[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.

30 files changed, 50 insertions, 50 deletions

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/Row.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/Row.scala
index 391001de26..d83eef7a41 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/Row.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/Row.scala
@@ -300,7 +300,7 @@ trait Row extends Serializable {
     getMap[K, V](i).asJava
 
   /**
-   * Returns the value at position i of struct type as an [[Row]] object.
+   * Returns the value at position i of struct type as a [[Row]] object.
    *
    * @throws ClassCastException when data type does not match.
    */
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
index 0e68656467..d1ca99f79e 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
@@ -37,7 +37,7 @@ import org.apache.spark.sql.catalyst.util.toPrettySQL
 import org.apache.spark.sql.types._
 
 /**
- * A trivial [[Analyzer]] with an dummy [[SessionCatalog]] and [[EmptyFunctionRegistry]].
+ * A trivial [[Analyzer]] with a dummy [[SessionCatalog]] and [[EmptyFunctionRegistry]].
  * Used for testing when all relations are already filled in and the analyzer needs only
  * to resolve attribute references.
  */
@@ -1496,7 +1496,7 @@ class Analyzer(
    * This rule handles three cases:
    *  - A [[Project]] having [[WindowExpression]]s in its projectList;
    *  - An [[Aggregate]] having [[WindowExpression]]s in its aggregateExpressions.
-   *  - An [[Filter]]->[[Aggregate]] pattern representing GROUP BY with a HAVING
+   *  - A [[Filter]]->[[Aggregate]] pattern representing GROUP BY with a HAVING
    *    clause and the [[Aggregate]] has [[WindowExpression]]s in its aggregateExpressions.
    * Note: If there is a GROUP BY clause in the query, aggregations and corresponding
    * filters (expressions in the HAVING clause) should be evaluated before any
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala
index eca837ccf0..a7388c71de 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala
@@ -410,7 +410,7 @@ object FunctionRegistry {
           case Failure(e) => throw new AnalysisException(e.getMessage)
         }
       } else {
-        // Otherwise, find an ctor method that matches the number of arguments, and use that.
+        // Otherwise, find a constructor method that matches the number of arguments, and use that.
         val params = Seq.fill(expressions.size)(classOf[Expression])
         val f = Try(tag.runtimeClass.getDeclaredConstructor(params : _*)) match {
           case Success(e) =>
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/MultiInstanceRelation.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/MultiInstanceRelation.scala
index 394be47a58..95a3837ae1 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/MultiInstanceRelation.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/MultiInstanceRelation.scala
@@ -20,7 +20,7 @@ package org.apache.spark.sql.catalyst.analysis
 import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
 
 /**
- * A trait that should be mixed into query operators where an single instance might appear multiple
+ * A trait that should be mixed into query operators where a single instance might appear multiple
  * times in a logical query plan.  It is invalid to have multiple copies of the same attribute
  * produced by distinct operators in a query tree as this breaks the guarantee that expression
  * ids, which are used to differentiate attributes, are unique.
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala
index 371c198aa3..943d1071e2 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/SessionCatalog.scala
@@ -241,7 +241,7 @@ class SessionCatalog(
   /**
    * Retrieve the metadata of an existing metastore table.
    * If no database is specified, assume the table is in the current database.
-   * If the specified table is not found in the database then an [[NoSuchTableException]] is thrown.
+   * If the specified table is not found in the database then a [[NoSuchTableException]] is thrown.
    */
   def getTableMetadata(name: TableIdentifier): CatalogTable = {
     val db = formatDatabaseName(name.database.getOrElse(getCurrentDatabase))
@@ -266,7 +266,7 @@ class SessionCatalog(
   /**
    * Load files stored in given path into an existing metastore table.
    * If no database is specified, assume the table is in the current database.
-   * If the specified table is not found in the database then an [[NoSuchTableException]] is thrown.
+   * If the specified table is not found in the database then a [[NoSuchTableException]] is thrown.
    */
   def loadTable(
       name: TableIdentifier,
@@ -283,7 +283,7 @@ class SessionCatalog(
   /**
    * Load files stored in given path into the partition of an existing metastore table.
    * If no database is specified, assume the table is in the current database.
-   * If the specified table is not found in the database then an [[NoSuchTableException]] is thrown.
+   * If the specified table is not found in the database then a [[NoSuchTableException]] is thrown.
    */
   def loadPartition(
       name: TableIdentifier,
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/functionResources.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/functionResources.scala
index c66d08d2cf..8e46b962ff 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/functionResources.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/functionResources.scala
@@ -19,7 +19,7 @@ package org.apache.spark.sql.catalyst.catalog
 
