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
|
/*
* 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.rdd
import java.nio.ByteBuffer
import java.util.Date
import java.text.SimpleDateFormat
import java.util.{HashMap => JHashMap}
import scala.collection.{mutable, Map}
import scala.collection.mutable.ArrayBuffer
import scala.collection.JavaConversions._
import scala.reflect.{ClassTag, classTag}
import org.apache.hadoop.mapred._
import org.apache.hadoop.io.compress.CompressionCodec
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.Path
import org.apache.hadoop.io.SequenceFile.CompressionType
import org.apache.hadoop.mapred.FileOutputFormat
import org.apache.hadoop.mapred.OutputFormat
import org.apache.hadoop.mapreduce.{OutputFormat => NewOutputFormat}
import org.apache.hadoop.mapreduce.lib.output.{FileOutputFormat => NewFileOutputFormat}
import org.apache.hadoop.mapreduce.SparkHadoopMapReduceUtil
import org.apache.hadoop.mapreduce.{Job => NewAPIHadoopJob}
import org.apache.hadoop.mapreduce.{RecordWriter => NewRecordWriter}
import com.clearspring.analytics.stream.cardinality.HyperLogLog
import org.apache.spark._
import org.apache.spark.SparkContext._
import org.apache.spark.partial.{BoundedDouble, PartialResult}
import org.apache.spark.Aggregator
import org.apache.spark.Partitioner
import org.apache.spark.Partitioner.defaultPartitioner
import org.apache.spark.util.SerializableHyperLogLog
/**
* Extra functions available on RDDs of (key, value) pairs through an implicit conversion.
* Import `org.apache.spark.SparkContext._` at the top of your program to use these functions.
*/
class PairRDDFunctions[K: ClassTag, V: ClassTag](self: RDD[(K, V)])
extends Logging
with SparkHadoopMapReduceUtil
with Serializable {
/**
* Generic function to combine the elements for each key using a custom set of aggregation
* functions. Turns an RDD[(K, V)] into a result of type RDD[(K, C)], for a "combined type" C
* Note that V and C can be different -- for example, one might group an RDD of type
* (Int, Int) into an RDD of type (Int, Seq[Int]). Users provide three functions:
*
* - `createCombiner`, which turns a V into a C (e.g., creates a one-element list)
* - `mergeValue`, to merge a V into a C (e.g., adds it to the end of a list)
* - `mergeCombiners`, to combine two C's into a single one.
*
* In addition, users can control the partitioning of the output RDD, and whether to perform
* map-side aggregation (if a mapper can produce multiple items with the same key).
*/
def combineByKey[C](createCombiner: V => C,
mergeValue: (C, V) => C,
mergeCombiners: (C, C) => C,
partitioner: Partitioner,
mapSideCombine: Boolean = true,
serializerClass: String = null): RDD[(K, C)] = {
if (getKeyClass().isArray) {
if (mapSideCombine) {
throw new SparkException("Cannot use map-side combining with array keys.")
}
if (partitioner.isInstanceOf[HashPartitioner]) {
throw new SparkException("Default partitioner cannot partition array keys.")
}
}
val aggregator = new Aggregator[K, V, C](createCombiner, mergeValue, mergeCombiners)
if (self.partitioner == Some(partitioner)) {
self.mapPartitionsWithContext((context, iter) => {
new InterruptibleIterator(context, aggregator.combineValuesByKey(iter))
}, preservesPartitioning = true)
} else if (mapSideCombine) {
val combined = self.mapPartitions(aggregator.combineValuesByKey, preservesPartitioning = true)
val partitioned = new ShuffledRDD[K, C, (K, C)](combined, partitioner)
.setSerializer(serializerClass)
partitioned.mapPartitionsWithContext((context, iter) => {
new InterruptibleIterator(context, aggregator.combineCombinersByKey(iter))
}, preservesPartitioning = true)
} else {
// Don't apply map-side combiner.
