org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 13.0 failed 1 times, most recent failure: Lost task 0.0 in stage 13.0 (TID 13, localhost): java.lang.ClassCastException: java.lang.String cannot be cast to org.apache.spark.sql.types.UTF8String

DataStax JIRA | Piotr Kołaczkowski | 2 years ago
tip
Your exception is missing from the Samebug knowledge base.
Here are the best solutions we found on the Internet.
Click on the to mark the helpful solution and get rewards for you help.
  1. 0

    [SPARKC-195] SparkSQL class cast exceptions when reading data from CassandraSQLRow - DataStax

    atlassian.net | 11 months ago
    org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 13.0 failed 1 times, most recent failure: Lost task 0.0 in stage 13.0 (TID 13, localhost): java.lang.ClassCastException: java.lang.String cannot be cast to org.apache.spark.sql.types.UTF8String
  2. 0

    {noformat} [info] - should allow to select rows for collection columns *** FAILED *** (83 milliseconds) [info] org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 62.0 failed 1 times, most recent failure: Lost task 0.0 in stage 62.0 (TID 2654, localhost): java.lang.ClassCastException: scala.collection.immutable.Set$Set3 cannot be cast to scala.collection.Seq [info] at org.apache.spark.sql.catalyst.CatalystTypeConverters$$anonfun$createToScalaConverter$2.apply(CatalystTypeConverters.scala:282) [info] at org.apache.spark.sql.catalyst.CatalystTypeConverters$.convertRowWithConverters(CatalystTypeConverters.scala:348) [info] at org.apache.spark.sql.catalyst.CatalystTypeConverters$$anonfun$createToScalaConverter$4.apply(CatalystTypeConverters.scala:301) [info] at org.apache.spark.sql.execution.SparkPlan$$anonfun$1$$anonfun$apply$1.apply(SparkPlan.scala:104) [info] at org.apache.spark.sql.execution.SparkPlan$$anonfun$1$$anonfun$apply$1.apply(SparkPlan.scala:104) [info] at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) [info] at scala.collection.Iterator$class.foreach(Iterator.scala:727) [info] at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) [info] at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48) [info] at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103) [info] at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47) [info] at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273) [info] at scala.collection.AbstractIterator.to(Iterator.scala:1157) [info] at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265) [info] at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157) [info] at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252) [info] at scala.collection.AbstractIterator.toArray(Iterator.scala:1157) [info] at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) [info] at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) [info] at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) [info] at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) [info] at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63) [info] at org.apache.spark.scheduler.Task.run(Task.scala:70) [info] at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213) [info] at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) [info] at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) [info] at java.lang.Thread.run(Thread.java:745) [info] [info] Driver stacktrace: [info] at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1266) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1257) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1256) [info] at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) [info] at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) [info] at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1256) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730) [info] at scala.Option.foreach(Option.scala:236) [info] at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:730) [info] at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1450) [info] at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1411) [info] at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) {noformat} {noformat} [info] - should allow to select rows with like clause *** FAILED *** (209 milliseconds) [info] org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 13.0 failed 1 times, most recent failure: Lost task 0.0 in stage 13.0 (TID 13, localhost): java.lang.ClassCastException: java.lang.String cannot be cast to org.apache.spark.sql.types.UTF8String [info] at org.apache.spark.sql.catalyst.expressions.StringComparison$class.eval(stringOperations.scala:175) [info] at org.apache.spark.sql.catalyst.expressions.EndsWith.eval(stringOperations.scala:203) [info] at org.apache.spark.sql.catalyst.expressions.InterpretedPredicate$$anonfun$create$1.apply(predicates.scala:30) [info] at org.apache.spark.sql.catalyst.expressions.InterpretedPredicate$$anonfun$create$1.apply(predicates.scala:30) [info] at scala.collection.Iterator$$anon$14.hasNext(Iterator.scala:390) [info] at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327) [info] at scala.collection.Iterator$class.foreach(Iterator.scala:727) [info] at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) [info] at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48) [info] at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103) [info] at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47) [info] at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273) [info] at scala.collection.AbstractIterator.to(Iterator.scala:1157) [info] at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265) [info] at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157) [info] at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252) [info] at scala.collection.AbstractIterator.toArray(Iterator.scala:1157) [info] at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) [info] at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) [info] at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) {noformat}

    DataStax JIRA | 2 years ago | Piotr Kołaczkowski
    org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 13.0 failed 1 times, most recent failure: Lost task 0.0 in stage 13.0 (TID 13, localhost): java.lang.ClassCastException: java.lang.String cannot be cast to org.apache.spark.sql.types.UTF8String
  3. 0

