ruby-changes:34410
From: naruse <ko1@a...>
Date: Sun, 22 Jun 2014 09:22:33 +0900 (JST)
Subject: [ruby-changes:34410] naruse:r46491 (trunk): support RFC3986 [Feature #2542]
naruse 2014-06-22 09:22:19 +0900 (Sun, 22 Jun 2014) New Revision: 46491 http://svn.ruby-lang.org/cgi-bin/viewvc.cgi?view=revision&revision=46491 Log: support RFC3986 [Feature #2542] * lib/uri/common.rb (URI::REGEXP): move to lib/uri/rfc2396_parser.rb. * lib/uri/common.rb (URI::Parser): ditto. * lib/uri/common.rb (URI.split): use RFC3986_Parser. * lib/uri/common.rb (URI.parse): ditto. * lib/uri/common.rb (URI.join): ditto. * lib/uri/common.rb (URI.extract): deprecated. * lib/uri/common.rb (URI.regexp): ditto. * lib/uri/rfc2396_parser.rb: added. * lib/uri/rfc3986_parser.rb: added. Added files: trunk/lib/uri/rfc2396_parser.rb trunk/lib/uri/rfc3986_parser.rb Modified files: trunk/ChangeLog trunk/NEWS trunk/lib/uri/common.rb trunk/test/open-uri/test_open-uri.rb trunk/test/uri/test_generic.rb Index: ChangeLog =================================================================== --- ChangeLog (revision 46490) +++ ChangeLog (revision 46491) @@ -1,3 +1,23 @@ https://github.com/ruby/ruby/blob/trunk/ChangeLog#L1 +Sun Jun 22 09:05:42 2014 NARUSE, Yui <naruse@r...> + + * lib/uri/common.rb (URI::REGEXP): move to lib/uri/rfc2396_parser.rb. + + * lib/uri/common.rb (URI::Parser): ditto. + + * lib/uri/common.rb (URI.split): use RFC3986_Parser. [Feature #2542] + + * lib/uri/common.rb (URI.parse): ditto. + + * lib/uri/common.rb (URI.join): ditto. + + * lib/uri/common.rb (URI.extract): deprecated. + + * lib/uri/common.rb (URI.regexp): ditto. + + * lib/uri/rfc2396_parser.rb: added. + + * lib/uri/rfc3986_parser.rb: added. + Sun Jun 22 09:04:50 2014 NARUSE, Yui <naruse@r...> * lib/uri/mailto.rb (initialize): as previous commit, fix arg_check Index: lib/uri/rfc3986_parser.rb =================================================================== --- lib/uri/rfc3986_parser.rb (revision 0) +++ lib/uri/rfc3986_parser.rb (revision 46491) @@ -0,0 +1,101 @@ https://github.com/ruby/ruby/blob/trunk/lib/uri/rfc3986_parser.rb#L1 +module URI + class RFC3986_Parser # :nodoc: + # URI defined in RFC3986 + # this regexp is modified not to host is not empty string + RFC3986_URI = /\A(?<URI>(?<scheme>[A-Za-z][+\-.0-9A-Za-z]*):(?<hier-part>\/\/(?<authority>(?:(?<userinfo>(?:%\h\h|[!$&-.0-;=A-Z_a-z~])*)@)?(?<host>(?<IP-literal>\[(?:(?<IPv6address>(?:\h{1,4}:){6}(?<ls32>\h{1,4}:\h{1,4}|(?<IPv4address>(?<dec-octet>[1-9]\d|1\d{2}|2[0-4]\d|25[0-5]|\d)\.\g<dec-octet>\.\g<dec-octet>\.\g<dec-octet>))|::(?:\h{1,4}:){5}\g<ls32>|\h{1,4}?::(?:\h{1,4}:){4}\g<ls32>|(?:(?:\h{1,4}:)?\h{1,4})?::(?:\h{1,4}:){3}\g<ls32>|(?:(?:\h{1,4}:){,2}\h{1,4})?::(?:\h{1,4}:){2}\g<ls32>|(?:(?:\h{1,4}:){,3}\h{1,4})?::\h{1,4}:\g<ls32>|(?:(?:\h{1,4}:){,4}\h{1,4})?::\g<ls32>|(?:(?:\h{1,4}:){,5}\h{1,4})?::\h{1,4}|(?:(?:\h{1,4}:){,6}\h{1,4})?::)|(?<IPvFuture>v\h+\.[!$&-.0-;=A-Z_a-z~]+))\])|\g<IPv4address>|(?<reg-name>(?:%\h\h|[!$&-.0-9;=A-Z_a-z~])+))?(?::(?<port>\d*))?)(?<path-abempty>(?:\/(?<segment>(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*))*)|(?<path-absolute>\/(?:(?<segment-nz>(?:%\h\h|[!$&-.0-;=@-Z_a-z~])+)(?:\/\g<segment>)*)?)|(?<path-rootless>\g<segment-nz>(?:\/\g<segment>)*)| (?<path-empty>))(?:\?(?<query>(?:%\h\h|[!$&-.0-;=@-Z_a-z~]|[\/?])*))?(?:\#(?<fragment>(?:%\h\h|[!$&-.0-;=@-Z_a-z~]|[\/?])*))?)\z/ + RFC3986_relative_ref = /\A(?<relative-ref>(?<relative-part>\/\/(?<authority>(?:(?<userinfo>(?:%\h\h|[!$&-.0-;=A-Z_a-z~])*)@)?(?<host>(?<IP-literal>\[(?<IPv6address>(?:\h{1,4}:){6}(?<ls32>\h{1,4}:\h{1,4}|(?<IPv4address>(?<dec-octet>[1-9]\d|1\d{2}|2[0-4]\d|25[0-5]|\d)\.\g<dec-octet>\.\g<dec-octet>\.\g<dec-octet>))|::(?:\h{1,4}:){5}\g<ls32>|\h{1,4}?::(?:\h{1,4}:){4}\g<ls32>|(?:(?:\h{1,4}:){,1}\h{1,4})?::(?:\h{1,4}:){3}\g<ls32>|(?:(?:\h{1,4}:){,2}\h{1,4})?::(?:\h{1,4}:){2}\g<ls32>|(?:(?:\h{1,4}:){,3}\h{1,4})?::\h{1,4}:\g<ls32>|(?:(?:\h{1,4}:){,4}\h{1,4})?::\g<ls32>|(?:(?:\h{1,4}:){,5}\h{1,4})?::\h{1,4}|(?:(?:\h{1,4}:){,6}\h{1,4})?::)|(?<IPvFuture>v\h+\.[!$&-.0-;=A-Z_a-z~]+)\])|\g<IPv4address>|(?<reg-name>(?:%\h\h|[!$&-.0-9;=A-Z_a-z~])+))?(?::(?<port>\d*))?)(?<path-abempty>(?:\/(?<segment>(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*))*)|(?<path-absolute>\/(?:(?<segment-nz>(?:%\h\h|[!$&-.0-;=@-Z_a-z~])+)(?:\/\g<segment>)*)?)|(?<path-noscheme>(?<segment-nz-nc>(?:%\h\h|[!$&-.0-9;=@-Z_a-z~])+) (?:\/\g<segment>)*)|(?<path-empty>(?:%\h\h|[!$&-.0-;=@-Z_a-z~]){0}))(?:\?(?<query>(?:%\h\h|[!$&-.0-;=@-Z_a-z~]|[\/?])*))?(?:\#(?<fragment>(?:%\h\h|[!$&-.0-;=@-Z_a-z~]|[\/?])*))?)\z/ + + def split(uri) #:nodoc: + if m = RFC3986_URI.match(uri) + ary = [] + ary << m["scheme"] + if m["path-rootless"] # opaque + ary << nil # userinfo + ary << nil # host + ary << nil # port + ary << nil # registry + ary << nil # path + ary << m["path-rootless"] + ary[-1] << '?' << m["query"] if m["query"] + ary << nil # query + ary << m["fragment"] + else # normal + ary << m["userinfo"] + ary << m["host"] + ary << m["port"] + ary << nil # registry + ary << (m["path-abempty"] || m["path-absolute"] || m["path-empty"]) + ary << nil # opaque + ary << m["query"] + ary << m["fragment"] + end + elsif m = RFC3986_relative_ref.match(uri) + ary = [nil] + ary << m["userinfo"] + ary << m["host"] + ary << m["port"] + ary << nil # registry + ary << (m["path-abempty"] || m["path-absolute"] || m["path-noscheme"] || m["path-empty"]) + ary << nil # opaque + ary << m["query"] + ary << m["fragment"] + else + raise InvalidURIError, "bad URI(is not URI?): #{uri}" + end + end + + def parse(uri) # :nodoc: + scheme, userinfo, host, port, + registry, path, opaque, query, fragment = self.split(uri) + + if scheme && URI.scheme_list.include?(scheme.upcase) + URI.scheme_list[scheme.upcase].new(scheme, userinfo, host, port, + registry, path, opaque, query, + fragment, self) + else + Generic.new(scheme, userinfo, host, port, + registry, path, opaque, query, + fragment, self) + end + end + + + def join(*uris) # :nodoc: + uris[0] = convert_to_uri(uris[0]) + uris.inject :merge + end + + @@to_s = Kernel.instance_method(:to_s) + def inspect + @@to_s.bind(self).call + end + + def regexp + { + SCHEME: /\A[A-Za-z][A-Za-z0-9+\-.]