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
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
|
/*
* 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.io.Closeable
import java.util
import java.util.{Map => JMap}
import scala.collection.JavaConversions
import scala.collection.JavaConversions._
import scala.language.implicitConversions
import scala.reflect.ClassTag
import com.google.common.base.Optional
import org.apache.hadoop.conf.Configuration
import org.apache.spark.input.PortableDataStream
import org.apache.hadoop.mapred.{InputFormat, JobConf}
import org.apache.hadoop.mapreduce.{InputFormat => NewInputFormat}
import org.apache.spark._
import org.apache.spark.SparkContext._
import org.apache.spark.annotation.Experimental
import org.apache.spark.api.java.JavaSparkContext.fakeClassTag
import org.apache.spark.broadcast.Broadcast
import org.apache.spark.rdd.{EmptyRDD, HadoopRDD, NewHadoopRDD, RDD}
/**
* 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 with Closeable {
/**
* Create a JavaSparkContext that loads settings from system properties (for instance, when
* launching with ./bin/spark-submit).
*/
def this() = this(new SparkContext())
/**
* @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, Map()))
private[spark] val env = sc.env
def isLocal: java.lang.Boolean = sc.isLocal
def sparkUser: String = sc.sparkUser
def master: String = sc.master
def appName: String = sc.appName
def jars: util.List[String] = sc.jars
def startTime: java.lang.Long = sc.startTime
/** The version of Spark on which this application is running. */
def version: String = sc.version
/** Default level of parallelism to use when not given by user (e.g. parallelize and makeRDD). */
def defaultParallelism: java.lang.Integer = sc.defaultParallelism
/**
* Default min number of partitions for Hadoop RDDs when not given by user.
* @deprecated As of Spark 1.0.0, defaultMinSplits is deprecated, use
* {@link #defaultMinPartitions()} instead
*/
@deprecated("use defaultMinPartitions", "1.0.0")
def defaultMinSplits: java.lang.Integer = sc.defaultMinSplits
/** Default min number of partitions for Hadoop RDDs when not given by user */
def defaultMinPartitions: java.lang.Integer = sc.defaultMinPartitions
/**
* Return a list of all known jobs in a particular job group. The returned list may contain
* running, failed, and completed jobs, and may vary across invocations of this method. This
* method does not guarantee the order of the elements in its result.
*/
def getJobIdsForGroup(jobGroup: String): Array[Int] = sc.getJobIdsForGroup(jobGroup)
/**
* Returns job information, or `null` if the job info could not be found or was garbage collected.
*/
def getJobInfo(jobId: Int): SparkJobInfo = sc.getJobInfo(jobId).orNull
/**
* Returns stage information, or `null` if the stage info could not be found or was
* garbage collected.
*/
def getStageInfo(stageId: Int): SparkStageInfo = sc.getStageInfo(stageId).orNull
/** Distribute a local Scala collection to form an RDD. */
def parallelize[T](list: java.util.List[T], numSlices: Int): JavaRDD[T] = {
implicit val ctag: ClassTag[T] = fakeClassTag
sc.parallelize(JavaConversions.asScalaBuffer(list), numSlices)
}
/** Get an RDD that has no partitions or elements. */
def emptyRDD[T]: JavaRDD[T] = {
implicit val ctag: ClassTag[T] = fakeClassTag
JavaRDD.fromRDD(new EmptyRDD[T](sc))
}
/** 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 ctagK: ClassTag[K] = fakeClassTag
implicit val ctagV: ClassTag[V] = fakeClassTag
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, minPartitions: Int): JavaRDD[String] =
sc.textFile(path, minPartitions)
/**
* Read a directory of text files from HDFS, a local file system (available on all nodes), or any
* Hadoop-supported file system URI. Each file is read as a single record and returned in a
* key-value pair, where the key is the path of each file, the value is the content of each file.
*
* <p> For example, if you have the following files:
* {{{
* hdfs://a-hdfs-path/part-00000
* hdfs://a-hdfs-path/part-00001
* ...
* hdfs://a-hdfs-path/part-nnnnn
* }}}
*
* Do
* {{{
* JavaPairRDD<String, String> rdd = sparkContext.wholeTextFiles("hdfs://a-hdfs-path")
* }}}
*
* <p> then `rdd` contains
* {{{
* (a-hdfs-path/part-00000, its content)
* (a-hdfs-path/part-00001, its content)
* ...
