"""
Download all audio recordings from S3 to a local directory.

Usage:
    python scripts/download_recordings.py
    python scripts/download_recordings.py --prefix benapi92  # filter by session code
    python scripts/download_recordings.py --out data/raw
"""

import argparse
import os
from pathlib import Path

import boto3
from botocore.config import Config as BotoConfig
from dotenv import load_dotenv

load_dotenv()

BUCKET      = 'ethz-otree-whisper'
REGION      = 'eu-north-1'
DEFAULT_OUT = Path('data/raw')


def download(prefix: str = '', out_dir: Path = DEFAULT_OUT):
    s3 = boto3.client(
        's3',
        aws_access_key_id=os.environ['S3_ACCESS_KEY'],
        aws_secret_access_key=os.environ['S3_SECRET_KEY'],
        region_name=REGION,
        config=BotoConfig(signature_version='s3v4'),
    )

    out_dir.mkdir(parents=True, exist_ok=True)

    paginator = s3.get_paginator('list_objects_v2')
    pages = paginator.paginate(Bucket=BUCKET, Prefix=prefix)

    total = 0
    for page in pages:
        for obj in page.get('Contents', []):
            key = obj['Key']
            dest = out_dir / key
            dest.parent.mkdir(parents=True, exist_ok=True)

            if dest.exists():
                print(f'  skip  {key}  (already exists)')
                continue

            print(f'  down  {key}')
            s3.download_file(BUCKET, key, str(dest))
            total += 1

    print(f'\nDone. {total} file(s) downloaded to {out_dir}/')


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--prefix', default='', help='Filter by key prefix (e.g. session code)')
    parser.add_argument('--out', default=str(DEFAULT_OUT), help='Local output directory')
    args = parser.parse_args()
    download(prefix=args.prefix, out_dir=Path(args.out))