7 files changed, 60 insertions(+), 4 deletions(-)

A alembic/versions/9468e73ed926_add_musicbrainz_metadata.py
M requirements.txt
M stewdio-api.conf
M stewdio/config.py
M stewdio/database.py
M stewdio/library.py
M stewdio/types/song.py

@@ 0,0 1,22 @@
+"""Add MusicBrainz metadata
+
+Revision ID: 9468e73ed926
+Revises: 74eaf7f47b52
+Create Date: 2018-03-29 23:37:07.888458
+
+"""
+
+# revision identifiers, used by Alembic.
+revision = '9468e73ed926'
+down_revision = '74eaf7f47b52'
+
+from alembic import op
+import sqlalchemy as sa
+
+
+def upgrade():
+    op.add_column('songs', sa.Column('mb_metadata', sa.JSON(), nullable=True))
+
+
+def downgrade():
+    op.drop_column('songs', 'mb_metadata')

@@ 1,3 1,4 @@
+pyacoustid
 flask
 flask-sockets
 gevent

@@ 11,7 11,10 @@ host = localhost
 port = 5432
 
 [search]
-off-vocal-regex=[^\w](w/o|without)[^\w].*[\)\]-]$|(instrumental|off vocal|カラオケ)[・\s]*(カラオケ|バージョン)?(.*ver(sion|.)?)?\s*[->~～\])）]?[)\]]?\s*$
+off-vocal-regex = [^\w](w/o|without)[^\w].*[\)\]-]$|(instrumental|off vocal|カラオケ)[・\s]*(カラオケ|バージョン)?(.*ver(sion|.)?)?\s*[->~～\])）]?[)\]]?\s*$
 
 [storage-status]
-test=/var/music/some.mp3
+test = /var/music/some.mp3
+
+[acoustid]
+api-key = nrUnHqXcsAE

@@ 42,3 42,7 @@ if off_vocal_regex:
 
 cfg_storage_status: configparser.SectionProxy = config['storage-status']
 storage_status = dict(cfg_storage_status)
+
+
+cfg_acoustid: configparser.SectionProxy = config['acoustid']
+acoustid_api_key = cfg_acoustid.get('api-key')

@@ 33,3 33,8 @@ class Database:
         Base.query = session.query_property()
 
         return session
+
+if __name__ == '__main__':
+    from .config import db
+    from .types import *
+    session = db.create_session()

@@ 5,6 5,8 @@ from functools import partial
 from pathlib import Path
 from typing import NamedTuple
 
+import acoustid
+from acoustid import WebServiceError
 from tinytag import TinyTag
 
 from stewdio.types.song import SongStatus


@@ 28,14 30,28 @@ def compute_hash(file):
 	return h.hexdigest()
 
 
+def augment_with_musicbrainz_metadata(song):
+	meta = 'recordings releases'
+	try:
+		data = acoustid.match(config.acoustid_api_key, song.path, meta=meta, parse=False)
+		if data.get('status') != 'ok':
+			raise WebServiceError("status not ok")
+		if not isinstance(data.get('results'), list):
+			raise WebServiceError("invalid results")
+		song.mb_metadata = data['results']
+		L.debug(f"Augmented {song} with MusicBrainz metadata")
+	except WebServiceError as e:
+		L.exception("Failed to fetch MusicBrainz metadata")
+
+
 def update(session, scan_dir):
 	songs = []
 	scan_dir = Path(scan_dir)
 	L.info(f"Scanning directory {scan_dir} for new files")
 	for root, dirs, files in os.walk(scan_dir):
 		root = Path(root)
-		for file in sorted(files):
-			path = root / file
+		for path in sorted(files):
+			path = root / path
 			path = path.absolute()
 			if path.suffix not in ('.flac', '.mp3', '.aac', '.opus', '.ogg'):
 				continue


@@ 43,6 59,8 @@ def update(session, scan_dir):
 			hash = compute_hash(path)
 			song = session.query(Song).filter_by(hash=hash).one_or_none()
 			if song:
+				if not song.mb_metadata:
+					augment_with_musicbrainz_metadata(song)
 				L.info(f"Song {song} (path: {song.path}) already exists in database (new path: {path}), skipping")
 				continue
 			metadata = TinyTag.get(str(path))


@@ 65,6 83,7 @@ def update(session, scan_dir):
 				artist=artist,
 				album=album,
 			)
+			augment_with_musicbrainz_metadata(song)
 			session.add(song)
 			session.flush()
 			L.info(f"Added song {song}")

@@ 46,6 46,8 @@ class Song(Base):
             collection_class=set,
             back_populates="songs")
 
+    mb_metadata = sa.Column(sa.JSON)
+
     def json(self):
         return dict(
             **{attr: getattr(self, attr)