feat: initial implementation of metadata aggregator

- gRPC service with MusicBrainz provider - PostgreSQL schema with migrations - Service layer with database-first caching - Repository pattern for data access - YAML configuration support - Research documentation for 17 music metadata projects
2026-04-28 16:27:14 +02:00
commit a1f6701bac
163 changed files with 95884 additions and 0 deletions
@@ -0,0 +1,199 @@
+-- Core Entities
+
+CREATE TABLE artists (
+    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+    name TEXT NOT NULL,
+    sort_name TEXT,
+    artist_type TEXT,
+    country TEXT,
+    formed_date DATE,
+    disbanded_date DATE,
+    description TEXT,
+    image_url TEXT,
+    source TEXT NOT NULL,
+    source_id TEXT,
+    created_at TIMESTAMPTZ DEFAULT now(),
+    updated_at TIMESTAMPTZ DEFAULT now()
+);
+
+CREATE TABLE works (
+    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+    title TEXT NOT NULL,
+    work_type TEXT,
+    language TEXT,
+    source TEXT NOT NULL,
+    source_id TEXT,
+    created_at TIMESTAMPTZ DEFAULT now(),
+    updated_at TIMESTAMPTZ DEFAULT now()
+);
+
+CREATE TABLE tracks (
+    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+    work_id UUID REFERENCES works(id),
+    title TEXT NOT NULL,
+    duration_ms INT,
+    isrc TEXT,
+    explicit BOOLEAN DEFAULT false,
+    source TEXT NOT NULL,
+    source_id TEXT,
+    created_at TIMESTAMPTZ DEFAULT now(),
+    updated_at TIMESTAMPTZ DEFAULT now()
+);
+
+CREATE TABLE labels (
+    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+    name TEXT NOT NULL,
+    country TEXT,
+    founded_date DATE,
+    source TEXT NOT NULL,
+    source_id TEXT,
+    created_at TIMESTAMPTZ DEFAULT now(),
+    updated_at TIMESTAMPTZ DEFAULT now()
+);
+
+CREATE TABLE albums (
+    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+    label_id UUID REFERENCES labels(id),
+    title TEXT NOT NULL,
+    album_type TEXT,
+    release_date DATE,
+    upc TEXT,
+    total_tracks INT,
+    total_discs INT DEFAULT 1,
+    cover_url TEXT,
+    source TEXT NOT NULL,
+    source_id TEXT,
+    created_at TIMESTAMPTZ DEFAULT now(),
+    updated_at TIMESTAMPTZ DEFAULT now()
+);
+
+CREATE TABLE genres (
+    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+    name TEXT NOT NULL UNIQUE,
+    parent_id UUID REFERENCES genres(id)
+);
+
+-- Relationships
+
+CREATE TABLE track_artists (
+    track_id UUID REFERENCES tracks(id) ON DELETE CASCADE,
+    artist_id UUID REFERENCES artists(id) ON DELETE CASCADE,
+    role TEXT DEFAULT 'primary',
+    position INT DEFAULT 0,
+    PRIMARY KEY (track_id, artist_id, role)
+);
+
+CREATE TABLE album_artists (
+    album_id UUID REFERENCES albums(id) ON DELETE CASCADE,
+    artist_id UUID REFERENCES artists(id) ON DELETE CASCADE,
+    role TEXT DEFAULT 'primary',
+    position INT DEFAULT 0,
+    PRIMARY KEY (album_id, artist_id, role)
+);
+
+CREATE TABLE album_tracks (
+    album_id UUID REFERENCES albums(id) ON DELETE CASCADE,
+    track_id UUID REFERENCES tracks(id) ON DELETE CASCADE,
+    disc_number INT DEFAULT 1,
+    track_number INT NOT NULL,
+    PRIMARY KEY (album_id, track_id)
+);
+
