MusicIndexer/main.py
Шурупов Илья Викторович ca1ca74244 Incremental Spotify ingest + --no-enrich
- spotify_raw: skip re-ingesting when the cache files are unchanged (signature
  in ingest_state), matching the iTunes/local incremental behaviour — so a
  re-run with no changes touches nothing.
- fetch --no-enrich: skip MusicBrainz enrichment and rely on MBIDs already on
  tracks (e.g. local Picard tags).

Verified on the real library: 1st run ~9s, unchanged re-run ~0.3s with all
three sources skipping; with enrichment off, 1164 Spotify tracks still match
locally by ISRC/MBID from tags.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-15 02:04:54 +03:00

81 lines
2.4 KiB
Python

"""MusicIndexer CLI. Two main workflows plus granular helpers.
python main.py fetch # do all the work: pull + scan + parse + enrich + match
python main.py display # open the GUI to see what you're missing
`fetch` is incremental and DB-backed (see Env.py): the first run is slow
(initial scan + MusicBrainz lookups), later runs only touch what changed.
Helpers: `enrich` (resume MBID resolution), `match` (print the summary).
"""
import argparse
import logging
def _setup_logging():
logging.basicConfig(level=logging.INFO, format="%(message)s")
def cmd_fetch(args):
_setup_logging()
from src.workflows import run_fetch
run_fetch(enrich_limit=args.enrich_limit, enrich=not args.no_enrich)
def cmd_display(args):
from src.workflows import run_display
run_display()
def cmd_enrich(args):
_setup_logging()
from src.db.database import init_db
from src.enrich.mbid import resolve_mbids, unresolved_count
init_db()
print(f"unresolved before: {unresolved_count(args.source)}")
print(f"resolved this run: {resolve_mbids(limit=args.limit, source=args.source)}")
print(f"unresolved after: {unresolved_count(args.source)}")
def cmd_match(args):
import json
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)
fetch = sub.add_parser("fetch", help="incrementally fetch + scan + enrich + match")
fetch.add_argument("--enrich-limit", type=int, default=None,
help="cap MBID lookups this run (default: resolve all)")
fetch.add_argument("--no-enrich", action="store_true",
help="skip MusicBrainz enrichment; use MBIDs already on tracks")
sub.add_parser("display", help="open the Streamlit GUI")
enrich = sub.add_parser("enrich", help="resume MBID resolution only")
enrich.add_argument("--limit", type=int, default=None)
enrich.add_argument("--source", choices=["spotify", "itunes", "local"], default=None)
sub.add_parser("match", help="print present/missing summary")
return parser
def main():
args = build_parser().parse_args()
{
"fetch": cmd_fetch,
"display": cmd_display,
"enrich": cmd_enrich,
"match": cmd_match,
}[args.cmd](args)
if __name__ == "__main__":
main()