Return to chapter index

33 Combinator Parsing

Sample run of chapter's interpreter examples

• 33.1 Example: Arithmetic expressions
• 33.2 Running your parser
• 33.3 Basic regular expression parsers
• 33.4 Another example: JSON
• 33.5 Parser output
• 33.6 Implementing combinator parsers
• 33.7 String literals and regular expressions
• 33.8 Lexing and parsing
• 33.9 Error reporting
• 33.10 Backtracking versus LL(1)
• 33.11 Conclusion

33.1 Example: Arithmetic expressions

// In file combinator-parsing/Arith.scala

  import scala.util.parsing.combinator._

  class Arith extends JavaTokenParsers {   
    def expr: Parser[Any] = term~rep("+"~term | "-"~term)
    def term: Parser[Any] = factor~rep("*"~factor | "/"~factor)
    def factor: Parser[Any] = floatingPointNumber | "("~expr~")"
  }


  

33.2 Running your parser

// In file combinator-parsing/Arith.scala

  object ParseExpr extends Arith {
    def main(args: Array[String]) = {
      println("input : " + args(0))
      println(parseAll(expr, args(0)))
    }
  }


  parseAll(expr, input)


  $ scala ParseExpr "2 * (3 + 7)"
  input: 2 * (3 + 7)
  [1.12] parsed: ((2~List((*~(((~((3~List())~List((+
  ~(7~List())))))~)))))~List())


  $ scala ParseExpr "2 * (3 + 7))"
  input: 2 * (3 + 7))
  [1.12] failure: `-' expected but `)' found
  
  2 * (3 + 7))
             ^


  

33.3 Basic regular expression parsers

  object MyParsers extends RegexParsers {
    val ident: Parser[String] = """[a-zA-Z_]\w*""".r
  }


  

33.4 Another example: JSON

// In file combinator-parsing/address-book.json

  {
    "address book": {
      "name": "John Smith",
      "address": {
        "street": "10 Market Street",
        "city"  : "San Francisco, CA",
        "zip"   : 94111
      },
      "phone numbers": [
        "408 338-4238",
        "408 111-6892"
      ]
    }
  }


// In file combinator-parsing/JSON.scala

import scala.util.parsing.combinator._

class JSON extends JavaTokenParsers {   

  def value : Parser[Any] = obj | arr | 
                            stringLiteral | 
                            floatingPointNumber | 
                            "null" | "true" | "false"

  def obj   : Parser[Any] = "{"~repsep(member, ",")~"}"

  def arr   : Parser[Any] = "["~repsep(value, ",")~"]"

  def member: Parser[Any] = stringLiteral~":"~value
}


// In file combinator-parsing/JSON.scala

  import java.io.FileReader

  object ParseJSON extends JSON {
    def main(args: Array[String]) = {
      val reader = new FileReader(args(0))
      println(parseAll(value, reader))
    }
  }


  $ scala ParseJSON address-book.json
  [13.4] parsed: (({~List((("address book"~:)~(({~List(((
  "name"~:)~"John Smith"), (("address"~:)~(({~List(((
  "street"~:)~"10 Market Street"), (("city"~:)~"San Francisco
  ,CA"), (("zip"~:)~94111)))~})), (("phone numbers"~:)~(([~
  List("408 338-4238", "408 111-6892"))~]))))~}))))~})


  

33.5 Parser output

  floatingPointNumber ^^ (_.toDouble)


  "true" ^^ (x => true)


  def obj: Parser[Map[String, Any]] = // Can be improved
    "{"~repsep(member, ",")~"}" ^^ 
      { case "{"~ms~"}" => Map() ++ ms }


  case class ~[+A, +B](x: A, y: B) {
    override def toString = "(" + x + "~" + y + ")"
  }


  def obj: Parser[Map[String, Any]] =
    "{"~> repsep(member, ",") <~"}" ^^ (Map() ++ _)


  $ scala JSON1Test address-book.json
  [14.1] parsed: Map(
    address book -> Map(
      name -> John Smith, 
      address -> Map(
        street -> 10 Market Street, 
        city -> San Francisco, CA, 
        zip -> 94111), 
      phone numbers -> List(408 338-4238, 408 111-6892)
    )
  )


// In file combinator-parsing/JSON1.scala

  import scala.util.parsing.combinator._

  class JSON1 extends JavaTokenParsers {   

    def obj: Parser[Map[String, Any]] = 
      "{"~> repsep(member, ",") <~"}" ^^ (Map() ++ _)

    def arr: Parser[List[Any]] =
      "["~> repsep(value, ",") <~"]" 

    def member: Parser[(String, Any)] = 
      stringLiteral~":"~value ^^ 
        { case name~":"~value => (name, value) }

    def value: Parser[Any] = (
      obj
    | arr 
    | stringLiteral
    | floatingPointNumber ^^ (_.toDouble) 
    | "null"  ^^ (x => null) 
    | "true"  ^^ (x => true) 
    | "false" ^^ (x => false)
    )
  }


  def value: Parser[Any] = 
    obj |
    arr |
    stringLiteral |
    ...


    obj;  // semicolon implicitly inserted
  | arr


  class ArithHypothetical extends JavaTokenParsers {   
    def expr: Parser[Any]   = 
      term andThen rep(("+" andThen term) orElse 
                       ("-" andThen term))
    def term: Parser[Any]   = 
      factor andThen rep(("*" andThen factor) orElse 
                         ("/" andThen factor))
    def factor: Parser[Any] = 
      floatingPointNumber orElse 
      ("(" andThen expr andThen ")")
  }


  

33.6 Implementing combinator parsers

  package scala.util.parsing.combinator
  trait Parsers {
    ... // code goes here unless otherwise stated
  }


  type Parser[T] = Input => ParseResult[T]


  type Input = Reader[Elem]   


  type Elem


  sealed abstract class ParseResult[+T] 
  case class Success[T](result: T, in: Input) 
    extends ParseResult[T]
  case class Failure(msg: String, in: Input) 
    extends ParseResult[Nothing]


  abstract class Parser[+T] extends (Input => ParseResult[T]) 
  { p =>
    // An unspecified method that defines 
    // the behavior of this parser.
    def apply(in: Input): ParseResult[T]

    def ~ ...
    def | ...
    ...
  }


  abstract class Parser[+T] extends ... { p =>


  val id = this


  class Outer { outer =>
    class Inner {
      println(Outer.this eq outer) // prints: true
    }
  }


  def elem(kind: String, p: Elem => Boolean) = 
    new Parser[Elem] {
      def apply(in: Input) =
        if (p(in.first)) Success(in.first, in.rest)
        else Failure(kind + " expected", in)
    }


  abstract class Parser[+T] ... { p =>
    ...
    def ~ [U](q: => Parser[U]) = new Parser[T~U] {
      def apply(in: Input) = p(in) match {
        case Success(x, in1) => 
          q(in1) match {
            case Success(y, in2) => Success(new ~(x, y), in2)
            case failure => failure
          }
        case failure => failure
      }
    }


    def <~ [U](q: => Parser[U]): Parser[T] = 
      (p~q) ^^ { case x~y => x }
    def ~> [U](q: => Parser[U]): Parser[U] = 
      (p~q) ^^ { case x~y => y }


    def | (q: => Parser[T]) = new Parser[T] {
      def apply(in: Input) = p(in) match {
        case s1 @ Success(_, _) => s1
        case failure => q(in) 
      }
    }


    def parens = floatingPointNumber | "("~parens~")" 


    def ^^ [U](f: T => U): Parser[U] = new Parser[U] {
      def apply(in: Input) = p(in) match {
        case Success(x, in1) => Success(f(x), in1)
        case failure => failure
      }
    }
  } // end Parser


  def success[T](v: T) = new Parser[T] {
    def apply(in: Input) = Success(v, in)
  }
  def failure(msg: String) = new Parser[Nothing] {
    def apply(in: Input) = Failure(msg, in)
  }


  def opt[T](p: => Parser[T]): Parser[Option[T]] = (
    p ^^ Some(_)  
  | success(None)
  )

  def rep[T](p: => Parser[T]): Parser[List[T]] = (
    p~rep(p) ^^ { case x~xs => x :: xs }  
  | success(List())
  )
  
  def repsep[T](p: => Parser[T],
      q: => Parser[Any]): Parser[List[T]] = (

    p~rep(q~> p) ^^ { case r~rs => r :: rs }  
  | success(List())
  )

} // end Parsers


  

33.7 String literals and regular expressions

  trait RegexParsers extends Parsers { 


    type Elem = Char


    implicit def literal(s: String): Parser[String] = ...
    implicit def regex(r: Regex): Parser[String] = ...


    protected val whiteSpace = """\s+""".r
  } // end RegexParsers


  object MyParsers extends RegexParsers {
    override val whiteSpace = "".r
    ...
  }


  

33.8 Lexing and parsing

  scala.util.parsing.combinator.lexical       
  scala.util.parsing.combinator.syntactical   


  

33.9 Error reporting

  { "name": John,


  [1.13] failure: "false" expected but identifier John found

    { "name": John,
              ^


  def value: Parser[Any] =
    obj | arr | stringLit | floatingPointNumber | "null" |
    "true" | "false" | failure("illegal start of value")


  [1.13] failure: illegal start of value

    { "name": John,
              ^


  var lastFailure: Option[Failure] = None


  case class Failure(msg: String, in: Input) 
      extends ParseResult[Nothing] {

    if (lastFailure.isDefined && 
        lastFailure.get.in.pos <= in.pos)
      lastFailure = Some(this)
  }


  def phrase[T](p: Parser[T]) = new Parser[T] {
    lastFailure = None
    def apply(in: Input) = p(in) match {
      case s @ Success(out, in1) =>
        if (in1.atEnd) s 
        else Failure("end of input expected", in1)
      case f : Failure => 
        lastFailure
    }
  }


  

33.10 Backtracking versus LL(1)

  def expr  : Parser[Any] = 
    term ~! rep("+" ~! term | "-" ~! term)
  def term  : Parser[Any] = 
    factor ~! rep("*" ~! factor | "/" ~! factor)
  def factor: Parser[Any] = 
    "(" ~! expr ~! ")" | floatingPointNumber


  

33.11 Conclusion

  val jsonParser = phrase(value)