progs/lecture2.scala
author Christian Urban <christian.urban@kcl.ac.uk>
Mon, 23 Nov 2020 02:43:03 +0000
changeset 365 fc118ee0fce4
parent 364 f1a6fa599d26
child 366 1c829680503e
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
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
     8
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
     9
def cube(n: Int) : Int = n * n * n
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
    10
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    11
val n = 3
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
    12
println("The cube of " + n + " is " + cube(n) + ".")
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    13
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    14
println(s"The cube of $n is ${cube(n)}.")
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    15
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
    16
// or even
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
    17
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    18
println(s"The cube of $n is ${n * n * n}.")
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    19
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    20
// helpful for debugging purposes
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    21
//
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    22
//     "The most effective debugging tool is still careful 
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    23
//          thought, coupled with judiciously placed print 
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    24
//                                             statements."
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    25
//       — Brian W. Kernighan, in Unix for Beginners (1979)
317
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
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    28
def gcd_db(a: Int, b: Int) : Int = {
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    29
  println(s"Function called with $a and $b.")
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    30
  if (b == 0) a else gcd_db(b, a % b)
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    31
}
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    32
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
    33
gcd_db(48, 18)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
    34
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
    35
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    36
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    37
// you can also implement your own string interpolations
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    38
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    39
import scala.language.implicitConversions
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    40
import scala.language.reflectiveCalls
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    41
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    42
implicit def sring_inters(sc: StringContext) = new {
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    43
    def i(args: Any*): String = s"\t${sc.s(args:_*)}\n"
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    44
    def l(args: Any*): String = s"${sc.s(args:_*)}:\n"
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
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    47
// this allows you to write things like
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    48
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    49
i"add ${3+2}" 
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    50
l"some_fresh_name"
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
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    53
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    54
// The Option Type
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    55
//=================
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    56
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    57
// in Java, if something unusually happens, you return null 
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    58
// or raise an exception
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    59
//
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    60
//in Scala you use Options instead
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    61
//   - if the value is present, you use Some(value)
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    62
//   - if no value is present, you use None
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
    63
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
    64
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    65
List(7,2,3,4,5,6).find(_ < 4)
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    66
List(5,6,7,8,9).find(_ < 4)
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
    67
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    68
// Int:      ..., 0, 1, 2,...
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    69
// Boolean:  true false
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    70
//
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    71
// List[Int]: Nil, List(_) 
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    72
//
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    73
// Option[Int]: None, Some(0), Some(1), ...
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
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    79
List(1,2,3,4,5,6).indexOf(7)
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    80
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    81
def my_min(ls: List[Int]) : Option[Int] = ls.minOption
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    82
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    83
my_min(List(1,2,3,4))
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    84
310
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
    85
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    86
// better error handling with Options (no exceptions)
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    87
//
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    88
//  Try(something).getOrElse(what_to_do_in_case_of_an_exception)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
    89
//
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    90
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    91
import scala.util._
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    92
import io.Source
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    93
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    94
val my_url = "https://nms.kcl.ac.uk/christian.urban2/"
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    95
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    96
Source.fromURL(my_url)("ISO-8859-1").mkString
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
    97
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
    98
Try(Source.fromURL(my_url)("ISO-8859-1").mkString).getOrElse("")
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
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
   101
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   102
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   103
// the same for files
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   104
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
   105
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   106
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   107
// how to implement a function for reading 
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   108
// (lines) something from files...
