#!/usr/bin/env /usr/local/miniconda3/bin/python
from __future__ import annotations

import argparse
import json
from pathlib import Path


def main() -> None:
    ap = argparse.ArgumentParser()
    ap.add_argument('--chunks-json', required=True)
    ap.add_argument('--song-id', required=True)
    ap.add_argument('--split', default='test')
    ap.add_argument('--output', required=True)
    ap.add_argument('--source-dataset', default='humming_real')
    args = ap.parse_args()

    payload = json.loads(Path(args.chunks_json).read_text(encoding='utf-8'))
    rows = []
    for chunk in payload.get('chunks', []):
        rows.append({
            'song_id': args.song_id,
            'audio_path': chunk['audio_path'],
            'duration': chunk['duration_sec'],
            'type': 'humming_real',
            'segment_type': 'humming_query',
            'offset': chunk['start_sec'],
            'source_dataset': args.source_dataset,
            'split': args.split,
        })

    out = Path(args.output)
    out.parent.mkdir(parents=True, exist_ok=True)
    out.write_text(json.dumps(rows, ensure_ascii=False, indent=2), encoding='utf-8')
    print(json.dumps({'rows': len(rows), 'output': str(out)}, ensure_ascii=False, indent=2))


if __name__ == '__main__':
    main()