sunchao commented on code in PR #42757:
URL: https://github.com/apache/spark/pull/42757#discussion_r1313484666
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/BatchScanExec.scala:
##########
@@ -137,81 +136,63 @@ case class BatchScanExec(
outputPartitioning match {
case p: KeyGroupedPartitioning =>
- if (conf.v2BucketingPushPartValuesEnabled &&
- conf.v2BucketingPartiallyClusteredDistributionEnabled) {
- assert(filteredPartitions.forall(_.size == 1),
- "Expect partitions to be not grouped when " +
-
s"${SQLConf.V2_BUCKETING_PARTIALLY_CLUSTERED_DISTRIBUTION_ENABLED.key} " +
- "is enabled")
-
- val groupedPartitions =
groupPartitions(finalPartitions.map(_.head),
- groupSplits = true).get
-
- // This means the input partitions are not grouped by partition
values. We'll need to
- // check `groupByPartitionValues` and decide whether to group and
replicate splits
- // within a partition.
- if (spjParams.commonPartitionValues.isDefined &&
- spjParams.applyPartialClustering) {
- // A mapping from the common partition values to how many splits
the partition
- // should contain.
- val commonPartValuesMap = spjParams.commonPartitionValues
+ val groupedPartitions = filteredPartitions.map(splits => {
+ assert(splits.nonEmpty &&
splits.head.isInstanceOf[HasPartitionKey])
+ (splits.head.asInstanceOf[HasPartitionKey].partitionKey(), splits)
+ })
+
+ // This means the input partitions are not grouped by partition
values. We'll need to
Review Comment:
Yes, let me improve this comments too.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