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   109
//
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   110
def get_contents(name: String) : List[String] = 
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   111
  Source.fromFile(name)("ISO-8859-1").getLines.toList
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   112
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   113
get_contents("text.txt")
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   114
get_contents("test.txt")
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   115
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   116
// slightly better - return Nil
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   117
def get_contents(name: String) : List[String] = 
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   118
  Try(Source.fromFile(name)("ISO-8859-1").getLines.toList).getOrElse(List())
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   119
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   120
get_contents("text.txt")
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   121
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   122
// much better - you record in the type that things can go wrong 
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   123
def get_contents(name: String) : Option[List[String]] = 
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   124
  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
   125
316
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   126
get_contents("text.txt")
8b57dd326a91 updated
Christian Urban <urbanc@in.tum.de>
parents: 310
diff changeset
   127
get_contents("test.txt")
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   128
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   129
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   130
// operations on options
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   131
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   132
val lst = List(None, Some(1), Some(2), None, Some(3))
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   133
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   134
lst.flatten
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   135
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   136
Some(1).get
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   137
None.get
310
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   138
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   139
Some(1).isDefined
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   140
None.isDefined
310
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   141
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   142
for (x <- lst) yield x.getOrElse(0)
310
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   143
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   144
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   145
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   146
val ps = List((3, 0), (4, 2), (6, 2), 
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   147
              (2, 0), (1, 0), (1, 1))
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   148
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   149
// division where possible
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   150
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   151
for ((x, y) <- ps) yield {
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   152
  if (y == 0) None else Some(x / y)
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   153
}
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   154
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   155
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   156
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   157
// getOrElse is for setting a default value
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   158
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   159
val lst = List(None, Some(1), Some(2), None, Some(3))
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   160
361
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   161
317
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
// a function that turns strings into numbers 
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   165
// (similar to .toInt)
f88b5cec2e5d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 334
diff changeset
   166
Integer.parseInt("1234")
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   167
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   168
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   169
def get_me_an_int(s: String) : Option[Int] = 
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   170
 Try(Some(Integer.parseInt(s))).getOrElse(None)
310
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   171
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   172
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   173
// 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
   174
// 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
   175
// 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
   176
// write that function.
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   177
//
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   178
// 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
   179
// 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
   180
// 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
   181
// code could potentially throw a NullPointerException.
310
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   182
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   183
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   184
// even Scala is not immune to problems like this:
310
335079d938aa updated
Christian Urban <urbanc@in.tum.de>
parents: 309
diff changeset
   185
317
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   186
List(5,6,7,8,9).indexOf(7)
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   187
List(5,6,7,8,9).indexOf(10)
607ceabeeffc updated
Christian Urban <urbanc@in.tum.de>
parents: 316
diff changeset
   188
List(5,6,7,8,9)(-1)
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
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   191
Try({
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   192
  val x = 3
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   193
  val y = 0
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   194
  Some(x / y)
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   195
}).getOrElse(None)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   196
323
1f8005b4cdf6 updated
Christian Urban <urbanc@in.tum.de>
parents: 320
diff changeset
   197
1f8005b4cdf6 updated
Christian Urban <urbanc@in.tum.de>
parents: 320
diff changeset
   198
// minOption 
1f8005b4cdf6 updated
Christian Urban <urbanc@in.tum.de>
parents: 320
diff changeset
   199
// maxOption 
1f8005b4cdf6 updated
Christian Urban <urbanc@in.tum.de>
parents: 320
diff changeset
   200
// minByOption 
1f8005b4cdf6 updated
Christian Urban <urbanc@in.tum.de>
parents: 320
diff changeset
   201
// maxByOption
1f8005b4cdf6 updated
Christian Urban <urbanc@in.tum.de>
parents: 320
diff changeset
   202
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   203
// Higher-Order Functions
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   204
//========================
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   205
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   206
// functions can take functions as arguments
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   207
// and produce functions as result
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   208
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   209
def even(x: Int) : Boolean = x % 2 == 0
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   210
def odd(x: Int) : Boolean = x % 2 == 1
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
val lst = (1 to 10).toList
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   213
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   214
lst.filter(even)
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   215
lst.count(odd)
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   216
lst.find(even)
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   217
lst.exists(even)
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   218
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   219
lst.find(_ < 4)
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   220
lst.filter(_ < 4) 
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   221
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   222
def less4(x: Int) : Boolean = x < 4
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   223
lst.find(less4)
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   224
lst.find(_ < 4)
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   225
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   226
lst.filter(x => x % 2 == 0)
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   227
lst.filter(_ % 2 == 0)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   228
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   229
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   230
lst.sortWith((x, y) => x < y)
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   231
lst.sortWith(_ > _)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   232
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   233
// but this only works when the arguments are clear, but 
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   234
// not with multiple occurences
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   235
lst.find(n => odd(n) && n > 2)
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   236
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   237
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   238
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   239
val ps = List((3, 0), (3, 2), (4, 2), (2, 2), 
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   240
              (2, 0), (1, 1), (1, 0))
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   241
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   242
def lex(x: (Int, Int), y: (Int, Int)) : Boolean = 
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   243
  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
   244
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   245
ps.sortWith(lex)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   246
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   247
ps.sortBy(x => x._1)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   248
ps.sortBy(_._2)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   249
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   250
ps.maxBy(_._1)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   251
ps.maxBy(_._2)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   252
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   253
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   254
// maps (lower-case)
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   255
//===================
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   256
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   257
def double(x: Int): Int = x + x
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   258
def square(x: Int): Int = x * x
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
val lst = (1 to 10).toList
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   261
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   262
lst.map(square)
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   263
lst.map(x => (double(x), square(x)))
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   264
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   265
// works also for strings
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   266
def tweet(c: Char) = c.toUpper
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   267
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   268
"Hello World".map(tweet)
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   269
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   270
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   271
// this can be iterated
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   272
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   273
lst.map(square).filter(_ > 4)
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   274
363
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   275
lst.map(square).find(_ > 4)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   276
lst.map(square).find(_ > 4).map(double)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   277
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   278
lst.map(square)
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   279
   .find(_ > 4)
363
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   280
   .map(double)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   281
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   282
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   283
// Option Type and maps
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
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   286
// a function that turns strings into numbers (similar to .toInt)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   287
Integer.parseInt("12u34")
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
// maps on Options
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   290
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   291
import scala.util._
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   292
363
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   293
def get_me_an_int(s: String) : Option[Int] = 
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   294
 Try(Some(Integer.parseInt(s))).getOrElse(None)
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
get_me_an_int("12345").map(_ % 2 == 0)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   297
get_me_an_int("12u34").map(_ % 2 == 0)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   298
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   299
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   300
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   301
val lst = List("12345", "foo", "5432", "bar", "x21", "456")
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   302
for (x <- lst) yield get_me_an_int(x)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   303
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   304
// summing up all the numbers
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
lst.map(get_me_an_int).flatten.sum
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
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   309
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   310
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   311
// this is actually how for-comprehensions are
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   312
// defined in Scala
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   313
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   314
lst.map(n => square(n))
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   315
for (n <- lst) yield square(n)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   316
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   317
// lets define our own higher-order functions
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   318
// type of functions is for example Int => Int
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   319
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   320
363
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   321
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
   322
{
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   323
  if (lst == Nil) Nil
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   324
  else f(lst.head) :: my_map_int(lst.tail, f)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   325
}
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   326
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   327
my_map_int(lst, square)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   328
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   329
// same function using pattern matching: a kind
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   330
// of switch statement on steroids (see more later on)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   331
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   332
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
   333
  lst match {
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   334
    case Nil => Nil
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   335
    case x::xs => f(x)::my_map_int(xs, f)
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   336
  }
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   337
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   338
363
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   339
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   340
val biglst = (1 to 10000).toList
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   341
my_map_int(biglst, double)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   342
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   343
(1 to 10000000).toList.map(double)
e5c1d69cffa4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 362
diff changeset
   344
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   345
// other function types
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   346
//
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   347
// f1: (Int, Int) => Int
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   348
// f2: List[String] => Option[Int]
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   349
// ... 
