import unittest import tempfile import json from pathlib import Path from unittest.mock import patch from paper_atlas.collectors.pmlr import load_metadata,venue_key,collect_volume class MetadataTests(unittest.TestCase): def test_legacy_binary_scalar_is_decoded_as_text(self): self.assertEqual(load_metadata('title: !binary |\n SGVsbG8=\n')['title'],'Hello') def test_trailing_empty_document_is_allowed(self): self.assertEqual(load_metadata('---\nyear: 2024\n---\n'),{'year':2024}) def test_conflicting_documents_are_not_silently_combined(self): with self.assertRaisesRegex(ValueError,'exactly one'): load_metadata('year: 2024\n---\nyear: 2025\n') def test_historical_conference_name_aliases(self): self.assertEqual(venue_key('AISTATS 2010'),'AISTATS') self.assertEqual(venue_key('AISTATS 2012'),'AISTATS') self.assertEqual(venue_key('COLT 2012'),'COLT') self.assertEqual(venue_key('ECML-PKDD'),'ECML-PKDD') def test_missing_abstract_is_reported_as_partial_collection(self): config=b'shortname: ICML\nyear: 2023\nbooktitle: ICML\n' paper='---\nid: paper1\nlayout: inproceedings\ntitle: Paper\nabstract:\n---\n' with tempfile.TemporaryDirectory() as tmp,patch('paper_atlas.collectors.pmlr.fetch',return_value=config),patch('paper_atlas.collectors.pmlr.metadata_texts',return_value=iter([('paper.md',paper)])): result=collect_volume(999,tmp,tmp) self.assertEqual(result['count'],1) self.assertEqual(result['missing_abstract_count'],1) self.assertEqual(result['status'],'partial') def test_duplicate_publication_posts_preserve_date_evidence_once(self): config=b'shortname: CoRL\nyear: 2023\nbooktitle: CoRL\n' paper='---\nid: paper1\nlayout: inproceedings\ntitle: Paper\nabstract: Real abstract\ndate: {date}\n---\n' posts=[('2023-11-13-paper1.md',paper.format(date='2023-11-13')),('2023-12-02-paper1.md',paper.format(date='2023-12-02'))] with tempfile.TemporaryDirectory() as tmp,patch('paper_atlas.collectors.pmlr.fetch',return_value=config),patch('paper_atlas.collectors.pmlr.metadata_texts',return_value=iter(posts)): result=collect_volume(229,tmp,tmp) rows=[json.loads(line) for line in Path(result['file']).read_text().splitlines()] self.assertEqual(result['count'],1) self.assertEqual(result['metadata_post_count'],2) self.assertEqual(result['duplicate_post_count'],1) self.assertEqual(len(rows[0]['metadata']['source_versions']),2) self.assertEqual(rows[0]['metadata']['date'],'2023-12-02') def test_publisher_preface_is_not_an_accepted_paper(self): config = b'shortname: UAI\nyear: 2024\nbooktitle: UAI\n' accepted = '---\nid: paper1\nlayout: inproceedings\ntitle: Paper\nabstract: Abstract\n---\n' preface = '---\nid: kiyavash24a\nlayout: inproceedings\ntitle: Volume Preface\nsection: Preface\n---\n' posts = [('paper.md', accepted), ('preface.md', preface)] with tempfile.TemporaryDirectory() as tmp, patch( 'paper_atlas.collectors.pmlr.fetch', return_value=config, ), patch('paper_atlas.collectors.pmlr.metadata_texts', return_value=iter(posts)): result = collect_volume(244, tmp, tmp) rows = [json.loads(line) for line in Path(result['file']).read_text().splitlines()] self.assertEqual(result['excluded_preface_ids'], ['v244/kiyavash24a']) self.assertEqual(result['files'][0]['count'], 1) self.assertEqual([row['external_id'] for row in rows], ['v244/paper1']) def test_corl_2021_sections_keep_blue_sky_apart_from_contributed_papers(self): config = b'shortname: CoRL\nyear: 2021\nbooktitle: Proceedings of the 5th Conference on Robot Learning\n' paper = '---\nid: {id}\nlayout: inproceedings\ntitle: Paper\nabstract: Abstract\nsection: {section}\n---\n' posts = [('one.md', paper.format(id='one', section='Contributed Papers')), ('two.md', paper.format(id='two', section='Blue Sky Papers'))] with tempfile.TemporaryDirectory() as tmp, patch('paper_atlas.collectors.pmlr.fetch', return_value=config), patch( 'paper_atlas.collectors.pmlr.metadata_texts', return_value=iter(posts), ): result = collect_volume(164, tmp, tmp) self.assertEqual(result['track'], 'mixed') files = {manifest['track']: Path(manifest['file']) for manifest in result['files']} self.assertEqual({key: path.name for key, path in files.items()}, {'main': 'pmlr-v164.jsonl', 'blue_sky': 'pmlr-v164-blue_sky.jsonl'}) rows = {track: json.loads(path.read_text()) for track, path in files.items()} self.assertEqual([(rows[t]['external_id'], rows[t]['track'], rows[t]['metadata']['pmlr_section']) for t in ('main', 'blue_sky')], [('v164/one', 'main', 'Contributed Papers'), ('v164/two', 'blue_sky', 'Blue Sky Papers')]) def test_conflicting_duplicate_posts_do_not_replace_previous_collection(self): config=b'shortname: CoRL\nyear: 2023\nbooktitle: CoRL\n' paper='---\nid: paper1\nlayout: inproceedings\ntitle: {title}\nabstract: Abstract\n---\n' with tempfile.TemporaryDirectory() as tmp,patch('paper_atlas.collectors.pmlr.fetch',return_value=config),patch('paper_atlas.collectors.pmlr.metadata_texts',return_value=iter([('a.md',paper.format(title='First paper')),('b.md',paper.format(title='Other paper'))])): previous=Path(tmp)/'pmlr-v229.jsonl';previous.write_text('previous valid collection') with self.assertRaisesRegex(ValueError,'Conflicting metadata posts'): collect_volume(229,tmp,tmp) self.assertEqual(previous.read_text(),'previous valid collection') if __name__=='__main__': unittest.main()