Http URL regex based on RFC 1738

httpurl.coffee

class HttpUrl

  ALPHA = "[a-zA-Z]"
  DIGIT = "[0-9]"
  DIGITS = "#{DIGIT}+"
  SAFE = "[-$_.+]"
  EXTRA = "[!*'(),]"

  ALPHADIGIT = "[a-zA-Z0-9]"
  TOPLABEL = "#{ALPHA}(#{ALPHADIGIT}|-)*#{ALPHADIGIT}|#{ALPHA}"
  DOMAINLABEL = "#{ALPHADIGIT}(#{ALPHADIGIT}|-)*#{ALPHADIGIT}|#{ALPHADIGIT}"
  HOSTNAME = "((#{DOMAINLABEL})\\.)*#{TOPLABEL}"
  HOSTNUMBER = "#{DIGITS}\\.#{DIGITS}\\.#{DIGITS}\\.#{DIGITS}"
  HOST = "#{HOSTNAME}|#{HOSTNUMBER}"
  HOSTPORT = "(#{HOST})(:#{DIGITS})?"

  HEX = "#{DIGIT}|A-F|a-f"
  ESCAPE = "%#{HEX}#{HEX}"
  UNRESERVED = "#{ALPHA}|#{DIGIT}|#{SAFE}|#{EXTRA}"
  UCHAR = "#{UNRESERVED}|#{ESCAPE}"

  HSEGMENT = "(#{UCHAR}|;|\\?|&|=)*"
  SEARCH = "(#{UCHAR}|;|\\?|&|=)*"

  HPATH = "#{HSEGMENT}(\/#{HSEGMENT})*"
  HTTPURL = "(http[s]?:\/\/#{HOSTPORT}(\/#{HPATH}(\\?#{SEARCH})?)?)"

  @buildRegExp: ->
    new RegExp(HTTPURL, "g")