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
|
/*
* 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.kafka
import kafka.common.TopicAndPartition
/**
* Represents any object that has a collection of [[OffsetRange]]s. This can be used to access the
* offset ranges in RDDs generated by the direct Kafka DStream (see
* [[KafkaUtils.createDirectStream()]]).
* {{{
* KafkaUtils.createDirectStream(...).foreachRDD { rdd =>
* val offsetRanges = rdd.asInstanceOf[HasOffsetRanges].offsetRanges
* ...
* }
* }}}
*/
trait HasOffsetRanges {
def offsetRanges: Array[OffsetRange]
}
/**
* Represents a range of offsets from a single Kafka TopicAndPartition. Instances of this class
* can be created with `OffsetRange.create()`.
* @param topic Kafka topic name
* @param partition Kafka partition id
* @param fromOffset Inclusive starting offset
* @param untilOffset Exclusive ending offset
*/
final class OffsetRange private(
val topic: String,
val partition: Int,
val fromOffset: Long,
val untilOffset: Long) extends Serializable {
import OffsetRange.OffsetRangeTuple
/** Kafka TopicAndPartition object, for convenience */
def topicAndPartition(): TopicAndPartition = TopicAndPartition(topic, partition)
/** Number of messages this OffsetRange refers to */
def count(): Long = untilOffset - fromOffset
override def equals(obj: Any): Boolean = obj match {
case that: OffsetRange =>
this.topic == that.topic &&
this.partition == that.partition &&
this.fromOffset == that.fromOffset &&
this.untilOffset == that.untilOffset
case _ => false
}
override def hashCode(): Int = {
toTuple.hashCode()
}
override def toString(): String = {
s"OffsetRange(topic: '$topic', partition: $partition, range: [$fromOffset -> $untilOffset])"
}
/** this is to avoid ClassNotFoundException during checkpoint restore */
private[streaming]
def toTuple: OffsetRangeTuple = (topic, partition, fromOffset, untilOffset)
}
/**
* Companion object the provides methods to create instances of [[OffsetRange]].
*/
object OffsetRange {
def create(topic: String, partition: Int, fromOffset: Long, untilOffset: Long): OffsetRange =
new OffsetRange(topic, partition, fromOffset, untilOffset)
def create(
topicAndPartition: TopicAndPartition,
fromOffset: Long,
untilOffset: Long): OffsetRange =
new OffsetRange(topicAndPartition.topic, topicAndPartition.partition, fromOffset, untilOffset)
def apply(topic: String, partition: Int, fromOffset: Long, untilOffset: Long): OffsetRange =
new OffsetRange(topic, partition, fromOffset, untilOffset)
def apply(
topicAndPartition: TopicAndPartition,
fromOffset: Long,
untilOffset: Long): OffsetRange =
new OffsetRange(topicAndPartition.topic, topicAndPartition.partition, fromOffset, untilOffset)
/** this is to avoid ClassNotFoundException during checkpoint restore */
private[kafka]
type OffsetRangeTuple = (String, Int, Long, Long)
private[kafka]
def apply(t: OffsetRangeTuple) =
new OffsetRange(t._1, t._2, t._3, t._4)
}
|
