RECORDGOD/build_disc_cache.py
type-two 5c10bdc06d feat: self-contained enrichment — disc_cache (own catalog copy), no external DB dependency
- schema: disc_cache (release_id→title/artist/thumb/weight); build_disc_cache.py populates it
  from the full Discogs dump on ultra (30,694 stocked releases).
- app/mirror.py: enrich() now reads RecordGod's OWN disc_cache via the main DB — no live
  discogs_full / dealgod-DB dependency. DealGod reached only via API key.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-21 13:16:56 +10:00

37 lines
1.4 KiB
Python

#!/usr/bin/env python3
"""Populate recordgod.disc_cache from the full Discogs mirror — RecordGod's own copy of just
the releases it stocks, so enrichment has no live cross-DB dependency. Run on ultra (where
discogs_full lives); re-run anytime to refresh for current inventory."""
import os
import psycopg
RG = os.getenv("RECORDGOD_DSN", "postgresql://localhost/recordgod")
DG = os.getenv("DISCOGS_FULL_DSN", "postgresql://localhost/discogs_full")
def main():
rg = psycopg.connect(RG)
dg = psycopg.connect(DG)
ids = [r[0] for r in rg.execute(
"SELECT DISTINCT release_id FROM inventory WHERE release_id IS NOT NULL").fetchall()]
rg.execute("""CREATE TABLE IF NOT EXISTS disc_cache (
release_id bigint PRIMARY KEY, title text, artist text, thumb text, weight int)""")
rg.execute("TRUNCATE disc_cache")
n = 0
for i in range(0, len(ids), 5000):
rows = dg.execute(
"SELECT id, title, artists_sort, COALESCE(thumb_local_url, thumb), estimated_weight "
"FROM release WHERE id = ANY(%s)", (ids[i:i + 5000],)).fetchall()
with rg.cursor() as c:
c.executemany(
"INSERT INTO disc_cache (release_id, title, artist, thumb, weight) "
"VALUES (%s,%s,%s,%s,%s) ON CONFLICT (release_id) DO NOTHING", rows)
n += len(rows)
rg.commit()
print(f"disc_cache: {n} of {len(ids)} stocked releases cached")
if __name__ == "__main__":
main()