nice

Flow.py

@@ -96,6 +96,10 @@ class Flow:
         self.spotify_library = LibraryLoader().load(work_dir / "spotify_library.json")
         self.local_library = LibraryLoader().load(work_dir / "local_library.json")
 
+    def save_libraries(self):
+        LibrarySaver(self.spotify_library).save(work_dir / "spotify_library.json")
+        LibrarySaver(self.local_library).save(work_dir / "local_library.json")
+
     def map_local_to_spotify(self):
         resolve_remote_tracks(client_id, client_secret, self.local_library, self.spotify_library, work_dir)
 

Gui.py

@@ -0,0 +1,206 @@
+import time
+
+import streamlit as st
+from st_aggrid import AgGrid, GridOptionsBuilder, GridUpdateMode
+import pandas as pd
+
+import Flow
+
+from src.Library import Library, Artist, Album, Track, Playlist
+
+def track_to_row(track: Track):
+    return {
+        "Title": track.title,
+        "Album": track.album.title if track.album else "",
+        "Artists": ", ".join(a.title if a.title else "no_arist_name" for a in track.artists),
+        "Lyrics": track.has_lyrics,
+        "AutoScore": track.auto_score,
+        "Added": track.added_at.strftime("%Y-%m-%d") if track.added_at else "",
+        "LocalId": str(track.local_id) if track.local_id else "",
+        "Path": str(track.local_path) if track.local_path else "",
+    }
+
+def artist_to_row(artist: Artist):
+    return {
+        "Title": artist.title,
+        "AutoScore": artist.auto_score,
+        "Resolved": int(artist.resolved_percentage * 100),
+        "LocalId": str(artist.local_id) if artist.local_id else "",
+    }
+
+def album_to_row(album: Album):
+    return {
+        "Title": album.title,
+        "AutoScore": album.auto_score,
+        "Resolved": int(album.resolved_percentage * 100),
+        "LocalId": str(album.local_id) if album.local_id else "",
+    }
+
+
+class LibraryView:
+    def __init__(self):
+        self.lib : Library = None
+        self.libs : list[Library] = None
+        self.view = None
+        self.lyrics_only = False
+        self.query = None
+
+    def add_libraries(self, libs : list[Library]):
+        self.libs = libs
+
+    def render(self):
+        st.set_page_config(layout="wide")
+
+        with st.sidebar:
+            lib = st.selectbox(
+                "Library",
+                options=[lib.name for lib in self.libs],
+            )
+
+            for iter in self.libs:
+                if iter.name == lib:
+                    self.lib = iter
+
+            st.write(f"Showing library '{self.lib.name}'")
+
+            self.view = st.radio(
+                "View",
+                ["Tree"]
+            )
+
+        if self.view == "Tree":
+            self.render_artists_albums_tracks()
+        # elif self.view == "Tracks":
+            # self.render_tracks()
+        # elif self.view == "Playlists":
+        #     self.render_playlists()
+
+    def track_visible(
+        self,
+        track: Track,
+        artist: Artist | None,
+        album: Album | None,
+    ):
+        if self.lyrics_only and not track.has_lyrics:
+            return False
+
+        if self.query and self.query.lower() not in track.title.lower():
+            return False
+
+        if artist and all(a.id != artist.id for a in track.artists):
+            return False
+
+        if album and (not track.album or track.album.id != album.id):
+            return False
+
+        return True
+
+    def render_artists_albums_tracks(self):
+        # --- ARTISTS TABLE ---
+        st.subheader("Artists")
+        artist_rows = [artist_to_row(a) for a in self.lib.artists]
+        df_artists = pd.DataFrame(artist_rows)
+
+        gb_artists = GridOptionsBuilder.from_dataframe(df_artists)
+        gb_artists.configure_selection(selection_mode="multiple", use_checkbox=True)
