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
|
/*
* 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.streaming.api.java
import java.io.{Closeable, InputStream}
import java.lang.{Boolean => JBoolean}
import java.util.{List => JList, Map => JMap}
import scala.collection.JavaConverters._
import scala.reflect.ClassTag
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.Path
import org.apache.hadoop.mapreduce.{InputFormat => NewInputFormat}
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.annotation.Experimental
import org.apache.spark.api.java.{JavaPairRDD, JavaRDD, JavaSparkContext}
import org.apache.spark.api.java.function.{Function => JFunction, Function2 => JFunction2}
import org.apache.spark.api.java.function.{Function0 => JFunction0}
import org.apache.spark.deploy.SparkHadoopUtil
import org.apache.spark.rdd.RDD
import org.apache.spark.storage.StorageLevel
import org.apache.spark.streaming._
import org.apache.spark.streaming.dstream.DStream
import org.apache.spark.streaming.receiver.Receiver
import org.apache.spark.streaming.scheduler.StreamingListener
/**
* A Java-friendly version of [[org.apache.spark.streaming.StreamingContext]] which is the main
* entry point for Spark Streaming functionality. It provides methods to create
* [[org.apache.spark.streaming.api.java.JavaDStream]] and
* [[org.apache.spark.streaming.api.java.JavaPairDStream.]] from input sources. The internal
* org.apache.spark.api.java.JavaSparkContext (see core Spark documentation) can be accessed
* using `context.sparkContext`. After creating and transforming DStreams, the streaming
* computation can be started and stopped using `context.start()` and `context.stop()`,
* respectively. `context.awaitTermination()` allows the current thread to wait for the
* termination of a context by `stop()` or by an exception.
*/
class JavaStreamingContext(val ssc: StreamingContext) extends Closeable {
/**
* Create a StreamingContext.
* @param master Name of the Spark Master
* @param appName Name to be used when registering with the scheduler
* @param batchDuration The time interval at which streaming data will be divided into batches
*/
def this(master: String, appName: String, batchDuration: Duration) =
this(new StreamingContext(master, appName, batchDuration, null, Nil, Map()))
/**
* Create a StreamingContext.
* @param master Name of the Spark Master
* @param appName Name to be used when registering with the scheduler
* @param batchDuration The time interval at which streaming data will be divided into batches
* @param sparkHome The SPARK_HOME directory on the slave nodes
* @param jarFile JAR file containing job code, to ship to 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,
batchDuration: Duration,
sparkHome: String,
jarFile: String) =
this(new StreamingContext(master, appName, batchDuration, sparkHome, Seq(jarFile), Map()))
/**
* Create a StreamingContext.
* @param master Name of the Spark Master
* @param appName Name to be used when registering with the scheduler
* @param batchDuration The time interval at which streaming data will be divided into batches
* @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,
batchDuration: Duration,
sparkHome: String,
jars: Array[String]) =
this(new StreamingContext(master, appName, batchDuration, sparkHome, jars, Map()))
/**
* Create a StreamingContext.
* @param master Name of the Spark Master
* @param appName Name to be used when registering with the scheduler
* @param batchDuration The time interval at which streaming data will be divided into batches
* @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,
batchDuration: Duration,
sparkHome: String,
jars: Array[String],
environment: JMap[String, String]) =
this(new StreamingContext(
master,
appName,
batchDuration,
sparkHome,
jars,
environment.asScala))
/**
* Create a JavaStreamingContext using an existing JavaSparkContext.
* @param sparkContext The underlying JavaSparkContext to use
* @param batchDuration The time interval at which streaming data will be divided into batches
*/
def this(sparkContext: JavaSparkContext, batchDuration: Duration) =
this(new StreamingContext(sparkContext.sc, batchDuration))
/**
* Create a JavaStreamingContext using a SparkConf configuration.
* @param conf A Spark application configuration
* @param batchDuration The time interval at which streaming data will be divided into batches
*/
def this(conf: SparkConf, batchDuration: Duration) =
this(new StreamingContext(conf, batchDuration))
/**
* Recreate a JavaStreamingContext from a checkpoint file.
