[SPARK-12046][DOC] Fixes various ScalaDoc/JavaDoc issues

liancheng · yhuai · commit 843a31afbdee · 2015-12-01T10:50:28.000-08:00
This PR backports PR apache#10039 to master Author: Cheng Lian <lian@databricks.com> Closes apache#10063 from liancheng/spark-12046.doc-fix.master. (cherry picked from commit 69dbe6b) Signed-off-by: Yin Huai <yhuai@databricks.com>
diff --git a/core/src/main/java/org/apache/spark/api/java/function/Function4.java b/core/src/main/java/org/apache/spark/api/java/function/Function4.java
@@ -23,5 +23,5 @@
  * A four-argument function that takes arguments of type T1, T2, T3 and T4 and returns an R.
  */
 public interface Function4<T1, T2, T3, T4, R> extends Serializable {
-  public R call(T1 v1, T2 v2, T3 v3, T4 v4) throws Exception;
+  R call(T1 v1, T2 v2, T3 v3, T4 v4) throws Exception;
 }
diff --git a/core/src/main/java/org/apache/spark/api/java/function/VoidFunction.java b/core/src/main/java/org/apache/spark/api/java/function/VoidFunction.java
@@ -23,5 +23,5 @@
  * A function with no return value.
  */
 public interface VoidFunction<T> extends Serializable {
-  public void call(T t) throws Exception;
+  void call(T t) throws Exception;
 }
diff --git a/core/src/main/java/org/apache/spark/api/java/function/VoidFunction2.java b/core/src/main/java/org/apache/spark/api/java/function/VoidFunction2.java
@@ -23,5 +23,5 @@
  * A two-argument function that takes arguments of type T1 and T2 with no return value.
  */
 public interface VoidFunction2<T1, T2> extends Serializable {
-  public void call(T1 v1, T2 v2) throws Exception;
+  void call(T1 v1, T2 v2) throws Exception;
 }
diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala b/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala
@@ -215,13 +215,13 @@ class JavaPairRDD[K, V](val rdd: RDD[(K, V)])
   /**
    * Generic function to combine the elements for each key using a custom set of aggregation
    * functions. Turns a JavaPairRDD[(K, V)] into a result of type JavaPairRDD[(K, C)], for a
-   * "combined type" C * Note that V and C can be different -- for example, one might group an
+   * "combined type" C. Note that V and C can be different -- for example, one might group an
    * RDD of type (Int, Int) into an RDD of type (Int, List[Int]). Users provide three
    * functions:
    *
-   * - `createCombiner`, which turns a V into a C (e.g., creates a one-element list)
-   * - `mergeValue`, to merge a V into a C (e.g., adds it to the end of a list)
-   * - `mergeCombiners`, to combine two C's into a single one.
+   *  - `createCombiner`, which turns a V into a C (e.g., creates a one-element list)
+   *  - `mergeValue`, to merge a V into a C (e.g., adds it to the end of a list)
+   *  - `mergeCombiners`, to combine two C's into a single one.
    *
    * In addition, users can control the partitioning of the output RDD, the serializer that is use
    * for the shuffle, and whether to perform map-side aggregation (if a mapper can produce multiple
@@ -247,13 +247,13 @@ class JavaPairRDD[K, V](val rdd: RDD[(K, V)])
   /**
    * Generic function to combine the elements for each key using a custom set of aggregation
    * functions. Turns a JavaPairRDD[(K, V)] into a result of type JavaPairRDD[(K, C)], for a
-   * "combined type" C * Note that V and C can be different -- for example, one might group an
+   * "combined type" C. Note that V and C can be different -- for example, one might group an
    * RDD of type (Int, Int) into an RDD of type (Int, List[Int]). Users provide three
    * functions:
    *
-   * - `createCombiner`, which turns a V into a C (e.g., creates a one-element list)
-   * - `mergeValue`, to merge a V into a C (e.g., adds it to the end of a list)
-   * - `mergeCombiners`, to combine two C's into a single one.
+   *  - `createCombiner`, which turns a V into a C (e.g., creates a one-element list)
+   *  - `mergeValue`, to merge a V into a C (e.g., adds it to the end of a list)
+   *  - `mergeCombiners`, to combine two C's into a single one.
