cloud-fan commented on code in PR #49027:
URL: https://github.com/apache/spark/pull/49027#discussion_r1908135003
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/V1Writes.scala:
##########
@@ -156,32 +167,34 @@ object V1WritesUtils {
}
}
- def getSortOrder(
+ def getClusteringSpec(
outputColumns: Seq[Attribute],
partitionColumns: Seq[Attribute],
bucketSpec: Option[BucketSpec],
options: Map[String, String],
- numStaticPartitionCols: Int = 0): Seq[SortOrder] = {
+ numStaticPartitionCols: Int = 0): Option[ClusteringSpec] = {
require(partitionColumns.size >= numStaticPartitionCols)
val partitionSet = AttributeSet(partitionColumns)
val dataColumns = outputColumns.filterNot(partitionSet.contains)
val writerBucketSpec = V1WritesUtils.getWriterBucketSpec(bucketSpec,
dataColumns, options)
val sortColumns = V1WritesUtils.getBucketSortColumns(bucketSpec,
dataColumns)
- // Static partition must to be ahead of dynamic partition
+ // Static partition must be ahead of dynamic partition
val dynamicPartitionColumns = partitionColumns.drop(numStaticPartitionCols)
if (SQLConf.get.maxConcurrentOutputFileWriters > 0 && sortColumns.isEmpty)
{
// Do not insert logical sort when concurrent output writers are enabled.
- Seq.empty
+ None
} else {
- // We should first sort by dynamic partition columns, then bucket id,
and finally sorting
+ // We should first cluster by dynamic partition columns, then bucket id,
and finally sorting
// columns.
- (dynamicPartitionColumns ++ writerBucketSpec.map(_.bucketIdExpression)
++ sortColumns)
- .map(SortOrder(_, Ascending))
+ val clusteringKeys = dynamicPartitionColumns ++
writerBucketSpec.map(_.bucketIdExpression)
+ val sortKeys = sortColumns.map(SortOrder(_, Ascending))
+ Some(ClusteringSpec(clusteringKeys, sortKeys))
}
}
+
Review Comment:
```suggestion
```
--
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]