+        gb_artists.configure_column("Title", filter="agTextColumnFilter")
+        gb_artists.configure_column("AutoScore", sort="desc")
+        grid_options_artists = gb_artists.build()
+
+        grid_response_artists = AgGrid(
+            df_artists,
+            gridOptions=grid_options_artists,
+            update_mode=GridUpdateMode.SELECTION_CHANGED,
+            allow_unsafe_jscode=True,
+            enable_enterprise_modules=False,
+            fit_columns_on_grid_load=True,
+        )
+
+        selected_rows_df = grid_response_artists.get("selected_rows")
+        selected_artist_titles = selected_rows_df["Title"].tolist() if selected_rows_df is not None and not selected_rows_df.empty else []
+        selected_artists = [a for a in self.lib.artists if a.title in selected_artist_titles]
+
+        # --- ALBUMS TABLE ---
+        st.subheader("Albums")
+        if selected_artists:
+            albums_list = []
+            for artist in selected_artists:
+                albums_list.extend(artist.albums)
+            albums_list = list({al.id: al for al in albums_list}.values())
+        else:
+            albums_list = self.lib.albums
+
+        album_rows = [album_to_row(a) for a in albums_list]
+        df_albums = pd.DataFrame(album_rows)
+
+        gb_albums = GridOptionsBuilder.from_dataframe(df_albums)
+        gb_albums.configure_selection(selection_mode="multiple", use_checkbox=True)
+        gb_albums.configure_column("Title", filter="agTextColumnFilter")
+        gb_albums.configure_column("AutoScore", sort="desc")
+        grid_options_albums = gb_albums.build()
+
+        grid_response_albums = AgGrid(
+            df_albums,
+            gridOptions=grid_options_albums,
+            update_mode=GridUpdateMode.SELECTION_CHANGED,
+            allow_unsafe_jscode=True,
+            enable_enterprise_modules=False,
+            fit_columns_on_grid_load=True,
+        )
+
+        selected_rows_df = grid_response_albums.get("selected_rows")
+        selected_album_titles = selected_rows_df["Title"].tolist() if selected_rows_df is not None and not selected_rows_df.empty else []
+        selected_albums = [al for al in albums_list if al.title in selected_album_titles]
+
+        # --- TRACKS TABLE ---
+        st.subheader("Tracks")
+        if selected_albums:
+            tracks_list = []
+            for album in selected_albums:
+                tracks_list.extend(album.tracks)
+        elif selected_artists:
+            tracks_list = []
+            for artist in selected_artists:
+                tracks_list.extend([t for t in self.lib.tracks if artist in t.artists])
+        else:
+            tracks_list = self.lib.tracks
+
+        track_rows = [track_to_row(t) for t in tracks_list]
+        df_tracks = pd.DataFrame(track_rows)
+
+        gb_tracks = GridOptionsBuilder.from_dataframe(df_tracks)
+        gb_tracks.configure_selection(selection_mode="multiple", use_checkbox=True)
+        gb_tracks.configure_column("Title", filter="agTextColumnFilter")
+        gb_tracks.configure_column("AutoScore", sort="desc")
+        grid_options_tracks = gb_tracks.build()
+
+        AgGrid(
+            df_tracks,
+            gridOptions=grid_options_tracks,
+            update_mode=GridUpdateMode.SELECTION_CHANGED,
+            allow_unsafe_jscode=True,
+            enable_enterprise_modules=False,
+            fit_columns_on_grid_load=True,
+        )
+
+
+def run():
+    flow = Flow.Flow()
+
+    # flow.fetch_spotify()
+    # flow.fetch_local()
+
+    # flow.parse_spotify_library()
+    # flow.parse_local_library()
+
+    flow.load_libraries()
+
+    # flow.map_local_to_spotify()
+
+    # flow.log_stats()
+
+    gui = LibraryView()
+    gui.add_libraries([flow.spotify_library, flow.local_library])
+    gui.render()
+
+run()

