diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala index be0d75a8304e9f6b0d4438c6831f4fff7dd689e3..d158a64a85bc080e93757d3eb7b0734fb238d965 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala @@ -509,6 +509,13 @@ object ScalaReflection extends ScalaReflection { serializerFor(unwrapped, optType, newPath)) } + // Since List[_] also belongs to localTypeOf[Product], we put this case before + // "case t if definedByConstructorParams(t)" to make sure it will match to the + // case "localTypeOf[Seq[_]]" + case t if t <:< localTypeOf[Seq[_]] => + val TypeRef(_, _, Seq(elementType)) = t + toCatalystArray(inputObject, elementType) + case t if definedByConstructorParams(t) => val params = getConstructorParameters(t) val nonNullOutput = CreateNamedStruct(params.flatMap { case (fieldName, fieldType) => @@ -524,10 +531,6 @@ object ScalaReflection extends ScalaReflection { val TypeRef(_, _, Seq(elementType)) = t toCatalystArray(inputObject, elementType) - case t if t <:< localTypeOf[Seq[_]] => - val TypeRef(_, _, Seq(elementType)) = t - toCatalystArray(inputObject, elementType) - case t if t <:< localTypeOf[Map[_, _]] => val TypeRef(_, _, Seq(keyType, valueType)) = t diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/ScalaReflectionSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/ScalaReflectionSuite.scala index 0672551b2972d1bc1911082dff3cf39504d607f6..c00e9c7e395618673b8add7bc7694a29b3bd8364 100644 --- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/ScalaReflectionSuite.scala +++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/ScalaReflectionSuite.scala @@ -23,8 +23,9 @@ import java.sql.{Date, Timestamp} import scala.reflect.runtime.universe.typeOf import org.apache.spark.SparkFunSuite -import org.apache.spark.sql.catalyst.expressions.{BoundReference, SpecificMutableRow} +import org.apache.spark.sql.catalyst.expressions.{BoundReference, Literal, NewInstance, SpecificMutableRow} import org.apache.spark.sql.types._ +import org.apache.spark.unsafe.types.UTF8String import org.apache.spark.util.Utils case class PrimitiveData( @@ -277,6 +278,18 @@ class ScalaReflectionSuite extends SparkFunSuite { assert(anyTypes === Seq(classOf[java.lang.Object], classOf[java.lang.Object])) } + test("SPARK-15062: Get correct serializer for List[_]") { + val list = List(1, 2, 3) + val serializer = serializerFor[List[Int]](BoundReference( + 0, ObjectType(list.getClass), nullable = false)) + assert(serializer.children.size == 2) + assert(serializer.children.head.isInstanceOf[Literal]) + assert(serializer.children.head.asInstanceOf[Literal].value === UTF8String.fromString("value")) + assert(serializer.children.last.isInstanceOf[NewInstance]) + assert(serializer.children.last.asInstanceOf[NewInstance] + .cls.isInstanceOf[Class[org.apache.spark.sql.catalyst.util.GenericArrayData]]) + } + private val dataTypeForComplexData = dataTypeFor[ComplexData] private val typeOfComplexData = typeOf[ComplexData]