[SPARK-27323][CORE][SQL][STREAMING] Use Single-Abstract-Method support in Scala 2.12 to simplify code

## What changes were proposed in this pull request?

Use Single Abstract Method syntax where possible (and minor related cleanup). Comments below. No logic should change here.

## How was this patch tested?

Existing tests.

Closes apache#24241 from srowen/SPARK-27323.

Authored-by: Sean Owen <[email protected]>
Signed-off-by: Dongjoon Hyun <[email protected]>

Author: srowen

core/src/main/scala/org/apache/spark/BarrierCoordinator.scala

@@ -19,7 +19,7 @@ package org.apache.spark
 
 import java.util.{Timer, TimerTask}
 import java.util.concurrent.ConcurrentHashMap
-import java.util.function.{Consumer, Function}
+import java.util.function.Consumer
 
 import scala.collection.mutable.ArrayBuffer
 
@@ -202,10 +202,8 @@ private[spark] class BarrierCoordinator(
     case request @ RequestToSync(numTasks, stageId, stageAttemptId, _, _) =>
       // Get or init the ContextBarrierState correspond to the stage attempt.
       val barrierId = ContextBarrierId(stageId, stageAttemptId)
-      states.computeIfAbsent(barrierId, new Function[ContextBarrierId, ContextBarrierState] {
-        override def apply(key: ContextBarrierId): ContextBarrierState =
-          new ContextBarrierState(key, numTasks)
-      })
+      states.computeIfAbsent(barrierId,
+        (key: ContextBarrierId) => new ContextBarrierState(key, numTasks))
       val barrierState = states.get(barrierId)
 
       barrierState.handleRequest(context, request)

core/src/main/scala/org/apache/spark/ContextCleaner.scala

@@ -123,9 +123,8 @@ private[spark] class ContextCleaner(sc: SparkContext) extends Logging {
     cleaningThread.setDaemon(true)
     cleaningThread.setName("Spark Context Cleaner")
     cleaningThread.start()
-    periodicGCService.scheduleAtFixedRate(new Runnable {
-      override def run(): Unit = System.gc()
-    }, periodicGCInterval, periodicGCInterval, TimeUnit.SECONDS)
+    periodicGCService.scheduleAtFixedRate(() => System.gc(),
+      periodicGCInterval, periodicGCInterval, TimeUnit.SECONDS)
   }
 
   /**

core/src/main/scala/org/apache/spark/HeartbeatReceiver.scala

@@ -98,11 +98,9 @@ private[spark] class HeartbeatReceiver(sc: SparkContext, clock: Clock)
   private val killExecutorThread = ThreadUtils.newDaemonSingleThreadExecutor("kill-executor-thread")
 
   override def onStart(): Unit = {
-    timeoutCheckingTask = eventLoopThread.scheduleAtFixedRate(new Runnable {
-      override def run(): Unit = Utils.tryLogNonFatalError {
-        Option(self).foreach(_.ask[Boolean](ExpireDeadHosts))
-      }
-    }, 0, checkTimeoutIntervalMs, TimeUnit.MILLISECONDS)
+    timeoutCheckingTask = eventLoopThread.scheduleAtFixedRate(
+      () => Utils.tryLogNonFatalError { Option(self).foreach(_.ask[Boolean](ExpireDeadHosts)) },
+      0, checkTimeoutIntervalMs, TimeUnit.MILLISECONDS)
   }
 
   override def receiveAndReply(context: RpcCallContext): PartialFunction[Any, Unit] = {

core/src/main/scala/org/apache/spark/SparkConf.scala

@@ -62,9 +62,7 @@ class SparkConf(loadDefaults: Boolean) extends Cloneable with Logging with Seria
 
   @transient private lazy val reader: ConfigReader = {
     val _reader = new ConfigReader(new SparkConfigProvider(settings))
-    _reader.bindEnv(new ConfigProvider {
-      override def get(key: String): Option[String] = Option(getenv(key))
-    })
+    _reader.bindEnv((key: String) => Option(getenv(key)))
     _reader
   }
 
@@ -392,7 +390,7 @@ class SparkConf(loadDefaults: Boolean) extends Cloneable with Logging with Seria
 
   /** Get an optional value, applying variable substitution. */
   private[spark] def getWithSubstitution(key: String): Option[String] = {
-    getOption(key).map(reader.substitute(_))
+    getOption(key).map(reader.substitute)
   }
 
