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 8bf4489e1aca718025477b62d7bbc08fc9ba7c88..8782fcda162c7ded94835f50ed775406ecab46ec 100644
--- a/core/src/main/scala/org/apache/spark/rdd/RDD.scala
+++ b/core/src/main/scala/org/apache/spark/rdd/RDD.scala
@@ -722,7 +722,7 @@ abstract class RDD[T: ClassTag](
* An example of pipe the RDD data of groupBy() in a streaming way,
* instead of constructing a huge String to concat all the elements:
* def printRDDElement(record:(String, Seq[String]), f:String=>Unit) =
- * for (e <- record._2){f(e)}
+ * for (e <- record._2) {f(e)}
* @param separateWorkingDir Use separate working directories for each task.
* @return the result RDD
*/
diff --git a/core/src/main/scala/org/apache/spark/rpc/RpcTimeout.scala b/core/src/main/scala/org/apache/spark/rpc/RpcTimeout.scala
index 8b4ebf34ba83c50e3b9f259e30ae51c1a6133021..2950df62bf285c702f34be59b8d3d8d6d0240a46 100644
--- a/core/src/main/scala/org/apache/spark/rpc/RpcTimeout.scala
+++ b/core/src/main/scala/org/apache/spark/rpc/RpcTimeout.scala
@@ -119,7 +119,7 @@ private[spark] object RpcTimeout {
// Find the first set property or use the default value with the first property
val itr = timeoutPropList.iterator
var foundProp: Option[(String, String)] = None
- while (itr.hasNext && foundProp.isEmpty){
+ while (itr.hasNext && foundProp.isEmpty) {
val propKey = itr.next()
conf.getOption(propKey).foreach { prop => foundProp = Some(propKey, prop) }
}
diff --git a/core/src/main/scala/org/apache/spark/scheduler/InputFormatInfo.scala b/core/src/main/scala/org/apache/spark/scheduler/InputFormatInfo.scala
index 8235b1024537658a7782ed0c2868eb581472e25e..def0aac720b64a5c5f18606bd2a996f28a2be1f6 100644
--- a/core/src/main/scala/org/apache/spark/scheduler/InputFormatInfo.scala
+++ b/core/src/main/scala/org/apache/spark/scheduler/InputFormatInfo.scala
@@ -173,7 +173,7 @@ object InputFormatInfo {
for (inputSplit <- formats) {
val splits = inputSplit.findPreferredLocations()
- for (split <- splits){
+ for (split <- splits) {
val location = split.hostLocation
val set = nodeToSplit.getOrElseUpdate(location, new HashSet[SplitInfo])
set += split
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 8b2f4973efe2279ef979d49a7ddba8c4424738fc..36df032c25141ff89d0390541146803686871a47 100644
--- a/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala
+++ b/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala
@@ -623,7 +623,7 @@ private[spark] object TaskSchedulerImpl {
val containerList: ArrayBuffer[T] = map.getOrElse(key, null)
assert(containerList != null)
// Get the index'th entry for this host - if present
- if (index < containerList.size){
+ if (index < containerList.size) {
retval += containerList.apply(index)
found = true
}
diff --git a/core/src/main/scala/org/apache/spark/status/api/v1/OneStageResource.scala b/core/src/main/scala/org/apache/spark/status/api/v1/OneStageResource.scala
index f9812f06cf527148c030a85879e4319eddfbc33d..3e6d2942d0fbb1d64c683e808a55a08ef2cf31e8 100644
--- a/core/src/main/scala/org/apache/spark/status/api/v1/OneStageResource.scala
+++ b/core/src/main/scala/org/apache/spark/status/api/v1/OneStageResource.scala
@@ -33,7 +33,7 @@ private[v1] class OneStageResource(ui: SparkUI) {
@GET
@Path("")
def stageData(@PathParam("stageId") stageId: Int): Seq[StageData] = {
- withStage(stageId){ stageAttempts =>
+ withStage(stageId) { stageAttempts =>
stageAttempts.map { stage =>
AllStagesResource.stageUiToStageData(stage.status, stage.info, stage.ui,
includeDetails = true)
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 69ac37511e730d1648ee44ae9afa1abfdffaf2a9..cae7c9ed952f12e3ebb9ed24ac5af75134e096b0 100644
--- a/core/src/main/scala/org/apache/spark/storage/BlockManagerId.scala
+++ b/core/src/main/scala/org/apache/spark/storage/BlockManagerId.scala
@@ -44,7 +44,7 @@ class BlockManagerId private (
def executorId: String = executorId_
- if (null != host_){
+ if (null != host_) {
Utils.checkHost(host_, "Expected hostname")
