From 941d1a135dd7b03834576855e8e9fdaa24c4e406 Mon Sep 17 00:00:00 2001 From: Christophe Besson Date: Mon, 24 Aug 2026 17:12:36 +0200 Subject: feat(node): Music app node-side — indexing, MusicBrainz enrichment, protocol MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Implements the node half of docs/musicbay.md against MNP 0.8: - IndexEntry gains artist/album/track_no (reuses duration/thumb_hash/ display_title, already generic). New musicbrainz_config/_enabled and music_meta_req/_resp message pairs, mirroring the TMDB shape. - title_parse.parse_track_filename: track-number-prefix + title parsing, fallback-only (embedded tags are the primary source, unlike Videos). - indexer.enrich_audio.AudioEnricher: mutagen-based tag/embedded-cover extraction through its own bounded pool (asyncio.to_thread, no subprocess — no ffmpeg-shaped deadlock risk). Gated on "music" in a group's enabled_apps rather than a video_root-style scoped folder. - musicbrainz.py: MusicBrainzClient — no API key (unlike TMDB), just a self-imposed ~1 req/s pace and a configurable, non-default User-Agent contact string; inert (no calls at all) when no contact is configured, never sends an unidentified client. - media_cache.py: file_mbid/mbid_meta tables alongside the existing TMDB ones, cover art reusing the thumbs table via a synthetic musicbrainz:{mbid} id, pruned on file deletion. - roster.py/ops.py/webrtc_server.py: musicbrainz_contact (node-wide) and musicbrainz_enabled (per-group, from the start) as signed operator settings, ALLOWED_APPS gains "music", _do_music_meta_request resolves and caches a release-level MusicBrainz match per (artist, album). - daemon.py: AudioEnricher/MusicBrainzClient wired alongside the video ones; a group's existing library is swept when "music" is newly enabled (no video_root equivalent — see musicbay.md §2.1). 41 new tests (musicbrainz.py against a mocked transport, admin-op policy for both new settings, media_cache round-trip/pruning, enrich_audio end-to-end against real ffmpeg-generated MP3s). Full suite (common + node + hub): 1116 passed, no regressions. Client-side (music-app.js, persistent player bar) not started yet. Co-Authored-By: Claude Sonnet 5 Claude-Session: https://claude.ai/code/session_01KBi7ALLGfwcjBXt57yNMcy --- .../src/meshbay_node/indexer/title_parse.py | 41 ++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'packages/meshbay-node/src/meshbay_node/indexer/title_parse.py') diff --git a/packages/meshbay-node/src/meshbay_node/indexer/title_parse.py b/packages/meshbay-node/src/meshbay_node/indexer/title_parse.py index ef522ad..6676e9b 100644 --- a/packages/meshbay-node/src/meshbay_node/indexer/title_parse.py +++ b/packages/meshbay-node/src/meshbay_node/indexer/title_parse.py @@ -146,6 +146,47 @@ def parse_movie_filename(filename: str) -> ParsedName: ) + +# ── Music app (docs/musicbay.md §2.1) ──────────────────────────────────────── +# +# Filename parsing is the *fallback* here, not the primary source (unlike +# Videos, where guessit does all the work): embedded ID3/Vorbis tags are read +# first by enrich_audio.py, and this only fills whatever a tag left empty. +# Scope is narrower than the video parser too — a track number and a title, +# nothing guessit-shaped is needed since there is no season/episode grammar +# to parse. + +# "01 - Venus As A Boy.mp3", "03. Human Behaviour.mp3", "12_Some_Title.mp3" — +# a leading track number, optionally disc-prefixed ("1-01 "), then a +# separator before the title. Capped at 3 digits so a filename that merely +# starts with a year ("1999 - Some Title.mp3") isn't misread as track 199. +_TRACK_PREFIX_RE = re.compile(r"^(?:\d+[\s._-]+)?(\d{1,3})[\s._-]+(?=\S)") + + +@dataclass +class ParsedTrack: + title: str | None + track_no: int | None + naive_title: str = "" + + +def parse_track_filename(filename: str) -> ParsedTrack: + """ + Split a leading track-number prefix from the rest of the filename and + clean up the remainder into a title. `track_no` is None when there's no + recognizable prefix — the caller (enrich_audio.py) then falls back to + the tag or leaves it unset, never guesses a number. + """ + stem = filename.rsplit(".", 1)[0] if "." in filename else filename + m = _TRACK_PREFIX_RE.match(stem) + track_no = int(m.group(1)) if m else None + rest = stem[m.end():] if m else stem + rest = re.sub(r"[._]+", " ", rest) + rest = re.sub(r"^[\s-]+", "", rest) # a leftover " - " separator + title = re.sub(r"\s+", " ", rest).strip() or None + return ParsedTrack(title=title, track_no=track_no, naive_title=naive_title(filename)) + + def parse_episode_filename(filename: str) -> ParsedName: """ Parse an episode filename. `display_title` may come back None (e.g. -- cgit v1.2.3