[MINOR][DOCS] Fix all typos in markdown files of `doc` and similar patterns in other comments

## What changes were proposed in this pull request?

This PR tries to fix all typos in all markdown files under `docs` module,
and fixes similar typos in other comments, too.

## How was the this patch tested?

manual tests.

Author: Dongjoon Hyun <dongjoon@apache.org>

Closes #11300 from dongjoon-hyun/minor_fix_typos.

9 files changed, 14 insertions, 14 deletions

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DistinctAggregationRewriter.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DistinctAggregationRewriter.scala
index b49885d469..7518946a94 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DistinctAggregationRewriter.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DistinctAggregationRewriter.scala
@@ -88,7 +88,7 @@ import org.apache.spark.sql.types.IntegerType
  *    this aggregate consists of the original group by clause, all the requested distinct columns
  *    and the group id. Both de-duplication of distinct column and the aggregation of the
  *    non-distinct group take advantage of the fact that we group by the group id (gid) and that we
- *    have nulled out all non-relevant columns for the the given group.
+ *    have nulled out all non-relevant columns the given group.
  * 3. Aggregating the distinct groups and combining this with the results of the non-distinct
  *    aggregation. In this step we use the group id to filter the inputs for the aggregate
  *    functions. The result of the non-distinct group are 'aggregated' by using the first operator,
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/HyperLogLogPlusPlus.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/HyperLogLogPlusPlus.scala
index ec833d6789..a474017221 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/HyperLogLogPlusPlus.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/HyperLogLogPlusPlus.scala
@@ -238,7 +238,7 @@ case class HyperLogLogPlusPlus(
       diff * diff
     }
 
-    // Keep moving bounds as long as the the (exclusive) high bound is closer to the estimate than
+    // Keep moving bounds as long as the (exclusive) high bound is closer to the estimate than
     // the lower (inclusive) bound.
     var low = math.max(nearestEstimateIndex - K + 1, 0)
     var high = math.min(low + K, numEstimates)
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/GenerateMutableProjection.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/GenerateMutableProjection.scala
index 5b4dc8df86..9abe92b1e7 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/GenerateMutableProjection.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/GenerateMutableProjection.scala
@@ -83,7 +83,7 @@ object GenerateMutableProjection extends CodeGenerator[Seq[Expression], () => Mu
         }
     }
 
-    // Evaluate all the the subexpressions.
+    // Evaluate all the subexpressions.
     val evalSubexpr = ctx.subexprFunctions.mkString("\n")
 
     val updates = validExpr.zip(index).map {
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/RandomDataGenerator.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/RandomDataGenerator.scala
index 7c173cbcee..8207d64798 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/RandomDataGenerator.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/RandomDataGenerator.scala
@@ -148,7 +148,7 @@ object RandomDataGenerator {
             // for "0001-01-01 00:00:00.000000". We need to find a
             // number that is greater or equals to this number as a valid timestamp value.
             while (milliseconds < -62135740800000L) {
-              // 253402329599999L is the the number of milliseconds since
+              // 253402329599999L is the number of milliseconds since
               // January 1, 1970, 00:00:00 GMT for "9999-12-31 23:59:59.999999".
               milliseconds = rand.nextLong() % 253402329599999L
             }
@@ -163,7 +163,7 @@ object RandomDataGenerator {
             // for "0001-01-01 00:00:00.000000". We need to find a
             // number that is greater or equals to this number as a valid timestamp value.
             while (milliseconds < -62135740800000L) {
-              // 253402329599999L is the the number of milliseconds since
+              // 253402329599999L is the number of milliseconds since
               // January 1, 1970, 00:00:00 GMT for "9999-12-31 23:59:59.999999".
               milliseconds = rand.nextLong() % 253402329599999L
             }
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/WriterContainer.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/WriterContainer.scala
index 6340229dbb..7e5c8f2f48 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/WriterContainer.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/WriterContainer.scala
@@ -145,7 +145,7 @@ private[sql] abstract class BaseWriterContainer(
       // If we are appending data to an existing dir, we will only use the output committer
       // associated with the file output format since it is not safe to use a custom
       // committer for appending. For example, in S3, direct parquet output committer may
-      // leave partial data in the destination dir when the the appending job fails.
+      // leave partial data in the destination dir when the appending job fails.
       //
       // See SPARK-8578 for more details
       logInfo(
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/ExchangeCoordinator.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/ExchangeCoordinator.scala
index 6f3bb0ad2b..7f54ea97cd 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/ExchangeCoordinator.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/ExchangeCoordinator.scala
@@ -55,7 +55,7 @@ import org.apache.spark.sql.execution.{ShuffledRowRDD, SparkPlan}
  *    If this coordinator has made the decision on how to shuffle data, this [[ShuffleExchange]]
  *    will immediately get its corresponding post-shuffle [[ShuffledRowRDD]].
  *  - If this coordinator has not made the decision on how to shuffle data, it will ask those
- *    registered [[ShuffleExchange]]s to submit their pre-shuffle stages. Then, based on the the
+ *    registered [[ShuffleExchange]]s to submit their pre-shuffle stages. Then, based on the
  *    size statistics of pre-shuffle partitions, this coordinator will determine the number of
  *    post-shuffle partitions and pack multiple pre-shuffle partitions with continuous indices
  *    to a single post-shuffle partition whenever necessary.
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
index 97c6992e18..510894afac 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
@@ -1782,7 +1782,7 @@ object functions extends LegacyFunctions {
   def round(e: Column, scale: Int): Column = withExpr { Round(e.expr, Literal(scale)) }
 
   /**
-   * Shift the the given value numBits left. If the given value is a long value, this function
+   * Shift the given value numBits left. If the given value is a long value, this function
    * will return a long value else it will return an integer value.
    *
    * @group math_funcs
@@ -1791,7 +1791,7 @@ object functions extends LegacyFunctions {
   def shiftLeft(e: Column, numBits: Int): Column = withExpr { ShiftLeft(e.expr, lit(numBits).expr) }
 
   /**
-   * Shift the the given value numBits right. If the given value is a long value, it will return
+   * Shift the given value numBits right. If the given value is a long value, it will return
    * a long value else it will return an integer value.
    *
    * @group math_funcs
@@ -1802,7 +1802,7 @@ object functions extends LegacyFunctions {
   }
 
   /**
-   * Unsigned shift the the given value numBits right. If the given value is a long value,
+   * Unsigned shift the given value numBits right. If the given value is a long value,
    * it will return a long value else it will return an integer value.
    *
    * @group math_funcs
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/StreamTest.scala b/sql/core/src/test/scala/org/apache/spark/sql/StreamTest.scala
index 62710e72fb..bb5135826e 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/StreamTest.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/StreamTest.scala
@@ -173,10 +173,10 @@ trait StreamTest extends QueryTest with Timeouts {
     testStream(stream.toDF())(actions: _*)
 
   /**
-   * Executes the specified actions on the the given streaming DataFrame and provides helpful
+   * Executes the specified actions on the given streaming DataFrame and provides helpful
    * error messages in the case of failures or incorrect answers.
    *
-   * Note that if the stream is not explictly started before an action that requires it to be
+   * Note that if the stream is not explicitly started before an action that requires it to be
    * running then it will be automatically started before performing any other actions.
    */
   def testStream(stream: DataFrame)(actions: StreamAction*): Unit = {
diff --git a/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/HiveThriftServer2Suites.scala b/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/HiveThriftServer2Suites.scala
index 865197e24c..5f9952a90a 100644
--- a/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/HiveThriftServer2Suites.scala
+++ b/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/HiveThriftServer2Suites.scala
@@ -721,13 +721,13 @@ abstract class HiveThriftServer2Test extends SparkFunSuite with BeforeAndAfterAl
   }
 
   /**
-   * String to scan for when looking for the the thrift binary endpoint running.
+   * String to scan for when looking for the thrift binary endpoint running.
    * This can change across Hive versions.
    */
   val THRIFT_BINARY_SERVICE_LIVE = "Starting ThriftBinaryCLIService on port"
 
   /**
-   * String to scan for when looking for the the thrift HTTP endpoint running.
+   * String to scan for when looking for the thrift HTTP endpoint running.
    * This can change across Hive versions.
    */
   val THRIFT_HTTP_SERVICE_LIVE = "Started ThriftHttpCLIService in http"