From 8712f08d756379b1ae286c15bb2d5df453616ef8 Mon Sep 17 00:00:00 2001 From: Wang Gengliang Date: Thu, 29 Jun 2017 15:01:17 -0700 Subject: [PATCH 1/8] first run --- .../scala/org/apache/spark/FutureAction.scala | 2 +- .../scala/org/apache/spark/Partitioner.scala | 6 +-- .../org/apache/spark/SecurityManager.scala | 2 +- .../scala/org/apache/spark/SparkConf.scala | 2 +- .../scala/org/apache/spark/SparkContext.scala | 2 +- .../org/apache/spark/TaskEndReason.scala | 2 +- .../org/apache/spark/api/java/JavaUtils.scala | 4 +- .../apache/spark/api/python/PythonRDD.scala | 4 +- .../WriteInputFormatTestDataGenerator.scala | 2 +- .../apache/spark/api/r/RBackendHandler.scala | 4 +- .../scala/org/apache/spark/api/r/RRDD.scala | 6 +-- .../spark/broadcast/BroadcastManager.scala | 2 +- .../broadcast/TorrentBroadcastFactory.scala | 2 +- .../spark/deploy/FaultToleranceTest.scala | 4 +- .../deploy/history/ApplicationCache.scala | 6 +-- .../apache/spark/deploy/worker/Worker.scala | 4 +- .../org/apache/spark/executor/Executor.scala | 2 +- .../spark/executor/ExecutorSource.scala | 2 +- .../org/apache/spark/internal/Logging.scala | 2 +- .../spark/launcher/LauncherBackend.scala | 2 +- .../spark/partial/GroupedCountEvaluator.scala | 2 +- .../apache/spark/partial/PartialResult.scala | 6 +-- .../org/apache/spark/rdd/CartesianRDD.scala | 4 +- .../org/apache/spark/rdd/CoalescedRDD.scala | 2 +- .../apache/spark/rdd/DoubleRDDFunctions.scala | 2 +- .../org/apache/spark/rdd/NewHadoopRDD.scala | 2 +- .../spark/rdd/OrderedRDDFunctions.scala | 4 +- .../apache/spark/rdd/PairRDDFunctions.scala | 8 ++-- .../spark/rdd/PartitionPruningRDD.scala | 2 +- .../main/scala/org/apache/spark/rdd/RDD.scala | 12 ++--- .../spark/rdd/SequenceFileRDDFunctions.scala | 2 +- .../apache/spark/rdd/WholeTextFileRDD.scala | 2 +- .../apache/spark/scheduler/DAGScheduler.scala | 2 +- .../scheduler/EventLoggingListener.scala | 4 +- .../org/apache/spark/scheduler/Stage.scala | 2 +- .../spark/scheduler/TaskResultGetter.scala | 2 +- .../spark/scheduler/TaskSchedulerImpl.scala | 2 +- .../GroupMappingServiceProvider.scala | 2 +- .../spark/status/api/v1/AllRDDResource.scala | 4 +- .../status/api/v1/AllStagesResource.scala | 2 +- .../org/apache/spark/status/api/v1/api.scala | 18 ++++---- .../apache/spark/storage/BlockManagerId.scala | 8 ++-- .../org/apache/spark/ui/JettyUtils.scala | 4 +- .../scala/org/apache/spark/ui/UIUtils.scala | 2 +- .../apache/spark/ui/jobs/AllJobsPage.scala | 2 +- .../apache/spark/ui/jobs/ExecutorTable.scala | 2 +- .../org/apache/spark/ui/jobs/StagePage.scala | 2 +- .../org/apache/spark/ui/jobs/StageTable.scala | 2 +- .../org/apache/spark/ui/jobs/UIData.scala | 32 ++++++------- .../org/apache/spark/ui/storage/RDDPage.scala | 2 +- .../apache/spark/util/CollectionsUtils.scala | 2 +- .../spark/util/CompletionIterator.scala | 2 +- .../org/apache/spark/util/ListenerBus.scala | 2 +- .../scala/org/apache/spark/util/Utils.scala | 4 +- .../apache/spark/util/collection/BitSet.scala | 14 +++--- .../spark/util/collection/OpenHashMap.scala | 2 +- .../util/collection/SortDataFormat.scala | 2 +- .../org/apache/spark/examples/LocalALS.scala | 4 +- .../org/apache/spark/examples/SparkALS.scala | 2 +- .../graphx/AggregateMessagesExample.scala | 4 +- .../graphx/ComprehensiveExample.scala | 2 +- .../examples/mllib/RandomRDDGeneration.scala | 4 +- .../examples/streaming/FlumeEventCount.scala | 2 +- .../streaming/FlumePollingEventCount.scala | 2 +- .../streaming/kafka/KafkaTestUtils.scala | 2 +- .../org/apache/spark/graphx/GraphOps.scala | 2 +- .../apache/spark/graphx/impl/GraphImpl.scala | 2 +- .../apache/spark/graphx/lib/PageRank.scala | 6 +-- .../spark/graphx/util/GraphGenerators.scala | 6 +-- .../org/apache/spark/ml/linalg/Vectors.scala | 2 +- .../apache/spark/ml/ann/LossFunction.scala | 2 +- .../apache/spark/ml/feature/RFormula.scala | 2 +- .../org/apache/spark/ml/r/KSTestWrapper.scala | 2 +- .../org/apache/spark/ml/tree/treeModels.scala | 2 +- .../mllib/api/python/PythonMLLibAPI.scala | 2 +- .../cluster/mesos/MesosSchedulerUtils.scala | 4 +- scalastyle-config.xml | 10 +++- .../scala/org/apache/spark/sql/Encoders.scala | 2 +- .../spark/sql/catalyst/ScalaReflection.scala | 6 +-- .../sql/catalyst/analysis/Analyzer.scala | 8 ++-- .../catalyst/analysis/FunctionRegistry.scala | 6 +-- .../spark/sql/catalyst/dsl/package.scala | 14 +++--- .../catalyst/encoders/ExpressionEncoder.scala | 2 +- .../spark/sql/catalyst/encoders/package.scala | 2 +- .../expressions/CallMethodViaReflection.scala | 2 +- .../expressions/aggregate/Percentile.scala | 2 +- .../sql/catalyst/expressions/literals.scala | 2 +- .../spark/sql/catalyst/expressions/misc.scala | 2 +- .../expressions/objects/objects.scala | 2 +- .../expressions/stringExpressions.scala | 6 +-- .../optimizer/CostBasedJoinReorder.scala | 2 +- .../sql/catalyst/optimizer/expressions.scala | 2 +- .../sql/catalyst/optimizer/subquery.scala | 12 ++--- .../parser/LegacyTypeStringParser.scala | 6 +-- .../plans/logical/basicLogicalOperators.scala | 8 ++-- .../sql/catalyst/plans/logical/object.scala | 20 ++++---- .../sql/catalyst/util/DateTimeUtils.scala | 2 +- .../sql/catalyst/util/NumberConverter.scala | 4 +- .../spark/sql/catalyst/util/package.scala | 4 +- .../apache/spark/sql/types/ArrayType.scala | 2 +- .../org/apache/spark/sql/types/Decimal.scala | 2 +- .../scala/org/apache/spark/sql/Column.scala | 6 +-- .../spark/sql/DataFrameNaFunctions.scala | 6 +-- .../apache/spark/sql/DataFrameReader.scala | 10 ++-- .../apache/spark/sql/DataFrameWriter.scala | 2 +- .../scala/org/apache/spark/sql/Dataset.scala | 46 +++++++++---------- .../org/apache/spark/sql/DatasetHolder.scala | 2 +- .../spark/sql/KeyValueGroupedDataset.scala | 10 ++-- .../spark/sql/RelationalGroupedDataset.scala | 12 ++--- .../org/apache/spark/sql/SQLContext.scala | 12 ++--- .../org/apache/spark/sql/SQLImplicits.scala | 14 +++--- .../org/apache/spark/sql/SparkSession.scala | 10 ++-- .../apache/spark/sql/UDFRegistration.scala | 2 +- .../aggregate/TypedAggregateExpression.scala | 2 +- .../parquet/ParquetSchemaConverter.scala | 2 +- .../joins/CartesianProductExec.scala | 4 +- .../sql/execution/joins/HashedRelation.scala | 2 +- .../sql/execution/stat/FrequentItems.scala | 4 +- .../streaming/CompactibleFileStreamLog.scala | 4 +- .../sql/execution/streaming/ForeachSink.scala | 2 +- .../execution/streaming/HDFSMetadataLog.scala | 2 +- .../sql/execution/streaming/LongOffset.scala | 2 +- .../sql/execution/streaming/Source.scala | 2 +- .../sql/execution/streaming/memory.scala | 6 +-- .../sql/execution/streaming/socket.scala | 2 +- .../state/HDFSBackedStateStoreProvider.scala | 2 +- .../apache/spark/sql/expressions/Window.scala | 8 ++-- .../org/apache/spark/sql/functions.scala | 10 ++-- .../spark/sql/jdbc/AggregatedDialect.scala | 2 +- .../apache/spark/sql/jdbc/JdbcDialects.scala | 10 ++-- .../apache/spark/sql/jdbc/MySQLDialect.scala | 2 +- .../apache/spark/sql/streaming/progress.scala | 2 +- .../hive/thriftserver/ReflectionUtils.scala | 2 +- .../hive/thriftserver/SparkSQLCLIDriver.scala | 4 +- .../spark/sql/hive/HiveInspectors.scala | 8 ++-- .../org/apache/spark/sql/hive/hiveUDFs.scala | 2 +- .../apache/spark/sql/hive/test/TestHive.scala | 2 +- 137 files changed, 321 insertions(+), 315 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/FutureAction.scala b/core/src/main/scala/org/apache/spark/FutureAction.scala index 0899693988016..0185056350e50 100644 --- a/core/src/main/scala/org/apache/spark/FutureAction.scala +++ b/core/src/main/scala/org/apache/spark/FutureAction.scala @@ -174,7 +174,7 @@ trait JobSubmitter { * jobs. */ @DeveloperApi -class ComplexFutureAction[T](run : JobSubmitter => Future[T]) +class ComplexFutureAction[T](run: JobSubmitter => Future[T]) extends FutureAction[T] { self => @volatile private var _cancelled = false diff --git a/core/src/main/scala/org/apache/spark/Partitioner.scala b/core/src/main/scala/org/apache/spark/Partitioner.scala index f83f5278e8b8f..37254696b23a1 100644 --- a/core/src/main/scala/org/apache/spark/Partitioner.scala +++ b/core/src/main/scala/org/apache/spark/Partitioner.scala @@ -105,7 +105,7 @@ class HashPartitioner(partitions: Int) extends Partitioner { * as the `partitions` parameter, in the case where the number of sampled records is less than * the value of `partitions`. */ -class RangePartitioner[K : Ordering : ClassTag, V]( +class RangePartitioner[K: Ordering: ClassTag, V]( partitions: Int, rdd: RDD[_ <: Product2[K, V]], private var ascending: Boolean = true) @@ -253,7 +253,7 @@ private[spark] object RangePartitioner { * @param sampleSizePerPartition max sample size per partition * @return (total number of items, an array of (partitionId, number of items, sample)) */ - def sketch[K : ClassTag]( + def sketch[K: ClassTag]( rdd: RDD[K], sampleSizePerPartition: Int): (Long, Array[(Int, Long, Array[K])]) = { val shift = rdd.id @@ -276,7 +276,7 @@ private[spark] object RangePartitioner { * @param partitions number of partitions * @return selected bounds */ - def determineBounds[K : Ordering : ClassTag]( + def determineBounds[K: Ordering: ClassTag]( candidates: ArrayBuffer[(K, Float)], partitions: Int): Array[K] = { val ordering = implicitly[Ordering[K]] diff --git a/core/src/main/scala/org/apache/spark/SecurityManager.scala b/core/src/main/scala/org/apache/spark/SecurityManager.scala index 2480e56b72ccf..eabbaba81a425 100644 --- a/core/src/main/scala/org/apache/spark/SecurityManager.scala +++ b/core/src/main/scala/org/apache/spark/SecurityManager.scala @@ -202,7 +202,7 @@ private[spark] class SecurityManager( stringToSet(sparkConf.get("spark.admin.acls", "")) // admin group acls should be set before view or modify group acls - private var adminAclsGroups : Set[String] = + private var adminAclsGroups: Set[String] = stringToSet(sparkConf.get("spark.admin.acls.groups", "")) private var viewAcls: Set[String] = _ diff --git a/core/src/main/scala/org/apache/spark/SparkConf.scala b/core/src/main/scala/org/apache/spark/SparkConf.scala index de2f475c6895f..fa25994cf512b 100644 --- a/core/src/main/scala/org/apache/spark/SparkConf.scala +++ b/core/src/main/scala/org/apache/spark/SparkConf.scala @@ -595,7 +595,7 @@ private[spark] object SparkConf extends Logging { DeprecatedConfig("spark.executor.port", "2.0.0", "Not used any more") ) - Map(configs.map { cfg => (cfg.key -> cfg) } : _*) + Map(configs.map { cfg => (cfg.key -> cfg) }: _*) } /** diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index b2a26c51d4de1..1fefc3dfb30b0 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -2869,7 +2869,7 @@ private[spark] class WritableFactory[T]( object WritableFactory { - private[spark] def simpleWritableFactory[T: ClassTag, W <: Writable : ClassTag](convert: T => W) + private[spark] def simpleWritableFactory[T: ClassTag, W <: Writable: ClassTag](convert: T => W) : WritableFactory[T] = { val writableClass = implicitly[ClassTag[W]].runtimeClass.asInstanceOf[Class[W]] new WritableFactory[T](_ => writableClass, convert) diff --git a/core/src/main/scala/org/apache/spark/TaskEndReason.scala b/core/src/main/scala/org/apache/spark/TaskEndReason.scala index a76283e33fa65..7f34fca4cfa97 100644 --- a/core/src/main/scala/org/apache/spark/TaskEndReason.scala +++ b/core/src/main/scala/org/apache/spark/TaskEndReason.scala @@ -192,7 +192,7 @@ private[spark] class ThrowableSerializationWrapper(var exception: Throwable) ext try { exception = in.readObject().asInstanceOf[Throwable] } catch { - case e : Exception => log.warn("Task exception could not be deserialized", e) + case e: Exception => log.warn("Task exception could not be deserialized", e) } } } diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaUtils.scala b/core/src/main/scala/org/apache/spark/api/java/JavaUtils.scala index f820401da2fc3..271261b1baf56 100644 --- a/core/src/main/scala/org/apache/spark/api/java/JavaUtils.scala +++ b/core/src/main/scala/org/apache/spark/api/java/JavaUtils.scala @@ -54,7 +54,7 @@ private[spark] object JavaUtils { override def iterator: ju.Iterator[ju.Map.Entry[A, B]] = new ju.Iterator[ju.Map.Entry[A, B]] { val ui = underlying.iterator - var prev : Option[A] = None + var prev: Option[A] = None def hasNext: Boolean = ui.hasNext @@ -65,7 +65,7 @@ private[spark] object JavaUtils { import scala.util.hashing.byteswap32 override def getKey: A = k override def getValue: B = v - override def setValue(v1 : B): B = self.put(k, v1) + override def setValue(v1: B): B = self.put(k, v1) override def hashCode: Int = byteswap32(k.hashCode) + (byteswap32(v.hashCode) << 16) override def equals(other: Any): Boolean = other match { case e: ju.Map.Entry[_, _] => k == e.getKey && v == e.getValue diff --git a/core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala b/core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala index fb0405b1a69c6..7dae65c9f6066 100644 --- a/core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala +++ b/core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala @@ -396,7 +396,7 @@ private class PairwiseRDD(prev: RDD[Array[Byte]]) extends RDD[(Long, Array[Byte] case Seq(a, b) => (Utils.deserializeLongValue(a), b) case x => throw new SparkException("PairwiseRDD: unexpected value: " + x) } - val asJavaPairRDD : JavaPairRDD[Long, Array[Byte]] = JavaPairRDD.fromRDD(this) + val asJavaPairRDD: JavaPairRDD[Long, Array[Byte]] = JavaPairRDD.fromRDD(this) } private object SpecialLengths { @@ -867,7 +867,7 @@ private[spark] object PythonRDD extends Logging { private class BytesToString extends org.apache.spark.api.java.function.Function[Array[Byte], String] { - override def call(arr: Array[Byte]) : String = new String(arr, StandardCharsets.UTF_8) + override def call(arr: Array[Byte]): String = new String(arr, StandardCharsets.UTF_8) } /** diff --git a/core/src/main/scala/org/apache/spark/api/python/WriteInputFormatTestDataGenerator.scala b/core/src/main/scala/org/apache/spark/api/python/WriteInputFormatTestDataGenerator.scala index 86965dbc2e778..5204d7318d44b 100644 --- a/core/src/main/scala/org/apache/spark/api/python/WriteInputFormatTestDataGenerator.scala +++ b/core/src/main/scala/org/apache/spark/api/python/WriteInputFormatTestDataGenerator.scala @@ -95,7 +95,7 @@ private[python] class DoubleArrayToWritableConverter extends Converter[Any, Writ private[python] class WritableToDoubleArrayConverter extends Converter[Any, Array[Double]] { override def convert(obj: Any): Array[Double] = obj match { - case daw : DoubleArrayWritable => daw.get().map(_.asInstanceOf[DoubleWritable].get()) + case daw: DoubleArrayWritable => daw.get().map(_.asInstanceOf[DoubleWritable].get()) case other => throw new SparkException(s"Data of type $other is not supported") } } diff --git a/core/src/main/scala/org/apache/spark/api/r/RBackendHandler.scala b/core/src/main/scala/org/apache/spark/api/r/RBackendHandler.scala index cfd37ac54ba23..818d2e60e03ad 100644 --- a/core/src/main/scala/org/apache/spark/api/r/RBackendHandler.scala +++ b/core/src/main/scala/org/apache/spark/api/r/RBackendHandler.scala @@ -164,7 +164,7 @@ private[r] class RBackendHandler(server: RBackend) throw new Exception(s"No matched method found for $cls.$methodName") } - val ret = selectedMethods(index.get).invoke(obj, args : _*) + val ret = selectedMethods(index.get).invoke(obj, args: _*) // Write status bit writeInt(dos, 0) @@ -185,7 +185,7 @@ private[r] class RBackendHandler(server: RBackend) throw new Exception(s"No matched constructor found for $cls") } - val obj = ctors(index.get).newInstance(args : _*) + val obj = ctors(index.get).newInstance(args: _*) writeInt(dos, 0) writeObject(dos, obj.asInstanceOf[AnyRef], server.jvmObjectTracker) diff --git a/core/src/main/scala/org/apache/spark/api/r/RRDD.scala b/core/src/main/scala/org/apache/spark/api/r/RRDD.scala index 295355c7bf018..adf96d769f298 100644 --- a/core/src/main/scala/org/apache/spark/api/r/RRDD.scala +++ b/core/src/main/scala/org/apache/spark/api/r/RRDD.scala @@ -67,7 +67,7 @@ private class PairwiseRRDD[T: ClassTag]( parent, numPartitions, hashFunc, deserializer, SerializationFormats.BYTE, packageNames, broadcastVars.map(x => x.asInstanceOf[Broadcast[Object]])) { - lazy val asJavaPairRDD : JavaPairRDD[Int, Array[Byte]] = JavaPairRDD.fromRDD(this) + lazy val asJavaPairRDD: JavaPairRDD[Int, Array[Byte]] = JavaPairRDD.fromRDD(this) } /** @@ -83,7 +83,7 @@ private class RRDD[T: ClassTag]( extends BaseRRDD[T, Array[Byte]]( parent, -1, func, deserializer, serializer, packageNames, broadcastVars.map(x => x.asInstanceOf[Broadcast[Object]])) { - lazy val asJavaRDD : JavaRDD[Array[Byte]] = JavaRDD.fromRDD(this) + lazy val asJavaRDD: JavaRDD[Array[Byte]] = JavaRDD.fromRDD(this) } /** @@ -98,7 +98,7 @@ private class StringRRDD[T: ClassTag]( extends BaseRRDD[T, String]( parent, -1, func, deserializer, SerializationFormats.STRING, packageNames, broadcastVars.map(x => x.asInstanceOf[Broadcast[Object]])) { - lazy val asJavaRDD : JavaRDD[String] = JavaRDD.fromRDD(this) + lazy val asJavaRDD: JavaRDD[String] = JavaRDD.fromRDD(this) } private[r] object RRDD { diff --git a/core/src/main/scala/org/apache/spark/broadcast/BroadcastManager.scala b/core/src/main/scala/org/apache/spark/broadcast/BroadcastManager.scala index e88988fe03b2e..8e0fac9ba1f62 100644 --- a/core/src/main/scala/org/apache/spark/broadcast/BroadcastManager.scala +++ b/core/src/main/scala/org/apache/spark/broadcast/BroadcastManager.scala @@ -52,7 +52,7 @@ private[spark] class BroadcastManager( private val nextBroadcastId = new AtomicLong(0) - def newBroadcast[T: ClassTag](value_ : T, isLocal: Boolean): Broadcast[T] = { + def newBroadcast[T: ClassTag](value_: T, isLocal: Boolean): Broadcast[T] = { broadcastFactory.newBroadcast[T](value_, isLocal, nextBroadcastId.getAndIncrement()) } diff --git a/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcastFactory.scala b/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcastFactory.scala index b11f9ba171b84..b6f35b73e8359 100644 --- a/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcastFactory.scala +++ b/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcastFactory.scala @@ -30,7 +30,7 @@ private[spark] class TorrentBroadcastFactory extends BroadcastFactory { override def initialize(isDriver: Boolean, conf: SparkConf, securityMgr: SecurityManager) { } - override def newBroadcast[T: ClassTag](value_ : T, isLocal: Boolean, id: Long): Broadcast[T] = { + override def newBroadcast[T: ClassTag](value_: T, isLocal: Boolean, id: Long): Broadcast[T] = { new TorrentBroadcast[T](value_, id) } diff --git a/core/src/main/scala/org/apache/spark/deploy/FaultToleranceTest.scala b/core/src/main/scala/org/apache/spark/deploy/FaultToleranceTest.scala index c6307da61c7eb..9764c46d6a6a2 100644 --- a/core/src/main/scala/org/apache/spark/deploy/FaultToleranceTest.scala +++ b/core/src/main/scala/org/apache/spark/deploy/FaultToleranceTest.scala @@ -406,7 +406,7 @@ private object SparkDocker { new TestWorkerInfo(ip, id, outFile) } - private def startNode(dockerCmd: ProcessBuilder) : (String, DockerId, File) = { + private def startNode(dockerCmd: ProcessBuilder): (String, DockerId, File) = { val ipPromise = Promise[String]() val outFile = File.createTempFile("fault-tolerance-test", "", Utils.createTempDir()) val outStream: FileWriter = new FileWriter(outFile) @@ -440,7 +440,7 @@ private object Docker extends Logging { cmd } - def kill(dockerId: DockerId) : Unit = { + def kill(dockerId: DockerId): Unit = { "docker kill %s".format(dockerId.id).! } diff --git a/core/src/main/scala/org/apache/spark/deploy/history/ApplicationCache.scala b/core/src/main/scala/org/apache/spark/deploy/history/ApplicationCache.scala index a370526c46f3d..db47649c70a21 100644 --- a/core/src/main/scala/org/apache/spark/deploy/history/ApplicationCache.scala +++ b/core/src/main/scala/org/apache/spark/deploy/history/ApplicationCache.scala @@ -602,7 +602,7 @@ private[history] object ApplicationCacheCheckFilterRelay extends Logging { * @param cache new cache */ def setApplicationCache(cache: ApplicationCache): Unit = { - applicationCache.foreach( c => logWarning(s"Overwriting application cache $c")) + applicationCache.foreach(c => logWarning(s"Overwriting application cache $c")) applicationCache = Some(cache) } @@ -650,13 +650,13 @@ private[history] object ApplicationCacheCheckFilterRelay extends Logging { def registerFilter( ui: SparkUI, appId: String, - attemptId: Option[String] ): Unit = { + attemptId: Option[String]): Unit = { require(ui != null) val enumDispatcher = java.util.EnumSet.of(DispatcherType.ASYNC, DispatcherType.REQUEST) val holder = new FilterHolder() holder.setClassName(FILTER_NAME) holder.setInitParameter(APP_ID, appId) - attemptId.foreach( id => holder.setInitParameter(ATTEMPT_ID, id)) + attemptId.foreach(id => holder.setInitParameter(ATTEMPT_ID, id)) require(ui.getHandlers != null, "null handlers") ui.getHandlers.foreach { handler => handler.addFilter(holder, "/*", enumDispatcher) diff --git a/core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala b/core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala index bed47455680dd..d5ce01a2ec588 100755 --- a/core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala +++ b/core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala @@ -114,7 +114,7 @@ private[deploy] class Worker( */ private var masterAddressToConnect: Option[RpcAddress] = None private var activeMasterUrl: String = "" - private[worker] var activeMasterWebUiUrl : String = "" + private[worker] var activeMasterWebUiUrl: String = "" private var workerWebUiUrl: String = "" private val workerUri = RpcEndpointAddress(rpcEnv.address, endpointName).toString private var registered = false @@ -178,7 +178,7 @@ private[deploy] class Worker( // This sporadically fails - not sure why ... !workDir.exists() && !workDir.mkdirs() // So attempting to create and then check if directory was created or not. workDir.mkdirs() - if ( !workDir.exists() || !workDir.isDirectory) { + if (!workDir.exists() || !workDir.isDirectory) { logError("Failed to create work directory " + workDir) System.exit(1) } diff --git a/core/src/main/scala/org/apache/spark/executor/Executor.scala b/core/src/main/scala/org/apache/spark/executor/Executor.scala index 19e7eb086f413..1d45c32058d8e 100644 --- a/core/src/main/scala/org/apache/spark/executor/Executor.scala +++ b/core/src/main/scala/org/apache/spark/executor/Executor.scala @@ -205,7 +205,7 @@ private[spark] class Executor( * tasks instead of taking the JVM down. * @param interruptThread whether to interrupt the task thread */ - def killAllTasks(interruptThread: Boolean, reason: String) : Unit = { + def killAllTasks(interruptThread: Boolean, reason: String): Unit = { runningTasks.keys().asScala.foreach(t => killTask(t, interruptThread = interruptThread, reason = reason)) } diff --git a/core/src/main/scala/org/apache/spark/executor/ExecutorSource.scala b/core/src/main/scala/org/apache/spark/executor/ExecutorSource.scala index d16f4a1fc4e3b..e634566a067d4 100644 --- a/core/src/main/scala/org/apache/spark/executor/ExecutorSource.scala +++ b/core/src/main/scala/org/apache/spark/executor/ExecutorSource.scala @@ -29,7 +29,7 @@ import org.apache.spark.metrics.source.Source private[spark] class ExecutorSource(threadPool: ThreadPoolExecutor, executorId: String) extends Source { - private def fileStats(scheme: String) : Option[FileSystem.Statistics] = + private def fileStats(scheme: String): Option[FileSystem.Statistics] = FileSystem.getAllStatistics.asScala.find(s => s.getScheme.equals(scheme)) private def registerFileSystemStat[T]( diff --git a/core/src/main/scala/org/apache/spark/internal/Logging.scala b/core/src/main/scala/org/apache/spark/internal/Logging.scala index c7f2847731fcb..28e17389c69a5 100644 --- a/core/src/main/scala/org/apache/spark/internal/Logging.scala +++ b/core/src/main/scala/org/apache/spark/internal/Logging.scala @@ -32,7 +32,7 @@ trait Logging { // Make the log field transient so that objects with Logging can // be serialized and used on another machine - @transient private var log_ : Logger = null + @transient private var log_: Logger = null // Method to get the logger name for this object protected def logName = { diff --git a/core/src/main/scala/org/apache/spark/launcher/LauncherBackend.scala b/core/src/main/scala/org/apache/spark/launcher/LauncherBackend.scala index a5d41a1eeb479..2fe79713c1e26 100644 --- a/core/src/main/scala/org/apache/spark/launcher/LauncherBackend.scala +++ b/core/src/main/scala/org/apache/spark/launcher/LauncherBackend.scala @@ -86,7 +86,7 @@ private[spark] abstract class LauncherBackend { /** * Callback for when the launcher handle disconnects from this backend. */ - protected def onDisconnected() : Unit = { } + protected def onDisconnected(): Unit = { } private def fireStopRequest(): Unit = { val thread = LauncherBackend.threadFactory.newThread(new Runnable() { diff --git a/core/src/main/scala/org/apache/spark/partial/GroupedCountEvaluator.scala b/core/src/main/scala/org/apache/spark/partial/GroupedCountEvaluator.scala index d2b4187df5d50..ae169b76529a8 100644 --- a/core/src/main/scala/org/apache/spark/partial/GroupedCountEvaluator.scala +++ b/core/src/main/scala/org/apache/spark/partial/GroupedCountEvaluator.scala @@ -26,7 +26,7 @@ import org.apache.spark.util.collection.OpenHashMap /** * An ApproximateEvaluator for counts by key. Returns a map of key to confidence interval. */ -private[spark] class GroupedCountEvaluator[T : ClassTag](totalOutputs: Int, confidence: Double) +private[spark] class GroupedCountEvaluator[T: ClassTag](totalOutputs: Int, confidence: Double) extends ApproximateEvaluator[OpenHashMap[T, Long], Map[T, BoundedDouble]] { private var outputsMerged = 0 diff --git a/core/src/main/scala/org/apache/spark/partial/PartialResult.scala b/core/src/main/scala/org/apache/spark/partial/PartialResult.scala index 25cb7490aa9c9..44c7d26ef3e7e 100644 --- a/core/src/main/scala/org/apache/spark/partial/PartialResult.scala +++ b/core/src/main/scala/org/apache/spark/partial/PartialResult.scala @@ -77,9 +77,9 @@ class PartialResult[R](initialVal: R, isFinal: Boolean) { /** * Transform this PartialResult into a PartialResult of type T. */ - def map[T](f: R => T) : PartialResult[T] = { + def map[T](f: R => T): PartialResult[T] = { new PartialResult[T](f(initialVal), isFinal) { - override def getFinalValue() : T = synchronized { + override def getFinalValue(): T = synchronized { f(PartialResult.this.getFinalValue()) } override def onComplete(handler: T => Unit): PartialResult[T] = synchronized { @@ -90,7 +90,7 @@ class PartialResult[R](initialVal: R, isFinal: Boolean) { PartialResult.this.onFail(handler) } } - override def toString : String = synchronized { + override def toString: String = synchronized { PartialResult.this.getFinalValueInternal() match { case Some(value) => "(final: " + f(value) + ")" case None => "(partial: " + initialValue + ")" diff --git a/core/src/main/scala/org/apache/spark/rdd/CartesianRDD.scala b/core/src/main/scala/org/apache/spark/rdd/CartesianRDD.scala index 57108dcedcf0c..f6ffec4d19b22 100644 --- a/core/src/main/scala/org/apache/spark/rdd/CartesianRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/CartesianRDD.scala @@ -48,8 +48,8 @@ class CartesianPartition( private[spark] class CartesianRDD[T: ClassTag, U: ClassTag]( sc: SparkContext, - var rdd1 : RDD[T], - var rdd2 : RDD[U]) + var rdd1: RDD[T], + var rdd2: RDD[U]) extends RDD[(T, U)](sc, Nil) with Serializable { 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 2cba1febe8759..6e848dbeebb11 100644 --- a/core/src/main/scala/org/apache/spark/rdd/CoalescedRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/CoalescedRDD.scala @@ -379,7 +379,7 @@ private class DefaultPartitionCoalescer(val balanceSlack: Double = 0.10) } } - def getPartitions: Array[PartitionGroup] = groupArr.filter( pg => pg.numPartitions > 0).toArray + def getPartitions: Array[PartitionGroup] = groupArr.filter(pg => pg.numPartitions > 0).toArray /** * Runs the packing algorithm and returns an array of PartitionGroups that if possible are diff --git a/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala b/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala index 14331dfd0c987..fc3a29b95c6dc 100644 --- a/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala +++ b/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala @@ -134,7 +134,7 @@ class DoubleRDDFunctions(self: RDD[Double]) extends Logging with Serializable { }.reduce { (maxmin1, maxmin2) => (maxmin1._1.max(maxmin2._1), maxmin1._2.min(maxmin2._2)) } - if (min.isNaN || max.isNaN || max.isInfinity || min.isInfinity ) { + if (min.isNaN || max.isNaN || max.isInfinity || min.isInfinity) { throw new UnsupportedOperationException( "Histogram on either an empty RDD or RDD containing +/-infinity or NaN") } diff --git a/core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala b/core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala index 482875e6c1ac5..dce16eb996221 100644 --- a/core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala @@ -67,7 +67,7 @@ private[spark] class NewHadoopPartition( */ @DeveloperApi class NewHadoopRDD[K, V]( - sc : SparkContext, + sc: SparkContext, inputFormatClass: Class[_ <: InputFormat[K, V]], keyClass: Class[K], valueClass: Class[V], 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 a5992022d0832..f14e9cb9c011c 100644 --- a/core/src/main/scala/org/apache/spark/rdd/OrderedRDDFunctions.scala +++ b/core/src/main/scala/org/apache/spark/rdd/OrderedRDDFunctions.scala @@ -42,9 +42,9 @@ import org.apache.spark.internal.Logging * rdd.sortByKey() * }}} */ -class OrderedRDDFunctions[K : Ordering : ClassTag, +class OrderedRDDFunctions[K: Ordering: ClassTag, V: ClassTag, - P <: Product2[K, V] : ClassTag] @DeveloperApi() ( + P <: Product2[K, V]: ClassTag] @DeveloperApi() ( self: RDD[P]) extends Logging with Serializable { private val ordering = implicitly[Ordering[K]] 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 58762cc0838cd..9b38899e65a21 100644 --- a/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala +++ b/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala @@ -348,7 +348,7 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)]) map.put(pair._1, if (old == null) pair._2 else cleanedF(old, pair._2)) } Iterator(map) - } : Iterator[JHashMap[K, V]] + }: Iterator[JHashMap[K, V]] val mergeMaps = (m1: JHashMap[K, V], m2: JHashMap[K, V]) => { m2.asScala.foreach { pair => @@ -356,7 +356,7 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)]) m1.put(pair._1, if (old == null) pair._2 else cleanedF(old, pair._2)) } m1 - } : JHashMap[K, V] + }: JHashMap[K, V] self.mapPartitions(reducePartition).reduce(mergeMaps).asScala } @@ -546,7 +546,7 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)]) * (k, v2) is in `other`. Uses the given Partitioner to partition the output RDD. */ def join[W](other: RDD[(K, W)], partitioner: Partitioner): RDD[(K, (V, W))] = self.withScope { - this.cogroup(other, partitioner).flatMapValues( pair => + this.cogroup(other, partitioner).flatMapValues(pair => for (v <- pair._1.iterator; w <- pair._2.iterator) yield (v, w) ) } @@ -944,7 +944,7 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)]) buf += pair._2 } buf - } : Seq[V] + }: Seq[V] val res = self.context.runJob(self, process, Array(index)) res(0) case None => diff --git a/core/src/main/scala/org/apache/spark/rdd/PartitionPruningRDD.scala b/core/src/main/scala/org/apache/spark/rdd/PartitionPruningRDD.scala index ce75a16031a3f..19cafdac64982 100644 --- a/core/src/main/scala/org/apache/spark/rdd/PartitionPruningRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/PartitionPruningRDD.scala @@ -38,7 +38,7 @@ private[spark] class PruneDependency[T](rdd: RDD[T], partitionFilterFunc: Int => @transient val partitions: Array[Partition] = rdd.partitions .filter(s => partitionFilterFunc(s.index)).zipWithIndex - .map { case(split, idx) => new PartitionPruningRDDPartition(idx, split) : Partition } + .map { case(split, idx) => new PartitionPruningRDDPartition(idx, split): Partition } override def getParents(partitionId: Int): List[Int] = { List(partitions(partitionId).asInstanceOf[PartitionPruningRDDPartition].parentSplit.index) 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 2985c90119468..6ad6c9db6ca73 100644 --- a/core/src/main/scala/org/apache/spark/rdd/RDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/RDD.scala @@ -223,8 +223,8 @@ abstract class RDD[T: ClassTag]( // Our dependencies and partitions will be gotten by calling subclass's methods below, and will // be overwritten when we're checkpointed - private var dependencies_ : Seq[Dependency[_]] = null - @transient private var partitions_ : Array[Partition] = null + private var dependencies_: Seq[Dependency[_]] = null + @transient private var partitions_: Array[Partition] = null /** An Option holding our checkpoint RDD, if we are checkpointed */ private def checkpointRDD: Option[CheckpointRDD[T]] = checkpointData.flatMap(_.checkpointRDD) @@ -455,7 +455,7 @@ abstract class RDD[T: ClassTag]( position = position + 1 (position, t) } - } : Iterator[(Int, T)] + }: Iterator[(Int, T)] // include a shuffle step so that our upstream tasks are still distributed new CoalescedRDD( @@ -533,7 +533,7 @@ abstract class RDD[T: ClassTag]( * @return A random sub-sample of the RDD without replacement. */ private[spark] def randomSampleWithRange(lb: Double, ub: Double, seed: Long): RDD[T] = { - this.mapPartitionsWithIndex( { (index, partition) => + this.mapPartitionsWithIndex({ (index, partition) => val sampler = new BernoulliCellSampler[T](lb, ub) sampler.setSeed(seed + index) sampler.sample(partition) @@ -1834,7 +1834,7 @@ abstract class RDD[T: ClassTag]( override def toString: String = "%s%s[%d] at %s".format( Option(name).map(_ + " ").getOrElse(""), getClass.getSimpleName, id, getCreationSite) - def toJavaRDD() : JavaRDD[T] = { + def toJavaRDD(): JavaRDD[T] = { new JavaRDD(this)(elementClassTag) } } @@ -1876,7 +1876,7 @@ object RDD { keyWritableFactory.writableClass(kt), valueWritableFactory.writableClass(vt)) } - implicit def rddToOrderedRDDFunctions[K : Ordering : ClassTag, V: ClassTag](rdd: RDD[(K, V)]) + implicit def rddToOrderedRDDFunctions[K: Ordering: ClassTag, V: ClassTag](rdd: RDD[(K, V)]) : OrderedRDDFunctions[K, V, (K, V)] = { new OrderedRDDFunctions[K, V, (K, V)](rdd) } diff --git a/core/src/main/scala/org/apache/spark/rdd/SequenceFileRDDFunctions.scala b/core/src/main/scala/org/apache/spark/rdd/SequenceFileRDDFunctions.scala index 86a332790fb00..24aa81d9c5bc1 100644 --- a/core/src/main/scala/org/apache/spark/rdd/SequenceFileRDDFunctions.scala +++ b/core/src/main/scala/org/apache/spark/rdd/SequenceFileRDDFunctions.scala @@ -32,7 +32,7 @@ import org.apache.spark.internal.Logging * @note This can't be part of PairRDDFunctions because we need more implicit parameters to * convert our keys and values to Writable. */ -class SequenceFileRDDFunctions[K <% Writable: ClassTag, V <% Writable : ClassTag]( +class SequenceFileRDDFunctions[K <% Writable: ClassTag, V <% Writable: ClassTag]( self: RDD[(K, V)], _keyWritableClass: Class[_ <: Writable], _valueWritableClass: Class[_ <: Writable]) diff --git a/core/src/main/scala/org/apache/spark/rdd/WholeTextFileRDD.scala b/core/src/main/scala/org/apache/spark/rdd/WholeTextFileRDD.scala index 8e1baae796fc5..c31d755f65c73 100644 --- a/core/src/main/scala/org/apache/spark/rdd/WholeTextFileRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/WholeTextFileRDD.scala @@ -29,7 +29,7 @@ import org.apache.spark.input.WholeTextFileInputFormat * An RDD that reads a bunch of text files in, and each text file becomes one record. */ private[spark] class WholeTextFileRDD( - sc : SparkContext, + sc: SparkContext, inputFormatClass: Class[_ <: WholeTextFileInputFormat], keyClass: Class[Text], valueClass: Class[Text], diff --git a/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala b/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala index 3422a5f204b12..784d7444dd0f9 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala @@ -1077,7 +1077,7 @@ class DAGScheduler( s"(available: ${stage.isAvailable}," + s"available outputs: ${stage.numAvailableOutputs}," + s"partitions: ${stage.numPartitions})" - case stage : ResultStage => + case stage: ResultStage => s"Stage ${stage} is actually done; (partitions: ${stage.numPartitions})" } logDebug(debugString) diff --git a/core/src/main/scala/org/apache/spark/scheduler/EventLoggingListener.scala b/core/src/main/scala/org/apache/spark/scheduler/EventLoggingListener.scala index 35690b2783ad3..df523556f9f4f 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/EventLoggingListener.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/EventLoggingListener.scala @@ -49,7 +49,7 @@ import org.apache.spark.util.{JsonProtocol, Utils} */ private[spark] class EventLoggingListener( appId: String, - appAttemptId : Option[String], + appAttemptId: Option[String], logBaseDir: URI, sparkConf: SparkConf, hadoopConf: Configuration) @@ -57,7 +57,7 @@ private[spark] class EventLoggingListener( import EventLoggingListener._ - def this(appId: String, appAttemptId : Option[String], logBaseDir: URI, sparkConf: SparkConf) = + def this(appId: String, appAttemptId: Option[String], logBaseDir: URI, sparkConf: SparkConf) = this(appId, appAttemptId, logBaseDir, sparkConf, SparkHadoopUtil.get.newConfiguration(sparkConf)) diff --git a/core/src/main/scala/org/apache/spark/scheduler/Stage.scala b/core/src/main/scala/org/apache/spark/scheduler/Stage.scala index 290fd073caf27..d5723fc634b42 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/Stage.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/Stage.scala @@ -89,7 +89,7 @@ private[scheduler] abstract class Stage( */ val fetchFailedAttemptIds = new HashSet[Int] - private[scheduler] def clearFailures() : Unit = { + private[scheduler] def clearFailures(): Unit = { fetchFailedAttemptIds.clear() } diff --git a/core/src/main/scala/org/apache/spark/scheduler/TaskResultGetter.scala b/core/src/main/scala/org/apache/spark/scheduler/TaskResultGetter.scala index a284f7956cd31..f6f01f5770223 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/TaskResultGetter.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/TaskResultGetter.scala @@ -126,7 +126,7 @@ private[spark] class TaskResultGetter(sparkEnv: SparkEnv, scheduler: TaskSchedul def enqueueFailedTask(taskSetManager: TaskSetManager, tid: Long, taskState: TaskState, serializedData: ByteBuffer) { - var reason : TaskFailedReason = UnknownReason + var reason: TaskFailedReason = UnknownReason try { getTaskResultExecutor.execute(new Runnable { override def run(): Unit = Utils.logUncaughtExceptions { diff --git a/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala b/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala index 737b383631148..0e57a85c78ea5 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala @@ -275,7 +275,7 @@ private[spark] class TaskSchedulerImpl( maxLocality: TaskLocality, shuffledOffers: Seq[WorkerOffer], availableCpus: Array[Int], - tasks: IndexedSeq[ArrayBuffer[TaskDescription]]) : Boolean = { + tasks: IndexedSeq[ArrayBuffer[TaskDescription]]): Boolean = { var launchedTask = false // nodes and executors that are blacklisted for the entire application have already been // filtered out by this point diff --git a/core/src/main/scala/org/apache/spark/security/GroupMappingServiceProvider.scala b/core/src/main/scala/org/apache/spark/security/GroupMappingServiceProvider.scala index ea047a4f75d55..989e30505a694 100644 --- a/core/src/main/scala/org/apache/spark/security/GroupMappingServiceProvider.scala +++ b/core/src/main/scala/org/apache/spark/security/GroupMappingServiceProvider.scala @@ -33,6 +33,6 @@ trait GroupMappingServiceProvider { * @param userName User's Name * @return set of groups that the user belongs to. Empty in case of an invalid user. */ - def getGroups(userName : String) : Set[String] + def getGroups(userName: String): Set[String] } diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/AllRDDResource.scala b/core/src/main/scala/org/apache/spark/status/api/v1/AllRDDResource.scala index 1279b281ad8d8..cc2705c0663d4 100644 --- a/core/src/main/scala/org/apache/spark/status/api/v1/AllRDDResource.scala +++ b/core/src/main/scala/org/apache/spark/status/api/v1/AllRDDResource.scala @@ -77,7 +77,7 @@ private[spark] object AllRDDResource { if (rddInfo.storageLevel.useOffHeap) status.memUsedByRdd(rddId) else 0L), onHeapMemoryRemaining = status.onHeapMemRemaining, offHeapMemoryRemaining = status.offHeapMemRemaining - ) } ) + ) }) } else { None } @@ -90,7 +90,7 @@ private[spark] object AllRDDResource { diskUsed = block.diskSize, executors = locations ) - } ) + }) } else { None } diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/AllStagesResource.scala b/core/src/main/scala/org/apache/spark/status/api/v1/AllStagesResource.scala index 56028710ecc66..37c17842c3131 100644 --- a/core/src/main/scala/org/apache/spark/status/api/v1/AllStagesResource.scala +++ b/core/src/main/scala/org/apache/spark/status/api/v1/AllStagesResource.scala @@ -69,7 +69,7 @@ private[v1] object AllStagesResource { } val taskData = if (includeDetails) { - Some(stageUiData.taskData.map { case (k, v) => k -> convertTaskData(v) } ) + Some(stageUiData.taskData.map { case (k, v) => k -> convertTaskData(v) }) } else { None } diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/api.scala b/core/src/main/scala/org/apache/spark/status/api/v1/api.scala index 05948f2661056..897784bf9ae1f 100644 --- a/core/src/main/scala/org/apache/spark/status/api/v1/api.scala +++ b/core/src/main/scala/org/apache/spark/status/api/v1/api.scala @@ -46,15 +46,15 @@ class ApplicationAttemptInfo private[spark]( } class ExecutorStageSummary private[spark]( - val taskTime : Long, - val failedTasks : Int, - val succeededTasks : Int, - val inputBytes : Long, - val outputBytes : Long, - val shuffleRead : Long, - val shuffleWrite : Long, - val memoryBytesSpilled : Long, - val diskBytesSpilled : Long) + val taskTime: Long, + val failedTasks: Int, + val succeededTasks: Int, + val inputBytes: Long, + val outputBytes: Long, + val shuffleRead: Long, + val shuffleWrite: Long, + val memoryBytesSpilled: Long, + val diskBytesSpilled: Long) class ExecutorSummary private[spark]( val id: String, diff --git a/core/src/main/scala/org/apache/spark/storage/BlockManagerId.scala b/core/src/main/scala/org/apache/spark/storage/BlockManagerId.scala index 2c3da0ee85e06..5c7d535278577 100644 --- a/core/src/main/scala/org/apache/spark/storage/BlockManagerId.scala +++ b/core/src/main/scala/org/apache/spark/storage/BlockManagerId.scala @@ -35,10 +35,10 @@ import org.apache.spark.util.Utils */ @DeveloperApi class BlockManagerId private ( - private var executorId_ : String, - private var host_ : String, - private var port_ : Int, - private var topologyInfo_ : Option[String]) + private var executorId_: String, + private var host_: String, + private var port_: Int, + private var topologyInfo_: Option[String]) extends Externalizable { private def this() = this(null, null, 0, None) // For deserialization only diff --git a/core/src/main/scala/org/apache/spark/ui/JettyUtils.scala b/core/src/main/scala/org/apache/spark/ui/JettyUtils.scala index edf328b5ae538..3624ea42d59ab 100644 --- a/core/src/main/scala/org/apache/spark/ui/JettyUtils.scala +++ b/core/src/main/scala/org/apache/spark/ui/JettyUtils.scala @@ -236,10 +236,10 @@ private[spark] object JettyUtils extends Logging { def addFilters(handlers: Seq[ServletContextHandler], conf: SparkConf) { val filters: Array[String] = conf.get("spark.ui.filters", "").split(',').map(_.trim()) filters.foreach { - case filter : String => + case filter: String => if (!filter.isEmpty) { logInfo("Adding filter: " + filter) - val holder : FilterHolder = new FilterHolder() + val holder: FilterHolder = new FilterHolder() holder.setClassName(filter) // Get any parameters for each filter conf.get("spark." + filter + ".params", "").split(',').map(_.trim()).toSet.foreach { diff --git a/core/src/main/scala/org/apache/spark/ui/UIUtils.scala b/core/src/main/scala/org/apache/spark/ui/UIUtils.scala index ba798df13c95d..7e0143887cd2e 100644 --- a/core/src/main/scala/org/apache/spark/ui/UIUtils.scala +++ b/core/src/main/scala/org/apache/spark/ui/UIUtils.scala @@ -518,7 +518,7 @@ private[spark] object UIUtils extends Logging { param } - def getTimeZoneOffset() : Int = + def getTimeZoneOffset(): Int = TimeZone.getDefault().getOffset(System.currentTimeMillis()) / 1000 / 60 /** diff --git a/core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala b/core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala index cce7a7611b420..6b855199c1e55 100644 --- a/core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala +++ b/core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala @@ -275,7 +275,7 @@ private[ui] class AllJobsPage(parent: JobsTab) extends WebUIPage("") { desc = jobSortDesc ).table(page) } catch { - case e @ (_ : IllegalArgumentException | _ : IndexOutOfBoundsException) => + case e @ (_: IllegalArgumentException | _: IndexOutOfBoundsException) =>

