Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/11141#discussion_r52836757
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala ---
@@ -118,6 +120,30 @@ private[sql] case class PhysicalRDD(
val metadataEntries = for ((key, value) <- metadata.toSeq.sorted)
yield s"$key: $value"
s"Scan $nodeName${output.mkString("[", ",",
"]")}${metadataEntries.mkString(" ", ", ", "")}"
}
+
+ override def upstream(): RDD[InternalRow] = {
+ rdd
+ }
+
+ // Support codegen so that we can avoid the UnsafeRow conversion in all
cases. Codegen
+ // never requires UnsafeRow as input.
+ override protected def doProduce(ctx: CodegenContext): String = {
+ val exprs = output.zipWithIndex.map(x => new BoundReference(x._2,
x._1.dataType, true))
+ val row = ctx.freshName("row")
+ ctx.INPUT_ROW = row
+ ctx.currentVars = null
+ val columns = exprs.map(_.gen(ctx))
+ s"""
+ | while (input.hasNext()) {
+ | InternalRow $row = (InternalRow) input.next();
+ | ${columns.map(_.code).mkString("\n").trim}
+ | ${consume(ctx, columns).trim}
--- End diff --
Could you add SQL metric for "numOutputRows"?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
