
AND drop_.id != keep.id
WHERE keep.source_id = :canonical
AND drop_.source_id = ANY(:others)
"""), """),
{"canonical": canonical_id, "others": other_ids}, {"canonical": canonical_id, "others": other_ids},
).fetchall() ).fetchall()
for keep_id, drop_id in colliding: by_epid: dict = {}
conn.execute( for epid, post_id, src_id in all_posts:
text(""" by_epid.setdefault(epid, []).append((post_id, src_id))
UPDATE image_provenance SET post_id = :keep for epid, posts in by_epid.items():
WHERE post_id = :drop_ if len(posts) <= 1:
"""), continue
{"keep": keep_id, "drop_": drop_id}, # Prefer a Post already under canonical as the keep.
) canonical_posts = [p for p in posts if p[1] == canonical_id]
conn.execute( if canonical_posts:
text(""" keep_id = canonical_posts[0][0]
UPDATE image_record SET primary_post_id = :keep else:
WHERE primary_post_id = :drop_ keep_id = posts[0][0] # already sorted by id ASC
"""), drop_ids = [p[0] for p in posts if p[0] != keep_id]
{"keep": keep_id, "drop_": drop_id}, for drop_id in drop_ids:
) conn.execute(
# Repointed provenance may now collide on text("""
# uq_image_provenance_image_post (alembic 0021). Dedupe: UPDATE image_provenance SET post_id = :keep
# keep min(id) per (image_record_id, post_id). WHERE post_id = :drop_
conn.execute(text(""" """),
DELETE FROM image_provenance ip1 {"keep": keep_id, "drop_": drop_id},
USING image_provenance ip2 )
WHERE ip1.image_record_id = ip2.image_record_id conn.execute(
AND ip1.post_id = ip2.post_id text("""
AND ip1.id > ip2.id UPDATE image_record SET primary_post_id = :keep
""")) WHERE primary_post_id = :drop_
conn.execute( """),
text("DELETE FROM post WHERE id = :drop_"), {"keep": keep_id, "drop_": drop_id},
{"drop_": drop_id}, )
) # Repointed provenance may now collide on
# uq_image_provenance_image_post (alembic 0021). Dedupe.
conn.execute(text("""
DELETE FROM image_provenance ip1
USING image_provenance ip2
WHERE ip1.image_record_id = ip2.image_record_id
AND ip1.post_id = ip2.post_id
AND ip1.id > ip2.id
"""))
conn.execute(
text("DELETE FROM post WHERE id = :drop_"),
{"drop_": drop_id},
)
# STEP 3: Bulk reparent the remaining Posts off the other # STEP 3: Bulk reparent the remaining Posts off the other
# Sources. After step 2, no collisions on # Sources. After step 2, no collisions on