spark之Scala+java+maven+idea实现wordcount

spark之scala+java+maven+idea实现wordcount

1、Idea打开工作目录

2、新建模块，建java模块即可，选择相应的SDK

3、添加framework support,选择maven

              在pom.xml中添加

<dependencies>
    <dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-core_2.11</artifactId>
    <version>2.3.0</version>
    </dependency>
</dependencies>

刷新，会自动下载依赖包

4、若写scala代码，需添加scala支持：add framework support中选择scala即可。

5、创建scala class文件，kind选择object

Wordcount scala版本：

import org.apache.spark.{SparkConf, SparkContext}
/**
  *
  */
object WordCountDemo {
  // unit类似于java中的void
  def main(args: Array[String]): Unit = {
    //创建Spark配置对象
    val conf = new SparkConf();
    conf.setAppName("WordCountScala")
    //设置master属性
    conf.setMaster("local")
    //conf.setMaster("spark://s201:7077")

    //通过conf创建sc
    val sc = new SparkContext(conf)

    //加载文本文件
    val rdd1 = sc.textFile("e:/sparkNote/word.txt")
    //val rdd1 = sc.textFile(args(0));
    //压扁
    val rdd2 = rdd1.flatMap(line => line.split(" "))
    //映射w => (w,1)
    val rdd3 = rdd2.map((_,1))
    val rdd4 = rdd3.reduceByKey(_ + _)
    val r = rdd4.collect()
    r.foreach(println)
  }
}

6、wordcount java版本

package com.sxt ;

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

/**
 * Java版Spark单词统计程序
 */
public class WordCountJava {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf();
        conf.setAppName("WordCountScala");
        //设置master属性
        conf.setMaster("local");
        //conf.setMaster("spark://s201:7077");
        JavaSparkContext sc = new JavaSparkContext(conf);
        //加载文件
        JavaRDD<String> rdd1 = sc.textFile("e:/sparkNote/word.txt");
        //JavaRDD<String> rdd1 = sc.textFile(args[0]);
        //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
        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);
            }
        });
        //聚合
        JavaPairRDD<String,Integer> rdd4 = rdd3.reduceByKey(new Function2<Integer, Integer, Integer>() {
            public Integer call(Integer v1, Integer v2) throws Exception {
                return v1 + v2;
            }
        });
        //收集,打印输出
        for(Object o : rdd4.collect()){
            System.out.println(o);
        }
    }
}