dongjoon-hyun commented on a change in pull request #23383: [SPARK-23817][SQL]
Create file source V2 framework and migrate ORC read path
URL: https://github.com/apache/spark/pull/23383#discussion_r247029463
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/orc/OrcFilterSuite.scala
##########
@@ -419,3 +428,78 @@ class OrcFilterSuite extends OrcTest with
SharedSQLContext {
}
}
}
+
+class OrcV1FilterSuite extends OrcFilterSuite {
+
+ override protected def sparkConf: SparkConf =
+ super.sparkConf.set(SQLConf.DISABLED_V2_FILE_READS, "orc")
+
+ override def checkFilterPredicate(
+ df: DataFrame,
+ predicate: Predicate,
+ checker: (SearchArgument) => Unit): Unit = {
+ val output = predicate.collect { case a: Attribute => a }.distinct
+ val query = df
+ .select(output.map(e => Column(e)): _*)
+ .where(Column(predicate))
+
+ var maybeRelation: Option[HadoopFsRelation] = None
+ val maybeAnalyzedPredicate = query.queryExecution.optimizedPlan.collect {
+ case PhysicalOperation(_, filters, LogicalRelation(orcRelation:
HadoopFsRelation, _, _, _)) =>
+ maybeRelation = Some(orcRelation)
+ filters
+ }.flatten.reduceLeftOption(_ && _)
+ assert(maybeAnalyzedPredicate.isDefined, "No filter is analyzed from the
given query")
+
+ val (_, selectedFilters, _) =
+ DataSourceStrategy.selectFilters(maybeRelation.get,
maybeAnalyzedPredicate.toSeq)
+ assert(selectedFilters.nonEmpty, "No filter is pushed down")
+
+ val maybeFilter = OrcFilters.createFilter(query.schema, selectedFilters)
+ assert(maybeFilter.isDefined, s"Couldn't generate filter predicate for
$selectedFilters")
+ checker(maybeFilter.get)
+ }
+
+ override def checkFilterPredicate
+ (predicate: Predicate, filterOperator: PredicateLeaf.Operator)
Review comment:
indentation?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on 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]
