diff options
53 files changed, 132 insertions, 114 deletions
diff --git a/core/src/main/java/org/apache/spark/network/netty/FileClient.java b/core/src/main/java/org/apache/spark/network/netty/FileClient.java index 20a7a3aa8c..edd0fc56f8 100644 --- a/core/src/main/java/org/apache/spark/network/netty/FileClient.java +++ b/core/src/main/java/org/apache/spark/network/netty/FileClient.java @@ -19,8 +19,6 @@ package org.apache.spark.network.netty; import io.netty.bootstrap.Bootstrap; import io.netty.channel.Channel; -import io.netty.channel.ChannelFuture; -import io.netty.channel.ChannelFutureListener; import io.netty.channel.ChannelOption; import io.netty.channel.oio.OioEventLoopGroup; import io.netty.channel.socket.oio.OioSocketChannel; diff --git a/core/src/main/java/org/apache/spark/network/netty/FileServer.java b/core/src/main/java/org/apache/spark/network/netty/FileServer.java index 666432474d..a99af348ce 100644 --- a/core/src/main/java/org/apache/spark/network/netty/FileServer.java +++ b/core/src/main/java/org/apache/spark/network/netty/FileServer.java @@ -20,7 +20,6 @@ package org.apache.spark.network.netty; import java.net.InetSocketAddress; import io.netty.bootstrap.ServerBootstrap; -import io.netty.channel.Channel; import io.netty.channel.ChannelFuture; import io.netty.channel.ChannelOption; import io.netty.channel.oio.OioEventLoopGroup; diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaSparkContextVarargsWorkaround.java b/core/src/main/scala/org/apache/spark/api/java/JavaSparkContextVarargsWorkaround.java index c9cbce5624..2090efd3b9 100644 --- a/core/src/main/scala/org/apache/spark/api/java/JavaSparkContextVarargsWorkaround.java +++ b/core/src/main/scala/org/apache/spark/api/java/JavaSparkContextVarargsWorkaround.java @@ -17,7 +17,6 @@ package org.apache.spark.api.java; -import java.util.Arrays; import java.util.ArrayList; import java.util.List; diff --git a/core/src/main/scala/org/apache/spark/api/java/function/DoubleFunction.java b/core/src/main/scala/org/apache/spark/api/java/function/DoubleFunction.java index db34cd190a..ed92d31af5 100644 --- a/core/src/main/scala/org/apache/spark/api/java/function/DoubleFunction.java +++ b/core/src/main/scala/org/apache/spark/api/java/function/DoubleFunction.java @@ -18,8 +18,6 @@ package org.apache.spark.api.java.function; -import scala.runtime.AbstractFunction1; - import java.io.Serializable; /** diff --git a/core/src/main/scala/org/apache/spark/api/java/function/Function.java b/core/src/main/scala/org/apache/spark/api/java/function/Function.java index f9dae6ed34..e97116986f 100644 --- a/core/src/main/scala/org/apache/spark/api/java/function/Function.java +++ b/core/src/main/scala/org/apache/spark/api/java/function/Function.java @@ -19,7 +19,6 @@ package org.apache.spark.api.java.function; import scala.reflect.ClassTag; import scala.reflect.ClassTag$; -import scala.runtime.AbstractFunction1; import java.io.Serializable; diff --git a/core/src/main/scala/org/apache/spark/api/java/function/Function2.java b/core/src/main/scala/org/apache/spark/api/java/function/Function2.java index 1659bfc552..cf77bb6b73 100644 --- a/core/src/main/scala/org/apache/spark/api/java/function/Function2.java +++ b/core/src/main/scala/org/apache/spark/api/java/function/Function2.java @@ -19,7 +19,6 @@ package org.apache.spark.api.java.function; import scala.reflect.ClassTag; import scala.reflect.ClassTag$; -import scala.runtime.AbstractFunction2; import java.io.Serializable; diff --git a/core/src/main/scala/org/apache/spark/api/java/function/PairFlatMapFunction.java b/core/src/main/scala/org/apache/spark/api/java/function/PairFlatMapFunction.java index 5a5c9b6296..fbd0cdabe0 100644 --- a/core/src/main/scala/org/apache/spark/api/java/function/PairFlatMapFunction.java +++ b/core/src/main/scala/org/apache/spark/api/java/function/PairFlatMapFunction.java @@ -20,7 +20,6 @@ package org.apache.spark.api.java.function; import scala.Tuple2; import scala.reflect.ClassTag; import scala.reflect.ClassTag$; -import scala.runtime.AbstractFunction1; import java.io.Serializable; diff --git a/core/src/main/scala/org/apache/spark/api/java/function/PairFunction.java b/core/src/main/scala/org/apache/spark/api/java/function/PairFunction.java index 4c39f483e5..f09559627d 100644 --- a/core/src/main/scala/org/apache/spark/api/java/function/PairFunction.java +++ b/core/src/main/scala/org/apache/spark/api/java/function/PairFunction.java @@ -20,7 +20,6 @@ package org.apache.spark.api.java.function; import scala.Tuple2; import scala.reflect.ClassTag; import scala.reflect.ClassTag$; -import scala.runtime.AbstractFunction1; import java.io.Serializable; diff --git a/core/src/main/scala/org/apache/spark/api/python/PythonWorkerFactory.scala b/core/src/main/scala/org/apache/spark/api/python/PythonWorkerFactory.scala index 67d45723ba..f291266fcf 100644 --- a/core/src/main/scala/org/apache/spark/api/python/PythonWorkerFactory.scala +++ b/core/src/main/scala/org/apache/spark/api/python/PythonWorkerFactory.scala @@ -64,7 +64,7 @@ private[spark] class PythonWorkerFactory(pythonExec: String, envVars: Map[String startDaemon() new Socket(daemonHost, daemonPort) } - case e => throw e + case e: Throwable => throw e } } } @@ -198,7 +198,7 @@ private[spark] class PythonWorkerFactory(pythonExec: String, envVars: Map[String } }.start() } catch { - case e => { + case e: Throwable => { stopDaemon() throw e } diff --git a/core/src/main/scala/org/apache/spark/deploy/ExecutorState.scala b/core/src/main/scala/org/apache/spark/deploy/ExecutorState.scala index fcfea96ad6..72f84c99fc 100644 --- a/core/src/main/scala/org/apache/spark/deploy/ExecutorState.scala +++ b/core/src/main/scala/org/apache/spark/deploy/ExecutorState.scala @@ -18,7 +18,7 @@ package org.apache.spark.deploy private[spark] object ExecutorState - extends Enumeration("LAUNCHING", "LOADING", "RUNNING", "KILLED", "FAILED", "LOST") { + extends Enumeration { val LAUNCHING, LOADING, RUNNING, KILLED, FAILED, LOST = Value diff --git a/core/src/main/scala/org/apache/spark/deploy/master/ApplicationState.scala b/core/src/main/scala/org/apache/spark/deploy/master/ApplicationState.scala index 7e804223cf..39ef090ddf 100644 --- a/core/src/main/scala/org/apache/spark/deploy/master/ApplicationState.scala +++ b/core/src/main/scala/org/apache/spark/deploy/master/ApplicationState.scala @@ -18,7 +18,7 @@ package org.apache.spark.deploy.master