diff options
Diffstat (limited to 'lib/uri/common.rb')
| -rw-r--r-- | lib/uri/common.rb | 1211 |
1 files changed, 447 insertions, 764 deletions
diff --git a/lib/uri/common.rb b/lib/uri/common.rb index e1bc3582c7..a2fb531631 100644 --- a/lib/uri/common.rb +++ b/lib/uri/common.rb @@ -1,555 +1,65 @@ +# 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 # -module URI - # - # Includes URI::REGEXP::PATTERN - # - module REGEXP - # - # Patterns used to parse URI's - # - module PATTERN - # :stopdoc: - - # RFC 2396 (URI Generic Syntax) - # RFC 2732 (IPv6 Literal Addresses in URL's) - # RFC 2373 (IPv6 Addressing Architecture) - - # alpha = lowalpha | upalpha - ALPHA = "a-zA-Z" - # alphanum = alpha | digit - ALNUM = "#{ALPHA}\\d" - - # hex = digit | "A" | "B" | "C" | "D" | "E" | "F" | - # "a" | "b" | "c" | "d" | "e" | "f" - HEX = "a-fA-F\\d" - # escaped = "%" hex hex - ESCAPED = "%[#{HEX}]{2}" - # mark = "-" | "_" | "." | "!" | "~" | "*" | "'" | - # "(" | ")" - # unreserved = alphanum | mark - UNRESERVED = "\\-_.!~*'()#{ALNUM}" - # reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" | - # "$" | "," - # reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" | - # "$" | "," | "[" | "]" (RFC 2732) - RESERVED = ";/?:@&=+$,\\[\\]" - - # domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum - DOMLABEL = "(?:[#{ALNUM}](?:[-#{ALNUM}]*[#{ALNUM}])?)" - # toplabel = alpha | alpha *( alphanum | "-" ) alphanum - TOPLABEL = "(?:[#{ALPHA}](?:[-#{ALNUM}]*[#{ALNUM}])?)" - # hostname = *( domainlabel "." ) toplabel [ "." ] - HOSTNAME = "(?:#{DOMLABEL}\\.)*#{TOPLABEL}\\.?" - - # :startdoc: - end # PATTERN - - # :startdoc: - end # REGEXP - - # class that Parses String's into URI's - # - # It contains a Hash set of patterns and Regexp's that match and validate. - # - class Parser - include REGEXP - - # - # == Synopsis - # - # URI::Parser.new([opts]) - # - # == Args - # - # The constructor accepts a hash as options for parser. - # Keys of options are pattern names of URI components - # and values of options are pattern strings. - # The constructor generates set of regexps for parsing URIs. - # - # You can use the following keys: - # - # * :ESCAPED (URI::PATTERN::ESCAPED in default) - # * :UNRESERVED (URI::PATTERN::UNRESERVED in default) - # * :DOMLABEL (URI::PATTERN::DOMLABEL in default) - # * :TOPLABEL (URI::PATTERN::TOPLABEL in default) - # * :HOSTNAME (URI::PATTERN::HOSTNAME in default) - # - # == Examples - # - # p = URI::Parser.new(:ESCAPED => "(?:%[a-fA-F0-9]{2}|%u[a-fA-F0-9]{4})") - # u = p.parse("http://example.jp/%uABCD") #=> #<URI::HTTP:0xb78cf4f8 URL:http://example.jp/%uABCD> - # URI.parse(u.to_s) #=> raises URI::InvalidURIError - # - # s = "http://examle.com/ABCD" - # u1 = p.parse(s) #=> #<URI::HTTP:0xb78c3220 URL:http://example.com/ABCD> - # u2 = URI.parse(s) #=> #<URI::HTTP:0xb78b6d54 URL:http://example.com/ABCD> - # u1 == u2 #=> true - # u1.eql?(u2) #=> false - # - def initialize(opts = {}) - @pattern = initialize_pattern(opts) - @pattern.each_value {|v| v.freeze} - @pattern.freeze - - @regexp = initialize_regexp(@pattern) - @regexp.each_value {|v| v.freeze} - @regexp.freeze - end - - # The Hash of patterns. - # - # see also URI::Parser.initialize_pattern - attr_reader :pattern - - # The Hash of Regexp - # - # see also URI::Parser.initialize_regexp - attr_reader :regexp - - # Returns a split URI against regexp[:ABS_URI] - def split(uri) - case uri - when '' - # null uri - - when @regexp[:ABS_URI] - scheme, opaque, userinfo, host, port, - registry, path, query, fragment = $~[1..