Flink程序wordcount

package Flink.HelloFlink
//导入隐式类型转换
import org.apache.flink.streaming.api.scala._
import org.apache.flink.streaming.api.windowing.time.Time

object wordCount {

  case class WordWithCount(word: String, count: Int)

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

    //获取运行环境
    //
    var env = StreamExecutionEnvironment.getExecutionEnvironment

    //设置分区数量为1(并行度为1)
    env.setParallelism(1)

    //获取数据源
    //
    val stream = env.socketTextStream("hadoop102", 9999, '\n')

    //写对流的转换处理逻辑
    val transformed: DataStream[WordWithCount] = stream
      //采用空格切分输入的字符串
      .flatMap(line => line.split("\\s"))
      //类似与mr中的map
      .map(w => WordWithCount(w, 1))
      //使用word字段进行分组,shuffle
      .keyBy(0)
      //开窗口为5秒钟滚动窗口
      .timeWindow(Time.seconds(5))
      //针对count字段进行累加操作,类似mr中的reduce
      .sum(1)

    //讲计算的结果输出到标准输出
    transformed.print()
    //执行计算逻辑
    env.execute()
  }

}

结果如下
Flink程序wordcount_第1张图片

你可能感兴趣的:(手写代码)