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
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
|
/*
* 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 java.util.{Map => JMap}
import scala.collection.JavaConversions
import scala.collection.JavaConversions._
import scala.reflect.ClassTag
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.mapred.InputFormat
import org.apache.hadoop.mapred.JobConf
import org.apache.hadoop.mapreduce.{InputFormat => NewInputFormat}
import com.google.common.base.Optional
import org.apache.spark._
import org.apache.spark.SparkContext.IntAccumulatorParam
import org.apache.spark.SparkContext.DoubleAccumulatorParam
import org.apache.spark.broadcast.Broadcast
import org.apache.spark.rdd.RDD
import scala.Tuple2
/**
* A Java-friendly version of [[org.apache.spark.SparkContext]] that returns [[org.apache.spark.api.java.JavaRDD]]s and
* works with Java collections instead of Scala ones.
*/
class JavaSparkContext(val sc: SparkContext) extends JavaSparkContextVarargsWorkaround {
/**
* @param conf a [[org.apache.spark.SparkConf]] object specifying Spark parameters
*/
def this(conf: SparkConf) = this(new SparkContext(conf))
/**
* @param master Cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]).
* @param appName A name for your application, to display on the cluster web UI
*/
def this(master: String, appName: String) = this(new SparkContext(master, appName))
/**
* @param master Cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]).
* @param appName A name for your application, to display on the cluster web UI
* @param conf a [[org.apache.spark.SparkConf]] object specifying other Spark parameters
*/
def this(master: String, appName: String, conf: SparkConf) =
this(conf.setMaster(master).setAppName(appName))
/**
* @param master Cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]).
* @param appName A name for your application, to display on the cluster web UI
* @param sparkHome The SPARK_HOME directory on the slave nodes
* @param jarFile JAR file to send to the cluster. This can be a path on the local file system
* or an HDFS, HTTP, HTTPS, or FTP URL.
*/
def this(master: String, appName: String, sparkHome: String, jarFile: String) =
this(new SparkContext(master, appName, sparkHome, Seq(jarFile)))
/**
* @param master Cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]).
* @param appName A name for your application, to display on the cluster web UI
* @param sparkHome The SPARK_HOME directory on the slave nodes
* @param jars Collection of JARs to send to the cluster. These can be paths on the local file
* system or HDFS, HTTP, HTTPS, or FTP URLs.
*/
def this(master: String, appName: String, sparkHome: String, jars: Array[String]) =
this(new SparkContext(master, appName, sparkHome, jars.toSeq))
/**
* @param master Cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]).
* @param appName A name for your application, to display on the cluster web UI
* @param sparkHome The SPARK_HOME directory on the slave nodes
* @param jars Collection of JARs to send to the cluster. These can be paths on the local file
* system or HDFS, HTTP, HTTPS, or FTP URLs.
* @param environment Environment variables to set on worker nodes
*/
def this(master: String, appName: String, sparkHome: String, jars: Array[String],
environment: JMap[String, String]) =
this(new SparkContext(master, appName, sparkHome, jars.toSeq, environment))
private[spark] val env = sc.env
/** Distribute a local Scala collection to form an RDD. */
def parallelize[T](list: java.util.List[T], numSlices: Int): JavaRDD[T] = {
implicit val cm: ClassTag[T] = implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]]
sc.parallelize(JavaConversions.asScalaBuffer(list), numSlices)
}
/** Distribute a local Scala collection to form an RDD. */
def parallelize[T](list: java.util.List[T]): JavaRDD[T] =
parallelize(list, sc.defaultParallelism)
/** Distribute a local Scala collection to form an RDD. */
def parallelizePairs[K, V](list: java.util.List[Tuple2[K, V]], numSlices: Int)
: JavaPairRDD[K, V] = {
implicit val kcm: ClassTag[K] = implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[K]]
implicit val vcm: ClassTag[V] = implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[V]]
JavaPairRDD.fromRDD(sc.parallelize(JavaConversions.asScalaBuffer(list), numSlices))
}
/** Distribute a local Scala collection to form an RDD. */
def parallelizePairs[K, V](list: java.util.List[Tuple2[K, V]]): JavaPairRDD[K, V] =
parallelizePairs(list, sc.defaultParallelism)
/** Distribute a local Scala collection to form an RDD. */
def parallelizeDoubles(list: java.util.List[java.lang.Double], numSlices: Int): JavaDoubleRDD =
JavaDoubleRDD.fromRDD(sc.parallelize(JavaConversions.asScalaBuffer(list).map(_.doubleValue()),
numSlices))
/** Distribute a local Scala collection to form an RDD. */
def parallelizeDoubles(list: java.util.List[java.lang.Double]): JavaDoubleRDD =
parallelizeDoubles(list, sc.defaultParallelism)
/**
* Read a text file from HDFS, a local file system (available on all nodes), or any
* Hadoop-supported file system URI, and return it as an RDD of Strings.
