[SPARK-30651][SQL] Add detailed information for Aggregate operators in EXPLAIN FORMATTED

sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/BaseAggregateExec.scala

@@ -0,0 +1,48 @@
+/*
+ * 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.expressions.{Attribute, NamedExpression}
+import org.apache.spark.sql.catalyst.expressions.aggregate.AggregateExpression
+import org.apache.spark.sql.execution.{ExplainUtils, UnaryExecNode}
+
+/**
+ * Holds common logic for aggregate operators
+ */
+trait BaseAggregateExec extends UnaryExecNode {
+  def groupingExpressions: Seq[NamedExpression]
+  def aggregateExpressions: Seq[AggregateExpression]
+  def aggregateAttributes: Seq[Attribute]
+  def resultExpressions: Seq[NamedExpression]
+
+  override def verboseStringWithOperatorId(): String = {
+    val inputString = child.output.mkString("[", ", ", "]")
+    val keyString = groupingExpressions.mkString("[", ", ", "]")
+    val functionString = aggregateExpressions.mkString("[", ", ", "]")
+    val aggregateAttributeString = aggregateAttributes.mkString("[", ", ", "]")
+    val resultString = resultExpressions.mkString("[", ", ", "]")
+    s"""
+       |(${ExplainUtils.getOpId(this)}) $nodeName ${ExplainUtils.getCodegenId(this)}
+       |Input: $inputString
+       |Keys: $keyString
+       |Functions: $functionString
+       |Aggregate Attributes: $aggregateAttributeString
+       |Results: $resultString
+     """.stripMargin
+  }
+}

sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala

@@ -53,7 +53,7 @@ case class HashAggregateExec(
     initialInputBufferOffset: Int,
     resultExpressions: Seq[NamedExpression],
     child: SparkPlan)
-  extends UnaryExecNode with BlockingOperatorWithCodegen with AliasAwareOutputPartitioning {
+  extends BaseAggregateExec with BlockingOperatorWithCodegen with AliasAwareOutputPartitioning {
 
   private[this] val aggregateBufferAttributes = {
     aggregateExpressions.flatMap(_.aggregateFunction.aggBufferAttributes)

sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/ObjectHashAggregateExec.scala

@@ -67,7 +67,7 @@ case class ObjectHashAggregateExec(
     initialInputBufferOffset: Int,
     resultExpressions: Seq[NamedExpression],
     child: SparkPlan)
-  extends UnaryExecNode with AliasAwareOutputPartitioning {
+  extends BaseAggregateExec with AliasAwareOutputPartitioning {
 
   private[this] val aggregateBufferAttributes = {
     aggregateExpressions.flatMap(_.aggregateFunction.aggBufferAttributes)

sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortAggregateExec.scala

@@ -24,7 +24,7 @@ import org.apache.spark.sql.catalyst.expressions._
 import org.apache.spark.sql.catalyst.expressions.aggregate._
 import org.apache.spark.sql.catalyst.plans.physical._
 import org.apache.spark.sql.catalyst.util.truncatedString
-import org.apache.spark.sql.execution.{AliasAwareOutputPartitioning, SparkPlan, UnaryExecNode}
+import org.apache.spark.sql.execution.{AliasAwareOutputPartitioning, SparkPlan}
 import org.apache.spark.sql.execution.metric.SQLMetrics
 
 /**
@@ -38,7 +38,7 @@ case class SortAggregateExec(
     initialInputBufferOffset: Int,
     resultExpressions: Seq[NamedExpression],
     child: SparkPlan)
-  extends UnaryExecNode with AliasAwareOutputPartitioning {
+  extends BaseAggregateExec with AliasAwareOutputPartitioning {
 
   private[this] val aggregateBufferAttributes = {
     aggregateExpressions.flatMap(_.aggregateFunction.aggBufferAttributes)

sql/core/src/test/resources/sql-tests/inputs/explain.sql

@@ -5,6 +5,7 @@
 CREATE table  explain_temp1 (key int, val int) USING PARQUET;
 CREATE table  explain_temp2 (key int, val int) USING PARQUET;
 CREATE table  explain_temp3 (key int, val int) USING PARQUET;
+CREATE table  explain_temp4 (key int, val string) USING PARQUET;
 
 SET spark.sql.codegen.wholeStage = true;
 
@@ -61,7 +62,7 @@ EXPLAIN FORMATTED
                 FROM   explain_temp2 
                 WHERE  val > 0) 
          OR
-         key = (SELECT max(key) 
+         key = (SELECT avg(key)
                 FROM   explain_temp3
                 WHERE  val > 0);
 
@@ -93,6 +94,25 @@ EXPLAIN FORMATTED
   CREATE VIEW explain_view AS
     SELECT key, val FROM explain_temp1;
 
+-- HashAggregate
+EXPLAIN FORMATTED
+  SELECT
+    COUNT(val) + SUM(key) as TOTAL,
+    COUNT(key) FILTER (WHERE val > 1)
+  FROM explain_temp1;
+
+-- ObjectHashAggregate
+EXPLAIN FORMATTED
+  SELECT key, sort_array(collect_set(val))[0]
+  FROM explain_temp4
+  GROUP BY key;
+
+-- SortAggregate
+EXPLAIN FORMATTED
+  SELECT key, MIN(val)
+  FROM explain_temp4
+  GROUP BY key;
+
 -- cleanup
 DROP TABLE explain_temp1;
 DROP TABLE explain_temp2;