Files
alfred/tests/domain/test_release_fixtures.py
T
francwa 3737f66851 refactor(release): simplify SHITTY to dict-driven token tagging
Replace the ~480-line legacy heuristic block in services.py with a
small dict-driven pass in pipeline._annotate_shitty: each token is
looked up against the kb buckets (resolutions / sources / codecs /
distributors / year / sxxexx) with first-match-wins semantics, the
leftmost contiguous UNKNOWN run becomes the title, done.

SHITTY's scope is intentionally narrow — releases that *look* like
scene names but don't have a registered group schema. Anything more
exotic (parenthesized tech, bare-dashed title fragments, YT slugs,
franchise boxes) is PATH OF PAIN territory and stays out of here.

- annotate() no longer returns None; SHITTY is the always-on fallback
- services.py shrunk from ~525 to ~85 lines (legacy extractors gone)
- 4 fixtures get xfail markers documenting PoP-grade pathologies
  (deutschland franchise box, sleaford YT slug, super_mario bilingual,
  predator space-separators — the last one moved from shitty/ → pop/)
- ReleaseFixture grows xfail_reason; the parametrized suite wires the
  pytest.mark.xfail(strict=False) automatically
2026-05-20 01:03:25 +02:00

65 lines
2.6 KiB
Python

"""Real-world release fixtures — anti-regression baseline for parse_release.
Each fixture under ``tests/fixtures/releases/<bucket>/<case>/expected.yaml``
declares a release name and the ``ParsedRelease`` fields it should produce.
Fields absent from the fixture's ``parsed`` block are not checked, so adding
new attributes to ``ParsedRelease`` never breaks existing fixtures.
The fixture's ``tree`` is materialized into a temp dir to prove the layout is
self-consistent, even though no filesystem assertions are made yet. The
``routing`` block (library / torrents / seed_hardlinks) is captured ahead of
the ``organize_media`` refactor — it will become verifiable once the planner
exists.
"""
from __future__ import annotations
from dataclasses import asdict
import pytest
from alfred.domain.release.services import parse_release
from alfred.infrastructure.knowledge.release_kb import YamlReleaseKnowledge
from tests.fixtures.releases.conftest import ReleaseFixture, discover_fixtures
_KB = YamlReleaseKnowledge()
FIXTURES = discover_fixtures()
def _fixture_param(f: ReleaseFixture) -> pytest.param:
marks = []
if f.xfail_reason:
marks.append(pytest.mark.xfail(reason=f.xfail_reason, strict=False))
return pytest.param(f, id=f.name, marks=marks)
@pytest.mark.parametrize(
"fixture",
[_fixture_param(f) for f in FIXTURES],
)
def test_parse_matches_fixture(fixture: ReleaseFixture, tmp_path) -> None:
# Materialize the tree to assert it is at least well-formed YAML +
# plausible filesystem paths. Catches typos / missing leading dirs early.
fixture.materialize(tmp_path)
result = asdict(parse_release(fixture.release_name, _KB))
# ``is_season_pack`` is a @property — asdict() does not include it.
result["is_season_pack"] = parse_release(fixture.release_name, _KB).is_season_pack
for field, expected in fixture.expected_parsed.items():
assert field in result, (
f"{fixture.name}: unknown field '{field}' in expected.parsed"
)
assert result[field] == expected, (
f"{fixture.name}: parsed.{field}"
f"expected {expected!r}, got {result[field]!r}"
)
def test_at_least_one_fixture_per_bucket() -> None:
"""Each bucket should hold at least one case once populated."""
buckets = {f.name.split("/")[0] for f in FIXTURES}
assert "easy" in buckets, "EASY bucket must have at least one fixture"
assert "shitty" in buckets, "SHITTY bucket must have at least one fixture"
assert "path_of_pain" in buckets, "PATH_OF_PAIN bucket must have at least one fixture"