*/
def textFile(path: String): JavaRDD[String] = sc.textFile(path)
/**
* Read a text file from HDFS, a local file system (available on all nodes), or any
* Hadoop-supported file system URI, and return it as an RDD of Strings.
*/
def textFile(path: String, minSplits: Int): JavaRDD[String] = sc.textFile(path, minSplits)
/**Get an RDD for a Hadoop SequenceFile with given key and value types. */
def sequenceFile[K, V](path: String,
keyClass: Class[K],
valueClass: Class[V],
minSplits: Int
): JavaPairRDD[K, V] = {
implicit val kcm: ClassTag[K] = ClassTag(keyClass)
implicit val vcm: ClassTag[V] = ClassTag(valueClass)
new JavaPairRDD(sc.sequenceFile(path, keyClass, valueClass, minSplits))
}
/**Get an RDD for a Hadoop SequenceFile. */
def sequenceFile[K, V](path: String, keyClass: Class[K], valueClass: Class[V]):
JavaPairRDD[K, V] = {
implicit val kcm: ClassTag[K] = ClassTag(keyClass)
implicit val vcm: ClassTag[V] = ClassTag(valueClass)
new JavaPairRDD(sc.sequenceFile(path, keyClass, valueClass))
}
/**
* Load an RDD saved as a SequenceFile containing serialized objects, with NullWritable keys and
* BytesWritable values that contain a serialized partition. This is still an experimental storage
* format and may not be supported exactly as is in future Spark releases. It will also be pretty
* slow if you use the default serializer (Java serialization), though the nice thing about it is
* that there's very little effort required to save arbitrary objects.
*/
def objectFile[T](path: String, minSplits: Int): JavaRDD[T] = {
implicit val cm: ClassTag[T] = implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]]
sc.objectFile(path, minSplits)(cm)
}
/**
* Load an RDD saved as a SequenceFile containing serialized objects, with NullWritable keys and
* BytesWritable values that contain a serialized partition. This is still an experimental storage
* format and may not be supported exactly as is in future Spark releases. It will also be pretty
* slow if you use the default serializer (Java serialization), though the nice thing about it is
* that there's very little effort required to save arbitrary objects.
*/
def objectFile[T](path: String): JavaRDD[T] = {
implicit val cm: ClassTag[T] = implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]]
sc.objectFile(path)(cm)
}
/**
* Get an RDD for a Hadoop-readable dataset from a Hadooop JobConf giving its InputFormat and any
* other necessary info (e.g. file name for a filesystem-based dataset, table name for HyperTable,
* etc).
*/
def hadoopRDD[K, V, F <: InputFormat[K, V]](
conf: JobConf,
inputFormatClass: Class[F],
keyClass: Class[K],
valueClass: Class[V],
minSplits: Int
): JavaPairRDD[K, V] = {
implicit val kcm: ClassTag[K] = ClassTag(keyClass)
implicit val vcm: ClassTag[V] = ClassTag(valueClass)
new JavaPairRDD(sc.hadoopRDD(conf, inputFormatClass, keyClass, valueClass, minSplits))
}
/**
* Get an RDD for a Hadoop-readable dataset from a Hadooop JobConf giving its InputFormat and any
* other necessary info (e.g. file name for a filesystem-based dataset, table name for HyperTable,
* etc).