   /** Get all parameters as a list of pairs */

core/src/main/scala/org/apache/spark/deploy/PythonRunner.scala

@@ -60,11 +60,7 @@ object PythonRunner {
       .javaAddress(localhost)
       .callbackClient(py4j.GatewayServer.DEFAULT_PYTHON_PORT, localhost, secret)
       .build()
-    val thread = new Thread(new Runnable() {
-      override def run(): Unit = Utils.logUncaughtExceptions {
-        gatewayServer.start()
-      }
-    })
+    val thread = new Thread(() => Utils.logUncaughtExceptions { gatewayServer.start() })
     thread.setName("py4j-gateway-init")
     thread.setDaemon(true)
     thread.start()

core/src/main/scala/org/apache/spark/deploy/SparkHadoopUtil.scala

@@ -20,7 +20,7 @@ package org.apache.spark.deploy
 import java.io.{ByteArrayInputStream, ByteArrayOutputStream, DataInputStream, DataOutputStream, File, IOException}
 import java.security.PrivilegedExceptionAction
 import java.text.DateFormat
-import java.util.{Arrays, Comparator, Date, Locale}
+import java.util.{Arrays, Date, Locale}
 
 import scala.collection.JavaConverters._
 import scala.collection.immutable.Map
@@ -270,11 +270,8 @@ private[spark] class SparkHadoopUtil extends Logging {
             name.startsWith(prefix) && !name.endsWith(exclusionSuffix)
           }
         })
-      Arrays.sort(fileStatuses, new Comparator[FileStatus] {
-        override def compare(o1: FileStatus, o2: FileStatus): Int = {
-          Longs.compare(o1.getModificationTime, o2.getModificationTime)
-        }
-      })
+      Arrays.sort(fileStatuses, (o1: FileStatus, o2: FileStatus) =>
+        Longs.compare(o1.getModificationTime, o2.getModificationTime))
       fileStatuses
     } catch {
       case NonFatal(e) =>
@@ -465,7 +462,7 @@ private[spark] object SparkHadoopUtil {
   // scalastyle:on line.size.limit
   def createNonECFile(fs: FileSystem, path: Path): FSDataOutputStream = {
     try {
-      // Use reflection as this uses apis only avialable in hadoop 3
+      // Use reflection as this uses APIs only available in Hadoop 3
       val builderMethod = fs.getClass().getMethod("createFile", classOf[Path])
       // the builder api does not resolve relative paths, nor does it create parent dirs, while
       // the old api does.

core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala

@@ -186,13 +186,8 @@ private[history] class FsHistoryProvider(conf: SparkConf, clock: Clock)
    * Return a runnable that performs the given operation on the event logs.
    * This operation is expected to be executed periodically.
    */
-  private def getRunner(operateFun: () => Unit): Runnable = {
-    new Runnable() {
-      override def run(): Unit = Utils.tryOrExit {
-        operateFun()
-      }
-    }
-  }
+  private def getRunner(operateFun: () => Unit): Runnable =
+    () => Utils.tryOrExit { operateFun() }
 
   /**
    * Fixed size thread pool to fetch and parse log files.
@@ -221,29 +216,25 @@ private[history] class FsHistoryProvider(conf: SparkConf, clock: Clock)
     // Cannot probe anything while the FS is in safe mode, so spawn a new thread that will wait
     // for the FS to leave safe mode before enabling polling. This allows the main history server
     // UI to be shown (so that the user can see the HDFS status).
-    val initThread = new Thread(new Runnable() {
-      override def run(): Unit = {
-        try {
-          while (isFsInSafeMode()) {
-            logInfo("HDFS is still in safe mode. Waiting...")
-            val deadline = clock.getTimeMillis() +
-              TimeUnit.SECONDS.toMillis(SAFEMODE_CHECK_INTERVAL_S)
-            clock.waitTillTime(deadline)
-          }
-          startPolling()
-        } catch {
-          case _: InterruptedException =>
+    val initThread = new Thread(() => {
+      try {
+        while (isFsInSafeMode()) {
+          logInfo("HDFS is still in safe mode. Waiting...")
+          val deadline = clock.getTimeMillis() +
+            TimeUnit.SECONDS.toMillis(SAFEMODE_CHECK_INTERVAL_S)
+          clock.waitTillTime(deadline)
         }
+        startPolling()
+      } catch {
+        case _: InterruptedException =>
       }
     })
     initThread.setDaemon(true)
     initThread.setName(s"${getClass().getSimpleName()}-init")
     initThread.setUncaughtExceptionHandler(errorHandler.getOrElse(
-      new Thread.UncaughtExceptionHandler() {
-        override def uncaughtException(t: Thread, e: Throwable): Unit = {
-          logError("Error initializing FsHistoryProvider.", e)
-          System.exit(1)
-        }
+      (_: Thread, e: Throwable) => {
+        logError("Error initializing FsHistoryProvider.", e)
+        System.exit(1)
       }))
     initThread.start()
     initThread
@@ -517,9 +508,8 @@ private[history] class FsHistoryProvider(conf: SparkConf, clock: Clock)
 