Error while rendering job table:

diff --git a/core/src/main/scala/org/apache/spark/ui/jobs/ExecutorTable.scala b/core/src/main/scala/org/apache/spark/ui/jobs/ExecutorTable.scala
index 382a6f979f2e6..7513254caa74b 100644
--- a/core/src/main/scala/org/apache/spark/ui/jobs/ExecutorTable.scala
+++ b/core/src/main/scala/org/apache/spark/ui/jobs/ExecutorTable.scala
@@ -106,7 +106,7 @@ private[ui] class ExecutorTable(stageId: Int, stageAttemptId: Int, parent: Stage
     
   }
 
-  private def createExecutorTable() : Seq[Node] = {
+  private def createExecutorTable(): Seq[Node] = {
     // Make an executor-id -> address map
     val executorIdToAddress = mutable.HashMap[String, String]()
     listener.blockManagerIds.foreach { blockManagerId =>
diff --git a/core/src/main/scala/org/apache/spark/ui/jobs/StagePage.scala b/core/src/main/scala/org/apache/spark/ui/jobs/StagePage.scala
index 6b3dadc333316..385bde1fdddb4 100644
--- a/core/src/main/scala/org/apache/spark/ui/jobs/StagePage.scala
+++ b/core/src/main/scala/org/apache/spark/ui/jobs/StagePage.scala
@@ -307,7 +307,7 @@ private[ui] class StagePage(parent: StagesTab) extends WebUIPage("stage") {
         )
         (_taskTable, _taskTable.table(page))
       } catch {
-        case e @ (_ : IllegalArgumentException | _ : IndexOutOfBoundsException) =>
+        case e @ (_: IllegalArgumentException | _: IndexOutOfBoundsException) =>
           val errorMessage =
             

               
Error while rendering stage table:

diff --git a/core/src/main/scala/org/apache/spark/ui/jobs/StageTable.scala b/core/src/main/scala/org/apache/spark/ui/jobs/StageTable.scala
index a28daf7f90451..b9ca28fc81155 100644
--- a/core/src/main/scala/org/apache/spark/ui/jobs/StageTable.scala
+++ b/core/src/main/scala/org/apache/spark/ui/jobs/StageTable.scala
@@ -95,7 +95,7 @@ private[ui] class StageTableBase(
       parameterOtherTable
     ).table(page)
   } catch {
-    case e @ (_ : IllegalArgumentException | _ : IndexOutOfBoundsException) =>
+    case e @ (_: IllegalArgumentException | _: IndexOutOfBoundsException) =>
       

         
Error while rendering stage table:

         
diff --git a/core/src/main/scala/org/apache/spark/ui/jobs/UIData.scala b/core/src/main/scala/org/apache/spark/ui/jobs/UIData.scala
index 9448baac096dc..54b60433a7d17 100644
--- a/core/src/main/scala/org/apache/spark/ui/jobs/UIData.scala
+++ b/core/src/main/scala/org/apache/spark/ui/jobs/UIData.scala
@@ -31,21 +31,21 @@ import org.apache.spark.util.collection.OpenHashSet
 private[spark] object UIData {
 
   class ExecutorSummary {
-    var taskTime : Long = 0
-    var failedTasks : Int = 0
-    var succeededTasks : Int = 0
-    var reasonToNumKilled : Map[String, Int] = Map.empty
-    var inputBytes : Long = 0
-    var inputRecords : Long = 0
-    var outputBytes : Long = 0
-    var outputRecords : Long = 0
-    var shuffleRead : Long = 0
-    var shuffleReadRecords : Long = 0
-    var shuffleWrite : Long = 0
-    var shuffleWriteRecords : Long = 0
-    var memoryBytesSpilled : Long = 0
-    var diskBytesSpilled : Long = 0
-    var isBlacklisted : Int = 0
+    var taskTime: Long = 0
+    var failedTasks: Int = 0
+    var succeededTasks: Int = 0
+    var reasonToNumKilled: Map[String, Int] = Map.empty
+    var inputBytes: Long = 0
+    var inputRecords: Long = 0
+    var outputBytes: Long = 0
+    var outputRecords: Long = 0
+    var shuffleRead: Long = 0
+    var shuffleReadRecords: Long = 0
+    var shuffleWrite: Long = 0
+    var shuffleWriteRecords: Long = 0
+    var memoryBytesSpilled: Long = 0
+    var diskBytesSpilled: Long = 0
+    var isBlacklisted: Int = 0
   }
 
   class JobUIData(
@@ -91,7 +91,7 @@ private[spark] object UIData {
     var outputBytes: Long = _
     var outputRecords: Long = _
     var shuffleReadTotalBytes: Long = _
-    var shuffleReadRecords : Long = _
+    var shuffleReadRecords: Long = _
     var shuffleWriteBytes: Long = _
     var shuffleWriteRecords: Long = _
     var memoryBytesSpilled: Long = _
diff --git a/core/src/main/scala/org/apache/spark/ui/storage/RDDPage.scala b/core/src/main/scala/org/apache/spark/ui/storage/RDDPage.scala
index 317e0aa5ea25c..7a3556caee46e 100644
--- a/core/src/main/scala/org/apache/spark/ui/storage/RDDPage.scala
+++ b/core/src/main/scala/org/apache/spark/ui/storage/RDDPage.scala
@@ -77,7 +77,7 @@ private[ui] class RDDPage(parent: StorageTab) extends WebUIPage("rdd") {
         blockSortDesc)
       _blockTable.table(page)
     } catch {
-      case e @ (_ : IllegalArgumentException | _ : IndexOutOfBoundsException) =>
+      case e @ (_: IllegalArgumentException | _: IndexOutOfBoundsException) =>
         
{e.getMessage}

     }
 
diff --git a/core/src/main/scala/org/apache/spark/util/CollectionsUtils.scala b/core/src/main/scala/org/apache/spark/util/CollectionsUtils.scala
index 85da2842e8ddb..40a3e9caa13c0 100644
--- a/core/src/main/scala/org/apache/spark/util/CollectionsUtils.scala
+++ b/core/src/main/scala/org/apache/spark/util/CollectionsUtils.scala
@@ -22,7 +22,7 @@ import java.util
 import scala.reflect.{classTag, ClassTag}
 
 private[spark] object CollectionsUtils {
-  def makeBinarySearch[K : Ordering : ClassTag] : (Array[K], K) => Int = {
+  def makeBinarySearch[K: Ordering: ClassTag]: (Array[K], K) => Int = {
     // For primitive keys, we can use the natural ordering. Otherwise, use the Ordering comparator.
     classTag[K] match {
       case ClassTag.Float =>
diff --git a/core/src/main/scala/org/apache/spark/util/CompletionIterator.scala b/core/src/main/scala/org/apache/spark/util/CompletionIterator.scala
index 31d230d0fec8e..16dcc3ea19ac6 100644
--- a/core/src/main/scala/org/apache/spark/util/CompletionIterator.scala
+++ b/core/src/main/scala/org/apache/spark/util/CompletionIterator.scala
@@ -41,7 +41,7 @@ abstract class CompletionIterator[ +A, +I <: Iterator[A]](sub: I) extends Iterat
 }
 
 private[spark] object CompletionIterator {
-  def apply[A, I <: Iterator[A]](sub: I, completionFunction: => Unit) : CompletionIterator[A, I] = {
+  def apply[A, I <: Iterator[A]](sub: I, completionFunction: => Unit): CompletionIterator[A, I] = {
     new CompletionIterator[A, I](sub) {
       def completion(): Unit = completionFunction
     }
diff --git a/core/src/main/scala/org/apache/spark/util/ListenerBus.scala b/core/src/main/scala/org/apache/spark/util/ListenerBus.scala
index 76a56298aaebc..66d3de8576dee 100644
--- a/core/src/main/scala/org/apache/spark/util/ListenerBus.scala
+++ b/core/src/main/scala/org/apache/spark/util/ListenerBus.scala
@@ -97,7 +97,7 @@ private[spark] trait ListenerBus[L <: AnyRef, E] extends Logging {
    */
   protected def doPostEvent(listener: L, event: E): Unit
 
-  private[spark] def findListenersByClass[T <: L : ClassTag](): Seq[T] = {
+  private[spark] def findListenersByClass[T <: L: ClassTag](): Seq[T] = {
     val c = implicitly[ClassTag[T]].runtimeClass
     listeners.asScala.filter(_.getClass == c).map(_.asInstanceOf[T]).toSeq
   }
diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala
index bbb7999e2a144..2b7558fdda303 100644
--- a/core/src/main/scala/org/apache/spark/util/Utils.scala
+++ b/core/src/main/scala/org/apache/spark/util/Utils.scala
@@ -162,7 +162,7 @@ private[spark] object Utils extends Logging {
   }
 
   /** Deserialize a Long value (used for [[org.apache.spark.api.python.PythonPartitioner]]) */
-  def deserializeLongValue(bytes: Array[Byte]) : Long = {
+  def deserializeLongValue(bytes: Array[Byte]): Long = {
     // Note: we assume that we are given a Long value encoded in network (big-endian) byte order
     var result = bytes(7) & 0xFFL
     result = result + ((bytes(6) & 0xFFL) << 8)
@@ -2068,7 +2068,7 @@ private[spark] object Utils extends Logging {
    */
   def updateSparkConfigFromProperties(
       conf: SparkConf,
-      properties: Map[String, String]) : Unit = {
+      properties: Map[String, String]): Unit = {
     properties.filter { case (k, v) =>
       k.startsWith("spark.")
     }.foreach { case (k, v) =>
diff --git a/core/src/main/scala/org/apache/spark/util/collection/BitSet.scala b/core/src/main/scala/org/apache/spark/util/collection/BitSet.scala
index e63e0e3e1f68f..6f9ab78f0809c 100644
--- a/core/src/main/scala/org/apache/spark/util/collection/BitSet.scala
+++ b/core/src/main/scala/org/apache/spark/util/collection/BitSet.scala
@@ -75,7 +75,7 @@ class BitSet(numBits: Int) extends Serializable {
     assert(newBS.numWords >= numWords)
     assert(newBS.numWords >= other.numWords)
     var ind = 0
-    while( ind < smaller ) {
+    while(ind < smaller) {
       newBS.words(ind) = words(ind) & other.words(ind)
       ind += 1
     }
@@ -92,15 +92,15 @@ class BitSet(numBits: Int) extends Serializable {
     assert(newBS.numWords >= other.numWords)
     val smaller = math.min(numWords, other.numWords)
     var ind = 0
-    while( ind < smaller ) {
+    while(ind < smaller) {
       newBS.words(ind) = words(ind) | other.words(ind)
       ind += 1
     }
-    while( ind < numWords ) {
+    while(ind < numWords) {
       newBS.words(ind) = words(ind)
       ind += 1
     }
-    while( ind < other.numWords ) {
+    while(ind < other.numWords) {
       newBS.words(ind) = other.words(ind)
       ind += 1
     }
@@ -120,10 +120,10 @@ class BitSet(numBits: Int) extends Serializable {
       ind += 1
     }
     if (ind < numWords) {
-      Array.copy( words, ind, newBS.words, ind, numWords - ind )
+      Array.copy(words, ind, newBS.words, ind, numWords - ind)
     }
     if (ind < other.numWords) {
-      Array.copy( other.words, ind, newBS.words, ind, other.numWords - ind )
+      Array.copy(other.words, ind, newBS.words, ind, other.numWords - ind)
     }
     newBS
   }
@@ -141,7 +141,7 @@ class BitSet(numBits: Int) extends Serializable {
       ind += 1
     }
     if (ind < numWords) {
-      Array.copy( words, ind, newBS.words, ind, numWords - ind )
+      Array.copy(words, ind, newBS.words, ind, numWords - ind)
     }
     newBS
   }
diff --git a/core/src/main/scala/org/apache/spark/util/collection/OpenHashMap.scala b/core/src/main/scala/org/apache/spark/util/collection/OpenHashMap.scala
index 10ab0b3f89964..0d81f4f746bfd 100644
--- a/core/src/main/scala/org/apache/spark/util/collection/OpenHashMap.scala
+++ b/core/src/main/scala/org/apache/spark/util/collection/OpenHashMap.scala
@@ -30,7 +30,7 @@ import scala.reflect.ClassTag
  * distinguish between the 0/0.0/0L and non-exist value
  */
 private[spark]
-class OpenHashMap[K : ClassTag, @specialized(Long, Int, Double) V: ClassTag](
+class OpenHashMap[K: ClassTag, @specialized(Long, Int, Double) V: ClassTag](
     initialCapacity: Int)
   extends Iterable[(K, V)]
   with Serializable {
diff --git a/core/src/main/scala/org/apache/spark/util/collection/SortDataFormat.scala b/core/src/main/scala/org/apache/spark/util/collection/SortDataFormat.scala
index 9a7a5a4e74868..c6434e4580b17 100644
--- a/core/src/main/scala/org/apache/spark/util/collection/SortDataFormat.scala
+++ b/core/src/main/scala/org/apache/spark/util/collection/SortDataFormat.scala
@@ -83,7 +83,7 @@ abstract class SortDataFormat[K, Buffer] {
  *           when the keys and values are not the same type.
  */
 private[spark]
-class KVArraySortDataFormat[K, T <: AnyRef : ClassTag] extends SortDataFormat[K, Array[T]] {
+class KVArraySortDataFormat[K, T <: AnyRef: ClassTag] extends SortDataFormat[K, Array[T]] {
 
   override def getKey(data: Array[T], pos: Int): K = data(2 * pos).asInstanceOf[K]
 
diff --git a/examples/src/main/scala/org/apache/spark/examples/LocalALS.scala b/examples/src/main/scala/org/apache/spark/examples/LocalALS.scala
index 97aefac025e55..b8e28e42e0a0e 100644
--- a/examples/src/main/scala/org/apache/spark/examples/LocalALS.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/LocalALS.scala
@@ -55,7 +55,7 @@ object LocalALS {
     math.sqrt(sumSqs / (M.toDouble * U.toDouble))
   }
 
-  def updateMovie(i: Int, m: RealVector, us: Array[RealVector], R: RealMatrix) : RealVector = {
+  def updateMovie(i: Int, m: RealVector, us: Array[RealVector], R: RealMatrix): RealVector = {
     var XtX: RealMatrix = new Array2DRowRealMatrix(F, F)
     var Xty: RealVector = new ArrayRealVector(F)
     // For each user that rated the movie
@@ -74,7 +74,7 @@ object LocalALS {
     new CholeskyDecomposition(XtX).getSolver.solve(Xty)
   }
 
-  def updateUser(j: Int, u: RealVector, ms: Array[RealVector], R: RealMatrix) : RealVector = {
+  def updateUser(j: Int, u: RealVector, ms: Array[RealVector], R: RealMatrix): RealVector = {
     var XtX: RealMatrix = new Array2DRowRealMatrix(F, F)
     var Xty: RealVector = new ArrayRealVector(F)
     // For each movie that the user rated
diff --git a/examples/src/main/scala/org/apache/spark/examples/SparkALS.scala b/examples/src/main/scala/org/apache/spark/examples/SparkALS.scala
index a99ddd9fd37db..f3bc9daf16280 100644
--- a/examples/src/main/scala/org/apache/spark/examples/SparkALS.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/SparkALS.scala
@@ -57,7 +57,7 @@ object SparkALS {
     math.sqrt(sumSqs / (M.toDouble * U.toDouble))
   }
 
-  def update(i: Int, m: RealVector, us: Array[RealVector], R: RealMatrix) : RealVector = {
+  def update(i: Int, m: RealVector, us: Array[RealVector], R: RealMatrix): RealVector = {
     val U = us.length
     val F = us(0).getDimension
     var XtX: RealMatrix = new Array2DRowRealMatrix(F, F)
diff --git a/examples/src/main/scala/org/apache/spark/examples/graphx/AggregateMessagesExample.scala b/examples/src/main/scala/org/apache/spark/examples/graphx/AggregateMessagesExample.scala
index 8f8262db374b8..9f905ef66f38c 100644
--- a/examples/src/main/scala/org/apache/spark/examples/graphx/AggregateMessagesExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/graphx/AggregateMessagesExample.scala
@@ -46,7 +46,7 @@ object AggregateMessagesExample {
     // Create a graph with "age" as the vertex property.
     // Here we use a random graph for simplicity.
     val graph: Graph[Double, Int] =
-      GraphGenerators.logNormalGraph(sc, numVertices = 100).mapVertices( (id, _) => id.toDouble )
+      GraphGenerators.logNormalGraph(sc, numVertices = 100).mapVertices((id, _) => id.toDouble )
     // Compute the number of older followers and their total age
     val olderFollowers: VertexRDD[(Int, Double)] = graph.aggregateMessages[(Int, Double)](
       triplet => { // Map Function
@@ -60,7 +60,7 @@ object AggregateMessagesExample {
     )
     // Divide total age by number of older followers to get average age of older followers
     val avgAgeOfOlderFollowers: VertexRDD[Double] =
-      olderFollowers.mapValues( (id, value) =>
+      olderFollowers.mapValues((id, value) =>
         value match { case (count, totalAge) => totalAge / count } )
     // Display the results
     avgAgeOfOlderFollowers.collect.foreach(println(_))
diff --git a/examples/src/main/scala/org/apache/spark/examples/graphx/ComprehensiveExample.scala b/examples/src/main/scala/org/apache/spark/examples/graphx/ComprehensiveExample.scala
index 6598863bd2ea0..b0598d7500b2a 100644
--- a/examples/src/main/scala/org/apache/spark/examples/graphx/ComprehensiveExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/graphx/ComprehensiveExample.scala
@@ -47,7 +47,7 @@ object ComprehensiveExample {
     // $example on$
     // Load my user data and parse into tuples of user id and attribute list
     val users = (sc.textFile("data/graphx/users.txt")
-      .map(line => line.split(",")).map( parts => (parts.head.toLong, parts.tail) ))
+      .map(line => line.split(",")).map(parts => (parts.head.toLong, parts.tail)))
 
     // Parse the edge data which is already in userId -> userId format
     val followerGraph = GraphLoader.edgeListFile(sc, "data/graphx/followers.txt")
diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/RandomRDDGeneration.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/RandomRDDGeneration.scala
index 7ccbb5a0640cd..4f1813b9f128e 100644
--- a/examples/src/main/scala/org/apache/spark/examples/mllib/RandomRDDGeneration.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/mllib/RandomRDDGeneration.scala
@@ -44,13 +44,13 @@ object RandomRDDGeneration {
     println(s"Generated RDD of ${normalRDD.count()}" +
       " examples sampled from the standard normal distribution")
     println("  First 5 samples:")
-    normalRDD.take(5).foreach( x => println(s"    $x") )
+    normalRDD.take(5).foreach(x => println(s"    $x") )
 
     // Example: RandomRDDs.normalVectorRDD
     val normalVectorRDD = RandomRDDs.normalVectorRDD(sc, numRows = numExamples, numCols = 2)
     println(s"Generated RDD of ${normalVectorRDD.count()} examples of length-2 vectors.")
     println("  First 5 samples:")
-    normalVectorRDD.take(5).foreach( x => println(s"    $x") )
+    normalVectorRDD.take(5).foreach(x => println(s"    $x") )
 
     println()
 
diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/FlumeEventCount.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/FlumeEventCount.scala
index 91e52e4eff5a7..d4fb5f6b5d101 100644
--- a/examples/src/main/scala/org/apache/spark/examples/streaming/FlumeEventCount.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/streaming/FlumeEventCount.scala
@@ -61,7 +61,7 @@ object FlumeEventCount {
     val stream = FlumeUtils.createStream(ssc, host, port, StorageLevel.MEMORY_ONLY_SER_2)
 
     // Print out the count of events received from this server in each batch
-    stream.count().map(cnt => "Received " + cnt + " flume events." ).print()
+    stream.count().map(cnt => "Received " + cnt + " flume events.").print()
 
     ssc.start()
     ssc.awaitTermination()
diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/FlumePollingEventCount.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/FlumePollingEventCount.scala
index dd725d72c23ef..6780f638cade1 100644
--- a/examples/src/main/scala/org/apache/spark/examples/streaming/FlumePollingEventCount.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/streaming/FlumePollingEventCount.scala
@@ -58,7 +58,7 @@ object FlumePollingEventCount {
     val stream = FlumeUtils.createPollingStream(ssc, host, port)
 
     // Print out the count of events received from this server in each batch
-    stream.count().map(cnt => "Received " + cnt + " flume events." ).print()
+    stream.count().map(cnt => "Received " + cnt + " flume events.").print()
 
     ssc.start()
     ssc.awaitTermination()
diff --git a/external/kafka-0-8/src/main/scala/org/apache/spark/streaming/kafka/KafkaTestUtils.scala b/external/kafka-0-8/src/main/scala/org/apache/spark/streaming/kafka/KafkaTestUtils.scala
index ef1968585be60..f96fe6666c749 100644
--- a/external/kafka-0-8/src/main/scala/org/apache/spark/streaming/kafka/KafkaTestUtils.scala
+++ b/external/kafka-0-8/src/main/scala/org/apache/spark/streaming/kafka/KafkaTestUtils.scala
@@ -188,7 +188,7 @@ private[kafka] class KafkaTestUtils extends Logging {
   /** Send the array of messages to the Kafka broker */
   def sendMessages(topic: String, messages: Array[String]): Unit = {
     producer = new Producer[String, String](new ProducerConfig(producerConfiguration))
-    producer.send(messages.map { new KeyedMessage[String, String](topic, _ ) }: _*)
+    producer.send(messages.map { new KeyedMessage[String, String](topic, _) }: _*)
     producer.close()
     producer = null
   }
diff --git a/graphx/src/main/scala/org/apache/spark/graphx/GraphOps.scala b/graphx/src/main/scala/org/apache/spark/graphx/GraphOps.scala
index 475bccf9bfc76..a24c4ff6184e5 100644
--- a/graphx/src/main/scala/org/apache/spark/graphx/GraphOps.scala
+++ b/graphx/src/main/scala/org/apache/spark/graphx/GraphOps.scala
@@ -397,7 +397,7 @@ class GraphOps[VD: ClassTag, ED: ClassTag](graph: Graph[VD, ED]) extends Seriali
    * that all random walks are started relative to the source vertices
    */
   def staticParallelPersonalizedPageRank(sources: Array[VertexId], numIter: Int,
-    resetProb: Double = 0.15) : Graph[Vector, Double] = {
+    resetProb: Double = 0.15): Graph[Vector, Double] = {
     PageRank.runParallelPersonalizedPageRank(graph, numIter, resetProb, sources)
   }
 
diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/GraphImpl.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/GraphImpl.scala
index 5d2a53782b55d..0cbca72721a68 100644
--- a/graphx/src/main/scala/org/apache/spark/graphx/impl/GraphImpl.scala
+++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/GraphImpl.scala
@@ -103,7 +103,7 @@ class GraphImpl[VD: ClassTag, ED: ClassTag] protected (
       (part, (e.srcId, e.dstId, e.attr))
     }
       .partitionBy(new HashPartitioner(numPartitions))
-      .mapPartitionsWithIndex( { (pid, iter) =>
+      .mapPartitionsWithIndex({ (pid, iter) =>
         val builder = new EdgePartitionBuilder[ED, VD]()(edTag, vdTag)
         iter.foreach { message =>
           val data = message._2
diff --git a/graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala b/graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala
index fd7b7f7c1c487..d9fe596d3e4a9 100644
--- a/graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala
+++ b/graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala
@@ -122,7 +122,7 @@ object PageRank extends Logging {
       // Associate the degree with each vertex
       .outerJoinVertices(graph.outDegrees) { (vid, vdata, deg) => deg.getOrElse(0) }
       // Set the weight on the edges based on the degree
-      .mapTriplets( e => 1.0 / e.srcAttr, TripletFields.Src )
+      .mapTriplets(e => 1.0 / e.srcAttr, TripletFields.Src)
       // Set the vertex attributes to the initial pagerank values
       .mapVertices { (id, attr) =>
         if (!(id != src && personalized)) 1.0 else 0.0
@@ -227,7 +227,7 @@ object PageRank extends Logging {
       // and adding start nodes back in with activation resetProb
       val rankUpdates = rankGraph.aggregateMessages[BV[Double]](
         ctx => ctx.sendToDst(ctx.srcAttr *:* ctx.attr),
-        (a : BV[Double], b : BV[Double]) => a +:+ b, TripletFields.Src)
+        (a: BV[Double], b: BV[Double]) => a +:+ b, TripletFields.Src)
 
       rankGraph = rankGraph.outerJoinVertices(rankUpdates) {
         (vid, oldRank, msgSumOpt) =>
@@ -310,7 +310,7 @@ object PageRank extends Logging {
         (vid, vdata, deg) => deg.getOrElse(0)
       }
       // Set the weight on the edges based on the degree
-      .mapTriplets( e => 1.0 / e.srcAttr )
+      .mapTriplets(e => 1.0 / e.srcAttr)
       // Set the vertex attributes to (initialPR, delta = 0)
       .mapVertices { (id, attr) =>
         if (id == src) (0.0, Double.NegativeInfinity) else (0.0, 0.0)
diff --git a/graphx/src/main/scala/org/apache/spark/graphx/util/GraphGenerators.scala b/graphx/src/main/scala/org/apache/spark/graphx/util/GraphGenerators.scala
index 2b3e5f98c4fe5..079acf2d45737 100644
--- a/graphx/src/main/scala/org/apache/spark/graphx/util/GraphGenerators.scala
+++ b/graphx/src/main/scala/org/apache/spark/graphx/util/GraphGenerators.scala
@@ -241,12 +241,12 @@ object GraphGenerators extends Logging {
     def sub2ind(r: Int, c: Int): VertexId = r * cols + c
 
     val vertices: RDD[(VertexId, (Int, Int))] = sc.parallelize(0 until rows).flatMap { r =>
-      (0 until cols).map( c => (sub2ind(r, c), (r, c)) )
+      (0 until cols).map(c => (sub2ind(r, c), (r, c)))
     }
     val edges: RDD[Edge[Double]] =
       vertices.flatMap{ case (vid, (r, c)) =>
-        (if (r + 1 < rows) { Seq( (sub2ind(r, c), sub2ind(r + 1, c))) } else { Seq.empty }) ++
-        (if (c + 1 < cols) { Seq( (sub2ind(r, c), sub2ind(r, c + 1))) } else { Seq.empty })
+        (if (r + 1 < rows) { Seq((sub2ind(r, c), sub2ind(r + 1, c))) } else { Seq.empty }) ++
+        (if (c + 1 < cols) { Seq((sub2ind(r, c), sub2ind(r, c + 1))) } else { Seq.empty })
       }.map{ case (src, dst) => Edge(src, dst, 1.0) }
     Graph(vertices, edges)
   } // end of gridGraph
diff --git a/mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala b/mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala
index 3fbc0958a0f11..3fe0d7c391f24 100644
--- a/mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala
+++ b/mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala
@@ -435,7 +435,7 @@ object Vectors {
  * A dense vector represented by a value array.
  */
 @Since("2.0.0")
-class DenseVector @Since("2.0.0") ( @Since("2.0.0") val values: Array[Double]) extends Vector {
+class DenseVector @Since("2.0.0") (@Since("2.0.0") val values: Array[Double]) extends Vector {
 
   override def size: Int = values.length
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/ann/LossFunction.scala b/mllib/src/main/scala/org/apache/spark/ml/ann/LossFunction.scala
index 3aea568cd6527..0f1bf6e9d8818 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/ann/LossFunction.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/ann/LossFunction.scala
@@ -119,6 +119,6 @@ private[ann] class SoftmaxLayerModelWithCrossEntropyLoss extends LayerModel with
 
   override def loss(output: BDM[Double], target: BDM[Double], delta: BDM[Double]): Double = {
     ApplyInPlace(output, target, delta, (o: Double, t: Double) => o - t)
-    -Bsum( target *:* brzlog(output)) / output.cols
+    -Bsum(target *:* brzlog(output)) / output.cols
   }
 }
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
index 4b44878784c90..08e4376cb0fc1 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
@@ -507,7 +507,7 @@ private class VectorAttributeRewriter(
     }
     val otherCols = dataset.columns.filter(_ != vectorCol).map(dataset.col)
     val rewrittenCol = dataset.col(vectorCol).as(vectorCol, metadata)
-    dataset.select(otherCols :+ rewrittenCol : _*)
+    dataset.select(otherCols:+ rewrittenCol: _*)
   }
 
   override def transformSchema(schema: StructType): StructType = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/r/KSTestWrapper.scala b/mllib/src/main/scala/org/apache/spark/ml/r/KSTestWrapper.scala
index 21531eb057ad3..a6cedc961473f 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/r/KSTestWrapper.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/r/KSTestWrapper.scala
@@ -49,7 +49,7 @@ private[r] object KSTestWrapper {
       case Row(feature: Double) => feature
     }
 