* @param path Path to the directory that was specified as the checkpoint directory
*/
def this(path: String) = this(new StreamingContext(path, SparkHadoopUtil.get.conf))
/**
* Re-creates a JavaStreamingContext from a checkpoint file.
* @param path Path to the directory that was specified as the checkpoint directory
*
*/
def this(path: String, hadoopConf: Configuration) = this(new StreamingContext(path, hadoopConf))
/** The underlying SparkContext */
val sparkContext = new JavaSparkContext(ssc.sc)
/**
* @deprecated As of 0.9.0, replaced by `sparkContext`
*/
@deprecated("use sparkContext", "0.9.0")
val sc: JavaSparkContext = sparkContext
/**
* Create an input stream from network source hostname:port. Data is received using
* a TCP socket and the receive bytes is interpreted as UTF8 encoded \n delimited
* lines.
* @param hostname Hostname to connect to for receiving data
* @param port Port to connect to for receiving data
* @param storageLevel Storage level to use for storing the received objects
*/
def socketTextStream(
hostname: String, port: Int,
storageLevel: StorageLevel
): JavaReceiverInputDStream[String] = {
ssc.socketTextStream(hostname, port, storageLevel)
}
/**
* Create an input stream from network source hostname:port. Data is received using
* a TCP socket and the receive bytes is interpreted as UTF8 encoded \n delimited
* lines. Storage level of the data will be the default StorageLevel.MEMORY_AND_DISK_SER_2.
* @param hostname Hostname to connect to for receiving data
* @param port Port to connect to for receiving data
*/
def socketTextStream(hostname: String, port: Int): JavaReceiverInputDStream[String] = {
ssc.socketTextStream(hostname, port)
}
/**
* Create an input stream from network source hostname:port. Data is received using
* a TCP socket and the receive bytes it interpreted as object using the given
* converter.
* @param hostname Hostname to connect to for receiving data
* @param port Port to connect to for receiving data
* @param converter Function to convert the byte stream to objects
* @param storageLevel Storage level to use for storing the received objects
* @tparam T Type of the objects received (after converting bytes to objects)
*/
def socketStream[T](
hostname: String,
port: Int,
converter: JFunction[InputStream, java.lang.Iterable[T]],
storageLevel: StorageLevel)
: JavaReceiverInputDStream[T] = {
def fn: (InputStream) => Iterator[T] = (x: InputStream) => converter.call(x).iterator().asScala
implicit val cmt: ClassTag[T] =
implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]]
ssc.socketStream(hostname, port, fn, storageLevel)
}
/**
* Create an input stream that monitors a Hadoop-compatible filesystem
* for new files and reads them as text files (using key as LongWritable, value
* as Text and input format as TextInputFormat). Files must be written to the
* monitored directory by "moving" them from another location within the same
* file system. File names starting with . are ignored.
* @param directory HDFS directory to monitor for new file
*/
def textFileStream(directory: String): JavaDStream[String] = {
ssc.textFileStream(directory)
}
/**
* Create an input stream that monitors a Hadoop-compatible filesystem
* for new files and reads them as flat binary files with fixed record lengths,
* yielding byte arrays
*
* '''Note:''' We ensure that the byte array for each record in the
* resulting RDDs of the DStream has the provided record length.
*
* @param directory HDFS directory to monitor for new files
* @param recordLength The length at which to split the records
*/
def binaryRecordsStream(directory: String, recordLength: Int): JavaDStream[Array[Byte]] = {
ssc.binaryRecordsStream(directory, recordLength)
}
/**
* Create an input stream from network source hostname:port, where data is received
* as serialized blocks (serialized using the Spark's serializer) that can be directly
* pushed into the block manager without deserializing them. This is the most efficient
* way to receive data.
* @param hostname Hostname to connect to for receiving data
* @param port Port to connect to for receiving data
* @param storageLevel Storage level to use for storing the received objects
* @tparam T Type of the objects in the received blocks
*/
def rawSocketStream[T](
hostname: String,
port: Int,
storageLevel: StorageLevel): JavaReceiverInputDStream[T] = {
implicit val cmt: ClassTag[T] =
implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]]
JavaReceiverInputDStream.fromReceiverInputDStream(
ssc.rawSocketStream(hostname, port, storageLevel))
}
/**
* Create an input stream from network source hostname:port, where data is received
* as serialized blocks (serialized using the Spark's serializer) that can be directly
* pushed into the block manager without deserializing them. This is the most efficient
* way to receive data.
