diff --git a/core/imports/side_effects.py b/core/imports/side_effects.py index 589166e4..d577db91 100644 --- a/core/imports/side_effects.py +++ b/core/imports/side_effects.py @@ -324,6 +324,17 @@ def record_soulsync_library_entry(context: Dict[str, Any], artist_context: Dict[ except Exception: pass + # File size on disk (powers Library Disk Usage card on Stats). + # SoulSync standalone is the only path where the file is local + # at insert time, so we read it directly via os.path.getsize. + # Mirrors what JellyfinTrack/NavidromeTrack pull from API + # responses for the media-server flows. + file_size = None + try: + file_size = os.path.getsize(final_path) or None + except OSError: + pass + artist_id = _stable_soulsync_id(artist_name.lower().strip()) album_id = _stable_soulsync_id(f"{artist_name}::{album_name}".lower().strip()) track_id = _stable_soulsync_id(final_path) @@ -410,9 +421,9 @@ def record_soulsync_library_entry(context: Dict[str, Any], artist_context: Dict[ cursor.execute( """ INSERT INTO tracks (id, album_id, artist_id, title, track_number, - duration, file_path, bitrate, track_artist, server_source, + duration, file_path, bitrate, file_size, track_artist, server_source, created_at, updated_at) - VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, 'soulsync', CURRENT_TIMESTAMP, CURRENT_TIMESTAMP) + VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, 'soulsync', CURRENT_TIMESTAMP, CURRENT_TIMESTAMP) """, ( track_id, @@ -423,6 +434,7 @@ def record_soulsync_library_entry(context: Dict[str, Any], artist_context: Dict[ duration_ms, final_path, bitrate, + file_size, track_artist, ), ) diff --git a/core/jellyfin_client.py b/core/jellyfin_client.py index 4cf1500e..28adba99 100644 --- a/core/jellyfin_client.py +++ b/core/jellyfin_client.py @@ -116,9 +116,15 @@ class JellyfinTrack: # File path and media info (used by quality scanner and DB update) self.path = jellyfin_data.get('Path') - # Extract bitrate from MediaSources if available + # Extract bitrate + file size from MediaSources if available. + # `file_size` powers the Library Disk Usage card on the Stats + # page — populated free during the deep scan from data Jellyfin + # already returns in MediaSources[]. media_sources = jellyfin_data.get('MediaSources', []) self.bitRate = (media_sources[0].get('Bitrate') or 0) // 1000 if media_sources else None # Convert bps to kbps + self.file_size = (media_sources[0].get('Size') or 0) if media_sources else None + if self.file_size == 0: + self.file_size = None def _parse_date(self, date_str: Optional[str]) -> Optional[datetime]: if not date_str: diff --git a/core/navidrome_client.py b/core/navidrome_client.py index 3730e36c..2cc010a7 100644 --- a/core/navidrome_client.py +++ b/core/navidrome_client.py @@ -117,6 +117,14 @@ class NavidromeTrack: self.suffix = navidrome_data.get('suffix') # e.g. "flac", "mp3" self.bitRate = navidrome_data.get('bitRate') # e.g. 320 self.path = navidrome_data.get('path') # e.g. "/music/Artist/Album/track.flac" + # File size in bytes (Subsonic ) — powers the + # Library Disk Usage card on Stats. None when the server didn't + # report a size (rare but possible for streaming-only nodes). + _nv_size = navidrome_data.get('size') + try: + self.file_size = int(_nv_size) if _nv_size else None + except (TypeError, ValueError): + self.file_size = None self._album_id = navidrome_data.get('albumId', '') self._artist_id = navidrome_data.get('artistId', '') diff --git a/core/soulsync_client.py b/core/soulsync_client.py index 39653768..a7b3ff98 100644 --- a/core/soulsync_client.py +++ b/core/soulsync_client.py @@ -98,6 +98,14 @@ class SoulSyncTrack: self.path = file_path self.bitRate = tags['bitrate'] self.suffix = os.path.splitext(file_path)[1].lstrip('.').lower() + # File size in bytes (powers Library Disk Usage card on Stats). + # SoulSync standalone is the only "server" where we can read + # size from disk directly — Plex/Jellyfin/Navidrome get theirs + # from the API response. + try: + self.file_size = os.path.getsize(file_path) if os.path.exists(file_path) else None + except OSError: + self.file_size = None def artist(self): return self._artist_ref diff --git a/core/stats/queries.py b/core/stats/queries.py index df7cfa68..c0021265 100644 --- a/core/stats/queries.py +++ b/core/stats/queries.py @@ -172,6 +172,17 @@ def get_db_storage(database) -> dict: return database.get_db_storage_stats() +def get_library_disk_usage(database) -> dict: + """On-disk size of the library, with per-format breakdown. + + Backed by `tracks.file_size` populated during the deep scan from + media-server-reported sizes (Plex MediaPart.size, Jellyfin + MediaSources[].Size, Navidrome , + SoulSync standalone os.path.getsize). + """ + return database.get_library_disk_usage() + + def get_recent_tracks(database, limit: int) -> list[dict]: """Recently played tracks from listening_history.""" conn = database._get_connection() diff --git a/database/music_database.py b/database/music_database.py index b8e3e39b..7fc9b901 100644 --- a/database/music_database.py +++ b/database/music_database.py @@ -294,6 +294,7 @@ class MusicDatabase: duration INTEGER, -- milliseconds file_path TEXT, bitrate INTEGER, + file_size INTEGER, -- bytes; populated by deep scan from media-server API created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP, updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP, FOREIGN KEY (album_id) REFERENCES albums (id) ON DELETE CASCADE, @@ -672,6 +673,23 @@ class MusicDatabase: except Exception: pass + # Migration: add file_size column so the Stats page can show + # total library size on disk without having to walk the + # filesystem on every request. Populated by the deep scan from + # whatever the media server reports (Plex MediaPart.size, + # Jellyfin MediaSources[].Size, Navidrome , + # SoulSync standalone os.path.getsize). NULL on existing rows + # until the next deep scan fills them in — UI handles the + # NULL case by showing "(run a Deep Scan to populate)". + try: + cursor.execute("SELECT file_size FROM tracks LIMIT 1") + except Exception: + try: + cursor.execute("ALTER TABLE tracks ADD COLUMN file_size INTEGER") + logger.info("Added file_size column to tracks table") + except Exception: + pass + # One-time migration: purge discovery cache entries that lack track_number. # Prior versions cached discovery results without track_number/disc_number/release_date, # causing incorrect file organization (all tracks as "01", missing album year). @@ -3648,6 +3666,85 @@ class MusicDatabase: if conn: conn.close() + def get_library_disk_usage(self): + """Aggregate disk usage of the on-disk music library. + + Returns: + { + 'total_bytes': int, # sum of all known file sizes + 'tracks_with_size': int, # count of tracks with a known size + 'tracks_without_size': int, # count of tracks where size is NULL + 'by_format': { # bytes per file extension + 'flac': int, 'mp3': int, ... + }, + 'has_data': bool, # False on fresh installs / before first deep scan + } + + Returns the empty-shape dict when the column doesn't exist (very + old install pre-migration) — UI shows "(run a Deep Scan)" in + that case rather than crashing. + """ + empty = { + 'total_bytes': 0, + 'tracks_with_size': 0, + 'tracks_without_size': 0, + 'by_format': {}, + 'has_data': False, + } + conn = None + try: + conn = self._get_connection() + cursor = conn.cursor() + + # Confirm column exists (defensive against fresh-install race + # where the migration hasn't run yet). + try: + cursor.execute("SELECT file_size FROM tracks LIMIT 1") + except Exception: + return empty + + cursor.execute( + "SELECT COALESCE(SUM(file_size), 0), " + " COUNT(file_size), " + " COUNT(*) - COUNT(file_size) " + "FROM tracks" + ) + row = cursor.fetchone() + total_bytes = int(row[0] or 0) + tracks_with_size = int(row[1] or 0) + tracks_without_size = int(row[2] or 0) + + # Per-format breakdown via Python aggregation. Doing the + # extension split in SQLite is fragile (paths with dots + # before the file extension would group wrong); doing it + # in Python is one os.path.splitext per row, which is + # negligible cost compared to the SUM() above. + cursor.execute( + "SELECT file_path, file_size FROM tracks " + "WHERE file_size IS NOT NULL AND file_path IS NOT NULL " + " AND file_path != ''" + ) + by_format: dict = {} + for path, size in cursor.fetchall(): + ext = os.path.splitext(path)[1].lstrip('.').lower() + if not ext or len(ext) > 6: + continue + by_format[ext] = by_format.get(ext, 0) + int(size or 0) + + return { + 'total_bytes': total_bytes, + 