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   350
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   351
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   352
204
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
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   355
// Map type (upper-case)
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   356
//=======================
204
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
// Note the difference between map and Map
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   359
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   360
val m = Map(1 -> "one", 2 -> "two", 10 -> "many")
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   361
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   362
List((1, "one"), (2, "two"), (10, "many")).toMap
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   363
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   364
m.get(1)
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   365
m.get(4)
204
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
m.getOrElse(1, "")
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   368
m.getOrElse(4, "")
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   369
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   370
val new_m = m + (10 -> "ten")
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   371
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   372
new_m.get(10)
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   373
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   374
val m2 = for ((k, v) <- m) yield (k, v.toUpperCase)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   375
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   376
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   377
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   378
// groupBy function on Maps
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   379
val lst = List("one", "two", "three", "four", "five")
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   380
lst.groupBy(_.head)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   381
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   382
lst.groupBy(_.length)
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   383
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   384
lst.groupBy(_.length).get(3)
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   385
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   386
val grps = lst.groupBy(_.length)
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   387
grps.keySet
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   388
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   389
51
0e60e6c24b99 updated
Christian Urban <urbanc@in.tum.de>
parents: 39
diff changeset
   390
192
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   391
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   392
// Pattern Matching
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   393
//==================
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   394
365
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   395
// A powerful tool which is supposed to come to Java in 
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   396
// 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
   397
// ...Scala already has it for many years ;o)
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
// The general schema:
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
//    expression match {
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   402
//       case pattern1 => expression1
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   403
//       case pattern2 => expression2
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   404
//       ...
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   405
//       case patternN => expressionN
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   406
//    }
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
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   409
// recall
365
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   410
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
   411
  lst match {
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   412
    case Nil => Nil
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   413
    case x::xs => f(x)::my_map_int(xs, f)
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   414
  }
58
93a2b6e4b84c updated
Christian Urban <urbanc@in.tum.de>
parents: 57
diff changeset
   415
365
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   416
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
   417
  o match {
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   418
    case None => None
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   419
    case Some(x) => Some(f(x))
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   420
  }
58
93a2b6e4b84c updated
Christian Urban <urbanc@in.tum.de>
parents: 57
diff changeset
   421
365
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   422
my_map_option(None, x => x * x)
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   423
my_map_option(Some(8), x => x * x)
192
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   424
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   425
192
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   426
// you can also have cases combined
266
ca48ac1d3c3e updated to 2.13
Christian Urban <urbanc@in.tum.de>
parents: 212
diff changeset
   427
def season(month: String) : String = month match {
192
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   428
  case "March" | "April" | "May" => "It's spring"
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   429
  case "June" | "July" | "August" => "It's summer"
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   430
  case "September" | "October" | "November" => "It's autumn"
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   431
  case "December" => "It's winter"
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   432
  case "January" | "February" => "It's unfortunately winter"
365
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   433
  case _ => "Wrong month"
266
ca48ac1d3c3e updated to 2.13
Christian Urban <urbanc@in.tum.de>
parents: 212
diff changeset
   434
}
ca48ac1d3c3e updated to 2.13
Christian Urban <urbanc@in.tum.de>
parents: 212
diff changeset
   435
365
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   436
// pattern-match on integers
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   437
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   438
def fib(n: Int) : Int = n match { 
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   439
  case 0 | 1 => 1
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   440
  case n => fib(n - 1) + fib(n - 2)
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   441
}
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   442
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   443
fib(10)
266
ca48ac1d3c3e updated to 2.13
Christian Urban <urbanc@in.tum.de>
parents: 212
diff changeset
   444
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   445
// Silly: fizz buzz
192
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   446
def fizz_buzz(n: Int) : String = (n % 3, n % 5) match {
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   447
  case (0, 0) => "fizz buzz"
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   448
  case (0, _) => "fizz"
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   449
  case (_, 0) => "buzz"
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   450
  case _ => n.toString  
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   451
}
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   452
365
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   453
for (n <- 1 to 20) 
192
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   454
 println(fizz_buzz(n))
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   455
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   456
365
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   457
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
   458
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   459
def my_flatten(xs: List[Option[Int]]): List[Int] = 
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   460
 xs match {
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   461
   case Nil => Nil 
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   462
   case None::rest => my_flatten(rest)
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   463
   case Some(v)::rest => v :: my_flatten(rest)
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   464
 }
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
my_flatten(List(None, Some(1), Some(2), None, Some(3)))
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   467
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   468
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   469
fc118ee0fce4 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 364
diff changeset
   470
 
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
278
0c2481cd8b1c updated
Christian Urban <urbanc@in.tum.de>
parents: 268
diff changeset
   473
0c2481cd8b1c updated
Christian Urban <urbanc@in.tum.de>
parents: 268
diff changeset
   474
309
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   475
// Recursion
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   476
//===========
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   477
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   478
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   479
/* Say you have characters a, b, c.
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   480
   What are all the combinations of a certain length?
309
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   481
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   482
   All combinations of length 2:
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   483
  
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   484
     aa, ab, ac, ba, bb, bc, ca, cb, cc
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   485
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   486
   Combinations of length 3:
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   487
   
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   488
     aaa, baa, caa, and so on......
309
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   489
*/
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   490
320
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   491
def combs(cs: List[Char], n: Int) : List[String] = {
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   492
  if (n == 0) List("")
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   493
  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
   494
}
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   495
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   496
combs(List('a', 'b', 'c'), 3)
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   497
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   498
cdfb2ce30a3d updated
Christian Urban <urbanc@in.tum.de>
parents: 319
diff changeset
   499
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   500
def combs(cs: List[Char], l: Int) : List[String] = {
309
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   501
  if (l == 0) List("")
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   502
  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
   503
}
b192bc772613 updated
Christian Urban <urbanc@in.tum.de>
parents: 278
diff changeset
   504
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   505
combs("abc".toList, 2)
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   506
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   507
329
8a34b2ebc8cc updated
Christian Urban <urbanc@in.tum.de>
parents: 323
diff changeset
   508
// When writing recursive functions you have to
8a34b2ebc8cc updated
Christian Urban <urbanc@in.tum.de>
parents: 323
diff changeset
   509
// think about three points
8a34b2ebc8cc updated
Christian Urban <urbanc@in.tum.de>
parents: 323
diff changeset
   510
// 
8a34b2ebc8cc updated
Christian Urban <urbanc@in.tum.de>
parents: 323
diff changeset
   511
// - How to start with a recursive function
8a34b2ebc8cc updated
Christian Urban <urbanc@in.tum.de>
parents: 323
diff changeset
   512
// - How to communicate between recursive calls
8a34b2ebc8cc updated
Christian Urban <urbanc@in.tum.de>
parents: 323
diff changeset
   513
// - Exit conditions
8a34b2ebc8cc updated
Christian Urban <urbanc@in.tum.de>
parents: 323
diff changeset
   514
8a34b2ebc8cc updated
Christian Urban <urbanc@in.tum.de>
parents: 323
diff changeset
   515
147
72f7dd1a3754 updated
Christian Urban <urbanc@in.tum.de>
parents: 95
diff changeset
   516
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   517
// A Recursive Web Crawler / Email Harvester
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   518
//===========================================
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   519
//
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   520
// the idea is to look for links using the
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   521
// regular expression "https?://[^"]*" and for
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   522
// email addresses using another regex.
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   523
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   524
import io.Source
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   525
import scala.util._
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   526
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   527
// gets the first 10K of a web-page
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   528
def get_page(url: String) : String = {
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   529
  Try(Source.fromURL(url)("ISO-8859-1").take(10000).mkString).
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   530
    getOrElse { println(s"  Problem with: $url"); ""}
147
72f7dd1a3754 updated
Christian Urban <urbanc@in.tum.de>
parents: 95
diff changeset
   531
}
72f7dd1a3754 updated
Christian Urban <urbanc@in.tum.de>
parents: 95
diff changeset
   532
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   533
// regex for URLs and emails
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   534
val http_pattern = """"https?://[^"]*"""".r
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   535
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
   536
268
e43f7e92ba26 updated
Christian Urban <urbanc@in.tum.de>
parents: 266
diff changeset
   537
//test case:
212
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   538
//email_pattern.findAllIn
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   539
//  ("foo bla christian@kcl.ac.uk 1234567").toList
4bda49ec24da updated
Christian Urban <urbanc@in.tum.de>
parents: 204
diff changeset
   540
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   541
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   542
// drops the first and last character from a string
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   543
def unquote(s: String) = s.drop(1).dropRight(1)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   544
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   545
def get_all_URLs(page: String): Set[String] = 
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   546
  http_pattern.findAllIn(page).map(unquote).toSet
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   547
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   548
// naive version of crawl - searches until a given depth,
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   549
// visits pages potentially more than once
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   550
def crawl(url: String, n: Int) : Unit = {
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   551
  if (n == 0) ()
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   552
  else {
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   553
    println(s"  Visiting: $n $url")
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   554
    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
   555
  }
147
72f7dd1a3754 updated
Christian Urban <urbanc@in.tum.de>
parents: 95
diff changeset
   556
}
72f7dd1a3754 updated
Christian Urban <urbanc@in.tum.de>
parents: 95
diff changeset
   557
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   558
// some starting URLs for the crawler
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   559
val startURL = """https://nms.kcl.ac.uk/christian.urban/"""
147
72f7dd1a3754 updated
Christian Urban <urbanc@in.tum.de>
parents: 95
diff changeset
   560
204
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   561
crawl(startURL, 2)
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   562
9b45dd24271b updated
Christian Urban <urbanc@in.tum.de>
parents: 192
diff changeset
   563
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   564
// a primitive email harvester
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   565
def emails(url: String, n: Int) : Set[String] = {
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   566
  if (n == 0) Set()
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   567
  else {
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   568
    println(s"  Visiting: $n $url")
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   569
    val page = get_page(url)
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   570
    val new_emails = email_pattern.findAllIn(page).toSet
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   571
    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
   572
  }
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   573
}
55
6610c1dfa8a9 updated
Christian Urban <urbanc@in.tum.de>
parents: 53
diff changeset
   574
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   575
emails(startURL, 3)
55
6610c1dfa8a9 updated
Christian Urban <urbanc@in.tum.de>
parents: 53
diff changeset
   576
6610c1dfa8a9 updated
Christian Urban <urbanc@in.tum.de>
parents: 53
diff changeset
   577
318
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   578
// if we want to explore the internet "deeper", then we
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   579
// first have to parallelise the request of webpages:
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   580
//
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   581
// scala -cp scala-parallel-collections_2.13-0.2.0.jar 
029e2862bb4e updated
Christian Urban <urbanc@in.tum.de>
parents: 317
diff changeset
   582
// import scala.collection.parallel.CollectionConverters._
55
6610c1dfa8a9 updated
Christian Urban <urbanc@in.tum.de>
parents: 53
diff changeset
   583
53
9f8751912560 updated
Christian Urban <urbanc@in.tum.de>
parents: 51
diff changeset
   584
9f8751912560 updated
Christian Urban <urbanc@in.tum.de>
parents: 51
diff changeset
   585
9f8751912560 updated
Christian Urban <urbanc@in.tum.de>
parents: 51
diff changeset
   586
192
a112e0e2325c updated
Christian Urban <urbanc@in.tum.de>
parents: 174
diff changeset
   587
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   588
// Jumping Towers
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   589
//================
278
0c2481cd8b1c updated
Christian Urban <urbanc@in.tum.de>
parents: 268
diff changeset
   590
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   591
364
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   592
def moves(xs: List[Int], n: Int) : List[List[Int]] = 
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   593
 (xs, n) match {
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   594
   case (Nil, _) => Nil
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   595
   case (xs, 0) => Nil
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   596
   case (x::xs, n) => (x::xs) :: moves(xs, n - 1)
f1a6fa599d26 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 363
diff changeset
   597
 }
319
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   598
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   599
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   600
moves(List(5,1,0), 1)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   601
