Reuses Row object in ExistingRdd.productToRowRdd()

witgo · Apr 17, 2014 · 52acec9 · 52acec9
1 parent bb76eae
commit 52acec9
Showing 1 changed file with 24 additions and 3 deletions.
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/basicOperators.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/basicOperators.scala
@@ -27,7 +27,6 @@ import org.apache.spark.sql.catalyst.expressions._
 import org.apache.spark.sql.catalyst.plans.physical.{OrderedDistribution, UnspecifiedDistribution}
 import org.apache.spark.util.MutablePair
 
-
 case class Project(projectList: Seq[NamedExpression], child: SparkPlan) extends UnaryNode {
   override def output = projectList.map(_.toAttribute)
 
@@ -143,8 +142,30 @@ object ExistingRdd {
   }
 
   def productToRowRdd[A <: Product](data: RDD[A]): RDD[Row] = {
-    // TODO: Reuse the row, don't use map on the product iterator.  Maybe code gen?
-    data.map(r => new GenericRow(r.productIterator.map(convertToCatalyst).toArray): Row)
+    data.mapPartitions { iterator =>
+      if (iterator.isEmpty) {
+        Iterator.empty
+      } else {
+        val first = iterator.next()
+        val mutableRow = new GenericMutableRow(first.productArity)
+
+        var i = 0
+        while (i < mutableRow.length) {
+          mutableRow(i) = first.productElement(i)
+          i += 1
+        }
+
+        Iterator.single(mutableRow) ++ iterator.map { r =>
+          var i = 0
+          while (i < mutableRow.length) {
+            mutableRow(i) = r.productElement(i)
+            i += 1
+          }
+
+          mutableRow
+        }
+      }
+    }
   }
 
   def fromProductRdd[A <: Product : TypeTag](productRdd: RDD[A]) = {