zhengruifeng commented on a change in pull request #34367: URL: https://github.com/apache/spark/pull/34367#discussion_r756752125
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/window/RankLimitExec.scala ########## @@ -0,0 +1,93 @@ +/* + * 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. + */ + + +package org.apache.spark.sql.execution.window + +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions._ +import org.apache.spark.sql.catalyst.expressions.codegen.LazilyGeneratedOrdering +import org.apache.spark.sql.catalyst.plans.physical._ +import org.apache.spark.sql.execution.{GroupedIterator, SparkPlan, UnaryExecNode} +import org.apache.spark.util.collection.Utils + +/** + * This operator is designed to filter out unnecessary rows before WindowExec, + * for top-k computation. + * @param partitionSpec Should be the same as [[WindowExec#partitionSpec]] + * @param orderSpec Should be the same as [[WindowExec#orderSpec]] + */ +case class RankLimitExec( + partitionSpec: Seq[Expression], + orderSpec: Seq[SortOrder], + limit: Int, + child: SparkPlan) extends UnaryExecNode { + assert(orderSpec.nonEmpty && limit > 0) + + // apply Utils.takeOrdered when partitionSpec is empty and row_number is used. + private def applyTakeOrdered: Boolean = partitionSpec.isEmpty + + override def output: Seq[Attribute] = child.output + + override def requiredChildOrdering: Seq[Seq[SortOrder]] = { + if (applyTakeOrdered) { + super.requiredChildOrdering + } else { + // Should be the same as [[WindowExec#requiredChildOrdering]] + Seq(partitionSpec.map(SortOrder(_, Ascending)) ++ orderSpec) + } + } + + override def outputOrdering: Seq[SortOrder] = { + if (applyTakeOrdered) { + orderSpec + } else { + child.outputOrdering + } + } + + override def outputPartitioning: Partitioning = child.outputPartitioning + + // TODO: support rank and dense_rank Review comment: The correctness exists in: for all three rank functions (row_number, rank, dense_rank), `global rank` >= `partial rank`, so we can safely remove rows with `partial rank > limit` -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