private[spark] object ApplicationState - extends Enumeration("WAITING", "RUNNING", "FINISHED", "FAILED") { + extends Enumeration { type ApplicationState = Value diff --git a/core/src/main/scala/org/apache/spark/deploy/master/WorkerState.scala b/core/src/main/scala/org/apache/spark/deploy/master/WorkerState.scala index b5ee6dca79..fb3fe88d92 100644 --- a/core/src/main/scala/org/apache/spark/deploy/master/WorkerState.scala +++ b/core/src/main/scala/org/apache/spark/deploy/master/WorkerState.scala @@ -17,7 +17,7 @@ package org.apache.spark.deploy.master -private[spark] object WorkerState extends Enumeration("ALIVE", "DEAD", "DECOMMISSIONED") { +private[spark] object WorkerState extends Enumeration { type WorkerState = Value val ALIVE, DEAD, DECOMMISSIONED = Value diff --git a/core/src/main/scala/org/apache/spark/rdd/BlockRDD.scala b/core/src/main/scala/org/apache/spark/rdd/BlockRDD.scala index bca6956a18..fe2946bcbe 100644 --- a/core/src/main/scala/org/apache/spark/rdd/BlockRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/BlockRDD.scala @@ -19,13 +19,14 @@ package org.apache.spark.rdd import org.apache.spark.{SparkContext, SparkEnv, Partition, TaskContext} import org.apache.spark.storage.BlockManager +import scala.reflect.ClassTag private[spark] class BlockRDDPartition(val blockId: String, idx: Int) extends Partition { val index = idx } private[spark] -class BlockRDD[T: ClassManifest](sc: SparkContext, @transient blockIds: Array[String]) +class BlockRDD[T: ClassTag](sc: SparkContext, @transient blockIds: Array[String]) extends RDD[T](sc, Nil) { @transient lazy val locations_ = BlockManager.blockIdsToHosts(blockIds, SparkEnv.get) diff --git a/core/src/main/scala/org/apache/spark/rdd/CoalescedRDD.scala b/core/src/main/scala/org/apache/spark/rdd/CoalescedRDD.scala index c5de6362a9..98da35763b 100644 --- a/core/src/main/scala/org/apache/spark/rdd/CoalescedRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/CoalescedRDD.scala @@ -22,6 +22,7 @@ import java.io.{ObjectOutputStream, IOException} import scala.collection.mutable import scala.Some import scala.collection.mutable.ArrayBuffer +import scala.reflect.ClassTag /** * Class that captures a coalesced RDD by essentially keeping track of parent partitions @@ -68,7 +69,7 @@ case class CoalescedRDDPartition( * @param maxPartitions number of desired partitions in the coalesced RDD * @param balanceSlack used to trade-off balance and locality. 1.0 is all locality, 0 is all balance */ -class CoalescedRDD[T: ClassManifest]( +class CoalescedRDD[T: ClassTag]( @transient var prev: RDD[T], maxPartitions: Int, balanceSlack: Double = 0.10) diff --git a/core/src/main/scala/org/apache/spark/rdd/EmptyRDD.scala b/core/src/main/scala/org/apache/spark/rdd/EmptyRDD.scala index c8900d1a93..99c34c6cc5 100644 --- a/core/src/main/scala/org/apache/spark/rdd/EmptyRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/EmptyRDD.scala @@ -18,12 +18,13 @@ package org.apache.spark.rdd import org.apache.spark.{SparkContext, SparkEnv, Partition, TaskContext} +import scala.reflect.ClassTag /** * An RDD that is empty, i.e. has no element in it. */ -class EmptyRDD[T: ClassManifest](sc: SparkContext) extends RDD[T](sc, Nil) { +class EmptyRDD[T: ClassTag](sc: SparkContext) extends RDD[T](sc, Nil) { override def getPartitions: Array[Partition] = Array.empty diff --git a/core/src/main/scala/org/apache/spark/rdd/FilteredRDD.scala b/core/src/main/scala/org/apache/spark/rdd/FilteredRDD.scala index 5312dc0b59..e74c83b90b 100644 --- a/core/src/main/scala/org/apache/spark/rdd/FilteredRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/FilteredRDD.scala @@ -18,8 +18,9 @@ package org.apache.spark.rdd import org.apache.spark.{OneToOneDependency, Partition, TaskContext} +import scala.reflect.ClassTag -private[spark] class FilteredRDD[T: ClassManifest]( +private[spark] class FilteredRDD[T: ClassTag]( prev: RDD[T], f: T => Boolean) extends RDD[T](prev) { diff --git a/core/src/main/scala/org/apache/spark/rdd/FlatMappedRDD.scala b/core/src/main/scala/org/apache/spark/rdd/FlatMappedRDD.scala index cbdf6d84c0..4d1878fc14 100644 --- a/core/src/main/scala/org/apache/spark/rdd/FlatMappedRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/FlatMappedRDD.scala @@ -18,10 +18,11 @@ package org.apache.spark.rdd import org.apache.spark.{Partition, TaskContext} +import scala.reflect.ClassTag private[spark] -class FlatMappedRDD[U: ClassManifest, T: ClassManifest]( +class FlatMappedRDD[U: ClassTag, T: ClassTag]( prev: RDD[T], f: T => TraversableOnce[U]) extends RDD[U](prev) { diff --git a/core/src/main/scala/org/apache/spark/rdd/GlommedRDD.scala b/core/src/main/scala/org/apache/spark/rdd/GlommedRDD.scala index 829545d7b0..1a694475f6 100644 --- a/core/src/main/scala/org/apache/spark/rdd/GlommedRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/GlommedRDD.scala @@ -18,8 +18,9 @@ package org.apache.spark.rdd import org.apache.spark.{Partition, TaskContext} +import scala.reflect.ClassTag -private[spark] class GlommedRDD[T: ClassManifest](prev: RDD[T]) +private[spark] class GlommedRDD[T: ClassTag](prev: RDD[T]) extends RDD[Array[T]](prev) { override def getPartitions: Array[Partition] = firstParent[T].partitions diff --git a/core/src/main/scala/org/apache/spark/rdd/MapPartitionsRDD.scala b/core/src/main/scala/org/apache/spark/rdd/MapPartitionsRDD.scala index 203179c4ea..cdb5946b49 100644 --- a/core/src/main/scala/org/apache/spark/rdd/MapPartitionsRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/MapPartitionsRDD.scala @@ -18,10 +18,11 @@ package org.apache.spark.rdd import org.apache.spark.{Partition, TaskContext} +import scala.reflect.ClassTag private[spark] -class MapPartitionsRDD[U: ClassManifest, T: ClassManifest]( +class MapPartitionsRDD[U: ClassTag, T: ClassTag]( prev: RDD[T], f: Iterator[T] => Iterator[U], preservesPartitioning: Boolean = false) diff --git a/core/src/main/scala/org/apache/spark/rdd/MapPartitionsWithIndexRDD.scala b/core/src/main/scala/org/apache/spark/rdd/MapPartitionsWithIndexRDD.scala index 3ed8339010..3cf22851dd 100644 --- a/core/src/main/scala/org/apache/spark/rdd/MapPartitionsWithIndexRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/MapPartitionsWithIndexRDD.scala @@ -18,6 +18,7 @@ package org.apache.spark.rdd import org.apache.spark.{Partition, TaskContext} +import scala.reflect.ClassTag /** @@ -26,7 +27,7 @@ import org.apache.spark.