Last active
August 30, 2016 15:39
-
-
Save nartamonov/9a3cd8715ece6904f7625c4ec4402fe3 to your computer and use it in GitHub Desktop.
Пример парсера URL на parboiled2 (из доклада "No more regular expressions", см. https://skillsmatter.com/skillscasts/5847-no-more-regular-expressions)
This file contains 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 org.parboiled2._ | |
import org.parboiled2.CharPredicate._ | |
class URLParser(val input: ParserInput) extends Parser { | |
def URL = rule { URLPattern ~> UrlParts } | |
def URLPattern = rule { Scheme ~ "://" ~ Host ~ Port ~ Path ~ QueryParams } | |
def QueryParams = rule { '?' ~ oneOrMore(QPPair).separatedBy('&') ~> (kvs => Map(kvs: _*)) } | |
def QPPair = rule { capture(oneOrMore(Alpha)) ~ '=' ~ capture(oneOrMore(Alpha)) ~> ((k: String, v: String) => (k, v)) } | |
def Path = rule { '/' ~ capture(oneOrMore(oneOrMore(Alpha)).separatedBy('/')) } | |
def Port = rule { optional(':' ~ capture(oneOrMore(Digit)) ~> (_.toInt)) } | |
def Host = rule { capture(oneOrMore(Alpha ++ ".-_")) } | |
def Scheme = rule { capture(oneOrMore(Alpha)) } | |
} | |
case class UrlParts(scheme: String, host: String, port: Option[Int], path: String, queryParams: Map[String,String]) | |
// For test: | |
// new URLParser("https://url.spec.whatwg.org:80/foo?foo=bar").URL.run() --> scala.util.Try[UrlParts] = Success(UrlParts(https,url.spec.whatwg.org,Some(80),foo,Map(foo -> bar))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment