Michael Armbrust created SPARK-10096:
----------------------------------------
Summary: CreateStruct broken with UDFs
Key: SPARK-10096
URL: https://issues.apache.org/jira/browse/SPARK-10096
Project: Spark
Issue Type: Bug
Components: SQL
Affects Versions: 1.5.0
Reporter: Michael Armbrust
Priority: Blocker
{code}
val f = udf((a: String) => a)
val df = sc.parallelize((1,1) :: Nil).toDF("a", "b")
df.select(struct($"a").as("s")).select(f($"s.a")).collect()
{code}
{code}
org.apache.spark.SparkException: Job aborted due to stage failure: Task 3 in
stage 9.0 failed 4 times, most recent failure: Lost task 3.3 in stage 9.0 (TID
78, 10.0.243.97): java.lang.UnsupportedOperationException
at
org.apache.spark.sql.catalyst.expressions.CreateStructUnsafe.eval(complexTypeCreator.scala:209)
at
org.apache.spark.sql.catalyst.expressions.UnaryExpression.eval(Expression.scala:247)
at
org.apache.spark.sql.catalyst.expressions.UnaryExpression.eval(Expression.scala:247)
at
org.apache.spark.sql.catalyst.expressions.ScalaUDF$$anonfun$2.apply(ScalaUDF.scala:76)
at
org.apache.spark.sql.catalyst.expressions.ScalaUDF$$anonfun$2.apply(ScalaUDF.scala:74)
at
org.apache.spark.sql.catalyst.expressions.ScalaUDF.eval(ScalaUDF.scala:964)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificUnsafeProjection.apply(Unknown
Source)
at
org.apache.spark.sql.execution.TungstenProject$$anonfun$3$$anonfun$apply$3.apply(basicOperators.scala:90)
at
org.apache.spark.sql.execution.TungstenProject$$anonfun$3$$anonfun$apply$3.apply(basicOperators.scala:88)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at
scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at
org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:905)
at
org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:905)
at
org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1826)
at
org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1826)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
{code}
--
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
