generated from john/python-template
zoltan57
97b3d0fd62
Removes the duplicated registry CRUD, the hand-written not-found raises, and the three divergent media writers. Behavior is preserved: every existing Document Type and Person Role test passes unchanged, which is the primary proof for MED-11. [MED-11] Generic registry service - New services/registry.py owns RegistryService[ModelT]: list, list with counts, create with IntegrityError -> conflict mapping, read, update, delete with built-in and referenced guards, is_referenced, and label normalization/casefold keying. - DocumentTypeRegistry and PersonRoleRegistry declare only the model, error class, noun, short noun, retainer phrase, and reference columns. - DocumentService and PeopleService keep their public method names and delegate. Every user-facing message, error category, and suggestion string is reproduced verbatim; only the noun is templated. - Deleted _normalize_registry_label, _document_type_label_key, _normalize_role_label, _person_role_label_key, _document_type_is_referenced, and _person_role_is_referenced. [MED-12] Shared not-found lookup - ServiceBase._get_or_raise(model, id, *, session, error, noun, suggestion, options) loads by primary key or raises the caller's error type. - documents.py: local _get_document_or_raise deleted; replaced by _read_document and adopted at read_document, delete_document, and set_document_type, which previously bypassed the helper and hand-wrote the raise. - sources.py: 8 identical Source raises and 1 Job raise collapsed into _read_source / _get_or_raise. - jobs.py and people.py already funneled through local _not_found builders and were left alone. [MED-13][MED-01] Single media writer - New services/media_storage.py owns validate -> name -> mkdir -> write -> wrap OSError. The write runs in asyncio.to_thread, so uploads no longer block the event loop. - store_source_file, store_person_portrait, and store_homepage_image now share it and are async. Callers in store.py, people_page.py, and home_page.py await them. mkdir failures are now also translated to a domain error instead of escaping as a raw OSError. - homepage_store gains HomepageStorageError so its write reports like the others. [MED-14, partial] Service independence - New services/source_media.py owns SOURCE_MIME_TYPES, SOURCE_EXTENSIONS, lookup_source_mime_type, and supported_source_formats. - documents.py no longer imports services/sources.py. Its print projection uses the non-raising lookup and raises DocumentError, so DocumentService no longer emits a TranscriptionError. - api/v4_print.py imports the mapping from the policy module. - store.py and workflows.py still import sources.py; both are orchestration modules, which services.instructions.md:75-77 explicitly permits. - Splitting SourceService itself remains deferred to V4.7. [LOW-08] Query shape - list_sources_detail filters job_id with a JOIN on JobSource instead of loading every Source and filtering in Python. - read_source_navigation replaces the full ordered-id scan and .index() with two row-value comparisons bounded by LIMIT 1. - list_processing_artifacts gains the limit parameter its summary sibling already had. - build_evidence_export runs artifact integrity hashing and file reads through asyncio.to_thread. Tests - tests/test_service_boundaries.py: AST guard asserting no service module imports a sibling service module, plus a guard that the scan is non-empty. - tests/services/test_transcription_service.py: asserts the job_id filter emits a JOIN, and that navigation emits exactly two LIMIT queries. - tests/services/test_store.py: the two storage tests are now async. Verified: 276 passed, 4 skipped; ruff check clean.
58 lines
1.7 KiB
Python
58 lines
1.7 KiB
Python
"""Single implementation for persisting uploaded media bytes to disk.
|
|
|
|
Source pages, Person portraits, and homepage images all follow the same
|
|
sequence: resolve a target directory, create it, write the bytes, and translate
|
|
an ``OSError`` into a domain error. The write itself runs on a worker thread so
|
|
it never blocks the event loop.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import logging
|
|
from pathlib import Path
|
|
from uuid import uuid4
|
|
|
|
from ..errors import AppError
|
|
from ..errors import ErrorCategory
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def build_stored_filename(*, filename: str, filename_stem: str | None = None) -> str:
|
|
"""Return a safe stored filename preserving the submitted extension."""
|
|
safe_name = Path(filename).name
|
|
suffix = Path(safe_name).suffix.lower()
|
|
stem = filename_stem or str(uuid4())
|
|
return f"{stem}{suffix}"
|
|
|
|
|
|
async def write_media_bytes(
|
|
*,
|
|
target_dir: Path,
|
|
stored_name: str,
|
|
file_bytes: bytes,
|
|
error: type[AppError],
|
|
failure_message: str,
|
|
failure_suggestion: str,
|
|
log_label: str,
|
|
) -> Path:
|
|
"""Create ``target_dir`` and write ``file_bytes`` into it off the event loop."""
|
|
stored_path = target_dir / stored_name
|
|
try:
|
|
await asyncio.to_thread(_write, stored_path, file_bytes)
|
|
except OSError as exc:
|
|
raise error(
|
|
failure_message,
|
|
category=ErrorCategory.INFRA_PERSISTENT,
|
|
suggestion=failure_suggestion,
|
|
) from exc
|
|
|
|
logger.info("Stored %s: %s", log_label, stored_path)
|
|
return stored_path
|
|
|
|
|
|
def _write(stored_path: Path, file_bytes: bytes) -> None:
|
|
stored_path.parent.mkdir(parents=True, exist_ok=True)
|
|
stored_path.write_bytes(file_bytes)
|