def get_cluster_list(patterns): cl = ClusterList() for pattern in patterns: c = Cluster(pattern) c.files = [File(f) for f in glob(pattern)] cl.append(c) return cl
def __init__(self, album_id, discid=None): DataObject.__init__(self, album_id) self.metadata = Metadata() self.orig_metadata = Metadata() self.tracks = [] self.loaded = False self.load_task = None self.release_group = None self._files_count = 0 self._requests = 0 self._tracks_loaded = False self._discids = set() self._recordings_map = {} if discid: self._discids.add(discid) self._after_load_callbacks = [] self.unmatched_files = Cluster(_("Unmatched Files"), special=True, related_album=self, hide_if_empty=True) self.unmatched_files.metadata_images_changed.connect( self.update_metadata_images) self.status = AlbumStatus.NONE self._album_artists = [] self.update_metadata_images_enabled = True
def test_add_no_changes(self): cluster = Cluster('Test') cluster.files = self.test_files update_metadata_images(cluster) added = add_metadata_images(cluster, [self.test_files[1]]) self.assertFalse(added) self.assertEqual(set(self.test_images), set(cluster.metadata.images))
def test_add_to_cluster(self): cluster = Cluster('Test') cluster.files = [self.test_files[0]] update_metadata_images(cluster) cluster.files += self.test_files[1:] add_metadata_images(cluster, self.test_files[1:]) self.assertEqual(set(self.test_images), set(cluster.metadata.images)) self.assertFalse(cluster.metadata.has_common_images)
def test_remove_from_cluster_with_common_images(self): cluster = Cluster('Test') cluster.files = list(self.test_files[1:]) update_metadata_images(cluster) cluster.files.remove(self.test_files[1]) remove_metadata_images(cluster, [self.test_files[1]]) self.assertEqual(set(self.test_images[1:]), set(cluster.metadata.images)) self.assertTrue(cluster.metadata.has_common_images)
def __init__(self, id, discid=None): DataObject.__init__(self, id) self.metadata = Metadata() self.tracks = [] self.loaded = False self.load_task = None self.release_group = None self._files = 0 self._requests = 0 self._tracks_loaded = False self._discid = discid self._after_load_callbacks = [] self.unmatched_files = Cluster(_("Unmatched Files"), special=True, related_album=self, hide_if_empty=True) self.errors = []
def test_remove_from_empty_cluster(self): cluster = Cluster('Test') cluster.files.append(File('test1.flac')) update_metadata_images(cluster) remove_metadata_images(cluster, [cluster.files[0]]) self.assertEqual(set(), set(cluster.metadata.images)) self.assertTrue(cluster.metadata.has_common_images)
def test_cluster_no_metadata(self): files = [ self._create_file(None, None, 'foo1.ogg'), self._create_file(None, None, 'foo2.ogg'), self._create_file(None, None, 'foo3.ogg'), ] clusters = list(Cluster.cluster(files)) self.assertEqual(0, len(clusters))
def test_cluster_single_cluster(self): files = [ self._create_file('album foo', 'artist bar'), self._create_file('album foo', 'artist foo'), self._create_file('album foo', 'artist foo'), ] clusters = list(Cluster.cluster(files)) self.assertEqual(1, len(clusters)) self.assertClusterEqual('album foo', 'artist foo', files, clusters[0])
def load_cluster(self, name, artist): for cluster in self.clusters: cm = cluster.metadata if name == cm["album"] and artist == cm["albumartist"]: return cluster cluster = Cluster(name, artist) self.clusters.append(cluster) self.cluster_added.emit(cluster) return cluster
def __init__(self, id, discid=None): DataObject.__init__(self, id) self.metadata = Metadata() self.tracks = [] self.format_str = "" self.loaded = False self.load_task = None self.rgloaded = False self.rgid = None self._files = 0 self._requests = 0 self._tracks_loaded = False self._discid = discid self._after_load_callbacks = queue.Queue() self.other_versions = [] self.unmatched_files = Cluster(_("Unmatched Files"), special=True, related_album=self, hide_if_empty=True)
def test_common_artist_name(self): files = [ self._create_file('cluster 1', 'artist 1'), self._create_file('cluster 1', 'artist 2'), self._create_file('cluster 1', 'artist2'), self._create_file('cluster 1', 'artist 1'), self._create_file('cluster 1', 'artist 2'), ] clusters = list(Cluster.cluster(files)) self.assertEqual(1, len(clusters)) self.assertClusterEqual('cluster 1', 'artist 2', files, clusters[0])
def cluster(self, objs): """Group files with similar metadata to 'clusters'.""" log.debug("Clustering %r", objs) if len(objs) <= 1 or self.unclustered_files in objs: files = list(self.unclustered_files.files) else: files = self.get_files_from_objects(objs) for name, artist, files in Cluster.cluster(files, 1.0): QtCore.QCoreApplication.processEvents() cluster = self.load_cluster(name, artist) for file in sorted(files, key=attrgetter('discnumber', 'tracknumber', 'base_filename')): file.move(cluster)
def test_update_cluster_images(self): cluster = Cluster('Test') cluster.files = list(self.test_files) update_metadata_images(cluster) self.assertEqual(set(self.test_images), set(cluster.metadata.images)) self.assertFalse(cluster.metadata.has_common_images) cluster.files.remove(self.test_files[2]) update_metadata_images(cluster) self.assertEqual(set(self.test_images), set(cluster.metadata.images)) self.assertFalse(cluster.metadata.has_common_images) cluster.files.remove(self.test_files[0]) update_metadata_images(cluster) self.assertEqual(set(self.test_images[1:]), set(cluster.metadata.images)) self.assertTrue(cluster.metadata.has_common_images) cluster.files.append(self.test_files[2]) update_metadata_images(cluster) self.assertEqual(set(self.test_images[1:]), set(cluster.metadata.images)) self.assertTrue(cluster.metadata.has_common_images)
def __init__(self, album_id, discid=None): self.tracks = [] self.loaded = False self.load_task = None self.release_group = None self._files = 0 self._requests = 0 self._tracks_loaded = False self._discid = discid self._after_load_callbacks = [] self.unmatched_files = Cluster(_("Unmatched Files"), special=True, related_album=self, hide_if_empty=True) self.errors = [] self.status = None
def __init__(self, id, discid=None): DataObject.__init__(self, id) self.metadata = Metadata() self.tracks = [] self.loaded = False self.load_task = None self.release_group = None self._files = 0 self._requests = 0 self._tracks_loaded = False self._discid = discid self._after_load_callbacks = queue.Queue() self.unmatched_files = Cluster(_("Unmatched Files"), special=True, related_album=self, hide_if_empty=True)
def cluster(self, objs): """Group files with similar metadata to 'clusters'.""" self.log.debug("Clustering %r", objs) if len(objs) <= 1 or self.unmatched_files in objs: files = list(self.unmatched_files.files) else: files = self.get_files_from_objects(objs) fcmp = lambda a, b: (cmp(a.discnumber, b.discnumber) or cmp( a.tracknumber, b.tracknumber) or cmp(a.base_filename, b. base_filename)) for name, artist, files in Cluster.cluster(files, 1.0): QtCore.QCoreApplication.processEvents() cluster = self.load_cluster(name, artist) for file in sorted(files, fcmp): file.move(cluster)
def test_cluster_multi(self): files = [ self._create_file('album cluster1', 'artist bar'), self._create_file('album cluster2', 'artist foo'), self._create_file('album cluster1', 'artist foo'), self._create_file('albumcluster2', 'artist bar'), self._create_file('album single', 'artist bar'), ] clusters = list(Cluster.cluster(files)) self.assertEqual(3, len(clusters)) self.assertClusterEqual('album cluster1', 'artist bar', {files[0], files[2]}, clusters[0]) self.assertClusterEqual('album cluster2', 'artist foo', {files[1], files[3]}, clusters[1]) self.assertClusterEqual('album single', 'artist bar', {files[4]}, clusters[2])
def cluster(self, objs): """Group files with similar metadata to 'clusters'.""" log.debug("Clustering %r", objs) if len(objs) <= 1 or self.unclustered_files in objs: files = list(self.unclustered_files.files) else: files = self.get_files_from_objects(objs) self.window.set_sorting(False) cluster_files = defaultdict(list) for name, artist, files in Cluster.cluster(files, 1.0, self): cluster = self.load_cluster(name, artist) cluster_files[cluster].extend(files) for cluster, files in process_events_iter(cluster_files.items()): cluster.add_files(files) self.window.set_sorting(True)
def cluster(self, objs): """Group files with similar metadata to 'clusters'.""" log.debug("Clustering %r", objs) if len(objs) <= 1 or self.unmatched_files in objs: files = list(self.unmatched_files.files) else: files = self.get_files_from_objects(objs) fcmp = lambda a, b: ( cmp(a.discnumber, b.discnumber) or cmp(a.tracknumber, b.tracknumber) or cmp(a.base_filename, b.base_filename)) for name, artist, files in Cluster.cluster(files, 1.0): QtCore.QCoreApplication.processEvents() cluster = self.load_cluster(name, artist) for file in sorted(files, fcmp): file.move(cluster)
def __init__(self, id, discid=None): DataObject.__init__(self, id) self.metadata = Metadata() self.tracks = [] self.format_str = "" self.tracks_str = "" self.loaded = False self.load_task = None self.rgloaded = False self.rgid = None self._files = 0 self._requests = 0 self._discid = discid self._after_load_callbacks = queue.Queue() self._metadata_processors = None self.other_versions = [] self.unmatched_files = Cluster(_("Unmatched Files"), special=True, related_album=self, hide_if_empty=True)
def test_cluster_by_path(self): files = [ self._create_file(None, None, 'artist1/album1/foo1.ogg'), self._create_file(None, None, 'album2/foo1.ogg'), self._create_file(None, None, 'artist1/album1/foo2.ogg'), self._create_file(None, None, 'album2/foo2.ogg'), self._create_file(None, None, 'single/foo.ogg'), self._create_file(None, None, 'album1/foo3.ogg'), ] clusters = list(Cluster.cluster(files)) self.assertEqual(3, len(clusters)) self.assertClusterEqual('album1', 'artist1', {files[0], files[2], files[5]}, clusters[0]) self.assertClusterEqual('album2', 'Diverse Interpreten', {files[1], files[3]}, clusters[1]) self.assertClusterEqual('single', 'Diverse Interpreten', {files[4]}, clusters[2])
def __init__(self, album_id, discid=None): DataObject.__init__(self, album_id) self.metadata = Metadata() self.orig_metadata = Metadata() self.tracks = [] self.loaded = False self.load_task = None self.release_group = None self._files = 0 self._requests = 0 self._tracks_loaded = False self._discid = discid self._after_load_callbacks = [] self.unmatched_files = Cluster(_("Unmatched Files"), special=True, related_album=self, hide_if_empty=True) self.errors = [] self.status = None self._album_artists = [] self.update_metadata_images_enabled = True
def cluster(self, objs): """Group files with similar metadata to 'clusters'.""" log.debug("Clustering %r", objs) if len(objs) <= 1 or self.unclustered_files in objs: files = list(self.unclustered_files.files) else: files = self.get_files_from_objects(objs) self.window.set_sorting(False) cluster_files = defaultdict(list) for name, artist, files in Cluster.cluster(files, 1.0, self): cluster = self.load_cluster(name, artist) cluster_files[cluster].extend( sorted(files, key=attrgetter('discnumber', 'tracknumber', 'base_filename'))) for cluster, files in cluster_files.items(): cluster.add_files(files) QtCore.QCoreApplication.processEvents() self.window.set_sorting(True)
class Album(object): release_group_loaded = QtCore.pyqtSignal() def __init__(self, album_id, discid=None): self.tracks = [] self.loaded = False self.load_task = None self.release_group = None self._files = 0 self._requests = 0 self._tracks_loaded = False self._discid = discid self._after_load_callbacks = [] self.unmatched_files = Cluster(_("Unmatched Files"), special=True, related_album=self, hide_if_empty=True) self.errors = [] self.status = None def __repr__(self): return '<Album %s MetadataAlbum>' % (self.id) def iterfiles(self, save=False): for track in self.tracks: for f in track.iterfiles(): yield f if not save: for f in self.unmatched_files.iterfiles(): yield f
class Album(DataObject, Item): release_group_loaded = QtCore.pyqtSignal() def __init__(self, id, discid=None): DataObject.__init__(self, id) self.metadata = Metadata() self.tracks = [] self.loaded = False self.load_task = None self.release_group = None self._files = 0 self._requests = 0 self._tracks_loaded = False self._discid = discid self._after_load_callbacks = [] self.unmatched_files = Cluster(_("Unmatched Files"), special=True, related_album=self, hide_if_empty=True) self.errors = [] self.status = None self._album_artists = [] def __repr__(self): return '<Album %s %r>' % (self.id, self.metadata[u"album"]) def iterfiles(self, save=False): for track in self.tracks: for file in track.iterfiles(): yield file if not save: for file in self.unmatched_files.iterfiles(): yield file def append_album_artist(self, id): """Append artist id to the list of album artists and return an AlbumArtist instance""" album_artist = AlbumArtist(id) self._album_artists.append(album_artist) return album_artist def get_album_artists(self): """Returns the list of album artists (as AlbumArtist objects)""" return self._album_artists def _parse_release(self, document): log.debug("Loading release %r ...", self.id) self._tracks_loaded = False release_node = document.metadata[0].release[0] if release_node.id != self.id: self.tagger.mbid_redirects[self.id] = release_node.id album = self.tagger.albums.get(release_node.id) if album: log.debug("Release %r already loaded", release_node.id) album.match_files(self.unmatched_files.files) album.update() self.tagger.remove_album(self) return False else: del self.tagger.albums[self.id] self.tagger.albums[release_node.id] = self self.id = release_node.id # Get release metadata m = self._new_metadata m.length = 0 rg_node = release_node.release_group[0] rg = self.release_group = self.tagger.get_release_group_by_id( rg_node.id) rg.loaded_albums.add(self.id) rg.refcount += 1 release_group_to_metadata(rg_node, rg.metadata, rg) m.copy(rg.metadata) release_to_metadata(release_node, m, album=self) if self._discid: m['musicbrainz_discid'] = self._discid # Custom VA name if m['musicbrainz_albumartistid'] == VARIOUS_ARTISTS_ID: m['albumartistsort'] = m['albumartist'] = config.setting['va_name'] # Convert Unicode punctuation if config.setting['convert_punctuation']: m.apply_func(asciipunct) m['totaldiscs'] = release_node.medium_list[0].count # Add album to collections if "collection_list" in release_node.children: for node in release_node.collection_list[0].collection: if node.editor[0].text.lower( ) == config.persist["oauth_username"].lower(): if node.id not in user_collections: user_collections[node.id] = \ Collection(node.id, node.name[0].text, node.release_list[0].count) user_collections[node.id].releases.add(self.id) # Run album metadata plugins try: run_album_metadata_processors(self, m, release_node) except: self.error_append(traceback.format_exc()) self._release_node = release_node return True def _release_request_finished(self, document, http, error): if self.load_task is None: return self.load_task = None parsed = False try: if error: self.error_append(unicode(http.errorString())) # Fix for broken NAT releases if error == QtNetwork.QNetworkReply.ContentNotFoundError: nats = False nat_name = config.setting["nat_name"] files = list(self.unmatched_files.files) for file in files: recordingid = file.metadata["musicbrainz_recordingid"] if mbid_validate(recordingid) and file.metadata[ "album"] == nat_name: nats = True self.tagger.move_file_to_nat(file, recordingid) self.tagger.nats.update() if nats and not self.get_num_unmatched_files(): self.tagger.remove_album(self) error = False else: try: parsed = self._parse_release(document) except: error = True self.error_append(traceback.format_exc()) finally: self._requests -= 1 if parsed or error: self._finalize_loading(error) # does http need to be set to None to free the memory used by the network response? # http://pyqt.sourceforge.net/Docs/PyQt4/qnetworkaccessmanager.html says: # After the request has finished, it is the responsibility of the user # to delete the QNetworkReply object at an appropriate time. # Do not directly delete it inside the slot connected to finished(). # You can use the deleteLater() function. def error_append(self, msg): log.error(msg) self.errors.append(msg) def _finalize_loading(self, error): if error: self.metadata.clear() self.status = _("[could not load album %s]") % self.id del self._new_metadata del self._new_tracks self.update() return if self._requests > 0: return if not self._tracks_loaded: artists = set() totalalbumtracks = 0 absolutetracknumber = 0 va = self._new_metadata[ 'musicbrainz_albumartistid'] == VARIOUS_ARTISTS_ID djmix_ars = {} if hasattr(self._new_metadata, "_djmix_ars"): djmix_ars = self._new_metadata._djmix_ars for medium_node in self._release_node.medium_list[0].medium: mm = Metadata() mm.copy(self._new_metadata) medium_to_metadata(medium_node, mm) discpregap = False for dj in djmix_ars.get(mm["discnumber"], []): mm.add("djmixer", dj) if "pregap" in medium_node.children: discpregap = True absolutetracknumber += 1 track = self._finalize_loading_track( medium_node.pregap[0], mm, artists, va, absolutetracknumber, discpregap) track.metadata['~pregap'] = "1" for track_node in medium_node.track_list[0].track: absolutetracknumber += 1 track = self._finalize_loading_track( track_node, mm, artists, va, absolutetracknumber, discpregap) if "data_track_list" in medium_node.children: for track_node in medium_node.data_track_list[0].track: absolutetracknumber += 1 track = self._finalize_loading_track( track_node, mm, artists, va, absolutetracknumber, discpregap) track.metadata['~datatrack'] = "1" totalalbumtracks = str(absolutetracknumber) for track in self._new_tracks: track.metadata["~totalalbumtracks"] = totalalbumtracks if len(artists) > 1: track.metadata["~multiartist"] = "1" del self._release_node self._tracks_loaded = True if not self._requests: # Prepare parser for user's script if config.setting["enable_tagger_script"]: script = config.setting["tagger_script"] if script: parser = ScriptParser() for track in self._new_tracks: # Run tagger script for each track try: parser.eval(script, track.metadata) except: self.error_append(traceback.format_exc()) # Strip leading/trailing whitespace track.metadata.strip_whitespace() # Run tagger script for the album itself try: parser.eval(script, self._new_metadata) except: self.error_append(traceback.format_exc()) self._new_metadata.strip_whitespace() for track in self.tracks: for file in list(track.linked_files): file.move(self.unmatched_files) self.metadata = self._new_metadata self.tracks = self._new_tracks del self._new_metadata del self._new_tracks self.loaded = True self.status = None self.match_files(self.unmatched_files.files) self.update() self.tagger.window.set_statusbar_message( N_('Album %(id)s loaded: %(artist)s - %(album)s'), { 'id': self.id, 'artist': self.metadata['albumartist'], 'album': self.metadata['album'] }, timeout=3000) for func in self._after_load_callbacks: func() self._after_load_callbacks = [] def _finalize_loading_track(self, track_node, metadata, artists, va, absolutetracknumber, discpregap): track = Track(track_node.recording[0].id, self) self._new_tracks.append(track) # Get track metadata tm = track.metadata tm.copy(metadata) track_to_metadata(track_node, track) track.metadata["~absolutetracknumber"] = absolutetracknumber track._customize_metadata() self._new_metadata.length += tm.length artists.add(tm["artist"]) if va: tm["compilation"] = "1" if discpregap: tm["~discpregap"] = "1" # Run track metadata plugins try: run_track_metadata_processors(self, tm, self._release_node, track_node) except: self.error_append(traceback.format_exc()) return track def load(self, priority=False, refresh=False): if self._requests: log.info("Not reloading, some requests are still active.") return self.tagger.window.set_statusbar_message( N_('Loading album %(id)s ...'), {'id': self.id}) self.loaded = False self.status = _("[loading album information]") if self.release_group: self.release_group.loaded = False self.release_group.folksonomy_tags.clear() self.metadata.clear() self.folksonomy_tags.clear() self.update() self._new_metadata = Metadata() self._new_tracks = [] self._requests = 1 self.errors = [] require_authentication = False inc = [ 'release-groups', 'media', 'recordings', 'artist-credits', 'artists', 'aliases', 'labels', 'isrcs', 'collections' ] if config.setting['release_ars'] or config.setting['track_ars']: inc += [ 'artist-rels', 'release-rels', 'url-rels', 'recording-rels', 'work-rels' ] if config.setting['track_ars']: inc += ['recording-level-rels', 'work-level-rels'] if config.setting['folksonomy_tags']: if config.setting['only_my_tags']: require_authentication = True inc += ['user-tags'] else: inc += ['tags'] if config.setting['enable_ratings']: require_authentication = True inc += ['user-ratings'] self.load_task = self.tagger.xmlws.get_release_by_id( self.id, self._release_request_finished, inc=inc, mblogin=require_authentication, priority=priority, refresh=refresh) def run_when_loaded(self, func): if self.loaded: func() else: self._after_load_callbacks.append(func) def stop_loading(self): if self.load_task: self.tagger.xmlws.remove_task(self.load_task) self.load_task = None def update(self, update_tracks=True): if self.item: self.item.update(update_tracks) def _add_file(self, track, file): self._files += 1 self.update(update_tracks=False) def _remove_file(self, track, file): self._files -= 1 self.update(update_tracks=False) def match_files(self, files, use_recordingid=True): """Match files to tracks on this album, based on metadata similarity or recordingid.""" for file in list(files): if file.state == File.REMOVED: continue matches = [] recordingid = file.metadata['musicbrainz_recordingid'] if use_recordingid and mbid_validate(recordingid): matches = self._get_recordingid_matches(file, recordingid) if not matches: for track in self.tracks: sim = track.metadata.compare(file.orig_metadata) if sim >= config.setting['track_matching_threshold']: matches.append((sim, track)) if matches: matches.sort(reverse=True) file.move(matches[0][1]) else: file.move(self.unmatched_files) def match_file(self, file, recordingid=None): """Match the file on a track on this album, based on recordingid or metadata similarity.""" if file.state == File.REMOVED: return if recordingid is not None: matches = self._get_recordingid_matches(file, recordingid) if matches: matches.sort(reverse=True) file.move(matches[0][1]) return self.match_files([file], use_recordingid=False) def _get_recordingid_matches(self, file, recordingid): matches = [] tracknumber = file.metadata['tracknumber'] discnumber = file.metadata['discnumber'] for track in self.tracks: tm = track.metadata if recordingid == tm['musicbrainz_recordingid']: if tracknumber == tm['tracknumber']: if discnumber == tm['discnumber']: matches.append((4.0, track)) break else: matches.append((3.0, track)) else: matches.append((2.0, track)) return matches def can_save(self): return self._files > 0 def can_remove(self): return True def can_edit_tags(self): return True def can_analyze(self): return False def can_autotag(self): return False def can_refresh(self): return True def can_view_info(self): return (self.loaded and self.metadata and self.metadata.images) or self.errors def is_album_like(self): return True def get_num_matched_tracks(self): num = 0 for track in self.tracks: if track.is_linked(): num += 1 return num def get_num_unmatched_files(self): return len(self.unmatched_files.files) def get_num_total_files(self): return self._files + len(self.unmatched_files.files) def is_complete(self): if not self.tracks: return False for track in self.tracks: if not track.is_complete(): return False else: return True def is_modified(self): if self.tracks: for track in self.tracks: for file in track.linked_files: if not file.is_saved(): return True return False def get_num_unsaved_files(self): count = 0 for track in self.tracks: for file in track.linked_files: if not file.is_saved(): count += 1 return count def column(self, column): if column == 'title': if self.status is not None: title = self.status else: title = self.metadata['album'] if self.tracks: linked_tracks = 0 for track in self.tracks: if track.is_linked(): linked_tracks += 1 text = u'%s\u200E (%d/%d' % (title, linked_tracks, len(self.tracks)) unmatched = self.get_num_unmatched_files() if unmatched: text += '; %d?' % (unmatched, ) unsaved = self.get_num_unsaved_files() if unsaved: text += '; %d*' % (unsaved, ) text += ungettext("; %i image", "; %i images", len(self.metadata.images)) % len( self.metadata.images) return text + ')' else: return title elif column == '~length': length = self.metadata.length if length: return format_time(length) else: return '' elif column == 'artist': return self.metadata['albumartist'] else: return '' def switch_release_version(self, mbid): if mbid == self.id: return for file in list(self.iterfiles(True)): file.move(self.unmatched_files) album = self.tagger.albums.get(mbid) if album: album.match_files(self.unmatched_files.files) album.update() self.tagger.remove_album(self) else: del self.tagger.albums[self.id] self.release_group.loaded_albums.discard(self.id) self.id = mbid self.tagger.albums[mbid] = self self.load(priority=True, refresh=True)
class Album(DataObject, Item): release_group_loaded = QtCore.pyqtSignal() def __init__(self, id, discid=None): DataObject.__init__(self, id) self.metadata = Metadata() self.tracks = [] self.format_str = "" self.loaded = False self.load_task = None self.rgloaded = False self.rgid = None self._files = 0 self._requests = 0 self._tracks_loaded = False self._discid = discid self._after_load_callbacks = queue.Queue() self.other_versions = [] self.unmatched_files = Cluster(_("Unmatched Files"), special=True, related_album=self, hide_if_empty=True) def __repr__(self): return '<Album %s %r>' % (self.id, self.metadata[u"album"]) def iterfiles(self, save=False): for track in self.tracks: for file in track.iterfiles(): yield file if not save: for file in self.unmatched_files.iterfiles(): yield file def _parse_release(self, document): self.log.debug("Loading release %r", self.id) self._tracks_loaded = False release_node = document.metadata[0].release[0] if release_node.id != self.id: self.tagger.mbid_redirects[self.id] = release_node.id album = self.tagger.albums.get(release_node.id) if album: self.log.debug("Release %r already loaded", release_node.id) album.match_files(self.unmatched_files.files) album.update() self.tagger.remove_album(self) return False else: del self.tagger.albums[self.id] self.tagger.albums[release_node.id] = self self.id = release_node.id # Get release metadata m = self._new_metadata m.length = 0 release_to_metadata(release_node, m, config=self.config, album=self) self.format_str = media_formats_from_node(release_node.medium_list[0]) self.rgid = release_node.release_group[0].id if self._discid: m['musicbrainz_discid'] = self._discid # Custom VA name if m['musicbrainz_albumartistid'] == VARIOUS_ARTISTS_ID: m['albumartistsort'] = m['albumartist'] = self.config.setting[ 'va_name'] # Convert Unicode punctuation if self.config.setting['convert_punctuation']: m.apply_func(asciipunct) m['totaldiscs'] = release_node.medium_list[0].count # Run album metadata plugins try: run_album_metadata_processors(self, m, release_node) except: self.log.error(traceback.format_exc()) self._release_node = release_node return True def _release_request_finished(self, document, http, error): if self.load_task is None: return self.load_task = None parsed = False try: if error: self.log.error("%r", unicode(http.errorString())) # Fix for broken NAT releases if error == QtNetwork.QNetworkReply.ContentNotFoundError: nats = False nat_name = self.config.setting["nat_name"] files = list(self.unmatched_files.files) for file in files: trackid = file.metadata["musicbrainz_trackid"] if mbid_validate(trackid) and file.metadata[ "album"] == nat_name: nats = True self.tagger.move_file_to_nat(file, trackid) self.tagger.nats.update() if nats and not self.get_num_unmatched_files(): self.tagger.remove_album(self) error = False else: try: parsed = self._parse_release(document) except: error = True self.log.error(traceback.format_exc()) finally: self._requests -= 1 if parsed or error: self._finalize_loading(error) def _parse_release_group(self, document): for node in document.metadata[0].release_list[0].release: v = {} v["mbid"] = node.id v["date"] = node.date[0].text if "date" in node.children else "" v["country"] = node.country[ 0].text if "country" in node.children else "" labels, catnums = label_info_from_node(node.label_info_list[0]) v["labels"] = ", ".join(set(labels)) v["catnums"] = ", ".join(set(catnums)) v["tracks"] = " + ".join( [m.track_list[0].count for m in node.medium_list[0].medium]) v["format"] = media_formats_from_node(node.medium_list[0]) self.other_versions.append(v) self.other_versions.sort(key=lambda x: x["date"]) def _release_group_request_finished(self, document, http, error): try: if error: self.log.error("%r", unicode(http.errorString())) else: try: self._parse_release_group(document) except: error = True self.log.error(traceback.format_exc()) finally: self.rgloaded = True self.release_group_loaded.emit() def _finalize_loading(self, error): if error: self.metadata.clear() self.metadata['album'] = _("[could not load album %s]") % self.id del self._new_metadata del self._new_tracks self.update() return if self._requests > 0: return if not self._tracks_loaded: artists = set() totalalbumtracks = 0 djmix_ars = {} if hasattr(self._new_metadata, "_djmix_ars"): djmix_ars = self._new_metadata._djmix_ars for medium_node in self._release_node.medium_list[0].medium: mm = Metadata() mm.copy(self._new_metadata) medium_to_metadata(medium_node, mm) totalalbumtracks += int(mm["totaltracks"]) for dj in djmix_ars.get(mm["discnumber"], []): mm.add("djmixer", dj) for track_node in medium_node.track_list[0].track: track = Track(track_node.recording[0].id, self) self._new_tracks.append(track) # Get track metadata tm = track.metadata tm.copy(mm) track_to_metadata(track_node, track, self.config) track._customize_metadata() self._new_metadata.length += tm.length artists.add(tm["musicbrainz_artistid"]) # Run track metadata plugins try: run_track_metadata_processors(self, tm, self._release_node, track_node) except: self.log.error(traceback.format_exc()) totalalbumtracks = str(totalalbumtracks) for track in self._new_tracks: track.metadata["~totalalbumtracks"] = totalalbumtracks if len(artists) > 1: track.metadata["compilation"] = "1" del self._release_node self._tracks_loaded = True if not self._requests: # Prepare parser for user's script if self.config.setting["enable_tagger_script"]: script = self.config.setting["tagger_script"] if script: parser = ScriptParser() for track in self._new_tracks: # Run tagger script for each track try: parser.eval(script, track.metadata) except: self.log.error(traceback.format_exc()) # Strip leading/trailing whitespace track.metadata.strip_whitespace() # Run tagger script for the album itself try: parser.eval(script, self._new_metadata) except: self.log.error(traceback.format_exc()) self._new_metadata.strip_whitespace() for track in self.tracks: for file in list(track.linked_files): file.move(self.unmatched_files) self.metadata = self._new_metadata self.tracks = self._new_tracks del self._new_metadata del self._new_tracks self.loaded = True self.match_files(self.unmatched_files.files) self.update() self.tagger.window.set_statusbar_message('Album %s loaded', self.id, timeout=3000) while self._after_load_callbacks.qsize() > 0: func = self._after_load_callbacks.get() func() def load(self): if self._requests: self.log.info("Not reloading, some requests are still active.") return self.tagger.window.set_statusbar_message('Loading album %s...', self.id) self.loaded = False self.rgloaded = False self.rgid = None self.other_versions = [] self.metadata.clear() self.metadata['album'] = _("[loading album information]") self.update() self._new_metadata = Metadata() self._new_tracks = [] self._requests = 1 require_authentication = False inc = [ 'release-groups', 'media', 'recordings', 'puids', 'artist-credits', 'artists', 'aliases', 'labels', 'isrcs' ] if self.config.setting['release_ars'] or self.config.setting[ 'track_ars']: inc += [ 'artist-rels', 'release-rels', 'url-rels', 'recording-rels', 'work-rels' ] if self.config.setting['track_ars']: inc += ['recording-level-rels', 'work-level-rels'] if self.config.setting['folksonomy_tags']: if self.config.setting['only_my_tags']: require_authentication = True inc += ['user-tags'] else: inc += ['tags'] if self.config.setting['enable_ratings']: require_authentication = True inc += ['user-ratings'] self.load_task = self.tagger.xmlws.get_release_by_id( self.id, self._release_request_finished, inc=inc, mblogin=require_authentication) def run_when_loaded(self, func): if self.loaded: func() else: self._after_load_callbacks.put(func) def stop_loading(self): if self.load_task: self.tagger.xmlws.remove_task(self.load_task) self.load_task = None def update(self, update_tracks=True): if self.item: self.item.update(update_tracks) def _add_file(self, track, file): self._files += 1 self.update(False) def _remove_file(self, track, file): self._files -= 1 self.update(False) def match_files(self, files, use_trackid=True): """Match files to tracks on this album, based on metadata similarity or trackid.""" for file in list(files): if file.state == File.REMOVED: continue matches = [] trackid = file.metadata['musicbrainz_trackid'] if use_trackid and mbid_validate(trackid): matches = self._get_trackid_matches(file, trackid) if not matches: for track in self.tracks: sim = track.metadata.compare(file.orig_metadata) if sim >= self.config.setting['track_matching_threshold']: matches.append((sim, track)) if matches: matches.sort(reverse=True) file.move(matches[0][1]) else: file.move(self.unmatched_files) def match_file(self, file, trackid=None): """Match the file on a track on this album, based on trackid or metadata similarity.""" if file.state == File.REMOVED: return if trackid is not None: matches = self._get_trackid_matches(file, trackid) if matches: matches.sort(reverse=True) file.move(matches[0][1]) return self.match_files([file], use_trackid=False) def _get_trackid_matches(self, file, trackid): matches = [] tracknumber = file.metadata['tracknumber'] discnumber = file.metadata['discnumber'] for track in self.tracks: tm = track.metadata if trackid == tm['musicbrainz_trackid']: if tracknumber == tm['tracknumber']: if discnumber == tm['discnumber']: matches.append((4.0, track)) break else: matches.append((3.0, track)) else: matches.append((2.0, track)) return matches def can_save(self): return self._files > 0 def can_remove(self): return True def can_edit_tags(self): return False def can_analyze(self): return False def can_autotag(self): return False def can_refresh(self): return True def get_num_matched_tracks(self): num = 0 for track in self.tracks: if track.is_linked(): num += 1 return num def get_num_unmatched_files(self): return len(self.unmatched_files.files) def is_complete(self): if not self.tracks: return False for track in self.tracks: if track.num_linked_files != 1: return False else: return True def get_num_unsaved_files(self): count = 0 for track in self.tracks: for file in track.linked_files: if not file.is_saved(): count += 1 return count def column(self, column): if column == 'title': if self.tracks: linked_tracks = 0 for track in self.tracks: if track.is_linked(): linked_tracks += 1 text = u'%s\u200E (%d/%d' % (self.metadata['album'], linked_tracks, len(self.tracks)) unmatched = self.get_num_unmatched_files() if unmatched: text += '; %d?' % (unmatched, ) unsaved = self.get_num_unsaved_files() if unsaved: text += '; %d*' % (unsaved, ) return text + ')' else: return self.metadata['album'] elif column == '~length': length = self.metadata.length if length: return format_time(length) else: return '' elif column == 'artist': return self.metadata['albumartist'] else: return '' def switch_release_version(self, mbid): if mbid == self.id: return for file in list(self.iterfiles(True)): file.move(self.unmatched_files) album = self.tagger.albums.get(mbid) if album: album.match_files(self.unmatched_files.files) album.update() self.tagger.remove_album(self) else: del self.tagger.albums[self.id] self.id = mbid self.tagger.albums[mbid] = self self.load()
class Album(DataObject, Item): release_group_loaded = QtCore.pyqtSignal() def __init__(self, album_id, discid=None): DataObject.__init__(self, album_id) self.metadata = Metadata() self.orig_metadata = Metadata() self.tracks = [] self.loaded = False self.load_task = None self.release_group = None self._files = 0 self._requests = 0 self._tracks_loaded = False self._discids = set() if discid: self._discids.add(discid) self._after_load_callbacks = [] self.unmatched_files = Cluster(_("Unmatched Files"), special=True, related_album=self, hide_if_empty=True) self.errors = [] self.status = None self._album_artists = [] self.update_metadata_images_enabled = True def __repr__(self): return '<Album %s %r>' % (self.id, self.metadata["album"]) def iterfiles(self, save=False): for track in self.tracks: for file in track.iterfiles(): yield file if not save: for file in self.unmatched_files.iterfiles(): yield file def enable_update_metadata_images(self, enabled): self.update_metadata_images_enabled = enabled def append_album_artist(self, album_artist_id): """Append artist id to the list of album artists and return an AlbumArtist instance""" album_artist = AlbumArtist(album_artist_id) self._album_artists.append(album_artist) return album_artist def add_discid(self, discid): if not discid: return self._discids.add(discid) for track in self.tracks: medium_discids = track.metadata.getall('~musicbrainz_discids') track_discids = list(self._discids.intersection(medium_discids)) if track_discids: track.metadata['musicbrainz_discid'] = track_discids track.update() for file in track.linked_files: file.metadata['musicbrainz_discid'] = track_discids file.update() def get_album_artists(self): """Returns the list of album artists (as AlbumArtist objects)""" return self._album_artists def _parse_release(self, release_node): log.debug("Loading release %r ...", self.id) self._tracks_loaded = False release_id = release_node['id'] if release_id != self.id: self.tagger.mbid_redirects[self.id] = release_id album = self.tagger.albums.get(release_id) if album: log.debug("Release %r already loaded", release_id) album.match_files(self.unmatched_files.files) album.update() self.tagger.remove_album(self) return False else: del self.tagger.albums[self.id] self.tagger.albums[release_id] = self self.id = release_id # Make the release artist nodes available, since they may # contain supplementary data (aliases, tags, genres, ratings) # which aren't present in the release group, track, or # recording artist nodes. We can copy them into those places # wherever the IDs match, so that the data is shared and # available for use in mbjson.py and external plugins. self._release_artist_nodes = _create_artist_node_dict(release_node) # Get release metadata m = self._new_metadata m.length = 0 rg_node = release_node['release-group'] rg = self.release_group = self.tagger.get_release_group_by_id(rg_node['id']) rg.loaded_albums.add(self.id) rg.refcount += 1 _copy_artist_nodes(self._release_artist_nodes, rg_node) release_group_to_metadata(rg_node, rg.metadata, rg) m.copy(rg.metadata) release_to_metadata(release_node, m, album=self) # Custom VA name if m['musicbrainz_albumartistid'] == VARIOUS_ARTISTS_ID: m['albumartistsort'] = m['albumartist'] = config.setting['va_name'] # Convert Unicode punctuation if config.setting['convert_punctuation']: m.apply_func(asciipunct) m['totaldiscs'] = len(release_node['media']) # Add album to collections add_release_to_user_collections(release_node) # Run album metadata plugins try: run_album_metadata_processors(self, m, release_node) except BaseException: self.error_append(traceback.format_exc()) self._release_node = release_node return True def _release_request_finished(self, document, http, error): if self.load_task is None: return self.load_task = None parsed = False try: if error: self.error_append(http.errorString()) # Fix for broken NAT releases if error == QtNetwork.QNetworkReply.ContentNotFoundError: nats = False nat_name = config.setting["nat_name"] files = list(self.unmatched_files.files) for file in files: recordingid = file.metadata["musicbrainz_recordingid"] if mbid_validate(recordingid) and file.metadata["album"] == nat_name: nats = True self.tagger.move_file_to_nat(file, recordingid) self.tagger.nats.update() if nats and not self.get_num_unmatched_files(): self.tagger.remove_album(self) error = False else: try: parsed = self._parse_release(document) except Exception: error = True self.error_append(traceback.format_exc()) finally: self._requests -= 1 if parsed or error: self._finalize_loading(error) # does http need to be set to None to free the memory used by the network response? # http://qt-project.org/doc/qt-5/qnetworkaccessmanager.html says: # After the request has finished, it is the responsibility of the user # to delete the QNetworkReply object at an appropriate time. # Do not directly delete it inside the slot connected to finished(). # You can use the deleteLater() function. def error_append(self, msg): log.error(msg) self.errors.append(msg) def _finalize_loading(self, error): if error: self.metadata.clear() self.status = _("[could not load album %s]") % self.id del self._new_metadata del self._new_tracks self.update() return if self._requests > 0: return if not self._tracks_loaded: artists = set() totalalbumtracks = 0 absolutetracknumber = 0 va = self._new_metadata['musicbrainz_albumartistid'] == VARIOUS_ARTISTS_ID djmix_ars = {} if hasattr(self._new_metadata, "_djmix_ars"): djmix_ars = self._new_metadata._djmix_ars for medium_node in self._release_node['media']: mm = Metadata() mm.copy(self._new_metadata) medium_to_metadata(medium_node, mm) discpregap = False for dj in djmix_ars.get(mm["discnumber"], []): mm.add("djmixer", dj) if 'discs' in medium_node: discids = [disc.get('id') for disc in medium_node['discs']] mm['~musicbrainz_discids'] = discids mm['musicbrainz_discid'] = list(self._discids.intersection(discids)) if "pregap" in medium_node: discpregap = True absolutetracknumber += 1 track = self._finalize_loading_track(medium_node['pregap'], mm, artists, va, absolutetracknumber, discpregap) track.metadata['~pregap'] = "1" track_count = medium_node['track-count'] if track_count: tracklist_node = medium_node['tracks'] for track_node in tracklist_node: absolutetracknumber += 1 track = self._finalize_loading_track(track_node, mm, artists, va, absolutetracknumber, discpregap) if "data-tracks" in medium_node: for track_node in medium_node['data-tracks']: absolutetracknumber += 1 track = self._finalize_loading_track(track_node, mm, artists, va, absolutetracknumber, discpregap) track.metadata['~datatrack'] = "1" totalalbumtracks = str(absolutetracknumber) for track in self._new_tracks: track.metadata["~totalalbumtracks"] = totalalbumtracks if len(artists) > 1: track.metadata["~multiartist"] = "1" del self._release_node del self._release_artist_nodes self._tracks_loaded = True if not self._requests: self.enable_update_metadata_images(False) # Prepare parser for user's script for s_name, s_text in enabled_tagger_scripts_texts(): parser = ScriptParser() for track in self._new_tracks: # Run tagger script for each track try: parser.eval(s_text, track.metadata) except ScriptError: log.exception("Failed to run tagger script %s on track", s_name) track.metadata.strip_whitespace() # Run tagger script for the album itself try: parser.eval(s_text, self._new_metadata) except ScriptError: log.exception("Failed to run tagger script %s on album", s_name) self._new_metadata.strip_whitespace() for track in self.tracks: track.metadata_images_changed.connect(self.update_metadata_images) for file in list(track.linked_files): file.move(self.unmatched_files) self.metadata = self._new_metadata self.tracks = self._new_tracks del self._new_metadata del self._new_tracks self.loaded = True self.status = None self.match_files(self.unmatched_files.files) self.enable_update_metadata_images(True) self.update() self.tagger.window.set_statusbar_message( N_('Album %(id)s loaded: %(artist)s - %(album)s'), { 'id': self.id, 'artist': self.metadata['albumartist'], 'album': self.metadata['album'] }, timeout=3000 ) for func in self._after_load_callbacks: func() self._after_load_callbacks = [] def _finalize_loading_track(self, track_node, metadata, artists, va, absolutetracknumber, discpregap): # As noted in `_parse_release` above, the release artist nodes # may contain supplementary data that isn't present in track # artist nodes. Similarly, the track artists may contain # information which the recording artists don't. Copy this # information across to wherever the artist IDs match. _copy_artist_nodes(self._release_artist_nodes, track_node) _copy_artist_nodes(self._release_artist_nodes, track_node['recording']) _copy_artist_nodes(_create_artist_node_dict(track_node), track_node['recording']) track = Track(track_node['recording']['id'], self) self._new_tracks.append(track) # Get track metadata tm = track.metadata tm.copy(metadata) track_to_metadata(track_node, track) tm["~absolutetracknumber"] = absolutetracknumber track.orig_metadata.copy(tm) track._customize_metadata() self._new_metadata.length += tm.length artists.add(tm["artist"]) if va: tm["compilation"] = "1" else: del tm["compilation"] if discpregap: tm["~discpregap"] = "1" # Run track metadata plugins try: run_track_metadata_processors(self, tm, self._release_node, track_node) except BaseException: self.error_append(traceback.format_exc()) return track def load(self, priority=False, refresh=False): if self._requests: log.info("Not reloading, some requests are still active.") return self.tagger.window.set_statusbar_message( N_('Loading album %(id)s ...'), {'id': self.id} ) self.loaded = False self.status = _("[loading album information]") if self.release_group: self.release_group.loaded = False self.release_group.genres.clear() self.metadata.clear() self.genres.clear() self.update() self._new_metadata = Metadata() self._new_tracks = [] self._requests = 1 self.errors = [] require_authentication = False inc = ['release-groups', 'media', 'discids', 'recordings', 'artist-credits', 