-    val ksTestResult = kolmogorovSmirnovTest(rddData, distName, distParams : _*)
+    val ksTestResult = kolmogorovSmirnovTest(rddData, distName, distParams: _*)
 
     new KSTestWrapper(ksTestResult, distName, distParams)
   }
diff --git a/mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala b/mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala
index 0d6e9034e5ce4..135095ddd4e4c 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala
@@ -198,7 +198,7 @@ private[ml] object TreeEnsembleModel {
    *                     If -1, then numFeatures is set based on the max feature index in all trees.
    * @return  Feature importance values, of length numFeatures.
    */
-  def featureImportances[M <: DecisionTreeModel : ClassTag](tree: M, numFeatures: Int): Vector = {
+  def featureImportances[M <: DecisionTreeModel: ClassTag](tree: M, numFeatures: Int): Vector = {
     featureImportances(Array(tree), numFeatures)
   }
 
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
index b32d3f252ae59..c443c18343912 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
@@ -590,7 +590,7 @@ private[python] class PythonMLLibAPI extends Serializable {
       data: JavaRDD[java.util.ArrayList[java.util.ArrayList[Any]]],
       minSupport: Double,
       maxPatternLength: Int,
-      localProjDBSize: Int ): PrefixSpanModelWrapper = {
+      localProjDBSize: Int): PrefixSpanModelWrapper = {
     val prefixSpan = new PrefixSpan()
       .setMinSupport(minSupport)
       .setMaxPatternLength(maxPatternLength)
diff --git a/resource-managers/mesos/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerUtils.scala b/resource-managers/mesos/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerUtils.scala
index 062ed1f93fa52..2737688267451 100644
--- a/resource-managers/mesos/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerUtils.scala
+++ b/resource-managers/mesos/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerUtils.scala
@@ -447,11 +447,11 @@ trait MesosSchedulerUtils extends Logging {
    * @return the ono-zero values of the ports
    */
   def nonZeroPortValuesFromConfig(conf: SparkConf): List[Long] = {
-    managedPortNames.map(conf.getLong(_, 0)).filter( _ != 0)
+    managedPortNames.map(conf.getLong(_, 0)).filter(_ != 0)
   }
 
   /** Creates a mesos resource for a specific port number. */
-  private def createResourcesFromPorts(portsAndRoles: List[(Long, String)]) : List[Resource] = {
+  private def createResourcesFromPorts(portsAndRoles: List[(Long, String)]): List[Resource] = {
     portsAndRoles.flatMap{ case (port, role) =>
       createMesosPortResource(List((port, port)), Some(role))}
   }
diff --git a/scalastyle-config.xml b/scalastyle-config.xml
index 0a4073b03957c..64b04d2c63723 100644
--- a/scalastyle-config.xml
+++ b/scalastyle-config.xml
@@ -46,7 +46,7 @@ This file is divided into 3 sections:
 
   
 
-  
+  
     
        
     
-      COMMA
+      COLON, COMMA, RPAREN
+    
+  
+
+  
+    
+      LPAREN
     
   
 
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/Encoders.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/Encoders.scala
index 0b95a8821b05a..de04ced831002 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/Encoders.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/Encoders.scala
@@ -272,7 +272,7 @@ object Encoders {
    * An encoder for Scala's product type (tuples, case classes, etc).
    * @since 2.0.0
    */
-  def product[T <: Product : TypeTag]: Encoder[T] = ExpressionEncoder()
+  def product[T <: Product: TypeTag]: Encoder[T] = ExpressionEncoder()
 
   /**
    * An encoder for Scala's primitive int type.
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala
index d580cf4d3391c..b32f99a6cbf7a 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala
@@ -60,7 +60,7 @@ object ScalaReflection extends ScalaReflection {
    * Unlike `schemaFor`, this function doesn't do any massaging of types into the Spark SQL type
    * system.  As a result, ObjectType will be returned for things like boxed Integers
    */
-  def dataTypeFor[T : TypeTag]: DataType = dataTypeFor(localTypeOf[T])
+  def dataTypeFor[T: TypeTag]: DataType = dataTypeFor(localTypeOf[T])
 
   private def dataTypeFor(tpe: `Type`): DataType = ScalaReflectionLock.synchronized {
     tpe match {
@@ -131,7 +131,7 @@ object ScalaReflection extends ScalaReflection {
    * from ordinal 0 (since there are no names to map to).  The actual location can be moved by
    * calling resolve/bind with a new schema.
    */
-  def deserializerFor[T : TypeTag]: Expression = {
+  def deserializerFor[T: TypeTag]: Expression = {
     val tpe = localTypeOf[T]
     val clsName = getClassNameFromType(tpe)
     val walkedTypePath = s"""- root class: "$clsName"""" :: Nil
@@ -414,7 +414,7 @@ object ScalaReflection extends ScalaReflection {
    *  * the element type of [[Array]] or [[Seq]]: `array element class: "abc.xyz.MyClass"`
    *  * the field of [[Product]]: `field (class: "abc.xyz.MyClass", name: "myField")`
    */
-  def serializerFor[T : TypeTag](inputObject: Expression): CreateNamedStruct = {
+  def serializerFor[T: TypeTag](inputObject: Expression): CreateNamedStruct = {
     val tpe = localTypeOf[T]
     val clsName = getClassNameFromType(tpe)
     val walkedTypePath = s"""- root class: "$clsName"""" :: Nil
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
index 53536496d0457..11d80f64b34ac 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
@@ -151,7 +151,7 @@ class Analyzer(
       ResolveInlineTables(conf) ::
       ResolveTimeZone(conf) ::
       TypeCoercion.typeCoercionRules ++
-      extendedResolutionRules : _*),
+      extendedResolutionRules: _*),
     Batch("Post-Hoc Resolution", Once, postHocResolutionRules: _*),
     Batch("View", Once,
       AliasViewChild(conf)),
@@ -182,7 +182,7 @@ class Analyzer(
 
     def substituteCTE(plan: LogicalPlan, cteRelations: Seq[(String, LogicalPlan)]): LogicalPlan = {
       plan transformDown {
-        case u : UnresolvedRelation =>
+        case u: UnresolvedRelation =>
           cteRelations.find(x => resolver(x._1, u.tableIdentifier.table))
             .map(_._2).getOrElse(u)
         case other =>
@@ -917,7 +917,7 @@ class Analyzer(
           })
         case c: CreateNamedStruct if containsStar(c.valExprs) =>
           val newChildren = c.children.grouped(2).flatMap {
-            case Seq(k, s : Star) => CreateStruct(s.expand(child, resolver)).children
+            case Seq(k, s: Star) => CreateStruct(s.expand(child, resolver)).children
             case kv => kv
           }
           c.copy(children = newChildren.toList )
@@ -2061,7 +2061,7 @@ class Analyzer(
         joinedCols ++
           lUniqueOutput.map(_.withNullability(true)) ++
           rUniqueOutput.map(_.withNullability(true))
-      case _ : InnerLike =>
+      case _: InnerLike =>
         leftKeys ++ lUniqueOutput ++ rUniqueOutput
       case _ =>
         sys.error("Unsupported natural join type " + joinType)
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala
index f4b3e86052d8e..35f9f0137af68 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala
@@ -525,7 +525,7 @@ object FunctionRegistry {
         val f = constructors.find(_.getParameterTypes.toSeq == params).getOrElse {
           throw new AnalysisException(s"Invalid number of arguments for function $name")
         }
-        Try(f.newInstance(expressions : _*).asInstanceOf[Expression]) match {
+        Try(f.newInstance(expressions: _*).asInstanceOf[Expression]) match {
           case Success(e) => e
           case Failure(e) =>
             // the exception is an invocation exception. To get a meaningful message, we need the
@@ -561,7 +561,7 @@ object FunctionRegistry {
   /**
    * Creates an [[ExpressionInfo]] for the function as defined by expression T using the given name.
    */
-  private def expressionInfo[T <: Expression : ClassTag](name: String): ExpressionInfo = {
+  private def expressionInfo[T <: Expression: ClassTag](name: String): ExpressionInfo = {
     val clazz = scala.reflect.classTag[T].runtimeClass
     val df = clazz.getAnnotation(classOf[ExpressionDescription])
     if (df != null) {
@@ -571,7 +571,7 @@ object FunctionRegistry {
     }
   }
 
-  private def expressionGeneratorOuter[T <: Generator : ClassTag](name: String)
+  private def expressionGeneratorOuter[T <: Generator: ClassTag](name: String)
     : (String, (ExpressionInfo, FunctionBuilder)) = {
     val (_, (info, generatorBuilder)) = expression[T](name)
     val outerBuilder = (args: Seq[Expression]) => {
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala
index f6792569b704e..c602f47472e8f 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala
@@ -63,9 +63,9 @@ package object dsl {
   trait ImplicitOperators {
     def expr: Expression
 
-    def unary_- : Expression = UnaryMinus(expr)
-    def unary_! : Predicate = Not(expr)
-    def unary_~ : Expression = BitwiseNot(expr)
+    def unary_-: Expression = UnaryMinus(expr)
+    def unary_!: Predicate = Not(expr)
+    def unary_~: Expression = BitwiseNot(expr)
 
     def + (other: Expression): Expression = Add(expr, other)
     def - (other: Expression): Expression = Subtract(expr, other)
@@ -144,7 +144,7 @@ package object dsl {
       // Note that if we make ExpressionConversions an object rather than a trait, we can
       // then make this a value class to avoid the small penalty of runtime instantiation.
       def $(args: Any*): analysis.UnresolvedAttribute = {
-        analysis.UnresolvedAttribute(sc.s(args : _*))
+        analysis.UnresolvedAttribute(sc.s(args: _*))
       }
     }
 
@@ -298,11 +298,11 @@ package object dsl {
 
       def where(condition: Expression): LogicalPlan = Filter(condition, logicalPlan)
 
-      def filter[T : Encoder](func: T => Boolean): LogicalPlan = TypedFilter(func, logicalPlan)
+      def filter[T: Encoder](func: T => Boolean): LogicalPlan = TypedFilter(func, logicalPlan)
 
-      def serialize[T : Encoder]: LogicalPlan = CatalystSerde.serialize[T](logicalPlan)
+      def serialize[T: Encoder]: LogicalPlan = CatalystSerde.serialize[T](logicalPlan)
 
-      def deserialize[T : Encoder]: LogicalPlan = CatalystSerde.deserialize[T](logicalPlan)
+      def deserialize[T: Encoder]: LogicalPlan = CatalystSerde.deserialize[T](logicalPlan)
 
       def limit(limitExpr: Expression): LogicalPlan = Limit(limitExpr, logicalPlan)
 
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoder.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoder.scala
index efc2882f0a3d3..22cbb8189f5f1 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoder.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoder.scala
@@ -43,7 +43,7 @@ import org.apache.spark.util.Utils
  *    to the name `value`.
  */
 object ExpressionEncoder {
-  def apply[T : TypeTag](): ExpressionEncoder[T] = {
+  def apply[T: TypeTag](): ExpressionEncoder[T] = {
     // We convert the not-serializable TypeTag into StructType and ClassTag.
     val mirror = ScalaReflection.mirror
     val tpe = typeTag[T].in(mirror).tpe
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/package.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/package.scala
index 59f7969e56144..ce9ebf98bf5e3 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/package.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/package.scala
@@ -26,7 +26,7 @@ package object encoders {
    * references from a specific schema.)  This requirement allows us to preserve whether a given
    * object type is being bound by name or by ordinal when doing resolution.
    */
-  def encoderFor[A : Encoder]: ExpressionEncoder[A] = implicitly[Encoder[A]] match {
+  def encoderFor[A: Encoder]: ExpressionEncoder[A] = implicitly[Encoder[A]] match {
     case e: ExpressionEncoder[A] =>
       e.assertUnresolved()
       e
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/CallMethodViaReflection.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/CallMethodViaReflection.scala
index 4859e0c537610..ee0a22123a3e3 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/CallMethodViaReflection.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/CallMethodViaReflection.scala
@@ -92,7 +92,7 @@ case class CallMethodViaReflection(children: Seq[Expression])
       }
       i += 1
     }
-    val ret = method.invoke(null, buffer : _*)
+    val ret = method.invoke(null, buffer: _*)
     UTF8String.fromString(String.valueOf(ret))
   }
 
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Percentile.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Percentile.scala
index 8433a93ea3032..549ce395cefb2 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Percentile.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Percentile.scala
@@ -58,7 +58,7 @@ import org.apache.spark.SparkException
 case class Percentile(
     child: Expression,
     percentageExpression: Expression,
-    frequencyExpression : Expression,
+    frequencyExpression: Expression,
     mutableAggBufferOffset: Int = 0,
     inputAggBufferOffset: Int = 0)
   extends TypedImperativeAggregate[OpenHashMap[AnyRef, Long]] with ImplicitCastInputTypes {
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala
index eaeaf08c37b4e..d079385e1eb1f 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala
@@ -155,7 +155,7 @@ object Literal {
     Literal(CatalystTypeConverters.convertToCatalyst(v), dataType)
   }
 
-  def create[T : TypeTag](v: T): Literal = Try {
+  def create[T: TypeTag](v: T): Literal = Try {
     val ScalaReflection.Schema(dataType, _) = ScalaReflection.schemaFor[T]
     val convert = CatalystTypeConverters.createToCatalystConverter(dataType)
     Literal(convert(v), dataType)
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
index 3fc4bb7041636..3d9de69318220 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
@@ -67,7 +67,7 @@ case class AssertTrue(child: Expression) extends UnaryExpression with ImplicitCa
 
   private val errMsg = s"'${child.simpleString}' is not true!"
 
-  override def eval(input: InternalRow) : Any = {
+  override def eval(input: InternalRow): Any = {
     val v = child.eval(input)
     if (v == null || java.lang.Boolean.FALSE.equals(v)) {
       throw new RuntimeException(errMsg)
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala
index 4b651836ff4d2..fa2b10e2d8235 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala
@@ -182,7 +182,7 @@ case class Invoke(
     dataType: DataType,
     arguments: Seq[Expression] = Nil,
     propagateNull: Boolean = true,
-    returnNullable : Boolean = true) extends InvokeLike {
+    returnNullable: Boolean = true) extends InvokeLike {
 
   override def nullable: Boolean = targetObject.nullable || needNullCheck || returnNullable
   override def children: Seq[Expression] = targetObject +: arguments
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala
index 83fdcfce9c3bd..fd2e06d9fb6fc 100755
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala
@@ -57,7 +57,7 @@ case class Concat(children: Seq[Expression]) extends Expression with ImplicitCas
 
   override def eval(input: InternalRow): Any = {
     val inputs = children.map(_.eval(input).asInstanceOf[UTF8String])
-    UTF8String.concat(inputs : _*)
+    UTF8String.concat(inputs: _*)
   }
 
   override protected def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
@@ -117,7 +117,7 @@ case class ConcatWs(children: Seq[Expression])
         case null => Iterator(null.asInstanceOf[UTF8String])
       }
     }
-    UTF8String.concatWs(flatInputs.head, flatInputs.tail : _*)
+    UTF8String.concatWs(flatInputs.head, flatInputs.tail: _*)
   }
 
   override protected def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
@@ -1640,7 +1640,7 @@ case class FormatNumber(x: Expression, d: Expression)
 
       def typeHelper(p: String): String = {
         x.dataType match {
-          case _ : DecimalType => s"""$p.toJavaBigDecimal()"""
+          case _: DecimalType => s"""$p.toJavaBigDecimal()"""
           case _ => s"$p"
         }
       }
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/CostBasedJoinReorder.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/CostBasedJoinReorder.scala
index 3a7543e2141e9..73e0d12c25576 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/CostBasedJoinReorder.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/CostBasedJoinReorder.scala
@@ -433,7 +433,7 @@ object JoinReorderDPFilters extends PredicateHelper {
   def starJoinFilter(
       oneSideJoinPlan: Set[Int],
       otherSideJoinPlan: Set[Int],
-      filters: JoinGraphInfo) : Boolean = {
+      filters: JoinGraphInfo): Boolean = {
     val starJoins = filters.starJoins
     val nonStarJoins = filters.nonStarJoins
     val join = oneSideJoinPlan.union(otherSideJoinPlan)
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala
index 66b8ca62e5e4c..a97575ff1856f 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala
@@ -361,7 +361,7 @@ object SimplifyConditionals extends Rule[LogicalPlan] with PredicateHelper {
         // a branc with a TRue condition eliminates all following branches,
         // these branches can be pruned away
         val (h, t) = branches.span(_._1 != TrueLiteral)
-        CaseWhen( h :+ t.head, None)
+        CaseWhen(h :+ t.head, None)
     }
   }
 }
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala
index 2a3e07aebe709..d3f0e796098fd 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala
@@ -44,7 +44,7 @@ import org.apache.spark.sql.types._
 object RewritePredicateSubquery extends Rule[LogicalPlan] with PredicateHelper {
   private def getValueExpression(e: Expression): Seq[Expression] = {
     e match {
-      case cns : CreateNamedStruct => cns.valExprs
+      case cns: CreateNamedStruct => cns.valExprs
       case expr => Seq(expr)
     }
   }
@@ -268,7 +268,7 @@ object RewriteCorrelatedScalarSubquery extends Rule[LogicalPlan] {
    * Statically evaluate an expression containing zero or more placeholders, given a set
    * of bindings for placeholder values.
    */
-  private def evalExpr(expr: Expression, bindings: Map[ExprId, Option[Any]]) : Option[Any] = {
+  private def evalExpr(expr: Expression, bindings: Map[ExprId, Option[Any]]): Option[Any] = {
     val rewrittenExpr = expr transform {
       case r: AttributeReference =>
         bindings(r.exprId) match {
@@ -282,7 +282,7 @@ object RewriteCorrelatedScalarSubquery extends Rule[LogicalPlan] {
   /**
    * Statically evaluate an expression containing one or more aggregates on an empty input.
    */
-  private def evalAggOnZeroTups(expr: Expression) : Option[Any] = {
+  private def evalAggOnZeroTups(expr: Expression): Option[Any] = {
     // AggregateExpressions are Unevaluable, so we need to replace all aggregates
     // in the expression with the value they would return for zero input tuples.
     // Also replace attribute refs (for example, for grouping columns) with NULL.
@@ -302,11 +302,11 @@ object RewriteCorrelatedScalarSubquery extends Rule[LogicalPlan] {
    * [[org.apache.spark.sql.catalyst.analysis.CheckAnalysis]]. If the checks in
    * CheckAnalysis become less restrictive, this method will need to change.
    */
-  private def evalSubqueryOnZeroTups(plan: LogicalPlan) : Option[Any] = {
+  private def evalSubqueryOnZeroTups(plan: LogicalPlan): Option[Any] = {
     // Inputs to this method will start with a chain of zero or more SubqueryAlias
     // and Project operators, followed by an optional Filter, followed by an
     // Aggregate. Traverse the operators recursively.
-    def evalPlan(lp : LogicalPlan) : Map[ExprId, Option[Any]] = lp match {
+    def evalPlan(lp: LogicalPlan): Map[ExprId, Option[Any]] = lp match {
       case SubqueryAlias(_, child) => evalPlan(child)
       case Filter(condition, child) =>
         val bindings = evalPlan(child)
@@ -349,7 +349,7 @@ object RewriteCorrelatedScalarSubquery extends Rule[LogicalPlan] {
    * (first part of returned value), the HAVING clause of the innermost query block
    * (optional second part) and the parts below the HAVING CLAUSE (third part).
    */
-  private def splitSubquery(plan: LogicalPlan) : (Seq[LogicalPlan], Option[Filter], Aggregate) = {
+  private def splitSubquery(plan: LogicalPlan): (Seq[LogicalPlan], Option[Filter], Aggregate) = {
     val topPart = ArrayBuffer.empty[LogicalPlan]
     var bottomPart: LogicalPlan = plan
     while (true) {
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/LegacyTypeStringParser.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/LegacyTypeStringParser.scala
index 60d7361242c69..98f6faede8537 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/LegacyTypeStringParser.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/LegacyTypeStringParser.scala
@@ -28,7 +28,7 @@ import org.apache.spark.sql.types._
 object LegacyTypeStringParser extends RegexParsers {
 
   protected lazy val primitiveType: Parser[DataType] =
-    ( "StringType" ^^^ StringType
+    ("StringType" ^^^ StringType
       | "FloatType" ^^^ FloatType
       | "IntegerType" ^^^ IntegerType
       | "ByteType" ^^^ ByteType
@@ -65,7 +65,7 @@ object LegacyTypeStringParser extends RegexParsers {
     }
 
   protected lazy val boolVal: Parser[Boolean] =
-    ( "true" ^^^ true
+    ("true" ^^^ true
       | "false" ^^^ false
       )
 
@@ -75,7 +75,7 @@ object LegacyTypeStringParser extends RegexParsers {
     }
 
   protected lazy val dataType: Parser[DataType] =
-    ( arrayType
+    (arrayType
       | mapType
       | structType
       | primitiveType
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala
index e89caabf252d7..7dd54db1000a9 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala
@@ -51,7 +51,7 @@ case class Project(projectList: Seq[NamedExpression], child: LogicalPlan) extend
   override def maxRows: Option[Long] = child.maxRows
 
   override lazy val resolved: Boolean = {
-    val hasSpecialExpressions = projectList.exists ( _.collect {
+    val hasSpecialExpressions = projectList.exists (_.collect {
         case agg: AggregateExpression => agg
         case generator: Generator => generator
         case window: WindowExpression => window
@@ -237,7 +237,7 @@ case class Union(children: Seq[LogicalPlan]) extends LogicalPlan {
   override lazy val resolved: Boolean = {
     // allChildrenCompatible needs to be evaluated after childrenResolved
     def allChildrenCompatible: Boolean =
-      children.tail.forall( child =>
+      children.tail.forall(child =>
         // compare the attribute number with the first child
         child.output.length == children.head.output.length &&
         // compare the data types with the first child
@@ -524,7 +524,7 @@ case class Range(
 
   override def computeStats: Statistics = {
     val sizeInBytes = LongType.defaultSize * numElements
-    Statistics( sizeInBytes = sizeInBytes )
+    Statistics(sizeInBytes = sizeInBytes)
   }
 
   override def simpleString: String = {
@@ -539,7 +539,7 @@ case class Aggregate(
   extends UnaryNode {
 
   override lazy val resolved: Boolean = {
-    val hasWindowExpressions = aggregateExpressions.exists ( _.collect {
+    val hasWindowExpressions = aggregateExpressions.exists (_.collect {
         case window: WindowExpression => window
       }.nonEmpty
     )
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala
index bfb70c2ef4c89..5aa6b70f2e8a2 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/object.scala
@@ -31,16 +31,16 @@ import org.apache.spark.sql.types._
 import org.apache.spark.util.Utils
 
 object CatalystSerde {
-  def deserialize[T : Encoder](child: LogicalPlan): DeserializeToObject = {
+  def deserialize[T: Encoder](child: LogicalPlan): DeserializeToObject = {
     val deserializer = UnresolvedDeserializer(encoderFor[T].deserializer)
     DeserializeToObject(deserializer, generateObjAttr[T], child)
   }
 
-  def serialize[T : Encoder](child: LogicalPlan): SerializeFromObject = {
+  def serialize[T: Encoder](child: LogicalPlan): SerializeFromObject = {
     SerializeFromObject(encoderFor[T].namedExpressions, child)
   }
 
-  def generateObjAttr[T : Encoder]: Attribute = {
+  def generateObjAttr[T: Encoder]: Attribute = {
     val enc = encoderFor[T]
     val dataType = enc.deserializer.dataType
     val nullable = !enc.clsTag.runtimeClass.isPrimitive
@@ -94,7 +94,7 @@ case class SerializeFromObject(
 }
 
 object MapPartitions {
-  def apply[T : Encoder, U : Encoder](
+  def apply[T: Encoder, U: Encoder](
       func: Iterator[T] => Iterator[U],
       child: LogicalPlan): LogicalPlan = {
     val deserialized = CatalystSerde.deserialize[T](child)
@@ -154,7 +154,7 @@ case class MapPartitionsInR(
 }
 
 object MapElements {
-  def apply[T : Encoder, U : Encoder](
+  def apply[T: Encoder, U: Encoder](
       func: AnyRef,
       child: LogicalPlan): LogicalPlan = {
     val deserialized = CatalystSerde.deserialize[T](child)
@@ -179,7 +179,7 @@ case class MapElements(
     child: LogicalPlan) extends ObjectConsumer with ObjectProducer
 
 object TypedFilter {
-  def apply[T : Encoder](func: AnyRef, child: LogicalPlan): TypedFilter = {
+  def apply[T: Encoder](func: AnyRef, child: LogicalPlan): TypedFilter = {
     TypedFilter(
       func,
       implicitly[Encoder[T]].clsTag.runtimeClass,
@@ -259,7 +259,7 @@ object FunctionUtils {
 
 /** Factory for constructing new `AppendColumn` nodes. */
 object AppendColumns {
-  def apply[T : Encoder, U : Encoder](
+  def apply[T: Encoder, U: Encoder](
       func: T => U,
       child: LogicalPlan): AppendColumns = {
     new AppendColumns(
@@ -271,7 +271,7 @@ object AppendColumns {
       child)
   }
 
-  def apply[T : Encoder, U : Encoder](
+  def apply[T: Encoder, U: Encoder](
       func: T => U,
       inputAttributes: Seq[Attribute],
       child: LogicalPlan): AppendColumns = {
@@ -319,7 +319,7 @@ case class AppendColumnsWithObject(
 
 /** Factory for constructing new `MapGroups` nodes. */
 object MapGroups {
-  def apply[K : Encoder, T : Encoder, U : Encoder](
+  def apply[K: Encoder, T: Encoder, U: Encoder](
       func: (K, Iterator[T]) => TraversableOnce[U],
       groupingAttributes: Seq[Attribute],
       dataAttributes: Seq[Attribute],
@@ -475,7 +475,7 @@ case class FlatMapGroupsInR(
 
 /** Factory for constructing new `CoGroup` nodes. */
 object CoGroup {
-  def apply[K : Encoder, L : Encoder, R : Encoder, OUT : Encoder](
+  def apply[K: Encoder, L: Encoder, R: Encoder, OUT: Encoder](
       func: (K, Iterator[L], Iterator[R]) => TraversableOnce[OUT],
       leftGroup: Seq[Attribute],
       rightGroup: Seq[Attribute],
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeUtils.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeUtils.scala
index 746c3e8950f7b..3581db0e3d744 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeUtils.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeUtils.scala
@@ -580,7 +580,7 @@ object DateTimeUtils {
    * The second year of a 400 year period (year 1) starts on day 365.
    */
   private[this] def yearBoundary(year: Int): Int = {
-    year * 365 + ((year / 4 ) - (year / 100) + (year / 400))
+    year * 365 + ((year / 4) - (year / 100) + (year / 400))
   }
 
   /**
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/NumberConverter.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/NumberConverter.scala
index 9c3f6b7c5d245..a8cd2776134b7 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/NumberConverter.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/NumberConverter.scala
@@ -118,7 +118,7 @@ object NumberConverter {
    * unsigned, otherwise it is signed.
    * NB: This logic is borrowed from org.apache.hadoop.hive.ql.ud.UDFConv
    */
-  def convert(n: Array[Byte], fromBase: Int, toBase: Int ): UTF8String = {
+  def convert(n: Array[Byte], fromBase: Int, toBase: Int): UTF8String = {
     if (fromBase < Character.MIN_RADIX || fromBase > Character.MAX_RADIX
         || Math.abs(toBase) < Character.MIN_RADIX
         || Math.abs(toBase) > Character.MAX_RADIX) {
@@ -157,7 +157,7 @@ object NumberConverter {
 
     // Find the first non-zero digit or the last digits if all are zero.
     val firstNonZeroPos = {
-      val firstNonZero = temp.indexWhere( _ != 0)
+      val firstNonZero = temp.indexWhere(_ != 0)
       if (firstNonZero != -1) firstNonZero else temp.length - 1
     }
     byte2char(Math.abs(toBase), firstNonZeroPos, temp)
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/package.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/package.scala
index 4005087dad05a..cffd28b9de018 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/package.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/package.scala
@@ -51,7 +51,7 @@ package object util {
     val outStream = new ByteArrayOutputStream
     try {
       var reading = true
-      while ( reading ) {
+      while (reading) {
         inStream.read() match {
           case -1 => reading = false
           case c => outStream.write(c)
@@ -72,7 +72,7 @@ package object util {
     val outStream = new ByteArrayOutputStream
     try {
       var reading = true
-      while ( reading ) {
+      while (reading) {
         inStream.read() match {
           case -1 => reading = false
           case c => outStream.write(c)
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/types/ArrayType.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/types/ArrayType.scala
index 38c40482fa4d9..d3fe9ee5bc444 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/types/ArrayType.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/types/ArrayType.scala
@@ -100,7 +100,7 @@ case class ArrayType(elementType: DataType, containsNull: Boolean) extends DataT
   private[sql] lazy val interpretedOrdering: Ordering[ArrayData] = new Ordering[ArrayData] {
     private[this] val elementOrdering: Ordering[Any] = elementType match {
       case dt: AtomicType => dt.ordering.asInstanceOf[Ordering[Any]]
-      case a : ArrayType => a.interpretedOrdering.asInstanceOf[Ordering[Any]]
+      case a: ArrayType => a.interpretedOrdering.asInstanceOf[Ordering[Any]]
       case s: StructType => s.interpretedOrdering.asInstanceOf[Ordering[Any]]
       case other =>
         throw new IllegalArgumentException(s"Type $other does not support ordered operations")
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/types/Decimal.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/types/Decimal.scala
index 1f1fb51addfd8..58b978388d60f 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/types/Decimal.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/types/Decimal.scala
@@ -381,7 +381,7 @@ final class Decimal extends Ordered[Decimal] with Serializable {
 
   def remainder(that: Decimal): Decimal = this % that
 
-  def unary_- : Decimal = {
+  def unary_-: Decimal = {
     if (decimalVal.ne(null)) {
       Decimal(-decimalVal, precision, scale)
     } else {
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/Column.scala b/sql/core/src/main/scala/org/apache/spark/sql/Column.scala
index 7e1f1d83cb3de..b545567029735 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/Column.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/Column.scala
@@ -193,7 +193,7 @@ class Column(val expr: Expression) extends Logging {
    * results into the correct JVM types.
    * @since 1.6.0
    */
-  def as[U : Encoder]: TypedColumn[Any, U] = new TypedColumn[Any, U](expr, encoderFor[U])
+  def as[U: Encoder]: TypedColumn[Any, U] = new TypedColumn[Any, U](expr, encoderFor[U])
 
   /**
    * Extracts a value or values from a complex type.
@@ -226,7 +226,7 @@ class Column(val expr: Expression) extends Logging {
    * @group expr_ops
    * @since 1.3.0
    */
-  def unary_- : Column = withExpr { UnaryMinus(expr) }
+  def unary_-: Column = withExpr { UnaryMinus(expr) }
 
   /**
    * Inversion of boolean expression, i.e. NOT.
@@ -242,7 +242,7 @@ class Column(val expr: Expression) extends Logging {
    * @group expr_ops
    * @since 1.3.0
    */
-  def unary_! : Column = withExpr { Not(expr) }
+  def unary_!: Column = withExpr { Not(expr) }
 
   /**
    * Equality test.
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameNaFunctions.scala b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameNaFunctions.scala
index 871fff71e5538..0280047774c9c 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameNaFunctions.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameNaFunctions.scala
@@ -391,7 +391,7 @@ final class DataFrameNaFunctions private[sql](df: DataFrame) {
         df.col(f.name)
       }
     }
-    df.select(projections : _*)
+    df.select(projections: _*)
   }
 
   private def fillMap(values: Seq[(String, Any)]): DataFrame = {
@@ -422,7 +422,7 @@ final class DataFrameNaFunctions private[sql](df: DataFrame) {
         }
       }.getOrElse(df.col(f.name))
     }
-    df.select(projections : _*)
+    df.select(projections: _*)
   }
 
   /**
@@ -495,6 +495,6 @@ final class DataFrameNaFunctions private[sql](df: DataFrame) {
         df.col(f.name)
       }
     }
-    df.select(projections : _*)
+    df.select(projections: _*)
   }
 }
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala
index a1d8b7f4af1b5..fa71612379211 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala
@@ -273,7 +273,7 @@ class DataFrameReader private[sql](sparkSession: SparkSession) extends Logging {
     val params = extraOptions.toMap ++ connectionProperties.asScala.toMap
     val options = new JDBCOptions(url, table, params)
     val parts: Array[Partition] = predicates.zipWithIndex.map { case (part, i) =>
-      JDBCPartition(part, i) : Partition
+      JDBCPartition(part, i): Partition
     }
     val relation = JDBCRelation(parts, options)(sparkSession)
     sparkSession.baseRelationToDataFrame(relation)
@@ -342,7 +342,7 @@ class DataFrameReader private[sql](sparkSession: SparkSession) extends Logging {
    * @since 2.0.0
    */
   @scala.annotation.varargs
-  def json(paths: String*): DataFrame = format("json").load(paths : _*)
+  def json(paths: String*): DataFrame = format("json").load(paths: _*)
 
