mcma-backend/app/application/metadata_service.py

"""MetadataEnrichmentService — the §6.2 pipeline orchestrator.

Order (tag-first): embedded tags → Chromaprint fingerprint → AcoustID lookup.
Tags fix the common well-tagged case offline; AcoustID identifies the rest and
supplies a MusicBrainz id. The result updates the track and sets
``metadata_status`` to ``enriched`` (identity found) or ``failed`` (nothing).

Invariants (plan §6.2, CLAUDE.md):
- **Never touch ``manual``** — a user-edited track is returned untouched.
- **Graceful degradation** — every external step is wrapped; one failure (no
  fpcalc, no API key, service down) degrades the result, never crashes.
- **Idempotent** — re-running only fills gaps; ``apply_enrichment`` never erases.
"""

import tempfile
import uuid
from dataclasses import dataclass
from pathlib import Path

from app.core.logging import get_logger
from app.domain.entities.album import Album
from app.domain.entities.cover import CoverArt
from app.domain.entities.metadata import AudioTags, RecordingMatch
from app.domain.ports import (
    AcoustIdClient,
    AlbumRepository,
    ArtistRepository,
    AudioFingerprinter,
    AudioTagReader,
    CoverArtExtractor,
    CoverArtProvider,
    FileStorage,
    TrackRepository,
)

log = get_logger(__name__)

_UNKNOWN_ARTIST = "Unknown Artist"


@dataclass(frozen=True)
class EnrichmentResult:
    track_id: uuid.UUID
    status: str  # "enriched" | "failed" | "skipped"
    matched_mbid: str | None = None


class MetadataEnrichmentService:
    def __init__(
        self,
        *,
        tracks: TrackRepository,
        artists: ArtistRepository,
        albums: AlbumRepository,
        storage: FileStorage,
        tag_reader: AudioTagReader,
        fingerprinter: AudioFingerprinter,
        acoustid: AcoustIdClient,
        cover_extractor: CoverArtExtractor | None = None,
        cover_provider: CoverArtProvider | None = None,
        acoustid_trust_score: float = 0.85,
    ) -> None:
        self._tracks = tracks
        self._artists = artists
        self._albums = albums
        self._storage = storage
        self._tag_reader = tag_reader
        self._fingerprinter = fingerprinter
        self._acoustid = acoustid
        self._cover_extractor = cover_extractor
        self._cover_provider = cover_provider
        self._acoustid_trust_score = acoustid_trust_score

    async def enrich(self, track_id: uuid.UUID) -> EnrichmentResult:
        track = await self._tracks.get_by_id(track_id)
        if track is None:
            log.info("enrich_track_missing", track_id=str(track_id))
            return EnrichmentResult(track_id=track_id, status="skipped")
        if track.metadata_status == "manual":
            log.info("enrich_skip_manual", track_id=str(track_id))
            return EnrichmentResult(track_id=track_id, status="skipped")
        storage_uri = track.storage_uri
        if storage_uri is None:
            log.info("enrich_skip_remote", track_id=str(track_id))
            return EnrichmentResult(track_id=track_id, status="skipped")

        tags = await self._read_local(storage_uri)
        match = await self._identify(storage_uri)

        # Merge order is tag-first by default — embedded tags fix the common
        # well-tagged offline case. But a *high-confidence* AcoustID match is the
        # more trustworthy identity (downloaded files routinely carry junk tags
        # like "Music Track"/"Sound_12345"), so above the trust threshold the
        # acoustic match wins for the identity fields and tags become fallback.
        tag_title = tags.title if tags else None
        tag_artist = tags.artist if tags else None
        tag_album = tags.album if tags else None
        match_title = match.title if match else None
        match_artist = match.artist if match else None
        match_album = match.album if match else None
        match_year = match.year if match else None
        tag_year = tags.year if tags else None
        trust_match = match is not None and match.score >= self._acoustid_trust_score

        if trust_match:
            title = _opt_str(match_title, tag_title) or track.title
            artist_name = _opt_str(match_artist, tag_artist)
            album_title = _opt_str(match_album, tag_album)
            year = _first_int(match_year, tag_year)
        else:
            title = _opt_str(tag_title, match_title) or track.title
            artist_name = _opt_str(tag_artist, match_artist)
            album_title = _opt_str(tag_album, match_album)
            year = _first_int(tag_year, match_year)
        genre = tags.genre if tags else None
        track_number = tags.track_number if tags else None
        duration = _first_int(
            tags.duration_seconds if tags else None,
            track.duration_seconds,
        )
        bitrate = tags.bitrate if tags else None
        mbid = match.recording_mbid if match else None
        acoustid_id = match.acoustid if match else None

        artist_id = await self._resolve_artist(artist_name, fallback=track.artist_id)
        album = await self._resolve_album(album_title, artist_id=artist_id, year=year, mbid=mbid)
        album_id = album.id if album is not None else None

        if album is not None:
            await self._resolve_cover(
                album,
                storage_uri=storage_uri,
                release_group_mbid=match.release_group_mbid if match else None,
            )

        identified = bool(artist_name) or album_id is not None or mbid is not None
        status = "enriched" if identified else "failed"
        # On a clean "no identity" outcome, record *why* so the UI shows a reason
        # rather than a bare "failed". A successful run clears any prior error.
        metadata_error = None if identified else self._no_match_reason()

