andygrove commented on code in PR #1111: URL: https://github.com/apache/datafusion-comet/pull/1111#discussion_r1865030540
########## native/core/src/execution/datafusion/spark_plan.rs: ########## @@ -0,0 +1,102 @@ +// 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. + +use crate::execution::operators::{CopyExec, ScanExec}; +use arrow_schema::SchemaRef; +use datafusion::physical_plan::ExecutionPlan; +use std::sync::Arc; + +/// Wrapper around a native plan that maps to a Spark plan and can optionally contain +/// references to other native plans that should contribute to the Spark SQL metrics +/// for the root plan (such as CopyExec and ScanExec nodes) +#[derive(Debug, Clone)] +pub(crate) struct SparkPlan { + /// Spark plan ID which is passed down in the protobuf + pub(crate) plan_id: u32, + /// The root native plan that was generated for this Spark plan + pub(crate) native_plan: Arc<dyn ExecutionPlan>, Review Comment: yes ########## native/core/src/execution/datafusion/planner.rs: ########## @@ -1148,13 +1220,40 @@ impl PhysicalPlanner { )?); // If the hash join is build right, we need to swap the left and right - let hash_join = if join.build_side == BuildSide::BuildLeft as i32 { - hash_join + if join.build_side == BuildSide::BuildLeft as i32 { + Ok(( + scans, + Arc::new(SparkPlan::new( + spark_plan.plan_id, + hash_join, + vec![join_params.left, join_params.right], + )), + )) } else { - swap_hash_join(hash_join.as_ref(), PartitionMode::Partitioned)? - }; - - Ok((scans, hash_join)) + // we insert a projection around the hash join in this case + let projection = + swap_hash_join(hash_join.as_ref(), PartitionMode::Partitioned)?; + let swapped_hash_join = Arc::clone(projection.children()[0]); + println!( Review Comment: removed, thanks -- 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
