kosiew commented on code in PR #16148: URL: https://github.com/apache/datafusion/pull/16148#discussion_r2106428855
########## datafusion/core/tests/integration_tests/schema_adapter_integration_tests.rs: ########## @@ -0,0 +1,197 @@ +// 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. + +//! Integration test for schema adapter factory functionality + +use arrow::datatypes::{DataType, Field, Schema, SchemaRef}; +use arrow::record_batch::RecordBatch; +use datafusion::datasource::object_store::ObjectStoreUrl; +use datafusion::datasource::physical_plan::arrow_file::ArrowSource; +use datafusion::prelude::*; +use datafusion_common::Result; +use datafusion_datasource::file::FileSource; +use datafusion_datasource::file_scan_config::FileScanConfigBuilder; +use datafusion_datasource::schema_adapter::{SchemaAdapter, SchemaAdapterFactory}; +use datafusion_datasource::source::DataSourceExec; +use std::sync::Arc; +use tempfile::TempDir; + +#[cfg(feature = "parquet")] +use datafusion_datasource_parquet::ParquetSource; +#[cfg(feature = "parquet")] +use parquet::arrow::ArrowWriter; +#[cfg(feature = "parquet")] +use parquet::file::properties::WriterProperties; + +#[cfg(feature = "csv")] +use datafusion_datasource_csv::CsvSource; + +/// A schema adapter factory that transforms column names to uppercase +#[derive(Debug)] +struct UppercaseAdapterFactory {} + +impl SchemaAdapterFactory for UppercaseAdapterFactory { + fn create(&self, schema: &Schema) -> Result<Box<dyn SchemaAdapter>> { + Ok(Box::new(UppercaseAdapter { + input_schema: Arc::new(schema.clone()), + })) + } +} + +/// Schema adapter that transforms column names to uppercase +#[derive(Debug)] +struct UppercaseAdapter { + input_schema: SchemaRef, +} + +impl SchemaAdapter for UppercaseAdapter { + fn adapt(&self, record_batch: RecordBatch) -> Result<RecordBatch> { + // In a real adapter, we might transform the data too + // For this test, we're just passing through the batch + Ok(record_batch) + } + + fn output_schema(&self) -> SchemaRef { + let fields = self + .input_schema + .fields() + .iter() + .map(|f| { + Field::new( + f.name().to_uppercase().as_str(), + f.data_type().clone(), + f.is_nullable(), + ) + }) + .collect(); + + Arc::new(Schema::new(fields)) + } +} + +#[cfg(feature = "parquet")] +#[tokio::test] +async fn test_parquet_integration_with_schema_adapter() -> Result<()> { + // Create a temporary directory for our test file + let tmp_dir = TempDir::new()?; + let file_path = tmp_dir.path().join("test.parquet"); + let file_path_str = file_path.to_str().unwrap(); + + // Create test data + let schema = Arc::new(Schema::new(vec![ + Field::new("id", DataType::Int32, false), + Field::new("name", DataType::Utf8, true), + ])); + + let batch = RecordBatch::try_new( + schema.clone(), + vec![ + Arc::new(arrow::array::Int32Array::from(vec![1, 2, 3])), + Arc::new(arrow::array::StringArray::from(vec!["a", "b", "c"])), + ], + )?; + + // Write test parquet file + let file = std::fs::File::create(file_path_str)?; + let props = WriterProperties::builder().build(); + let mut writer = ArrowWriter::try_new(file, schema.clone(), Some(props))?; + writer.write(&batch)?; + writer.close()?; + + // Create a session context + let ctx = SessionContext::new(); + + // Create a ParquetSource with the adapter factory + let source = ParquetSource::default() + .with_schema_adapter_factory(Arc::new(UppercaseAdapterFactory {})); + + // Create a scan config + let config = FileScanConfigBuilder::new( + ObjectStoreUrl::parse(&format!("file://{}", file_path_str))?, + schema.clone(), + ) + .with_source(source) + .build(); + + // Create a data source executor + let exec = DataSourceExec::from_data_source(config); + + // Collect results + let task_ctx = ctx.task_ctx(); + let stream = exec.execute(0, task_ctx)?; + let batches = datafusion::physical_plan::common::collect(stream).await?; + + // There should be one batch + assert_eq!(batches.len(), 1); + + // Verify the schema has uppercase column names + let result_schema = batches[0].schema(); + assert_eq!(result_schema.field(0).name(), "ID"); + assert_eq!(result_schema.field(1).name(), "NAME"); + + Ok(()) +} + +#[tokio::test] +async fn test_multi_source_schema_adapter_reuse() -> Result<()> { Review Comment: The test checks that: 1. The UppercaseAdapterFactory can be applied to different source types (ArrowSource, ParquetSource, CsvSource) 2. After applying the factory, each source correctly reports having a schema adapter factory 3. The factory reference is properly maintained across different source instances -- 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: github-unsubscr...@datafusion.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For additional commands, e-mail: github-h...@datafusion.apache.org