'artists', 'aliases', 'labels', 'isrcs', 'collections'] if self.tagger.webservice.oauth_manager.is_authorized(): require_authentication = True inc += ['user-collections'] if config.setting['release_ars'] or config.setting['track_ars']: inc += ['artist-rels', 'release-rels', 'url-rels', 'recording-rels', 'work-rels'] if config.setting['track_ars']: inc += ['recording-level-rels', 'work-level-rels'] require_authentication = self.set_genre_inc_params(inc) or require_authentication if config.setting['enable_ratings']: require_authentication = True inc += ['user-ratings'] self.load_task = self.tagger.mb_api.get_release_by_id( self.id, self._release_request_finished, inc=inc, mblogin=require_authentication, priority=priority, refresh=refresh) def run_when_loaded(self, func): if self.loaded: func() else: self._after_load_callbacks.append(func) def stop_loading(self): if self.load_task: self.tagger.webservice.remove_task(self.load_task) self.load_task = None def update(self, update_tracks=True): if self.item: self.item.update(update_tracks) def _add_file(self, track, file): self._files += 1 self.update(update_tracks=False) add_metadata_images(self, [file]) file.metadata_images_changed.connect(self.update_metadata_images) def _remove_file(self, track, file): self._files -= 1 self.update(update_tracks=False) file.metadata_images_changed.disconnect(self.update_metadata_images) remove_metadata_images(self, [file]) def _match_files(self, files, recordingid=None, threshold=0): """Match files to tracks on this album, based on metadata similarity or recordingid.""" tracks_cache = defaultdict(lambda: None) def build_tracks_cache(): for track in self.tracks: tm_recordingid = track.orig_metadata['musicbrainz_recordingid'] tm_tracknumber = track.orig_metadata['tracknumber'] tm_discnumber = track.orig_metadata['discnumber'] for tup in ( (tm_recordingid, tm_tracknumber, tm_discnumber), (tm_recordingid, tm_tracknumber), (tm_recordingid, )): tracks_cache[tup] = track SimMatchAlbum = namedtuple('SimMatchAlbum', 'similarity track') for file in list(files): if file.state == File.REMOVED: continue # if we have a recordingid to match against, use that in priority recid = recordingid or file.metadata['musicbrainz_recordingid'] if recid and mbid_validate(recid): if not tracks_cache: build_tracks_cache() tracknumber = file.metadata['tracknumber'] discnumber = file.metadata['discnumber'] track = (tracks_cache[(recid, tracknumber, discnumber)] or tracks_cache[(recid, tracknumber)] or tracks_cache[(recid, )]) if track: yield (file, track) continue # try to match by similarity def candidates(): for track in self.tracks: yield SimMatchAlbum( similarity=track.metadata.compare(file.orig_metadata), track=track ) no_match = SimMatchAlbum(similarity=-1, track=self.unmatched_files) best_match = find_best_match(candidates, no_match) if best_match.similarity < threshold: yield (file, no_match.track) else: yield (file, best_match.result.track) def match_files(self, files, recordingid=None): """Match and move files to tracks on this album, based on metadata similarity or recordingid.""" moves = self._match_files(files, recordingid=recordingid, threshold=config.setting['track_matching_threshold']) for file, target in moves: file.move(target) def can_save(self): return self._files > 0 def can_remove(self): return True def can_edit_tags(self): return True def can_analyze(self): return False def can_autotag(self): return False def can_refresh(self): return True def can_view_info(self): return (self.loaded and (self.metadata.images or self.orig_metadata.images)) or self.errors def is_album_like(self): return True def get_num_matched_tracks(self): num = 0 for track in self.tracks: if track.is_linked(): num += 1 return num def get_num_unmatched_files(self): return len(self.unmatched_files.files) def get_num_total_files(self): return self._files + len(self.unmatched_files.files) def is_complete(self): if not self.tracks: return False for track in self.tracks: if not track.is_complete(): return False if self.get_num_unmatched_files(): return False else: return True def is_modified(self): if self.tracks: for track in self.tracks: for file in track.linked_files: if not file.is_saved(): return True return False def get_num_unsaved_files(self): count = 0 for track in self.tracks: for file in track.linked_files: if not file.is_saved(): count += 1 return count def column(self, column): if column == 'title': if self.status is not None: title = self.status else: title = self.metadata['album'] if self.tracks: linked_tracks = 0 for track in self.tracks: if track.is_linked(): linked_tracks += 1 text = '%s\u200E (%d/%d' % (title, linked_tracks, len(self.tracks)) unmatched = self.get_num_unmatched_files() if unmatched: text += '; %d?' % (unmatched,) unsaved = self.get_num_unsaved_files() if unsaved: text += '; %d*' % (unsaved,) # CoverArt.set_metadata uses the orig_metadata.images if metadata.images is empty # in order to show existing cover art if there's no cover art for a release. So # we do the same here in order to show the number of images consistently. if self.metadata.images: metadata = self.metadata else: metadata = self.orig_metadata number_of_images = len(metadata.images) if getattr(metadata, 'has_common_images', True): text += ngettext("; %i image", "; %i images", number_of_images) % number_of_images else: text += ngettext("; %i image not in all tracks", "; %i different images among tracks", number_of_images) % number_of_images return text + ')' else: return title elif column == '~length': length = self.metadata.length if length: return format_time(length) else: return '' elif column == 'artist': return self.metadata['albumartist'] else: return '' def switch_release_version(self, mbid): if mbid == self.id: return for file in list(self.iterfiles(True)): file.move(self.unmatched_files) album = self.tagger.albums.get(mbid) if album: album.match_files(self.unmatched_files.files) album.update() self.tagger.remove_album(self) else: del self.tagger.albums[self.id] self.release_group.loaded_albums.discard(self.id) self.id = mbid self.tagger.albums[mbid] = self self.load(priority=True, refresh=True) def update_metadata_images(self): if not self.update_metadata_images_enabled: return update_metadata_images(self) self.update(False) def keep_original_images(self): self.enable_update_metadata_images(False) for track in self.tracks: track.keep_original_images() for file in list(self.unmatched_files.files): file.keep_original_images() self.enable_update_metadata_images(True) self.update_metadata_images()
class Album(DataObject, Item): release_group_loaded = QtCore.pyqtSignal() def __init__(self, album_id, discid=None): DataObject.__init__(self, album_id) self.metadata = Metadata() self.orig_metadata = Metadata() self.tracks = [] self.loaded = False self.load_task = None self.release_group = None self._files = 0 self._requests = 0 self._tracks_loaded = False self._discids = set() if discid: self._discids.add(discid) self._after_load_callbacks = [] self.unmatched_files = Cluster(_("Unmatched Files"), special=True, related_album=self, hide_if_empty=True) self.errors = [] self.status = None self._album_artists = [] self.update_metadata_images_enabled = True def __repr__(self): return '<Album %s %r>' % (self.id, self.metadata["album"]) def iterfiles(self, save=False): for track in self.tracks: for file in track.iterfiles(): yield file if not save: for file in self.unmatched_files.iterfiles(): yield file def enable_update_metadata_images(self, enabled): self.update_metadata_images_enabled = enabled def append_album_artist(self, album_artist_id): """Append artist id to the list of album artists and return an AlbumArtist instance""" album_artist = AlbumArtist(album_artist_id) self._album_artists.append(album_artist) return album_artist def add_discid(self, discid): if not discid: return self._discids.add(discid) for track in self.tracks: medium_discids = track.metadata.getall('~musicbrainz_discids') track_discids = list(self._discids.intersection(medium_discids)) if track_discids: track.metadata['musicbrainz_discid'] = track_discids track.update() for file in track.linked_files: file.metadata['musicbrainz_discid'] = track_discids file.update() def get_album_artists(self): """Returns the list of album artists (as AlbumArtist objects)""" return self._album_artists def _parse_release(self, release_node): log.debug("Loading release %r ...", self.id) self._tracks_loaded = False release_id = release_node['id'] if release_id != self.id: self.tagger.mbid_redirects[self.id] = release_id album = self.tagger.albums.get(release_id) if album: log.debug("Release %r already loaded", release_id) album.match_files(self.unmatched_files.files) album.update() self.tagger.remove_album(self) return False else: del self.tagger.albums[self.id] self.tagger.albums[release_id] = self self.id = release_id # Make the release artist nodes available, since they may # contain supplementary data (aliases, tags, genres, ratings) # which aren't present in the release group, track, or # recording artist nodes. We can copy them into those places # wherever the IDs match, so that the data is shared and # available for use in mbjson.py and external plugins. self._release_artist_nodes = _create_artist_node_dict(release_node) # Get release metadata m = self._new_metadata m.length = 0 rg_node = release_node['release-group'] rg = self.release_group = self.tagger.get_release_group_by_id(rg_node['id']) rg.loaded_albums.add(self.id) rg.refcount += 1 _copy_artist_nodes(self._release_artist_nodes, rg_node) release_group_to_metadata(rg_node, rg.metadata, rg) m.copy(rg.metadata) release_to_metadata(release_node, m, album=self) # Custom VA name if m['musicbrainz_albumartistid'] == VARIOUS_ARTISTS_ID: m['albumartistsort'] = m['albumartist'] = config.setting['va_name'] # Convert Unicode punctuation if config.setting['convert_punctuation']: m.apply_func(asciipunct) m['totaldiscs'] = len(release_node['media']) # Add album to collections add_release_to_user_collections(release_node) # Run album metadata plugins try: run_album_metadata_processors(self, m, release_node) except BaseException: self.error_append(traceback.format_exc()) self._release_node = release_node return True def _release_request_finished(self, document, http, error): if self.load_task is None: return self.load_task = None parsed = False try: if error: self.error_append(http.errorString()) # Fix for broken NAT releases if error == QtNetwork.QNetworkReply.ContentNotFoundError: nats = False nat_name = config.setting["nat_name"] files = list(self.unmatched_files.files) for file in files: recordingid = file.metadata["musicbrainz_recordingid"] if mbid_validate(recordingid) and file.metadata["album"] == nat_name: nats = True self.tagger.move_file_to_nat(file, recordingid) self.tagger.nats.update() if nats and not self.get_num_unmatched_files(): self.tagger.remove_album(self) error = False else: try: parsed = self._parse_release(document) except Exception: error = True self.error_append(traceback.format_exc()) finally: self._requests -= 1 if parsed or error: self._finalize_loading(error) # does http need to be set to None to free the memory used by the network response? # http://qt-project.org/doc/qt-5/qnetworkaccessmanager.html says: # After the request has finished, it is the responsibility of the user # to delete the QNetworkReply object at an appropriate time. # Do not directly delete it inside the slot connected to finished(). # You can use the deleteLater() function. def error_append(self, msg): log.error(msg) self.errors.append(msg) def _finalize_loading(self, error): if error: self.metadata.clear() self.status = _("[could not load album %s]") % self.id del self._new_metadata del self._new_tracks self.update() return if self._requests > 0: return if not self._tracks_loaded: artists = set() all_media = [] absolutetracknumber = 0 va = self._new_metadata['musicbrainz_albumartistid'] == VARIOUS_ARTISTS_ID djmix_ars = {} if hasattr(self._new_metadata, "_djmix_ars"): djmix_ars = self._new_metadata._djmix_ars for medium_node in self._release_node['media']: mm = Metadata() mm.copy(self._new_metadata) medium_to_metadata(medium_node, mm) discpregap = False format = medium_node.get('format') if format: all_media.append(format) for dj in djmix_ars.get(mm["discnumber"], []): mm.add("djmixer", dj) if 'discs' in medium_node: discids = [disc.get('id') for disc in medium_node['discs']] mm['~musicbrainz_discids'] = discids mm['musicbrainz_discid'] = list(self._discids.intersection(discids)) if "pregap" in medium_node: discpregap = True absolutetracknumber += 1 track = self._finalize_loading_track(medium_node['pregap'], mm, artists, va, absolutetracknumber, discpregap) track.metadata['~pregap'] = "1" track_count = medium_node['track-count'] if track_count: tracklist_node = medium_node['tracks'] for track_node in tracklist_node: absolutetracknumber += 1 track = self._finalize_loading_track(track_node, mm, artists, va, absolutetracknumber, discpregap) if "data-tracks" in medium_node: for track_node in medium_node['data-tracks']: absolutetracknumber += 1 track = self._finalize_loading_track(track_node, mm, artists, va, absolutetracknumber, discpregap) track.metadata['~datatrack'] = "1" totalalbumtracks = absolutetracknumber self._new_metadata['~totalalbumtracks'] = totalalbumtracks # Generate a list of unique media, but keep order of first appearance self._new_metadata['media'] = " / ".join(list(OrderedDict.fromkeys(all_media))) for track in self._new_tracks: track.metadata["~totalalbumtracks"] = totalalbumtracks if len(artists) > 1: track.metadata["~multiartist"] = "1" del self._release_node del self._release_artist_nodes self._tracks_loaded = True if not self._requests: self.enable_update_metadata_images(False) # Prepare parser for user's script for s_name, s_text in enabled_tagger_scripts_texts(): parser = ScriptParser() for track in self._new_tracks: # Run tagger script for each track try: parser.eval(s_text, track.metadata) except ScriptError: log.exception("Failed to run tagger script %s on track", s_name) track.metadata.strip_whitespace() # Run tagger script for the album itself try: parser.eval(s_text, self._new_metadata) except ScriptError: log.exception("Failed to run tagger script %s on album", s_name) self._new_metadata.strip_whitespace() for track in self.tracks: track.metadata_images_changed.connect(self.update_metadata_images) for file in list(track.linked_files): file.move(self.unmatched_files) self.metadata = self._new_metadata self.tracks = self._new_tracks del self._new_metadata del self._new_tracks self.loaded = True self.status = None self.match_files(self.unmatched_files.files) self.enable_update_metadata_images(True) self.update() self.tagger.window.set_statusbar_message( N_('Album %(id)s loaded: %(artist)s - %(album)s'), { 'id': self.id, 'artist': self.metadata['albumartist'], 'album': self.metadata['album'] }, timeout=3000 ) for func in self._after_load_callbacks: func() self._after_load_callbacks = [] def _finalize_loading_track(self, track_node, metadata, artists, va, absolutetracknumber, discpregap): # As noted in `_parse_release` above, the release artist nodes # may contain supplementary data that isn't present in track # artist nodes. Similarly, the track artists may contain # information which the recording artists don't. Copy this # information across to wherever the artist IDs