diff --git a/docs/data-sources.md b/docs/data-sources.md index 8a3b133..f06e3e0 100644 --- a/docs/data-sources.md +++ b/docs/data-sources.md @@ -300,3 +300,13 @@ paper-atlas collect cvf --cache /data/paper-index/raw/http-cache \ ``` parser_version 2 的清单还保存实际遍历的 index_urls、入口错误及缺失摘要页面。补采结果经过清单与身份核验后才导入,不能因重试任务启动就标记缺口已解决。 + +## PMLR 中的 ICML 多轨道论文 + +ICML 2024 起的一个 PMLR 卷可以同时包含研究主轨道与 Position Paper,不能把整卷都标为 `main`。采集器 v3 按轨道输出 `pmlr-v-main.jsonl`、`pmlr-v-position.jsonl` 及各自 manifest;卷级 `pmlr-v.inventory.json` 和目录清单的 `files` 数组列出实际文件。导入队列应展开 `files`,不能假定每卷只有一个 `file`。 + +2025、2026 年通过出版社元数据的真实 OpenReview forum ID,匹配官方完整节目单中的 `Conference` / `Position_Paper_Track` 来源组;忽略负编号生成的口头报告副本,遇到冲突、缺少身份或未匹配的发表记录停止发布结果。每条记录保存节目单 URL、SHA-256、事件 ID、关联身份及轨道证据。 + +2024 年的官方节目单把两轨都放在 `Conference`,但提供 PMLR 论文自链接。该年仅采用组织方在 [2025 Position CFP](https://icml.cc/Conferences/2025/CallForPositionPapers) 明确链接的 [2024 Position 论文标题筛选](https://icml.cc/virtual/2024/papers.html?filter=titles&search=position%3A) 规则;同时保存规则页面的哈希。这个规则不用于其他会议或年份。官方节目单将 `guyard24a` 链接误写为 `theo24a`:只对这条已核查的映射额外要求标题精确一致、至少两名公开作者重合,不进行全库模糊匹配。 + +导入与身份回填拒绝 ICML 2024 起 parser_version<3 或没有官方轨道证据的旧文件。已有主库中的错误轨道需要在独占维护锁内迁移原投稿事件、保留决定与来源关联;仅重新导入拆分文件会留下旧的主轨道事件,不能作为修复方式。完成迁移前,不把新文件直接导入现有库。 diff --git a/paper_atlas/collectors/pmlr.py b/paper_atlas/collectors/pmlr.py index f76f8a0..3544424 100644 --- a/paper_atlas/collectors/pmlr.py +++ b/paper_atlas/collectors/pmlr.py @@ -1,5 +1,7 @@ """Collect official PMLR metadata, never the PDFs linked by the metadata.""" import argparse +from collections import defaultdict +import hashlib from paper_atlas.config import DEFAULT_REGISTRY import io import json @@ -8,6 +10,7 @@ import os import subprocess import tarfile import time +import tempfile from pathlib import Path import yaml @@ -37,6 +40,7 @@ def venue_key(shortname): from paper_atlas.io.http import fetch +from paper_atlas.collectors.pmlr_tracks import collect_track_evidence, record_track def metadata_texts(volume,cache): @@ -98,57 +102,88 @@ def collect_volume(volume,cache,out,allowed=None): track = 'workshop' if 'workshop' in title.lower() else 'main' path = Path(out)/f'pmlr-v{volume}.jsonl' path.parent.mkdir(parents=True,exist_ok=True) - part = path.with_suffix('.part') + mixed_icml = venue == 'ICML' and year >= 2024 + mapping, track_program = collect_track_evidence(year, cache) if mixed_icml else ({}, None) records = {} duplicate_posts = 0 - with part.open('w') as output: - for member_name,content in metadata_texts(volume,cache): - parts = re.split(r'(?m)^---\s*$',content,maxsplit=2) - if len(parts)<3 or parts[0].strip(): - raise RuntimeError('Missing YAML frontmatter: '+member_name) - row = load_metadata(parts[1]) - if row.get('layout') not in ('inproceedings','article'): - continue - if not row.get('title'): - raise ValueError('Paper metadata has no title: '+member_name) - if not row.get('id'): - raise ValueError('Paper metadata has no publication ID: '+member_name) - external = f"v{volume}/{row['id']}" - ids = {} - for key in ('doi','openreview','arxiv'): - value = row.get(key) - if value: - value = str(value) - if key=='arxiv': - value = re.sub(r'^https?://arxiv.org/(abs|pdf)/','',value).removesuffix('.pdf') - if key=='openreview': - value = value.split('id=')[-1].split('&')[0] - ids[key] = value - record = {'source':'pmlr','external_id':external,'url':f"https://proceedings.mlr.press/v{volume}/{row.get('id')}.html",'title':row['title'],'abstract':row.get('abstract'),'authors':row.get('author',[]),'identifiers':ids,'venue':venue,'year':year,'track':track,'status':'accepted','list_url':f'https://proceedings.mlr.press/v{volume}/','metadata':{key:row[key] for key in ('id','volume','date','page','doi','openreview','arxiv','publisher') if key in row}} - version={'path':member_name,'date':row.get('date')} - if external in records: - previous=records[external] - if ({k:v for k,v in previous.items() if k!='metadata'} != {k:v for k,v in record.items() if k!='metadata'} - or {k:v for k,v in previous['metadata'].items() if k not in ('date','source_versions')} != {k:v for k,v in record['metadata'].items() if k!='date'}): - raise ValueError('Conflicting metadata posts share a publication ID: '+external) - previous['metadata']['source_versions'].append(version) - if str(row.get('date') or '')>str(previous['metadata'].get('date') or ''): - previous['metadata']['date']=row['date'] - duplicate_posts+=1 - continue - record['metadata']['source_versions']=[version] - records[external]=record - for record in records.values(): - output.write(json.dumps(record,ensure_ascii=False,default=str)+'\n') + for member_name,content in metadata_texts(volume,cache): + parts = re.split(r'(?m)^---\s*$',content,maxsplit=2) + if len(parts)<3 or parts[0].strip(): + raise RuntimeError('Missing YAML frontmatter: '+member_name) + row = load_metadata(parts[1]) + if row.get('layout') not in ('inproceedings','article'): + continue + if not row.get('title'): + raise ValueError('Paper metadata has no title: '+member_name) + if not row.get('id'): + raise ValueError('Paper metadata has no publication ID: '+member_name) + external = f"v{volume}/{row['id']}" + ids = {} + for key in ('doi','openreview','arxiv'): + value = row.get(key) + if value: + value = str(value) + if key=='arxiv': + value = re.sub(r'^https?://arxiv.org/(abs|pdf)/','',value).removesuffix('.pdf') + if key=='openreview': + value = value.split('id=')[-1].split('&')[0] + ids[key] = value + record = {'source':'pmlr','external_id':external,'url':f"https://proceedings.mlr.press/v{volume}/{row.get('id')}.html",'title':row['title'],'abstract':row.get('abstract'),'authors':row.get('author',[]),'identifiers':ids,'venue':venue,'year':year,'track':track,'status':'accepted','list_url':f'https://proceedings.mlr.press/v{volume}/','metadata':{key:row[key] for key in ('id','volume','date','page','doi','openreview','arxiv','publisher') if key in row}} + version={'path':member_name,'date':row.get('date')} + if external in records: + previous=records[external] + if ({k:v for k,v in previous.items() if k!='metadata'} != {k:v for k,v in record.items() if k!='metadata'} + or {k:v for k,v in previous['metadata'].items() if k not in ('date','source_versions')} != {k:v for k,v in record['metadata'].items() if k!='date'}): + raise ValueError('Conflicting metadata posts share a publication ID: '+external) + previous['metadata']['source_versions'].append(version) + if str(row.get('date') or '')>str(previous['metadata'].get('date') or ''): + previous['metadata']['date']=row['date'] + duplicate_posts+=1 + continue + record['metadata']['source_versions']=[version] + records[external]=record count=len(records) missing_abstracts=sum(not (record.get('abstract') or '').strip() for record in records.values()) if count==0: - part.unlink(missing_ok=True) raise RuntimeError('No papers parsed; refusing an empty successful collection') - part.replace(path) - result = {'source':'pmlr','parser_version':2,'venue':venue,'year':year,'track':track,'volume':volume,'count':count,'metadata_post_count':count+duplicate_posts,'duplicate_post_count':duplicate_posts,'missing_abstract_count':missing_abstracts,'list_url':f'https://proceedings.mlr.press/v{volume}/','file':str(path),'status':'partial' if missing_abstracts else 'collected'} - path.with_suffix('.manifest.json').write_text(json.dumps(result,indent=2)) - print(json.dumps(result),flush=True) + grouped = defaultdict(list) + for record in records.values(): + if mixed_icml: + record_track(record, mapping, track_program) + grouped[record['track']].append(record) + # Parse and verify the entire volume before replacing any published output. + manifests = [] + with tempfile.TemporaryDirectory(prefix=f'.pmlr-v{volume}-', dir=path.parent) as