diff options
Diffstat (limited to 'lib/uri')
| -rw-r--r-- | lib/uri/common.rb | 670 | ||||
| -rw-r--r-- | lib/uri/file.rb | 100 | ||||
| -rw-r--r-- | lib/uri/ftp.rb | 70 | ||||
| -rw-r--r-- | lib/uri/generic.rb | 545 | ||||
| -rw-r--r-- | lib/uri/http.rb | 93 | ||||
| -rw-r--r-- | lib/uri/https.rb | 6 | ||||
| -rw-r--r-- | lib/uri/ldap.rb | 84 | ||||
| -rw-r--r-- | lib/uri/ldaps.rb | 5 | ||||
| -rw-r--r-- | lib/uri/mailto.rb | 45 | ||||
| -rw-r--r-- | lib/uri/rfc2396_parser.rb | 109 | ||||
| -rw-r--r-- | lib/uri/rfc3986_parser.rb | 181 | ||||
| -rw-r--r-- | lib/uri/uri.gemspec | 42 | ||||
| -rw-r--r-- | lib/uri/version.rb | 6 | ||||
| -rw-r--r-- | lib/uri/ws.rb | 83 | ||||
| -rw-r--r-- | lib/uri/wss.rb | 23 |
15 files changed, 1323 insertions, 739 deletions
diff --git a/lib/uri/common.rb b/lib/uri/common.rb index ec85bbc1e7..a2fb531631 100644 --- a/lib/uri/common.rb +++ b/lib/uri/common.rb @@ -1,32 +1,65 @@ -# frozen_string_literal: false +# frozen_string_literal: true #-- # = uri/common.rb # # Author:: Akira Yamada <akira@ruby-lang.org> -# Revision:: $Id$ # License:: # You can redistribute it and/or modify it under the same term as Ruby. # # See URI for general documentation # -require "uri/rfc2396_parser" -require "uri/rfc3986_parser" +require_relative "rfc2396_parser" +require_relative "rfc3986_parser" module URI - REGEXP = RFC2396_REGEXP - Parser = RFC2396_Parser + # The default parser instance for RFC 2396. + RFC2396_PARSER = RFC2396_Parser.new + Ractor.make_shareable(RFC2396_PARSER) if defined?(Ractor) + + # The default parser instance for RFC 3986. RFC3986_PARSER = RFC3986_Parser.new + Ractor.make_shareable(RFC3986_PARSER) if defined?(Ractor) + + # The default parser instance. + DEFAULT_PARSER = RFC3986_PARSER + Ractor.make_shareable(DEFAULT_PARSER) if defined?(Ractor) + + # Set the default parser instance. + def self.parser=(parser = RFC3986_PARSER) + remove_const(:Parser) if defined?(::URI::Parser) + const_set("Parser", parser.class) + + remove_const(:PARSER) if defined?(::URI::PARSER) + const_set("PARSER", parser) + + remove_const(:REGEXP) if defined?(::URI::REGEXP) + remove_const(:PATTERN) if defined?(::URI::PATTERN) + if Parser == RFC2396_Parser + const_set("REGEXP", URI::RFC2396_REGEXP) + const_set("PATTERN", URI::RFC2396_REGEXP::PATTERN) + end - # URI::Parser.new - DEFAULT_PARSER = Parser.new - DEFAULT_PARSER.pattern.each_pair do |sym, str| - unless REGEXP::PATTERN.const_defined?(sym) - REGEXP::PATTERN.const_set(sym, str) + Parser.new.regexp.each_pair do |sym, str| + remove_const(sym) if const_defined?(sym, false) + const_set(sym, str) end end - DEFAULT_PARSER.regexp.each_pair do |sym, str| - const_set(sym, str) + self.parser = RFC3986_PARSER + + def self.const_missing(const) # :nodoc: + if const == :REGEXP + warn "URI::REGEXP is obsolete. Use URI::RFC2396_REGEXP explicitly.", uplevel: 1 if $VERBOSE + URI::RFC2396_REGEXP + elsif value = RFC2396_PARSER.regexp[const] + warn "URI::#{const} is obsolete. Use URI::RFC2396_PARSER.regexp[#{const.inspect}] explicitly.", uplevel: 1 if $VERBOSE + value + elsif value = RFC2396_Parser.const_get(const) + warn "URI::#{const} is obsolete. Use URI::RFC2396_Parser::#{const} explicitly.", uplevel: 1 if $VERBOSE + value + else + super + end end module Util # :nodoc: @@ -61,84 +94,104 @@ module URI module_function :make_components_hash end - # module for escaping unsafe characters with codes. - module Escape - # - # == Synopsis - # - # URI.escape(str [, unsafe]) - # - # == Args - # - # +str+:: - # String to replaces in. - # +unsafe+:: - # Regexp that matches all symbols that must be replaced with codes. - # By default uses <tt>UNSAFE</tt>. - # When this argument is a String, it represents a character set. - # - # == Description - # - # Escapes the string, replacing all unsafe characters with codes. - # - # This method is obsolete and should not be used. Instead, use - # CGI.escape, URI.encode_www_form or URI.encode_www_form_component - # depending on your specific use case. - # - # == Usage - # - # require 'uri' - # - # enc_uri = URI.escape("http://example.com/?a=\11\15") - # p enc_uri - # # => "http://example.com/?a=%09%0D" - # - # p URI.unescape(enc_uri) - # # => "http://example.com/?a=\t\r" - # - # p URI.escape("@?@!", "!?") - # # => "@%3F@%21" - # - def escape(*arg) - warn "#{caller(1)[0]}: warning: URI.escape is obsolete" if $VERBOSE - DEFAULT_PARSER.escape(*arg) - end - alias encode escape - # - # == Synopsis - # - # URI.unescape(str) - # - # == Args - # - # +str+:: - # Unescapes the string. - # - # == Usage - # - # require 'uri' - # - # enc_uri = URI.escape("http://example.com/?a=\11\15") - # p enc_uri - # # => "http://example.com/?a=%09%0D" - # - # p URI.unescape(enc_uri) - # # => "http://example.com/?a=\t\r" - # - def unescape(*arg) - warn "#{caller(1)[0]}: warning: URI.unescape is obsolete" if $VERBOSE - DEFAULT_PARSER.unescape(*arg) + module Schemes # :nodoc: + class << self + ReservedChars = ".+-" + EscapedChars = "\u01C0\u01C1\u01C2" + # Use Lo category chars as escaped chars for TruffleRuby, which + # does not allow Symbol categories as identifiers. + + def escape(name) + unless name and name.ascii_only? + return nil + end + name.upcase.tr(ReservedChars, EscapedChars) + end + + def unescape(name) + name.tr(EscapedChars, ReservedChars).encode(Encoding::US_ASCII).upcase + end + + def find(name) + const_get(name, false) if name and const_defined?(name, false) + end + + def register(name, klass) + unless scheme = escape(name) + raise ArgumentError, "invalid character as scheme - #{name}" + end + const_set(scheme, klass) + end + + def list + constants.map { |name| + [unescape(name.to_s), const_get(name)] + }.to_h + end end - alias decode unescape - end # module Escape + end + private_constant :Schemes - extend Escape - include REGEXP + # 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.register(scheme, klass) + end - @@schemes = {} - # 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 + Schemes.list + end + + # :stopdoc: + INITIAL_SCHEMES = scheme_list + private_constant :INITIAL_SCHEMES + Ractor.make_shareable(INITIAL_SCHEMES) if defined?(Ractor) + # :startdoc: + + # 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: + # + # 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 = Schemes.escape(scheme) + + uri_class = INITIAL_SCHEMES[const_name] + uri_class ||= Schemes.find(const_name) + uri_class ||= default + + return uri_class.new(scheme, *arguments) end # @@ -158,115 +211,67 @@ 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' - # - # p 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) + PARSER.split(uri) end + # Returns a new \URI object constructed from the given string +uri+: # - # == Synopsis - # - # URI::parse(uri_str) + # 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> # - # == 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 = URI.parse("http://www.ruby-lang.org/") - # p uri - # # => #<URI::HTTP:0x202281be URL:http://www.ruby-lang.org/> - # p uri.scheme - # # => "http" - # p 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 URI::RFC2396_PARSER.escape string +uri+ + # if it may contain invalid URI characters. # def self.parse(uri) - RFC3986_PARSER.parse(uri) + PARSER.parse(uri) end + # Merges the given URI strings +str+ + # per {RFC 2396}[https://www.rfc-editor.org/rfc/rfc2396.html]. # - # == Synopsis + # Each string in +str+ is converted to an + # {RFC3986 URI}[https://www.rfc-editor.org/rfc/rfc3986.html] before being merged. # - # URI::join(str[, str, ...]) + # Examples: # - # == Args + # URI.join("http://example.com/","main.rbx") + # # => #<URI::HTTP http://example.com/main.rbx> # - # +str+:: - # String(s) to work with, will be converted to RFC3986 URIs before merging. - # - # == Description + # URI.join('http://example.com', 'foo') + # # => #<URI::HTTP http://example.com/foo> # - # Joins URIs. - # - # == Usage - # - # require 'uri' + # URI.join('http://example.com', '/foo', '/bar') + # # => #<URI::HTTP http://example.com/bar> # - # p URI.join("http://example.com/","main.rbx") - # # => #<URI::HTTP:0x2022ac02 URL:http://example.com/main.rbx> - # - # p URI.join('http://example.com', 'foo') - # # => #<URI::HTTP:0x01ab80a0 URL:http://example.com/foo> - # - # p URI.join('http://example.com', '/foo', '/bar') - # # => #<URI::HTTP:0x01aaf0b0 URL:http://example.com/bar> - # - # p URI.join('http://example.com', '/foo', 'bar') - # # => #<URI::HTTP:0x801a92af0 URL:http://example.com/bar> - # - # p URI.join('http://example.com', '/foo/', 'bar') - # # => #<URI::HTTP:0x80135a3a0 URL:http://example.com/foo/bar> + # URI.join('http://example.com', '/foo', 'bar') + # # => #<URI::HTTP http://example.com/bar> # + # URI.join('http://example.com', '/foo/', 'bar') + # # => #<URI::HTTP http://example.com/foo/bar> # def self.join(*str) - RFC3986_PARSER.join(*str) + PARSER.join(*str) end # @@ -279,7 +284,7 @@ module URI # +str+:: # String to extract URIs from. # +schemes+:: - # Limit URI matching to a specific schemes. + # Limit URI matching to specific schemes. # # == Description # @@ -293,9 +298,9 @@ 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) - warn "#{caller(1)[0]}: warning: URI.extract is obsolete" if $VERBOSE - DEFAULT_PARSER.extract(str, schemes, &block) + def self.extract(str, schemes = nil, &block) # :nodoc: + warn "URI.extract is obsolete", uplevel: 1 if $VERBOSE + PARSER.extract(str, schemes, &block) end # @@ -310,9 +315,10 @@ module URI # whose scheme is one of the match_schemes. # # == Description + # # Returns a Regexp object which matches to URI-like strings. # The Regexp object returned by this method includes arbitrary - # number of capture group (parentheses). Never rely on it's number. + # number of capture group (parentheses). Never rely on its number. # # == Usage # @@ -322,99 +328,242 @@ module URI # html_string.slice(URI.regexp) # # # remove ftp URIs - # html_string.sub(URI.regexp(['ftp']) + # html_string.sub(URI.regexp(['ftp']), '') # # # You should not rely on the number of parentheses # html_string.scan(URI.regexp) do |*matches| # p $& # end # - def self.regexp(schemes = nil) - warn "#{caller(1)[0]}: warning: URI.regexp is obsolete" if $VERBOSE - DEFAULT_PARSER.make_regexp(schemes) + def self.regexp(schemes = nil)# :nodoc: + warn "URI.regexp is obsolete", uplevel: 1 if $VERBOSE + PARSER.make_regexp(schemes) end TBLENCWWWCOMP_ = {} # :nodoc: 256.times do |i| - TBLENCWWWCOMP_[i.chr] = '%%%02X' % i + TBLENCWWWCOMP_[-i.chr] = -('%%%02X' % i) end + TBLENCURICOMP_ = TBLENCWWWCOMP_.dup.freeze # :nodoc: TBLENCWWWCOMP_[' '] = '+' TBLENCWWWCOMP_.freeze TBLDECWWWCOMP_ = {} # :nodoc: 256.times do |i| h, l = i>>4, i&15 - TBLDECWWWCOMP_['%%%X%X' % [h, l]] = i.chr - TBLDECWWWCOMP_['%%%x%X' % [h, l]] = i.chr - TBLDECWWWCOMP_['%%%X%x' % [h, l]] = i.chr - TBLDECWWWCOMP_['%%%x%x' % [h, l]] = i.chr + TBLDECWWWCOMP_[-('%%%X%X' % [h, l])] = -i.chr + TBLDECWWWCOMP_[-('%%%x%X' % [h, l])] = -i.chr + TBLDECWWWCOMP_[-('%%%X%x' % [h, l])] = -i.chr + TBLDECWWWCOMP_[-('%%%x%x' % [h, l])] = -i.chr end TBLDECWWWCOMP_['+'] = ' ' TBLDECWWWCOMP_.freeze - HTML5ASCIIINCOMPAT = defined? Encoding::UTF_7 ? [Encoding::UTF_7, Encoding::UTF_16BE, Encoding::UTF_16LE, - Encoding::UTF_32BE, Encoding::UTF_32LE] : [] # :nodoc: - - # Encode 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: # - # 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('*.