* @param hostname Hostname to connect to for receiving data
* @param port Port to connect to for receiving data
* @tparam T Type of the objects in the received blocks
*/
def rawSocketStream[T](hostname: String, port: Int): JavaReceiverInputDStream[T] = {
implicit val cmt: ClassTag[T] =
implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]]
JavaReceiverInputDStream.fromReceiverInputDStream(
ssc.rawSocketStream(hostname, port))
}
/**
* Create an input stream that monitors a Hadoop-compatible filesystem
* for new files and reads them using the given key-value types and input format.
* Files must be written to the monitored directory by "moving" them from another
* location within the same file system. File names starting with . are ignored.
* @param directory HDFS directory to monitor for new file
* @param kClass class of key for reading HDFS file
* @param vClass class of value for reading HDFS file
* @param fClass class of input format for reading HDFS file
* @tparam K Key type for reading HDFS file
* @tparam V Value type for reading HDFS file
* @tparam F Input format for reading HDFS file
*/
def fileStream[K, V, F <: NewInputFormat[K, V]](
directory: String,
kClass: Class[K],
vClass: Class[V],
fClass: Class[F]): JavaPairInputDStream[K, V] = {
implicit val cmk: ClassTag[K] = ClassTag(kClass)
implicit val cmv: ClassTag[V] = ClassTag(vClass)
implicit val cmf: ClassTag[F] = ClassTag(fClass)
ssc.fileStream[K, V, F](directory)
}
/**
* Create an input stream that monitors a Hadoop-compatible filesystem
* for new files and reads them using the given key-value types and input format.
* Files must be written to the monitored directory by "moving" them from another
* location within the same file system. File names starting with . are ignored.
* @param directory HDFS directory to monitor for new file
* @param kClass class of key for reading HDFS file
* @param vClass class of value for reading HDFS file
* @param fClass class of input format for reading HDFS file
* @param filter Function to filter paths to process
* @param newFilesOnly Should process only new files and ignore existing files in the directory
* @tparam K Key type for reading HDFS file
* @tparam V Value type for reading HDFS file
* @tparam F Input format for reading HDFS file
*/
def fileStream[K, V, F <: NewInputFormat[K, V]](
directory: String,
kClass: Class[K],
vClass: Class[V],
fClass: Class[F],
filter: JFunction[Path, JBoolean],
newFilesOnly: Boolean): JavaPairInputDStream[K, V] = {
implicit val cmk: ClassTag[K] = ClassTag(kClass)
implicit val cmv: ClassTag[V] = ClassTag(vClass)
implicit val cmf: ClassTag[F] = ClassTag(fClass)
def fn: (Path) => Boolean = (x: Path) => filter.call(x).booleanValue()
ssc.fileStream[K, V, F](directory, fn, newFilesOnly)
}
/**
* Create an input stream that monitors a Hadoop-compatible filesystem
* for new files and reads them using the given key-value types and input format.
* Files must be written to the monitored directory by "moving" them from another
* location within the same file system. File names starting with . are ignored.
* @param directory HDFS directory to monitor for new file
* @param kClass class of key for reading HDFS file
* @param vClass class of value for reading HDFS file
* @param fClass class of input format for reading HDFS file
* @param filter Function to filter paths to process
* @param newFilesOnly Should process only new files and ignore existing files in the directory
* @param conf Hadoop configuration
* @tparam K Key type for reading HDFS file
* @tparam V Value type for reading HDFS file
* @tparam F Input format for reading HDFS file
*/
def fileStream[K, V, F <: NewInputFormat[K, V]](
directory: String,
kClass: Class[K],
vClass: Class[V],
fClass: Class[F],
filter: JFunction[Path, JBoolean],
newFilesOnly: Boolean,
conf: Configuration): JavaPairInputDStream[K, V] = {
implicit val cmk: ClassTag[K] = ClassTag(kClass)
implicit val cmv: ClassTag[V] = ClassTag(vClass)
implicit val cmf: ClassTag[F] = ClassTag(fClass)
def fn: (Path) => Boolean = (x: Path) => filter.call(x).booleanValue()
ssc.fileStream[K, V, F](directory, fn, newFilesOnly, conf)
}
/**
* Create an input stream from an queue of RDDs. In each batch,
* it will process either one or all of the RDDs returned by the queue.
*
* NOTE:
* 1. Changes to the queue after the stream is created will not be recognized.
* 2. Arbitrary RDDs can be added to `queueStream`, there is no way to recover data of
* those RDDs, so `queueStream` doesn't support checkpointing.
*
* @param queue Queue of RDDs
* @tparam T Type of objects in the RDD
*/
def queueStream[T](queue: java.util.Queue[JavaRDD[T]]): JavaDStream[T] = {
implicit val cm: ClassTag[T] =
implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]]
val sQueue = new scala.collection.mutable.Queue[RDD[T]]
sQueue.enqueue(queue.asScala.map(_.rdd).toSeq: _*)
ssc.queueStream(sQueue)
}
/**
* Create an input stream from an queue of RDDs. In each batch,
* it will process either one or all of the RDDs returned by the queue.
*
* NOTE:
* 1. Changes to the queue after the stream is created will not be recognized.
* 2. Arbitrary RDDs can be added to `queueStream`, there is no way to recover data of
* those RDDs, so `queueStream` doesn't support checkpointing.
*
* @param queue Queue of RDDs
* @param oneAtATime Whether only one RDD should be consumed from the queue in every interval
* @tparam T Type of objects in the RDD
*/
def queueStream[T](
queue: java.util.Queue[JavaRDD[T]],
oneAtATime: Boolean
): JavaInputDStream[T] = {
implicit val cm: ClassTag[T] =
implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]]
val sQueue = new scala.collection.mutable.Queue[RDD[T]]
sQueue.enqueue(queue.asScala.map(_.rdd).toSeq: _*)
ssc.queueStream(sQueue, oneAtATime)
}
/**
* Create an input stream from an queue of RDDs. In each batch,
* it will process either one or all of the RDDs returned by the queue.
*
* NOTE:
* 1. Changes to the queue after the stream is created will not be recognized.
* 2. Arbitrary RDDs can be added to `queueStream`, there is no way to recover data of
* those RDDs, so `queueStream` doesn't support checkpointing.
*
* @param queue Queue of RDDs
* @param oneAtATime Whether only one RDD should be consumed from the queue in every interval
* @param defaultRDD Default RDD is returned by the DStream when the queue is empty
* @tparam T Type of objects in the RDD
*/
def queueStream[T](
queue: java.util.Queue[JavaRDD[T]],
oneAtATime: Boolean,
defaultRDD: JavaRDD[T]): JavaInputDStream[T] = {
implicit val cm: ClassTag[T] =
implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]]
val sQueue = new scala.collection.mutable.Queue[RDD[T]]
sQueue.enqueue(queue.asScala.map(_.rdd).toSeq: _*)
ssc.queueStream(sQueue, oneAtATime, defaultRDD.rdd)
}
/**
* Create an input stream with any arbitrary user implemented receiver.
* Find more details at: http://spark.apache.org/docs/latest/streaming-custom-receivers.html
* @param receiver Custom implementation of Receiver
*/
def receiverStream[T](receiver: Receiver[T]): JavaReceiverInputDStream[T] = {
implicit val cm: ClassTag[T] =
implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]]
ssc.receiverStream(receiver)
}
/**
* Create a unified DStream from multiple DStreams of the same type and same slide duration.
*/
def union[T](first: JavaDStream[T], rest: JList[JavaDStream[T]]): JavaDStream[T] = {
val dstreams: Seq[DStream[T]] = (Seq(first) ++ rest.asScala).map(_.dstream)
implicit val cm: ClassTag[T] = first.classTag
ssc.union(dstreams)(cm)
}
/**
* Create a unified DStream from multiple DStreams of the same type and same slide duration.