 import org.apache.spark.sql.AnalysisException
 
-/** An trait that represents the type of a resourced needed by a function. */
+/** A trait that represents the type of a resourced needed by a function. */
 abstract class FunctionResourceType(val resourceType: String)
 
 object JarResource extends FunctionResourceType("jar")
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExpectsInputTypes.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExpectsInputTypes.scala
index b3dfac806f..c15a2df508 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExpectsInputTypes.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExpectsInputTypes.scala
@@ -21,7 +21,7 @@ import org.apache.spark.sql.catalyst.analysis.TypeCheckResult
 import org.apache.spark.sql.types.AbstractDataType
 
 /**
- * An trait that gets mixin to define the expected input types of an expression.
+ * A trait that gets mixin to define the expected input types of an expression.
  *
  * This trait is typically used by operator expressions (e.g. [[Add]], [[Subtract]]) to define
  * expected input types without any implicit casting.
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Projection.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Projection.scala
index 27ad8e4cf2..c8d18667f7 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Projection.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Projection.scala
@@ -158,7 +158,7 @@ object UnsafeProjection {
 object FromUnsafeProjection {
 
   /**
-   * Returns an Projection for given StructType.
+   * Returns a Projection for given StructType.
    */
   def apply(schema: StructType): Projection = {
     apply(schema.fields.map(_.dataType))
@@ -172,7 +172,7 @@ object FromUnsafeProjection {
   }
 
   /**
-   * Returns an Projection for given sequence of Expressions (bounded).
+   * Returns a Projection for given sequence of Expressions (bounded).
    */
   private def create(exprs: Seq[Expression]): Projection = {
     GenerateSafeProjection.generate(exprs)
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala
index f60d278c54..d603d3c73e 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala
@@ -91,7 +91,7 @@ case class CreateMap(children: Seq[Expression]) extends Expression {
 
   override def checkInputDataTypes(): TypeCheckResult = {
     if (children.size % 2 != 0) {
-      TypeCheckResult.TypeCheckFailure(s"$prettyName expects an positive even number of arguments.")
+      TypeCheckResult.TypeCheckFailure(s"$prettyName expects a positive even number of arguments.")
     } else if (keys.map(_.dataType).distinct.length > 1) {
       TypeCheckResult.TypeCheckFailure("The given keys of function map should all be the same " +
         "type, but they are " + keys.map(_.dataType.simpleString).mkString("[", ", ", "]"))
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/types/AbstractDataType.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/types/AbstractDataType.scala
index 03ea349221..65eae869d4 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/types/AbstractDataType.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/types/AbstractDataType.scala
@@ -148,7 +148,7 @@ abstract class NumericType extends AtomicType {
   // implicitly[Numeric[JvmType]] to be valid, we have to change JvmType from a type variable to a
   // type parameter and add a numeric annotation (i.e., [JvmType : Numeric]). This gets
   // desugared by the compiler into an argument to the objects constructor. This means there is no
-  // longer an no argument constructor and thus the JVM cannot serialize the object anymore.
+  // longer a no argument constructor and thus the JVM cannot serialize the object anymore.
   private[sql] val numeric: Numeric[InternalType]
 }
 
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala
index 88fa5cd21d..b248583d79 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala
@@ -314,7 +314,7 @@ class DataFrameReader private[sql](sparkSession: SparkSession) extends Logging {
   def json(paths: String*): DataFrame = format("json").load(paths : _*)
 
   /**
-   * Loads an `JavaRDD[String]` storing JSON objects (one object per record) and
+   * Loads a `JavaRDD[String]` storing JSON objects (one object per record) and
    * returns the result as a [[DataFrame]].
    *
    * Unless the schema is specified using [[schema]] function, this function goes through the
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala b/sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala
index 2e14c5d486..0fb2400d1b 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala
@@ -370,7 +370,7 @@ class SQLContext private[sql](val sparkSession: SparkSession)
 
   /**
    * :: DeveloperApi ::
-   * Creates a [[DataFrame]] from an [[JavaRDD]] containing [[Row]]s using the given schema.
+   * Creates a [[DataFrame]] from a [[JavaRDD]] containing [[Row]]s using the given schema.
    * It is important to make sure that the structure of every [[Row]] of the provided RDD matches
    * the provided schema. Otherwise, there will be runtime exception.
    *
@@ -384,7 +384,7 @@ class SQLContext private[sql](val sparkSession: SparkSession)
 
   /**
    * :: DeveloperApi ::
-   * Creates a [[DataFrame]] from an [[java.util.List]] containing [[Row]]s using the given schema.
+   * Creates a [[DataFrame]] from a [[java.util.List]] containing [[Row]]s using the given schema.
    * It is important to make sure that the structure of every [[Row]] of the provided List matches
    * the provided schema. Otherwise, there will be runtime exception.
    *
@@ -421,7 +421,7 @@ class SQLContext private[sql](val sparkSession: SparkSession)
   }
 
   /**
-   * Applies a schema to an List of Java Beans.
+   * Applies a schema to a List of Java Beans.
    *
    * WARNING: Since there is no guaranteed ordering for fields in a Java Bean,
    *          SELECT * queries will return the columns in an undefined order.
@@ -552,7 +552,7 @@ class SQLContext private[sql](val sparkSession: SparkSession)
   /**
    * :: Experimental ::
    * Creates a [[Dataset]] with a single [[LongType]] column named `id`, containing elements
-   * in an range from 0 to `end` (exclusive) with step value 1.
+   * in a range from 0 to `end` (exclusive) with step value 1.
    *
    * @since 2.0.0
    * @group dataset
@@ -563,7 +563,7 @@ class SQLContext private[sql](val sparkSession: SparkSession)
   /**
    * :: Experimental ::
    * Creates a [[Dataset]] with a single [[LongType]] column named `id`, containing elements
-   * in an range from `start` to `end` (exclusive) with step value 1.
+   * in a range from `start` to `end` (exclusive) with step value 1.
    *
    * @since 2.0.0
    * @group dataset
@@ -574,7 +574,7 @@ class SQLContext private[sql](val sparkSession: SparkSession)
   /**
    * :: Experimental ::
    * Creates a [[Dataset]] with a single [[LongType]] column named `id`, containing elements
-   * in an range from `start` to `end` (exclusive) with an step value.
+   * in a range from `start` to `end` (exclusive) with a step value.
    *
    * @since 2.0.0
    * @group dataset
@@ -587,7 +587,7 @@ class SQLContext private[sql](val sparkSession: SparkSession)
   /**
    * :: Experimental ::
    * Creates a [[Dataset]] with a single [[LongType]] column named `id`, containing elements
-   * in an range from `start` to `end` (exclusive) with an step value, with partition number
+   * in a range from `start` to `end` (exclusive) with a step value, with partition number
    * specified.
    *
    * @since 2.0.0
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/SQLImplicits.scala b/sql/core/src/main/scala/org/apache/spark/sql/SQLImplicits.scala
index b7ea2a8917..440952572d 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/SQLImplicits.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/SQLImplicits.scala
@@ -33,7 +33,7 @@ abstract class SQLImplicits {
   protected def _sqlContext: SQLContext
 
   /**
-   * Converts $"col name" into an [[Column]].
+   * Converts $"col name" into a [[Column]].
    *
    * @since 2.0.0
    */
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala b/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala
index 7d7fd0399d..f5b16d07ad 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala
@@ -305,7 +305,7 @@ class SparkSession private(
 
   /**
    * :: DeveloperApi ::
-   * Creates a [[DataFrame]] from an [[JavaRDD]] containing [[Row]]s using the given schema.
+   * Creates a [[DataFrame]] from a [[JavaRDD]] containing [[Row]]s using the given schema.
    * It is important to make sure that the structure of every [[Row]] of the provided RDD matches
    * the provided schema. Otherwise, there will be runtime exception.
    *
@@ -319,7 +319,7 @@ class SparkSession private(
 
   /**
    * :: DeveloperApi ::
-   * Creates a [[DataFrame]] from an [[java.util.List]] containing [[Row]]s using the given schema.
+   * Creates a [[DataFrame]] from a [[java.util.List]] containing [[Row]]s using the given schema.
    * It is important to make sure that the structure of every [[Row]] of the provided List matches
    * the provided schema. Otherwise, there will be runtime exception.
    *
@@ -365,7 +365,7 @@ class SparkSession private(
   }
 
   /**
-   * Applies a schema to an List of Java Beans.
+   * Applies a schema to a List of Java Beans.
    *
    * WARNING: Since there is no guaranteed ordering for fields in a Java Bean,
    *          SELECT * queries will return the columns in an undefined order.
@@ -475,7 +475,7 @@ class SparkSession private(
   /**
    * :: Experimental ::
    * Creates a [[Dataset]] with a single [[LongType]] column named `id`, containing elements
-   * in an range from 0 to `end` (exclusive) with step value 1.
+   * in a range from 0 to `end` (exclusive) with step value 1.
    *
    * @since 2.0.0
    * @group dataset
@@ -486,7 +486,7 @@ class SparkSession private(
   /**
    * :: Experimental ::
    * Creates a [[Dataset]] with a single [[LongType]] column named `id`, containing elements
-   * in an range from `start` to `end` (exclusive) with step value 1.
+   * in a range from `start` to `end` (exclusive) with step value 1.
    *
    * @since 2.0.0
    * @group dataset
@@ -499,7 +499,7 @@ class SparkSession private(
   /**
    * :: Experimental ::
    * Creates a [[Dataset]] with a single [[LongType]] column named `id`, containing elements
-   * in an range from `start` to `end` (exclusive) with an step value.
+   * in a range from `start` to `end` (exclusive) with a step value.
    *
    * @since 2.0.0
    * @group dataset
@@ -512,7 +512,7 @@ class SparkSession private(
   /**
    * :: Experimental ::
    * Creates a [[Dataset]] with a single [[LongType]] column named `id`, containing elements
-   * in an range from `start` to `end` (exclusive) with an step value, with partition number
+   * in a range from `start` to `end` (exclusive) with a step value, with partition number
    * specified.
    *
    * @since 2.0.0
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/catalyst/SQLBuilder.scala b/sql/core/src/main/scala/org/apache/spark/sql/catalyst/SQLBuilder.scala
index 9dc367920e..a8cc72f2e7 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/catalyst/SQLBuilder.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/catalyst/SQLBuilder.scala
@@ -274,7 +274,7 @@ class SQLBuilder(logicalPlan: LogicalPlan) extends Logging {
     //   5. the table alias for output columns of generator.
     //   6. the AS keyword
     //   7. the column alias, can be more than one, e.g. AS key, value
-    // An concrete example: "tbl LATERAL VIEW EXPLODE(map_col) sub_q AS key, value", and the builder
+    // A concrete example: "tbl LATERAL VIEW EXPLODE(map_col) sub_q AS key, value", and the builder
     // will put it in FROM clause later.
     build(
       childSQL,
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortBasedAggregationIterator.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortBasedAggregationIterator.scala
index f392b135ce..3f7f849885 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortBasedAggregationIterator.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortBasedAggregationIterator.scala
@@ -86,7 +86,7 @@ class SortBasedAggregationIterator(
   // The aggregation buffer used by the sort-based aggregation.
   private[this] val sortBasedAggregationBuffer: MutableRow = newBuffer
 
-  // An SafeProjection to turn UnsafeRow into GenericInternalRow, because UnsafeRow can't be
+  // A SafeProjection to turn UnsafeRow into GenericInternalRow, because UnsafeRow can't be
   // compared to MutableRow (aggregation buffer) directly.
   private[this] val safeProj: Projection = FromUnsafeProjection(valueAttributes.map(_.dataType))
 
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/udaf.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/udaf.scala
index 4ceb710f4b..b047bc0641 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/udaf.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/udaf.scala
@@ -202,7 +202,7 @@ sealed trait BufferSetterGetterUtils {
 }
 
 /**
- * A Mutable [[Row]] representing an mutable aggregation buffer.
+ * A Mutable [[Row]] representing a mutable aggregation buffer.
  */
 private[sql] class MutableAggregationBufferImpl (
     schema: StructType,
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/GenerateColumnAccessor.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/GenerateColumnAccessor.scala
index 1041bab9d5..7a14879b8b 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/GenerateColumnAccessor.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/GenerateColumnAccessor.scala
@@ -58,7 +58,7 @@ class MutableUnsafeRow(val writer: UnsafeRowWriter) extends GenericMutableRow(nu
 }
 
 /**
- * Generates bytecode for an [[ColumnarIterator]] for columnar cache.
+ * Generates bytecode for a [[ColumnarIterator]] for columnar cache.
  */
 object GenerateColumnAccessor extends CodeGenerator[Seq[DataType], ColumnarIterator] with Logging {
 
