初识Flink-从WorldCount开始

　　Apache Flink是一个用于分布式流和批处理数据处理的开源平台。Flink的核心是流数据流引擎，为数据流上的分布式计算提供数据分发，通信和容错。Flink在流引擎之上构建批处理，覆盖本机迭代支持，托管内存和程序优化。

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

object BatchWordCountScala {
  def main(args: Array[String]): Unit = {
    
    val inputPath = "E:\data\file" //存放文件路径
    val outPut = "E:\data\result"  //结果

    val env = ExecutionEnvironment.getExecutionEnvironment
    val text = env.readTextFile(inputPath)

    //引入隐式转换
    import org.apache.flink.api.scala._

    val counts = text.flatMap(_.toLowerCase.split("\W+"))
      .filter(_.nonEmpty)
      .map((_,1))
      .groupBy(0)
      .sum(1)
    counts.writeAsCsv(outPut,"
"," ").setParallelism(1)
    env.execute("batch word count")
  }
}