error.log

@@ -0,0 +1,2 @@
+
+(process:38049): GLib-GIO-CRITICAL **: 14:06:16.561: g_dbus_connection_emit_signal: assertion 'G_IS_DBUS_CONNECTION (connection)' failed

gui.sh

@@ -0,0 +1 @@
+streamlit run Gui.py

main.py

@@ -5,15 +5,14 @@ import Flow
 def test1():
     flow = Flow.Flow()
 
-    flow.fetch_local()
+    # flow.fetch_local()
     flow.parse_local_library()
     flow.load_libraries()
 
     # flow.map_local_to_spotify()
     # flow.log_stats()
 
-    flow.fetch_and_save_lyrics()
+    # flow.fetch_and_save_lyrics()
-
 
 def main():
     flow = Flow.Flow()
@@ -27,11 +26,12 @@ def main():
     flow.load_libraries()
 
     flow.map_local_to_spotify()
+    flow.save_libraries()
 
-    flow.log_stats()
+    # flow.log_stats()
 
-    print("asd")
+    # print("asd")
 
 
-test1()
+# test1()
-# main()
+main()

src/Library.py

@@ -11,6 +11,11 @@ class Artist:
         self.title: str = None
         self.tracks: List[Track] = []
         self.albums: List[Album] = []
+        self.local_id: str = None
+        self.auto_score: float = 0
+        self.fav: bool = False
+        self.rating: int = 0
+        self.resolved_percentage : float = 0
 
 
 class Track:
@@ -23,6 +28,10 @@ class Track:
         self.added_at: datetime = None
         self.local_path: Path = None
         self.has_lyrics: bool = False
+        self.local_id: str = None
+        self.auto_score: float = 0
+        self.fav: bool = False
+        self.rating: int = 0
 
 
 class Album:
@@ -32,6 +41,11 @@ class Album:
         self.release_date: datetime = None
         self.tracks: List[Track] = []
         self.artists: List[Artist] = []
+        self.local_id: str = None
+        self.auto_score: float = 0
+        self.fav: bool = False
+        self.rating: int = 0
+        self.resolved_percentage : float = 0
 
 
 class Playlist:
@@ -40,6 +54,10 @@ class Playlist:
         self.tracks: List[Track] = []
         self.created_at: datetime = None
         self.description: str = None
+        self.auto_score: float = 0
+        self.fav: bool = False
+        self.rating: int = 0
+        self.resolved_percentage : float = 0
 
 
 class Library:
@@ -48,6 +66,7 @@ class Library:
         self.playlists: List[Playlist] = []
         self.tracks: List[Track] = []
         self.albums: List[Album] = []
+
         self.liked_tracks: List[Track] = []
         self.top_tracks: List[Track] = []
         self.top_artists: List[Artist] = []
@@ -56,10 +75,13 @@ class Library:
         self.album_map: dict[str, Album] = None
         self.track_map: dict[str, Track] = None
 
+        self.name = "Unnamed"
 
     def update_cache(self):
         self.update_id_maps()
         self.create_reverse_links()
+        self.score_albums()
+        self.calc_resolved_percentage()
 
     def update_id_maps(self):
         self.artist_map: dict[str, Artist] = {artist.id: artist for artist in self.artists}
@@ -79,3 +101,36 @@ class Library:
             for artist in album.artists:
                 if album not in artist.albums:
                     artist.albums.append(album)
+
+    def auto_score(self):
+        self.score_tracks()
+        self.score_artists()
+        self.score_albums()
+
+    def score_tracks(self):
+        for idx, track in enumerate(self.top_tracks):
+            score = len(self.top_tracks) - idx
+            track.auto_score = score
+
+    def score_artists(self):
+        for track in self.tracks:
+            for artist in track.artists:
+                artist.auto_score += track.auto_score
+
+    def score_albums(self):
+        for track in self.tracks:
+            track.album.auto_score += track.auto_score
+
+    def calc_resolved_percentage(self):
+        for artist in self.artists:
+            artist_count_resolved = 0
+            artist_count = 0
+            for album in artist.albums:
+                album_count_resolved = 0
+                for track in album.tracks:
+                    if track.local_id:
+                        album_count_resolved += 1
+                album.resolved_percentage = album_count_resolved / len(album.tracks)
+                artist_count_resolved += album_count_resolved
+                artist_count += len(album.tracks)
+            artist.resolved_percentage = artist_count_resolved / artist_count

src/LibrarySerializer.py

@@ -33,6 +33,10 @@ class LibrarySaver:
             "title": artist.title,
             "tracks": [track.id for track in artist.tracks],
             "albums": [album.id for album in artist.albums],
+            "local_id": artist.local_id,
+            "auto_score": artist.auto_score,
+            "fav" : artist.fav,
+            "rating" : artist.rating,
         }
 
     @staticmethod
@@ -46,6 +50,10 @@ class LibrarySaver:
             "added_at": _dt_to_str(track.added_at),
             "local_path": track.local_path,
             "has_lyrics": track.has_lyrics,
+            "local_id": track.local_id,
+            "auto_score": track.auto_score,
+            "fav" : track.fav,
+            "rating" : track.rating,
         }
 
     @staticmethod
@@ -55,6 +63,9 @@ class LibrarySaver:
             "tracks": [track.id for track in playlist.tracks],
             "created_at": _dt_to_str(playlist.created_at),
             "description": playlist.description,
+            "auto_score": playlist.auto_score,
+            "fav" : playlist.fav,
+            "rating" : playlist.rating,
         }
 
