[SPARK-32238] Use Utils.getSimpleName to avoid hitting Malformed class name in ScalaUDF

• Type: Bug
• Status: Resolved
• Priority: Minor
• Resolution: Fixed
• Affects Version/s: 2.0.2, 2.1.3, 2.2.3, 2.3.4, 2.4.6, 3.0.0
• Fix Version/s: 2.4.7, 3.0.1, 3.1.0
• Component/s: SQL
• Assignee: wuyi
• Reporter: wuyi
• Created: 09/Jul/20 07:19
• Updated: 11/Jul/20 13:46
• Resolved: 11/Jul/20 13:46

Description

BEFORE

object MalformedClassObject extends Serializable {
    class MalformedFunction extends (String => Int) with Serializable {
      override def apply(v1: String): Int = v1.toInt / 0
    }
}
Seq("20").toDF("col").select(udf(new MalformedFunction).apply(Column("col"))).collect()

An exception or error caused a run to abort: Malformed class name 
java.lang.InternalError: Malformed class name
	at java.lang.Class.getSimpleName(Class.java:1330)
	at org.apache.spark.sql.catalyst.expressions.ScalaUDF.udfErrorMessage$lzycompute(ScalaUDF.scala:1157)
	at org.apache.spark.sql.catalyst.expressions.ScalaUDF.udfErrorMessage(ScalaUDF.scala:1155)
	at org.apache.spark.sql.catalyst.expressions.ScalaUDF.doGenCode(ScalaUDF.scala:1077)
	at org.apache.spark.sql.catalyst.expressions.Expression.$anonfun$genCode$3(Expression.scala:147)
	at scala.Option.getOrElse(Option.scala:189)
	at org.apache.spark.sql.catalyst.expressions.Expression.genCode(Expression.scala:142)
	at org.apache.spark.sql.catalyst.expressions.Alias.genCode(namedExpressions.scala:160)
	at org.apache.spark.sql.execution.ProjectExec.$anonfun$doConsume$1(basicPhysicalOperators.scala:69)
	....

AFTER

org.apache.spark.SparkException: Failed to execute user defined function(UDFSuite$MalformedClassObject$MalformedNonPrimitiveFunction: (string) => int)
	at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
	at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
	at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:753)
	at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:340)
	at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898)
	at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898)
	at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
	at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
	at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
	at org.apache.spark.scheduler.Task.run(Task.scala:127)
	at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:464)
	at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1377)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:467)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
	at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.ArithmeticException: / by zero
	at org.apache.spark.sql.UDFSuite$MalformedClassObject$MalformedNonPrimitiveFunction.apply(UDFSuite.scala:677)
	at org.apache.spark.sql.UDFSuite$MalformedClassObject$MalformedNonPrimitiveFunction.apply(UDFSuite.scala:676)
	... 17 more

Issue Links

• links to: [Github] Pull Request #29050 (Ngone51)