diff options
Diffstat (limited to 'lib/uri')
-rw-r--r-- | lib/uri/common.rb | 416 | ||||
-rw-r--r-- | lib/uri/file.rb | 6 | ||||
-rw-r--r-- | lib/uri/ftp.rb | 2 | ||||
-rw-r--r-- | lib/uri/generic.rb | 33 | ||||
-rw-r--r-- | lib/uri/http.rb | 39 | ||||
-rw-r--r-- | lib/uri/mailto.rb | 2 | ||||
-rw-r--r-- | lib/uri/rfc2396_parser.rb | 4 | ||||
-rw-r--r-- | lib/uri/rfc3986_parser.rb | 129 | ||||
-rw-r--r-- | lib/uri/uri.gemspec | 18 | ||||
-rw-r--r-- | lib/uri/version.rb | 2 |
10 files changed, 461 insertions, 190 deletions
diff --git a/lib/uri/common.rb b/lib/uri/common.rb index 26b179add2..dce09fbc1e 100644 --- a/lib/uri/common.rb +++ b/lib/uri/common.rb @@ -13,6 +13,8 @@ require_relative "rfc2396_parser" require_relative "rfc3986_parser" module URI + include RFC2396_REGEXP + REGEXP = RFC2396_REGEXP Parser = RFC2396_Parser RFC3986_PARSER = RFC3986_Parser.new @@ -62,17 +64,36 @@ module URI module_function :make_components_hash end - include REGEXP - module Schemes end private_constant :Schemes + # Registers the given +klass+ as the class to be instantiated + # when parsing a \URI with the given +scheme+: + # + # URI.register_scheme('MS_SEARCH', URI::Generic) # => URI::Generic + # URI.scheme_list['MS_SEARCH'] # => URI::Generic + # + # Note that after calling String#upcase on +scheme+, it must be a valid + # constant name. def self.register_scheme(scheme, klass) - Schemes.const_set(scheme, klass) + Schemes.const_set(scheme.to_s.upcase, klass) end - # Returns a Hash of the defined schemes. + # Returns a hash of the defined schemes: + # + # URI.scheme_list + # # => + # {"MAILTO"=>URI::MailTo, + # "LDAPS"=>URI::LDAPS, + # "WS"=>URI::WS, + # "HTTP"=>URI::HTTP, + # "HTTPS"=>URI::HTTPS, + # "LDAP"=>URI::LDAP, + # "FILE"=>URI::File, + # "FTP"=>URI::FTP} + # + # Related: URI.register_scheme. def self.scheme_list Schemes.constants.map { |name| [name.to_s.upcase, Schemes.const_get(name)] @@ -83,9 +104,21 @@ module URI private_constant :INITIAL_SCHEMES Ractor.make_shareable(INITIAL_SCHEMES) if defined?(Ractor) + # Returns a new object constructed from the given +scheme+, +arguments+, + # and +default+: + # + # - The new object is an instance of <tt>URI.scheme_list[scheme.upcase]</tt>. + # - The object is initialized by calling the class initializer + # using +scheme+ and +arguments+. + # See URI::Generic.new. + # + # Examples: # - # Construct a URI instance, using the scheme to detect the appropriate class - # from +URI.scheme_list+. + # values = ['john.doe', 'www.example.com', '123', nil, '/forum/questions/', nil, 'tag=networking&order=newest', 'top'] + # URI.for('https', *values) + # # => #<URI::HTTPS https://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top> + # URI.for('foo', *values, default: URI::HTTP) + # # => #<URI::HTTP foo://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top> # def self.for(scheme, *arguments, default: Generic) const_name = scheme.to_s.upcase @@ -116,95 +149,49 @@ module URI # class BadURIError < Error; end - # - # == Synopsis - # - # URI::split(uri) - # - # == Args - # - # +uri+:: - # String with URI. - # - # == Description - # - # Splits the string on following parts and returns array with result: - # - # * Scheme - # * Userinfo - # * Host - # * Port - # * Registry - # * Path - # * Opaque - # * Query - # * Fragment - # - # == Usage - # - # require 'uri' - # - # URI.split("http://www.ruby-lang.org/") - # # => ["http", nil, "www.ruby-lang.org", nil, nil, "/", nil, nil, nil] + # Returns a 9-element array representing the parts of the \URI + # formed from the string +uri+; + # each array element is a string or +nil+: + # + # names = %w[scheme userinfo host port registry path opaque query fragment] + # values = URI.split('https://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top') + # names.zip(values) + # # => + # [["scheme", "https"], + # ["userinfo", "john.doe"], + # ["host", "www.example.com"], + # ["port", "123"], + # ["registry", nil], + # ["path", "/forum/questions/"], + # ["opaque", nil], + # ["query", "tag=networking&order=newest"], + # ["fragment", "top"]] # def self.split(uri) RFC3986_PARSER.split(uri) end + # Returns a new \URI object constructed from the given string +uri+: # - # == Synopsis - # - # URI::parse(uri_str) - # - # == Args - # - # +uri_str+:: - # String with URI. - # - # == Description - # - # Creates one of the URI's subclasses instance from the string. - # - # == Raises - # - # URI::InvalidURIError:: - # Raised if URI given is not a correct one. - # - # == Usage - # - # require 'uri' + # URI.parse('https://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top') + # # => #<URI::HTTPS https://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top> + # URI.parse('http://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top') + # # => #<URI::HTTP http://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top> # - # uri = URI.parse("http://www.ruby-lang.org/") - # # => #<URI::HTTP http://www.ruby-lang.org/> - # uri.scheme - # # => "http" - # uri.host - # # => "www.ruby-lang.org" - # - # It's recommended to first ::escape the provided +uri_str+ if there are any - # invalid URI characters. + # It's recommended to first ::escape string +uri+ + # if it may contain invalid URI characters. # def self.parse(uri) RFC3986_PARSER.parse(uri) end + # Merges the given URI strings +str+ + # per {RFC 2396}[https://www.rfc-editor.org/rfc/rfc2396.html]. # - # == Synopsis - # - # URI::join(str[, str, ...]) + # Each string in +str+ is converted to an + # {RFC3986 URI}[https://www.rfc-editor.org/rfc/rfc3986.html] before being merged. # - # == Args - # - # +str+:: - # String(s) to work with, will be converted to RFC3986 URIs before merging. - # - # == Description - # - # Joins URIs. - # - # == Usage - # - # require 'uri' + # Examples: # # URI.join("http://example.com/","main.rbx") # # => #<URI::HTTP http://example.com/main.rbx> @@ -249,7 +236,7 @@ module URI # URI.extract("text here http://foo.example.org/bla and here mailto:test@example.com and here also.") # # => ["http://foo.example.com/bla", "mailto:test@example.com"] # - def self.extract(str, schemes = nil, &block) + def self.extract(str, schemes = nil, &block) # :nodoc: warn "URI.extract is obsolete", uplevel: 1 if $VERBOSE DEFAULT_PARSER.extract(str, schemes, &block) end @@ -286,7 +273,7 @@ module URI # p $& # end # - def self.regexp(schemes = nil) + def self.regexp(schemes = nil)# :nodoc: warn "URI.regexp is obsolete", uplevel: 1 if $VERBOSE DEFAULT_PARSER.make_regexp(schemes) end @@ -295,6 +282,7 @@ module URI 256.times do |i| TBLENCWWWCOMP_[-i.chr] = -('%%%02X' % i) end + TBLENCURICOMP_ = TBLENCWWWCOMP_.dup.freeze TBLENCWWWCOMP_[' '] = '+' TBLENCWWWCOMP_.freeze TBLDECWWWCOMP_ = {} # :nodoc: @@ -308,18 +296,91 @@ module URI TBLDECWWWCOMP_['+'] = ' ' TBLDECWWWCOMP_.freeze - # Encodes given +str+ to URL-encoded form data. + # Returns a URL-encoded string derived from the given string +str+. + # + # The returned string: + # + # - Preserves: + # + # - Characters <tt>'*'</tt>, <tt>'.'</tt>, <tt>'-'</tt>, and <tt>'_'</tt>. + # - Character in ranges <tt>'a'..'z'</tt>, <tt>'A'..'Z'</tt>, + # and <tt>'0'..'9'</tt>. + # + # Example: + # + # URI.encode_www_form_component('*.-_azAZ09') + # # => "*.