    *
    * In addition, users can control the partitioning of the output RDD. This method automatically
    * uses map-side aggregation in shuffling the RDD.
diff --git a/core/src/main/scala/org/apache/spark/memory/package.scala b/core/src/main/scala/org/apache/spark/memory/package.scala
@@ -21,13 +21,13 @@ package org.apache.spark
  * This package implements Spark's memory management system. This system consists of two main
  * components, a JVM-wide memory manager and a per-task manager:
  *
- * - [[org.apache.spark.memory.MemoryManager]] manages Spark's overall memory usage within a JVM.
- *   This component implements the policies for dividing the available memory across tasks and for
- *   allocating memory between storage (memory used caching and data transfer) and execution (memory
- *   used by computations, such as shuffles, joins, sorts, and aggregations).
- * - [[org.apache.spark.memory.TaskMemoryManager]] manages the memory allocated by individual tasks.
- *   Tasks interact with TaskMemoryManager and never directly interact with the JVM-wide
- *   MemoryManager.
+ *  - [[org.apache.spark.memory.MemoryManager]] manages Spark's overall memory usage within a JVM.
+ *    This component implements the policies for dividing the available memory across tasks and for
+ *    allocating memory between storage (memory used caching and data transfer) and execution
+ *    (memory used by computations, such as shuffles, joins, sorts, and aggregations).
+ *  - [[org.apache.spark.memory.TaskMemoryManager]] manages the memory allocated by individual
+ *    tasks. Tasks interact with TaskMemoryManager and never directly interact with the JVM-wide
+ *    MemoryManager.
  *
  * Internally, each of these components have additional abstractions for memory bookkeeping:
  *
diff --git a/core/src/main/scala/org/apache/spark/rdd/CoGroupedRDD.scala b/core/src/main/scala/org/apache/spark/rdd/CoGroupedRDD.scala
@@ -70,7 +70,7 @@ private[spark] class CoGroupPartition(
  *
  * Note: This is an internal API. We recommend users use RDD.cogroup(...) instead of
  * instantiating this directly.
-
+ *
  * @param rdds parent RDDs.
  * @param part partitioner used to partition the shuffle output
  */
diff --git a/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala b/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala
@@ -65,9 +65,9 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])
    * Note that V and C can be different -- for example, one might group an RDD of type
    * (Int, Int) into an RDD of type (Int, Seq[Int]). Users provide three functions:
    *
-   * - `createCombiner`, which turns a V into a C (e.g., creates a one-element list)
-   * - `mergeValue`, to merge a V into a C (e.g., adds it to the end of a list)
-   * - `mergeCombiners`, to combine two C's into a single one.
+   *  - `createCombiner`, which turns a V into a C (e.g., creates a one-element list)
+   *  - `mergeValue`, to merge a V into a C (e.g., adds it to the end of a list)
+   *  - `mergeCombiners`, to combine two C's into a single one.
    *
    * In addition, users can control the partitioning of the output RDD, and whether to perform
    * map-side aggregation (if a mapper can produce multiple items with the same key).
