e5a532a8bc
- Introduced `test_nlp_extractor.py` with unit tests for the InstitutionExtractor, covering various extraction patterns (ISIL, Wikidata, VIAF, city names) and ensuring proper classification of institutions (museum, library, archive). - Added tests for extracted entities and result handling to validate the extraction process. - Created `test_partnership_rdf_integration.py` to validate the end-to-end process of extracting partnerships from a conversation and exporting them to RDF format. - Implemented tests for temporal properties in partnerships and ensured compliance with W3C Organization Ontology patterns. - Verified that extracted partnerships are correctly linked with PROV-O provenance metadata.
46 lines
1.5 KiB
Python
46 lines
1.5 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Fix BCE dates by using placeholder date '0001-01-01' for ancient events.
|
|
|
|
For archaeological sites with BCE founding dates, we use:
|
|
- event_date: '0001-01-01' (earliest representable date in ISO 8601)
|
|
- event_description: Contains the actual BCE date context
|
|
"""
|
|
|
|
import yaml
|
|
from pathlib import Path
|
|
|
|
# Paths
|
|
LIBYA_YAML = Path(__file__).parent.parent / "data/instances/libya/libyan_institutions.yaml"
|
|
|
|
def main():
|
|
print("Fixing BCE date events with placeholder dates...\n")
|
|
|
|
# Load YAML
|
|
with open(LIBYA_YAML, 'r', encoding='utf-8') as f:
|
|
data = yaml.safe_load(f)
|
|
|
|
fixes = 0
|
|
|
|
for inst in data:
|
|
name = inst.get('name', '')
|
|
|
|
if 'change_history' in inst and inst['change_history']:
|
|
for event in inst['change_history']:
|
|
# If event has no event_date (removed because it was BCE)
|
|
if 'event_date' not in event:
|
|
# Add placeholder date for ancient events
|
|
event['event_date'] = '0001-01-01'
|
|
fixes += 1
|
|
print(f"✅ {name}: Added placeholder date for ancient event")
|
|
|
|
# Save
|
|
if fixes > 0:
|
|
with open(LIBYA_YAML, 'w', encoding='utf-8') as f:
|
|
yaml.dump(data, f, allow_unicode=True, sort_keys=False, default_flow_style=False)
|
|
print(f"\n💾 Saved {fixes} fixes to {LIBYA_YAML}")
|
|
else:
|
|
print("No fixes needed!")
|
|
|
|
if __name__ == '__main__':
|
|
main()
|