-_azAZ09" + # + # - Converts: + # + # - Character <tt>' '</tt> to character <tt>'+'</tt>. + # - Any other character to "percent notation"; + # the percent notation for character <i>c</i> is <tt>'%%%X' % c.ord</tt>. + # + # Example: # - # This method doesn't convert *, -, ., 0-9, A-Z, _, a-z, but does convert SP - # (ASCII space) to + and converts others to %XX. + # URI.encode_www_form_component('Here are some punctuation characters: ,;?:') + # # => "Here+are+some+punctuation+characters%3A+%2C%3B%3F%3A" # - # If +enc+ is given, convert +str+ to the encoding before percent encoding. + # Encoding: # - # This is an implementation of - # https://www.w3.org/TR/2013/CR-html5-20130806/forms.html#url-encoded-form-data. + # - If +str+ has encoding Encoding::ASCII_8BIT, argument +enc+ is ignored. + # - Otherwise +str+ is converted first to Encoding::UTF_8 + # (with suitable character replacements), + # and then to encoding +enc+. # - # See URI.decode_www_form_component, URI.encode_www_form. + # In either case, the returned string has forced encoding Encoding::US_ASCII. + # + # Related: URI.encode_uri_component (encodes <tt>' '</tt> as <tt>'%20'</tt>). def self.encode_www_form_component(str, enc=nil) + _encode_uri_component(/[^*\-.0-9A-Z_a-z]/, TBLENCWWWCOMP_, str, enc) + end + + # Returns a string decoded from the given \URL-encoded string +str+. + # + # The given string is first encoded as Encoding::ASCII-8BIT (using String#b), + # then decoded (as below), and finally force-encoded to the given encoding +enc+. + # + # The returned string: + # + # - Preserves: + # + # - Characters <tt>'*'</tt>, <tt>'.'</tt>, <tt>'-'</tt>, and <tt>'_'</tt>. + # - Character in ranges <tt>'a'..'z'</tt>, <tt>'A'..'Z'</tt>, + # and <tt>'0'..'9'</tt>. + # + # Example: + # + # URI.decode_www_form_component('*.-_azAZ09') + # # => "*.-_azAZ09" + # + # - Converts: + # + # - Character <tt>'+'</tt> to character <tt>' '</tt>. + # - Each "percent notation" to an ASCII character. + # + # Example: + # + # URI.decode_www_form_component('Here+are+some+punctuation+characters%3A+%2C%3B%3F%3A') + # # => "Here are some punctuation characters: ,;?:" + # + # Related: URI.decode_uri_component (preserves <tt>'+'</tt>). + def self.decode_www_form_component(str, enc=Encoding::UTF_8) + _decode_uri_component(/\+|%\h\h/, str, enc) + end + + # Like URI.encode_www_form_component, except that <tt>' '</tt> (space) + # is encoded as <tt>'%20'</tt> (instead of <tt>'+'</tt>). + def self.encode_uri_component(str, enc=nil) + _encode_uri_component(/[^*\-.0-9A-Z_a-z]/, TBLENCURICOMP_, str, enc) + end + + # Like URI.decode_www_form_component, except that <tt>'+'</tt> is preserved. + def self.decode_uri_component(str, enc=Encoding::UTF_8) + _decode_uri_component(/%\h\h/, str, enc) + end + + def self._encode_uri_component(regexp, table, str, enc) str = str.to_s.dup if str.encoding != Encoding::ASCII_8BIT if enc && enc != Encoding::ASCII_8BIT @@ -328,47 +389,115 @@ module URI end str.force_encoding(Encoding::ASCII_8BIT) end - str.gsub!(/[^*\-.0-9A-Z_a-z]/, TBLENCWWWCOMP_) + str.gsub!(regexp, table) str.force_encoding(Encoding::US_ASCII) end + private_class_method :_encode_uri_component - # Decodes given +str+ of URL-encoded form data. - # - # This decodes + to SP. - # - # See URI.encode_www_form_component, URI.decode_www_form. - def self.decode_www_form_component(str, enc=Encoding::UTF_8) + def self._decode_uri_component(regexp, str, enc) raise ArgumentError, "invalid %-encoding (#{str})" if /%(?!\h\h)/.match?