progs/lecture2.scala
author Christian Urban <christian.urban@kcl.ac.uk>
Mon, 26 Dec 2022 16:49:53 +0000
changeset 458 d9f8245d0861
parent 447 f51e593903ac
child 471 135bf034ac30
permissions -rw-r--r--
updated
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
51
0e60e6c24b99 updated
Christian Urban <urbanc@in.tum.de>
parents: 39
diff changeset
     1
// Scala Lecture 2
0e60e6c24b99 updated
Christian Urban <urbanc@in.tum.de>
parents: 39
diff changeset
     2
//=================
363
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
     3
 
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
     4
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
     5
// String Interpolations
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
     6
//=======================
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
     7
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
     8
def cube(n: Int) : Int = n * n * n
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
     9
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    10
val n = 3
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
    11
println("The cube of " + n + " is " + cube(n) + ".")
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    12
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    13
println(s"The cube of $n is ${cube(n)}.")
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    14
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
    15
// or even
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
    16
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    17
println(s"The cube of $n is ${n * n * n}.")
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    18
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    19
// helpful for debugging purposes
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    20
//
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    21
//     "The most effective debugging tool is still careful 
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    22
//          thought, coupled with judiciously placed print 
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    23
//                                             statements."
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    24
//       — Brian W. Kernighan, in Unix for Beginners (1979)
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    25
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    26
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    27
def gcd_db(a: Int, b: Int) : Int = {
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    28
  println(s"Function called with $a and $b.")
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    29
  if (b == 0) a else gcd_db(b, a % b)
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    30
}
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    31
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    32
gcd_db(48, 18)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
    33
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
    34
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    35
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    36
// you can also implement your own string interpolations
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    37
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    38
import scala.language.implicitConversions
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    39
import scala.language.reflectiveCalls
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    40
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    41
implicit def sring_inters(sc: StringContext) = new {
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    42
    def i(args: Any*): String = s"\t${sc.s(args:_*)}\n"
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    43
    def l(args: Any*): String = s"${sc.s(args:_*)}:\n"
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    44
}
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    45
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    46
// this allows you to write things like
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    47
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    48
i"add ${3+2}" 
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    49
l"some_fresh_name"
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    50
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    51
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    52
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    53
// The Option Type
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    54
//=================
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    55
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    56
// in Java, if something unusually happens, you return null 
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    57
// or raise an exception
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    58
//
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    59
//in Scala you use Options instead
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    60
//   - if the value is present, you use Some(value)
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    61
//   - if no value is present, you use None
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
    62
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
    63
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    64
List(7,2,3,4,5,6).find(_ < 4)
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    65
List(5,6,7,8,9).find(_ < 4)
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
    66
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    67
// Int:      ..., 0, 1, 2,...
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    68
// Boolean:  true false
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    69
//
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    70
// List[Int]: Nil, List(_) 
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    71
//
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    72
// Option[Int]: None, Some(0), Some(1), ...
447
f51e593903ac updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 384
diff changeset
    73
// Option[Boolean]: None, Some(true), Some(false)
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    74
// Option[...]: None, Some(_)
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    75
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    76
def safe_div(x: Int, y: Int) : Option[Int] = 
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    77
  if (y == 0) None else Some(x / y)
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    78
447
f51e593903ac updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 384
diff changeset
    79
safe_div(10 + 5, 4 - 1)  
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    80
447
f51e593903ac updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 384
diff changeset
    81
List(1,2,3,4,5,6).indexOf(7)
f51e593903ac updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 384
diff changeset
    82
List[Int]().minOption
f51e593903ac updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 384
diff changeset
    83
f51e593903ac updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 384
diff changeset
    84
def my_min(ls: List[Int]) : Option[Int] = 
f51e593903ac updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 384
diff changeset
    85
  ls.minOption
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    86
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    87
my_min(List(1,2,3,4))
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    88
310
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
    89
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    90
// better error handling with Options (no exceptions)
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    91
//
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    92
//  Try(something).getOrElse(what_to_do_in_case_of_an_exception)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
    93
//
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    94
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    95
import scala.util._
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    96
import io.Source
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    97
447
f51e593903ac updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 384
diff changeset
    98
val my_url = "https://nms.kcl.ac.uk/christian.urban/"
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    99
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   100
Source.fromURL(my_url)("ISO-8859-1").mkString
447
f51e593903ac updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 384
diff changeset
   101
Source.fromURL(my_url)("ISO-8859-1").getLines().toList
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   102
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   103
Try(Source.fromURL(my_url)("ISO-8859-1").mkString).getOrElse("")
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   104
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   105
Try(Some(Source.fromURL(my_url)("ISO-8859-1").mkString)).getOrElse(None)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   106
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   107
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   108
// the same for files
447
f51e593903ac updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 384
diff changeset
   109
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   110
Try(Some(Source.fromFile("test.txt")("ISO-8859-1").mkString)).getOrElse(None)
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   111
447
f51e593903ac updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 384
diff changeset
   112
Try(Source.fromFile("test.txt")("ISO-8859-1").mkString).toOption
f51e593903ac updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 384
diff changeset
   113
f51e593903ac updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 384
diff changeset
   114
Using(Source.fromFile("test.txt")("ISO-8859-1"))(_.mkString).toOption
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   115
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   116
// how to implement a function for reading 
447
f51e593903ac updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 384
diff changeset
   117
// (lines) from files...