   /**
    * Loads a `JavaRDD[String]` storing JSON objects (JSON
@@ -542,7 +542,7 @@ class DataFrameReader private[sql](sparkSession: SparkSession) extends Logging {
    * @since 2.0.0
    */
   @scala.annotation.varargs
-  def csv(paths: String*): DataFrame = format("csv").load(paths : _*)
+  def csv(paths: String*): DataFrame = format("csv").load(paths: _*)
 
   /**
    * Loads a Parquet file, returning the result as a `DataFrame`. See the documentation
@@ -632,7 +632,7 @@ class DataFrameReader private[sql](sparkSession: SparkSession) extends Logging {
    * @since 1.6.0
    */
   @scala.annotation.varargs
-  def text(paths: String*): DataFrame = format("text").load(paths : _*)
+  def text(paths: String*): DataFrame = format("text").load(paths: _*)
 
   /**
    * Loads text files and returns a [[Dataset]] of String. See the documentation on the
@@ -666,7 +666,7 @@ class DataFrameReader private[sql](sparkSession: SparkSession) extends Logging {
   @scala.annotation.varargs
   def textFile(paths: String*): Dataset[String] = {
     assertNoSpecifiedSchema("textFile")
-    text(paths : _*).select("value").as[String](sparkSession.implicits.newStringEncoder)
+    text(paths: _*).select("value").as[String](sparkSession.implicits.newStringEncoder)
   }
 
   /**
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameWriter.scala b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameWriter.scala
index 255c4064eb574..59db4e10c9311 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameWriter.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameWriter.scala
@@ -308,7 +308,7 @@ final class DataFrameWriter[T] private[sql](ds: Dataset[T]) {
 
   private def assertNotPartitioned(operation: String): Unit = {
     if (partitioningColumns.isDefined) {
-      throw new AnalysisException( s"'$operation' does not support partitioning")
+      throw new AnalysisException(s"'$operation' does not support partitioning")
     }
   }
 
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala b/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
index 7be4aa1ca9562..fde2a1aec4e59 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
@@ -413,7 +413,7 @@ class Dataset[T] private[sql](
    */
   @Experimental
   @InterfaceStability.Evolving
-  def as[U : Encoder]: Dataset[U] = Dataset[U](sparkSession, logicalPlan)
+  def as[U: Encoder]: Dataset[U] = Dataset[U](sparkSession, logicalPlan)
 
   /**
    * Converts this strongly typed collection of data to generic `DataFrame` with columns renamed.
@@ -438,7 +438,7 @@ class Dataset[T] private[sql](
     val newCols = logicalPlan.output.zip(colNames).map { case (oldAttribute, newName) =>
       Column(oldAttribute).as(newName)
     }
-    select(newCols : _*)
+    select(newCols: _*)
   }
 
   /**
@@ -1083,7 +1083,7 @@ class Dataset[T] private[sql](
    */
   @scala.annotation.varargs
   def sortWithinPartitions(sortCol: String, sortCols: String*): Dataset[T] = {
-    sortWithinPartitions((sortCol +: sortCols).map(Column(_)) : _*)
+    sortWithinPartitions((sortCol +: sortCols).map(Column(_)): _*)
   }
 
   /**
@@ -1113,7 +1113,7 @@ class Dataset[T] private[sql](
    */
   @scala.annotation.varargs
   def sort(sortCol: String, sortCols: String*): Dataset[T] = {
-    sort((sortCol +: sortCols).map(apply) : _*)
+    sort((sortCol +: sortCols).map(apply): _*)
   }
 
   /**
@@ -1138,7 +1138,7 @@ class Dataset[T] private[sql](
    * @since 2.0.0
    */
   @scala.annotation.varargs
-  def orderBy(sortCol: String, sortCols: String*): Dataset[T] = sort(sortCol, sortCols : _*)
+  def orderBy(sortCol: String, sortCols: String*): Dataset[T] = sort(sortCol, sortCols: _*)
 
   /**
    * Returns a new Dataset sorted by the given expressions.
@@ -1148,7 +1148,7 @@ class Dataset[T] private[sql](
    * @since 2.0.0
    */
   @scala.annotation.varargs
-  def orderBy(sortExprs: Column*): Dataset[T] = sort(sortExprs : _*)
+  def orderBy(sortExprs: Column*): Dataset[T] = sort(sortExprs: _*)
 
   /**
    * Selects column based on the column name and return it as a [[Column]].
@@ -1254,7 +1254,7 @@ class Dataset[T] private[sql](
    * @since 2.0.0
    */
   @scala.annotation.varargs
-  def select(col: String, cols: String*): DataFrame = select((col +: cols).map(Column(_)) : _*)
+  def select(col: String, cols: String*): DataFrame = select((col +: cols).map(Column(_)): _*)
 
   /**
    * Selects a set of SQL expressions. This is a variant of `select` that accepts
@@ -1659,7 +1659,7 @@ class Dataset[T] private[sql](
    * @since 2.0.0
    */
   def agg(aggExpr: (String, String), aggExprs: (String, String)*): DataFrame = {
-    groupBy().agg(aggExpr, aggExprs : _*)
+    groupBy().agg(aggExpr, aggExprs: _*)
   }
 
   /**
@@ -1700,7 +1700,7 @@ class Dataset[T] private[sql](
    * @since 2.0.0
    */
   @scala.annotation.varargs
-  def agg(expr: Column, exprs: Column*): DataFrame = groupBy().agg(expr, exprs : _*)
+  def agg(expr: Column, exprs: Column*): DataFrame = groupBy().agg(expr, exprs: _*)
 
   /**
    * Returns a new Dataset by taking the first `n` rows. The difference between this function
@@ -1859,7 +1859,7 @@ class Dataset[T] private[sql](
    */
   def randomSplitAsList(weights: Array[Double], seed: Long): java.util.List[Dataset[T]] = {
     val values = randomSplit(weights, seed)
-    java.util.Arrays.asList(values : _*)
+    java.util.Arrays.asList(values: _*)
   }
 
   /**
@@ -1911,7 +1911,7 @@ class Dataset[T] private[sql](
    * @since 2.0.0
    */
   @deprecated("use flatMap() or select() with functions.explode() instead", "2.0.0")
-  def explode[A <: Product : TypeTag](input: Column*)(f: Row => TraversableOnce[A]): DataFrame = {
+  def explode[A <: Product: TypeTag](input: Column*)(f: Row => TraversableOnce[A]): DataFrame = {
     val elementSchema = ScalaReflection.schemaFor[A].dataType.asInstanceOf[StructType]
 
     val convert = CatalystTypeConverters.createToCatalystConverter(elementSchema)
@@ -1948,7 +1948,7 @@ class Dataset[T] private[sql](
    * @since 2.0.0
    */
   @deprecated("use flatMap() or select() with functions.explode() instead", "2.0.0")
-  def explode[A, B : TypeTag](inputColumn: String, outputColumn: String)(f: A => TraversableOnce[B])
+  def explode[A, B: TypeTag](inputColumn: String, outputColumn: String)(f: A => TraversableOnce[B])
     : DataFrame = {
     val dataType = ScalaReflection.schemaFor[B].dataType
     val attributes = AttributeReference(outputColumn, dataType)() :: Nil
@@ -1986,7 +1986,7 @@ class Dataset[T] private[sql](
           Column(field)
         }
       }
-      select(columns : _*)
+      select(columns: _*)
     } else {
       select(Column("*"), col.as(colName))
     }
@@ -2018,7 +2018,7 @@ class Dataset[T] private[sql](
           Column(col)
         }
       }
-      select(columns : _*)
+      select(columns: _*)
     } else {
       toDF()
     }
@@ -2035,7 +2035,7 @@ class Dataset[T] private[sql](
    * @since 2.0.0
    */
   def drop(colName: String): DataFrame = {
-    drop(Seq(colName) : _*)
+    drop(Seq(colName): _*)
   }
 
   /**
@@ -2082,7 +2082,7 @@ class Dataset[T] private[sql](
     val colsAfterDrop = attrs.filter { attr =>
       attr != expression
     }.map(attr => Column(attr))
-    select(colsAfterDrop : _*)
+    select(colsAfterDrop: _*)
   }
 
   /**
@@ -2302,7 +2302,7 @@ class Dataset[T] private[sql](
    */
   @Experimental
   @InterfaceStability.Evolving
-  def map[U : Encoder](func: T => U): Dataset[U] = withTypedPlan {
+  def map[U: Encoder](func: T => U): Dataset[U] = withTypedPlan {
     MapElements[T, U](func, logicalPlan)
   }
 
@@ -2331,7 +2331,7 @@ class Dataset[T] private[sql](
    */
   @Experimental
   @InterfaceStability.Evolving
-  def mapPartitions[U : Encoder](func: Iterator[T] => Iterator[U]): Dataset[U] = {
+  def mapPartitions[U: Encoder](func: Iterator[T] => Iterator[U]): Dataset[U] = {
     new Dataset[U](
       sparkSession,
       MapPartitions[T, U](func, logicalPlan),
@@ -2379,7 +2379,7 @@ class Dataset[T] private[sql](
    */
   @Experimental
   @InterfaceStability.Evolving
-  def flatMap[U : Encoder](func: T => TraversableOnce[U]): Dataset[U] =
+  def flatMap[U: Encoder](func: T => TraversableOnce[U]): Dataset[U] =
     mapPartitions(_.flatMap(func))
 
   /**
@@ -2457,7 +2457,7 @@ class Dataset[T] private[sql](
    * @group action
    * @since 1.6.0
    */
-  def takeAsList(n: Int): java.util.List[T] = java.util.Arrays.asList(take(n) : _*)
+  def takeAsList(n: Int): java.util.List[T] = java.util.Arrays.asList(take(n): _*)
 
   /**
    * Returns an array that contains all rows in this Dataset.
@@ -2483,7 +2483,7 @@ class Dataset[T] private[sql](
    */
   def collectAsList(): java.util.List[T] = withAction("collectAsList", queryExecution) { plan =>
     val values = collectFromPlan(plan)
-    java.util.Arrays.asList(values : _*)
+    java.util.Arrays.asList(values: _*)
   }
 
   /**
@@ -2954,12 +2954,12 @@ class Dataset[T] private[sql](
   }
 
   /** A convenient function to wrap a logical plan and produce a Dataset. */
-  @inline private def withTypedPlan[U : Encoder](logicalPlan: LogicalPlan): Dataset[U] = {
+  @inline private def withTypedPlan[U: Encoder](logicalPlan: LogicalPlan): Dataset[U] = {
     Dataset(sparkSession, logicalPlan)
   }
 
   /** A convenient function to wrap a set based logical plan and produce a Dataset. */
-  @inline private def withSetOperator[U : Encoder](logicalPlan: LogicalPlan): Dataset[U] = {
+  @inline private def withSetOperator[U: Encoder](logicalPlan: LogicalPlan): Dataset[U] = {
     if (classTag.runtimeClass.isAssignableFrom(classOf[Row])) {
       // Set operators widen types (change the schema), so we cannot reuse the row encoder.
       Dataset.ofRows(sparkSession, logicalPlan).asInstanceOf[Dataset[U]]
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DatasetHolder.scala b/sql/core/src/main/scala/org/apache/spark/sql/DatasetHolder.scala
index 582d4a3670b8e..2d1f4dd658fb7 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/DatasetHolder.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/DatasetHolder.scala
@@ -41,5 +41,5 @@ case class DatasetHolder[T] private[sql](private val ds: Dataset[T]) {
   // `rdd.toDF("1")` as invoking this toDF and then apply on the returned DataFrame.
   def toDF(): DataFrame = ds.toDF()
 
-  def toDF(colNames: String*): DataFrame = ds.toDF(colNames : _*)
+  def toDF(colNames: String*): DataFrame = ds.toDF(colNames: _*)
 }
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/KeyValueGroupedDataset.scala b/sql/core/src/main/scala/org/apache/spark/sql/KeyValueGroupedDataset.scala
index cb42e9e4560cf..7bf258c39f7e0 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/KeyValueGroupedDataset.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/KeyValueGroupedDataset.scala
@@ -60,7 +60,7 @@ class KeyValueGroupedDataset[K, V] private[sql](
    *
    * @since 1.6.0
    */
-  def keyAs[L : Encoder]: KeyValueGroupedDataset[L, V] =
+  def keyAs[L: Encoder]: KeyValueGroupedDataset[L, V] =
     new KeyValueGroupedDataset(
       encoderFor[L],
       vExprEnc,
@@ -79,7 +79,7 @@ class KeyValueGroupedDataset[K, V] private[sql](
    *
    * @since 2.1.0
    */
-  def mapValues[W : Encoder](func: V => W): KeyValueGroupedDataset[K, W] = {
+  def mapValues[W: Encoder](func: V => W): KeyValueGroupedDataset[K, W] = {
     val withNewData = AppendColumns(func, dataAttributes, logicalPlan)
     val projected = Project(withNewData.newColumns ++ groupingAttributes, withNewData)
     val executed = sparkSession.sessionState.executePlan(projected)
@@ -142,7 +142,7 @@ class KeyValueGroupedDataset[K, V] private[sql](
    *
    * @since 1.6.0
    */
-  def flatMapGroups[U : Encoder](f: (K, Iterator[V]) => TraversableOnce[U]): Dataset[U] = {
+  def flatMapGroups[U: Encoder](f: (K, Iterator[V]) => TraversableOnce[U]): Dataset[U] = {
     Dataset[U](
       sparkSession,
       MapGroups(
@@ -193,7 +193,7 @@ class KeyValueGroupedDataset[K, V] private[sql](
    *
    * @since 1.6.0
    */
-  def mapGroups[U : Encoder](f: (K, Iterator[V]) => U): Dataset[U] = {
+  def mapGroups[U: Encoder](f: (K, Iterator[V]) => U): Dataset[U] = {
     val func = (key: K, it: Iterator[V]) => Iterator(f(key, it))
     flatMapGroups(func)
   }
@@ -533,7 +533,7 @@ class KeyValueGroupedDataset[K, V] private[sql](
    *
    * @since 1.6.0
    */
-  def cogroup[U, R : Encoder](
+  def cogroup[U, R: Encoder](
       other: KeyValueGroupedDataset[K, U])(
       f: (K, Iterator[V], Iterator[U]) => TraversableOnce[R]): Dataset[R] = {
     implicit val uEncoder = other.vExprEnc
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/RelationalGroupedDataset.scala b/sql/core/src/main/scala/org/apache/spark/sql/RelationalGroupedDataset.scala
index 147b549964913..d9878a825c133 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/RelationalGroupedDataset.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/RelationalGroupedDataset.scala
@@ -246,7 +246,7 @@ class RelationalGroupedDataset protected[sql](
    */
   @scala.annotation.varargs
   def mean(colNames: String*): DataFrame = {
-    aggregateNumericColumns(colNames : _*)(Average)
+    aggregateNumericColumns(colNames: _*)(Average)
   }
 
   /**
@@ -258,7 +258,7 @@ class RelationalGroupedDataset protected[sql](
    */
   @scala.annotation.varargs
   def max(colNames: String*): DataFrame = {
-    aggregateNumericColumns(colNames : _*)(Max)
+    aggregateNumericColumns(colNames: _*)(Max)
   }
 
   /**
@@ -270,7 +270,7 @@ class RelationalGroupedDataset protected[sql](
    */
   @scala.annotation.varargs
   def avg(colNames: String*): DataFrame = {
-    aggregateNumericColumns(colNames : _*)(Average)
+    aggregateNumericColumns(colNames: _*)(Average)
   }
 
   /**
@@ -282,7 +282,7 @@ class RelationalGroupedDataset protected[sql](
    */
   @scala.annotation.varargs
   def min(colNames: String*): DataFrame = {
-    aggregateNumericColumns(colNames : _*)(Min)
+    aggregateNumericColumns(colNames: _*)(Min)
   }
 
   /**
@@ -294,7 +294,7 @@ class RelationalGroupedDataset protected[sql](
    */
   @scala.annotation.varargs
   def sum(colNames: String*): DataFrame = {
-    aggregateNumericColumns(colNames : _*)(Sum)
+    aggregateNumericColumns(colNames: _*)(Sum)
   }
 
   /**
@@ -419,7 +419,7 @@ class RelationalGroupedDataset protected[sql](
       outputSchema: StructType): DataFrame = {
       val groupingNamedExpressions = groupingExprs.map(alias)
       val groupingCols = groupingNamedExpressions.map(Column(_))
-      val groupingDataFrame = df.select(groupingCols : _*)
+      val groupingDataFrame = df.select(groupingCols: _*)
       val groupingAttributes = groupingNamedExpressions.map(_.toAttribute)
       Dataset.ofRows(
         df.sparkSession,
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala b/sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala
index 7fde6e9469e5e..2c6b434ff3920 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala
@@ -268,7 +268,7 @@ class SQLContext private[sql](val sparkSession: SparkSession)
    */
   @Experimental
   @InterfaceStability.Evolving
-  def createDataFrame[A <: Product : TypeTag](rdd: RDD[A]): DataFrame = {
+  def createDataFrame[A <: Product: TypeTag](rdd: RDD[A]): DataFrame = {
     sparkSession.createDataFrame(rdd)
   }
 
@@ -281,7 +281,7 @@ class SQLContext private[sql](val sparkSession: SparkSession)
    */
   @Experimental
   @InterfaceStability.Evolving
-  def createDataFrame[A <: Product : TypeTag](data: Seq[A]): DataFrame = {
+  def createDataFrame[A <: Product: TypeTag](data: Seq[A]): DataFrame = {
     sparkSession.createDataFrame(data)
   }
 
@@ -373,7 +373,7 @@ class SQLContext private[sql](val sparkSession: SparkSession)
    */
   @Experimental
   @InterfaceStability.Evolving
-  def createDataset[T : Encoder](data: Seq[T]): Dataset[T] = {
+  def createDataset[T: Encoder](data: Seq[T]): Dataset[T] = {
     sparkSession.createDataset(data)
   }
 
@@ -388,7 +388,7 @@ class SQLContext private[sql](val sparkSession: SparkSession)
    * @group dataset
    */
   @Experimental
-  def createDataset[T : Encoder](data: RDD[T]): Dataset[T] = {
+  def createDataset[T: Encoder](data: RDD[T]): Dataset[T] = {
     sparkSession.createDataset(data)
   }
 
@@ -411,7 +411,7 @@ class SQLContext private[sql](val sparkSession: SparkSession)
    */
   @Experimental
   @InterfaceStability.Evolving
-  def createDataset[T : Encoder](data: java.util.List[T]): Dataset[T] = {
+  def createDataset[T: Encoder](data: java.util.List[T]): Dataset[T] = {
     sparkSession.createDataset(data)
   }
 
@@ -803,7 +803,7 @@ class SQLContext private[sql](val sparkSession: SparkSession)
     if (paths.isEmpty) {
       emptyDataFrame
     } else {
-      read.parquet(paths : _*)
+      read.parquet(paths: _*)
     }
   }
 
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/SQLImplicits.scala b/sql/core/src/main/scala/org/apache/spark/sql/SQLImplicits.scala
index 86574e2f71d92..c95eb1be98e96 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/SQLImplicits.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/SQLImplicits.scala
@@ -162,14 +162,14 @@ abstract class SQLImplicits extends LowPrioritySQLImplicits {
    * @since 1.6.1
    * @deprecated use [[newSequenceEncoder]]
    */
-  def newProductSeqEncoder[A <: Product : TypeTag]: Encoder[Seq[A]] = ExpressionEncoder()
+  def newProductSeqEncoder[A <: Product: TypeTag]: Encoder[Seq[A]] = ExpressionEncoder()
 
   /** @since 2.2.0 */
-  implicit def newSequenceEncoder[T <: Seq[_] : TypeTag]: Encoder[T] = ExpressionEncoder()
+  implicit def newSequenceEncoder[T <: Seq[_]: TypeTag]: Encoder[T] = ExpressionEncoder()
 
   // Maps
   /** @since 2.3.0 */
-  implicit def newMapEncoder[T <: Map[_, _] : TypeTag]: Encoder[T] = ExpressionEncoder()
+  implicit def newMapEncoder[T <: Map[_, _]: TypeTag]: Encoder[T] = ExpressionEncoder()
 
   // Arrays
 
@@ -198,7 +198,7 @@ abstract class SQLImplicits extends LowPrioritySQLImplicits {
   implicit def newStringArrayEncoder: Encoder[Array[String]] = ExpressionEncoder()
 
   /** @since 1.6.1 */
-  implicit def newProductArrayEncoder[A <: Product : TypeTag]: Encoder[Array[A]] =
+  implicit def newProductArrayEncoder[A <: Product: TypeTag]: Encoder[Array[A]] =
     ExpressionEncoder()
 
   /**
@@ -206,7 +206,7 @@ abstract class SQLImplicits extends LowPrioritySQLImplicits {
    *
    * @since 1.6.0
    */
-  implicit def rddToDatasetHolder[T : Encoder](rdd: RDD[T]): DatasetHolder[T] = {
+  implicit def rddToDatasetHolder[T: Encoder](rdd: RDD[T]): DatasetHolder[T] = {
     DatasetHolder(_sqlContext.createDataset(rdd))
   }
 
@@ -214,7 +214,7 @@ abstract class SQLImplicits extends LowPrioritySQLImplicits {
    * Creates a [[Dataset]] from a local Seq.
    * @since 1.6.0
    */
-  implicit def localSeqToDatasetHolder[T : Encoder](s: Seq[T]): DatasetHolder[T] = {
+  implicit def localSeqToDatasetHolder[T: Encoder](s: Seq[T]): DatasetHolder[T] = {
     DatasetHolder(_sqlContext.createDataset(s))
   }
 
@@ -235,6 +235,6 @@ abstract class SQLImplicits extends LowPrioritySQLImplicits {
  */
 trait LowPrioritySQLImplicits {
   /** @since 1.6.0 */
-  implicit def newProductEncoder[T <: Product : TypeTag]: Encoder[T] = Encoders.product[T]
+  implicit def newProductEncoder[T <: Product: TypeTag]: Encoder[T] = Encoders.product[T]
 
 }
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala b/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala
index 2c38f7d7c88da..3a28db867c30a 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala
@@ -282,7 +282,7 @@ class SparkSession private(
    */
   @Experimental
   @InterfaceStability.Evolving
-  def createDataFrame[A <: Product : TypeTag](rdd: RDD[A]): DataFrame = {
+  def createDataFrame[A <: Product: TypeTag](rdd: RDD[A]): DataFrame = {
     SparkSession.setActiveSession(this)
     val encoder = Encoders.product[A]
     Dataset.ofRows(self, ExternalRDD(rdd, self)(encoder))
@@ -296,7 +296,7 @@ class SparkSession private(
    */
   @Experimental
   @InterfaceStability.Evolving
-  def createDataFrame[A <: Product : TypeTag](data: Seq[A]): DataFrame = {
+  def createDataFrame[A <: Product: TypeTag](data: Seq[A]): DataFrame = {
     SparkSession.setActiveSession(this)
     val schema = ScalaReflection.schemaFor[A].dataType.asInstanceOf[StructType]
     val attributeSeq = schema.toAttributes
@@ -454,7 +454,7 @@ class SparkSession private(
    */
   @Experimental
   @InterfaceStability.Evolving
-  def createDataset[T : Encoder](data: Seq[T]): Dataset[T] = {
+  def createDataset[T: Encoder](data: Seq[T]): Dataset[T] = {
     val enc = encoderFor[T]
     val attributes = enc.schema.toAttributes
     val encoded = data.map(d => enc.toRow(d).copy())
@@ -473,7 +473,7 @@ class SparkSession private(
    */
   @Experimental
   @InterfaceStability.Evolving
-  def createDataset[T : Encoder](data: RDD[T]): Dataset[T] = {
+  def createDataset[T: Encoder](data: RDD[T]): Dataset[T] = {
     Dataset[T](self, ExternalRDD(data, self))
   }
 
@@ -495,7 +495,7 @@ class SparkSession private(
    */
   @Experimental
   @InterfaceStability.Evolving
-  def createDataset[T : Encoder](data: java.util.List[T]): Dataset[T] = {
+  def createDataset[T: Encoder](data: java.util.List[T]): Dataset[T] = {
     createDataset(data.asScala)
   }
 
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/UDFRegistration.scala b/sql/core/src/main/scala/org/apache/spark/sql/UDFRegistration.scala
index ad01b889429c7..0d2383420ce72 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/UDFRegistration.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/UDFRegistration.scala
@@ -90,7 +90,7 @@ class UDFRegistration private[sql] (functionRegistry: FunctionRegistry) extends
    * @since 2.2.0
    */
   def register(name: String, udf: UserDefinedFunction): UserDefinedFunction = {
-    def builder(children: Seq[Expression]) = udf.apply(children.map(Column.apply) : _*).expr
+    def builder(children: Seq[Expression]) = udf.apply(children.map(Column.apply): _*).expr
     functionRegistry.createOrReplaceTempFunction(name, builder)
     udf
   }
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/TypedAggregateExpression.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/TypedAggregateExpression.scala
index 717758fdf716f..3b4e64c624d24 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/TypedAggregateExpression.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/TypedAggregateExpression.scala
@@ -31,7 +31,7 @@ import org.apache.spark.sql.expressions.Aggregator
 import org.apache.spark.sql.types._
 
 object TypedAggregateExpression {
-  def apply[BUF : Encoder, OUT : Encoder](
+  def apply[BUF: Encoder, OUT: Encoder](
       aggregator: Aggregator[_, BUF, OUT]): TypedAggregateExpression = {
     val bufferEncoder = encoderFor[BUF]
     val bufferSerializer = bufferEncoder.namedExpressions
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaConverter.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaConverter.scala
index 0b805e4362883..d6197e062341c 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaConverter.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaConverter.scala
@@ -582,7 +582,7 @@ private[parquet] object ParquetSchemaConverter {
     }
   }
 
-  private def computeMinBytesForPrecision(precision : Int) : Int = {
+  private def computeMinBytesForPrecision(precision: Int): Int = {
     var numBytes = 1
     while (math.pow(2.0, 8 * numBytes - 1) < math.pow(10.0, precision)) {
       numBytes += 1
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/CartesianProductExec.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/CartesianProductExec.scala
index f380986951317..b7499e4937c8e 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/CartesianProductExec.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/CartesianProductExec.scala
@@ -32,8 +32,8 @@ import org.apache.spark.util.CompletionIterator
  * materialize the right RDD (in case of the right RDD is nondeterministic).
  */
 class UnsafeCartesianRDD(
-    left : RDD[UnsafeRow],
-    right : RDD[UnsafeRow],
+    left: RDD[UnsafeRow],
+    right: RDD[UnsafeRow],
     numFieldsOfRight: Int,
     spillThreshold: Int)
   extends CartesianRDD[UnsafeRow, UnsafeRow](left.sparkContext, left, right) {
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala
index 3c702856114f9..0994165a86fcd 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala
@@ -189,7 +189,7 @@ private[joins] class UnsafeHashedRelation(
   private def write(
       writeInt: (Int) => Unit,
       writeLong: (Long) => Unit,
-      writeBuffer: (Array[Byte], Int, Int) => Unit) : Unit = {
+      writeBuffer: (Array[Byte], Int, Int) => Unit): Unit = {
     writeInt(numFields)
     // TODO: move these into BytesToBytesMap
     writeLong(binaryMap.numKeys())
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/stat/FrequentItems.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/stat/FrequentItems.scala
index cdb755edc79a1..b48ad96845078 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/stat/FrequentItems.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/stat/FrequentItems.scala
@@ -95,7 +95,7 @@ object FrequentItems extends Logging {
       (name, originalSchema.fields(index).dataType)
     }.toArray
 
-    val freqItems = df.select(cols.map(Column(_)) : _*).rdd.aggregate(countMaps)(
+    val freqItems = df.select(cols.map(Column(_)): _*).rdd.aggregate(countMaps)(
       seqOp = (counts, row) => {
         var i = 0
         while (i < numCols) {
@@ -116,7 +116,7 @@ object FrequentItems extends Logging {
       }
     )
     val justItems = freqItems.map(m => m.baseMap.keys.toArray)
-    val resultRow = Row(justItems : _*)
+    val resultRow = Row(justItems: _*)
     // append frequent Items to the column name for easy debugging
     val outputCols = colInfo.map { v =>
       StructField(v._1 + "_freqItems", ArrayType(v._2, false))
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/CompactibleFileStreamLog.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/CompactibleFileStreamLog.scala
index 408c8f81f17ba..403e6244ba5ed 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/CompactibleFileStreamLog.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/CompactibleFileStreamLog.scala
@@ -39,7 +39,7 @@ import org.apache.spark.sql.SparkSession
  * compact log files every 10 batches by default into a big file. When
  * doing a compaction, it will read all old log files and merge them with the new batch.
  */
-abstract class CompactibleFileStreamLog[T <: AnyRef : ClassTag](
+abstract class CompactibleFileStreamLog[T <: AnyRef: ClassTag](
     metadataLogVersion: Int,
     sparkSession: SparkSession,
     path: String)
@@ -305,7 +305,7 @@ object CompactibleFileStreamLog {
    * Derives a compact interval from the latest compact batch id and
    * a default compact interval.
    */
-  def deriveCompactInterval(defaultInterval: Int, latestCompactBatchId: Int) : Int = {
+  def deriveCompactInterval(defaultInterval: Int, latestCompactBatchId: Int): Int = {
     if (latestCompactBatchId + 1 <= defaultInterval) {
       latestCompactBatchId + 1
     } else if (defaultInterval < (latestCompactBatchId + 1) / 2) {
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/ForeachSink.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/ForeachSink.scala
index de09fb568d2a6..a4cbc712a472e 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/ForeachSink.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/ForeachSink.scala
@@ -28,7 +28,7 @@ import org.apache.spark.sql.catalyst.encoders.encoderFor
  * @param writer The [[ForeachWriter]] to process all data.
  * @tparam T The expected type of the sink.
  */
-class ForeachSink[T : Encoder](writer: ForeachWriter[T]) extends Sink with Serializable {
+class ForeachSink[T: Encoder](writer: ForeachWriter[T]) extends Sink with Serializable {
 
   override def addBatch(batchId: Long, data: DataFrame): Unit = {
     // This logic should've been as simple as:
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/HDFSMetadataLog.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/HDFSMetadataLog.scala
index 46bfc297931fb..5996de9c13f18 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/HDFSMetadataLog.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/HDFSMetadataLog.scala
@@ -45,7 +45,7 @@ import org.apache.spark.sql.SparkSession
  * Note: [[HDFSMetadataLog]] doesn't support S3-like file systems as they don't guarantee listing
  * files in a directory always shows the latest files.
  */
-class HDFSMetadataLog[T <: AnyRef : ClassTag](sparkSession: SparkSession, path: String)
+class HDFSMetadataLog[T <: AnyRef: ClassTag](sparkSession: SparkSession, path: String)
   extends MetadataLog[T] with Logging {
 
   private implicit val formats = Serialization.formats(NoTypeHints)
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/LongOffset.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/LongOffset.scala
index 5f0b195fcfcb8..c47b137040fb2 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/LongOffset.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/LongOffset.scala
@@ -34,7 +34,7 @@ object LongOffset {
    * LongOffset factory from serialized offset.
    * @return new LongOffset
    */
-  def apply(offset: SerializedOffset) : LongOffset = new LongOffset(offset.json.toLong)
+  def apply(offset: SerializedOffset): LongOffset = new LongOffset(offset.json.toLong)
 
   /**
    * Convert generic Offset to LongOffset if possible.
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Source.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Source.scala
index 311942f6dbd84..9167923f8ca8f 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Source.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Source.scala
@@ -60,7 +60,7 @@ trait Source {
    * Informs the source that Spark has completed processing all data for offsets less than or
    * equal to `end` and will only request offsets greater than `end` in the future.
    */
-  def commit(end: Offset) : Unit = {}
+  def commit(end: Offset): Unit = {}
 
   /** Stop this source and free any resources it has allocated. */
   def stop(): Unit
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/memory.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/memory.scala
index 4979873ee3c7f..c61dac7e9d282 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/memory.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/memory.scala
@@ -38,7 +38,7 @@ object MemoryStream {
   protected val currentBlockId = new AtomicInteger(0)
   protected val memoryStreamId = new AtomicInteger(0)
 
-  def apply[A : Encoder](implicit sqlContext: SQLContext): MemoryStream[A] =
+  def apply[A: Encoder](implicit sqlContext: SQLContext): MemoryStream[A] =
     new MemoryStream[A](memoryStreamId.getAndIncrement(), sqlContext)
 }
 
@@ -47,7 +47,7 @@ object MemoryStream {
  * is primarily intended for use in unit tests as it can only replay data when the object is still
  * available.
  */
-case class MemoryStream[A : Encoder](id: Int, sqlContext: SQLContext)
+case class MemoryStream[A: Encoder](id: Int, sqlContext: SQLContext)
     extends Source with Logging {
   protected val encoder = encoderFor[A]
   protected val logicalPlan = StreamingExecutionRelation(this)
@@ -68,7 +68,7 @@ case class MemoryStream[A : Encoder](id: Int, sqlContext: SQLContext)
    * -1 is used in calculations below and isn't just an arbitrary constant.
    */
   @GuardedBy("this")
-  protected var lastOffsetCommitted : LongOffset = new LongOffset(-1)
+  protected var lastOffsetCommitted: LongOffset = new LongOffset(-1)
 
   def schema: StructType = encoder.schema
 
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/socket.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/socket.scala
index 8e63207959575..28d30db349724 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/socket.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/socket.scala
@@ -65,7 +65,7 @@ class TextSocketSource(host: String, port: Int, includeTimestamp: Boolean, sqlCo
   protected var currentOffset: LongOffset = new LongOffset(-1)
 
   @GuardedBy("this")
-  protected var lastOffsetCommitted : LongOffset = new LongOffset(-1)
+  protected var lastOffsetCommitted: LongOffset = new LongOffset(-1)
 
   initialize()
 
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala
index bae7a15165e43..c6c9e9f20c950 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala
@@ -237,7 +237,7 @@ private[state] class HDFSBackedStateStoreProvider extends StateStoreProvider wit
 
   /* Internal fields and methods */
 
-  @volatile private var stateStoreId_ : StateStoreId = _
+  @volatile private var stateStoreId_: StateStoreId = _
   @volatile private var keySchema: StructType = _
   @volatile private var valueSchema: StructType = _
   @volatile private var storeConf: StateStoreConf = _
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/expressions/Window.scala b/sql/core/src/main/scala/org/apache/spark/sql/expressions/Window.scala
index cd79128d8f375..6667e9f6ec7f2 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/expressions/Window.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/expressions/Window.scala
@@ -44,7 +44,7 @@ object Window {
    */
   @scala.annotation.varargs
   def partitionBy(colName: String, colNames: String*): WindowSpec = {
-    spec.partitionBy(colName, colNames : _*)
+    spec.partitionBy(colName, colNames: _*)
   }
 
   /**
@@ -53,7 +53,7 @@ object Window {
    */
   @scala.annotation.varargs
   def partitionBy(cols: Column*): WindowSpec = {
-    spec.partitionBy(cols : _*)
+    spec.partitionBy(cols: _*)
   }
 
   /**
@@ -62,7 +62,7 @@ object Window {
    */
   @scala.annotation.varargs
   def orderBy(colName: String, colNames: String*): WindowSpec = {
-    spec.orderBy(colName, colNames : _*)
+    spec.orderBy(colName, colNames: _*)
   }
 
   /**
@@ -71,7 +71,7 @@ object Window {
    */
   @scala.annotation.varargs
   def orderBy(cols: Column*): WindowSpec = {
-    spec.orderBy(cols : _*)
+    spec.orderBy(cols: _*)
   }
 
   /**
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
index 839cbf42024e3..6ae6ae594af22 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
@@ -106,7 +106,7 @@ object functions {
    * @group normal_funcs
    * @since 2.2.0
    */
-  def typedLit[T : TypeTag](literal: T): Column = literal match {
+  def typedLit[T: TypeTag](literal: T): Column = literal match {
     case c: Column => c
     case s: Symbol => new ColumnName(s.name)
     case _ => Column(Literal.create(literal))
@@ -373,7 +373,7 @@ object functions {
    */
   @scala.annotation.varargs
   def countDistinct(columnName: String, columnNames: String*): Column =
-    countDistinct(Column(columnName), columnNames.map(Column.apply) : _*)
+    countDistinct(Column(columnName), columnNames.map(Column.apply): _*)
 
   /**
    * Aggregate function: returns the population covariance for two columns.
@@ -509,7 +509,7 @@ object functions {
    * @since 2.0.0
    */
   def grouping_id(colName: String, colNames: String*): Column = {
-    grouping_id((Seq(colName) ++ colNames).map(n => Column(n)) : _*)
+    grouping_id((Seq(colName) ++ colNames).map(n => Column(n)): _*)
   }
 
