03b98d9a1d
Wire the incremental pipeline to real sources and expose two workflows. Config (Env.py): three explicit paths — LOCAL_LIBRARY_PATH (scan source), ITUNES_XML_PATH (manual export), DATA_DIR (storage root: DB + Spotify cache). Real, incremental ingesters: - local_scan: walks the library, skips files whose mtime/size are unchanged, prunes deleted ones, and reads embedded ISRC + recording MBID from tags (tagged files get real IDs with no network), via tags.py. - itunes_xml: parse the iTunes Library.xml as a plist; skip if mtime unchanged. - spotify_raw: ingest raw Spotify JSON (ISRC from external_ids); live fetch wrapper for when credentials are set. Workflows (src/workflows.py + main.py): - `fetch` — pull + scan + parse + enrich + match, with readable step logs. First run is slow (full scan + MB lookups); later runs only touch changes (verified: ~71s first, ~0.6s second). - `display` — launch the GUI. Also: enrich uses ISRC-first again (local MBIDs now come from tags), fix --enrich-limit 0, quiet musicbrainzngs XML warnings, ignore /data/. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
39 lines
1.5 KiB
Python
39 lines
1.5 KiB
Python
"""Configuration. The three things you point at your own data:
|
|
|
|
LOCAL_LIBRARY_PATH folder of audio files to scan
|
|
ITUNES_XML_PATH iTunes/Music "Library.xml" you exported manually
|
|
DATA_DIR storage root: the database + cached fetches live here
|
|
|
|
Everything can be overridden via environment variables (see .env.example).
|
|
"""
|
|
import os
|
|
from pathlib import Path
|
|
|
|
|
|
def _path(env, default):
|
|
return Path(os.environ.get(env, default)).expanduser()
|
|
|
|
|
|
# --- where YOUR data is read from / written to -------------------------------
|
|
# Local music library to scan (tags incl. ISRC/MusicBrainz id are read).
|
|
local_library_path = _path("LOCAL_LIBRARY_PATH", "~/Music")
|
|
|
|
# iTunes / Apple Music library export. In the Music app:
|
|
# File -> Library -> Export Library… (produces an XML/plist file).
|
|
itunes_xml_path = _path("ITUNES_XML_PATH", "~/Music/iTunes Library.xml")
|
|
|
|
# Storage root — the database and cached Spotify responses go here.
|
|
data_dir = _path("DATA_DIR", "./data")
|
|
|
|
# --- derived storage locations -----------------------------------------------
|
|
spotify_cache_dir = data_dir / "spotify" # raw Spotify API responses
|
|
database_url = os.environ.get(
|
|
"DATABASE_URL", f"sqlite:///{(data_dir / 'musicindexer.db').as_posix()}"
|
|
)
|
|
|
|
# --- Spotify app credentials (only needed for live fetching) -----------------
|
|
client_id = os.environ.get("SPOTIFY_CLIENT_ID")
|
|
client_secret = os.environ.get("SPOTIFY_CLIENT_SECRET")
|
|
|
|
# Contact string sent to MusicBrainz in the User-Agent.
|
|
mb_contact = os.environ.get("MB_CONTACT", "music-indexer@example.com")
|