ulysses-you commented on code in PR #5655: URL: https://github.com/apache/incubator-gluten/pull/5655#discussion_r1596532823
########## backends-velox/src/main/scala/org/apache/gluten/extension/CollectRewriteRule.scala: ########## @@ -0,0 +1,123 @@ +/* + * 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.gluten.extension + +import org.apache.gluten.expression.ExpressionMappings +import org.apache.gluten.expression.aggregate.{VeloxCollectList, VeloxCollectSet} +import org.apache.gluten.utils.LogicalPlanSelector + +import org.apache.spark.sql.SparkSession +import org.apache.spark.sql.catalyst.expressions.{And, Coalesce, Expression, IsNotNull, Literal, WindowExpression} +import org.apache.spark.sql.catalyst.expressions.aggregate._ +import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, LogicalPlan, Window} +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.types.ArrayType + +import scala.reflect.{classTag, ClassTag} + +/** + * Velox's collect_list / collect_set use array as intermediate data type so aren't compatible with + * vanilla Spark. We here replace the two functions with velox_collect_list / velox_collect_set to + * distinguish. + */ +case class CollectRewriteRule(spark: SparkSession) extends Rule[LogicalPlan] { + import CollectRewriteRule._ + override def apply(plan: LogicalPlan): LogicalPlan = LogicalPlanSelector.maybe(spark, plan) { + val out = plan.transformUp { + case node => + val out = replaceCollectSet(replaceCollectList(node)) + out + } + if (out.fastEquals(plan)) { + return plan + } + spark.sessionState.analyzer.checkAnalysis(out) + out + } + + private def replaceCollectList(node: LogicalPlan): LogicalPlan = { + node.transformExpressions { + case func @ AggregateExpression(l: CollectList, _, _, _, _) if has[VeloxCollectList] => + func.copy(VeloxCollectList(l.child)) + } + } + + private def replaceCollectSet(node: LogicalPlan): LogicalPlan = { + // 1. Replace null result from VeloxCollectSet with empty array to align with + // vanilla Spark. + // 2. Filter out null inputs from VeloxCollectSet to align with vanilla Spark. + // + // Since https://github.com/apache/incubator-gluten/pull/4805 + node match { + case agg: Aggregate => + agg.transformExpressions { + case ToVeloxCollectSet(newAggFunc) => + val out = ensureNonNull(newAggFunc) + out + } + case w: Window => + w.transformExpressions { + case func @ WindowExpression(ToVeloxCollectSet(newAggFunc), _) => + val out = ensureNonNull(func.copy(newAggFunc)) Review Comment: I'm not sure adding ensureNonNull for window expression is been actually evaluated. It seems window operator only collects the window expression to eval. Is there a test for window + collect_set with null input ? -- 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]