   /**
@@ -992,7 +992,7 @@ object functions {
    */
   @scala.annotation.varargs
   def array(colName: String, colNames: String*): Column = {
-    array((colName +: colNames).map(col) : _*)
+    array((colName +: colNames).map(col): _*)
   }
 
   /**
@@ -1228,7 +1228,7 @@ object functions {
    */
   @scala.annotation.varargs
   def struct(colName: String, colNames: String*): Column = {
-    struct((colName +: colNames).map(col) : _*)
+    struct((colName +: colNames).map(col): _*)
   }
 
   /**
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/jdbc/AggregatedDialect.scala b/sql/core/src/main/scala/org/apache/spark/sql/jdbc/AggregatedDialect.scala
index 467d8d62d1b7f..d2c31d6e04107 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/jdbc/AggregatedDialect.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/jdbc/AggregatedDialect.scala
@@ -30,7 +30,7 @@ private class AggregatedDialect(dialects: List[JdbcDialect]) extends JdbcDialect
 
   require(dialects.nonEmpty)
 
-  override def canHandle(url : String): Boolean =
+  override def canHandle(url: String): Boolean =
     dialects.map(_.canHandle(url)).reduce(_ && _)
 
   override def getCatalystType(
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/jdbc/JdbcDialects.scala b/sql/core/src/main/scala/org/apache/spark/sql/jdbc/JdbcDialects.scala
index a86a86d408906..622789723b455 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/jdbc/JdbcDialects.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/jdbc/JdbcDialects.scala
@@ -32,7 +32,7 @@ import org.apache.spark.sql.types._
  */
 @DeveloperApi
 @InterfaceStability.Evolving
-case class JdbcType(databaseTypeDefinition : String, jdbcNullType : Int)
+case class JdbcType(databaseTypeDefinition: String, jdbcNullType: Int)
 
 /**
  * :: DeveloperApi ::
@@ -62,7 +62,7 @@ abstract class JdbcDialect extends Serializable {
    * @return True if the dialect can be applied on the given jdbc url.
    * @throws NullPointerException if the url is null.
    */
-  def canHandle(url : String): Boolean
+  def canHandle(url: String): Boolean
 
   /**
    * Get the custom datatype mapping for the given jdbc meta information.
@@ -153,7 +153,7 @@ object JdbcDialects {
    *
    * @param dialect The new dialect.
    */
-  def registerDialect(dialect: JdbcDialect) : Unit = {
+  def registerDialect(dialect: JdbcDialect): Unit = {
     dialects = dialect :: dialects.filterNot(_ == dialect)
   }
 
@@ -162,7 +162,7 @@ object JdbcDialects {
    *
    * @param dialect The jdbc dialect.
    */
-  def unregisterDialect(dialect : JdbcDialect) : Unit = {
+  def unregisterDialect(dialect: JdbcDialect): Unit = {
     dialects = dialects.filterNot(_ == dialect)
   }
 
@@ -193,5 +193,5 @@ object JdbcDialects {
  * NOOP dialect object, always returning the neutral element.
  */
 private object NoopDialect extends JdbcDialect {
-  override def canHandle(url : String): Boolean = true
+  override def canHandle(url: String): Boolean = true
 }
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/jdbc/MySQLDialect.scala b/sql/core/src/main/scala/org/apache/spark/sql/jdbc/MySQLDialect.scala
index b2cff7877d8b5..634f643b9b0fd 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/jdbc/MySQLDialect.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/jdbc/MySQLDialect.scala
@@ -23,7 +23,7 @@ import org.apache.spark.sql.types.{BooleanType, DataType, LongType, MetadataBuil
 
 private case object MySQLDialect extends JdbcDialect {
 
-  override def canHandle(url : String): Boolean = url.startsWith("jdbc:mysql")
+  override def canHandle(url: String): Boolean = url.startsWith("jdbc:mysql")
 
   override def getCatalystType(
       sqlType: Int, typeName: String, size: Int, md: MetadataBuilder): Option[DataType] = {
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/streaming/progress.scala b/sql/core/src/main/scala/org/apache/spark/sql/streaming/progress.scala
index fb590e7df996b..78dfae96cb340 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/streaming/progress.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/streaming/progress.scala
@@ -116,7 +116,7 @@ class StreamingQueryProgress private[sql](
     def safeMapToJValue[T](map: ju.Map[String, T], valueToJValue: T => JValue): JValue = {
       if (map.isEmpty) return JNothing
       val keys = map.asScala.keySet.toSeq.sorted
-      keys.map { k => k -> valueToJValue(map.get(k)) : JObject }.reduce(_ ~ _)
+      keys.map { k => k -> valueToJValue(map.get(k)): JObject }.reduce(_ ~ _)
     }
 
     ("id" -> JString(id.toString)) ~
diff --git a/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ReflectionUtils.scala b/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ReflectionUtils.scala
index 599294dfbb7d7..d1d8a68f6d196 100644
--- a/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ReflectionUtils.scala
+++ b/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ReflectionUtils.scala
@@ -18,7 +18,7 @@
 package org.apache.spark.sql.hive.thriftserver
 
 private[hive] object ReflectionUtils {
-  def setSuperField(obj : Object, fieldName: String, fieldValue: Object) {
+  def setSuperField(obj: Object, fieldName: String, fieldValue: Object) {
     setAncestorField(obj, 1, fieldName, fieldValue)
   }
 
diff --git a/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala b/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala
index 33e18a8da60fb..b57347fd4550d 100644
--- a/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala
+++ b/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala
@@ -327,7 +327,7 @@ private[hive] class SparkSQLCLIDriver extends CliDriver with Logging {
         // scalastyle:off println
         if (proc.isInstanceOf[Driver] || proc.isInstanceOf[SetProcessor] ||
           proc.isInstanceOf[AddResourceProcessor] || proc.isInstanceOf[ListResourceProcessor] ||
-          proc.isInstanceOf[ResetProcessor] ) {
+          proc.isInstanceOf[ResetProcessor]) {
           val driver = new SparkSQLDriver
 
           driver.init()
@@ -345,7 +345,7 @@ private[hive] class SparkSQLCLIDriver extends CliDriver with Logging {
           if (ret != 0) {
             // For analysis exception, only the error is printed out to the console.
             rc.getException() match {
-              case e : AnalysisException =>
+              case e: AnalysisException =>
                 err.println(s"""Error in query: ${e.getMessage}""")
               case _ => err.println(rc.getErrorMessage())
             }
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala
index 4dec2f71b8a50..9a3fd5b8e0e4e 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala
@@ -784,8 +784,8 @@ private[hive] trait HiveInspectors {
     case DecimalType() => PrimitiveObjectInspectorFactory.javaHiveDecimalObjectInspector
     case StructType(fields) =>
       ObjectInspectorFactory.getStandardStructObjectInspector(
-        java.util.Arrays.asList(fields.map(f => f.name) : _*),
-        java.util.Arrays.asList(fields.map(f => toInspector(f.dataType)) : _*))
+        java.util.Arrays.asList(fields.map(f => f.name): _*),
+        java.util.Arrays.asList(fields.map(f => toInspector(f.dataType)): _*))
   }
 
   /**
@@ -1030,8 +1030,8 @@ private[hive] trait HiveInspectors {
         getListTypeInfo(elemType.toTypeInfo)
       case StructType(fields) =>
         getStructTypeInfo(
-          java.util.Arrays.asList(fields.map(_.name) : _*),
-          java.util.Arrays.asList(fields.map(_.dataType.toTypeInfo) : _*))
+          java.util.Arrays.asList(fields.map(_.name): _*),
+          java.util.Arrays.asList(fields.map(_.dataType.toTypeInfo): _*))
       case MapType(keyType, valueType, _) =>
         getMapTypeInfo(keyType.toTypeInfo, valueType.toTypeInfo)
       case BinaryType => binaryTypeInfo
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala
index a83ad61b204ad..34c76d5aefefd 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala
@@ -91,7 +91,7 @@ private[hive] case class HiveSimpleUDF(
     val ret = FunctionRegistry.invoke(
       method,
       function,
-      conversionHelper.convertIfNecessary(inputs : _*): _*)
+      conversionHelper.convertIfNecessary(inputs: _*): _*)
     unwrapper(ret)
   }
 
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/test/TestHive.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/test/TestHive.scala
index 4e1792321c89b..de06b8625bd92 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/test/TestHive.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/test/TestHive.scala
@@ -248,7 +248,7 @@ private[hive] class TestHiveSparkSession(
     new File(Thread.currentThread().getContextClassLoader.getResource(path).getFile)
   }
 
-  private def quoteHiveFile(path : String) = if (Utils.isWindows) {
+  private def quoteHiveFile(path: String) = if (Utils.isWindows) {
     getHiveFile(path).getPath.replace('\\', '/')
   } else {
     getHiveFile(path).getPath

From abf2994c475cfd40b36132286fc6124e75542288 Mon Sep 17 00:00:00 2001
From: Wang Gengliang 
Date: Thu, 29 Jun 2017 16:20:57 -0700
Subject: [PATCH 2/8] resolve hard ones

---
 .../scala/org/apache/spark/Accumulable.scala  |  2 +
 .../spark/broadcast/BroadcastManager.scala    |  4 +-
 .../broadcast/TorrentBroadcastFactory.scala   |  4 +-
 .../spark/deploy/ExternalShuffleService.scala |  2 +
 .../org/apache/spark/internal/Logging.scala   |  8 ++--
 .../main/scala/org/apache/spark/rdd/RDD.scala | 22 +++++------
 .../apache/spark/storage/BlockManagerId.scala | 38 +++++++++----------
 .../org/apache/spark/util/MutablePair.scala   |  4 +-
 .../clustering/PowerIterationClustering.scala |  8 +++-
 .../spark/sql/catalyst/dsl/package.scala      |  9 +++--
 .../spark/sql/catalyst/trees/TreeNode.scala   |  4 +-
 .../org/apache/spark/sql/types/Decimal.scala  |  5 ++-
 .../scala/org/apache/spark/sql/Column.scala   |  8 ++--
 .../InsertIntoHadoopFsRelationCommand.scala   |  2 +
 .../state/HDFSBackedStateStoreProvider.scala  |  6 +--
 .../sql/hive/client/HiveClientImpl.scala      |  4 +-
 16 files changed, 74 insertions(+), 56 deletions(-)

diff --git a/core/src/main/scala/org/apache/spark/Accumulable.scala b/core/src/main/scala/org/apache/spark/Accumulable.scala
index 5532931e2a794..41c233e131df0 100644
--- a/core/src/main/scala/org/apache/spark/Accumulable.scala
+++ b/core/src/main/scala/org/apache/spark/Accumulable.scala
@@ -68,7 +68,9 @@ class Accumulable[R, T] private (
   }
 
   private[spark] def this(initialValue: R, param: AccumulableParam[R, T], name: Option[String]) = {
+    // scalastyle:off
     this(initialValue, param, name, false /* countFailedValues */)
+    // scalastyle:on
   }
 
   def this(initialValue: R, param: AccumulableParam[R, T]) = this(initialValue, param, None)
diff --git a/core/src/main/scala/org/apache/spark/broadcast/BroadcastManager.scala b/core/src/main/scala/org/apache/spark/broadcast/BroadcastManager.scala
index 8e0fac9ba1f62..d82fadcd1715e 100644
--- a/core/src/main/scala/org/apache/spark/broadcast/BroadcastManager.scala
+++ b/core/src/main/scala/org/apache/spark/broadcast/BroadcastManager.scala
@@ -52,8 +52,8 @@ private[spark] class BroadcastManager(
 
   private val nextBroadcastId = new AtomicLong(0)
 
-  def newBroadcast[T: ClassTag](value_: T, isLocal: Boolean): Broadcast[T] = {
-    broadcastFactory.newBroadcast[T](value_, isLocal, nextBroadcastId.getAndIncrement())
+  def newBroadcast[T: ClassTag](_value: T, isLocal: Boolean): Broadcast[T] = {
+    broadcastFactory.newBroadcast[T](_value, isLocal, nextBroadcastId.getAndIncrement())
   }
 
   def unbroadcast(id: Long, removeFromDriver: Boolean, blocking: Boolean) {
diff --git a/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcastFactory.scala b/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcastFactory.scala
index b6f35b73e8359..52ca4493f1c45 100644
--- a/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcastFactory.scala
+++ b/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcastFactory.scala
@@ -30,8 +30,8 @@ private[spark] class TorrentBroadcastFactory extends BroadcastFactory {
 
   override def initialize(isDriver: Boolean, conf: SparkConf, securityMgr: SecurityManager) { }
 
-  override def newBroadcast[T: ClassTag](value_: T, isLocal: Boolean, id: Long): Broadcast[T] = {
-    new TorrentBroadcast[T](value_, id)
+  override def newBroadcast[T: ClassTag](_value: T, isLocal: Boolean, id: Long): Broadcast[T] = {
+    new TorrentBroadcast[T](_value, id)
   }
 
   override def stop() { }
diff --git a/core/src/main/scala/org/apache/spark/deploy/ExternalShuffleService.scala b/core/src/main/scala/org/apache/spark/deploy/ExternalShuffleService.scala
index 8d491ddf6e092..cc1e4fe89ce8f 100644
--- a/core/src/main/scala/org/apache/spark/deploy/ExternalShuffleService.scala
+++ b/core/src/main/scala/org/apache/spark/deploy/ExternalShuffleService.scala
@@ -89,7 +89,9 @@ class ExternalShuffleService(sparkConf: SparkConf, securityManager: SecurityMana
 
   /** Clean up all shuffle files associated with an application that has exited. */
   def applicationRemoved(appId: String): Unit = {
+    // scalastyle:off
     blockHandler.applicationRemoved(appId, true /* cleanupLocalDirs */)
+    // scalastyle:on
   }
 
   def stop() {
diff --git a/core/src/main/scala/org/apache/spark/internal/Logging.scala b/core/src/main/scala/org/apache/spark/internal/Logging.scala
index 28e17389c69a5..c4a13287b4367 100644
--- a/core/src/main/scala/org/apache/spark/internal/Logging.scala
+++ b/core/src/main/scala/org/apache/spark/internal/Logging.scala
@@ -32,7 +32,7 @@ trait Logging {
 
   // Make the log field transient so that objects with Logging can
   // be serialized and used on another machine
-  @transient private var log_: Logger = null
+  @transient private var _log: Logger = null
 
   // Method to get the logger name for this object
   protected def logName = {
@@ -42,11 +42,11 @@ trait Logging {
 
   // Method to get or create the logger for this object
   protected def log: Logger = {
-    if (log_ == null) {
+    if (_log == null) {
       initializeLogIfNecessary(false)
-      log_ = LoggerFactory.getLogger(logName)
+      _log = LoggerFactory.getLogger(logName)
     }
-    log_
+    _log
   }
 
   // Log methods that take only a String
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 6ad6c9db6ca73..0b8c60fc9e581 100644
--- a/core/src/main/scala/org/apache/spark/rdd/RDD.scala
+++ b/core/src/main/scala/org/apache/spark/rdd/RDD.scala
@@ -223,8 +223,8 @@ abstract class RDD[T: ClassTag](
 
   // Our dependencies and partitions will be gotten by calling subclass's methods below, and will
   // be overwritten when we're checkpointed
-  private var dependencies_: Seq[Dependency[_]] = null
-  @transient private var partitions_: Array[Partition] = null
+  private var _dependencies: Seq[Dependency[_]] = null
+  @transient private var _partitions: Array[Partition] = null
 
   /** An Option holding our checkpoint RDD, if we are checkpointed */
   private def checkpointRDD: Option[CheckpointRDD[T]] = checkpointData.flatMap(_.checkpointRDD)
@@ -235,10 +235,10 @@ abstract class RDD[T: ClassTag](
    */
   final def dependencies: Seq[Dependency[_]] = {
     checkpointRDD.map(r => List(new OneToOneDependency(r))).getOrElse {
-      if (dependencies_ == null) {
-        dependencies_ = getDependencies
+      if (_dependencies == null) {
+        _dependencies = getDependencies
       }
-      dependencies_
+      _dependencies
     }
   }
 
@@ -248,14 +248,14 @@ abstract class RDD[T: ClassTag](
    */
   final def partitions: Array[Partition] = {
     checkpointRDD.map(_.partitions).getOrElse {
-      if (partitions_ == null) {
-        partitions_ = getPartitions
-        partitions_.zipWithIndex.foreach { case (partition, index) =>
+      if (_partitions == null) {
+        _partitions = getPartitions
+        _partitions.zipWithIndex.foreach { case (partition, index) =>
           require(partition.index == index,
             s"partitions($index).partition == ${partition.index}, but it should equal $index")
         }
       }
-      partitions_
+      _partitions
     }
   }
 
@@ -1743,7 +1743,7 @@ abstract class RDD[T: ClassTag](
    */
   private[spark] def markCheckpointed(): Unit = {
     clearDependencies()
-    partitions_ = null
+    _partitions = null
     deps = null    // Forget the constructor argument for dependencies too
   }
 
@@ -1754,7 +1754,7 @@ abstract class RDD[T: ClassTag](
    * logic. See [[org.apache.spark.rdd.UnionRDD]] for an example.
    */
   protected def clearDependencies() {
-    dependencies_ = null
+    _dependencies = null
   }
 
   /** A description of this RDD and its recursive dependencies for debugging. */
diff --git a/core/src/main/scala/org/apache/spark/storage/BlockManagerId.scala b/core/src/main/scala/org/apache/spark/storage/BlockManagerId.scala
index 5c7d535278577..b64c346324bfc 100644
--- a/core/src/main/scala/org/apache/spark/storage/BlockManagerId.scala
+++ b/core/src/main/scala/org/apache/spark/storage/BlockManagerId.scala
@@ -35,19 +35,19 @@ import org.apache.spark.util.Utils
  */
 @DeveloperApi
 class BlockManagerId private (
-    private var executorId_: String,
-    private var host_: String,
-    private var port_: Int,
-    private var topologyInfo_: Option[String])
+    private var _executorId: String,
+    private var _host: String,
+    private var _port: Int,
+    private var _topologyInfo: Option[String])
   extends Externalizable {
 
   private def this() = this(null, null, 0, None)  // For deserialization only
 
-  def executorId: String = executorId_
+  def executorId: String = _executorId
 
-  if (null != host_) {
-    Utils.checkHost(host_)
-    assert (port_ > 0)
+  if (null != _host) {
+    Utils.checkHost(_host)
+    assert (_port > 0)
   }
 
   def hostPort: String = {
@@ -57,11 +57,11 @@ class BlockManagerId private (
     host + ":" + port
   }
 
-  def host: String = host_
+  def host: String = _host
 
-  def port: Int = port_
+  def port: Int = _port
 
-  def topologyInfo: Option[String] = topologyInfo_
+  def topologyInfo: Option[String] = _topologyInfo
 
   def isDriver: Boolean = {
     executorId == SparkContext.DRIVER_IDENTIFIER ||
@@ -69,20 +69,20 @@ class BlockManagerId private (
   }
 
   override def writeExternal(out: ObjectOutput): Unit = Utils.tryOrIOException {
-    out.writeUTF(executorId_)
-    out.writeUTF(host_)
-    out.writeInt(port_)
-    out.writeBoolean(topologyInfo_.isDefined)
+    out.writeUTF(_executorId)
+    out.writeUTF(_host)
+    out.writeInt(_port)
+    out.writeBoolean(_topologyInfo.isDefined)
     // we only write topologyInfo if we have it
     topologyInfo.foreach(out.writeUTF(_))
   }
 
   override def readExternal(in: ObjectInput): Unit = Utils.tryOrIOException {
-    executorId_ = in.readUTF()
-    host_ = in.readUTF()
-    port_ = in.readInt()
+    _executorId = in.readUTF()
+    _host = in.readUTF()
+    _port = in.readInt()
     val isTopologyInfoAvailable = in.readBoolean()
-    topologyInfo_ = if (isTopologyInfoAvailable) Option(in.readUTF()) else None
+    _topologyInfo = if (isTopologyInfoAvailable) Option(in.readUTF()) else None
   }
 
   @throws(classOf[IOException])
diff --git a/core/src/main/scala/org/apache/spark/util/MutablePair.scala b/core/src/main/scala/org/apache/spark/util/MutablePair.scala
index 3d95b7869f494..3c25b415f83b8 100644
--- a/core/src/main/scala/org/apache/spark/util/MutablePair.scala
+++ b/core/src/main/scala/org/apache/spark/util/MutablePair.scala
@@ -28,8 +28,8 @@ import org.apache.spark.annotation.DeveloperApi
  * @param  _2   Element 2 of this MutablePair
  */
 @DeveloperApi
-case class MutablePair[@specialized(Int, Long, Double, Char, Boolean/* , AnyRef */) T1,
-                       @specialized(Int, Long, Double, Char, Boolean/* , AnyRef */) T2]
+case class MutablePair[@specialized(Int, Long, Double, Char, Boolean) T1,
+                       @specialized(Int, Long, Double, Char, Boolean) T2]
   (var _1: T1, var _2: T2)
   extends Product2[T1, T2]
 {
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/PowerIterationClustering.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/PowerIterationClustering.scala
index b2437b845f826..a7d4c15ea8e87 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/PowerIterationClustering.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/PowerIterationClustering.scala
@@ -270,9 +270,11 @@ object PowerIterationClustering extends Logging {
     Graph(vD, graph.edges)
       .mapTriplets(
         e => e.attr / math.max(e.srcAttr, MLUtils.EPSILON),
+        // scalastyle:off
         new TripletFields(/* useSrc */ true,
                           /* useDst */ false,
                           /* useEdge */ true))
+        // scalastyle:on
   }
 
   /**
@@ -301,9 +303,11 @@ object PowerIterationClustering extends Logging {
     Graph(vD, gA.edges)
       .mapTriplets(
         e => e.attr / math.max(e.srcAttr, MLUtils.EPSILON),
+        // scalastyle:off
         new TripletFields(/* useSrc */ true,
-                          /* useDst */ false,
-                          /* useEdge */ true))
+          /* useDst */ false,
+          /* useEdge */ true))
+        // scalastyle:on
   }
 
   /**
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala
index c602f47472e8f..4291f368bcde1 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala
@@ -63,10 +63,11 @@ package object dsl {
   trait ImplicitOperators {
     def expr: Expression
 
-    def unary_-: Expression = UnaryMinus(expr)
-    def unary_!: Predicate = Not(expr)
-    def unary_~: Expression = BitwiseNot(expr)
-
+    // scalastyle:off
+    def unary_- : Expression = UnaryMinus(expr)
+    def unary_! : Predicate = Not(expr)
+    def unary_~ : Expression = BitwiseNot(expr)
+    // scalastyle:on
     def + (other: Expression): Expression = Add(expr, other)
     def - (other: Expression): Expression = Subtract(expr, other)
     def * (other: Expression): Expression = Multiply(expr, other)
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala
index 7375a0bcbae75..56b0971b9faa6 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/trees/TreeNode.scala
@@ -402,7 +402,9 @@ abstract class TreeNode[BaseType <: TreeNode[BaseType]] extends Product {
         false
       } else {
         val argsArray: Array[Class[_]] = allArgs.map(_.getClass)
-        ClassUtils.isAssignable(argsArray, ctor.getParameterTypes, true /* autoboxing */)
+        // scalastyle:off
+        ClassUtils.isAssignable(argsArray, ctor.getParameterTypes, true  /* autoboxing */)
+        // scalastyle:on
       }
     }.getOrElse(ctors.maxBy(_.getParameterTypes.length)) // fall back to older heuristic
 
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/types/Decimal.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/types/Decimal.scala
index 58b978388d60f..be8043bda33d5 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/types/Decimal.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/types/Decimal.scala
@@ -380,8 +380,9 @@ final class Decimal extends Ordered[Decimal] with Serializable {
     else Decimal(toJavaBigDecimal.remainder(that.toJavaBigDecimal, MATH_CONTEXT))
 
   def remainder(that: Decimal): Decimal = this % that
-
-  def unary_-: Decimal = {
+  // scalastyle:off
+  def unary_- : Decimal = {
+    // scalastyle:on
     if (decimalVal.ne(null)) {
       Decimal(-decimalVal, precision, scale)
     } else {
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/Column.scala b/sql/core/src/main/scala/org/apache/spark/sql/Column.scala
index b545567029735..7b62777e44154 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/Column.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/Column.scala
@@ -211,7 +211,7 @@ class Column(val expr: Expression) extends Logging {
   def apply(extraction: Any): Column = withExpr {
     UnresolvedExtractValue(expr, lit(extraction).expr)
   }
-
+  // scalastyle:off
   /**
    * Unary minus, i.e. negate the expression.
    * {{{
@@ -226,7 +226,7 @@ class Column(val expr: Expression) extends Logging {
    * @group expr_ops
    * @since 1.3.0
    */
-  def unary_-: Column = withExpr { UnaryMinus(expr) }
+  def unary_- : Column = withExpr { UnaryMinus(expr) }
 
   /**
    * Inversion of boolean expression, i.e. NOT.
@@ -242,7 +242,9 @@ class Column(val expr: Expression) extends Logging {
    * @group expr_ops
    * @since 1.3.0
    */
-  def unary_!: Column = withExpr { Not(expr) }
+
+  def unary_! : Column = withExpr { Not(expr) }
+  // scalastyle:on
 
   /**
    * Equality test.
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/InsertIntoHadoopFsRelationCommand.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/InsertIntoHadoopFsRelationCommand.scala
index ab26f2affbce5..f1dee6947bc4c 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/InsertIntoHadoopFsRelationCommand.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/InsertIntoHadoopFsRelationCommand.scala
@@ -138,7 +138,9 @@ case class InsertIntoHadoopFsRelationCommand(
               AlterTableDropPartitionCommand(
                 catalogTable.get.identifier, deletedPartitions.toSeq,
                 ifExists = true, purge = false,
+                // scalastyle:off
                 retainData = true /* already deleted */).run(sparkSession)
+                // scalastyle:on
             }
           }
         }
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala
index c6c9e9f20c950..64076b9a7c234 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala
@@ -205,7 +205,7 @@ private[state] class HDFSBackedStateStoreProvider extends StateStoreProvider wit
       indexOrdinal: Option[Int], // for sorting the data
       storeConf: StateStoreConf,
       hadoopConf: Configuration): Unit = {
-    this.stateStoreId_ = stateStoreId
+    this._stateStoreId = stateStoreId
     this.keySchema = keySchema
     this.valueSchema = valueSchema
     this.storeConf = storeConf
@@ -213,7 +213,7 @@ private[state] class HDFSBackedStateStoreProvider extends StateStoreProvider wit
     fs.mkdirs(baseDir)
   }
 
-  override def stateStoreId: StateStoreId = stateStoreId_
+  override def stateStoreId: StateStoreId = _stateStoreId
 
   /** Do maintenance backing data files, including creating snapshots and cleaning up old files */
   override def doMaintenance(): Unit = {
@@ -237,7 +237,7 @@ private[state] class HDFSBackedStateStoreProvider extends StateStoreProvider wit
 
   /* Internal fields and methods */
 
-  @volatile private var stateStoreId_: StateStoreId = _
+  @volatile private var _stateStoreId: StateStoreId = _
   @volatile private var keySchema: StructType = _
   @volatile private var valueSchema: StructType = _
   @volatile private var storeConf: StateStoreConf = _
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
index be024adac8eb0..039b4546bf972 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
@@ -365,7 +365,9 @@ private[hive] class HiveClientImpl(
   }
 
   override def tableExists(dbName: String, tableName: String): Boolean = withHiveState {
-    Option(client.getTable(dbName, tableName, false /* do not throw exception */)).nonEmpty
+    // scalastyle:off
+    Option(client.getTable(dbName, tableName, false/* do not throw exception */)).nonEmpty
+    // scalastyle:on
   }
 
   override def getTableOption(

From d509834bdc3eeea98fe4066ef14a1bf6a4b166a6 Mon Sep 17 00:00:00 2001
From: Wang Gengliang 
Date: Thu, 29 Jun 2017 16:24:47 -0700
Subject: [PATCH 3/8] fix one error

---
 .../spark/mllib/clustering/PowerIterationClustering.scala       | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/PowerIterationClustering.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/PowerIterationClustering.scala
index a7d4c15ea8e87..8e543a995ea63 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/PowerIterationClustering.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/PowerIterationClustering.scala
@@ -368,9 +368,11 @@ object PowerIterationClustering extends Logging {
       val v = curG.aggregateMessages[Double](
         sendMsg = ctx => ctx.sendToSrc(ctx.attr * ctx.dstAttr),
         mergeMsg = _ + _,
+        // scalastyle:off
         new TripletFields(/* useSrc */ false,
                           /* useDst */ true,
                           /* useEdge */ true)).cache()
+        // scalastyle:on
       // normalize v
       val norm = v.values.map(math.abs).sum()
       logInfo(s"$msgPrefix: norm(v) = $norm.")

From ffbcbbb0d9028c8a2876b4a64f54f7a464eba798 Mon Sep 17 00:00:00 2001
From: Wang Gengliang 
Date: Thu, 29 Jun 2017 16:28:09 -0700
Subject: [PATCH 4/8] resolve more

---
 .../org/apache/spark/AccumulatorSuite.scala   |  6 +-
 .../apache/spark/ContextCleanerSuite.scala    |  6 +-
 .../test/scala/org/apache/spark/Smuggle.scala |  4 +-
 .../apache/spark/deploy/DeployTestUtils.scala |  2 +-
 .../spark/deploy/SparkSubmitSuite.scala       |  2 +-
 .../history/ApplicationCacheSuite.scala       |  4 +-
 .../spark/deploy/worker/WorkerSuite.scala     |  2 +-
 .../org/apache/spark/rdd/JdbcRDDSuite.scala   |  4 +-
 .../spark/rdd/ZippedPartitionsSuite.scala     |  2 +-
 .../org/apache/spark/rpc/RpcEnvSuite.scala    |  8 +-
 .../spark/scheduler/DAGSchedulerSuite.scala   |  2 +-
 .../GenericAvroSerializerSuite.scala          |  2 +-
 .../serializer/KryoSerializerSuite.scala      |  8 +-
 .../BypassMergeSortShuffleWriterSuite.scala   |  8 +-
 .../spark/storage/FlatmapIteratorSuite.scala  |  2 +-
 .../ui/jobs/JobProgressListenerSuite.scala    |  2 +-
 .../spark/util/ClosureCleanerSuite.scala      |  4 +-
 .../apache/spark/util/FileAppenderSuite.scala |  8 +-
 .../spark/util/SizeEstimatorSuite.scala       |  2 +-
 .../org/apache/spark/util/UtilsSuite.scala    |  2 +-
 .../spark/util/collection/BitSetSuite.scala   | 46 ++++-----
 .../sql/kafka010/KafkaRelationSuite.scala     |  2 +-
 .../org/apache/spark/graphx/GraphSuite.scala  |  4 +-
 .../graphx/lib/ConnectedComponentsSuite.scala |  8 +-
 .../spark/graphx/lib/PageRankSuite.scala      |  2 +-
 .../spark/graphx/lib/TriangleCountSuite.scala |  2 +-
 .../ml/classification/NaiveBayesSuite.scala   |  2 +-
 .../ml/clustering/GaussianMixtureSuite.scala  |  8 +-
 .../spark/ml/feature/ImputerSuite.scala       | 12 +--
 .../ml/feature/QuantileDiscretizerSuite.scala |  2 +-
 .../classification/NaiveBayesSuite.scala      |  2 +-
 .../clustering/GaussianMixtureSuite.scala     |  8 +-
 .../evaluation/MultilabelMetricsSuite.scala   |  2 +-
 .../deploy/yarn/YarnAllocatorSuite.scala      |  2 +-
 .../encoders/EncoderErrorMessageSuite.scala   |  2 +-
 .../encoders/ExpressionEncoderSuite.scala     |  6 +-
 .../expressions/StringExpressionsSuite.scala  |  2 +-
 .../aggregate/PercentileSuite.scala           |  6 +-
 .../BooleanSimplificationSuite.scala          | 12 +--
 .../optimizer/ColumnPruningSuite.scala        |  2 +-
 .../optimizer/ConstantFoldingSuite.scala      |  2 +-
 .../EliminateSerializationSuite.scala         |  2 +-
 .../StarJoinCostBasedReorderSuite.scala       |  2 +-
 .../optimizer/StarJoinReorderSuite.scala      |  2 +-
 .../TypedFilterOptimizationSuite.scala        |  2 +-
 .../optimizer/complexTypesSuite.scala         |  4 +-
 .../parser/ExpressionParserSuite.scala        |  4 +-
 .../spark/sql/DatasetAggregatorSuite.scala    |  2 +-
 .../org/apache/spark/sql/DatasetSuite.scala   | 10 +-
 .../org/apache/spark/sql/QueryTest.scala      |  2 +-
 .../org/apache/spark/sql/SQLQuerySuite.scala  |  4 +-
 .../apache/spark/sql/SessionStateSuite.scala  |  2 +-
 .../spark/sql/StatisticsCollectionSuite.scala |  6 +-
 .../spark/sql/execution/ReferenceSort.scala   |  2 +-
 .../benchmark/BenchmarkWideTable.scala        |  2 +-
 .../benchmark/UnsafeArrayDataBenchmark.scala  |  2 +-
 .../datasources/parquet/ParquetIOSuite.scala  |  2 +-
 .../parquet/ParquetQuerySuite.scala           |  6 +-
 .../execution/joins/BroadcastJoinSuite.scala  |  2 +-
 .../streaming/state/StateStoreSuite.scala     |  2 +-
 .../org/apache/spark/sql/jdbc/JDBCSuite.scala |  4 +-
 .../spark/sql/jdbc/JDBCWriteSuite.scala       |  2 +-
 .../spark/sql/streaming/StreamTest.scala      | 10 +-
 .../spark/sql/hive/HiveInspectorSuite.scala   |  4 +-
 .../spark/sql/hive/StatisticsSuite.scala      |  2 +-
 .../sql/hive/execution/HiveDDLSuite.scala     | 12 +--
 .../sql/hive/execution/HiveQuerySuite.scala   |  2 +-
 .../apache/spark/sql/hive/parquetSuites.scala | 10 +-
 .../streaming/BasicOperationsSuite.scala      | 98 +++++++++----------
 .../spark/streaming/CheckpointSuite.scala     |  2 +-
 .../streaming/ReceivedBlockHandlerSuite.scala |  2 +-
 .../spark/streaming/UISeleniumSuite.scala     |  6 +-
 .../streaming/WindowOperationsSuite.scala     | 54 +++++-----
 73 files changed, 241 insertions(+), 241 deletions(-)

diff --git a/core/src/test/scala/org/apache/spark/AccumulatorSuite.scala b/core/src/test/scala/org/apache/spark/AccumulatorSuite.scala
index 3990ee1ec326d..78c0069c2de77 100644
--- a/core/src/test/scala/org/apache/spark/AccumulatorSuite.scala
+++ b/core/src/test/scala/org/apache/spark/AccumulatorSuite.scala
@@ -47,15 +47,15 @@ class AccumulatorSuite extends SparkFunSuite with Matchers with LocalSparkContex
 
   implicit def setAccum[A]: AccumulableParam[mutable.Set[A], A] =
     new AccumulableParam[mutable.Set[A], A] {
-      def addInPlace(t1: mutable.Set[A], t2: mutable.Set[A]) : mutable.Set[A] = {
+      def addInPlace(t1: mutable.Set[A], t2: mutable.Set[A]): mutable.Set[A] = {
         t1 ++= t2
         t1
       }
-      def addAccumulator(t1: mutable.Set[A], t2: A) : mutable.Set[A] = {
+      def addAccumulator(t1: mutable.Set[A], t2: A): mutable.Set[A] = {
         t1 += t2
         t1
       }
-      def zero(t: mutable.Set[A]) : mutable.Set[A] = {
+      def zero(t: mutable.Set[A]): mutable.Set[A] = {
         new mutable.HashSet[A]()
       }
     }
diff --git a/core/src/test/scala/org/apache/spark/ContextCleanerSuite.scala b/core/src/test/scala/org/apache/spark/ContextCleanerSuite.scala
index 6724af952505f..c1641bab7a074 100644
--- a/core/src/test/scala/org/apache/spark/ContextCleanerSuite.scala
+++ b/core/src/test/scala/org/apache/spark/ContextCleanerSuite.scala
@@ -523,14 +523,14 @@ class CleanerTester(
     toBeCheckpointIds.synchronized { toBeCheckpointIds.isEmpty }
 
   private def getRDDBlocks(rddId: Int): Seq[BlockId] = {
-    blockManager.master.getMatchingBlockIds( _ match {
+    blockManager.master.getMatchingBlockIds(_ match {
       case RDDBlockId(`rddId`, _) => true
       case _ => false
     }, askSlaves = true)
   }
 
   private def getShuffleBlocks(shuffleId: Int): Seq[BlockId] = {
-    blockManager.master.getMatchingBlockIds( _ match {
+    blockManager.master.getMatchingBlockIds(_ match {
       case ShuffleBlockId(`shuffleId`, _, _) => true
       case ShuffleIndexBlockId(`shuffleId`, _, _) => true
       case _ => false
@@ -538,7 +538,7 @@ class CleanerTester(
   }
 
   private def getBroadcastBlocks(broadcastId: Long): Seq[BlockId] = {
-    blockManager.master.getMatchingBlockIds( _ match {
+    blockManager.master.getMatchingBlockIds(_ match {
       case BroadcastBlockId(`broadcastId`, _) => true
       case _ => false
     }, askSlaves = true)
diff --git a/core/src/test/scala/org/apache/spark/Smuggle.scala b/core/src/test/scala/org/apache/spark/Smuggle.scala
index 9d9217ea1b485..24bd2242e73fb 100644
--- a/core/src/test/scala/org/apache/spark/Smuggle.scala
+++ b/core/src/test/scala/org/apache/spark/Smuggle.scala
@@ -62,7 +62,7 @@ object Smuggle {
   private val lock = new ReentrantReadWriteLock
   private val smuggledObjects = mutable.WeakHashMap.empty[Symbol, Any]
 
-  private def get[T](key: Symbol) : T = {
+  private def get[T](key: Symbol): T = {
     lock.readLock().lock()
     try {
       smuggledObjects(key).asInstanceOf[T]
@@ -78,6 +78,6 @@ object Smuggle {
    * @tparam T
    * @return the smuggled object represented by the wrapper.
    */
-  implicit def unpackSmuggledObject[T](smuggle : Smuggle[T]): T = smuggle.smuggledObject
+  implicit def unpackSmuggledObject[T](smuggle: Smuggle[T]): T = smuggle.smuggledObject
 
 }
diff --git a/core/src/test/scala/org/apache/spark/deploy/DeployTestUtils.scala b/core/src/test/scala/org/apache/spark/deploy/DeployTestUtils.scala
index 55a541d60ea3c..b21aea95b0ce7 100644
--- a/core/src/test/scala/org/apache/spark/deploy/DeployTestUtils.scala
+++ b/core/src/test/scala/org/apache/spark/deploy/DeployTestUtils.scala
@@ -30,7 +30,7 @@ private[deploy] object DeployTestUtils {
     new ApplicationDescription("name", Some(4), 1234, cmd, "appUiUrl")
   }
 
-  def createAppInfo() : ApplicationInfo = {
+  def createAppInfo(): ApplicationInfo = {
     val appDesc = createAppDesc()
     val appInfo = new ApplicationInfo(JsonConstants.appInfoStartTime,
       "id", appDesc, JsonConstants.submitDate, null, Int.MaxValue)
diff --git a/core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala b/core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala
index b089357e7b868..0c4b23aff1cbe 100644
--- a/core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala
+++ b/core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala
@@ -64,7 +64,7 @@ trait TestPrematureExit {
   private[spark] def testPrematureExit(
       input: Array[String],
       searchString: String,
-      mainObject: CommandLineUtils = SparkSubmit) : Unit = {
+      mainObject: CommandLineUtils = SparkSubmit): Unit = {
     val printStream = new BufferPrintStream()
     mainObject.printStream = printStream
 
diff --git a/core/src/test/scala/org/apache/spark/deploy/history/ApplicationCacheSuite.scala b/core/src/test/scala/org/apache/spark/deploy/history/ApplicationCacheSuite.scala
index 871c87415d35d..f98ea0c996215 100644
--- a/core/src/test/scala/org/apache/spark/deploy/history/ApplicationCacheSuite.scala
+++ b/core/src/test/scala/org/apache/spark/deploy/history/ApplicationCacheSuite.scala
@@ -77,7 +77,7 @@ class ApplicationCacheSuite extends SparkFunSuite with Logging with MockitoSugar
     override def getAppUI(appId: String, attemptId: Option[String]): Option[LoadedAppUI] = {
       logDebug(s"getAppUI($appId, $attemptId)")
       getAppUICount += 1
-      instances.get(CacheKey(appId, attemptId)).map( e =>
+      instances.get(CacheKey(appId, attemptId)).map(e =>
         LoadedAppUI(e.ui, updateProbe(appId, attemptId, e.probeTime)))
     }
 
@@ -393,7 +393,7 @@ class ApplicationCacheSuite extends SparkFunSuite with Logging with MockitoSugar
     val ids = new ListBuffer[String]()
     // build a list of applications
     val count = 100
-    for (i <- 1 to count ) {
+    for (i <- 1 to count) {
       val appId = f"app-$i%04d"
       ids += appId
       clock.advance(10)
diff --git a/core/src/test/scala/org/apache/spark/deploy/worker/WorkerSuite.scala b/core/src/test/scala/org/apache/spark/deploy/worker/WorkerSuite.scala
index ce212a7513310..46dc3ab42f584 100644
--- a/core/src/test/scala/org/apache/spark/deploy/worker/WorkerSuite.scala
+++ b/core/src/test/scala/org/apache/spark/deploy/worker/WorkerSuite.scala
@@ -30,7 +30,7 @@ class WorkerSuite extends SparkFunSuite with Matchers with BeforeAndAfter {
   import org.apache.spark.deploy.DeployTestUtils._
 
   def cmd(javaOpts: String*): Command = {
-    Command("", Seq.empty, Map.empty, Seq.empty, Seq.empty, Seq(javaOpts : _*))
+    Command("", Seq.empty, Map.empty, Seq.empty, Seq.empty, Seq(javaOpts: _*))
   }
   def conf(opts: (String, String)*): SparkConf = new SparkConf(loadDefaults = false).setAll(opts)
 
diff --git a/core/src/test/scala/org/apache/spark/rdd/JdbcRDDSuite.scala b/core/src/test/scala/org/apache/spark/rdd/JdbcRDDSuite.scala
index 05013fbc49b8e..380074809de9b 100644
--- a/core/src/test/scala/org/apache/spark/rdd/JdbcRDDSuite.scala
+++ b/core/src/test/scala/org/apache/spark/rdd/JdbcRDDSuite.scala
@@ -78,7 +78,7 @@ class JdbcRDDSuite extends SparkFunSuite with BeforeAndAfter with LocalSparkCont
       () => { DriverManager.getConnection("jdbc:derby:target/JdbcRDDSuiteDb") },
       "SELECT DATA FROM FOO WHERE ? <= ID AND ID <= ?",
       1, 100, 3,
-      (r: ResultSet) => { r.getInt(1) } ).cache()
+      (r: ResultSet) => { r.getInt(1) }).cache()
 
     assert(rdd.count === 100)
     assert(rdd.reduce(_ + _) === 10100)
@@ -91,7 +91,7 @@ class JdbcRDDSuite extends SparkFunSuite with BeforeAndAfter with LocalSparkCont
       () => { DriverManager.getConnection("jdbc:derby:target/JdbcRDDSuiteDb") },
       "SELECT DATA FROM BIGINT_TEST WHERE ? <= ID AND ID <= ?",
       1131544775L, 567279358897692673L, 20,
-      (r: ResultSet) => { r.getInt(1) } ).cache()
+      (r: ResultSet) => { r.getInt(1) }).cache()
     assert(rdd.count === 100)
     assert(rdd.reduce(_ + _) === 5050)
   }
diff --git a/core/src/test/scala/org/apache/spark/rdd/ZippedPartitionsSuite.scala b/core/src/test/scala/org/apache/spark/rdd/ZippedPartitionsSuite.scala
index 5d7b973fbd9ac..95755ceac124b 100644
--- a/core/src/test/scala/org/apache/spark/rdd/ZippedPartitionsSuite.scala
+++ b/core/src/test/scala/org/apache/spark/rdd/ZippedPartitionsSuite.scala
@@ -20,7 +20,7 @@ package org.apache.spark.rdd
 import org.apache.spark.{SharedSparkContext, SparkFunSuite}
 
 object ZippedPartitionsSuite {
-  def procZippedData(i: Iterator[Int], s: Iterator[String], d: Iterator[Double]) : Iterator[Int] = {
+  def procZippedData(i: Iterator[Int], s: Iterator[String], d: Iterator[Double]): Iterator[Int] = {
     Iterator(i.toArray.size, s.toArray.size, d.toArray.size)
   }
 }
diff --git a/core/src/test/scala/org/apache/spark/rpc/RpcEnvSuite.scala b/core/src/test/scala/org/apache/spark/rpc/RpcEnvSuite.scala
index 59d8c14d74e30..c26b702047ee4 100644
--- a/core/src/test/scala/org/apache/spark/rpc/RpcEnvSuite.scala
+++ b/core/src/test/scala/org/apache/spark/rpc/RpcEnvSuite.scala
@@ -745,18 +745,18 @@ abstract class RpcEnvSuite extends SparkFunSuite with BeforeAndAfterAll {
 
     // Construct RpcTimeout with a single property
     val rt1 = RpcTimeout(conf, testProp)
-    assert( testDurationSeconds === rt1.duration.toSeconds )
+    assert(testDurationSeconds === rt1.duration.toSeconds )
 
     // Construct RpcTimeout with prioritized list of properties
     val rt2 = RpcTimeout(conf, Seq("spark.ask.invalid.timeout", testProp, secondaryProp), "1s")
-    assert( testDurationSeconds === rt2.duration.toSeconds )
+    assert(testDurationSeconds === rt2.duration.toSeconds )
 
     // Construct RpcTimeout with default value,
     val defaultProp = "spark.ask.default.timeout"
     val defaultDurationSeconds = 1
     val rt3 = RpcTimeout(conf, Seq(defaultProp), defaultDurationSeconds.toString + "s")
-    assert( defaultDurationSeconds === rt3.duration.toSeconds )
-    assert( rt3.timeoutProp.contains(defaultProp) )
+    assert(defaultDurationSeconds === rt3.duration.toSeconds )
+    assert(rt3.timeoutProp.contains(defaultProp) )
 
     // Try to construct RpcTimeout with an unconfigured property
     intercept[NoSuchElementException] {
diff --git a/core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala b/core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala
index 453be26ed8d0c..40809771b1241 100644
--- a/core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala
+++ b/core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala
@@ -760,7 +760,7 @@ class DAGSchedulerSuite extends SparkFunSuite with LocalSparkContext with Timeou
   // when we abort the stage. This message will also be consumed by the EventLoggingListener
   // so this will propagate up to the user.
   var ended = false
-  var jobResult : JobResult = null
+  var jobResult: JobResult = null
 
   class EndListener extends SparkListener {
     override def onJobEnd(jobEnd: SparkListenerJobEnd): Unit = {
diff --git a/core/src/test/scala/org/apache/spark/serializer/GenericAvroSerializerSuite.scala b/core/src/test/scala/org/apache/spark/serializer/GenericAvroSerializerSuite.scala
index 3734f1cb408fe..00d5c378119c4 100644
--- a/core/src/test/scala/org/apache/spark/serializer/GenericAvroSerializerSuite.scala
+++ b/core/src/test/scala/org/apache/spark/serializer/GenericAvroSerializerSuite.scala
@@ -29,7 +29,7 @@ import org.apache.spark.{SharedSparkContext, SparkFunSuite}
 class GenericAvroSerializerSuite extends SparkFunSuite with SharedSparkContext {
   conf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
 
-  val schema : Schema = SchemaBuilder
+  val schema: Schema = SchemaBuilder
     .record("testRecord").fields()
     .requiredString("data")
     .endRecord()
diff --git a/core/src/test/scala/org/apache/spark/serializer/KryoSerializerSuite.scala b/core/src/test/scala/org/apache/spark/serializer/KryoSerializerSuite.scala
index 7c3922e47fbb9..56b5a89dc5a7f 100644
--- a/core/src/test/scala/org/apache/spark/serializer/KryoSerializerSuite.scala
+++ b/core/src/test/scala/org/apache/spark/serializer/KryoSerializerSuite.scala
@@ -268,19 +268,19 @@ class KryoSerializerSuite extends SparkFunSuite with SharedSparkContext {
   }
 
   test("kryo with parallelize for specialized tuples") {
-    assert (sc.parallelize( Array((1, 11), (2, 22), (3, 33)) ).count === 3)
+    assert (sc.parallelize(Array((1, 11), (2, 22), (3, 33))).count === 3)
   }
 
   test("kryo with parallelize for primitive arrays") {
-    assert (sc.parallelize( Array(1, 2, 3) ).count === 3)
+    assert (sc.parallelize(Array(1, 2, 3)).count === 3)
   }
 
   test("kryo with collect for specialized tuples") {
-    assert (sc.parallelize( Array((1, 11), (2, 22), (3, 33)) ).collect().head === (1, 11))
+    assert (sc.parallelize(Array((1, 11), (2, 22), (3, 33))).collect().head === (1, 11))
   }
 
   test("kryo with SerializableHyperLogLog") {
-    assert(sc.parallelize( Array(1, 2, 3, 2, 3, 3, 2, 3, 1) ).countApproxDistinct(0.01) === 3)
+    assert(sc.parallelize(Array(1, 2, 3, 2, 3, 3, 2, 3, 1)).countApproxDistinct(0.01) === 3)
   }
 
   test("kryo with reduce") {
diff --git a/core/src/test/scala/org/apache/spark/shuffle/sort/BypassMergeSortShuffleWriterSuite.scala b/core/src/test/scala/org/apache/spark/shuffle/sort/BypassMergeSortShuffleWriterSuite.scala
index 85ccb33471048..6a059916522bd 100644
--- a/core/src/test/scala/org/apache/spark/shuffle/sort/BypassMergeSortShuffleWriterSuite.scala
+++ b/core/src/test/scala/org/apache/spark/shuffle/sort/BypassMergeSortShuffleWriterSuite.scala
@@ -140,7 +140,7 @@ class BypassMergeSortShuffleWriterSuite extends SparkFunSuite with BeforeAndAfte
       conf
     )
     writer.write(Iterator.empty)
-    writer.stop( /* success = */ true)
+    writer.stop(/* success = */ true)
     assert(writer.getPartitionLengths.sum === 0)
     assert(outputFile.exists())
     assert(outputFile.length() === 0)
@@ -164,7 +164,7 @@ class BypassMergeSortShuffleWriterSuite extends SparkFunSuite with BeforeAndAfte
       conf
     )
     writer.write(records)
-    writer.stop( /* success = */ true)
+    writer.stop(/* success = */ true)
     assert(temporaryFilesCreated.nonEmpty)
     assert(writer.getPartitionLengths.sum === outputFile.length())
     assert(writer.getPartitionLengths.count(_ == 0L) === 4) // should be 4 zero length files
@@ -207,7 +207,7 @@ class BypassMergeSortShuffleWriterSuite extends SparkFunSuite with BeforeAndAfte
     // Only 3 temp shuffle files will be created
     assert(temporaryFilesCreated.count(_.exists()) === 3)
 
-    writer.stop( /* success = */ false)
+    writer.stop(/* success = */ false)
     assert(temporaryFilesCreated.count(_.exists()) === 0) // check that temporary files were deleted
   }
 
@@ -229,7 +229,7 @@ class BypassMergeSortShuffleWriterSuite extends SparkFunSuite with BeforeAndAfte
       }))
     }
     assert(temporaryFilesCreated.nonEmpty)
-    writer.stop( /* success = */ false)
+    writer.stop(/* success = */ false)
     assert(temporaryFilesCreated.count(_.exists()) === 0)
   }
 
diff --git a/core/src/test/scala/org/apache/spark/storage/FlatmapIteratorSuite.scala b/core/src/test/scala/org/apache/spark/storage/FlatmapIteratorSuite.scala
index b21c91f75d5c7..a8cd3ddec8229 100644
--- a/core/src/test/scala/org/apache/spark/storage/FlatmapIteratorSuite.scala
+++ b/core/src/test/scala/org/apache/spark/storage/FlatmapIteratorSuite.scala
@@ -36,7 +36,7 @@ class FlatmapIteratorSuite extends SparkFunSuite with LocalSparkContext {
     sc = new SparkContext(sconf)
     val expand_size = 100
     val data = sc.parallelize((1 to 5).toSeq).
-      flatMap( x => Stream.range(0, expand_size))
+      flatMap(x => Stream.range(0, expand_size))
     var persisted = data.persist(StorageLevel.DISK_ONLY)
     assert(persisted.count()===500)
     assert(persisted.filter(_==1).count()===5)
diff --git a/core/src/test/scala/org/apache/spark/ui/jobs/JobProgressListenerSuite.scala b/core/src/test/scala/org/apache/spark/ui/jobs/JobProgressListenerSuite.scala
index 48be3be81755a..b54949706ef08 100644
--- a/core/src/test/scala/org/apache/spark/ui/jobs/JobProgressListenerSuite.scala
+++ b/core/src/test/scala/org/apache/spark/ui/jobs/JobProgressListenerSuite.scala
@@ -84,7 +84,7 @@ class JobProgressListenerSuite extends SparkFunSuite with LocalSparkContext with
   }
 
   test("test LRU eviction of stages") {
-    def runWithListener(listener: JobProgressListener) : Unit = {
+    def runWithListener(listener: JobProgressListener): Unit = {
       for (i <- 1 to 50) {
         listener.onStageSubmitted(createStageStartEvent(i))
         listener.onStageCompleted(createStageEndEvent(i))
diff --git a/core/src/test/scala/org/apache/spark/util/ClosureCleanerSuite.scala b/core/src/test/scala/org/apache/spark/util/ClosureCleanerSuite.scala
index 4920b7ee8bfb4..54738a41a4f0d 100644
--- a/core/src/test/scala/org/apache/spark/util/ClosureCleanerSuite.scala
+++ b/core/src/test/scala/org/apache/spark/util/ClosureCleanerSuite.scala
@@ -312,11 +312,11 @@ private object TestUserClosuresActuallyCleaned {
   // Test SparkContext runJob
   def testRunJob1(sc: SparkContext): Unit = {
     val rdd = sc.parallelize(1 to 10, 10)
-    sc.runJob(rdd, { (ctx: TaskContext, iter: Iterator[Int]) => return; 1 } )
+    sc.runJob(rdd, { (ctx: TaskContext, iter: Iterator[Int]) => return; 1 })
   }
   def testRunJob2(sc: SparkContext): Unit = {
     val rdd = sc.parallelize(1 to 10, 10)
-    sc.runJob(rdd, { iter: Iterator[Int] => return; 1 } )
+    sc.runJob(rdd, { iter: Iterator[Int] => return; 1 })
   }
   def testRunApproximateJob(sc: SparkContext): Unit = {
     val rdd = sc.parallelize(1 to 10, 10)
diff --git a/core/src/test/scala/org/apache/spark/util/FileAppenderSuite.scala b/core/src/test/scala/org/apache/spark/util/FileAppenderSuite.scala
index 7e2da8e141532..40553314a2f90 100644
--- a/core/src/test/scala/org/apache/spark/util/FileAppenderSuite.scala
+++ b/core/src/test/scala/org/apache/spark/util/FileAppenderSuite.scala
@@ -65,7 +65,7 @@ class FileAppenderSuite extends SparkFunSuite with BeforeAndAfter with Logging {
     val rolloverIntervalMillis = 100
     val durationMillis = 1000
     val numRollovers = durationMillis / rolloverIntervalMillis
-    val textToAppend = (1 to numRollovers).map( _.toString * 10 )
+    val textToAppend = (1 to numRollovers).map(_.toString * 10 )
 
     val appender = new RollingFileAppender(testInputStream, testFile,
       new TimeBasedRollingPolicy(rolloverIntervalMillis, s"--HH-mm-ss-SSSS", false),
@@ -81,7 +81,7 @@ class FileAppenderSuite extends SparkFunSuite with BeforeAndAfter with Logging {
     val rolloverIntervalMillis = 100
     val durationMillis = 1000
     val numRollovers = durationMillis / rolloverIntervalMillis
-    val textToAppend = (1 to numRollovers).map( _.toString * 10 )
+    val textToAppend = (1 to numRollovers).map(_.toString * 10 )
 
     val sparkConf = new SparkConf()
     sparkConf.set("spark.executor.logs.rolling.enableCompression", "true")
@@ -98,7 +98,7 @@ class FileAppenderSuite extends SparkFunSuite with BeforeAndAfter with Logging {
     val testOutputStream = new PipedOutputStream()
     val testInputStream = new PipedInputStream(testOutputStream, 100 * 1000)
     val rolloverSize = 1000
-    val textToAppend = (1 to 3).map( _.toString * 1000 )
+    val textToAppend = (1 to 3).map(_.toString * 1000 )
 
     val appender = new RollingFileAppender(testInputStream, testFile,
       new SizeBasedRollingPolicy(rolloverSize, false), new SparkConf(), 99)
@@ -115,7 +115,7 @@ class FileAppenderSuite extends SparkFunSuite with BeforeAndAfter with Logging {
     val testOutputStream = new PipedOutputStream()
     val testInputStream = new PipedInputStream(testOutputStream, 100 * 1000)
     val rolloverSize = 1000
-    val textToAppend = (1 to 3).map( _.toString * 1000 )
+    val textToAppend = (1 to 3).map(_.toString * 1000 )
 
     val sparkConf = new SparkConf()
     sparkConf.set("spark.executor.logs.rolling.enableCompression", "true")
diff --git a/core/src/test/scala/org/apache/spark/util/SizeEstimatorSuite.scala b/core/src/test/scala/org/apache/spark/util/SizeEstimatorSuite.scala
index 2695295d451d5..7174899e08135 100644
--- a/core/src/test/scala/org/apache/spark/util/SizeEstimatorSuite.scala
+++ b/core/src/test/scala/org/apache/spark/util/SizeEstimatorSuite.scala
@@ -52,7 +52,7 @@ class DummyClass7 {
 }
 
 object DummyString {
-  def apply(str: String) : DummyString = new DummyString(str.toArray)
+  def apply(str: String): DummyString = new DummyString(str.toArray)
 }
 class DummyString(val arr: Array[Char]) {
   override val hashCode: Int = 0
diff --git a/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala b/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala
index f7bc8f888b0d5..4311048793385 100644
--- a/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala
+++ b/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala
@@ -384,7 +384,7 @@ class UtilsSuite extends SparkFunSuite with ResetSystemProperties with Logging {
   }
 
   test("deserialize long value") {
-    val testval : Long = 9730889947L
+    val testval: Long = 9730889947L
     val bbuf = ByteBuffer.allocate(8)
     assert(bbuf.hasArray)
     bbuf.order(ByteOrder.BIG_ENDIAN)
diff --git a/core/src/test/scala/org/apache/spark/util/collection/BitSetSuite.scala b/core/src/test/scala/org/apache/spark/util/collection/BitSetSuite.scala
index 0169c9926e68f..d516f9cdf8906 100644
--- a/core/src/test/scala/org/apache/spark/util/collection/BitSetSuite.scala
+++ b/core/src/test/scala/org/apache/spark/util/collection/BitSetSuite.scala
@@ -70,13 +70,13 @@ class BitSetSuite extends SparkFunSuite {
     assert(bitset.nextSetBit(97) === -1)
   }
 
-  test( "xor len(bitsetX) < len(bitsetY)" ) {
-    val setBitsX = Seq( 0, 2, 3, 37, 41 )
-    val setBitsY = Seq( 0, 1, 3, 37, 38, 41, 85)
+  test("xor len(bitsetX) < len(bitsetY)") {
+    val setBitsX = Seq(0, 2, 3, 37, 41 )
+    val setBitsY = Seq(0, 1, 3, 37, 38, 41, 85)
     val bitsetX = new BitSet(60)
-    setBitsX.foreach( i => bitsetX.set(i))
+    setBitsX.foreach(i => bitsetX.set(i))
     val bitsetY = new BitSet(100)
-    setBitsY.foreach( i => bitsetY.set(i))
+    setBitsY.foreach(i => bitsetY.set(i))
 
     val bitsetXor = bitsetX ^ bitsetY
 
@@ -92,13 +92,13 @@ class BitSetSuite extends SparkFunSuite {
 
   }
 
-  test( "xor len(bitsetX) > len(bitsetY)" ) {
-    val setBitsX = Seq( 0, 1, 3, 37, 38, 41, 85)
-    val setBitsY = Seq( 0, 2, 3, 37, 41)
+  test("xor len(bitsetX) > len(bitsetY)") {
+    val setBitsX = Seq(0, 1, 3, 37, 38, 41, 85)
+    val setBitsY = Seq(0, 2, 3, 37, 41)
     val bitsetX = new BitSet(100)
-    setBitsX.foreach( i => bitsetX.set(i))
+    setBitsX.foreach(i => bitsetX.set(i))
     val bitsetY = new BitSet(60)
-    setBitsY.foreach( i => bitsetY.set(i))
+    setBitsY.foreach(i => bitsetY.set(i))
 
     val bitsetXor = bitsetX ^ bitsetY
 
@@ -114,15 +114,15 @@ class BitSetSuite extends SparkFunSuite {
 
   }
 
-  test( "andNot len(bitsetX) < len(bitsetY)" ) {
-    val setBitsX = Seq( 0, 2, 3, 37, 41, 48 )
-    val setBitsY = Seq( 0, 1, 3, 37, 38, 41, 85)
+  test("andNot len(bitsetX) < len(bitsetY)") {
+    val setBitsX = Seq(0, 2, 3, 37, 41, 48 )
+    val setBitsY = Seq(0, 1, 3, 37, 38, 41, 85)
     val bitsetX = new BitSet(60)
-    setBitsX.foreach( i => bitsetX.set(i))
+    setBitsX.foreach(i => bitsetX.set(i))
     val bitsetY = new BitSet(100)
-    setBitsY.foreach( i => bitsetY.set(i))
+    setBitsY.foreach(i => bitsetY.set(i))
 
-    val bitsetDiff = bitsetX.andNot( bitsetY )
+    val bitsetDiff = bitsetX.andNot(bitsetY )
 
     assert(bitsetDiff.nextSetBit(0) === 2)
     assert(bitsetDiff.nextSetBit(1) === 2)
@@ -133,15 +133,15 @@ class BitSetSuite extends SparkFunSuite {
     assert(bitsetDiff.nextSetBit(65) === -1)
   }
 
-  test( "andNot len(bitsetX) > len(bitsetY)" ) {
-    val setBitsX = Seq( 0, 1, 3, 37, 38, 41, 85)
-    val setBitsY = Seq( 0, 2, 3, 37, 41, 48 )
+  test("andNot len(bitsetX) > len(bitsetY)") {
+    val setBitsX = Seq(0, 1, 3, 37, 38, 41, 85)
+    val setBitsY = Seq(0, 2, 3, 37, 41, 48 )
     val bitsetX = new BitSet(100)
-    setBitsX.foreach( i => bitsetX.set(i))
+    setBitsX.foreach(i => bitsetX.set(i))
     val bitsetY = new BitSet(60)
-    setBitsY.foreach( i => bitsetY.set(i))
+    setBitsY.foreach(i => bitsetY.set(i))
 
-    val bitsetDiff = bitsetX.andNot( bitsetY )
+    val bitsetDiff = bitsetX.andNot(bitsetY )
 
     assert(bitsetDiff.nextSetBit(0) === 1)
     assert(bitsetDiff.nextSetBit(1) === 1)
@@ -153,7 +153,7 @@ class BitSetSuite extends SparkFunSuite {
     assert(bitsetDiff.nextSetBit(86) === -1)
   }
 
-  test( "[gs]etUntil" ) {
+  test("[gs]etUntil") {
     val bitSet = new BitSet(100)
 
     bitSet.setUntil(bitSet.capacity)
diff --git a/external/kafka-0-10-sql/src/test/scala/org/apache/spark/sql/kafka010/KafkaRelationSuite.scala b/external/kafka-0-10-sql/src/test/scala/org/apache/spark/sql/kafka010/KafkaRelationSuite.scala
index 91893df4ec32f..eae4175583638 100644
--- a/external/kafka-0-10-sql/src/test/scala/org/apache/spark/sql/kafka010/KafkaRelationSuite.scala
+++ b/external/kafka-0-10-sql/src/test/scala/org/apache/spark/sql/kafka010/KafkaRelationSuite.scala
@@ -205,7 +205,7 @@ class KafkaRelationSuite extends QueryTest with BeforeAndAfter with SharedSQLCon
       "for batch queries on Kafka")
 
     // Now do it with an explicit json start offset indicating latest
-    val startPartitionOffsets = Map( new TopicPartition("t", 0) -> -1L)
+    val startPartitionOffsets = Map(new TopicPartition("t", 0) -> -1L)
     val startingOffsets = JsonUtils.partitionOffsets(startPartitionOffsets)
     testBadOptions("subscribe" -> "t", "startingOffsets" -> startingOffsets)(
       "startingOffsets for t-0 can't be latest for batch queries on Kafka")
diff --git a/graphx/src/test/scala/org/apache/spark/graphx/GraphSuite.scala b/graphx/src/test/scala/org/apache/spark/graphx/GraphSuite.scala
index 88b59a343a83c..3aaca3a40b26f 100644
--- a/graphx/src/test/scala/org/apache/spark/graphx/GraphSuite.scala
+++ b/graphx/src/test/scala/org/apache/spark/graphx/GraphSuite.scala
@@ -59,9 +59,9 @@ class GraphSuite extends SparkFunSuite with LocalSparkContext {
       val edges: RDD[Edge[Int]] = sc.parallelize(rawEdges).map { case (s, t) => Edge(s, t, 1) }
       val vertices: RDD[(VertexId, Boolean)] = sc.parallelize((0L until 10L).map(id => (id, true)))
       val graph = Graph(vertices, edges, false)
-      assert( graph.edges.count() === rawEdges.size )
+      assert(graph.edges.count() === rawEdges.size )
       // Vertices not explicitly provided but referenced by edges should be created automatically
-      assert( graph.vertices.count() === 100)
+      assert(graph.vertices.count() === 100)
       graph.triplets.collect().foreach { et =>
         assert((et.srcId < 10 && et.srcAttr) || (et.srcId >= 10 && !et.srcAttr))
         assert((et.dstId < 10 && et.dstAttr) || (et.dstId >= 10 && !et.dstAttr))
diff --git a/graphx/src/test/scala/org/apache/spark/graphx/lib/ConnectedComponentsSuite.scala b/graphx/src/test/scala/org/apache/spark/graphx/lib/ConnectedComponentsSuite.scala
index 1b81423563372..8b485e3a3b64b 100644
--- a/graphx/src/test/scala/org/apache/spark/graphx/lib/ConnectedComponentsSuite.scala
+++ b/graphx/src/test/scala/org/apache/spark/graphx/lib/ConnectedComponentsSuite.scala
@@ -53,7 +53,7 @@ class ConnectedComponentsSuite extends SparkFunSuite with LocalSparkContext {
       val twoChains = Graph.fromEdgeTuples(rawEdges, 1.0)
       val ccGraph = twoChains.connectedComponents()
       val vertices = ccGraph.vertices.collect()
-      for ( (id, cc) <- vertices ) {
+      for ((id, cc) <- vertices) {
         if (id < 10) {
           assert(cc === 0)
         } else {
@@ -79,7 +79,7 @@ class ConnectedComponentsSuite extends SparkFunSuite with LocalSparkContext {
       val twoChains = Graph.fromEdgeTuples(rawEdges, true).reverse
       val ccGraph = twoChains.connectedComponents()
       val vertices = ccGraph.vertices.collect()
-      for ( (id, cc) <- vertices ) {
+      for ((id, cc) <- vertices) {
         if (id < 10) {
           assert(cc === 0)
         } else {
@@ -87,7 +87,7 @@ class ConnectedComponentsSuite extends SparkFunSuite with LocalSparkContext {
         }
       }
       val ccMap = vertices.toMap
-      for ( id <- 0 until 20 ) {
+      for (id <- 0 until 20) {
         if (id < 10) {
           assert(ccMap(id) === 0)
         } else {
@@ -121,7 +121,7 @@ class ConnectedComponentsSuite extends SparkFunSuite with LocalSparkContext {
       val graph = Graph(users, relationships, defaultUser)
       val ccGraph = graph.connectedComponents()
       val vertices = ccGraph.vertices.collect()
-      for ( (id, cc) <- vertices ) {
+      for ((id, cc) <- vertices) {
         assert(cc === 0)
       }
     }
diff --git a/graphx/src/test/scala/org/apache/spark/graphx/lib/PageRankSuite.scala b/graphx/src/test/scala/org/apache/spark/graphx/lib/PageRankSuite.scala
index 9779553ce85d1..7854dff2ee926 100644
--- a/graphx/src/test/scala/org/apache/spark/graphx/lib/PageRankSuite.scala
+++ b/graphx/src/test/scala/org/apache/spark/graphx/lib/PageRankSuite.scala
@@ -47,7 +47,7 @@ object GridPageRank {
       pr = new Array[Double](nRows * nCols)
       for (ind <- 0 until (nRows * nCols)) {
         pr(ind) = resetProb + (1.0 - resetProb) *
-          inNbrs(ind).map( nbr => oldPr(nbr) / outDegree(nbr)).sum
+          inNbrs(ind).map(nbr => oldPr(nbr) / outDegree(nbr)).sum
       }
     }
     val prSum = pr.sum
diff --git a/graphx/src/test/scala/org/apache/spark/graphx/lib/TriangleCountSuite.scala b/graphx/src/test/scala/org/apache/spark/graphx/lib/TriangleCountSuite.scala
index f19c3acdc85cf..feeebf0171847 100644
--- a/graphx/src/test/scala/org/apache/spark/graphx/lib/TriangleCountSuite.scala
+++ b/graphx/src/test/scala/org/apache/spark/graphx/lib/TriangleCountSuite.scala
@@ -26,7 +26,7 @@ class TriangleCountSuite extends SparkFunSuite with LocalSparkContext {
 
   test("Count a single triangle") {
     withSpark { sc =>
-      val rawEdges = sc.parallelize(Array( 0L -> 1L, 1L -> 2L, 2L -> 0L ), 2)
+      val rawEdges = sc.parallelize(Array(0L -> 1L, 1L -> 2L, 2L -> 0L), 2)
       val graph = Graph.fromEdgeTuples(rawEdges, true).cache()
       val triangleCount = graph.triangleCount()
       val verts = triangleCount.vertices
diff --git a/mllib/src/test/scala/org/apache/spark/ml/classification/NaiveBayesSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/classification/NaiveBayesSuite.scala
index 3a2be236f1257..2c4747faeb94a 100644
--- a/mllib/src/test/scala/org/apache/spark/ml/classification/NaiveBayesSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/ml/classification/NaiveBayesSuite.scala
@@ -333,7 +333,7 @@ object NaiveBayesSuite {
       val y = calcLabel(rnd.nextDouble(), _pi)
       val xi = modelType match {
         case Bernoulli => Array.tabulate[Double] (D) { j =>
-            if (rnd.nextDouble () < _theta(y)(j) ) 1 else 0
+            if (rnd.nextDouble () < _theta(y)(j)) 1 else 0
         }
         case Multinomial =>
           val mult = BrzMultinomial(BDV(_theta(y)))
diff --git a/mllib/src/test/scala/org/apache/spark/ml/clustering/GaussianMixtureSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/clustering/GaussianMixtureSuite.scala
index 08b800b7e4183..60aff9f829695 100644
--- a/mllib/src/test/scala/org/apache/spark/ml/clustering/GaussianMixtureSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/ml/clustering/GaussianMixtureSuite.scala
@@ -274,10 +274,10 @@ object GaussianMixtureSuite extends SparkFunSuite {
 
   val denseData = Seq(
     Vectors.dense(-5.1971), Vectors.dense(-2.5359), Vectors.dense(-3.8220),
-    Vectors.dense(-5.2211), Vectors.dense(-5.0602), Vectors.dense( 4.7118),
-    Vectors.dense( 6.8989), Vectors.dense( 3.4592), Vectors.dense( 4.6322),
-    Vectors.dense( 5.7048), Vectors.dense( 4.6567), Vectors.dense( 5.5026),
-    Vectors.dense( 4.5605), Vectors.dense( 5.2043), Vectors.dense( 6.2734)
+    Vectors.dense(-5.2211), Vectors.dense(-5.0602), Vectors.dense(4.7118),
+    Vectors.dense(6.8989), Vectors.dense(3.4592), Vectors.dense(4.6322),
+    Vectors.dense(5.7048), Vectors.dense(4.6567), Vectors.dense(5.5026),
+    Vectors.dense(4.5605), Vectors.dense(5.2043), Vectors.dense(6.2734)
   )
 
   val decompositionData: Seq[Vector] = Seq.tabulate(25) { i: Int =>
diff --git a/mllib/src/test/scala/org/apache/spark/ml/feature/ImputerSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/feature/ImputerSuite.scala
index ee2ba73fa96d5..c9867afb62de2 100644
--- a/mllib/src/test/scala/org/apache/spark/ml/feature/ImputerSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/ml/feature/ImputerSuite.scala
@@ -25,7 +25,7 @@ import org.apache.spark.sql.{DataFrame, Row}
 class ImputerSuite extends SparkFunSuite with MLlibTestSparkContext with DefaultReadWriteTest {
 