assert (port_ > 0)
}
diff --git a/core/src/test/scala/org/apache/spark/AccumulatorSuite.scala b/core/src/test/scala/org/apache/spark/AccumulatorSuite.scala
index 4ff8ae57ab3c099a258e12de3090a1c61c1fb782..61ab24051e6007d9b75370d645a9ac37023013a6 100644
--- a/core/src/test/scala/org/apache/spark/AccumulatorSuite.scala
+++ b/core/src/test/scala/org/apache/spark/AccumulatorSuite.scala
@@ -57,7 +57,7 @@ class AccumulatorSuite extends SparkFunSuite with Matchers with LocalSparkContex
}
}
- test ("basic accumulation"){
+ test ("basic accumulation") {
sc = new SparkContext("local", "test")
val acc : Accumulator[Int] = sc.accumulator(0)
diff --git a/core/src/test/scala/org/apache/spark/ImplicitOrderingSuite.scala b/core/src/test/scala/org/apache/spark/ImplicitOrderingSuite.scala
index 4399f25626472d6d88e91c2d78c0a9a26927503c..939f12f94f5c3642c10894d91610fde70bd76af1 100644
--- a/core/src/test/scala/org/apache/spark/ImplicitOrderingSuite.scala
+++ b/core/src/test/scala/org/apache/spark/ImplicitOrderingSuite.scala
@@ -21,7 +21,7 @@ import org.apache.spark.rdd.RDD
class ImplicitOrderingSuite extends SparkFunSuite with LocalSparkContext {
// Tests that PairRDDFunctions grabs an implicit Ordering in various cases where it should.
- test("basic inference of Orderings"){
+ test("basic inference of Orderings") {
sc = new SparkContext("local", "test")
val rdd = sc.parallelize(1 to 10)
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 de6680c61006d11aa3f5688c6c4a14d28d4c8d59..e24188781f7cd28329594890a5e34e9e5dca5940 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
@@ -476,7 +476,7 @@ class ApplicationCacheSuite extends SparkFunSuite with Logging with MockitoSugar
when(request.getRequestURI()).thenReturn("http://localhost:18080/history/local-123/jobs/job/")
when(request.getQueryString()).thenReturn("id=2")
val resp = mock[HttpServletResponse]
- when(resp.encodeRedirectURL(any())).thenAnswer(new Answer[String](){
+ when(resp.encodeRedirectURL(any())).thenAnswer(new Answer[String]() {
override def answer(invocationOnMock: InvocationOnMock): String = {
invocationOnMock.getArguments()(0).asInstanceOf[String]
}
diff --git a/examples/src/main/scala/org/apache/spark/examples/LocalFileLR.scala b/examples/src/main/scala/org/apache/spark/examples/LocalFileLR.scala
index f2e4c96fa56c53e5ac68a8fb37fedb02b0c8ac29..bec89f7c3dff01e5ff87b519cc585b8e56a96bd1 100644
--- a/examples/src/main/scala/org/apache/spark/examples/LocalFileLR.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/LocalFileLR.scala
@@ -58,7 +58,7 @@ object LocalFileLR {
val ITERATIONS = args(1).toInt
// Initialize w to a random value
- var w = DenseVector.fill(D){2 * rand.nextDouble - 1}
+ var w = DenseVector.fill(D) {2 * rand.nextDouble - 1}
println("Initial w: " + w)
for (i <- 1 to ITERATIONS) {
diff --git a/examples/src/main/scala/org/apache/spark/examples/LocalKMeans.scala b/examples/src/main/scala/org/apache/spark/examples/LocalKMeans.scala
index 19bebffcb0272ba631e02afd185bf61efd125a13..f8961847f3df20d307eda58041a1c763ebb28a35 100644
--- a/examples/src/main/scala/org/apache/spark/examples/LocalKMeans.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/LocalKMeans.scala
@@ -41,7 +41,7 @@ object LocalKMeans {
def generateData: Array[DenseVector[Double]] = {
def generatePoint(i: Int): DenseVector[Double] = {
- DenseVector.fill(D){rand.nextDouble * R}
+ DenseVector.fill(D) {rand.nextDouble * R}
}
Array.tabulate(N)(generatePoint)
}
diff --git a/examples/src/main/scala/org/apache/spark/examples/LocalLR.scala b/examples/src/main/scala/org/apache/spark/examples/LocalLR.scala
index 58adbabe4454d3d3b4767c34a06ad99fa04c5220..0baf6db607ad9db5b7ef4ab214b5c11f767af95d 100644
--- a/examples/src/main/scala/org/apache/spark/examples/LocalLR.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/LocalLR.scala
@@ -41,7 +41,7 @@ object LocalLR {
def generateData: Array[DataPoint] = {
def generatePoint(i: Int): DataPoint = {
val y = if (i % 2 == 0) -1 else 1
