-
Notifications
You must be signed in to change notification settings - Fork 28.2k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
SPARK-2028: Expose mapPartitionsWithInputSplit in HadoopRDD
This allows users to gain access to the InputSplit which backs each partition. An alternative solution would have been to have a .withInputSplit() method which returns a new RDD[(InputSplit, (K, V))], but this is confusing because you could not cache this RDD or shuffle it, as InputSplit is not inherently serializable. Author: Aaron Davidson <aaron@databricks.com> Closes #973 from aarondav/hadoop and squashes the following commits: 9c9112b [Aaron Davidson] Add JavaAPISuite test 9942cd7 [Aaron Davidson] Add Java API 1284a3a [Aaron Davidson] SPARK-2028: Expose mapPartitionsWithInputSplit in HadoopRDD
- Loading branch information
Showing
7 changed files
with
222 additions
and
11 deletions.
There are no files selected for viewing
43 changes: 43 additions & 0 deletions
43
core/src/main/scala/org/apache/spark/api/java/JavaHadoopRDD.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,43 @@ | ||
/* | ||
* Licensed to the Apache Software Foundation (ASF) under one or more | ||
* contributor license agreements. See the NOTICE file distributed with | ||
* this work for additional information regarding copyright ownership. | ||
* The ASF licenses this file to You under the Apache License, Version 2.0 | ||
* (the "License"); you may not use this file except in compliance with | ||
* the License. You may obtain a copy of the License at | ||
* | ||
* http://www.apache.org/licenses/LICENSE-2.0 | ||
* | ||
* Unless required by applicable law or agreed to in writing, software | ||
* distributed under the License is distributed on an "AS IS" BASIS, | ||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
* See the License for the specific language governing permissions and | ||
* limitations under the License. | ||
*/ | ||
|
||
package org.apache.spark.api.java | ||
|
||
import scala.collection.JavaConversions._ | ||
import scala.reflect.ClassTag | ||
|
||
import org.apache.hadoop.mapred.InputSplit | ||
|
||
import org.apache.spark.annotation.DeveloperApi | ||
import org.apache.spark.api.java.JavaSparkContext._ | ||
import org.apache.spark.api.java.function.{Function2 => JFunction2} | ||
import org.apache.spark.rdd.HadoopRDD | ||
|
||
@DeveloperApi | ||
class JavaHadoopRDD[K, V](rdd: HadoopRDD[K, V]) | ||
(implicit override val kClassTag: ClassTag[K], implicit override val vClassTag: ClassTag[V]) | ||
extends JavaPairRDD[K, V](rdd) { | ||
|
||
/** Maps over a partition, providing the InputSplit that was used as the base of the partition. */ | ||
@DeveloperApi | ||
def mapPartitionsWithInputSplit[R]( | ||
f: JFunction2[InputSplit, java.util.Iterator[(K, V)], java.util.Iterator[R]], | ||
preservesPartitioning: Boolean = false): JavaRDD[R] = { | ||
new JavaRDD(rdd.mapPartitionsWithInputSplit((a, b) => f.call(a, asJavaIterator(b)), | ||
preservesPartitioning)(fakeClassTag))(fakeClassTag) | ||
} | ||
} |
43 changes: 43 additions & 0 deletions
43
core/src/main/scala/org/apache/spark/api/java/JavaNewHadoopRDD.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,43 @@ | ||
/* | ||
* Licensed to the Apache Software Foundation (ASF) under one or more | ||
* contributor license agreements. See the NOTICE file distributed with | ||
* this work for additional information regarding copyright ownership. | ||
* The ASF licenses this file to You under the Apache License, Version 2.0 | ||
* (the "License"); you may not use this file except in compliance with | ||
* the License. You may obtain a copy of the License at | ||
* | ||
* http://www.apache.org/licenses/LICENSE-2.0 | ||
* | ||
* Unless required by applicable law or agreed to in writing, software | ||
* distributed under the License is distributed on an "AS IS" BASIS, | ||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
* See the License for the specific language governing permissions and | ||
* limitations under the License. | ||
*/ | ||
|
||
package org.apache.spark.api.java | ||
|
||
import scala.collection.JavaConversions._ | ||
import scala.reflect.ClassTag | ||
|
||
import org.apache.hadoop.mapreduce.InputSplit | ||
|
||
import org.apache.spark.annotation.DeveloperApi | ||
import org.apache.spark.api.java.JavaSparkContext._ | ||
import org.apache.spark.api.java.function.{Function2 => JFunction2} | ||
import org.apache.spark.rdd.NewHadoopRDD | ||
|
||
@DeveloperApi | ||
class JavaNewHadoopRDD[K, V](rdd: NewHadoopRDD[K, V]) | ||
(implicit override val kClassTag: ClassTag[K], implicit override val vClassTag: ClassTag[V]) | ||
extends JavaPairRDD[K, V](rdd) { | ||
|
||
/** Maps over a partition, providing the InputSplit that was used as the base of the partition. */ | ||
@DeveloperApi | ||
def mapPartitionsWithInputSplit[R]( | ||
f: JFunction2[InputSplit, java.util.Iterator[(K, V)], java.util.Iterator[R]], | ||
preservesPartitioning: Boolean = false): JavaRDD[R] = { | ||
new JavaRDD(rdd.mapPartitionsWithInputSplit((a, b) => f.call(a, asJavaIterator(b)), | ||
preservesPartitioning)(fakeClassTag))(fakeClassTag) | ||
} | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters