UserView--第二种方式（避免第一种方式Set饱和），基于Spark算子的java代码实现

 

---

UserView--第二种方式（避免第一种方式Set饱和），基于Spark算子的java代码实现

 

测试数据

java代码

 package com.hzf.spark.study;

 import java.util.Map;
 import java.util.Set;

 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.Function;
 import org.apache.spark.api.java.function.PairFunction;
 import org.apache.spark.broadcast.Broadcast;

 import scala.Tuple2;

 public class UVAnalysis02 {
     public static void main(String[] args) {
         SparkConf conf = new SparkConf().setAppName("UV_ANA").setMaster("local")
                 .set("spark.testing.memory", "2147480000");
         @SuppressWarnings("resource")
         JavaSparkContext sc = new JavaSparkContext(conf);
         JavaRDD<String> logRDD = sc.textFile("userLog1");
         String str = "View";
         final Broadcast<String> broadcast = sc.broadcast(str);
         uvAnalyzeOptz(logRDD, broadcast);
     }

     private static void uvAnalyzeOptz(JavaRDD<String> logRDD, final Broadcast<String> broadcast) {
         JavaRDD<String> filteredLogRDD = logRDD.filter(new Function<String, Boolean>() {

             private static final long serialVersionUID = 1L;

             @Override
             public Boolean call(String v1) throws Exception {
                 String actionParam = broadcast.value();
                 String action = v1.split("\t")[5];
                 return actionParam.equals(action);
             }
         });

         JavaPairRDD<String, String> up2LogRDD = filteredLogRDD.mapToPair(new PairFunction<String, String, String>() {

             private static final long serialVersionUID = 1L;

             @Override
             public Tuple2<String, String> call(String val) throws Exception {
                 String[] splited = val.split("\t");
                 String userId = splited[2];
                 String pageId = splited[3];

                 return new Tuple2<String, String>(userId + "_" + pageId,null);
             }
         });

         JavaPairRDD<String, Iterable<String>> groupUp2LogRDD = up2LogRDD.groupByKey();

         Map<String, Object> countByKey = groupUp2LogRDD.mapToPair(new PairFunction<Tuple2<String,Iterable<String>>, String, String>() {

             private static final long serialVersionUID = 1L;

             @Override
             public Tuple2<String, String> call(Tuple2<String, Iterable<String>> tuple) throws Exception {
                 String pu = tuple._1;
                 String[] splited = pu.split("_");
                 String pageId = splited[1];
                 return new Tuple2<String, String>(pageId,null);
             }
         }).countByKey();

         Set<String> keySet = countByKey.keySet();
         for (String key : keySet) {
             System.out.println("PAGEID:"+key+"\tUV_COUNT："+countByKey.get(key));
         }
     }
 }

result