alamb commented on code in PR #18591: URL: https://github.com/apache/datafusion/pull/18591#discussion_r2515703787
########## datafusion-examples/examples/data_io/main.rs: ########## @@ -0,0 +1,160 @@ +// Licensed to the Apache Software Foundation (ASF) under one +// or more contributor license agreements. See the NOTICE file +// distributed with this work for additional information +// regarding copyright ownership. The ASF licenses this file +// to you under the Apache License, Version 2.0 (the +// "License"); you may not use this file except in compliance +// with the License. You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, +// software distributed under the License is distributed on an +// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +// KIND, either express or implied. See the License for the +// specific language governing permissions and limitations +// under the License. + +//! # These examples of data formats and I/O +//! +//! These examples demonstrate data formats and I/O. +//! +//! ## Usage +//! ```bash +//! cargo run --example data_io -- [catalog|json_shredding|parquet_adv_idx|parquet_emb_idx|parquet_enc_with_kms|parquet_enc|parquet_exec_visitor|parquet_idx|query_http_csv|remote_catalog] +//! ``` +//! +//! Each subcommand runs a corresponding example: +//! - `catalog` — register the table into a custom catalog +//! - `json_shredding` — shows how to implement custom filter rewriting for JSON shredding +//! - `parquet_adv_idx` — create a detailed secondary index that covers the contents of several parquet files +//! - `parquet_emb_idx` — store a custom index inside a Parquet file and use it to speed up queries +//! - `parquet_enc_with_kms` — read and write encrypted Parquet files using an encryption factory +//! - `parquet_enc` — read and write encrypted Parquet files using DataFusion +//! - `parquet_exec_visitor` — extract statistics by visiting an ExecutionPlan after execution +//! - `parquet_idx` — create an secondary index over several parquet files and use it to speed up queries +//! - `query_http_csv` — configure `object_store` and run a query against files via HTTP +//! - `remote_catalog` — interfacing with a remote catalog (e.g. over a network) + +mod catalog; Review Comment: 😍 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