// A sanity check to make sure mergeCombiners is not defined.
assert(mergeCombiners == null)
val values = new ShuffledRDD[K, V, (K, V)](self, partitioner).setSerializer(serializerClass)
values.mapPartitionsWithContext((context, iter) => {
new InterruptibleIterator(context, aggregator.combineValuesByKey(iter))
}, preservesPartitioning = true)
}
}
/**
* Simplified version of combineByKey that hash-partitions the output RDD.
*/
def combineByKey[C](createCombiner: V => C,
mergeValue: (C, V) => C,
mergeCombiners: (C, C) => C,
numPartitions: Int): RDD[(K, C)] = {
combineByKey(createCombiner, mergeValue, mergeCombiners, new HashPartitioner(numPartitions))
}
/**
* Merge the values for each key using an associative function and a neutral "zero value" which may
* be added to the result an arbitrary number of times, and must not change the result (e.g., Nil for
* list concatenation, 0 for addition, or 1 for multiplication.).
*/
def foldByKey(zeroValue: V, partitioner: Partitioner)(func: (V, V) => V): RDD[(K, V)] = {
// Serialize the zero value to a byte array so that we can get a new clone of it on each key
val zeroBuffer = SparkEnv.get.closureSerializer.newInstance().serialize(zeroValue)
val zeroArray = new Array[Byte](zeroBuffer.limit)
zeroBuffer.get(zeroArray)
// When deserializing, use a lazy val to create just one instance of the serializer per task
lazy val cachedSerializer = SparkEnv.get.closureSerializer.newInstance()
def createZero() = cachedSerializer.deserialize[V](ByteBuffer.wrap(zeroArray))
combineByKey[V]((v: V) => func(createZero(), v), func, func, partitioner)
}
/**
* Merge the values for each key using an associative function and a neutral "zero value" which may
* be added to the result an arbitrary number of times, and must not change the result (e.g., Nil for
* list concatenation, 0 for addition, or 1 for multiplication.).
*/
def foldByKey(zeroValue: V, numPartitions: Int)(func: (V, V) => V): RDD[(K, V)] = {
foldByKey(zeroValue, new HashPartitioner(numPartitions))(func)
}
/**
* Merge the values for each key using an associative function and a neutral "zero value" which may
* be added to the result an arbitrary number of times, and must not change the result (e.g., Nil for
* list concatenation, 0 for addition, or 1 for multiplication.).
*/
def foldByKey(zeroValue: V)(func: (V, V) => V): RDD[(K, V)] = {
foldByKey(zeroValue, defaultPartitioner(self))(func)
}
/**
* Merge the values for each key using an associative reduce function. This will also perform
* the merging locally on each mapper before sending results to a reducer, similarly to a
* "combiner" in MapReduce.
*/
def reduceByKey(partitioner: Partitioner, func: (V, V) => V): RDD[(K, V)] = {
combineByKey[V]((v: V) => v, func, func, partitioner)
}
/**
* Merge the values for each key using an associative reduce function, but return the results
* immediately to the master as a Map. This will also perform the merging locally on each mapper
* before sending results to a reducer, similarly to a "combiner" in MapReduce.
*/
def reduceByKeyLocally(func: (V, V) => V): Map[K, V] = {
if (getKeyClass().isArray) {
throw new SparkException("reduceByKeyLocally() does not support array keys")
}
def reducePartition(iter: Iterator[(K, V)]): Iterator[JHashMap[K, V]] = {
val map = new JHashMap[K, V]
iter.foreach { case (k, v) =>
val old = map.get(k)
map.put(k, if (old == null) v else func(old, v))
}
Iterator(map)
}
def mergeMaps(m1: JHashMap[K, V], m2: JHashMap[K, V]): JHashMap[K, V] = {
m2.foreach { case (k, v) =>
val old = m1.get(k)
m1.put(k, if (old == null) v else func(old, v))
}
m1
}
self.mapPartitions(reducePartition).reduce(mergeMaps)
}
/** Alias for reduceByKeyLocally */
def reduceByKeyToDriver(func: (V, V) => V): Map[K, V] = reduceByKeyLocally(func)
/** Count the number of elements for each key, and return the result to the master as a Map. */
def countByKey(): Map[K, Long] = self.map(_._1).countByValue()
/**
* (Experimental) Approximate version of countByKey that can return a partial result if it does
* not finish within a timeout.
