Spark---Word Count

Point 1：Java版本

package com.Spark.wordcount;
//use spark-assembly-1.6.0-hadoop2.4.0.jar
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.Tuple2;
import scala.collection.generic.BitOperations.Int;

public class wordcount {
    public static void main(String[] args) {
        SparkConf sc = new SparkConf().setAppName("Word Count").setMaster("local");
        JavaSparkContext context = new JavaSparkContext(sc);
        JavaRDD<String> input = context.textFile(args[0]);
        JavaRDD<String> words = input.flatMap(new FlatMapFunction<String, String>() {
            private static final long serialVersionUID = 1L;
            public Iterable<String> call(String line) throws Exception {
                return Arrays.asList(line.split(" "));
            }
        });
        JavaPairRDD<String, Integer> pairs = words.mapToPair(new PairFunction<String, String, Integer>() {
            private static final long serialVersionUID = 1L;
            public Tuple2<String, Integer> call(String word) throws Exception {
                return new Tuple2<String, Integer>(word, 1);
            }
        });
        JavaPairRDD<String, Integer> result = pairs.reduceByKey(new Function2<Integer, Integer, Integer>() {
            private static final long serialVersionUID = 1L;
            public Integer call(Integer v1, Integer v2) throws Exception {
                return v1+v2;
            }
        });
        JavaPairRDD<Integer, String> temp = result.mapToPair(new PairFunction<Tuple2<String,Integer>, Integer, String>() {
            private static final long serialVersionUID = 1L;
            public Tuple2<Integer, String> call(Tuple2<String, Integer> tuple)
                    throws Exception {
                return new Tuple2<Integer, String>(tuple._2,tuple._1);
            }
        });
        JavaPairRDD<Integer, String> temp1 = temp.sortByKey(false);
        JavaPairRDD<String, Integer> finalResult = temp1.mapToPair(new PairFunction<Tuple2<Integer,String>, String, Integer>() {
            private static final long serialVersionUID = 1L;
            public Tuple2<String, Integer> call(Tuple2<Integer, String> tuple)
                    throws Exception {
                return new Tuple2<String, Integer>(tuple._2, tuple._1);
            }
        });
        finalResult.foreach(new VoidFunction<Tuple2<String,Integer>>() {
            private static final long serialVersionUID = 1L;
            public void call(Tuple2<String, Integer> tuple) throws Exception {
                System.out.println("word:"+tuple._1+" count:"+tuple._2);
            }
        });
        context.close();
    }
}

Point 2：Scala 版本

package com.scala.wordcount

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext

object wordcount {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("workcount").setMaster("local")
    val sc = new SparkContext(conf)
    val lines = sc.textFile("./data/text.txt")
    val words = lines.flatMap { line => line.split(" ") }
    val pairs = words.map { word => (word,1) }
    val result = pairs.reduceByKey(_+_)
    val sorted = result.sortBy(tuple=>tuple._2)
    sorted.foreach(pair=>println(pair._1+" "+pair._2))
  }