   test("Imputer for Double with default missing Value NaN") {
-    val df = spark.createDataFrame( Seq(
+    val df = spark.createDataFrame(Seq(
       (0, 1.0, 4.0, 1.0, 1.0, 4.0, 4.0),
       (1, 11.0, 12.0, 11.0, 11.0, 12.0, 12.0),
       (2, 3.0, Double.NaN, 3.0, 3.0, 10.0, 12.0),
@@ -39,7 +39,7 @@ class ImputerSuite extends SparkFunSuite with MLlibTestSparkContext with Default
   }
 
   test("Imputer should handle NaNs when computing surrogate value, if missingValue is not NaN") {
-    val df = spark.createDataFrame( Seq(
+    val df = spark.createDataFrame(Seq(
       (0, 1.0, 1.0, 1.0),
       (1, 3.0, 3.0, 3.0),
       (2, Double.NaN, Double.NaN, Double.NaN),
@@ -51,7 +51,7 @@ class ImputerSuite extends SparkFunSuite with MLlibTestSparkContext with Default
   }
 
   test("Imputer for Float with missing Value -1.0") {
-    val df = spark.createDataFrame( Seq(
+    val df = spark.createDataFrame(Seq(
       (0, 1.0F, 1.0F, 1.0F),
       (1, 3.0F, 3.0F, 3.0F),
       (2, 10.0F, 10.0F, 10.0F),
@@ -64,7 +64,7 @@ class ImputerSuite extends SparkFunSuite with MLlibTestSparkContext with Default
   }
 
   test("Imputer should impute null as well as 'missingValue'") {
-    val rawDf = spark.createDataFrame( Seq(
+    val rawDf = spark.createDataFrame(Seq(
       (0, 4.0, 4.0, 4.0),
       (1, 10.0, 10.0, 10.0),
       (2, 10.0, 10.0, 10.0),
@@ -77,7 +77,7 @@ class ImputerSuite extends SparkFunSuite with MLlibTestSparkContext with Default
   }
 
   test("Imputer throws exception when surrogate cannot be computed") {
-    val df = spark.createDataFrame( Seq(
+    val df = spark.createDataFrame(Seq(
       (0, Double.NaN, 1.0, 1.0),
       (1, Double.NaN, 3.0, 3.0),
       (2, Double.NaN, Double.NaN, Double.NaN)
@@ -95,7 +95,7 @@ class ImputerSuite extends SparkFunSuite with MLlibTestSparkContext with Default
   }
 
   test("Imputer input & output column validation") {
-    val df = spark.createDataFrame( Seq(
+    val df = spark.createDataFrame(Seq(
       (0, 1.0, 1.0, 1.0),
       (1, Double.NaN, 3.0, 3.0),
       (2, Double.NaN, Double.NaN, Double.NaN)
diff --git a/mllib/src/test/scala/org/apache/spark/ml/feature/QuantileDiscretizerSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/feature/QuantileDiscretizerSuite.scala
index f219f775b2186..886990ed2e7dd 100644
--- a/mllib/src/test/scala/org/apache/spark/ml/feature/QuantileDiscretizerSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/ml/feature/QuantileDiscretizerSuite.scala
@@ -45,7 +45,7 @@ class QuantileDiscretizerSuite
 
     val relativeError = discretizer.getRelativeError
     val isGoodBucket = udf {
-      (size: Int) => math.abs( size - (datasetSize / numBuckets)) <= (relativeError * datasetSize)
+      (size: Int) => math.abs(size - (datasetSize / numBuckets)) <= (relativeError * datasetSize)
     }
     val numGoodBuckets = result.groupBy("result").count.filter(isGoodBucket($"count")).count
     assert(numGoodBuckets === numBuckets,
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/classification/NaiveBayesSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/classification/NaiveBayesSuite.scala
index 5ec4c15387e94..37ef7e01a67db 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/classification/NaiveBayesSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/classification/NaiveBayesSuite.scala
@@ -60,7 +60,7 @@ object NaiveBayesSuite {
       val y = calcLabel(rnd.nextDouble(), _pi)
       val xi = modelType match {
         case Bernoulli => Array.tabulate[Double] (D) { j =>
-            if (rnd.nextDouble () < _theta(y)(j) ) 1 else 0
+            if (rnd.nextDouble () < _theta(y)(j)) 1 else 0
         }
         case Multinomial =>
           val mult = BrzMultinomial(BDV(_theta(y)))
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/clustering/GaussianMixtureSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/clustering/GaussianMixtureSuite.scala
index 11189d8bd4776..36c291d81a4dc 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/clustering/GaussianMixtureSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/clustering/GaussianMixtureSuite.scala
@@ -190,10 +190,10 @@ class GaussianMixtureSuite extends SparkFunSuite with MLlibTestSparkContext {
 
     val data = Array(
       Vectors.dense(-5.1971), Vectors.dense(-2.5359), Vectors.dense(-3.8220),
-      Vectors.dense(-5.2211), Vectors.dense(-5.0602), Vectors.dense( 4.7118),
-      Vectors.dense( 6.8989), Vectors.dense( 3.4592), Vectors.dense( 4.6322),
-      Vectors.dense( 5.7048), Vectors.dense( 4.6567), Vectors.dense( 5.5026),
-      Vectors.dense( 4.5605), Vectors.dense( 5.2043), Vectors.dense( 6.2734)
+      Vectors.dense(-5.2211), Vectors.dense(-5.0602), Vectors.dense(4.7118),
+      Vectors.dense(6.8989), Vectors.dense(3.4592), Vectors.dense(4.6322),
+      Vectors.dense(5.7048), Vectors.dense(4.6567), Vectors.dense(5.5026),
+      Vectors.dense(4.5605), Vectors.dense(5.2043), Vectors.dense(6.2734)
     )
 
     val data2: Array[Vector] = Array.tabulate(25) { i: Int =>
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/evaluation/MultilabelMetricsSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/evaluation/MultilabelMetricsSuite.scala
index a660492c7ae59..8a09b1f441bd3 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/evaluation/MultilabelMetricsSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/evaluation/MultilabelMetricsSuite.scala
@@ -74,7 +74,7 @@ class MultilabelMetricsSuite extends SparkFunSuite with MLlibTestSparkContext {
     val macroRecallDoc = 1.0 / 7 *
       (1.0 / 2 + 1.0 / 2 + 0 / 1 + 1.0 / 1 + 2.0 / 2 + 2.0 / 2 + 1.0 / 2)
     val macroF1MeasureDoc = (1.0 / 7) *
-      2 * ( 1.0 / (2 + 2) + 1.0 / (2 + 2) + 0 + 1.0 / (1 + 1) +
+      2 * (1.0 / (2 + 2) + 1.0 / (2 + 2) + 0 + 1.0 / (1 + 1) +
         2.0 / (2 + 2) + 2.0 / (3 + 2) + 1.0 / (1 + 2) )
     val hammingLoss = (1.0 / (7 * 3)) * (2 + 2 + 1 + 0 + 0 + 1 + 1)
     val strictAccuracy = 2.0 / 7
diff --git a/resource-managers/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnAllocatorSuite.scala b/resource-managers/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnAllocatorSuite.scala
index 97b0e8aca3330..112cd938267f0 100644
--- a/resource-managers/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnAllocatorSuite.scala
+++ b/resource-managers/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnAllocatorSuite.scala
@@ -245,7 +245,7 @@ class YarnAllocatorSuite extends SparkFunSuite with Matchers with BeforeAndAfter
     handler.handleAllocatedContainers(Array(container1, container2))
 
     handler.requestTotalExecutorsWithPreferredLocalities(1, 0, Map.empty, Set.empty)
-    handler.executorIdToContainer.keys.foreach { id => handler.killExecutor(id ) }
+    handler.executorIdToContainer.keys.foreach { id => handler.killExecutor(id) }
 
     val statuses = Seq(container1, container2).map { c =>
       ContainerStatus.newInstance(c.getId(), ContainerState.COMPLETE, "Finished", 0)
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/encoders/EncoderErrorMessageSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/encoders/EncoderErrorMessageSuite.scala
index 8c766ef829923..a1c4a861c610f 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/encoders/EncoderErrorMessageSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/encoders/EncoderErrorMessageSuite.scala
@@ -98,5 +98,5 @@ class EncoderErrorMessageSuite extends SparkFunSuite {
       s"""array element class: "${clsName[NonEncodable]}""""))
   }
 
-  private def clsName[T : ClassTag]: String = implicitly[ClassTag[T]].runtimeClass.getName
+  private def clsName[T: ClassTag]: String = implicitly[ClassTag[T]].runtimeClass.getName
 }
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoderSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoderSuite.scala
index 080f11b769388..b63b382d841cc 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoderSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/encoders/ExpressionEncoderSuite.scala
@@ -114,7 +114,7 @@ object ReferenceValueClass {
 class ExpressionEncoderSuite extends PlanTest with AnalysisTest {
   OuterScopes.addOuterScope(this)
 
-  implicit def encoder[T : TypeTag]: ExpressionEncoder[T] = ExpressionEncoder()
+  implicit def encoder[T: TypeTag]: ExpressionEncoder[T] = ExpressionEncoder()
 
   // test flat encoders
   encodeDecodeTest(false, "primitive boolean")
@@ -189,7 +189,7 @@ class ExpressionEncoderSuite extends PlanTest with AnalysisTest {
     encoderFor(Encoders.javaSerialization[JavaSerializable]))
 
   // test product encoders
-  private def productTest[T <: Product : ExpressionEncoder](input: T): Unit = {
+  private def productTest[T <: Product: ExpressionEncoder](input: T): Unit = {
     encodeDecodeTest(input, input.getClass.getSimpleName)
   }
 
@@ -361,7 +361,7 @@ class ExpressionEncoderSuite extends PlanTest with AnalysisTest {
     assert(e.getMessage.contains("Cannot use null as map key"))
   }
 
-  private def encodeDecodeTest[T : ExpressionEncoder](
+  private def encodeDecodeTest[T: ExpressionEncoder](
       input: T,
       testName: String): Unit = {
     test(s"encode/decode for $testName: $input") {
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala
index 4f08031153ab0..918edd1b662d8 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala
@@ -251,7 +251,7 @@ class StringExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
       SubstringIndex(Literal("大千世界大千世界"), Literal( "千"), Literal(2)), "大千世界大")
     // scalastyle:on
     checkEvaluation(
-      SubstringIndex(Literal("www||apache||org"), Literal( "||"), Literal(2)), "www||apache")
+      SubstringIndex(Literal("www||apache||org"), Literal("||"), Literal(2)), "www||apache")
   }
 
   test("ascii for string") {
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/aggregate/PercentileSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/aggregate/PercentileSuite.scala
index 2420ba513f287..7859efddc468e 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/aggregate/PercentileSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/aggregate/PercentileSuite.scala
@@ -75,13 +75,13 @@ class PercentileSuite extends SparkFunSuite {
 
     // Run test with Flatten data
     val flattenRows = (1 to countForFrequencyTest).flatMap(current =>
-      (1 to current).map(y => current )).map(Seq(_))
+      (1 to current).map(y => current)).map(Seq(_))
     runTest(agg, flattenRows, expectedPercentilesWithFrquency)
   }
 
   private def runTest(agg: Percentile,
-        rows : Seq[Seq[Any]],
-        expectedPercentiles : Seq[Double]) {
+        rows: Seq[Seq[Any]],
+        expectedPercentiles: Seq[Double]) {
     assert(agg.nullable)
     val group1 = (0 until rows.length / 2)
     val group1Buffer = agg.createAggregationBuffer()
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/BooleanSimplificationSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/BooleanSimplificationSuite.scala
index c6345b60b744b..f635807bbef57 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/BooleanSimplificationSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/BooleanSimplificationSuite.scala
@@ -103,13 +103,13 @@ class BooleanSimplificationSuite extends PlanTest with PredicateHelper {
   }
 
   test("e && (!e || f)") {
-    checkCondition('e && (!'e || 'f ), 'e && 'f)
+    checkCondition('e && (!'e || 'f), 'e && 'f)
 
-    checkCondition('e && ('f || !'e ), 'e && 'f)
+    checkCondition('e && ('f || !'e), 'e && 'f)
 
-    checkCondition((!'e || 'f ) && 'e, 'f && 'e)
+    checkCondition((!'e || 'f) && 'e, 'f && 'e)
 
-    checkCondition(('f || !'e ) && 'e, 'f && 'e)
+    checkCondition(('f || !'e) && 'e, 'f && 'e)
   }
 
   test("a < 1 && (!(a < 1) || f)") {
@@ -127,10 +127,10 @@ class BooleanSimplificationSuite extends PlanTest with PredicateHelper {
   }
 
   test("a < 1 && ((a >= 1) || f)") {
-    checkCondition('a < 1 && ('a >= 1 || 'f ), ('a < 1) && 'f)
+    checkCondition('a < 1 && ('a >= 1 || 'f), ('a < 1) && 'f)
     checkCondition('a < 1 && ('f || 'a >= 1), ('a < 1) && 'f)
 
-    checkCondition('a <= 1 && ('a > 1 || 'f ), ('a <= 1) && 'f)
+    checkCondition('a <= 1 && ('a > 1 || 'f), ('a <= 1) && 'f)
     checkCondition('a <= 1 && ('f || 'a > 1), ('a <= 1) && 'f)
 
     checkCondition('a > 1 && (('a <= 1) || 'f), ('a > 1) && 'f)
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/ColumnPruningSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/ColumnPruningSuite.scala
index 08e58d47e0e25..008571f5b7e4f 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/ColumnPruningSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/ColumnPruningSuite.scala
@@ -334,7 +334,7 @@ class ColumnPruningSuite extends PlanTest {
     comparePlans(optimized, expected)
   }
 
-  implicit private def productEncoder[T <: Product : TypeTag] = ExpressionEncoder[T]()
+  implicit private def productEncoder[T <: Product: TypeTag] = ExpressionEncoder[T]()
   private val func = identity[Iterator[OtherTuple]] _
 
   test("Column pruning on MapPartitions") {
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/ConstantFoldingSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/ConstantFoldingSuite.scala
index 25c592b9c1dde..e6c05f996d3c7 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/ConstantFoldingSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/ConstantFoldingSuite.scala
@@ -68,7 +68,7 @@ class ConstantFoldingSuite extends PlanTest {
         .where(
           Literal(1) === Literal(1) &&
           Literal(2) > Literal(3) ||
-          Literal(3) > Literal(2) )
+          Literal(3) > Literal(2))
         .groupBy(
           Literal(2) * Literal(3) - Literal(6) / (Literal(4) - Literal(2))
         )(Literal(9) / Literal(3) as Symbol("9/3"))
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/EliminateSerializationSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/EliminateSerializationSuite.scala
index 3c033ddc374cf..41453d4a0b7fd 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/EliminateSerializationSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/EliminateSerializationSuite.scala
@@ -35,7 +35,7 @@ class EliminateSerializationSuite extends PlanTest {
         EliminateSerialization) :: Nil
   }
 
-  implicit private def productEncoder[T <: Product : TypeTag] = ExpressionEncoder[T]()
+  implicit private def productEncoder[T <: Product: TypeTag] = ExpressionEncoder[T]()
   implicit private def intEncoder = ExpressionEncoder[Int]()
 
   test("back to back serialization") {
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/StarJoinCostBasedReorderSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/StarJoinCostBasedReorderSuite.scala
index a23d6266b2840..c445443b39325 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/StarJoinCostBasedReorderSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/StarJoinCostBasedReorderSuite.scala
@@ -418,7 +418,7 @@ class StarJoinCostBasedReorderSuite extends PlanTest with StatsEstimationTestBas
     assertEqualPlans(query, expected)
   }
 
-  private def assertEqualPlans( plan1: LogicalPlan, plan2: LogicalPlan): Unit = {
+  private def assertEqualPlans(plan1: LogicalPlan, plan2: LogicalPlan): Unit = {
     val optimized = Optimize.execute(plan1.analyze)
     val expected = plan2.analyze
     compareJoinOrder(optimized, expected)
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/StarJoinReorderSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/StarJoinReorderSuite.scala
index 605c01b7220d1..b43bc6f6c307a 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/StarJoinReorderSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/StarJoinReorderSuite.scala
@@ -571,7 +571,7 @@ class StarJoinReorderSuite extends PlanTest with StatsEstimationTestBase {
     assertEqualPlans(query, expected)
   }
 
-  private def assertEqualPlans( plan1: LogicalPlan, plan2: LogicalPlan): Unit = {
+  private def assertEqualPlans(plan1: LogicalPlan, plan2: LogicalPlan): Unit = {
     val optimized = Optimize.execute(plan1.analyze)
     val expected = plan2.analyze
     compareJoinOrder(optimized, expected)
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/TypedFilterOptimizationSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/TypedFilterOptimizationSuite.scala
index 56f096f3ecf8c..af1ca0641e466 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/TypedFilterOptimizationSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/TypedFilterOptimizationSuite.scala
@@ -36,7 +36,7 @@ class TypedFilterOptimizationSuite extends PlanTest {
         CombineTypedFilters) :: Nil
   }
 
-  implicit private def productEncoder[T <: Product : TypeTag] = ExpressionEncoder[T]()
+  implicit private def productEncoder[T <: Product: TypeTag] = ExpressionEncoder[T]()
 
   test("filter after serialize with the same object type") {
     val input = LocalRelation('_1.int, '_2.int)
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/complexTypesSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/complexTypesSuite.scala
index 0a18858350e1f..37a753b24637a 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/complexTypesSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/complexTypesSuite.scala
@@ -55,7 +55,7 @@ class ComplexTypesSuite extends PlanTest{
     val query = relation
       .select(
         GetStructField(
-          CreateNamedStruct(Seq("att", 'id )),
+          CreateNamedStruct(Seq("att", 'id)),
           0,
           None) as "outerAtt").analyze
     val expected = relation.select('id as "outerAtt").analyze
@@ -301,7 +301,7 @@ class ComplexTypesSuite extends PlanTest{
             Literal(2L), 'id,
             ('id + 3L), ('id + 4L),
             ('id + 4L), ('id + 5L))),
-          2L ) as "a")
+          2L) as "a")
       .analyze
 
     val expected = relation
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/ExpressionParserSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/ExpressionParserSuite.scala
index 4d08f016a4a16..196a9f2d6707b 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/ExpressionParserSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/ExpressionParserSuite.scala
@@ -249,8 +249,8 @@ class ExpressionParserSuite extends PlanTest {
     assertEqual("foo(*) over (partition by a, b)", windowed(Seq('a, 'b)))
     assertEqual("foo(*) over (distribute by a, b)", windowed(Seq('a, 'b)))
     assertEqual("foo(*) over (cluster by a, b)", windowed(Seq('a, 'b)))
-    assertEqual("foo(*) over (order by a desc, b asc)", windowed(Seq.empty, Seq('a.desc, 'b.asc )))
-    assertEqual("foo(*) over (sort by a desc, b asc)", windowed(Seq.empty, Seq('a.desc, 'b.asc )))
+    assertEqual("foo(*) over (order by a desc, b asc)", windowed(Seq.empty, Seq('a.desc, 'b.asc)))
+    assertEqual("foo(*) over (sort by a desc, b asc)", windowed(Seq.empty, Seq('a.desc, 'b.asc)))
     assertEqual("foo(*) over (partition by a, b order by c)", windowed(Seq('a, 'b), Seq('c.asc)))
     assertEqual("foo(*) over (distribute by a, b sort by c)", windowed(Seq('a, 'b), Seq('c.asc)))
 
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DatasetAggregatorSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DatasetAggregatorSuite.scala
index 0e7eaa9e88d57..ddb6af6409c33 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/DatasetAggregatorSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/DatasetAggregatorSuite.scala
@@ -102,7 +102,7 @@ object SeqAgg extends Aggregator[AggData, Seq[Int], Seq[(Int, Int)]] {
 }
 
 
-class ParameterizedTypeSum[IN, OUT : Numeric : Encoder](f: IN => OUT)
+class ParameterizedTypeSum[IN, OUT: Numeric: Encoder](f: IN => OUT)
   extends Aggregator[IN, OUT, OUT] {
 
   private val numeric = implicitly[Numeric[OUT]]
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala
index 87b7b090de3bf..9894d10d3ac15 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala
@@ -213,7 +213,7 @@ class DatasetSuite extends QueryTest with SharedSQLContext {
     checkDataset(
       ds.select(
         expr("_1").as[String],
-        expr("_2").as[Int]) : Dataset[(String, Int)],
+        expr("_2").as[Int]): Dataset[(String, Int)],
       ("a", 1), ("b", 2), ("c", 3))
   }
 
@@ -577,7 +577,7 @@ class DatasetSuite extends QueryTest with SharedSQLContext {
   }
 
   test("SPARK-14696: implicit encoders for boxed types") {
-    assert(spark.range(1).map { i => i : java.lang.Long }.head == 0L)
+    assert(spark.range(1).map { i => i: java.lang.Long }.head == 0L)
   }
 
   test("SPARK-11894: Incorrect results are returned when using null") {
@@ -727,9 +727,9 @@ class DatasetSuite extends QueryTest with SharedSQLContext {
   }
 
   test("SPARK-14554: Dataset.map may generate wrong java code for wide table") {
-    val wideDF = spark.range(10).select(Seq.tabulate(1000) {i => ('id + i).as(s"c$i")} : _*)
+    val wideDF = spark.range(10).select(Seq.tabulate(1000) {i => ('id + i).as(s"c$i")}: _*)
     // Make sure the generated code for this plan can compile and execute.
-    checkDataset(wideDF.map(_.getLong(0)), 0L until 10 : _*)
+    checkDataset(wideDF.map(_.getLong(0)), 0L until 10: _*)
   }
 
   test("SPARK-14838: estimating sizeInBytes in operators with ObjectProducer shouldn't fail") {
@@ -1144,7 +1144,7 @@ class DatasetSuite extends QueryTest with SharedSQLContext {
   test ("SPARK-17460: the sizeInBytes in Statistics shouldn't overflow to a negative number") {
     // Since the sizeInBytes in Statistics could exceed the limit of an Int, we should use BigInt
     // instead of Int for avoiding possible overflow.
-    val ds = (0 to 10000).map( i =>
+    val ds = (0 to 10000).map(i =>
       (i, Seq((i, Seq((i, "This is really not that long of a string")))))).toDS()
     val sizeInBytes = ds.logicalPlan.stats.sizeInBytes
     // sizeInBytes is 2404280404, before the fix, it overflows to a negative number
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/QueryTest.scala b/sql/core/src/test/scala/org/apache/spark/sql/QueryTest.scala
index f9808834df4a5..cddab52c28112 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/QueryTest.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/QueryTest.scala
@@ -89,7 +89,7 @@ abstract class QueryTest extends PlanTest {
    * Evaluates a dataset to make sure that the result of calling collect matches the given
    * expected answer, after sort.
    */
-  protected def checkDatasetUnorderly[T : Ordering](
+  protected def checkDatasetUnorderly[T: Ordering](
       ds: => Dataset[T],
       expectedAnswer: T*): Unit = {
     val result = getResult(ds)
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
index 68f61cfab6d2f..909869f030312 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
@@ -1466,7 +1466,7 @@ class SQLQuerySuite extends QueryTest with SharedSQLContext {
     import org.apache.spark.unsafe.types.CalendarInterval
 
     val df = sql("select interval 3 years -3 month 7 week 123 microseconds")
-    checkAnswer(df, Row(new CalendarInterval(12 * 3 - 3, 7L * 1000 * 1000 * 3600 * 24 * 7 + 123 )))
+    checkAnswer(df, Row(new CalendarInterval(12 * 3 - 3, 7L * 1000 * 1000 * 3600 * 24 * 7 + 123)))
     withTempPath(f => {
       // Currently we don't yet support saving out values of interval data type.
       val e = intercept[AnalysisException] {
@@ -2549,7 +2549,7 @@ class SQLQuerySuite extends QueryTest with SharedSQLContext {
     withTable("_tbl") {
       sql("CREATE TABLE `_tbl`(i INT) USING parquet")
       sql("INSERT INTO `_tbl` VALUES (1), (2), (3)")
-      checkAnswer( sql("SELECT * FROM `_tbl`"), Row(1) :: Row(2) :: Row(3) :: Nil)
+      checkAnswer(sql("SELECT * FROM `_tbl`"), Row(1) :: Row(2) :: Row(3) :: Nil)
     }
   }
 
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/SessionStateSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/SessionStateSuite.scala
index c01666770720c..aa5cba6cdd5e9 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/SessionStateSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/SessionStateSuite.scala
@@ -129,7 +129,7 @@ class SessionStateSuite extends SparkFunSuite
   test("fork new session and inherit listener manager") {
     class CommandCollector extends QueryExecutionListener {
       val commands: ArrayBuffer[String] = ArrayBuffer.empty[String]
-      override def onFailure(funcName: String, qe: QueryExecution, ex: Exception) : Unit = {}
+      override def onFailure(funcName: String, qe: QueryExecution, ex: Exception): Unit = {}
       override def onSuccess(funcName: String, qe: QueryExecution, duration: Long): Unit = {
         commands += funcName
       }
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/StatisticsCollectionSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/StatisticsCollectionSuite.scala
index b031c52dad8b5..b75f3840c009a 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/StatisticsCollectionSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/StatisticsCollectionSuite.scala
@@ -104,7 +104,7 @@ class StatisticsCollectionSuite extends StatisticsCollectionTestBase with Shared
 
   test("column stats round trip serialization") {
     // Make sure we serialize and then deserialize and we will get the result data
-    val df = data.toDF(stats.keys.toSeq :+ "carray" : _*)
+    val df = data.toDF(stats.keys.toSeq:+ "carray": _*)
     stats.zip(df.schema).foreach { case ((k, v), field) =>
       withClue(s"column $k with type ${field.dataType}") {
         val roundtrip = ColumnStat.fromMap("table_is_foo", field, v.toMap(k, field.dataType))
@@ -116,7 +116,7 @@ class StatisticsCollectionSuite extends StatisticsCollectionTestBase with Shared
   test("analyze column command - result verification") {
     // (data.head.productArity - 1) because the last column does not support stats collection.
     assert(stats.size == data.head.productArity - 1)
-    val df = data.toDF(stats.keys.toSeq :+ "carray" : _*)
+    val df = data.toDF(stats.keys.toSeq:+ "carray": _*)
     checkColStats(df, stats)
   }
 
@@ -147,7 +147,7 @@ class StatisticsCollectionSuite extends StatisticsCollectionTestBase with Shared
       BigInt(4444444444L) -> ("4.1 GB", "4.44E+9"),
       BigInt(5555555555555L) -> ("5.1 TB", "5.56E+12"),
       BigInt(6666666666666666L) -> ("5.9 PB", "6.67E+15"),
-      BigInt(1L << 10 ) * (1L << 60) -> ("1024.0 EB", "1.18E+21"),
+      BigInt(1L << 10) * (1L << 60) -> ("1024.0 EB", "1.18E+21"),
       BigInt(1L << 11) * (1L << 60) -> ("2.36E+21 B", "2.36E+21")
     )
     numbers.foreach { case (input, (expectedSize, expectedRows)) =>
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/ReferenceSort.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/ReferenceSort.scala
index 6abcb1f067968..8829580e42ac7 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/execution/ReferenceSort.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/ReferenceSort.scala
@@ -40,7 +40,7 @@ case class ReferenceSort(
     if (global) OrderedDistribution(sortOrder) :: Nil else UnspecifiedDistribution :: Nil
 
   protected override def doExecute(): RDD[InternalRow] = attachTree(this, "sort") {
-    child.execute().mapPartitions( { iterator =>
+    child.execute().mapPartitions({ iterator =>
       val ordering = newOrdering(sortOrder, child.output)
       val sorter = new ExternalSorter[InternalRow, Null, InternalRow](
         TaskContext.get(), ordering = Some(ordering))
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/BenchmarkWideTable.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/BenchmarkWideTable.scala
index 9dcaca0ca93ee..65314834bcbe7 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/BenchmarkWideTable.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/BenchmarkWideTable.scala
@@ -35,7 +35,7 @@ class BenchmarkWideTable extends BenchmarkBase {
     val columns = (0 until 400).map{ i => s"id as id$i"}
     val benchmark = new Benchmark("projection on wide table", N)
     benchmark.addCase("wide table", numIters = 5) { iter =>
-      df.selectExpr(columns : _*).queryExecution.toRdd.count()
+      df.selectExpr(columns: _*).queryExecution.toRdd.count()
     }
     benchmark.run()
 
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/UnsafeArrayDataBenchmark.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/UnsafeArrayDataBenchmark.scala
index 6c7779b5790d0..f118f06920ace 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/UnsafeArrayDataBenchmark.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/UnsafeArrayDataBenchmark.scala
@@ -34,7 +34,7 @@ import org.apache.spark.util.Benchmark
  */
 class UnsafeArrayDataBenchmark extends BenchmarkBase {
 
-  def calculateHeaderPortionInBytes(count: Int) : Int = {
+  def calculateHeaderPortionInBytes(count: Int): Int = {
     /* 4 + 4 * count // Use this expression for SPARK-15962 */
     UnsafeArrayData.calculateHeaderPortionInBytes(count)
   }
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetIOSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetIOSuite.scala
index 94a2f9a00b3f3..1431e977c209a 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetIOSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetIOSuite.scala
@@ -77,7 +77,7 @@ class ParquetIOSuite extends QueryTest with ParquetTest with SharedSQLContext {
   /**
    * Writes `data` to a Parquet file, reads it back and check file contents.
    */
-  protected def checkParquetFile[T <: Product : ClassTag: TypeTag](data: Seq[T]): Unit = {
+  protected def checkParquetFile[T <: Product: ClassTag: TypeTag](data: Seq[T]): Unit = {
     withParquetDataFrame(data)(r => checkAnswer(r, data.map(Row.fromTuple)))
   }
 
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala
index 2efff3f57d7d3..4efdc78429df1 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala
@@ -756,7 +756,7 @@ class ParquetQuerySuite extends QueryTest with ParquetTest with SharedSQLContext
     withSQLConf(SQLConf.WHOLESTAGE_MAX_NUM_FIELDS.key -> "10") {
       withTempPath { dir =>
         val path = dir.getCanonicalPath
-        val df = spark.range(10).select(Seq.tabulate(11) {i => ('id + i).as(s"c$i")} : _*)
+        val df = spark.range(10).select(Seq.tabulate(11) {i => ('id + i).as(s"c$i")}: _*)
         df.write.mode(SaveMode.Overwrite).parquet(path)
 
         // donot return batch, because whole stage codegen is disabled for wide table (>200 columns)
@@ -767,10 +767,10 @@ class ParquetQuerySuite extends QueryTest with ParquetTest with SharedSQLContext
 
         // return batch
         val columns = Seq.tabulate(9) {i => s"c$i"}
-        val df3 = df2.selectExpr(columns : _*)
+        val df3 = df2.selectExpr(columns: _*)
         val fileScan3 = df3.queryExecution.sparkPlan.find(_.isInstanceOf[FileSourceScanExec]).get
         assert(fileScan3.asInstanceOf[FileSourceScanExec].supportsBatch)
-        checkAnswer(df3, df.selectExpr(columns : _*))
+        checkAnswer(df3, df.selectExpr(columns: _*))
       }
     }
   }
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/joins/BroadcastJoinSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/joins/BroadcastJoinSuite.scala
index afb8ced53e25c..d3e48d9f35256 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/execution/joins/BroadcastJoinSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/joins/BroadcastJoinSuite.scala
@@ -126,7 +126,7 @@ class BroadcastJoinSuite extends QueryTest with SQLTestUtils {
     }
   }
 
-  private def assertBroadcastJoin(df : Dataset[Row]) : Unit = {
+  private def assertBroadcastJoin(df: Dataset[Row]): Unit = {
     val df1 = spark.createDataFrame(Seq((1, "4"), (2, "2"))).toDF("key", "value")
     val joined = df1.join(df, Seq("key"), "inner")
 
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/state/StateStoreSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/state/StateStoreSuite.scala
index c2087ec219e57..501656deae635 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/state/StateStoreSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/state/StateStoreSuite.scala
@@ -160,7 +160,7 @@ class StateStoreSuite extends StateStoreSuiteBase[HDFSBackedStateStoreProvider]
       store.commit()
       provider.doMaintenance() // do cleanup
     }
-    val snapshotVersion = (0 to 10).find( version =>
+    val snapshotVersion = (0 to 10).find(version =>
       fileExists(provider, version, isSnapshot = true)).getOrElse(fail("snapshot file not found"))
 
     // Corrupt snapshot file and verify that it throws error
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala
index d1daf860fdfff..1c09d92d441be 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala
@@ -48,7 +48,7 @@ class JDBCSuite extends SparkFunSuite
   val testBytes = Array[Byte](99.toByte, 134.toByte, 135.toByte, 200.toByte, 205.toByte)
 
   val testH2Dialect = new JdbcDialect {
-    override def canHandle(url: String) : Boolean = url.startsWith("jdbc:h2")
+    override def canHandle(url: String): Boolean = url.startsWith("jdbc:h2")
     override def getCatalystType(
         sqlType: Int, typeName: String, size: Int, md: MetadataBuilder): Option[DataType] =
       Some(StringType)
@@ -694,7 +694,7 @@ class JDBCSuite extends SparkFunSuite
 
   test("Aggregated dialects") {
     val agg = new AggregatedDialect(List(new JdbcDialect {
-      override def canHandle(url: String) : Boolean = url.startsWith("jdbc:h2:")
+      override def canHandle(url: String): Boolean = url.startsWith("jdbc:h2:")
       override def getCatalystType(
           sqlType: Int, typeName: String, size: Int, md: MetadataBuilder): Option[DataType] =
         if (sqlType % 2 == 0) {
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCWriteSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCWriteSuite.scala
index bf1fd160704fa..af55eacfe26bc 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCWriteSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCWriteSuite.scala
@@ -44,7 +44,7 @@ class JDBCWriteSuite extends SharedSQLContext with BeforeAndAfter {
   properties.setProperty("rowId", "false")
 
   val testH2Dialect = new JdbcDialect {
-    override def canHandle(url: String) : Boolean = url.startsWith("jdbc:h2")
+    override def canHandle(url: String): Boolean = url.startsWith("jdbc:h2")
     override def isCascadingTruncateTable(): Option[Boolean] = Some(false)
   }
 
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamTest.scala b/sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamTest.scala
index b2c42eef88f6d..c2a4b0a8be485 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamTest.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamTest.scala
@@ -120,7 +120,7 @@ trait StreamTest extends QueryTest with SharedSQLContext with Timeouts with Befo
    * This operation automatically blocks until all added data has been processed.
    */
   object CheckAnswer {
-    def apply[A : Encoder](data: A*): CheckAnswerRows = {
+    def apply[A: Encoder](data: A*): CheckAnswerRows = {
       val encoder = encoderFor[A]
       val toExternalRow = RowEncoder(encoder.schema).resolveAndBind()
       CheckAnswerRows(
@@ -137,7 +137,7 @@ trait StreamTest extends QueryTest with SharedSQLContext with Timeouts with Befo
    * This operation automatically blocks until all added data has been processed.
    */
   object CheckLastBatch {
-    def apply[A : Encoder](data: A*): CheckAnswerRows = {
+    def apply[A: Encoder](data: A*): CheckAnswerRows = {
       apply(isSorted = false, data: _*)
     }
 
@@ -179,7 +179,7 @@ trait StreamTest extends QueryTest with SharedSQLContext with Timeouts with Befo
    *                     UncaughtExceptionHandler.
    * @param assertFailure a function to verify the error.
    */
-  case class ExpectFailure[T <: Throwable : ClassTag](
+  case class ExpectFailure[T <: Throwable: ClassTag](
       assertFailure: Throwable => Unit = _ => {},
       isFatalError: Boolean = false) extends StreamAction {
     val causeClass: Class[T] = implicitly[ClassTag[T]].runtimeClass.asInstanceOf[Class[T]]
@@ -195,8 +195,8 @@ trait StreamTest extends QueryTest with SharedSQLContext with Timeouts with Befo
 
   object Assert {
     def apply(condition: => Boolean, message: String = ""): Assert = new Assert(condition, message)
-    def apply(message: String)(body: => Unit): Assert = new Assert( { body; true }, message)
-    def apply(body: => Unit): Assert = new Assert( { body; true }, "")
+    def apply(message: String)(body: => Unit): Assert = new Assert({ body; true }, message)
+    def apply(body: => Unit): Assert = new Assert({ body; true }, "")
   }
 
