0e64d439c4
Replace the JSON-file pipeline with a SQLite/SQLAlchemy store (Postgres via DATABASE_URL) and an incremental, ID-based matcher whose goal is "which Spotify/iTunes tracks am I missing locally". - src/db: models (Track/MbCache/FileState/IngestState) + engine/session. - src/ingest: upsert prefetched spotify/itunes/local (work_dir/latest-1) by (source, source_id); pulls ISRC from raw Spotify; preserves enrichment. - src/enrich: MusicBrainz recording-MBID resolver. Resolves via NORMALIZED text search (so the same song across sources lands on one MBID + one cached lookup), ISRC as exact fallback. Only touches unresolved tracks, caches positive AND negative results, rate-limited and resumable. - src/match: normalization + cross-source matcher with tiers ISRC > MBID > normalized text; reports present/missing and the match method. - main.py: CLI (ingest / enrich / match). Gui.py: missing-tracks viewer. - README + requirements (SQLAlchemy, musicbrainzngs); ignore *.db. Incremental everywhere: re-running updates only what changed; enrich continues where it stopped. Live Spotify/local backends are left intact. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
78 lines
2.3 KiB
Python
78 lines
2.3 KiB
Python
"""MusicIndexer pipeline CLI.
|
|
|
|
Everything is incremental and DB-backed (see Env.database_url). Typical flow:
|
|
|
|
python main.py ingest # load prefetched data into the DB (upsert)
|
|
python main.py enrich # resolve recording MBIDs (resumable, cached)
|
|
python main.py match # print present/missing summary
|
|
./gui.sh # browse what you're missing
|
|
|
|
`enrich` only queries MusicBrainz for still-unresolved tracks, so re-running it
|
|
just continues where it stopped.
|
|
"""
|
|
import argparse
|
|
import json
|
|
|
|
from src.db.database import init_db
|
|
|
|
|
|
def cmd_init(args):
|
|
init_db()
|
|
print("Database initialized.")
|
|
|
|
|
|
def cmd_ingest(args):
|
|
init_db()
|
|
from src.ingest.ingest import ingest_all
|
|
|
|
results = ingest_all()
|
|
for source, (new, updated) in results.items():
|
|
print(f"{source:8} +{new} new, {updated} updated")
|
|
|
|
|
|
def cmd_enrich(args):
|
|
init_db()
|
|
from src.enrich.mbid import resolve_mbids, unresolved_count
|
|
|
|
print(f"unresolved before: {unresolved_count(args.source)}")
|
|
stats = resolve_mbids(limit=args.limit, source=args.source)
|
|
print(f"resolved this run: {stats}")
|
|
print(f"unresolved after: {unresolved_count(args.source)}")
|
|
|
|
|
|
def cmd_match(args):
|
|
from src.match.matcher import summary
|
|
|
|
print(json.dumps(summary(), indent=2))
|
|
|
|
|
|
def build_parser():
|
|
parser = argparse.ArgumentParser(prog="musicindexer", description=__doc__)
|
|
sub = parser.add_subparsers(dest="cmd", required=True)
|
|
|
|
sub.add_parser("init", help="create database tables")
|
|
sub.add_parser("ingest", help="load prefetched JSON into the DB (upsert)")
|
|
|
|
enrich = sub.add_parser("enrich", help="resolve MBIDs for unresolved tracks")
|
|
enrich.add_argument("--limit", type=int, default=None,
|
|
help="cap how many tracks to resolve this run")
|
|
enrich.add_argument("--source", choices=["spotify", "itunes", "local"],
|
|
default=None, help="restrict to one source")
|
|
|
|
sub.add_parser("match", help="print present/missing summary")
|
|
return parser
|
|
|
|
|
|
def main():
|
|
args = build_parser().parse_args()
|
|
handlers = {
|
|
"init": cmd_init,
|
|
"ingest": cmd_ingest,
|
|
"enrich": cmd_enrich,
|
|
"match": cmd_match,
|
|
}
|
|
handlers[args.cmd](args)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|