*/
def hadoopRDD[K, V, F <: InputFormat[K, V]](
conf: JobConf,
inputFormatClass: Class[F],
keyClass: Class[K],
valueClass: Class[V]
): JavaPairRDD[K, V] = {
implicit val kcm: ClassTag[K] = ClassTag(keyClass)
implicit val vcm: ClassTag[V] = ClassTag(valueClass)
new JavaPairRDD(sc.hadoopRDD(conf, inputFormatClass, keyClass, valueClass))
}
/** Get an RDD for a Hadoop file with an arbitrary InputFormat */
def hadoopFile[K, V, F <: InputFormat[K, V]](
path: String,
inputFormatClass: Class[F],
keyClass: Class[K],
valueClass: Class[V],
minSplits: Int
): JavaPairRDD[K, V] = {
implicit val kcm: ClassTag[K] = ClassTag(keyClass)
implicit val vcm: ClassTag[V] = ClassTag(valueClass)
new JavaPairRDD(sc.hadoopFile(path, inputFormatClass, keyClass, valueClass, minSplits))
}
/** Get an RDD for a Hadoop file with an arbitrary InputFormat */
def hadoopFile[K, V, F <: InputFormat[K, V]](
path: String,
inputFormatClass: Class[F],
keyClass: Class[K],
valueClass: Class[V]
): JavaPairRDD[K, V] = {
implicit val kcm: ClassTag[K] = ClassTag(keyClass)
implicit val vcm: ClassTag[V] = ClassTag(valueClass)
new JavaPairRDD(sc.hadoopFile(path,
inputFormatClass, keyClass, valueClass))
}
/**
* Get an RDD for a given Hadoop file with an arbitrary new API InputFormat
* and extra configuration options to pass to the input format.
*/
def newAPIHadoopFile[K, V, F <: NewInputFormat[K, V]](
path: String,
fClass: Class[F],
kClass: Class[K],
vClass: Class[V],
conf: Configuration): JavaPairRDD[K, V] = {
implicit val kcm: ClassTag[K] = ClassTag(kClass)
implicit val vcm: ClassTag[V] = ClassTag(vClass)
new JavaPairRDD(sc.newAPIHadoopFile(path, fClass, kClass, vClass, conf))
}
/**
* Get an RDD for a given Hadoop file with an arbitrary new API InputFormat
* and extra configuration options to pass to the input format.
*/
def newAPIHadoopRDD[K, V, F <: NewInputFormat[K, V]](
conf: Configuration,
fClass: Class[F],
kClass: Class[K],
vClass: Class[V]): JavaPairRDD[K, V] = {
implicit val kcm: ClassTag[K] = ClassTag(kClass)
implicit val vcm: ClassTag[V] = ClassTag(vClass)
new JavaPairRDD(sc.newAPIHadoopRDD(conf, fClass, kClass, vClass))
}
/** Build the union of two or more RDDs. */
override def union[T](first: JavaRDD[T], rest: java.util.List[JavaRDD[T]]): JavaRDD[T] = {
val rdds: Seq[RDD[T]] = (Seq(first) ++ asScalaBuffer(rest)).map(_.rdd)
implicit val cm: ClassTag[T] = first.classTag
sc.union(rdds)(cm)
}
/** Build the union of two or more RDDs. */
override def union[K, V](first: JavaPairRDD[K, V], rest: java.util.List[JavaPairRDD[K, V]])
: JavaPairRDD[K, V] = {
val rdds: Seq[RDD[(K, V)]] = (Seq(first) ++ asScalaBuffer(rest)).map(_.rdd)
implicit val cm: ClassTag[(K, V)] = first.classTag
implicit val kcm: ClassTag[K] = first.kClassTag
implicit val vcm: ClassTag[V] = first.vClassTag
new JavaPairRDD(sc.union(rdds)(cm))(kcm, vcm)
}
/** Build the union of two or more RDDs. */
override def union(first: JavaDoubleRDD, rest: java.util.List[JavaDoubleRDD]): JavaDoubleRDD = {
val rdds: Seq[RDD[Double]] = (Seq(first) ++ asScalaBuffer(rest)).map(_.srdd)
new JavaDoubleRDD(sc.union(rdds))
}
/**
* Create an [[org.apache.spark.Accumulator]] integer variable, which tasks can "add" values
* to using the `add` method. Only the master can access the accumulator's `value`.
*/
def intAccumulator(initialValue: Int): Accumulator[java.lang.Integer] =
sc.accumulator(initialValue)(IntAccumulatorParam).asInstanceOf[Accumulator[java.lang.Integer]]
/**
* Create an [[org.apache.spark.Accumulator]] double variable, which tasks can "add" values
* to using the `add` method. Only the master can access the accumulator's `value`.