{Partition, TaskContext} * information such as the number of tuples in a partition. */ private[spark] -class MapPartitionsWithIndexRDD[U: ClassManifest, T: ClassManifest]( +class MapPartitionsWithIndexRDD[U: ClassTag, T: ClassTag]( prev: RDD[T], f: (Int, Iterator[T]) => Iterator[U], preservesPartitioning: Boolean diff --git a/core/src/main/scala/org/apache/spark/rdd/MappedRDD.scala b/core/src/main/scala/org/apache/spark/rdd/MappedRDD.scala index e8be1c4816..eb3b19907d 100644 --- a/core/src/main/scala/org/apache/spark/rdd/MappedRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/MappedRDD.scala @@ -18,9 +18,10 @@ package org.apache.spark.rdd import org.apache.spark.{Partition, TaskContext} +import scala.reflect.ClassTag private[spark] -class MappedRDD[U: ClassManifest, T: ClassManifest](prev: RDD[T], f: T => U) +class MappedRDD[U: ClassTag, T: ClassTag](prev: RDD[T], f: T => U) extends RDD[U](prev) { override def getPartitions: Array[Partition] = firstParent[T].partitions diff --git a/core/src/main/scala/org/apache/spark/rdd/OrderedRDDFunctions.scala b/core/src/main/scala/org/apache/spark/rdd/OrderedRDDFunctions.scala index 697be8b997..4a465840c6 100644 --- a/core/src/main/scala/org/apache/spark/rdd/OrderedRDDFunctions.scala +++ b/core/src/main/scala/org/apache/spark/rdd/OrderedRDDFunctions.scala @@ -18,6 +18,7 @@ package org.apache.spark.rdd import org.apache.spark.{RangePartitioner, Logging} +import scala.reflect.ClassTag /** * Extra functions available on RDDs of (key, value) pairs where the key is sortable through @@ -25,9 +26,9 @@ import org.apache.spark.{RangePartitioner, Logging} * use these functions. They will work with any key type that has a `scala.math.Ordered` * implementation. */ -class OrderedRDDFunctions[K <% Ordered[K]: ClassManifest, - V: ClassManifest, - P <: Product2[K, V] : ClassManifest]( +class OrderedRDDFunctions[K <% Ordered[K]: ClassTag, + V: ClassTag, + P <: Product2[K, V] : ClassTag]( self: RDD[P]) extends Logging with Serializable { diff --git a/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala b/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala index aed585e6a1..c8e623081a 100644 --- a/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala +++ b/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala @@ -51,7 +51,7 @@ import org.apache.spark.Partitioner.defaultPartitioner * Extra functions available on RDDs of (key, value) pairs through an implicit conversion. * Import `org.apache.spark.SparkContext._` at the top of your program to use these functions. */ -class PairRDDFunctions[K: ClassManifest, V: ClassManifest](self: RDD[(K, V)]) +class PairRDDFunctions[K: ClassTag, V: ClassTag](self: RDD[(K, V)]) extends Logging with SparkHadoopMapReduceUtil with Serializable { diff --git a/core/src/main/scala/org/apache/spark/rdd/ShuffledRDD.scala b/core/src/main/scala/org/apache/spark/rdd/ShuffledRDD.scala index 9537152335..b7205865cf 100644 --- a/core/src/main/scala/org/apache/spark/rdd/ShuffledRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/ShuffledRDD.scala @@ -18,6 +18,7 @@ package org.apache.spark.rdd import org.apache.spark.{Dependency, Partitioner, SparkEnv, ShuffleDependency, Partition, TaskContext} +import scala.reflect.ClassTag private[spark] class ShuffledRDDPartition(val idx: Int) extends Partition { @@ -32,7 +33,7 @@ private[spark] class ShuffledRDDPartition(val idx: Int) extends Partition { * @tparam K the key class. * @tparam V the value class. */ -class ShuffledRDD[K, V, P <: Product2[K, V] : ClassManifest]( +class ShuffledRDD[K, V, P <: Product2[K, V] : ClassTag]( @transient var prev: RDD[P], part: Partitioner) extends RDD[P](prev.context, Nil) { diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/ClusterTaskSetManager.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/ClusterTaskSetManager.scala index 0ac3d7bcfd..f61fde6957 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/ClusterTaskSetManager.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/ClusterTaskSetManager.scala @@ -461,7 +461,7 @@ private[spark] class ClusterTaskSetManager( case cnf: ClassNotFoundException => val loader = Thread.currentThread().getContextClassLoader throw new SparkException("ClassNotFound with classloader: " + loader, cnf) - case ex => throw ex + case ex: Throwable => throw ex } // Mark finished and stop if we've finished all the tasks finished(index) = true diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/SchedulingMode.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/SchedulingMode.scala index 34811389a0..16013b3208 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/SchedulingMode.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/SchedulingMode.scala @@ -22,7 +22,7 @@ package org.apache.spark.scheduler.cluster * to order tasks amongst a Schedulable's sub-queues * "NONE" is used when the a Schedulable has no sub-queues. */ -object SchedulingMode extends Enumeration("FAIR", "FIFO", "NONE") { +object SchedulingMode extends Enumeration { type SchedulingMode = Value val FAIR,FIFO,NONE = Value diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/TaskLocality.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/TaskLocality.scala index 5d4130e14a..8d8d708612 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/TaskLocality.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/TaskLocality.scala @@ -19,7 +19,7 @@ package org.apache.spark.scheduler.cluster private[spark] object TaskLocality - extends Enumeration("PROCESS_LOCAL", "NODE_LOCAL", "RACK_LOCAL", "ANY") + extends Enumeration { // process local is expected to be used ONLY within tasksetmanager for now. val PROCESS_LOCAL, NODE_LOCAL, RACK_LOCAL, ANY = Value diff --git a/core/src/test/scala/org/apache/spark/DistributedSuite.scala b/core/src/test/scala/org/apache/spark/DistributedSuite.scala index c719a54a61..adc6ca94ff 100644 --- a/core/src/test/scala/org/apache/spark/DistributedSuite.scala +++ b/core/src/test/scala/org/apache/spark/DistributedSuite.scala @@ -313,7 +313,7 @@ class DistributedSuite extends FunSuite with ShouldMatchers with BeforeAndAfter Thread.sleep(200) } } catch { - case _ => { Thread.sleep(10) } + case _: Throwable => { Thread.sleep(10) } // Do nothing. We might see exceptions because block manager // is racing this thread to remove entries from the driver. } diff --git a/core/src/test/scala/org/apache/spark/UnpersistSuite.scala