当将带有Java语音匹配库的rdd映射到null值时，Spark会引发java.lang.NullPointerException

Question

我有一个RDD，我是使用map从DataFrame转到的：

case class Record(id_1: Int, fnam_1: String, lnam_1: String, id_2: Long, fnam_2: String, lnam_2: String)
val rdd = df.map {
  case Row(id_1: Int, fnam_1: String, lnam_1: String, id_2: Long, fnam_2: String, lnam_2: String) =>
    Record(id_1, fnam_1, lnam_1, id_2, fnam_2, lnam_2)
}

然后，我使用Java语音匹配库对此rdd执行过滤操作（如下所示）：

import edu.ualr.oyster.utilities.DoubleMetaphone

def matchFirstName(rec: Record) = {
  val s1 = Option(rec.fnam_1).getOrElse("")
  val s2 = Option(rec.fnam_2).getOrElse("")
  if (s1.isEmpty || s2.isEmpty)
    false
  else
    new DoubleMetaphone().compareDoubleMetaphone(s1, s2)
}

val rdd_filtered = rdd.filter(matchFirstName(_))

运行此命令时，出现NPE错误：

17/04/06 19:06:31 WARN scheduler.TaskSetManager: Lost task 0.0 in stage 4.0 (TID 160, my.work.cluster.com): java.lang.NullPointerException
    at edu.ualr.oyster.utilities.DoubleMetaphone.compareDoubleMetaphone(DoubleMetaphone.java:1020)
    at funpackage.EntityResolution$.phoneticMatching(EntityResolution.scala:106)
    at esurance.EntityResolution$.esurance$EntityResolution$$matchNames$1(EntityResolution.scala:118)
    at esurance.EntityResolution$$anonfun$8.apply(EntityResolution.scala:137)
    at esurance.EntityResolution$$anonfun$8.apply(EntityResolution.scala:137)
    at scala.collection.Iterator$$anon$14.hasNext(Iterator.scala:390)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
    at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:308)
    at scala.collection.Iterator$class.foreach(Iterator.scala:727)
    at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
    at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
    at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
    at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
    at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
    at scala.collection.AbstractIterator.to(Iterator.scala:1157)
    at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
    at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
    at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
    at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
    at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
    at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
    at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
    at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
    at org.apache.spark.scheduler.Task.run(Task.scala:88)
    at org.apache.spark.executor.Executor$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)

我尝试在项目中的一对字符串上使用语音匹配，并且确实可以正常工作。 我还使用了包装在用户定义函数中的spark sql中的相同库，没有任何问题。 我怀疑问题可能是由于我的某些值可能会丢失（空）。 但是我尝试使用其中的Option来解决这个问题。 知道为什么这失败了吗？

Answer 1

我没有尝试深入edu.ualr.oyster库以查看是否引起异常。 但这似乎是事实。 我切换为使用org.apache.commons.codec.language库（相同的双元音功能），并且该程序可以正常工作在火花上。