temporary: + stage = Path(temporary) + for current_track, rows in sorted(grouped.items()): + filename = f'pmlr-v{volume}-{current_track}.jsonl' if mixed_icml else path.name + output = stage / filename + output.write_text(''.join(json.dumps(row, ensure_ascii=False, default=str)+'\n' for row in rows)) + absent = sum(not (row.get('abstract') or '').strip() for row in rows) + manifest = {'source': 'pmlr', 'parser_version': 3, 'venue': venue, 'year': year, + 'track': current_track, 'volume': volume, 'count': len(rows), + 'missing_abstract_count': absent, 'list_url': f'https://proceedings.mlr.press/v{volume}/', + 'file': str(path.parent / filename), 'file_sha256': hashlib.sha256(output.read_bytes()).hexdigest(), + 'status': 'partial' if absent else 'collected'} + if track_program: + manifest['track_program'] = track_program + output.with_suffix('.manifest.json').write_text(json.dumps(manifest, indent=2)+'\n') + manifests.append(manifest) + result = {'source': 'pmlr', 'parser_version': 3, 'venue': venue, 'year': year, + 'track': next(iter(grouped)) if len(grouped) == 1 else 'mixed', 'volume': volume, + 'count': count, 'metadata_post_count': count + duplicate_posts, + 'duplicate_post_count': duplicate_posts, 'missing_abstract_count': missing_abstracts, + 'list_url': f'https://proceedings.mlr.press/v{volume}/', 'files': manifests, + 'status': 'partial' if missing_abstracts else 'collected'} + if len(manifests) == 1: + result['file'] = manifests[0]['file'] + if track_program: + result['track_program'] = track_program + inventory = stage / f'pmlr-v{volume}.inventory.json' + inventory.write_text(json.dumps(result, indent=2)+'\n') + for child in sorted(stage.iterdir(), key=lambda child: child == inventory): + child.replace(path.parent / child.name) + print(json.dumps(result), flush=True) return result diff --git a/paper_atlas/collectors/pmlr_tracks.py b/paper_atlas/collectors/pmlr_tracks.py new file mode 100644 index 0000000..c3973e6 --- /dev/null +++ b/paper_atlas/collectors/pmlr_tracks.py @@ -0,0 +1,140 @@ +"""Resolve mixed ICML proceedings tracks from the official paper program.""" +from collections import Counter +import hashlib +import json +import re +from urllib.parse import parse_qs, urlsplit + +from paper_atlas.collectors.iclr import identifiers, source_number +from paper_atlas.db.store import author_keys, normalized +from paper_atlas.io.html import Document, clean +from paper_atlas.io.http import fetch + + +POSITION_LIST_POLICY = 'https://icml.cc/Conferences/2025/CallForPositionPapers' +PUBLISHER_LINK_ALIASES = {'v235/theo24a': 'v235/guyard24a'} + + +def position_list_policy(data): + """The organizers explicitly link this title filter as the 2024 position list.""" + for node in Document(data.decode()).root.walk(): + if node.tag != 'a' or clean(node.text()).casefold() != 'position papers': + continue + url = node.attrs.get('href', '') + parsed = urlsplit(url) + query = parse_qs(parsed.query) + if (parsed.netloc in ('', 'icml.cc') and parsed.path == '/virtual/2024/papers.html' + and query.get('filter') == ['titles'] and query.get('search') == ['position:']): + return {'url': POSITION_LIST_POLICY, 'sha256': hashlib.sha256(data).hexdigest(), + 'position_list_url': 'https://icml.cc' + parsed.path + '?' + parsed.query} + raise ValueError('Official policy no longer identifies the 2024 position-paper title list') + + +def program_tracks(data, year, policy=None): + program = json.loads(data) + events = program.get('results') if isinstance(program, dict) else None + if (not isinstance(events, list) or program.get('count') != len(events) + or program.get('next') or program.get('previous')): + raise ValueError('Official ICML program must be a complete counted event list') + if len({str(row['id']) for row in events}) != len(events): + raise ValueError('Repeated event