xuanyuanking commented on a change in pull request #31987: URL: https://github.com/apache/spark/pull/31987#discussion_r656850924
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/MergingSessionsIterator.scala ########## @@ -0,0 +1,254 @@ +/* + * 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.aggregate + +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.{Attribute, Expression, GenericInternalRow, JoinedRow, MutableProjection, NamedExpression, SpecificInternalRow, UnsafeProjection, UnsafeRow} +import org.apache.spark.sql.catalyst.expressions.aggregate.AggregateExpression +import org.apache.spark.sql.catalyst.expressions.codegen.GenerateUnsafeProjection +import org.apache.spark.sql.execution.metric.SQLMetric + +/** + * This is a variant of SortAggregateIterator which merges the session windows based on the fact + * input rows are sorted by "group keys + the start time of session window". + * + * When merging windows, it also applies aggregations on merged window, which eliminates the + * necessity on buffering inputs (which requires copying rows) and update the session spec + * for each input. + */ +class MergingSessionsIterator( + partIndex: Int, + groupingExpressions: Seq[NamedExpression], + sessionExpression: NamedExpression, + valueAttributes: Seq[Attribute], + inputIterator: Iterator[InternalRow], + aggregateExpressions: Seq[AggregateExpression], + aggregateAttributes: Seq[Attribute], + initialInputBufferOffset: Int, + resultExpressions: Seq[NamedExpression], + newMutableProjection: (Seq[Expression], Seq[Attribute]) => MutableProjection, + numOutputRows: SQLMetric) + extends AggregationIterator( + partIndex, + groupingExpressions, + valueAttributes, + aggregateExpressions, + aggregateAttributes, + initialInputBufferOffset, + resultExpressions, + newMutableProjection) { + + val groupingWithoutSession: Seq[NamedExpression] = + groupingExpressions.diff(Seq(sessionExpression)) + val groupingWithoutSessionAttributes: Seq[Attribute] = groupingWithoutSession.map(_.toAttribute) + + /** + * Creates a new aggregation buffer and initializes buffer values + * for all aggregate functions. + */ + private def newBuffer: InternalRow = { Review comment: Yea, agree. -- 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. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
