Github user ericl commented on a diff in the pull request:
https://github.com/apache/spark/pull/14241#discussion_r71090902
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala ---
@@ -205,17 +209,17 @@ private[sql] trait DataSourceScanExec extends
LeafExecNode {
/** Physical plan node for scanning data from a relation. */
private[sql] case class RowDataSourceScanExec(
output: Seq[Attribute],
- rdd: RDD[InternalRow],
+ @transient buildScan: () => RDD[InternalRow],
@transient relation: BaseRelation,
override val outputPartitioning: Partitioning,
override val metadata: Map[String, String],
override val metastoreTableIdentifier: Option[TableIdentifier])
- extends DataSourceScanExec with CodegenSupport {
+ extends DataSourceScanExec {
private[sql] override lazy val metrics =
Map("numOutputRows" -> SQLMetrics.createMetric(sparkContext, "number
of output rows"))
- val outputUnsafeRows = relation match {
+ private val outputUnsafeRows = relation match {
--- End diff --
TODO: why do we need to output unsafe rows? It's weird since this operator
has to inspect the relation implementation to decide whether to do this.
---
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]