* (a-hdfs-path/part-nnnnn, its content)
* }}}
*
* @note Small files are preferred, large file is also allowable, but may cause bad performance.
*
* @param minPartitions A suggestion value of the minimal splitting number for input data.
*/
def wholeTextFiles(path: String, minPartitions: Int): JavaPairRDD[String, String] =
new JavaPairRDD(sc.wholeTextFiles(path, minPartitions))
/**
* Read a directory of text files from HDFS, a local file system (available on all nodes), or any
* Hadoop-supported file system URI. Each file is read as a single record and returned in a
* key-value pair, where the key is the path of each file, the value is the content of each file.
*
* @see `wholeTextFiles(path: String, minPartitions: Int)`.
*/
def wholeTextFiles(path: String): JavaPairRDD[String, String] =
new JavaPairRDD(sc.wholeTextFiles(path))
/**
* Read a directory of binary files from HDFS, a local file system (available on all nodes),
* or any Hadoop-supported file system URI as a byte array. Each file is read as a single
* record and returned in a key-value pair, where the key is the path of each file,
* the value is the content of each file.
*
* For example, if you have the following files:
* {{{
* hdfs://a-hdfs-path/part-00000
* hdfs://a-hdfs-path/part-00001
* ...
* hdfs://a-hdfs-path/part-nnnnn
* }}}
*
* Do
* `JavaPairRDD<String, byte[]> rdd = sparkContext.dataStreamFiles("hdfs://a-hdfs-path")`,
*
* then `rdd` contains
* {{{
* (a-hdfs-path/part-00000, its content)
* (a-hdfs-path/part-00001, its content)
* ...
* (a-hdfs-path/part-nnnnn, its content)
* }}}
*
* @note Small files are preferred; very large files but may cause bad performance.
*
* @param minPartitions A suggestion value of the minimal splitting number for input data.
*/
def binaryFiles(path: String, minPartitions: Int): JavaPairRDD[String, PortableDataStream] =
new JavaPairRDD(sc.binaryFiles(path, minPartitions))
/**
* :: Experimental ::
*
* Read a directory of binary files from HDFS, a local file system (available on all nodes),
* or any Hadoop-supported file system URI as a byte array. Each file is read as a single
* record and returned in a key-value pair, where the key is the path of each file,
* the value is the content of each file.
*
* For example, if you have the following files:
* {{{
* hdfs://a-hdfs-path/part-00000
* hdfs://a-hdfs-path/part-00001
* ...
* hdfs://a-hdfs-path/part-nnnnn
* }}}
*
* Do
* `JavaPairRDD<String, byte[]> rdd = sparkContext.dataStreamFiles("hdfs://a-hdfs-path")`,
*
* then `rdd` contains
* {{{
* (a-hdfs-path/part-00000, its content)
* (a-hdfs-path/part-00001, its content)
* ...
* (a-hdfs-path/part-nnnnn, its content)
* }}}
*
* @note Small files are preferred; very large files but may cause bad performance.
*/
@Experimental
def binaryFiles(path: String): JavaPairRDD[String, PortableDataStream] =
new JavaPairRDD(sc.binaryFiles(path, defaultMinPartitions))
/**
* :: Experimental ::
*
* Load data from a flat binary file, assuming the length of each record is constant.
*
* @param path Directory to the input data files
* @return An RDD of data with values, represented as byte arrays
*/
@Experimental
def binaryRecords(path: String, recordLength: Int): JavaRDD[Array[Byte]] = {
new JavaRDD(sc.binaryRecords(path, recordLength))
}
/** Get an RDD for a Hadoop SequenceFile with given key and value types.
*
* '''Note:''' Because Hadoop's RecordReader class re-uses the same Writable object for each
* record, directly caching the returned RDD will create many references to the same object.
* If you plan to directly cache Hadoop writable objects, you should first copy them using
* a `map` function.
* */
def sequenceFile[K, V](path: String,
keyClass: Class[K],
valueClass: Class[V],
minPartitions: Int
): JavaPairRDD[K, V] = {
implicit val ctagK: ClassTag[K] = ClassTag(keyClass)
implicit val ctagV: ClassTag[V] = ClassTag(valueClass)
new JavaPairRDD(sc.sequenceFile(path, keyClass, valueClass, minPartitions))
}
/** Get an RDD for a Hadoop SequenceFile.
