Correctly handle self joins of in-memory cached tables.

apache · Apr 3, 2014 · 87211ce · 87211ce
1 parent 69e195e
commit 87211ce
Showing 1 changed file with 3 additions and 0 deletions.
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlan.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlan.scala
@@ -24,6 +24,7 @@ import org.apache.spark.sql.catalyst.analysis.MultiInstanceRelation
 import org.apache.spark.sql.catalyst.expressions.GenericRow
 import org.apache.spark.sql.catalyst.plans.{QueryPlan, logical}
 import org.apache.spark.sql.catalyst.plans.physical._
+import org.apache.spark.sql.columnar.InMemoryColumnarTableScan
 
 abstract class SparkPlan extends QueryPlan[SparkPlan] with Logging {
   self: Product =>
@@ -69,6 +70,8 @@ case class SparkLogicalPlan(alreadyPlanned: SparkPlan)
     SparkLogicalPlan(
       alreadyPlanned match {
         case ExistingRdd(output, rdd) => ExistingRdd(output.map(_.newInstance), rdd)
+        case InMemoryColumnarTableScan(output, child) =>
+          InMemoryColumnarTableScan(output.map(_.newInstance), child)
         case _ => sys.error("Multiple instance of the same relation detected.")
       }).asInstanceOf[this.type]
   }