*/
def countByKeyApprox(timeout: Long, confidence: Double = 0.95)
: PartialResult[Map[K, BoundedDouble]] = {
self.map(_._1).countByValueApprox(timeout, confidence)
}
/**
* Return approximate number of distinct values for each key in this RDD.
* The accuracy of approximation can be controlled through the relative standard deviation
* (relativeSD) parameter, which also controls the amount of memory used. Lower values result in
* more accurate counts but increase the memory footprint and vise versa. Uses the provided
* Partitioner to partition the output RDD.
*/
def countApproxDistinctByKey(relativeSD: Double, partitioner: Partitioner): RDD[(K, Long)] = {
val createHLL = (v: V) => new SerializableHyperLogLog(new HyperLogLog(relativeSD)).add(v)
val mergeValueHLL = (hll: SerializableHyperLogLog, v: V) => hll.add(v)
val mergeHLL = (h1: SerializableHyperLogLog, h2: SerializableHyperLogLog) => h1.merge(h2)
combineByKey(createHLL, mergeValueHLL, mergeHLL, partitioner).mapValues(_.value.cardinality())
}
/**
* Return approximate number of distinct values for each key in this RDD.
* The accuracy of approximation can be controlled through the relative standard deviation
* (relativeSD) parameter, which also controls the amount of memory used. Lower values result in
* more accurate counts but increase the memory footprint and vise versa. HashPartitions the
* output RDD into numPartitions.
*
*/
def countApproxDistinctByKey(relativeSD: Double, numPartitions: Int): RDD[(K, Long)] = {
countApproxDistinctByKey(relativeSD, new HashPartitioner(numPartitions))
}
/**
* Return approximate number of distinct values for each key this RDD.
* The accuracy of approximation can be controlled through the relative standard deviation
* (relativeSD) parameter, which also controls the amount of memory used. Lower values result in
* more accurate counts but increase the memory footprint and vise versa. The default value of
* relativeSD is 0.05. Hash-partitions the output RDD using the existing partitioner/parallelism
* level.
*/
def countApproxDistinctByKey(relativeSD: Double = 0.05): RDD[(K, Long)] = {
countApproxDistinctByKey(relativeSD, defaultPartitioner(self))
}
/**
* Merge the values for each key using an associative reduce function. This will also perform
* the merging locally on each mapper before sending results to a reducer, similarly to a
* "combiner" in MapReduce. Output will be hash-partitioned with numPartitions partitions.
*/
def reduceByKey(func: (V, V) => V, numPartitions: Int): RDD[(K, V)] = {
reduceByKey(new HashPartitioner(numPartitions), func)
}
/**
* Group the values for each key in the RDD into a single sequence. Allows controlling the
* partitioning of the resulting key-value pair RDD by passing a Partitioner.
*/
def groupByKey(partitioner: Partitioner): RDD[(K, Seq[V])] = {
// groupByKey shouldn't use map side combine because map side combine does not
// reduce the amount of data shuffled and requires all map side data be inserted
// into a hash table, leading to more objects in the old gen.
def createCombiner(v: V) = ArrayBuffer(v)
def mergeValue(buf: ArrayBuffer[V], v: V) = buf += v
val bufs = combineByKey[ArrayBuffer[V]](
createCombiner _, mergeValue _, null, partitioner, mapSideCombine=false)
bufs.asInstanceOf[RDD[(K, Seq[V])]]
}
/**
* Group the values for each key in the RDD into a single sequence. Hash-partitions the
* resulting RDD with into `numPartitions` partitions.
*/
def groupByKey(numPartitions: Int): RDD[(K, Seq[V])] = {
groupByKey(new HashPartitioner(numPartitions))
}
/**
* Return a copy of the RDD partitioned using the specified partitioner.
*/
def partitionBy(partitioner: Partitioner): RDD[(K, V)] = {
if (getKeyClass().isArray && partitioner.isInstanceOf[HashPartitioner]) {
throw new SparkException("Default partitioner cannot partition array keys.")
