[MINOR][DOCS] Remove consecutive duplicated words/typo in Spark Repo

## What changes were proposed in this pull request?
There are many locations in the Spark repo where the same word occurs consecutively. Sometimes they are appropriately placed, but many times they are not. This PR removes the inappropriately duplicated words.

## How was this patch tested?
N/A since only docs or comments were updated.

Author: Niranjan Padmanabhan <niranjan.padmanabhan@gmail.com>

Closes #16455 from neurons/np.structure_streaming_doc.

3 files changed, 4 insertions, 4 deletions

diff --git a/core/src/test/scala/org/apache/spark/deploy/history/ApplicationCacheSuite.scala b/core/src/test/scala/org/apache/spark/deploy/history/ApplicationCacheSuite.scala
index e3304be792..7998e3702c 100644
--- a/core/src/test/scala/org/apache/spark/deploy/history/ApplicationCacheSuite.scala
+++ b/core/src/test/scala/org/apache/spark/deploy/history/ApplicationCacheSuite.scala
@@ -253,7 +253,7 @@ class ApplicationCacheSuite extends SparkFunSuite with Logging with MockitoSugar
     assertNotFound(appId, None)
   }
 
-  test("Test that if an attempt ID is is set, it must be used in lookups") {
+  test("Test that if an attempt ID is set, it must be used in lookups") {
     val operations = new StubCacheOperations()
     val clock = new ManualClock(1)
     implicit val cache = new ApplicationCache(operations, retainedApplications = 10, clock = clock)
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 5e8a854e46..f3d3f701af 100644
--- a/core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala
+++ b/core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala
@@ -1819,7 +1819,7 @@ class DAGSchedulerSuite extends SparkFunSuite with LocalSparkContext with Timeou
     assert(mapOutputTracker.getMapSizesByExecutorId(shuffleId, 0).map(_._1).toSet ===
       HashSet(makeBlockManagerId("hostA")))
 
-    // Reducer should run where RDD 2 has preferences, even though though it also has a shuffle dep
+    // Reducer should run where RDD 2 has preferences, even though it also has a shuffle dep
     val reduceTaskSet = taskSets(1)
     assertLocations(reduceTaskSet, Seq(Seq("hostB")))
     complete(reduceTaskSet, Seq((Success, 42)))
@@ -2058,7 +2058,7 @@ class DAGSchedulerSuite extends SparkFunSuite with LocalSparkContext with Timeou
 
     // Now complete tasks in the second task set
     val newTaskSet = taskSets(1)
-    assert(newTaskSet.tasks.size === 2)     // Both tasks 0 and 1 were on on hostA
+    assert(newTaskSet.tasks.size === 2)     // Both tasks 0 and 1 were on hostA
     runEvent(makeCompletionEvent(newTaskSet.tasks(0), Success, makeMapStatus("hostB", 2)))
     assert(results.size === 0)    // Map stage job should not be complete yet
     runEvent(makeCompletionEvent(newTaskSet.tasks(1), Success, makeMapStatus("hostB", 2)))
diff --git a/core/src/test/scala/org/apache/spark/util/collection/ExternalAppendOnlyMapSuite.scala b/core/src/test/scala/org/apache/spark/util/collection/ExternalAppendOnlyMapSuite.scala
index 7f0838268a..c8b6a3346a 100644
--- a/core/src/test/scala/org/apache/spark/util/collection/ExternalAppendOnlyMapSuite.scala
+++ b/core/src/test/scala/org/apache/spark/util/collection/ExternalAppendOnlyMapSuite.scala
@@ -53,7 +53,7 @@ class ExternalAppendOnlyMapSuite extends SparkFunSuite with LocalSparkContext {
     conf
   }
 
-  test("single insert insert") {
+  test("single insert") {
     val conf = createSparkConf(loadDefaults = false)
     sc = new SparkContext("local", "test", conf)
     val map = createExternalMap[Int]