soulsync/core/playlists/sources/lastfm.py
Broque Thomas 246503066b Fold provider-matching into PlaylistSource contract (Phase 1b)
Adds ``discover_tracks(tracks) -> List[NormalizedTrack]`` to the
PlaylistSource interface. Sources whose tracks already carry
provider IDs (Spotify, Tidal, Qobuz, YouTube, Deezer, Spotify
public, iTunes link, SoulSync Discovery) inherit a no-op default;
ListenBrainz + Last.fm override to run the matching engine.

This closes the last gap before LB / Last.fm / SoulSync Discovery
can land as Sync-page mirror sources: the refresh handler now
calls ``source.discover_tracks(...)`` whenever a source returns
tracks with ``needs_discovery=True``, so mirrored LB rows arrive
already discovered + ready for the sync pipeline. Previously, LB
playlists ran through a separate state-machine worker tied to the
Discover-page UI, with results stored in ``discovery_cache``
instead of ``mirrored_playlist_tracks.extra_data``.

Changes:

- ``core/playlists/sources/base.py`` — PlaylistSource switches from
  Protocol to ABC so a concrete default for ``discover_tracks``
  can live on the base class. The four real-work methods stay
  ``@abstractmethod``; instantiating an adapter that forgets one
  fails loudly at construction.
- ``core/discovery/matching.py`` (new) — pure ``match_mb_tracks``
  helper that runs Strategy-1-only matching-engine queries against
  Spotify (primary) or iTunes (fallback). No state machine, no
  discovery-cache writes, no wing-it stub — that richer flow stays
  in ``core/discovery/listenbrainz.py`` for the Discover-page UI.
- ``ListenBrainzPlaylistSource`` + ``LastFMPlaylistSource`` take
  an optional ``discover_callable`` constructor arg. Last.fm reuses
  the LB implementation since the track shape is identical.
- ``bootstrap.build_playlist_source_registry`` accepts a
  ``discover_callable`` kwarg and wires it into LB + Last.fm
  adapters.
- ``web_server.py`` boot constructs the discovery callable from the
  existing matching engine + ``_discovery_score_candidates`` +
  Spotify / iTunes clients, passes through to the registry.
- ``refresh_mirrored.py`` adds a small ``_maybe_discover`` helper
  that calls ``source.discover_tracks(...)`` between fetch and
  ``to_mirror_track_dict`` projection — only fires when at least
  one track has ``needs_discovery=True``, so the normal Spotify /
  Tidal / etc. refresh path stays a zero-cost pass-through.

Tests:

- 5 new adapter tests: default no-op pass-through, LB discovery
  with mixed matches/misses, LB no-callable fallback, Last.fm
  shares the LB implementation, mirror-dict spotify_hint emit.
- 1 new automation test: end-to-end LB refresh with a stub
  discover_callable proves the matched_data lands in
  ``mirror_playlist_tracks.extra_data`` after the registry
  refresh + discover hop.

225 tests across adapter + automation suites green.
2026-05-26 13:07:01 -07:00

134 lines
4.8 KiB
Python

"""Last.fm radio playlist source adapter.
Last.fm radio playlists are persisted by
``ListenBrainzManager.save_lastfm_radio_playlist`` under
``playlist_type='lastfm_radio'`` in the ``listenbrainz_playlists``
table — they share the same storage as ListenBrainz playlists but
originate from Last.fm's similar-tracks API.
Like ListenBrainz, tracks are MB metadata only, so ``needs_discovery``
is True on every track.
"""
from __future__ import annotations
from typing import Any, Callable, Dict, List, Optional
from core.playlists.sources.base import (
NormalizedTrack,
PlaylistDetail,
PlaylistMeta,
PlaylistSource,
SOURCE_LASTFM,
)
from core.playlists.sources.listenbrainz import (
DiscoverCallable,
ListenBrainzPlaylistSource,
)
LASTFM_PLAYLIST_TYPE = "lastfm_radio"
class LastFMPlaylistSource(PlaylistSource):
name = SOURCE_LASTFM
supports_listing = True
supports_refresh = False # Refresh requires re-running the radio generator
requires_auth = True
def __init__(
self,
manager_getter: Callable[[], Any],
discover_callable: Optional[DiscoverCallable] = None,
):
"""``manager_getter`` returns the profile's ``ListenBrainzManager``
(Last.fm radio playlists share that storage layer).
``discover_callable`` runs matching-engine + provider search;
Last.fm radio tracks are MB-metadata only, so this is needed
for ``discover_tracks`` to do real work."""
self._manager_getter = manager_getter
self._discover_callable = discover_callable
def _manager(self):
return self._manager_getter()
def is_authenticated(self) -> bool:
# Last.fm radio rows exist independently of any auth state —
# they're persisted snapshots. Treat "manager exists" as enough.
return self._manager() is not None
def list_playlists(self) -> List[PlaylistMeta]:
manager = self._manager()
if manager is None:
return []
try:
rows = manager.get_cached_playlists(LASTFM_PLAYLIST_TYPE) or []
except Exception:
rows = []
return [self._meta_from_cache_row(r) for r in rows]
def get_playlist(self, playlist_id: str) -> Optional[PlaylistDetail]:
manager = self._manager()
if manager is None:
return None
try:
rows = manager.get_cached_playlists(LASTFM_PLAYLIST_TYPE) or []
except Exception:
rows = []
meta_row = next(
(r for r in rows if str(r.get("playlist_mbid")) == str(playlist_id)),
None,
)
if meta_row is None:
return None
try:
tracks_raw = manager.get_cached_tracks(playlist_id) or []
except Exception:
tracks_raw = []
meta = self._meta_from_cache_row(meta_row)
meta.track_count = len(tracks_raw)
tracks = [self._track_from_cache_row(t, idx) for idx, t in enumerate(tracks_raw)]
return PlaylistDetail(meta=meta, tracks=tracks)
def refresh_playlist(self, playlist_id: str) -> Optional[PlaylistDetail]:
# Regenerating a Last.fm radio playlist needs the seed track +
# the Last.fm client — that lives outside this adapter. Phase 1
# wires up the regeneration; Phase 0 just returns the current
# snapshot.
return self.get_playlist(playlist_id)
# Discovery shares the LB adapter's implementation — same track
# shape (MB metadata), same matching needs.
discover_tracks = ListenBrainzPlaylistSource.discover_tracks
# ---- projection helpers ------------------------------------------------
def _meta_from_cache_row(self, row: Dict[str, Any]) -> PlaylistMeta:
return PlaylistMeta(
source=self.name,
source_playlist_id=str(row.get("playlist_mbid", "")),
name=row.get("title") or "Last.fm Radio",
owner=row.get("creator") or "Last.fm",
track_count=int(row.get("track_count", 0) or 0),
extra={
"annotation": row.get("annotation") or {},
"last_updated": row.get("last_updated"),
},
)
def _track_from_cache_row(self, row: Dict[str, Any], position: int) -> NormalizedTrack:
return NormalizedTrack(
position=position,
track_name=row.get("track_name", "Unknown Track"),
artist_name=row.get("artist_name", "Unknown Artist"),
album_name=row.get("album_name") or None,
duration_ms=int(row.get("duration_ms", 0) or 0),
source_track_id=row.get("recording_mbid") or None,
image_url=row.get("album_cover_url") or None,
needs_discovery=True,
extra={
"recording_mbid": row.get("recording_mbid"),
"release_mbid": row.get("release_mbid"),
},
)