139、Spark核心编程进阶之mapPartitionsWithIndex以开学分班案例-优快云博客

本文介绍Spark中mapPartitionsWithIndex算子的使用方法，通过示例展示了如何利用该算子获取每个partition的index，并进行数据处理。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

mapPartitionsWithIndex，这个算子可以拿到每个partition的index

PartitionsWithIndex {
    public static void main(String[] args) {

        SparkConf conf = new SparkConf().setAppName("MapPartitionsWithIndexJava").setMaster("local");

        JavaSparkContext sparkContext = new JavaSparkContext(conf);
        // 准备一下模拟数据
        List<String> studentNames = Arrays.asList("张三", "李四", "王二", "麻子");

        JavaRDD<String> studentNamesRDD = sparkContext.parallelize(studentNames, 2);

        JavaRDD<String> studentWithClassRDD = studentNamesRDD.mapPartitionsWithIndex(new Function2<Integer, Iterator<String>, Iterator<String>>() {
            @Override
            public Iterator<String> call(Integer integer, Iterator<String> stringIterator) throws Exception {
                List<String> studentWithClassList = new ArrayList<String>();

                while (stringIterator.hasNext()) {
                    String studentName = stringIterator.next();
                    String studentWithClass = studentName + "_" + (integer + 1);
                    studentWithClassList.add(studentWithClass);
                }

                return studentWithClassList.iterator();
            }
        }, true);

        studentWithClassRDD.foreach(new VoidFunction<String>() {
            @Override
            public void call(String s) throws Exception {
                System.out.println("s = " + s);
            }
        });
    }
}