'tracks_with_size': tracks_with_size, + 'tracks_without_size': tracks_without_size, + 'by_format': by_format, + 'has_data': tracks_with_size > 0, + } + except Exception as e: + logger.error(f"Error getting library disk usage: {e}") + return empty + finally: + if conn: + conn.close() + @staticmethod def _listening_time_filter(time_range, alias=''): """Build a WHERE clause for time-range filtering.""" @@ -4970,12 +5067,20 @@ class MusicDatabase: # Get file path and media info (Plex-specific, Jellyfin may not have these) file_path = None bitrate = None + file_size = None if hasattr(track_obj, 'media') and track_obj.media: media = track_obj.media[0] if track_obj.media else None if media: if hasattr(media, 'parts') and media.parts: part = media.parts[0] file_path = getattr(part, 'file', None) + # Plex's MediaPart exposes the file size in bytes + # via plexapi — pull it for the Library Disk + # Usage card on Stats. None when the server + # didn't report a size. + _plex_size = getattr(part, 'size', None) + if isinstance(_plex_size, int) and _plex_size > 0: + file_size = _plex_size bitrate = getattr(media, 'bitrate', None) # Fallback for Navidrome/Subsonic tracks @@ -4985,6 +5090,14 @@ class MusicDatabase: bitrate = track_obj.bitRate if file_path is None and hasattr(track_obj, 'suffix') and track_obj.suffix: file_path = f"{track_obj.title}.{track_obj.suffix}" + # File size: Jellyfin / Navidrome / SoulSync-standalone + # all set track_obj.file_size on their wrapper class. + # Plex came in via the media.parts[0].size path above — + # don't clobber that. + if file_size is None and hasattr(track_obj, 'file_size'): + _wrapper_size = getattr(track_obj, 'file_size', None) + if isinstance(_wrapper_size, int) and _wrapper_size > 0: + file_size = _wrapper_size # Extract per-track artist for compilations/DJ mixes. # Only stored when it differs from the album artist. @@ -5040,21 +5153,26 @@ class MusicDatabase: if is_new_track: cursor.execute(""" INSERT INTO tracks - (id, album_id, artist_id, title, track_number, duration, file_path, bitrate, server_source, track_artist, musicbrainz_recording_id, updated_at) - VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, CURRENT_TIMESTAMP) - """, (track_id, album_id, artist_id, title, track_number, duration, file_path, bitrate, server_source, track_artist, mbid)) + (id, album_id, artist_id, title, track_number, duration, file_path, bitrate, file_size, server_source, track_artist, musicbrainz_recording_id, updated_at) + VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, CURRENT_TIMESTAMP) + """, (track_id, album_id, artist_id, title, track_number, duration, file_path, bitrate, file_size, server_source, track_artist, mbid)) else: # Update server-provided fields only — preserves spotify_track_id, deezer_id, - # isrc, bpm, and all other enrichment data + # isrc, bpm, and all other enrichment data. file_size uses + # COALESCE(?, file_size) so a NULL from the server (e.g. + # Jellyfin sometimes omits Size on first sync) doesn't wipe + # an existing value. cursor.execute(""" UPDATE tracks SET album_id = ?, artist_id = ?, title = ?, track_number = ?, - duration = ?, file_path = ?, bitrate = ?, server_source = ?, + duration = ?, file_path = ?, bitrate = ?, + file_size = COALESCE(?, file_size), + server_source = ?, track_artist = COALESCE(?, track_artist), musicbrainz_recording_id = COALESCE(?, musicbrainz_recording_id), updated_at = CURRENT_TIMESTAMP WHERE id = ? - """, (album_id, artist_id, title, track_number, duration, file_path, bitrate, server_source, track_artist, mbid, track_id)) + """, (album_id, artist_id, title, track_number, duration, file_path, bitrate, file_size, server_source, track_artist, mbid, track_id)) conn.commit() diff --git a/tests/imports/test_import_side_effects.py b/tests/imports/test_import_side_effects.py index 2091f0b0..33bfa1e4 100644 --- a/tests/imports/test_import_side_effects.py +++ b/tests/imports/test_import_side_effects.py @@ -1,3 +1,4 @@ +import os import sqlite3 from types import SimpleNamespace @@ -58,6 +59,7 @@ def _make_soulsync_db(): duration INTEGER, file_path TEXT, bitrate INTEGER, + file_size INTEGER, track_artist TEXT, server_source TEXT, created_at TEXT, @@ -142,6 +144,10 @@ def test_record_soulsync_library_entry_writes_artist_album_and_track(tmp_path, m