441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
     1  | 
  | 
| 
444
 | 
     2  | 
// Task 1 
  | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
     3  | 
  | 
| 
444
 | 
     4  | 
List(7,2,3,4,5,6).find(_ < 4)  // => Some(3)
  | 
| 
 | 
     5  | 
List(5,6,7,8,9).find(_ < 4)    // => None
  | 
| 
 | 
     6  | 
List(5,6,7,8,9).min            // => 5
  | 
| 
 | 
     7  | 
List(5,6,7,8,9).minOption      // => Some(5)
  | 
| 
 | 
     8  | 
List[Int]().minOption          // => None 
  | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
     9  | 
  | 
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    10  | 
  | 
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    11  | 
// Task 2
  | 
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    12  | 
  | 
| 
444
 | 
    13  | 
Try(Some(List(5,6,7,8,9).min)).getOrElse(None)
  | 
| 
 | 
    14  | 
Try(Some(List[Int]().min)).getOrElse(None)
  | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    15  | 
  | 
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    16  | 
// Task 3
  | 
| 
444
 | 
    17  | 
import scala.util._
  | 
| 
 | 
    18  | 
import io.Source
  | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    19  | 
  | 
| 
444
 | 
    20  | 
val my_url = "https://nms.kcl.ac.uk/christian.urban/"
  | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    21  | 
  | 
| 
444
 | 
    22  | 
// fails if there is no file with that name
  | 
| 
 | 
    23  | 
Source.fromFile("test.txt")("ISO-8859-1").mkString
 | 
| 
 | 
    24  | 
Source.fromFile("test.txt")("ISO-8859-1").getLines().toList
 | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    25  | 
  | 
| 
444
 | 
    26  | 
// encapsulates the failure case as None
  | 
| 
 | 
    27  | 
Try(Some(Source.fromFile("test.txt")("ISO-8859-1").mkString)).getOrElse(None)
 | 
| 
 | 
    28  | 
Try(Source.fromFile("test.txt")("ISO-8859-1").mkString).toOption // same but shorter
 | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    29  | 
  | 
| 
444
 | 
    30  | 
// for files with propper closing of the file after reading
  | 
| 
 | 
    31  | 
Using(Source.fromFile("test.txt")("ISO-8859-1"))(_.mkString).toOption
 | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    32  | 
  | 
| 
444
 | 
    33  | 
// Task 4 (Higher-Order Functions)
  | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    34  | 
  | 
| 
444
 | 
    35  | 
List(7,2,3,4,5,6).find(_ < 4)
  | 
| 
 | 
    36  | 
List(7,2,3,4,5,6).count(_ % 2 == 0)
  | 
| 
 | 
    37  | 
List(7,2,3,4,5,6).sortWith(_ > _)
  | 
| 
 | 
    38  | 
List(7,2,3,4,5,6).filter(_ > 4)
  | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    39  | 
  | 
| 
444
 | 
    40  | 
// Task 5 (Maps)
  | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    41  | 
  | 
| 
444
 | 
    42  | 
List(7,2,3,4,5,6).map(n => n * n)
  | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    43  | 
  | 
| 
444
 | 
    44  | 
for (n <- List(7,2,3,4,5,6)) yield n * n
  | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    45  | 
  | 
| 
444
 | 
    46  | 
// The advantages of for-comprehensions is that they
  | 
| 
 | 
    47  | 
// can be nested and also can contain guards. In such
  | 
| 
 | 
    48  | 
// cases the translations to maps and filters is a bit
  | 
| 
 | 
    49  | 
// involved. 
  | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    50  | 
  | 
| 
444
 | 
    51  | 
// Task 6 (Pattern-Matching)
  | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    52  | 
  | 
| 
444
 | 
    53  | 
def my_map(lst: List[Int], f: Int => Int) : List[Int] = {
 | 
| 
 | 
    54  | 
 if (lst == Nil) Nil
  | 
| 
 | 
    55  | 
 else f(lst.head) :: my_map(lst.tail, f)
  | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    56  | 
}
  | 
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    57  | 
  | 
| 
444
 | 
    58  | 
def my_map(lst: List[Int], f: Int => Int) : List[Int] = lst macth {
 | 
| 
 | 
    59  | 
 case Nil => Nil
  | 
| 
 | 
    60  | 
 case x::xs => f(x) :: my_map(xs, f)
  | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    61  | 
}
  | 
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    62  | 
  | 
| 
444
 | 
    63  | 
// Task 7 (Web-Crawler, hard)
  | 
| 
 | 
    64  | 
  | 
| 
 | 
    65  | 
// see lecture2.scala
  | 
| 
 | 
    66  | 
  | 
| 
 | 
    67  | 
// requires an accumulator that records all pages that have 
  | 
| 
 | 
    68  | 
// already been visited, for example
  | 
441
Christian Urban <christian.urban@kcl.ac.uk> 
parents:  
diff
changeset
 
 | 
    69  | 
  | 
| 
444
 | 
    70  | 
def crawl(url: String, n: Int, acc : Set[String] = Set()) : Unit = {
 | 
| 
 | 
    71  | 
  if (n == 0) ()
  | 
| 
 | 
    72  | 
  else {
 | 
| 
 | 
    73  | 
    println(s"  Visiting: $n $url")
  | 
| 
 | 
    74  | 
    val urls = get_all_URLs(get_page(url))
  | 
| 
 | 
    75  | 
    for (u <- urls) crawl(u, n - 1, acc | urls)
  | 
| 
 | 
    76  | 
  }
  | 
| 
 | 
    77  | 
}
  |