"""Write and verify two staging batches from original synthetic fixtures."""
import argparse
import hashlib
import json
from pathlib import Path
import tempfile
from quarantine import validate_batch, write_batch

ROOT = Path(__file__).resolve().parent


def record():
    reports = {}
    with tempfile.TemporaryDirectory(prefix='mlops-validation-') as temporary:
        for name in ('events.jsonl', 'valid-events.jsonl'):
            raw = (ROOT / name).read_bytes()
            target = Path(temporary) / name
            manifest = write_batch(validate_batch(raw), target)
            assert (target / 'source.bin').read_bytes() == raw
            assert all(hashlib.sha256((target / file).read_bytes()).hexdigest() == digest for file,digest in manifest['files'].items())
            reports[name] = manifest
    return {'mode': 'Local synthetic JSON Lines validation and real staging writes; no training or model',
            'files': {name: hashlib.sha256((ROOT / name).read_bytes()).hexdigest() for name in
                      ('quarantine.py', 'inspect_dataset.py', 'vendor/availability.py', 'events.jsonl', 'valid-events.jsonl')},
            'batches': reports}


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('--save', type=Path)
    parser.add_argument('--check', action='store_true')
    args = parser.parse_args()
    result = record()
    if args.check and result != json.loads((ROOT / 'result.json').read_text()):
        raise SystemExit('validation results or source bindings differ')
    if args.save:
        args.save.write_text(json.dumps(result, indent=2)+'\n')
    print('Synthetic event batches; original bytes retained, no automatic repair')
    for name, row in result['batches'].items():
        print(f"{name}: {row['status']}; source={row['source_lines']}; accepted={row['accepted']}; "
              f"quarantined={row['quarantined']}; training_file={row['training_file']}")
    print('The valid fixture is a separate reference batch, not the dirty batch with bad rows silently removed.')


if __name__ == '__main__':
    main()