diff --git a/docs/data-sources.md b/docs/data-sources.md
index 10f11e4..8a3b133 100644
--- a/docs/data-sources.md
+++ b/docs/data-sources.md
@@ -253,6 +253,25 @@ python3 -B -m paper_atlas query --db /data/paper-index/papers.sqlite \
只将 Conference 来源的论文视为 ICLR 主会录用，排除 Blog 和期刊转会展示，并在审计清单保存排除计数。2020/2021 旧数据允许依据官方主会 paper program 形成录用证据；无 forum ID 时保留 program 身份和匹配候选，不伪造标识。历史年度返回 404 会登记 unavailable，未来未发表届次登记 not_yet_published，其他访问或解析失败登记 blocked；这些状态都不能宣称该年已覆盖。
+ICLR 2020 的现代程序 JSON 没有真实 forum 链接，数字 event ID 也不能拼接为旧版海报地址。该年未核验身份的记录先使用官方 Papers 索引地址。旧版官方页面实际引用的 [papers.json](https://iclr.cc/virtual_2020/papers.json) 提供 687 个 forum；可用固定大小及 SHA-256 校验的副本进行独立身份核对：
+
+```sh
+paper-atlas download --url https://iclr.cc/virtual_2020/papers.json \
+ --output /data/paper-index/raw/iclr-2020-legacy-papers.json \
+ --expected-bytes 391687 \
+ --sha256 2405f2da6e2641fa600762f7d7cdf7c9d27f4d0ae65799168f3aee46036d30d2
+
+paper-atlas audit iclr-legacy \
+ --program /data/paper-index/collected/iclr-program-2020-main.jsonl \
+ --snapshot /data/paper-index/collected/openreview-snapshot-2020-main.jsonl \
+ --legacy /data/paper-index/raw/iclr-2020-legacy-papers.json \
+ --out /data/paper-index/collected/iclr-2020-verified
+```
+
+核对同时要求同届公开录用、唯一投稿编号和官方 forum 清单一致；编号只是候选关联，还必须有独立的标题/摘要/公开作者证据。旧版作者缩写或姓名格式差异不会放宽全库作者匹配规则。一篇 Explain Your Move 有三个来源中的三种标题，使用逐个核对的精确标题组合及至少两名共同公开作者作例外，不启用通用模糊标题合并。
+
+输出保留原 `2020/program-编号` 来源 ID、标题、摘要和作者，补充真实 forum、核验证据和旧版官方海报 URL。它不写数据库，也不修改输入文件。先在维护锁下使用输出的 `iclr-2020-backfill-queue.json` 给已有程序投稿回填身份，再导入核验后的程序文件与原始投稿快照；这样补充拒稿不会把已有录用事件再建一次。`iclr-2020-snapshot-queue.json` 和审计报告均记录待用文件的哈希，合并前仍须复核。
+
主题、关键词使用 `iclr_program:topic`、`iclr_program:keyword` 命名空间。通用导入器按源记录刷新标签证据，保留同一论文其他源记录及 `custom:*` 标签。每年的 JSONL、manifest、`iclr-program-year-status.json` 和 `iclr-program-last-run.json` 保存实际范围、独立展示数、主会展示数、论文数、缺失摘要与缺失 forum 数。录用程序不能提供拒稿全集，公开投稿及拒稿补充仍需独立来源。
### CVF / ECVA 视觉会议元数据
diff --git a/paper_atlas/audits/iclr_legacy.py b/paper_atlas/audits/iclr_legacy.py
new file mode 100644
index 0000000..debd531
--- /dev/null
+++ b/paper_atlas/audits/iclr_legacy.py
@@ -0,0 +1,172 @@
+"""Reconcile the 2020 program with independently identified official papers."""
+import argparse
+from collections import Counter, defaultdict
+import copy
+import fcntl
+import hashlib
+import json
+from pathlib import Path
+import re
+import tempfile
+
+from paper_atlas.audits.iclr import load
+from paper_atlas.db.store import author_keys, normalized
+from paper_atlas.db.submissions import timestamp
+
+
+LEGACY_URL = 'https://iclr.cc/virtual_2020/papers.json'
+LEGACY_SHA256 = '2405f2da6e2641fa600762f7d7cdf7c9d27f4d0ae65799168f3aee46036d30d2'
+LEGACY_BYTES = 391687
+EXPECTED = 687
+# This one paper has three documented titles across the pinned official legacy
+# list, current official program, and public submission snapshot. The exception
+# also requires independent public-author agreement; it is not fuzzy matching.
+REVIEWED_TITLE_VARIANT = {
+ 'forum': 'SJgzLkBKPB',
+ 'program': 'Explain Your Move: Understanding Agent Actions Using Salient and Relevant Feature Attribution',
+ 'legacy': 'Explain Your Move: Understanding Agent Actions Using Focused Feature Saliency',
+ 'snapshot': 'Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution',
+}
+
+
+def reconcile(program, snapshot, legacy):
+ by_number = defaultdict(list)
+ for row in snapshot.values():
+ by_number[row['metadata'].get('source_submission_number')].append(row)
+ legacy_by_forum = {}
+ for note in legacy:
+ forum = note.get('forum')
+ content = note.get('content') or {}
+ if not isinstance(forum, str) or not re.fullmatch(r'[A-Za-z0-9_-]+', forum):
+ raise ValueError('Invalid legacy forum identity')
+ if note.get('id') != forum or content.get('iclr_id') != forum or forum in legacy_by_forum:
+ raise ValueError('Conflicting or repeated official legacy forum')
+ if not isinstance(content.get('title'), str) or not content['title'].strip() or not isinstance(content.get('authors'), list):
+ raise ValueError('Legacy paper lacks title or public authors')
+ legacy_by_forum[forum] = content
+ if len(program) != len(legacy_by_forum):
+ raise ValueError('Official program and legacy inventories differ')
+ title_counts = Counter(normalized(row['title']) for row in legacy_by_forum.values())
+ enriched = []
+ assigned = set()
+ numbers = set()
+ evidence_counts = Counter()
+ for original in program:
+ if any(original.get(k) != v for k, v in {'source': 'iclr_program', 'venue': 'ICLR', 'year': 2020, 'track': 'main', 'status': 'accepted'}.items()):
+ raise ValueError('Program record is outside the accepted 2020 main track')
+ metadata = original.get('metadata') or {}
+ number = metadata.get('program_source_id')
+ if metadata.get('program_identity_type') != 'submission' or type(number) is not int or number <= 0 or number in numbers:
+ raise ValueError('Missing or repeated program submission number')
+ numbers.add(number)
+ candidates = by_number[number]
+ if len(candidates) != 1:
+ raise ValueError('Submission number is absent or ambiguous in the public snapshot')
+ submission = candidates[0]
+ forum = submission['identifiers']['openreview']
+ if submission['status'] != 'accepted' or forum not in legacy_by_forum or forum in assigned:
+ raise ValueError('Snapshot acceptance and official forum inventory do not agree')
+ content = legacy_by_forum[forum]
+ shared_legacy = len(author_keys(original['authors']) & author_keys(content['authors']))
+ shared_snapshot = len(author_keys(original['authors']) & author_keys(submission['authors']))
+ checks = {'legacy_title': normalized(original['title']) == normalized(content['title']),
+ 'snapshot_title': normalized(original['title']) == normalized(submission['title']),
+ 'snapshot_abstract': bool(original.get('abstract')) and original['abstract'].strip() == (submission.get('abstract') or '').strip(),
+ 'two_snapshot_authors': shared_snapshot >= 2}
+ independent_snapshot = sum(checks[k] for k in ('snapshot_title', 'snapshot_abstract', 'two_snapshot_authors')) >= 2
+ checks['legacy_title_unique'] = title_counts[normalized(content['title'])] == 1
+ independent_legacy = checks['legacy_title'] and checks['legacy_title_unique'] and shared_legacy >= 1
+ reviewed_variant = (forum == REVIEWED_TITLE_VARIANT['forum']
+ and normalized(original['title']) == normalized(REVIEWED_TITLE_VARIANT['program'])
+ and normalized(content['title']) == normalized(REVIEWED_TITLE_VARIANT['legacy'])
+ and normalized(submission['title']) == normalized(REVIEWED_TITLE_VARIANT['snapshot'])
+ and shared_legacy >= 2 and shared_snapshot >= 2)
+ if not (independent_snapshot or independent_legacy or reviewed_variant):
+ raise ValueError('Submission number alone cannot establish forum identity: ' + original['external_id'])
+ own = original.get('identifiers') or {}
+ if own.get('openreview') not in (None, forum):
+ raise ValueError('Existing program forum conflicts with independent evidence')
+ row = copy.deepcopy(original)
+ row['identifiers'] = {**own, 'openreview': forum}
+ row['url'] = 'https://iclr.cc/virtual_2020/poster_' + forum + '.html'
+ row['metadata'].update(identity_state='forum', program_submission_number_verified=True,
+ program_identity_verification={'method': 'official_legacy_and_public_submission_crosscheck',
+ 'legacy_url': LEGACY_URL, 'legacy_sha256': LEGACY_SHA256,
+ 'original_program_url': original['url'], 'legacy_forum': forum,
+ 'checks': checks, 'shared_legacy_authors': shared_legacy,
+ 'shared_snapshot_authors': shared_snapshot, 'reviewed_title_variant': reviewed_variant})
+ enriched.append(row)
+ assigned.add(forum)
+ evidence_counts.update({'independent_snapshot': int(independent_snapshot),
+ 'independent_legacy': int(independent_legacy),
+ 'reviewed_title_variant': int(reviewed_variant)})
+ if assigned != legacy_by_forum.keys():
+ raise ValueError('Unmatched official legacy forum identities remain')
+ if assigned != {forum for forum, row in snapshot.items() if row['status'] == 'accepted'}:
+ raise ValueError('Accepted snapshot forum inventory differs from the official program')
+ return enriched, dict(evidence_counts)
+
+
+def audit(program_path, snapshot_path, legacy_path, out):
+ program_path, snapshot_path, legacy_path = map(lambda p: Path(p).resolve(), (program_path, snapshot_path, legacy_path))
+ raw = legacy_path.read_bytes()
+ if len(raw) != LEGACY_BYTES or hashlib.sha256(raw).hexdigest() != LEGACY_SHA256:
+ raise ValueError('Official legacy snapshot checksum mismatch')
+ legacy = json.loads(raw)
+ if not isinstance(legacy, list) or len(legacy) != EXPECTED:
+ raise ValueError('Official legacy count mismatch')
+ manifest = json.loads(program_path.with_suffix('.manifest.json').read_text())
+ if manifest.get('parser_version', 0) < 2 or any(manifest.get(k) != v for k, v in {'source': 'iclr_program', 'venue': 'ICLR', 'year': 2020, 'track': 'main', 'count': EXPECTED}.items()):
+ raise ValueError('Invalid collected program inventory')
+ program_bytes = program_path.read_bytes()
+ program = [json.loads(line) for line in program_bytes.splitlines()]
+ if len(program) != EXPECTED or len({r['external_id'] for r in program}) != EXPECTED:
+ raise ValueError('Program count or source identity mismatch')
+ snapshot, snapshot_manifest, snapshot_sha = load(snapshot_path, 'openreview_snapshot', 2020)
+ rows, checks = reconcile(program, snapshot, legacy)
+ out = Path(out).resolve()
+ if out / 'iclr-program-2020-main.jsonl' in (program_path, snapshot_path, legacy_path):
+ raise ValueError('Output must preserve the original input files')
+ out.mkdir(parents=True, exist_ok=True)
+ with (out / 'iclr-legacy.lock').open('a') as lock:
