diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala index c6aae1a4db2e41cee3f8ca79d967e103ac29b37b..26fb6103953fc80e548bf60eb59a813e46c3dc33 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala @@ -371,6 +371,7 @@ case class SortMergeJoinExec( keys: Seq[Expression], input: Seq[Attribute]): Seq[ExprCode] = { ctx.INPUT_ROW = row + ctx.currentVars = null keys.map(BindReferences.bindReference(_, input).genCode(ctx)) } diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameJoinSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameJoinSuite.scala index 4a52af6c32c377c7c2006408a14a75d5e57a64a9..aef0d7f3e425bf86281299b423824617ea2f1bf2 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameJoinSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameJoinSuite.scala @@ -264,4 +264,14 @@ class DataFrameJoinSuite extends QueryTest with SharedSQLContext { val ab = a.join(b, Seq("a"), "fullouter") checkAnswer(ab.join(c, "a"), Row(3, null, 4, 1) :: Nil) } + + test("SPARK-17685: WholeStageCodegenExec throws IndexOutOfBoundsException") { + val df = Seq((1, 1, "1"), (2, 2, "3")).toDF("int", "int2", "str") + val df2 = Seq((1, 1, "1"), (2, 3, "5")).toDF("int", "int2", "str") + val limit = 1310721 + val innerJoin = df.limit(limit).join(df2.limit(limit), Seq("int", "int2"), "inner") + .agg(count($"int")) + checkAnswer(innerJoin, Row(1) :: Nil) + } + }