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileSourceStrategy.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileSourceStrategy.scala
index 350508c1d9..7503285ee2 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileSourceStrategy.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileSourceStrategy.scala
@@ -41,7 +41,7 @@ import org.apache.spark.sql.execution.SparkPlan
  *    is only done on top level columns, but formats should support pruning of nested columns as
  *    well.
  *  - Construct a reader function by passing filters and the schema into the FileFormat.
- *  - Using an partition pruning predicates, enumerate the list of files that should be read.
+ *  - Using a partition pruning predicates, enumerate the list of files that should be read.
  *  - Split the files into tasks and construct a FileScanRDD.
  *  - Add any projection or filters that must be evaluated after the scan.
  *
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JacksonParser.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JacksonParser.scala
index aeee2600a1..733fcbfea1 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JacksonParser.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JacksonParser.scala
@@ -50,7 +50,7 @@ object JacksonParser extends Logging {
 
   /**
    * Parse the current token (and related children) according to a desired schema
-   * This is an wrapper for the method `convertField()` to handle a row wrapped
+   * This is a wrapper for the method `convertField()` to handle a row wrapped
    * with an array.
    */
   def convertRootField(
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/CatalystRowConverter.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/CatalystRowConverter.scala
index 6bf82bee67..85b0bc17ed 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/CatalystRowConverter.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/CatalystRowConverter.scala
@@ -68,7 +68,7 @@ private[parquet] trait HasParentContainerUpdater {
 }
 
 /**
- * A convenient converter class for Parquet group types with an [[HasParentContainerUpdater]].
+ * A convenient converter class for Parquet group types with a [[HasParentContainerUpdater]].
  */
 private[parquet] abstract class CatalystGroupConverter(val updater: ParentContainerUpdater)
   extends GroupConverter with HasParentContainerUpdater
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 fb60d68f98..2ea6ee38a9 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
@@ -47,10 +47,10 @@ import org.apache.spark.sql.execution.{ShuffledRowRDD, SparkPlan}
  *    partitions.
  *
  * The workflow of this coordinator is described as follows:
- *  - Before the execution of a [[SparkPlan]], for an [[ShuffleExchange]] operator,
+ *  - Before the execution of a [[SparkPlan]], for a [[ShuffleExchange]] operator,
  *    if an [[ExchangeCoordinator]] is assigned to it, it registers itself to this coordinator.
  *    This happens in the `doPrepare` method.
- *  - Once we start to execute a physical plan, an [[ShuffleExchange]] registered to this
+ *  - Once we start to execute a physical plan, a [[ShuffleExchange]] registered to this
  *    coordinator will call `postShuffleRDD` to get its corresponding post-shuffle
  *    [[ShuffledRowRDD]].
  *    If this coordinator has made the decision on how to shuffle data, this [[ShuffleExchange]]
@@ -61,7 +61,7 @@ import org.apache.spark.sql.execution.{ShuffledRowRDD, SparkPlan}
  *    post-shuffle partitions and pack multiple pre-shuffle partitions with continuous indices
  *    to a single post-shuffle partition whenever necessary.
  *  - Finally, this coordinator will create post-shuffle [[ShuffledRowRDD]]s for all registered
- *    [[ShuffleExchange]]s. So, when an [[ShuffleExchange]] calls `postShuffleRDD`, this coordinator
+ *    [[ShuffleExchange]]s. So, when a [[ShuffleExchange]] calls `postShuffleRDD`, this coordinator
  *    can lookup the corresponding [[RDD]].
  *
  * The strategy used to determine the number of post-shuffle partitions is described as follows.
@@ -98,8 +98,8 @@ private[sql] class ExchangeCoordinator(
   @volatile private[this] var estimated: Boolean = false
 
   /**
-   * Registers an [[ShuffleExchange]] operator to this coordinator. This method is only allowed to
-   * be called in the `doPrepare` method of an [[ShuffleExchange]] operator.
+   * Registers a [[ShuffleExchange]] operator to this coordinator. This method is only allowed to
+   * be called in the `doPrepare` method of a [[ShuffleExchange]] operator.
    */
   @GuardedBy("this")
   def registerExchange(exchange: ShuffleExchange): Unit = synchronized {
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala
index f0efa52c3d..32f0bc5bf9 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala
@@ -30,7 +30,7 @@ import org.apache.spark.sql.execution.metric.{SQLMetric, SQLMetrics}
 import org.apache.spark.util.collection.BitSet
 