-_azAZ09') + # # => "*.-_azAZ09" # - # If +enc+ is given, convert +str+ to the encoding before percent encoding. + # - Converts: # - # This is an implementation of - # http://www.w3.org/TR/2013/CR-html5-20130806/forms.html#url-encoded-form-data + # - 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>. # - # See URI.decode_www_form_component, URI.encode_www_form + # Example: + # + # URI.encode_www_form_component('Here are some punctuation characters: ,;?:') + # # => "Here+are+some+punctuation+characters%3A+%2C%3B%3F%3A" + # + # Encoding: + # + # - 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+. + # + # 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 + + # Returns a string derived from the given string +str+ with + # URI-encoded characters matching +regexp+ according to +table+. + 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 str.encode!(Encoding::UTF_8, invalid: :replace, undef: :replace) - str.encode!(enc, fallback: ->(x){"&#{x.ord};"}) + str.encode!(enc, fallback: ->(x){"&##{x.ord};"}) 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 - # Decode 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) - raise ArgumentError, "invalid %-encoding (#{str})" if /%(?!\h\h)/ =~ str - str.b.gsub(/\+|%\h\h/, TBLDECWWWCOMP_).force_encoding(enc) + # Returns a string decoding characters matching +regexp+ from the + # given \URL-encoded string +str+. + def self._decode_uri_component(regexp, str, enc) + raise ArgumentError, "invalid %-encoding (#{str})" if /%(?!\h\h)/.match?(str) + str.b.gsub(regexp, TBLDECWWWCOMP_).force_encoding(enc) end + private_class_method :_decode_uri_component - # Generate 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: + # + # URI.encode_www_form('f#o': '/', 'b-r': '$', 'b z': '@') + # # => "f%23o=%2F&b-r=%24&b+z=%40" + # + # When +enum+ is Array-like, each element +ele+ is converted to a field: + # + # - 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): + # + # name = URI.encode_www_form_component(ele[0], enc) + # value = URI.encode_www_form_component(ele[1], enc) + # "#{name}=#{value}" + # + # Examples: + # + # 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) # - # This generates application/x-www-form-urlencoded data defined in HTML5 - # from given an Enumerable object. + # Example: # - # This internally uses URI.encode_www_form_component(str). + # URI.encode_www_form(['foo', :bar, 0]) + # # => "foo&bar&0" # - # This method doesn't convert the encoding of given items, so convert them - # before call 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.) + # The elements of an Array-like +enum+ may be mixture: # - # This method doesn't handle files. When you send a file, use - # multipart/form-data. + # URI.encode_www_form([['foo', 0], ['bar', 1, 2], ['baz'], :bat]) + # # => "foo=0&bar=1&baz&bat" # - # This refers http://url.spec.whatwg.org/#concept-urlencoded-serializer + # When +enum+ is Hash-like, + # each +key+/+value+ pair is converted to one or more fields: # - # 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" + # - 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? @@ -435,22 +584,39 @@ module URI end.join('&') end - # Decode URL-encoded form data from given +str+. + # Returns name/value pairs derived from the given string +str+, + # which must be an ASCII string. # - # This decodes application/x-www-form-urlencoded data - # and returns array of key-value array. + # 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 refers http://url.spec.whatwg.org/#concept-urlencoded-parser , - # so this supports only &-separator, don't support ;-separator. + # 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]. # - # ary = URI.decode_www_form("a=1&a=2&b=3") - # p ary #=> [['a', '1'], ['a', '2'], ['b', '3']] - # p ary.assoc('a').last #=> '1' - # p ary.assoc('b').last #=> '3' - # p ary.rassoc('a').last #=> '2' - # p Hash[ary] # => {"a"=>"2", "b"=>"3"} + # A simple example: + # + # 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 = [] @@ -462,7 +628,7 @@ module URI if isindex if sep.empty? val = key - key = '' + key = +'' end isindex = false end @@ -476,7 +642,7 @@ module URI if val val.gsub!(/\+|%\h\h/, TBLDECWWWCOMP_) else - val = '' + val = +'' end ary << [key, val] @@ -716,6 +882,7 @@ module URI "utf-16"=>"utf-16le", "utf-16le"=>"utf-16le", } # :nodoc: + Ractor.make_shareable(WEB_ENCODINGS_) if defined?(Ractor) # :nodoc: # return encoding or nil @@ -728,7 +895,18 @@ end # module URI module Kernel # - # Returns +uri+ converted to a URI object. + # Returns a \URI object derived from the given +uri+, + # which may be a \URI string or an existing \URI object: + # + # require 'uri' + # # 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> + # + # You must require 'uri' to use this method. # def URI(uri) if uri.is_a?(URI::Generic) diff --git a/lib/uri/file.rb b/lib/uri/file.rb new file mode 100644 index 0000000000..47b5aef067 --- /dev/null +++ b/lib/uri/file.rb @@ -0,0 +1,100 @@ +# frozen_string_literal: true + +require_relative 'generic' + +module URI + + # + # The "file" URI is defined by RFC8089. + # + class File < Generic + # A Default port of nil for URI::File. + DEFAULT_PORT = nil + + # + # An Array of the available components for URI::File. + # + COMPONENT = [ + :scheme, + :host, + :path + ].freeze + + # + # == Description + # + # Creates a new URI::File object from components, with syntax checking. + # + # The components accepted are +host+ and +path+. + # + # The components should be provided either as an Array, or as a Hash + # with keys formed by preceding the component names with a colon. + # + # 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' + # + # uri1 = URI::File.build(['host.example.com', '/path/file.zip']) + # uri1.to_s # => "file://host.example.com/path/file.zip" + # + # uri2 = URI::File.build({:host => 'host.example.com', + # :path => '/ruby/src'}) + # uri2.to_s # => "file://host.example.com/ruby/src" + # + # uri3 = URI::File.build({:path => URI::RFC2396_PARSER.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) + end + + # Protected setter for the host component +v+. + # + # See also URI::Generic.host=. + # + def set_host(v) + v = "" if v.nil? || v == "localhost" + @host = v + end + + # do nothing + def set_port(v) + end + + # raise InvalidURIError + def check_userinfo(user) + raise URI::InvalidURIError, "cannot set userinfo for file URI" + end + + # raise InvalidURIError + def check_user(user) + raise URI::InvalidURIError, "cannot set user for file URI" + end + + # raise InvalidURIError + def check_password(user) + raise URI::InvalidURIError, "cannot set password for file URI" + end + + # do nothing + def set_userinfo(v) + end + + # do nothing + def set_user(v) + end + + # do nothing + def set_password(v) + end + end + + register_scheme 'FILE', File +end diff --git a/lib/uri/ftp.rb b/lib/uri/ftp.rb index e5c00b34da..1c75e242ba 100644 --- a/lib/uri/ftp.rb +++ b/lib/uri/ftp.rb @@ -3,12 +3,11 @@ # # Author:: Akira Yamada <akira@ruby-lang.org> # License:: You can redistribute it and/or modify it under the same term as Ruby. -# Revision:: $Id$ # # See URI for general documentation # -require 'uri/generic' +require_relative 'generic' module URI @@ -18,14 +17,14 @@ 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 + # A Default port of 21 for URI::FTP. DEFAULT_PORT = 21 # - # An Array of the available components for URI::FTP + # An Array of the available components for URI::FTP. # COMPONENT = [ :scheme, @@ -34,7 +33,7 @@ module URI ].freeze # - # Typecode is "a", "i" or "d". + # Typecode is "a", "i", or "d". # # * "a" indicates a text file (the FTP command was ASCII) # * "i" indicates a binary file (FTP command IMAGE) @@ -42,8 +41,7 @@ module URI # TYPECODE = ['a', 'i', 'd'].freeze - # Typecode prefix - # ';type=' + # Typecode prefix ";type=". TYPECODE_PREFIX = ';type='.freeze def self.new2(user, password, host, port, path, @@ -71,27 +69,29 @@ module URI # # Creates a new URI::FTP object from components, with syntax checking. # - # The components accepted are +userinfo+, +host+, +port+, +path+ and + # The components accepted are +userinfo+, +host+, +port+, +path+, and # +typecode+. # # The components should be provided either as an Array, or as a Hash # with keys formed by preceding the component names with a colon. # - # If an Array is used, the components must be passed in the order - # [userinfo, host, port, path, typecode] + # If an Array is used, the components must be passed in the + # order <code>[userinfo, host, port, path, typecode]</code>. # # If the path supplied is absolute, it will be escaped in order to - # make it absolute in the URI. Examples: + # make it absolute in the URI. + # + # Examples: # # require 'uri' # - # uri = URI::FTP.build(['user:password', 'ftp.example.com', nil, + # uri1 = URI::FTP.build(['user:password', 'ftp.example.com', nil, # '/path/file.zip', 'i']) - # puts uri.to_s -> ftp://user:password@ftp.example.com/%2Fpath/file.zip;type=i + # uri1.to_s # => "ftp://user:password@ftp.example.com/%2Fpath/file.zip;type=i" # # uri2 = URI::FTP.build({:host => 'ftp.example.com', # :path => 'ruby/src'}) - # puts uri2.to_s -> ftp://ftp.example.com/ruby/src + # uri2.to_s # => "ftp://ftp.example.com/ruby/src" # def self.build(args) @@ -128,7 +128,7 @@ module URI # required by RFC1738; instead it is treated as per RFC2396. # # Arguments are +scheme+, +userinfo+, +host+, +port+, +registry+, +path+, - # +opaque+, +query+ and +fragment+, in that order. + # +opaque+, +query+, and +fragment+, in that order. # def initialize(scheme, userinfo, host, port, registry, @@ -155,13 +155,13 @@ module URI end end - # typecode accessor + # typecode accessor. # - # see URI::FTP::COMPONENT + # See URI::FTP::COMPONENT. attr_reader :typecode - # validates typecode +v+, - # returns a +true+ or +false+ boolean + # Validates typecode +v+, + # returns +true+ or +false+. # def check_typecode(v) if TYPECODE.include?