Github user lianhuiwang commented on a diff in the pull request:
https://github.com/apache/spark/pull/18193#discussion_r121985050
--- Diff:
sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveStrategies.scala ---
@@ -139,6 +138,54 @@ class DetermineTableStats(session: SparkSession)
extends Rule[LogicalPlan] {
}
}
+case class DeterminePartitionedTableStats(
+ session: SparkSession) extends Rule[LogicalPlan] with PredicateHelper {
+ override def apply(plan: LogicalPlan): LogicalPlan = plan transformDown {
+ case filter @ Filter(condition, relation: CatalogRelation)
+ if DDLUtils.isHiveTable(relation.tableMeta) &&
relation.isPartitioned =>
+ val predicates = splitConjunctivePredicates(condition)
+ val normalizedFilters = predicates.map { e =>
+ e transform {
+ case a: AttributeReference =>
+ a.withName(relation.output.find(_.semanticEquals(a)).get.name)
+ }
+ }
+ val partitionSet = AttributeSet(relation.partitionCols)
+ val pruningPredicates = normalizedFilters.filter { predicate =>
+ !predicate.references.isEmpty &&
+ predicate.references.subsetOf(partitionSet)
+ }
+ if (pruningPredicates.nonEmpty &&
session.sessionState.conf.fallBackToHdfsForStatsEnabled &&
+ session.sessionState.conf.metastorePartitionPruning) {
+ val prunedPartitions =
session.sharedState.externalCatalog.listPartitionsByFilter(
+ relation.tableMeta.database,
+ relation.tableMeta.identifier.table,
+ pruningPredicates,
+ session.sessionState.conf.sessionLocalTimeZone)
+ val hiveTable = HiveClientImpl.toHiveTable(relation.tableMeta)
+ val partitions =
prunedPartitions.map(HiveClientImpl.toHivePartition(_, hiveTable))
+ val sizeInBytes = try {
--- End diff --
If we already have partition level statistics, But we cannot know total
number of partition, so it cannot compute the statistics for pruned partitions.
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
