SparkStreaming实现HDFS的wordCount(java版)

           利用sparkstreaming实现hdfs文件系统中的某个目录下的wordcount

代码如下：

package sparkTestJava;

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("wordcount").setMaster("local[2]");
JavaStreamingContext jssc = new JavaStreamingContext(conf,Durations.seconds(5));

JavaDStream<String> lines = jssc.textFileStream("hdfs://hadoop:9000/sparkTest");

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);
}

});

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.stop();
jssc.close();
}
}

在运行程序前先启动hdfs，spark，这里不再赘述
test-data.txt的内容为：

hadoop hadoop

hadoop1 hadoop1 hadoop1

hadoop2 hadoop2 hadoop2 hadoop2

hadoop3

spark spark

spark

spark1

先运行程序，然后再将测试文件test-data.txt传到hdfs中的对应的sparkTest目录下，这是可以看到结果如下：