diff --git a/core/src/main/scala/org/apache/spark/rdd/ShuffledRDD.scala b/core/src/main/scala/org/apache/spark/rdd/ShuffledRDD.scala
@@ -86,7 +86,7 @@ class ShuffledRDD[K: ClassTag, V: ClassTag, C: ClassTag](
     Array.tabulate[Partition](part.numPartitions)(i => new ShuffledRDDPartition(i))
   }
 
-  override def getPreferredLocations(partition: Partition): Seq[String] = {
+  override protected def getPreferredLocations(partition: Partition): Seq[String] = {
     val tracker = SparkEnv.get.mapOutputTracker.asInstanceOf[MapOutputTrackerMaster]
     val dep = dependencies.head.asInstanceOf[ShuffleDependency[K, V, C]]
     tracker.getPreferredLocationsForShuffle(dep, partition.index)
diff --git a/core/src/main/scala/org/apache/spark/scheduler/Task.scala b/core/src/main/scala/org/apache/spark/scheduler/Task.scala
@@ -33,8 +33,9 @@ import org.apache.spark.util.Utils
 
 /**
  * A unit of execution. We have two kinds of Task's in Spark:
- * - [[org.apache.spark.scheduler.ShuffleMapTask]]
- * - [[org.apache.spark.scheduler.ResultTask]]
+ *
+ *  - [[org.apache.spark.scheduler.ShuffleMapTask]]
+ *  - [[org.apache.spark.scheduler.ResultTask]]
  *
  * A Spark job consists of one or more stages. The very last stage in a job consists of multiple
  * ResultTasks, while earlier stages consist of ShuffleMapTasks. A ResultTask executes the task
diff --git a/core/src/main/scala/org/apache/spark/serializer/SerializationDebugger.scala b/core/src/main/scala/org/apache/spark/serializer/SerializationDebugger.scala
@@ -53,12 +53,13 @@ private[spark] object SerializationDebugger extends Logging {
   /**
    * Find the path leading to a not serializable object. This method is modeled after OpenJDK's
    * serialization mechanism, and handles the following cases:
-   * - primitives
-   * - arrays of primitives
-   * - arrays of non-primitive objects
-   * - Serializable objects
-   * - Externalizable objects
-   * - writeReplace
+   *
+   *  - primitives
+   *  - arrays of primitives
+   *  - arrays of non-primitive objects
+   *  - Serializable objects
+   *  - Externalizable objects
+   *  - writeReplace
    *
    * It does not yet handle writeObject override, but that shouldn't be too hard to do either.
    */
diff --git a/core/src/main/scala/org/apache/spark/util/Vector.scala b/core/src/main/scala/org/apache/spark/util/Vector.scala
@@ -122,6 +122,7 @@ class Vector(val elements: Array[Double]) extends Serializable {
   override def toString: String = elements.mkString("(", ", ", ")")
 }
 
+@deprecated("Use Vectors.dense from Spark's mllib.linalg package instead.", "1.0.0")
 object Vector {
   def apply(elements: Array[Double]): Vector = new Vector(elements)
 
diff --git a/core/src/main/scala/org/apache/spark/util/collection/ExternalSorter.scala b/core/src/main/scala/org/apache/spark/util/collection/ExternalSorter.scala
@@ -67,24 +67,24 @@ import org.apache.spark.storage.{BlockId, DiskBlockObjectWriter}
  *
  * At a high level, this class works internally as follows:
  *
- * - We repeatedly fill up buffers of in-memory data, using either a PartitionedAppendOnlyMap if
- *   we want to combine by key, or a PartitionedPairBuffer if we don't.
- *   Inside these buffers, we sort elements by partition ID and then possibly also by key.
- *   To avoid calling the partitioner multiple times with each key, we store the partition ID
- *   alongside each record.
+ *  - We repeatedly fill up buffers of in-memory data, using either a PartitionedAppendOnlyMap if
+ *    we want to combine by key, or a PartitionedPairBuffer if we don't.
+ *    Inside these buffers, we sort elements by partition ID and then possibly also by key.
+ *    To avoid calling the partitioner multiple times with each key, we store the partition ID
+ *    alongside each record.
  *
- * - When each buffer reaches our memory limit, we spill it to a file. This file is sorted first
- *   by partition ID and possibly second by key or by hash code of the key, if we want to do
- *   aggregation. For each file, we track how many objects were in each partition in memory, so we
- *   don't have to write out the partition ID for every element.
+ *  - When each buffer reaches our memory limit, we spill it to a file. This file is sorted first
+ *    by partition ID and possibly second by key or by hash code of the key, if we want to do
+ *    aggregation. For each file, we track how many objects were in each partition in memory, so we
+ *    don't have to write out the partition ID for every element.
  *
- * - When the user requests an iterator or file output, the spilled files are merged, along with
- *   any remaining in-memory data, using the same sort order defined above (unless both sorting
- *   and aggregation are disabled). If we need to aggregate by key, we either use a total ordering
- *   from the ordering parameter, or read the keys with the same hash code and compare them with
- *   each other for equality to merge values.
+ *  - When the user requests an iterator or file output, the spilled files are merged, along with
+ *    any remaining in-memory data, using the same sort order defined above (unless both sorting
+ *    and aggregation are disabled). If we need to aggregate by key, we either use a total ordering
+ *    from the ordering parameter, or read the keys with the same hash code and compare them with
+ *    each other for equality to merge values.
