[ https://issues.apache.org/jira/browse/SPARK-13456?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Yin Huai resolved SPARK-13456. ------------------------------ Resolution: Fixed Fix Version/s: 2.0.0 Issue resolved by pull request 11410 [https://github.com/apache/spark/pull/11410] > Cannot create encoders for case classes defined in Spark shell after > upgrading to Scala 2.11 > -------------------------------------------------------------------------------------------- > > Key: SPARK-13456 > URL: https://issues.apache.org/jira/browse/SPARK-13456 > Project: Spark > Issue Type: Bug > Components: SQL > Affects Versions: 2.0.0 > Reporter: Cheng Lian > Priority: Blocker > Fix For: 2.0.0 > > > Spark 2.0 started to use Scala 2.11 by default since [PR > #10608|https://github.com/apache/spark/pull/10608]. Unfortunately, after > this upgrade, Spark fails to create encoders for case classes defined in REPL: > {code} > import sqlContext.implicits._ > case class T(a: Int, b: Double) > val ds = Seq(1 -> T(1, 1D), 2 -> T(2, 2D)).toDS() > {code} > Exception thrown: > {noformat} > org.apache.spark.sql.AnalysisException: Unable to generate an encoder for > inner class `T` without access to the scope that this class was defined in. > Try moving this class out of its parent class.; > at > org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$resolveDeserializer$1.applyOrElse(Analyzer.scala:565) > at > org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$resolveDeserializer$1.applyOrElse(Analyzer.scala:561) > at > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:262) > at > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:262) > at > org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70) > at > org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:261) > at > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:267) > at > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:267) > at > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:304) > at scala.collection.Iterator$$anon$11.next(Iterator.scala:370) > at scala.collection.Iterator$class.foreach(Iterator.scala:742) > at scala.collection.AbstractIterator.foreach(Iterator.scala:1194) > at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59) > at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:104) > at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:48) > at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:308) > at scala.collection.AbstractIterator.to(Iterator.scala:1194) > at > scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:300) > at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1194) > at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:287) > at scala.collection.AbstractIterator.toArray(Iterator.scala:1194) > at > org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:353) > at > org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:267) > at > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:267) > at > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:267) > at > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5$$anonfun$apply$11.apply(TreeNode.scala:333) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245) > at scala.collection.immutable.List.foreach(List.scala:381) > at scala.collection.TraversableLike$class.map(TraversableLike.scala:245) > at scala.collection.immutable.List.map(List.scala:285) > at > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:331) > at scala.collection.Iterator$$anon$11.next(Iterator.scala:370) > at scala.collection.Iterator$class.foreach(Iterator.scala:742) > at scala.collection.AbstractIterator.foreach(Iterator.scala:1194) > at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59) > at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:104) > at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:48) > at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:308) > at scala.collection.AbstractIterator.to(Iterator.scala:1194) > at > scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:300) > at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1194) > at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:287) > at scala.collection.AbstractIterator.toArray(Iterator.scala:1194) > at > org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:353) > at > org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:267) > at > org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:251) > at > org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.resolveDeserializer(Analyzer.scala:561) > at > org.apache.spark.sql.catalyst.encoders.ExpressionEncoder.resolve(ExpressionEncoder.scala:315) > at org.apache.spark.sql.Dataset.<init>(Dataset.scala:81) > at org.apache.spark.sql.Dataset.<init>(Dataset.scala:92) > at org.apache.spark.sql.SQLContext.createDataset(SQLContext.scala:482) > at > org.apache.spark.sql.SQLImplicits.localSeqToDatasetHolder(SQLImplicits.scala:140) > ... 51 elided > {noformat} > However, existing Dataset REPL test case does pass: > {code} > test("SPARK-2576 importing SQLContext.implicits._") { > // We need to use local-cluster to test this case. > val output = runInterpreter("local-cluster[1,1,1024]", > """ > |val sqlContext = new org.apache.spark.sql.SQLContext(sc) > |import sqlContext.implicits._ > |case class TestCaseClass(value: Int) > |sc.parallelize(1 to 10).map(x => TestCaseClass(x)).toDF().collect() > | > |// Test Dataset Serialization in the REPL > |Seq(TestCaseClass(1)).toDS().collect() > """.stripMargin) > assertDoesNotContain("error:", output) > assertDoesNotContain("Exception", output) > } > {code} > One possible clue is that, {{ReplSuite}} calls {{SparkILoop}} directly, while > Spark shell is started by {{o.a.s.repl.Main}}, which also sets option > {{-Yrepl-class-based}}. -- This message was sent by Atlassian JIRA (v6.3.4#6332) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org