package com.bjsxt.scala;
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 groovy.lang.Tuple;
import scala.Tuple2;
import scala.actors.threadpool.Arrays;
public class SuanZi {
public static void main(String[] args) {
SparkConf conf=new SparkConf().setAppName("test").setMaster("local");
JavaSparkContext sc=new JavaSparkContext(conf);
JavaRDD<String> rdd1 = sc.textFile("./words");
JavaRDD<String> rdd2 = rdd1.flatMap(new FlatMapFunction<String, String>() {
@Override
public Iterable<String> call(String line) throws Exception {
// TODO Auto-generated method stub
return Arrays.asList(line.split(" "));
}
});
JavaPairRDD<String, Integer> rdd3 = rdd2.mapToPair(new PairFunction<String, String, Integer>() {
@Override
public Tuple2<String, Integer> call(String word) throws Exception {
// TODO Auto-generated method stub
return new Tuple2<String,Integer>(word,1);
}
});
JavaPairRDD<String, Integer> rdd4 = rdd3.reduceByKey(new Function2<Integer, Integer, Integer>() {
@Override
public Integer call(Integer v1, Integer v2) throws Exception {
// TODO Auto-generated method stub
return v1+v2;
}
});
JavaPairRDD<Integer, String> rdd5 = rdd4.mapToPair(new PairFunction<Tuple2<String,Integer>,Integer , String>() {
@Override
public Tuple2<Integer, String> call(Tuple2<String, Integer> tuple) throws Exception {
// TODO Auto-generated method stub
return new Tuple2<Integer,String>(tuple._2,tuple._1);
}
});
/**
* 排序
*/
JavaPairRDD<Integer, String> rdd6 = rdd5.sortByKey();
JavaPairRDD<String, Integer> result = rdd6.mapToPair(new PairFunction<Tuple2<Integer,String>, String,Integer>() {
@Override
public Tuple2<String, Integer> call(Tuple2<Integer, String> tuple) throws Exception {
// TODO Auto-generated method stub
return new Tuple2<String,Integer>(tuple._2,tuple._1);
}
});
result.foreach(new VoidFunction<Tuple2<String,Integer>>() {
@Override
public void call(Tuple2<String, Integer> arg0) throws Exception {
System.out.println(arg0);
}
});
}
}
Spark部分:Java版Wordcount(包括flatmap切割,maptopair转换,reducebykey排序,foreach遍历输出)【Java版纯代码】
最新推荐文章于 2022-05-05 15:27:13 发布