  *
- * - Users are expected to call stop() at the end to delete all the intermediate files.
+ *  - Users are expected to call stop() at the end to delete all the intermediate files.
  */
 private[spark] class ExternalSorter[K, V, C](
     context: TaskContext,
diff --git a/core/src/main/scala/org/apache/spark/util/collection/WritablePartitionedPairCollection.scala b/core/src/main/scala/org/apache/spark/util/collection/WritablePartitionedPairCollection.scala
@@ -23,9 +23,10 @@ import org.apache.spark.storage.DiskBlockObjectWriter
 
 /**
  * A common interface for size-tracking collections of key-value pairs that
- * - Have an associated partition for each key-value pair.
- * - Support a memory-efficient sorted iterator
- * - Support a WritablePartitionedIterator for writing the contents directly as bytes.
+ *
+ *  - Have an associated partition for each key-value pair.
+ *  - Support a memory-efficient sorted iterator
+ *  - Support a WritablePartitionedIterator for writing the contents directly as bytes.
  */
 private[spark] trait WritablePartitionedPairCollection[K, V] {
   /**
diff --git a/extras/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisReceiver.scala b/extras/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisReceiver.scala
@@ -46,17 +46,18 @@ case class SerializableAWSCredentials(accessKeyId: String, secretKey: String)
  * https://github.com/awslabs/amazon-kinesis-client
  *
  * The way this Receiver works is as follows:
- * - The receiver starts a KCL Worker, which is essentially runs a threadpool of multiple
- *   KinesisRecordProcessor
- * - Each KinesisRecordProcessor receives data from a Kinesis shard in batches. Each batch is
- *   inserted into a Block Generator, and the corresponding range of sequence numbers is recorded.
- * - When the block generator defines a block, then the recorded sequence number ranges that were
- *   inserted into the block are recorded separately for being used later.
- * - When the block is ready to be pushed, the block is pushed and the ranges are reported as
- *   metadata of the block. In addition, the ranges are used to find out the latest sequence
- *   number for each shard that can be checkpointed through the DynamoDB.
- * - Periodically, each KinesisRecordProcessor checkpoints the latest successfully stored sequence
- *   number for it own shard.
+ *
+ *  - The receiver starts a KCL Worker, which is essentially runs a threadpool of multiple
+ *    KinesisRecordProcessor
+ *  - Each KinesisRecordProcessor receives data from a Kinesis shard in batches. Each batch is
+ *    inserted into a Block Generator, and the corresponding range of sequence numbers is recorded.
+ *  - When the block generator defines a block, then the recorded sequence number ranges that were
+ *    inserted into the block are recorded separately for being used later.
+ *  - When the block is ready to be pushed, the block is pushed and the ranges are reported as
+ *    metadata of the block. In addition, the ranges are used to find out the latest sequence
+ *    number for each shard that can be checkpointed through the DynamoDB.
+ *  - Periodically, each KinesisRecordProcessor checkpoints the latest successfully stored sequence
+ *    number for it own shard.
  *
  * @param streamName   Kinesis stream name
  * @param endpointUrl  Url of Kinesis service (e.g., https://kinesis.us-east-1.amazonaws.com)
diff --git a/extras/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisUtils.scala b/extras/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisUtils.scala
@@ -226,12 +226,13 @@ object KinesisUtils {
    * This uses the Kinesis Client Library (KCL) to pull messages from Kinesis.
    *
    * Note:
-   * - The AWS credentials will be discovered using the DefaultAWSCredentialsProviderChain
-   *   on the workers. See AWS documentation to understand how DefaultAWSCredentialsProviderChain
-   *   gets AWS credentials.
-   * - The region of the `endpointUrl` will be used for DynamoDB and CloudWatch.
-   * - The Kinesis application name used by the Kinesis Client Library (KCL) will be the app name in
-   *   [[org.apache.spark.SparkConf]].
+   *
+   *  - The AWS credentials will be discovered using the DefaultAWSCredentialsProviderChain
+   *    on the workers. See AWS documentation to understand how DefaultAWSCredentialsProviderChain
+   *    gets AWS credentials.
+   *  - The region of the `endpointUrl` will be used for DynamoDB and CloudWatch.
