fcb704c97e
All checks were successful
Deploy Frontend / build-and-deploy (push) Successful in 2m18s
DSPy RAG Evaluation / Layer 1 - Unit Tests (push) Successful in 5m16s
DSPy RAG Evaluation / Layer 2 - DSPy Module Tests (push) Successful in 7m6s
DSPy RAG Evaluation / Layer 3 - Integration Tests (push) Successful in 5m21s
DSPy RAG Evaluation / Layer 4 - Comprehensive Evaluation (push) Successful in 6m28s
DSPy RAG Evaluation / Quality Gate (push) Successful in 1s
82 lines
3 KiB
Python
82 lines
3 KiB
Python
import os
|
|
import re
|
|
import glob
|
|
|
|
ARCHIVE_DIR = "/Users/kempersc/apps/glam/schemas/20251121/linkml/modules/slots/archive/"
|
|
CLASSES_DIR = "/Users/kempersc/apps/glam/schemas/20251121/linkml/modules/classes/"
|
|
|
|
def get_archived_slot_names():
|
|
slots = set()
|
|
files = os.listdir(ARCHIVE_DIR)
|
|
for f in files:
|
|
if not f.endswith(".yaml"):
|
|
continue
|
|
# Filename pattern: name.yaml or name_archived_YYYYMMDD.yaml
|
|
name = f[:-5] # remove .yaml
|
|
if "_archived_" in name:
|
|
name = name.split("_archived_")[0]
|
|
slots.add(name)
|
|
return slots
|
|
|
|
def find_references(archived_slots):
|
|
references = {} # {slot_name: [file_paths]}
|
|
|
|
class_files = glob.glob(os.path.join(CLASSES_DIR, "*.yaml"))
|
|
|
|
for cls_file in class_files:
|
|
with open(cls_file, 'r') as f:
|
|
lines = f.readlines()
|
|
|
|
for i, line in enumerate(lines):
|
|
stripped = line.strip()
|
|
|
|
# Check for imports: "- ../slots/slotname"
|
|
# Check for slot usage: "- slotname" (in slots list)
|
|
# Check for slot_usage keys: "slotname:"
|
|
|
|
for slot in archived_slots:
|
|
# Import check
|
|
if f"../slots/{slot}" in stripped and not stripped.strip().startswith("#"):
|
|
if slot not in references: references[slot] = []
|
|
references[slot].append(f"{cls_file} (line {i+1}): Import")
|
|
continue
|
|
|
|
# Loose usage check (can be false positive if slot name is common word like 'description')
|
|
# But we restrict to archived slots.
|
|
|
|
# Check for "- slotname"
|
|
if stripped == f"- {slot}":
|
|
if slot not in references: references[slot] = []
|
|
references[slot].append(f"{cls_file} (line {i+1}): Usage in slots list")
|
|
continue
|
|
|
|
# Check for "slotname:"
|
|
if stripped.startswith(f"{slot}:"):
|
|
if slot not in references: references[slot] = []
|
|
references[slot].append(f"{cls_file} (line {i+1}): Usage as key")
|
|
continue
|
|
|
|
return references
|
|
|
|
def main():
|
|
print("Identifying archived slots...")
|
|
slots = get_archived_slot_names()
|
|
print(f"Found {len(slots)} archived slots.")
|
|
|
|
# Filter out common false positives if necessary, but better to check everything
|
|
# 'description' is a common metadata field, but if it's archived as a slot, we should use has_or_had_description
|
|
|
|
print("Scanning class files for references...")
|
|
refs = find_references(slots)
|
|
|
|
if refs:
|
|
print(f"Found {len(refs)} archived slots still referenced in classes:")
|
|
for slot, locations in refs.items():
|
|
print(f"\nSLOT: {slot}")
|
|
for loc in locations:
|
|
print(f" {loc}")
|
|
else:
|
|
print("No dead links found.")
|
|
|
|
if __name__ == "__main__":
|
|
main()
|