(str) - str.b.gsub(/\+|%\h\h/, TBLDECWWWCOMP_).force_encoding(enc) + str.b.gsub(regexp, TBLDECWWWCOMP_).force_encoding(enc) end + private_class_method :_decode_uri_component - # Generates URL-encoded form data from given +enum+. + # Returns a URL-encoded string derived from the given + # {Enumerable}[rdoc-ref:Enumerable@Enumerable+in+Ruby+Classes] + # +enum+. + # + # The result is suitable for use as form data + # for an \HTTP request whose <tt>Content-Type</tt> is + # <tt>'application/x-www-form-urlencoded'</tt>. + # + # The returned string consists of the elements of +enum+, + # each converted to one or more URL-encoded strings, + # and all joined with character <tt>'&'</tt>. + # + # Simple examples: + # + # URI.encode_www_form([['foo', 0], ['bar', 1], ['baz', 2]]) + # # => "foo=0&bar=1&baz=2" + # URI.encode_www_form({foo: 0, bar: 1, baz: 2}) + # # => "foo=0&bar=1&baz=2" + # + # The returned string is formed using method URI.encode_www_form_component, + # which converts certain characters: # - # This generates application/x-www-form-urlencoded data defined in HTML5 - # from given an Enumerable object. + # URI.encode_www_form('f#o': '/', 'b-r': '$', 'b z': '@') + # # => "f%23o=%2F&b-r=%24&b+z=%40" # - # This internally uses URI.encode_www_form_component(str). + # When +enum+ is Array-like, each element +ele+ is converted to a field: # - # This method doesn't convert the encoding of given items, so convert them - # before calling this method if you want to send data as other than original - # encoding or mixed encoding data. (Strings which are encoded in an HTML5 - # ASCII incompatible encoding are converted to UTF-8.) + # - If +ele+ is an array of two or more elements, + # the field is formed from its first two elements + # (and any additional elements are ignored): # - # This method doesn't handle files. When you send a file, use - # multipart/form-data. + # name = URI.encode_www_form_component(ele[0], enc) + # value = URI.encode_www_form_component(ele[1], enc) + # "#{name}=#{value}" # - # This refers https://url.spec.whatwg.org/#concept-urlencoded-serializer + # Examples: # - # URI.encode_www_form([["q", "ruby"], ["lang", "en"]]) - # #=> "q=ruby&lang=en" - # URI.encode_www_form("q" => "ruby", "lang" => "en") - # #=> "q=ruby&lang=en" - # URI.encode_www_form("q" => ["ruby", "perl"], "lang" => "en") - # #=> "q=ruby&q=perl&lang=en" - # URI.encode_www_form([["q", "ruby"], ["q", "perl"], ["lang", "en"]]) - # #=> "q=ruby&q=perl&lang=en" + # URI.encode_www_form([%w[foo bar], %w[baz bat bah]]) + # # => "foo=bar&baz=bat" + # URI.encode_www_form([['foo', 0], ['bar', :baz, 'bat']]) + # # => "foo=0&bar=baz" + # + # - If +ele+ is an array of one element, + # the field is formed from <tt>ele[0]</tt>: + # + # URI.encode_www_form_component(ele[0]) + # + # Example: + # + # URI.encode_www_form([['foo'], [:bar], [0]]) + # # => "foo&bar&0" + # + # - Otherwise the field is formed from +ele+: + # + # URI.encode_www_form_component(ele) + # + # Example: + # + # URI.encode_www_form(['foo', :bar, 0]) + # # => "foo&bar&0" + # + # The elements of an Array-like +enum+ may be mixture: + # + # URI.encode_www_form([['foo', 0], ['bar', 1, 2], ['baz'], :bat]) + # # => "foo=0&bar=1&baz&bat" + # + # When +enum+ is Hash-like, + # each +key+/+value+ pair is converted to one or more fields: + # + # - If +value+ is + # {Array-convertible}[rdoc-ref:implicit_conversion.rdoc@Array-Convertible+Objects], + # each element +ele+ in +value+ is paired with +key+ to form a field: + # + # name = URI.encode_www_form_component(key, enc) + # value = URI.encode_www_form_component(ele, enc) + # "#{name}=#{value}" + # + # Example: + # + # URI.encode_www_form({foo: [:bar, 1], baz: [:bat, :bam, 2]}) + # # => "foo=bar&foo=1&baz=bat&baz=bam&baz=2" + # + # - Otherwise, +key+ and +value+ are