spark wordcount java_spark入门: wordcount-java

wordcount-java：

pom.xml文件如下:

junit

junit

3.8.1

test

org.apache.spark

spark-core_2.10

1.3.0

org.apache.spark

spark-sql_2.10

1.3.0

org.apache.spark

spark-hive_2.10

1.3.0

org.apache.spark

spark-streaming_2.10

1.3.0

org.apache.hadoop

hadoop-client

2.4.1

org.apache.spark

spark-streaming-kafka_2.10

1.3.0

package cn.spark.study.core;

import java.util.Arrays;

import org.apache.spark.SparkConf;

import org.apache.spark.api.java.JavaPairRDD;

import org.apache.spark.api.java.JavaRDD;

import org.apache.spark.api.java.JavaSparkContext;

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.api.java.function.VoidFunction;

import scala.Tuple2;

public class WordCount3 {

public static void main(String[] args) {

SparkConf conf=new SparkConf().setAppName("WorldCountLocal").setMaster("local");

JavaSparkContext sc=new JavaSparkContext(conf);

JavaRDD lines=sc.textFile("C:\\Users\\wanglonglong\\Desktop\\word.txt");

JavaRDD words=lines.flatMap(new FlatMapFunction() {

@Override

public Iterable call(String t) throws Exception {

// TODO Auto-generated method stub

return Arrays.asList(t.split(" "));

}

});

JavaPairRDD pairs = words.mapToPair(new PairFunction() {

private static final long serialVersionUID=1;

@Override

public Tuple2 call(String word) throws Exception {

return new Tuple2(word,1);

}

});

JavaPairRDD wordCounts = pairs.reduceByKey(

new Function2() {

private static final long serialVersionUID = 1L;

public Integer call(Integer v1, Integer v2) throws Exception {

return v1 + v2;

}

});

wordCounts.foreach(new VoidFunction>() {

private static final long serialVersionUID = 1L;

public void call(Tuple2 wordCount) throws Exception {

System.out.println("("+wordCount._1 + "," + wordCount._2 + " )");

}

});

sc.close();

}

}