    {noformat} [info] - should allow to select rows for collection columns *** FAILED *** (83 milliseconds) [info] org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 62.0 failed 1 times, most recent failure: Lost task 0.0 in stage 62.0 (TID 2654, localhost): java.lang.ClassCastException: scala.collection.immutable.Set$Set3 cannot be cast to scala.collection.Seq [info] at org.apache.spark.sql.catalyst.CatalystTypeConverters$$anonfun$createToScalaConverter$2.apply(CatalystTypeConverters.scala:282) [info] at org.apache.spark.sql.catalyst.CatalystTypeConverters$.convertRowWithConverters(CatalystTypeConverters.scala:348) [info] at org.apache.spark.sql.catalyst.CatalystTypeConverters$$anonfun$createToScalaConverter$4.apply(CatalystTypeConverters.scala:301) [info] at org.apache.spark.sql.execution.SparkPlan$$anonfun$1$$anonfun$apply$1.apply(SparkPlan.scala:104) [info] at org.apache.spark.sql.execution.SparkPlan$$anonfun$1$$anonfun$apply$1.apply(SparkPlan.scala:104) [info] at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) [info] at scala.collection.Iterator$class.foreach(Iterator.scala:727) [info] at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) [info] at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48) [info] at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103) [info] at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47) [info] at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273) [info] at scala.collection.AbstractIterator.to(Iterator.scala:1157) [info] at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265) [info] at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157) [info] at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252) [info] at scala.collection.AbstractIterator.toArray(Iterator.scala:1157) [info] at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) [info] at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) [info] at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) [info] at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) [info] at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63) [info] at org.apache.spark.scheduler.Task.run(Task.scala:70) [info] at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213) [info] at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) [info] at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) [info] at java.lang.Thread.run(Thread.java:745) [info] [info] Driver stacktrace: [info] at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1266) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1257) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1256) [info] at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) [info] at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) [info] at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1256) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730) [info] at scala.Option.foreach(Option.scala:236) [info] at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:730) [info] at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1450) [info] at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1411) [info] at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) {noformat} {noformat} [info] - should allow to select rows with like clause *** FAILED *** (209 milliseconds) [info] org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 13.0 failed 1 times, most recent failure: Lost task 0.0 in stage 13.0 (TID 13, localhost): java.lang.ClassCastException: java.lang.String cannot be cast to org.apache.spark.sql.types.UTF8String [info] at org.apache.spark.sql.catalyst.expressions.StringComparison$class.eval(stringOperations.scala:175) [info] at org.apache.spark.sql.catalyst.expressions.EndsWith.eval(stringOperations.scala:203) [info] at org.apache.spark.sql.catalyst.expressions.InterpretedPredicate$$anonfun$create$1.apply(predicates.scala:30) [info] at org.apache.spark.sql.catalyst.expressions.InterpretedPredicate$$anonfun$create$1.apply(predicates.scala:30) [info] at scala.collection.Iterator$$anon$14.hasNext(Iterator.scala:390) [info] at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327) [info] at scala.collection.Iterator$class.foreach(Iterator.scala:727) [info] at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) [info] at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48) [info] at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103) [info] at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47) [info] at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273) [info] at scala.collection.AbstractIterator.to(Iterator.scala:1157) [info] at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265) [info] at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157) [info] at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252) [info] at scala.collection.AbstractIterator.toArray(Iterator.scala:1157) [info] at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) [info] at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) [info] at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) {noformat}

    DataStax JIRA | 2 years ago | Piotr Kołaczkowski
    org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 13.0 failed 1 times, most recent failure: Lost task 0.0 in stage 13.0 (TID 13, localhost): java.lang.ClassCastException: java.lang.String cannot be cast to org.apache.spark.sql.types.UTF8String
  4. Speed up your debug routine!

    Automated exception search integrated into your IDE

  5. 0

    {noformat} [info] - should allow to select rows with like clause *** FAILED *** (209 milliseconds) [info] org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 13.0 failed 1 times, most recent failure: Lost task 0.0 in stage 13.0 (TID 13, localhost): java.lang.ClassCastException: java.lang.String cannot be cast to org.apache.spark.sql.types.UTF8String [info] at org.apache.spark.sql.catalyst.expressions.StringComparison$class.eval(stringOperations.scala:175) [info] at org.apache.spark.sql.catalyst.expressions.EndsWith.eval(stringOperations.scala:203) [info] at org.apache.spark.sql.catalyst.expressions.InterpretedPredicate$$anonfun$create$1.apply(predicates.scala:30) [info] at org.apache.spark.sql.catalyst.expressions.InterpretedPredicate$$anonfun$create$1.apply(predicates.scala:30) [info] at scala.collection.Iterator$$anon$14.hasNext(Iterator.scala:390) [info] at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327) [info] at scala.collection.Iterator$class.foreach(Iterator.scala:727) [info] at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) [info] at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48) [info] at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103) [info] at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47) [info] at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273) [info] at scala.collection.AbstractIterator.to(Iterator.scala:1157) [info] at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265) [info] at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157) [info] at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252) [info] at scala.collection.AbstractIterator.toArray(Iterator.scala:1157) [info] at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) [info] at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) [info] at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) [info] at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) [info] at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63) [info] at org.apache.spark.scheduler.Task.run(Task.scala:70) [info] at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213) [info] at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) [info] at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) [info] at java.lang.Thread.run(Thread.java:745) [info] [info] Driver stacktrace: [info] at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1266) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1257) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1256) [info] at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) [info] at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) [info] at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1256) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730) [info] at scala.Option.foreach(Option.scala:236) [info] at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:730) [info] at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1450) [info] at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1411) [info] at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) {noformat}