*/
def union[K, V](
first: JavaPairDStream[K, V],
rest: JList[JavaPairDStream[K, V]]
): JavaPairDStream[K, V] = {
val dstreams: Seq[DStream[(K, V)]] = (Seq(first) ++ rest.asScala).map(_.dstream)
implicit val cm: ClassTag[(K, V)] = first.classTag
implicit val kcm: ClassTag[K] = first.kManifest
implicit val vcm: ClassTag[V] = first.vManifest
new JavaPairDStream[K, V](ssc.union(dstreams)(cm))(kcm, vcm)
}
/**
* Create a new DStream in which each RDD is generated by applying a function on RDDs of
* the DStreams. The order of the JavaRDDs in the transform function parameter will be the
* same as the order of corresponding DStreams in the list. Note that for adding a
* JavaPairDStream in the list of JavaDStreams, convert it to a JavaDStream using
* [[org.apache.spark.streaming.api.java.JavaPairDStream]].toJavaDStream().
* In the transform function, convert the JavaRDD corresponding to that JavaDStream to
* a JavaPairRDD using org.apache.spark.api.java.JavaPairRDD.fromJavaRDD().
*/
def transform[T](
dstreams: JList[JavaDStream[_]],
transformFunc: JFunction2[JList[JavaRDD[_]], Time, JavaRDD[T]]
): JavaDStream[T] = {
implicit val cmt: ClassTag[T] =
implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]]
val scalaTransformFunc = (rdds: Seq[RDD[_]], time: Time) => {
val jrdds = rdds.map(JavaRDD.fromRDD(_)).asJava
transformFunc.call(jrdds, time).rdd
}
ssc.transform(dstreams.asScala.map(_.dstream).toSeq, scalaTransformFunc)
}
/**
* Create a new DStream in which each RDD is generated by applying a function on RDDs of
* the DStreams. The order of the JavaRDDs in the transform function parameter will be the
* same as the order of corresponding DStreams in the list. Note that for adding a
* JavaPairDStream in the list of JavaDStreams, convert it to a JavaDStream using
* [[org.apache.spark.streaming.api.java.JavaPairDStream]].toJavaDStream().
* In the transform function, convert the JavaRDD corresponding to that JavaDStream to
* a JavaPairRDD using org.apache.spark.api.java.JavaPairRDD.fromJavaRDD().
*/
def transformToPair[K, V](
dstreams: JList[JavaDStream[_]],
transformFunc: JFunction2[JList[JavaRDD[_]], Time, JavaPairRDD[K, V]]
): JavaPairDStream[K, V] = {
implicit val cmk: ClassTag[K] =
implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[K]]
implicit val cmv: ClassTag[V] =
implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[V]]
val scalaTransformFunc = (rdds: Seq[RDD[_]], time: Time) => {
val jrdds = rdds.map(JavaRDD.fromRDD(_)).asJava
transformFunc.call(jrdds, time).rdd
}
ssc.transform(dstreams.asScala.map(_.dstream).toSeq, scalaTransformFunc)
}
/**
* Sets the context to periodically checkpoint the DStream operations for master
* fault-tolerance. The graph will be checkpointed every batch interval.
* @param directory HDFS-compatible directory where the checkpoint data will be reliably stored
*/
def checkpoint(directory: String) {
ssc.checkpoint(directory)
}
/**
* Sets each DStreams in this context to remember RDDs it generated in the last given duration.
* DStreams remember RDDs only for a limited duration of duration and releases them for garbage
* collection. This method allows the developer to specify how long to remember the RDDs (
* if the developer wishes to query old data outside the DStream computation).
* @param duration Minimum duration that each DStream should remember its RDDs
*/
def remember(duration: Duration) {
ssc.remember(duration)
}
/** Add a [[org.apache.spark.streaming.scheduler.StreamingListener]] object for
* receiving system events related to streaming.
*/
def addStreamingListener(streamingListener: StreamingListener) {
ssc.addStreamingListener(streamingListener)
}
/**
* :: DeveloperApi ::
*
* Return the current state of the context. The context can be in three possible states -
* <ul>
* <li>
* StreamingContextState.INTIALIZED - The context has been created, but not been started yet.
* Input DStreams, transformations and output operations can be created on the context.
* </li>
* <li>
* StreamingContextState.ACTIVE - The context has been started, and been not stopped.
* Input DStreams, transformations and output operations cannot be created on the context.
