[MINOR][DOCS] Fix more typos in comments/strings.

## What changes were proposed in this pull request?

This PR fixes 135 typos over 107 files:
* 121 typos in comments
* 11 typos in testcase name
* 3 typos in log messages

## How was this patch tested?

Manual.

Author: Dongjoon Hyun <dongjoon@apache.org>

Closes #11689 from dongjoon-hyun/fix_more_typos.

15 files changed, 20 insertions, 20 deletions

diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala b/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala
index 13e18a56c8..0d3a5237d9 100644
--- a/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala
+++ b/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala
@@ -66,7 +66,7 @@ class JavaDoubleRDD(val srdd: RDD[scala.Double])
    */
   def unpersist(blocking: Boolean): JavaDoubleRDD = fromRDD(srdd.unpersist(blocking))
 
-  // first() has to be overriden here in order for its return type to be Double instead of Object.
+  // first() has to be overridden here in order for its return type to be Double instead of Object.
   override def first(): JDouble = srdd.first()
 
   // Transformations (return a new RDD)
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 f1aebbcd39..d362c40b7a 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
@@ -351,7 +351,7 @@ class JavaSparkContext(val sc: SparkContext)
   }
 
   /**
-   * Get an RDD for a Hadoop-readable dataset from a Hadooop JobConf giving its InputFormat and any
+   * Get an RDD for a Hadoop-readable dataset from a Hadoop JobConf giving its InputFormat and any
    * other necessary info (e.g. file name for a filesystem-based dataset, table name for HyperTable,
    * etc).
    *
@@ -383,7 +383,7 @@ class JavaSparkContext(val sc: SparkContext)
   }
 
   /**
-   * Get an RDD for a Hadoop-readable dataset from a Hadooop JobConf giving its InputFormat and any
+   * Get an RDD for a Hadoop-readable dataset from a Hadoop JobConf giving its InputFormat and any
    * other necessary info (e.g. file name for a filesystem-based dataset, table name for HyperTable,
    *
    * @param conf JobConf for setting up the dataset. Note: This will be put into a Broadcast.
diff --git a/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcast.scala b/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcast.scala
index 550e1ba6d3..8091aa8062 100644
--- a/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcast.scala
+++ b/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcast.scala
@@ -74,7 +74,7 @@ private[spark] class TorrentBroadcast[T: ClassTag](obj: T, id: Long)
     } else {
       None
     }
-    // Note: use getSizeAsKb (not bytes) to maintain compatiblity if no units are provided
+    // Note: use getSizeAsKb (not bytes) to maintain compatibility if no units are provided
     blockSize = conf.getSizeAsKb("spark.broadcast.blockSize", "4m").toInt * 1024
   }
   setConf(SparkEnv.get.conf)
diff --git a/core/src/main/scala/org/apache/spark/deploy/history/ApplicationCache.scala b/core/src/main/scala/org/apache/spark/deploy/history/ApplicationCache.scala
index e2fda29044..000f7e8e1e 100644
--- a/core/src/main/scala/org/apache/spark/deploy/history/ApplicationCache.scala
+++ b/core/src/main/scala/org/apache/spark/deploy/history/ApplicationCache.scala
@@ -87,7 +87,7 @@ private[history] class ApplicationCache(
   /**
    * The cache of applications.
    *
-   * Tagged as `protected` so as to allow subclasses in tests to accesss it directly
+   * Tagged as `protected` so as to allow subclasses in tests to access it directly
    */
   protected val appCache: LoadingCache[CacheKey, CacheEntry] = {
     CacheBuilder.newBuilder()
@@ -447,7 +447,7 @@ private[history] class CacheMetrics(prefix: String) extends Source {
 private[history] trait ApplicationCacheOperations {
 
   /**
-   * Get the application UI and the probe neededed to see if it has been updated.
+   * Get the application UI and the probe needed to see if it has been updated.
    * @param appId application ID
    * @param attemptId attempt ID
    * @return If found, the Spark UI and any history information to be used in the cache
@@ -590,7 +590,7 @@ private[history] object ApplicationCacheCheckFilterRelay extends Logging {
   // name of the attempt ID entry in the filter configuration. Optional.
   val ATTEMPT_ID = "attemptId"
 
-  // namer of the filter to register
+  // name of the filter to register
   val FILTER_NAME = "org.apache.spark.deploy.history.ApplicationCacheCheckFilter"
 
   /** the application cache to relay requests to */
diff --git a/core/src/main/scala/org/apache/spark/executor/Executor.scala b/core/src/main/scala/org/apache/spark/executor/Executor.scala
index 07e3c12bc9..48372d70d5 100644
--- a/core/src/main/scala/org/apache/spark/executor/Executor.scala
+++ b/core/src/main/scala/org/apache/spark/executor/Executor.scala
@@ -124,7 +124,7 @@ private[spark] class Executor(
   private val HEARTBEAT_MAX_FAILURES = conf.getInt("spark.executor.heartbeat.maxFailures", 60)
 
   /**
-   * Count the failure times of heartbeat. It should only be acessed in the heartbeat thread. Each
+   * Count the failure times of heartbeat. It should only be accessed in the heartbeat thread. Each
    * successful heartbeat will reset it to 0.
    */
   private var heartbeatFailures = 0
diff --git a/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala b/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala
index c9606600ed..0f579cfe42 100644
--- a/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala
+++ b/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala
@@ -141,7 +141,7 @@ class DoubleRDDFunctions(self: RDD[Double]) extends Logging with Serializable {
    *  And on the input of 1 and 50 we would have a histogram of 1, 0, 1
    *
    * Note: if your histogram is evenly spaced (e.g. [0, 10, 20, 30]) this can be switched
-   * from an O(log n) inseration to O(1) per element. (where n = # buckets) if you set evenBuckets
+   * from an O(log n) insertion to O(1) per element. (where n = # buckets) if you set evenBuckets
    * to true.
    * buckets must be sorted and not contain any duplicates.
    * buckets array must be at least two elements
diff --git a/core/src/main/scala/org/apache/spark/scheduler/InputFormatInfo.scala b/core/src/main/scala/org/apache/spark/scheduler/InputFormatInfo.scala
index def0aac720..dfcdd113df 100644
--- a/core/src/main/scala/org/apache/spark/scheduler/InputFormatInfo.scala
+++ b/core/src/main/scala/org/apache/spark/scheduler/InputFormatInfo.scala
@@ -157,7 +157,7 @@ object InputFormatInfo {
     b) Decrement the currently allocated containers on that host.
     c) Compute rack info for each host and update rack -> count map based on (b).
     d) Allocate nodes based on (c)
-    e) On the allocation result, ensure that we dont allocate "too many" jobs on a single node
+    e) On the allocation result, ensure that we don't allocate "too many" jobs on a single node
        (even if data locality on that is very high) : this is to prevent fragility of job if a
        single (or small set of) hosts go down.
 
diff --git a/core/src/main/scala/org/apache/spark/scheduler/SplitInfo.scala b/core/src/main/scala/org/apache/spark/scheduler/SplitInfo.scala
index 1ce83485f0..6e9337bb90 100644
--- a/core/src/main/scala/org/apache/spark/scheduler/SplitInfo.scala
+++ b/core/src/main/scala/org/apache/spark/scheduler/SplitInfo.scala
@@ -45,7 +45,7 @@ class SplitInfo(
     hashCode
   }
 
-  // This is practically useless since most of the Split impl's dont seem to implement equals :-(
+  // This is practically useless since most of the Split impl's don't seem to implement equals :-(
   // So unless there is identity equality between underlyingSplits, it will always fail even if it
   // is pointing to same block.
   override def equals(other: Any): Boolean = other match {
diff --git a/core/src/main/scala/org/apache/spark/storage/BlockManager.scala b/core/src/main/scala/org/apache/spark/storage/BlockManager.scala
index bcf65e9d7e..996c1f5d9e 100644
--- a/core/src/main/scala/org/apache/spark/storage/BlockManager.scala
+++ b/core/src/main/scala/org/apache/spark/storage/BlockManager.scala
@@ -1057,7 +1057,7 @@ private[spark] class BlockManager(
               failures += 1
               replicationFailed = true
               peersFailedToReplicateTo += peer
-              if (failures > maxReplicationFailures) { // too many failures in replcating to peers
+              if (failures > maxReplicationFailures) { // too many failures in replicating to peers
                 done = true
               }
           }
diff --git a/core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala b/core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala
index 478a928acd..b19c30e2ff 100644
--- a/core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala
+++ b/core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala
@@ -70,7 +70,7 @@ final class ShuffleBlockFetcherIterator(
   private[this] var numBlocksToFetch = 0
 