identity in official ICML program') + if year == 2024 and policy is None: + raise ValueError('The 2024 position-list policy is required') + mapping = {} + excluded = Counter() + for row in events: + number = source_number(row) + if number is not None and number < 0: + excluded['synthetic_oral_event'] += 1 + continue + parsed = urlsplit(row.get('sourceurl') or '') + group = parse_qs(parsed.query).get('id', []) + groups = {f'ICML.cc/{year}/Conference': 'main', + f'ICML.cc/{year}/Position_Paper_Track': 'position'} + if (parsed.netloc != 'openreview.net' or parsed.path != '/group' + or len(group) != 1 or group[0] not in groups): + excluded['other_source'] += 1 + continue + if not str(row.get('decision') or '').casefold().startswith('accept'): + raise ValueError('Non-accepted event in official ICML paper program') + if year == 2024: + # The 2024 program flattens both tracks into Conference and links + # PMLR publication IDs instead of forums. Use only this year-specific, + # organizer-endorsed list rule, never a global title heuristic. + link = urlsplit(row.get('paper_pdf_url') or '') + if link.netloc != 'proceedings.mlr.press' or not re.fullmatch(r'/v\d+/[^/]+\.html', link.path): + raise ValueError('2024 ICML paper has no publisher self-link') + key = ('pmlr', link.path.lstrip('/').removesuffix('.html')) + track = 'position' if re.match(r'^Position(?: Paper)?:', row.get('name') or '', re.I) else 'main' + kind = 'official_2024_position_list' + else: + forum = identifiers(row).get('openreview') + if not forum: + raise ValueError('ICML paper has no real OpenReview self-identity') + key = ('openreview', forum) + track, kind = groups[group[0]], 'official_openreview_track_group' + evidence = {'track': track, 'kind': kind, 'event_ids': [row['id']], + 'source_group': group[0], 'program_title': row.get('name')} + if key[0] == 'pmlr' and key[1] in PUBLISHER_LINK_ALIASES: + evidence['publisher_link_alias'] = key[1] + evidence['_authors'] = [author['fullname'] for author in row.get('authors', [])] + key = ('pmlr', PUBLISHER_LINK_ALIASES[key[1]]) + if key in mapping: + if mapping[key]['track'] != track: + raise ValueError('One paper identity has conflicting official tracks') + mapping[key]['event_ids'].append(row['id']) + else: + mapping[key] = evidence + if not mapping: + raise ValueError('Official ICML program contains no supported paper identities') + return mapping, {'event_count': len(events), 'paper_identity_count': len(mapping), + 'excluded_events': dict(excluded)} + + +def collect_track_evidence(year, cache): + url = f'https://icml.cc/static/virtual/data/icml-{year}-orals-posters.json' + data = fetch(url, cache) + policy = position_list_policy(fetch(POSITION_LIST_POLICY, cache)) if year == 2024 else None + mapping, inventory = program_tracks(data, year, policy) + provenance = {'url': url, 'sha256': hashlib.sha256(data).hexdigest(), **inventory} + if policy: + provenance['position_list_policy'] = policy + return mapping, provenance + + +def record_track(record, mapping, provenance): + key = ('pmlr', record['external_id']) if record['year'] == 2024 else ('openreview', record['identifiers'].get('openreview')) + if key not in mapping: + raise ValueError('Published ICML paper is absent from the verified official track inventory: ' + record['external_id']) + evidence = {**mapping[key], 'identity_scheme': key[0], 'identity_value': key[1], + 'program_url': provenance['url'], 'program_sha256': provenance['sha256']} + if 'publisher_link_alias' in evidence: + overlap = author_keys(record.get('authors', [])) & author_keys(evidence.pop('_authors', [])) + if normalized(record['title']) != normalized(evidence['program_title']) or len(overlap) < 2: + raise ValueError('Reviewed publisher-link alias lacks exact title and independent author corroboration') + evidence['corroborating_author_count'] = len(overlap) + if 