diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala index a602894efbcae1e7e57ddbb865131549d4fb22c5..a391c513ad384df412be1b6c219c1718f7984e78 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala @@ -124,8 +124,6 @@ abstract class Optimizer(sessionCatalog: SessionCatalog) SimplifyCreateMapOps, CombineConcats) ++ extendedOperatorOptimizationRules: _*) :: - Batch("Check Cartesian Products", Once, - CheckCartesianProducts) :: Batch("Join Reorder", Once, CostBasedJoinReorder) :: Batch("Decimal Optimizations", fixedPoint, @@ -136,6 +134,8 @@ abstract class Optimizer(sessionCatalog: SessionCatalog) Batch("LocalRelation", fixedPoint, ConvertToLocalRelation, PropagateEmptyRelation) :: + Batch("Check Cartesian Products", Once, + CheckCartesianProducts) :: Batch("OptimizeCodegen", Once, OptimizeCodegen) :: Batch("RewriteSubquery", Once, diff --git a/sql/core/src/test/scala/org/apache/spark/sql/JoinSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/JoinSuite.scala index 9d50e8be60891e8c19362189eb625eb7669d1d25..226cc3028b13571de5c89e451b9db7bbba867183 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/JoinSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/JoinSuite.scala @@ -200,6 +200,14 @@ class JoinSuite extends QueryTest with SharedSQLContext { Nil) } + test("SPARK-22141: Propagate empty relation before checking Cartesian products") { + Seq("inner", "left", "right", "left_outer", "right_outer", "full_outer").foreach { joinType => + val x = testData2.where($"a" === 2 && !($"a" === 2)).as("x") + val y = testData2.where($"a" === 1 && !($"a" === 1)).as("y") + checkAnswer(x.join(y, Seq.empty, joinType), Nil) + } + } + test("big inner join, 4 matches per row") { val bigData = testData.union(testData).union(testData).union(testData) val bigDataX = bigData.as("x")