        await self._tracks.apply_enrichment(
            track_id,
            title=title,
            artist_id=artist_id,
            album_id=album_id,
            genre=genre,
            year=year,
            track_number=track_number,
            duration_seconds=duration,
            bitrate=bitrate,
            acoustid_fingerprint=acoustid_id,
            musicbrainz_id=mbid,
            metadata_status=status,
            metadata_error=metadata_error,
        )
        log.info("enrich_complete", track_id=str(track_id), status=status, mbid=mbid)
        return EnrichmentResult(track_id=track_id, status=status, matched_mbid=mbid)

    def _no_match_reason(self) -> str:
        """Explain a ``failed`` (no-identity) run in terms a user can act on:
        which optional identification step was unavailable, if any."""
        if not self._fingerprinter.is_available():
            return "No metadata match: audio fingerprinting (fpcalc) is unavailable."
        if not self._acoustid.is_available():
            return "No metadata match: AcoustID lookup is unavailable (no API key)."
        return "No metadata match found in tags or AcoustID."

    async def find_matches(self, track_id: uuid.UUID) -> list[RecordingMatch]:
        """AcoustID candidates for the metadata editor's match picker (§A7).

        Read-only — unlike :meth:`enrich`, never touches the track. Runs
        inline (single track, user-triggered) rather than via the worker.
        Degrades to ``[]`` whenever fingerprinting/AcoustID is unavailable or
        the file can't be read, same as the enrichment pipeline.
        """
        track = await self._tracks.get_by_id(track_id)
        if track is None:
            return []
        if not self._acoustid.is_available() or not self._fingerprinter.is_available():
            return []
        if track.storage_uri is None:
            return []
        try:
            async with self._storage.as_local_path(track.storage_uri) as path:
                fingerprint = await self._fingerprinter.calculate(path)
            if fingerprint is None:
                return []
            return await self._acoustid.lookup_all(fingerprint)
        except Exception:
            log.warning("find_matches_failed", track_id=str(track_id))
            return []

    async def _read_local(self, storage_uri: str) -> AudioTags | None:
        try:
            async with self._storage.as_local_path(storage_uri) as path:
                return await self._tag_reader.read(path)
        except Exception:
            log.warning("enrich_tag_step_failed", storage_uri=storage_uri)
            return None

    async def _identify(self, storage_uri: str) -> RecordingMatch | None:
        if not self._acoustid.is_available() or not self._fingerprinter.is_available():
            return None
        try:
            async with self._storage.as_local_path(storage_uri) as path:
                fingerprint = await self._fingerprinter.calculate(path)
            if fingerprint is None:
                return None
            return await self._acoustid.lookup(fingerprint)
        except Exception:
            log.warning("enrich_identify_step_failed", storage_uri=storage_uri)
            return None

    async def _resolve_artist(self, name: str | None, *, fallback: uuid.UUID) -> uuid.UUID:
        if not name or name == _UNKNOWN_ARTIST:
            return fallback
        artist = await self._artists.get_or_create(name)
        return artist.id

    async def _resolve_album(
        self,
        title: str | None,
        *,
        artist_id: uuid.UUID,
        year: int | None,
        mbid: str | None,
    ) -> Album | None:
        if not title:
            return None
        return await self._albums.get_or_create(
            title=title,
            artist_id=artist_id,
            year=year,
            musicbrainz_id=mbid,
        )

    async def _resolve_cover(
        self,
        album: Album,
        *,
        storage_uri: str,
        release_group_mbid: str | None,
    ) -> None:
        """Fill in an album cover when it has none. Source order mirrors the
        tag-first pipeline: embedded artwork (offline) → Cover Art Archive
        (network, by release-group). Best-effort — any failure is swallowed so a
        missing cover never affects enrichment status."""
        if album.cover_path:
            return  # already has one — never overwrite (idempotent)

        cover = await self._extract_cover(storage_uri)
        if cover is None:
            cover = await self._fetch_cover(release_group_mbid)
        if cover is None:
            return

        try:
            key = await self._save_cover(album.id, cover)
            await self._albums.set_cover_path(album.id, key)
            log.info("cover_resolved", album_id=str(album.id), content_type=cover.content_type)
        except Exception:
            log.warning("cover_save_failed", album_id=str(album.id))

    async def _extract_cover(self, storage_uri: str) -> CoverArt | None:
        if self._cover_extractor is None:
            return None
        try:
            async with self._storage.as_local_path(storage_uri) as path:
                return await self._cover_extractor.extract(path)
        except Exception:
            log.warning("cover_extract_step_failed", storage_uri=storage_uri)
            return None

    async def _fetch_cover(self, release_group_mbid: str | None) -> CoverArt | None:
        if self._cover_provider is None or not release_group_mbid:
            return None
        if not self._cover_provider.is_available():
            return None
        try:
            return await self._cover_provider.fetch_release_group(release_group_mbid)
        except Exception:
            log.warning("cover_fetch_step_failed", release_group=release_group_mbid)
            return None

    async def _save_cover(self, album_id: uuid.UUID, cover: CoverArt) -> str:
        key = f"covers/{album_id}.{cover.extension}"
        with tempfile.NamedTemporaryFile(suffix=f".{cover.extension}") as tmp:
            tmp.write(cover.data)
            tmp.flush()
            await self._storage.save_file(key, Path(tmp.name))
        return key


def _opt_str(*values: str | None) -> str | None:
    for value in values:
        if value:
            return value
    return None


def _first_int(*values: int | None) -> int | None:
    for value in values:
        if value is not None:
            return value
    return None