"""Historical accepted lists, repeated presentations and preserved work histories.""" import hashlib import json from pathlib import Path import sqlite3 import tempfile import unittest from unittest.mock import patch from paper_atlas.collectors import iclr_archive as archive from paper_atlas.db.store import Store from paper_atlas.ingestion.records import ingest_file OBSERVED = '2026-11-09T00:00:00Z' def entry(identifier, title='A shared research paper', display='Jane Doe and Bob Smith'): return f'
  • {title}, {display}
    • ' def page2015(): return ('

    Main Conference - Oral Presentations

      '+entry('1412.0001v2')+'
    ' '

    Main Conference - Poster Presentations

      '+entry('1412.0001v2')+'
    ' '

    Workshop Papers

      '+entry('1412.0002', 'A workshop paper')+'
    ') class IclrArchiveTests(unittest.TestCase): def frozen(self, root, year, html): root.mkdir() data = html.encode() (root/'page.html').write_bytes(data) receipt = {'url': archive.PAGES[year][0], 'file': 'page.html', 'status': 200, 'bytes': len(data), 'sha256': hashlib.sha256(data).hexdigest(), 'finished_at': OBSERVED} (root/'receipts.json').write_text(json.dumps({'receipts': [receipt]})) return root def test_oral_poster_repeat_is_one_attempt_with_all_source_variants(self): rows = archive.parse_page(page2015(), 2015, {'observed_at': OBSERVED}) main, workshop = rows self.assertEqual((main['track'], workshop['track']), ('main', 'workshop')) self.assertEqual(main['identifiers'], {'arxiv': '1412.0001'}) self.assertEqual(main['external_id'], '2015/main/1412.0001') self.assertEqual(main['metadata']['presentations'], ['oral', 'poster']) self.assertEqual(len(main['metadata']['source_variants']), 2) self.assertEqual(main['metadata']['source_variants'][0]['version'], 'v2') self.assertEqual(main['authors'], ['Jane Doe', 'Bob Smith']) self.assertTrue(all(r['status'] == 'accepted' and r['abstract'] is None for r in rows)) def test_2014_author_span_outside_paragraph_and_trailing_separator(self): html = ('

    Conference Proceedings

    conference papers accepted

    ' '
    A research title
    ' '

    Jane Doe; ' 'Bob Smith; Carol Wu;

    ' '
    Another title' '
    First Author; Second Author
    ') row, unwrapped = archive.parse_page(html, 2014, {'observed_at': OBSERVED}) self.assertEqual(row['title'], 'A research title') self.assertEqual(row['authors'], ['Jane Doe', 'Bob Smith', 'Carol Wu']) self.assertEqual(row['metadata']['source_variants'][0]['authors_display'], 'Jane Doe; Bob Smith; Carol Wu;') self.assertEqual(row['track'], 'main') self.assertEqual(unwrapped['authors'], ['First Author', 'Second Author']) def test_same_arxiv_in_different_tracks_keeps_separate_source_attempts(self): html = page2015().replace('1412.0002', '1412.0001v3') rows = archive.parse_page(html, 2015, {'observed_at': OBSERVED}) self.assertEqual(len(rows), 2) self.assertEqual({r['external_id'] for r in rows}, {'2015/main/1412.0001', '2015/workshop/1412.0001'}) self.assertEqual(rows[1]['metadata']['source_variants'][0]['version'], 'v3') def test_2016_code_links_and_breaks_do_not_become_authors(self): html = ('

    Accepted Papers (Conference Track)

    Oral Presentations

      ' '
    1. A title' '[code]
      Jane Doe, Bob Smith
    ' '