(v) @@ -173,9 +173,9 @@ module URI end private :check_typecode - # Private setter for the typecode +v+ + # Private setter for the typecode +v+. # - # see also URI::FTP.typecode= + # See also URI::FTP.typecode=. # def set_typecode(v) @typecode = v @@ -190,21 +190,20 @@ module URI # # == Description # - # public setter for the typecode +v+. - # (with validation) + # Public setter for the typecode +v+ + # (with validation). # - # see also URI::FTP.check_typecode + # See also URI::FTP.check_typecode. # # == Usage # # require 'uri' # # uri = URI.parse("ftp://john@ftp.example.com/my_file.img") - # #=> #<URI::FTP:0x00000000923650 URL:ftp://john@ftp.example.com/my_file.img> + # #=> #<URI::FTP ftp://john@ftp.example.com/my_file.img> # uri.typecode = "i" - # # => "i" # uri - # #=> #<URI::FTP:0x00000000923650 URL:ftp://john@ftp.example.com/my_file.img;type=i> + # #=> #<URI::FTP ftp://john@ftp.example.com/my_file.img;type=i> # def typecode=(typecode) check_typecode(typecode) @@ -226,29 +225,29 @@ module URI # RFC 1738 specifically states that the path for an FTP URI does not # include the / which separates the URI path from the URI host. Example: # - # ftp://ftp.example.com/pub/ruby + # <code>ftp://ftp.example.com/pub/ruby</code> # # The above URI indicates that the client should connect to - # ftp.example.com then cd pub/ruby from the initial login directory. + # ftp.example.com then cd to pub/ruby from the initial login directory. # # If you want to cd to an absolute directory, you must include an # escaped / (%2F) in the path. Example: # - # ftp://ftp.example.com/%2Fpub/ruby + # <code>ftp://ftp.example.com/%2Fpub/ruby</code> # - # This method will then return "/pub/ruby" + # This method will then return "/pub/ruby". # def path return @path.sub(/^\//,'').sub(/^%2F/,'/') end - # Private setter for the path of the URI::FTP + # Private setter for the path of the URI::FTP. def set_path(v) super("/" + v.sub(/^\//, "%2F")) end protected :set_path - # Returns a String representation of the URI::FTP + # Returns a String representation of the URI::FTP. def to_s save_path = nil if @typecode @@ -263,5 +262,6 @@ module URI return str end end - @@schemes['FTP'] = FTP + + register_scheme 'FTP', FTP end diff --git a/lib/uri/generic.rb b/lib/uri/generic.rb index 80d9616c1e..6a0f638d76 100644 --- a/lib/uri/generic.rb +++ b/lib/uri/generic.rb @@ -4,12 +4,13 @@ # # Author:: Akira Yamada <akira@ruby-lang.org> # License:: You can redistribute it and/or modify it under the same term as Ruby. -# Revision:: $Id$ # # See URI for general documentation # -require 'uri/common' +require_relative 'common' +autoload :IPSocket, 'socket' +autoload :IPAddr, 'ipaddr' module URI @@ -21,26 +22,26 @@ module URI include URI # - # A Default port of nil for URI::Generic + # A Default port of nil for URI::Generic. # DEFAULT_PORT = nil # - # Returns default port + # Returns default port. # def self.default_port self::DEFAULT_PORT end # - # Returns default port + # Returns default port. # def default_port self.class.default_port end # - # An Array of the available components for URI::Generic + # An Array of the available components for URI::Generic. # COMPONENT = [ :scheme, @@ -66,14 +67,13 @@ module URI # # == Synopsis # - # See #new + # See ::new. # # == Description # # At first, tries to create a new URI::Generic instance using # URI::Generic::build. But, if exception URI::InvalidComponentError is raised, - # then it URI::Escape.escape all URI components and tries again. - # + # then it does URI::RFC2396_PARSER.escape all URI components and tries again. # def self.build2(args) begin @@ -82,7 +82,7 @@ module URI if args.kind_of?(Array) return self.build(args.collect{|x| if x.is_a?(String) - DEFAULT_PARSER.escape(x) + URI::RFC2396_PARSER.escape(x) else x end @@ -91,7 +91,7 @@ module URI tmp = {} args.each do |key, value| tmp[key] = if value - DEFAULT_PARSER.escape(value) + URI::RFC2396_PARSER.escape(value) else value end @@ -104,14 +104,14 @@ module URI # # == Synopsis # - # See #new + # See ::new. # # == Description # # Creates a new URI::Generic instance from components of URI::Generic # with check. Components are: scheme, userinfo, host, port, registry, path, - # opaque, query and fragment. You can provide arguments either by an Array or a Hash. - # See #new for hash keys to use or for order of array items. + # opaque, query, and fragment. You can provide arguments either by an Array or a Hash. + # See ::new for hash keys to use or for order of array items. # def self.build(args) if args.kind_of?(Array) && @@ -126,40 +126,41 @@ module URI end end else - component = self.class.component rescue ::URI::Generic::COMPONENT + component = self.component rescue ::URI::Generic::COMPONENT raise ArgumentError, - "expected Array of or Hash of components of #{self.class} (#{component.join(', ')})" + "expected Array of or Hash of components of #{self} (#{component.join(', ')})" end tmp << nil tmp << true return self.new(*tmp) end + # # == Args # # +scheme+:: # Protocol scheme, i.e. 'http','ftp','mailto' and so on. # +userinfo+:: - # User name and password, i.e. 'sdmitry:bla' + # User name and password, i.e. 'sdmitry:bla'. # +host+:: - # Server host name + # Server host name. # +port+:: - # Server port + # Server port. # +registry+:: # Registry of naming authorities. # +path+:: - # Path on server + # Path on server. # +opaque+:: - # Opaque part + # Opaque part. # +query+:: - # Query data + # Query data. # +fragment+:: - # A part of URI after '#' sign + # Part of the URI after '#' character. # +parser+:: - # Parser for internal use [URI::DEFAULT_PARSER by default] + # Parser for internal use [URI::DEFAULT_PARSER by default]. # +arg_check+:: - # Check arguments [false by default] + # Check arguments [false by default]. # # == Description # @@ -185,18 +186,18 @@ module URI if arg_check self.scheme = scheme - self.userinfo = userinfo self.hostname = host self.port = port + self.userinfo = userinfo self.path = path self.query = query self.opaque = opaque self.fragment = fragment else self.set_scheme(scheme) - self.set_userinfo(userinfo) self.set_host(host) self.set_port(port) + self.set_userinfo(userinfo) self.set_path(path) self.query = query self.set_opaque(opaque) @@ -213,39 +214,38 @@ module URI end # - # returns the scheme component of the URI. + # Returns the scheme component of the URI. # # URI("http://foo/bar/baz").scheme #=> "http" # attr_reader :scheme - # returns the host component of the URI. + # Returns the host component of the URI. # # URI("http://foo/bar/baz").host #=> "foo" # - # It returns nil if no host component. + # It returns nil if no host component exists. # # URI("mailto:foo@example.org").host #=> nil # - # The component doesn't contains the port number. + # The component does not contain the port number. # # URI("http://foo:8080/bar/baz").host #=> "foo" # - # Since IPv6 addresses are wrapped by brackets in URIs, - # this method returns IPv6 addresses wrapped by brackets. - # This form is not appropriate to pass socket methods such as TCPSocket.open. - # If unwrapped host names are required, use "hostname" method. + # Since IPv6 addresses are wrapped with brackets in URIs, + # this method returns IPv6 addresses wrapped with brackets. + # This form is not appropriate to pass to socket methods such as TCPSocket.open. + # If unwrapped host names are required, use the #hostname method. # - # URI("http://[::1]/bar/baz").host #=> "[::1]" + # URI("http://[::1]/bar/baz").host #=> "[::1]" # URI("http://[::1]/bar/baz").hostname #=> "::1" # attr_reader :host - # returns the port component of the URI. - # - # URI("http://foo/bar/baz").port #=> "80" + # Returns the port component of the URI. # - # URI("http://foo:8080/bar/baz").port #=> "8080" + # URI("http://foo/bar/baz").port #=> 80 + # URI("http://foo:8080/bar/baz").port #=> 8080 # attr_reader :port @@ -253,37 +253,38 @@ module URI nil end - # returns the path component of the URI. + # Returns the path component of the URI. # # URI("http://foo/bar/baz").path #=> "/bar/baz" # attr_reader :path - # returns the query component of the URI. + # Returns the query component of the URI. # # URI("http://foo/bar/baz?search=FooBar").query #=> "search=FooBar" # attr_reader :query - # returns the opaque part of the URI. + # Returns the opaque part of the URI. # # URI("mailto:foo@example.org").opaque #=> "foo@example.org" + # URI("http://foo/bar/baz").opaque #=> nil # - # Portion of the path that does make use of the slash '/'. - # The path typically refers to the absolute path and the opaque part. - # (see RFC2396 Section 3 and 5.2) + # The portion of the path that does not make use of the slash '/'. + # The path typically refers to an absolute path or an opaque part. + # (See RFC2396 Section 3 and 5.2.) # attr_reader :opaque - # returns the fragment component of the URI. + # Returns the fragment component of the URI. # # URI("http://foo/bar/baz?search=FooBar#ponies").fragment #=> "ponies" # attr_reader :fragment - # returns the parser to be used. + # Returns the parser to be used. # - # Unless a URI::Parser is defined, then DEFAULT_PARSER is used. + # Unless the +parser+ is defined, DEFAULT_PARSER is used. # def parser if !defined?(@parser) || !@parser @@ -293,7 +294,8 @@ module URI end end - # replace self by other URI object + # Replaces self by other URI object. + # def replace!(oth) if self.class != oth.class raise ArgumentError, "expected #{self.class} object" @@ -313,7 +315,7 @@ module URI end # - # check the scheme +v+ component against the URI::Parser Regexp for :SCHEME + # Checks the scheme +v+ component against the +parser+ Regexp for :SCHEME. # def check_scheme(v) if v && parser.regexp[:SCHEME] !