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 9013fd050b5f99535b6f53622de0c9026254b053..ecff8605706de9b50d8304817552ac46edd8f4f4 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 @@ -184,7 +184,7 @@ object ScalaReflection extends ScalaReflection { val TypeRef(_, _, Seq(optType)) = t val className = getClassNameFromType(optType) val newTypePath = s"""- option value class: "$className"""" +: walkedTypePath - WrapOption(constructorFor(optType, path, newTypePath)) + WrapOption(constructorFor(optType, path, newTypePath), dataTypeFor(optType)) case t if t <:< localTypeOf[java.lang.Integer] => val boxedType = classOf[java.lang.Integer] diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoder.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoder.scala index 3e8420ecb9ccf64ce8cf3f0665cd31965f2cdcbd..363178b0e21a21807e469a37fa512a0d1e8ef1b2 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoder.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoder.scala @@ -251,6 +251,7 @@ case class ExpressionEncoder[T]( val plan = Project(Alias(unbound, "")() :: Nil, LocalRelation(schema)) val analyzedPlan = SimpleAnalyzer.execute(plan) + SimpleAnalyzer.checkAnalysis(analyzedPlan) val optimizedPlan = SimplifyCasts(analyzedPlan) // In order to construct instances of inner classes (for example those declared in a REPL cell), diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects.scala index 96bc4fe67a985b8e09ddf10430a511d2dc48a104..10ec75eca37f2ea1a0b8a2f999edd6f5f87e08ea 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects.scala @@ -23,11 +23,9 @@ import scala.reflect.ClassTag import org.apache.spark.SparkConf import org.apache.spark.serializer._ import org.apache.spark.sql.Row -import org.apache.spark.sql.catalyst.analysis.SimpleAnalyzer -import org.apache.spark.sql.catalyst.plans.logical.{Project, LocalRelation} -import org.apache.spark.sql.catalyst.util.GenericArrayData import org.apache.spark.sql.catalyst.InternalRow -import org.apache.spark.sql.catalyst.expressions.codegen.{GeneratedExpressionCode, CodeGenContext} +import org.apache.spark.sql.catalyst.expressions.codegen.{CodeGenContext, GeneratedExpressionCode} +import org.apache.spark.sql.catalyst.util.GenericArrayData import org.apache.spark.sql.types._ /** @@ -295,13 +293,17 @@ case class UnwrapOption( * Converts the result of evaluating `child` into an option, checking both the isNull bit and * (in the case of reference types) equality with null. * @param child The expression to evaluate and wrap. + * @param optType The type of this option. */ -case class WrapOption(child: Expression) extends UnaryExpression { +case class WrapOption(child: Expression, optType: DataType) + extends UnaryExpression with ExpectsInputTypes { override def dataType: DataType = ObjectType(classOf[Option[_]]) override def nullable: Boolean = true + override def inputTypes: Seq[AbstractDataType] = optType :: Nil + override def eval(input: InternalRow): Any = throw new UnsupportedOperationException("Only code-generated evaluation is supported") diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala index 542e4d6c43b9fdcad3f8115815230424d1fef002..8f8db318261db7622797cd7155ac5445f598eb7c 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala @@ -481,10 +481,18 @@ class DatasetSuite extends QueryTest with SharedSQLContext { val ds = Seq(2 -> 2.toByte, 3 -> 3.toByte).toDF("a", "b").as[ClassData] assert(ds.collect().toSeq == Seq(ClassData("2", 2), ClassData("3", 3))) } -} + test("verify mismatching field names fail with a good error") { + val ds = Seq(ClassData("a", 1)).toDS() + val e = intercept[AnalysisException] { + ds.as[ClassData2].collect() + } + assert(e.getMessage.contains("cannot resolve 'c' given input columns a, b"), e.getMessage) + } +} case class ClassData(a: String, b: Int) +case class ClassData2(c: String, d: Int) case class ClassNullableData(a: String, b: Integer) /**