paired to form a field: + # + # name = URI.encode_www_form_component(key, enc) + # value = URI.encode_www_form_component(value, enc) + # "#{name}=#{value}" + # + # Example: + # + # URI.encode_www_form({foo: 0, bar: 1, baz: 2}) + # # => "foo=0&bar=1&baz=2" + # + # The elements of a Hash-like +enum+ may be mixture: + # + # URI.encode_www_form({foo: [0, 1], bar: 2}) + # # => "foo=0&foo=1&bar=2" # - # See URI.encode_www_form_component, URI.decode_www_form. def self.encode_www_form(enum, enc=nil) enum.map do |k,v| if v.nil? @@ -389,22 +518,39 @@ module URI end.join('&') end - # Decodes URL-encoded form data from given +str+. + # Returns name/value pairs derived from the given string +str+, + # which must be an ASCII string. + # + # The method may be used to decode the body of Net::HTTPResponse object +res+ + # for which <tt>res['Content-Type']</tt> is <tt>'application/x-www-form-urlencoded'</tt>. # - # This decodes application/x-www-form-urlencoded data - # and returns an array of key-value arrays. + # The returned data is an array of 2-element subarrays; + # each subarray is a name/value pair (both are strings). + # Each returned string has encoding +enc+, + # and has had invalid characters removed via + # {String#scrub}[rdoc-ref:String#scrub]. # - # This refers http://url.spec.whatwg.org/#concept-urlencoded-parser, - # so this supports only &-separator, and doesn't support ;-separator. + # A simple example: # - # ary = URI.decode_www_form("a=1&a=2&b=3") - # ary #=> [['a', '1'], ['a', '2'], ['b', '3']] - # ary.assoc('a').last #=> '1' - # ary.assoc('b').last #=> '3' - # ary.rassoc('a').last #=> '2' - # Hash[ary] #=> {"a"=>"2", "b"=>"3"} + # URI.decode_www_form('foo=0&bar=1&baz') + # # => [["foo", "0"], ["bar", "1"], ["baz", ""]] + # + # The returned strings have certain conversions, + # similar to those performed in URI.decode_www_form_component: + # + # URI.decode_www_form('f%23o=%2F&b-r=%24&b+z=%40') + # # => [["f#o", "/"], ["b-r", "$"], ["b z", "@"]] + # + # The given string may contain consecutive separators: + # + # URI.decode_www_form('foo=0&&bar=1&&baz=2') + # # => [["foo", "0"], ["", ""], ["bar", "1"], ["", ""], ["baz", "2"]] + # + # A different separator may be specified: + # + # URI.decode_www_form('foo=0--bar=1--baz', separator: '--') + # # => [["foo", "0"], ["bar", "1"], ["baz", ""]] # - # See URI.decode_www_form_component, URI.encode_www_form. def self.decode_www_form(str, enc=Encoding::UTF_8, separator: '&', use__charset_: false, isindex: false) raise ArgumentError, "the input of #{self.name}.#{__method__} must be ASCII only string" unless str.ascii_only? ary = [] @@ -683,7 +829,15 @@ end # module URI module Kernel # - # Returns +uri+ converted to an URI object. + # Returns a \URI object derived from the given +uri+, + # which may be a \URI string or an existing \URI object: + # + # # Returns a new URI. + # uri = URI('http://github.com/ruby/ruby') + # # => #<URI::HTTP http://github.com/ruby/ruby> + # # Returns the given URI. + # URI(uri) + # # => #<URI::HTTP http://github.com/ruby/ruby> # def URI(uri) if uri.is_a?(URI::Generic) diff --git a/lib/uri/file.rb b/lib/uri/file.rb index 7671ad6470..4ff0bc097e 100644 --- a/lib/uri/file.rb +++ b/lib/uri/file.rb @@ -33,6 +33,9 @@ module URI # If an Array is used, the components must be passed in the # order <code>[host, path]</code>. # + # A path from e.g. the File class should be escaped before + # being passed. + # # Examples: # # require 'uri' @@ -44,6 +47,9 @@ module URI # :path => '/ruby/src'}) # uri2.to_s # => "file://host.example.com/ruby/src" # + # uri3 = URI::File.build({:path => URI::escape('/path/my file.txt')}) + # uri3.to_s # => "file:///path/my%20file.txt" + # def self.build(args) tmp = Util::make_components_hash(self, args) super(tmp) diff --git a/lib/uri/ftp.rb b/lib/uri/ftp.rb index abad613c33..1c75e242ba 100644 --- a/lib/uri/ftp.rb +++ b/lib/uri/ftp.rb @@ -17,7 +17,7 @@ module URI # This class will be redesigned because of difference of implementations; # the structure of its path. draft-hoffman-ftp-uri-04 is a draft but it # is a good summary about the de facto spec. - # http://tools.ietf.org/html/draft-hoffman-ftp-uri-04 + # https://datatracker.ietf.org/doc/html/draft-hoffman-ftp-uri-04 # class FTP < Generic # A Default port of 21 for URI::FTP. diff --git a/lib/uri/generic.rb b/lib/uri/generic.rb index cfa0de6b74..bdd366661e 100644 --- a/lib/uri/generic.rb +++ b/lib/uri/generic.rb @@ -564,16 +564,26 @@ module URI end end - # Returns the user component. + # Returns the user component (without URI decoding). def user @user end - # Returns the password component. + # Returns the password component (without URI decoding). def password @password end + # Returns the user component after URI decoding. + def decoded_user + URI.decode_uri_component(@user) if @user + end + + # Returns the password component after URI decoding. + def decoded_password + URI.decode_uri_component(@password) if @password + end + # # Checks the host +v+ component for RFC2396 compliance # and against the URI::Parser Regexp for :HOST. @@ -935,7 +945,7 @@ module URI # == Description # # URI has components listed in order of decreasing significance from left to right, - # see RFC3986 https://tools.ietf.org/html/rfc3986 1.2.3. + # see RFC3986 https://www.rfc-editor.org/rfc/rfc3986 1.2.3. # # == Usage # @@ -1354,6 +1364,9 @@ module URI str << ':' str << @port.to_s end + if (@host || @port) && !@path.empty? && !@path.start_with?('/') + str << '/' + end str << @path if @query str << '?' @@ -1366,6 +1379,7 @@ module URI end str end + alias to_str to_s # # Compares two URIs. @@ -1388,19 +1402,6 @@ module URI self.component_ary.eql?(oth.component_ary) end -=begin - ---- URI::Generic#===(oth) - -=end -# def ===(oth) -# raise NotImplementedError -# end - -=begin -=end - - # Returns an Array of the components defined from the COMPONENT Array. def component_ary component.collect do |x| diff --git a/lib/uri/http.rb b/lib/uri/http.rb index 6e9c963ef1..900b132c8c 100644 --- a/lib/uri/http.rb +++ b/lib/uri/http.rb @@ -80,6 +80,45 @@ module URI url = @query ? "#@path?#@query" : @path.dup url.start_with?(?/.freeze) ? url : ?/ + url end + + # + # == Description + # + # Returns the authority for an HTTP uri, as defined in + # https://www.rfc-editor.org/rfc/rfc3986#section-3.2. + # + # + # Example: + # + # URI::HTTP.build(host: 'www.example.com', path: '/foo/bar').authority #=> "www.example.com" + # URI::HTTP.build(host: 'www.example.com', port: 8000, path: '/foo/bar').authority #=> "www.example.com:8000" + # URI::HTTP.build(host: 'www.example.com', port: 80, path: '/foo/bar').authority #=> "www.example.com" + # + def authority + if port == default_port + host + else + "#{host}:#{port}" + end + end + + # + # == Description + # + # Returns the origin for an HTTP uri, as defined in + # https://www.rfc-editor.org/rfc/rfc6454. + # + # + # Example: + # + # URI::HTTP.build(host: 'www.example.com', path: '/foo/bar').origin #=> "http://www.example.com" + # URI::HTTP.build(host: 'www.example.com', port: 8000, path: '/foo/bar').origin #=> "http://www.example.com:8000" + # URI::HTTP.build(host: 'www.example.com', port: 80, path: '/foo/bar').origin #=> "http://www.example.com" + # URI::HTTPS.build(host: 'www.example.com', path: '/foo/bar').origin #=> "https://www.example.com" + # + def origin + "#{scheme}://#{authority}" + end end register_scheme 'HTTP', HTTP diff --git a/lib/uri/mailto.rb b/lib/uri/mailto.rb index 87cb99656f..cb8024f301 100644 --- a/lib/uri/mailto.rb +++ b/lib/uri/mailto.rb @@ -15,7 +15,7 @@ module URI # RFC6068, the mailto URL scheme. # class MailTo < Generic - include REGEXP + include RFC2396_REGEXP # A Default port of nil for URI::MailTo. DEFAULT_PORT = nil diff --git a/lib/uri/rfc2396_parser.rb b/lib/uri/rfc2396_parser.rb index 76a8f99fd4..00c66cf042 100644 --- a/lib/uri/rfc2396_parser.rb +++ b/lib/uri/rfc2396_parser.rb @@ -497,8 +497,8 @@ module URI ret = {} # for URI::split - ret[:ABS_URI] = Regexp.new('\A\s*' + pattern[:X_ABS_URI] + '\s*\z', Regexp::EXTENDED) - ret[:REL_URI] = Regexp.new('\A\s*' + pattern[:X_REL_URI] + '\s*\z', Regexp::EXTENDED) + ret[:ABS_URI] = Regexp.new('\A\s*+' + pattern[:X_ABS_URI] + '\s*\z', Regexp::EXTENDED) + ret[:REL_URI] = Regexp.new('\A\s*+' + pattern[:X_REL_URI] + '\s*\z', Regexp::EXTENDED) # for URI::extract ret[:URI_REF] = Regexp.new(pattern[:URI_REF]) diff --git a/lib/uri/rfc3986_parser.rb b/lib/uri/rfc3986_parser.rb index 3e07de4805..092a1ac89d 100644 --- a/lib/uri/rfc3986_parser.rb +++ b/lib/uri/rfc3986_parser.rb @@ -1,10 +1,73 @@ -# frozen_string_literal: false +# frozen_string_literal: true 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|[!$&-.0-;=@-Z_a-z~])+)(?:\/\g<segment>)*)?)|(?<path-rootless>\g<segment-nz>(?:\/\g<segment>)*)|(?<path-empty>))(?:\?(?<query>[^#]*))?(?:\#(?<fragment>(?:%\h\h|[!$&-.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>))(?:\?(?<query>[^#]*))?(?:\#(?<fragment>(?:%\h\h|[!$&-.0-;=@-Z_a-z~\/?])*))?)\z/ + HOST = %r[ + (?<IP-literal>\[(?: + (?<IPv6address> + (?:\h{1,4}:){6} + (?<ls32>\h{1,4}:\h{1,4} + | (?<IPv4address>(?<dec-octet>[1-9]\d|1\d{2}|2[0-4]\d|25[0-5]|\d) + \.\g<dec-octet>\.\g<dec-octet>\.\g<dec-octet>) + ) + | ::(?:\h{1,4}:){5}\g<ls32> + | \h{1,4}?::(?:\h{1,4}:){4}\g<ls32> + | (?:(?:\h{1,4}:)?\h{1,4})?::(?:\h{1,4}:){3}\g<ls32> + | (?:(?:\h{1,4}:){,2}\h{1,4})?::(?:\h{1,4}:){2}\g<ls32> + | (?:(?:\h{1,4}:){,3}\h{1,4})?::\h{1,4}:\g<ls32> + | (?:(?:\h{1,4}:){,4}\h{1,4})?::\g<ls32> + | (?:(?:\h{1,4}:){,5}\h{1,4})?::\h{1,4} + | (?:(?:\h{1,4}:){,6}\h{1,4})?:: + ) + | (?<IPvFuture>v\h++\.[!$&-.0-9:;=A-Z_a-z~]++) + )\]) + | \g<IPv4address> + | (?<reg-name>(?:%\h\h|[!$&-.0-9;=A-Z_a-z~])*+) + ]x + + USERINFO = /(?:%\h\h|[!$&-.0-9:;=A-Z_a-z~])*+/ + + SCHEME = %r[[A-Za-z][+\-.0-9A-Za-z]*+].source + SEG = %r[(?:%\h\h|[!$&-.0-9:;=@A-Z_a-z~/])].source + SEG_NC = %r[(?:%\h\h|[!$&-.0-9;=@A-Z_a-z~])].source + FRAGMENT = %r[(?:%\h\h|[!$&-.0-9:;=@A-Z_a-z~/?])*+].source + + RFC3986_URI = %r[\A + (?<seg>#{SEG}){0} + (?<URI> + (?<scheme>#{SCHEME}): + (?<hier-part>// + (?<authority> + (?:(?<userinfo>#{USERINFO.source})@)? + (?<host>#{HOST.source.delete(" \n")}) + (?::(?<port>\d*+))? + ) + (?<path-abempty>(?:/\g<seg>*+)?) + | (?<path-absolute>/((?!/)\g<seg>++)?) + | (?<path-rootless>(?!/)\g<seg>++) + | (?<path-empty>) + ) + (?:\?(?<query>[^\#]*+))? + (?:\#(?<fragment>#{FRAGMENT}))? + )\z]x + + RFC3986_relative_ref = %r[\A + (?<seg>#{SEG}){0} + (?<relative-ref> + (?<relative-part>// + (?<authority> + (?:(?<userinfo>#{USERINFO.source})@)? + (?<host>#{HOST.source.delete(" \n")}(?<!/))? + (?::(?<port>\d*+))? + ) + (?<path-abempty>(?:/\g<seg>*+)?) + | (?<path-absolute>/\g<seg>*+) + | (?<path-noscheme>#{SEG_NC}++(?:/\g<seg>*+)?) + | (?<path-empty>) + ) + (?:\?(?<query>[^#]*+))? + (?:\#(?