package com.bjsxt.cn;
import java.util.Arrays;
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.Function;
import scala.Tuple2;
public class SparkWordCount {
public static void main(String[] args) {
SparkConf conf=new SparkConf().setAppName("local").setMaster("local");
JavaSparkContext sc=new JavaSparkContext(conf);
JavaRDD<String> rdd1 = sc.textFile("./word");
JavaRDD<String> word = rdd1.flatMap(new FlatMapFunction<String, String>() {
@Override
public Iterable<String> call(String s) throws Exception {
return Arrays.asList(s.split(" "));
}
});
JavaPairRDD<String, Integer> map = word.mapToPair(new PairFunction<String, String, Integer>() {
@Override
public Tuple2<String, Integer> call(String s) throws Exception {
return new Tuple2<String, Integer>(s,1);
}
});
JavaPairRDD<String, Integer> reduce = map.reduceByKey(new Function2<Integer, Integer, Integer>() {
@Override
public Integer call(Integer v1, Integer v2) throws Exception {
return v1+v2;
}
});
JavaPairRDD<Integer, String> result = reduce.mapToPair(new PairFunction<Tuple2<String,Integer>, Integer, String>() {
@Override
public Tuple2<Integer, String> call(Tuple2<String, Integer> s) throws Exception {
return new Tuple2<Integer, String>(s._2, s._1);
}
});
JavaPairRDD<Integer, String> sort = result.sortByKey();
JavaPairRDD<String, Integer> res = sort.mapToPair(new PairFunction<Tuple2<Integer,String>, String, Integer>() {
@Override
public Tuple2<String, Integer> call(Tuple2<Integer, String> sd) throws Exception {
return new Tuple2<String, Integer>(sd._2, sd._1);
}
});
res.foreach(new VoidFunction<Tuple2<String,Integer>>() {
@Override
public void call(Tuple2<String, Integer> arg0) throws Exception {
System.out.println(arg0);
}
});
}
}
Spark写WordCount
猜你喜欢
转载自blog.csdn.net/wyqwilliam/article/details/82820223
今日推荐
周排行