   /**
-   * The number of blocks proccessed by the caller. The iterator is exhausted when
+   * The number of blocks processed by the caller. The iterator is exhausted when
    * [[numBlocksProcessed]] == [[numBlocksToFetch]].
    */
   private[this] var numBlocksProcessed = 0
diff --git a/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala b/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala
index 5a8c291431..094953f2f5 100644
--- a/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala
+++ b/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala
@@ -102,7 +102,7 @@ private[spark] object UIWorkloadGenerator {
             try {
               setProperties(desc)
               job()
-              println("Job funished: " + desc)
+              println("Job finished: " + desc)
             } catch {
               case e: Exception =>
                 println("Job Failed: " + desc)
diff --git a/core/src/main/scala/org/apache/spark/util/ParentClassLoader.scala b/core/src/main/scala/org/apache/spark/util/ParentClassLoader.scala
index 73d126ff62..c9b7493fcd 100644
--- a/core/src/main/scala/org/apache/spark/util/ParentClassLoader.scala
+++ b/core/src/main/scala/org/apache/spark/util/ParentClassLoader.scala
@@ -18,7 +18,7 @@
 package org.apache.spark.util
 
 /**
- * A class loader which makes some protected methods in ClassLoader accesible.
+ * A class loader which makes some protected methods in ClassLoader accessible.
  */
 private[spark] class ParentClassLoader(parent: ClassLoader) extends ClassLoader(parent) {
 
diff --git a/core/src/main/scala/org/apache/spark/util/SizeEstimator.scala b/core/src/main/scala/org/apache/spark/util/SizeEstimator.scala
index 83ded92609..a06db9a4fc 100644
--- a/core/src/main/scala/org/apache/spark/util/SizeEstimator.scala
+++ b/core/src/main/scala/org/apache/spark/util/SizeEstimator.scala
@@ -253,7 +253,7 @@ object SizeEstimator extends Logging {
       } else {
         // Estimate the size of a large array by sampling elements without replacement.
         // To exclude the shared objects that the array elements may link, sample twice
-        // and use the min one to caculate array size.
+        // and use the min one to calculate array size.
         val rand = new Random(42)
         val drawn = new OpenHashSet[Int](2 * ARRAY_SAMPLE_SIZE)
         val s1 = sampleArray(array, state, rand, drawn, length)
diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala
index b5a98ce569..37c6c9bf90 100644
--- a/core/src/main/scala/org/apache/spark/util/Utils.scala
+++ b/core/src/main/scala/org/apache/spark/util/Utils.scala
@@ -1530,7 +1530,7 @@ private[spark] object Utils extends Logging {
     rawMod + (if (rawMod < 0) mod else 0)
   }
 
-  // Handles idiosyncracies with hash (add more as required)
+  // Handles idiosyncrasies with hash (add more as required)
   // This method should be kept in sync with
   // org.apache.spark.network.util.JavaUtils#nonNegativeHash().
   def nonNegativeHash(obj: AnyRef): Int = {
@@ -1600,7 +1600,7 @@ private[spark] object Utils extends Logging {
    * @param f function to be executed. If prepare is not None, the running time of each call to f
    *          must be an order of magnitude longer than one millisecond for accurate timing.
    * @param prepare function to be executed before each call to f. Its running time doesn't count.
-   * @return the total time across all iterations (not couting preparation time)
+   * @return the total time across all iterations (not counting preparation time)
    */
   def timeIt(numIters: Int)(f: => Unit, prepare: Option[() => Unit] = None): Long = {
     if (prepare.isEmpty) {
diff --git a/core/src/main/scala/org/apache/spark/util/random/RandomSampler.scala b/core/src/main/scala/org/apache/spark/util/random/RandomSampler.scala
index 1314217023..3c61528ab5 100644
--- a/core/src/main/scala/org/apache/spark/util/random/RandomSampler.scala
+++ b/core/src/main/scala/org/apache/spark/util/random/RandomSampler.scala
@@ -54,7 +54,7 @@ object RandomSampler {
   /**
    * Default maximum gap-sampling fraction.
    * For sampling fractions <= this value, the gap sampling optimization will be applied.
-   * Above this value, it is assumed that "tradtional" Bernoulli sampling is faster.  The
+   * Above this value, it is assumed that "traditional" Bernoulli sampling is faster.  The
    * optimal value for this will depend on the RNG.  More expensive RNGs will tend to make
    * the optimal value higher.  The most reliable way to determine this value for a new RNG
    * is to experiment.  When tuning for a new RNG, I would expect a value of 0.5 to be close
@@ -319,7 +319,7 @@ class GapSamplingReplacementIterator[T: ClassTag](
   /**
    * Skip elements with replication factor zero (i.e. elements that won't be sampled).
    * Samples 'k' from geometric distribution  P(k) = (1-q)(q)^k, where q = e^(-f), that is
-   * q is the probabililty of Poisson(0; f)
+   * q is the probability of Poisson(0; f)
    */
   private def advance(): Unit = {
     val u = math.max(rng.nextDouble(), epsilon)