diff options
| -rw-r--r-- | sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/LogicalRelation.scala | 5 | ||||
| -rw-r--r-- | sql/hive/src/test/scala/org/apache/spark/sql/hive/CachedTableSuite.scala | 11 |
2 files changed, 16 insertions, 0 deletions
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/LogicalRelation.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/LogicalRelation.scala index 783252e0a2..219dae88e5 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/LogicalRelation.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/LogicalRelation.scala @@ -62,6 +62,11 @@ case class LogicalRelation( case _ => false } + // When comparing two LogicalRelations from within LogicalPlan.sameResult, we only need + // LogicalRelation.cleanArgs to return Seq(relation), since expectedOutputAttribute's + // expId can be different but the relation is still the same. + override lazy val cleanArgs: Seq[Any] = Seq(relation) + @transient override lazy val statistics: Statistics = Statistics( sizeInBytes = BigInt(relation.sizeInBytes) ) diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/CachedTableSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/CachedTableSuite.scala index 9adb3780a2..5c2fc7d82f 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/CachedTableSuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/CachedTableSuite.scala @@ -20,6 +20,7 @@ package org.apache.spark.sql.hive import java.io.File import org.apache.spark.sql.columnar.InMemoryColumnarTableScan +import org.apache.spark.sql.execution.datasources.parquet.ParquetRelation import org.apache.spark.sql.hive.test.TestHiveSingleton import org.apache.spark.sql.{AnalysisException, QueryTest, SaveMode} import org.apache.spark.storage.RDDBlockId @@ -203,4 +204,14 @@ class CachedTableSuite extends QueryTest with TestHiveSingleton { sql("DROP TABLE refreshTable") Utils.deleteRecursively(tempPath) } + + test("SPARK-11246 cache parquet table") { + sql("CREATE TABLE cachedTable STORED AS PARQUET AS SELECT 1") + + cacheTable("cachedTable") + val sparkPlan = sql("SELECT * FROM cachedTable").queryExecution.sparkPlan + assert(sparkPlan.collect { case e: InMemoryColumnarTableScan => e }.size === 1) + + sql("DROP TABLE cachedTable") + } } |