assert track_row["track_artist"] == "Guest Artist" assert track_row["album_id"] == album_row["id"] assert track_row["file_path"] == str(final_path) + # File size in bytes — populates the Library Disk Usage card on Stats. + # Read via os.path.getsize at insert time since SoulSync standalone is + # the only flow where the file is local at the moment we write the row. + assert track_row["file_size"] == os.path.getsize(str(final_path)) def test_record_soulsync_library_entry_ignores_numeric_spotify_ids(tmp_path, monkeypatch): diff --git a/tests/test_library_disk_usage.py b/tests/test_library_disk_usage.py new file mode 100644 index 00000000..00707aa7 --- /dev/null +++ b/tests/test_library_disk_usage.py @@ -0,0 +1,282 @@ +"""Tests for the Library Disk Usage stat. + +Discord request (Samuel [KC]): show how much disk space the library +takes on the System Statistics page. Implementation piggybacks on the +existing deep scan — Plex/Jellyfin/Navidrome all return file size in +their track API responses, so we read it during the deep scan and +aggregate via SQL on demand. No filesystem walk involved. + +Tests pin: +- Schema migration is idempotent and backward-compatible (existing + rows get NULL file_size; new column doesn't break old inserts). +- Aggregator returns the empty-shape dict for fresh installs and + walks/sums correctly when populated. +- Per-format breakdown handles mixed extensions correctly. +- Defensive: empty / NULL / malformed paths don't crash. +""" + +from __future__ import annotations + +import os +import sqlite3 +import tempfile +import uuid +from pathlib import Path + +import pytest + +from database.music_database import MusicDatabase + + +@pytest.fixture +def db(tmp_path: Path) -> MusicDatabase: + """Build a fresh isolated MusicDatabase against a temp file.""" + db_path = tmp_path / 'test_library_size.db' + return MusicDatabase(database_path=str(db_path)) + + +def _insert_track(db: MusicDatabase, *, track_id: str, file_path: str, + file_size, album_id: str = 'a1', artist_id: str = 'ar1') -> None: + """Helper: seed an artist+album+track row with the given size.""" + conn = db._get_connection() + cur = conn.cursor() + cur.execute("INSERT OR IGNORE INTO artists (id, name) VALUES (?, ?)", + (artist_id, 'Test Artist')) + cur.execute("INSERT OR IGNORE INTO albums (id, artist_id, title) VALUES (?, ?, ?)", + (album_id, artist_id, 'Test Album')) + cur.execute( + "INSERT INTO tracks (id, album_id, artist_id, title, file_path, file_size) " + "VALUES (?, ?, ?, ?, ?, ?)", + (track_id, album_id, artist_id, f'track-{track_id}', file_path, file_size), + ) + conn.commit() + conn.close() + + +# --------------------------------------------------------------------------- +# Schema migration +# --------------------------------------------------------------------------- + + +def test_file_size_column_exists_after_init(db: MusicDatabase) -> None: + """Fresh install should have the column from the canonical + CREATE TABLE.""" + conn = db._get_connection() + cur = conn.cursor() + cur.execute("PRAGMA table_info(tracks)") + cols = {row[1] for row in cur.fetchall()} + conn.close() + assert 'file_size' in cols + + +def test_existing_tracks_have_null_file_size_after_migration(db: MusicDatabase) -> None: + """Backward-compat: rows inserted via the OLD schema (no file_size) + must still be readable, and querying file_size returns NULL — not + an error. Simulated by inserting a track without specifying + file_size (relies on column default = NULL).""" + conn = db._get_connection() + cur = conn.cursor() + cur.execute("INSERT OR IGNORE INTO artists (id, name) VALUES ('ar1', 'A')") + cur.execute("INSERT OR IGNORE INTO albums (id, artist_id, title) VALUES ('a1', 'ar1', 'Al')") + # Note: NOT specifying file_size — should default to NULL + cur.execute( + "INSERT INTO tracks (id, album_id, artist_id, title, file_path) " + "VALUES ('legacy_t', 'a1', 'ar1', 'L', '/x/legacy.flac')" + ) + conn.commit() + cur.execute("SELECT file_size FROM tracks WHERE id = 'legacy_t'") + row = cur.fetchone() + conn.close() + # Could be sqlite3.Row or tuple; both index by 0 + assert row[0] is None + + +# --------------------------------------------------------------------------- +# Aggregator +# --------------------------------------------------------------------------- + + +def test_aggregator_returns_empty_shape_for_fresh_install(db: MusicDatabase) -> None: + """No tracks inserted → has_data=False, total=0, no formats.""" + result = db.get_library_disk_usage() + assert result == { + 'total_bytes': 0, + 'tracks_with_size': 0, + 'tracks_without_size': 0, + 'by_format': {}, + 'has_data': False, + } + + +def test_aggregator_sums_known_sizes(db: MusicDatabase) -> None: + _insert_track(db, track_id='t1', file_path='/x/song1.flac', file_size=10_000_000) + _insert_track(db, track_id='t2', file_path='/x/song2.flac', file_size=5_000_000) + _insert_track(db, track_id='t3', file_path='/x/song3.mp3', file_size=3_000_000) + + result = db.get_library_disk_usage() + assert result['total_bytes'] == 18_000_000 + assert result['tracks_with_size'] == 3 + assert result['tracks_without_size'] == 0 + assert result['has_data'] is True + + +def test_aggregator_excludes_null_sizes_from_sum(db: MusicDatabase) -> None: + """Tracks without size are counted but don't contribute to total_bytes.""" + _insert_track(db, track_id='t1', file_path='/x/sized.flac', file_size=10_000_000) + _insert_track(db, track_id='t2', file_path='/x/null.flac', file_size=None) + + result = db.get_library_disk_usage() + assert result['total_bytes'] == 10_000_000 + assert result['tracks_with_size'] == 1 + assert result['tracks_without_size'] == 1 + # Has data — at least one track was measured + assert result['has_data'] is True + + +def test_aggregator_per_format_breakdown(db: MusicDatabase) -> None: + _insert_track(db, track_id='t1', file_path='/x/song.flac', file_size=10_000_000) + _insert_track(db, track_id='t2', file_path='/x/other.flac', file_size=5_000_000) + _insert_track(db, track_id='t3', file_path='/x/song.mp3', file_size=3_000_000) + _insert_track(db, track_id='t4', file_path='/x/song.m4a', file_size=2_000_000) + + result = db.get_library_disk_usage() + assert result['by_format'] == { + 'flac': 15_000_000, + 'mp3': 3_000_000, + 'm4a': 2_000_000, + } + + +def test_aggregator_handles_mixed_case_extensions(db: MusicDatabase) -> None: + """Extensions get lowercased so .FLAC and .flac group together.""" + _insert_track(db, track_id='t1', file_path='/x/song.FLAC', file_size=5_000_000) + _insert_track(db, track_id='t2', file_path='/x/other.flac', file_size=5_000_000) + + result = db.get_library_disk_usage() + assert result['by_format'] == {'flac': 10_000_000} + + +def test_aggregator_handles_paths_with_dots_in_album_name(db: MusicDatabase) -> None: + """Albums like 'M.A.A.D City' have dots in the path. Extension + extraction must use the LAST dot, not the first.""" + _insert_track( + db, track_id='t1', + file_path='/music/Kendrick Lamar/M.A.A.D City/01 - track.flac', + file_size=10_000_000, + ) + result = db.get_library_disk_usage() + assert result['by_format'] == {'flac': 10_000_000} + + +def test_aggregator_skips_paths_without_extension(db: MusicDatabase) -> None: + """Defensive: files without an extension don't show up in + by_format (would otherwise produce an empty-string key or junk).""" + _insert_track(db, track_id='t1', file_path='/x/no_extension', file_size=5_000_000) + _insert_track(db, track_id='t2', file_path='/x/song.flac', file_size=10_000_000) + + result = db.get_library_disk_usage() + assert result['total_bytes'] == 15_000_000 + assert result['by_format'] == {'flac': 10_000_000} + assert '' not in result['by_format'] + + +def test_aggregator_skips_empty_file_path(db: MusicDatabase) -> None: + """Empty string file_path → shouldn't appear in by_format.""" + _insert_track(db, track_id='t1', file_path='', file_size=5_000_000) + _insert_track(db, track_id='t2', file_path='/x/song.flac', file_size=10_000_000) + + result = db.get_library_disk_usage() + # Total still includes the empty-path track (it was measured) + assert result['total_bytes'] == 15_000_000 + # But by_format only has the one with a real extension + assert result['by_format'] == {'flac': 10_000_000} + + +def test_aggregator_skips_implausibly_long_extension(db: MusicDatabase) -> None: + """Extensions over 6 chars are filtered (would be junk from an + unusual filename like 'song.somethingweird').""" + _insert_track(db, track_id='t1', file_path='/x/song.somethingweird', file_size=5_000_000) + _insert_track(db, track_id='t2', file_path='/x/song.flac', file_size=10_000_000) + + result = db.get_library_disk_usage() + assert result['by_format'] == {'flac': 10_000_000} + + +# --------------------------------------------------------------------------- +# Backward compatibility — schema column ordering / NULL writes +# --------------------------------------------------------------------------- + + +def test_insert_or_update_media_track_persists_size_for_object_with_file_size(db: MusicDatabase) -> None: + """The Jellyfin/Navidrome/SoulSync track wrappers expose + `track_obj.file_size`. Verify insert_or_update_media_track reads + it and persists to the new column.""" + + class _FakeTrack: + def __init__(self): + self.ratingKey = 'fake_track_id_1' + self.title = 'Test Track' + self.trackNumber = 1 + self.duration = 200000 + self.path = '/library/Artist/Album/01 - track.flac' + self.bitRate = 1411 + self.file_size = 42_000_000 + + # Seed parent rows so FK constraints are satisfied + conn = db._get_connection() + cur = conn.cursor() + cur.execute("INSERT OR IGNORE INTO artists (id, name) VALUES ('ar2', 'Artist')") + cur.execute("INSERT OR IGNORE INTO albums (id, artist_id, title) VALUES ('al2', 'ar2', 'Album')") + conn.commit() + conn.close() + + db.insert_or_update_media_track(_FakeTrack(), album_id='al2', artist_id='ar2', + server_source='jellyfin') + + conn = db._get_connection() + cur = conn.cursor() + cur.execute("SELECT file_size FROM tracks WHERE id = 'fake_track_id_1'") + row = cur.fetchone() + conn.close() + assert row[0] == 42_000_000 + + +def test_insert_or_update_media_track_preserves_size_on_null_re_sync(db: MusicDatabase) -> None: + """If a subsequent deep scan returns no file_size for a track that + previously had one (e.g. server hiccup, rare Jellyfin response), + the COALESCE on UPDATE preserves the existing value rather than + blanking it. Pin the regression — losing data on every scan would + be worse than the original problem.""" + + class _FakeTrack: + def __init__(self, size): + self.ratingKey = 'fake_track_id_2' + self.title = 'Test' + self.trackNumber = 1 + self.duration = 200000 + self.path = '/library/Artist/Album/02 - track.flac' + self.bitRate = 1411 + self.file_size = size + + conn = db._get_connection() + cur = conn.cursor() + cur.execute("INSERT OR IGNORE INTO artists (id, name) VALUES ('ar3', 'Artist')") + cur.execute("INSERT OR IGNORE INTO albums (id, artist_id, title) VALUES ('al3', 'ar3', 'Album')") + conn.commit() + conn.close() + + # First sync — server reports 30 MB + db.insert_or_update_media_track(_FakeTrack(size=30_000_000), album_id='al3', + artist_id='ar3', server_source='jellyfin') + + # Second sync — server reports None (didn't include Size in MediaSources this time) + db.insert_or_update_media_track(_FakeTrack(size=None), album_id='al3', + artist_id='ar3', server_source='jellyfin') + + conn = db._get_connection() + cur = conn.cursor() + cur.execute("SELECT file_size FROM tracks WHERE id = 'fake_track_id_2'") + row = cur.fetchone() + conn.close() + # Original size preserved + assert row[0] == 30_000_000 diff --git a/web_server.py b/web_server.py index 4275e39a..b56c158b 100644 --- a/web_server.py +++ b/web_server.py @@ -32845,6 +32845,21 @@ def stats_db_storage(): except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 +@app.route('/api/stats/library-disk-usage', methods=['GET']) +def stats_library_disk_usage(): + """Library on-disk size + per-format breakdown. + + Reads `tracks.file_size` populated by the deep scan from data the + media server already returns. Returns ``has_data: false`` on fresh + installs that haven't run a deep scan since the migration — UI + shows "Run a Deep Scan to populate" in that case. + """ + try: + data = _stats_queries.get_library_disk_usage(get_database()) + return jsonify({'success': True, **data}) + except Exception as e: + return jsonify({'success': False, 'error': str(e)}), 500 + @app.route('/api/stats/recent', methods=['GET']) def stats_recent(): """Get recently played tracks.""" diff --git a/webui/index.html b/webui/index.html index 3992d14d..f0f8e908 100644 --- a/webui/index.html +++ b/webui/index.html @@ -6055,6 +6055,18 @@
+ +
+
Library Disk Usage
+
+
+
—
+
Run a Deep Scan to populate
+
+
+
+
+
Database Storage
