richox commented on code in PR #2242: URL: https://github.com/apache/arrow-datafusion/pull/2242#discussion_r853106363
########## datafusion/core/src/physical_plan/sort_merge_join.rs: ########## @@ -0,0 +1,1730 @@ +// 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. + +//! Defines the Sort-Merge join execution plan. +//! A sort-merge join plan consumes two sorted children plan and produces +//! joined output by given join type and other options. + +use std::any::Any; +use std::cmp::Ordering; +use std::collections::VecDeque; +use std::ops::Range; +use std::pin::Pin; +use std::sync::Arc; +use std::task::{Context, Poll}; + +use arrow::array::*; +use arrow::compute::SortOptions; +use arrow::datatypes::{DataType, Schema, SchemaRef}; +use arrow::error::{ArrowError, Result as ArrowResult}; +use arrow::record_batch::RecordBatch; +use async_trait::async_trait; +use futures::{Stream, StreamExt}; + +use crate::error::DataFusionError; +use crate::error::Result; +use crate::execution::context::TaskContext; +use crate::logical_plan::JoinType; +use crate::physical_plan::coalesce_partitions::CoalescePartitionsExec; +use crate::physical_plan::expressions::Column; +use crate::physical_plan::expressions::PhysicalSortExpr; +use crate::physical_plan::join_utils::{build_join_schema, check_join_is_valid, JoinOn}; +use crate::physical_plan::metrics::{ExecutionPlanMetricsSet, MetricBuilder, MetricsSet}; +use crate::physical_plan::{ + metrics, ExecutionPlan, Partitioning, RecordBatchStream, SendableRecordBatchStream, + Statistics, +}; + +/// join execution plan executes partitions in parallel and combines them into a set of +/// partitions. +#[derive(Debug)] +pub struct SortMergeJoinExec { + /// Left sorted joining execution plan + left: Arc<dyn ExecutionPlan>, + /// Right sorting joining execution plan + right: Arc<dyn ExecutionPlan>, + /// Set of common columns used to join on + on: JoinOn, + /// How the join is performed + join_type: JoinType, + /// The schema once the join is applied + schema: SchemaRef, + /// Execution metrics + metrics: ExecutionPlanMetricsSet, + /// Sort options of join columns used in sorting left and right execution plans + sort_options: Vec<SortOptions>, + /// If null_equals_null is true, null == null else null != null + null_equals_null: bool, +} + +impl SortMergeJoinExec { + /// Tries to create a new [SortMergeJoinExec]. + /// # Error + /// This function errors when it is not possible to join the left and right sides on keys `on`. + pub fn try_new( + left: Arc<dyn ExecutionPlan>, + right: Arc<dyn ExecutionPlan>, + on: JoinOn, + join_type: JoinType, + sort_options: Vec<SortOptions>, Review Comment: i guest there may be some chance to reduce extra sorting if we support different ordering for different columns. for example: ``` select c, d from ( select a, b, c from table1 order by a ASC, b DESC ) t1 join ( select a, b, d from table2 order by a ASC, b DESC ) t2 on t2.a = t1.a and t2.b = t1.b ``` in the above case, column `a` and `b` are sorted in different directions. if we support different ordering, we need no extra `SortExec` before joining. -- 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]
