cloud-fan commented on a change in pull request #34575:
URL: https://github.com/apache/spark/pull/34575#discussion_r755163320
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala
##########
@@ -194,10 +195,22 @@ case class FileSourceScanExec(
disableBucketedScan: Boolean = false)
extends DataSourceScanExec {
+ lazy val outputMetadataStruct: Option[AttributeReference] =
+ output.collectFirst { case MetadataAttribute(attr) => attr }
+
// Note that some vals referring the file-based relation are lazy
intentionally
// so that this plan can be canonicalized on executor side too. See
SPARK-23731.
override lazy val supportsColumnar: Boolean = {
- relation.fileFormat.supportBatch(relation.sparkSession, schema)
+ // schema without the file metadata column
+ val fileSchema = if (outputMetadataStruct.isEmpty) schema else {
+ StructType.fromAttributes(
Review comment:
nit: `output.filterNot(_.exprId ==
metadataStructCol.get.exprId).toStruct`
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