*
* '''Note:''' Because Hadoop's RecordReader class re-uses the same Writable object for each
* record, directly caching the returned RDD will create many references to the same object.
* If you plan to directly cache Hadoop writable objects, you should first copy them using
* a `map` function.
*/
def sequenceFile[K, V](path: String, keyClass: Class[K], valueClass: Class[V]):
JavaPairRDD[K, V] = {
implicit val ctagK: ClassTag[K] = ClassTag(keyClass)
implicit val ctagV: 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, minPartitions: Int): JavaRDD[T] = {
implicit val ctag: ClassTag[T] = fakeClassTag
sc.objectFile(path, minPartitions)(ctag)
}
/**
* 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 ctag: ClassTag[T] = fakeClassTag
sc.objectFile(path)(ctag)
}
/**
* 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).
*
* '''Note:''' Because Hadoop's RecordReader class re-uses the same Writable object for each
* record, directly caching the returned RDD will create many references to the same object.
* If you plan to directly cache Hadoop writable objects, you should first copy them using
* a `map` function.
*/
def hadoopRDD[K, V, F <: InputFormat[K, V]](
conf: JobConf,
inputFormatClass: Class[F],
keyClass: Class[K],
valueClass: Class[V],
minPartitions: Int
): JavaPairRDD[K, V] = {
implicit val ctagK: ClassTag[K] = ClassTag(keyClass)
implicit val ctagV: ClassTag[V] = ClassTag(valueClass)
val rdd = sc.hadoopRDD(conf, inputFormatClass, keyClass, valueClass, minPartitions)
new JavaHadoopRDD(rdd.asInstanceOf[HadoopRDD[K, V]])
}
/**
* 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,
*
* '''Note:''' Because Hadoop's RecordReader class re-uses the same Writable object for each
* record, directly caching the returned RDD will create many references to the same object.
* If you plan to directly cache Hadoop writable objects, you should first copy them using
* a `map` function.
*/
def hadoopRDD[K, V, F <: InputFormat[K, V]](
conf: JobConf,
inputFormatClass: Class[F],
keyClass: Class[K],
valueClass: Class[V]
): JavaPairRDD[K, V] = {
implicit val ctagK: ClassTag[K] = ClassTag(keyClass)
implicit val ctagV: ClassTag[V] = ClassTag(valueClass)
val rdd = sc.hadoopRDD(conf, inputFormatClass, keyClass, valueClass)
new JavaHadoopRDD(rdd.asInstanceOf[HadoopRDD[K, V]])
}
/** Get an RDD for a Hadoop file with an arbitrary InputFormat.
*
* '''Note:''' Because Hadoop's RecordReader class re-uses the same Writable object for each
* record, directly caching the returned RDD will create many references to the same object.
* If you plan to directly cache Hadoop writable objects, you should first copy them using
* a `map` function.
*/
def hadoopFile[K, V, F <: InputFormat[K, V]](
path: String,
inputFormatClass: Class[F],
keyClass: Class[K],
valueClass: Class[V],
minPartitions: Int
): JavaPairRDD[K, V] = {
implicit val ctagK: ClassTag[K] = ClassTag(keyClass)
implicit val ctagV: ClassTag[V] = ClassTag(valueClass)
val rdd = sc.hadoopFile(path, inputFormatClass, keyClass, valueClass, minPartitions)
new JavaHadoopRDD(rdd.asInstanceOf[HadoopRDD[K, V]])
}
/** Get an RDD for a Hadoop file with an arbitrary InputFormat
*
* '''Note:''' Because Hadoop's RecordReader class re-uses the same Writable object for each
* record, directly caching the returned RDD will create many references to the same object.
* If you plan to directly cache Hadoop writable objects, you should first copy them using
* a `map` function.
*/
def hadoopFile[K, V, F <: InputFormat[K, V]](
path: String,
inputFormatClass: Class[F],
keyClass: Class[K],
valueClass: Class[V]
): JavaPairRDD[K, V] = {
implicit val ctagK: ClassTag[K] = ClassTag(keyClass)
implicit val ctagV: ClassTag[V] = ClassTag(valueClass)
val rdd = sc.hadoopFile(path, inputFormatClass, keyClass, valueClass)
new JavaHadoopRDD(rdd.asInstanceOf[HadoopRDD[K, V]])
}
/**
* Get an RDD for a given Hadoop file with an arbitrary new API InputFormat
* and extra configuration options to pass to the input format.