}
new ShuffledRDD[K, V, (K, V)](self, partitioner)
}
/**
* Return an RDD containing all pairs of elements with matching keys in `this` and `other`. Each
* pair of elements will be returned as a (k, (v1, v2)) tuple, where (k, v1) is in `this` and
* (k, v2) is in `other`. Uses the given Partitioner to partition the output RDD.
*/
def join[W](other: RDD[(K, W)], partitioner: Partitioner): RDD[(K, (V, W))] = {
this.cogroup(other, partitioner).flatMapValues { case (vs, ws) =>
for (v <- vs.iterator; w <- ws.iterator) yield (v, w)
}
}
/**
* Perform a left outer join of `this` and `other`. For each element (k, v) in `this`, the
* resulting RDD will either contain all pairs (k, (v, Some(w))) for w in `other`, or the
* pair (k, (v, None)) if no elements in `other` have key k. Uses the given Partitioner to
* partition the output RDD.
*/
def leftOuterJoin[W](other: RDD[(K, W)], partitioner: Partitioner): RDD[(K, (V, Option[W]))] = {
this.cogroup(other, partitioner).flatMapValues { case (vs, ws) =>
if (ws.isEmpty) {
vs.iterator.map(v => (v, None))
} else {
for (v <- vs.iterator; w <- ws.iterator) yield (v, Some(w))
}
}
}
/**
* Perform a right outer join of `this` and `other`. For each element (k, w) in `other`, the
* resulting RDD will either contain all pairs (k, (Some(v), w)) for v in `this`, or the
* pair (k, (None, w)) if no elements in `this` have key k. Uses the given Partitioner to
* partition the output RDD.
*/
def rightOuterJoin[W](other: RDD[(K, W)], partitioner: Partitioner)
: RDD[(K, (Option[V], W))] = {
this.cogroup(other, partitioner).flatMapValues { case (vs, ws) =>
if (vs.isEmpty) {
ws.iterator.map(w => (None, w))
} else {
for (v <- vs.iterator; w <- ws.iterator) yield (Some(v), w)
}
}
}
/**
* Simplified version of combineByKey that hash-partitions the resulting RDD using the
* existing partitioner/parallelism level.
*/
def combineByKey[C](createCombiner: V => C, mergeValue: (C, V) => C, mergeCombiners: (C, C) => C)
: RDD[(K, C)] = {
combineByKey(createCombiner, mergeValue, mergeCombiners, defaultPartitioner(self))
}
/**
* Merge the values for each key using an associative reduce function. This will also perform
* the merging locally on each mapper before sending results to a reducer, similarly to a
* "combiner" in MapReduce. Output will be hash-partitioned with the existing partitioner/
* parallelism level.
*/
def reduceByKey(func: (V, V) => V): RDD[(K, V)] = {
reduceByKey(defaultPartitioner(self), func)
}
/**
* Group the values for each key in the RDD into a single sequence. Hash-partitions the
* resulting RDD with the existing partitioner/parallelism level.
*/
def groupByKey(): RDD[(K, Seq[V])] = {
groupByKey(defaultPartitioner(self))
}
/**
* Return an RDD containing all pairs of elements with matching keys in `this` and `other`. Each
* pair of elements will be returned as a (k, (v1, v2)) tuple, where (k, v1) is in `this` and
* (k, v2) is in `other`. Performs a hash join across the cluster.
*/
def join[W](other: RDD[(K, W)]): RDD[(K, (V, W))] = {
join(other, defaultPartitioner(self, other))
}
/**
* Return an RDD containing all pairs of elements with matching keys in `this` and `other`. Each
* pair of elements will be returned as a (k, (v1, v2)) tuple, where (k, v1) is in `this` and
* (k, v2) is in `other`. Performs a hash join across the cluster.
*/
def join[W](other: RDD[(K, W)], numPartitions: Int): RDD[(K, (V, W))] = {
join(other, new HashPartitioner(numPartitions))
}
/**
* Perform a left outer join of `this` and `other`. For each element (k, v) in `this`, the
* resulting RDD will either contain all pairs (k, (v, Some(w))) for w in `other`, or the
* pair (k, (v, None)) if no elements in `other` have key k. Hash-partitions the output
* using the existing partitioner/parallelism level.
