[MINOR] Fix Typos 'an -> a'

## What changes were proposed in this pull request?

`an -> a`

Use cmds like `find . -name '*.R' | xargs -i sh -c "grep -in ' an [^aeiou]' {} && echo {}"` to generate candidates, and review them one by one.

## How was this patch tested?
manual tests

Author: Zheng RuiFeng <ruifengz@foxmail.com>

Closes #13515 from zhengruifeng/an_a.

11 files changed, 16 insertions, 16 deletions

diff --git a/core/src/main/scala/org/apache/spark/Accumulable.scala b/core/src/main/scala/org/apache/spark/Accumulable.scala
index 812145aaee..5532931e2a 100644
--- a/core/src/main/scala/org/apache/spark/Accumulable.scala
+++ b/core/src/main/scala/org/apache/spark/Accumulable.scala
@@ -28,7 +28,7 @@ import org.apache.spark.util.{AccumulatorContext, AccumulatorMetadata, LegacyAcc
 
 
 /**
- * A data type that can be accumulated, i.e. has an commutative and associative "add" operation,
+ * A data type that can be accumulated, i.e. has a commutative and associative "add" operation,
  * but where the result type, `R`, may be different from the element type being added, `T`.
  *
  * You must define how to add data, and how to merge two of these together.  For some data types,
diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala b/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala
index bfb6a35f5b..485a8b4222 100644
--- a/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala
+++ b/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala
@@ -789,7 +789,7 @@ class JavaSparkContext(val sc: SparkContext)
   def cancelAllJobs(): Unit = sc.cancelAllJobs()
 
   /**
-   * Returns an Java map of JavaRDDs that have marked themselves as persistent via cache() call.
+   * Returns a Java map of JavaRDDs that have marked themselves as persistent via cache() call.
    * Note that this does not necessarily mean the caching or computation was successful.
    */
   def getPersistentRDDs: JMap[java.lang.Integer, JavaRDD[_]] = {
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 ab5b6c8380..2822eb5d60 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
@@ -919,7 +919,7 @@ private class PythonAccumulatorParam(@transient private val serverHost: String,
 }
 
 /**
- * An Wrapper for Python Broadcast, which is written into disk by Python. It also will
+ * A Wrapper for Python Broadcast, which is written into disk by Python. It also will
  * write the data into disk after deserialization, then Python can read it from disks.
  */
 // scalastyle:off no.finalize
diff --git a/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala b/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala
index 78606e06fb..9be4cadcb4 100644
--- a/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala
+++ b/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala
@@ -408,12 +408,12 @@ object SparkSubmit {
       printErrorAndExit("SparkR is not supported for Mesos cluster.")
     }
 
-    // If we're running a R app, set the main class to our specific R runner
+    // If we're running an R app, set the main class to our specific R runner
     if (args.isR && deployMode == CLIENT) {
       if (args.primaryResource == SPARKR_SHELL) {
         args.mainClass = "org.apache.spark.api.r.RBackend"
       } else {
-        // If a R file is provided, add it to the child arguments and list of files to deploy.
+        // If an R file is provided, add it to the child arguments and list of files to deploy.
         // Usage: RRunner <main R file> [app arguments]
         args.mainClass = "org.apache.spark.deploy.RRunner"
         args.childArgs = ArrayBuffer(args.primaryResource) ++ args.childArgs
@@ -422,7 +422,7 @@ object SparkSubmit {
     }
 
     if (isYarnCluster && args.isR) {
-      // In yarn-cluster mode for a R app, add primary resource to files
+      // In yarn-cluster mode for an R app, add primary resource to files
       // that can be distributed with the job
       args.files = mergeFileLists(args.files, args.primaryResource)
     }
diff --git a/core/src/main/scala/org/apache/spark/rdd/JdbcRDD.scala b/core/src/main/scala/org/apache/spark/rdd/JdbcRDD.scala
index 5426bf80ba..2f42916439 100644
--- a/core/src/main/scala/org/apache/spark/rdd/JdbcRDD.scala
+++ b/core/src/main/scala/org/apache/spark/rdd/JdbcRDD.scala
@@ -34,7 +34,7 @@ private[spark] class JdbcPartition(idx: Int, val lower: Long, val upper: Long) e
 
 // TODO: Expose a jdbcRDD function in SparkContext and mark this as semi-private
 /**
- * An RDD that executes an SQL query on a JDBC connection and reads results.
+ * An RDD that executes a SQL query on a JDBC connection and reads results.
  * For usage example, see test case JdbcRDDSuite.
  *
  * @param getConnection a function that returns an open Connection.
@@ -138,7 +138,7 @@ object JdbcRDD {
   }
 
   /**
-   * Create an RDD that executes an SQL query on a JDBC connection and reads results.
+   * Create an RDD that executes a SQL query on a JDBC connection and reads results.
    * For usage example, see test case JavaAPISuite.testJavaJdbcRDD.
    *
    * @param connectionFactory a factory that returns an open Connection.
@@ -178,7 +178,7 @@ object JdbcRDD {
   }
 
