delta-kernel-rust-sharing-wrapper

import delta_kernel_python import pyarrow.dataset as ds import os # Path to a Delta Lake table. # For a runnable example, ensure this path points to a valid Delta table. # For cloud paths (s3://, abfss://, etc.), ensure appropriate AWS/Azure credentials # are configured (e.g., via environment variables or default credential providers). # Example: Create a test table first using `delta-rs` or `pyspark`. table_path = os.environ.get("DELTA_TABLE_PATH", "./my_local_delta_table") print(f"Attempting to read Delta table at: {table_path}") try: # Scan the Delta table to get an Arrow Dataset object. # This object can then be used for querying and reading data. dataset: ds.Dataset = delta_kernel_python.scan_table(table_path) print(f"\nSchema of the Delta table:\n{dataset.schema}") print("\nFirst 5 records from the table:") # Read data in batches (e.g., as PyArrow RecordBatches). count = 0 for batch in dataset.to_batches(): print(batch.to_pylist()) count += len(batch) if count >= 5: break if count == 0: print("No records found or processed.") except Exception as e: print(f"\nERROR: Could not read Delta table at '{table_path}'.") print("Please ensure the path is correct and points to an existing Delta table.") print(f"Original error: {e}") print("Tip: You can create a simple Delta table for testing, e.g., with `delta-rs`:") print(" import pandas as pd\n from deltalake import write_deltalake\n df = pd.DataFrame({\"id\": [1, 2], \"value\": [\"A\", \"B\"]})\n write_deltalake(\"./my_local_delta_table\", df, mode=\"overwrite\")")