*/
def leftOuterJoin[W](other: RDD[(K, W)]): RDD[(K, (V, Option[W]))] = {
leftOuterJoin(other, defaultPartitioner(self, other))
}
/**
* Perform a left outer join of `this` and `other`. For each element (k, v) in `this`, the
* resulting RDD will either contain all pairs (k, (v, Some(w))) for w in `other`, or the
* pair (k, (v, None)) if no elements in `other` have key k. Hash-partitions the output
* into `numPartitions` partitions.
*/
def leftOuterJoin[W](other: RDD[(K, W)], numPartitions: Int): RDD[(K, (V, Option[W]))] = {
leftOuterJoin(other, new HashPartitioner(numPartitions))
}
/**
* Perform a right outer join of `this` and `other`. For each element (k, w) in `other`, the
* resulting RDD will either contain all pairs (k, (Some(v), w)) for v in `this`, or the
* pair (k, (None, w)) if no elements in `this` have key k. Hash-partitions the resulting
* RDD using the existing partitioner/parallelism level.
*/
def rightOuterJoin[W](other: RDD[(K, W)]): RDD[(K, (Option[V], W))] = {
rightOuterJoin(other, defaultPartitioner(self, other))
}
/**
* Perform a right outer join of `this` and `other`. For each element (k, w) in `other`, the
* resulting RDD will either contain all pairs (k, (Some(v), w)) for v in `this`, or the
* pair (k, (None, w)) if no elements in `this` have key k. Hash-partitions the resulting
* RDD into the given number of partitions.
*/
def rightOuterJoin[W](other: RDD[(K, W)], numPartitions: Int): RDD[(K, (Option[V], W))] = {
rightOuterJoin(other, new HashPartitioner(numPartitions))
}
/**
* Return the key-value pairs in this RDD to the master as a Map.
*/
def collectAsMap(): Map[K, V] = {
val data = self.toArray()
val map = new mutable.HashMap[K, V]
map.sizeHint(data.length)
data.foreach { case (k, v) => map.put(k, v) }
map
}
/**
* Pass each value in the key-value pair RDD through a map function without changing the keys;
* this also retains the original RDD's partitioning.
*/
def mapValues[U](f: V => U): RDD[(K, U)] = {
val cleanF = self.context.clean(f)
new MappedValuesRDD(self, cleanF)
}
/**
* Pass each value in the key-value pair RDD through a flatMap function without changing the
* keys; this also retains the original RDD's partitioning.
*/
def flatMapValues[U](f: V => TraversableOnce[U]): RDD[(K, U)] = {
val cleanF = self.context.clean(f)
new FlatMappedValuesRDD(self, cleanF)
}
/**
* For each key k in `this` or `other`, return a resulting RDD that contains a tuple with the
* list of values for that key in `this` as well as `other`.
*/
def cogroup[W](other: RDD[(K, W)], partitioner: Partitioner): RDD[(K, (Seq[V], Seq[W]))] = {
if (partitioner.isInstanceOf[HashPartitioner] && getKeyClass().isArray) {
throw new SparkException("Default partitioner cannot partition array keys.")
}
val cg = new CoGroupedRDD[K](Seq(self, other), partitioner)
val prfs = new PairRDDFunctions[K, Seq[Seq[_]]](cg)(classTag[K], ClassTags.seqSeqClassTag)
prfs.mapValues { case Seq(vs, ws) =>
(vs.asInstanceOf[Seq[V]], ws.asInstanceOf[Seq[W]])
}
}
/**
* For each key k in `this` or `other1` or `other2`, return a resulting RDD that contains a
* tuple with the list of values for that key in `this`, `other1` and `other2`.
*/
def cogroup[W1, W2](other1: RDD[(K, W1)], other2: RDD[(K, W2)], partitioner: Partitioner)
: RDD[(K, (Seq[V], Seq[W1], Seq[W2]))] = {
if (partitioner.isInstanceOf[HashPartitioner] && getKeyClass().isArray) {
throw new SparkException("Default partitioner cannot partition array keys.")