'position_list_policy' in provenance: + evidence['position_list_policy'] = provenance['position_list_policy'] + record['track'] = evidence['track'] + record['metadata']['track_evidence'] = evidence + + +def require_track_manifest(manifest): + if (manifest.get('source') == 'pmlr' and str(manifest.get('venue', '')).upper() == 'ICML' + and int(manifest.get('year', 0)) >= 2024 + and (manifest.get('parser_version', 0) < 3 or not manifest.get('track_program'))): + raise ValueError('Recollect mixed ICML PMLR proceedings with parser_version>=3 and official track evidence') + + +def require_track_record(row, manifest): + require_track_manifest({**manifest, **{key: row.get(key) for key in ('source', 'venue', 'year')}}) + if manifest.get('track_program'): + evidence = row.get('metadata', {}).get('track_evidence', {}) + program = manifest['track_program'] + if (evidence.get('track') != row.get('track') or evidence.get('program_url') != program.get('url') + or evidence.get('program_sha256') != program.get('sha256') + or not evidence.get('event_ids') or evidence.get('identity_scheme') not in ('pmlr', 'openreview')): + raise ValueError('PMLR record differs from its official track evidence') + own = row['external_id'] if evidence['identity_scheme'] == 'pmlr' else row.get('identifiers', {}).get('openreview') + if not own or evidence.get('identity_value') != own: + raise ValueError('PMLR track evidence belongs to a different paper identity') diff --git a/paper_atlas/ingestion/backfill.py b/paper_atlas/ingestion/backfill.py index b943b4e..7b973e6 100644 --- a/paper_atlas/ingestion/backfill.py +++ b/paper_atlas/ingestion/backfill.py @@ -6,6 +6,7 @@ from pathlib import Path from paper_atlas.db.store import Store from paper_atlas.db.submissions import attach_submission,identities_for_row +from paper_atlas.collectors.pmlr_tracks import require_track_manifest, require_track_record def queue_files(path): @@ -21,6 +22,7 @@ def queue_files(path): def backfill(db,files): for filename in files: manifest=json.loads(Path(filename).with_suffix('.manifest.json').read_text()) + require_track_manifest(manifest) if manifest['source'] in ('colm','neurips','iclr_program') and manifest.get('parser_version',0)<2: raise ValueError('Recollect old parser output before submission evidence backfill') store=Store(db);c=store.conn;count=0 @@ -35,6 +37,7 @@ def backfill(db,files): seen.add(row['external_id']) if any(row.get(key)!=manifest.get(key) for key in ('source','venue','year','track')): raise ValueError('Evidence row differs from edition manifest') + require_track_record(row, manifest) record=c.execute('SELECT r.id,r.paper_id,r.metadata_json FROM source_records r JOIN sources s ON s.id=r.source_id WHERE s.name=? AND r.external_id=?',(row['source'],row['external_id'])).fetchone() edition=c.execute('SELECT e.id FROM editions e JOIN venues v ON v.id=e.venue_id WHERE v.acronym=? COLLATE NOCASE AND e.year=? AND e.track=?',(row['venue'],row['year'],row['track'])).fetchone() if not record or not edition:raise ValueError('Evidence backfill requires an already imported record and edition') diff --git a/paper_atlas/ingestion/records.py b/paper_atlas/ingestion/records.py index a06545d..b71020d 100644 --- a/paper_atlas/ingestion/records.py +++ b/paper_atlas/ingestion/records.py @@ -6,12 +6,14 @@ from pathlib import Path from paper_atlas.db.store import Store from paper_atlas.db.submissions import identities_for_row,timestamp +from paper_atlas.collectors.pmlr_tracks import require_track_manifest, require_track_record def ingest_file(db,path): path = Path(path) manifest_path = path.with_suffix('.manifest.json') manifest = json.loads(manifest_path.read_text()) if manifest_path.exists() else {} + require_track_manifest(manifest) if manifest.get('source') in ('colm','neurips') and manifest.get('parser_version',0)<2: raise ValueError('Recollect proceedings with parser_version>=2 before identity matching') if manifest.get('source')=='iclr_program' and manifest.get('parser_version',0)<2: @@ -36,6 +38,7 @@ def ingest_file(db,path): raise ValueError('Source differs from manifest') if any(key in manifest and manifest[key]!