#!/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):
        # artists_sort is NULL for most of this dump (~9.1M of 10.4M releases), and reading it
        # alone silently cached a NULL artist — which is not merely a blank column in the admin
        # list: dc.artist is also what the admin SEARCH and SORT run on, so an affected record
        # becomes unfindable by artist name. Seen live on release 447087, cached as title
        # "Mezcal" with no artist while its genre/style/label/country all populated, because
        # those read disc_release_* and only the artist reads this cache.
        #
        # The name is in release_artist regardless. extra=0 is the RELEASE artist; extra=1 rows
        # are credits — 447087 also lists Carl Clarke and Jim Eliot as Producers, and folding
        # those into the artist name would be worse than leaving it blank.
        #
        # Comma-joined rather than reconstructing Discogs' join_string ("&", "Featuring"): this
        # only fires where artists_sort is already NULL, and a predictable "A, B" beats both NULL
        # and a dangling separator.
        rows = dg.execute(
            "SELECT r.id, r.title, "
            "       COALESCE(r.artists_sort, ("
            "         SELECT string_agg(ra.artist_name, ', ' ORDER BY ra.position, ra.id) "
            "         FROM release_artist ra "
            "         WHERE ra.release_id = r.id AND ra.extra = 0)), "
            "       COALESCE(r.thumb_local_url, r.thumb), r.estimated_weight "
            "FROM release r WHERE r.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()