~ v @@ -325,9 +327,9 @@ module URI end private :check_scheme - # protected setter for the scheme component +v+ + # Protected setter for the scheme component +v+. # - # see also URI::Generic.scheme= + # See also URI::Generic.scheme=. # def set_scheme(v) @scheme = v&.downcase @@ -342,10 +344,10 @@ module URI # # == Description # - # public setter for the scheme component +v+. - # (with validation) + # Public setter for the scheme component +v+ + # (with validation). # - # see also URI::Generic.check_scheme + # See also URI::Generic.check_scheme. # # == Usage # @@ -353,9 +355,7 @@ module URI # # uri = URI.parse("http://my.example.com") # uri.scheme = "https" - # # => "https" - # uri - # #=> #<URI::HTTP:0x000000008e89e8 URL:https://my.example.com> + # uri.to_s #=> "https://my.example.com" # def scheme=(v) check_scheme(v) @@ -364,13 +364,13 @@ module URI end # - # check the +user+ and +password+. + # Checks the +user+ and +password+. # # If +password+ is not provided, then +user+ is # split, using URI::Generic.split_userinfo, to # pull +user+ and +password. # - # see also URI::Generic.check_user, URI::Generic.check_password + # See also URI::Generic.check_user, URI::Generic.check_password. # def check_userinfo(user, password = nil) if !password @@ -384,8 +384,8 @@ module URI private :check_userinfo # - # check the user +v+ component for RFC2396 compliance - # and against the URI::Parser Regexp for :USERINFO + # Checks the user +v+ component for RFC2396 compliance + # and against the +parser+ Regexp for :USERINFO. # # Can not have a registry or opaque component defined, # with a user component defined. @@ -393,7 +393,7 @@ module URI def check_user(v) if @opaque raise InvalidURIError, - "can not set user with opaque" + "cannot set user with opaque" end return v unless v @@ -408,8 +408,8 @@ module URI private :check_user # - # check the password +v+ component for RFC2396 compliance - # and against the URI::Parser Regexp for :USERINFO + # Checks the password +v+ component for RFC2396 compliance + # and against the +parser+ Regexp for :USERINFO. # # Can not have a registry or opaque component defined, # with a user component defined. @@ -417,7 +417,7 @@ module URI def check_password(v, user = @user) if @opaque raise InvalidURIError, - "can not set password with opaque" + "cannot set password with opaque" end return v unless v @@ -436,7 +436,7 @@ module URI private :check_password # - # Sets userinfo, argument is string like 'name:pass' + # Sets userinfo, argument is string like 'name:pass'. # def userinfo=(userinfo) if userinfo.nil? @@ -455,10 +455,10 @@ module URI # # == Description # - # public setter for the +user+ component. - # (with validation) + # Public setter for the +user+ component + # (with validation). # - # see also URI::Generic.check_user + # See also URI::Generic.check_user. # # == Usage # @@ -466,9 +466,7 @@ module URI # # uri = URI.parse("http://john:S3nsit1ve@my.example.com") # uri.user = "sam" - # # => "sam" - # uri - # #=> #<URI::HTTP:0x00000000881d90 URL:http://sam:V3ry_S3nsit1ve@my.example.com> + # uri.to_s #=> "http://sam@my.example.com" # def user=(user) check_user(user) @@ -484,10 +482,10 @@ module URI # # == Description # - # public setter for the +password+ component. - # (with validation) + # Public setter for the +password+ component + # (with validation). # - # see also URI::Generic.check_password + # See also URI::Generic.check_password. # # == Usage # @@ -495,9 +493,7 @@ module URI # # uri = URI.parse("http://john:S3nsit1ve@my.example.com") # uri.password = "V3ry_S3nsit1ve" - # # => "V3ry_S3nsit1ve" - # uri - # #=> #<URI::HTTP:0x00000000881d90 URL:http://john:V3ry_S3nsit1ve@my.example.com> + # uri.to_s #=> "http://john:V3ry_S3nsit1ve@my.example.com" # def password=(password) check_password(password) @@ -505,35 +501,35 @@ module URI # returns password end - # protect setter for the +user+ component, and +password+ if available. - # (with validation) + # Protected setter for the +user+ component, and +password+ if available + # (with validation). # - # see also URI::Generic.userinfo= + # See also URI::Generic.userinfo=. # def set_userinfo(user, password = nil) unless password user, password = split_userinfo(user) end @user = user - @password = password if password + @password = password [@user, @password] end protected :set_userinfo - # protected setter for the user component +v+ + # Protected setter for the user component +v+. # - # see also URI::Generic.user= + # See also URI::Generic.user=. # def set_user(v) - set_userinfo(v, @password) + set_userinfo(v, nil) v end protected :set_user - # protected setter for the password component +v+ + # Protected setter for the password component +v+. # - # see also URI::Generic.password= + # See also URI::Generic.password=. # def set_password(v) @password = v @@ -541,8 +537,8 @@ module URI end protected :set_password - # returns the userinfo +ui+ as user, password - # if properly formatted as 'user:password' + # Returns the userinfo +ui+ as <code>[user, password]</code> + # if properly formatted as 'user:password'. def split_userinfo(ui) return nil, nil unless ui user, password = ui.split(':', 2) @@ -551,13 +547,13 @@ module URI end private :split_userinfo - # escapes 'user:password' +v+ based on RFC 1738 section 3.1 + # Escapes 'user:password' +v+ based on RFC 1738 section 3.1. def escape_userpass(v) parser.escape(v, /[@:\/]/o) # RFC 1738 section 3.1 #/ end private :escape_userpass - # returns the userinfo, either as 'user' or 'user:password' + # Returns the userinfo, either as 'user' or 'user:password'. def userinfo if @user.nil? nil @@ -568,19 +564,35 @@ 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 authority info (array of user, password, host and + # port), if any is set. Or returns +nil+. + def authority + return @user, @password, @host, @port if @user || @password || @host || @port + 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 + # - # check the host +v+ component for RFC2396 compliance - # and against the URI::Parser Regexp for :HOST + # Checks the host +v+ component for RFC2396 compliance + # and against the +parser+ Regexp for :HOST. # # Can not have a registry or opaque component defined, # with a host component defined. @@ -590,7 +602,7 @@ module URI if @opaque raise InvalidURIError, - "can not set host with registry or opaque" + "cannot set host with registry or opaque" elsif parser.regexp[:HOST] !~ v raise InvalidComponentError, "bad component(expected host component): #{v}" @@ -600,15 +612,22 @@ module URI end private :check_host - # protected setter for the host component +v+ + # Protected setter for the host component +v+. # - # see also URI::Generic.host= + # See also URI::Generic.host=. # def set_host(v) @host = v end protected :set_host + # Protected setter for the authority info (+user+, +password+, +host+ + # and +port+). If +port+ is +nil+, +default_port+ will be set. + # + protected def set_authority(user, password, host, port = nil) + @user, @password, @host, @port = user, password, host, port || self.default_port + end + # # == Args # @@ -617,10 +636,10 @@ module URI # # == Description # - # public setter for the host component +v+. - # (with validation) + # Public setter for the host component +v+ + # (with validation). # - # see also URI::Generic.check_host + # See also URI::Generic.check_host. # # == Usage # @@ -628,51 +647,49 @@ module URI # # uri = URI.parse("http://my.example.com") # uri.host = "foo.com" - # # => "foo.com" - # uri - # #=> #<URI::HTTP:0x000000008e89e8 URL:http://foo.com> + # uri.to_s #=> "http://foo.com" # def host=(v) check_host(v) set_host(v) + set_userinfo(nil) v end - # extract the host part of the URI and unwrap brackets for IPv6 addresses. + # Extract the host part of the URI and unwrap brackets for IPv6 addresses. # - # This method is same as URI::Generic#host except + # This method is the same as URI::Generic#host except # brackets for IPv6 (and future IP) addresses are removed. # - # u = URI("http://[::1]/bar") - # p u.hostname #=> "::1" - # p u.host #=> "[::1]" + # uri = URI("http://[::1]/bar") + # uri.hostname #=> "::1" + # uri.host #=> "[::1]" # def hostname v = self.host - /\A\[(.*)\]\z/ =~ v ? $1 : v + v&.start_with?('[') && v.end_with?(']') ? v[1..-2] : v end - # set the host part of the URI as the argument with brackets for IPv6 addresses. + # Sets the host part of the URI as the argument with brackets for IPv6 addresses. # - # This method is same as URI::Generic#host= except - # the argument can be bare IPv6 address. + # This method is the same as URI::Generic#host= except + # the argument can be a bare IPv6 address. # - # u = URI("http://foo/bar") - # p u.to_s #=> "http://foo/bar" - # u.hostname = "::1" - # p u.to_s #=> "http://[::1]/bar" + # uri = URI("http://foo/bar") + # uri.hostname = "::1" + # uri.to_s #=> "http://[::1]/bar" # - # If the argument seems IPv6 address, - # it is wrapped by brackets. + # If the argument seems to be an IPv6 address, + # it is wrapped with brackets. # def hostname=(v) - v = "[#{v}]" if /\A\[.*\]\z/ !~ v && /:/ =~ v + v = "[#{v}]" if !(v&.start_with?('[') && v&.end_with?(']')) && v&.index(':') self.host = v end # - # check the port +v+ component for RFC2396 compliance - # and against the URI::Parser Regexp for :PORT + # Checks the port +v+ component for RFC2396 compliance + # and against the +parser+ Regexp for :PORT. # # Can not have a registry or opaque component defined, # with a port component defined. @@ -682,7 +699,7 @@ module URI if @opaque raise InvalidURIError, - "can not set port with registry or opaque" + "cannot set port with registry or opaque" elsif !v.kind_of?(Integer) && parser.regexp[:PORT] !~ v raise InvalidComponentError, "bad component(expected port component): #{v.inspect}" @@ -692,9 +709,9 @@ module URI end private :check_port - # protected setter for the port component +v+ + # Protected setter for the port component +v+. # - # see also URI::Generic.port= + # See also URI::Generic.port=. # def set_port(v) v = v.empty? ? nil : v.to_i unless !v || v.kind_of?