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   118
//
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   119
def get_contents(name: String) : List[String] = 
447
f51e593903ac updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 384
diff changeset
   120
  Source.fromFile(name)("ISO-8859-1").getLines().toList
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   121
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   122
get_contents("text.txt")
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   123
get_contents("test.txt")
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   124
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   125
// slightly better - return Nil
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   126
def get_contents(name: String) : List[String] = 
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   127
  Try(Source.fromFile(name)("ISO-8859-1").getLines.toList).getOrElse(List())
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   128
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   129
get_contents("text.txt")
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   130
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   131
// much better - you record in the type that things can go wrong 
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   132
def get_contents(name: String) : Option[List[String]] = 
447
f51e593903ac updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 384
diff changeset
   133
  Try(Some(Source.fromFile(name)("ISO-8859-1").getLines().toList)).getOrElse(None)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   134
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   135
get_contents("text.txt")
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   136
get_contents("test.txt")
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   137
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   138
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   139
// operations on options
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   140
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   141
val lst = List(None, Some(1), Some(2), None, Some(3))
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   142
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   143
lst.flatten
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   144
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   145
Some(1).get
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   146
None.get
310
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   147
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   148
Some(1).isDefined
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   149
None.isDefined
310
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   150
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   151
for (x <- lst) yield x.getOrElse(0)
310
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   152
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   153
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   154
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   155
val ps = List((3, 0), (4, 2), (6, 2), 
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   156
              (2, 0), (1, 0), (1, 1))
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   157
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   158
// division where possible
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   159
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   160
for ((x, y) <- ps) yield {
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   161
  if (y == 0) None else Some(x / y)
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   162
}
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   163
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   164
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   165
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   166
// getOrElse is for setting a default value
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   167
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   168
val lst = List(None, Some(1), Some(2), None, Some(3))
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   169
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   170
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   171
// a function that turns strings into numbers 
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   172
// (similar to .toInt)
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   173
Integer.parseInt("1234")
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   174
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   175
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   176
def get_me_an_int(s: String) : Option[Int] = 
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   177
 Try(Some(Integer.parseInt(s))).getOrElse(None)
310
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   178
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   179
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   180
// This may not look any better than working with null in Java, but to
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   181
// see the value, you have to put yourself in the shoes of the
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   182
// consumer of the get_me_an_int function, and imagine you didn't
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   183
// write that function.
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   184
//
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   185
// In Java, if you didn't write this function, you'd have to depend on
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   186
// the Javadoc of the get_me_an_int. If you didn't look at the Javadoc, 
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   187
// you might not know that get_me_an_int could return null, and your 
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   188
// code could potentially throw a NullPointerException.
310
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   189
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   190
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   191
// even Scala is not immune to problems like this:
310
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   192
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   193
List(5,6,7,8,9).indexOf(7)
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   194
List(5,6,7,8,9).indexOf(10)
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   195
List(5,6,7,8,9)(-1)
310
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   196
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   197
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   198
Try({
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   199
  val x = 3
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   200
  val y = 0
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   201
  Some(x / y)
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   202
}).getOrElse(None)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   203
323
1f8005b4cdf6 updated
Christian Urban <urbanc@in.tum.de>
parents: 320
diff changeset
   204
1f8005b4cdf6 updated
Christian Urban <urbanc@in.tum.de>
parents: 320
diff changeset
   205
// minOption 
1f8005b4cdf6 updated
Christian Urban <urbanc@in.tum.de>
parents: 320
diff changeset
   206
// maxOption 
1f8005b4cdf6 updated
Christian Urban <urbanc@in.tum.de>
parents: 320
diff changeset
   207
// minByOption 
1f8005b4cdf6 updated
Christian Urban <urbanc@in.tum.de>
parents: 320
diff changeset
   208
// maxByOption
1f8005b4cdf6 updated
Christian Urban <urbanc@in.tum.de>
parents: 320
diff changeset
   209
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   210
// Higher-Order Functions
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   211
//========================
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   212
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   213
// functions can take functions as arguments
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   214
// and produce functions as result
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   215
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   216
def even(x: Int) : Boolean = x % 2 == 0
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   217
def odd(x: Int) : Boolean = x % 2 == 1
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   218
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   219
val lst = (1 to 10).toList
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   220
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   221
lst.filter(even)
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   222
lst.count(odd)
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   223
lst.find(even)
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   224
lst.exists(even)
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   225
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   226
lst.find(_ < 4)
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   227
lst.filter(_ < 4) 
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   228
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   229
def less4(x: Int) : Boolean = x < 4
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   230
lst.find(less4)
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   231
lst.find(_ < 4)
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   232
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   233
lst.filter(x => x % 2 == 0)
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   234
lst.filter(_ % 2 == 0)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   235
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   236
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   237
lst.sortWith((x, y) => x < y)
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   238
lst.sortWith(_ > _)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   239
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   240
// but this only works when the arguments are clear, but 
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   241
// not with multiple occurences
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   242
lst.find(n => odd(n) && n > 2)
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   243
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   244
447
f51e593903ac updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 384
diff changeset
   245
// lexicographic ordering
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   246
val ps = List((3, 0), (3, 2), (4, 2), (2, 2), 
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   247
              (2, 0), (1, 1), (1, 0))
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   248
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   249
def lex(x: (Int, Int), y: (Int, Int)) : Boolean = 
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   250
  if (x._1 == y._1) x._2 < y._2 else x._1 < y._1
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   251
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   252
ps.sortWith(lex)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   253
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   254
ps.sortBy(x => x._1)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   255
ps.sortBy(_._2)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   256
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   257
ps.maxBy(_._1)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   258
ps.maxBy(_._2)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   259
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   260
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   261
// maps (lower-case)
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   262
//===================
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   263
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   264
def double(x: Int): Int = x + x
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   265
def square(x: Int): Int = x * x
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   266
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   267
val lst = (1 to 10).toList
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   268
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   269
lst.map(square)
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   270
lst.map(x => (double(x), square(x)))
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   271
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   272
// works also for strings
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   273
def tweet(c: Char) = c.toUpper
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   274
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   275
"Hello World".map(tweet)
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   276
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   277
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   278
// this can be iterated
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   279
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   280
lst.map(square).filter(_ > 4)
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   281
363
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   282
lst.map(square).find(_ > 4)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   283
lst.map(square).find(_ > 4).map(double)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   284
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   285
lst.map(square)
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   286
   .find(_ > 4)
363
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   287
   .map(double)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   288
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   289
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   290
// Option Type and maps
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   291
//======================
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   292
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   293
// a function that turns strings into numbers (similar to .toInt)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   294
Integer.parseInt("12u34")
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   295
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   296
// maps on Options
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   297
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   298
import scala.util._
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   299
363
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   300
def get_me_an_int(s: String) : Option[Int] = 
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   301
 Try(Some(Integer.parseInt(s))).getOrElse(None)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   302
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   303
get_me_an_int("12345").map(_ % 2 == 0)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   304
get_me_an_int("12u34").map(_ % 2 == 0)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   305
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   306
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   307
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   308
val lst = List("12345", "foo", "5432", "bar", "x21", "456")
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   309
for (x <- lst) yield get_me_an_int(x)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   310
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   311
// summing up all the numbers
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   312
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   313
lst.map(get_me_an_int).flatten.sum
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   314
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   315
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   316
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   317
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   318
// this is actually how for-comprehensions are
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   319
// defined in Scala
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   320
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   321
lst.map(n => square(n))
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   322
for (n <- lst) yield square(n)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   323
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   324
// lets define our own higher-order functions
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   325
// type of functions is for example Int => Int
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   326
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   327
363
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   328
def my_map_int(lst: List[Int], f: Int => Int) : List[Int] = 
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   329
{
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   330
  if (lst == Nil) Nil
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   331
  else f(lst.head) :: my_map_int(lst.tail, f)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   332
}
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   333
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   334
my_map_int(lst, square)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   335
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   336
// same function using pattern matching: a kind
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   337
// of switch statement on steroids (see more later on)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   338
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   339
def my_map_int(lst: List[Int], f: Int => Int) : List[Int] = 
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   340
  lst match {
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   341
    case Nil => Nil
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   342
    case x::xs => f(x)::my_map_int(xs, f)
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   343
  }
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   344
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   345
363
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   346
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   347
val biglst = (1 to 10000).toList
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   348
my_map_int(biglst, double)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   349
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   350
(1 to 10000000).toList.map(double)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   351
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   352
// other function types
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   353
//
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   354
// f1: (Int, Int) => Int
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   355
// f2: List[String] => Option[Int]
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   356
// ... 
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   357
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   358
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   359
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   360
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   361
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   362
// Map type (upper-case)
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   363
//=======================
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   364
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   365
// Note the difference between map and Map
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   366
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   367
val m = Map(1 -> "one", 2 -> "two", 10 -> "many")
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   368
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   369
List((1, "one"), (2, "two"), (10, "many")).toMap
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   370
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   371
m.get(1)
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   372
m.get(4)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   373
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   374
m.getOrElse(1, "")
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   375
m.getOrElse(4, "")
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   376
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   377
val new_m = m + (10 -> "ten")
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   378
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   379
new_m.get(10)
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   380
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   381
val m2 = for ((k, v) <- m) yield (k, v.toUpperCase)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   382
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   383
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   384
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   385
// groupBy function on Maps
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   386
val lst = List("one", "two", "three", "four", "five")
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   387
lst.groupBy(_.head)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   388
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   389
lst.groupBy(_.length)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   390
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   391
lst.groupBy(_.length).get(3)
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   392
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   393
val grps = lst.groupBy(_.length)
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   394
grps.keySet
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   395
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   396
51
0e60e6c24b99 updated
Christian Urban <urbanc@in.tum.de>
parents: 39
diff changeset
   397
192
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   398
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   399
// Pattern Matching
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   400
//==================
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   401
365
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   402
// A powerful tool which is supposed to come to Java in 
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   403
// a few years time (https://www.youtube.com/watch?v=oGll155-vuQ).
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   404
// ...Scala already has it for many years ;o)
192
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   405
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   406
// The general schema:
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   407
//
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   408
//    expression match {
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   409
//       case pattern1 => expression1
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   410
//       case pattern2 => expression2
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   411
//       ...
