cloud-fan commented on a change in pull request #35691:
URL: https://github.com/apache/spark/pull/35691#discussion_r817405246
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PruneFileSourcePartitions.scala
##########
@@ -46,21 +46,27 @@ private[sql] object PruneFileSourcePartitions
private def getPartitionKeyFiltersAndDataFilters(
sparkSession: SparkSession,
relation: LeafNode,
+ dataSchema: StructType,
partitionSchema: StructType,
filters: Seq[Expression],
output: Seq[AttributeReference]): (ExpressionSet, Seq[Expression]) = {
val normalizedFilters = DataSourceStrategy.normalizeExprs(
filters.filter(f => f.deterministic &&
!SubqueryExpression.hasSubquery(f)), output)
val partitionColumns =
relation.resolve(partitionSchema,
sparkSession.sessionState.analyzer.resolver)
+ val dataColumns =
+ relation.resolve(dataSchema, sparkSession.sessionState.analyzer.resolver)
val partitionSet = AttributeSet(partitionColumns)
- val (partitionFilters, dataFilters) = normalizedFilters.partition(f =>
- f.references.subsetOf(partitionSet)
- )
- val extraPartitionFilter =
- dataFilters.flatMap(extractPredicatesWithinOutputSet(_, partitionSet))
Review comment:
Does this line cause stack overflow?
--
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]