- val x = DenseVector.fill(D){rand.nextGaussian + y * R}
+ val x = DenseVector.fill(D) {rand.nextGaussian + y * R}
DataPoint(x, y)
}
Array.tabulate(N)(generatePoint)
@@ -62,7 +62,7 @@ object LocalLR {
val data = generateData
// Initialize w to a random value
- var w = DenseVector.fill(D){2 * rand.nextDouble - 1}
+ var w = DenseVector.fill(D) {2 * rand.nextDouble - 1}
println("Initial w: " + w)
for (i <- 1 to ITERATIONS) {
diff --git a/examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala b/examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala
index f7eb9e99367a4f77281e9955b63f242b61683989..7463b868ff19b0e759a41e09d1fc7171cce0d0bf 100644
--- a/examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala
@@ -78,7 +78,7 @@ object SparkHdfsLR {
val ITERATIONS = args(1).toInt
// Initialize w to a random value
- var w = DenseVector.fill(D){2 * rand.nextDouble - 1}
+ var w = DenseVector.fill(D) {2 * rand.nextDouble - 1}
println("Initial w: " + w)
for (i <- 1 to ITERATIONS) {
diff --git a/examples/src/main/scala/org/apache/spark/examples/SparkLR.scala b/examples/src/main/scala/org/apache/spark/examples/SparkLR.scala
index 036e3d24c985f3b585ed42844ead8b24d2fe1ee4..acd8656b65a69e4b9a16c0aee1d66272e09ab9a9 100644
--- a/examples/src/main/scala/org/apache/spark/examples/SparkLR.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/SparkLR.scala
@@ -46,7 +46,7 @@ object SparkLR {
def generateData: Array[DataPoint] = {
def generatePoint(i: Int): DataPoint = {
val y = if (i % 2 == 0) -1 else 1
- val x = DenseVector.fill(D){rand.nextGaussian + y * R}
+ val x = DenseVector.fill(D) {rand.nextGaussian + y * R}
DataPoint(x, y)
}
Array.tabulate(N)(generatePoint)
@@ -71,7 +71,7 @@ object SparkLR {
val points = sc.parallelize(generateData, numSlices).cache()
// Initialize w to a random value
- var w = DenseVector.fill(D){2 * rand.nextDouble - 1}
+ var w = DenseVector.fill(D) {2 * rand.nextDouble - 1}
println("Initial w: " + w)
for (i <- 1 to ITERATIONS) {
diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/ActorWordCount.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/ActorWordCount.scala
index 2770b8af1c0ca29ea62fe9391f084730887e1c32..844772a289284628e9eda80a515d62f2f0b1b575 100644
--- a/examples/src/main/scala/org/apache/spark/examples/streaming/ActorWordCount.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/streaming/ActorWordCount.scala
@@ -100,7 +100,7 @@ class SampleActorReceiver[T](urlOfPublisher: String) extends ActorReceiver {
object FeederActor {
def main(args: Array[String]) {
- if (args.length < 2){
+ if (args.length < 2) {
System.err.println("Usage: FeederActor <hostname> <port>\n")
System.exit(1)
}
diff --git a/mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala b/mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala
index d02806a6ea227f29297aa2f266f488c9d318a50e..f21b623e93253684138481204d6f6f1e4751bcab 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala
@@ -213,8 +213,8 @@ private[ann] object AffineLayerModel {
*/
def randomWeights(numIn: Int, numOut: Int, seed: Long = 11L): (BDM[Double], BDV[Double]) = {
val rand: XORShiftRandom = new XORShiftRandom(seed)
- val weights = BDM.fill[Double](numOut, numIn){ (rand.nextDouble * 4.8 - 2.4) / numIn }
- val bias = BDV.fill[Double](numOut){ (rand.nextDouble * 4.8 - 2.4) / numIn }
+ val weights = BDM.fill[Double](numOut, numIn) { (rand.nextDouble * 4.8 - 2.4) / numIn }
+ val bias = BDV.fill[Double](numOut) { (rand.nextDouble * 4.8 - 2.4) / numIn }
(weights, bias)
}
}
@@ -529,7 +529,7 @@ private[ml] object FeedForwardTopology {
*/
def multiLayerPerceptron(layerSizes: Array[Int], softmax: Boolean = true): FeedForwardTopology = {
val layers = new Array[Layer]((layerSizes.length - 1) * 2)
- for(i <- 0 until layerSizes.length - 1){
+ for(i <- 0 until layerSizes.length - 1) {
layers(i * 2) = new AffineLayer(layerSizes(i), layerSizes(i + 1))
layers(i * 2 + 1) =
if (softmax && i == layerSizes.length - 2) {