*
* '''Note:''' Because Hadoop's RecordReader class re-uses the same Writable object for each
* record, directly caching the returned RDD will create many references to the same object.
* If you plan to directly cache Hadoop writable objects, you should first copy them using
* a `map` function.
*/
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 ctagK: ClassTag[K] = ClassTag(kClass)
implicit val ctagV: ClassTag[V] = ClassTag(vClass)
val rdd = sc.newAPIHadoopFile(path, fClass, kClass, vClass, conf)
new JavaNewHadoopRDD(rdd.asInstanceOf[NewHadoopRDD[K, V]])
}
/**
* Get an RDD for a given Hadoop file with an arbitrary new API InputFormat
* and extra configuration options to pass to the input format.
*
* '''Note:''' Because Hadoop's RecordReader class re-uses the same Writable object for each
* record, directly caching the returned RDD will create many references to the same object.
* If you plan to directly cache Hadoop writable objects, you should first copy them using
* a `map` function.
*/
def newAPIHadoopRDD[K, V, F <: NewInputFormat[K, V]](
conf: Configuration,
fClass: Class[F],
kClass: Class[K],
vClass: Class[V]): JavaPairRDD[K, V] = {
implicit val ctagK: ClassTag[K] = ClassTag(kClass)
implicit val ctagV: ClassTag[V] = ClassTag(vClass)
val rdd = sc.newAPIHadoopRDD(conf, fClass, kClass, vClass)
new JavaNewHadoopRDD(rdd.asInstanceOf[NewHadoopRDD[K, V]])
}
/** 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 ctag: ClassTag[T] = first.classTag
sc.union(rdds)
}
/** 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 ctag: ClassTag[(K, V)] = first.classTag
implicit val ctagK: ClassTag[K] = first.kClassTag
implicit val ctagV: ClassTag[V] = first.vClassTag
new JavaPairRDD(sc.union(rdds))
}
/** 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]] integer variable, which tasks can "add" values
* to using the `add` method. Only the master can access the accumulator's `value`.
*
* This version supports naming the accumulator for display in Spark's web UI.
*/
def intAccumulator(initialValue: Int, name: String): Accumulator[java.lang.Integer] =
sc.accumulator(initialValue, name)(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]] double variable, which tasks can "add" values
* to using the `add` method. Only the master can access the accumulator's `value`.
*
* This version supports naming the accumulator for display in Spark's web UI.
*/
def doubleAccumulator(initialValue: Double, name: String): Accumulator[java.lang.Double] =
sc.accumulator(initialValue, name)(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]] integer variable, which tasks can "add" values
* to using the `add` method. Only the master can access the accumulator's `value`.
*
* This version supports naming the accumulator for display in Spark's web UI.
*/
def accumulator(initialValue: Int, name: String): Accumulator[java.lang.Integer] =
intAccumulator(initialValue, name)
/**
* 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]] double variable, which tasks can "add" values
* to using the `add` method. Only the master can access the accumulator's `value`.
*
* This version supports naming the accumulator for display in Spark's web UI.
*/
def accumulator(initialValue: Double, name: String): Accumulator[java.lang.Double] =
doubleAccumulator(initialValue, name)
/**
* 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.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`.
*
* This version supports naming the accumulator for display in Spark's web UI.
*/
def accumulator[T](initialValue: T, name: String, accumulatorParam: AccumulatorParam[T])
: Accumulator[T] =
sc.accumulator(initialValue, name)(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)
/**
* 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`.
*
* This version supports naming the accumulator for display in Spark's web UI.
*/
def accumulable[T, R](initialValue: T, name: String, param: AccumulableParam[T, R])
: Accumulable[T, R] =
sc.accumulable(initialValue, name)(param)
/**
* Broadcast a read-only variable to the cluster, returning a
* [[org.apache.spark.broadcast.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)(fakeClassTag)
/** Shut down the SparkContext. */
def stop() {
sc.stop()
}
override def close(): Unit = 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(fileName)` 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.
*/
@deprecated("adding jars no longer creates local copies that need to be deleted", "1.0.0")
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.