b/core/src/test/scala/org/apache/spark/UnpersistSuite.scala index 46a2da1724..768ca3850e 100644 --- a/core/src/test/scala/org/apache/spark/UnpersistSuite.scala +++ b/core/src/test/scala/org/apache/spark/UnpersistSuite.scala @@ -37,7 +37,7 @@ class UnpersistSuite extends FunSuite with LocalSparkContext { Thread.sleep(200) } } catch { - case _ => { Thread.sleep(10) } + case _: Throwable => { Thread.sleep(10) } // Do nothing. We might see exceptions because block manager // is racing this thread to remove entries from the driver. } 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 c1df5e151e..096023f476 100644 --- a/core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala +++ b/core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala @@ -225,8 +225,8 @@ class RDDSuite extends FunSuite with SharedSparkContext { // test that you get over 90% locality in each group val minLocality = coalesced2.partitions .map(part => part.asInstanceOf[CoalescedRDDPartition].localFraction) - .foldLeft(1.)((perc, loc) => math.min(perc,loc)) - assert(minLocality >= 0.90, "Expected 90% locality but got " + (minLocality*100.).toInt + "%") + .foldLeft(1.0)((perc, loc) => math.min(perc,loc)) + assert(minLocality >= 0.90, "Expected 90% locality but got " + (minLocality*100.0).toInt + "%") // test that the groups are load balanced with 100 +/- 20 elements in each val maxImbalance = coalesced2.partitions @@ -238,9 +238,9 @@ class RDDSuite extends FunSuite with SharedSparkContext { val coalesced3 = data3.coalesce(numMachines*2) val minLocality2 = coalesced3.partitions .map(part => part.asInstanceOf[CoalescedRDDPartition].localFraction) - .foldLeft(1.)((perc, loc) => math.min(perc,loc)) + .foldLeft(1.0)((perc, loc) => math.min(perc,loc)) assert(minLocality2 >= 0.90, "Expected 90% locality for derived RDD but got " + - (minLocality2*100.).toInt + "%") + (minLocality2*100.0).toInt + "%") } test("zipped RDDs") { diff --git a/examples/src/main/java/org/apache/spark/examples/JavaLogQuery.java b/examples/src/main/java/org/apache/spark/examples/JavaLogQuery.java index 152f029213..407cd7ccfa 100644 --- a/examples/src/main/java/org/apache/spark/examples/JavaLogQuery.java +++ b/examples/src/main/java/org/apache/spark/examples/JavaLogQuery.java @@ -123,7 +123,7 @@ public class JavaLogQuery { }); List<Tuple2<Tuple3<String, String, String>, Stats>> output = counts.collect(); - for (Tuple2 t : output) { + for (Tuple2<?,?> t : output) { System.out.println(t._1 + "\t" + t._2); } System.exit(0); diff --git a/examples/src/main/java/org/apache/spark/examples/JavaPageRank.java b/examples/src/main/java/org/apache/spark/examples/JavaPageRank.java index c5603a639b..89aed8f279 100644 --- a/examples/src/main/java/org/apache/spark/examples/JavaPageRank.java +++ b/examples/src/main/java/org/apache/spark/examples/JavaPageRank.java @@ -21,7 +21,6 @@ import scala.Tuple2; import org.apache.spark.api.java.JavaPairRDD; import org.apache.spark.api.java.JavaRDD; import org.apache.spark.api.java.JavaSparkContext; -import org.apache.spark.api.java.function.FlatMapFunction; import org.apache.spark.api.java.function.Function; import org.apache.spark.api.java.function.Function2; import org.apache.spark.api.java.function.PairFlatMapFunction; @@ -106,7 +105,7 @@ public class JavaPageRank { // Collects all URL ranks and dump them to console. List<Tuple2<String, Double>> output = ranks.collect(); - for (Tuple2 tuple : output) { + for (Tuple2<?,?> tuple : output) { System.out.println(tuple._1 + " has rank: " + tuple._2 + "."); } diff --git a/examples/src/main/java/org/apache/spark/examples/JavaWordCount.java b/examples/src/main/java/org/apache/spark/examples/JavaWordCount.java index 07d32ad659..bd6383e13d 100644 --- a/examples/src/main/java/org/apache/spark/examples/JavaWordCount.java +++ b/examples/src/main/java/org/apache/spark/examples/JavaWordCount.java @@ -58,7 +58,7 @@ public class JavaWordCount { }); List<Tuple2<String, Integer>> output = counts.collect(); - for (Tuple2 tuple : output) { + for (Tuple2<?,?> tuple : output) { System.out.println(tuple._1 + ": " + tuple._2); } System.exit(0); diff --git a/examples/src/main/java/org/apache/spark/mllib/examples/JavaALS.java b/examples/src/main/java/org/apache/spark/mllib/examples/JavaALS.java index 628cb892b6..45a0d237da 100644 --- a/examples/src/main/java/org/apache/spark/mllib/examples/JavaALS.java +++ b/examples/src/main/java/org/apache/spark/mllib/examples/JavaALS.java @@ -25,7 +25,6 @@ import org.apache.spark.mllib.recommendation.ALS; import org.apache.spark.mllib.recommendation.MatrixFactorizationModel; import org.apache.spark.mllib.recommendation.Rating; -import java.io.Serializable; import java.util.Arrays; import java.util.StringTokenizer; diff --git a/mllib/src/test/java/org/apache/spark/mllib/clustering/JavaKMeansSuite.java b/mllib/src/test/java/org/apache/spark/mllib/clustering/JavaKMeansSuite.java index 32d3934ac1..33b99f4bd3 100644 --- a/mllib/src/test/java/org/apache/spark/mllib/clustering/JavaKMeansSuite.java +++ b/mllib/src/test/java/org/apache/spark/mllib/clustering/JavaKMeansSuite.java @@ -77,7 +77,7 @@ public class JavaKMeansSuite implements Serializable { @Test public void runKMeansUsingStaticMethods() { - List<double[]> points = new ArrayList(); + List<double[]> points = new ArrayList<double[]>(); points.add(new double[]{1.0, 2.0, 6.0}); points.add(new double[]{1.0, 3.0, 0.0}); points.add(new double[]{1.0, 4.0, 6.0}); @@ -94,7 +94,7 @@ public class JavaKMeansSuite implements Serializable { @Test public void runKMeansUsingConstructor() { - List<double[]> points = new ArrayList(); + List<double[]> points = new ArrayList<double[]>(); points.add(new double[]{1.0, 2.0, 6.0}); points.add(new double[]{1.0, 3.0, 0.0}); points.add(new double[]{1.0, 4.0, 6.0}); diff --git a/mllib/src/test/java/org/apache/spark/mllib/recommendation/JavaALSSuite.java b/mllib/src/test/java/org/apache/spark/mllib/recommendation/JavaALSSuite.java index 3323f6cee2..c474e01188 100644 --- a/mllib/src/test/java/org/apache/spark/mllib/recommendation/JavaALSSuite.java +++ b/mllib/src/test/java/org/apache/spark/mllib/recommendation/JavaALSSuite.java @@ -20,8 +20,6 @@ package org.apache.spark.mllib.recommendation; import java.io.Serializable; import java.util.List; -import scala.Tuple2; - import org.junit.After; import org.junit.Assert; import org.junit.Before; @@ -75,10 +75,10 @@ <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding> <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding> - <java.version>1.5</java.version> + <java.version>1.6</java.version> <scala-short.version>2.10</scala-short.version> - <scala.version>2.10.2</scala.version> + <scala.version>2.10.3</scala.version> <mesos.version>0.13.0</mesos.version> <akka.version>2.2.1</akka.version> <slf4j.version>1.7.2</slf4j.version> @@ -257,7 +257,7 @@ <dependency> <groupId>io.netty</groupId> <artifactId>netty-all</artifactId> - <version>4.0.0.Beta2</version> + <version>4.0.0.CR1</version> </dependency> <dependency> <groupId>org.apache.derby</groupId> @@ -269,6 +269,12 @@ <groupId>net.liftweb</groupId> <artifactId>lift-json_${scala-short.version}</artifactId> <version>2.5.1</version> + <exclusions> + <exclusion> + <groupId>org.scala-lang</groupId> + <artifactId>scalap</artifactId> + </exclusion> + </exclusions> </dependency> <dependency> <groupId>com.codahale.metrics</groupId> diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala index b5e65a1856..5d4250a53b 100644 --- a/project/SparkBuild.scala +++ b/project/SparkBuild.scala @@ -34,8 +34,8 @@ object SparkBuild extends Build { val HBASE_VERSION = "0.94.6" // Target JVM version - val SCALAC_JVM_VERSION = "jvm-1.5" - val JAVAC_JVM_VERSION = "1.5" + val SCALAC_JVM_VERSION = "jvm-1.6" + val JAVAC_JVM_VERSION = "1.6" lazy val root = Project("root", file("."), settings = rootSettings) aggregate(allProjects: _*) @@ -80,7 +80,7 @@ object SparkBuild extends Build { def sharedSettings = Defaults.defaultSettings ++ Seq( organization := "org.apache.spark", version := "0.8.0-SNAPSHOT", - scalaVersion := "2.10.2", + scalaVersion := "2.10.3", scalacOptions := Seq("-unchecked", "-optimize", "-deprecation", "-target:" + SCALAC_JVM_VERSION), javacOptions := Seq("-target", JAVAC_JVM_VERSION, "-source", JAVAC_JVM_VERSION), unmanagedJars in Compile <<= baseDirectory map { base => (base / "lib" ** "*.jar").classpath }, diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/CoGroupedDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/CoGroupedDStream.scala index 4eddc755b9..16c1567355 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/CoGroupedDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/CoGroupedDStream.scala @@ -21,9 +21,10 @@ import org.apache.spark.Partitioner import org.apache.spark.rdd.RDD import org.apache.spark.rdd.CoGroupedRDD import org.apache.spark.streaming.{Time, DStream, Duration} +import scala.reflect.ClassTag private[streaming] -class CoGroupedDStream[K : ClassManifest]( +class CoGroupedDStream[K : ClassTag]( parents: Seq[DStream[(K, _)]], partitioner: Partitioner ) extends DStream[(K, Seq[Seq[_]])](parents.head.ssc) { diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/ConstantInputDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/ConstantInputDStream.scala index a9a05c9981..f396c34758 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/ConstantInputDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/ConstantInputDStream.scala @@ -19,11 +19,12 @@ package org.apache.spark.streaming.dstream import org.apache.spark.rdd.RDD import org.apache.spark.streaming.{Time, StreamingContext} +import scala.reflect.ClassTag /** * An input stream that always returns the same RDD on each timestep. Useful for testing. */ -class ConstantInputDStream[T: ClassManifest](ssc_ : StreamingContext, rdd: RDD[T]) +class ConstantInputDStream[T: ClassTag](ssc_ : StreamingContext, rdd: RDD[T]) extends InputDStream[T](ssc_) { override def start() {} diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/FilteredDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/FilteredDStream.scala index 91ee2c1a36..db2e0a4cee 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/FilteredDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/FilteredDStream.scala @@ -19,9 +19,10 @@ package org.apache.spark.streaming.dstream import org.apache.spark.streaming.{Duration, DStream, Time} import org.apache.spark.rdd.RDD +import scala.reflect.ClassTag private[streaming] -class FilteredDStream[T: ClassManifest]( +class FilteredDStream[T: ClassTag]( parent: DStream[T], filterFunc: T => Boolean ) extends DStream[T](parent.ssc) { diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/FlatMapValuedDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/FlatMapValuedDStream.scala index ca7d7ca49e..244dc3ee4f 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/FlatMapValuedDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/FlatMapValuedDStream.scala @@ -20,9 +20,10 @@ package org.apache.spark.streaming.dstream import org.apache.spark.streaming.{Duration, DStream, Time} import org.apache.spark.rdd.RDD import org.apache.spark.SparkContext._ +import scala.reflect.ClassTag private[streaming] -class FlatMapValuedDStream[K: ClassManifest, V: ClassManifest, U: ClassManifest]( +class FlatMapValuedDStream[K: ClassTag, V: ClassTag, U: ClassTag]( parent: DStream[(K, V)], flatMapValueFunc: V => TraversableOnce[U] ) extends DStream[(K, U)](parent.ssc) { diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/FlatMappedDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/FlatMappedDStream.scala index b37966f9a7..336c4b7a92 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/FlatMappedDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/FlatMappedDStream.scala @@ -19,9 +19,10 @@ package org.apache.spark.streaming.dstream import org.apache.spark.streaming.{Duration, DStream, Time} import org.apache.spark.rdd.RDD +import scala.reflect.ClassTag private[streaming] -class FlatMappedDStream[T: ClassManifest, U: ClassManifest]( +class FlatMappedDStream[T: ClassTag, U: ClassTag]( parent: DStream[T], flatMapFunc: T => Traversable[U] ) extends DStream[U](parent.ssc) { diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/ForEachDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/ForEachDStream.scala index e21bac4602..98b14cb224 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/ForEachDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/ForEachDStream.scala @@ -19,9 +19,10 @@ package org.apache.spark.streaming.dstream import org.apache.spark.rdd.RDD import org.apache.spark.streaming.