match. _copy_artist_nodes(self._release_artist_nodes, track_node) _copy_artist_nodes(self._release_artist_nodes, track_node['recording']) _copy_artist_nodes(_create_artist_node_dict(track_node), track_node['recording']) track = Track(track_node['recording']['id'], self) self._new_tracks.append(track) # Get track metadata tm = track.metadata tm.copy(metadata) track_to_metadata(track_node, track) tm["~absolutetracknumber"] = absolutetracknumber track.orig_metadata.copy(tm) track._customize_metadata() self._new_metadata.length += tm.length artists.add(tm["artist"]) if va: tm["compilation"] = "1" else: del tm["compilation"] if discpregap: tm["~discpregap"] = "1" # Run track metadata plugins try: run_track_metadata_processors(self, tm, track_node, self._release_node) except BaseException: self.error_append(traceback.format_exc()) return track def load(self, priority=False, refresh=False): if self._requests: log.info("Not reloading, some requests are still active.") return self.tagger.window.set_statusbar_message( N_('Loading album %(id)s ...'), {'id': self.id} ) self.loaded = False self.status = _("[loading album information]") if self.release_group: self.release_group.loaded = False self.release_group.genres.clear() self.metadata.clear() self.genres.clear() self.update() self._new_metadata = Metadata() self._new_tracks = [] self._requests = 1 self.errors = [] require_authentication = False inc = ['release-groups', 'media', 'discids', 'recordings', 'artist-credits', 'artists', 'aliases', 'labels', 'isrcs', 'collections'] if self.tagger.webservice.oauth_manager.is_authorized(): require_authentication = True inc += ['user-collections'] if config.setting['release_ars'] or config.setting['track_ars']: inc += ['artist-rels', 'release-rels', 'url-rels', 'recording-rels', 'work-rels'] if config.setting['track_ars']: inc += ['recording-level-rels', 'work-level-rels'] require_authentication = self.set_genre_inc_params(inc) or require_authentication if config.setting['enable_ratings']: require_authentication = True inc += ['user-ratings'] self.load_task = self.tagger.mb_api.get_release_by_id( self.id, self._release_request_finished, inc=inc, mblogin=require_authentication, priority=priority, refresh=refresh) def run_when_loaded(self, func): if self.loaded: func() else: self._after_load_callbacks.append(func) def stop_loading(self): if self.load_task: self.tagger.webservice.remove_task(self.load_task) self.load_task = None def update(self, update_tracks=True): if self.item: self.item.update(update_tracks) def _add_file(self, track, file): self._files += 1 self.update(update_tracks=False) add_metadata_images(self, [file]) file.metadata_images_changed.connect(self.update_metadata_images) def _remove_file(self, track, file): self._files -= 1 self.update(update_tracks=False) file.metadata_images_changed.disconnect(self.update_metadata_images) remove_metadata_images(self, [file]) def _match_files(self, files, recordingid=None, threshold=0): """Match files to tracks on this album, based on metadata similarity or recordingid.""" tracks_cache = defaultdict(lambda: None) def build_tracks_cache(): for track in self.tracks: tm_recordingid = track.orig_metadata['musicbrainz_recordingid'] tm_tracknumber = track.orig_metadata['tracknumber'] tm_discnumber = track.orig_metadata['discnumber'] for tup in ( (tm_recordingid, tm_tracknumber, tm_discnumber), (tm_recordingid, tm_tracknumber), (tm_recordingid, )): tracks_cache[tup] = track SimMatchAlbum = namedtuple('SimMatchAlbum', 'similarity track') for file in list(files): if file.state == File.REMOVED: continue # if we have a recordingid to match against, use that in priority recid = recordingid or file.metadata['musicbrainz_recordingid'] if recid and mbid_validate(recid): if not tracks_cache: build_tracks_cache() tracknumber = file.metadata['tracknumber'] discnumber = file.metadata['discnumber'] track = (tracks_cache[(recid, tracknumber, discnumber)] or tracks_cache[(recid, tracknumber)] or tracks_cache[(recid, )]) if track: yield (file, track) continue # try to match by similarity def candidates(): for track in self.tracks: yield SimMatchAlbum( similarity=track.metadata.compare(file.orig_metadata), track=track ) no_match = SimMatchAlbum(similarity=-1, track=self.unmatched_files) best_match = find_best_match(candidates, no_match) if best_match.similarity < threshold: yield (file, no_match.track) else: yield (file, best_match.result.track) def match_files(self, files, recordingid=None): """Match and move files to tracks on this album, based on metadata similarity or recordingid.""" moves = self._match_files(files, recordingid=recordingid, threshold=config.setting['track_matching_threshold']) for file, target in moves: file.move(target) def can_save(self): return self._files > 0 def can_remove(self): return True def can_edit_tags(self): return True def can_analyze(self): return False def can_autotag(self): return False def can_refresh(self): return True def can_view_info(self): return (self.loaded and (self.metadata.images or self.orig_metadata.images)) or self.errors def is_album_like(self): return True def get_num_matched_tracks(self): num = 0 for track in self.tracks: if track.is_linked(): num += 1 return num def get_num_unmatched_files(self): return len(self.unmatched_files.files) def get_num_total_files(self): return self._files + len(self.unmatched_files.files) def is_complete(self): if not self.tracks: return False for track in self.tracks: if not track.is_complete(): return False if self.get_num_unmatched_files(): return False else: return True def is_modified(self): if self.tracks: for track in self.tracks: for file in track.linked_files: if not file.is_saved(): return True return False def get_num_unsaved_files(self): count = 0 for track in self.tracks: for file in track.linked_files: if not file.is_saved(): count += 1 return count def column(self, column): if column == 'title': if self.status is not None: title = self.status else: title = self.metadata['album'] if self.tracks: linked_tracks = 0 for track in self.tracks: if track.is_linked(): linked_tracks += 1 text = '%s\u200E (%d/%d' % (title, linked_tracks, len(self.tracks)) unmatched = self.get_num_unmatched_files() if unmatched: text += '; %d?' % (unmatched,) unsaved = self.get_num_unsaved_files() if unsaved: text += '; %d*' % (unsaved,) # CoverArt.set_metadata uses the orig_metadata.images if metadata.images is empty # in order to show existing cover art if there's no cover art for a release. So # we do the same here in order to show the number of images consistently. if self.metadata.images: metadata = self.metadata else: metadata = self.orig_metadata number_of_images = len(metadata.images) if getattr(metadata, 'has_common_images', True): text += ngettext("; %i image", "; %i images", number_of_images) % number_of_images else: text += ngettext("; %i image not in all tracks", "; %i different images among tracks", number_of_images) % number_of_images return text + ')' else: return title elif column == '~length': length = self.metadata.length if length: return format_time(length) else: return '' elif column == 'artist': return self.metadata['albumartist'] elif column == 'tracknumber': return self.metadata['~totalalbumtracks'] elif column == 'discnumber': return self.metadata['totaldiscs'] else: return self.metadata[column] def switch_release_version(self, mbid): if mbid == self.id: return for file in list(self.iterfiles(True)): file.move(self.unmatched_files) album = self.tagger.albums.get(mbid) if album: album.match_files(self.unmatched_files.files) album.update() self.tagger.remove_album(self) else: del self.tagger.albums[self.id] self.release_group.loaded_albums.discard(self.id) self.id = mbid self.tagger.albums[mbid] = self self.load(priority=True, refresh=True) def update_metadata_images(self): if not self.update_metadata_images_enabled: return update_metadata_images(self) self.update(False) def keep_original_images(self): self.enable_update_metadata_images(False) for track in self.tracks: track.keep_original_images() for file in list(self.unmatched_files.files): file.keep_original_images() self.enable_update_metadata_images(True) self.update_metadata_images()
def _do_clustering(self, files): # The clustering algorithm should completely run in the thread, # hence do not return the iterator. return list(Cluster.cluster(files))
def test_cmd_matchedtracks_with_cluster(self): file = MagicMock() cluster = Cluster(name="Test") cluster.files.append(file) file.parent = cluster self.assertScriptResultEquals("$matchedtracks()", "0", file=file)
class Album(DataObject, Item): release_group_loaded = QtCore.pyqtSignal() def __init__(self, id, discid=None): DataObject.__init__(self, id) self.metadata = Metadata() self.tracks = [] self.format_str = "" self.loaded = False self.load_task = None self.rgloaded = False self.rgid = None self._files = 0 self._requests = 0 self._tracks_loaded = False self._discid = discid self._after_load_callbacks = queue.Queue() self.other_versions = [] self.unmatched_files = Cluster(_("Unmatched Files"), special=True, related_album=self, hide_if_empty=True) def __repr__(self): return '<Album %s %r>' % (self.id, self.metadata[u"album"]) def iterfiles(self, save=False): for track in self.tracks: for file in track.iterfiles(): yield file if not save: for file in self.unmatched_files.iterfiles(): yield file def _parse_release(self, document): self.log.debug("Loading release %r", self.id) self._tracks_loaded = False release_node = document.metadata[0].release[0] if release_node.id != self.id: self.tagger.mbid_redirects[self.id] = release_node.id album = self.tagger.albums.get(release_node.id) if album: self.log.debug("Release %r already loaded", release_node.id) album.match_files(self.unmatched_files.files) album.update() self.tagger.remove_album(self) return False else: del self.tagger.albums[self.id] self.tagger.albums[release_node.id] = self self.id = release_node.id # Get release metadata m = self._new_metadata m.length = 0 release_to_metadata(release_node, m, config=self.config, album=self) self.format_str = media_formats_from_node(release_node.medium_list[0]) self.rgid = release_node.release_group[0].id if self._discid: m['musicbrainz_discid'] = self._discid # Custom VA name if m['musicbrainz_albumartistid'] == VARIOUS_ARTISTS_ID: m['albumartistsort'] = m['albumartist'] = self.config.setting['va_name'] # Convert Unicode punctuation if self.config.setting['convert_punctuation']: m.apply_func(asciipunct) m['totaldiscs'] = release_node.medium_list[0].count # Run album metadata plugins try: run_album_metadata_processors(self, m, release_node) except: self.log.error(traceback.format_exc()) self._release_node = release_node return True def _release_request_finished(self, document, http, error): if self.load_task is None: return self.load_task = None parsed = False try: if error: self.log.error("%r", unicode(http.errorString())) # Fix for broken NAT releases if error == QtNetwork.QNetworkReply.ContentNotFoundError: nats = False nat_name = self.config.setting["nat_name"] files = list(self.unmatched_files.files) for file in files: trackid = file.metadata["musicbrainz_trackid"] if mbid_validate(trackid) and file.metadata["album"] == nat_name: nats = True self.tagger.move_file_to_nat(file, trackid) self.tagger.nats.update() if nats and not self.get_num_unmatched_files(): self.tagger.remove_album(self) error = False else: try: parsed = self._parse_release(document) except: error = True self.log.error(traceback.format_exc()) finally: self._requests -= 1 if parsed or error: self._finalize_loading(error) def _parse_release_group(self, document): for node in document.metadata[0].release_list[0].release: v = {} v["mbid"] = node.id v["date"] = node.date[0].text if "date" in node.children else "" v["country"] = node.country[0].text if "country" in node.children else "" labels, catnums = label_info_from_node(node.label_info_list[0]) v["labels"] = ", ".join(set(labels)) v["catnums"] = ", ".join(set(catnums)) v["tracks"] = " + ".join([m.track_list[0].count for m in node.medium_list[0].medium]) v["format"] = media_formats_from_node(node.medium_list[0]) self.other_versions.append(v) self.other_versions.sort(key=lambda x: x["date"]) def _release_group_request_finished(self, document, http, error): try: if error: self.log.error("%r", unicode(http.errorString())) else: try: self._parse_release_group(document) except: error = True self.log.error(traceback.format_exc()) finally: self.rgloaded = True self.release_group_loaded.emit() def _finalize_loading(self, error): if error: self.metadata.clear() self.metadata['album'] = _("[could not load album %s]") % self.id del self._new_metadata del self._new_tracks self.update() return if self._requests > 0: return if not self._tracks_loaded: artists = set() totalalbumtracks = 0 djmix_ars = {} if hasattr(self._new_metadata, "_djmix_ars"): djmix_ars = self._new_metadata._djmix_ars for medium_node in self._release_node.medium_list[0].medium: mm = Metadata() mm.copy(self._new_metadata) medium_to_metadata(medium_node, mm) totalalbumtracks += int(mm["totaltracks"]) for dj in djmix_ars.get(mm["discnumber"], []): mm.add("djmixer", dj) for track_node in medium_node.track_list[0].track: track = Track(track_node.recording[0].id, self) self._new_tracks.append(track) # Get track metadata tm = track.metadata tm.copy(mm) track_to_metadata(track_node, track, self.config) track._customize_metadata() self._new_metadata.length += tm.length artists.add(tm["musicbrainz_artistid"]) # Run track metadata plugins try: run_track_metadata_processors(self, tm, self._release_node, track_node) except: self.log.error(traceback.format_exc()) totalalbumtracks = str(totalalbumtracks) for track in self._new_tracks: track.metadata["~totalalbumtracks"] = totalalbumtracks if len(artists) > 1: track.metadata["compilation"] = "1" del self._release_node self._tracks_loaded = True if not self._requests: # Prepare parser for user's script if self.config.setting["enable_tagger_script"]: script = self.config.setting["tagger_script"] if script: parser = ScriptParser() for track in self._new_tracks: # Run tagger script for each track try: parser.eval(script, track.metadata) except: self.log.error(traceback.format_exc()) # Strip leading/trailing whitespace track.metadata.strip_whitespace() # Run tagger script for the album itself try: parser.eval(script, self._new_metadata) except: self.log.error(traceback.format_exc()) self._new_metadata.strip_whitespace() for track in self.tracks: for file in list(track.linked_files): file.move(self.unmatched_files) self.metadata = self._new_metadata self.tracks = self._new_tracks del self._new_metadata del self._new_tracks self.loaded = True self.match_files(self.unmatched_files.files) self.update() self.tagger.window.set_statusbar_message(_('Album %s loaded'), self.id, timeout=3000) while self._after_load_callbacks.qsize() > 0: func = self._after_load_callbacks.get() func() def load(self): if self._requests: self.log.info("Not reloading, some requests are still active.") return self.tagger.window.set_statusbar_message('Loading album %s...', self.id) self.loaded = False self.rgloaded = False self.rgid = None self.other_versions = [] self.metadata.clear() self.folksonomy_tags.clear() self.metadata['album'] = _("[loading album information]") self.update() self._new_metadata = Metadata() self._new_tracks = [] self._requests = 1 require_authentication = False inc = ['release-groups', 'media', 'recordings', 'puids', 'artist-credits', 'artists', 'aliases', 'labels', 'isrcs'] if self.config.setting['release_ars'] or