cloud-fan commented on code in PR #38924:
URL: https://github.com/apache/spark/pull/38924#discussion_r1041721325
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/BatchScanExec.scala:
##########
@@ -114,8 +117,21 @@ case class BatchScanExec(
// return an empty RDD with 1 partition if dynamic filtering removed the
only split
sparkContext.parallelize(Array.empty[InternalRow], 1)
} else {
+ var finalPartitions = filteredPartitions
+
+ outputPartitioning match {
+ case p: KeyGroupedPartitioning =>
+ val partitionMapping = finalPartitions.map(s =>
+ s.head.asInstanceOf[HasPartitionKey].partitionKey() -> s).toMap
+ finalPartitions = p.partitionValuesOpt.get.map { partKey =>
Review Comment:
shall we move this logic to `lazy val filteredPartitions`?
--
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
