7cf10084b4
- Added `fix_dual_class_link.py` to remove dual class link references from specified YAML files. - Created `fix_specific_ghosts.py` to apply specific replacements in YAML files based on defined mappings. - Introduced `migrate_staff_count.py` to migrate staff count references to a new structure in specified YAML files. - Developed `migrate_type_slots.py` to replace type-related slots with new identifiers across YAML files. - Implemented `scan_ghost_references.py` to identify and report ghost references to archived slots and classes in YAML files. - Added `verify_ontology_terms.py` to verify the presence of ontology terms in specified ontology files against schema definitions.
102 lines
4.3 KiB
Python
102 lines
4.3 KiB
Python
import os
|
|
import yaml
|
|
import re
|
|
|
|
FILES = [
|
|
"/Users/kempersc/apps/glam/schemas/20251121/linkml/modules/classes/ConservationLab.yaml",
|
|
"/Users/kempersc/apps/glam/schemas/20251121/linkml/modules/classes/OrganizationBranch.yaml",
|
|
"/Users/kempersc/apps/glam/schemas/20251121/linkml/modules/classes/OrganizationalStructure.yaml",
|
|
"/Users/kempersc/apps/glam/schemas/20251121/linkml/modules/classes/ResearchCenter.yaml",
|
|
"/Users/kempersc/apps/glam/schemas/20251121/linkml/modules/classes/GiftShop.yaml"
|
|
]
|
|
|
|
def migrate_staff_count(filepath):
|
|
print(f"Processing {filepath}...")
|
|
try:
|
|
with open(filepath, 'r') as f:
|
|
lines = f.readlines()
|
|
|
|
new_lines = []
|
|
in_slot_usage_staff_count = False
|
|
staff_count_indent = 0
|
|
|
|
has_quantity_import = False
|
|
has_quantity_class_import = False
|
|
|
|
# First pass to check existing imports
|
|
for line in lines:
|
|
if "has_or_had_quantity" in line:
|
|
has_quantity_import = True
|
|
if "../classes/Quantity" in line:
|
|
has_quantity_class_import = True
|
|
|
|
for line in lines:
|
|
# 1. Imports
|
|
if line.strip() == "- ../slots/staff_count":
|
|
if not has_quantity_import:
|
|
new_lines.append("- ../slots/has_or_had_quantity\n")
|
|
has_quantity_import = True
|
|
if not has_quantity_class_import:
|
|
new_lines.append("- ../classes/Quantity\n")
|
|
has_quantity_class_import = True
|
|
continue
|
|
|
|
# 2. Slots list
|
|
if line.strip() == "- staff_count":
|
|
new_lines.append(line.replace("staff_count", "has_or_had_quantity"))
|
|
continue
|
|
|
|
# 3. Slot usage
|
|
if "staff_count:" in line and "range:" not in line: # start of slot_usage block
|
|
# Detect indentation
|
|
staff_count_indent = len(line) - len(line.lstrip())
|
|
in_slot_usage_staff_count = True
|
|
# Don't add this line
|
|
continue
|
|
|
|
if in_slot_usage_staff_count:
|
|
current_indent = len(line) - len(line.lstrip())
|
|
if current_indent > staff_count_indent:
|
|
# Skip lines inside staff_count block
|
|
continue
|
|
else:
|
|
# End of staff_count block
|
|
in_slot_usage_staff_count = False
|
|
# Add new slot usage for has_or_had_quantity if we want
|
|
# But simpler to just let the class use the default or manual add if needed
|
|
# Let's add a basic one
|
|
usage_indent = " " * staff_count_indent
|
|
new_lines.append(f"{usage_indent}has_or_had_quantity:\n")
|
|
new_lines.append(f"{usage_indent} range: Quantity\n")
|
|
new_lines.append(f"{usage_indent} inlined: true\n")
|
|
new_lines.append(f"{usage_indent} description: Quantity of staff members. MIGRATED from staff_count (2026-01-28).\n")
|
|
new_lines.append(line) # Add the line that broke the block
|
|
else:
|
|
# 4. Examples
|
|
# Simple regex replacement for examples: staff_count: 12
|
|
# This assumes examples are simple key-value pairs on one line
|
|
match = re.match(r"(\s+)staff_count:\s+(\d+)", line)
|
|
if match:
|
|
indent = match.group(1)
|
|
count = match.group(2)
|
|
new_lines.append(f"{indent}has_or_had_quantity:\n")
|
|
new_lines.append(f"{indent}- numeric_value: {count}\n")
|
|
new_lines.append(f"{indent} has_or_had_unit:\n")
|
|
new_lines.append(f"{indent} unit_text: staff_members\n")
|
|
else:
|
|
new_lines.append(line)
|
|
|
|
with open(filepath, 'w') as f:
|
|
f.writelines(new_lines)
|
|
|
|
print(f"Updated {filepath}")
|
|
|
|
except Exception as e:
|
|
print(f"Error processing {filepath}: {e}")
|
|
|
|
if __name__ == "__main__":
|
|
for f in FILES:
|
|
if os.path.exists(f):
|
|
migrate_staff_count(f)
|
|
else:
|
|
print(f"File not found: {f}")
|