Classify two SR004 businesses and preserve unresolved brand founding dates

This commit is contained in:
2026-11-01 02:28:52 +08:00
parent d631be2617
commit 9c32f77722
6 changed files with 437 additions and 44 deletions
+4
View File
@@ -93,6 +93,10 @@ def source_register():
assert sum(e['foundedYear'] in [2025, 2026] for e in entries) == audit['targetYearSelfReports']
assert sum(candidates[e['candidateId']]['status'] == 'linked' for e in entries) == audit['newLinkedCompanies']
assert sum(candidates[e['candidateId']]['status'] == 'pending-ai' for e in entries) == audit['pendingCurrentAIOrIdentity']
assert sum(candidates[e['candidateId']]['status'] == 'pending-year' for e in entries) == audit['pendingFoundingIdentity']
assert audit['targetYearSelfReports'] == (
audit['newLinkedCompanies'] + audit['pendingCurrentAIOrIdentity'] + audit['pendingFoundingIdentity']
), 'self-reported years must retain unresolved brand/entity dates'
if source['url']:
assert urlsplit(source['url']).scheme in {'http', 'https'} and urlsplit(source['url']).netloc
for host in source['hosts']: