課程筆記：
變量與函數
>def fun1(name: String) {println(name)}
fun1: (name: String)Unit
>val fun1_v = fun1 _ //注意，是空格和下劃線
fun1_v: String => Unit = <function1>
>fun1("Spark")
Spark
>fun1_v("Spark")
Spark
>fun1_v("Scala")
Scala
//匿名函數
>val fun2 = (content: String) => println(content:)
fun2: String => Unit = <function1>
>fun2("Hadoop")
Hadoop
//函數的參數可以是函數
>val hiScala = (content : String) => println(context)
hiScala: String => Unit = <function1>
>def bigData(func: (String) => Unit, context: String) {func(content)}
bigData:(func: String => Unit, content: String) Unit
>bigData(hiScala,"Spark")
Spark
//循環遍歷數組每個值
>val array = Array(1,2,3,4,5,6,7,8,9)
>array.map(item => 2 * item)
Array[Int] = Array(2,4,6,8,10,12,14,16,18)
>array.map(item => print(item))
//函數作爲返回值
>def func_Returned(content : String) = (message : String) => println(message)
func_Returned: (content: String)String => Unit
>func_Returned("Spark")
res7: String => Unit = <function1>
>val returned = func_Returned("Spark")
returned: String => Unit = <function1>
//用變量調用執行
>returned("Scala")
Spark Scala
>def spark(fun: (String) => Unit, name: String) {func(name)}
>spark((name: String) => println(name),"Scala")
Scala
>spark((name) => println(name),"Scala")
Scala
>spark(name => println(name),"Scala")
>spark(println(_), "Scala")
Scala
>spark(println,"Scala")
Scala
>array.map(2*_)
res17:Array[Int] = Array(2,4,6,8,10,12,14,16,18)
// print array elements
>array.map(2*_).foreach(println(_))
>array.map(2*_).foreach(println _)
>array.map(2*_).filter(_ >12).foreach(println)
14
16
18
//閉包：函數的變量超出函數的作用域時，在外部還可以對它進行訪問； Scala內部維護了函數的參數（參數作爲函數的成員被保存）
>def scala(content : String) = (message : String) => println(content + " :" + message)
scala: (content: String) String => Unit
>val funcResult = scala("Spark")
funcResult: String => Unit = <function1>
>funcResult("Flink")
Spark :Flink
//柯里化：如果一個函數有兩個參數，那麼可以把這個函數轉換成兩個函數來實現，返回值也是一個函數。
>def sum(x: Int, y: Int) = x+y
>sum(1,2)
res24: Int = 3
>def sum_currying(x : Int) = (y: Int) => x + y
sum_currying: (x: Int) Int => Int
>sum_currying(1)(2)
也可以把兩個函數合併起來定義和使用。
>def sum_Currying_Better(x : Int) (y: Int) = x + y
sum_Currying_Better: (x: Int) (y: Int) Int
>sum_Currying_better(1)(3)
res27: Int = 4
//很奇妙的處理方式
>(1 to 100).reduceLeft(_+_)
res28: Int = 5050
集合
>val list = List("Scala","Spark","Flink")
list: List[String] = List(Scala,Spark,Flink)
>list.map("The content is : " + _)
res29: List[String] = List(The content is : Scala,The content is : Spark, The content is : Scalaala
作業：統計一個文件夾下面所有的單詞出現的總次數(轉)
http://blog.sina.com.cn/s/blog_7dc74d730102vyhv.html
object WordCounter {
import scala.io.Source
import java.io._
// store word and counter
var map = Map.empty[String, Int]
def main(args: Array[String]): Unit = {
scanDir(new File("D:/workspace"))
map.foreach(f =>
println(f)
)
}
def scanDir(dir: File): Unit = {
dir.listFiles.foreach { file =>
if(file.isFile()){
readFile(file)
println(file)
}
}
}
def readFile(file: File){
val f = Source.fromFile(file)
for (line <- f.getLines()){
count(line)
}
}
def count(line: String) = {
for(word <- line.split("[,:.!\\s?*\\/-=+]()><")){
if(map.contains(word))
map += (word -> (map(word)+1))
else
map += (word -> 1)
}
}
}
object WordCounter {
//導入jar包
import scala.io.Source
import java.io._
//存儲單詞和個數
var map = Map.empty[String, Int]
def main(args: Array[String]): Unit = {
scanDir(new File("D:/TMPFOLDER"))
map.foreach(f =>
println(f)
)
}
def scanDir(dir: File): Unit = {
dir.listFiles.foreach { file =>
if(file.isFile()){
readFile(file)
println(file)
}
}
}
def readFile(file: File){
val f = Source.fromFile(file)
for (line <- f.getLines()){
count(line)
}
}
def count(line: String) = {
for(word <- line.split("[,:.!\\s?*\\/-=+]()><")){
if(map.contains(word))
map += (word -> (map(word)+1))
else
map += (word -> 1)
}
}
}