(Integer) @@ -710,10 +727,10 @@ module URI # # == Description # - # public setter for the port component +v+. - # (with validation) + # Public setter for the port component +v+ + # (with validation). # - # see also URI::Generic.check_port + # See also URI::Generic.check_port. # # == Usage # @@ -721,34 +738,33 @@ module URI # # uri = URI.parse("http://my.example.com") # uri.port = 8080 - # # => 8080 - # uri - # #=> #<URI::HTTP:0x000000008e89e8 URL:http://my.example.com:8080> + # uri.to_s #=> "http://my.example.com:8080" # def port=(v) check_port(v) set_port(v) + set_userinfo(nil) port end def check_registry(v) # :nodoc: - raise InvalidURIError, "can not set registry" + raise InvalidURIError, "cannot set registry" end private :check_registry - def set_registry(v) #:nodoc: - raise InvalidURIError, "can not set registry" + def set_registry(v) # :nodoc: + raise InvalidURIError, "cannot set registry" end protected :set_registry - def registry=(v) - raise InvalidURIError, "can not set registry" + def registry=(v) # :nodoc: + raise InvalidURIError, "cannot set registry" end # - # check the path +v+ component for RFC2396 compliance - # and against the URI::Parser Regexp - # for :ABS_PATH and :REL_PATH + # Checks the path +v+ component for RFC2396 compliance + # and against the +parser+ Regexp + # for :ABS_PATH and :REL_PATH. # # Can not have a opaque component defined, # with a path component defined. @@ -781,9 +797,9 @@ module URI end private :check_path - # protected setter for the path component +v+ + # Protected setter for the path component +v+. # - # see also URI::Generic.path= + # See also URI::Generic.path=. # def set_path(v) @path = v @@ -798,10 +814,10 @@ module URI # # == Description # - # public setter for the path component +v+. - # (with validation) + # Public setter for the path component +v+ + # (with validation). # - # see also URI::Generic.check_path + # See also URI::Generic.check_path. # # == Usage # @@ -809,9 +825,7 @@ module URI # # uri = URI.parse("http://my.example.com/pub/files") # uri.path = "/faq/" - # # => "/faq/" - # uri - # #=> #<URI::HTTP:0x000000008e89e8 URL:http://my.example.com/faq/> + # uri.to_s #=> "http://my.example.com/faq/" # def path=(v) check_path(v) @@ -827,7 +841,7 @@ module URI # # == Description # - # public setter for the query component +v+. + # Public setter for the query component +v+. # # == Usage # @@ -835,9 +849,7 @@ module URI # # uri = URI.parse("http://my.example.com/?id=25") # uri.query = "id=1" - # # => "id=1" - # uri - # #=> #<URI::HTTP:0x000000008e89e8 URL:http://my.example.com/?id=1> + # uri.to_s #=> "http://my.example.com/?id=1" # def query=(v) return @query = nil unless v @@ -848,16 +860,17 @@ module URI v.encode!(Encoding::UTF_8) rescue nil v.delete!("\t\r\n") v.force_encoding(Encoding::ASCII_8BIT) + raise InvalidURIError, "invalid percent escape: #{$1}" if /(%\H\H)/n.match(v) v.gsub!(/(?!%\h\h|[!$-&(-;=?-_a-~])./n.freeze){'%%%02X' % $&.ord} v.force_encoding(Encoding::US_ASCII) @query = v end # - # check the opaque +v+ component for RFC2396 compliance and - # against the URI::Parser Regexp for :OPAQUE + # Checks the opaque +v+ component for RFC2396 compliance and + # against the +parser+ Regexp for :OPAQUE. # - # Can not have a host, port, user or path component defined, + # Can not have a host, port, user, or path component defined, # with an opaque component defined. # def check_opaque(v) @@ -868,7 +881,7 @@ module URI # hier_part = ( net_path | abs_path ) [ "?" query ] if @host || @port || @user || @path # userinfo = @user + ':' + @password raise InvalidURIError, - "can not set opaque with host, port, userinfo or path" + "cannot set opaque with host, port, userinfo or path" elsif v && parser.regexp[:OPAQUE] !~ v raise InvalidComponentError, "bad component(expected opaque component): #{v}" @@ -878,9 +891,9 @@ module URI end private :check_opaque - # protected setter for the opaque component +v+ + # Protected setter for the opaque component +v+. # - # see also URI::Generic.opaque= + # See also URI::Generic.opaque=. # def set_opaque(v) @opaque = v @@ -895,10 +908,10 @@ module URI # # == Description # - # public setter for the opaque component +v+. - # (with validation) + # Public setter for the opaque component +v+ + # (with validation). # - # see also URI::Generic.check_opaque + # See also URI::Generic.check_opaque. # def opaque=(v) check_opaque(v) @@ -907,7 +920,7 @@ module URI end # - # check the fragment +v+ component against the URI::Parser Regexp for :FRAGMENT + # Checks the fragment +v+ component against the +parser+ Regexp for :FRAGMENT. # # # == Args @@ -917,8 +930,8 @@ module URI # # == Description # - # public setter for the fragment component +v+. - # (with validation) + # Public setter for the fragment component +v+ + # (with validation). # # == Usage # @@ -926,9 +939,7 @@ module URI # # uri = URI.parse("http://my.example.com/?id=25#time=1305212049") # uri.fragment = "time=1305212086" - # # => "time=1305212086" - # uri - # #=> #<URI::HTTP:0x000000007a81f8 URL:http://my.example.com/?id=25#time=1305212086> + # uri.to_s #=> "http://my.example.com/?id=25#time=1305212086" # def fragment=(v) return @fragment = nil unless v @@ -944,7 +955,23 @@ module URI end # - # Checks if URI has a path + # Returns true if URI is hierarchical. + # + # == Description + # + # URI has components listed in order of decreasing significance from left to right, + # see RFC3986 https://www.rfc-editor.org/rfc/rfc3986 1.2.3. + # + # == Usage + # + # require 'uri' + # + # uri = URI.parse("http://my.example.com/") + # uri.hierarchical? + # #=> true + # uri = URI.parse("mailto:joe@example.com") + # uri.hierarchical? + # #=> false # def hierarchical? if @path @@ -955,7 +982,7 @@ module URI end # - # Checks if URI is an absolute one + # Returns true if URI has a scheme (e.g. http:// or https://) specified. # def absolute? if @scheme @@ -967,17 +994,17 @@ module URI alias absolute absolute? # - # Checks if URI is relative + # Returns true if URI does not have a scheme (e.g. http:// or https://) specified. # def relative? !absolute? end # - # returns an Array of the path split on '/' + # Returns an Array of the path split on '/'. # def split_path(path) - path.split(%r{/+}, -1) + path.split("/", -1) end private :split_path @@ -1056,7 +1083,7 @@ module URI # # == Description # - # Destructive form of #merge + # Destructive form of #merge. # # == Usage # @@ -1064,8 +1091,7 @@ module URI # # uri = URI.parse("http://my.example.com") # uri.merge!("/main.rbx?page=1") - # p uri - # # => #<URI::HTTP:0x2021f3b0 URL:http://my.example.com/main.rbx?page=1> + # uri.to_s # => "http://my.example.com/main.rbx?page=1" # def merge!(oth) t = merge(oth) @@ -1085,18 +1111,18 @@ module URI # # == Description # - # Merges two URI's. + # Merges two URIs. # # == Usage # # require 'uri' # # uri = URI.parse("http://my.example.com") - # p uri.merge("/main.rbx?page=1") - # # => #<URI::HTTP:0x2021f3b0 URL:http://my.example.com/main.rbx?page=1> + # uri.merge("/main.rbx?page=1") + # # => "http://my.example.com/main.rbx?page=1" # def merge(oth) - rel = parser.send(:convert_to_uri, oth) + rel = parser.__send__(:convert_to_uri, oth) if rel.absolute? #raise BadURIError, "both URI are absolute" if absolute? @@ -1110,7 +1136,7 @@ module URI base = self.dup - authority = rel.userinfo || rel.host || rel.port + authority = rel.authority # RFC2396, Section 5.2, 2) if (rel.path.nil? || rel.path.empty?) && !authority && !rel.query @@ -1122,17 +1148,14 @@ module URI base.fragment=(nil) # RFC2396, Section 5.2, 4) - if !authority - base.set_path(merge_path(base.path, rel.path)) if base.path && rel.path - else - # RFC2396, Section 5.2, 4) - base.set_path(rel.path) if rel.path + if authority + base.set_authority(*authority) + base.set_path(rel.path) + elsif base.path && rel.path + base.set_path(merge_path(base.path, rel.path)) end # RFC2396, Section 5.2, 7) - base.set_userinfo(rel.userinfo) if rel.userinfo - base.set_host(rel.host) if rel.host - base.set_port(rel.port) if rel.port base.query = rel.query if rel.query base.fragment=(rel.fragment) if rel.fragment @@ -1152,8 +1175,8 @@ module URI return dst.dup end - src_path = src.scan(%r{(?:\A|[^/]+)/}) - dst_path = dst.scan(%r{(?:\A|[^/]+)/?}) + src_path = src.scan(%r{[^/]*/}) + dst_path = dst.scan(%r{[^/]*/?}) # discard same parts while !dst_path.empty? && dst_path.first == src_path.first @@ -1181,7 +1204,7 @@ module URI # :stopdoc: def route_from0(oth) - oth = parser.send(:convert_to_uri, oth) + oth = parser.__send__(:convert_to_uri, oth) if self.relative? raise BadURIError, "relative URI: #{self}" @@ -1224,7 +1247,7 @@ module URI return rel, rel end - # you can modify `rel', but can not `oth'. + # you can modify `rel', but cannot `oth'. return oth, rel end private :route_from0 @@ -1238,18 +1261,18 @@ module URI # # == Description # - # Calculates relative path from oth to self + # Calculates relative path from oth to self. # # == Usage # # require 'uri' # # uri = URI.parse('http://my.example.com/main.rbx?page=1') - # p uri.route_from('http://my.example.com') - # #=> #<URI::Generic:0x20218858 URL:/main.rbx?page=1> + # uri.route_from('http://my.example.com') + # #=> #<URI::Generic /main.rbx?page=1> # def route_from(oth) - # you can modify `rel', but can not `oth'. + # you can modify `rel', but cannot `oth'. begin oth, rel = route_from0(oth) rescue @@ -1278,22 +1301,32 @@ module URI # # == Description # - # Calculates relative path to oth from self + # Calculates relative path to oth from self. # # == Usage # # require 'uri' # # uri = URI.parse('http://my.example.com') - # p uri.route_to('http://my.example.com/main.rbx?page=1') - # #=> #<URI::Generic:0x2020c2f6 URL:/main.rbx?page=1> + # uri.route_to('http://my.example.com/main.rbx?page=1') + # #=> #<URI::Generic /main.rbx?page=1> # def route_to(oth) - parser.send(:convert_to_uri, oth).route_from(self) + parser.__send__(:convert_to_uri, oth).route_from(self) end # - # Returns normalized URI + # Returns normalized URI. + # + # require 'uri' + # + # URI("HTTP://my.EXAMPLE.com").normalize + # #=> #<URI::HTTP http://my.example.com/> + # + # Normalization here means: + # + # * scheme and host are converted to lowercase, + # * an empty path component is set to "/". # def normalize uri = dup @@ -1302,7 +1335,7 @@ module URI end # - # Destructive version of #normalize + # Destructive version of #normalize. # def normalize! if path&.empty? @@ -1317,7 +1350,7 @@ module URI end # - # Constructs String from URI + # Constructs String from URI. # def to_s str = ''.dup @@ -1329,7 +1362,7 @@ module URI if @opaque str << @opaque else - if @host + if @host || %w[file postgres].include?(@scheme) str << '//' end if self.userinfo @@ -1343,6 +1376,9 @@ module URI str << ':' str << @port.to_s end + if (@host || @port) && !@path.empty? && !@path.start_with?('/') + str << '/' + end str << @path if @query str << '?' @@ -1355,9 +1391,10 @@ module URI end str end + alias to_str to_s # - # Compares to URI's + # Compares two URIs. # def ==(oth) if self.class == oth.class @@ -1367,33 +1404,22 @@ module URI end end + # Returns the hash value. def hash self.component_ary.hash end + # Compares with _oth_ for Hash. def eql?(oth) self.class == oth.class && parser == oth.parser && 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 + # Returns an Array of the components defined from the COMPONENT Array. def component_ary component.collect do |x| - self.send(x) + self.