Hi,
I've worked out how to use explode on my input avro dataset with the
following structure
root
|-- pageViewId: string (nullable = false)
|-- components: array (nullable = true)
| |-- element: struct (containsNull = false)
| | |-- name: string (nullable = false)
| | |-- loadTimeMs: long (nullable = true)
I'm trying to turn this into this layout with repeated pageViewIds for each
row of my components:
root
|-- pageViewId: string (nullable = false)
|-- name: string (nullable = false)
|-- loadTimeMs: long (nullable = true)
Explode words fine for the first 10 records using this bit of code, but my
big problem is that loadTimeMs has nulls in it, which I think is causing
the error. Any ideas how I can trap those nulls? Perhaps by converting to
zeros and then I can deal with them later? I tried writing a udf which
just takes the loadTimeMs column and swaps nulls for zeros, but this
separates the struct and then I don't know how to use explode.
avroFile.filter($"lazyComponents.components".isNotNull)
.explode($"lazyComponents.components")
{ case Row(lazyComponents: Seq[Row]) => lazyComponents
.map(x => x.getString(0) -> x.getLong(1))}
.select('pageViewId, '_1, '_2)
.take(10).foreach(println)
15/06/04 12:01:21 ERROR Executor: Exception in task 0.0 in stage 19.0 (TID
65)
java.lang.RuntimeException: Failed to check null bit for primitive long
value.
at scala.sys.package$.error(package.scala:27)
at
org.apache.spark.sql.catalyst.expressions.GenericRow.getLong(rows.scala:87)
at
$line127.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$anonfun$1$$anonfun$apply$1.apply(<console>:33)
at
$line127.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$anonfun$1$$anonfun$apply$1.apply(<console>:33)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.WrappedArray.foreach(WrappedArray.scala:34)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.AbstractTraversable.map(Traversable.scala:105)
at
$line127.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:33)
at
$line127.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:33)
at scala.Function1$$anonfun$andThen$1.apply(Function1.scala:55)
at
org.apache.spark.sql.catalyst.expressions.UserDefinedGenerator.eval(generators.scala:89)
at
org.apache.spark.sql.execution.Generate$$anonfun$2$$anonfun$apply$1.apply(Generate.scala:71)
at
org.apache.spark.sql.execution.Generate$$anonfun$2$$anonfun$apply$1.apply(Generate.scala:70)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
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$2.apply(SparkPlan.scala:122)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:122)
at
org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1498)
at
org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1498)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:64)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:203)
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:744)
