arrow-odbc

import os from arrow_odbc import read_arrow_tables import pyarrow.parquet as pq # NOTE: You must have an ODBC driver installed on your system # for the target database (e.g., SQL Server, PostgreSQL, MySQL). # The connection string below is an example. Adjust it for your setup. # Example connection strings: # SQL Server (Windows/Linux): DRIVER={ODBC Driver 17 for SQL Server};SERVER=localhost;DATABASE=testdb;UID=user;PWD=password # PostgreSQL (Linux): DRIVER={PostgreSQL Unicode};SERVER=localhost;DATABASE=testdb;UID=user;PASSWORD=password connection_string = os.environ.get( 'ARROW_ODBC_CONNECTION_STRING', 'DRIVER={ODBC Driver 17 for SQL Server};SERVER=localhost;DATABASE=testdb;UID=user;PWD=password' ) # Example query. Adjust 'YourTable' and syntax for your database. # For SQL Server: "SELECT TOP 100 * FROM YourTable" # For PostgreSQL: "SELECT * FROM YourTable LIMIT 100" query = "SELECT TOP 100 * FROM YourTable" try: # Read data into a PyArrow Table arrow_table = read_arrow_tables( connection_string=connection_string, query=query ) print(f"Successfully read {arrow_table.num_rows} rows.") print(f"Schema:\n{arrow_table.schema}") if arrow_table.num_rows > 0: print(f"First 5 rows:\n{arrow_table.slice(0, min(5, arrow_table.num_rows)).to_pylist()}") # Example: Save to Parquet # pq.write_table(arrow_table, "output.parquet") except Exception as e: print(f"An error occurred: {e}") print("Please ensure your ODBC driver is installed and the connection string/query are correct.")