__send__(x) end end protected :component_ary @@ -1401,24 +1427,24 @@ module URI # == Args # # +components+:: - # Multiple Symbol arguments defined in URI::HTTP + # Multiple Symbol arguments defined in URI::HTTP. # # == Description # - # Selects specified components from URI + # Selects specified components from URI. # # == Usage # # require 'uri' # # uri = URI.parse('http://myuser:mypass@my.example.com/test.rbx') - # p uri.select(:userinfo, :host, :path) + # uri.select(:userinfo, :host, :path) # # => ["myuser:mypass", "my.example.com", "/test.rbx"] # def select(*components) components.collect do |c| if component.include?(c) - self.send(c) + self.__send__(c) else raise ArgumentError, "expected of components of #{self.class} (#{self.class.component.join(', ')})" @@ -1426,7 +1452,7 @@ module URI end end - def inspect + def inspect # :nodoc: "#<#{self.class} #{self}>" end @@ -1438,8 +1464,8 @@ module URI # # == Description # - # attempt to parse other URI +oth+ - # return [parsed_oth, self] + # Attempts to parse other URI +oth+, + # returns [parsed_oth, self]. # # == Usage # @@ -1447,7 +1473,7 @@ module URI # # uri = URI.parse("http://my.example.com") # uri.coerce("http://foo.com") - # #=> [#<URI::HTTP:0x00000000bcb028 URL:http://foo.com/>, #<URI::HTTP:0x00000000d92178 URL:http://my.example.com>] + # #=> [#<URI::HTTP http://foo.com>, #<URI::HTTP http://my.example.com>] # def coerce(oth) case oth @@ -1460,15 +1486,15 @@ module URI return oth, self end - # returns a proxy URI. + # Returns a proxy URI. # The proxy URI is obtained from environment variables such as http_proxy, # ftp_proxy, no_proxy, etc. # If there is no proper proxy, nil is returned. # - # If the optional parameter, +env+, is specified, it is used instead of ENV. + # If the optional parameter +env+ is specified, it is used instead of ENV. # # Note that capitalized variables (HTTP_PROXY, FTP_PROXY, NO_PROXY, etc.) - # are examined too. + # are examined, too. # # But http_proxy and HTTP_PROXY is treated specially under CGI environment. # It's because HTTP_PROXY may be set by Proxy: header. @@ -1503,9 +1529,19 @@ module URI proxy_uri = env["CGI_#{name.upcase}"] end elsif name == 'http_proxy' - unless proxy_uri = env[name] - if proxy_uri = env[name.upcase] - warn 'The environment variable HTTP_PROXY is discouraged. Use http_proxy.' + if RUBY_ENGINE == 'jruby' && p_addr = ENV_JAVA['http.proxyHost'] + p_port = ENV_JAVA['http.proxyPort'] + if p_user = ENV_JAVA['http.proxyUser'] + p_pass = ENV_JAVA['http.proxyPass'] + proxy_uri = "http://#{p_user}:#{p_pass}@#{p_addr}:#{p_port}" + else + proxy_uri = "http://#{p_addr}:#{p_port}" + end + else + unless proxy_uri = env[name] + if proxy_uri = env[name.upcase] + warn 'The environment variable HTTP_PROXY is discouraged. Please use http_proxy instead.', uplevel: 1 + end end end else @@ -1517,7 +1553,6 @@ module URI end if self.hostname - require 'socket' begin addr = IPSocket.getaddress(self.hostname) return nil if /\A127\.|\A::1\z/ =~ addr @@ -1527,23 +1562,31 @@ module URI name = 'no_proxy' if no_proxy = env[name] || env[name.upcase] - no_proxy.scan(/(?!\.)([^:,\s]+)(?::(\d+))?/) {|host, port| - if (!port || self.port == port.to_i) - if /(\A|\.)#{Regexp.quote host}\z/i =~ self.host - return nil - elsif addr - require 'ipaddr' - return nil if - begin - IPAddr.new(host) - rescue IPAddr::InvalidAddressError - next - end.include?(addr) - end - end - } + return nil unless URI::Generic.use_proxy?(self.hostname, addr, self.port, no_proxy) end URI.parse(proxy_uri) end + + def self.use_proxy?(hostname, addr, port, no_proxy) # :nodoc: + hostname = hostname.downcase + dothostname = ".#{hostname}" + no_proxy.scan(/([^:,\s]+)(?::(\d+))?/) {|p_host, p_port| + if !p_port || port == p_port.to_i + if p_host.start_with?('.') + return false if hostname.end_with?(p_host.downcase) + else + return false if dothostname.end_with?(".#{p_host.downcase}") + end + if addr + begin + return false if IPAddr.new(p_host).include?(addr) + rescue IPAddr::InvalidAddressError + next + end + end + end + } + true + end end end diff --git a/lib/uri/http.rb b/lib/uri/http.rb index d4373e73e5..3c41cd4e93 100644 --- a/lib/uri/http.rb +++ b/lib/uri/http.rb @@ -3,12 +3,11 @@ # # Author:: Akira Yamada <akira@ruby-lang.org> # License:: You can redistribute it and/or modify it under the same term as Ruby. -# Revision:: $Id$ # # See URI for general documentation # -require 'uri/generic' +require_relative 'generic' module URI @@ -21,10 +20,10 @@ module URI # update. See <URL:http://support.microsoft.com/kb/834489>. # class HTTP < Generic - # A Default port of 80 for URI::HTTP + # A Default port of 80 for URI::HTTP. DEFAULT_PORT = 80 - # An Array of the available components for URI::HTTP + # An Array of the available components for URI::HTTP. COMPONENT = %i[ scheme userinfo host port @@ -36,22 +35,22 @@ module URI # # == Description # - # Create a new URI::HTTP object from components, with syntax checking. + # Creates a new URI::HTTP object from components, with syntax checking. # - # The components accepted are userinfo, host, port, path, query and + # The components accepted are userinfo, host, port, path, query, and # fragment. # # The components should be provided either as an Array, or as a Hash # with keys formed by preceding the component names with a colon. # - # If an Array is used, the components must be passed in the order - # [userinfo, host, port, path, query, fragment]. + # If an Array is used, the components must be passed in the + # order <code>[userinfo, host, port, path, query, fragment]</code>. # # Example: # - # newuri = URI::HTTP.build(host: 'www.example.com', path: '/foo/bar') + # uri = URI::HTTP.build(host: 'www.example.com', path: '/foo/bar') # - # newuri = URI::HTTP.build([nil, "www.example.com", nil, "/path", + # uri = URI::HTTP.build([nil, "www.example.com", nil, "/path", # "query", 'fragment']) # # Currently, if passed userinfo components this method generates @@ -62,51 +61,77 @@ module URI super(tmp) end -=begin + # Do not allow empty host names, as they are not allowed by RFC 3986. + def check_host(v) + ret = super + + if ret && v.empty? + raise InvalidComponentError, + "bad component(expected host component): #{v}" + end + + ret + end + # # == Description # - # Create a new URI::HTTP object from generic URI components as per - # RFC 2396. No HTTP-specific syntax checking (as per RFC 1738) is - # performed. + # Returns the full path for an HTTP request, as required by Net::HTTP::Get. # - # Arguments are +scheme+, +userinfo+, +host+, +port+, +registry+, +path+, - # +opaque+, +query+ and +fragment+, in that order. + # If the URI contains a query, the full path is URI#path + '?' + URI#query. + # Otherwise, the path is simply URI#path. # # Example: # - # uri = URI::HTTP.new("http", nil, "www.example.com", nil, nil, - # "/path", nil, "query", "fragment") + # uri = URI::HTTP.build(path: '/foo/bar', query: 'test=true') + # uri.request_uri # => "/foo/bar?test=true" # + def request_uri + return unless @path + + url = @query ? "#@path?#@query" : @path.dup + url.start_with?(?/.freeze) ? url : ?/ + url + end + # - # See also URI::Generic.new + # == Description # - def initialize(*arg) - super(*arg) + # 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 -=end # # == Description # - # Returns the full path for an HTTP request, as required by Net::HTTP::Get. + # Returns the origin for an HTTP uri, as defined in + # https://www.rfc-editor.org/rfc/rfc6454. # - # If the URI contains a query, the full path is URI#path + '?' + URI#query. - # Otherwise, the path is simply URI#path. # # Example: # - # newuri = URI::HTTP.build(path: '/foo/bar', query: 'test=true') - # newuri.request_uri # => "/foo/bar?test=true" + # 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 request_uri - return unless @path - - url = @query ? "#@path?#@query" : @path.dup - url.start_with?(?/.freeze) ? url : ?/ + url + def origin + "#{scheme}://#{authority}" end end - @@schemes['HTTP'] = HTTP - + register_scheme 'HTTP', HTTP end diff --git a/lib/uri/https.rb b/lib/uri/https.rb index 3c8c905cc3..50a5cabaf8 100644 --- a/lib/uri/https.rb +++ b/lib/uri/https.rb @@ -3,12 +3,11 @@ # # Author:: Akira Yamada <akira@ruby-lang.org> # License:: You can redistribute it and/or modify it under the same term as Ruby. -# Revision:: $Id$ # # See URI for general documentation # -require 'uri/http' +require_relative 'http' module URI @@ -19,5 +18,6 @@ module URI # A Default port of 443 for URI::HTTPS DEFAULT_PORT = 443 end - @@schemes['HTTPS'] = HTTPS + + register_scheme 'HTTPS', HTTPS end diff --git a/lib/uri/ldap.rb b/lib/uri/ldap.rb index 4345875e28..4544349f18 100644 --- a/lib/uri/ldap.rb +++ b/lib/uri/ldap.rb @@ -7,25 +7,25 @@ # License:: # URI::LDAP is copyrighted free software by Takaaki Tateishi and Akira Yamada. # You can redistribute it and/or modify it under the same term as Ruby. -# Revision:: $Id$ # # See URI for general documentation # -require 'uri/generic' +require_relative 'generic' module URI # - # LDAP URI SCHEMA (described in RFC2255) + # LDAP URI SCHEMA (described in RFC2255). + #-- # ldap://<host>/<dn>[?<attrs>[?<scope>[?<filter>[?<extensions>]]]] - # + #++ class LDAP < Generic - # A Default port of 389 for URI::LDAP + # A Default port of 389 for URI::LDAP. DEFAULT_PORT = 389 - # An Array of the available components for URI::LDAP + # An Array of the available components for URI::LDAP. COMPONENT = [ :scheme, :host, :port, @@ -40,8 +40,8 @@ module URI # # * SCOPE_BASE - the Base DN # * SCOPE_ONE - one level under the Base DN, not including the base DN and - # not including any entries under this. - # * SCOPE_SUB - subtress, all entries at all levels + # not including any entries under this + # * SCOPE_SUB - subtrees, all entries at all levels # SCOPE = [ SCOPE_ONE = 'one', @@ -52,7 +52,7 @@ module URI # # == Description # - # Create a new URI::LDAP object from components, with syntax checking. + # Creates a new URI::LDAP object from components, with syntax checking. # # The components accepted are host, port, dn, attributes, # scope, filter, and extensions. @@ -60,15 +60,15 @@ module URI # The components should be provided either as an Array, or as a Hash # with keys formed by preceding the component names with a colon. # - # If an Array is used, the components must be passed in the order - # [host, port, dn, attributes, scope, filter, extensions]. + # If an Array is used, the components must be passed in the + # order <code>[host, port, dn, attributes, scope, filter, extensions]</code>. # # Example: # - # newuri = URI::LDAP.build({:host => 'ldap.example.com', - # :dn> => '/dc=example'}) + # uri = URI::LDAP.build({:host => 'ldap.example.com', + # :dn => '/dc=example'}) # - # newuri = URI::LDAP.build(["ldap.example.com", nil, + # uri = URI::LDAP.build(["ldap.example.com", nil, # "/dc=example;dc=com", "query", nil, nil, nil]) # def self.build(args) @@ -92,19 +92,18 @@ module URI # # == Description # - # Create a new URI::LDAP object from generic URI components as per + # Creates a new URI::LDAP object from generic URI components as per # RFC 2396. No LDAP-specific syntax checking is performed. # # Arguments are +scheme+, +userinfo+, +host+, +port+, +registry+, +path+, - # +opaque+, +query+ and +fragment+, in that order. + # +opaque+, +query+, and +fragment+, in that order. # # Example: # - # uri = URI::LDAP.new("ldap", nil, "ldap.example.com", nil, - # "/dc=example;dc=com", "query", nil, nil, nil, nil) - # + # uri = URI::LDAP.new("ldap", nil, "ldap.example.com", nil, nil, + # "/dc=example;dc=com", nil, "query", nil) # - # See also URI::Generic.new + # See also URI::Generic.new. # def initialize(*arg) super(*arg) @@ -117,14 +116,15 @@ module URI parse_query end - # private method to cleanup +dn+ from using the +path+ component attribute + # Private method to cleanup +dn+ from using the +path+ component attribute. def parse_dn + raise InvalidURIError, 'bad LDAP URL' unless @path @dn = @path[1..