    DataStax JIRA | 2 years ago | Piotr Kołaczkowski
    org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 13.0 failed 1 times, most recent failure: Lost task 0.0 in stage 13.0 (TID 13, localhost): java.lang.ClassCastException: java.lang.String cannot be cast to org.apache.spark.sql.types.UTF8String
  6. 0

    {noformat} [info] - should allow to select rows with like clause *** FAILED *** (209 milliseconds) [info] org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 13.0 failed 1 times, most recent failure: Lost task 0.0 in stage 13.0 (TID 13, localhost): java.lang.ClassCastException: java.lang.String cannot be cast to org.apache.spark.sql.types.UTF8String [info] at org.apache.spark.sql.catalyst.expressions.StringComparison$class.eval(stringOperations.scala:175) [info] at org.apache.spark.sql.catalyst.expressions.EndsWith.eval(stringOperations.scala:203) [info] at org.apache.spark.sql.catalyst.expressions.InterpretedPredicate$$anonfun$create$1.apply(predicates.scala:30) [info] at org.apache.spark.sql.catalyst.expressions.InterpretedPredicate$$anonfun$create$1.apply(predicates.scala:30) [info] at scala.collection.Iterator$$anon$14.hasNext(Iterator.scala:390) [info] at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327) [info] at scala.collection.Iterator$class.foreach(Iterator.scala:727) [info] at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) [info] at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48) [info] at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103) [info] at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47) [info] at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273) [info] at scala.collection.AbstractIterator.to(Iterator.scala:1157) [info] at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265) [info] at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157) [info] at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252) [info] at scala.collection.AbstractIterator.toArray(Iterator.scala:1157) [info] at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) [info] at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) [info] at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) [info] at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) [info] at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63) [info] at org.apache.spark.scheduler.Task.run(Task.scala:70) [info] at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213) [info] at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) [info] at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) [info] at java.lang.Thread.run(Thread.java:745) [info] [info] Driver stacktrace: [info] at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1266) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1257) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1256) [info] at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) [info] at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) [info] at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1256) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730) [info] at scala.Option.foreach(Option.scala:236) [info] at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:730) [info] at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1450) [info] at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1411) [info] at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) {noformat}

    DataStax JIRA | 2 years ago | Piotr Kołaczkowski
    org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 13.0 failed 1 times, most recent failure: Lost task 0.0 in stage 13.0 (TID 13, localhost): java.lang.ClassCastException: java.lang.String cannot be cast to org.apache.spark.sql.types.UTF8String

    Root Cause Analysis

    1. org.apache.spark.SparkException

      Job aborted due to stage failure: Task 0 in stage 13.0 failed 1 times, most recent failure: Lost task 0.0 in stage 13.0 (TID 13, localhost): java.lang.ClassCastException: java.lang.String cannot be cast to org.apache.spark.sql.types.UTF8String

      at org.apache.spark.sql.catalyst.expressions.StringComparison$class.eval()
    2. Spark Project Catalyst
      InterpretedPredicate$$anonfun$create$1.apply
      1. org.apache.spark.sql.catalyst.expressions.StringComparison$class.eval(stringOperations.scala:175)
      2. org.apache.spark.sql.catalyst.expressions.EndsWith.eval(stringOperations.scala:203)
      3. org.apache.spark.sql.catalyst.expressions.InterpretedPredicate$$anonfun$create$1.apply(predicates.scala:30)
      4. org.apache.spark.sql.catalyst.expressions.InterpretedPredicate$$anonfun$create$1.apply(predicates.scala:30)
      4 frames
    3. Scala
      AbstractIterator.toArray
      1. scala.collection.Iterator$$anon$14.hasNext(Iterator.scala:390)
      2. scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
      3. scala.collection.Iterator$class.foreach(Iterator.scala:727)
      4. scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
      5. scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
      6. scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
      7. scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
      8. scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
      9. scala.collection.AbstractIterator.to(Iterator.scala:1157)
      10. scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
      11. scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
      12. scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
      13. scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
      13 frames
    4. Spark
      SparkContext$$anonfun$runJob$5.apply
      1. org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885)
      2. org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885)
      3. org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765)
      3 frames