Github user navis commented on a diff in the pull request:
https://github.com/apache/spark/pull/6767#discussion_r45292499
--- Diff:
sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala ---
@@ -523,6 +531,30 @@ class HiveContext(sc: SparkContext) extends
SQLContext(sc) with Logging {
super.dialectClassName
}
+ override protected[sql] def newOptimizer: Optimizer = new Optimizer {
+ override protected val batches =
+ DefaultOptimizer.batches.asInstanceOf[Seq[Batch]] ++
+ Seq(Batch("Hive Table Stats", Once, new HiveTableStats))
+ }
+
+ class HiveTableStats extends Rule[LogicalPlan] {
+ def apply(plan: LogicalPlan): LogicalPlan = plan match {
+ case PhysicalOperation(projectList, predicates, relation:
MetastoreRelation) =>
+ // 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.partitionKeys)
+ val (pruningPredicates, _) = predicates.partition { predicate =>
+ !predicate.references.isEmpty &&
--- End diff --
ok
---
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]
