Flink快速入门之批计算的WordCount案例

数据源wc.txt

hello spark
hello flink
hello java
hello java
hello php
hello python
hello scala

package stream

import org.apache.flink.api.scala.ExecutionEnvironment

/**
 * @Author yqq
 * @Date 2021/12/23 01:46
 * @Version 1.0
 */
object BatchWordCount {
  def main(args: Array[String]): Unit = {
    //1.初始化flink批处理环境
    val environment: ExecutionEnvironment = ExecutionEnvironment.getExecutionEnvironment
    //2.导入隐式转换
    import org.apache.flink.api.scala._
    //3.读取数据，读取sock流中的数据，DataSet=>类似spark RDD
    val set: DataSet[String] = environment.readTextFile("data/wc.txt")
    //4.计算和打印
    set.flatMap(_.split(" "))
      .map((_,1))
      .groupBy(0)
      .sum(1)
      .print()
  }
}