import hashlib import json from pathlib import Path import tempfile import unittest from unittest.mock import patch from paper_atlas.collectors import icml_public_archive as archive from paper_atlas.audits.public_openreview import audit from paper_atlas.db.store import Store from paper_atlas.ingestion.records import ingest_file class ICMLPublicArchiveTests(unittest.TestCase): def note(self, **changes): return {'id': 'PublicRoot1', 'forum': 'PublicRoot1', 'readers': ['everyone'], 'domain': archive.DOMAIN, 'invitations': [archive.DOMAIN + '/-/Submission'], 'license': 'CC BY 4.0', 'cdate': 1769251630136, 'content': {'title': {'value': 'A public rejected submission'}, 'abstract': {'value': 'Public abstract'}, 'authors': {'value': ['Anonymous', 'Jane Doe']}, 'authorids': {'value': ['private@example.org']}, 'venue': {'value': 'Submitted to ICML 2026'}, 'venueid': {'value': archive.VENUEID}, 'primary_area': {'value': 'learning'}, 'pdf': {'value': '/private.pdf'}}, 'details': {'reviews': ['not retained']}, **changes} def test_explicit_platform_classification_requires_public_root_and_correct_scope(self): original = self.note() normalized = archive.normalize(original) self.assertEqual(normalized['status'], 'rejected') self.assertEqual(normalized['raw_decision'], archive.VENUEID) self.assertEqual(normalized['metadata']['license'], 'CC BY 4.0') self.assertEqual(normalized['metadata']['evidence_kind'], 'public_submission_venueid') self.assertFalse(normalized['metadata']['original_decision_signature_verified']) self.assertNotIn('private@example.org', json.dumps(normalized)) self.assertNotIn('not retained', json.dumps(normalized)) for changes in ({'readers': ['authors']}, {'forum': 'AnotherRoot'}, {'ddate': 1000}, {'domain': 'ICML.cc/2026/Position_Papers'}, {'invitations': []}): with self.subTest(changes=changes), self.assertRaises(ValueError): archive.normalize(self.note(**changes)) for venueid in (None, 'ICML.cc/2026/Conference/Submission', 'ICML.cc/2026/Conference/Accepted_Submission'): candidate = self.note() candidate['content']['venueid'] = {'value': venueid} with self.assertRaisesRegex(ValueError, 'classification'): archive.normalize(candidate) def collect_fixture(self, out, notes, count=None, corrupt=False): data = json.dumps({'count': len(notes) if count is None else count, 'notes': notes}).encode() blob = hashlib.sha1(b'blob ' + str(len(data)).encode() + b'\0' + data).hexdigest() with patch.multiple(archive, BYTES=len(data), BLOB_SHA1=blob, EXPECTED=len(notes)), \ patch.object(archive.shutil, 'disk_usage', return_value=type('Space', (), {'free': 20 * 1024**3})()): return archive.collect(out, fetcher=lambda url, limit: data + b'x' if corrupt else data) def test_verified_archive_roundtrips_through_preflight_and_idempotent_import(self): with tempfile.TemporaryDirectory() as tmp: root = Path(tmp) result = self.collect_fixture(root / 'source', [self.note()]) db = root / 'db.sqlite' Store(db).conn.close() report = audit(db, root / 'source/public-openreview-inventory.json', root / 'audit.json') self.assertEqual(report['status'], 'ready_for_serial_import') self.assertEqual(report['source'], archive.SOURCE) self.assertEqual(result['files'][0]['status'], 'partial') for _ in range(2): ingest_file(db, report['files'][0]) store = Store(db) try: self.assertEqual(store.conn.execute('SELECT count(*) FROM submissions').fetchone()[0], 1) self.assertEqual(store.conn.execute('SELECT status FROM decisions').fetchall(), [('rejected',)]) finally: store.conn.close() def test_bad_hash_count_or_duplicate_identity_publishes_nothing(self): for kwargs in ({'corrupt': True}, {'count': 99}, {}): notes = [self.note(), self.note()] if not kwargs else [self.note()] with self.subTest(kwargs=kwargs), tempfile.TemporaryDirectory() as tmp: with self.assertRaises(ValueError): self.collect_fixture(tmp, notes, **kwargs) self.assertEqual(list(Path(tmp).glob('*.jsonl')), []) self.assertFalse((Path(tmp) / 'public-openreview-inventory.json').exists()) if __name__ == '__main__': unittest.main()