* </li>
* <li>
* StreamingContextState.STOPPED - The context has been stopped and cannot be used any more.
* </li>
* </ul>
*/
def getState(): StreamingContextState = {
ssc.getState()
}
/**
* Start the execution of the streams.
*/
def start(): Unit = {
ssc.start()
}
/**
* Wait for the execution to stop. Any exceptions that occurs during the execution
* will be thrown in this thread.
*/
def awaitTermination(): Unit = {
ssc.awaitTermination()
}
/**
* Wait for the execution to stop. Any exceptions that occurs during the execution
* will be thrown in this thread.
* @param timeout time to wait in milliseconds
* @deprecated As of 1.3.0, replaced by `awaitTerminationOrTimeout(Long)`.
*/
@deprecated("Use awaitTerminationOrTimeout(Long) instead", "1.3.0")
def awaitTermination(timeout: Long): Unit = {
ssc.awaitTermination(timeout)
}
/**
* Wait for the execution to stop. Any exceptions that occurs during the execution
* will be thrown in this thread.
*
* @param timeout time to wait in milliseconds
* @return `true` if it's stopped; or throw the reported error during the execution; or `false`
* if the waiting time elapsed before returning from the method.
*/
def awaitTerminationOrTimeout(timeout: Long): Boolean = {
ssc.awaitTerminationOrTimeout(timeout)
}
/**
* Stop the execution of the streams. Will stop the associated JavaSparkContext as well.
*/
def stop(): Unit = {
ssc.stop()
}
/**
* Stop the execution of the streams.
* @param stopSparkContext Stop the associated SparkContext or not
*/
def stop(stopSparkContext: Boolean): Unit = ssc.stop(stopSparkContext)
/**
* Stop the execution of the streams.
* @param stopSparkContext Stop the associated SparkContext or not
* @param stopGracefully Stop gracefully by waiting for the processing of all
* received data to be completed
*/
def stop(stopSparkContext: Boolean, stopGracefully: Boolean): Unit = {
ssc.stop(stopSparkContext, stopGracefully)
}
override def close(): Unit = stop()
}
/**
* JavaStreamingContext object contains a number of utility functions.
*/
object JavaStreamingContext {
/**
* Either recreate a StreamingContext from checkpoint data or create a new StreamingContext.
* If checkpoint data exists in the provided `checkpointPath`, then StreamingContext will be
* recreated from the checkpoint data. If the data does not exist, then the provided factory
* will be used to create a JavaStreamingContext.
*
* @param checkpointPath Checkpoint directory used in an earlier JavaStreamingContext program
* @param factory JavaStreamingContextFactory object to create a new JavaStreamingContext
* @deprecated As of 1.4.0, replaced by `getOrCreate` without JavaStreamingContextFactory.
*/
@deprecated("use getOrCreate without JavaStreamingContextFactory", "1.4.0")
def getOrCreate(
checkpointPath: String,
factory: JavaStreamingContextFactory
): JavaStreamingContext = {
val ssc = StreamingContext.getOrCreate(checkpointPath, () => {
factory.create.ssc
})
new JavaStreamingContext(ssc)
}
/**
* Either recreate a StreamingContext from checkpoint data or create a new StreamingContext.
* If checkpoint data exists in the provided `checkpointPath`, then StreamingContext will be
* recreated from the checkpoint data. If the data does not exist, then the provided factory
* will be used to create a JavaStreamingContext.
*
* @param checkpointPath Checkpoint directory used in an earlier StreamingContext program
* @param factory JavaStreamingContextFactory object to create a new JavaStreamingContext
* @param hadoopConf Hadoop configuration if necessary for reading from any HDFS compatible
* file system
* @deprecated As of 1.4.0, replaced by `getOrCreate` without JavaStreamingContextFactory.
*/
@deprecated("use getOrCreate without JavaStreamingContextFactory", "1.4.0")
def getOrCreate(
checkpointPath: String,
hadoopConf: Configuration,
factory: JavaStreamingContextFactory
): JavaStreamingContext = {
val ssc = StreamingContext.getOrCreate(checkpointPath, () => {
factory.create.ssc
}, hadoopConf)
new JavaStreamingContext(ssc)
}
/**
* Either recreate a StreamingContext from checkpoint data or create a new StreamingContext.