@@ -655,7 +655,7 @@ private[ann] object FeedForwardModel {
val layers = topology.layers
val layerModels = new Array[LayerModel](layers.length)
var offset = 0
- for(i <- 0 until layers.length){
+ for(i <- 0 until layers.length) {
layerModels(i) = layers(i).getInstance(seed)
offset += layerModels(i).size
}
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala
index 718f49d3aedcd098d0c11913a7baacaab72ea699..483ef0d88ca64f04ee91847ab888d108cbffcf85 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala
@@ -145,7 +145,7 @@ class NaiveBayesModel private[ml] (
case Multinomial => (None, None)
case Bernoulli =>
val negTheta = theta.map(value => math.log(1.0 - math.exp(value)))
- val ones = new DenseVector(Array.fill(theta.numCols){1.0})
+ val ones = new DenseVector(Array.fill(theta.numCols) {1.0})
val thetaMinusNegTheta = theta.map { value =>
value - math.log(1.0 - math.exp(value))
}
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 886cd60687779d27c14affa498396486409efd27..132dc174a894e4ec213228d353639243caf33e1b 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
@@ -428,7 +428,7 @@ private[python] class PythonMLLibAPI extends Serializable {
val weight = wt.toArray
val mean = mu.map(_.asInstanceOf[DenseVector])
val sigma = si.map(_.asInstanceOf[DenseMatrix])
- val gaussians = Array.tabulate(weight.length){
+ val gaussians = Array.tabulate(weight.length) {
i => new MultivariateGaussian(mean(i), sigma(i))
}
val model = new GaussianMixtureModel(weight, gaussians)
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala b/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala
index aef9ef2cb052d8a68b805ab48b5713d18b029064..9026b97f1cbef95e16475e644e409fbf43060eb3 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala
@@ -74,7 +74,7 @@ class NaiveBayesModel private[spark] (
case Multinomial => (None, None)
case Bernoulli =>
val negTheta = thetaMatrix.map(value => math.log(1.0 - math.exp(value)))
- val ones = new DenseVector(Array.fill(thetaMatrix.numCols){1.0})
+ val ones = new DenseVector(Array.fill(thetaMatrix.numCols) {1.0})
val thetaMinusNegTheta = thetaMatrix.map { value =>
value - math.log(1.0 - math.exp(value))
}
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/evaluation/MultilabelMetrics.scala b/mllib/src/main/scala/org/apache/spark/mllib/evaluation/MultilabelMetrics.scala
index 6dd541e5c070c8a59654f163d29444b3fceda4a3..77bd0aa30dda1accc2e01116736248fd05f9b12b 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/evaluation/MultilabelMetrics.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/evaluation/MultilabelMetrics.scala
@@ -152,7 +152,7 @@ class MultilabelMetrics @Since("1.2.0") (predictionAndLabels: RDD[(Array[Double]
*/
@Since("1.2.0")
lazy val microPrecision: Double = {
- val sumFp = fpPerClass.foldLeft(0L){ case(cum, (_, fp)) => cum + fp}
+ val sumFp = fpPerClass.foldLeft(0L) { case(cum, (_, fp)) => cum + fp}
sumTp.toDouble / (sumTp + sumFp)
}
@@ -162,7 +162,7 @@ class MultilabelMetrics @Since("1.2.0") (predictionAndLabels: RDD[(Array[Double]
*/
@Since("1.2.0")
lazy val microRecall: Double = {
- val sumFn = fnPerClass.foldLeft(0.0){ case(cum, (_, fn)) => cum + fn}
+ val sumFn = fnPerClass.foldLeft(0.0) { case(cum, (_, fn)) => cum + fn}
sumTp.toDouble / (sumTp + sumFn)
}
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala
index d2687dc11bc9eb429d68d4f923fc2c6043380907..27a73805678db5d9516c98e2cee407740b70a602 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/BLAS.scala
@@ -420,7 +420,7 @@ private[spark] object BLAS extends Serializable with Logging {
val AcolPtrs = A.colPtrs
// Slicing is easy in this case. This is the optimal multiplication setting for sparse matrices
- if (A.isTransposed){
+ if (A.isTransposed) {
var colCounterForB = 0
if (!B.isTransposed) { // Expensive to put the check inside the loop
while (colCounterForB < nB) {
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/IsotonicRegression.scala b/mllib/src/main/scala/org/apache/spark/mllib/regression/IsotonicRegression.scala