diff --git a/webui/static/helper.js b/webui/static/helper.js index 0bf31bd8..7729ce9e 100644 --- a/webui/static/helper.js +++ b/webui/static/helper.js @@ -3444,6 +3444,7 @@ const WHATS_NEW = { '2.4.2': [ // --- post-2.4.1 dev work — entries hidden by _getLatestWhatsNewVersion until the build version bumps --- { date: 'Unreleased — 2.4.2 dev cycle' }, + { title: 'Library Disk Usage on Stats Page', desc: 'discord request (samuel [KC]): show how much disk space the library takes. new card on stats → system statistics shows total bytes + per-format breakdown (FLAC vs MP3 vs M4A bars). data comes from `tracks.file_size` populated during deep scan from whatever the media server already returns (plex MediaPart.size, jellyfin MediaSources[].Size, navidrome song.size, soulsync standalone os.path.getsize) — zero filesystem walk overhead. existing libraries see "Run a Deep Scan to populate" until the next deep scan fills in sizes; partial coverage shown as "X tracks measured (+Y pending)". migration is additive (NULL on legacy rows) so upgrading users have nothing to do.', page: 'stats' }, { title: 'Fix: ReplayGain Wrote Same +52 dB Gain to Every Track', desc: 'noticed every downloaded track came out with `replaygain_track_gain: +52.00 dB` regardless of actual loudness. cause: parser used `re.search` which returned the FIRST `I:` (integrated loudness) reading from ffmpeg\'s ebur128 output. that\'s the per-window measurement at t=0.5s — almost always ~-70 LUFS because tracks start with silence/encoder padding. -18 (RG2 reference) - (-70) = +52 dB on every track. fix: parser now anchors to the `Summary:` block at the end of ffmpeg\'s output and reads the actual integrated loudness from there, not the silent-intro partial. defensive fallback uses the LAST per-window reading if Summary is missing (still better than the first). gains now reflect real per-track loudness.', page: 'downloads' }, { title: 'Fix: Tracks Showed Completed When File Was Quarantined', desc: 'caught downloading kendrick mr morale: three tracks (rich interlude, savior interlude, savior) showed ✅ completed in the modal but were missing on disk. two layered bugs. (1) the post-process verification wrapper had a fallback that assumed success when no `_final_processed_path` was in context — but integrity-rejected files (which get quarantined instead of moved) leave that path unset, so the wrapper marked them complete. now wrapper explicitly checks `_integrity_failure_msg` and `_race_guard_failed` markers before the assume-success fallback. failed integrity = task marked failed, batch tracker notified with success=false. (2) acoustid skip-logic was too lenient — when fingerprint confidence was very high and either title OR artist matched a bit, it skipped verification with reason "likely same song in different language/script." that fired for english-vs-english by the same artist with the word "interlude" in both — same artist + 0.55 title sim = skip = wrong file accepted. tightened: skip now requires non-ASCII chars present (real language/script case) AND artist match, OR very high title similarity (≥0.80) AND artist match. english-vs-english with very different titles by same artist no longer skipped — verification correctly returns FAIL and the wrong file gets quarantined.', page: 'downloads' }, { title: 'Stop Navidrome From Splitting Albums Over Inconsistent MBIDs', desc: 'discord report (samuel [KC]): tracks of the same album sometimes carry different MUSICBRAINZ_ALBUMID tags, which causes navidrome to split the album into multiple entries. two-part fix: (1) the MBID Mismatch Detector now does a second scan that groups tracks by db album, finds the consensus (most-common) album mbid, and flags dissenters — fix action rewrites the dissenter\'s tag to match. catches existing inconsistencies in your library. (2) root cause: per-track musicbrainz release lookups went through an in-memory cache that\'s capped at 4096 entries and dies on server restart, so big libraries / restarts could resolve different release ids for tracks of the same album. added a persistent sqlite-backed cache so a release mbid resolved ONCE for an album applies to every future track of that album for the install\'s lifetime. strictly additive: any failure in the