self.config.setting['track_ars']: inc += ['artist-rels', 'release-rels', 'url-rels', 'recording-rels', 'work-rels'] if self.config.setting['track_ars']: inc += ['recording-level-rels', 'work-level-rels'] if self.config.setting['folksonomy_tags']: if self.config.setting['only_my_tags']: require_authentication = True inc += ['user-tags'] else: inc += ['tags'] if self.config.setting['enable_ratings']: require_authentication = True inc += ['user-ratings'] self.load_task = self.tagger.xmlws.get_release_by_id( self.id, self._release_request_finished, inc=inc, mblogin=require_authentication) def run_when_loaded(self, func): if self.loaded: func() else: self._after_load_callbacks.put(func) def stop_loading(self): if self.load_task: self.tagger.xmlws.remove_task(self.load_task) self.load_task = None def update(self, update_tracks=True): if self.item: self.item.update(update_tracks) def _add_file(self, track, file): self._files += 1 self.update(update_tracks=False) def _remove_file(self, track, file): self._files -= 1 self.update(update_tracks=False) def match_files(self, files, use_trackid=True): """Match files to tracks on this album, based on metadata similarity or trackid.""" for file in list(files): if file.state == File.REMOVED: continue matches = [] trackid = file.metadata['musicbrainz_trackid'] if use_trackid and mbid_validate(trackid): matches = self._get_trackid_matches(file, trackid) if not matches: for track in self.tracks: sim = track.metadata.compare(file.orig_metadata) if sim >= self.config.setting['track_matching_threshold']: matches.append((sim, track)) if matches: matches.sort(reverse=True) file.move(matches[0][1]) else: file.move(self.unmatched_files) def match_file(self, file, trackid=None): """Match the file on a track on this album, based on trackid or metadata similarity.""" if file.state == File.REMOVED: return if trackid is not None: matches = self._get_trackid_matches(file, trackid) if matches: matches.sort(reverse=True) file.move(matches[0][1]) return self.match_files([file], use_trackid=False) def _get_trackid_matches(self, file, trackid): matches = [] tracknumber = file.metadata['tracknumber'] discnumber = file.metadata['discnumber'] for track in self.tracks: tm = track.metadata if trackid == tm['musicbrainz_trackid']: if tracknumber == tm['tracknumber']: if discnumber == tm['discnumber']: matches.append((4.0, track)) break else: matches.append((3.0, track)) else: matches.append((2.0, track)) return matches def can_save(self): return self._files > 0 def can_remove(self): return True def can_edit_tags(self): return True def can_analyze(self): return False def can_autotag(self): return False def can_refresh(self): return True def is_album_like(self): return True def get_num_matched_tracks(self): num = 0 for track in self.tracks: if track.is_linked(): num += 1 return num def get_num_unmatched_files(self): return len(self.unmatched_files.files) def is_complete(self): if not self.tracks: return False for track in self.tracks: if track.num_linked_files != 1: return False else: return True def get_num_unsaved_files(self): count = 0 for track in self.tracks: for file in track.linked_files: if not file.is_saved(): count+=1 return count def column(self, column): if column == 'title': if self.tracks: linked_tracks = 0 for track in self.tracks: if track.is_linked(): linked_tracks+=1 text = u'%s\u200E (%d/%d' % (self.metadata['album'], linked_tracks, len(self.tracks)) unmatched = self.get_num_unmatched_files() if unmatched: text += '; %d?' % (unmatched,) unsaved = self.get_num_unsaved_files() if unsaved: text += '; %d*' % (unsaved,) return text + ')' else: return self.metadata['album'] elif column == '~length': length = self.metadata.length if length: return format_time(length) else: return '' elif column == 'artist': return self.metadata['albumartist'] else: return '' def switch_release_version(self, mbid): if mbid == self.id: return for file in list(self.iterfiles(True)): file.move(self.unmatched_files) album = self.tagger.albums.get(mbid) if album: album.match_files(self.unmatched_files.files) album.update() self.tagger.remove_album(self) else: del self.tagger.albums[self.id] self.id = mbid self.tagger.albums[mbid] = self self.load()
class Album(DataObject, Item): release_group_loaded = QtCore.pyqtSignal() def __init__(self, id, discid=None): DataObject.__init__(self, id) self.metadata = Metadata() self.tracks = [] self.loaded = False self.load_task = None self.release_group = None self._files = 0 self._requests = 0 self._tracks_loaded = False self._discid = discid self._after_load_callbacks = [] self.unmatched_files = Cluster(_("Unmatched Files"), special=True, related_album=self, hide_if_empty=True) self.errors = [] def __repr__(self): return "<Album %s %r>" % (self.id, self.metadata[u"album"]) def iterfiles(self, save=False): for track in self.tracks: for file in track.iterfiles(): yield file if not save: for file in self.unmatched_files.iterfiles(): yield file def _parse_release(self, document): log.debug("Loading release %r", self.id) self._tracks_loaded = False release_node = document.metadata[0].release[0] if release_node.id != self.id: self.tagger.mbid_redirects[self.id] = release_node.id album = self.tagger.albums.get(release_node.id) if album: log.debug("Release %r already loaded", release_node.id) album.match_files(self.unmatched_files.files) album.update() self.tagger.remove_album(self) return False else: del self.tagger.albums[self.id] self.tagger.albums[release_node.id] = self self.id = release_node.id # Get release metadata m = self._new_metadata m.length = 0 rg_node = release_node.release_group[0] rg = self.release_group = self.tagger.get_release_group_by_id(rg_node.id) rg.loaded_albums.add(self.id) rg.refcount += 1 release_group_to_metadata(rg_node, rg.metadata, rg) m.copy(rg.metadata) release_to_metadata(release_node, m, album=self) if self._discid: m["musicbrainz_discid"] = self._discid # Custom VA name if m["musicbrainz_albumartistid"] == VARIOUS_ARTISTS_ID: m["albumartistsort"] = m["albumartist"] = config.setting["va_name"] # Convert Unicode punctuation if config.setting["convert_punctuation"]: m.apply_func(asciipunct) m["totaldiscs"] = release_node.medium_list[0].count # Add album to collections if "collection_list" in release_node.children: for node in release_node.collection_list[0].collection: if node.editor[0].text.lower() == config.setting["username"].lower(): if node.id not in user_collections: user_collections[node.id] = Collection(node.id, node.name[0].text, node.release_list[0].count) user_collections[node.id].releases.add(self.id) # Run album metadata plugins try: run_album_metadata_processors(self, m, release_node) except: self.error_append(traceback.format_exc()) self._release_node = release_node return True def _release_request_finished(self, document, http, error): if self.load_task is None: return self.load_task = None parsed = False try: if error: self.error_append(unicode(http.errorString())) # Fix for broken NAT releases if error == QtNetwork.QNetworkReply.ContentNotFoundError: nats = False nat_name = config.setting["nat_name"] files = list(self.unmatched_files.files) for file in files: trackid = file.metadata["musicbrainz_trackid"] if mbid_validate(trackid) and file.metadata["album"] == nat_name: nats = True self.tagger.move_file_to_nat(file, trackid) self.tagger.nats.update() if nats and not self.get_num_unmatched_files(): self.tagger.remove_album(self) error = False else: try: parsed = self._parse_release(document) except: error = True self.error_append(traceback.format_exc()) finally: self._requests -= 1 if parsed or error: self._finalize_loading(error) def error_append(self, msg): log.error(msg) self.errors.append(msg) def _finalize_loading(self, error): if error: self.metadata.clear() self.metadata["album"] = _("[could not load album %s]") % self.id del self._new_metadata del self._new_tracks self.update() return if self._requests > 0: return if not self._tracks_loaded: artists = set() totalalbumtracks = 0 djmix_ars = {} if hasattr(self._new_metadata, "_djmix_ars"): djmix_ars = self._new_metadata._djmix_ars for medium_node in self._release_node.medium_list[0].medium: mm = Metadata() mm.copy(self._new_metadata) medium_to_metadata(medium_node, mm) totalalbumtracks += int(mm["totaltracks"]) for dj in djmix_ars.get(mm["discnumber"], []): mm.add("djmixer", dj) for track_node in medium_node.track_list[0].track: track = Track(track_node.recording[0].id, self) self._new_tracks.append(track) # Get track metadata tm = track.metadata tm.copy(mm) track_to_metadata(track_node, track) track._customize_metadata() self._new_metadata.length += tm.length artists.add(tm["musicbrainz_artistid"]) # Run track metadata plugins try: run_track_metadata_processors(self, tm, self._release_node, track_node) except: self.error_append(traceback.format_exc()) totalalbumtracks = str(totalalbumtracks) for track in self._new_tracks: track.metadata["~totalalbumtracks"] = totalalbumtracks if len(artists) > 1: track.metadata["compilation"] = "1" del self._release_node self._tracks_loaded = True if not self._requests: # Prepare parser for user's script if config.setting["enable_tagger_script"]: script = config.setting["tagger_script"] if script: parser = ScriptParser() for track in self._new_tracks: # Run tagger script for each track try: parser.eval(script, track.metadata) except: self.error_append(traceback.format_exc()) # Strip leading/trailing whitespace track.metadata.strip_whitespace() # Run tagger script for the album itself try: parser.eval(script, self._new_metadata) except: self.error_append(traceback.format_exc()) self._new_metadata.strip_whitespace() for track in self.tracks: for file in list(track.linked_files): file.move(self.unmatched_files) self.metadata = self._new_metadata self.tracks = self._new_tracks del self._new_metadata del self._new_tracks self.loaded = True self.match_files(self.unmatched_files.files) self.update() self.tagger.window.set_statusbar_message(_("Album %s loaded"), self.id, timeout=3000) for func in self._after_load_callbacks: func() self._after_load_callbacks = [] def load(self): if self._requests: log.info("Not reloading, some requests are still active.") return self.tagger.window.set_statusbar_message("Loading album %s...", self.id) self.loaded = False if self.release_group: self.release_group.loaded = False self.release_group.folksonomy_tags.clear() self.metadata.clear() self.folksonomy_tags.clear() self.metadata["album"] = _("[loading album information]") self.update() self._new_metadata = Metadata() self._new_tracks = [] self._requests = 1 self.errors = [] require_authentication = False inc = [ "release-groups", "media", "recordings", "artist-credits", "artists", "aliases", "labels", "isrcs", "collections", ] if config.setting["release_ars"] or config.setting["track_ars"]: inc += ["artist-rels", "release-rels", "url-rels", "recording-rels", "work-rels"] if config.setting["track_ars"]: inc += ["recording-level-rels", "work-level-rels"] if config.setting["folksonomy_tags"]: if config.setting["only_my_tags"]: require_authentication = True inc += ["user-tags"] else: inc += ["tags"] if config.setting["enable_ratings"]: require_authentication = True inc += ["user-ratings"] self.load_task = self.tagger.xmlws.get_release_by_id( self.id, self._release_request_finished, inc=inc, mblogin=require_authentication ) def run_when_loaded(self, func): if self.loaded: func() else: self._after_load_callbacks.append(func) def stop_loading(self): if self.load_task: self.tagger.xmlws.remove_task(self.load_task) self.load_task = None def update(self, update_tracks=True): if self.item: self.item.update(update_tracks) def _add_file(self, track, file): self._files += 1 self.update(update_tracks=False) def _remove_file(self, track, file): self._files -= 1 self.update(update_tracks=False) def match_files(self, files, use_trackid=True): """Match files to tracks on this album, based on metadata similarity or trackid.""" for file in list(files): if file.state == File.REMOVED: continue matches = [] trackid = file.metadata["musicbrainz_trackid"] if use_trackid and mbid_validate(trackid): matches = self._get_trackid_matches(file, trackid) if not matches: for track in self.tracks: sim = track.metadata.compare(file.orig_metadata) if sim >= config.setting["track_matching_threshold"]: matches.append((sim, track)) if matches: matches.sort(reverse=True) file.move(matches[0][1]) else: file.move(self.unmatched_files) def match_file(self, file, trackid=None): """Match the file on a track on this album, based on trackid or metadata similarity.""" if file.state == File.REMOVED: return if trackid is not None: matches = self._get_trackid_matches(file, trackid) if matches: matches.sort(reverse=True) file.move(matches[0][1]) return self.match_files([file], use_trackid=False) def _get_trackid_matches(self, file, trackid): matches = [] tracknumber = file.metadata["tracknumber"] discnumber = file.metadata["discnumber"] for track in self.tracks: tm = track.metadata if trackid == tm["musicbrainz_trackid"]: if tracknumber == tm["tracknumber"]: if discnumber == tm["discnumber"]: matches.append((4.0, track)) break else: matches.append((3.0, track)) else: matches.append((2.0, track)) return matches def can_save(self): return self._files > 0 def can_remove(self): return True def can_edit_tags(self): return True def can_analyze(self): return False def can_autotag(self): return False def can_refresh(self): return True def can_view_info(self): return (self.loaded and self.metadata and self.metadata.images) or self.errors def is_album_like(self): return True def get_num_matched_tracks(self): num = 0 for track in self.tracks: if track.is_linked(): num += 1 return num def get_num_unmatched_files(self): return len(self.unmatched_files.files) def is_complete(self): if not self.tracks: return False for track in self.tracks: if track.num_linked_files != 1: return False else: return True def is_modified(self): if self.tracks: for track in self.tracks: for file in track.linked_files: if not file.is_saved(): return True return False def get_num_unsaved_files(self): count = 0 for track in self.tracks: for file in track.linked_files: if not file.is_saved(): count += 1 return count def column(self, column): if column == "title": if self.tracks: linked_tracks = 0 for track in self.tracks: if track.is_linked(): linked_tracks += 1 text = u"%s\u200E (%d/%d" % (self.metadata["album"], linked_tracks, len(self.tracks)) unmatched = self.get_num_unmatched_files() if unmatched: text += "; %d?" % (unmatched,) unsaved = self.get_num_unsaved_files() if unsaved: text += "; %d*" % (unsaved,) text += ungettext("; %i image", "; %i images", len(self.metadata.images)) % len(self.metadata.images) return text + ")" else: return self.metadata["album"] elif column == "~length": length = self.metadata.length if length: return format_time(length) else: return "" elif column == "artist": return self.metadata["albumartist"] else: return "" def switch_release_version(self, mbid): if mbid == self.id: return for file in list(self.iterfiles(True)): file.move(self.unmatched_files) album = self.tagger.albums.get(mbid) if album: album.match_files(self.unmatched_files.files) album.update() self.tagger.remove_album(self) else: del self.tagger.albums[self.id] self.release_group.loaded_albums.discard(self.id) self.id = mbid self.tagger.albums[mbid] = self self.load()
def test_cluster_none(self): clusters = list(Cluster.cluster([])) # No cluster is being created self.assertEqual(0, len(clusters))