index f235089873ab855cf18a1e1e4354ae15a77b856a..abdd7981970fae54c5bab1360ecd300135ae66d2 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/regression/IsotonicRegression.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/regression/IsotonicRegression.scala
@@ -136,7 +136,7 @@ class IsotonicRegressionModel @Since("1.3.0") (
// higher than all values, in between two values or exact match.
if (insertIndex == 0) {
predictions.head
- } else if (insertIndex == boundaries.length){
+ } else if (insertIndex == boundaries.length) {
predictions.last
} else if (foundIndex < 0) {
linearInterpolation(
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/NumericParser.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/NumericParser.scala
index a841c5caf014248316d03f0bbf791a6b7d320648..2c613348c2d9225458eef71ce2756c89217d57b8 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/util/NumericParser.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/util/NumericParser.scala
@@ -98,7 +98,7 @@ private[mllib] object NumericParser {
}
} else if (token == ")") {
parsing = false
- } else if (token.trim.isEmpty){
+ } else if (token.trim.isEmpty) {
// ignore whitespaces between delim chars, e.g. ", ["
} else {
// expecting a number
diff --git a/mllib/src/test/scala/org/apache/spark/ml/classification/RandomForestClassifierSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/classification/RandomForestClassifierSuite.scala
index 6b810ab9eaa179122fa812b0826913ab3a2ee885..4c7c56782c35d4ddee2b17d8d8283cf1218d1509 100644
--- a/mllib/src/test/scala/org/apache/spark/ml/classification/RandomForestClassifierSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/ml/classification/RandomForestClassifierSuite.scala
@@ -105,7 +105,7 @@ class RandomForestClassifierSuite extends SparkFunSuite with MLlibTestSparkConte
compareAPIs(rdd, rf, categoricalFeatures, numClasses)
}
- test("subsampling rate in RandomForest"){
+ test("subsampling rate in RandomForest") {
val rdd = orderedLabeledPoints5_20
val categoricalFeatures = Map.empty[Int, Int]
val numClasses = 2
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 fb3bd3f412f817f69215a9471c3748d13c3928ee..67e680be73303947b45d4daf00cd8adcafffaced 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
@@ -182,7 +182,7 @@ class GaussianMixtureSuite extends SparkFunSuite with MLlibTestSparkContext {
Vectors.dense( 4.5605), Vectors.dense( 5.2043), Vectors.dense( 6.2734)
)
- val data2: Array[Vector] = Array.tabulate(25){ i: Int =>
+ val data2: Array[Vector] = Array.tabulate(25) { i: Int =>
Vectors.dense(Array.tabulate(50)(i + _.toDouble))
}
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/tree/RandomForestSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/tree/RandomForestSuite.scala
index e6df5d974bf36d4cd2d79b110a3154884cd61d13..c72fc9bb4f5d0f0f2dc24e856765bf51e041a9b6 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/tree/RandomForestSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/tree/RandomForestSuite.scala
@@ -197,7 +197,7 @@ class RandomForestSuite extends SparkFunSuite with MLlibTestSparkContext {
featureSubsetStrategy = "sqrt", seed = 12345)
}
- test("subsampling rate in RandomForest"){
+ test("subsampling rate in RandomForest") {
val arr = EnsembleTestHelper.generateOrderedLabeledPoints(5, 20)
val rdd = sc.parallelize(arr)
val strategy = new Strategy(algo = Classification, impurity = Gini, maxDepth = 2,
diff --git a/repl/scala-2.10/src/main/scala/org/apache/spark/repl/SparkILoop.scala b/repl/scala-2.10/src/main/scala/org/apache/spark/repl/SparkILoop.scala
index 22749c4609345a8c57a39199158515f6c76b6337..2a8fa45e3c615b60f776491144250e33d7e2557f 100644
--- a/repl/scala-2.10/src/main/scala/org/apache/spark/repl/SparkILoop.scala
+++ b/repl/scala-2.10/src/main/scala/org/apache/spark/repl/SparkILoop.scala
@@ -169,7 +169,7 @@ class SparkILoop(
}
- private def sparkCleanUp(){
+ private def sparkCleanUp() {
echo("Stopping spark context.")
intp.beQuietDuring {
command("sc.stop()")
diff --git a/scalastyle-config.xml b/scalastyle-config.xml
index 64619d21089993b0e64fad4442a863c3abcec790..37d2ecf48ec0234812dd868ce023129c3192a768 100644
--- a/scalastyle-config.xml
+++ b/scalastyle-config.xml
@@ -215,6 +215,14 @@ This file is divided into 3 sections:
</parameters>
</check>
+ <!-- SPARK-3854: Single Space between ')' and '{' -->
+ <check customId="SingleSpaceBetweenRParenAndLCurlyBrace" level="error" class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter name="regex">\)\{</parameter></parameters>
+ <customMessage><![CDATA[
+ Single Space between ')' and `{`.
+ ]]></customMessage>
+ </check>
+
<!-- ================================================================================ -->
<!-- rules we'd like to enforce, but haven't cleaned up the codebase yet -->
<!-- ================================================================================ -->
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala
index 87e43429e6587f5fc90bead9abf7eb796e0d1b57..efd75295b2ef15a0394c39276158b02b97f9616a 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala
@@ -159,7 +159,7 @@ case class CreateNamedStruct(children: Seq[Expression]) extends Expression {
TypeCheckResult.TypeCheckFailure(
s"Only foldable StringType expressions are allowed to appear at odd position , got :" +
s" ${invalidNames.mkString(",")}")
- } else if (!names.contains(null)){
+ } else if (!names.contains(null)) {
TypeCheckResult.TypeCheckSuccess
} else {
TypeCheckResult.TypeCheckFailure("Field name should not be null")
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala
index bc2df0fb4adf2486716c567ee7ac20fe9ac3f5ea..12fcc40376e10cd4a9ed36833ef8b8947f080097 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala
@@ -806,14 +806,14 @@ case class Round(child: Expression, scale: Expression)
case FloatType => // if child eval to NaN or Infinity, just return it.
if (_scale == 0) {
s"""
- if (Float.isNaN(${ce.value}) || Float.isInfinite(${ce.value})){
+ if (Float.isNaN(${ce.value}) || Float.isInfinite(${ce.value})) {
${ev.value} = ${ce.value};
} else {
${ev.value} = Math.round(${ce.value});
}"""
} else {
s"""
- if (Float.isNaN(${ce.value}) || Float.isInfinite(${ce.value})){
+ if (Float.isNaN(${ce.value}) || Float.isInfinite(${ce.value})) {
${ev.value} = ${ce.value};
} else {
${ev.value} = java.math.BigDecimal.valueOf(${ce.value}).
@@ -823,14 +823,14 @@ case class Round(child: Expression, scale: Expression)
case DoubleType => // if child eval to NaN or Infinity, just return it.
if (_scale == 0) {
s"""
- if (Double.isNaN(${ce.value}) || Double.isInfinite(${ce.value})){
+ if (Double.isNaN(${ce.value}) || Double.isInfinite(${ce.value})) {
${ev.value} = ${ce.value};
} else {
${ev.value} = Math.round(${ce.value});
}"""
} else {
s"""
- if (Double.isNaN(${ce.value}) || Double.isInfinite(${ce.value})){
+ if (Double.isNaN(${ce.value}) || Double.isInfinite(${ce.value})) {
${ev.value} = ${ce.value};
} else {
${ev.value} = java.math.BigDecimal.valueOf(${ce.value}).
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/RowTest.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/RowTest.scala
index 1e7118144f2ec064d7b9c525fda651b1453d5308..d9577dea1be36f1dd709dfb3a054a8f636057d84 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/RowTest.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/RowTest.scala
@@ -86,7 +86,7 @@ class RowTest extends FunSpec with Matchers {
}
}
- it("getAs() on type extending AnyVal does not throw exception when value is null"){
+ it("getAs() on type extending AnyVal does not throw exception when value is null") {
sampleRowWithoutCol3.getAs[String](sampleRowWithoutCol3.fieldIndex("col1")) shouldBe null
}
}
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/FilterPushdownSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/FilterPushdownSuite.scala
index 97a0cde381233886df8583b87dc791d6fbbdb62e..a636d6301245464889b1d442c0d40ded386bdd8d 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/FilterPushdownSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/FilterPushdownSuite.scala
@@ -535,7 +535,7 @@ class FilterPushdownSuite extends PlanTest {
// Filter("c" > 6)
assertResult(classOf[Filter])(optimized.getClass)
assertResult(1)(optimized.asInstanceOf[Filter].condition.references.size)
- assertResult("c"){
+ assertResult("c") {
optimized.asInstanceOf[Filter].condition.references.toSeq(0).name
}
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala b/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala
index 339e61e5723baa722e7757c27529f6acfa7ffcaf..24f61992d496b991854706a326274e25ded56e30 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala
@@ -1147,7 +1147,7 @@ class DataFrame private[sql](
* columns of the input row are implicitly joined with each value that is output by the function.
*
* {{{
- * df.explode("words", "word"){words: String => words.split(" ")}
+ * df.explode("words", "word") {words: String => words.split(" ")}
* }}}
* @group dfops
* @since 1.3.0
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 dd1fbcf3c881a2233d28345c337fa91c375c4533..daddf6e0c57e7545ba49e4d759afca195a734bf5 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
@@ -605,7 +605,7 @@ class Dataset[T] private[sql](
* duplicate items. As such, it is analogous to `UNION ALL` in SQL.
* @since 1.6.0
*/
- def union(other: Dataset[T]): Dataset[T] = withPlan[T](other){ (left, right) =>
+ def union(other: Dataset[T]): Dataset[T] = withPlan[T](other) { (left, right) =>
// This breaks caching, but it's usually ok because it addresses a very specific use case:
// using union to union many files or partitions.
CombineUnions(Union(left, right))
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/CompressionCodecs.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/CompressionCodecs.scala
index 032ba61d9dc641d309be18f037217d261836d66a..41cff07472d1e9f3b0f69efaa092117d30400c1e 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/CompressionCodecs.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/CompressionCodecs.scala
@@ -57,7 +57,7 @@ private[datasources] object CompressionCodecs {
* `codec` should be a full class path
*/
def setCodecConfiguration(conf: Configuration, codec: String): Unit = {
- if (codec != null){
+ if (codec != null) {
conf.set("mapreduce.output.fileoutputformat.compress", "true")
conf.set("mapreduce.output.fileoutputformat.compress.type", CompressionType.BLOCK.toString)
conf.set("mapreduce.output.fileoutputformat.compress.codec", codec)
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/ExecutionPage.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/ExecutionPage.scala
index 49915adf6cd29c8a264134c0fe58803f8781e6b9..9d3cd9bb14ecd8d971228dc5ddddb2b62c0f882f 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/ExecutionPage.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/ExecutionPage.scala
@@ -114,7 +114,7 @@ private[sql] class ExecutionPage(parent: SQLTab) extends WebUIPage("execution")
{metadata}
</div>
{planVisualizationResources}
- <script>$(function(){{ renderPlanViz(); }})</script>
+ <script>$(function() {{ renderPlanViz(); }})</script>
</div>
}
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 34e914cb1eb4d847d9a2b3edfeeecae668c837f7..b7834d76ccb6f35c4103de5c7e0ea98ae09023ae 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
