Files
mcma-backend/app/application/import_service.py
T
Senko-san 48e3418c7f
Docker Build & Publish / build (push) Has been cancelled
Docker Build & Publish / push (push) Has been cancelled
Docker Build & Publish / Prune old image versions (push) Has been cancelled
feat(sources): local_folder source backend + import pipeline
First ingest path beyond manual upload (plan §1C). Source abstraction +
the first concrete backend, so a homelab can index an existing library.

- domain: SourceBackend/IndexableSource ports + SourceInfo/SourceFile shapes
- infrastructure/sources: LocalFolderSource (walks a mounted dir, idempotent
  source_id = relative path) + registry built from settings
- application: LibraryImportService — batch sibling of UploadService; dedup on
  (source, source_id), copy into storage, minimal track (metadata_status=pending,
  enrichment fills the rest in 1D), per-file failures isolated
- workers: scan_local_folder arq task (registered) + enqueue helper (503 if
  Redis down)
- api: GET /sources, POST /sources/{source}/scan (admin, enqueues), /health
- config: LOCAL_MEDIA_IMPORT_PATH; README + .env.example documented
- tests: scanner, registry, import service (fakes) + DB-gated sources API path

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-08 20:02:09 +03:00

97 lines
3.1 KiB
Python

"""LibraryImportService — imports files discovered by an indexable source.
Batch sibling of :class:`UploadService`: for each discovered file it dedups on
``(source, source_id)``, copies the file into managed storage, creates a minimal
track (artist ``Unknown Artist``, ``metadata_status=pending``), and leaves the
rest to enrichment (plan §6.2). Per-file failures are isolated — one bad file
must not abort the whole scan (graceful degradation).
"""
import contextlib
import uuid
from dataclasses import dataclass
from app.core.logging import get_logger
from app.domain.ports import ArtistRepository, FileStorage, IndexableSource, TrackRepository
from app.domain.sources import SourceFile
log = get_logger(__name__)
_UNKNOWN_ARTIST = "Unknown Artist"
@dataclass(frozen=True)
class ImportSummary:
source: str
seen: int
imported: int
skipped: int
failed: int
class LibraryImportService:
def __init__(
self,
*,
tracks: TrackRepository,
artists: ArtistRepository,
storage: FileStorage,
) -> None:
self._tracks = tracks
self._artists = artists
self._storage = storage
async def scan_and_import(
self, source: IndexableSource, *, added_by: uuid.UUID | None
) -> ImportSummary:
seen = imported = skipped = failed = 0
for file in source.scan():
seen += 1
try:
existing = await self._tracks.get_by_source(source.name, file.source_id)
if existing is not None:
skipped += 1
continue
await self._import_one(source.name, file, added_by)
imported += 1
except Exception:
failed += 1
log.warning("import_file_failed", source=source.name, source_id=file.source_id)
summary = ImportSummary(
source=source.name, seen=seen, imported=imported, skipped=skipped, failed=failed
)
log.info(
"import_complete",
source=summary.source,
seen=summary.seen,
imported=summary.imported,
skipped=summary.skipped,
failed=summary.failed,
)
return summary
async def _import_one(
self, source_name: str, file: SourceFile, added_by: uuid.UUID | None
) -> None:
track_id = uuid.uuid4()
key = f"tracks/{str(track_id)[:2]}/{track_id}.{file.file_format}"
await self._storage.save_file(key, file.path)
try:
artist = await self._artists.get_or_create(_UNKNOWN_ARTIST)
await self._tracks.add(
id=track_id,
title=file.suggested_title,
artist_id=artist.id,
storage_uri=key,
file_format=file.file_format,
file_size=file.file_size,
source=source_name,
source_id=file.source_id,
metadata_status="pending",
added_by=added_by,
)
except Exception:
with contextlib.suppress(Exception):
await self._storage.delete(key)
raise