rdblue commented on a change in pull request #31355:
URL: https://github.com/apache/spark/pull/31355#discussion_r577006463



##########
File path: 
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DistributionAndOrderingUtils.scala
##########
@@ -32,23 +32,34 @@ object DistributionAndOrderingUtils {
     case write: RequiresDistributionAndOrdering =>
       val resolver = conf.resolver
 
-      val distribution = write.requiredDistribution match {
+      val numParts = write.requiredNumPartitions()
+      val (distribution, numPartitions) = write.requiredDistribution match {
         case d: OrderedDistribution =>
-          d.ordering.map(e => toCatalyst(e, query, resolver))
+          val dist = d.ordering.map(e => toCatalyst(e, query, resolver))
+          (dist, numParts)
         case d: ClusteredDistribution =>
-          d.clustering.map(e => toCatalyst(e, query, resolver))
+          val dist = d.clustering.map(e => toCatalyst(e, query, resolver))
+          (dist, numParts)
         case _: UnspecifiedDistribution =>
-          Array.empty[Expression]
+          (Array.empty[Expression], numParts)
       }
 
       val queryWithDistribution = if (distribution.nonEmpty) {
-        val numShufflePartitions = conf.numShufflePartitions
+        val finalNumPartitions = if (numPartitions > 0) {
+          numPartitions
+        } else {
+          conf.numShufflePartitions
+        }
         // the conversion to catalyst expressions above produces SortOrder 
expressions
         // for OrderedDistribution and generic expressions for 
ClusteredDistribution
         // this allows RepartitionByExpression to pick either range or hash 
partitioning
-        RepartitionByExpression(distribution, query, numShufflePartitions)
+        RepartitionByExpression(distribution, query, finalNumPartitions)
       } else {
-        query
+        if (numPartitions > 0) {

Review comment:
       You could avoid changing a few more lines by using `else if`.




----------------------------------------------------------------
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.

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

Reply via email to