-1] - - # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ] - - # absoluteURI = scheme ":" ( hier_part | opaque_part ) - # hier_part = ( net_path | abs_path ) [ "?" query ] - # opaque_part = uric_no_slash *uric - - # abs_path = "/" path_segments - # net_path = "//" authority [ abs_path ] - - # authority = server | reg_name - # server = [ [ userinfo "@" ] hostport ] - - if !scheme - raise InvalidURIError, - "bad URI(absolute but no scheme): #{uri}" - end - if !opaque && (!path && (!host && !registry)) - raise InvalidURIError, - "bad URI(absolute but no path): #{uri}" - end - - when @regexp[:REL_URI] - scheme = nil - opaque = nil - - userinfo, host, port, registry, - rel_segment, abs_path, query, fragment = $~[1..-1] - if rel_segment && abs_path - path = rel_segment + abs_path - elsif rel_segment - path = rel_segment - elsif abs_path - path = abs_path - end - - # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ] - - # relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ] +require_relative "rfc2396_parser" +require_relative "rfc3986_parser" - # net_path = "//" authority [ abs_path ] - # abs_path = "/" path_segments - # rel_path = rel_segment [ abs_path ] - - # authority = server | reg_name - # server = [ [ userinfo "@" ] hostport ] - - else - raise InvalidURIError, "bad URI(is not URI?): #{uri}" - end - - path = '' if !path && !opaque # (see RFC2396 Section 5.2) - ret = [ - scheme, - userinfo, host, port, # X - registry, # X - path, # Y - opaque, # Y - query, - fragment - ] - return ret - end - - # - # == Args - # - # +uri+:: - # String - # - # == Description - # - # parses +uri+ and constructs either matching URI scheme object - # (FTP, HTTP, HTTPS, LDAP, LDAPS, or MailTo) or URI::Generic - # - # == Usage - # - # p = URI::Parser.new - # p.parse("ldap://ldap.example.com/dc=example?user=john") - # #=> #<URI::LDAP:0x00000000b9e7e8 URL:ldap://ldap.example.com/dc=example?user=john> - # - def parse(uri) - scheme, userinfo, host, port, - registry, path, opaque, query, fragment = self.split(uri) - - if scheme && URI.scheme_list.include?(scheme.upcase) - URI.scheme_list[scheme.upcase].new(scheme, userinfo, host, port, - registry, path, opaque, query, - fragment, self) - else - Generic.new(scheme, userinfo, host, port, - registry, path, opaque, query, - fragment, self) - end - end - - - # - # == Args - # - # +uris+:: - # an Array of Strings - # - # == Description - # - # Attempts to parse and merge a set of URIs - # - def join(*uris) - uris[0] = convert_to_uri(uris[0]) - uris.inject :merge - end - - # - # :call-seq: - # extract( str ) - # extract( str, schemes ) - # extract( str, schemes ) {|item| block } - # - # == Args - # - # +str+:: - # String to search - # +schemes+:: - # Patterns to apply to +str+ - # - # == Description - # - # Attempts to parse and merge a set of URIs - # If no +block+ given , then returns the result, - # else it calls +block+ for each element in result. - # - # see also URI::Parser.make_regexp - # - def extract(str, schemes = nil) - if block_given? - str.scan(make_regexp(schemes)) { yield $& } - nil - else - result = [] - str.scan(make_regexp(schemes)) { result.push $& } - result - end - end - - # returns Regexp that is default self.regexp[:ABS_URI_REF], - # unless +schemes+ is provided. Then it is a Regexp.union with self.pattern[:X_ABS_URI] - def make_regexp(schemes = nil) - unless schemes - @regexp[:ABS_URI_REF] - else - /(?