       val tasks = updated.flatMap { entry =>
         try {
-          val task: Future[Unit] = replayExecutor.submit(new Runnable {
-            override def run(): Unit = mergeApplicationListing(entry, newLastScanTime, true)
-          }, Unit)
+          val task: Future[Unit] = replayExecutor.submit(
+            () => mergeApplicationListing(entry, newLastScanTime, true))
           Some(task -> entry.getPath)
         } catch {
           // let the iteration over the updated entries break, since an exception on

core/src/main/scala/org/apache/spark/deploy/master/Master.scala

@@ -150,11 +150,9 @@ private[deploy] class Master(
       logInfo(s"Spark Master is acting as a reverse proxy. Master, Workers and " +
        s"Applications UIs are available at $masterWebUiUrl")
     }
-    checkForWorkerTimeOutTask = forwardMessageThread.scheduleAtFixedRate(new Runnable {
-      override def run(): Unit = Utils.tryLogNonFatalError {
-        self.send(CheckForWorkerTimeOut)
-      }
-    }, 0, workerTimeoutMs, TimeUnit.MILLISECONDS)
+    checkForWorkerTimeOutTask = forwardMessageThread.scheduleAtFixedRate(
+      () => Utils.tryLogNonFatalError { self.send(CheckForWorkerTimeOut) },
+      0, workerTimeoutMs, TimeUnit.MILLISECONDS)
 
     if (restServerEnabled) {
       val port = conf.get(MASTER_REST_SERVER_PORT)

core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala

@@ -325,11 +325,9 @@ private[deploy] class Worker(
         if (connectionAttemptCount == INITIAL_REGISTRATION_RETRIES) {
           registrationRetryTimer.foreach(_.cancel(true))
           registrationRetryTimer = Some(
-            forwardMessageScheduler.scheduleAtFixedRate(new Runnable {
-              override def run(): Unit = Utils.tryLogNonFatalError {
-                self.send(ReregisterWithMaster)
-              }
-            }, PROLONGED_REGISTRATION_RETRY_INTERVAL_SECONDS,
+            forwardMessageScheduler.scheduleAtFixedRate(
+              () => Utils.tryLogNonFatalError { self.send(ReregisterWithMaster) },
+              PROLONGED_REGISTRATION_RETRY_INTERVAL_SECONDS,
               PROLONGED_REGISTRATION_RETRY_INTERVAL_SECONDS,
               TimeUnit.SECONDS))
         }
@@ -341,7 +339,7 @@ private[deploy] class Worker(
   }
 
