parquet-metadata

import subprocess import os # Create a dummy Parquet file for demonstration (requires pyarrow) # In a real scenario, you would use an existing Parquet file. try: import pyarrow as pa import pyarrow.parquet as pq table = pa.table({'col1': [1, 2, 3], 'col2': ['a', 'b', 'c']}) dummy_file = 'dummy.parquet' pq.write_table(table, dummy_file) print(f"Created dummy Parquet file: {dummy_file}") # Run the parquet-metadata command-line tool command = ['parquet-metadata', dummy_file] result = subprocess.run(command, capture_output=True, text=True, check=True) print("\n--- Parquet Metadata Output ---") print(result.stdout) if result.stderr: print("--- Errors ---") print(result.stderr) # Clean up dummy file os.remove(dummy_file) print(f"Removed dummy Parquet file: {dummy_file}") except ImportError: print("Pyarrow not installed. Cannot create dummy parquet file for quickstart.") print("To run quickstart, install pyarrow: pip install pyarrow") print("You can still try 'parquet-metadata your_file.parquet' in your terminal.") except Exception as e: print(f"An error occurred: {e}")