class Album(DataObject, Item): metadata_images_changed = QtCore.pyqtSignal() def __init__(self, album_id, discid=None): DataObject.__init__(self, album_id) self.metadata = Metadata() self.orig_metadata = Metadata() self.tracks = [] self.loaded = False self.load_task = None self.release_group = None self._files_count = 0 self._requests = 0 self._tracks_loaded = False self._discids = set() if discid: self._discids.add(discid) self._after_load_callbacks = [] self.unmatched_files = Cluster(_("Unmatched Files"), special=True, related_album=self, hide_if_empty=True) self.unmatched_files.metadata_images_changed.connect( self.update_metadata_images) self.status = AlbumStatus.NONE self._album_artists = [] self.update_metadata_images_enabled = True def __repr__(self): return '<Album %s %r>' % (self.id, self.metadata["album"]) def iterfiles(self, save=False): for track in self.tracks: yield from track.iterfiles() if not save: yield from self.unmatched_files.iterfiles() def enable_update_metadata_images(self, enabled): self.update_metadata_images_enabled = enabled def append_album_artist(self, album_artist_id): """Append artist id to the list of album artists and return an AlbumArtist instance""" album_artist = AlbumArtist(album_artist_id) self._album_artists.append(album_artist) return album_artist def add_discid(self, discid): if not discid: return self._discids.add(discid) for track in self.tracks: medium_discids = track.metadata.getall('~musicbrainz_discids') track_discids = list(self._discids.intersection(medium_discids)) if track_discids: track.metadata['musicbrainz_discid'] = track_discids track.update() for file in track.files: file.metadata['musicbrainz_discid'] = track_discids file.update() def get_next_track(self, track): try: index = self.tracks.index(track) return self.tracks[index + 1] except (IndexError, ValueError): return None def get_album_artists(self): """Returns the list of album artists (as AlbumArtist objects)""" return self._album_artists def _parse_release(self, release_node): log.debug("Loading release %r ...", self.id) self._tracks_loaded = False release_id = release_node['id'] if release_id != self.id: self.tagger.mbid_redirects[self.id] = release_id album = self.tagger.albums.get(release_id) if album: log.debug("Release %r already loaded", release_id) album.match_files(self.unmatched_files.files) album.update() self.tagger.remove_album(self) return False else: del self.tagger.albums[self.id] self.tagger.albums[release_id] = self self.id = release_id # Make the release artist nodes available, since they may # contain supplementary data (aliases, tags, genres, ratings) # which aren't present in the release group, track, or # recording artist nodes. We can copy them into those places # wherever the IDs match, so that the data is shared and # available for use in mbjson.py and external plugins. self._release_artist_nodes = _create_artist_node_dict(release_node) # Get release metadata m = self._new_metadata m.length = 0 rg_node = release_node['release-group'] rg = self.release_group = self.tagger.get_release_group_by_id( rg_node['id']) rg.loaded_albums.add(self.id) rg.refcount += 1 _copy_artist_nodes(self._release_artist_nodes, rg_node) release_group_to_metadata(rg_node, rg.metadata, rg) m.copy(rg.metadata) release_to_metadata(release_node, m, album=self) config = get_config() # Custom VA name if m['musicbrainz_albumartistid'] == VARIOUS_ARTISTS_ID: m['albumartistsort'] = m['albumartist'] = config.setting['va_name'] # Convert Unicode punctuation if config.setting['convert_punctuation']: m.apply_func(asciipunct) m['totaldiscs'] = len(release_node['media']) # Add album to collections add_release_to_user_collections(release_node) # Run album metadata plugins try: run_album_metadata_processors(self, m, release_node) except BaseException: self.error_append(traceback.format_exc()) self._release_node = release_node return True def _release_request_finished(self, document, http, error): if self.load_task is None: return self.load_task = None parsed = False try: if error: self.error_append(http.errorString()) # Fix for broken NAT releases if error == QtNetwork.QNetworkReply.ContentNotFoundError: config = get_config() nats = False nat_name = config.setting["nat_name"] files = list(self.unmatched_files.files) for file in files: recordingid = file.metadata["musicbrainz_recordingid"] if mbid_validate(recordingid) and file.metadata[ "album"] == nat_name: nats = True self.tagger.move_file_to_nat(file, recordingid) self.tagger.nats.update() if nats and not self.get_num_unmatched_files(): self.tagger.remove_album(self) error = False else: try: parsed = self._parse_release(document) except Exception: error = True self.error_append(traceback.format_exc()) finally: self._requests -= 1 if parsed or error: self._finalize_loading(error) def _finalize_loading(self, error): if error: self.metadata.clear() self.status = AlbumStatus.ERROR del self._new_metadata del self._new_tracks self.update() if not self._requests: self.loaded = True for func, always in self._after_load_callbacks: if always: func() return if self._requests > 0: return if not self._tracks_loaded: artists = set() all_media = [] absolutetracknumber = 0 va = self._new_metadata[ 'musicbrainz_albumartistid'] == VARIOUS_ARTISTS_ID djmix_ars = {} if hasattr(self._new_metadata, "_djmix_ars"): djmix_ars = self._new_metadata._djmix_ars for medium_node in self._release_node['media']: mm = Metadata() mm.copy(self._new_metadata) medium_to_metadata(medium_node, mm) format = medium_node.get('format') if format: all_media.append(format) for dj in djmix_ars.get(mm["discnumber"], []): mm.add("djmixer", dj) if va: mm["compilation"] = "1" else: del mm["compilation"] if 'discs' in medium_node: discids = [disc.get('id') for disc in medium_node['discs']] mm['~musicbrainz_discids'] = discids mm['musicbrainz_discid'] = list( self._discids.intersection(discids)) if "pregap" in medium_node: absolutetracknumber += 1 mm['~discpregap'] = '1' extra_metadata = { '~pregap': '1', '~absolutetracknumber': absolutetracknumber, } self._finalize_loading_track(medium_node['pregap'], mm, artists, extra_metadata) track_count = medium_node['track-count'] if track_count: tracklist_node = medium_node['tracks'] for track_node in tracklist_node: absolutetracknumber += 1 extra_metadata = { '~absolutetracknumber': absolutetracknumber, } self._finalize_loading_track(track_node, mm, artists, extra_metadata) if "data-tracks" in medium_node: for track_node in medium_node['data-tracks']: absolutetracknumber += 1 extra_metadata = { '~datatrack': '1', '~absolutetracknumber': absolutetracknumber, } self._finalize_loading_track(track_node, mm, artists, extra_metadata) totalalbumtracks = absolutetracknumber self._new_metadata['~totalalbumtracks'] = totalalbumtracks # Generate a list of unique media, but keep order of first appearance self._new_metadata['media'] = " / ".join( list(OrderedDict.fromkeys(all_media))) for track in self._new_tracks: track.metadata["~totalalbumtracks"] = totalalbumtracks if len(artists) > 1: track.metadata["~multiartist"] = "1" del self._release_node del self._release_artist_nodes self._tracks_loaded = True if not self._requests: self.enable_update_metadata_images(False) for track in self._new_tracks: track.orig_metadata.copy(track.metadata) track.metadata_images_changed.connect( self.update_metadata_images) # Prepare parser for user's script for s_name, s_text in enabled_tagger_scripts_texts(): parser = ScriptParser() for track in self._new_tracks: # Run tagger script for each track try: parser.eval(s_text, track.metadata) except ScriptError: log.exception( "Failed to run tagger script %s on track", s_name) track.metadata.strip_whitespace() track.scripted_metadata.update(track.metadata) # Run tagger script for the album itself try: parser.eval(s_text, self._new_metadata) except ScriptError: log.exception("Failed to run tagger script %s on album", s_name) self._new_metadata.strip_whitespace() unmatched_files = [ file for track in self.tracks for file in track.files ] self.metadata = self._new_metadata self.orig_metadata.copy(self.metadata) self.orig_metadata.images.clear() self.tracks = self._new_tracks del self._new_metadata del self._new_tracks self.loaded = True self.status = AlbumStatus.LOADED self.match_files(unmatched_files + self.unmatched_files.files) self.enable_update_metadata_images(True) self.update_metadata_images() self.update() self.tagger.window.set_statusbar_message( N_('Album %(id)s loaded: %(artist)s - %(album)s'), { 'id': self.id, 'artist': self.metadata['albumartist'], 'album': self.metadata['album'] }, timeout=3000) for func, always in self._after_load_callbacks: func() self._after_load_callbacks = [] if self.item.isSelected(): self.tagger.window.refresh_metadatabox() def _finalize_loading_track(self, track_node, metadata, artists, extra_metadata=None): # As noted in `_parse_release` above, the release artist nodes # may contain supplementary data that isn't present in track # artist nodes. Similarly, the track artists may contain # information which the recording artists don't. Copy this # information across to wherever the artist IDs match. _copy_artist_nodes(self._release_artist_nodes, track_node) _copy_artist_nodes(self._release_artist_nodes, track_node['recording']) _copy_artist_nodes(_create_artist_node_dict(track_node), track_node['recording']) track = Track(track_node['recording']['id'], self) self._new_tracks.append(track) # Get track metadata tm = track.metadata tm.copy(metadata) track_to_metadata(track_node, track) track._customize_metadata() self._new_metadata.length += tm.length artists.add(tm["artist"]) if extra_metadata: tm.update(extra_metadata) # Run track metadata plugins try: run_track_metadata_processors(self, tm, track_node, self._release_node) except BaseException: self.error_append(traceback.format_exc()) return track def load(self, priority=False, refresh=False): if self._requests: log.info("Not reloading, some requests are still active.") return self.tagger.window.set_statusbar_message( N_('Loading album %(id)s ...'), {'id': self.id}) self.loaded = False self.status = AlbumStatus.LOADING if self.release_group: self.release_group.loaded = False self.release_group.genres.clear() self.metadata.clear() self.genres.clear() self.update(update_selection=False) self._new_metadata = Metadata() self._new_tracks = [] self._requests = 1 self.clear_errors() config = get_config() require_authentication = False inc = { 'aliases', 'annotation', 'artist-credits', 'artists', 'collections', 'discids', 'isrcs', 'labels', 'media', 'recordings', 'release-groups', } if self.tagger.webservice.oauth_manager.is_authorized(): require_authentication = True inc |= {'user-collections'} if config.setting['release_ars'] or config.setting['track_ars']: inc |= { 'artist-rels', 'recording-rels', 'release-rels', 'url-rels', 'work-rels' } if config.setting['track_ars']: inc |= { 'recording-level-rels', 'work-level-rels', } require_authentication = self.set_genre_inc_params( inc, config) or require_authentication if config.setting['enable_ratings']: require_authentication = True inc |= {'user-ratings'} self.load_task = self.tagger.mb_api.get_release_by_id( self.id, self._release_request_finished, inc=tuple(inc), mblogin=require_authentication, priority=priority, refresh=refresh) def run_when_loaded(self, func, always=False): if self.loaded: func() else: self._after_load_callbacks.append((func, always)) def stop_loading(self): if self.load_task: self.tagger.webservice.remove_task(self.load_task) self.load_task = None def update(self, update_tracks=True, update_selection=True): if self.item: self.item.update(update_tracks, update_selection=update_selection) def add_file(self, track, file, new_album=True): self._files_count += 1 if new_album: self.update(update_tracks=False) add_metadata_images(self, [file]) def remove_file(self, track, file, new_album=True): self._files_count -= 1 if new_album: self.update(update_tracks=False) remove_metadata_images(self, [file]) @staticmethod def _match_files(files, tracks, unmatched_files, threshold=0, use_events_iter=False): """Match files to tracks on this album, based on metadata similarity or recordingid.""" if use_events_iter: # TODO: get rid of this completely at some point events_iter = process_events_iter else: def _events_iter(seq): return seq events_iter = _events_iter tracks_cache = defaultdict(lambda: None) def build_tracks_cache(): for track in tracks: tm_recordingid = track.orig_metadata['musicbrainz_recordingid'] tm_tracknumber = track.orig_metadata['tracknumber'] tm_discnumber = track.orig_metadata['discnumber'] for tup in ((tm_recordingid, tm_tracknumber, tm_discnumber), (tm_recordingid, tm_tracknumber), (tm_recordingid, )): tracks_cache[tup] = track SimMatchAlbum = namedtuple('SimMatchAlbum', 'similarity track') no_match = SimMatchAlbum(similarity=-1, track=unmatched_files) for file in list(files): if file.state == File.REMOVED: continue # if we have a recordingid to match against, use that in priority recid = file.match_recordingid or file.metadata[ 'musicbrainz_recordingid'] if recid and mbid_validate(recid): if not tracks_cache: build_tracks_cache() tracknumber = file.metadata['tracknumber'] discnumber = file.metadata['discnumber'] track = (tracks_cache[(recid, tracknumber, discnumber)] or tracks_cache[(recid, tracknumber)] or tracks_cache[(recid, )]) if track: yield (file, track) continue # try to match by similarity def candidates(): for track in events_iter(tracks): similarity = track.metadata.compare(file.orig_metadata) if similarity >= threshold: yield SimMatchAlbum(similarity=similarity, track=track) best_match = find_best_match(candidates, no_match) yield (file, best_match.result.track) def match_files(self, files): """Match and move files to tracks on this album, based on metadata similarity or recordingid.""" if self.loaded: config = get_config() threshold = config.setting['track_matching_threshold'] moves = self._match_files(files, self.tracks, self.unmatched_files, threshold=threshold) for file, target in moves: file.move(target) else: for file in list(files): file.move(self.unmatched_files) def can_save(self): return self._files_count > 0 def can_remove(self): return True def can_edit_tags(self): return True def can_analyze(self): return False def can_autotag(self): return False def can_refresh(self): return True def can_view_info(self): return self.loaded or bool(self.errors) def can_extract(self): return any(track.can_extract() for track in self.tracks) def is_album_like(self): return True def get_num_matched_tracks(self): return sum(1 for track in self.tracks if track.is_linked()) def get_num_unmatched_files(self): return len(self.unmatched_files.files) def get_num_total_files(self): return self._files_count + len(self.unmatched_files.files) def is_complete(self): if not self.tracks: return False for track in self.tracks: if not track.is_complete(): return False return not self.get_num_unmatched_files() def is_modified(self): return any(self._iter_unsaved_files()) def get_num_unsaved_files(self): return sum(1 for file in self._iter_unsaved_files()) def _iter_unsaved_files(self): yield from (file for file in self.iterfiles(save=True) if not file.is_saved()) def column(self, column): if column == 'title': if self.status == AlbumStatus.LOADING: title = _("[loading album information]") elif self.status == AlbumStatus.ERROR: title = _("[could not load album %s]") % self.id else: title = self.metadata['album'] if self.tracks: elems = [ '%d/%d' % (self.get_num_matched_tracks(), len(self.tracks)) ] unmatched = self.get_num_unmatched_files() if unmatched: elems.append('%d?' % (unmatched, )) unsaved = self.get_num_unsaved_files() if unsaved: elems.append('%d*' % (unsaved, )) ca_detailed = self.cover_art_description_detailed() if ca_detailed: elems.append(ca_detailed) return '%s\u200E (%s)' % (title, '; '.join(elems)) else: return title elif column == '~length': length = self.metadata.length if length: return format_time(length) else: return '' elif column == 'artist': return self.metadata['albumartist'] elif column == 'tracknumber': return self.metadata['~totalalbumtracks'] elif column == 'discnumber': return self.metadata['totaldiscs'] elif column == 'covercount': return self.cover_art_description() else: return self.metadata[column] def switch_release_version(self, mbid): if mbid == self.id: return for file in list(self.iterfiles(True)): file.move(self.unmatched_files) album = self.tagger.albums.get(mbid) if album: album.match_files(self.unmatched_files.files) album.update() self.tagger.remove_album(self) else: del self.tagger.albums[self.id] self.release_group.loaded_albums.discard(self.id) self.id = mbid self.tagger.albums[mbid] = self self.load(priority=True, refresh=True) def update_metadata_images(self): if not self.update_metadata_images_enabled: return if update_metadata_images(self): self.update(False) self.metadata_images_changed.emit() def keep_original_images(self): self.enable_update_metadata_images(False) for track in self.tracks: track.keep_original_images() for file in list(self.unmatched_files.files): file.keep_original_images() self.enable_update_metadata_images(True) self.update_metadata_images()