*/
def doubleAccumulator(initialValue: Double): Accumulator[java.lang.Double] =
sc.accumulator(initialValue)(DoubleAccumulatorParam).asInstanceOf[Accumulator[java.lang.Double]]
/**
* Create an [[org.apache.spark.Accumulator]] integer variable, which tasks can "add" values
* to using the `add` method. Only the master can access the accumulator's `value`.
*/
def accumulator(initialValue: Int): Accumulator[java.lang.Integer] = intAccumulator(initialValue)
/**
* Create an [[org.apache.spark.Accumulator]] double variable, which tasks can "add" values
* to using the `add` method. Only the master can access the accumulator's `value`.
*/
def accumulator(initialValue: Double): Accumulator[java.lang.Double] =
doubleAccumulator(initialValue)
/**
* Create an [[org.apache.spark.Accumulator]] variable of a given type, which tasks can "add" values
* to using the `add` method. Only the master can access the accumulator's `value`.
*/
def accumulator[T](initialValue: T, accumulatorParam: AccumulatorParam[T]): Accumulator[T] =
sc.accumulator(initialValue)(accumulatorParam)
/**
* Create an [[org.apache.spark.Accumulable]] shared variable of the given type, to which tasks can
* "add" values with `add`. Only the master can access the accumuable's `value`.
*/
def accumulable[T, R](initialValue: T, param: AccumulableParam[T, R]): Accumulable[T, R] =
sc.accumulable(initialValue)(param)
/**
* Broadcast a read-only variable to the cluster, returning a [[org.apache.spark.Broadcast]] object for
* reading it in distributed functions. The variable will be sent to each cluster only once.
*/
def broadcast[T](value: T): Broadcast[T] = sc.broadcast(value)
/** Shut down the SparkContext. */
def stop() {
sc.stop()
}
/**
* Get Spark's home location from either a value set through the constructor,
* or the spark.home Java property, or the SPARK_HOME environment variable
* (in that order of preference). If neither of these is set, return None.
*/
def getSparkHome(): Optional[String] = JavaUtils.optionToOptional(sc.getSparkHome())
/**
* Add a file to be downloaded with this Spark job on every node.
* The `path` passed can be either a local file, a file in HDFS (or other Hadoop-supported
* filesystems), or an HTTP, HTTPS or FTP URI. To access the file in Spark jobs,
* use `SparkFiles.get(path)` to find its download location.
*/
def addFile(path: String) {
sc.addFile(path)
}
/**
* Adds a JAR dependency for all tasks to be executed on this SparkContext in the future.
* The `path` passed can be either a local file, a file in HDFS (or other Hadoop-supported
* filesystems), or an HTTP, HTTPS or FTP URI.
*/
def addJar(path: String) {
sc.addJar(path)
}
/**
* Clear the job's list of JARs added by `addJar` so that they do not get downloaded to
* any new nodes.
*/
def clearJars() {
sc.clearJars()
}
/**
* Clear the job's list of files added by `addFile` so that they do not get downloaded to
* any new nodes.
*/
def clearFiles() {
sc.clearFiles()
}
/**
* Returns the Hadoop configuration used for the Hadoop code (e.g. file systems) we reuse.
*/
def hadoopConfiguration(): Configuration = {
sc.hadoopConfiguration
}
/**
* Set the directory under which RDDs are going to be checkpointed. The directory must
* be a HDFS path if running on a cluster.
*/
def setCheckpointDir(dir: String) {
sc.setCheckpointDir(dir)
}
protected def checkpointFile[T](path: String): JavaRDD[T] = {
implicit val cm: ClassTag[T] =
implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]]
new JavaRDD(sc.checkpointFile(path))
}
/**
* Return a copy of this JavaSparkContext's configuration. The configuration ''cannot'' be
* changed at runtime.
*/
def getConf: SparkConf = sc.getConf
/**
* Pass-through to SparkContext.setCallSite. For API support only.
*/
def setCallSite(site: String) {
sc.setCallSite(site)
}
/**
* Pass-through to SparkContext.setCallSite. For API support only.
*/
def clearCallSite() {
sc.clearCallSite()
}
}
object JavaSparkContext {
implicit def fromSparkContext(sc: SparkContext): JavaSparkContext = new JavaSparkContext(sc)
implicit def toSparkContext(jsc: JavaSparkContext): SparkContext = jsc.sc
}
|