[PIG-4192] Make ruby udfs work with Spark

• Type: Sub-task
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Fix Version/s: spark-branch
• Component/s: spark
• Assignee: liyunzhang
• Reporter: Praveen Rachabattuni
• Created: 22/Sep/14 10:43
• Updated: 21/Jun/17 09:18
• Resolved: 02/Dec/14 10:53

Description

Related e2e tests: RubyUDFs_1 - RubyUDFs_13

Sample script:
register './libexec/ruby/scriptingudfs.rb' using jruby as myfuncs;
a = load '/user/pig/tests/data/singlefile/studenttab10k' using PigStorage() as (name, age:int, gpa:double);
b = foreach a generate myfuncs.square(age);
store b into '/user/pig/out/praveenr-1411382446-nightly.conf/RubyUDFs_1.out';

Pig Stack Trace
---------------
ERROR 0: org.apache.spark.SparkException: Job aborted: Task 0.0:0 failed 1 times (most recent failure: Exception failure: java.lang.RuntimeException: org.apache.pig.backend.executionengine.ExecException: ERROR 0: Exception while executing [POUserFunc (Name: POUserFunc(org.apache.pig.scripting.jruby.JrubyEvalFunc)[int] - scope-3 Operator Key: scope-3) children: null at []]: java.lang.NullPointerException)

org.apache.pig.backend.executionengine.ExecException: ERROR 0: org.apache.spark.SparkException: Job aborted: Task 0.0:0 failed 1 times (most recent failure: Exception failure: java.lang.RuntimeException: org.apache.pig.backend.executionengine.ExecException: ERROR 0: Exception while executing [POUserFunc (Name: POUserFunc(org.apache.pig.scripting.jruby.JrubyEvalFunc)[int] - scope-3 Operator Key: scope-3) children: null at []]: java.lang.NullPointerException)
at org.apache.pig.backend.hadoop.executionengine.HExecutionEngine.launchPig(HExecutionEngine.java:285)
at org.apache.pig.PigServer.launchPlan(PigServer.java:1378)
at org.apache.pig.PigServer.executeCompiledLogicalPlan(PigServer.java:1363)
at org.apache.pig.PigServer.execute(PigServer.java:1352)
at org.apache.pig.PigServer.executeBatch(PigServer.java:403)
at org.apache.pig.PigServer.executeBatch(PigServer.java:386)
at org.apache.pig.tools.grunt.GruntParser.executeBatch(GruntParser.java:170)
at org.apache.pig.tools.grunt.GruntParser.parseStopOnError(GruntParser.java:233)
at org.apache.pig.tools.grunt.GruntParser.parseStopOnError(GruntParser.java:204)
at org.apache.pig.tools.grunt.Grunt.exec(Grunt.java:81)
at org.apache.pig.Main.run(Main.java:611)
at org.apache.pig.Main.main(Main.java:164)
Caused by: org.apache.spark.SparkException: Job aborted: Task 0.0:0 failed 1 times (most recent failure: Exception failure: java.lang.RuntimeException: org.apache.pig.backend.executionengine.ExecException: ERROR 0: Exception while executing [POUserFunc (Name: POUserFunc(org.apache.pig.scripting.jruby.JrubyEvalFunc)[int] - scope-3 Operator Key: scope-3) children: null at []]: java.lang.NullPointerException)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$abortStage$1.apply(DAGScheduler.scala:1028)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$org$apache$spark$scheduler$DAGScheduler$$abortStage$1.apply(DAGScheduler.scala:1026)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$abortStage(DAGScheduler.scala:1026)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$processEvent$10.apply(DAGScheduler.scala:619)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$processEvent$10.apply(DAGScheduler.scala:619)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.processEvent(DAGScheduler.scala:619)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$start$1$$anon$2$$anonfun$receive$1.applyOrElse(DAGScheduler.scala:207)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
at akka.actor.ActorCell.invoke(ActorCell.scala:456)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
at akka.dispatch.Mailbox.run(Mailbox.scala:219)
at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386)
at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
================================================================================