eatoncys closed pull request #23517: [SPARK-26599][SQL]BroardCast hint can not
work with PruneFileSourcePartitions
URL: https://github.com/apache/spark/pull/23517
This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:
As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):
diff --git
a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PruneFileSourcePartitions.scala
b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PruneFileSourcePartitions.scala
index 329b9539f52e3..0a1547cf6aac2 100644
---
a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PruneFileSourcePartitions.scala
+++
b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PruneFileSourcePartitions.scala
@@ -20,11 +20,12 @@ package org.apache.spark.sql.execution.datasources
import org.apache.spark.sql.catalyst.catalog.CatalogStatistics
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.planning.PhysicalOperation
-import org.apache.spark.sql.catalyst.plans.logical.{Filter, LogicalPlan,
Project}
+import org.apache.spark.sql.catalyst.plans.logical.{Filter, LogicalPlan,
Project, ResolvedHint}
import org.apache.spark.sql.catalyst.rules.Rule
private[sql] object PruneFileSourcePartitions extends Rule[LogicalPlan] {
override def apply(plan: LogicalPlan): LogicalPlan = plan transformDown {
+ case h: ResolvedHint => h
case op @ PhysicalOperation(projects, filters,
logicalRelation @
LogicalRelation(fsRelation @
diff --git
a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/PruneFileSourcePartitionsSuite.scala
b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/PruneFileSourcePartitionsSuite.scala
index 94384185d190a..4de2776841851 100644
---
a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/PruneFileSourcePartitionsSuite.scala
+++
b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/PruneFileSourcePartitionsSuite.scala
@@ -21,7 +21,7 @@ import org.apache.spark.sql.QueryTest
import org.apache.spark.sql.catalyst.TableIdentifier
import org.apache.spark.sql.catalyst.dsl.expressions._
import org.apache.spark.sql.catalyst.dsl.plans._
-import org.apache.spark.sql.catalyst.plans.logical.{Filter, LogicalPlan,
Project}
+import org.apache.spark.sql.catalyst.plans.logical.{Filter, LogicalPlan,
Project, ResolvedHint}
import org.apache.spark.sql.catalyst.rules.RuleExecutor
import org.apache.spark.sql.execution.datasources.{CatalogFileIndex,
HadoopFsRelation, LogicalRelation, PruneFileSourcePartitions}
import org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat
@@ -91,4 +91,16 @@ class PruneFileSourcePartitionsSuite extends QueryTest with
SQLTestUtils with Te
assert(size2 < tableStats.get.sizeInBytes)
}
}
+
+ test("PruneFileSourcePartitions should not remove the hint") {
+ withTable("t") {
+ spark.range(2).selectExpr("id", "id as
p").write.partitionBy("p").saveAsTable("t")
+ val query = sql("select /*+ broadcastjoin(a) */ * from " +
+ "(select id from t where p=1) a " )
+ val hints = query.queryExecution.optimizedPlan.collect{
+ case h: ResolvedHint => h
+ }
+ assert(hints.size === 1)
+ }
+ }
}
----------------------------------------------------------------
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]