    Poster Presentations

    ') row, = archive.parse_page(html, 2016, {'observed_at': OBSERVED}) self.assertEqual(row['authors'], ['Jane Doe', 'Bob Smith']) self.assertEqual(row['metadata']['presentations'], ['oral']) def test_conflicting_repeat_unknown_sections_and_unparsed_links_fail(self): variants = [page2015().replace('Poster Presentations', 'Other Presentations'), page2015().replace('', 'stray', 1), page2015().replace('Jane Doe and Bob Smith', 'Different Author', 1)] for html in variants: with self.subTest(html=html), self.assertRaises(ValueError): archive.parse_page(html, 2015, {'observed_at': OBSERVED}) def test_arxiv_versions_are_preserved_and_unsafe_links_rejected(self): self.assertEqual(archive.arxiv_link('https://arxiv.org/pdf/1511.00001v3.pdf'), ('1511.00001', 'v3')) self.assertIsNone(archive.arxiv_link('https://arxiv.org.example.org/abs/1511.00001')) for url in ['https://arxiv.org/abs/1511.00001?other=1', 'ftp://arxiv.org/abs/1511.00001', 'https://user@arxiv.org/abs/1511.00001', 'https://arxiv.org/abs/not-a-paper']: with self.subTest(url=url), self.assertRaises(ValueError): archive.arxiv_link(url) def test_receipt_hash_status_path_and_symlink_cannot_escape_snapshot(self): for failure in ['hash', 'status', 'path', 'symlink']: with self.subTest(failure=failure), tempfile.TemporaryDirectory() as temporary: root = Path(temporary) source = self.frozen(root/'source', 2015, page2015()) file = source/'receipts.json' data = json.loads(file.read_text()) receipt = data['receipts'][0] if failure == 'hash': receipt['sha256'] = '0'*64 elif failure == 'status': receipt['status'] = 404 elif failure == 'path': receipt['file'] = '../outside.html' else: (root/'outside.html').write_text(page2015()) (source/'page.html').unlink() (source/'page.html').symlink_to(root/'outside.html') file.write_text(json.dumps(data)) with self.assertRaises(ValueError): archive.read_page(2015, snapshots=source) def test_changed_inventory_leaves_no_completed_output(self): with tempfile.TemporaryDirectory() as temporary: root = Path(temporary) source = self.frozen(root/'source', 2015, page2015()) with self.assertRaises(ValueError): archive.collect(2015, root/'out', snapshots=source) self.assertFalse((root/'out/iclr-archive-2015.json').exists()) def test_native_import_keeps_rejected_to_accepted_history_and_abstract(self): with tempfile.TemporaryDirectory() as temporary: root = Path(temporary) source = self.frozen(root/'source', 2015, page2015()) with patch.dict(archive.PAGES, {2015: (archive.PAGES[2015][0], {'main': 1, 'workshop': 1})}): result = archive.collect(2015, root/'out', snapshots=source) with self.assertRaises(FileExistsError): archive.collect(2015, root/'out', snapshots=source) db = root/'sample.sqlite' store = Store(db) pid, rid = store.record('arxiv', '1412.0001', 'https://arxiv.org/abs/1412.0001', 'A shared research paper', 'Keep this canonical abstract.', ['Jane Doe', 'Bob Smith'], {'arxiv': '1412.0001'}, {}) store.decision(pid, rid, 'Earlier Conference', 2014, 'main', 'original-attempt', 'https://example.org/rejected', 'rejected', 'explicit earlier decision', observed_at=OBSERVED) store.conn.commit() store.conn.close() for manifest in result['files']: ingest_file(db, manifest['file']) ingest_file(db, manifest['file']) with sqlite3.connect(db) as c: self.assertEqual(c.execute('SELECT count(*) FROM papers').fetchone()[0], 2) self.assertEqual(c.execute('SELECT abstract FROM papers WHERE id=?', (pid,)).fetchone()[0], 'Keep this canonical abstract.') history = c.execute('SELECT v.acronym,e.year,d.status FROM decisions d JOIN submissions s ON s.id=d.submission_id JOIN editions e ON e.id=s.edition_id JOIN venues v ON v.id=e.venue_id WHERE s.paper_id=? ORDER BY e.year', (pid,)).fetchall() self.assertEqual(history, [('Earlier Conference', 2014, 'rejected'), ('ICLR', 2015, 'accepted')]) self.assertEqual(c.execute('SELECT count(*) FROM submissions').fetchone()[0], 3) self.assertEqual(c.execute('PRAGMA foreign_key_check').fetchall(), [])