Return to chapter index

26 Extractors

Sample run of chapter's interpreter examples

• 26.1 An example: extracting email addresses
• 26.2 Extractors
• 26.3 Patterns with zero or one variables
• 26.4 Variable argument extractors
• 26.5 Extractors and sequence patterns
• 26.6 Extractors versus case classes
• 26.7 Regular expressions
• 26.8 Conclusion

26.1 An example: extracting email addresses

  def isEMail(s: String): Boolean
  def domain(s: String): String
  def user(s: String): String


  if (isEMail(s)) println(user(s) +" AT "+ domain(s))
  else println("not an email address")


  EMail(user, domain)


// In file extractors/IsEmail.scala

  s match {
    case EMail(user, domain) => println(user +" AT "+ domain)
    case _ => println("not an email address")
  }


  ss match {
    case EMail(u1, d1) :: EMail(u2, d2) :: _ if (u1 == u2) => ...
    ...
  }


  

26.2 Extractors

// In file extractors/EMail.scala

  object EMail {

    // The injection method (optional)
    def apply(user: String, domain: String) = user +"@"+ domain

    // The extraction method (mandatory)
    def unapply(str: String): Option[(String, String)] = {
      val parts = str split "@"
      if (parts.length == 2) Some(parts(0), parts(1)) else None
    }
  }


  object EMail extends ((String, String) => String) { ... }


  unapply("John@epfl.ch")  equals  Some("John", "epfl.ch")
  unapply("John Doe")  equals  None


  selectorString match { case EMail(user, domain) => ... }


  EMail.unapply(selectorString)


  val x: Any = ...
  x match { case EMail(user, domain) => ... }


// In file extractors/Misc.scala

  EMail.unapply(EMail.apply(user, domain))


  Some(user, domain)


  EMail.unapply(obj) match { 
    case Some(u, d) => EMail.apply(u, d) 
  }


  

26.3 Patterns with zero or one variables

// In file extractors/Twice.scala

  object Twice {
    def apply(s: String): String = s + s
    def unapply(s: String): Option[String] = {
      val length = s.length / 2
      val half = s.substring(0, length)
      if (half == s.substring(length)) Some(half) else None
    }
  }


// In file extractors/UpperCase.scala

  object UpperCase {
    def unapply(s: String): Boolean = s.toUpperCase == s
  }


// In file extractors/Test2.scala

  def userTwiceUpper(s: String) = s match {
    case EMail(Twice(x @ UpperCase()), domain) =>
      "match: "+ x +" in domain "+ domain
    case _ => 
      "no match"
  }


  scala> userTwiceUpper("DIDI@hotmail.com")
  res0: java.lang.String = match: DI in domain hotmail.com

  scala> userTwiceUpper("DIDO@hotmail.com")
  res1: java.lang.String = no match

  scala> userTwiceUpper("didi@hotmail.com")
  res2: java.lang.String = no match


  

26.4 Variable argument extractors

// In file extractors/DomainTest.scala

  dom match {
    case Domain("org", "acm") => println("acm.org")
    case Domain("com", "sun", "java") => println("java.sun.com")
    case Domain("net", _*) => println("a .net domain")
  }


// In file extractors/Domain.scala

  object Domain {

    // The injection method (optional)
    def apply(parts: String*): String = 
      parts.reverse.mkString(".")

    // The extraction method (mandatory)
    def unapplySeq(whole: String): Option[Seq[String]] = 
      Some(whole.split("\\.").reverse)
  }


// In file extractors/DomainTest.scala

  def isTomInDotCom(s: String): Boolean = s match {
    case EMail("tom", Domain("com", _*)) => true
    case _ => false
  }


  scala> isTomInDotCom("tom@sun.com")
  res3: Boolean = true

  scala> isTomInDotCom("peter@sun.com")
  res4: Boolean = false

  scala> isTomInDotCom("tom@acm.org")
  res5: Boolean = false


// In file extractors/ExpandedEMail.scala

  object ExpandedEMail {
    def unapplySeq(email: String)
        : Option[(String, Seq[String])] = {
      val parts = email split "@"
      if (parts.length == 2) 
        Some(parts(0), parts(1).split("\\.").reverse)
      else 
        None
    }
  }


  scala> val s = "tom@support.epfl.ch"
  s: java.lang.String = tom@support.epfl.ch

  scala> val ExpandedEMail(name, topdom, subdoms @ _*) = s
  name: String = tom
  topdom: String = ch
  subdoms: Seq[String] = WrappedArray(epfl, support)


  

26.5 Extractors and sequence patterns

  List()
  List(x, y, _*)
  Array(x, 0, 0, _)


  package scala
  object List {
    def apply[T](elems: T*) = elems.toList
    def unapplySeq[T](x: List[T]): Option[Seq[T]] = Some(x)
    ... 
  }


  List()
  List(1, 2, 3)


  

26.6 Extractors versus case classes

  case C(...)


  

26.7 Regular expressions

  scala> import scala.util.matching.Regex


  scala> val Decimal = new Regex("(-)?(\\d+)(\\.\\d*)?")
  Decimal: scala.util.matching.Regex = (-)?(\d+)(\.\d*)?


  scala> val Decimal = new Regex("""(-)?(\d+)(\.\d*)?""")
  Decimal: scala.util.matching.Regex = (-)?(\d+)(\.\d*)?


  scala> val Decimal = """(-)?(\d+)(\.\d*)?""".r
  Decimal: scala.util.matching.Regex = (-)?(\d+)(\.\d*)?


  package scala.runtime
  import scala.util.matching.Regex

  class StringOps(self: String) ... {
    ...
    def r = new Regex(self)
  }


  scala> val Decimal = """(-)?(\d+)(\.\d*)?""".r
  Decimal: scala.util.matching.Regex = (-)?(\d+)(\.\d*)?

  scala> val input = "for -1.0 to 99 by 3"      
  input: java.lang.String = for -1.0 to 99 by 3

  scala> for (s <- Decimal findAllIn input)
       | println(s)
  -1.0
  99
  3

  scala> Decimal findFirstIn input
  res7: Option[String] = Some(-1.0)

  scala> Decimal findPrefixOf input
  res8: Option[String] = None


  scala> val Decimal(sign, integerpart, decimalpart) = "-1.23"  
  sign: String = -
  integerpart: String = 1
  decimalpart: String = .23


  scala> val Decimal(sign, integerpart, decimalpart) = "1.0"
  sign: String = null
  integerpart: String = 1
  decimalpart: String = .0


  scala> for (Decimal(s, i, d) <- Decimal findAllIn input)
       |   println("sign: "+ s +", integer: "+
       |       i +", decimal: "+ d)
  sign: -, integer: 1, decimal: .0
  sign: null, integer: 99, decimal: null
  sign: null, integer: 3, decimal: null


  

26.8 Conclusion