feat(lyrics): LRCLIB provider + cached lyrics endpoints (§6.7)

GET /tracks/{id}/lyrics (get-or-fetch, caches found/not_found with a 7-day
miss TTL) and POST /tracks/{id}/lyrics/refetch (force). Hexagonal wiring:
LyricsProvider/LyricsRepository ports, LrclibHttpClient adapter (keyless,
degrades to not_found on error), SqlAlchemyLyricsRepository (upsert on the
existing lyrics table), LyricsService, LyricsOut schema, deps.py factory.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Цвылев Александр Вадимович
2026-07-28 20:58:28 +03:00
parent 048854f92a
commit 8271de34eb
9 changed files with 413 additions and 0 deletions
@@ -7,6 +7,7 @@ from app.infrastructure.db.repositories.download_job_repository import (
)
from app.infrastructure.db.repositories.history_repository import SqlAlchemyHistoryRepository
from app.infrastructure.db.repositories.like_repository import SqlAlchemyLikeRepository
from app.infrastructure.db.repositories.lyrics_repository import SqlAlchemyLyricsRepository
from app.infrastructure.db.repositories.playlist_repository import SqlAlchemyPlaylistRepository
from app.infrastructure.db.repositories.refresh_token_repository import (
SqlAlchemyRefreshTokenRepository,
@@ -23,6 +24,7 @@ __all__ = [
"SqlAlchemyDownloadJobRepository",
"SqlAlchemyHistoryRepository",
"SqlAlchemyLikeRepository",
"SqlAlchemyLyricsRepository",
"SqlAlchemyPlaylistRepository",
"SqlAlchemyRefreshTokenRepository",
"SqlAlchemyTrackRepository",
@@ -0,0 +1,72 @@
"""Lyrics repository — adapter over ``AsyncSession``.
One cached row per track (``track_id`` unique). ``upsert`` refreshes the row and
bumps ``fetched_at`` so the service's TTL is measured from the last fetch.
"""
import uuid
from sqlalchemy import func, select
from sqlalchemy.dialects.postgresql import insert as pg_insert
from sqlalchemy.ext.asyncio import AsyncSession
from app.domain.entities.lyrics import Lyrics
from app.infrastructure.db.models.lyrics import LyricsModel
def _to_entity(row: LyricsModel) -> Lyrics:
return Lyrics(
track_id=row.track_id,
synced=row.synced,
plain=row.plain,
source=row.source,
status=row.status,
fetched_at=row.fetched_at,
)
class SqlAlchemyLyricsRepository:
def __init__(self, session: AsyncSession) -> None:
self._session = session
async def get(self, track_id: uuid.UUID) -> Lyrics | None:
row = await self._session.scalar(
select(LyricsModel).where(LyricsModel.track_id == track_id)
)
return _to_entity(row) if row is not None else None
async def upsert(
self,
*,
track_id: uuid.UUID,
synced: str | None,
plain: str | None,
source: str | None,
status: str,
) -> Lyrics:
values = {
"track_id": track_id,
"synced": synced,
"plain": plain,
"source": source,
"status": status,
"fetched_at": func.now(),
}
stmt = (
pg_insert(LyricsModel)
.values(**values)
.on_conflict_do_update(
index_elements=[LyricsModel.track_id],
set_={
"synced": synced,
"plain": plain,
"source": source,
"status": status,
"fetched_at": func.now(),
},
)
.returning(LyricsModel)
)
row = (await self._session.scalars(stmt)).one()
await self._session.flush()
return _to_entity(row)
+100
View File
@@ -0,0 +1,100 @@
"""LrclibHttpClient — fetches lyrics from LRCLIB (plan §6.7).
LRCLIB is a free, keyless lyrics database. ``/api/get`` does an exact match on
artist+track+album+duration; if that misses we fall back to ``/api/search`` and
take the best-scoring hit. Graceful degradation: any network/parse error →
``fetch`` returns ``None`` (the service then caches a ``not_found``), never
raising. No API key is needed, so this provider is always "available".
"""
import httpx
from app.core.logging import get_logger
from app.domain.entities.lyrics import LyricsResult
log = get_logger(__name__)
_BASE_URL = "https://lrclib.net"
_TIMEOUT_SECONDS = 10.0
_SOURCE = "lrclib"
class LrclibHttpClient:
"""Implements :class:`app.domain.ports.LyricsProvider`."""
def __init__(self, *, user_agent: str, base_url: str = _BASE_URL) -> None:
self._user_agent = user_agent
self._base_url = base_url.rstrip("/")
async def fetch(
self,
*,
artist: str,
title: str,
album: str | None,
duration_seconds: int | None,
) -> LyricsResult | None:
try:
async with httpx.AsyncClient(
timeout=_TIMEOUT_SECONDS,
headers={"User-Agent": self._user_agent},
base_url=self._base_url,
) as client:
hit = await self._get(client, artist, title, album, duration_seconds)
if hit is None:
hit = await self._search(client, artist, title)
except (httpx.HTTPError, ValueError) as exc:
log.warning("lrclib.fetch_failed", error=str(exc))
return None
return hit
async def _get(
self,
client: httpx.AsyncClient,
artist: str,
title: str,
album: str | None,
duration_seconds: int | None,
) -> LyricsResult | None:
"""Exact match via ``/api/get`` (404 when nothing matches exactly)."""
params = {"artist_name": artist, "track_name": title}
if album:
params["album_name"] = album
if duration_seconds is not None:
params["duration"] = str(duration_seconds)
resp = await client.get("/api/get", params=params)
if resp.status_code == httpx.codes.NOT_FOUND:
return None
resp.raise_for_status()
return _to_result(resp.json())
async def _search(
self, client: httpx.AsyncClient, artist: str, title: str
) -> LyricsResult | None:
"""Fuzzy fallback via ``/api/search`` — take the first usable hit."""
resp = await client.get(
"/api/search", params={"artist_name": artist, "track_name": title}
)
resp.raise_for_status()
results = resp.json()
if not isinstance(results, list):
return None
for item in results:
result = _to_result(item)
if result is not None:
return result
return None
def _to_result(payload: object) -> LyricsResult | None:
"""Map an LRCLIB record to a ``LyricsResult``. Instrumental tracks and empty
records yield ``None`` (nothing worth caching as "found")."""
if not isinstance(payload, dict):
return None
if payload.get("instrumental"):
return None
synced = payload.get("syncedLyrics") or None
plain = payload.get("plainLyrics") or None
if synced is None and plain is None:
return None
return LyricsResult(synced=synced, plain=plain, source=_SOURCE)