spark实现简单的pagerank

/**
 * Created by Administrator on 2016/8/9 .
 */
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.api.java.function.PairFlatMapFunction;
import scala.Tuple2;

import java.util.*;

public class PageRank{
   
    public static void main(String[] args){
        SparkConf conf=new SparkConf();
        conf.setAppName("pagerank");
        conf.setMaster("local");
        conf.set("spark.testing.memory", "500000000");//设置运行内存大小
        JavaSparkContext sc=new JavaSparkContext(conf);
        //partitionBy()只对kv RDD起作用, 进行该操作后，将相同key值的数据放到同一机器上，并进行持久化操作，对后续循环中的join操作进行优化，使得省去join操作 shuffle的开销
        ArrayList<String> list=new ArrayList<String>(4);
        list.add("A,D");//网页之间的连接关系，A页面链接到网页D
        list.add("B,A");
        list.add(