win7上用java开发spark_Win7 Eclipse 搭建spark java1.8(lambda)环境：WordCount helloworld例子...

[学习笔记]

Win7 Eclipse 搭建spark java1.8(lambda)环境：WordCount helloworld例子

lambda表达式是java8给我们带来的一个重量的新特性，借用lambda表达式可以让我们的程序设计更加简洁。

package com;

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.VoidFunction;

import scala.Tuple2;

import java.util.Arrays;

import java.util.List;

public class WordCountLambda {

public static void main(String[] args) {

SparkConf conf = new SparkConf().setAppName("WordCountLambda马克-to-win @ 马克java社区：").setMaster("local");

JavaSparkContext sc = new JavaSparkContext(conf);

JavaRDD lines = sc.textFile("E://temp//input//friend.txt");

JavaRDD words = lines.flatMap(line -> Arrays.asList(line.split(" ")));

JavaPairRDD wordAndOne = words.mapToPair(word -> new Tuple2<>(word, 1));

JavaPairRDD results = wordAndOne.reduceByKey((x, y) -> x + y);

/* 下面一句也能工作。*/

//       reduced.saveAsTextFile("E://temp//input//friend1.txt");

/*word:o1abc count:4

word:45 count:1

word:77 count:1*/

results.foreach(new VoidFunction>() {

public void call(Tuple2 tuple) throws Exception {

System.out.println("word:" + tuple._1 + " count:" + tuple._2);

}

});

/*resultsPair is (o1abc,4)

resultsPair is (45,1)

resultsPair is (77,1)*/

List> resultsPairs = results.collect();

for (Tuple2 resultsPair : resultsPairs) {