[GitHub] [spark] tanelk commented on a change in pull request #31914: [SPARK-33122][SQL][FOLLOWUP] Remove redundant aggregates in the Optimzier

[GitBox <gi...@apache.org>]

tanelk commented on a change in pull request #31914:
URL: https://github.com/apache/spark/pull/31914#discussion_r598273073



##########
File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RemoveRedundantAggregates.scala
##########
@@ -0,0 +1,77 @@
+/*
+ * 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.catalyst.optimizer
+
+import org.apache.spark.sql.catalyst.analysis.PullOutNondeterministic
+import org.apache.spark.sql.catalyst.expressions.{AliasHelper, AttributeSet, Expression, PythonUDF}
+import org.apache.spark.sql.catalyst.expressions.aggregate.AggregateExpression
+import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, LogicalPlan}
+import org.apache.spark.sql.catalyst.rules.Rule
+
+/**
+ * Remove redundant aggregates from a query plan. A redundant aggregate is an aggregate whose
+ * only goal is to keep distinct values, while its parent aggregate would ignore duplicate values.
+ */
+object RemoveRedundantAggregates extends Rule[LogicalPlan] with AliasHelper {
+  def apply(plan: LogicalPlan): LogicalPlan = plan transformUp {
+    case upper @ Aggregate(_, _, lower: Aggregate) if isLowerRedundant(upper, lower) =>
+      val aliasMap = getAliasMap(lower)
+
+      val newAggregate = upper.copy(
+        child = lower.child,
+        groupingExpressions = upper.groupingExpressions.map(replaceAlias(_, aliasMap)),
+        aggregateExpressions = upper.aggregateExpressions.map(
+          replaceAliasButKeepName(_, aliasMap))
+      )
+
+      // We might have introduced non-deterministic grouping expressions
+      if (newAggregate.groupingExpressions.exists(!_.deterministic)) {
+        PullOutNondeterministic.applyLocally.applyOrElse(newAggregate, identity[LogicalPlan])
+      } else {
+        newAggregate
+      }
+  }
+
+  private def isLowerRedundant(upper: Aggregate, lower: Aggregate): Boolean = {
+    val upperHasNoDuplicateSensitiveAgg = !upper
+      .aggregateExpressions
+      .exists(isDuplicateSensitiveAggregate)
+
+    lazy val upperRefsOnlyDeterministicNonAgg = upper.references.subsetOf(AttributeSet(
+      lower
+        .aggregateExpressions
+        .filter(_.deterministic)
+        .filterNot(isAggregate)
+        .map(_.toAttribute)
+    ))
+
+    upperHasNoDuplicateSensitiveAgg && upperRefsOnlyDeterministicNonAgg
+  }
+
+  private def isAggregate(expr: Expression): Boolean = {
+    expr.find(e => e.isInstanceOf[AggregateExpression] ||
+      PythonUDF.isGroupedAggPandasUDF(e)).isDefined
+  }
+
+  private def isDuplicateSensitiveAggregate(expr: Expression): Boolean = {

Review comment:
       Added this check, previously `isAggregate` was used twice.




-- 
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:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org