+ fcntl.flock(lock, fcntl.LOCK_EX | fcntl.LOCK_NB)
+ if (out / 'iclr-2020-identity-audit.json').exists():
+ raise ValueError('Completed identity audit exists; choose a new output directory')
+ with tempfile.TemporaryDirectory(prefix='.iclr-legacy-', dir=out) as temporary:
+ stage = Path(temporary)
+ path = stage / 'iclr-program-2020-main.jsonl'
+ path.write_text(''.join(json.dumps(row, ensure_ascii=False) + '\n' for row in rows))
+ digest = hashlib.sha256(path.read_bytes()).hexdigest()
+ manifest.update(parser_version=3, file=str(out / path.name), file_sha256=digest,
+ missing_forum_count=0, legacy_identity_sha256=LEGACY_SHA256)
+ path.with_suffix('.manifest.json').write_text(json.dumps(manifest, indent=2) + '\n')
+ backfill = {'files': [str(out / path.name)], 'file_sha256': {str(out / path.name): digest}}
+ snapshots = {'files': [str(snapshot_path)], 'file_sha256': {str(snapshot_path): snapshot_sha}}
+ result = {'year': 2020, 'checked_at': timestamp(), 'program_records': len(rows),
+ 'snapshot_records': len(snapshot), 'snapshot_status_counts': snapshot_manifest['submission_status_counts'],
+ 'legacy_url': LEGACY_URL, 'legacy_sha256': LEGACY_SHA256,
+ 'program_input_sha256': hashlib.sha256(program_bytes).hexdigest(),
+ 'corroboration_counts': checks, 'backfill_queue': backfill, 'snapshot_files': snapshots,
+ 'note': 'No database writes. Backfill existing program identities before importing the snapshot; source IDs, titles and abstracts are preserved.'}
+ (stage / 'iclr-2020-backfill-queue.json').write_text(json.dumps(backfill, indent=2) + '\n')
+ (stage / 'iclr-2020-snapshot-queue.json').write_text(json.dumps(snapshots, indent=2) + '\n')
+ report = stage / 'iclr-2020-identity-audit.json'
+ report.write_text(json.dumps(result, ensure_ascii=False, indent=2) + '\n')
+ for child in sorted(stage.iterdir(), key=lambda child: child == report):
+ child.replace(out / child.name)
+ print(json.dumps(result), flush=True)
+ return result
+
+
+def main(argv=None, *, prog=None):
+ parser = argparse.ArgumentParser(prog=prog)
+ parser.add_argument('--program', required=True)
+ parser.add_argument('--snapshot', required=True)
+ parser.add_argument('--legacy', required=True)
+ parser.add_argument('--out', required=True)
+ args = parser.parse_args(argv)
+ audit(args.program, args.snapshot, args.legacy, args.out)
+
+
+if __name__ == '__main__':
+ main()
diff --git a/paper_atlas/cli.py b/paper_atlas/cli.py
index 3e0d414..25722ed 100644
--- a/paper_atlas/cli.py
+++ b/paper_atlas/cli.py
@@ -28,6 +28,7 @@ COMMANDS = {
('maintain','backfill'): ('paper_atlas.ingestion.backfill', {}, '回填既有投稿的来源身份'),
('maintain','arxiv-tags'): ('paper_atlas.ingestion.arxiv_tags', {}, '恢复逐来源记录的 arXiv 类别证据'),
('audit','iclr'): ('paper_atlas.audits.iclr', {}, '核对 ICLR 快照与同届官方程序'),
+ ('audit','iclr-legacy'): ('paper_atlas.audits.iclr_legacy', {}, '独立核验 ICLR 2020 旧目录投稿身份'),
('audit','arxiv'): ('paper_atlas.audits.arxiv', {}, '核验 arXiv 原始编号、重复行与 ZIP 完整性'),
('audit','public-openreview'): ('paper_atlas.audits.public_openreview', {}, '核对公开负面决定与已有投稿历史'),
}
diff --git a/paper_atlas/collectors/iclr.py b/paper_atlas/collectors/iclr.py
index b6a7610..2a6b621 100644
--- a/paper_atlas/collectors/iclr.py
+++ b/paper_atlas/collectors/iclr.py
@@ -141,6 +141,10 @@ def parse_program(data, abstracts, year, index_url):
external = f'{year}/{forum}' if forum else f'{year}/program-{identity[1]}'
missing_identity += not bool(forum)
page = urljoin(ROOT, primary.get('virtualsite_url') or f'/virtual/{year}/{str(primary.get("eventtype", "Poster")).lower()}/{primary["id"]}')
+ if year == 2020 and not primary.get('virtualsite_url'):
+ # Numeric modern event IDs do not identify legacy poster pages.
