Jonathan
06e7f91897
MusicBrainz search returns release-groups tied on title similarity in an arbitrary order; `max(groups, key=_ratio)` kept the first, so Michael Jackson's "Off the Wall" resolved to the 2-track *single* release-group (Off the Wall / Get on the Floor) instead of the 10-track album. Because plan_track_names labels files purely by position, that short tracklist got mapped onto the full album — track 2 became "Get on the Floor" instead of "Rock with You", and the real "Off the Wall"/"Get on the Floor" files kept their streamrip names, yielding duplicate titles. Extract selection into a pure `_best_release_group()` that breaks title- similarity ties toward primary-type == "Album". Similarity still dominates; album preference only settles ties. Live-verified: Off the Wall now resolves to the 10-track album with track 2 = "Rock With You". Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
97 lines
3.6 KiB
Python
97 lines
3.6 KiB
Python
from difflib import SequenceMatcher
|
|
|
|
from lyra_worker.types import MBTarget
|
|
|
|
_MIN_TITLE_RATIO = 0.6
|
|
|
|
|
|
def _ratio(a: str, b: str) -> float:
|
|
return SequenceMatcher(None, a.strip().casefold(), b.strip().casefold()).ratio()
|
|
|
|
|
|
def _is_album(g: dict) -> bool:
|
|
return (g.get("primary-type") or "").casefold() == "album"
|
|
|
|
|
|
def _best_release_group(album: str, groups: list) -> dict | None:
|
|
"""Choose the best release-group match for `album`. Highest title similarity wins;
|
|
an Album primary-type breaks ties so a famous album (e.g. Michael Jackson's "Off the
|
|
Wall") isn't resolved to its same-named single, whose short tracklist would then be
|
|
mapped positionally onto the full album's files. Returns None below the title threshold.
|
|
Pure — no network I/O."""
|
|
if not groups:
|
|
return None
|
|
best = max(groups, key=lambda g: (_ratio(album, g.get("title", "")), _is_album(g)))
|
|
if _ratio(album, best.get("title", "")) < _MIN_TITLE_RATIO:
|
|
return None
|
|
return best
|
|
|
|
|
|
class MusicBrainzResolver:
|
|
"""Real MbResolver using the MusicBrainz webservice via musicbrainzngs.
|
|
|
|
NOT unit-tested offline; see test_musicbrainz_live.py. musicbrainzngs is
|
|
imported lazily so importing/constructing this class stays offline.
|
|
"""
|
|
|
|
def __init__(self, app_name: str = "Lyra", version: str = "0.1", contact: str = "lyra@localhost"):
|
|
self._app = app_name
|
|
self._version = version
|
|
self._contact = contact
|
|
|
|
def resolve(self, artist: str, album: str) -> MBTarget | None:
|
|
import musicbrainzngs
|
|
|
|
musicbrainzngs.set_useragent(self._app, self._version, self._contact)
|
|
|
|
res = musicbrainzngs.search_release_groups(query=album, artist=artist, limit=5)
|
|
groups = res.get("release-group-list", [])
|
|
rg = _best_release_group(album, groups)
|
|
if rg is None:
|
|
return None
|
|
|
|
canonical_album = rg.get("title", album)
|
|
canonical_artist = artist
|
|
artist_mbid = ""
|
|
credit = rg.get("artist-credit")
|
|
if isinstance(credit, list) and credit and isinstance(credit[0], dict):
|
|
_artist = credit[0].get("artist") or {}
|
|
canonical_artist = _artist.get("name", artist)
|
|
artist_mbid = _artist.get("id", "") or ""
|
|
|
|
year = None
|
|
frd = rg.get("first-release-date", "") or ""
|
|
if frd[:4].isdigit():
|
|
year = int(frd[:4])
|
|
|
|
track_count = None
|
|
total_duration_s = None
|
|
titles: tuple[str, ...] = ()
|
|
rgid = rg.get("id")
|
|
if rgid:
|
|
rgfull = musicbrainzngs.get_release_group_by_id(rgid, includes=["releases"])
|
|
releases = rgfull.get("release-group", {}).get("release-list", [])
|
|
if releases:
|
|
rel = musicbrainzngs.get_release_by_id(
|
|
releases[0]["id"], includes=["recordings"]
|
|
).get("release", {})
|
|
tracks = []
|
|
for medium in rel.get("medium-list", []):
|
|
tracks.extend(medium.get("track-list", []))
|
|
if tracks:
|
|
track_count = len(tracks)
|
|
total_ms = sum(int((t.get("recording") or {}).get("length") or 0) for t in tracks)
|
|
total_duration_s = total_ms // 1000 if total_ms else None
|
|
titles = tuple((t.get("recording") or {}).get("title", "") for t in tracks)
|
|
|
|
return MBTarget(
|
|
artist=canonical_artist,
|
|
album=canonical_album,
|
|
track_count=track_count,
|
|
total_duration_s=total_duration_s,
|
|
year=year,
|
|
tracklist=titles,
|
|
rg_mbid=rg.get("id", "") or "",
|
|
artist_mbid=artist_mbid,
|
|
)
|