<fragment>#{FRAGMENT}))? + )\z]x attr_reader :regexp def initialize @@ -20,9 +83,9 @@ module URI uri.ascii_only? or raise InvalidURIError, "URI must be ascii only #{uri.dump}" if m = RFC3986_URI.match(uri) - query = m["query".freeze] - scheme = m["scheme".freeze] - opaque = m["path-rootless".freeze] + query = m["query"] + scheme = m["scheme"] + opaque = m["path-rootless"] if opaque opaque << "?#{query}" if query [ scheme, @@ -33,35 +96,35 @@ module URI nil, # path opaque, nil, # query - m["fragment".freeze] + m["fragment"] ] else # normal [ scheme, - m["userinfo".freeze], - m["host".freeze], - m["port".freeze], + m["userinfo"], + m["host"], + m["port"], nil, # registry - (m["path-abempty".freeze] || - m["path-absolute".freeze] || - m["path-empty".freeze]), + (m["path-abempty"] || + m["path-absolute"] || + m["path-empty"]), nil, # opaque query, - m["fragment".freeze] + m["fragment"] ] end elsif m = RFC3986_relative_ref.match(uri) [ nil, # scheme - m["userinfo".freeze], - m["host".freeze], - m["port".freeze], + m["userinfo"], + m["host"], + m["port"], nil, # registry, - (m["path-abempty".freeze] || - m["path-absolute".freeze] || - m["path-noscheme".freeze] || - m["path-empty".freeze]), + (m["path-abempty"] || + m["path-absolute"] || + m["path-noscheme"] || + m["path-empty"]), nil, # opaque - m["query".freeze], - m["fragment".freeze] + m["query"], + m["fragment"] ] else raise InvalidURIError, "bad URI(is not URI?): #{uri.inspect}" @@ -93,15 +156,15 @@ module URI def default_regexp # :nodoc: { - 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|[!$&-.0-;=@-Z_a-z~\/?])*\z/, - OPAQUE: /\A(?:[^\/].*)?\z/, - PORT: /\A[\x09\x0a\x0c\x0d ]*\d*[\x09\x0a\x0c\x0d ]*\z/, + SCHEME: %r[\A#{SCHEME}\z]o, + USERINFO: %r[\A#{USERINFO}\z]o, + HOST: %r[\A#{HOST}\z]o, + ABS_PATH: %r[\A/#{SEG}*+\z]o, + REL_PATH: %r[\A(?!/)#{SEG}++\z]o, + QUERY: %r[\A(?:%\h\h|[!$&-.0-9:;=@A-Z_a-z~/?])*+\z], + FRAGMENT: %r[\A#{FRAGMENT}\z]o, + OPAQUE: %r[\A(?:[^/].*)?\z], + PORT: /\A[\x09\x0a\x0c\x0d ]*+\d*[\x09\x0a\x0c\x0d ]*\z/, } end diff --git a/lib/uri/uri.gemspec b/lib/uri/uri.gemspec index 584a4faa11..9cf0a71196 100644 --- a/lib/uri/uri.gemspec +++ b/lib/uri/uri.gemspec @@ -12,18 +12,26 @@ Gem::Specification.new do |spec| spec.summary = %q{URI is a module providing classes to handle Uniform Resource Identifiers} spec.description = spec.summary - spec.homepage = "https://github.com/ruby/uri" + + github_link = "https://github.com/ruby/uri" + + spec.homepage = github_link spec.licenses = ["Ruby", "BSD-2-Clause"] - spec.required_ruby_version = '>= 2.4' + spec.required_ruby_version = '>= 2.5' - spec.metadata["homepage_uri"] = spec.homepage - spec.metadata["source_code_uri"] = spec.homepage + spec.metadata = { + "bug_tracker_uri" => "#{github_link}/issues", + "changelog_uri" => "#{github_link}/releases", + "documentation_uri" => "https://ruby.github.io/uri/", + "homepage_uri" => spec.homepage, + "source_code_uri" => github_link + } # Specify which files should be added to the gem when it is released. # The `git ls-files -z` loads the files in the RubyGem that have been added into git. spec.files = Dir.chdir(File.expand_path('..', __FILE__)) do - `git ls-files -z 2>/dev/null`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) } + `git ls-files -z 2>#{IO::NULL}`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) } end spec.bindir = "exe" spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) } diff --git a/lib/uri/version.rb b/lib/uri/version.rb index 41da51d844..2dafa57d59 100644 --- a/lib/uri/version.rb +++ b/lib/uri/version.rb @@ -1,6 +1,6 @@ module URI # :stopdoc: - VERSION_CODE = '001001'.freeze + VERSION_CODE = '001300'.freeze VERSION = VERSION_CODE.scan(/../).collect{|n| n.to_i}.join('.').freeze # :startdoc: end |