+ # The independently verified forum bridge supplies the paper URL.
+ page = index_url
topics = sorted({str(row['topic']).strip() for row in group if row.get('topic')})
keywords = sorted({str(keyword).strip() for row in group for keyword in row.get('keywords', []) if keyword})
records.append({'source': SOURCE, 'external_id': external, 'url': page,
diff --git a/tests/test_iclr.py b/tests/test_iclr.py
index dd595ff..313ee08 100644
--- a/tests/test_iclr.py
+++ b/tests/test_iclr.py
@@ -64,6 +64,7 @@ class ICLRTests(unittest.TestCase):
rows,_=self.parse([dict(row,paper_pdf_url=None)],year=2020)
self.assertEqual(rows[0]['metadata']['identity_state'],'program_only')
self.assertEqual(rows[0]['identifiers'],{})
+ self.assertEqual(rows[0]['url'],'https://iclr.cc/virtual/2020/papers.html')
def test_only_referenced_official_assets_and_real_navigation_years(self):
html='201320262025'
diff --git a/tests/test_iclr_legacy.py b/tests/test_iclr_legacy.py
new file mode 100644
index 0000000..151bec4
--- /dev/null
+++ b/tests/test_iclr_legacy.py
@@ -0,0 +1,143 @@
+import copy
+import hashlib
+import json
+from pathlib import Path
+import tempfile
+import unittest
+from unittest.mock import patch
+
+from paper_atlas.audits import iclr_legacy
+from paper_atlas.ingestion.backfill import backfill, queue_files
+from paper_atlas.ingestion.records import ingest_file
+from paper_atlas.db.store import Store
+
+
+class ICLRLegacyTests(unittest.TestCase):
+ def program(self):
+ return {'source': 'iclr_program', 'external_id': '2020/program-42', 'venue': 'ICLR',
+ 'year': 2020, 'track': 'main', 'status': 'accepted',
+ 'url': 'https://iclr.cc/virtual/2020/papers.html', 'title': 'Historical paper title',
+ 'abstract': 'Historical abstract', 'authors': ['Jane Doe', 'John Smith'],
+ 'identifiers': {}, 'raw_decision': 'listed in official program',
+ 'evidence_url': 'https://iclr.cc/virtual/2020/papers.html',
+ 'metadata': {'program_identity_type': 'submission', 'program_source_id': 42}}
+
+ def snapshot(self):
+ return {'source': 'openreview_snapshot', 'external_id': '2020/realForum', 'venue': 'ICLR',
+ 'year': 2020, 'track': 'main', 'status': 'accepted',
+ 'url': 'https://openreview.net/forum?id=realForum', 'title': 'Historical paper title',
+ 'abstract': 'Historical abstract', 'authors': ['Jane Doe', 'John Smith'],
+ 'identifiers': {'openreview': 'realForum'},
+ 'submission_identifiers': [{'scheme': 'openreview', 'value': 'realForum'},
+ {'scheme': 'iclr_number', 'value': '42'}],
+ 'decision_events': [{'status': 'accepted', 'raw_value': 'Accept',
+ 'source_decision_id': 'decision1', 'evidence_url': 'https://openreview.net/forum?id=realForum¬eId=decision1',
+ 'authority': {'public_readers_verified': True}}],
+ 'metadata': {'source_submission_number': 42, 'public_readers_verified': True}}
+
+ def legacy(self):
+ return {'id': 'realForum', 'forum': 'realForum', 'content': {
