[jira] [Reopened] (SPARK-13456) Cannot create encoders for case classes defined in Spark shell after upgrading to Scala 2.11
[
https://issues.apache.org/jira/browse/SPARK-13456?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Jacek Laskowski reopened SPARK-13456:
-
It appears that the issue has not been resolved properly entirely yet.
> 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
>Assignee: Wenchen Fan
>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
[jira] [Reopened] (SPARK-13456) Cannot create encoders for case classes defined in Spark shell after upgrading to Scala 2.11
[
https://issues.apache.org/jira/browse/SPARK-13456?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Jacek Laskowski reopened SPARK-13456:
-
In today's Spark 2.0.0-SNAPSHOT:
{code}
scala> :pa
// Entering paste mode (ctrl-D to finish)
import sqlContext.implicits._
case class Token(name: String, productId: Int, score: Double)
val data = Token("aaa", 100, 0.12) ::
Token("aaa", 200, 0.29) ::
Token("bbb", 200, 0.53) ::
Token("bbb", 300, 0.42) :: Nil
val ds = data.toDS
// Exiting paste mode, now interpreting.
java.lang.NullPointerException
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at
org.apache.spark.sql.catalyst.encoders.OuterScopes$.getOuterScope(OuterScopes.scala:64)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$resolveDeserializer$1.applyOrElse(Analyzer.scala:588)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$resolveDeserializer$1.applyOrElse(Analyzer.scala:580)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:259)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:259)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:67)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:258)
at org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:248)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.resolveDeserializer(Analyzer.scala:580)
at
org.apache.spark.sql.catalyst.encoders.ExpressionEncoder.resolve(ExpressionEncoder.scala:321)
at org.apache.spark.sql.Dataset.(Dataset.scala:197)
at org.apache.spark.sql.Dataset.(Dataset.scala:164)
at org.apache.spark.sql.Dataset$.apply(Dataset.scala:53)
at org.apache.spark.sql.SQLContext.createDataset(SQLContext.scala:448)
at
org.apache.spark.sql.SQLImplicits.localSeqToDatasetHolder(SQLImplicits.scala:152)
... 47 elided
{code}
> Cannot create encoders for case classes defined in Spark shell after
> upgrading to Scala 2.11
>
>
> Key: SPARK-13456
> URL: https://issues.apache.org/jira/browse/SPARK-13456
> Project: Spark
> Issue Type: Bug
> Components: SQL
>Affects Versions: 2.0.0
>Reporter: Cheng Lian
>Assignee: Wenchen Fan
>Priority: Blocker
> Fix For: 2.0.0
>
>
> Spark 2.0 started to use Scala 2.11 by default since [PR
> #10608|https://github.com/apache/spark/pull/10608]. Unfortunately, after
> this upgrade, Spark fails to create encoders for case classes defined in REPL:
> {code}
> import sqlContext.implicits._
> case class T(a: Int, b: Double)
> val ds = Seq(1 -> T(1, 1D), 2 -> T(2, 2D)).toDS()
> {code}
> Exception thrown:
> {noformat}
> org.apache.spark.sql.AnalysisException: Unable to generate an encoder for
> inner class `T` without access to the scope that this class was defined in.
> Try moving this class out of its parent class.;
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$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
