[SPARK-14355][BUILD] Fix typos in Exception/Testcase/Comments and static analysis results

## What changes were proposed in this pull request?

This PR contains the following 5 types of maintenance fix over 59 files (+94 lines, -93 lines).
- Fix typos(exception/log strings, testcase name, comments) in 44 lines.
- Fix lint-java errors (MaxLineLength) in 6 lines. (New codes after SPARK-14011)
- Use diamond operators in 40 lines. (New codes after SPARK-13702)
- Fix redundant semicolon in 5 lines.
- Rename class `InferSchemaSuite` to `CSVInferSchemaSuite` in CSVInferSchemaSuite.scala.

## How was this patch tested?

Manual and pass the Jenkins tests.

Author: Dongjoon Hyun <dongjoon@apache.org>

Closes #12139 from dongjoon-hyun/SPARK-14355.

12 files changed, 17 insertions, 17 deletions

diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
index 23c4af17f9..4525bf71f6 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
@@ -205,7 +205,7 @@ final class DecisionTreeClassificationModel private[ml] (
   @Since("2.0.0")
   lazy val featureImportances: Vector = TreeEnsembleModel.featureImportances(this, numFeatures)
 
-  /** Convert to spark.mllib DecisionTreeModel (losing some infomation) */
+  /** Convert to spark.mllib DecisionTreeModel (losing some information) */
   override private[spark] def toOld: OldDecisionTreeModel = {
     new OldDecisionTreeModel(rootNode.toOld(1), OldAlgo.Classification)
   }
diff --git a/mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala b/mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala
index 3ce129b12c..1d03a5b4f4 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala
@@ -62,7 +62,7 @@ private[shared] object SharedParamsCodeGen {
         "every 10 iterations", isValid = "(interval: Int) => interval == -1 || interval >= 1"),
       ParamDesc[Boolean]("fitIntercept", "whether to fit an intercept term", Some("true")),
       ParamDesc[String]("handleInvalid", "how to handle invalid entries. Options are skip (which " +
-        "will filter out rows with bad values), or error (which will throw an errror). More " +
+        "will filter out rows with bad values), or error (which will throw an error). More " +
         "options may be added later",
         isValid = "ParamValidators.inArray(Array(\"skip\", \"error\"))"),
       ParamDesc[Boolean]("standardization", "whether to standardize the training features" +
diff --git a/mllib/src/main/scala/org/apache/spark/ml/param/shared/sharedParams.scala b/mllib/src/main/scala/org/apache/spark/ml/param/shared/sharedParams.scala
index 96263c5baf..64d6af2766 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/param/shared/sharedParams.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/param/shared/sharedParams.scala
@@ -270,10 +270,10 @@ private[ml] trait HasFitIntercept extends Params {
 private[ml] trait HasHandleInvalid extends Params {
 
   /**
-   * Param for how to handle invalid entries. Options are skip (which will filter out rows with bad values), or error (which will throw an errror). More options may be added later.
+   * Param for how to handle invalid entries. Options are skip (which will filter out rows with bad values), or error (which will throw an error). More options may be added later.
    * @group param
    */
-  final val handleInvalid: Param[String] = new Param[String](this, "handleInvalid", "how to handle invalid entries. Options are skip (which will filter out rows with bad values), or error (which will throw an errror). More options may be added later", ParamValidators.inArray(Array("skip", "error")))
+  final val handleInvalid: Param[String] = new Param[String](this, "handleInvalid", "how to handle invalid entries. Options are skip (which will filter out rows with bad values), or error (which will throw an error). More options may be added later", ParamValidators.inArray(Array("skip", "error")))
 
   /** @group getParam */
   final def getHandleInvalid: String = $(handleInvalid)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala
index 0a3d00e470..1289a317ee 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala
@@ -205,7 +205,7 @@ final class DecisionTreeRegressionModel private[ml] (
   @Since("2.0.0")
   lazy val featureImportances: Vector = TreeEnsembleModel.featureImportances(this, numFeatures)
 
-  /** Convert to spark.mllib DecisionTreeModel (losing some infomation) */
+  /** Convert to spark.mllib DecisionTreeModel (losing some information) */
   override private[spark] def toOld: OldDecisionTreeModel = {
     new OldDecisionTreeModel(rootNode.toOld(1), OldAlgo.Regression)
   }
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 1fad9d6d8c..8ea767b2b3 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
@@ -71,7 +71,7 @@ private[spark] trait DecisionTreeModel {
    */
   private[ml] def maxSplitFeatureIndex(): Int = rootNode.maxSplitFeatureIndex()
 
-  /** Convert to spark.mllib DecisionTreeModel (losing some infomation) */
+  /** Convert to spark.mllib DecisionTreeModel (losing some information) */
   private[spark] def toOld: OldDecisionTreeModel
 }
 
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala b/mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala
index c0404be019..f10570e662 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala
@@ -418,7 +418,7 @@ class LogisticRegressionWithLBFGS
 
   private def run(input: RDD[LabeledPoint], initialWeights: Vector, userSuppliedWeights: Boolean):
       LogisticRegressionModel = {
-    // ml's Logisitic regression only supports binary classifcation currently.
+    // ml's Logistic regression only supports binary classification currently.
     if (numOfLinearPredictor == 1) {
       def runWithMlLogisitcRegression(elasticNetParam: Double) = {
         // Prepare the ml LogisticRegression based on our settings
diff --git a/mllib/src/test/java/org/apache/spark/ml/param/JavaTestParams.java b/mllib/src/test/java/org/apache/spark/ml/param/JavaTestParams.java
index 65841182df..06f7fbb86e 100644
--- a/mllib/src/test/java/org/apache/spark/ml/param/JavaTestParams.java
+++ b/mllib/src/test/java/org/apache/spark/ml/param/JavaTestParams.java
@@ -89,7 +89,7 @@ public class JavaTestParams extends JavaParams {
     myDoubleParam_ = new DoubleParam(this, "myDoubleParam", "this is a double param",
       ParamValidators.inRange(0.0, 1.0));
     List<String> validStrings = Arrays.asList("a", "b");
-    myStringParam_ = new Param<String>(this, "myStringParam", "this is a string param",
+    myStringParam_ = new Param<>(this, "myStringParam", "this is a string param",
       ParamValidators.inArray(validStrings));
     myDoubleArrayParam_ =
       new DoubleArrayParam(this, "myDoubleArrayParam", "this is a double param");
diff --git a/mllib/src/test/java/org/apache/spark/mllib/classification/JavaStreamingLogisticRegressionSuite.java b/mllib/src/test/java/org/apache/spark/mllib/classification/JavaStreamingLogisticRegressionSuite.java
index c9e5ee22f3..62c6d9b7e3 100644
--- a/mllib/src/test/java/org/apache/spark/mllib/classification/JavaStreamingLogisticRegressionSuite.java
+++ b/mllib/src/test/java/org/apache/spark/mllib/classification/JavaStreamingLogisticRegressionSuite.java
@@ -66,8 +66,8 @@ public class JavaStreamingLogisticRegressionSuite implements Serializable {
     JavaDStream<LabeledPoint> training =
       attachTestInputStream(ssc, Arrays.asList(trainingBatch, trainingBatch), 2);
     List<Tuple2<Integer, Vector>> testBatch = Arrays.asList(
-      new Tuple2<Integer, Vector>(10, Vectors.dense(1.0)),
-      new Tuple2<Integer, Vector>(11, Vectors.dense(0.0)));
+      new Tuple2<>(10, Vectors.dense(1.0)),
+      new Tuple2<>(11, Vectors.dense(0.0)));
     JavaPairDStream<Integer, Vector> test = JavaPairDStream.fromJavaDStream(
       attachTestInputStream(ssc, Arrays.asList(testBatch, testBatch), 2));
     StreamingLogisticRegressionWithSGD slr = new StreamingLogisticRegressionWithSGD()
diff --git a/mllib/src/test/java/org/apache/spark/mllib/clustering/JavaStreamingKMeansSuite.java b/mllib/src/test/java/org/apache/spark/mllib/clustering/JavaStreamingKMeansSuite.java
index d644766d1e..62edbd3a29 100644
--- a/mllib/src/test/java/org/apache/spark/mllib/clustering/JavaStreamingKMeansSuite.java
+++ b/mllib/src/test/java/org/apache/spark/mllib/clustering/JavaStreamingKMeansSuite.java
@@ -66,8 +66,8 @@ public class JavaStreamingKMeansSuite implements Serializable {
     JavaDStream<Vector> training =
       attachTestInputStream(ssc, Arrays.asList(trainingBatch, trainingBatch), 2);
     List<Tuple2<Integer, Vector>> testBatch = Arrays.asList(
-      new Tuple2<Integer, Vector>(10, Vectors.dense(1.0)),
-      new Tuple2<Integer, Vector>(11, Vectors.dense(0.0)));
+      new Tuple2<>(10, Vectors.dense(1.0)),
+      new Tuple2<>(11, Vectors.dense(0.0)));
     JavaPairDStream<Integer, Vector> test = JavaPairDStream.fromJavaDStream(
       attachTestInputStream(ssc, Arrays.asList(testBatch, testBatch), 2));
     StreamingKMeans skmeans = new StreamingKMeans()
diff --git a/mllib/src/test/java/org/apache/spark/mllib/linalg/JavaVectorsSuite.java b/mllib/src/test/java/org/apache/spark/mllib/linalg/JavaVectorsSuite.java
index 77c8c6274f..4ba8e543a9 100644
--- a/mllib/src/test/java/org/apache/spark/mllib/linalg/JavaVectorsSuite.java
+++ b/mllib/src/test/java/org/apache/spark/mllib/linalg/JavaVectorsSuite.java
@@ -37,8 +37,8 @@ public class JavaVectorsSuite implements Serializable {
   public void sparseArrayConstruction() {
     @SuppressWarnings("unchecked")
     Vector v = Vectors.sparse(3, Arrays.asList(
-        new Tuple2<Integer, Double>(0, 2.0),
-        new Tuple2<Integer, Double>(2, 3.0)));
+        new Tuple2<>(0, 2.0),
+        new Tuple2<>(2, 3.0)));
     assertArrayEquals(new double[]{2.0, 0.0, 3.0}, v.toArray(), 0.0);
   }
 }
diff --git a/mllib/src/test/java/org/apache/spark/mllib/regression/JavaStreamingLinearRegressionSuite.java b/mllib/src/test/java/org/apache/spark/mllib/regression/JavaStreamingLinearRegressionSuite.java
index dbf6488d41..ea0ccd7448 100644
--- a/mllib/src/test/java/org/apache/spark/mllib/regression/JavaStreamingLinearRegressionSuite.java
+++ b/mllib/src/test/java/org/apache/spark/mllib/regression/JavaStreamingLinearRegressionSuite.java
@@ -65,8 +65,8 @@ public class JavaStreamingLinearRegressionSuite implements Serializable {
     JavaDStream<LabeledPoint> training =
       attachTestInputStream(ssc, Arrays.asList(trainingBatch, trainingBatch), 2);
     List<Tuple2<Integer, Vector>> testBatch = Arrays.asList(
-      new Tuple2<Integer, Vector>(10, Vectors.dense(1.0)),
-      new Tuple2<Integer, Vector>(11, Vectors.dense(0.0)));
+      new Tuple2<>(10, Vectors.dense(1.0)),
+      new Tuple2<>(11, Vectors.dense(0.0)));
     JavaPairDStream<Integer, Vector> test = JavaPairDStream.fromJavaDStream(
       attachTestInputStream(ssc, Arrays.asList(testBatch, testBatch), 2));
     StreamingLinearRegressionWithSGD slr = new StreamingLinearRegressionWithSGD()
diff --git a/mllib/src/test/scala/org/apache/spark/ml/regression/LinearRegressionSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/regression/LinearRegressionSuite.scala
index cccb7f8d1b..eb19d13093 100644
--- a/mllib/src/test/scala/org/apache/spark/ml/regression/LinearRegressionSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/ml/regression/LinearRegressionSuite.scala
@@ -759,7 +759,7 @@ class LinearRegressionSuite
             .sliding(2)
             .forall(x => x(0) >= x(1)))
       } else {
-        // To clalify that the normal solver is used here.
+        // To clarify that the normal solver is used here.
         assert(model.summary.objectiveHistory.length == 1)
         assert(model.summary.objectiveHistory(0) == 0.0)
         val devianceResidualsR = Array(-0.47082, 0.34635)