* If checkpoint data exists in the provided `checkpointPath`, then StreamingContext will be
* recreated from the checkpoint data. If the data does not exist, then the provided factory
* will be used to create a JavaStreamingContext.
*
* @param checkpointPath Checkpoint directory used in an earlier StreamingContext program
* @param factory JavaStreamingContextFactory object to create a new JavaStreamingContext
* @param hadoopConf Hadoop configuration if necessary for reading from any HDFS compatible
* file system
* @param createOnError Whether to create a new JavaStreamingContext if there is an
* error in reading checkpoint data.
* @deprecated As of 1.4.0, replaced by `getOrCreate` without JavaStreamingContextFactory.
*/
@deprecated("use getOrCreate without JavaStreamingContextFactory", "1.4.0")
def getOrCreate(
checkpointPath: String,
hadoopConf: Configuration,
factory: JavaStreamingContextFactory,
createOnError: Boolean
): JavaStreamingContext = {
val ssc = StreamingContext.getOrCreate(checkpointPath, () => {
factory.create.ssc
}, hadoopConf, createOnError)
new JavaStreamingContext(ssc)
}
/**
* Either recreate a StreamingContext from checkpoint data or create a new StreamingContext.
* If checkpoint data exists in the provided `checkpointPath`, then StreamingContext will be
* recreated from the checkpoint data. If the data does not exist, then the provided factory
* will be used to create a JavaStreamingContext.
*
* @param checkpointPath Checkpoint directory used in an earlier JavaStreamingContext program
* @param creatingFunc Function to create a new JavaStreamingContext
*/
def getOrCreate(
checkpointPath: String,
creatingFunc: JFunction0[JavaStreamingContext]
): JavaStreamingContext = {
val ssc = StreamingContext.getOrCreate(checkpointPath, () => {
creatingFunc.call().ssc
})
new JavaStreamingContext(ssc)
}
/**
* Either recreate a StreamingContext from checkpoint data or create a new StreamingContext.
* If checkpoint data exists in the provided `checkpointPath`, then StreamingContext will be
* recreated from the checkpoint data. If the data does not exist, then the provided factory
* will be used to create a JavaStreamingContext.
*
* @param checkpointPath Checkpoint directory used in an earlier StreamingContext program
* @param creatingFunc Function to create a new JavaStreamingContext
* @param hadoopConf Hadoop configuration if necessary for reading from any HDFS compatible
* file system
*/
def getOrCreate(
checkpointPath: String,
creatingFunc: JFunction0[JavaStreamingContext],
hadoopConf: Configuration
): JavaStreamingContext = {
val ssc = StreamingContext.getOrCreate(checkpointPath, () => {
creatingFunc.call().ssc
}, hadoopConf)
new JavaStreamingContext(ssc)
}
/**
* Either recreate a StreamingContext from checkpoint data or create a new StreamingContext.
* If checkpoint data exists in the provided `checkpointPath`, then StreamingContext will be
* recreated from the checkpoint data. If the data does not exist, then the provided factory
* will be used to create a JavaStreamingContext.
*
* @param checkpointPath Checkpoint directory used in an earlier StreamingContext program
* @param creatingFunc Function to create a new JavaStreamingContext
* @param hadoopConf Hadoop configuration if necessary for reading from any HDFS compatible
* file system
* @param createOnError Whether to create a new JavaStreamingContext if there is an
* error in reading checkpoint data.
*/
def getOrCreate(
checkpointPath: String,
creatingFunc: JFunction0[JavaStreamingContext],
hadoopConf: Configuration,
createOnError: Boolean
): JavaStreamingContext = {
val ssc = StreamingContext.getOrCreate(checkpointPath, () => {
creatingFunc.call().ssc
}, hadoopConf, createOnError)
new JavaStreamingContext(ssc)
}
/**
* Find the JAR from which a given class was loaded, to make it easy for users to pass
* their JARs to StreamingContext.
*/
def jarOfClass(cls: Class[_]): Array[String] = SparkContext.jarOfClass(cls).toArray
}
/**
* Factory interface for creating a new JavaStreamingContext
*/
trait JavaStreamingContextFactory {
def create(): JavaStreamingContext
}
|