     @staticmethod
@@ -64,12 +75,17 @@ class LibrarySaver:
             "title": album.title,
             "release_date": album.release_date,
             "tracks": [track.id for track in album.tracks],
-            "artists": [artist.id for artist in album.artists]
+            "artists": [artist.id for artist in album.artists],
+            "local_id": album.local_id,
+            "auto_score": album.auto_score,
+            "fav" : album.fav,
+            "rating" : album.rating,
         }
 
     def save(self, path: Path) -> None:
 
         data = {
+            "name": self.library.name,
             "tracks": [self._track_to_dict(track) for track in self.library.tracks],
             "albums": [self._album_to_dict(album) for album in self.library.albums],
             "artists": [self._artist_to_dict(artist) for artist in self.library.artists],
@@ -121,6 +137,10 @@ class LibraryLoader:
         track.artists = [self.get_artist(artist_id) for artist_id in data.get("artists")]
         track.album = self.get_album(data.get("album"))
         track.has_lyrics = data.get("has_lyrics")
+        track.local_id = data.get("local_id")
+        track.auto_score = data.get("auto_score")
+        track.fav = data.get("fav")
+        track.rating = data.get("rating")
 
         self.track_map[track.id] = track
         return track
@@ -131,6 +151,10 @@ class LibraryLoader:
         artist.title = data.get("title")
         artist.tracks = [self.get_track(track_id) for track_id in data.get("tracks")]
         artist.albums = [self.get_album(album_id) for album_id in data.get("albums")] if data.get("albums") else []
+        artist.local_id = data.get("local_id")
+        artist.auto_score = data.get("auto_score")
+        artist.fav = data.get("fav")
+        artist.rating = data.get("rating")
 
         self.artist_map[artist.id] = artist
         return artist
@@ -141,6 +165,10 @@ class LibraryLoader:
         album.tracks = [self.get_track(track_id) for track_id in data.get("tracks")]
         album.title = data.get("title")
         album.artists = [self.get_artist(artist_id) for artist_id in data.get("artists")]
+        album.local_id = data.get("local_id")
+        album.auto_score = data.get("auto_score")
+        album.fav = data.get("fav")
+        album.rating = data.get("rating")
 
         self.album_map[album.id] = album
         return album
@@ -151,6 +179,7 @@ class LibraryLoader:
 
         library = Library()
 
+        library.name = data.get("name")
         library.tracks = [self.load_track(track) for track in data.get("tracks")]
         library.albums = [self.load_album(album) for album in data.get("albums")]
         library.artists = [self.load_artist(artist) for artist in data.get("artists")]

src/StatGenerator.py

@@ -15,13 +15,12 @@ def get_mapping(mapping_path) -> dict[str, Any]:
     with Path(mapping_path).open("r", encoding="utf-8") as f:
         data = json.load(f)
 
-    return data
+    return data["track_map"]
 
 
 class AlbumStat:
     def __init__(self):
         self.album: Album = Album()
-        self.score: int = 0
         self.resolved_precent: float = 0
 
     def calc_resolved_precent(self):
@@ -37,7 +36,6 @@ class AlbumStat:
 class ArtistStat:
     def __init__(self):
         self.artist: Artist = Artist()
-        self.score: int = 0
         self.resolved_precent: float = 0
         self.albums_stats: list[AlbumStat] = []
 
@@ -87,18 +85,22 @@ class LibraryStats:
         for remote, local in self.mapping.items():
             self.remote_id_map[remote].local_path = self.local_id_map[local].local_path
 
+    def score_tracks(self):
+        for idx, track in enumerate(self.remote_lib.top_tracks):
+            score = len(self.remote_lib.top_tracks) - idx
+            track.auto_score = score
+
     def score_artists(self):
         for artist in self.remote_lib.artists:
             artist_stat = ArtistStat()
             artist_stat.artist = artist
-            artist_stat.score = 0
+            artist_stat.artist.auto_score = 0
             self.artists_map[artist_stat.artist.id] = artist_stat
             self.artists.append(artist_stat)
 
-        for idx, track in enumerate(self.remote_lib.top_tracks):
+        for track in self.remote_lib.tracks:
-            score = len(self.remote_lib.top_tracks) - idx
             for artist in track.artists:
-                self.artists_map[artist.id].score += score
+                self.artists_map[artist.id].artist.auto_score += track.auto_score
 
         for artist_stat in self.artists:
             artist_stat.calc_resolved_precent()
@@ -111,9 +113,8 @@ class LibraryStats:
             stat.album = album
             self.albums_map[album.id] = stat
 
