viirya commented on a change in pull request #29831:
URL: https://github.com/apache/spark/pull/29831#discussion_r494671976
##########
File path:
sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveStrategies.scala
##########
@@ -254,22 +254,28 @@ private[hive] trait HiveStrategies {
* Retrieves data using a HiveTableScan. Partition pruning predicates are
also detected and
* applied.
*/
- object HiveTableScans extends Strategy {
+ object HiveTableScans extends Strategy with PredicateHelper {
def apply(plan: LogicalPlan): Seq[SparkPlan] = plan match {
- case ScanOperation(projectList, predicates, relation: HiveTableRelation)
=>
+ case ScanOperation(projectList, filters, relation: HiveTableRelation) =>
// Filter out all predicates that only deal with partition keys, these
are given to the
// hive table scan operator to be used for partition pruning.
val partitionKeyIds = AttributeSet(relation.partitionCols)
- val (pruningPredicates, otherPredicates) = predicates.partition {
predicate =>
- !predicate.references.isEmpty &&
- predicate.references.subsetOf(partitionKeyIds)
+ val normalized = DataSourceStrategy.normalizeExprs(
+ filters.filter(_.deterministic), relation.output)
+ val partitionKeyFilters = if (relation.partitionCols.isEmpty) {
+ ExpressionSet(Nil)
+ } else {
+ val predicates = ExpressionSet(normalized
+ .flatMap(extractPredicatesWithinOutputSet(_, partitionKeyIds)))
+ logInfo(s"Pruning partitions with: ${filters.mkString(",")}")
+ predicates
}
pruneFilterProject(
projectList,
- otherPredicates,
+ (ExpressionSet(filters) -- partitionKeyFilters).toSeq,
Review comment:
Hmm, looks should be fine as `ExpressionSet` will canonicalize
expressions.
----------------------------------------------------------------
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:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