@@ -145,7 +145,7 @@ class ParquetIOSuite extends QueryTest with ParquetTest with SharedSQLContext {
withTempPath { dir =>
val data = makeDecimalRDD(DecimalType(precision, scale))
data.write.parquet(dir.getCanonicalPath)
- readParquetFile(dir.getCanonicalPath){ df => {
+ readParquetFile(dir.getCanonicalPath) { df => {
checkAnswer(df, data.collect().toSeq)
}}
}
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/client/FiltersSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/client/FiltersSuite.scala
index 5e7b93d45710604c3504385289fe39bdd06bf19d..16b2d042a24886655608b2db0044ef6ee8c7c00a 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/client/FiltersSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/client/FiltersSuite.scala
@@ -65,7 +65,7 @@ class FiltersSuite extends SparkFunSuite with Logging {
"")
private def filterTest(name: String, filters: Seq[Expression], result: String) = {
- test(name){
+ test(name) {
val converted = shim.convertFilters(testTable, filters)
if (converted != result) {
fail(
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDFSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDFSuite.scala
index 703cfffee1587a106133fc9ad5db1f9498a7cfc8..d7c529ab0e10db892e196c2cccfb3015e9c2075c 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDFSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDFSuite.scala
@@ -361,7 +361,7 @@ class HiveUDFSuite extends QueryTest with TestHiveSingleton with SQLTestUtils {
}
}
- test("SPARK-11522 select input_file_name from non-parquet table"){
+ test("SPARK-11522 select input_file_name from non-parquet table") {
withTempDir { tempDir =>
diff --git a/streaming/src/main/scala/org/apache/spark/streaming/Checkpoint.scala b/streaming/src/main/scala/org/apache/spark/streaming/Checkpoint.scala
index 298cdc05acfa9292373b924566dd9f47a7c01d1e..11a4c7dfd011fa234c723e085ae08b0141908849 100644
--- a/streaming/src/main/scala/org/apache/spark/streaming/Checkpoint.scala
+++ b/streaming/src/main/scala/org/apache/spark/streaming/Checkpoint.scala
@@ -230,7 +230,7 @@ class CheckpointWriter(
// If the checkpoint file exists, back it up
// If the backup exists as well, just delete it, otherwise rename will fail
if (fs.exists(checkpointFile)) {
- if (fs.exists(backupFile)){
+ if (fs.exists(backupFile)) {
fs.delete(backupFile, true) // just in case it exists
}
if (!fs.rename(checkpointFile, backupFile)) {
diff --git a/streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingPage.scala b/streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingPage.scala
index eb1e5b0fdc98f4b43a8b9c7bf5352c283b3bbaa1..b1bcd0680380e0725edad61f54a742316888aa8f 100644
--- a/streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingPage.scala
+++ b/streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingPage.scala
@@ -558,7 +558,7 @@ private[ui] class JsCollector {
def toHtml: Seq[Node] = {
val js =
s"""
- |$$(document).ready(function(){
+ |$$(document).ready(function() {
| ${preparedStatements.mkString("\n")}
| ${statements.mkString("\n")}
|});""".stripMargin
diff --git a/streaming/src/test/scala/org/apache/spark/streaming/receiver/RateLimiterSuite.scala b/streaming/src/test/scala/org/apache/spark/streaming/receiver/RateLimiterSuite.scala
index c6330eb3673fb6e5894df7a5bd964ba10d74c2c2..ee3817c4b605da09b4edbff70708c072c2509071 100644
--- a/streaming/src/test/scala/org/apache/spark/streaming/receiver/RateLimiterSuite.scala
+++ b/streaming/src/test/scala/org/apache/spark/streaming/receiver/RateLimiterSuite.scala
@@ -25,21 +25,21 @@ class RateLimiterSuite extends SparkFunSuite {
test("rate limiter initializes even without a maxRate set") {
val conf = new SparkConf()
- val rateLimiter = new RateLimiter(conf){}
+ val rateLimiter = new RateLimiter(conf) {}
rateLimiter.updateRate(105)
assert(rateLimiter.getCurrentLimit == 105)
}
test("rate limiter updates when below maxRate") {
val conf = new SparkConf().set("spark.streaming.receiver.maxRate", "110")
- val rateLimiter = new RateLimiter(conf){}
+ val rateLimiter = new RateLimiter(conf) {}
rateLimiter.updateRate(105)
assert(rateLimiter.getCurrentLimit == 105)
}
test("rate limiter stays below maxRate despite large updates") {
val conf = new SparkConf().set("spark.streaming.receiver.maxRate", "100")
- val rateLimiter = new RateLimiter(conf){}
+ val rateLimiter = new RateLimiter(conf) {}
rateLimiter.updateRate(105)
assert(rateLimiter.getCurrentLimit === 100)
}