=row[key] for key in ('venue','year','track')): raise ValueError('Conference edition differs from manifest') + require_track_record(row, manifest) external = row['external_id'] if external in seen: raise ValueError('Duplicate external ID in one collected file: '+external) diff --git a/tests/test_index_core.py b/tests/test_index_core.py index 2f4373d..0e18a06 100644 --- a/tests/test_index_core.py +++ b/tests/test_index_core.py @@ -55,7 +55,7 @@ class StoreTests(unittest.TestCase): def test_manifest_count_mismatch_rolls_back_records(self): path=Path(self.tmp.name)/'source.jsonl' - path.write_text(json.dumps({'source':'pmlr','external_id':'v1/paper','url':'https://example.org/paper','title':'Paper','abstract':'Abstract','authors':[],'venue':'ICML','year':2025,'track':'main','status':'accepted'})+'\n') + path.write_text(json.dumps({'source':'pmlr','external_id':'v1/paper','url':'https://example.org/paper','title':'Paper','abstract':'Abstract','authors':[],'venue':'ICML','year':2023,'track':'main','status':'accepted'})+'\n') path.with_suffix('.manifest.json').write_text(json.dumps({'source':'pmlr','list_url':'https://example.org/list','count':2})) with self.assertRaisesRegex(ValueError,'differs'): ingest_file(self.db,path) @@ -100,7 +100,7 @@ class StoreTests(unittest.TestCase): def test_missing_abstract_is_checked_even_when_manifest_claims_complete(self): path=Path(self.tmp.name)/'incomplete.jsonl' - row={'source':'pmlr','external_id':'v1/paper','url':'https://example.org/paper','title':'Paper','abstract':None,'authors':[],'venue':'ICML','year':2025,'track':'main','status':'accepted'} + row={'source':'pmlr','external_id':'v1/paper','url':'https://example.org/paper','title':'Paper','abstract':None,'authors':[],'venue':'ICML','year':2023,'track':'main','status':'accepted'} path.write_text(json.dumps(row)+'\n') path.with_suffix('.manifest.json').write_text(json.dumps({'source':'pmlr','list_url':'https://example.org/list','count':1,'status':'collected','missing_abstract_count':0})) ingest_file(self.db,path) @@ -108,7 +108,7 @@ class StoreTests(unittest.TestCase): def test_manifest_edition_mismatch_rolls_back_instead_of_marking_coverage(self): path=Path(self.tmp.name)/'wrong-edition.jsonl' - row={'source':'pmlr','external_id':'v1/paper','url':'https://example.org/paper','title':'Paper','abstract':'Abstract','authors':[],'venue':'ICML','year':2025,'track':'main','status':'accepted'} + row={'source':'pmlr','external_id':'v1/paper','url':'https://example.org/paper','title':'Paper','abstract':'Abstract','authors':[],'venue':'ICML','year':2023,'track':'main','status':'accepted'} path.write_text(json.dumps(row)+'\n') path.with_suffix('.manifest.json').write_text(json.dumps({'source':'pmlr','list_url':'https://example.org/list','count':1,'year':2024})) with self.assertRaisesRegex(ValueError,'edition differs'): diff --git a/tests/test_pmlr.py b/tests/test_pmlr.py index e2da93e..9877532 100644 --- a/tests/test_pmlr.py +++ b/tests/test_pmlr.py @@ -25,7 +25,7 @@ class MetadataTests(unittest.TestCase): self.assertEqual(venue_key('ECML-PKDD'),'ECML-PKDD') def test_missing_abstract_is_reported_as_partial_collection(self): - config=b'shortname: ICML\nyear: 2025\nbooktitle: ICML\n' + 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) diff --git a/tests/test_pmlr_tracks.py b/tests/test_pmlr_tracks.py new file mode 100644 index 0000000..79f2f21 --- /dev/null +++ b/tests/test_pmlr_tracks.py @@ -0,0 +1,148 @@ +import copy +import json +from pathlib import Path +import tempfile +import unittest +from unittest.mock import