From 83c226d454722d5dea186d48070fb98652d0dafb Mon Sep 17 00:00:00 2001 From: Doris Xin Date: Thu, 12 Jun 2014 12:53:07 -0700 Subject: [SPARK-2088] fix NPE in toString After deserialization, the transient field creationSiteInfo does not get backfilled with the default value, but the toString method, which is invoked by the serializer, expects the field to always be non-null. An NPE is thrown when toString is called by the serializer when creationSiteInfo is null. Author: Doris Xin Closes #1028 from dorx/toStringNPE and squashes the following commits: f20021e [Doris Xin] unit test for toString after desrialization 6f0a586 [Doris Xin] Merge branch 'master' into toStringNPE f47fecf [Doris Xin] Merge branch 'master' into toStringNPE 76199c6 [Doris Xin] [SPARK-2088] fix NPE in toString --- core/src/main/scala/org/apache/spark/rdd/RDD.scala | 2 +- core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala | 9 ++++++++- 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/rdd/RDD.scala b/core/src/main/scala/org/apache/spark/rdd/RDD.scala index 54bdc3e7cb..b6fc4b13ad 100644 --- a/core/src/main/scala/org/apache/spark/rdd/RDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/RDD.scala @@ -1180,7 +1180,7 @@ abstract class RDD[T: ClassTag]( /** User code that created this RDD (e.g. `textFile`, `parallelize`). */ @transient private[spark] val creationSiteInfo = Utils.getCallSiteInfo - private[spark] def getCreationSite: String = creationSiteInfo.toString + private[spark] def getCreationSite: String = Option(creationSiteInfo).getOrElse("").toString private[spark] def elementClassTag: ClassTag[T] = classTag[T] diff --git a/core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala b/core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala index 55af1666df..2e2ccc5a18 100644 --- a/core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala +++ b/core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala @@ -24,7 +24,7 @@ import org.scalatest.FunSuite import org.apache.spark._ import org.apache.spark.SparkContext._ -import org.apache.spark.rdd._ +import org.apache.spark.util.Utils class RDDSuite extends FunSuite with SharedSparkContext { @@ -66,6 +66,13 @@ class RDDSuite extends FunSuite with SharedSparkContext { } } + test("serialization") { + val empty = new EmptyRDD[Int](sc) + val serial = Utils.serialize(empty) + val deserial: EmptyRDD[Int] = Utils.deserialize(serial) + assert(!deserial.toString().isEmpty()) + } + test("countApproxDistinct") { def error(est: Long, size: Long) = math.abs(est - size) / size.toDouble -- cgit v1.2.3