Use ExpressionSet.

Author: dongjoon-hyun

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala

@@ -1447,7 +1447,7 @@ object RemoveLiteralFromGroupExpressions extends Rule[LogicalPlan] {
 object RemoveRepetitionFromGroupExpressions extends Rule[LogicalPlan] {
   def apply(plan: LogicalPlan): LogicalPlan = plan transform {
     case a @ Aggregate(grouping, _, _) =>
-      val newGrouping = grouping.distinct
+      val newGrouping = ExpressionSet(grouping).toSeq
       a.copy(groupingExpressions = newGrouping)
   }
 }

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/AggregateOptimizeSuite.scala

@@ -17,6 +17,9 @@
 
 package org.apache.spark.sql.catalyst.optimizer
 
+import org.apache.spark.sql.catalyst.SimpleCatalystConf
+import org.apache.spark.sql.catalyst.analysis.{Analyzer, EmptyFunctionRegistry}
+import org.apache.spark.sql.catalyst.catalog.{InMemoryCatalog, SessionCatalog}
 import org.apache.spark.sql.catalyst.dsl.expressions._
 import org.apache.spark.sql.catalyst.dsl.plans._
 import org.apache.spark.sql.catalyst.expressions.Literal
@@ -25,6 +28,9 @@ import org.apache.spark.sql.catalyst.plans.logical.{LocalRelation, LogicalPlan}
 import org.apache.spark.sql.catalyst.rules.RuleExecutor
 
 class AggregateOptimizeSuite extends PlanTest {
+  val conf = new SimpleCatalystConf(caseSensitiveAnalysis = false)
+  val catalog = new SessionCatalog(new InMemoryCatalog, EmptyFunctionRegistry, conf)
+  val analyzer = new Analyzer(catalog, conf)
 
   object Optimize extends RuleExecutor[LogicalPlan] {
     val batches = Batch("Aggregate", FixedPoint(100),
@@ -47,10 +53,10 @@ class AggregateOptimizeSuite extends PlanTest {
   test("remove repetition in grouping expression") {
     val input = LocalRelation('a.int, 'b.int, 'c.int)
 
-    val query = input.groupBy('a, 'b, 'b, 'a)(sum('c))
-    val optimized = Optimize.execute(query)
+    val query = input.groupBy('a + 1, 'b + 2, Literal(1) + 'A, Literal(2) + 'B)(sum('c))
+    val optimized = Optimize.execute(analyzer.execute(query))
 
-    val correctAnswer = input.groupBy('a, 'b)(sum('c))
+    val correctAnswer = analyzer.execute(input.groupBy('a + 1, 'b + 2)(sum('c)))
 
     comparePlans(optimized, correctAnswer)
   }