Github user yhuai commented on a diff in the pull request:
https://github.com/apache/spark/pull/9399#discussion_r43590284
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala
---
@@ -266,26 +267,39 @@ private[sql] object DataSourceStrategy extends
Strategy with Logging {
relation,
projects,
filterPredicates,
- (requestedColumns, pushedFilters) => {
- scanBuilder(requestedColumns, selectFilters(pushedFilters).toArray)
+ (requestedColumns, _, pushedFilters) => {
+ scanBuilder(requestedColumns, pushedFilters.toArray)
})
}
// Based on Catalyst expressions.
protected def pruneFilterProjectRaw(
- relation: LogicalRelation,
- projects: Seq[NamedExpression],
- filterPredicates: Seq[Expression],
- scanBuilder: (Seq[Attribute], Seq[Expression]) => RDD[InternalRow])
= {
+ relation: LogicalRelation,
+ projects: Seq[NamedExpression],
+ filterPredicates: Seq[Expression],
+ scanBuilder: (Seq[Attribute], Seq[Expression], Seq[Filter]) =>
RDD[InternalRow]) = {
val projectSet = AttributeSet(projects.flatMap(_.references))
val filterSet = AttributeSet(filterPredicates.flatMap(_.references))
- val filterCondition =
filterPredicates.reduceLeftOption(expressions.And)
- val pushedFilters = filterPredicates.map { _ transform {
- case a: AttributeReference => relation.attributeMap(a) // Match
original case of attributes.
+ val candidatePredicates = filterPredicates.map { _ transform {
+ case a: AttributeReference => relation.attributeMap(a) // Match
original case of attributes.
}}
+ val (unhandledPredicates, pushedFilters) =
+ selectFilters(relation.relation, candidatePredicates)
+
+ val handledSet = {
+ val handledPredicates =
filterPredicates.filterNot(unhandledPredicates.contains)
+ val unhandledSet =
AttributeSet(unhandledPredicates.flatMap(_.references))
+ AttributeSet(handledPredicates.flatMap(_.references)) --
+ (projectSet ++ unhandledSet).map(relation.attributeMap)
+ }
--- End diff --
Let's add comments?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
