1.源数据
hello word
hello java
hello python
hello waad
hello word
hello java
hello python
hello waad
hello word
hello java
hello python
hello waad
hello word
hello java
hello python
hello waad
hello word
hello java
hello python
hello waad
2.Java版
package com.bjsxt.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.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;
import scala.actors.threadpool.Arrays;
public class Test {
public static void main(String[] args) {
SparkConf conf = new SparkConf().setAppName("test").setMaster("local");
JavaSparkConte