+CREATE TABLE work_artists (
+    work_id UUID REFERENCES works(id) ON DELETE CASCADE,
+    artist_id UUID REFERENCES artists(id) ON DELETE CASCADE,
+    role TEXT DEFAULT 'writer',
+    PRIMARY KEY (work_id, artist_id, role)
+);
+
+CREATE TABLE artist_genres (
+    artist_id UUID REFERENCES artists(id) ON DELETE CASCADE,
+    genre_id UUID REFERENCES genres(id) ON DELETE CASCADE,
+    PRIMARY KEY (artist_id, genre_id)
+);
+
+CREATE TABLE album_genres (
+    album_id UUID REFERENCES albums(id) ON DELETE CASCADE,
+    genre_id UUID REFERENCES genres(id) ON DELETE CASCADE,
+    PRIMARY KEY (album_id, genre_id)
+);
+
+CREATE TABLE similar_artists (
+    artist_id UUID REFERENCES artists(id) ON DELETE CASCADE,
+    similar_artist_id UUID REFERENCES artists(id) ON DELETE CASCADE,
+    score REAL DEFAULT 0.5,
+    PRIMARY KEY (artist_id, similar_artist_id)
+);
+
+-- Content
+
+CREATE TABLE lyrics (
+    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+    track_id UUID REFERENCES tracks(id) ON DELETE CASCADE,
+    content TEXT,
+    synced_content JSONB,
+    language TEXT,
+    source TEXT NOT NULL,
+    source_id TEXT,
+    created_at TIMESTAMPTZ DEFAULT now()
+);
+
+CREATE TABLE playlists (
+    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+    name TEXT NOT NULL,
+    description TEXT,
+    is_public BOOLEAN DEFAULT true,
+    cover_url TEXT,
+    created_at TIMESTAMPTZ DEFAULT now(),
+    updated_at TIMESTAMPTZ DEFAULT now()
+);
+
+CREATE TABLE playlist_tracks (
+    playlist_id UUID REFERENCES playlists(id) ON DELETE CASCADE,
+    track_id UUID REFERENCES tracks(id) ON DELETE CASCADE,
+    position INT NOT NULL,
+    added_at TIMESTAMPTZ DEFAULT now(),
+    PRIMARY KEY (playlist_id, track_id)
+);
+
+-- External IDs
+
+CREATE TABLE artist_external_ids (
+    artist_id UUID REFERENCES artists(id) ON DELETE CASCADE,
+    source TEXT NOT NULL,
+    source_id TEXT NOT NULL,
+    url TEXT,
+    fetched_at TIMESTAMPTZ DEFAULT now(),
+    PRIMARY KEY (artist_id, source, source_id)
+);
+
+CREATE TABLE album_external_ids (
+    album_id UUID REFERENCES albums(id) ON DELETE CASCADE,
+    source TEXT NOT NULL,
+    source_id TEXT NOT NULL,
+    url TEXT,
+    fetched_at TIMESTAMPTZ DEFAULT now(),
+    PRIMARY KEY (album_id, source, source_id)
+);
+
+CREATE TABLE track_external_ids (
+    track_id UUID REFERENCES tracks(id) ON DELETE CASCADE,
+    source TEXT NOT NULL,
+    source_id TEXT NOT NULL,
+    url TEXT,
+    fetched_at TIMESTAMPTZ DEFAULT now(),
+    PRIMARY KEY (track_id, source, source_id)
+);
+
+-- Indexes
+
+CREATE INDEX idx_artists_name ON artists(name);
+CREATE INDEX idx_artists_source ON artists(source, source_id);
+CREATE INDEX idx_tracks_isrc ON tracks(isrc) WHERE isrc IS NOT NULL;
+CREATE INDEX idx_tracks_source ON tracks(source, source_id);
+CREATE INDEX idx_albums_upc ON albums(upc) WHERE upc IS NOT NULL;
+CREATE INDEX idx_albums_source ON albums(source, source_id);
+CREATE INDEX idx_albums_release_date ON albums(release_date);
+CREATE INDEX idx_genres_name ON genres(name);
+CREATE INDEX idx_lyrics_track_id ON lyrics(track_id);
+CREATE INDEX idx_playlist_tracks_position ON playlist_tracks(playlist_id, position);