-1] end private :parse_dn - # private method to cleanup +attributes+, +scope+, +filter+ and +extensions+, - # from using the +query+ component attribute + # Private method to cleanup +attributes+, +scope+, +filter+, and +extensions+ + # from using the +query+ component attribute. def parse_query @attributes = nil @scope = nil @@ -142,7 +142,7 @@ module URI end private :parse_query - # private method to assemble +query+ from +attributes+, +scope+, +filter+ and +extensions+. + # Private method to assemble +query+ from +attributes+, +scope+, +filter+, and +extensions+. def build_path_query @path = '/' + @dn @@ -155,12 +155,12 @@ module URI end private :build_path_query - # returns dn. + # Returns dn. def dn @dn end - # private setter for dn +val+ + # Private setter for dn +val+. def set_dn(val) @dn = val build_path_query @@ -168,18 +168,18 @@ module URI end protected :set_dn - # setter for dn +val+ + # Setter for dn +val+. def dn=(val) set_dn(val) val end - # returns attributes. + # Returns attributes. def attributes @attributes end - # private setter for attributes +val+ + # Private setter for attributes +val+. def set_attributes(val) @attributes = val build_path_query @@ -187,18 +187,18 @@ module URI end protected :set_attributes - # setter for attributes +val+ + # Setter for attributes +val+. def attributes=(val) set_attributes(val) val end - # returns scope. + # Returns scope. def scope @scope end - # private setter for scope +val+ + # Private setter for scope +val+. def set_scope(val) @scope = val build_path_query @@ -206,18 +206,18 @@ module URI end protected :set_scope - # setter for scope +val+ + # Setter for scope +val+. def scope=(val) set_scope(val) val end - # returns filter. + # Returns filter. def filter @filter end - # private setter for filter +val+ + # Private setter for filter +val+. def set_filter(val) @filter = val build_path_query @@ -225,18 +225,18 @@ module URI end protected :set_filter - # setter for filter +val+ + # Setter for filter +val+. def filter=(val) set_filter(val) val end - # returns extensions. + # Returns extensions. def extensions @extensions end - # private setter for extensions +val+ + # Private setter for extensions +val+. def set_extensions(val) @extensions = val build_path_query @@ -244,18 +244,18 @@ module URI end protected :set_extensions - # setter for extensions +val+ + # Setter for extensions +val+. def extensions=(val) set_extensions(val) val end - # Checks if URI has a path - # For URI::LDAP this will return +false+ + # Checks if URI has a path. + # For URI::LDAP this will return +false+. def hierarchical? false end end - @@schemes['LDAP'] = LDAP + register_scheme 'LDAP', LDAP end diff --git a/lib/uri/ldaps.rb b/lib/uri/ldaps.rb index d03f8efa2d..58228f5894 100644 --- a/lib/uri/ldaps.rb +++ b/lib/uri/ldaps.rb @@ -6,7 +6,7 @@ # See URI for general documentation # -require 'uri/ldap' +require_relative 'ldap' module URI @@ -17,5 +17,6 @@ module URI # A Default port of 636 for URI::LDAPS DEFAULT_PORT = 636 end - @@schemes['LDAPS'] = LDAPS + + register_scheme 'LDAPS', LDAPS end diff --git a/lib/uri/mailto.rb b/lib/uri/mailto.rb index 1494c3952b..cb8024f301 100644 --- a/lib/uri/mailto.rb +++ b/lib/uri/mailto.rb @@ -3,25 +3,24 @@ # # Author:: Akira Yamada <akira@ruby-lang.org> # License:: You can redistribute it and/or modify it under the same term as Ruby. -# Revision:: $Id$ # # See URI for general documentation # -require 'uri/generic' +require_relative 'generic' module URI # - # RFC6068, The mailto URL scheme + # RFC6068, the mailto URL scheme. # class MailTo < Generic - include REGEXP + include RFC2396_REGEXP - # A Default port of nil for URI::MailTo + # A Default port of nil for URI::MailTo. DEFAULT_PORT = nil - # An Array of the available components for URI::MailTo + # An Array of the available components for URI::MailTo. COMPONENT = [ :scheme, :to, :headers ].freeze # :stopdoc: @@ -52,7 +51,7 @@ module URI # pct-encoded = "%" HEXDIG HEXDIG HEADER_REGEXP = /\A(?<hfield>(?:%\h\h|[!$'-.0-;@-Z_a-z~])*=(?:%\h\h|[!$'-.0-;@-Z_a-z~])*)(?:&\g<hfield>)*\z/ # practical regexp for email address - # http://www.whatwg.org/specs/web-apps/current-work/multipage/states-of-the-type-attribute.html#valid-e-mail-address + # https://html.spec.whatwg.org/multipage/input.html#valid-e-mail-address EMAIL_REGEXP = /\A[a-zA-Z0-9.!\#$%&'*+\/=?^_`{|}~-]+@[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(?:\.[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*\z/ # :startdoc: @@ -62,26 +61,26 @@ module URI # Creates a new URI::MailTo object from components, with syntax checking. # # Components can be provided as an Array or Hash. If an Array is used, - # the components must be supplied as [to, headers]. + # the components must be supplied as <code>[to, headers]</code>. # # If a Hash is used, the keys are the component names preceded by colons. # # The headers can be supplied as a pre-encoded string, such as - # "subject=subscribe&cc=address", or as an Array of Arrays like - # [['subject', 'subscribe'], ['cc', 'address']] + # <code>"subject=subscribe&cc=address"</code>, or as an Array of Arrays + # like <code>[['subject', 'subscribe'], ['cc', 'address']]</code>. # # Examples: # # require 'uri' # # m1 = URI::MailTo.build(['joe@example.com', 'subject=Ruby']) - # puts m1.to_s -> mailto:joe@example.com?subject=Ruby + # m1.to_s # => "mailto:joe@example.com?subject=Ruby" # # m2 = URI::MailTo.build(['john@example.com', [['Subject', 'Ruby'], ['Cc', 'jack@example.com']]]) - # puts m2.to_s -> mailto:john@example.com?Subject=Ruby&Cc=jack@example.com + # m2.to_s # => "mailto:john@example.com?Subject=Ruby&Cc=jack@example.com" # # m3 = URI::MailTo.build({:to => 'listman@example.com', :headers => [['subject', 'subscribe']]}) - # puts m3.to_s -> mailto:listman@example.com?subject=subscribe + # m3.to_s # => "mailto:listman@example.com?subject=subscribe" # def self.build(args) tmp = Util.make_components_hash(self, args) @@ -160,13 +159,13 @@ module URI end end - # The primary e-mail address of the URL, as a String + # The primary e-mail address of the URL, as a String. attr_reader :to - # E-mail headers set by the URL, as an Array of Arrays + # E-mail headers set by the URL, as an Array of Arrays. attr_reader :headers - # check the to +v+ component + # Checks the to +v+ component. def check_to(v) return true unless v return true if v.size == 0 @@ -191,20 +190,20 @@ module URI end private :check_to - # private setter for to +v+ + # Private setter for to +v+. def set_to(v) @to = v end protected :set_to - # setter for to +v+ + # Setter for to +v+. def to=(v) check_to(v) set_to(v) v end - # check the headers +v+ component against either + # Checks the headers +v+ component against either # * HEADER_REGEXP def check_headers(v) return true unless v @@ -218,7 +217,7 @@ module URI end private :check_headers - # private setter for headers +v+ + # Private setter for headers +v+. def set_headers(v) @headers = [] if v @@ -229,14 +228,14 @@ module URI end protected :set_headers - # setter for headers +v+ + # Setter for headers +v+. def headers=(v) check_headers(v) set_headers(v) v end - # Constructs String from URI + # Constructs String from URI. def to_s @scheme + ':' + if @to @@ -290,5 +289,5 @@ module URI alias to_rfc822text to_mailtext end - @@schemes['MAILTO'] = MailTo + register_scheme 'MAILTO', MailTo end diff --git a/lib/uri/rfc2396_parser.rb b/lib/uri/rfc2396_parser.rb index b9e7b2b26e..cefd126cc6 100644 --- a/lib/uri/rfc2396_parser.rb +++ b/lib/uri/rfc2396_parser.rb @@ -3,7 +3,6 @@ # = uri/common.rb # # Author:: Akira Yamada <akira@ruby-lang.org> -# Revision:: $Id$ # License:: # You can redistribute it and/or modify it under the same term as Ruby. # @@ -58,7 +57,7 @@ module URI # :startdoc: end # REGEXP - # class that Parses String's into URI's + # Class that parses String's into URI's. # # It contains a Hash set of patterns and Regexp's that match and validate. # @@ -68,7 +67,7 @@ module URI # # == Synopsis # - # URI::Parser.new([opts]) + # URI::RFC2396_Parser.new([opts]) # # == Args # @@ -87,13 +86,13 @@ module URI # # == 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> + # p = URI::RFC2396_Parser.new(:ESCAPED => "(?:%[a-fA-F0-9]{2}|%u[a-fA-F0-9]{4})") + # u = p.parse("http://example.jp/%uABCD") #=> #<URI::HTTP 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 = p.parse(s) #=> #<URI::HTTP http://example.com/ABCD> + # u2 = URI.parse(s) #=> #<URI::HTTP http://example.com/ABCD> # u1 == u2 #=> true # u1.eql?(u2) #=> false # @@ -109,15 +108,15 @@ module URI # The Hash of patterns. # - # see also URI::Parser.initialize_pattern + # See also #initialize_pattern. attr_reader :pattern - # The Hash of Regexp + # The Hash of Regexp. # - # see also URI::Parser.initialize_regexp + # See also #initialize_regexp. attr_reader :regexp - # Returns a split URI against regexp[:ABS_URI] + # Returns a split URI against +regexp[:ABS_URI]+. def split(uri) case uri when '' @@ -141,11 +140,11 @@ module URI if !scheme raise InvalidURIError, - "bad URI(absolute but no scheme): #{uri}" + "bad URI (absolute but no scheme): #{uri}" end if !opaque && (!path && (!host && !registry)) raise InvalidURIError, - "bad URI(absolute but no path): #{uri}" + "bad URI (absolute but no path): #{uri}" end when @regexp[:REL_URI] @@ -174,7 +173,7 @@ module URI # server = [ [ userinfo "@" ] hostport ] else - raise InvalidURIError, "bad URI(is not URI?): #{uri}" + raise InvalidURIError, "bad URI (is not URI?): #{uri}" end path = '' if !path && !opaque # (see RFC2396 Section 5.2) @@ -198,31 +197,18 @@ module URI # # == Description # - # parses +uri+ and constructs either matching URI scheme object - # (FTP, HTTP, HTTPS, LDAP, LDAPS, or MailTo) or URI::Generic + # Parses +uri+ and constructs either matching URI scheme object + # (File, 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> + # URI::RFC2396_PARSER.parse("ldap://ldap.example.com/dc=example?user=john") + # #=> #<URI::LDAP 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 + URI.for(*self.split(uri), self) end - # # == Args # @@ -231,7 +217,7 @@ module URI # # == Description # - # Attempts to parse and merge a set of URIs + # Attempts to parse and merge a set of URIs. # def join(*uris) uris[0] = convert_to_uri(uris[0]) @@ -253,11 +239,11 @@ module URI # # == Description # - # Attempts to parse and merge a set of URIs - # If no +block+ given , then returns the result, + # 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 + # See also #make_regexp. # def extract(str, schemes = nil) if block_given? @@ -270,13 +256,13 @@ module URI 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] + # 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 + /(?=(?i:#{Regexp.union(*schemes).source}):)#{@pattern[:X_ABS_URI]}/x end end @@ -290,11 +276,11 @@ module URI # +str+:: # String to make safe # +unsafe+:: - # Regexp to apply. Defaults to self.regexp[:UNSAFE] + # Regexp to apply. Defaults to +self.regexp[:UNSAFE]+ # # == Description # - # constructs a safe String from +str+, removing unsafe characters, + # Constructs a safe String from +str+, removing unsafe characters, # replacing them with codes. # def escape(str, unsafe = @regexp[:UNSAFE]) @@ -315,31 +301,39 @@ module URI # # :call-seq: # unescape( str ) - # unescape( str, unsafe ) + # unescape( str, escaped ) # # == Args # # +str+:: # String to remove escapes from - # +unsafe+:: - # Regexp to apply. Defaults to self.regexp[:ESCAPED] + # +escaped+:: + # Regexp to apply. Defaults to +self.regexp[:ESCAPED]+ # # == Description # - # Removes escapes from +str+ + # Removes escapes from +str+. # def unescape(str, escaped = @regexp[:ESCAPED]) - str.gsub(escaped) { [$&[1, 2].hex].pack('C') }.force_encoding(str.encoding) + enc = str.encoding + enc = Encoding::UTF_8 if enc == Encoding::US_ASCII + str.gsub(escaped) { [$&[1, 2]].pack('H2').force_encoding(enc) } end - @@to_s = Kernel.instance_method(:to_s) - def inspect - @@to_s.bind(self).call + TO_S = Kernel.instance_method(:to_s) # :nodoc: + if TO_S.respond_to?(:bind_call) + def inspect # :nodoc: + TO_S.bind_call(self) + end + else + def inspect # :nodoc: + TO_S.bind(self).call + end end private - # Constructs the default Hash of patterns + # Constructs the default Hash of patterns. def initialize_pattern(opts = {}) ret = {} ret[:ESCAPED] = escaped = (opts.delete(:ESCAPED) || PATTERN::ESCAPED) @@ -497,13 +491,13 @@ module URI ret end - # Constructs the default Hash of Regexp's + # Constructs the default Hash of Regexp's. def initialize_regexp(pattern) 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]) @@ -529,6 +523,8 @@ module URI ret end + # Returns +uri+ as-is if it is URI, or convert it to URI if it is + # a String. def convert_to_uri(uri) if uri.is_a?(URI::Generic) uri @@ -541,4 +537,11 @@ module URI end end # class Parser + + # Backward compatibility for URI::REGEXP::PATTERN::* + RFC2396_Parser.new.pattern.each_pair do |sym, str| + unless RFC2396_REGEXP::PATTERN.const_defined?(sym, false) + RFC2396_REGEXP::PATTERN.const_set(sym, str) + end + end end # module URI diff --git a/lib/uri/rfc3986_parser.rb b/lib/uri/rfc3986_parser.rb index 871280044a..0b5f0c4488 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 @@ -15,14 +78,14 @@ module URI begin uri = uri.to_str rescue NoMethodError - raise InvalidURIError, "bad URI(is not URI?): #{uri}" + raise InvalidURIError, "bad URI (is not URI?): #{uri.inspect}" end 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, @@ -33,80 +96,98 @@ 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}" + raise InvalidURIError, "bad URI (is not URI?): #{uri.inspect}" end end def parse(uri) # :nodoc: - scheme, userinfo, host, port, - registry, path, opaque, query, fragment = self.split(uri) - scheme_list = URI.scheme_list - if scheme && scheme_list.include?(uc = scheme.upcase) - scheme_list[uc].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 + URI.for(*self.split(uri), self) end - def join(*uris) # :nodoc: uris[0] = convert_to_uri(uris[0]) uris.inject :merge end + # Compatibility for RFC2396 parser + def extract(str, schemes = nil, &block) # :nodoc: + warn "URI::RFC3986_PARSER.extract is obsolete. Use URI::RFC2396_PARSER.extract explicitly.", uplevel: 1 if $VERBOSE + RFC2396_PARSER.extract(str, schemes, &block) + end + + # Compatibility for RFC2396 parser + def make_regexp(schemes = nil) # :nodoc: + warn "URI::RFC3986_PARSER.make_regexp is obsolete. Use URI::RFC2396_PARSER.make_regexp explicitly.", uplevel: 1 if $VERBOSE + RFC2396_PARSER.make_regexp(schemes) + end + + # Compatibility for RFC2396 parser + def escape(str, unsafe = nil) # :nodoc: + warn "URI::RFC3986_PARSER.escape is obsolete. Use URI::RFC2396_PARSER.escape explicitly.", uplevel: 1 if $VERBOSE + unsafe ? RFC2396_PARSER.escape(str, unsafe) : RFC2396_PARSER.escape(str) + end + + # Compatibility for RFC2396 parser + def unescape(str, escaped = nil) # :nodoc: + warn "URI::RFC3986_PARSER.unescape is obsolete. Use URI::RFC2396_PARSER.unescape explicitly.", uplevel: 1 if $VERBOSE + escaped ? RFC2396_PARSER.unescape(str, escaped) : RFC2396_PARSER.unescape(str) + end + @@to_s = Kernel.instance_method(:to_s) - def inspect - @@to_s.bind(self).call + if @@to_s.respond_to?(:bind_call) + def inspect + @@to_s.bind_call(self) + end + else + def inspect + @@to_s.bind(self).call + end end private def default_regexp # :nodoc: { - SCHEME: /\A[A-Za-z][A-Za-z0-9+\-.]*\z/, - USERINFO: /\A(?:%\h\h|[!$&-.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 new file mode 100644 index 0000000000..0d0f897cba --- /dev/null +++ b/lib/uri/uri.gemspec @@ -0,0 +1,42 @@ +begin + require_relative "lib/uri/version" +rescue LoadError # Fallback to load version file in ruby core repository + require_relative "version" +end + +Gem::Specification.new do |spec| + spec.name = "uri" + spec.version = URI::VERSION + spec.authors = ["Akira Yamada"] + spec.email = ["akira@ruby-lang.org"] + + spec.summary = %q{URI is a module providing classes to handle Uniform Resource Identifiers} + spec.description = spec.summary + + github_link = "https://github.com/ruby/uri" + + spec.homepage = github_link + spec.licenses = ["Ruby", "BSD-2-Clause"] + + spec.required_ruby_version = '>= 2.5' + + 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. + gemspec = File.basename(__FILE__) + spec.files = Dir.chdir(File.expand_path('..', __FILE__)) do + `git ls-files -z 2>#{IO::NULL}`.split("\x0").reject do |file| + (file == gemspec) || file.start_with?(*%w[bin/ test/ rakelib/ .github/ .gitignore Gemfile Rakefile]) + end + end + spec.bindir = "exe" + spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) } + spec.require_paths = ["lib"] +end diff --git a/lib/uri/version.rb b/lib/uri/version.rb new file mode 100644 index 0000000000..1f810602eb --- /dev/null +++ b/lib/uri/version.rb @@ -0,0 +1,6 @@ +module URI + # :stopdoc: + VERSION = '1.1.1'.freeze + VERSION_CODE = VERSION.split('.').map{|s| s.rjust(2, '0')}.join.freeze + # :startdoc: +end diff --git a/lib/uri/ws.rb b/lib/uri/ws.rb new file mode 100644 index 0000000000..ff3c554484 --- /dev/null +++ b/lib/uri/ws.rb @@ -0,0 +1,83 @@ +# frozen_string_literal: false +# = uri/ws.rb +# +# Author:: Matt Muller <mamuller@amazon.com> +# License:: You can redistribute it and/or modify it under the same term as Ruby. +# +# See URI for general documentation +# + +require_relative 'generic' + +module URI + + # + # The syntax of WS URIs is defined in RFC6455 section 3. + # + # Note that the Ruby URI library allows WS URLs containing usernames and + # passwords. This is not legal as per the RFC, but used to be + # supported in Internet Explorer 5 and 6, before the MS04-004 security + # update. See <URL:http://support.microsoft.com/kb/834489>. + # + class WS < Generic + # A Default port of 80 for URI::WS. + DEFAULT_PORT = 80 + + # An Array of the available components for URI::WS. + COMPONENT = %i[ + scheme + userinfo host port + path + query + ].freeze + + # + # == Description + # + # Creates a new URI::WS object from components, with syntax checking. + # + # The components accepted are userinfo, host, port, path, and query. + # + # The components should be provided either as an Array, or as a Hash + # with keys formed by preceding the component names with a colon. + # + # If an Array is used, the components must be passed in the + # order <code>[userinfo, host, port, path, query]</code>. + # + # Example: + # + # uri = URI::WS.build(host: 'www.example.com', path: '/foo/bar') + # + # uri = URI::WS.build([nil, "www.example.com", nil, "/path", "query"]) + # + # Currently, if passed userinfo components this method generates + # invalid WS URIs as per RFC 1738. + # + def self.build(args) + tmp = Util.make_components_hash(self, args) + super(tmp) + end + + # + # == Description + # + # Returns the full path for a WS URI, as required by Net::HTTP::Get. + # + # If the URI contains a query, the full path is URI#path + '?' + URI#query. + # Otherwise, the path is simply URI#path. + # + # Example: + # + # uri = URI::WS.build(path: '/foo/bar', query: 'test=true') + # uri.request_uri # => "/foo/bar?test=true" + # + def request_uri + return unless @path + + url = @query ? "#@path?#@query" : @path.dup + url.start_with?(?/.freeze) ? url : ?/ + url + end + end + + register_scheme 'WS', WS +end diff --git a/lib/uri/wss.rb b/lib/uri/wss.rb new file mode 100644 index 0000000000..7cea9d773b --- /dev/null +++ b/lib/uri/wss.rb @@ -0,0 +1,23 @@ +# frozen_string_literal: false +# = uri/wss.rb +# +# Author:: Matt Muller <mamuller@amazon.com> +# License:: You can redistribute it and/or modify it under the same term as Ruby. +# +# See URI for general documentation +# + +require_relative 'ws' + +module URI + + # The default port for WSS URIs is 443, and the scheme is 'wss:' rather + # than 'ws:'. Other than that, WSS URIs are identical to WS URIs; + # see URI::WS. + class WSS < WS + # A Default port of 443 for URI::WSS + DEFAULT_PORT = 443 + end + + register_scheme 'WSS', WSS +end |