+   *  - The Kinesis application name used by the Kinesis Client Library (KCL) will be the app name
+   *    in [[org.apache.spark.SparkConf]].
    *
    * @param ssc StreamingContext object
    * @param streamName   Kinesis stream name
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala b/mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala
@@ -81,11 +81,13 @@ class GradientDescent private[spark] (private var gradient: Gradient, private va
    * Set the convergence tolerance. Default 0.001
    * convergenceTol is a condition which decides iteration termination.
    * The end of iteration is decided based on below logic.
-   * - If the norm of the new solution vector is >1, the diff of solution vectors
-   *   is compared to relative tolerance which means normalizing by the norm of
-   *   the new solution vector.
-   * - If the norm of the new solution vector is <=1, the diff of solution vectors
-   *   is compared to absolute tolerance which is not normalizing.
+   *
+   *  - If the norm of the new solution vector is >1, the diff of solution vectors
+   *    is compared to relative tolerance which means normalizing by the norm of
+   *    the new solution vector.
+   *  - If the norm of the new solution vector is <=1, the diff of solution vectors
+   *    is compared to absolute tolerance which is not normalizing.
+   *
    * Must be between 0.0 and 1.0 inclusively.
    */
   def setConvergenceTol(tolerance: Double): this.type = {
diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala
@@ -535,6 +535,8 @@ object Unidoc {
       .map(_.filterNot(_.getName.contains("$")))
       .map(_.filterNot(_.getCanonicalPath.contains("akka")))
       .map(_.filterNot(_.getCanonicalPath.contains("org/apache/spark/deploy")))
+      .map(_.filterNot(_.getCanonicalPath.contains("org/apache/spark/examples")))
+      .map(_.filterNot(_.getCanonicalPath.contains("org/apache/spark/memory")))
       .map(_.filterNot(_.getCanonicalPath.contains("org/apache/spark/network")))
       .map(_.filterNot(_.getCanonicalPath.contains("org/apache/spark/shuffle")))
       .map(_.filterNot(_.getCanonicalPath.contains("org/apache/spark/executor")))
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/Column.scala b/sql/core/src/main/scala/org/apache/spark/sql/Column.scala
@@ -136,11 +136,12 @@ class Column(protected[sql] val expr: Expression) extends Logging {
   /**
    * Extracts a value or values from a complex type.
    * The following types of extraction are supported:
-   * - Given an Array, an integer ordinal can be used to retrieve a single value.
-   * - Given a Map, a key of the correct type can be used to retrieve an individual value.
-   * - Given a Struct, a string fieldName can be used to extract that field.
-   * - Given an Array of Structs, a string fieldName can be used to extract filed
-   *   of every struct in that array, and return an Array of fields
+   *
+   *  - Given an Array, an integer ordinal can be used to retrieve a single value.
+   *  - Given a Map, a key of the correct type can be used to retrieve an individual value.
+   *  - Given a Struct, a string fieldName can be used to extract that field.
+   *  - Given an Array of Structs, a string fieldName can be used to extract filed
+   *    of every struct in that array, and return an Array of fields
    *
    * @group expr_ops
    * @since 1.4.0
diff --git a/streaming/src/main/scala/org/apache/spark/streaming/StreamingContext.scala b/streaming/src/main/scala/org/apache/spark/streaming/StreamingContext.scala
@@ -574,11 +574,12 @@ class StreamingContext private[streaming] (
    * :: DeveloperApi ::
    *
    * Return the current state of the context. The context can be in three possible states -
-   * - StreamingContextState.INTIALIZED - The context has been created, but not been started yet.
-   *   Input DStreams, transformations and output operations can be created on the context.
-   * - StreamingContextState.ACTIVE - The context has been started, and been not stopped.
-   *   Input DStreams, transformations and output operations cannot be created on the context.
-   * - StreamingContextState.STOPPED - The context has been stopped and cannot be used any more.
+   *
+   *  - StreamingContextState.INTIALIZED - The context has been created, but not been started yet.
+   *    Input DStreams, transformations and output operations can be created on the context.
+   *  - StreamingContextState.ACTIVE - The context has been started, and been not stopped.
+   *    Input DStreams, transformations and output operations cannot be created on the context.
