个文本文件进行单词计数

个文本文件进行单词计数


对单个文本文件进行单词计数

import scala.actors.Actor
import scala.io.Source //读取文件名称样例类
case class SubmitTask(fileName:String) class Actor2WordCount extends Actor{
override def act(): Unit = {
loop{
react{
case SubmitTask(fileName) =>
//根据文件名称读取文件内容 Source.formFile
val fileContent: String = Source.fromFile(fileName).mkString
//拿到文件内容后进行分割
//首先文件有两行,所以按照换行符先进行分割 window系统:/r/n linux系统:/n mac OS系统:/r
val lines: Array[String] = fileContent.split("\r")
//再根据单词间的分隔符进行切割压平
val words: Array[String] = lines.flatMap(x => x.split(" "))
//还有一种写法
// val words = lines.flatMap(_.split(" "))
//每个单词都标记成一次
val countOne: Array[(String, Int)] = words.map(x => (x, 1))
//进行分组,把元祖第一个元素相同分配到一组
val groupedWords: Map[String, Array[(String, Int)]] = countOne.groupBy(_._1)
//mapValues方法可以作用于map中的v,操作之后和和之前的k返回构成一个新的map
val wordsCount: Map[String, Int] = groupedWords.mapValues(_.length)
println(wordsCount.toBuffer)
}
}
}
} object WordCount{
def main(args: Array[String]): Unit = {
//创建Actor2WordCount对象
val actor = new Actor2WordCount
//启动Actor2WordCount
actor.start()
//发送待处理文件名称给Actor2WordCount
actor ! SubmitTask("/Users/zhaozhuang/Desktop/3、Scala/2、Scala第二天/wordCount/1.txt")
}
}

对多个文本文件进行单词计数

import scala.actors.{Actor,Future}
import scala.collection.mutable
import scala.collection.mutable.ListBuffer
import scala.io.{BufferedSource,Source} //读取文件名称样例类
case class SubmitTask(fileName: String) case class Reply(wordsCount: Map[String, Int]) class Actor2WordCount extends Actor {
override def act(): Unit = {
loop {
react {
case SubmitTask(fileName) =>
//根据文件名称读取文件内容 Source.formFile
val fileContent: String = Source.fromFile(fileName).mkString
//拿到文件内容后进行分割
//首先文件有两行,所以按照换行符先进行分割 window系统:/r/n linux系统:/n mac OS系统:/r
val lines: Array[String] = fileContent.split("\r")
//再根据单词间的分隔符进行切割压平
val words: Array[String] = lines.flatMap(x => x.split(" "))
//还有一种写法
// val words = lines.flatMap(_.split(" "))
//每个单词都标记成一次
val countOne: Array[(String, Int)] = words.map(x => (x, 1))
//进行分组,把元祖第一个元素相同分配到一组
val groupedWords: Map[String, Array[(String, Int)]] = countOne.groupBy(_._1)
//mapValues方法可以作用于map中的v,操作之后和和之前的k返回构成一个新的map
val wordsCount: Map[String, Int] = groupedWords.mapValues(_.length) sender ! Reply(wordsCount)
// println(wordsCount.toBuffer)
}
}
}
} object WordCount {
def main(args: Array[String]): Unit = {
//将要读取的文件路径封装到一个数组中
val files = Array("/Users/zhaozhuang/Desktop/3、Scala/2、Scala第二天/wordCount/1.txt",
"/Users/zhaozhuang/Desktop/3、Scala/2、Scala第二天/wordCount/2.txt",
"/Users/zhaozhuang/Desktop/3、Scala/2、Scala第二天/wordCount/3.txt") //定义一个集合,用于保存每个actor处理完返回的状态
val futureSet: mutable.HashSet[Future[Any]] = new mutable.HashSet[Future[Any]]()
//定义一个集合,用于保存买个actor返回的结果
val resultList = new ListBuffer[Reply]
//循环遍历每一个文件
for (f <- files) {
//创建Actor2WordCount对象
val actor = new Actor2WordCount
//启动Actor2WordCount
actor.start()
//发送待处理文件名称给Actor2WordCount 异步消息且有返回值
val future = actor !! SubmitTask(f)
//把返回状态添加到future集合中
futureSet.+=(future)
}
//遍历futureSet,找出真正处理完的actor,提取其结果future.apply()
while (futureSet.size > 0){
val completeFuture: mutable.HashSet[Future[Any]] = futureSet.filter(x => x.isSet)
//提取处理的结果
for(f <- completeFuture){
val finalResult: Any = f.apply()
val reply: Reply = finalResult.asInstanceOf[Reply]
resultList += reply
//提取完结果后,把future从futureSet移除
futureSet.remove(f)
}
}
println(resultList.map(_.wordsCount).flatten.groupBy(_._1).mapValues(x => x.foldLeft(0)(_+_._2)))
}
}
05-04 12:25