flink wordcount demo

demo 

package com.hbn.wc

import org.apache.flink.api.scala.{DataSet, ExecutionEnvironment}

import org.apache.flink.api.scala._


object WordCount {
  def main(args: Array[String]): Unit = {

    //獲取執行環境
    val env = ExecutionEnvironment.getExecutionEnvironment

    //加載數據源
    //val inputData = env.fromElements("china is the best country","beijing is the capital of china")

    val  inputData:DataSet[String] = env.readTextFile("/Users/H/Code/flinklearning/src/main/resources/wordcount.txt")
    //轉化處理數據
    val result:DataSet[(String ,Int)] = inputData.flatMap(_.split(" ")).map((_,1)).groupBy(0).sum(1)

    //輸出至目的端
    result.print()

    // 執行操作
    // 由於是Batch操作，當DataSet調用print方法時，源碼內部已經調用Excute方法，所以此處不再調用，如果調用會出現錯誤
    //env.execute("Flink Batch Word Count By Scala")

  }
}

執行結果如圖 

(you,2)
(flink,1)
(ok,1)
(world,1)
(hello,3)
(are,2)
(,3)
(how,1)
(spark,1)