"""Recheck archived citations against archived tool sources, without generation.

This changes only citation eligibility; it does not replace historical gold or
claim a new full semantic evaluation. Missing archived context is unverifiable.
"""
import argparse
import json
from pathlib import Path

from tools.graphrag.evaluation.reproducibility import sha256_file
from .context_policy import citation_check, allowed_urls


def main():
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument('--input', type=Path, action='append', required=True)
    parser.add_argument('--output', type=Path, required=True)
    args = parser.parse_args()
    if args.output.exists(): parser.error('Refusing to overwrite regrading.')
    reports = []
    for path in args.input:
        data = json.loads(path.read_text()); rows = []
        for old in data.get('questions', data.get('results', [])):
            answer = old.get('answer') or ''
            if isinstance(answer, str): answer = {'answer': answer, 'source_urls': []}
            context = old.get('graph_context')
            legacy_sources = ({row['source_url'] for row in context.get('documents', []) if row.get('source_url')}
                              if isinstance(context, dict) and 'documents' in context else None)
            urls = (allowed_urls(context) if isinstance(context, dict) and 'sources' in context else
                    legacy_sources if legacy_sources is not None else
                    set(old['rag_source_urls']) if isinstance(old.get('rag_source_urls'), list) else None)
            check = citation_check(answer, urls) if urls is not None else {'citations_ok': None, 'unsupported_urls': []}
            strict = bool(old.get('strict', old.get('strict_pass', False)))
            rows.append({'id': old['id'], 'previous_strict': strict, **check,
                         'citation_adjusted_strict': (strict and check['citations_ok']) if urls is not None else None})
        reports.append({'file': str(path), 'sha256': sha256_file(path), 'rows': rows,
            'summary': {'questions': len(rows), 'checked': sum(r['citations_ok'] is not None for r in rows),
                        'invalid_citations': sum(r['citations_ok'] is False for r in rows),
                        'previous_strict': sum(r['previous_strict'] for r in rows),
                        'strict_after_citation_check': sum(r['citation_adjusted_strict'] is True for r in rows)}})
    args.output.parent.mkdir(parents=True, exist_ok=True)
    args.output.write_text(json.dumps({'method': __doc__, 'files': reports}, ensure_ascii=False, indent=2)+'\n')
    print(json.dumps([{'file': r['file'], **r['summary']} for r in reports], ensure_ascii=False))


if __name__ == '__main__': main()