*\z/, + USERINFO: /\A(?:%\h\h|[!$&-.0-;=A-Z_a-z~])*\z/, + HOST: /\A(?:(?<IP-literal>\[(?:(?<IPv6address>(?:\h{1,4}:){6}(?<ls32>\h{1,4}:\h{1,4}|(?<IPv4address>(?<dec-octet>[1-9]\d|1\d{2}|2[0-4]\d|25[0-5]|\d)\.\g<dec-octet>\.\g<dec-octet>\.\g<dec-octet>))|::(?:\h{1,4}:){5}\g<ls32>|\h{,4}::(?:\h{1,4}:){4}\g<ls32>|(?:(?:\h{1,4}:)?\h{1,4})?::(?:\h{1,4}:){3}\g<ls32>|(?:(?:\h{1,4}:){,2}\h{1,4})?::(?:\h{1,4}:){2}\g<ls32>|(?:(?:\h{1,4}:){,3}\h{1,4})?::\h{1,4}:\g<ls32>|(?:(?:\h{1,4}:){,4}\h{1,4})?::\g<ls32>|(?:(?:\h{1,4}:){,5}\h{1,4})?::\h{1,4}|(?:(?:\h{1,4}:){,6}\h{1,4})?::)|(?<IPvFuture>v\h+\.[!$&-.0-;=A-Z_a-z~]+))\])|\g<IPv4address>|(?<reg-name>(?:%\h\h|[!$&-.0-9;=A-Z_a-z~])*))\z/, + ABS_PATH: /\A\/(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*(?:\/(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*)*\z/, + REL_PATH: /\A(?:%\h\h|[!$&-.0-;=@-Z_a-z~])+(?:\/(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*)*\z/, + QUERY: /\A(?:%\h\h|[!$&-.0-;=@-Z_a-z~]|[\/?])*\z/, + FRAGMENT: /\A(?:%\h\h|[!$&-.0-;=@-Z_a-z~]|[\/?])*\z/, + OPAQUE: nil, + PORT: nil, + } + end + + private + + def convert_to_uri(uri) + if uri.is_a?(URI::Generic) + uri + elsif uri = String.try_convert(uri) + parse(uri) + else + raise ArgumentError, + "bad argument (expected URI object or URI string)" + end + end + + end # class Parser +end # module URI Index: lib/uri/common.rb =================================================================== --- lib/uri/common.rb (revision 46490) +++ lib/uri/common.rb (revision 46491) @@ -9,537 +9,13 @@ https://github.com/ruby/ruby/blob/trunk/lib/uri/common.rb#L9 # See URI for general documentation # -module URI - # - # Includes URI::REGEXP::PATTERN - # - module REGEXP - # - # Patterns used to parse URI's - # - module PATTERN - # :stopdoc: - - # RFC 2396 (URI Generic Syntax) - # RFC 2732 (IPv6 Literal Addresses in URL's) - # RFC 2373 (IPv6 Addressing Architecture) - - # alpha = lowalpha | upalpha - ALPHA = "a-zA-Z" - # alphanum = alpha | digit - ALNUM = "#{ALPHA}\\d" - - # hex = digit | "A" | "B" | "C" | "D" | "E" | "F" | - # "a" | "b" | "c" | "d" | "e" | "f" - HEX = "a-fA-F\\d" - # escaped = "%" hex hex - ESCAPED = "%[#{HEX}]{2}" - # mark = "-" | "_" | "." | "!" | "~" | "*" | "'" | - # "(" | ")" - # unreserved = alphanum | mark - UNRESERVED = "\\-_.!~*'()#{ALNUM}" - # reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" | - # "$" | "," - # reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" | - # "$" | "," | "[" | "]" (RFC 2732) - RESERVED = ";/?:@&=+$,\\[\\]" - - # domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum - DOMLABEL = "(?:[#{ALNUM}](?:[-#{ALNUM}]*[#{ALNUM}])?)" - # toplabel = alpha | alpha *( alphanum | "-" ) alphanum - TOPLABEL = "(?:[#{ALPHA}](?:[-#{ALNUM}]*[#{ALNUM}])?)" - # hostname = *( domainlabel "." ) toplabel [ "." ] - HOSTNAME = "(?:#{DOMLABEL}\\.)*#{TOPLABEL}\\.?" - - # :startdoc: - end # PATTERN - - # :startdoc: - end # REGEXP - - # class that Parses String's into URI's - # - # It contains a Hash set of patterns and Regexp's that match and validate. - # - class Parser - include REGEXP - - # - # == Synopsis - # - # URI::Parser.new([opts]) - # - # == Args - # - # The constructor accepts a hash as options for parser. - # Keys of options are pattern names of URI components - # and values of options are pattern strings. - # The constructor generates set of regexps for parsing URIs. - # - # You can use the following keys: - # - # * :ESCAPED (URI::PATTERN::ESCAPED in default) - # * :UNRESERVED (URI::PATTERN::UNRESERVED in default) - # * :DOMLABEL (URI::PATTERN::DOMLABEL in default) - # * :TOPLABEL (URI::PATTERN::TOPLABEL in default) - # * :HOSTNAME (URI::PATTERN::HOSTNAME in default) - # - # == Examples - # - # p = URI::Parser.new(:ESCAPED => "(?:%[a-fA-F0-9]{2}|%u[a-fA-F0-9]{4})") - # u = p.parse("http://example.jp/%uABCD") #=> #<URI::HTTP:0xb78cf4f8 URL:http://example.jp/%uABCD> - # URI.parse(u.to_s) #=> raises URI::InvalidURIError - # - # s = "http://example.com/ABCD" - # u1 = p.parse(s) #=> #<URI::HTTP:0xb78c3220 URL:http://example.com/ABCD> - # u2 = URI.parse(s) #=> #<URI::HTTP:0xb78b6d54 URL:http://example.com/ABCD> - # u1 == u2 #=> true - # u1.eql?(u2) #=> false - # - def initialize(opts = {}) - @pattern = initialize_pattern(opts) - @pattern.each_value {|v| v.freeze} - @pattern.freeze - - @regexp = initialize_regexp(@pattern) - @regexp.each_value {|v| v.freeze} - @regexp.freeze - end - - # The Hash of patterns. - # - # see also URI::Parser.initialize_pattern - attr_reader :pattern - - # The Hash of Regexp - # - # see also URI::Parser.initialize_regexp - attr_reader :regexp - - # Returns a split URI against regexp[:ABS_URI] - def split(uri) - case uri - when '' - # null uri - - when @regexp[:ABS_URI] - scheme, opaque, userinfo, host, port, - registry, path, query, fragment = $~[1..-1] - - # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ] - - # absoluteURI = scheme ":" ( hier_part | opaque_part ) - # hier_part = ( net_path | abs_path ) [ "?" query ] - # opaque_part = uric_no_slash *uric - - # abs_path = "/" path_segments - # net_path = "//" authority [ abs_path ] - - # authority = server | reg_name - # server = [ [ userinfo "@" ] hostport ] - - if !scheme - raise InvalidURIError, - "bad URI(absolute but no scheme): #{uri}" - end - if !opaque && (!path && (!host && !registry)) - raise InvalidURIError, - "bad URI(absolute but no path): #{uri}" - end - - when @regexp[:REL_URI] - scheme = nil - opaque = nil - - userinfo, host, port, registry, - rel_segment, abs_path, query, fragment = $~[1..-1] - if rel_segment && abs_path - path = rel_segment + abs_path - elsif rel_segment - path = rel_segment - elsif abs_path - path = abs_path - end - - # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ] - - # relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ] - - # net_path = "//" authority [ abs_path ] - # abs_path = "/" path_segments - # rel_path = rel_segment [ abs_path ] - - # authority = server | reg_name - # server = [ [ userinfo "@" ] hostport ] - - else - raise InvalidURIError, "bad URI(is not URI?): #{uri}" - end +require "uri/rfc2396_parser" +require "uri/rfc3986_parser" - path = '' if !path && !opaque # (see RFC2396 Section 5.2) - ret = [ - scheme, - userinfo, host, port, # X - registry, # X - path, # Y - opaque, # Y - query, - fragment - ] - return ret - end - - # - # == Args - # - # +uri+:: - # String - # - # == Description - # - # parses +uri+ and constructs either matching URI scheme object - # (FTP, HTTP, HTTPS, LDAP, LDAPS, or MailTo) or URI::Generic - # - # == Usage - # - # p = URI::Parser.new - # p.parse("ldap://ldap.example.com/dc=example?user=john") - # #=> #<URI::LDAP:0x00000000b9e7e8 URL:ldap://ldap.example.com/dc=example?user=john> - # - def parse(uri) - scheme, userinfo, host, port, - registry, path, opaque, query, fragment = self.split(uri) - - if scheme && URI.scheme_list.include?(scheme.upcase) - URI.scheme_list[scheme.upcase].new(scheme, userinfo, host, port, - registry, path, opaque, query, - fragment, self) - else - Generic.new(scheme, userinfo, host, port, - registry, path, opaque, query, - fragment, self) - end - end - - - # - # == Args - # - # +uris+:: - # an Array of Strings - # - # == Description - # - # Attempts to parse and merge a set of URIs - # - def join(*uris) - uris[0] = convert_to_uri(uris[0]) - uris.inject :merge - end - - # - # :call-seq: - # extract( str ) - # extract( str, schemes ) - # extract( str, schemes ) {|item| block } - # - # == Args - # - # +str+:: - # String to search - # +schemes+:: - # Patterns to apply to +str+ - # - # == Description - # - # Attempts to parse and merge a set of URIs - # If no +block+ given , then returns the result, - # else it calls +block+ for each element in result. - # - # see also URI::Parser.make_regexp - # - def extract(str, schemes = nil) - if block_given? - str.scan(make_regexp(schemes)) { yield $& } - nil - else - result = [] - str.scan(make_regexp(schemes)) { result.push $& } - result - end - end - - # returns Regexp that is default self.regexp[:ABS_URI_REF], - # unless +schemes+ is provided. Then it is a Regexp.union with self.pattern[:X_ABS_URI] - def make_regexp(schemes = nil) - unless schemes - @regexp[:ABS_URI_REF] - else - /(?=#{Regexp.union(*schemes)}:)#{@pattern[:X_ABS_URI]}/x - end - end - - # - # :call-seq: - # escape( str ) - # escape( str, unsafe ) - # - # == Args - # - # +str+:: - # String to make safe - # +unsafe+:: - # Regexp to apply. Defaults to self.regexp[:UNSAFE] - # - # == Description - # - # constructs a safe String from +str+, removing unsafe characters, - # replacing them with codes. - # - def escape(str, unsafe = @regexp[:UNSAFE]) - unless unsafe.kind_of?(Regexp) - # perhaps unsafe is String object - unsafe = Regexp.new("[#{Regexp.quote(unsafe)}]", false) - end - str.gsub(unsafe) do - us = $& - tmp = '' - us.each_byte do |uc| - tmp << sprintf('%%%02X', uc) - end - tmp - end.force_encoding(Encoding::US_ASCII) - end - - # - # :call-seq: - # unescape( str ) - # unescape( str, unsafe ) - # - # == Args - # - # +str+:: - # String to remove escapes from - # +unsafe+:: - # Regexp to apply. Defaults to self.regexp[:ESCAPED] - # - # == Description - # - # Removes escapes from +str+ - # - def unescape(str, escaped = @regexp[:ESCAPED]) - str.gsub(escaped) { [$&[1, 2].hex].pack('C') }.force_encoding(str.encoding) - end - - @@to_s = Kernel.instance_method(:to_s) - def inspect - @@to_s.bind(self).call - end - - private - - # Constructs the default Hash of patterns - def initialize_pattern(opts = {}) - ret = {} - ret[:ESCAPED] = escaped = (opts.delete(:ESCAPED) || PATTERN::ESCAPED) - ret[:UNRESERVED] = unreserved = opts.delete(:UNRESERVED) || PATTERN::UNRESERVED - ret[:RESERVED] = reserved = opts.delete(:RESERVED) || PATTERN::RESERVED - ret[:DOMLABEL] = opts.delete(:DOMLABEL) || PATTERN::DOMLABEL - ret[:TOPLABEL] = opts.delete(:TOPLABEL) || PATTERN::TOPLABEL - ret[:HOSTNAME] = hostname = opts.delete(:HOSTNAME) - - # RFC 2396 (URI Generic Syntax) - # RFC 2732 (IPv6 Literal Addresses in URL's) - # RFC 2373 (IPv6 Addressing Architecture) - - # uric = reserved | unreserved | escaped - ret[:URIC] = uric = "(?:[#{unreserved}#{reserved}]|#{escaped})" - # uric_no_slash = unreserved | escaped | ";" | "?" | ":" | "@" | - # "&" | "=" | "+" | "$" | "," - ret[:URIC_NO_SLASH] = uric_no_slash = "(?:[#{unreserved};?:@&=+$,]|#{escaped})" - # query = *uric - ret[:QUERY] = query = "#{uric}*" - # fragment = *uric - ret[:FRAGMENT] = fragment = "#{uric}*" - - # hostname = *( domainlabel "." ) toplabel [ "." ] - # reg-name = *( unreserved / pct-encoded / sub-delims ) # RFC3986 - unless hostname - ret[:HOSTNAME] = hostname = "(?:[a-zA-Z0-9\\-.]|%\\h\\h)+" - end - - # RFC 2373, APPENDIX B: - # IPv6address = hexpart [ ":" IPv4address ] - # IPv4address = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT - # hexpart = hexseq | hexseq "::" [ hexseq ] | "::" [ hexseq ] - # hexseq = hex4 *( ":" hex4) - # hex4 = 1*4HEXDIG - # - # XXX: This definition has a flaw. "::" + IPv4address must be - # allowed too. Here is a replacement. - # - # IPv4address = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT - ret[:IPV4ADDR] = ipv4addr = "\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}" - # hex4 = 1*4HEXDIG - hex4 = "[#{PATTERN::HEX}]{1,4}" - # lastpart = hex4 | IPv4address - lastpart = "(?:#{hex4}|#{ipv4addr})" - # hexseq1 = *( hex4 ":" ) hex4 - hexseq1 = "(?:#{hex4}:)*#{hex4}" - # hexseq2 = *( hex4 ":" ) lastpart - hexseq2 = "(?:#{hex4}:)*#{lastpart}" - # IPv6address = hexseq2 | [ hexseq1 ] "::" [ hexseq2 ] - ret[:IPV6ADDR] = ipv6addr = "(?:#{hexseq2}|(?:#{hexseq1})?::(?:#{hexseq2})?)" - - # IPv6prefix = ( hexseq1 | [ hexseq1 ] "::" [ hexseq1 ] ) "/" 1*2DIGIT - # unused - - # ipv6reference = "[" IPv6address "]" (RFC 2732) - ret[:IPV6REF] = ipv6ref = "\\[#{ipv6addr}\\]" - - # host = hostname | IPv4address - # host = hostname | IPv4address | IPv6reference (RFC 2732) - ret[:HOST] = host = "(?:#{hostname}|#{ipv4addr}|#{ipv6ref})" - # port = *digit - port = '\d*' - # hostport = host [ ":" port ] - ret[:HOSTPORT] = hostport = "#{host}(?::#{port})?" - - # userinfo = *( unreserved | escaped | - # (... truncated) -- ML: ruby-changes@q... Info: http://www.atdot.net/~ko1/quickml/