+   *  - StreamingContextState.STOPPED - The context has been stopped and cannot be used any more.
    */
   @DeveloperApi
   def getState(): StreamingContextState = synchronized {
diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/FileInputDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/FileInputDStream.scala
diff --git a/streaming/src/main/scala/org/apache/spark/streaming/receiver/BlockGenerator.scala b/streaming/src/main/scala/org/apache/spark/streaming/receiver/BlockGenerator.scala
diff --git a/streaming/src/main/scala/org/apache/spark/streaming/scheduler/ReceiverSchedulingPolicy.scala b/streaming/src/main/scala/org/apache/spark/streaming/scheduler/ReceiverSchedulingPolicy.scala
diff --git a/streaming/src/main/scala/org/apache/spark/streaming/util/FileBasedWriteAheadLog.scala b/streaming/src/main/scala/org/apache/spark/streaming/util/FileBasedWriteAheadLog.scala
diff --git a/streaming/src/main/scala/org/apache/spark/streaming/util/RecurringTimer.scala b/streaming/src/main/scala/org/apache/spark/streaming/util/RecurringTimer.scala
diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala b/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala

Original file line number	Diff line number	Diff line change
`@@ -23,5 +23,5 @@`
`23`	`23`	`* A four-argument function that takes arguments of type T1, T2, T3 and T4 and returns an R.`
`24`	`24`	`*/`
`25`	`25`	`public interface Function4<T1, T2, T3, T4, R> extends Serializable {`
`26`		`- public R call(T1 v1, T2 v2, T3 v3, T4 v4) throws Exception;`
	`26`	`+ R call(T1 v1, T2 v2, T3 v3, T4 v4) throws Exception;`
`27`	`27`	`}`
Original file line number	Diff line number	Diff line change
`@@ -70,7 +70,7 @@ private[spark] class CoGroupPartition(`
`70`	`70`	`*`
`71`	`71`	`* Note: This is an internal API. We recommend users use RDD.cogroup(...) instead of`
`72`	`72`	`* instantiating this directly.`
`73`		`-`
	`73`	`+ *`
`74`	`74`	`* @param rdds parent RDDs.`
`75`	`75`	`* @param part partitioner used to partition the shuffle output`
`76`	`76`	`*/`
Original file line number	Diff line number	Diff line change
`@@ -65,9 +65,9 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])`
`65`	`65`	`* Note that V and C can be different -- for example, one might group an RDD of type`
`66`	`66`	`* (Int, Int) into an RDD of type (Int, Seq[Int]). Users provide three functions:`
`67`	`67`	`*`
`68`		- * - `createCombiner`, which turns a V into a C (e.g., creates a one-element list)
`69`		- * - `mergeValue`, to merge a V into a C (e.g., adds it to the end of a list)
`70`		- * - `mergeCombiners`, to combine two C's into a single one.
	`68`	+ * - `createCombiner`, which turns a V into a C (e.g., creates a one-element list)
	`69`	+ * - `mergeValue`, to merge a V into a C (e.g., adds it to the end of a list)
	`70`	+ * - `mergeCombiners`, to combine two C's into a single one.
`71`	`71`	`*`
`72`	`72`	`* In addition, users can control the partitioning of the output RDD, and whether to perform`
`73`	`73`	`* map-side aggregation (if a mapper can produce multiple items with the same key).`
Original file line number	Diff line number	Diff line change
`@@ -86,7 +86,7 @@ class ShuffledRDD[K: ClassTag, V: ClassTag, C: ClassTag](`
`86`	`86`	`Array.tabulate[Partition](part.numPartitions)(i => new ShuffledRDDPartition(i))`
`87`	`87`	`}`
`88`	`88`
`89`		`- override def getPreferredLocations(partition: Partition): Seq[String] = {`
	`89`	`+ override protected def getPreferredLocations(partition: Partition): Seq[String] = {`
`90`	`90`	`val tracker = SparkEnv.get.mapOutputTracker.asInstanceOf[MapOutputTrackerMaster]`
`91`	`91`	`val dep = dependencies.head.asInstanceOf[ShuffleDependency[K, V, C]]`
`92`	`92`	`tracker.getPreferredLocationsForShuffle(dep, partition.index)`