*/
@deprecated("adding files no longer creates local copies that need to be deleted", "1.0.0")
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)
}
def getCheckpointDir: Optional[String] = JavaUtils.optionToOptional(sc.getCheckpointDir)
protected def checkpointFile[T](path: String): JavaRDD[T] = {
implicit val ctag: ClassTag[T] = fakeClassTag
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()
}
/**
* Set a local property that affects jobs submitted from this thread, such as the
* Spark fair scheduler pool.
*/
def setLocalProperty(key: String, value: String): Unit = sc.setLocalProperty(key, value)
/**
* Get a local property set in this thread, or null if it is missing. See
* [[org.apache.spark.api.java.JavaSparkContext.setLocalProperty]].
*/
def getLocalProperty(key: String): String = sc.getLocalProperty(key)
/**
* Assigns a group ID to all the jobs started by this thread until the group ID is set to a
* different value or cleared.
*
* Often, a unit of execution in an application consists of multiple Spark actions or jobs.
* Application programmers can use this method to group all those jobs together and give a
* group description. Once set, the Spark web UI will associate such jobs with this group.
*
* The application can also use [[org.apache.spark.api.java.JavaSparkContext.cancelJobGroup]]
* to cancel all running jobs in this group. For example,
* {{{
* // In the main thread:
* sc.setJobGroup("some_job_to_cancel", "some job description");
* rdd.map(...).count();
*
* // In a separate thread:
* sc.cancelJobGroup("some_job_to_cancel");
* }}}
*
* If interruptOnCancel is set to true for the job group, then job cancellation will result
* in Thread.interrupt() being called on the job's executor threads. This is useful to help ensure
* that the tasks are actually stopped in a timely manner, but is off by default due to HDFS-1208,
* where HDFS may respond to Thread.interrupt() by marking nodes as dead.
*/
def setJobGroup(groupId: String, description: String, interruptOnCancel: Boolean): Unit =
sc.setJobGroup(groupId, description, interruptOnCancel)
/**
* Assigns a group ID to all the jobs started by this thread until the group ID is set to a
* different value or cleared.
*
* @see `setJobGroup(groupId: String, description: String, interruptThread: Boolean)`.
* This method sets interruptOnCancel to false.
*/
def setJobGroup(groupId: String, description: String): Unit = sc.setJobGroup(groupId, description)
/** Clear the current thread's job group ID and its description. */
def clearJobGroup(): Unit = sc.clearJobGroup()
/**
* Cancel active jobs for the specified group. See
* [[org.apache.spark.api.java.JavaSparkContext.setJobGroup]] for more information.
*/
def cancelJobGroup(groupId: String): Unit = sc.cancelJobGroup(groupId)
/** Cancel all jobs that have been scheduled or are running. */
def cancelAllJobs(): Unit = sc.cancelAllJobs()
}
object JavaSparkContext {
implicit def fromSparkContext(sc: SparkContext): JavaSparkContext = new JavaSparkContext(sc)
implicit def toSparkContext(jsc: JavaSparkContext): SparkContext = jsc.sc
/**
* Find the JAR from which a given class was loaded, to make it easy for users to pass
* their JARs to SparkContext.
*/
def jarOfClass(cls: Class[_]): Array[String] = SparkContext.jarOfClass(cls).toArray
/**
* Find the JAR that contains the class of a particular object, to make it easy for users
* to pass their JARs to SparkContext. In most cases you can call jarOfObject(this) in
* your driver program.
*/
def jarOfObject(obj: AnyRef): Array[String] = SparkContext.jarOfObject(obj).toArray
/**
* Produces a ClassTag[T], which is actually just a casted ClassTag[AnyRef].
*
* This method is used to keep ClassTags out of the external Java API, as the Java compiler
* cannot produce them automatically. While this ClassTag-faking does please the compiler,
* it can cause problems at runtime if the Scala API relies on ClassTags for correctness.
*
* Often, though, a ClassTag[AnyRef] will not lead to incorrect behavior, just worse performance
* or security issues. For instance, an Array[AnyRef] can hold any type T, but may lose primitive
* specialization.
*/
private[spark]
def fakeClassTag[T]: ClassTag[T] = ClassTag.AnyRef.asInstanceOf[ClassTag[T]]
}
|