import json
import sys

# Read roster
with open(r'C:\Users\decid\AppData\Local\Temp\claude\C--Users-decid-Documents-projects\f6498a32-4d94-4746-9b85-956d8b1953da\scratchpad\dispatch-stage-C\slices\s1c\r071.json', encoding='utf-8') as f:
    content = f.read()
    roster = json.loads(content)

# Build req map
req_map = {}
for req in roster:
    req_map[req['id']] = {
        'title': req['title'],
        'doc': req.get('doc', '')
    }

# Read pairs
with open(r'C:\Users\decid\AppData\Local\Temp\claude\C--Users-decid-Documents-projects\f6498a32-4d94-4746-9b85-956d8b1953da\scratchpad\dispatch-stage-C\slices\s1c\q071.tsv', encoding='utf-8') as f:
    pairs_lines = [line.strip() for line in f if line.strip()]

pairs = []
for line in pairs_lines:
    parts = line.split('\t')
    if len(parts) == 2:
        pairs.append({'a': parts[0], 'b': parts[1]})

print(f"Total pairs: {len(pairs)}")
print(f"Sample pair 0: {pairs[0]}")
print(f"Sample pair 1: {pairs[1]}")

# Verify all required req IDs exist
missing = []
for p in pairs:
    if p['a'] not in req_map:
        missing.append(p['a'])
    if p['b'] not in req_map:
        missing.append(p['b'])

if missing:
    print(f"Missing requirements: {set(missing)}")
else:
    print("All requirement IDs found")

# Save structured data
output = {
    'pairs': pairs,
    'req_map': req_map
}
with open(r'C:\temp\scoring_data.json', 'w', encoding='utf-8') as f:
    json.dump(output, f, ensure_ascii=False, indent=2)
print("Saved scoring data")