email_pattern.rb

# encoding: utf-8
# #
# # RFC822 Email Address Regex
# # --------------------------
# #
# # Originally written by Cal Henderson
# # c.f. http://iamcal.com/publish/articles/php/parsing_email/
# #
# # Translated to Ruby by Tim Fletcher, with changes suggested by Dan Kubb.
# #
# # Licensed under a Creative Commons Attribution-ShareAlike 2.5 License
# # http://creativecommons.org/licenses/by-sa/2.5/
# #
# module RFC822
#   EmailAddress = begin
#     qtext = '[^\\x0d\\x22\\x5c\\x80-\\xff]'
#     dtext = '[^\\x0d\\x5b-\\x5d\\x80-\\xff]'
#     atom = '[^\\x00-\\x20\\x22\\x28\\x29\\x2c\\x2e\\x3a-' +
#       '\\x3c\\x3e\\x40\\x5b-\\x5d\\x7f-\\xff]+'
#     quoted_pair = '\\x5c[\\x00-\\x7f]'
#     domain_literal = "\\x5b(?:#{dtext}|#{quoted_pair})*\\x5d"
#     quoted_string = "\\x22(?:#{qtext}|#{quoted_pair})*\\x22"
#     domain_ref = atom
#     sub_domain = "(?:#{domain_ref}|#{domain_literal})"
#     word = "(?:#{atom}|#{quoted_string})"
#     domain = "#{sub_domain}(?:\\x2e#{sub_domain})*"
#     local_part = "#{word}(?:\\x2e#{word})*"
#     addr_spec = "#{local_part}\\x40#{domain}"
#     pattern = /\A#{addr_spec}\z/
#   end
# end

# coding:utf-8
module RFC822
  class Email

    def self.compile(string)
      Regexp.new string, nil, 'n'
    end

    # Patterns
    QTEXT     = compile "[^\\x0d\\x22\\x5c\\x80-\\xff]"
    DTEXT     = compile "[^\\x0d\\x5b-\\x5d\\x80-\\xff]"

    ATOM_CORE = compile "[^\\x00-\\x20\\x22\\x28\\x29\\x2c\\x2e\\x3a-\\x3c\\x3e\\x40\\x5b-\\x5d\\x7f-\\xff]+"
    ATOM_EDGE = compile "[^\\x00-\\x20\\x22\\x28\\x29\\x2c-\\x2e\\x3a-\\x3c\\x3e\\x40\\x5b-\\x5d\\x7f-\\xff]"
    ATOM      = compile "(?:#{ATOM_EDGE}{1,2}|#{ATOM_EDGE}#{ATOM_CORE}#{ATOM_EDGE})"

    QPAIR     = compile "\\x5c[\\x00-\\x7f]"
    QSTRING   = compile "\\x22(?:#{QTEXT}|#{QPAIR})*\\x22"

    WORD      = compile "(?:#{ATOM}|#{QSTRING})"

    DOMAIN_PT = compile "(?:[a-zA-Z0-9][\-a-zA-Z0-9]*[a-zA-Z0-9]|[a-zA-Z0-9]+)"

    DOMAIN    = compile "#{DOMAIN_PT}(?:\\x2e#{DOMAIN_PT})*"
    LOCAL_PT  = compile "#{WORD}(?:\\x2e#{WORD})*"
    ADDRESS   = compile "#{LOCAL_PT}\\x40#{DOMAIN}"

    REGEXP = /\A#{ ADDRESS }\z/
  end
end