Scala中WordCountLow

import scala.io.Source
object $17_WordCountLow {
  def main(args: Array[String]): Unit = {
    //1、读取文件
    val datas = Source.fromFile("datas/wc2.txt","utf-8").getLines().toList
    //List(hello hadoop flume kafka,kafka spark scala hadoop,hello java python hadoop,kafka flume spark spark,hello flume scala java)
    //2、切割+压平
    val words = datas.flatMap(line=> line.split(" "))
    //List(hello,hadoop,flume,kafka,kafka,spark,....)

    //3、按照单词分组
    val groupedMap = words.groupBy(x=>x)
    //Map(
    //    hello-> List(hello,hello，hello，hello，..)
    //    ...
    // )
    //
    //4、统计次数
    val result = groupedMap.map(x=>{
      //x = hello-> List(hello,hello，hello，hello，..)
      (x._1,x._2.size)
    })
    //List( (单词，总次数),(单词,总次数),... )
    result.foreach(x=>println(x))
    println("-"*100)
    //
    Source.fromFile("datas/wc.txt","utf-8").getLines().toList.flatMap(_.split(" ")).groupBy(x=>x).map(x=>(x._1,x._2.size)).foreach(println(_))
  }
}