   /**
-   * Cancel last registeration retry, or do nothing if no retry
+   * Cancel last registration retry, or do nothing if no retry
    */
   private def cancelLastRegistrationRetry(): Unit = {
     if (registerMasterFutures != null) {
@@ -361,11 +359,7 @@ private[deploy] class Worker(
         registerMasterFutures = tryRegisterAllMasters()
         connectionAttemptCount = 0
         registrationRetryTimer = Some(forwardMessageScheduler.scheduleAtFixedRate(
-          new Runnable {
-            override def run(): Unit = Utils.tryLogNonFatalError {
-              Option(self).foreach(_.send(ReregisterWithMaster))
-            }
-          },
+          () => Utils.tryLogNonFatalError { Option(self).foreach(_.send(ReregisterWithMaster)) },
           INITIAL_REGISTRATION_RETRY_INTERVAL_SECONDS,
           INITIAL_REGISTRATION_RETRY_INTERVAL_SECONDS,
           TimeUnit.SECONDS))
@@ -407,19 +401,15 @@ private[deploy] class Worker(
         }
         registered = true
         changeMaster(masterRef, masterWebUiUrl, masterAddress)
-        forwardMessageScheduler.scheduleAtFixedRate(new Runnable {
-          override def run(): Unit = Utils.tryLogNonFatalError {
-            self.send(SendHeartbeat)
-          }
-        }, 0, HEARTBEAT_MILLIS, TimeUnit.MILLISECONDS)
+        forwardMessageScheduler.scheduleAtFixedRate(
+          () => Utils.tryLogNonFatalError { self.send(SendHeartbeat) },
+          0, HEARTBEAT_MILLIS, TimeUnit.MILLISECONDS)
         if (CLEANUP_ENABLED) {
           logInfo(
             s"Worker cleanup enabled; old application directories will be deleted in: $workDir")
-          forwardMessageScheduler.scheduleAtFixedRate(new Runnable {
-            override def run(): Unit = Utils.tryLogNonFatalError {
-              self.send(WorkDirCleanup)
-            }
-          }, CLEANUP_INTERVAL_MILLIS, CLEANUP_INTERVAL_MILLIS, TimeUnit.MILLISECONDS)
+          forwardMessageScheduler.scheduleAtFixedRate(
+            () => Utils.tryLogNonFatalError { self.send(WorkDirCleanup) },
+            CLEANUP_INTERVAL_MILLIS, CLEANUP_INTERVAL_MILLIS, TimeUnit.MILLISECONDS)
         }
 
         val execs = executors.values.map { e =>
@@ -568,7 +558,7 @@ private[deploy] class Worker(
         }
       }
 
-    case executorStateChanged @ ExecutorStateChanged(appId, execId, state, message, exitStatus) =>
+    case executorStateChanged: ExecutorStateChanged =>
       handleExecutorStateChanged(executorStateChanged)
 
     case KillExecutor(masterUrl, appId, execId) =>
@@ -632,7 +622,7 @@ private[deploy] class Worker(
 
   override def onDisconnected(remoteAddress: RpcAddress): Unit = {
     if (master.exists(_.address == remoteAddress) ||
-      masterAddressToConnect.exists(_ == remoteAddress)) {
+        masterAddressToConnect.contains(remoteAddress)) {
       logInfo(s"$remoteAddress Disassociated !")
       masterDisconnected()
     }
@@ -815,7 +805,7 @@ private[deploy] object Worker extends Logging {
     val systemName = SYSTEM_NAME + workerNumber.map(_.toString).getOrElse("")
     val securityMgr = new SecurityManager(conf)
     val rpcEnv = RpcEnv.create(systemName, host, port, conf, securityMgr)
-    val masterAddresses = masterUrls.map(RpcAddress.fromSparkURL(_))
+    val masterAddresses = masterUrls.map(RpcAddress.fromSparkURL)
     rpcEnv.setupEndpoint(ENDPOINT_NAME, new Worker(rpcEnv, webUiPort, cores, memory,
       masterAddresses, ENDPOINT_NAME, workDir, conf, securityMgr))
     rpcEnv

core/src/main/scala/org/apache/spark/executor/Executor.scala

@@ -89,17 +89,14 @@ private[spark] class Executor(
   }
 
   // Start worker thread pool
+  // Use UninterruptibleThread to run tasks so that we can allow running codes without being
+  // interrupted by `Thread.interrupt()`. Some issues, such as KAFKA-1894, HADOOP-10622,
+  // will hang forever if some methods are interrupted.
   private val threadPool = {
     val threadFactory = new ThreadFactoryBuilder()
       .setDaemon(true)
       .setNameFormat("Executor task launch worker-%d")
-      .setThreadFactory(new ThreadFactory {
-        override def newThread(r: Runnable): Thread =
-          // Use UninterruptibleThread to run tasks so that we can allow running codes without being
-          // interrupted by `Thread.interrupt()`. Some issues, such as KAFKA-1894, HADOOP-10622,
-          // will hang forever if some methods are interrupted.
-          new UninterruptibleThread(r, "unused") // thread name will be set by ThreadFactoryBuilder
-      })
+      .setThreadFactory((r: Runnable) => new UninterruptibleThread(r, "unused"))
       .build()
     Executors.newCachedThreadPool(threadFactory).asInstanceOf[ThreadPoolExecutor]
   }