import json
import re
import sys

sys.stdout.reconfigure(encoding='utf-8')

with open(r'C:\Users\qq318\Desktop\rag-agent\test_files\rag_output.txt', 'r', encoding='utf-8') as f:
    for line in f:
        line = line.strip()
        if line.startswith('data: ') and '"type": "finish"' in line:
            data = json.loads(line[6:])
            citations = data.get('citations', [])
            print(f'Citation count: {len(citations)}')
            for i, c in enumerate(citations):
                coll = c.get('collection', '')
                cid = c.get('chunk_id', '')
                src = c.get('source', '')
                preview = c.get('content', '')[:80]
                print(f'  [{i+1}] collection={coll}, chunk_id={cid}, source={src}')
                print(f'       content: {preview}...')
            print()
            answer = data.get('answer', '')
            refs = re.findall(r'\[ref:([^\]]+)\]', answer)
            print(f'Ref tags in answer: {refs}')
            print(f'Answer preview: {answer[:200]}...')