moves(List(5,1,0), 2)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   602
moves(List(5,1,0), 5)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   603
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   604
// checks whether a jump tour exists at all
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   605
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   606
def search(xs: List[Int]) : Boolean = xs match {
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   607
  case Nil => true
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   608
  case (x::xs) =>
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   609
    if (xs.length < x) true else moves(xs, x).exists(search(_))
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
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
search(List(5,3,2,5,1,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   614
search(List(3,5,1,0,0,0,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   615
search(List(3,5,1,0,0,0,0,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   616
search(List(3,5,1,0,0,0,1,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   617
search(List(3,5,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   618
search(List(5,1,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   619
search(Nil)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   620
search(List(1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   621
search(List(5,1,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   622
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
   623
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   624
// generate *all* jump tours
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   625
//    if we are only interested in the shortes one, we could
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   626
//    shortcircut the calculation and only return List(x) in
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   627
//    case where xs.length < x, because no tour can be shorter
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   628
//    than 1
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   629
// 
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   630
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   631
def jumps(xs: List[Int]) : List[List[Int]] = xs match {
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   632
  case Nil => Nil
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   633
  case (x::xs) => {
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   634
    val children = moves(xs, x)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   635
    val results = children.map(cs => jumps(cs).map(x :: _)).flatten
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   636
    if (xs.length < x) List(x) :: results else results
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   637
  }
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   638
}
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   639
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   640
jumps(List(3,5,1,2,1,2,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   641
jumps(List(3,5,1,2,3,4,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   642
jumps(List(3,5,1,0,0,0,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   643
jumps(List(3,5,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   644
jumps(List(5,1,1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   645
jumps(Nil)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   646
jumps(List(1))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   647
jumps(List(5,1,2))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   648
moves(List(1,2), 5)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   649
jumps(List(1,5,1,2))
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   650
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
   651
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   652
jumps(List(5,3,2,5,1,1)).minBy(_.length)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   653
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
   654
jumps(List(1,3,6,1,0,9)).minBy(_.length)
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   655
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
   656
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   657
b84ea52bfd8f updated
Christian Urban <urbanc@in.tum.de>
parents: 318
diff changeset
   658
334
841727e27252 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 329
diff changeset
   659
841727e27252 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 329
diff changeset
   660
841727e27252 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 329
diff changeset
   661
841727e27252 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 329
diff changeset
   662
/*
841727e27252 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 329
diff changeset
   663
 *               1
362
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   664
 *             / |  \
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   665
 *           /   |   \
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   666
 *         /     |    \
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   667
 *        2      3     8
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   668
 *      /  \    / \   / \
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   669
 *     4    5  6   7 9  10
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   670
 * Preorder: 1,2,4,5,3,6,7,8,9,10
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   671
 * InOrder: 4,2,5,1,6,3,7,9,8,10
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   672
 * PostOrder: 4,5,2,6,7,3,9,10,8,1
1bde878ba6c9 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 361
diff changeset
   673
 *
334
841727e27252 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 329
diff changeset
   674
 
841727e27252 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 329
diff changeset
   675
show inorder, preorder, postorder
841727e27252 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 329
diff changeset
   676
841727e27252 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 329
diff changeset
   677
841727e27252 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 329
diff changeset
   678
841727e27252 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 329
diff changeset
   679
*/