jonathanc-n commented on code in PR #16660: URL: https://github.com/apache/datafusion/pull/16660#discussion_r2265598367
########## datafusion/physical-plan/src/joins/piecewise_merge_join.rs: ########## @@ -0,0 +1,2059 @@ +// 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 arrow::array::{new_null_array, Array, RecordBatchOptions}; +use arrow::compute::take; +use arrow::{ + array::{ + ArrayRef, BooleanBufferBuilder, RecordBatch, UInt32Array, UInt32Builder, + UInt64Array, UInt64Builder, + }, + compute::{concat_batches, sort_to_indices, take_record_batch}, + util::bit_util, +}; +use arrow_schema::{ArrowError, Schema, SchemaRef, SortOptions}; +use datafusion_common::NullEquality; +use datafusion_common::{ + exec_err, internal_err, plan_err, utils::compare_rows, JoinSide, Result, ScalarValue, +}; +use datafusion_execution::{ + memory_pool::{MemoryConsumer, MemoryReservation}, + RecordBatchStream, SendableRecordBatchStream, +}; +use datafusion_expr::{JoinType, Operator}; +use datafusion_functions_aggregate_common::min_max::{max_batch, min_batch}; +use datafusion_physical_expr::equivalence::join_equivalence_properties; +use datafusion_physical_expr::{ + LexOrdering, OrderingRequirements, PhysicalExpr, PhysicalExprRef, PhysicalSortExpr, +}; +use datafusion_physical_expr_common::physical_expr::fmt_sql; +use futures::{Stream, StreamExt, TryStreamExt}; +use parking_lot::Mutex; +use std::fmt::Formatter; +use std::{cmp::Ordering, task::ready}; +use std::{sync::Arc, task::Poll}; + +use crate::execution_plan::{boundedness_from_children, EmissionType}; + +use crate::joins::sort_merge_join::compare_join_arrays; +use crate::joins::utils::{ + get_final_indices_from_shared_bitmap, symmetric_join_output_partitioning, +}; +use crate::{handle_state, DisplayAs, DisplayFormatType, ExecutionPlanProperties}; +use crate::{ + joins::{ + utils::{ + build_join_schema, BuildProbeJoinMetrics, OnceAsync, OnceFut, + StatefulStreamResult, + }, + SharedBitmapBuilder, + }, + metrics::ExecutionPlanMetricsSet, + spill::get_record_batch_memory_size, + ExecutionPlan, PlanProperties, +}; + +/// `PiecewiseMergeJoinExec` is a join execution plan that only evaluates single range filter. +/// +/// The physical planner will choose to evalute this join when there is only one range predicate. This +/// is a binary expression which contains [`Operator::Lt`], [`Operator::LtEq`], [`Operator::Gt`], and +/// [`Operator::GtEq`].: +/// Examples: +/// - `col0` < `colb`, `col0` <= `colb`, `col0` > `colb`, `col0` >= `colb` +/// +/// Since the join only support range predicates, equijoins are not supported in `PiecewiseMergeJoinExec`, +/// however you can first evaluate another join and run `PiecewiseMergeJoinExec` if left with one range +/// predicate. +/// +/// # Execution Plan Inputs +/// For `PiecewiseMergeJoin` we label all left inputs as the `streamed' side and the right outputs as the Review Comment: Ah yes this should be done, I had mixed them up in my head. Is it fine to do this in a follow up pull request? Shouldn't be too big of an issue for review as the inputs are labelled as streamed and buffered throughout the code. -- 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
