namrathamyske commented on code in PR #8042:
URL: https://github.com/apache/iceberg/pull/8042#discussion_r1281298546
##########
spark/v3.3/spark-extensions/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ExtendedDistributionAndOrderingUtils.scala:
##########
@@ -57,10 +57,28 @@ object ExtendedDistributionAndOrderingUtils {
} 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(ArraySeq.unsafeWrapArray(distribution), query,
finalNumPartitions)
+
+ val isHashDistributionMode = write.requiredDistribution match {
+ case _ : ClusteredDistribution => true
+ case _ => false
+ }
+
+ val strictDistributionMode =
conf.getConfString(SparkSQLProperties.STRICT_TABLE_DISTRIBUTION,
+ SparkSQLProperties.STRICT_TABLE_DISTRIBUTION_DEFAULT)
+
+ if (strictDistributionMode.equals("false") && isHashDistributionMode) {
Review Comment:
Thanks for suggestion @ConeyLiu !
--
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]
