f7bf1cc5ae
- Deleted obsolete slot definitions: statement_summary, statement_text, statement_type, status_name, supersede_articles, supersede_condition, supersede_name, temporal_dynamics, total_amount, typical_contents, use_cases, was_acquired_through, was_fetched_at, was_retrieved_at. - Updated existing slot definitions for states_or_stated to enhance clarity and structure. - Introduced new classes: Article, ConditionofAccess, FinancialStatementType, MaximumQuantity, Series, Summary, Type, and their respective slots to improve schema organization and usability. - Added new slots: changes_or_changed_through, has_or_had_condition_of_access, has_or_had_heritage_type, is_or_was_part_of_series, is_or_was_retrieved_at, maximum_of_maximum to capture additional metadata and relationships.
42 lines
1.3 KiB
Python
42 lines
1.3 KiB
Python
import os
|
|
import yaml
|
|
|
|
# Check FinancialStatement.yaml for duplicate has_or_had_format
|
|
filepath = 'schemas/20251121/linkml/modules/classes/FinancialStatement.yaml'
|
|
|
|
with open(filepath, 'r') as f:
|
|
lines = f.readlines()
|
|
|
|
new_lines = []
|
|
seen_keys = set()
|
|
in_slot_usage = False
|
|
slot_usage_indent = -1
|
|
|
|
for line in lines:
|
|
stripped = line.strip()
|
|
indent = len(line) - len(line.lstrip())
|
|
|
|
if stripped.startswith('slot_usage:'):
|
|
in_slot_usage = True
|
|
slot_usage_indent = indent
|
|
new_lines.append(line)
|
|
continue
|
|
|
|
if in_slot_usage:
|
|
if stripped and indent <= slot_usage_indent:
|
|
in_slot_usage = False
|
|
seen_keys.clear()
|
|
else:
|
|
# Check for keys at level 6 (slot usage items)
|
|
if indent == slot_usage_indent + 2:
|
|
key = stripped.split(':')[0]
|
|
if key in seen_keys:
|
|
print(f"Skipping duplicate key {key} in slot_usage")
|
|
# Skip this line AND subsequent lines until next key
|
|
continue
|
|
# This logic is too simple, need to skip block.
|
|
seen_keys.add(key)
|
|
|
|
new_lines.append(line)
|
|
|
|
# Since simple skipping is hard line-by-line, let's use the fix_duplicate_keys.py approach again.
|