backend/scripts/sync_reference_resumes.py

from __future__ import annotations

import argparse
import sys
from pathlib import Path

BACKEND_ROOT = Path(__file__).resolve().parents[1]
if str(BACKEND_ROOT) not in sys.path:
    sys.path.insert(0, str(BACKEND_ROOT))

from services.reference_data_service import sync_reference_resumes_to_local


def main() -> None:
    parser = argparse.ArgumentParser(description="Copy reference resumes into local project storage")
    parser.add_argument(
        "--max-files",
        type=int,
        default=120,
        help="Maximum number of PDF resumes to copy",
    )
    parser.add_argument(
        "--source-dir",
        type=str,
        default=None,
        help="Optional source directory containing PDF resumes",
    )
    args = parser.parse_args()

    summary = sync_reference_resumes_to_local(
        max_files=max(1, min(args.max_files, 1000)),
        source_dir=args.source_dir,
    )

    print("Reference resume sync summary")
    print(f"source_dir: {summary['source_dir']}")
    print(f"target_dir: {summary['target_dir']}")
    print(f"files_seen: {summary['files_seen']}")
    print(f"copied: {summary['copied']}")
    print(f"skipped: {summary['skipped']}")


if __name__ == "__main__":
    main()