-        for idx, track in enumerate(self.remote_lib.top_tracks):
+        for track in self.remote_lib.tracks:
-            score = len(self.remote_lib.top_tracks) - idx
+            self.albums_map[track.album.id].album.auto_score += track.auto_score
-            self.albums_map[track.album.id].score += score
 
         for _, album in self.albums_map.items():
             album.calc_resolved_precent()

src/backends/local/LocalLibraryIndexer.py

@@ -1,64 +1,97 @@
+import os
 import fnmatch
-import mutagen
-import eyed3
-from mutagen.flac import FLAC
 from mutagen import File as MutagenFile
+from mutagen.id3 import ID3, ID3NoHeaderError
+from mutagen.flac import FLAC
+from mutagen.mp4 import MP4
+from mutagen.oggvorbis import OggVorbis
+from tqdm import tqdm
 
 from src.helpers import *
 
-
 music_extensions = ('*.mp3', '*.flac', '*.wav', '*.aac', '*.ogg', '*.m4a')
 exclude_directories = ("*mary--*", "*example-word*")
 
 
-from mutagen.id3 import ID3
-from mutagen.id3 import ID3NoHeaderError
-
-
 def detect_lyrics(abs_path, ext):
     ext = ext.lower()
 
-    # ---------- MP3 ----------
-    if ext == ".mp3":
-        try:
-            tags = ID3(abs_path)
-        except ID3NoHeaderError:
-            return False
-
-        return bool(
-            tags.getall("SYLT") or
-            tags.getall("USLT")
-        )
-
-    # ---------- FLAC / OGG / OPUS ----------
-    if ext in {".flac", ".ogg", ".opus"}:
     try:
         audio = MutagenFile(abs_path)
         if not audio or not audio.tags:
             return False
 
-            for key in audio.tags.keys():
+        # MP3-specific SYLT/USLT detection
-                k = key.upper()
+        if ext == ".mp3" and isinstance(audio, ID3):
-                if k in {"LYRICS", "LRC", "SYNCEDLYRICS"}:
+            return bool(audio.getall("SYLT") or audio.getall("USLT"))
-                    if audio.tags[key]:
-                        return True
-        except Exception:
-            return False
 
-    # ---------- Fallback ----------
+        # FLAC/OGG/OPUS lyrics detection
-    try:
+        for key, value in audio.tags.items():
-        audio = MutagenFile(abs_path)
+            k = key.upper()
-        if audio and audio.tags:
+            if k in {"LYRICS", "LRC", "SYNCEDLYRICS"} and value:
+                return True
+
+        # Generic fallback
         for key in audio.tags.keys():
             if "LYRIC" in key.upper():
                 return True
+
     except Exception:
-        pass
+        return False
 
     return False
 
-def update_local_library(root_dir, output_dir):
 
+def get_artist(tags, fallback=None) -> list :
+    # FLAC / OGG / general multiple artist fields
+    artist_fields = ["ARTISTS", "TXXX:ARTISTS", "©ART", "artist"]
+    for field in artist_fields:
+        if field in tags and tags[field]:
+            values = tags.get(field)
+            if not isinstance(values, list):
+                return values.text
+            return values
+
+    # M4A
+    if '\xa9ART' in tags and tags['\xa9ART']:
+        values = tags['\xa9ART']
+        return values
+
+    if tags.get("TPE1"):
+        text = getattr(tags.get("TPE1"), "text", None)
+        if text:
+            return text
+
+    return fallback
+
+def safe_tag_get(tags, key, index=0):
+    try:
+        value = tags.get(key, None)
+        if isinstance(value, list):
+            # filter out None/empty, convert to str
+            value = [str(v) for v in value if v]
+            return value[index] if len(value) > index else fallback
+        return str(value)
+    except (KeyError, ValueError, TypeError):
+        return None
+
+def get_title(tags):
+    ids = ["TIT2", "TITLE", "title", "\xa9nam"]
+    for key in ids:
+        val = safe_tag_get(tags, key)
+        if val and val != "None":
+            return val
+    return None
+
+def get_album(tags):
+    ids = ["TALB", "album", "\xa9alb"]
+    for key in ids:
+        val = safe_tag_get(tags, key)
+        if val and val != "None":
+            return val
+    return None
+
+def update_local_library(root_dir, output_dir):
     set_workdir(output_dir / "local")
 
     old_library = get_data("local_library")
@@ -91,61 +124,48 @@ def update_local_library(root_dir, output_dir):
             song_id = get_new_song_id(song_id, relative_path)
 
             new_library[song_id] = {
-                "name": song_name,
+                "name": None,
                 "path": relative_path,
                 "type": track_type,
-                "artist": "",
+                "artists": None,
-                "album": "",
+                "album": None,
                 "duration": None
             }
 
+    to_remove = []
+
+    with tqdm(total=len(new_library.items()), desc='Indexing local library') as process_bar:
         for track_id, track in new_library.items():
+            process_bar.update(1)
+
             abs_path = os.path.join(root_dir, track['path'])
+            track["has_lyrics"] = detect_lyrics(abs_path, track['type'].lower())
 
-        track_abs_path = os.path.join(root_dir, track["path"])
-        track["has_lyrics"] = detect_lyrics(track_abs_path, track['type'].lower())
-
-        match track['type'].lower():
-            case ".mp3":
-                mp3track = eyed3.load(abs_path)
-                if not mp3track or not mp3track.info:
-                    print(f"Failed to load mp3 {abs_path}")
-                    track['name'] = track['path']
-                else:
-                    track['duration'] = mp3track.info.time_secs
-
-                    tag = mp3track.tag
-                    if tag:
-                        track['artist'] = tag.artist
-                        track['name'] = tag.title
-                        track['album'] = tag.album
-
-            case ".flac":
-                try:
-                    audio = FLAC(abs_path)
-
-                    if audio.info:
-                        track['duration'] = audio.info.length
-
-                    metadata = audio.tags
-                    if metadata:
-                        if 'artist' in metadata:
-                            track['artist'] = " ".join(metadata['artist'])
-                        if 'TITLE' in metadata:
-                            track['name'] = " ".join(metadata['TITLE'])
-                        if 'album' in metadata:
-                            track['album'] = " ".join(metadata['album'])
-
-                except mutagen.MutagenError:
-                    print(f"Invalid flac header {abs_path}")
-                    track['name'] = track['path']
-
-            case _:
             try:
                 audio = MutagenFile(abs_path)
-                    if audio and audio.info:
+                if audio and audio.tags:
-                        track['duration'] = audio.info.length
+                    tags = audio.tags
-                except Exception:
+
-                    pass
+                    track['artists'] = get_artist(tags)
+                    track['name'] = get_title(tags)
+                    track['album'] = get_album(tags)
+
+                    if not len(track['artists']) or not track['name'] or not track['album']:
+                        print(track)
+                        raise "Cannot index track"
+
+                else:
+                    print(track)
+                    to_remove.append(track_id)
+                    # raise "Cannot index track"
+
+            except Exception as e:
+                print(e)
+                print(abs_path)
+                raise e
+
+
+    for rem in to_remove:
+        new_library.pop(rem)
 
     save_data(new_library, "local_library")

src/backends/local/ParseLocal.py

@@ -10,46 +10,6 @@ PROTECTED_ARTISTS = {
     "The Good, The Bad & The Queen",
 }
 
-def split_artists(artist_tag: str) -> list[str]:
-    if not artist_tag:
-        return []
-
-    placeholder_comma = "§COMMA§"
-    placeholder_amp = "§AMP§"
-
-    protected_map = {}
-
-    # Protect known artist names
-    for artist in PROTECTED_ARTISTS:
-        protected = (
-            artist
-            .replace(",", placeholder_comma)
-            .replace("&", placeholder_amp)
-        )
-        protected_map[protected] = artist
-        artist_tag = artist_tag.replace(artist, protected)
-
-    # Split remaining separators
-    parts = re.split(r"[,&]", artist_tag)
-
-    # Restore protected names and trim spaces
-    result = []
-    for part in parts:
-        part = part.strip()
-        if not part:
-            continue
-
-        part = (
-            part
-            .replace(placeholder_comma, ",")
-            .replace(placeholder_amp, "&")
-        )
-
-        result.append(part)
-
-    return result
-
-
 class LocalParser:
     def __init__(self):
         self.track_map: dict[str, Track] = {}
@@ -60,9 +20,7 @@ class LocalParser:
 
     def parse_artists(self, data: str) -> List[Artist]:
         if not data:
-            data = "unknown"
+            raise "No artist found"
-
-        data = split_artists(data)
 
         artists = []
 
@@ -87,7 +45,7 @@ class LocalParser:
 
     def parse_album(self, data: str) -> Album:
         if not data:
-            data = "unknown"
+            raise "album is none"
 
         name = data
         album_id = name
@@ -113,12 +71,15 @@ class LocalParser:
 
             track.id = track_id
             track.title = data.get("name")
-            track.artists = self.parse_artists(data.get("artist"))
+            track.artists = self.parse_artists(data.get("artists"))
             track.album = self.parse_album(data.get("album"))
             track.local_path = data.get("path")
             track.duration_ms = data.get("duration")
             track.has_lyrics = data.get("has_lyrics")
 