persistent layer falls through to the live musicbrainz lookup exactly as before.', page: 'library' }, diff --git a/webui/static/stats-automations.js b/webui/static/stats-automations.js index b413f1e7..53540d52 100644 --- a/webui/static/stats-automations.js +++ b/webui/static/stats-automations.js @@ -200,6 +200,8 @@ async function loadStatsData() { // DB storage chart (separate fetch — not part of cached stats) _loadDbStorageChart(); + // Library disk usage (separate fetch — populated by deep scan) + _loadLibraryDiskUsage(); // Recent plays _renderRecentPlays(data.recent || []); @@ -387,6 +389,70 @@ async function _loadDbStorageChart() { } } +async function _loadLibraryDiskUsage() { + try { + const resp = await fetch('/api/stats/library-disk-usage'); + const data = await resp.json(); + if (!data.success) return; + _renderLibraryDiskUsage(data); + } catch (e) { + console.debug('Library disk usage load failed:', e); + } +} + +function _formatBytes(n) { + if (!n || n <= 0) return '0 B'; + const units = ['B', 'KB', 'MB', 'GB', 'TB']; + let i = 0; + let v = n; + while (v >= 1024 && i < units.length - 1) { v /= 1024; i++; } + return `${v.toFixed(v < 10 ? 2 : 1)} ${units[i]}`; +} + +function _renderLibraryDiskUsage(data) { + const totalEl = document.getElementById('stats-disk-total-value'); + const metaEl = document.getElementById('stats-disk-total-meta'); + const formatsEl = document.getElementById('stats-disk-formats'); + if (!totalEl || !metaEl || !formatsEl) return; + + if (!data.has_data || !data.total_bytes) { + totalEl.textContent = '—'; + metaEl.textContent = data.tracks_without_size > 0 + ? `Run a Deep Scan to populate (${data.tracks_without_size.toLocaleString()} tracks pending)` + : 'No tracks in library yet'; + formatsEl.innerHTML = ''; + return; + } + + totalEl.textContent = _formatBytes(data.total_bytes); + + const withSize = data.tracks_with_size || 0; + const withoutSize = data.tracks_without_size || 0; + const trackBits = `${withSize.toLocaleString()} tracks measured`; + const pendingBits = withoutSize > 0 + ? ` (+${withoutSize.toLocaleString()} pending next Deep Scan)` + : ''; + metaEl.textContent = trackBits + pendingBits; + + // Per-format bars sorted by size descending. Skip if no breakdown. + const formats = Object.entries(data.by_format || {}).sort((a, b) => b[1] - a[1]); + if (!formats.length) { formatsEl.innerHTML = ''; return; } + + const max = formats[0][1] || 1; + formatsEl.innerHTML = formats.map(([ext, bytes]) => { + const pct = Math.max(2, Math.round((bytes / max) * 100)); + return ` +
+ ${ext.toUpperCase()} +
+
+
+ ${_formatBytes(bytes)} +
+ `; + }).join(''); +} + function _renderDbStorageChart(tables, totalFileSize, method) { const canvas = document.getElementById('stats-db-storage-chart'); if (!canvas || typeof Chart === 'undefined') return; diff --git a/webui/static/style.css b/webui/static/style.css index 9fc3a8cd..25ef3398 100644 --- a/webui/static/style.css +++ b/webui/static/style.css @@ -39449,6 +39449,72 @@ div.artist-hero-badge { text-align: right; } +/* Library Disk Usage */ +.stats-disk-usage-wrap { + display: flex; + flex-direction: column; + gap: 14px; + margin-top: 8px; +} + +.stats-disk-total-row { + display: flex; + align-items: baseline; + gap: 16px; + flex-wrap: wrap; +} + +.stats-disk-total-value { + font-size: 28px; + font-weight: 700; + color: rgb(var(--accent-rgb)); +} + +.stats-disk-total-meta { + font-size: 12px; + color: rgba(255, 255, 255, 0.55); +} + +.stats-disk-formats { + display: flex; + flex-direction: column; + gap: 6px; +} + +.stats-disk-format-row { + display: grid; + grid-template-columns: 60px 1fr 80px; + align-items: center; + gap: 10px; + font-size: 12px; +} + +.stats-disk-format-name { + font-weight: 600; + color: rgba(255, 255, 255, 0.8); +} + +.stats-disk-format-bar { + height: 8px; + background: rgba(255, 255, 255, 0.05); + border-radius: 4px; + overflow: hidden; +} + +.stats-disk-format-fill { + height: 100%; + background: linear-gradient(90deg, + rgb(var(--accent-rgb)) 0%, + rgba(var(--accent-rgb), 0.6) 100%); + border-radius: 4px; +} + +.stats-disk-format-size { + text-align: right; + color: rgba(255, 255, 255, 0.55); + font-variant-numeric: tabular-nums; +} + /* Database Storage Chart */ .stats-db-storage-wrap { display: flex;