Files
shelfmark/tests/download/test_postprocess_scan_archives.py
T
splitsec2 9011319ade refactor: one lookup for the supported formats, public names for two shared helpers (#1576)
Six places read the Supported Book Formats and Supported Audiobook
Formats settings on their own: post-processing, the post-process scan,
IRC, slskd, Prowlarr and direct download. For ebooks they already
agreed, since they all fall back to `DEFAULT_EBOOK_FORMATS`. For
audiobooks they did not. The settings registry and slskd fall back to
every audio format plus zip and rar, while post-processing and IRC fell
back to m4b and mp3 only.

They now share `shelfmark/core/formats.py`, with
`get_supported_formats`, `get_supported_audiobook_formats` and a
content-type aware `get_supported_formats_for`, and a shared
`DEFAULT_AUDIOBOOK_FORMATS` in `core/utils.py` next to the ebook one.
`policy.py` re-exports the same functions, so nothing that imports them
from there changes. It is not in `policy.py` itself because importing
the `postprocess` package pulls in the router, which imports the release
sources, so a source could not import from it without a cycle.

One behaviour difference, and only in the fallback: with the audiobook
setting unset, or emptied, post-processing and IRC used to accept m4b
and mp3 and now accept the full default list like slskd and the settings
page already did. A configured list is read exactly as before. Direct
download's own helper used the raw configured list and now reads the
same normalized one, which is identical for any list the settings page
can save.

Also public now: `parse_size` in the Prowlarr source (slskd and Newznab
imported it with the underscore) and
`coerce_completed_path_timeout_seconds` in the client base handler
(slskd imported that too).

Not changed on purpose: slskd's `_coerce_int` looks like a copy of
`coerce_int` but is not. It reads `"12.0"` as 12 and `True` as 0, where
`coerce_int` gives 0 and 1. And the `_parse_size` in the IRC source is a
different function, string to bytes.

Tests: a new set checks that post-processing, IRC and slskd all fall
back to the shared defaults and that the settings default is the shared
one, and the scan-archive and IRC tests now patch the shared config
instead of the per-module copies. Full suite passes.
2026-10-24 16:31:07 -06:00

104 lines
3.3 KiB
Python

from __future__ import annotations
import zipfile
from shelfmark.core import formats as formats_mod
from shelfmark.core.models import DownloadTask
from shelfmark.core.utils import DEFAULT_AUDIOBOOK_FORMATS
from shelfmark.download import archive as archive_mod
from shelfmark.download.postprocess import scan as scan_mod
# The shipped default for SUPPORTED_AUDIOBOOK_FORMATS, which includes archives.
_DEFAULT_AUDIOBOOK_FORMATS = list(DEFAULT_AUDIOBOOK_FORMATS)
def _audiobook_task() -> DownloadTask:
return DownloadTask(task_id="t", source="audiobookbay", title="Test", content_type="audiobook")
def _use_default_audiobook_formats(monkeypatch, tmp_path) -> None:
monkeypatch.setattr(
formats_mod, "get_supported_audiobook_formats", lambda: list(_DEFAULT_AUDIOBOOK_FORMATS)
)
monkeypatch.setattr(
archive_mod, "get_supported_audiobook_formats", lambda: list(_DEFAULT_AUDIOBOOK_FORMATS)
)
staging = tmp_path / "staging"
def build_staging_dir(prefix, _task_id):
path = staging / str(prefix)
path.mkdir(parents=True, exist_ok=True)
return path
monkeypatch.setattr(scan_mod, "build_staging_dir", build_staging_dir)
def _write_series_zip(directory):
directory.mkdir()
archive = directory / "Series - Books 1-3.zip"
with zipfile.ZipFile(archive, "w") as zf:
for n in (1, 2, 3):
zf.writestr(f"Series/Book {n}/Book {n}.mp3", b"audio")
return archive
def test_archive_is_not_counted_as_book_file(tmp_path, monkeypatch) -> None:
_use_default_audiobook_formats(monkeypatch, tmp_path)
download = tmp_path / "download"
archive = _write_series_zip(download)
book_files, _rejected, archive_files, error = scan_mod.scan_directory_tree(
download, "audiobook"
)
assert error is None
assert book_files == []
assert archive_files == [archive]
def test_archive_is_extracted_with_default_audiobook_formats(tmp_path, monkeypatch) -> None:
_use_default_audiobook_formats(monkeypatch, tmp_path)
download = tmp_path / "download"
_write_series_zip(download)
files, _rejected, _cleanup, error = scan_mod.collect_directory_files(
download,
_audiobook_task(),
allow_archive_extraction=True,
)
assert error is None
assert sorted(f.name for f in files) == ["Book 1.mp3", "Book 2.mp3", "Book 3.mp3"]
def test_archive_imported_as_is_when_extraction_disabled(tmp_path, monkeypatch) -> None:
_use_default_audiobook_formats(monkeypatch, tmp_path)
download = tmp_path / "download"
archive = _write_series_zip(download)
files, _rejected, _cleanup, error = scan_mod.collect_directory_files(
download,
_audiobook_task(),
allow_archive_extraction=False,
)
assert error is None
assert files == [archive]
def test_loose_audio_still_preferred_over_archives(tmp_path, monkeypatch) -> None:
_use_default_audiobook_formats(monkeypatch, tmp_path)
download = tmp_path / "download"
_write_series_zip(download)
loose = download / "Book.m4b"
loose.write_bytes(b"audio")
files, _rejected, _cleanup, error = scan_mod.collect_directory_files(
download,
_audiobook_task(),
allow_archive_extraction=True,
)
assert error is None
assert files == [loose]