}
val cg = new CoGroupedRDD[K](Seq(self, other1, other2), partitioner)
val prfs = new PairRDDFunctions[K, Seq[Seq[_]]](cg)(classTag[K], ClassTags.seqSeqClassTag)
prfs.mapValues { case Seq(vs, w1s, w2s) =>
(vs.asInstanceOf[Seq[V]], w1s.asInstanceOf[Seq[W1]], w2s.asInstanceOf[Seq[W2]])
}
}
/**
* For each key k in `this` or `other`, return a resulting RDD that contains a tuple with the
* list of values for that key in `this` as well as `other`.
*/
def cogroup[W](other: RDD[(K, W)]): RDD[(K, (Seq[V], Seq[W]))] = {
cogroup(other, defaultPartitioner(self, other))
}
/**
* For each key k in `this` or `other1` or `other2`, return a resulting RDD that contains a
* tuple with the list of values for that key in `this`, `other1` and `other2`.
*/
def cogroup[W1, W2](other1: RDD[(K, W1)], other2: RDD[(K, W2)])
: RDD[(K, (Seq[V], Seq[W1], Seq[W2]))] = {
cogroup(other1, other2, defaultPartitioner(self, other1, other2))
}
/**
* For each key k in `this` or `other`, return a resulting RDD that contains a tuple with the
* list of values for that key in `this` as well as `other`.
*/
def cogroup[W](other: RDD[(K, W)], numPartitions: Int): RDD[(K, (Seq[V], Seq[W]))] = {
cogroup(other, new HashPartitioner(numPartitions))
}
/**
* For each key k in `this` or `other1` or `other2`, return a resulting RDD that contains a
* tuple with the list of values for that key in `this`, `other1` and `other2`.
*/
def cogroup[W1, W2](other1: RDD[(K, W1)], other2: RDD[(K, W2)], numPartitions: Int)
: RDD[(K, (Seq[V], Seq[W1], Seq[W2]))] = {
cogroup(other1, other2, new HashPartitioner(numPartitions))
}
/** Alias for cogroup. */
def groupWith[W](other: RDD[(K, W)]): RDD[(K, (Seq[V], Seq[W]))] = {
cogroup(other, defaultPartitioner(self, other))
}
/** Alias for cogroup. */
def groupWith[W1, W2](other1: RDD[(K, W1)], other2: RDD[(K, W2)])
: RDD[(K, (Seq[V], Seq[W1], Seq[W2]))] = {
cogroup(other1, other2, defaultPartitioner(self, other1, other2))
}
/**
* Return an RDD with the pairs from `this` whose keys are not in `other`.
*
* Uses `this` partitioner/partition size, because even if `other` is huge, the resulting
* RDD will be <= us.
*/
def subtractByKey[W: ClassTag](other: RDD[(K, W)]): RDD[(K, V)] =
subtractByKey(other, self.partitioner.getOrElse(new HashPartitioner(self.partitions.size)))
/** Return an RDD with the pairs from `this` whose keys are not in `other`. */
def subtractByKey[W: ClassTag](other: RDD[(K, W)], numPartitions: Int): RDD[(K, V)] =
subtractByKey(other, new HashPartitioner(numPartitions))
/** Return an RDD with the pairs from `this` whose keys are not in `other`. */
def subtractByKey[W: ClassTag](other: RDD[(K, W)], p: Partitioner): RDD[(K, V)] =
new SubtractedRDD[K, V, W](self, other, p)
/**
* Return the list of values in the RDD for key `key`. This operation is done efficiently if the
* RDD has a known partitioner by only searching the partition that the key maps to.
*/
def lookup(key: K): Seq[V] = {
self.partitioner match {
case Some(p) =>
val index = p.getPartition(key)
def process(it: Iterator[(K, V)]): Seq[V] = {
val buf = new ArrayBuffer[V]
for ((k, v) <- it if k == key) {
buf += v
}
buf
}
val res = self.context.runJob(self, process _, Array(index), false)
res(0)
case None =>
self.filter(_._1 == key).map(_._2).collect()
}
}
/**
* Output the RDD to any Hadoop-supported file system, using a Hadoop `OutputFormat` class
* supporting the key and value types K and V in this RDD.
