Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/11509#discussion_r55070549
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala ---
@@ -173,16 +173,17 @@ private[sql] object PhysicalRDD {
rdd: RDD[InternalRow],
relation: BaseRelation,
metadata: Map[String, String] = Map.empty): PhysicalRDD = {
- val outputUnsafeRows = if (relation.isInstanceOf[ParquetRelation]) {
- // The vectorized parquet reader does not produce unsafe rows.
-
!SQLContext.getActive().get.conf.getConf(SQLConf.PARQUET_VECTORIZED_READER_ENABLED)
- } else {
- // All HadoopFsRelations output UnsafeRows
- relation.isInstanceOf[HadoopFsRelation]
+
+ val outputUnsafeRows = relation match {
+ case r: HadoopFsRelation if r.fileFormat.isInstanceOf[DefaultSource]
=>
--- End diff --
import DefaultSource as ParquetSource ? Or this looks confusing.
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
