一、需求描述

需求：文件中存储的各种各样的单词，统计在这些文件中每个单词的出现次数。比如下面txt文件，统计各个单词出现的次数。

image.png

好了。。不多说。。。直接上代码。。。

二、使用Java实现

import org.apache.spark.SparkConf;
import org.apache.spark.SparkContext;
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 scala.Tuple2;

import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;


public class SparkJavaTest {
    public static void main(String[] args) {
        //创建SparkConf对象
        SparkConf conf = new SparkConf();
        conf.setAppName("WordCountJava2");
        conf.setMaster("local");

        //创建java sc
        JavaSparkContext sc = new JavaSparkContext(conf);
        //加载文本文件
        JavaRDD<String> rdd1 = sc.textFile("d:/input_file.txt");

        //压扁
        JavaRDD<String> rdd2 = rdd1.flatMap(new FlatMapFunction<String, String>() {
            public Iterator<String> call(String s) throws Exception {
                List<String> list = new ArrayList<String>();
                String[] arr = s.split(" ");
                for(String ss :arr){
                    list.add(ss);
                }
                return list.iterator();
            }
        });

        //映射,word -> (word,1)
        JavaPairRDD<String,Integer> rdd3 = rdd2.mapToPair(new PairFunction<String, String, Integer>() {
            public Tuple2<String, Integer> call(String s) throws Exception {
                return new Tuple2<String, Integer>(s,1);
            }
        });

        //reduce化简
        JavaPairRDD<String,Integer> rdd4 = rdd3.reduceByKey(new Function2<Integer, Integer, Integer>() {
            public Integer call(Integer v1, Integer v2) throws Exception {
                return v1 + v2;
            }
        });

        //
        List<Tuple2<String,Integer>> list = rdd4.collect();
        for(Tuple2<String, Integer> t : list){
            System.out.println(t._1() + " : " + t._2());
        }
    }
}

输出结果：

image.png

三、使用Scala实现

import org.apache.spark.{SparkConf, SparkContext}

object SparkScalaTest {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("wc_java").setMaster("local[*]")
    val sc = new SparkContext(conf)
    val lines = sc.textFile("d:/input_file.txt")
    val rdd1 = lines.flatMap(line=>line.split(" "))
    val totalLength = rdd1.map(word=>(word,1))
    val total_KV = totalLength.reduceByKey(_+_)
    total_KV.collect()
    total_KV.foreach(println)
  }
}

输出结果：

image.png