import gzip import hashlib import json from pathlib import Path import tempfile import unittest from paper_atlas.collectors import icdm2026 as c class ICDM2026Tests(unittest.TestCase): @classmethod def setUpClass(cls): cls.fixture = json.loads(gzip.decompress((Path(__file__).parent/'fixtures/icdm2026-source.json.gz').read_bytes())) cls.raw = cls.fixture['files'][c.SNAPSHOT+'/icdm-detailed-sessions.html'].encode() cls.gold = cls.fixture['independent_inventory'] def snapshots(self, root): for name, text in self.fixture['files'].items(): path = root/name; path.parent.mkdir(parents=True, exist_ok=True); path.write_bytes(text.encode()) def test_all_rows_match_separately_parsed_frozen_inventory(self): result = c.parse_program(self.raw) self.assertEqual(len(result), len(self.gold['entries'])) for position, (row, gold) in enumerate(zip(result, self.gold['entries']), 1): for field in ('paper_id_literal', 'title', 'authors_literal', 'source_reported_authors', 'time_literal'): self.assertEqual(row[field], gold[field]) self.assertEqual(row['source_position'], position) for field, value in gold['session'].items(): self.assertEqual(row['session'][field], value) def test_instantiable_collection_retains_scope_fields_and_source_bytes(self): with tempfile.TemporaryDirectory() as tmp: root = Path(tmp); self.snapshots(root/'src') report = c.collect(root/'out', snapshots=root/'src') self.assertEqual(report['track_counts'], self.gold['track_counts_literal']) self.assertEqual(report['presentation_counts'], self.gold['presentation_counts_literal']) self.assertEqual((report['records'], report['missing_abstract_count']), (324, 324)) self.assertFalse(report['database_written']); self.assertEqual(report['network_requests'], 0) self.assertEqual(report['public_rejected_metadata'], 'unknown_no_public_export_verified') all_rows = [] for manifest in report['files']: path = Path(manifest['file']); raw = path.read_bytes() self.assertEqual(hashlib.sha256(raw).hexdigest(), manifest['file_sha256']) self.assertEqual(manifest['status'], 'partial') rows = [json.loads(line) for line in raw.splitlines()] self.assertEqual(len(rows), manifest['missing_abstract_count']) for row in rows: self.assertEqual((row['venue'], row['year'], row['track']), ('ICDM', 2026, manifest['track'])) self.assertIsNone(row['abstract']); self.assertIsNone(row['metadata']['paper_type']) self.assertEqual(row['identifiers'], {}); self.assertEqual(row['submission_identifiers'], []) self.assertFalse(row['metadata']['original_decision_signature_verified']) self.assertEqual(row['external_id'], '2026/'+row['metadata']['program_fields']['paper_id_literal']) self.assertTrue(row['url'].startswith(c.PROGRAM+'#paper-DM')) self.assertTrue(all(t['namespace'].startswith(c.SOURCE+':') for t in row['tags'])) self.assertNotIn('doi', row['metadata']); self.assertNotIn('decision_date', row) all_rows.extend(rows) self.assertEqual(len({r['external_id'] for r in all_rows}), 324) for item in report['evidence']: raw = (root/'out'/item['output_file']).read_bytes() self.assertEqual(raw, self.fixture['files'][c.SNAPSHOT+'/'+item['file']].encode()) self.assertTrue((root/'out/collection-report.json').is_file()) self.assertFalse((root/'out/collection-report.json.part').exists()) with self.assertRaisesRegex(ValueError, 'Output exists'): c.collect(root/'out', snapshots=root/'src') def test_stale_or_different_conference_rejected(self): for old, new in [(b'IEEE ICDM 2026', b'IEEE ICDM 2025'), (b'In-person session presentation list.', b'Workshop presentation list.')]: with self.subTest(old=old), self.assertRaises(ValueError): c.parse_program(self.raw.replace(old, new)) def test_track_attribute_must_agree_with_visible_label(self): changed = self.raw.replace(b'data-track="research"', b'data-track="applied"', 1) with self.assertRaisesRegex(ValueError, 'track'): c.parse_program(changed) def test_presentation_attribute_is_not_inferred_from_session_id(self): changed = self.raw.replace(b'data-format="long"', b'data-format="short"', 1) with self.assertRaisesRegex(ValueError, 'presentation'): c.parse_program(changed) def test_repeated_paper_and_source_locator_disagreement_rejected(self): for old, new in [(b'DM1278', b'DM827'), (b'id="paper-DM827"', b'id="paper-DM99999"')]: with self.subTest(old=old), self.assertRaises(ValueError): c.parse_program(self.raw.replace(old, new)) def test_lost_session_or_changed_session_counts_rejected(self): for old, new in [(b'data-session-id="L1"', b'data-session-id="L2"'), (b'Long \xc2\xb7 7 papers', b'Long \xc2\xb7 6 papers')]: with self.subTest(old=old), self.assertRaises(ValueError): c.parse_program(self.raw.replace(old, new, 1)) def test_empty_author_is_not_silently_dropped(self): changed = self.raw.replace(b'Qishuang Fu; Andreas Deppeler;', b'Qishuang Fu;;', 1) with self.assertRaisesRegex(ValueError, 'author'): c.parse_program(changed) def test_snapshot_manifest_and_body_corruption_rejected_before_output(self): for name in ('manifest.json', 'icdm-detailed-sessions.html', 'icdm-research-policy.html', 'icdm-applied-policy.html'): with self.subTest(name=name), tempfile.TemporaryDirectory() as tmp: root = Path(tmp); self.snapshots(root/'src'); path = root/'src'/c.SNAPSHOT/name path.write_bytes(path.read_bytes()+b' ') with self.assertRaises(ValueError): c.collect(root/'out', snapshots=root/'src') self.assertFalse((root/'out').exists()) def test_snapshot_source_symlink_rejected(self): with tempfile.TemporaryDirectory() as tmp: root = Path(tmp); self.snapshots(root/'src'); path = root/'src'/c.SNAPSHOT/'icdm-detailed-sessions.html' real = root/'real.html'; path.rename(real); path.symlink_to(real) with self.assertRaisesRegex(ValueError, 'Unsafe source'): c.collect(root/'out', snapshots=root/'src')