Created
June 25, 2014 23:43
-
-
Save OlegIlyenko/c452a5692a61336d87b1 to your computer and use it in GitHub Desktop.
Parboiled2 Predicate Parser
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import scala.annotation.switch | |
import org.parboiled2._ | |
import scala.io.Source | |
import scala.util.{Failure, Success} | |
class PredicateParser(val input: ParserInput) extends Parser with CommonRules { | |
def And = Keyword("and") | |
def Or = Keyword("or") | |
def Not = Keyword("not") | |
def Predicate = rule { WhiteSpace ~ Expression ~ EOI } | |
def Expression: Rule1[AstNode] = rule { Term ~ zeroOrMore(Or ~ Term ~> AstNode.Or.apply _) } | |
def Term: Rule1[AstNode] = rule { Factor ~ zeroOrMore(And ~ Factor ~> AstNode.And.apply _) } | |
def Factor = rule { Not ~ Primary ~> AstNode.Not.apply _ | Primary } | |
def Primary = rule { | |
IntLiteral ~> AstNode.IntLiteral.apply _ | | |
StringLiteral ~> AstNode.StringLiteral.apply _ | | |
Identifier ~> AstNode.Identifier.apply _ | | |
Parens | |
} | |
def Parens = rule { ws('(') ~ Expression ~ ws(')') } | |
} | |
trait CommonRules extends StringBuilding { | |
this: Parser => | |
import CharPredicate.{HexDigit, Digit} | |
def ws(char: Char): Rule0 = rule { ch(char) ~ WhiteSpace } | |
def ws(s: String): Rule0 = rule { str(s) ~ WhiteSpace } | |
def Keyword(s: String) = rule { ignoreCase(s) ~ WhiteSpace } | |
def IntLiteral = rule { capture(Digits) ~> (_.trim.toInt) } | |
def StringLiteral = rule { '"' ~ clearSB() ~ Characters ~ ws('"') ~ push(sb.toString) } | |
def Characters = rule { zeroOrMore(NormalChar | '\\' ~ EscapedChar) } | |
def NormalChar = rule { !QuoteBackslash ~ ANY ~ appendSB() } | |
def EscapedChar = rule { | |
QuoteSlashBackSlash ~ appendSB() | | |
'b' ~ appendSB('\b') | | |
'f' ~ appendSB('\f') | | |
'n' ~ appendSB('\n') | | |
'r' ~ appendSB('\r') | | |
't' ~ appendSB('\t') | | |
Unicode ~> { code => sb.append(code.asInstanceOf[Char]); () } | |
} | |
def Unicode = rule { 'u' ~ capture(4 times HexDigit) ~> (Integer.parseInt(_, 16)) } | |
def Digits = rule { oneOrMore(CharPredicate.Digit) ~ WhiteSpace } | |
def WhiteSpace = rule { zeroOrMore(WhiteSpaceChar) } | |
def Identifier = rule { capture(IdentifierFirstChar ~ zeroOrMore(IdentifierChar)) ~ WhiteSpace } | |
val WhiteSpaceChar = CharPredicate(" \n\r\t\f") | |
val IdentifierFirstChar = CharPredicate.Alpha ++ '_' | |
val IdentifierChar = IdentifierFirstChar ++ CharPredicate.Digit | |
val QuoteBackslash = CharPredicate("\"\\") | |
val QuoteSlashBackSlash = QuoteBackslash ++ "/" | |
} | |
sealed trait AstNode | |
object AstNode { | |
case class And(left: AstNode, right: AstNode) extends AstNode | |
case class Or(left: AstNode, right: AstNode) extends AstNode | |
case class Not(node: AstNode) extends AstNode | |
case class StringLiteral(string: String) extends AstNode | |
case class IntLiteral(num: Int) extends AstNode | |
case class Identifier(name: String) extends AstNode | |
} | |
object Parser extends App { | |
new PredicateParser(Source.fromInputStream(getClass.getResourceAsStream("foo.txt")).mkString) | |
.Predicate.run() match { | |
case Success(node) => println(node) | |
case Failure(e: ParseError) => | |
println(e.formatExpectedAsString) | |
println(e.position) | |
println(e.formatTraces) | |
case Failure(e) => | |
throw e | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment