[SPARK-25565][BUILD] Add scalastyle rule to check add Locale.ROOT to .toLowerCase and .toUpperCase for internal calls

## What changes were proposed in this pull request?

This PR adds a rule to force `.toLowerCase(Locale.ROOT)` or `toUpperCase(Locale.ROOT)`.

It produces an error as below:

```
[error]       Are you sure that you want to use toUpperCase or toLowerCase without the root locale? In most cases, you
[error]       should use toUpperCase(Locale.ROOT) or toLowerCase(Locale.ROOT) instead.
[error]       If you must use toUpperCase or toLowerCase without the root locale, wrap the code block with
[error]       // scalastyle:off caselocale
[error]       .toUpperCase
[error]       .toLowerCase
[error]       // scalastyle:on caselocale
```

This PR excludes the cases above for SQL code path for external calls like table name, column name and etc.

For test suites, or when it's clear there's no locale problem like Turkish locale problem, it uses `Locale.ROOT`.

One minor problem is, `UTF8String` has both methods, `toLowerCase` and `toUpperCase`, and the new rule detects them as well. They are ignored.

## How was this patch tested?

Manually tested, and Jenkins tests.

Closes apache#22581 from HyukjinKwon/SPARK-25565.

Authored-by: hyukjinkwon <[email protected]>
Signed-off-by: hyukjinkwon <[email protected]>

Author: HyukjinKwon

common/unsafe/src/test/scala/org/apache/spark/unsafe/types/UTF8StringPropertyCheckSuite.scala

@@ -63,6 +63,7 @@ class UTF8StringPropertyCheckSuite extends FunSuite with GeneratorDrivenProperty
     }
   }
 
+  // scalastyle:off caselocale
   test("toUpperCase") {
     forAll { (s: String) =>
       assert(toUTF8(s).toUpperCase === toUTF8(s.toUpperCase))
@@ -74,6 +75,7 @@ class UTF8StringPropertyCheckSuite extends FunSuite with GeneratorDrivenProperty
       assert(toUTF8(s).toLowerCase === toUTF8(s.toLowerCase))
     }
   }
+  // scalastyle:on caselocale
 
   test("compare") {
     forAll { (s1: String, s2: String) =>

core/src/main/scala/org/apache/spark/metrics/sink/StatsdSink.scala

@@ -17,7 +17,7 @@
 
 package org.apache.spark.metrics.sink
 
-import java.util.Properties
+import java.util.{Locale, Properties}
 import java.util.concurrent.TimeUnit
 
 import com.codahale.metrics.MetricRegistry
@@ -52,7 +52,8 @@ private[spark] class StatsdSink(
 
   val pollPeriod = property.getProperty(STATSD_KEY_PERIOD, STATSD_DEFAULT_PERIOD).toInt
   val pollUnit =
-    TimeUnit.valueOf(property.getProperty(STATSD_KEY_UNIT, STATSD_DEFAULT_UNIT).toUpperCase)
+    TimeUnit.valueOf(
+      property.getProperty(STATSD_KEY_UNIT, STATSD_DEFAULT_UNIT).toUpperCase(Locale.ROOT))
 
   val prefix = property.getProperty(STATSD_KEY_PREFIX, STATSD_DEFAULT_PREFIX)
 

core/src/main/scala/org/apache/spark/rdd/OrderedRDDFunctions.scala

@@ -35,7 +35,8 @@ import org.apache.spark.internal.Logging
  *
  *   val rdd: RDD[(String, Int)] = ...
  *   implicit val caseInsensitiveOrdering = new Ordering[String] {
- *     override def compare(a: String, b: String) = a.toLowerCase.compare(b.toLowerCase)
+ *     override def compare(a: String, b: String) =
+ *       a.toLowerCase(Locale.ROOT).compare(b.toLowerCase(Locale.ROOT))
  *   }
  *
  *   // Sort by key, using the above case insensitive ordering.

core/src/main/scala/org/apache/spark/util/Utils.scala

@@ -2736,7 +2736,7 @@ private[spark] object Utils extends Logging {
     }
 
     val masterScheme = new URI(masterWithoutK8sPrefix).getScheme
-    val resolvedURL = masterScheme.toLowerCase match {
+    val resolvedURL = masterScheme.toLowerCase(Locale.ROOT) match {
       case "https" =>
         masterWithoutK8sPrefix
       case "http" =>

core/src/test/scala/org/apache/spark/deploy/history/FsHistoryProviderSuite.scala

@@ -19,7 +19,7 @@ package org.apache.spark.deploy.history
 
 import java.io._
 import java.nio.charset.StandardCharsets
-import java.util.Date
+import java.util.{Date, Locale}
 import java.util.concurrent.TimeUnit
 import java.util.zip.{ZipInputStream, ZipOutputStream}
 
@@ -834,7 +834,7 @@ class FsHistoryProviderSuite extends SparkFunSuite with BeforeAndAfter with Matc
     doThrow(new AccessControlException("Cannot read accessDenied file")).when(mockedFs).open(
       argThat(new ArgumentMatcher[Path]() {
         override def matches(path: Any): Boolean = {
-          path.asInstanceOf[Path].getName.toLowerCase == "accessdenied"
+          path.asInstanceOf[Path].getName.toLowerCase(Locale.ROOT) == "accessdenied"
         }
       }))
     val mockedProvider = spy(provider)

mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala

@@ -118,7 +118,9 @@ class StopWordsRemover @Since("1.5.0") (@Since("1.5.0") override val uid: String
       }
     } else {
       val lc = new Locale($(locale))
+      // scalastyle:off caselocale
       val toLower = (s: String) => if (s != null) s.toLowerCase(lc) else s
+      // scalastyle:on caselocale
       val lowerStopWords = $(stopWords).map(toLower(_)).toSet
       udf { terms: Seq[String] =>
         terms.filter(s => !lowerStopWords.contains(toLower(s)))

mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala

@@ -36,7 +36,9 @@ class Tokenizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
   def this() = this(Identifiable.randomUID("tok"))
 
   override protected def createTransformFunc: String => Seq[String] = {
+    // scalastyle:off caselocale
     _.toLowerCase.split("\\s")
+    // scalastyle:on caselocale
   }
 
   override protected def validateInputType(inputType: DataType): Unit = {
@@ -140,7 +142,9 @@ class RegexTokenizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
 
   override protected def createTransformFunc: String => Seq[String] = { originStr =>
     val re = $(pattern).r
+    // scalastyle:off caselocale
     val str = if ($(toLowercase)) originStr.toLowerCase() else originStr
+    // scalastyle:on caselocale
     val tokens = if ($(gaps)) re.split(str).toSeq else re.findAllIn(str).toSeq
     val minLength = $(minTokenLength)
     tokens.filter(_.length >= minLength)

resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/submit/KubernetesClientApplication.scala

@@ -17,7 +17,7 @@
 package org.apache.spark.deploy.k8s.submit
 
 import java.io.StringWriter
-import java.util.{Collections, UUID}
+import java.util.{Collections, Locale, UUID}
 import java.util.Properties
 
 import io.fabric8.kubernetes.api.model._
@@ -260,7 +260,7 @@ private[spark] object KubernetesClientApplication {
     val launchTime = System.currentTimeMillis()
     s"$appName-$launchTime"
       .trim
-      .toLowerCase
+      .toLowerCase(Locale.ROOT)
       .replaceAll("\\s+", "-")
       .replaceAll("\\.", "-")
       .replaceAll("[^a-z0-9\\-]", "")

resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/ExecutorPodsSnapshot.scala

@@ -16,6 +16,8 @@
  */
 package org.apache.spark.scheduler.cluster.k8s
 
+import java.util.Locale
+
 import io.fabric8.kubernetes.api.model.Pod
 
 import org.apache.spark.deploy.k8s.Constants._
@@ -52,7 +54,7 @@ object ExecutorPodsSnapshot extends Logging {
     if (isDeleted(pod)) {
       PodDeleted(pod)
     } else {
-      val phase = pod.getStatus.getPhase.toLowerCase
+      val phase = pod.getStatus.getPhase.toLowerCase(Locale.ROOT)
       phase match {
         case "pending" =>
           PodPending(pod)

resource-managers/mesos/src/main/scala/org/apache/spark/deploy/mesos/MesosClusterDispatcher.scala

@@ -17,6 +17,7 @@
 
 package org.apache.spark.deploy.mesos
 
+import java.util.Locale
 import java.util.concurrent.CountDownLatch
 
 import org.apache.spark.{SecurityManager, SparkConf, SparkException}
@@ -60,7 +61,7 @@ private[mesos] class MesosClusterDispatcher(
   }
 
   private val publicAddress = Option(conf.getenv("SPARK_PUBLIC_DNS")).getOrElse(args.host)
-  private val recoveryMode = conf.get(RECOVERY_MODE).toUpperCase()
+  private val recoveryMode = conf.get(RECOVERY_MODE).toUpperCase(Locale.ROOT)
   logInfo("Recovery mode in Mesos dispatcher set to: " + recoveryMode)
 
   private val engineFactory = recoveryMode match {