   /**
-   * Create an RDD that executes an SQL query on a JDBC connection and reads results. Each row is
+   * Create an RDD that executes a SQL query on a JDBC connection and reads results. Each row is
    * converted into a `Object` array. For usage example, see test case JavaAPISuite.testJavaJdbcRDD.
    *
    * @param connectionFactory a factory that returns an open Connection.
diff --git a/core/src/main/scala/org/apache/spark/scheduler/Pool.scala b/core/src/main/scala/org/apache/spark/scheduler/Pool.scala
index 732c89c39f..2a69a6c5e8 100644
--- a/core/src/main/scala/org/apache/spark/scheduler/Pool.scala
+++ b/core/src/main/scala/org/apache/spark/scheduler/Pool.scala
@@ -26,7 +26,7 @@ import org.apache.spark.internal.Logging
 import org.apache.spark.scheduler.SchedulingMode.SchedulingMode
 
 /**
- * An Schedulable entity that represents collection of Pools or TaskSetManagers
+ * A Schedulable entity that represents collection of Pools or TaskSetManagers
  */
 private[spark] class Pool(
     val poolName: String,
diff --git a/core/src/test/scala/org/apache/spark/broadcast/BroadcastSuite.scala b/core/src/test/scala/org/apache/spark/broadcast/BroadcastSuite.scala
index 6657104823..973676398a 100644
--- a/core/src/test/scala/org/apache/spark/broadcast/BroadcastSuite.scala
+++ b/core/src/test/scala/org/apache/spark/broadcast/BroadcastSuite.scala
@@ -138,7 +138,7 @@ class BroadcastSuite extends SparkFunSuite with LocalSparkContext {
   }
 
   /**
-   * Verify the persistence of state associated with an TorrentBroadcast in a local-cluster.
+   * Verify the persistence of state associated with a TorrentBroadcast in a local-cluster.
    *
    * This test creates a broadcast variable, uses it on all executors, and then unpersists it.
    * In between each step, this test verifies that the broadcast blocks are present only on the
diff --git a/core/src/test/scala/org/apache/spark/deploy/rest/StandaloneRestSubmitSuite.scala b/core/src/test/scala/org/apache/spark/deploy/rest/StandaloneRestSubmitSuite.scala
index a7bb9aa468..dd50e33da3 100644
--- a/core/src/test/scala/org/apache/spark/deploy/rest/StandaloneRestSubmitSuite.scala
+++ b/core/src/test/scala/org/apache/spark/deploy/rest/StandaloneRestSubmitSuite.scala
@@ -408,7 +408,7 @@ class StandaloneRestSubmitSuite extends SparkFunSuite with BeforeAndAfterEach {
 
   /**
    * Start a [[StandaloneRestServer]] that communicates with the given endpoint.
-   * If `faulty` is true, start an [[FaultyStandaloneRestServer]] instead.
+   * If `faulty` is true, start a [[FaultyStandaloneRestServer]] instead.
    * Return the master URL that corresponds to the address of this server.
    */
   private def startServer(
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 505cd476ff..acdf21df9a 100644
--- a/core/src/test/scala/org/apache/spark/rpc/RpcEnvSuite.scala
+++ b/core/src/test/scala/org/apache/spark/rpc/RpcEnvSuite.scala
@@ -489,7 +489,7 @@ abstract class RpcEnvSuite extends SparkFunSuite with BeforeAndAfterAll {
   /**
    * Setup an [[RpcEndpoint]] to collect all network events.
    *
-   * @return the [[RpcEndpointRef]] and an `ConcurrentLinkedQueue` that contains network events.
+   * @return the [[RpcEndpointRef]] and a `ConcurrentLinkedQueue` that contains network events.
    */
   private def setupNetworkEndpoint(
       _env: RpcEnv,
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 b6765f0645..f28f429e0c 100644
--- a/core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala
+++ b/core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala
@@ -1712,7 +1712,7 @@ class DAGSchedulerSuite extends SparkFunSuite with LocalSparkContext with Timeou
   }
 
   test("reduce tasks should be placed locally with map output") {
-    // Create an shuffleMapRdd with 1 partition
+    // Create a shuffleMapRdd with 1 partition
     val shuffleMapRdd = new MyRDD(sc, 1, Nil)
     val shuffleDep = new ShuffleDependency(shuffleMapRdd, new HashPartitioner(2))
     val shuffleId = shuffleDep.shuffleId
@@ -1733,7 +1733,7 @@ class DAGSchedulerSuite extends SparkFunSuite with LocalSparkContext with Timeou
 
   test("reduce task locality preferences should only include machines with largest map outputs") {
     val numMapTasks = 4
-    // Create an shuffleMapRdd with more partitions
+    // Create a shuffleMapRdd with more partitions
     val shuffleMapRdd = new MyRDD(sc, numMapTasks, Nil)
     val shuffleDep = new ShuffleDependency(shuffleMapRdd, new HashPartitioner(1))
     val shuffleId = shuffleDep.shuffleId
diff --git a/core/src/test/scala/org/apache/spark/util/JsonProtocolSuite.scala b/core/src/test/scala/org/apache/spark/util/JsonProtocolSuite.scala
index 0a8bbba6c5..85ca9d39d4 100644
--- a/core/src/test/scala/org/apache/spark/util/JsonProtocolSuite.scala
+++ b/core/src/test/scala/org/apache/spark/util/JsonProtocolSuite.scala
@@ -258,7 +258,7 @@ class JsonProtocolSuite extends SparkFunSuite {
   }
 
   test("FetchFailed backwards compatibility") {
-    // FetchFailed in Spark 1.1.0 does not have an "Message" property.
+    // FetchFailed in Spark 1.1.0 does not have a "Message" property.
     val fetchFailed = FetchFailed(BlockManagerId("With or", "without you", 15), 17, 18, 19,
       "ignored")
     val oldEvent = JsonProtocol.taskEndReasonToJson(fetchFailed)