mustafasrepo commented on code in PR #9125: URL: https://github.com/apache/arrow-datafusion/pull/9125#discussion_r1478106057
########## datafusion/physical-plan/src/sorts/partial_sort.rs: ########## @@ -0,0 +1,1005 @@ +// 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. + +//! Partial Sort deals with cases where the input data partially +//! satisfies the required sort order and the input dataset has +//! segments where sorted column/columns already has the required +//! information for lexicographic sorting. Then these segments +//! can be sorted without loading the entire dataset. +//! +//! Consider the input with ordering a ASC, b ASC +//! ```text +//! +---+---+---+ +//! | a | b | d | +//! +---+---+---+ +//! | 0 | 0 | 3 | +//! | 0 | 0 | 2 | +//! | 0 | 1 | 1 | +//! | 0 | 2 | 0 | +//!``` +//! and required ordering is a ASC, b ASC, d ASC. +//! The first 3 rows(segment) can be sorted as the segment already has the required +//! information for the sort, but the last row requires further information +//! as the input can continue with a batch starting with a row where a and b +//! does not change as below +//! ```text +//! +---+---+---+ +//! | a | b | d | +//! +---+---+---+ +//! | 0 | 2 | 4 | +//!``` +//! The plan concats these last segments with incoming data and continues +//! incremental sorting of segments. + +use std::any::Any; +use std::fmt::Debug; +use std::pin::Pin; +use std::sync::Arc; +use std::task::{Context, Poll}; + +use arrow::compute; +use arrow::compute::{lexsort_to_indices, take}; +use arrow::datatypes::SchemaRef; +use arrow::record_batch::RecordBatch; + +use datafusion_common::utils::evaluate_partition_ranges; +use datafusion_common::Result; +use datafusion_execution::{RecordBatchStream, TaskContext}; +use datafusion_physical_expr::EquivalenceProperties; + +use crate::expressions::PhysicalSortExpr; +use crate::metrics::{BaselineMetrics, ExecutionPlanMetricsSet, MetricsSet}; +use crate::{ + DisplayAs, DisplayFormatType, Distribution, ExecutionPlan, Partitioning, + SendableRecordBatchStream, Statistics, +}; + +use futures::{ready, Stream, StreamExt}; +use log::trace; + +/// Partial Sort execution plan. +#[derive(Debug, Clone)] +pub struct PartialSortExec { + /// Input schema + pub(crate) input: Arc<dyn ExecutionPlan>, + /// Sort expressions + expr: Vec<PhysicalSortExpr>, + /// Length of continuous matching columns of input that satisfy + /// the required ordering for the sort + common_prefix_length: usize, + /// Containing all metrics set created during sort + metrics_set: ExecutionPlanMetricsSet, + /// TODO: check usage Review Comment: This todo seems leftover -- 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]
