使用scala基于'A'，'E'，'I'，'O'，'U‘元音在Spark(Core using RDD) WordCount程序中创建5分区文件

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

val conf = new SparkConf().setAppName("WordCount")

val sc = new SparkContext(conf)

val input = sc.textFile("input.txt")

val vowels = Set('A', 'E', 'I', 'O', 'U')
val filtered = input.flatMap(line => line.split(" "))
                    .filter(word => vowels.contains(word.charAt(0).toUpper))
                    .map(word => (word, 1))
                    .partitionBy(new org.apache.spark.HashPartitioner(5))

val wordCounts = filtered.reduceByKey(_ + _)

wordCounts.saveAsTextFile("output")

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

object WordCount {
  def main(args: Array[String]) {
    val conf = new SparkConf().setAppName("WordCount")
    val sc = new SparkContext(conf)

    val input = sc.textFile("input.txt")
    val vowels = Set('A', 'E', 'I', 'O', 'U')
    val filtered = input.flatMap(line => line.split(" "))
                        .filter(word => vowels.contains(word.charAt(0).toUpper))
                        .map(word => (word, 1))
                        .partitionBy(new org.apache.spark.HashPartitioner(5))

    val wordCounts = filtered.reduceByKey(_ + _)
    wordCounts.saveAsTextFile("output")

    sc.stop()
  }
}