soulsync/core/playlists/sources/youtube.py
Broque Thomas 8c41b05fe8 Refactor refresh_mirrored to use unified PlaylistSource registry
Phase 1a of the Discover-to-Sync unification. The mirrored-playlist
refresh handler used to branch per-source through a ~190-line
if/elif chain (Spotify, Spotify public, Deezer, Tidal, YouTube).
Each branch hand-built its own ``extra_data`` JSON for the matched-
data block. With every new source we considered for Sync-page mirror
support (ListenBrainz, Last.fm radio, SoulSync Discovery, iTunes
link), that chain would have grown a new elif.

This commit lifts the per-source logic into the existing adapter
layer and collapses the dispatch to a registry lookup:

- ``core/playlists/sources/deezer.py`` — new adapter so the registry
  covers every source the refresh handler previously branched on.
- ``core/playlists/sources/bootstrap.py`` — single helper that builds
  a populated registry from injected getter callables. Both
  ``web_server.py`` boot and the automation test fixtures call it,
  so the two construction paths can't drift.
- ``core/playlists/sources/base.py`` — ``to_mirror_track_dict``
  projection helper centralises the NormalizedTrack → DB-row
  conversion (including the discovered/matched_data and
  spotify_hint extra_data shapes the downstream sync + wishlist
  consumers already expect).
- Spotify adapter now populates ``extra['discovered']`` + an
  ``extra['matched_data']`` block when fetching via the authed API,
  so Spotify mirrors keep landing pre-discovered (matches the
  pre-refactor contract pinned by
  ``test_spotify_refresh_writes_to_db``).
- Spotify-public adapter populates ``extra['spotify_hint']`` so the
  discovery worker can skip its search step and jump straight to
  enrichment for the known track ID.
- All artist-name fields now project to first-artist-only across
  every adapter — matches the pre-refactor mirror_playlist DB shape
  (``t.artists[0]``).

``refresh_mirrored.py`` shrinks ~190 → ~80 lines and keeps:

- the file/beatport unrefreshable-source filter,
- URL extraction from ``description`` via ``require_refresh_url``
  for spotify_public + youtube,
- the Spotify-public → authed-Spotify fallback when the user is
  signed in (handler-level branch, not in any adapter),
- the Tidal-not-authenticated soft-skip log (skip, not error),
- existing-extra_data preservation across refreshes,
- the ``playlist_changed`` automation event emit on track-set delta.

Test scaffolding:

- ``_build_deps`` in ``tests/automation/test_handlers_playlist.py``
  now builds a default registry from the passed clients via
  ``build_playlist_source_registry``, so existing refresh tests
  exercise the same path without per-test changes. New tests cover
  Tidal-not-authed soft-skip, Deezer refresh writes plain tracks,
  YouTube refresh reads URL from description, and Spotify-public
  uses authed Spotify when signed in.
- 4 new adapter tests for Deezer projection +
  ``to_mirror_track_dict`` (minimal track, Spotify matched_data,
  Spotify-public spotify_hint).
- ``playlist_source_registry`` field on ``AutomationDeps`` defaults
  to ``None`` so the other 5 automation test files (which don't
  exercise refresh_mirrored) keep working unchanged.

220 tests across automation + adapter suites green.
2026-05-26 12:52:39 -07:00

87 lines
3 KiB
Python

"""YouTube playlist source adapter.
Wraps ``parse_youtube_playlist`` (currently a free function in
``web_server.py`` — Phase 0 doesn't move it, just calls it via an
injected callable to avoid the circular import). ``supports_listing``
is False — YouTube playlists are URL-input only, no user library.
"""
from __future__ import annotations
import hashlib
from typing import Any, Callable, List, Optional
from core.playlists.sources.base import (
NormalizedTrack,
PlaylistDetail,
PlaylistMeta,
PlaylistSource,
SOURCE_YOUTUBE,
)
class YouTubePlaylistSource(PlaylistSource):
name = SOURCE_YOUTUBE
supports_listing = False
supports_refresh = True
requires_auth = False
def __init__(self, parser: Callable[[str], Optional[dict]]):
"""``parser`` matches the signature of ``parse_youtube_playlist``
in web_server.py — takes a URL, returns the playlist dict or
``None``. Injected so adapter can be constructed at import time."""
self._parser = parser
def is_authenticated(self) -> bool:
return True
def list_playlists(self) -> List[PlaylistMeta]:
return []
def get_playlist(self, playlist_id: str) -> Optional[PlaylistDetail]:
"""``playlist_id`` is the full YouTube playlist URL."""
data = self._parser(playlist_id)
if not data:
return None
source_url = data.get("url") or playlist_id
url_hash = hashlib.md5(source_url.encode()).hexdigest()[:12]
tracks_raw = data.get("tracks") or []
meta = PlaylistMeta(
source=self.name,
source_playlist_id=url_hash,
name=data.get("name", "YouTube Playlist"),
track_count=int(data.get("track_count", len(tracks_raw))),
image_url=data.get("image_url") or None,
source_url=source_url,
extra={
"youtube_playlist_id": data.get("id"),
},
)
tracks = [self._track_from_yt(t, idx) for idx, t in enumerate(tracks_raw) if t]
return PlaylistDetail(meta=meta, tracks=tracks)
def refresh_playlist(self, playlist_id: str) -> Optional[PlaylistDetail]:
return self.get_playlist(playlist_id)
# ---- projection helpers ------------------------------------------------
def _track_from_yt(self, track: dict, position: int) -> NormalizedTrack:
artists = track.get("artists") or []
artist_name = artists[0] if artists else "Unknown Artist"
return NormalizedTrack(
position=position,
track_name=track.get("name", "Unknown Track"),
artist_name=artist_name,
album_name=None,
duration_ms=int(track.get("duration_ms", 0) or 0),
source_track_id=str(track.get("id", "")),
needs_discovery=False,
extra={
"url": track.get("url"),
"raw_title": track.get("raw_title"),
"raw_artist": track.get("raw_artist"),
},
)