Scala&Java --WordCount入门程序对比

1.---Java的WordCount

package com.hjm.spark.daydayup;

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 scala.Tuple2;

import java.util.Arrays;
import java.util.Iterator;

/**
 * 对比Java来说 scala更加优雅  api丰富 且有隐式转换 避免写各种泛型 匿名内部类
 */
public class JavaWordCount {
    public static void main(String[] args) {
        //创建conf对象
        SparkConf conf = new SparkConf().setAppName("JavaWordCount");
        //
        JavaSparkContext jsc = new JavaSparkContext(conf);
        JavaRDD<String> lines = jsc.textFile(args[0]);
        //begin transformation
        //压平
        JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public Iterator<String> call(String line) throws Exception {
                return Arrays.asList(line.split(" ")).iterator();
            }
        });
        //拉姆达
        // JavaRDD<String> words = lines.flatMap(line -> Arrays.stream(line.split(" ")).iterator());
        //变成对子 输入string 输出元组<String ,Integer>
        JavaPairRDD<String, Integer> wordAndOne = words.mapToPair(new PairFunction<String, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(String s) throws Exception {
                return Tuple2.apply(s, 1);
            }
        });
        //拉姆达
        //JavaPairRDD<String, Integer> wordAndOne = words.mapToPair((PairFunction<String, String, Integer>) s -> Tuple2.apply(s, 1));

        //进行规约
        JavaPairRDD<String, Integer> reduced = wordAndOne.reduceByKey(new Function2<Integer, Integer, Integer>() {
            @Override
            public Integer call(Integer v1, Integer v2) throws Exception {
                return v1 + v2;
            }
        });
        //拉姆达
        //JavaPairRDD<String, Integer> reduced = wordAndOne.reduceByKey((Function2<Integer, Integer, Integer>) (v1, v2) -> v1 + v2);

        JavaPairRDD<Integer, String> swaped = reduced.mapToPair(new PairFunction<Tuple2<String, Integer>, Integer, String>() {
            @Override
            public Tuple2<Integer, String> call(Tuple2<String, Integer> tp) throws Exception {
                return tp.swap();
            }
        });
        //拉姆达
        //JavaPairRDD<Integer, String> swaped = reduced.mapToPair((PairFunction<Tuple2<String, Integer>, Integer, String>) tp -> tp.swap());


        JavaPairRDD<Integer, String> sorted = swaped.sortByKey(false);

        //交换kv顺序
        JavaPairRDD<String, Integer> result = sorted.mapToPair(new PairFunction<Tuple2<Integer, String>, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(Tuple2<Integer, String> tp) throws Exception {
                return tp.swap();
            }
        });
        //拉姆达
        //JavaPairRDD<String, Integer> result = sorted.mapToPair((PairFunction<Tuple2<Integer, String>, String, Integer>) tp -> tp.swap());
        //保存到路径上
        result.saveAsTextFile(args[1]);


    }
}

args(0):传入素材的文件路径,本地或 hdfs上都可以

args(1):输出目录\路径,

例如:

查看结果

2.--Scala的WordCount

idea--->

package com.hjm.spark.daydayup

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

object WordCount {
  def main(args: Array[String]): Unit = {
    //
    val conf = new SparkConf().setAppName("WordCount")
    val sc = new SparkContext(conf)
    //创建RDD
    val lines: RDD[String] = sc.textFile(args(0))
    //Transforma开始
    //切分压平
    val words: RDD[String] = lines.flatMap(_.split(" "))
    //
    val WordAndOne: RDD[(String, Int)] = words.map((_, 1))
    //分组聚合 排序
    val value: RDD[(String, Int)] = WordAndOne.reduceByKey(_ + _).sortBy(_._2, false)
    //Action算子,触发任务执行
    value.saveAsTextFile(args(1))
    //释放资源
    sc.stop()



  }

}

--->甚至直接在Linux命令一行输入,(已启动spark等必要组件)

 scala>sc.textFile("args(0)").flatMap(_.split(" ")).map((_,1)).reduceByKey(_+_).sortBy(_._2, false).SaveAsFile("(args(1))")

args(0):传入素材的文件路径,本地或 hdfs上都可以

args(1):输出目录\路径