guykhazma commented on a change in pull request #27157: [SPARK-30475][SQL] File
source V2: Push data filters for file listing
URL: https://github.com/apache/spark/pull/27157#discussion_r365657255
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PruneFileSourcePartitions.scala
##########
@@ -28,20 +28,25 @@ import org.apache.spark.sql.types.StructType
private[sql] object PruneFileSourcePartitions extends Rule[LogicalPlan] {
- private def getPartitionKeyFilters(
+ private def getPartitionKeyFiltersAndDataFilters(
sparkSession: SparkSession,
relation: LeafNode,
partitionSchema: StructType,
filters: Seq[Expression],
- output: Seq[AttributeReference]): ExpressionSet = {
+ 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 partitionSet = AttributeSet(partitionColumns)
- ExpressionSet(normalizedFilters.filter { f =>
+ val partitionKeyFilters = ExpressionSet(normalizedFilters.filter { f =>
Review comment:
fixed
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