*/
def saveAsHadoopFile[F <: OutputFormat[K, V]](path: String)(implicit fm: ClassTag[F]) {
saveAsHadoopFile(path, getKeyClass, getValueClass, fm.runtimeClass.asInstanceOf[Class[F]])
}
/**
* Output the RDD to any Hadoop-supported file system, using a Hadoop `OutputFormat` class
* supporting the key and value types K and V in this RDD. Compress the result with the
* supplied codec.
*/
def saveAsHadoopFile[F <: OutputFormat[K, V]](
path: String, codec: Class[_ <: CompressionCodec]) (implicit fm: ClassTag[F]) {
saveAsHadoopFile(path, getKeyClass, getValueClass, fm.runtimeClass.asInstanceOf[Class[F]], codec)
}
/**
* Output the RDD to any Hadoop-supported file system, using a new Hadoop API `OutputFormat`
* (mapreduce.OutputFormat) object supporting the key and value types K and V in this RDD.
*/
def saveAsNewAPIHadoopFile[F <: NewOutputFormat[K, V]](path: String)(implicit fm: ClassTag[F]) {
saveAsNewAPIHadoopFile(path, getKeyClass, getValueClass, fm.runtimeClass.asInstanceOf[Class[F]])
}
/**
* Output the RDD to any Hadoop-supported file system, using a new Hadoop API `OutputFormat`
* (mapreduce.OutputFormat) object supporting the key and value types K and V in this RDD.
*/
def saveAsNewAPIHadoopFile(
path: String,
keyClass: Class[_],
valueClass: Class[_],
outputFormatClass: Class[_ <: NewOutputFormat[_, _]],
conf: Configuration = self.context.hadoopConfiguration) {
val job = new NewAPIHadoopJob(conf)
job.setOutputKeyClass(keyClass)
job.setOutputValueClass(valueClass)
val wrappedConf = new SerializableWritable(job.getConfiguration)
NewFileOutputFormat.setOutputPath(job, new Path(path))
val formatter = new SimpleDateFormat("yyyyMMddHHmm")
val jobtrackerID = formatter.format(new Date())
val stageId = self.id
def writeShard(context: TaskContext, iter: Iterator[(K,V)]): Int = {
// Hadoop wants a 32-bit task attempt ID, so if ours is bigger than Int.MaxValue, roll it
// around by taking a mod. We expect that no task will be attempted 2 billion times.
val attemptNumber = (context.attemptId % Int.MaxValue).toInt
/* "reduce task" <split #> <attempt # = spark task #> */
val attemptId = newTaskAttemptID(jobtrackerID, stageId, false, context.partitionId, attemptNumber)
val hadoopContext = newTaskAttemptContext(wrappedConf.value, attemptId)
val format = outputFormatClass.newInstance
val committer = format.getOutputCommitter(hadoopContext)
committer.setupTask(hadoopContext)
val writer = format.getRecordWriter(hadoopContext).asInstanceOf[NewRecordWriter[K,V]]
while (iter.hasNext) {
val (k, v) = iter.next()
writer.write(k, v)
}
writer.close(hadoopContext)
committer.commitTask(hadoopContext)
return 1
}
val jobFormat = outputFormatClass.newInstance
/* apparently we need a TaskAttemptID to construct an OutputCommitter;
* however we're only going to use this local OutputCommitter for
* setupJob/commitJob, so we just use a dummy "map" task.
*/
val jobAttemptId = newTaskAttemptID(jobtrackerID, stageId, true, 0, 0)
val jobTaskContext = newTaskAttemptContext(wrappedConf.value, jobAttemptId)
val jobCommitter = jobFormat.getOutputCommitter(jobTaskContext)
jobCommitter.setupJob(jobTaskContext)
val count = self.context.runJob(self, writeShard _).sum
jobCommitter.commitJob(jobTaskContext)
jobCommitter.cleanupJob(jobTaskContext)
}
/**
* Output the RDD to any Hadoop-supported file system, using a Hadoop `OutputFormat` class
* supporting the key and value types K and V in this RDD. Compress with the supplied codec.
*/
def saveAsHadoopFile(
path: String,
keyClass: Class[_],
valueClass: Class[_],
outputFormatClass: Class[_ <: OutputFormat[_, _]],
codec: Class[_ <: CompressionCodec]) {
saveAsHadoopFile(path, keyClass, valueClass, outputFormatClass,
new JobConf(self.context.hadoopConfiguration), Some(codec))
}
/**
* Output the RDD to any Hadoop-supported file system, using a Hadoop `OutputFormat` class
* supporting the key and value types K and V in this RDD.
*/
def saveAsHadoopFile(
path: String,
keyClass: Class[_],
valueClass: Class[_],
outputFormatClass: Class[_ <: OutputFormat[_, _]],
conf: JobConf = new JobConf(self.context.hadoopConfiguration),
codec: Option[Class[_ <: CompressionCodec]] = None) {
conf.setOutputKeyClass(keyClass)
conf.setOutputValueClass(valueClass)
// conf.setOutputFormat(outputFormatClass) // Doesn't work in Scala 2.9 due to what may be a generics bug
conf.set("mapred.output.format.class", outputFormatClass.getName)
for (c <- codec) {
conf.setCompressMapOutput(true)
conf.set("mapred.output.compress", "true")
conf.setMapOutputCompressorClass(c)
conf.set("mapred.output.compression.codec", c.getCanonicalName)
conf.set("mapred.output.compression.type", CompressionType.BLOCK.toString)
}
conf.setOutputCommitter(classOf[FileOutputCommitter])
FileOutputFormat.setOutputPath(conf, SparkHadoopWriter.createPathFromString(path, conf))
saveAsHadoopDataset(conf)
}
/**
* Output the RDD to any Hadoop-supported storage system, using a Hadoop JobConf object for
* that storage system. The JobConf should set an OutputFormat and any output paths required
* (e.g. a table name to write to) in the same way as it would be configured for a Hadoop
* MapReduce job.
*/
def saveAsHadoopDataset(conf: JobConf) {
val outputFormatClass = conf.getOutputFormat
val keyClass = conf.getOutputKeyClass
val valueClass = conf.getOutputValueClass
if (outputFormatClass == null) {
throw new SparkException("Output format class not set")
}
if (keyClass == null) {
throw new SparkException("Output key class not set")
}
if (valueClass == null) {
throw new SparkException("Output value class not set")
}
logInfo("Saving as hadoop file of type (" + keyClass.getSimpleName+ ", " + valueClass.getSimpleName+ ")")
val writer = new SparkHadoopWriter(conf)
writer.preSetup()
def writeToFile(context: TaskContext, iter: Iterator[(K, V)]) {
// Hadoop wants a 32-bit task attempt ID, so if ours is bigger than Int.MaxValue, roll it
// around by taking a mod. We expect that no task will be attempted 2 billion times.
val attemptNumber = (context.attemptId % Int.MaxValue).toInt
writer.setup(context.stageId, context.partitionId, attemptNumber)
writer.open()
var count = 0
while(iter.hasNext) {
val record = iter.next()
count += 1
writer.write(record._1.asInstanceOf[AnyRef], record._2.asInstanceOf[AnyRef])
}
writer.close()
writer.commit()
}
self.context.runJob(self, writeToFile _)
writer.commitJob()
writer.cleanup()
}
/**
* Return an RDD with the keys of each tuple.
*/
def keys: RDD[K] = self.map(_._1)
/**
* Return an RDD with the values of each tuple.
*/
def values: RDD[V] = self.map(_._2)
private[spark] def getKeyClass() = implicitly[ClassTag[K]].runtimeClass
private[spark] def getValueClass() = implicitly[ClassTag[V]].runtimeClass
}
private[spark] object ClassTags {
val seqSeqClassTag = classTag[Seq[Seq[_]]]
}
|