请用java,scala,python三种语言实现spark的sortByKey算子的案例

Java实现：

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 scala.Tuple2;

public class SortByKeyDemo {

    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setAppName("SortByKeyDemo").setMaster("local");
        JavaSparkContext sc = new JavaSparkContext(conf);

        // 创建RDD
        JavaRDD<String> lines = sc.parallelize(Arrays.asList("apple 3", "banana 2", "orange 1"));

        // 转换为JavaPairRDD
        JavaPairRDD<String, Integer> pairs = lines.mapToPair(line -> {
            String[] parts = line.split(" ");
            return new Tuple2<>(parts[0], Integer.parseInt(parts[1]));
        });

        // 按照key排序
        JavaPairRDD<String, Integer> sortedPairs = pairs.sortByKey();

        // 输出结果
        sortedPairs.foreach(tuple -> System.out.println(tuple._1 + " : " + tuple._2));

        sc.stop();
    }
}

Scala实现：

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

object SortByKeyDemo {

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("SortByKeyDemo").setMaster("local")
    val sc = new SparkContext(conf)

    // 创建RDD
    val lines = sc.parallelize(Seq("apple 3", "banana 2", "orange 1"))

    // 转换为PairRDD
    val pairs = lines.map(line => {
      val parts = line.split(" ")
      (parts(0), parts(1).toInt)
    })

    // 按照key排序
    val sortedPairs = pairs.sortByKey()

    // 输出结果
    sortedPairs.foreach(tuple => println(s"${tuple._1} : ${tuple._2}"))

    sc.stop()
  }
}

Python实现：

from pyspark import SparkConf, SparkContext

conf = SparkConf().setAppName("SortByKeyDemo").setMaster("local")
sc = SparkContext(conf=conf)

# 创建RDD
lines = sc.parallelize(["apple 3", "banana 2", "orange 1"])

# 转换为PairRDD
pairs = lines.map(lambda line: (line.split(" ")[0], int(line.split(" ")[1])))

# 按照key排序
sortedPairs = pairs.sortByKey()

# 输出结果
sortedPairs.foreach(lambda tuple: print("{} : {}".format(tuple[0], tuple[1])))

sc.stop()