=#{Regexp.union(*schemes)}:)#{@pattern[:X_ABS_URI]}/x - end - end - - # - # :call-seq: - # escape( str ) - # escape( str, unsafe ) - # - # == Args - # - # +str+:: - # String to make safe - # +unsafe+:: - # Regexp to apply. Defaults to self.regexp[:UNSAFE] - # - # == Description - # - # constructs a safe String from +str+, removing unsafe characters, - # replacing them with codes. - # - def escape(str, unsafe = @regexp[:UNSAFE]) - unless unsafe.kind_of?(Regexp) - # perhaps unsafe is String object - unsafe = Regexp.new("[#{Regexp.quote(unsafe)}]", false) - end - str.gsub(unsafe) do - us = $& - tmp = '' - us.each_byte do |uc| - tmp << sprintf('%%%02X', uc) - end - tmp - end.force_encoding(Encoding::US_ASCII) - end - - # - # :call-seq: - # unescape( str ) - # unescape( str, unsafe ) - # - # == Args - # - # +str+:: - # String to remove escapes from - # +unsafe+:: - # Regexp to apply. Defaults to self.regexp[:ESCAPED] - # - # == Description - # - # Removes escapes from +str+ - # - def unescape(str, escaped = @regexp[:ESCAPED]) - str.gsub(escaped) { [$&[1, 2].hex].pack('C') }.force_encoding(str.encoding) - end - - @@to_s = Kernel.instance_method(:to_s) - def inspect - @@to_s.bind(self).call - end - - private - - # Constructs the default Hash of patterns - def initialize_pattern(opts = {}) - ret = {} - ret[:ESCAPED] = escaped = (opts.delete(:ESCAPED) || PATTERN::ESCAPED) - ret[:UNRESERVED] = unreserved = opts.delete(:UNRESERVED) || PATTERN::UNRESERVED - ret[:RESERVED] = reserved = opts.delete(:RESERVED) || PATTERN::RESERVED - ret[:DOMLABEL] = opts.delete(:DOMLABEL) || PATTERN::DOMLABEL - ret[:TOPLABEL] = opts.delete(:TOPLABEL) || PATTERN::TOPLABEL - ret[:HOSTNAME] = hostname = opts.delete(:HOSTNAME) - - # RFC 2396 (URI Generic Syntax) - # RFC 2732 (IPv6 Literal Addresses in URL's) - # RFC 2373 (IPv6 Addressing Architecture) - - # uric = reserved | unreserved | escaped - ret[:URIC] = uric = "(?:[#{unreserved}#{reserved}]|#{escaped})" - # uric_no_slash = unreserved | escaped | ";" | "?" | ":" | "@" | - # "&" | "=" | "+" | "$" | "," - ret[:URIC_NO_SLASH] = uric_no_slash = "(?:[#{unreserved};?:@&=+$,]|#{escaped})" - # query = *uric - ret[:QUERY] = query = "#{uric}*" - # fragment = *uric - ret[:FRAGMENT] = fragment = "#{uric}*" - - # hostname = *( domainlabel "." ) toplabel [ "." ] - # reg-name = *( unreserved / pct-encoded / sub-delims ) # RFC3986 - unless hostname - ret[:HOSTNAME] = hostname = "(?:[a-zA-Z0-9\\-.]|%\\h\\h)+" - end - - # RFC 2373, APPENDIX B: - # IPv6address = hexpart [ ":" IPv4address ] - # IPv4address = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT - # hexpart = hexseq | hexseq "::" [ hexseq ] | "::" [ hexseq ] - # hexseq = hex4 *( ":" hex4) - # hex4 = 1*4HEXDIG - # - # XXX: This definition has a flaw. "::" + IPv4address must be - # allowed too. Here is a replacement. - # - # IPv4address = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT - ret[:IPV4ADDR] = ipv4addr = "\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}" - # hex4 = 1*4HEXDIG - hex4 = "[#{PATTERN::HEX}]{1,4}" - # lastpart = hex4 | IPv4address - lastpart = "(?:#{hex4}|#{ipv4addr})" - # hexseq1 = *( hex4 ":" ) hex4 - hexseq1 = "(?:#{hex4}:)*#{hex4}" - # hexseq2 = *( hex4 ":" ) lastpart - hexseq2 = "(?:#{hex4}:)*#{lastpart}" - # IPv6address = hexseq2 | [ hexseq1 ] "::" [ hexseq2 ] - ret[:IPV6ADDR] = ipv6addr = "(?:#{hexseq2}|(?:#{hexseq1})?::(?:#{hexseq2})?)" - - # IPv6prefix = ( hexseq1 | [ hexseq1 ] "::" [ hexseq1 ] ) "/" 1*2DIGIT - # unused - - # ipv6reference = "[" IPv6address "]" (RFC 2732) - ret[:IPV6REF] = ipv6ref = "\\[#{ipv6addr}\\]" - - # host = hostname | IPv4address - # host = hostname | IPv4address | IPv6reference (RFC 2732) - ret[:HOST] = host = "(?:#{hostname}|#{ipv4addr}|#{ipv6ref})" - # port = *digit - port = '\d*' - # hostport = host [ ":" port ] - ret[:HOSTPORT] = hostport = "#{host}(?::#{port})?" - - # userinfo = *( unreserved | escaped | - # ";" | ":" | "&" | "=" | "+" | "$" | "," ) - ret[:USERINFO] = userinfo = "(?:[#{unreserved};:&=+$,]|#{escaped})*" - - # pchar = unreserved | escaped | - # ":" | "@" | "&" | "=" | "+" | "$" | "," - pchar = "(?:[#{unreserved}:@&=+$,]|#{escaped})" - # param = *pchar - param = "#{pchar}*" - # segment = *pchar *( ";" param ) - segment = "#{pchar}*(?:;#{param})*" - # path_segments = segment *( "/" segment ) - ret[:PATH_SEGMENTS] = path_segments = "#{segment}(?:/#{segment})*" - - # server = [ [ userinfo "@" ] hostport ] - server = "(?:#{userinfo}@)?#{hostport}" - # reg_name = 1*( unreserved | escaped | "$" | "," | - # ";" | ":" | "@" | "&" | "=" | "+" ) - ret[:REG_NAME] = reg_name = "(?:[#{unreserved}$,;:@&=+]|#{escaped})+" - # authority = server | reg_name - authority = "(?:#{server}|#{reg_name})" - - # rel_segment = 1*( unreserved | escaped | - # ";" | "@" | "&" | "=" | "+" | "$" | "," ) - ret[:REL_SEGMENT] = rel_segment = "(?:[#{unreserved};@&=+$,]|#{escaped})+" - - # scheme = alpha *( alpha | digit | "+" | "-" | "." ) - ret[:SCHEME] = scheme = "[#{PATTERN::ALPHA}][\\-+.#{PATTERN::ALPHA}\\d]*" - - # abs_path = "/" path_segments - ret[:ABS_PATH] = abs_path = "/#{path_segments}" - # rel_path = rel_segment [ abs_path ] - ret[:REL_PATH] = rel_path = "#{rel_segment}(?:#{abs_path})?" - # net_path = "//" authority [ abs_path ] - ret[:NET_PATH] = net_path = "//#{authority}(?:#{abs_path})?" - - # hier_part = ( net_path | abs_path ) [ "?" query ] - ret[:HIER_PART] = hier_part = "(?:#{net_path}|#{abs_path})(?:\\?(?:#{query}))?" - # opaque_part = uric_no_slash *uric - ret[:OPAQUE_PART] = opaque_part = "#{uric_no_slash}#{uric}*" - - # absoluteURI = scheme ":" ( hier_part | opaque_part ) - ret[:ABS_URI] = abs_uri = "#{scheme}:(?:#{hier_part}|#{opaque_part})" - # relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ] - ret[:REL_URI] = rel_uri = "(?:#{net_path}|#{abs_path}|#{rel_path})(?:\\?#{query})?" - - # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ] - ret[:URI_REF] = "(?:#{abs_uri}|#{rel_uri})?(?:##{fragment})?" - - ret[:X_ABS_URI] = " - (#{scheme}): (?# 1: scheme) - (?: - (#{opaque_part}) (?# 2: opaque) - | - (?:(?: - //(?: - (?:(?:(#{userinfo})@)? (?# 3: userinfo) - (?:(#{host})(?::(\\d*))?))? (?# 4: host, 5: port) - | - (#{reg_name}) (?# 6: registry) - ) - | - (?!//)) (?# XXX: '//' is the mark for hostport) - (#{abs_path})? (?# 7: path) - )(?:\\?(#{query}))? (?# 8: query) - ) - (?:\\#(#{fragment}))? (?# 9: fragment) - " - - ret[:X_REL_URI] = " - (?: - (?: - // - (?: - (?:(#{userinfo})@)? (?# 1: userinfo) - (#{host})?(?::(\\d*))? (?# 2: host, 3: port) - | - (#{reg_name}) (?# 4: registry) - ) - ) - | - (#{rel_segment}) (?# 5: rel_segment) - )? - (#{abs_path})? (?# 6: abs_path) - (?:\\?(#{query}))? (?# 7: query) - (?:\\#(#{fragment}))? (?# 8: fragment) - " - - ret - end - - # 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) - - # for URI::extract - ret[:URI_REF] = Regexp.new(pattern[:URI_REF]) - ret[:ABS_URI_REF] = Regexp.new(pattern[:X_ABS_URI], Regexp::EXTENDED) - ret[:REL_URI_REF] = Regexp.new(pattern[:X_REL_URI], Regexp::EXTENDED) - - # for URI::escape/unescape - ret[:ESCAPED] = Regexp.new(pattern[:ESCAPED]) - ret[:UNSAFE] = Regexp.new("[^#{pattern[:UNRESERVED]}#{pattern[:RESERVED]}]") - - # for Generic#initialize - ret[:SCHEME] = Regexp.new("\\A#{pattern[:SCHEME]}\\z") - ret[:USERINFO] = Regexp.new("\\A#{pattern[:USERINFO]}\\z") - ret[:HOST] = Regexp.new("\\A#{pattern[:HOST]}\\z") - ret[:PORT] = Regexp.new("\\A#{pattern[:PORT]}\\z") - ret[:OPAQUE] = Regexp.new("\\A#{pattern[:OPAQUE_PART]}\\z") - ret[:REGISTRY] = Regexp.new("\\A#{pattern[:REG_NAME]}\\z") - ret[:ABS_PATH] = Regexp.new("\\A#{pattern[:ABS_PATH]}\\z") - ret[:REL_PATH] = Regexp.new("\\A#{pattern[:REL_PATH]}\\z") - ret[:QUERY] = Regexp.new("\\A#{pattern[:QUERY]}\\z") - ret[:FRAGMENT] = Regexp.new("\\A#{pattern[:FRAGMENT]}\\z") - - ret - end - - def convert_to_uri(uri) - if uri.is_a?(URI::Generic) - uri - elsif uri = String.try_convert(uri) - parse(uri) - else - raise ArgumentError, - "bad argument (expected URI object or URI string)" - end +module URI + # 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 - end # class Parser - - # 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: @@ -575,7 +85,7 @@ module URI end else raise ArgumentError, - "expected Array of or Hash of components of #{klass.to_s} (#{klass.component[1..-1].join(', ')})" + "expected Array of or Hash of components of #{klass} (#{klass.component[1..-1].join(', ')})" end tmp[:scheme] = klass.to_s.sub(/\A.*::/, '').downcase @@ -584,80 +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>REGEXP::UNSAFE</tt>. - # When this argument is a String, it represents a character set. - # - # == Description - # - # Escapes the string, replacing all unsafe characters with codes. - # - # == 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 # @@ -677,112 +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) - DEFAULT_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 URI::RFC2396_PARSER.escape string +uri+ + # if it may contain invalid URI characters. # def self.parse(uri) - DEFAULT_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 - # - # URI::join(str[, str, ...]) - # - # == Args - # - # +str+:: - # String(s) to work with - # - # == Description - # - # Joins URIs. - # - # == Usage - # - # require 'uri' + # Each string in +str+ is converted to an + # {RFC3986 URI}[https://www.rfc-editor.org/rfc/rfc3986.html] before being merged. # - # p URI.join("http://example.com/","main.rbx") - # # => #<URI::HTTP:0x2022ac02 URL:http://localhost/main.rbx> + # Examples: # - # p URI.join('http://example.com', 'foo') - # # => #<URI::HTTP:0x01ab80a0 URL:http://example.com/foo> + # URI.join("http://example.com/","main.rbx") + # # => #<URI::HTTP http://example.com/main.rbx> # - # p URI.join('http://example.com', '/foo', '/bar') - # # => #<URI::HTTP:0x01aaf0b0 URL:http://example.com/bar> + # URI.join('http://example.com', 'foo') + # # => #<URI::HTTP http://example.com/foo> # - # p URI.join('http://example.com', '/foo', 'bar') - # # => #<URI::HTTP:0x801a92af0 URL:http://example.com/bar> + # URI.join('http://example.com', '/foo', '/bar') + # # => #<URI::HTTP 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) - DEFAULT_PARSER.join(*str) + PARSER.join(*str) end # @@ -795,7 +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 # @@ -809,8 +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) - 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 # @@ -825,9 +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 # @@ -837,98 +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) - 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 = [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/html5/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})" unless /\A[^%]*(?:%\h\h[^%]*)*\z/ =~ 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}" # - # This generates application/x-www-form-urlencoded data defined in HTML5 - # from given an Enumerable object. + # Examples: # - # This internally uses URI.encode_www_form_component(str). + # 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" # - # 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.) + # - If +ele+ is an array of one element, + # the field is formed from <tt>ele[0]</tt>: # - # This method doesn't handle files. When you send a file, use - # multipart/form-data. + # URI.encode_www_form_component(ele[0]) # - # This refers http://url.spec.whatwg.org/#concept-urlencoded-serializer + # Example: # - # URI.encode_www_form([["q", "ruby"], ["lang", "en"]]) - # #=> "q=ruby&lang=en" - # URI.encode_www_form("q" => "ruby", "lang" => "en") - # #=> "q=ruby&lang=en" - # URI.encode_www_form("q" => ["ruby", "perl"], "lang" => "en") - # #=> "q=ruby&q=perl&lang=en" - # URI.encode_www_form([["q", "ruby"], ["q", "perl"], ["lang", "en"]]) - # #=> "q=ruby&q=perl&lang=en" + # URI.encode_www_form([['foo'], [:bar], [0]]) + # # => "foo&bar&0" + # + # - Otherwise the field is formed from +ele+: + # + # URI.encode_www_form_component(ele) + # + # Example: + # + # URI.encode_www_form(['foo', :bar, 0]) + # # => "foo&bar&0" + # + # The elements of an Array-like +enum+ may be mixture: + # + # URI.encode_www_form([['foo', 0], ['bar', 1, 2], ['baz'], :bat]) + # # => "foo=0&bar=1&baz&bat" + # + # When +enum+ is Hash-like, + # each +key+/+value+ pair is converted to one or more fields: + # + # - If +value+ is + # {Array-convertible}[rdoc-ref:implicit_conversion.rdoc@Array-Convertible+Objects], + # each element +ele+ in +value+ is paired with +key+ to form a field: + # + # name = URI.encode_www_form_component(key, enc) + # value = URI.encode_www_form_component(ele, enc) + # "#{name}=#{value}" + # + # Example: + # + # URI.encode_www_form({foo: [:bar, 1], baz: [:bat, :bam, 2]}) + # # => "foo=bar&foo=1&baz=bat&baz=bam&baz=2" + # + # - Otherwise, +key+ and +value+ are paired to form a field: + # + # name = URI.encode_www_form_component(key, enc) + # value = URI.encode_www_form_component(value, enc) + # "#{name}=#{value}" + # + # Example: + # + # URI.encode_www_form({foo: 0, bar: 1, baz: 2}) + # # => "foo=0&bar=1&baz=2" + # + # The elements of a Hash-like +enum+ may be mixture: + # + # URI.encode_www_form({foo: [0, 1], bar: 2}) + # # => "foo=0&foo=1&bar=2" # - # See URI.encode_www_form_component, URI.decode_www_form