补核6项缺年候选并以登记证据纳入Zymbly

This commit is contained in:
2026-10-31 16:38:01 +08:00
parent ac04839571
commit baaea4fc61
6 changed files with 489 additions and 14 deletions
+10 -4
View File
@@ -173,12 +173,18 @@ def missing_year_followups():
assert len(set(urls)) == len(urls) and set(urls) <= original
evidence = {e['id']: e for e in DATA['evidence']}
for row in rows:
assert row['status'] in {'outside-cohort', 'pending-year', 'pending-ai'}
assert not row.get('companyId') and row.get('evidenceIds')
assert all(eid in evidence and evidence[eid]['companyId'] is None for eid in row['evidenceIds'])
assert row['status'] in {'outside-cohort', 'pending-year', 'pending-ai', 'linked'}
assert row.get('evidenceIds')
if row['status'] == 'linked':
matches = [r for r in DATA.get('directoryRechecks', []) if r['companyId'] == row.get('companyId')]
assert len(matches) == 1 and matches[0]['originalStatus'] == 'year-outside-or-missing'
assert all(eid in evidence and evidence[eid]['companyId'] == row['companyId'] for eid in row['evidenceIds'])
else:
assert not row.get('companyId')
assert all(eid in evidence and evidence[eid]['companyId'] is None for eid in row['evidenceIds'])
counts = Counter(row['status'] for row in rows)
return ['', '## 原缺少成立年名单的后续覆盖', '',
f"原快照缺年{len(original)}项,外部补核已有{len(rows)}项:{counts['outside-cohort']}项既有主体/业务范围外、{counts['pending-year']}项成立年待核、{counts['pending-ai']}项AI主营待核,{len(original)-len(rows)}项尚无本系列外部补核记录。", '',
f"原快照缺年{len(original)}项,外部补核已有{len(rows)}项:{counts['linked']}项关联公司、{counts['outside-cohort']}项既有主体/业务范围外、{counts['pending-year']}项成立年待核、{counts['pending-ai']}项AI主营待核,{len(original)-len(rows)}项尚无本系列外部补核记录。", '',
'当前YC缺年字段复读与外部主体核查分别统计。登记创建日、公司自述年、产品发布、条款更新和批次不相互替代;已查英国或法国主体不代表完整集团沿革已核。原54项发现计数不回写,也不以Inactive补零收入。', '']