patch + +from paper_atlas.collectors.pmlr import collect_volume +from paper_atlas.collectors.pmlr_tracks import program_tracks, record_track, position_list_policy +from paper_atlas.ingestion.records import ingest_file +from paper_atlas.ingestion.backfill import backfill + + +def event(forum='realForum1', track='Conference', event_id=1, year=2025, **values): + return {'id': event_id, 'sourceid': event_id, 'name': 'A published paper', + 'sourceurl': f'https://openreview.net/group?id=ICML.cc/{year}/' + track, + 'paper_url': 'https://openreview.net/forum?id=' + forum, + 'decision': 'Accept (Poster)', **values} + + +def program(*events, **changes): + return json.dumps({'count': len(events), 'results': list(events), **changes}).encode() + + +def record(forum='realForum1', external='v267/paper1', year=2025, title='A published paper'): + return {'source': 'pmlr', 'external_id': external, 'venue': 'ICML', 'year': year, + 'title': title, 'abstract': 'Original abstract', 'authors': ['Jane Doe', 'John Smith'], + 'identifiers': {'openreview': forum}, 'metadata': {}, 'track': 'main'} + + +class PmlrTrackTests(unittest.TestCase): + def provenance(self): + return {'url': 'https://icml.cc/static/virtual/data/icml-2025-orals-posters.json', 'sha256': 'a' * 64} + + def test_real_groups_not_title_prefixes_determine_modern_tracks(self): + mapping, inventory = program_tracks(program( + event(name='Position: still a main-track paper'), + event('position1', 'Position_Paper_Track', 2, name='No prefix needed'), + event('2025-Oral-fake', event_id=3, sourceid=-1), + event('workshop1', 'Workshop', 4)), 2025) + main = record(title='Position: still a main-track paper') + position = record('position1', 'v267/paper2', title='No prefix needed') + record_track(main, mapping, self.provenance()); record_track(position, mapping, self.provenance()) + self.assertEqual((main['track'], position['track']), ('main', 'position')) + self.assertEqual(inventory['paper_identity_count'], 2) + self.assertEqual(inventory['excluded_events'], {'synthetic_oral_event': 1, 'other_source': 1}) + + def test_conflicting_forums_pagination_and_missing_real_ids_fail(self): + for data in [program(event(), event(track='Position_Paper_Track', event_id=2)), + program(event(), next='page2'), program(event(), count=2), + program(event(paper_url='')), program(event(decision='Reject')), + program(event(), event())]: + with self.subTest(data=data), self.assertRaises(ValueError): + program_tracks(data, 2025) + + def test_missing_publication_identity_has_no_main_track_fallback(self): + mapping, _ = program_tracks(program(event()), 2025) + with self.assertRaisesRegex(ValueError, 'absent'): + record_track(record('unknownForum'), mapping, self.provenance()) + + def test_2024_requires_organizer_endorsed_list_and_publisher_self_links(self): + html = b'position papers' + policy = position_list_policy(html) + with self.assertRaises(ValueError): + position_list_policy(html.replace(b'2024', b'2023')) + e = event(year=2024, name='Position: An explicit position', paper_url='', + paper_pdf_url='https://proceedings.mlr.press/v235/paper1.html') + with self.assertRaisesRegex(ValueError, 'policy'): + program_tracks(program(e), 2024) + mapping, _ = program_tracks(program(e), 2024, policy) + row = record(external='v235/paper1', year=2024) + record_track(row, mapping, {**self.provenance(), 'position_list_policy': policy}) + self.assertEqual(row['track'], 'position') + self.assertEqual(row['metadata']['track_evidence']['identity_scheme'], 'pmlr') + + def test_reviewed_2024_link_alias_still_needs_title_and_two_authors(self): + e = event(year=2024, paper_url='', paper_pdf_url='https://proceedings.mlr.press/v235/theo24a.html', + authors=[{'fullname': 'Jane Doe'}, {'fullname': 'John Smith'}]) + mapping, _ = program_tracks(program(e), 2024, {'verified': True}) + row = record(external='v235/guyard24a', year=2024) + record_track(row, mapping, self.provenance()) + self.assertEqual(row['metadata']['track_evidence']['corroborating_author_count'], 2) + self.assertNotIn('_authors', row['metadata']['track_evidence']) + for changed in [dict(title='Different title'), dict(authors=['Someone Else'])]: + bad = record(external='v235/guyard24a', year=2024); bad.update(changed) + with self.assertRaisesRegex(ValueError, 'corroboration'): + record_track(bad, mapping, self.provenance()) + + def test_collector_splits_tracks_preserves_ids_and_imports_one_event_each(self): + config = b'shortname: ICML\nyear: 2025\nbooktitle: ICML\n' + template = '---\nid: {id}\nlayout: inproceedings\ntitle: {title}\nabstract: Original abstract\nopenreview: {forum}\n---\n' + posts = [('a.md', template.format(id='paper1', title='Main paper', forum='realForum1')), + ('b.md', template.format(id='paper2', title='Position paper', forum='position1'))] + mapping, inventory = program_tracks(program(event(), event('position1', 'Position_Paper_Track', 2)), 2025) + 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)), \ + patch('paper_atlas.collectors.pmlr.collect_track_evidence', return_value=(mapping, self.provenance())): + result = collect_volume(267, tmp, tmp) + self.assertNotIn('file', result) + self.assertEqual(result['track'], 'mixed') + self.assertEqual({m['track']: m['count'] for m in result['files']}, {'main': 1, 'position': 1}) + self.assertEqual(result['count'], 2) + db = Path(tmp) / 'papers.sqlite' + for manifest in result['files']: + ingest_file(db, manifest['file']) + import sqlite3 + with sqlite3.connect(db) as c: + self.assertEqual(c.execute('SELECT count(*) FROM submissions').fetchone()[0], 2) + self.assertEqual(c.execute('SELECT track,count(*) FROM submissions s JOIN editions e ON s.edition_id=e.id GROUP BY track').fetchall(), [('main', 1), ('position', 1)]) + self.assertEqual(c.execute('PRAGMA foreign_key_check').fetchall(), []) + + def test_unknown_track_does_not_replace_existing_volume_output(self): + config = b'shortname: ICML\nyear: 2025\nbooktitle: ICML\n' + post = '---\nid: paper1\nlayout: inproceedings\ntitle: Paper\nopenreview: missing123\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', post)])), \ + patch('paper_atlas.collectors.pmlr.collect_track_evidence', return_value=({}, self.provenance())): + old = Path(tmp) / 'pmlr-v267.jsonl'; old.write_text('previous collection') + with self.assertRaisesRegex(ValueError, 'absent'): + collect_volume(267, tmp, tmp) + self.assertEqual(old.read_text(), 'previous collection') + self.assertFalse((Path(tmp) / 'pmlr-v267.inventory.json').exists()) + + def test_old_mixed_manifest_is_rejected_before_opening_database(self): + with tempfile.TemporaryDirectory() as tmp: + path = Path(tmp) / 'pmlr-v267.jsonl'; path.write_text('') + path.with_suffix('.manifest.json').write_text(json.dumps({'source': 'pmlr', 'venue': 'ICML', 'year': 2025, 'parser_version': 2})) + db = Path(tmp) / 'absent.sqlite' + for action in [lambda: ingest_file(db, path), lambda: backfill(db, [path])]: + with self.assertRaisesRegex(ValueError, 'Recollect mixed'): + action() + self.assertFalse(db.exists()) + + def test_changed_track_or_own_identity_rolls_back_import(self): + from paper_atlas.collectors.pmlr_tracks import require_track_record + row = record(); mapping, _ = program_tracks(program(event()), 2025) + record_track(row, mapping, self.provenance()) + manifest = {'source': 'pmlr', 'venue': 'ICML', 'year': 2025, 'parser_version': 3, + 'track_program': self.provenance()} + require_track_record(row, manifest) + for change in [dict(track='position'), dict(identifiers={'openreview': 'otherForum'})]: + bad = copy.deepcopy(row); bad.update(change) + with self.assertRaises(ValueError): + require_track_record(bad, manifest) + + +if __name__ == '__main__': + unittest.main()