+            if not track.album or not len(track.artists) or not track.title:
+                raise "error parsing"
+
             self.track_map[track.id] = track
             self.library.tracks.append(track)
 
@@ -129,6 +90,8 @@ class LocalParser:
 
         self.library.update_cache()
 
+        self.library.name = "Local"
+
         return self.library
 
 

src/backends/navidrome/navidrome.py

@@ -0,0 +1,110 @@
+import sqlite3
+import os
+from dataclasses import dataclass, field
+from typing import List, Optional
+
+@dataclass
+class Track:
+    id: int
+    title: str
+    path: str
+    favorite: bool
+    rating: Optional[int]
+    play_count: int
+    last_played: Optional[str]
+    playlists: List[str] = field(default_factory=list)
+
+@dataclass
+class Album:
+    id: int
+    title: str
+    tracks: List[Track] = field(default_factory=list)
+
+@dataclass
+class Artist:
+    id: str
+    name: str
+    albums: List[Album] = field(default_factory=list)
+
+class NavidromeDB:
+    def __init__(self, db_path: str):
+        if not os.path.isfile(db_path):
+            raise FileNotFoundError(f"Navidrome DB not found: {db_path}")
+        self.conn = sqlite3.connect(db_path)
+        self.conn.row_factory = sqlite3.Row
+
+    def close(self):
+        self.conn.close()
+
+    def get_artists(self) -> List[Artist]:
+        artists = []
+        c = self.conn.cursor()
+        c.execute("SELECT id, name FROM artist ORDER BY name")
+        for row in c.fetchall():
+            artist = Artist(id=row["id"], name=row["name"])
+            artist.albums = self.get_albums(artist.id)
+            artists.append(artist)
+        return artists
+
+    def get_albums(self, artist_id: str) -> List[Album]:
+        albums = []
+        c = self.conn.cursor()
+        c.execute(
+            "SELECT id, name FROM album WHERE album_artist_id=? ORDER BY name",
+            (artist_id,)
+        )
+        for row in c.fetchall():
+            album = Album(id=row["id"], title=row["name"])
+            album.tracks = self.get_tracks(album.id)
+            albums.append(album)
+        return albums
+
+    def get_tracks(self, album_id: int) -> List[Track]:
+        tracks = []
+        c = self.conn.cursor()
+        c.execute(
+            "SELECT t.id, t.name AS Title, t.path, ut.favorite, ut.rating, ut.play_count AS PlayCount, ut.last_played AS LastPlayed "
+            "FROM track t "
+            "LEFT JOIN usertrack ut ON ut.track_id = t.id "
+            "WHERE t.album_id=? ORDER BY t.track_number",
+            (album_id,)
+        )
+        for row in c.fetchall():
+            track = Track(
+                id=row["id"],
+                title=row["Title"],
+                path=row["path"],
+                favorite=bool(row["favorite"]),
+                rating=row["rating"],
+                play_count=row["PlayCount"] or 0,
+                last_played=row["LastPlayed"],
+                playlists=self.get_playlists_for_track(row["id"])
+            )
+            tracks.append(track)
+        return tracks
+
+    def get_playlists_for_track(self, track_id: int) -> List[str]:
+        c = self.conn.cursor()
+        c.execute(
+            "SELECT p.name FROM playlist p "
+            "JOIN playlisttrack pt ON pt.playlist_id=p.id "
+            "WHERE pt.track_id=?",
+            (track_id,)
+        )
+        return [row["name"] for row in c.fetchall()]
+
+# Example usage
+if __name__ == "__main__":
+    db_path = "/mnt/main/data/music/navidrome.db"
+    navidb = NavidromeDB(db_path)
+
+    try:
+        artists = navidb.get_artists()
+        for artist in artists:
+            print(f"Artist: {artist.name}")
+            for album in artist.albums:
+                print(f"  Album: {album.title}")
+                for track in album.tracks:
+                    print(f"    Track: {track.title} | Path: {track.path} | Fav: {track.favorite} | Plays: {track.play_count}")
+    finally:
+        navidb.close()

src/backends/spotify/ParseSpotify.py

@@ -30,6 +30,8 @@ class Parser:
         self.parse_top_tracks(json.loads(top_tracks.read_text()))
 
         self.library.update_cache()
+        self.library.name = "Spotify"
+        self.library.auto_score()
 
         return self.library
 
@@ -75,7 +77,7 @@ class Parser:
 
         track.id = track_id
         track.title = data.get("name")
-        track.artists = [self.parse_artist(artist) for artist in data.get("artists")]
+        track.artists = [] + self.parse_album(data.get("album")).artists
         track.album = self.parse_album(data.get("album"))
         track.duration_ms = data.get("duration_ms")
 
