spark二次排序java版

最新推荐文章于 2022-07-22 15:37:35 发布

原创最新推荐文章于 2022-07-22 15:37:35 发布 · 271 阅读

CC 4.0 BY-SA版权

本文介绍使用 Apache Spark 的 Java API 实现基于元组的二次排序过程。通过创建 SparkConf 和 JavaSparkContext 来配置并启动 Spark 应用程序，读取文件数据，将数据映射为键值对，键为自定义的 SecondSortEntity 对象，值为原始字符串。利用 sortByKey 方法对键进行排序，并展示排序后的结果。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

public class SecondSort_java {
    public static void main(String[] args){
        SparkConf conf = new SparkConf().
                setMaster("local").
                setAppName("SecondSort_java");
        JavaSparkContext jsc = new JavaSparkContext(conf);
        JavaRDD<String> textFileRDD = jsc.textFile("E:\\2.txt");
        JavaPairRDD<SecondSortEntity, String> pairRDD = textFileRDD.mapToPair(new PairFunction<String, SecondSortEntity, String>() {
            public Tuple2<SecondSortEntity, String> call(String s)
                    throws Exception {
                String[] splits = s.split("\\s");
                SecondSortEntity sse = new SecondSortEntity
                        (Integer.parseInt(splits[0]), Integer.parseInt(splits[1]),Integer.parseInt(splits[2]));

                return new Tuple2<SecondSortEntity, String>(sse, s);
            }
        });
        JavaPairRDD<SecondSortEntity, String> sortRDD = pairRDD.sortByKey(true);
        JavaRDD<String> map = sortRDD.map(new Function<Tuple2<SecondSortEntity, String>, String>() {
            public String call(Tuple2<SecondSortEntity, String> v1) throws Exception {
                return v1._2;
            }
        });
        map.foreach(new VoidFunction<String>() {
            public void call(String s) throws Exception {
                System.out.println(s);
            }
        });
        jsc.stop();
    }
}

//实体类

public class SecondSortEntity implements
        Ordered<SecondSortEntity>, Serializable{
    private int firstNum;
    private int secondNum;
    private int thirdNum;

    public int getSecondNum() {
        return secondNum;
    }

    public void setSecondNum(int secondNum) {
        this.secondNum = secondNum;
    }

    public int getFirstNum() {
        return firstNum;
    }

    public int getThirdNum() {
        return thirdNum;
    }

    public void setThirdNum(int thirdNum) {
        this.thirdNum = thirdNum;
    }

    public void setFirstNum(int firstNum) {
        this.firstNum = firstNum;
    }

    public SecondSortEntity() {

    }

    public SecondSortEntity(int firstNum ,int secondNum,int thirdNum) {
        this.secondNum = secondNum;
        this.firstNum = firstNum;
        this.thirdNum = thirdNum;
    }

    //如何比较
    public int compare(SecondSortEntity that) {
        int result = this.firstNum-that.firstNum;
        if(result == 0){
            result = that.secondNum - this.secondNum;
            if(result == 0){
                result = that.thirdNum - this.thirdNum;
            }
        }
        return result;
    }
    //如何比较 同上
    public int compareTo(SecondSortEntity that) {
        int result = this.firstNum-that.firstNum;
        if(result == 0){
            result = that.secondNum - this.secondNum;
            if(result == 0){
                result = that.thirdNum - this.thirdNum;
            }
        }
        return result;
    }