Spark Streaming---HDFSwordcount

package com.spark.streaming;

import java.util.Arrays;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.streaming.Durations;
import org.apache.spark.streaming.api.java.JavaDStream;
import org.apache.spark.streaming.api.java.JavaPairDStream;
import org.apache.spark.streaming.api.java.JavaStreamingContext;

import scala.Tuple2;

public class HDFSWordcount {

public static void main(String[] args) {
SparkConf conf = new SparkConf().setAppName("HDFSWordcount");
JavaStreamingContext jssc = new JavaStreamingContext(conf, Durations.seconds(5));

JavaDStream<String> lines = jssc.textFileStream("hdfs://node12:8020/Spark/Streaming/WordCount");
JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {

private static final long serialVersionUID = 1L;

@Override
public Iterable<String> call(String line) throws Exception {
return Arrays.asList(line.split(" "));
}
});
JavaPairDStream<String, Integer> pairs = words.mapToPair(new PairFunction<String, String, Integer>() {

private static final long serialVersionUID = 1L;

@Override
public Tuple2<String, Integer> call(String word) throws Exception {
return new Tuple2<String,Integer>(word, 1);
}
})<
4000
span class="hljs-comment">;
JavaPairDStream<String, Integer> wordcounts = pairs.reduceByKey(new Function2<Integer, Integer, Integer>() {

private static final long serialVersionUID = 1L;

@Override
public Integer call(Integer v1, Integer v2) throws Exception {
return v1 + v2;
}
});

wordcounts.print();

jssc.start();
jssc.awaitTermination();
jssc.close();
}
}

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