[MINOR][DOCS] Fix few typos in the java docs

JIRA :https://issues.apache.org/jira/browse/SPARK-29050
'a hdfs' change into  'an hdfs'
'an unique' change into 'a unique'
'an url' change into 'a url'
'a error' change into 'an error'

Closes #25756 from dengziming/feature_fix_typos.

Authored-by: dengziming <dengziming@growingio.com>
Signed-off-by: HyukjinKwon <gurwls223@apache.org>

Author: dengziming

R/pkg/R/context.R

@@ -301,7 +301,7 @@ broadcastRDD <- function(sc, object) {
 #' Set the checkpoint directory
 #'
 #' Set the directory under which RDDs are going to be checkpointed. The
-#' directory must be a HDFS path if running on a cluster.
+#' directory must be an HDFS path if running on a cluster.
 #'
 #' @param sc Spark Context to use
 #' @param dirName Directory path
@@ -446,7 +446,7 @@ setLogLevel <- function(level) {
 #' Set checkpoint directory
 #'
 #' Set the directory under which SparkDataFrame are going to be checkpointed. The directory must be
-#' a HDFS path if running on a cluster.
+#' an HDFS path if running on a cluster.
 #'
 #' @rdname setCheckpointDir
 #' @param directory Directory path to checkpoint to

core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala

@@ -609,7 +609,7 @@ class JavaSparkContext(val sc: SparkContext) extends Closeable {
 
   /**
    * Set the directory under which RDDs are going to be checkpointed. The directory must
-   * be a HDFS path if running on a cluster.
+   * be an HDFS path if running on a cluster.
    */
   def setCheckpointDir(dir: String) {
     sc.setCheckpointDir(dir)

core/src/main/scala/org/apache/spark/metrics/MetricsSystem.scala

@@ -124,7 +124,7 @@ private[spark] class MetricsSystem private (
    * If either ID is not available, this defaults to just using <source name>.
    *
    * @param source Metric source to be named by this method.
-   * @return An unique metric name for each combination of
+   * @return A unique metric name for each combination of
    *         application, executor/driver and metric source.
    */
   private[spark] def buildRegistryName(source: Source): String = {

core/src/main/scala/org/apache/spark/storage/BlockManagerId.scala

@@ -27,7 +27,7 @@ import org.apache.spark.util.Utils
 
 /**
  * :: DeveloperApi ::
- * This class represent an unique identifier for a BlockManager.
+ * This class represent a unique identifier for a BlockManager.
  *
  * The first 2 constructors of this class are made private to ensure that BlockManagerId objects
  * can be created only using the apply method in the companion object. This allows de-duplication

core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala

@@ -600,7 +600,7 @@ class SparkSubmitSuite
   }
 
   // TODO(SPARK-9603): Building a package is flaky on Jenkins Maven builds.
-  // See https://gist.github.com/shivaram/3a2fecce60768a603dac for a error log
+  // See https://gist.github.com/shivaram/3a2fecce60768a603dac for an error log
   ignore("correctly builds R packages included in a jar with --packages") {
     assume(RUtils.isRInstalled, "R isn't installed on this machine.")
     assume(RUtils.isSparkRInstalled, "SparkR is not installed in this build.")

docs/spark-standalone.md

@@ -432,7 +432,7 @@ In addition, detailed log output for each job is also written to the work direct
 
 # Running Alongside Hadoop
 
-You can run Spark alongside your existing Hadoop cluster by just launching it as a separate service on the same machines. To access Hadoop data from Spark, just use a hdfs:// URL (typically `hdfs://<namenode>:9000/path`, but you can find the right URL on your Hadoop Namenode's web UI). Alternatively, you can set up a separate cluster for Spark, and still have it access HDFS over the network; this will be slower than disk-local access, but may not be a concern if you are still running in the same local area network (e.g. you place a few Spark machines on each rack that you have Hadoop on).
+You can run Spark alongside your existing Hadoop cluster by just launching it as a separate service on the same machines. To access Hadoop data from Spark, just use an hdfs:// URL (typically `hdfs://<namenode>:9000/path`, but you can find the right URL on your Hadoop Namenode's web UI). Alternatively, you can set up a separate cluster for Spark, and still have it access HDFS over the network; this will be slower than disk-local access, but may not be a concern if you are still running in the same local area network (e.g. you place a few Spark machines on each rack that you have Hadoop on).
 
 
 # Configuring Ports for Network Security

external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisCheckpointer.scala

@@ -68,7 +68,7 @@ private[kinesis] class KinesisCheckpointer(
     if (checkpointer != null) {
       try {
         // We must call `checkpoint()` with no parameter to finish reading shards.
-        // See an URL below for details:
+        // See a URL below for details:
         // https://forums.aws.amazon.com/thread.jspa?threadID=244218
         KinesisRecordProcessor.retryRandom(checkpointer.checkpoint(), 4, 100)
       } catch {

python/pyspark/context.py

@@ -950,7 +950,7 @@ def addPyFile(self, path):
     def setCheckpointDir(self, dirName):
         """
         Set the directory under which RDDs are going to be checkpointed. The
-        directory must be a HDFS path if running on a cluster.
+        directory must be an HDFS path if running on a cluster.
         """
         self._jsc.sc().setCheckpointDir(dirName)
 

sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala

@@ -43,7 +43,7 @@ import org.apache.spark.util.{SizeEstimator, Utils}
 
 /**
  * An implementation of [[StateStoreProvider]] and [[StateStore]] in which all the data is backed
- * by files in a HDFS-compatible file system. All updates to the store has to be done in sets
+ * by files in an HDFS-compatible file system. All updates to the store has to be done in sets
  * transactionally, and each set of updates increments the store's version. These versions can
  * be used to re-execute the updates (by retries in RDD operations) on the correct version of
  * the store, and regenerate the store version.
@@ -79,7 +79,7 @@ private[state] class HDFSBackedStateStoreProvider extends StateStoreProvider wit
   //   java.util.ConcurrentModificationException
   type MapType = java.util.concurrent.ConcurrentHashMap[UnsafeRow, UnsafeRow]
 
-  /** Implementation of [[StateStore]] API which is backed by a HDFS-compatible file system */
+  /** Implementation of [[StateStore]] API which is backed by an HDFS-compatible file system */
   class HDFSBackedStateStore(val version: Long, mapToUpdate: MapType)
     extends StateStore {
 

sql/core/src/main/scala/org/apache/spark/sql/streaming/StreamingQueryListener.scala

@@ -79,7 +79,7 @@ object StreamingQueryListener {
 
   /**
    * Event representing the start of a query
-   * @param id An unique query id that persists across restarts. See `StreamingQuery.id()`.
+   * @param id A unique query id that persists across restarts. See `StreamingQuery.id()`.
    * @param runId A query id that is unique for every start/restart. See `StreamingQuery.runId()`.
    * @param name User-specified name of the query, null if not specified.
    * @since 2.1.0
@@ -101,7 +101,7 @@ object StreamingQueryListener {
   /**
    * Event representing that termination of a query.
    *
-   * @param id An unique query id that persists across restarts. See `StreamingQuery.id()`.
+   * @param id A unique query id that persists across restarts. See `StreamingQuery.id()`.
    * @param runId A query id that is unique for every start/restart. See `StreamingQuery.runId()`.
    * @param exception The exception message of the query if the query was terminated
    *                  with an exception. Otherwise, it will be `None`.