wsheets/wsh02.scala
author Christian Urban <christian.urban@kcl.ac.uk>
Mon, 25 Dec 2023 01:10:55 +0100
changeset 479 78cb5cdda3c3
parent 444 e6df3c7ff132
permissions -rw-r--r--
updated jars
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
     1
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
     2
// Task 1 
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
     3
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
     4
List(7,2,3,4,5,6).find(_ < 4)  // => Some(3)
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
     5
List(5,6,7,8,9).find(_ < 4)    // => None
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
     6
List(5,6,7,8,9).min            // => 5
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
     7
List(5,6,7,8,9).minOption      // => Some(5)
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
     8
List[Int]().minOption          // => None 
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
     9
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    10
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    11
// Task 2
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    12
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    13
Try(Some(List(5,6,7,8,9).min)).getOrElse(None)
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    14
Try(Some(List[Int]().min)).getOrElse(None)
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    15
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    16
// Task 3
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    17
import scala.util._
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    18
import io.Source
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    19
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    20
val my_url = "https://nms.kcl.ac.uk/christian.urban/"
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    21
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    22
// fails if there is no file with that name
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    23
Source.fromFile("test.txt")("ISO-8859-1").mkString
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    24
Source.fromFile("test.txt")("ISO-8859-1").getLines().toList
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    25
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    26
// encapsulates the failure case as None
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    27
Try(Some(Source.fromFile("test.txt")("ISO-8859-1").mkString)).getOrElse(None)
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    28
Try(Source.fromFile("test.txt")("ISO-8859-1").mkString).toOption // same but shorter
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    29
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    30
// for files with propper closing of the file after reading
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    31
Using(Source.fromFile("test.txt")("ISO-8859-1"))(_.mkString).toOption
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    32
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    33
// Task 4 (Higher-Order Functions)
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    34
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    35
List(7,2,3,4,5,6).find(_ < 4)
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    36
List(7,2,3,4,5,6).count(_ % 2 == 0)
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    37
List(7,2,3,4,5,6).sortWith(_ > _)
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    38
List(7,2,3,4,5,6).filter(_ > 4)
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    39
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    40
// Task 5 (Maps)
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    41
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    42
List(7,2,3,4,5,6).map(n => n * n)
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    43
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    44
for (n <- List(7,2,3,4,5,6)) yield n * n
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    45
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    46
// The advantages of for-comprehensions is that they
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    47
// can be nested and also can contain guards. In such
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    48
// cases the translations to maps and filters is a bit
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    49
// involved. 
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    50
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    51
// Task 6 (Pattern-Matching)
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    52
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    53
def my_map(lst: List[Int], f: Int => Int) : List[Int] = {
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    54
 if (lst == Nil) Nil
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    55
 else f(lst.head) :: my_map(lst.tail, f)
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    56
}
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    57
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    58
def my_map(lst: List[Int], f: Int => Int) : List[Int] = lst macth {
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    59
 case Nil => Nil
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    60
 case x::xs => f(x) :: my_map(xs, f)
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    61
}
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    62
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    63
// Task 7 (Web-Crawler, hard)
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    64
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    65
// see lecture2.scala
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    66
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    67
// requires an accumulator that records all pages that have 
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    68
// already been visited, for example
441
5266495f4aad updated
Christian Urban <christian.urban@kcl.ac.uk>
parents:
diff changeset
    69
444
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    70
def crawl(url: String, n: Int, acc : Set[String] = Set()) : Unit = {
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    71
  if (n == 0) ()
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    72
  else {
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    73
    println(s"  Visiting: $n $url")
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    74
    val urls = get_all_URLs(get_page(url))
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    75
    for (u <- urls) crawl(u, n - 1, acc | urls)
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    76
  }
e6df3c7ff132 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 441
diff changeset
    77
}