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   412
//       case patternN => expressionN
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   413
//    }
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   414
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   415
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   416
// recall
365
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   417
def my_map_int(lst: List[Int], f: Int => Int) : List[Int] = 
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   418
  lst match {
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   419
    case Nil => Nil
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   420
    case x::xs => f(x)::my_map_int(xs, f)
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   421
  }
58
93a2b6e4b84c updated
Christian Urban <urbanc@in.tum.de>
parents: 57
diff changeset
   422
365
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   423
def my_map_option(o: Option[Int], f: Int => Int) : Option[Int] = 
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   424
  o match {
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   425
    case None => None
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   426
    case Some(x) => Some(f(x))
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   427
  }
58
93a2b6e4b84c updated
Christian Urban <urbanc@in.tum.de>
parents: 57
diff changeset
   428
365
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   429
my_map_option(None, x => x * x)
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   430
my_map_option(Some(8), x => x * x)
192
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   431
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   432
192
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   433
// you can also have cases combined
266
ca48ac1d3c3e updated to 2.13
Christian Urban <urbanc@in.tum.de>
parents: 212
diff changeset
   434
def season(month: String) : String = month match {
192
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   435
  case "March" | "April" | "May" => "It's spring"
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   436
  case "June" | "July" | "August" => "It's summer"
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   437
  case "September" | "October" | "November" => "It's autumn"
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   438
  case "December" => "It's winter"
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   439
  case "January" | "February" => "It's unfortunately winter"
365
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   440
  case _ => "Wrong month"
266
ca48ac1d3c3e updated to 2.13
Christian Urban <urbanc@in.tum.de>
parents: 212
diff changeset
   441
}
ca48ac1d3c3e updated to 2.13
Christian Urban <urbanc@in.tum.de>
parents: 212
diff changeset
   442
365
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   443
// pattern-match on integers
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   444
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   445
def fib(n: Int) : Int = n match { 
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   446
  case 0 | 1 => 1
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   447
  case n => fib(n - 1) + fib(n - 2)
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   448
}
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   449
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   450
fib(10)
266
ca48ac1d3c3e updated to 2.13
Christian Urban <urbanc@in.tum.de>
parents: 212
diff changeset
   451
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   452
// Silly: fizz buzz
192
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   453
def fizz_buzz(n: Int) : String = (n % 3, n % 5) match {
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   454
  case (0, 0) => "fizz buzz"
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   455
  case (0, _) => "fizz"
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   456
  case (_, 0) => "buzz"
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   457
  case _ => n.toString  
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   458
}
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   459
365
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   460
for (n <- 1 to 20) 
192
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   461
 println(fizz_buzz(n))
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   462
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   463
365
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   464
val lst = List(None, Some(1), Some(2), None, Some(3)).flatten
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   465
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   466
def my_flatten(xs: List[Option[Int]]): List[Int] = 
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   467
 xs match {
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   468
   case Nil => Nil 
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   469
   case None::rest => my_flatten(rest)
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   470
   case Some(v)::rest => v :: my_flatten(rest)
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   471
 }
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   472
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   473
my_flatten(List(None, Some(1), Some(2), None, Some(3)))
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   474
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   475
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   476
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   477
 
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   478
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   479
278
0c2481cd8b1c updated
Christian Urban <urbanc@in.tum.de>
parents: 268
diff changeset
   480
0c2481cd8b1c updated
Christian Urban <urbanc@in.tum.de>
parents: 268
diff changeset
   481
309
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   482
// Recursion
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   483
//===========
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   484
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   485
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   486
/* Say you have characters a, b, c.
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   487
   What are all the combinations of a certain length?
309
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   488
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   489
   All combinations of length 2:
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   490
  
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   491
     aa, ab, ac, ba, bb, bc, ca, cb, cc
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   492
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   493
   Combinations of length 3:
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   494
   
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   495
     aaa, baa, caa, and so on......
309
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   496
*/
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   497
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   498
def combs(cs: List[Char], n: Int) : List[String] = {
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   499
  if (n == 0) List("")
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   500
  else for (c <- cs; s <- combs(cs, n - 1)) yield s"$c$s"
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   501
}
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   502
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   503
combs(List('a', 'b', 'c'), 3)
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   504
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   505
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   506
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   507
def combs(cs: List[Char], l: Int) : List[String] = {
309
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   508
  if (l == 0) List("")
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   509
  else for (c <- cs; s <- combs(cs, l - 1)) yield s"$c$s"
309
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   510
}
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   511
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   512
combs("abc".toList, 2)
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   513
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   514
329
8a34b2ebc8cc updated
Christian Urban <urbanc@in.tum.de>
parents: 323
diff changeset
   515
// When writing recursive functions you have to
8a34b2ebc8cc updated
Christian Urban <urbanc@in.tum.de>
parents: 323
diff changeset
   516
// think about three points
8a34b2ebc8cc updated
Christian Urban <urbanc@in.tum.de>
parents: 323
diff changeset
   517
// 
8a34b2ebc8cc updated
Christian Urban <urbanc@in.tum.de>
parents: 323
diff changeset
   518
// - How to start with a recursive function
8a34b2ebc8cc updated
Christian Urban <urbanc@in.tum.de>
parents: 323
diff changeset
   519
// - How to communicate between recursive calls
8a34b2ebc8cc updated
Christian Urban <urbanc@in.tum.de>
parents: 323
diff changeset
   520
// - Exit conditions
8a34b2ebc8cc updated
Christian Urban <urbanc@in.tum.de>
parents: 323
diff changeset
   521
8a34b2ebc8cc updated
Christian Urban <urbanc@in.tum.de>
parents: 323
diff changeset
   522
147
72f7dd1a3754 updated
Christian Urban <urbanc@in.tum.de>
parents: 95
diff changeset
   523
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   524
// A Recursive Web Crawler / Email Harvester
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   525
//===========================================
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   526
//
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   527
// the idea is to look for links using the
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   528
// regular expression "https?://[^"]*" and for
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   529
// email addresses using another regex.
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   530
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   531
import io.Source
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   532
import scala.util._
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   533
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   534
// gets the first 10K of a web-page
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   535
def get_page(url: String) : String = {
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   536
  Try(Source.fromURL(url)("ISO-8859-1").take(10000).mkString).
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   537
    getOrElse { println(s"  Problem with: $url"); ""}
147
72f7dd1a3754 updated
Christian Urban <urbanc@in.tum.de>
parents: 95
diff changeset
   538
}
72f7dd1a3754 updated
Christian Urban <urbanc@in.tum.de>
parents: 95
diff changeset
   539
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   540
// regex for URLs and emails
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   541
val http_pattern = """"https?://[^"]*"""".r
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   542
val email_pattern = """([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z\.]{2,6})""".r
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   543
268
e43f7e92ba26 updated
Christian Urban <urbanc@in.tum.de>
parents: 266
diff changeset
   544
//test case:
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   545
//email_pattern.findAllIn
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   546
//  ("foo bla christian@kcl.ac.uk 1234567").toList
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   547
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   548
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   549
// drops the first and last character from a string
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   550
def unquote(s: String) = s.drop(1).dropRight(1)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   551
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   552
def get_all_URLs(page: String): Set[String] = 
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   553
  http_pattern.findAllIn(page).map(unquote).toSet
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   554
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   555
// naive version of crawl - searches until a given depth,
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   556
// visits pages potentially more than once
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   557
def crawl(url: String, n: Int) : Unit = {
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   558
  if (n == 0) ()
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   559
  else {
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   560
    println(s"  Visiting: $n $url")
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   561
    for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   562
  }
147
72f7dd1a3754 updated
Christian Urban <urbanc@in.tum.de>
parents: 95
diff changeset
   563
}
72f7dd1a3754 updated
Christian Urban <urbanc@in.tum.de>
parents: 95
diff changeset
   564
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   565
// some starting URLs for the crawler
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   566
val startURL = """https://nms.kcl.ac.uk/christian.urban/"""
147
72f7dd1a3754 updated
Christian Urban <urbanc@in.tum.de>
parents: 95
diff changeset
   567
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   568
crawl(startURL, 2)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   569
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   570
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   571
// a primitive email harvester
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   572
def emails(url: String, n: Int) : Set[String] = {
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   573
  if (n == 0) Set()
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   574
  else {
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   575
    println(s"  Visiting: $n $url")
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   576
    val page = get_page(url)
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   577
    val new_emails = email_pattern.findAllIn(page).toSet
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   578
    new_emails ++ (for (u <- get_all_URLs(page)) yield emails(u, n - 1)).flatten
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   579
  }
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   580
}
55
6610c1dfa8a9 updated
Christian Urban <urbanc@in.tum.de>
parents: 53
diff changeset
   581
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   582
emails(startURL, 3)
55
6610c1dfa8a9 updated
Christian Urban <urbanc@in.tum.de>
parents: 53
diff changeset
   583
6610c1dfa8a9 updated
Christian Urban <urbanc@in.tum.de>
parents: 53
diff changeset
   584
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   585
// if we want to explore the internet "deeper", then we
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   586
// first have to parallelise the request of webpages:
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   587
//
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   588
// scala -cp scala-parallel-collections_2.13-0.2.0.jar 
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   589
// import scala.collection.parallel.CollectionConverters._
55
6610c1dfa8a9 updated
Christian Urban <urbanc@in.tum.de>
parents: 53
diff changeset
   590
53
9f8751912560 updated
Christian Urban <urbanc@in.tum.de>
parents: 51
diff changeset
   591
9f8751912560 updated
Christian Urban <urbanc@in.tum.de>
parents: 51
diff changeset
   592
9f8751912560 updated
Christian Urban <urbanc@in.tum.de>
parents: 51
diff changeset
   593
192
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   594
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   595
// Jumping Towers
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   596
//================
278
0c2481cd8b1c updated
Christian Urban <urbanc@in.tum.de>
parents: 268
diff changeset
   597
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   598
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   599
def moves(xs: List[Int], n: Int) : List[List[Int]] = 
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   600
 (xs, n) match {
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   601
   case (Nil, _) => Nil
366
1c829680503e updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 365
diff changeset
   602
   case (_, 0) => Nil
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   603
   case (x::xs, n) => (x::xs) :: moves(xs, n - 1)
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   604
 }
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   605
366
1c829680503e updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 365
diff changeset
   606
// List(5,5,1,0) -> moves(List(5,1,0), 5)
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   607
moves(List(5,1,0), 1)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   608
moves(List(5,1,0), 2)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   609
moves(List(5,1,0), 5)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   610
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   611
// checks whether a jump tour exists at all
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   612
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   613
def search(xs: List[Int]) : Boolean = xs match {
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   614
  case Nil => true
366
1c829680503e updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 365
diff changeset
   615
  case x::xs =>
1c829680503e updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 365
diff changeset
   616
    if (xs.length < x) true 
1c829680503e updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 365
diff changeset
   617
    else moves(xs, x).exists(search(_))
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   618
}
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   619
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   620
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   621
search(List(5,3,2,5,1,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   622
search(List(3,5,1,0,0,0,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   623
search(List(3,5,1,0,0,0,0,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   624
search(List(3,5,1,0,0,0,1,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   625
search(List(3,5,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   626
search(List(5,1,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   627
search(Nil)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   628
search(List(1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   629
search(List(5,1,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   630
search(List(3,5,1,0,0,0,0,0,0,0,0,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   631
366
1c829680503e updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 365
diff changeset
   632
1c829680503e updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 365
diff changeset
   633
import scala.util._
1c829680503e updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 365
diff changeset
   634
List.fill(100)(Random.nextInt(2))
1c829680503e updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 365
diff changeset
   635
search(List.fill(100)(Random.nextInt(10)))
1c829680503e updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 365
diff changeset
   636
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   637
// generate *all* jump tours
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   638
//    if we are only interested in the shortes one, we could
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   639
//    shortcircut the calculation and only return List(x) in
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   640
//    case where xs.length < x, because no tour can be shorter
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   641
//    than 1
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   642
// 
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   643
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   644
def jumps(xs: List[Int]) : List[List[Int]] = xs match {
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   645
  case Nil => Nil
366
1c829680503e updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 365
diff changeset
   646
  case x::xs => {
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   647
    val children = moves(xs, x)
366
1c829680503e updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 365
diff changeset
   648
    val results = 
1c829680503e updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 365
diff changeset
   649
      children.map(cs => jumps(cs).map(x :: _)).flatten
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   650
    if (xs.length < x) List(x) :: results else results
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   651
  }
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   652
}
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   653
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   654
jumps(List(3,5,1,2,1,2,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   655
jumps(List(3,5,1,2,3,4,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   656
jumps(List(3,5,1,0,0,0,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   657
jumps(List(3,5,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   658
jumps(List(5,1,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   659
jumps(Nil)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   660
jumps(List(1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   661
jumps(List(5,1,2))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   662
moves(List(1,2), 5)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   663
jumps(List(1,5,1,2))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   664
jumps(List(3,5,1,0,0,0,0,0,0,0,0,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   665
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   666
jumps(List(5,3,2,5,1,1)).minBy(_.length)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   667
jumps(List(1,3,5,8,9,2,6,7,6,8,9)).minBy(_.length)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   668
jumps(List(1,3,6,1,0,9)).minBy(_.length)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   669
jumps(List(2,3,1,1,2,4,2,0,1,1)).minBy(_.length)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   670
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   671