diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala index 037f8cb2873bf1f6dfdff255a7577272896af841..893af5146c5b3f2b4e187b858fdeffb88cb83431 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala @@ -618,7 +618,9 @@ abstract class TreeNode[BaseType <: TreeNode[BaseType]] extends Product { case s: String => JString(s) case u: UUID => JString(u.toString) case dt: DataType => dt.jsonValue - case m: Metadata => m.jsonValue + // SPARK-17356: In usage of mllib, Metadata may store a huge vector of data, transforming + // it to JSON may trigger OutOfMemoryError. + case m: Metadata => Metadata.empty.jsonValue case s: StorageLevel => ("useDisk" -> s.useDisk) ~ ("useMemory" -> s.useMemory) ~ ("useOffHeap" -> s.useOffHeap) ~ ("deserialized" -> s.deserialized) ~ ("replication" -> s.replication) diff --git a/sql/core/src/test/scala/org/apache/spark/sql/QueryTest.scala b/sql/core/src/test/scala/org/apache/spark/sql/QueryTest.scala index c7af40227d45fb62679400947c3c94fe100e40e9..d361f61764d1fad32a609389def30000cf36d8a6 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/QueryTest.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/QueryTest.scala @@ -33,7 +33,7 @@ import org.apache.spark.sql.execution.aggregate.TypedAggregateExpression import org.apache.spark.sql.execution.columnar.InMemoryRelation import org.apache.spark.sql.execution.datasources.LogicalRelation import org.apache.spark.sql.execution.streaming.MemoryPlan -import org.apache.spark.sql.types.ObjectType +import org.apache.spark.sql.types.{Metadata, ObjectType} abstract class QueryTest extends PlanTest { @@ -274,6 +274,14 @@ abstract class QueryTest extends PlanTest { val normalized1 = logicalPlan.transformAllExpressions { case udf: ScalaUDF => udf.copy(function = null) case gen: UserDefinedGenerator => gen.copy(function = null) + // After SPARK-17356: the JSON representation no longer has the Metadata. We need to remove + // the Metadata from the normalized plan so that we can compare this plan with the + // JSON-deserialzed plan. + case a @ Alias(child, name) if a.explicitMetadata.isDefined => + Alias(child, name)(a.exprId, a.qualifier, Some(Metadata.empty), a.isGenerated) + case a: AttributeReference if a.metadata != Metadata.empty => + AttributeReference(a.name, a.dataType, a.nullable, Metadata.empty)(a.exprId, a.qualifier, + a.isGenerated) } // RDDs/data are not serializable to JSON, so we need to collect LogicalPlans that contains