+ 'iclr_id': 'realForum', 'title': 'Historical paper title', 'authors': ['Jane Doe', 'John Smith']}}
+
+ def test_independent_legacy_identity_preserves_existing_source_id_and_text(self):
+ program, submission = self.program(), self.snapshot()
+ submission.update(title='A later title', abstract='A later abstract', authors=['Jane Doe'])
+ rows, checks = iclr_legacy.reconcile([program], {'realForum': submission}, [self.legacy()])
+ self.assertEqual(rows[0]['external_id'], '2020/program-42')
+ self.assertEqual(rows[0]['url'], 'https://iclr.cc/virtual_2020/poster_realForum.html')
+ for field in ('title', 'abstract', 'authors'):
+ self.assertEqual(rows[0][field], program[field])
+ self.assertEqual(rows[0]['identifiers']['openreview'], 'realForum')
+ self.assertTrue(rows[0]['metadata']['program_submission_number_verified'])
+ self.assertEqual(checks['independent_legacy'], 1)
+ self.assertEqual(program['identifiers'], {})
+
+ def test_program_number_and_shared_authors_alone_do_not_assign_a_forum(self):
+ program = self.program()
+ program.update(title='A different paper', abstract='An unrelated abstract')
+ with self.assertRaisesRegex(ValueError, 'number alone'):
+ iclr_legacy.reconcile([program], {'realForum': self.snapshot()}, [self.legacy()])
+
+ def test_independent_snapshot_title_and_abstract_handle_legacy_name_variants(self):
+ legacy = self.legacy()
+ legacy['content']['authors'] = ['J. Doe', 'J. Smith']
+ rows, checks = iclr_legacy.reconcile([self.program()], {'realForum': self.snapshot()}, [legacy])
+ self.assertEqual(checks['independent_snapshot'], 1)
+ self.assertEqual(rows[0]['identifiers']['openreview'], 'realForum')
+
+ def test_reviewed_title_variant_is_exact_and_requires_public_author_corroboration(self):
+ variant = iclr_legacy.REVIEWED_TITLE_VARIANT
+ program, submission, legacy = self.program(), self.snapshot(), self.legacy()
+ program['title'] = variant['program']
+ submission.update(title=variant['snapshot'], abstract='A different revision')
+ submission['identifiers']['openreview'] = variant['forum']
+ legacy.update(id=variant['forum'], forum=variant['forum'])
+ legacy['content'].update(iclr_id=variant['forum'], title=variant['legacy'])
+ rows, checks = iclr_legacy.reconcile([program], {variant['forum']: submission}, [legacy])
+ self.assertEqual(checks['reviewed_title_variant'], 1)
+ self.assertTrue(rows[0]['metadata']['program_identity_verification']['reviewed_title_variant'])
+ program['authors'] = ['Jane Doe']
+ with self.assertRaisesRegex(ValueError, 'number alone'):
+ iclr_legacy.reconcile([program], {variant['forum']: submission}, [legacy])
+
+ def test_conflicting_forum_ambiguous_number_and_repeated_legacy_identity_fail(self):
+ p = self.program()
+ p['identifiers']['openreview'] = 'anotherForum'
+ with self.assertRaisesRegex(ValueError, 'conflicts'):
+ iclr_legacy.reconcile([p], {'realForum': self.snapshot()}, [self.legacy()])
+ duplicate = copy.deepcopy(self.snapshot())
+ duplicate['identifiers']['openreview'] = 'otherForum'