 /**
- * Performs an sort merge join of two child relations.
+ * Performs a sort merge join of two child relations.
  */
 case class SortMergeJoinExec(
     leftKeys: Seq[Expression],
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/r/MapPartitionsRWrapper.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/r/MapPartitionsRWrapper.scala
index dc6f2ef371..6c76328c74 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/r/MapPartitionsRWrapper.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/r/MapPartitionsRWrapper.scala
@@ -40,7 +40,7 @@ private[sql] case class MapPartitionsRWrapper(
 
     val (newIter, deserializer, colNames) =
       if (!isSerializedRData) {
-        // Serialize each row into an byte array that can be deserialized in the R worker
+        // Serialize each row into a byte array that can be deserialized in the R worker
         (iter.asInstanceOf[Iterator[Row]].map {row => rowToRBytes(row)},
          SerializationFormats.ROW, inputSchema.fieldNames)
       } else {
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/expressions/udaf.scala b/sql/core/src/main/scala/org/apache/spark/sql/expressions/udaf.scala
index 48925910ac..eac658c617 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/expressions/udaf.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/expressions/udaf.scala
@@ -133,7 +133,7 @@ abstract class UserDefinedAggregateFunction extends Serializable {
 
 /**
  * :: Experimental ::
- * A [[Row]] representing an mutable aggregation buffer.
+ * A [[Row]] representing a mutable aggregation buffer.
  *
  * This is not meant to be extended outside of Spark.
  */
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/internal/SharedState.scala b/sql/core/src/main/scala/org/apache/spark/sql/internal/SharedState.scala
index 9f6137d6e3..0d6f98416b 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/internal/SharedState.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/internal/SharedState.scala
@@ -52,7 +52,7 @@ private[sql] class SharedState(val sparkContext: SparkContext) {
     org.apache.spark.util.Utils.getContextOrSparkClassLoader)
 
   /**
-   * Create a SQLListener then add it into SparkContext, and create an SQLTab if there is SparkUI.
+   * Create a SQLListener then add it into SparkContext, and create a SQLTab if there is SparkUI.
    */
   private def createListenerAndUI(sc: SparkContext): SQLListener = {
     if (SparkSession.sqlListener.get() == null) {
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/streaming/ContinuousQuery.scala b/sql/core/src/main/scala/org/apache/spark/sql/streaming/ContinuousQuery.scala
index 451cfd85e3..3bbb0b8a88 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/streaming/ContinuousQuery.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/streaming/ContinuousQuery.scala
@@ -93,7 +93,7 @@ trait ContinuousQuery {
   def awaitTermination(timeoutMs: Long): Boolean
 
   /**
-   * Blocks until all available data in the source has been processed an committed to the sink.
+   * Blocks until all available data in the source has been processed and committed to the sink.
    * This method is intended for testing. Note that in the case of continually arriving data, this
    * method may block forever. Additionally, this method is only guaranteed to block until data that
    * has been synchronously appended data to a [[org.apache.spark.sql.execution.streaming.Source]]
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClient.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClient.scala
index befdda1621..5f89696918 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClient.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClient.scala
@@ -218,7 +218,7 @@ private[hive] trait HiveClient {
   /** Create a function in an existing database. */
   def createFunction(db: String, func: CatalogFunction): Unit
 
-  /** Drop an existing function an the database. */
+  /** Drop an existing function in the database. */
   def dropFunction(db: String, name: String): Unit
 
   /** Rename an existing function in the database. */
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileOperator.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileOperator.scala
index 0589c8ece3..f5db73b715 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileOperator.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileOperator.scala
@@ -30,7 +30,7 @@ import org.apache.spark.sql.types.StructType
 private[orc] object OrcFileOperator extends Logging {
   /**
    * Retrieves an ORC file reader from a given path.  The path can point to either a directory or a
-   * single ORC file.  If it points to an directory, it picks any non-empty ORC file within that
+   * single ORC file.  If it points to a directory, it picks any non-empty ORC file within that
    * directory.
    *
    * The reader returned by this method is mainly used for two purposes:
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveComparisonTest.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveComparisonTest.scala
index 65d53debd6..a7652143a4 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveComparisonTest.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveComparisonTest.scala
@@ -37,7 +37,7 @@ import org.apache.spark.sql.hive.test.{TestHive, TestHiveQueryExecution}
  * Allows the creations of tests that execute the same query against both hive
  * and catalyst, comparing the results.
  *
- * The "golden" results from Hive are cached in an retrieved both from the classpath and
+ * The "golden" results from Hive are cached in and retrieved both from the classpath and
  * [[answerCache]] to speed up testing.
  *
  * See the documentation of public vals in this class for information on how test execution can be