   /** Assert that a condition on the active query is true */
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveInspectorSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveInspectorSuite.scala
index 3de1f4aeb74dc..e44649ff4951a 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveInspectorSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveInspectorSuite.scala
@@ -125,8 +125,8 @@ class HiveInspectorSuite extends SparkFunSuite with HiveInspectors {
     case DecimalType() => PrimitiveObjectInspectorFactory.writableHiveDecimalObjectInspector
     case StructType(fields) =>
       ObjectInspectorFactory.getStandardStructObjectInspector(
-        java.util.Arrays.asList(fields.map(f => f.name) : _*),
-        java.util.Arrays.asList(fields.map(f => toWritableInspector(f.dataType)) : _*))
+        java.util.Arrays.asList(fields.map(f => f.name): _*),
+        java.util.Arrays.asList(fields.map(f => toWritableInspector(f.dataType)): _*))
   }
 
   def checkDataType(dt1: Seq[DataType], dt2: Seq[DataType]): Unit = {
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala
index 5fd266c2d033c..e29c6cdd43ab0 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala
@@ -612,7 +612,7 @@ class StatisticsSuite extends StatisticsCollectionTestBase with TestHiveSingleto
     val tableName = "column_stats_test2"
     // (data.head.productArity - 1) because the last column does not support stats collection.
     assert(stats.size == data.head.productArity - 1)
-    val df = data.toDF(stats.keys.toSeq :+ "carray" : _*)
+    val df = data.toDF(stats.keys.toSeq:+ "carray": _*)
 
     withTable(tableName) {
       df.write.saveAsTable(tableName)
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala
index 31fa3d2447467..7ef7c50b3904c 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala
@@ -956,7 +956,7 @@ class HiveDDLSuite
     }
   }
 
-  private def withCreateTableLikeTempView(location : Option[String]): Unit = {
+  private def withCreateTableLikeTempView(location: Option[String]): Unit = {
     val sourceViewName = "tab1"
     val targetTabName = "tab2"
     val tableType = if (location.isDefined) CatalogTableType.EXTERNAL else CatalogTableType.MANAGED
@@ -988,7 +988,7 @@ class HiveDDLSuite
     }
   }
 
-  private def withCreateTableLikeDSTable(location : Option[String]): Unit = {
+  private def withCreateTableLikeDSTable(location: Option[String]): Unit = {
     val sourceTabName = "tab1"
     val targetTabName = "tab2"
     val tableType = if (location.isDefined) CatalogTableType.EXTERNAL else CatalogTableType.MANAGED
@@ -1023,7 +1023,7 @@ class HiveDDLSuite
     }
   }
 
-  private def withCreateTableLikeExtDSTable(location : Option[String]): Unit = {
+  private def withCreateTableLikeExtDSTable(location: Option[String]): Unit = {
     val sourceTabName = "tab1"
     val targetTabName = "tab2"
     val tableType = if (location.isDefined) CatalogTableType.EXTERNAL else CatalogTableType.MANAGED
@@ -1061,7 +1061,7 @@ class HiveDDLSuite
     }
   }
 
-  private def withCreateTableLikeManagedHiveTable(location : Option[String]): Unit = {
+  private def withCreateTableLikeManagedHiveTable(location: Option[String]): Unit = {
     val sourceTabName = "tab1"
     val targetTabName = "tab2"
     val tableType = if (location.isDefined) CatalogTableType.EXTERNAL else CatalogTableType.MANAGED
@@ -1093,7 +1093,7 @@ class HiveDDLSuite
     }
   }
 
-  private def withCreateTableLikeExtHiveTable(location : Option[String]): Unit = {
+  private def withCreateTableLikeExtHiveTable(location: Option[String]): Unit = {
     val catalog = spark.sessionState.catalog
     val tableType = if (location.isDefined) CatalogTableType.EXTERNAL else CatalogTableType.MANAGED
     withTempDir { tmpDir =>
@@ -1143,7 +1143,7 @@ class HiveDDLSuite
     }
   }
 
-  private def withCreateTableLikeView(location : Option[String]): Unit = {
+  private def withCreateTableLikeView(location: Option[String]): Unit = {
     val sourceTabName = "tab1"
     val sourceViewName = "view"
     val targetTabName = "tab2"
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala
index cf33760360724..08f87ea194200 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala
@@ -265,7 +265,7 @@ class HiveQuerySuite extends HiveComparisonTest with SQLTestUtils with BeforeAnd
   // Jdk version leads to different query output for double, so not use createQueryTest here
   test("division") {
     val res = sql("SELECT 2 / 1, 1 / 2, 1 / 3, 1 / COUNT(*) FROM src LIMIT 1").collect().head
-    Seq(2.0, 0.5, 0.3333333333333333, 0.002).zip(res.toSeq).foreach( x =>
+    Seq(2.0, 0.5, 0.3333333333333333, 0.002).zip(res.toSeq).foreach(x =>
       assert(x._1 == x._2.asInstanceOf[Double]))
   }
 
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/parquetSuites.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/parquetSuites.scala
index 23f21e6b9931e..6cd8120f0d9b6 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/parquetSuites.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/parquetSuites.scala
@@ -691,7 +691,7 @@ class ParquetSourceSuite extends ParquetPartitioningTest {
       "partitioned_parquet_with_key_and_complextypes",
       "normal_parquet")
 
-    sql( s"""
+    sql(s"""
       CREATE TEMPORARY VIEW partitioned_parquet
       USING org.apache.spark.sql.parquet
       OPTIONS (
@@ -699,7 +699,7 @@ class ParquetSourceSuite extends ParquetPartitioningTest {
       )
     """)
 
-    sql( s"""
+    sql(s"""
       CREATE TEMPORARY VIEW partitioned_parquet_with_key
       USING org.apache.spark.sql.parquet
       OPTIONS (
@@ -707,7 +707,7 @@ class ParquetSourceSuite extends ParquetPartitioningTest {
       )
     """)
 
-    sql( s"""
+    sql(s"""
       CREATE TEMPORARY VIEW normal_parquet
       USING org.apache.spark.sql.parquet
       OPTIONS (
@@ -715,7 +715,7 @@ class ParquetSourceSuite extends ParquetPartitioningTest {
       )
     """)
 
-    sql( s"""
+    sql(s"""
       CREATE TEMPORARY VIEW partitioned_parquet_with_key_and_complextypes
       USING org.apache.spark.sql.parquet
       OPTIONS (
@@ -723,7 +723,7 @@ class ParquetSourceSuite extends ParquetPartitioningTest {
       )
     """)
 
-    sql( s"""
+    sql(s"""
       CREATE TEMPORARY VIEW partitioned_parquet_with_complextypes
       USING org.apache.spark.sql.parquet
       OPTIONS (
diff --git a/streaming/src/test/scala/org/apache/spark/streaming/BasicOperationsSuite.scala b/streaming/src/test/scala/org/apache/spark/streaming/BasicOperationsSuite.scala
index a3062ac94614b..717b7c0960598 100644
--- a/streaming/src/test/scala/org/apache/spark/streaming/BasicOperationsSuite.scala
+++ b/streaming/src/test/scala/org/apache/spark/streaming/BasicOperationsSuite.scala
@@ -64,9 +64,9 @@ class BasicOperationsSuite extends TestSuiteBase {
     assert(numInputPartitions === 2, "Number of input partitions has been changed from 2")
     val input = Seq(1 to 4, 5 to 8, 9 to 12)
     val output = Seq(
-      Seq( Seq(1, 2), Seq(3, 4) ),
-      Seq( Seq(5, 6), Seq(7, 8) ),
-      Seq( Seq(9, 10), Seq(11, 12) )
+      Seq(Seq(1, 2), Seq(3, 4)),
+      Seq(Seq(5, 6), Seq(7, 8)),
+      Seq(Seq(9, 10), Seq(11, 12))
     )
     val operation = (r: DStream[Int]) => r.glom().map(_.toSeq)
     testOperation(input, operation, output)
@@ -124,18 +124,18 @@ class BasicOperationsSuite extends TestSuiteBase {
 
   test("groupByKey") {
     testOperation(
-      Seq( Seq("a", "a", "b"), Seq("", ""), Seq() ),
+      Seq(Seq("a", "a", "b"), Seq("", ""), Seq()),
       (s: DStream[String]) => s.map(x => (x, 1)).groupByKey().mapValues(_.toSeq),
-      Seq( Seq(("a", Seq(1, 1)), ("b", Seq(1))), Seq(("", Seq(1, 1))), Seq() ),
+      Seq(Seq(("a", Seq(1, 1)), ("b", Seq(1))), Seq(("", Seq(1, 1))), Seq()),
       true
     )
   }
 
   test("reduceByKey") {
     testOperation(
-      Seq( Seq("a", "a", "b"), Seq("", ""), Seq() ),
+      Seq(Seq("a", "a", "b"), Seq("", ""), Seq()),
       (s: DStream[String]) => s.map(x => (x, 1)).reduceByKey(_ + _),
-      Seq( Seq(("a", 2), ("b", 1)), Seq(("", 2)), Seq() ),
+      Seq(Seq(("a", 2), ("b", 1)), Seq(("", 2)), Seq()),
       true
     )
   }
@@ -167,20 +167,20 @@ class BasicOperationsSuite extends TestSuiteBase {
 
   test("mapValues") {
     testOperation(
-      Seq( Seq("a", "a", "b"), Seq("", ""), Seq() ),
+      Seq(Seq("a", "a", "b"), Seq("", ""), Seq()),
       (s: DStream[String]) => s.map(x => (x, 1)).reduceByKey(_ + _).mapValues(_ + 10),
-      Seq( Seq(("a", 12), ("b", 11)), Seq(("", 12)), Seq() ),
+      Seq(Seq(("a", 12), ("b", 11)), Seq(("", 12)), Seq()),
       true
     )
   }
 
   test("flatMapValues") {
     testOperation(
-      Seq( Seq("a", "a", "b"), Seq("", ""), Seq() ),
+      Seq(Seq("a", "a", "b"), Seq("", ""), Seq()),
       (s: DStream[String]) => {
         s.map(x => (x, 1)).reduceByKey(_ + _).flatMapValues(x => Seq(x, x + 10))
       },
-      Seq( Seq(("a", 2), ("a", 12), ("b", 1), ("b", 11)), Seq(("", 2), ("", 12)), Seq() ),
+      Seq(Seq(("a", 2), ("a", 12), ("b", 1), ("b", 11)), Seq(("", 2), ("", 12)), Seq()),
       true
     )
   }
@@ -256,13 +256,13 @@ class BasicOperationsSuite extends TestSuiteBase {
   }
 
   test("transformWith") {
-    val inputData1 = Seq( Seq("a", "b"), Seq("a", ""), Seq(""), Seq() )
-    val inputData2 = Seq( Seq("a", "b"), Seq("b", ""), Seq(), Seq("")   )
+    val inputData1 = Seq(Seq("a", "b"), Seq("a", ""), Seq(""), Seq() )
+    val inputData2 = Seq(Seq("a", "b"), Seq("b", ""), Seq(), Seq("")   )
     val outputData = Seq(
-      Seq( ("a", (1, "x")), ("b", (1, "x")) ),
-      Seq( ("", (1, "x")) ),
-      Seq(  ),
-      Seq(  )
+      Seq(("a", (1, "x")), ("b", (1, "x"))),
+      Seq(("", (1, "x"))),
+      Seq(),
+      Seq()
     )
     val operation = (s1: DStream[String], s2: DStream[String]) => {
       val t1 = s1.map(x => (x, 1))
@@ -276,8 +276,8 @@ class BasicOperationsSuite extends TestSuiteBase {
   }
 
   test("transformWith with input stream return None") {
-    val inputData1 = Seq( Seq("a", "b"), Seq("a", ""), Seq(""), null )
-    val inputData2 = Seq( Seq("a", "b"), Seq("b", ""), Seq(), null )
+    val inputData1 = Seq(Seq("a", "b"), Seq("a", ""), Seq(""), null )
+    val inputData2 = Seq(Seq("a", "b"), Seq("b", ""), Seq(), null )
     val outputData = Seq(
       Seq("a", "b", "a", "b"),
       Seq("a", "b", "", ""),
@@ -331,13 +331,13 @@ class BasicOperationsSuite extends TestSuiteBase {
   }
 
   test("cogroup") {
-    val inputData1 = Seq( Seq("a", "a", "b"), Seq("a", ""), Seq(""), Seq() )
-    val inputData2 = Seq( Seq("a", "a", "b"), Seq("b", ""), Seq(), Seq()   )
+    val inputData1 = Seq(Seq("a", "a", "b"), Seq("a", ""), Seq(""), Seq() )
+    val inputData2 = Seq(Seq("a", "a", "b"), Seq("b", ""), Seq(), Seq()   )
     val outputData = Seq(
-      Seq( ("a", (Seq(1, 1), Seq("x", "x"))), ("b", (Seq(1), Seq("x"))) ),
-      Seq( ("a", (Seq(1), Seq())), ("b", (Seq(), Seq("x"))), ("", (Seq(1), Seq("x"))) ),
-      Seq( ("", (Seq(1), Seq())) ),
-      Seq(  )
+      Seq(("a", (Seq(1, 1), Seq("x", "x"))), ("b", (Seq(1), Seq("x")))),
+      Seq(("a", (Seq(1), Seq())), ("b", (Seq(), Seq("x"))), ("", (Seq(1), Seq("x")))),
+      Seq(("", (Seq(1), Seq()))),
+      Seq()
     )
     val operation = (s1: DStream[String], s2: DStream[String]) => {
       s1.map(x => (x, 1)).cogroup(s2.map(x => (x, "x"))).mapValues(x => (x._1.toSeq, x._2.toSeq))
@@ -346,13 +346,13 @@ class BasicOperationsSuite extends TestSuiteBase {
   }
 
   test("join") {
-    val inputData1 = Seq( Seq("a", "b"), Seq("a", ""), Seq(""), Seq() )
-    val inputData2 = Seq( Seq("a", "b"), Seq("b", ""), Seq(), Seq("")   )
+    val inputData1 = Seq(Seq("a", "b"), Seq("a", ""), Seq(""), Seq() )
+    val inputData2 = Seq(Seq("a", "b"), Seq("b", ""), Seq(), Seq("")   )
     val outputData = Seq(
-      Seq( ("a", (1, "x")), ("b", (1, "x")) ),
-      Seq( ("", (1, "x")) ),
-      Seq(  ),
-      Seq(  )
+      Seq(("a", (1, "x")), ("b", (1, "x"))),
+      Seq(("", (1, "x"))),
+      Seq(),
+      Seq()
     )
     val operation = (s1: DStream[String], s2: DStream[String]) => {
       s1.map(x => (x, 1)).join(s2.map(x => (x, "x")))
@@ -361,13 +361,13 @@ class BasicOperationsSuite extends TestSuiteBase {
   }
 
   test("leftOuterJoin") {
-    val inputData1 = Seq( Seq("a", "b"), Seq("a", ""), Seq(""), Seq() )
-    val inputData2 = Seq( Seq("a", "b"), Seq("b", ""), Seq(), Seq("")   )
+    val inputData1 = Seq(Seq("a", "b"), Seq("a", ""), Seq(""), Seq() )
+    val inputData2 = Seq(Seq("a", "b"), Seq("b", ""), Seq(), Seq("")   )
     val outputData = Seq(
-      Seq( ("a", (1, Some("x"))), ("b", (1, Some("x"))) ),
-      Seq( ("", (1, Some("x"))), ("a", (1, None)) ),
-      Seq( ("", (1, None)) ),
-      Seq(  )
+      Seq(("a", (1, Some("x"))), ("b", (1, Some("x")))),
+      Seq(("", (1, Some("x"))), ("a", (1, None))),
+      Seq(("", (1, None))),
+      Seq()
     )
     val operation = (s1: DStream[String], s2: DStream[String]) => {
       s1.map(x => (x, 1)).leftOuterJoin(s2.map(x => (x, "x")))
@@ -376,13 +376,13 @@ class BasicOperationsSuite extends TestSuiteBase {
   }
 
   test("rightOuterJoin") {
-    val inputData1 = Seq( Seq("a", "b"), Seq("a", ""), Seq(""), Seq() )
-    val inputData2 = Seq( Seq("a", "b"), Seq("b", ""), Seq(), Seq("")   )
+    val inputData1 = Seq(Seq("a", "b"), Seq("a", ""), Seq(""), Seq() )
+    val inputData2 = Seq(Seq("a", "b"), Seq("b", ""), Seq(), Seq("")   )
     val outputData = Seq(
-      Seq( ("a", (Some(1), "x")), ("b", (Some(1), "x")) ),
-      Seq( ("", (Some(1), "x")), ("b", (None, "x")) ),
-      Seq(  ),
-      Seq( ("", (None, "x")) )
+      Seq(("a", (Some(1), "x")), ("b", (Some(1), "x"))),
+      Seq(("", (Some(1), "x")), ("b", (None, "x"))),
+      Seq(),
+      Seq(("", (None, "x")))
     )
     val operation = (s1: DStream[String], s2: DStream[String]) => {
       s1.map(x => (x, 1)).rightOuterJoin(s2.map(x => (x, "x")))
@@ -391,13 +391,13 @@ class BasicOperationsSuite extends TestSuiteBase {
   }
 
   test("fullOuterJoin") {
-    val inputData1 = Seq( Seq("a", "b"), Seq("a", ""), Seq(""), Seq() )
-    val inputData2 = Seq( Seq("a", "b"), Seq("b", ""), Seq(), Seq("")   )
+    val inputData1 = Seq(Seq("a", "b"), Seq("a", ""), Seq(""), Seq() )
+    val inputData2 = Seq(Seq("a", "b"), Seq("b", ""), Seq(), Seq("")   )
     val outputData = Seq(
-      Seq( ("a", (Some(1), Some("x"))), ("b", (Some(1), Some("x"))) ),
-      Seq( ("", (Some(1), Some("x"))), ("a", (Some(1), None)), ("b", (None, Some("x"))) ),
-      Seq( ("", (Some(1), None)) ),
-      Seq( ("", (None, Some("x"))) )
+      Seq(("a", (Some(1), Some("x"))), ("b", (Some(1), Some("x")))),
+      Seq(("", (Some(1), Some("x"))), ("a", (Some(1), None)), ("b", (None, Some("x")))),
+      Seq(("", (Some(1), None))),
+      Seq(("", (None, Some("x"))))
     )
     val operation = (s1: DStream[String], s2: DStream[String]) => {
       s1.map(x => (x, 1)).fullOuterJoin(s2.map(x => (x, "x")))
diff --git a/streaming/src/test/scala/org/apache/spark/streaming/CheckpointSuite.scala b/streaming/src/test/scala/org/apache/spark/streaming/CheckpointSuite.scala
index ee2fd45a7e851..c28377816617e 100644
--- a/streaming/src/test/scala/org/apache/spark/streaming/CheckpointSuite.scala
+++ b/streaming/src/test/scala/org/apache/spark/streaming/CheckpointSuite.scala
@@ -415,7 +415,7 @@ class CheckpointSuite extends TestSuiteBase with DStreamCheckpointTester
   // source - TestInputDStream.
   test("recovery with map and reduceByKey operations") {
     testCheckpointedOperation(
-      Seq( Seq("a", "a", "b"), Seq("", ""), Seq(), Seq("a", "a", "b"), Seq("", ""), Seq() ),
+      Seq(Seq("a", "a", "b"), Seq("", ""), Seq(), Seq("a", "a", "b"), Seq("", ""), Seq()),
       (s: DStream[String]) => s.map(x => (x, 1)).reduceByKey(_ + _),
       Seq(
         Seq(("a", 2), ("b", 1)),
diff --git a/streaming/src/test/scala/org/apache/spark/streaming/ReceivedBlockHandlerSuite.scala b/streaming/src/test/scala/org/apache/spark/streaming/ReceivedBlockHandlerSuite.scala
index fe65353b9d502..933ec126d525b 100644
--- a/streaming/src/test/scala/org/apache/spark/streaming/ReceivedBlockHandlerSuite.scala
+++ b/streaming/src/test/scala/org/apache/spark/streaming/ReceivedBlockHandlerSuite.scala
@@ -100,7 +100,7 @@ abstract class BaseReceivedBlockHandlerSuite(enableEncryption: Boolean)
   }
 
   after {
-    for ( blockManager <- blockManagerBuffer ) {
+    for (blockManager <- blockManagerBuffer) {
       if (blockManager != null) {
         blockManager.stop()
       }
diff --git a/streaming/src/test/scala/org/apache/spark/streaming/UISeleniumSuite.scala b/streaming/src/test/scala/org/apache/spark/streaming/UISeleniumSuite.scala
index e7cec999c219e..7a1429d0eb4e3 100644
--- a/streaming/src/test/scala/org/apache/spark/streaming/UISeleniumSuite.scala
+++ b/streaming/src/test/scala/org/apache/spark/streaming/UISeleniumSuite.scala
@@ -93,7 +93,7 @@ class UISeleniumSuite
 
       eventually(timeout(10 seconds), interval(50 milliseconds)) {
         go to (sparkUI.webUrl.stripSuffix("/"))
-        find(cssSelector( """ul li a[href*="streaming"]""")) should not be (None)
+        find(cssSelector("""ul li a[href*="streaming"]""")) should not be (None)
       }
 
       eventually(timeout(10 seconds), interval(50 milliseconds)) {
@@ -154,7 +154,7 @@ class UISeleniumSuite
         outputOpIds.map(_.text) should be (List("0", "1"))
 
         // Check job ids
-        val jobIdCells = findAll(cssSelector( """#batch-job-table a""")).toSeq
+        val jobIdCells = findAll(cssSelector("""#batch-job-table a""")).toSeq
         jobIdCells.map(_.text) should be (List("0", "1", "2", "3"))
 
         val jobLinks = jobIdCells.flatMap(_.attribute("href"))
@@ -192,7 +192,7 @@ class UISeleniumSuite
 
       eventually(timeout(10 seconds), interval(50 milliseconds)) {
         go to (sparkUI.webUrl.stripSuffix("/"))
-        find(cssSelector( """ul li a[href*="streaming"]""")) should be(None)
+        find(cssSelector("""ul li a[href*="streaming"]""")) should be(None)
       }
 
       eventually(timeout(10 seconds), interval(50 milliseconds)) {
diff --git a/streaming/src/test/scala/org/apache/spark/streaming/WindowOperationsSuite.scala b/streaming/src/test/scala/org/apache/spark/streaming/WindowOperationsSuite.scala
index c7d085ec0799b..7b529f3e64ef8 100644
--- a/streaming/src/test/scala/org/apache/spark/streaming/WindowOperationsSuite.scala
+++ b/streaming/src/test/scala/org/apache/spark/streaming/WindowOperationsSuite.scala
@@ -116,36 +116,36 @@ class WindowOperationsSuite extends TestSuiteBase {
 
   testWindow(
     "basic window",
-    Seq( Seq(0), Seq(1), Seq(2), Seq(3), Seq(4), Seq(5)),
-    Seq( Seq(0), Seq(0, 1), Seq(1, 2), Seq(2, 3), Seq(3, 4), Seq(4, 5))
+    Seq(Seq(0), Seq(1), Seq(2), Seq(3), Seq(4), Seq(5)),
+    Seq(Seq(0), Seq(0, 1), Seq(1, 2), Seq(2, 3), Seq(3, 4), Seq(4, 5))
   )
 
   testWindow(
     "tumbling window",
-    Seq( Seq(0), Seq(1), Seq(2), Seq(3), Seq(4), Seq(5)),
-    Seq( Seq(0, 1), Seq(2, 3), Seq(4, 5)),
+    Seq(Seq(0), Seq(1), Seq(2), Seq(3), Seq(4), Seq(5)),
+    Seq(Seq(0, 1), Seq(2, 3), Seq(4, 5)),
     Seconds(2),
     Seconds(2)
   )
 
   testWindow(
     "larger window",
-    Seq( Seq(0), Seq(1), Seq(2), Seq(3), Seq(4), Seq(5)),
-    Seq( Seq(0, 1), Seq(0, 1, 2, 3), Seq(2, 3, 4, 5), Seq(4, 5)),
+    Seq(Seq(0), Seq(1), Seq(2), Seq(3), Seq(4), Seq(5)),
+    Seq(Seq(0, 1), Seq(0, 1, 2, 3), Seq(2, 3, 4, 5), Seq(4, 5)),
     Seconds(4),
     Seconds(2)
   )
 
   testWindow(
     "non-overlapping window",
-    Seq( Seq(0), Seq(1), Seq(2), Seq(3), Seq(4), Seq(5)),
-    Seq( Seq(1, 2), Seq(4, 5)),
+    Seq(Seq(0), Seq(1), Seq(2), Seq(3), Seq(4), Seq(5)),
+    Seq(Seq(1, 2), Seq(4, 5)),
     Seconds(2),
     Seconds(3)
   )
 
   test("window - persistence level") {
-    val input = Seq( Seq(0), Seq(1), Seq(2), Seq(3), Seq(4), Seq(5))
+    val input = Seq(Seq(0), Seq(1), Seq(2), Seq(3), Seq(4), Seq(5))
     val ssc = new StreamingContext(conf, batchDuration)
     val inputStream = new TestInputStream[Int](ssc, input, 1)
     val windowStream1 = inputStream.window(batchDuration * 2)
@@ -161,26 +161,26 @@ class WindowOperationsSuite extends TestSuiteBase {
 
   testReduceByKeyAndWindow(
     "basic reduction",
-    Seq( Seq(("a", 1), ("a", 3)) ),
-    Seq( Seq(("a", 4)) )
+    Seq(Seq(("a", 1), ("a", 3))),
+    Seq(Seq(("a", 4)))
   )
 
   testReduceByKeyAndWindow(
     "key already in window and new value added into window",
-    Seq( Seq(("a", 1)), Seq(("a", 1)) ),
-    Seq( Seq(("a", 1)), Seq(("a", 2)) )
+    Seq(Seq(("a", 1)), Seq(("a", 1))),
+    Seq(Seq(("a", 1)), Seq(("a", 2)))
   )
 
   testReduceByKeyAndWindow(
     "new key added into window",
-    Seq( Seq(("a", 1)), Seq(("a", 1), ("b", 1)) ),
-    Seq( Seq(("a", 1)), Seq(("a", 2), ("b", 1)) )
+    Seq(Seq(("a", 1)), Seq(("a", 1), ("b", 1))),
+    Seq(Seq(("a", 1)), Seq(("a", 2), ("b", 1)))
   )
 
   testReduceByKeyAndWindow(
     "key removed from window",
-    Seq( Seq(("a", 1)), Seq(("a", 1)), Seq(), Seq() ),
-    Seq( Seq(("a", 1)), Seq(("a", 2)), Seq(("a", 1)), Seq() )
+    Seq(Seq(("a", 1)), Seq(("a", 1)), Seq(), Seq()),
+    Seq(Seq(("a", 1)), Seq(("a", 2)), Seq(("a", 1)), Seq())
   )
 
   testReduceByKeyAndWindow(
@@ -197,26 +197,26 @@ class WindowOperationsSuite extends TestSuiteBase {
 
   testReduceByKeyAndWindowWithInverse(
     "basic reduction",
-    Seq(Seq(("a", 1), ("a", 3)) ),
-    Seq(Seq(("a", 4)) )
+    Seq(Seq(("a", 1), ("a", 3))),
+    Seq(Seq(("a", 4)))
   )
 
   testReduceByKeyAndWindowWithInverse(
     "key already in window and new value added into window",
-    Seq( Seq(("a", 1)), Seq(("a", 1)) ),
-    Seq( Seq(("a", 1)), Seq(("a", 2)) )
+    Seq(Seq(("a", 1)), Seq(("a", 1))),
+    Seq(Seq(("a", 1)), Seq(("a", 2)))
   )
 
   testReduceByKeyAndWindowWithInverse(
     "new key added into window",
-    Seq( Seq(("a", 1)), Seq(("a", 1), ("b", 1)) ),
-    Seq( Seq(("a", 1)), Seq(("a", 2), ("b", 1)) )
+    Seq(Seq(("a", 1)), Seq(("a", 1), ("b", 1))),
+    Seq(Seq(("a", 1)), Seq(("a", 2), ("b", 1)))
   )
 
   testReduceByKeyAndWindowWithInverse(
     "key removed from window",
-    Seq( Seq(("a", 1)), Seq(("a", 1)), Seq(), Seq() ),
-    Seq( Seq(("a", 1)), Seq(("a", 2)), Seq(("a", 1)), Seq(("a", 0)) )
+    Seq(Seq(("a", 1)), Seq(("a", 1)), Seq(), Seq()),
+    Seq(Seq(("a", 1)), Seq(("a", 2)), Seq(("a", 1)), Seq(("a", 0)))
   )
 
   testReduceByKeyAndWindowWithInverse(
@@ -245,7 +245,7 @@ class WindowOperationsSuite extends TestSuiteBase {
 
   test("countByWindow") {
     val input = Seq(Seq(1), Seq(1), Seq(1, 2), Seq(0), Seq(), Seq() )
-    val expectedOutput = Seq( Seq(1), Seq(2), Seq(3), Seq(3), Seq(1), Seq(0))
+    val expectedOutput = Seq(Seq(1), Seq(2), Seq(3), Seq(3), Seq(1), Seq(0))
     val windowDuration = Seconds(2)
     val slideDuration = Seconds(1)
     val numBatches = expectedOutput.size * (slideDuration / batchDuration).toInt
@@ -257,7 +257,7 @@ class WindowOperationsSuite extends TestSuiteBase {
 
   test("countByValueAndWindow") {
     val input = Seq(Seq("a"), Seq("b", "b"), Seq("a", "b"))
-    val expectedOutput = Seq( Seq(("a", 1)), Seq(("a", 1), ("b", 2)), Seq(("a", 1), ("b", 3)))
+    val expectedOutput = Seq(Seq(("a", 1)), Seq(("a", 1), ("b", 2)), Seq(("a", 1), ("b", 3)))
     val windowDuration = Seconds(2)
     val slideDuration = Seconds(1)
     val numBatches = expectedOutput.size * (slideDuration / batchDuration).toInt

From 3acc1d36ac307d723dcb5d7399ffb3adb1ce08b0 Mon Sep 17 00:00:00 2001
From: Wang Gengliang 
Date: Thu, 29 Jun 2017 16:34:53 -0700
Subject: [PATCH 5/8] more scalastyle off/on

---
 .../org/apache/spark/scheduler/TaskSetManagerSuite.scala | 2 ++
 .../shuffle/sort/BypassMergeSortShuffleWriterSuite.scala | 9 ++++++++-
 .../spark/sql/streaming/FileStreamSourceSuite.scala      | 2 ++
 .../spark/sql/hive/PartitionedTablePerfStatsSuite.scala  | 2 ++
 4 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/core/src/test/scala/org/apache/spark/scheduler/TaskSetManagerSuite.scala b/core/src/test/scala/org/apache/spark/scheduler/TaskSetManagerSuite.scala
index 80fb674725814..ef38963201db4 100644
--- a/core/src/test/scala/org/apache/spark/scheduler/TaskSetManagerSuite.scala
+++ b/core/src/test/scala/org/apache/spark/scheduler/TaskSetManagerSuite.scala
@@ -85,8 +85,10 @@ object FakeRackUtil {
  * a list of "live" executors and their hostnames for isExecutorAlive and hasExecutorsAliveOnHost
  * to work, and these are required for locality in TaskSetManager.
  */
+// scalastyle:off
 class FakeTaskScheduler(sc: SparkContext, liveExecutors: (String, String)* /* execId, host */)
   extends TaskSchedulerImpl(sc)
+// scalastyle:on
 {
   val startedTasks = new ArrayBuffer[Long]
   val endedTasks = new mutable.HashMap[Long, TaskEndReason]
diff --git a/core/src/test/scala/org/apache/spark/shuffle/sort/BypassMergeSortShuffleWriterSuite.scala b/core/src/test/scala/org/apache/spark/shuffle/sort/BypassMergeSortShuffleWriterSuite.scala
index 6a059916522bd..ea57f9f03fd0c 100644
--- a/core/src/test/scala/org/apache/spark/shuffle/sort/BypassMergeSortShuffleWriterSuite.scala
+++ b/core/src/test/scala/org/apache/spark/shuffle/sort/BypassMergeSortShuffleWriterSuite.scala
@@ -140,7 +140,9 @@ class BypassMergeSortShuffleWriterSuite extends SparkFunSuite with BeforeAndAfte
       conf
     )
     writer.write(Iterator.empty)
+    // scalastyle:off
     writer.stop(/* success = */ true)
+    // scalastyle:on
     assert(writer.getPartitionLengths.sum === 0)
     assert(outputFile.exists())
     assert(outputFile.length() === 0)
@@ -164,7 +166,9 @@ class BypassMergeSortShuffleWriterSuite extends SparkFunSuite with BeforeAndAfte
       conf
     )
     writer.write(records)
+    // scalastyle:off
     writer.stop(/* success = */ true)
+    // scalastyle:on
     assert(temporaryFilesCreated.nonEmpty)
     assert(writer.getPartitionLengths.sum === outputFile.length())
     assert(writer.getPartitionLengths.count(_ == 0L) === 4) // should be 4 zero length files
@@ -206,8 +210,9 @@ class BypassMergeSortShuffleWriterSuite extends SparkFunSuite with BeforeAndAfte
     assert(temporaryFilesCreated.nonEmpty)
     // Only 3 temp shuffle files will be created
     assert(temporaryFilesCreated.count(_.exists()) === 3)
-
+    // scalastyle:off
     writer.stop(/* success = */ false)
+    // scalastyle:on
     assert(temporaryFilesCreated.count(_.exists()) === 0) // check that temporary files were deleted
   }
 
@@ -229,7 +234,9 @@ class BypassMergeSortShuffleWriterSuite extends SparkFunSuite with BeforeAndAfte
       }))
     }
     assert(temporaryFilesCreated.nonEmpty)
+    // scalastyle:off
     writer.stop(/* success = */ false)
+    // scalastyle:on
     assert(temporaryFilesCreated.count(_.exists()) === 0)
   }
 
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSourceSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSourceSuite.scala
index 2108b118bf059..1b7a5cff9e201 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSourceSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSourceSuite.scala
@@ -1232,7 +1232,9 @@ class FileStreamSourceSuite extends FileStreamSourceTest {
       f2.setLastModified(f1.lastModified + 3600 * 1000 /* 1 hour later */)
 
       runTwoBatchesAndVerifyResults(src, latestFirst = true, firstBatch = "2", secondBatch = "1",
+        // scalastyle:off
         maxFileAge = Some("1m") /* 1 minute */)
+        // scalastyle:on
     }
   }
 
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/PartitionedTablePerfStatsSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/PartitionedTablePerfStatsSuite.scala
index 50506197b3138..1b9551c01b076 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/PartitionedTablePerfStatsSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/PartitionedTablePerfStatsSuite.scala
@@ -241,7 +241,9 @@ class PartitionedTablePerfStatsSuite
   genericTest("file status cache respects size limit") { spec =>
     withSQLConf(
         SQLConf.HIVE_MANAGE_FILESOURCE_PARTITIONS.key -> "true",
+        //scalastyle:off
         SQLConf.HIVE_FILESOURCE_PARTITION_FILE_CACHE_SIZE.key -> "1" /* 1 byte */) {
+        //scalastyle:on
       withTable("test") {
         withTempDir { dir =>
           spec.setupTable("test", dir)

From d1b4bbe46a279959816e57a9c16636dd5e2d23ad Mon Sep 17 00:00:00 2001
From: Wang Gengliang 
Date: Thu, 29 Jun 2017 16:36:48 -0700
Subject: [PATCH 6/8] Insert a space after the start of the comment

---
 .../spark/sql/hive/PartitionedTablePerfStatsSuite.scala       | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/PartitionedTablePerfStatsSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/PartitionedTablePerfStatsSuite.scala
index 1b9551c01b076..8887a92d6d613 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/PartitionedTablePerfStatsSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/PartitionedTablePerfStatsSuite.scala
@@ -241,9 +241,9 @@ class PartitionedTablePerfStatsSuite
   genericTest("file status cache respects size limit") { spec =>
     withSQLConf(
         SQLConf.HIVE_MANAGE_FILESOURCE_PARTITIONS.key -> "true",
-        //scalastyle:off
+        // scalastyle:off
         SQLConf.HIVE_FILESOURCE_PARTITION_FILE_CACHE_SIZE.key -> "1" /* 1 byte */) {
-        //scalastyle:on
+        // scalastyle:on
       withTable("test") {
         withTempDir { dir =>
           spec.setupTable("test", dir)

From 05084a9706b2c3a9cf6dc1c733d7d16b8bac0f41 Mon Sep 17 00:00:00 2001
From: Wang Gengliang 
Date: Thu, 29 Jun 2017 21:01:48 -0700
Subject: [PATCH 7/8] fix mistake: enable
 org.scalastyle.file.HeaderMatchesChecker

---
 scalastyle-config.xml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scalastyle-config.xml b/scalastyle-config.xml
index 64b04d2c63723..fec44d86107e8 100644
--- a/scalastyle-config.xml
+++ b/scalastyle-config.xml
@@ -46,7 +46,7 @@ This file is divided into 3 sections:
 
   
 
-  
+  
     
        
Date: Thu, 29 Jun 2017 22:06:43 -0700
Subject: [PATCH 8/8] add customId for new rule; scala files will be updated
 later

---
 scalastyle-config.xml | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/scalastyle-config.xml b/scalastyle-config.xml
index fec44d86107e8..8dc541db1933a 100644
--- a/scalastyle-config.xml
+++ b/scalastyle-config.xml
@@ -243,16 +243,26 @@ This file is divided into 3 sections:
     
   
 
-  
+  
     
       COLON, COMMA, RPAREN
     
+    
   
 
-  
+  
     
       LPAREN
     
+