def self.encode_www_form(enum, enc=nil) enum.map do |k,v| if v.nil? @@ -949,22 +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. + # + # 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>. + # + # 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]. + # + # 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", "$"], ["b z", "@"]] # - # This decodes application/x-www-form-urlencoded data - # and returns array of key-value array. + # The given string may contain consecutive separators: # - # This refers http://url.spec.whatwg.org/#concept-urlencoded-parser , - # so this supports only &-separator, don't support ;-separator. + # URI.decode_www_form('foo=0&&bar=1&&baz=2') + # # => [["foo", "0"], ["", ""], ["bar", "1"], ["", ""], ["baz", "2"]] # - # ary = URI.decode_www_form("a=1&a=2&b=3") - # p ary #=> [['a', '1'], ['a', '2'], ['b', '3']] - # p ary.assoc('a').last #=> '1' - # p ary.assoc('b').last #=> '3' - # p ary.rassoc('a').last #=> '2' - # p Hash[ary] # => {"a"=>"2", "b"=>"3"} + # A different separator may be specified: + # + # URI.decode_www_form('foo=0--bar=1--baz', separator: '--') + # # => [["foo", "0"], ["bar", "1"], ["baz", ""]] # - # See URI.decode_www_form_component, URI.encode_www_form def self.decode_www_form(str, enc=Encoding::UTF_8, separator: '&', use__charset_: false, isindex: false) raise ArgumentError, "the input of #{self.name}.#{__method__} must be ASCII only string" unless str.ascii_only? ary = [] @@ -976,7 +628,7 @@ module URI if isindex if sep.empty? val = key - key = '' + key = +'' end isindex = false end @@ -990,7 +642,7 @@ module URI if val val.gsub!(/\+|%\h\h/, TBLDECWWWCOMP_) else - val = '' + val = +'' end ary << [key, val] @@ -1005,7 +657,24 @@ module URI end private - # curl http://encoding.spec.whatwg.org/encodings.json|rb -rpp -rjson -e'H={};h={"shift_jis"=>"Windows-31J","euc-jp"=>"cp51932","iso-2022-jp"=>"cp50221","x-mac-cyrillic"=>"macCyrillic"};JSON($<.read).map{|x|x["encodings"]}.flatten.each{|x|Encoding.find(n=h.fetch(n=x["name"],n))rescue next;x["labels"].each{|y|H[y]=n}};pp H' +=begin command for WEB_ENCODINGS_ + curl https://encoding.spec.whatwg.org/encodings.json| + ruby -rjson -e 'H={} + h={ + "shift_jis"=>"Windows-31J", + "euc-jp"=>"cp51932", + "iso-2022-jp"=>"cp50221", + "x-mac-cyrillic"=>"macCyrillic", + } + JSON($<.read).map{|x|x["encodings"]}.flatten.each{|x| + Encoding.find(n=h.fetch(n=x["name"].downcase,n))rescue next + x["labels"].each{|y|H[y]=n} + } + puts "{" + H.each{|k,v|puts %[ #{k.dump}=>#{v.dump},]} + puts "}" +' +=end WEB_ENCODINGS_ = { "unicode-1-1-utf-8"=>"utf-8", "utf-8"=>"utf-8", @@ -1111,6 +780,7 @@ module URI "koi8"=>"koi8-r", "koi8-r"=>"koi8-r", "koi8_r"=>"koi8-r", + "koi8-ru"=>"koi8-u", "koi8-u"=>"koi8-u", "dos-874"=>"windows-874", "iso-8859-11"=>"windows-874", @@ -1191,6 +861,7 @@ module URI "csiso2022jp"=>"cp50221", "iso-2022-jp"=>"cp50221", "csshiftjis"=>"Windows-31J", + "ms932"=>"Windows-31J", "ms_kanji"=>"Windows-31J", "shift-jis"=>"Windows-31J", "shift_jis"=>"Windows-31J", @@ -1209,8 +880,9 @@ module URI "windows-949"=>"euc-kr", "utf-16be"=>"utf-16be", "utf-16"=>"utf-16le", - "utf-16le"=>"utf-16le" + "utf-16le"=>"utf-16le", } # :nodoc: + Ractor.make_shareable(WEB_ENCODINGS_) if defined?(Ractor) # :nodoc: # return encoding or nil @@ -1223,7 +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) |