+ with self.assertRaisesRegex(ValueError, 'ambiguous'):
+ iclr_legacy.reconcile([self.program()], {'realForum': self.snapshot(), 'otherForum': duplicate}, [self.legacy()])
+ with self.assertRaisesRegex(ValueError, 'repeated'):
+ iclr_legacy.reconcile([self.program()], {'realForum': self.snapshot()}, [self.legacy(), self.legacy()])
+
+ def write_file(self, path, rows, source):
+ path.write_text(''.join(json.dumps(row) + '\n' for row in rows))
+ manifest = {'source': source, 'venue': 'ICLR', 'year': 2020, 'track': 'main',
+ 'parser_version': 2, 'count': len(rows), 'missing_abstract_count': 0,
+ 'list_url': 'https://iclr.cc/virtual/2020/papers.html', 'status': 'collected',
+ 'submission_status_counts': {status: sum(r['status'] == status for r in rows)
+ for status in {r['status'] for r in rows}}}
+ path.with_suffix('.manifest.json').write_text(json.dumps(manifest))
+
+ def test_audited_bridge_then_snapshot_import_keeps_one_accepted_attempt(self):
+ with tempfile.TemporaryDirectory() as tmp:
+ root = Path(tmp)
+ program_path, snapshot_path, legacy_path = (root / name for name in ('program.jsonl', 'snapshot.jsonl', 'legacy.json'))
+ self.write_file(program_path, [self.program()], 'iclr_program')
+ self.write_file(snapshot_path, [self.snapshot()], 'openreview_snapshot')
+ raw = json.dumps([self.legacy()]).encode()
+ legacy_path.write_bytes(raw)
+ with patch.multiple(iclr_legacy, LEGACY_BYTES=len(raw), LEGACY_SHA256=hashlib.sha256(raw).hexdigest(), EXPECTED=1):
+ report = iclr_legacy.audit(program_path, snapshot_path, legacy_path, root / 'out')
+ db = root / 'papers.sqlite'
+ ingest_file(db, program_path)
+ queue = root / 'out/iclr-2020-backfill-queue.json'
+ result = backfill(db, queue_files(queue))
+ self.assertEqual(result['submissions_before'], result['submissions_after'])
+ ingest_file(db, report['backfill_queue']['files'][0])
+ ingest_file(db, snapshot_path)
+ store = Store(db)
+ try:
+ self.assertEqual(store.conn.execute('SELECT count(*) FROM papers').fetchone()[0], 1)
+ self.assertEqual(store.conn.execute('SELECT count(*) FROM submissions').fetchone()[0], 1)
+ self.assertEqual(store.conn.execute('SELECT count(*) FROM submission_sources').fetchone()[0], 2)
+ self.assertEqual(store.conn.execute('SELECT url FROM source_records WHERE external_id=?', ('2020/program-42',)).fetchone()[0],
+ 'https://iclr.cc/virtual_2020/poster_realForum.html')
+ self.assertEqual(store.conn.execute('PRAGMA foreign_key_check').fetchall(), [])
+ finally:
+ store.conn.close()
+
+ def test_unverified_legacy_bytes_publish_no_output(self):
+ with tempfile.TemporaryDirectory() as tmp:
+ root = Path(tmp)
+ legacy = root / 'legacy.json'
+ legacy.write_text('[]')
+ with self.assertRaisesRegex(ValueError, 'checksum'):
+ iclr_legacy.audit(root / 'program', root / 'snapshot', legacy, root / 'out')
+ self.assertFalse((root / 'out').exists())
+
+
+if __name__ == '__main__':
+ unittest.main()