{Duration, DStream, Job, Time} +import scala.reflect.ClassTag private[streaming] -class ForEachDStream[T: ClassManifest] ( +class ForEachDStream[T: ClassTag] ( parent: DStream[T], foreachFunc: (RDD[T], Time) => Unit ) extends DStream[Unit](parent.ssc) { diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/GlommedDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/GlommedDStream.scala index 4294b07d91..23136f44fa 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/GlommedDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/GlommedDStream.scala @@ -19,9 +19,10 @@ package org.apache.spark.streaming.dstream import org.apache.spark.streaming.{Duration, DStream, Time} import org.apache.spark.rdd.RDD +import scala.reflect.ClassTag private[streaming] -class GlommedDStream[T: ClassManifest](parent: DStream[T]) +class GlommedDStream[T: ClassTag](parent: DStream[T]) extends DStream[Array[T]](parent.ssc) { override def dependencies = List(parent) diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/MapPartitionedDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/MapPartitionedDStream.scala index 5329601a6f..8a04060e5b 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/MapPartitionedDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/MapPartitionedDStream.scala @@ -19,9 +19,10 @@ package org.apache.spark.streaming.dstream import org.apache.spark.streaming.{Duration, DStream, Time} import org.apache.spark.rdd.RDD +import scala.reflect.ClassTag private[streaming] -class MapPartitionedDStream[T: ClassManifest, U: ClassManifest]( +class MapPartitionedDStream[T: ClassTag, U: ClassTag]( parent: DStream[T], mapPartFunc: Iterator[T] => Iterator[U], preservePartitioning: Boolean diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/MapValuedDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/MapValuedDStream.scala index 8290df90a2..0ce364fd46 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/MapValuedDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/MapValuedDStream.scala @@ -20,9 +20,10 @@ package org.apache.spark.streaming.dstream import org.apache.spark.streaming.{Duration, DStream, Time} import org.apache.spark.rdd.RDD import org.apache.spark.SparkContext._ +import scala.reflect.ClassTag private[streaming] -class MapValuedDStream[K: ClassManifest, V: ClassManifest, U: ClassManifest]( +class MapValuedDStream[K: ClassTag, V: ClassTag, U: ClassTag]( parent: DStream[(K, V)], mapValueFunc: V => U ) extends DStream[(K, U)](parent.ssc) { diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/MappedDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/MappedDStream.scala index b1682afea3..c0b7491d09 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/MappedDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/MappedDStream.scala @@ -19,9 +19,10 @@ package org.apache.spark.streaming.dstream import org.apache.spark.streaming.{Duration, DStream, Time} import org.apache.spark.rdd.RDD +import scala.reflect.ClassTag private[streaming] -class MappedDStream[T: ClassManifest, U: ClassManifest] ( +class MappedDStream[T: ClassTag, U: ClassTag] ( parent: DStream[T], mapFunc: T => U ) extends DStream[U](parent.ssc) { diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/PluggableInputDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/PluggableInputDStream.scala index 15782f5c11..6f9477020a 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/PluggableInputDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/PluggableInputDStream.scala @@ -18,9 +18,10 @@ package org.apache.spark.streaming.dstream import org.apache.spark.streaming.StreamingContext +import scala.reflect.ClassTag private[streaming] -class PluggableInputDStream[T: ClassManifest]( +class PluggableInputDStream[T: ClassTag]( @transient ssc_ : StreamingContext, receiver: NetworkReceiver[T]) extends NetworkInputDStream[T](ssc_) { diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/QueueInputDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/QueueInputDStream.scala index 7d9f3521b1..97325f8ea3 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/QueueInputDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/QueueInputDStream.scala @@ -19,13 +19,13 @@ package org.apache.spark.streaming.dstream import org.apache.spark.rdd.RDD import org.apache.spark.rdd.UnionRDD - import scala.collection.mutable.Queue import scala.collection.mutable.ArrayBuffer import org.apache.spark.streaming.{Time, StreamingContext} +import scala.reflect.ClassTag private[streaming] -class QueueInputDStream[T: ClassManifest]( +class QueueInputDStream[T: ClassTag]( @transient ssc: StreamingContext, val queue: Queue[RDD[T]], oneAtATime: Boolean, diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/ShuffledDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/ShuffledDStream.scala index a95e66d761..e6e0022097 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/ShuffledDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/ShuffledDStream.scala @@ -21,9 +21,10 @@ import org.apache.spark.Partitioner import org.apache.spark.rdd.RDD import org.apache.spark.SparkContext._ import org.apache.spark.streaming.{Duration, DStream, Time} +import scala.reflect.ClassTag private[streaming] -class ShuffledDStream[K: ClassManifest, V: ClassManifest, C: ClassManifest]( +class ShuffledDStream[K: ClassTag, V: ClassTag, C: ClassTag]( parent: DStream[(K,V)], createCombiner: V => C, mergeValue: (C, V) => C, diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/TransformedDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/TransformedDStream.scala index 60485adef9..73e1ddf7a4 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/TransformedDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/TransformedDStream.scala @@ -19,9 +19,10 @@ package org.apache.spark.streaming.dstream import org.apache.spark.rdd.RDD import org.apache.spark.streaming.{Duration, DStream, Time} +import scala.reflect.ClassTag private[streaming] -class TransformedDStream[T: ClassManifest, U: ClassManifest] ( +class TransformedDStream[T: ClassTag, U: ClassTag] ( parent: DStream[T], transformFunc: (RDD[T], Time) => RDD[U] ) extends DStream[U](parent.ssc) { diff --git a/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java b/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java index 783b8dea31..076fb53fa1 100644 --- a/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java +++ b/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java @@ -21,34 +21,36 @@ import com.google.common.base.Optional; import com.google.common.collect.Lists; import com.google.common.collect.Maps; import com.google.common.io.Files; + import kafka.serializer.StringDecoder; + import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat; import org.junit.After; import org.junit.Assert; import org.junit.Before; import org.junit.Test; + import scala.Tuple2; +import twitter4j.Status; + import org.apache.spark.HashPartitioner; import org.apache.spark.api.java.JavaPairRDD; import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.api.java.JavaRDDLike; -import org.apache.spark.api.java.JavaPairRDD; import org.apache.spark.api.java.JavaSparkContext; import org.apache.spark.api.java.function.*; import org.apache.spark.storage.StorageLevel; import org.apache.spark.streaming.api.java.JavaDStream; import org.apache.spark.streaming.api.java.JavaPairDStream; import org.apache.spark.streaming.api.java.JavaStreamingContext; +import org.apache.spark.streaming.dstream.SparkFlumeEvent; import org.apache.spark.streaming.JavaTestUtils; import org.apache.spark.streaming.JavaCheckpointTestUtils; -import org.apache.spark.streaming.InputStreamsSuite; import java.io.*; import java.util.*; import akka.actor.Props; import akka.zeromq.Subscribe; -import akka.util.ByteString; // The test suite itself is Serializable so that anonymous Function implementations can be @@ -85,8 +87,8 @@ public class JavaAPISuite implements Serializable { Arrays.asList(3L), Arrays.asList(1L)); - JavaDStream stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); - JavaDStream count = stream.count(); + JavaDStream<Integer> stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); + JavaDStream<Long> count = stream.count(); JavaTestUtils.attachTestOutputStream(count); List<List<Long>> result = JavaTestUtils.runStreams(ssc, 3, 3); assertOrderInvariantEquals(expected, result); @@ -102,8 +104,8 @@ public class JavaAPISuite implements Serializable { Arrays.asList(5,5), Arrays.asList(9,4)); - JavaDStream stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); - JavaDStream letterCount = stream.map(new Function<String, Integer>() { + JavaDStream<String> stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); + JavaDStream<Integer> letterCount = stream.map(new Function<String, Integer>() { @Override public Integer call(String s) throws Exception { return s.length(); @@ -128,8 +130,8 @@ public class JavaAPISuite implements Serializable { Arrays.asList(7,8,9,4,5,6), Arrays.asList(7,8,9)); - JavaDStream stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); - JavaDStream windowed = stream.window(new Duration(2000)); + JavaDStream<Integer> stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); + JavaDStream<Integer> windowed = stream.window(new Duration(2000)); JavaTestUtils.attachTestOutputStream(windowed); List<List<Integer>> result = JavaTestUtils.runStreams(ssc, 4, 4); @@ -152,8 +154,8 @@ public class JavaAPISuite implements Serializable { Arrays.asList(7,8,9,10,11,12,13,14,15,16,17,18), Arrays.asList(13,14,15,16,17,18)); - JavaDStream stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); - JavaDStream windowed = stream.window(new Duration(4000), new Duration(2000)); + JavaDStream<Integer> stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); + JavaDStream<Integer> windowed = stream.window(new Duration(4000), new Duration(2000)); JavaTestUtils.attachTestOutputStream(windowed); List<List<Integer>> result = JavaTestUtils.runStreams(ssc, 8, 4); @@ -170,8 +172,8 @@ public class JavaAPISuite implements Serializable { Arrays.asList("giants"), Arrays.asList("yankees")); - JavaDStream stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); - JavaDStream filtered = stream.filter(new Function<String, Boolean>() { + JavaDStream<String> stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); + JavaDStream<String> filtered = stream.filter(new Function<String, Boolean>() { @Override public Boolean call(String s) throws Exception { return s.contains("a"); @@ -193,8 +195,8 @@ public class JavaAPISuite implements Serializable { Arrays.asList(Arrays.asList("giants", "dodgers")), Arrays.asList(Arrays.asList("yankees", "red socks"))); - JavaDStream stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); - JavaDStream glommed = stream.glom(); + JavaDStream<String> stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); + JavaDStream<List<String>> glommed = stream.glom(); JavaTestUtils.attachTestOutputStream(glommed); List<List<List<String>>> result = JavaTestUtils.runStreams(ssc, 2, 2); @@ -211,8 +213,8 @@ public class JavaAPISuite implements Serializable { Arrays.asList("GIANTSDODGERS"), Arrays.asList("YANKEESRED SOCKS")); - JavaDStream stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); - JavaDStream mapped = stream.mapPartitions(new FlatMapFunction<Iterator<String>, String>() { + JavaDStream<String> stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); + JavaDStream<String> mapped = stream.mapPartitions(new FlatMapFunction<Iterator<String>, String>() { @Override public Iterable<String> call(Iterator<String> in) { String out = ""; @@ -254,8 +256,8 @@ public class JavaAPISuite implements Serializable { Arrays.asList(15), Arrays.asList(24)); - JavaDStream stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); - JavaDStream reduced = stream.reduce(new IntegerSum()); + JavaDStream<Integer> stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); + JavaDStream<Integer> reduced = stream.reduce(new IntegerSum()); JavaTestUtils.attachTestOutputStream(reduced); List<List<Integer>> result = JavaTestUtils.runStreams(ssc, 3, 3); @@ -275,8 +277,8 @@ public class JavaAPISuite implements Serializable { Arrays.asList(39), Arrays.asList(24)); - JavaDStream stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); - JavaDStream reducedWindowed = stream.reduceByWindow(new IntegerSum(), + JavaDStream<Integer> stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); + JavaDStream<Integer> reducedWindowed = stream.reduceByWindow(new IntegerSum(), new IntegerDifference(), new Duration(2000), new Duration(1000)); JavaTestUtils.attachTestOutputStream(reducedWindowed); List<List<Integer>> result = JavaTestUtils.runStreams(ssc, 4, 4); @@ -349,8 +351,8 @@ public class JavaAPISuite implements Serializable { Arrays.asList("b", "o", "o", "d","o","d","g","e","r","s"), Arrays.asList("a","t","h","l","e","t","i","c","s")); - JavaDStream stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); - JavaDStream flatMapped = stream.flatMap(new FlatMapFunction<String, String>() { + JavaDStream<String> stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); + JavaDStream<String> flatMapped = stream.flatMap(new FlatMapFunction<String, String>() { @Override public Iterable<String> call(String x) { return Lists.newArrayList(x.split("(?!^)")); @@ -396,8 +398,8 @@ public class JavaAPISuite implements Serializable { new Tuple2<Integer, String>(9, "c"), new Tuple2<Integer, String>(9, "s"))); - JavaDStream stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); - JavaPairDStream flatMapped = stream.flatMap(new PairFlatMapFunction<String, Integer, String>() { + JavaDStream<String> stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); + JavaPairDStream<Integer,String> flatMapped = stream.flatMap(new PairFlatMapFunction<String, Integer, String>() { @Override public Iterable<Tuple2<Integer, String>> call(String in) throws Exception { List<Tuple2<Integer, String>> out = Lists.newArrayList(); @@ -430,10 +432,10 @@ public class JavaAPISuite implements Serializable { Arrays.asList(2,2,5,5), Arrays.asList(3,3,6,6)); - JavaDStream stream1 = JavaTestUtils.attachTestInputStream(ssc, inputData1, 2); - JavaDStream stream2 = JavaTestUtils.attachTestInputStream(ssc, inputData2, 2); + JavaDStream<Integer> stream1 = JavaTestUtils.attachTestInputStream(ssc, inputData1, 2); + JavaDStream<Integer> stream2 = JavaTestUtils.attachTestInputStream(ssc, inputData2, 2); - JavaDStream unioned = stream1.union(stream2); + JavaDStream<Integer> unioned = stream1.union(stream2); JavaTestUtils.attachTestOutputStream(unioned); List<List<Integer>> result = JavaTestUtils.runStreams(ssc, 3, 3); @@ -444,7 +446,7 @@ public class JavaAPISuite implements Serializable { * Performs an order-invariant comparison of lists representing two RDD streams. This allows * us to account for ordering variation within individual RDD's which occurs during windowing. */ - public static <T extends Comparable> void assertOrderInvariantEquals( + public static <T extends Comparable<T>> void assertOrderInvariantEquals( List<List<T>> expected, List<List<T>> actual) { for (List<T> list: expected) { Collections.sort(list); @@ -467,11 +469,11 @@ public class JavaAPISuite implements Serializable { Arrays.asList(new Tuple2<String, Integer>("giants", 6)), Arrays.asList(new Tuple2<String, Integer>("yankees", 7))); - JavaDStream stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); + JavaDStream<String> stream = JavaTestUtils.attachTestInputStream(ssc, inputData, 1); JavaPairDStream<String, Integer> pairStream = stream.map( new PairFunction<String, String, Integer>() { @Override - public Tuple2 call(String in) throws Exception { + public Tuple2<String, Integer> call(String in) throws Exception { return new Tuple2<String, Integer>(in, in.length()); } }); @@ -1163,8 +1165,8 @@ public class JavaAPISuite implements Serializable { File tempDir = Files.createTempDir(); ssc.checkpoint(tempDir.getAbsolutePath()); - JavaDStream stream = JavaCheckpointTestUtils.attachTestInputStream(ssc, inputData, 1); - JavaDStream letterCount = stream.map(new Function<String, Integer>() { + JavaDStream<String> stream = JavaCheckpointTestUtils.attachTestInputStream(ssc, inputData, 1); + JavaDStream<Integer> letterCount = stream.map(new Function<String, Integer>() { @Override public Integer call(String s) throws Exception { return s.length(); @@ -1220,20 +1222,20 @@ public class JavaAPISuite implements Serializable { @Test public void testKafkaStream() { HashMap<String, Integer> topics = Maps.newHashMap(); - JavaDStream test1 = ssc.kafkaStream("localhost:12345", "group", topics); - JavaDStream test2 = ssc.kafkaStream("localhost:12345", "group", topics, + JavaDStream<String> test1 = ssc.kafkaStream("localhost:12345", "group", topics); + JavaDStream<String> test2 = ssc.kafkaStream("localhost:12345", "group", topics, StorageLevel.MEMORY_AND_DISK()); HashMap<String, String> kafkaParams = Maps.newHashMap(); kafkaParams.put("zk.connect","localhost:12345"); kafkaParams.put("groupid","consumer-group"); - JavaDStream test3 = ssc.kafkaStream(String.class, StringDecoder.class, kafkaParams, topics, + JavaDStream<String> test3 = ssc.kafkaStream(String.class, StringDecoder.class, kafkaParams, topics, StorageLevel.MEMORY_AND_DISK()); } @Test public void testSocketTextStream() { - JavaDStream test = ssc.socketTextStream("localhost", 12345); + JavaDStream<String> test = ssc.socketTextStream("localhost", 12345); } @Test @@ -1253,7 +1255,7 @@ public class JavaAPISuite implements Serializable { } } - JavaDStream test = ssc.socketStream( + JavaDStream<String> test = ssc.socketStream( "localhost", 12345, new Converter(), @@ -1262,39 +1264,39 @@ public class JavaAPISuite implements Serializable { @Test public void testTextFileStream() { - JavaDStream test = ssc.textFileStream("/tmp/foo"); + JavaDStream<String> test = ssc.textFileStream("/tmp/foo"); } @Test public void testRawSocketStream() { - JavaDStream test = ssc.rawSocketStream("localhost", 12345); + JavaDStream<String> test = ssc.rawSocketStream("localhost", 12345); } @Test public void testFlumeStream() { - JavaDStream test = ssc.flumeStream("localhost", 12345, StorageLevel.MEMORY_ONLY()); + JavaDStream<SparkFlumeEvent> test = ssc.flumeStream("localhost", 12345, StorageLevel.MEMORY_ONLY()); } @Test public void testFileStream() { JavaPairDStream<String, String> foo = - ssc.<String, String, SequenceFileInputFormat>fileStream("/tmp/foo"); + ssc.<String, String, SequenceFileInputFormat<String,String>>fileStream("/tmp/foo"); } @Test public void testTwitterStream() { String[] filters = new String[] { "good", "bad", "ugly" }; - JavaDStream test = ssc.twitterStream(filters, StorageLevel.MEMORY_ONLY()); + JavaDStream<Status> test = ssc.twitterStream(filters, StorageLevel.MEMORY_ONLY()); } @Test public void testActorStream() { - JavaDStream test = ssc.actorStream((Props)null, "TestActor", StorageLevel.MEMORY_ONLY()); + JavaDStream<String> test = ssc.actorStream((Props)null, "TestActor", StorageLevel.MEMORY_ONLY()); } @Test public void testZeroMQStream() { - JavaDStream test = ssc.zeroMQStream("url", (Subscribe) null, new Function<byte[][], Iterable<String>>() { + JavaDStream<String> test = ssc.zeroMQStream("url", (Subscribe) null, new Function<byte[][], Iterable<String>>() { @Override public Iterable<String> call(byte[][] b) throws Exception { return null; |