Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/1009#discussion_r13690317
--- Diff: core/src/main/scala/org/apache/spark/rdd/ShuffledRDD.scala ---
@@ -42,10 +42,11 @@ class ShuffledRDD[K, V, P <: Product2[K, V] : ClassTag](
part: Partitioner)
extends RDD[P](prev.context, Nil) {
- private var serializer: Serializer = null
+ private var serializer: Option[Serializer] = None
+ /** Set a serializer for this RDD's shuffle, or null to use the default
(spark.serializer) */
def setSerializer(serializer: Serializer): ShuffledRDD[K, V, P] = {
- this.serializer = serializer
+ this.serializer = Option(serializer)
--- End diff --
```
scala> var serializer: Option[java.lang.Integer] = null
serializer: Option[Integer] = null
scala> serializer = Some(1)
serializer: Option[Integer] = Some(1)
scala> serializer.get
res0: Integer = 1
scala> serializer = Some(null)
serializer: Option[Integer] = Some(null)
scala> serializer.get
res1: Integer = null
scala> serializer.isDefined
res2: Boolean = true
scala> serializer = Option(null)
serializer: Option[Integer] = None
scala> serializer.isDefined
res3: Boolean = false
```
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
