使用 Spark Java Api 進行 WordCount

 pom文件

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.smj</groupId>
    <artifactId>test</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>2.2.2</version>
        </dependency>

    </dependencies>
</project>

 源碼

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

/*這個是 spark java api 的 wordcount 例子*/
public class JavaSparkWordCountOps {
    public static void main(String[] args) {
        //1 創建編程入口類
        SparkConf conf = new SparkConf();
        conf.setMaster("local[*]").setAppName(JavaSparkWordCountOps.class.getSimpleName());

        JavaSparkContext jsc = new JavaSparkContext(conf);

        //2 加載外部數據 形成spark中的計算的編程模型RDD，本地文件需要在前面加 file:\\
        JavaRDD<String> linesRDD = jsc.textFile("file:\\D:\\Workspace\\test\\src\\main\\resources\\hello.txt");

        // 例子 直接打印輸出
        System.out.println("------ 直接打印輸出文件內容 ------");
        linesRDD.foreach(new VoidFunction<String>() {
            public void call(String s) throws Exception {
                System.out.println(s);
            }
        });

        //3 對數據進行處理，轉換操作 transformation , flatMap 把一行數據拆成多個
        System.out.println("------ 拆分RDD數據 ------");
        JavaRDD<String> wordsRDD = linesRDD.flatMap(new FlatMapFunction<String, String>() {
            public Iterator<String> call(String line) throws Exception {
                return Arrays.asList(line.split(",")).iterator();
            }
        });

        // 打印經過拆分的RDD數據
        wordsRDD.foreach(new VoidFunction<String>() {
            public void call(String s) throws Exception {
                System.out.println(s);
            }
        });

        // mapToPair , 拼裝鍵值對，把詞爲key，鍵爲1
        System.out.println("------ 拼裝鍵值對 ------");
        JavaPairRDD<String, Integer> pairRDD = wordsRDD.mapToPair(new PairFunction<String, String, Integer>() {
            public Tuple2<String, Integer> call(String word) throws Exception {
                return new Tuple2<String, Integer>(word, 1);
            }
        });

        // 打印輸出已拼裝好的鍵值對
        pairRDD.foreach(new VoidFunction<Tuple2<String, Integer>>() {
            public void call(Tuple2<String, Integer> t) throws Exception {
                System.out.println(t._1 + "-" + t._2);
            }
        });

        System.out.println("------ 按照相同的value累加 ------");
        JavaPairRDD<String, Integer> retRDD = pairRDD.reduceByKey(new Function2<Integer, Integer, Integer>() {
            public Integer call(Integer v1, Integer v2) throws Exception {
                return v1 + v2;
            }
        });

        // 打印累加後的內容
        retRDD.foreach(new VoidFunction<Tuple2<String, Integer>>() {
            public void call(Tuple2<String, Integer> t) throws Exception {
                System.out.println(t._1 + "-" + t._2);
            }
        });
    }
}