Github user rjurney commented on the pull request:
https://github.com/apache/spark/pull/455#issuecomment-50084602
When I load my records, I get:
Py4JJavaError: An error occurred while calling
z:org.apache.spark.api.python.PythonRDD.newAPIHadoopFile.
: org.apache.spark.SparkDriverExecutionException: Execution error
at
org.apache.spark.scheduler.DAGScheduler.runLocallyWithinThread(DAGScheduler.scala:585)
at
org.apache.spark.scheduler.DAGScheduler$$anon$1.run(DAGScheduler.scala:563)
Caused by: scala.MatchError: UNION (of class org.apache.avro.Schema$Type)
at
org.apache.spark.examples.pythonconverters.AvroGenericConverter.org$apache$spark$examples$pythonconverters$AvroGenericConverter$$unpack$1(AvroGenericConverter.scala:24)
at
org.apache.spark.examples.pythonconverters.AvroGenericConverter$$anonfun$unpackRecord$1$1.apply(AvroGenericConverter.scala:17)
at
org.apache.spark.examples.pythonconverters.AvroGenericConverter$$anonfun$unpackRecord$1$1.apply(AvroGenericConverter.scala:17)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.AbstractTraversable.map(Traversable.scala:105)
at
org.apache.spark.examples.pythonconverters.AvroGenericConverter.unpackRecord$1(AvroGenericConverter.scala:17)
at
org.apache.spark.examples.pythonconverters.AvroGenericConverter.convert(AvroGenericConverter.scala:36)
at
org.apache.spark.examples.pythonconverters.AvroGenericConverter.convert(AvroGenericConverter.scala:12)
at
org.apache.spark.api.python.PythonHadoopUtil$$anonfun$convertRDD$1.apply(PythonHadoopUtil.scala:126)
at
org.apache.spark.api.python.PythonHadoopUtil$$anonfun$convertRDD$1.apply(PythonHadoopUtil.scala:126)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$10.next(Iterator.scala:312)
at scala.collection.Iterator$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.rdd.RDD$$anonfun$28.apply(RDD.scala:1068)
at org.apache.spark.rdd.RDD$$anonfun$28.apply(RDD.scala:1068)
at
org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1096)
at
org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1096)
at
org.apache.spark.scheduler.DAGScheduler.runLocallyWithinThread(DAGScheduler.scala:578)
... 1 more
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
