alamb commented on code in PR #5326: URL: https://github.com/apache/arrow-datafusion/pull/5326#discussion_r1111056677
########## datafusion-examples/examples/catalog.rs: ########## @@ -0,0 +1,287 @@ +// 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. + +//! Simple example of a catalog/schema implementation. +//! +//! Example requires git submodules to be initialized in repo as it uses data from +//! the `parquet-testing` repo. +use async_trait::async_trait; +use datafusion::{ + arrow::util::pretty, + catalog::{ + catalog::{CatalogList, CatalogProvider}, + schema::SchemaProvider, + }, + datasource::{ + file_format::{csv::CsvFormat, parquet::ParquetFormat, FileFormat}, + listing::{ListingOptions, ListingTable, ListingTableConfig, ListingTableUrl}, + TableProvider, + }, + error::Result, + execution::context::SessionState, + prelude::SessionContext, +}; +use std::sync::RwLock; +use std::{ + any::Any, + collections::HashMap, + path::{Path, PathBuf}, + sync::Arc, +}; + +#[tokio::main] +async fn main() -> Result<()> { + let repo_dir = std::fs::canonicalize( + PathBuf::from(env!("CARGO_MANIFEST_DIR")) + // parent dir of datafusion-examples = repo root + .join(".."), + ) + .unwrap(); + let mut ctx = SessionContext::new(); + let state = ctx.state(); + let catlist = Arc::new(CustomCatalogList::new()); + // use our custom catalog list for context. each context has a single catalog list. + // context will by default have MemoryCatalogList + ctx.register_catalog_list(catlist.clone()); + + // intitialize our catalog and schemas + let catalog = DirCatalog::new(); + let parquet_schema = DirSchema::create( + &state, + DirSchemaOpts { + format: Arc::new(ParquetFormat::default()), + dir: &repo_dir.join("parquet-testing").join("data"), + ext: "parquet", + }, + ) + .await?; + let csv_schema = DirSchema::create( + &state, + DirSchemaOpts { + format: Arc::new(CsvFormat::default()), + dir: &repo_dir.join("testing").join("data").join("csv"), + ext: "csv", + }, + ) + .await?; + // register schemas into catalog + catalog.register_schema("parquet", parquet_schema.clone())?; + catalog.register_schema("csv", csv_schema.clone())?; + // register our catalog in the context + ctx.register_catalog("dircat", Arc::new(catalog)); + { + // catalog was passed down into our custom catalog list since we overide the ctx's default + let catalogs = catlist.catalogs.read().unwrap(); + assert!(catalogs.contains_key("dircat")); + }; + let parquet_tables = { + let tables = parquet_schema.tables.read().unwrap(); + tables.keys().take(5).cloned().collect::<Vec<_>>() Review Comment: I wonder if there is some reason to limit it to 5 files? Maybe we could add a comment about the choice of that value -- 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]
