"""Every committed artifact matches the schema its generator declares.""" import pytest from common.artifacts import REGISTRY from conftest import REPO, load # Artifacts whose producing sweep was never committed, so provenance.generator # is null. A new entry here is a new gap and has to be added deliberately. KNOWN_GAPS = { 'eval_tight_fpr.json', 'discovery/dim_selection.json', 'discovery/dim48_characterization.json', 'discovery/prop_specificity.json', 'discovery/prop_image_manifest.json', 'discovery/variant_leaderboard.json', } @pytest.mark.parametrize('rel', sorted(REGISTRY)) def test_artifact_exists(rel): assert (REPO / rel).exists(), f'{rel} is registered but missing' @pytest.mark.parametrize('rel', sorted(REGISTRY)) def test_artifact_has_provenance(rel): doc = load(rel) assert 'provenance' in doc, f'{rel} has no provenance block' assert next(iter(doc)) == 'provenance', f'{rel} does not open with its provenance block' @pytest.mark.parametrize('rel', sorted(r for r in REGISTRY if REGISTRY[r].payload_keys)) def test_artifact_payload_keys(rel): spec = REGISTRY[rel] got = tuple(k for k in load(rel) if k != 'provenance') assert got == spec.payload_keys, f'{rel} payload keys {got} != declared {spec.payload_keys}' @pytest.mark.parametrize('rel', sorted(REGISTRY)) def test_artifact_generator(rel): spec = REGISTRY[rel] generator = load(rel)['provenance']['generator'] assert generator in (spec.generator, None), \ f'{rel} claims generator {generator!r}, registry says {spec.generator!r}' @pytest.mark.parametrize('rel', sorted(REGISTRY)) def test_artifact_pool(rel): spec = REGISTRY[rel] pool = load(rel)['provenance'].get('pool') if spec.pool is not None and pool is not None: assert pool == spec.pool, f'{rel} names pool {pool!r}, registry says {spec.pool!r}' def test_known_gaps_are_exactly_the_ungenerated_artifacts(): ungenerated = {rel for rel in REGISTRY if load(rel)['provenance']['generator'] is None} assert ungenerated == KNOWN_GAPS def test_classifier_hashes_are_current(): """Every artifact naming a classifier config records that file's current hash.""" from common.artifacts import sha256_of for rel in sorted(REGISTRY): p = load(rel)['provenance'] if 'classifier' not in p: continue assert p['classifier_sha256'] == sha256_of(REPO / p['classifier']), \ f'{rel} pins a stale hash for {p["classifier"]}'