loicdescotte
9/1/2015 - 1:43 PM

Word Count with Apache Spark and Kotlin

Word Count with Apache Spark and Kotlin

package org.cakesolutions.spark

import org.apache.spark.SparkConf
import org.apache.spark.api.java.JavaSparkContext
import scala.Tuple2


fun main(args: Array<String>) {
    val inputFile = args[0]
    val outputFile = args[1]

    val conf = SparkConf().setAppName("wordCount")
    val sc = JavaSparkContext(conf)

    val input = sc.textFile(inputFile)
    val words = input.flatMap { x -> x.splitBy(" ") }

    val counts = words.mapToPair { x -> Tuple2(x, 1) }.reduceByKey { x, y -> x + y }

    counts.saveAsTextFile(outputFile)
}