1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
|
/*
* 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.language.implicitConversions
import scala.reflect.ClassTag
import org.apache.spark._
import org.apache.spark.api.java.function.{Function => JFunction}
import org.apache.spark.rdd.RDD
import org.apache.spark.storage.StorageLevel
class JavaRDD[T](val rdd: RDD[T])(implicit val classTag: ClassTag[T])
extends JavaRDDLike[T, JavaRDD[T]] {
override def wrapRDD(rdd: RDD[T]): JavaRDD[T] = JavaRDD.fromRDD(rdd)
// Common RDD functions
/** Persist this RDD with the default storage level (`MEMORY_ONLY`). */
def cache(): JavaRDD[T] = wrapRDD(rdd.cache())
/**
* Set this RDD's storage level to persist its values across operations after the first time
* it is computed. This can only be used to assign a new storage level if the RDD does not
* have a storage level set yet..
*/
def persist(newLevel: StorageLevel): JavaRDD[T] = wrapRDD(rdd.persist(newLevel))
/**
* Mark the RDD as non-persistent, and remove all blocks for it from memory and disk.
* This method blocks until all blocks are deleted.
*/
def unpersist(): JavaRDD[T] = wrapRDD(rdd.unpersist())
/**
* Mark the RDD as non-persistent, and remove all blocks for it from memory and disk.
*
* @param blocking Whether to block until all blocks are deleted.
*/
def unpersist(blocking: Boolean): JavaRDD[T] = wrapRDD(rdd.unpersist(blocking))
// Transformations (return a new RDD)
/**
* Return a new RDD containing the distinct elements in this RDD.
*/
def distinct(): JavaRDD[T] = wrapRDD(rdd.distinct())
/**
* Return a new RDD containing the distinct elements in this RDD.
*/
def distinct(numPartitions: Int): JavaRDD[T] = wrapRDD(rdd.distinct(numPartitions))
/**
* Return a new RDD containing only the elements that satisfy a predicate.
*/
def filter(f: JFunction[T, java.lang.Boolean]): JavaRDD[T] =
wrapRDD(rdd.filter((x => f.call(x).booleanValue())))
/**
* Return a new RDD that is reduced into `numPartitions` partitions.
*/
def coalesce(numPartitions: Int): JavaRDD[T] = rdd.coalesce(numPartitions)
/**
* Return a new RDD that is reduced into `numPartitions` partitions.
*/
def coalesce(numPartitions: Int, shuffle: Boolean): JavaRDD[T] =
rdd.coalesce(numPartitions, shuffle)
/**
* Return a new RDD that has exactly numPartitions partitions.
*
* Can increase or decrease the level of parallelism in this RDD. Internally, this uses
* a shuffle to redistribute data.
*
* If you are decreasing the number of partitions in this RDD, consider using `coalesce`,
* which can avoid performing a shuffle.
*/
def repartition(numPartitions: Int): JavaRDD[T] = rdd.repartition(numPartitions)
/**
* Return a sampled subset of this RDD.
*/
def sample(withReplacement: Boolean, fraction: Double, seed: Int): JavaRDD[T] =
wrapRDD(rdd.sample(withReplacement, fraction, seed))
/**
* Return the union of this RDD and another one. Any identical elements will appear multiple
* times (use `.distinct()` to eliminate them).
*/
def union(other: JavaRDD[T]): JavaRDD[T] = wrapRDD(rdd.union(other.rdd))
/**
* Return the intersection of this RDD and another one. The output will not contain any duplicate
* elements, even if the input RDDs did.
*
* Note that this method performs a shuffle internally.
*/
def intersection(other: JavaRDD[T]): JavaRDD[T] = wrapRDD(rdd.intersection(other.rdd))
/**
* Return an RDD with the elements from `this` that are not in `other`.
*
* Uses `this` partitioner/partition size, because even if `other` is huge, the resulting
* RDD will be <= us.
*/
def subtract(other: JavaRDD[T]): JavaRDD[T] = wrapRDD(rdd.subtract(other))
/**
* Return an RDD with the elements from `this` that are not in `other`.
*/
def subtract(other: JavaRDD[T], numPartitions: Int): JavaRDD[T] =
wrapRDD(rdd.subtract(other, numPartitions))
/**
* Return an RDD with the elements from `this` that are not in `other`.
*/
def subtract(other: JavaRDD[T], p: Partitioner): JavaRDD[T] =
wrapRDD(rdd.subtract(other, p))
override def toString = rdd.toString
/** Assign a name to this RDD */
def setName(name: String): JavaRDD[T] = {
rdd.setName(name)
this
}
}
object JavaRDD {
implicit def fromRDD[T: ClassTag](rdd: RDD[T]): JavaRDD[T] = new JavaRDD[T](rdd)
implicit def toRDD[T](rdd: JavaRDD[T]): RDD[T] = rdd.rdd
}
|