Spaces:
Sleeping
Sleeping
| #!/usr/bin/env python3 | |
| """Standalone script to list remote parquet files and verify connectivity. | |
| Usage: | |
| python scripts/sync_data.py | |
| """ | |
| import sys | |
| from pathlib import Path | |
| # Allow running as a script from project root | |
| sys.path.insert(0, str(Path(__file__).resolve().parent.parent)) | |
| from app.config import settings | |
| from app.core.logging_config import setup_logging | |
| from app.core.database import db_manager | |
| def main() -> None: | |
| setup_logging() | |
| print(f"Connecting to DuckDB (remote mode) …") | |
| db_manager.connect() | |
| print(f"Listing files from HuggingFace repo: {settings.HF_REPO_ID}") | |
| db_manager.build_metadata_index() | |
| print(f"\n=== Remote Metadata ===") | |
| print(f" Total files : {len(db_manager.metadata)}") | |
| print(f" Symbols : {len(db_manager.symbols)}") | |
| if db_manager.symbols: | |
| print(f" First 10 : {db_manager.symbols[:10]}") | |
| db_manager.close() | |
| if __name__ == "__main__": | |
| main() | |