@@ -114,6 +116,9 @@ class Parser:
         artist.id = data.get("id")
         artist.title = data.get("name")
 
+        if artist.title is None:
+            artist.title = "err_no_title"
+
         self.library.artists.append(artist)
 
         return artist

src/mappers/FuzzyMapper.py

@@ -5,12 +5,46 @@ from tqdm import tqdm
 from src.Library import *
 from src.helpers import *
 
+import unicodedata
+
+user_def_artist_map = {
+    "donda" : "kanye west",
+}
+
+def normalize(s):
+    return unicodedata.normalize("NFKC", s).replace("‐", "-")
 
 def get_score(first: str, second: str) -> float:
+    first_norm = normalize(first).lower()
+    second_norm = normalize(second).lower()
+    return float(first_norm == second_norm) * 100
     return fuzz.token_set_ratio(first, second)
 
+def get_album_score(first: str, second: str) -> float:
+    return get_score(first, second)
+
+def get_track_score(first: str, second: str) -> float:
+    return get_score(first, second)
+
+def get_artist_score(first: str, second: str) -> float:
+    if not first or not second:
+        return 0.0
+
+    first_lower = first.lower()
+    second_lower = second.lower()
+
+    for key, value in user_def_artist_map.items():
+        key_lower = key.lower()
+        value_lower = value.lower()
+        if (first_lower == key_lower and second_lower == value_lower) or \
+           (first_lower == value_lower and second_lower == key_lower):
+            return 100.0
+
+    return get_score(first, second)
+
+
 def is_close_enough(first: float) -> bool:
-    return first > 50
+    return first > 90
 
 def generate_map(local_lib : Library, remote_lib : Library, output_dir : Path):
 
@@ -21,12 +55,13 @@ def generate_map(local_lib : Library, remote_lib : Library, output_dir : Path):
     with (tqdm(total=len(remote_lib.artists), desc='searching remote artists in local library') as process_bar):
         for remote_artist in remote_lib.artists:
             for local_artist in local_lib.artists:
-                score = get_score(remote_artist.title, local_artist.title)
+                score = get_artist_score(remote_artist.title, local_artist.title)
                 if not is_close_enough(score):
                     continue
 
                 if remote_artist.id not in artist_map or score > artist_map[remote_artist.id][1]:
                     artist_map[remote_artist.id] = (local_artist.id, score)
+                    remote_artist.local_id = local_artist.id
 
             process_bar.update(1)
 
@@ -38,12 +73,13 @@ def generate_map(local_lib : Library, remote_lib : Library, output_dir : Path):
 
             for remote_album in remote_artist.albums:
                 for local_album in local_artist.albums:
-                    score = get_score(remote_album.title, local_album.title)
+                    score = get_album_score(remote_album.title, local_album.title)
                     if not is_close_enough(score):
                         continue
 
                     if remote_album.id not in artist_map or score > album_map[remote_album.id][1]:
                         album_map[remote_album.id] = (local_album.id, score)
+                        remote_album.local_id = local_album.id
 
             process_bar.update(1)
 
@@ -54,15 +90,23 @@ def generate_map(local_lib : Library, remote_lib : Library, output_dir : Path):
 
             for remote_track in remote_album.tracks:
                 for local_track in local_album.tracks:
-                    score = get_score(remote_track.title, local_track.title)
+                    score = get_track_score(remote_track.title, local_track.title)
                     if not is_close_enough(score):
                         continue
 
                     if remote_track.id not in artist_map or score > track_map[remote_track.id][1]:
                         track_map[remote_track.id] = (local_track.id, score)
+                        remote_track.local_id = local_track.id
 
             process_bar.update(1)
 
-    out = { remote_track_id : local_track_id for remote_track_id, (local_track_id, _)  in track_map.items() }
+    remote_lib.calc_resolved_percentage()
+
+    out = {
+        "artist_map" : { remote_track_id : local_track_id for remote_track_id, (local_track_id, _)  in artist_map.items() },
+        "album_map" : { remote_track_id : local_track_id for remote_track_id, (local_track_id, _)  in album_map.items() },
+        "track_map" : { remote_track_id : local_track_id for remote_track_id, (local_track_id, _)  in track_map.items() },
+    }
+
     set_workdir(output_dir)
     save_data(out, "remote_to_local_map")