def test_cmd_is_complete_with_cluster(self): file = MagicMock() cluster = Cluster(name="Test") cluster.files.append(file) file.parent = cluster self.assertScriptResultEquals("$is_complete()", "", file=file)
def test_add_nothing(self): cluster = Cluster('Test') cluster.files = self.test_files update_metadata_images(cluster) added = add_metadata_images(cluster, []) self.assertFalse(added)
class Album(DataObject, Item): release_group_loaded = QtCore.pyqtSignal() def __init__(self, id, discid=None): DataObject.__init__(self, id) self.metadata = Metadata() self.tracks = [] self.loaded = False self.load_task = None self.release_group = None self._files = 0 self._requests = 0 self._tracks_loaded = False self._discid = discid self._after_load_callbacks = [] self.unmatched_files = Cluster(_("Unmatched Files"), special=True, related_album=self, hide_if_empty=True) self.errors = [] self.status = None self._album_artists = [] def __repr__(self): return '<Album %s %r>' % (self.id, self.metadata[u"album"]) def iterfiles(self, save=False): for track in self.tracks: for file in track.iterfiles(): yield file if not save: for file in self.unmatched_files.iterfiles(): yield file def append_album_artist(self, id): """Append artist id to the list of album artists and return an AlbumArtist instance""" album_artist = AlbumArtist(id) self._album_artists.append(album_artist) return album_artist def get_album_artists(self): """Returns the list of album artists (as AlbumArtist objects)""" return self._album_artists def _parse_release(self, document): log.debug("Loading release %r ...", self.id) self._tracks_loaded = False release_node = document.metadata[0].release[0] if release_node.id != self.id: self.tagger.mbid_redirects[self.id] = release_node.id album = self.tagger.albums.get(release_node.id) if album: log.debug("Release %r already loaded", release_node.id) album.match_files(self.unmatched_files.files) album.update() self.tagger.remove_album(self) return False else: del self.tagger.albums[self.id] self.tagger.albums[release_node.id] = self self.id = release_node.id # Get release metadata m = self._new_metadata m.length = 0 rg_node = release_node.release_group[0] rg = self.release_group = self.tagger.get_release_group_by_id(rg_node.id) rg.loaded_albums.add(self.id) rg.refcount += 1 release_group_to_metadata(rg_node, rg.metadata, rg) m.copy(rg.metadata) release_to_metadata(release_node, m, album=self) if self._discid: m['musicbrainz_discid'] = self._discid # Custom VA name if m['musicbrainz_albumartistid'] == VARIOUS_ARTISTS_ID: m['albumartistsort'] = m['albumartist'] = config.setting['va_name'] # Convert Unicode punctuation if config.setting['convert_punctuation']: m.apply_func(asciipunct) m['totaldiscs'] = release_node.medium_list[0].count # Add album to collections if "collection_list" in release_node.children: for node in release_node.collection_list[0].collection: if node.editor[0].text.lower() == config.persist["oauth_username"].lower(): if node.id not in user_collections: user_collections[node.id] = \ Collection(node.id, node.name[0].text, node.release_list[0].count) user_collections[node.id].releases.add(self.id) # Run album metadata plugins try: run_album_metadata_processors(self, m, release_node) except: self.error_append(traceback.format_exc()) self._release_node = release_node return True def _release_request_finished(self, document, http, error): if self.load_task is None: return self.load_task = None parsed = False try: if error: self.error_append(unicode(http.errorString())) # Fix for broken NAT releases if error == QtNetwork.QNetworkReply.ContentNotFoundError: nats = False nat_name = config.setting["nat_name"] files = list(self.unmatched_files.files) for file in files: recordingid = file.metadata["musicbrainz_recordingid"] if mbid_validate(recordingid) and file.metadata["album"] == nat_name: nats = True self.tagger.move_file_to_nat(file, recordingid) self.tagger.nats.update() if nats and not self.get_num_unmatched_files(): self.tagger.remove_album(self) error = False else: try: parsed = self._parse_release(document) except: error = True self.error_append(traceback.format_exc()) finally: self._requests -= 1 if parsed or error: self._finalize_loading(error) # does http need to be set to None to free the memory used by the network response? # http://pyqt.sourceforge.net/Docs/PyQt4/qnetworkaccessmanager.html says: # After the request has finished, it is the responsibility of the user # to delete the QNetworkReply object at an appropriate time. # Do not directly delete it inside the slot connected to finished(). # You can use the deleteLater() function. def error_append(self, msg): log.error(msg) self.errors.append(msg) def _finalize_loading(self, error): if error: self.metadata.clear() self.status = _("[could not load album %s]") % self.id del self._new_metadata del self._new_tracks self.update() return if self._requests > 0: return if not self._tracks_loaded: artists = set() totalalbumtracks = 0 absolutetracknumber = 0 va = self._new_metadata['musicbrainz_albumartistid'] == VARIOUS_ARTISTS_ID djmix_ars = {} if hasattr(self._new_metadata, "_djmix_ars"): djmix_ars = self._new_metadata._djmix_ars for medium_node in self._release_node.medium_list[0].medium: mm = Metadata() mm.copy(self._new_metadata) medium_to_metadata(medium_node, mm) discpregap = False for dj in djmix_ars.get(mm["discnumber"], []): mm.add("djmixer", dj) if "pregap" in medium_node.children: discpregap = True absolutetracknumber += 1 track = self._finalize_loading_track(medium_node.pregap[0], mm, artists, va, absolutetracknumber, discpregap) track.metadata['~pregap'] = "1" for track_node in medium_node.track_list[0].track: absolutetracknumber += 1 track = self._finalize_loading_track(track_node, mm, artists, va, absolutetracknumber, discpregap) if "data_track_list" in medium_node.children: for track_node in medium_node.data_track_list[0].track: absolutetracknumber += 1 track = self._finalize_loading_track(track_node, mm, artists, va, absolutetracknumber, discpregap) track.metadata['~datatrack'] = "1" totalalbumtracks = str(absolutetracknumber) for track in self._new_tracks: track.metadata["~totalalbumtracks"] = totalalbumtracks if len(artists) > 1: track.metadata["~multiartist"] = "1" del self._release_node self._tracks_loaded = True if not self._requests: # Prepare parser for user's script if config.setting["enable_tagger_script"]: script = config.setting["tagger_script"] if script: parser = ScriptParser() for track in self._new_tracks: # Run tagger script for each track try: parser.eval(script, track.metadata) except: self.error_append(traceback.format_exc()) # Strip leading/trailing whitespace track.metadata.strip_whitespace() # Run tagger script for the album itself try: parser.eval(script, self._new_metadata) except: self.error_append(traceback.format_exc()) self._new_metadata.strip_whitespace() for track in self.tracks: for file in list(track.linked_files): file.move(self.unmatched_files) self.metadata = self._new_metadata self.tracks = self._new_tracks del self._new_metadata del self._new_tracks self.loaded = True self.status = None self.match_files(self.unmatched_files.files) self.update() self.tagger.window.set_statusbar_message( N_('Album %(id)s loaded: %(artist)s - %(album)s'), { 'id': self.id, 'artist': self.metadata['albumartist'], 'album': self.metadata['album'] }, timeout=3000 ) for func in self._after_load_callbacks: func() self._after_load_callbacks = [] def _finalize_loading_track(self, track_node, metadata, artists, va, absolutetracknumber, discpregap): track = Track(track_node.recording[0].id, self) self._new_tracks.append(track) # Get track metadata tm = track.metadata tm.copy(metadata) track_to_metadata(track_node, track) track.metadata["~absolutetracknumber"] = absolutetracknumber track._customize_metadata() self._new_metadata.length += tm.length artists.add(tm["artist"]) if va: tm["compilation"] = "1" if discpregap: tm["~discpregap"] = "1" # Run track metadata plugins try: run_track_metadata_processors(self, tm, self._release_node, track_node) except: self.error_append(traceback.format_exc()) return track def load(self, priority=False, refresh=False): if self._requests: log.info("Not reloading, some requests are still active.") return self.tagger.window.set_statusbar_message( N_('Loading album %(id)s ...'), {'id': self.id} ) self.loaded = False self.status = _("[loading album information]") if self.release_group: self.release_group.loaded = False self.release_group.folksonomy_tags.clear() self.metadata.clear() self.folksonomy_tags.clear() self.update() self._new_metadata = Metadata() self._new_tracks = [] self._requests = 1 self.errors = [] require_authentication = False inc = ['release-groups', 'media', 'recordings', 'artist-credits', 'artists', 'aliases', 'labels', 'isrcs', 'collections'] if config.setting['release_ars'] or config.setting['track_ars']: inc += ['artist-rels', 'release-rels', 'url-rels', 'recording-rels', 'work-rels'] if config.setting['track_ars']: inc += ['recording-level-rels', 'work-level-rels'] if config.setting['folksonomy_tags']: if config.setting['only_my_tags']: require_authentication = True inc += ['user-tags'] else: inc += ['tags'] if config.setting['enable_ratings']: require_authentication = True inc += ['user-ratings'] self.load_task = self.tagger.xmlws.get_release_by_id( self.id, self._release_request_finished, inc=inc, mblogin=require_authentication, priority=priority, refresh=refresh) def run_when_loaded(self, func): if self.loaded: func() else: self._after_load_callbacks.append(func) def stop_loading(self): if self.load_task: self.tagger.xmlws.remove_task(self.load_task) self.load_task = None def update(self, update_tracks=True): if self.item: self.item.update(update_tracks) def _add_file(self, track, file): self._files += 1 self.update(update_tracks=False) def _remove_file(self, track, file): self._files -= 1 self.update(update_tracks=False) def match_files(self, files, use_recordingid=True): """Match files to tracks on this album, based on metadata similarity or recordingid.""" for file in list(files): if file.state == File.REMOVED: continue matches = [] recordingid = file.metadata['musicbrainz_recordingid'] if use_recordingid and mbid_validate(recordingid): matches = self._get_recordingid_matches(file, recordingid) if not matches: for track in self.tracks: sim = track.metadata.compare(file.orig_metadata) if sim >= config.setting['track_matching_threshold']: matches.append((sim, track)) if matches: matches.sort(reverse=True) file.move(matches[0][1]) else: file.move(self.unmatched_files) def match_file(self, file, recordingid=None): """Match the file on a track on this album, based on recordingid or metadata similarity.""" if file.state == File.REMOVED: return if recordingid is not None: matches = self._get_recordingid_matches(file, recordingid) if matches: matches.sort(reverse=True) file.move(matches[0][1]) return self.match_files([file], use_recordingid=False) def _get_recordingid_matches(self, file, recordingid): matches = [] tracknumber = file.metadata['tracknumber'] discnumber = file.metadata['discnumber'] for track in self.tracks: tm = track.metadata if recordingid == tm['musicbrainz_recordingid']: if tracknumber == tm['tracknumber']: if discnumber == tm['discnumber']: matches.append((4.0, track)) break else: matches.append((3.0, track)) else: matches.append((2.0, track)) return matches def can_save(self): return self._files > 0 def can_remove(self): return True def can_edit_tags(self): return True def can_analyze(self): return False def can_autotag(self): return False def can_refresh(self): return True def can_view_info(self): return (self.loaded and self.metadata and self.metadata.images) or self.errors def is_album_like(self): return True def get_num_matched_tracks(self): num = 0 for track in self.tracks: if track.is_linked(): num += 1 return num def get_num_unmatched_files(self): return len(self.unmatched_files.files) def get_num_total_files(self): return self._files + len(self.unmatched_files.files) def is_complete(self): if not self.tracks: return False for track in self.tracks: if not track.is_complete(): return False else: return True def is_modified(self): if self.tracks: for track in self.tracks: for file in track.linked_files: if not file.is_saved(): return True return False def get_num_unsaved_files(self): count = 0 for track in self.tracks: for file in track.linked_files: if not file.is_saved(): count += 1 return count def column(self, column): if column == 'title': if self.status is not None: title = self.status else: title = self.metadata['album'] if self.tracks: linked_tracks = 0 for track in self.tracks: if track.is_linked(): linked_tracks += 1 text = u'%s\u200E (%d/%d' % (title, linked_tracks, len(self.tracks)) unmatched = self.get_num_unmatched_files() if unmatched: text += '; %d?' % (unmatched,) unsaved = self.get_num_unsaved_files() if unsaved: text += '; %d*' % (unsaved,) text += ungettext("; %i image", "; %i images", len(self.metadata.images)) % len(self.metadata.images) return text + ')' else: return title elif column == '~length': length = self.metadata.length if length: return format_time(length) else: return '' elif column == 'artist': return self.metadata['albumartist'] else: return '' def switch_release_version(self, mbid): if mbid == self.id: return for file in list(self.iterfiles(True)): file.move(self.unmatched_files) album = self.tagger.albums.get(mbid) if album: album.match_files(self.unmatched_files.files) album.update() self.tagger.remove_album(self) else: del self.tagger.albums[self.id] self.release_group.loaded_albums.discard(self.id) self.id = mbid self.tagger.albums[mbid] = self self.load(priority=True, refresh=True)