diff options
Diffstat (limited to 'lib/uri/common.rb')
| -rw-r--r-- | lib/uri/common.rb | 1248 |
1 files changed, 864 insertions, 384 deletions
diff --git a/lib/uri/common.rb b/lib/uri/common.rb index fbb3558a32..a2fb531631 100644 --- a/lib/uri/common.rb +++ b/lib/uri/common.rb @@ -1,239 +1,91 @@ +# frozen_string_literal: true +#-- +# = uri/common.rb # -# $Id$ +# Author:: Akira Yamada <akira@ruby-lang.org> +# License:: +# You can redistribute it and/or modify it under the same term as Ruby. # -# Copyright (c) 2001 akira yamada <akira@ruby-lang.org> -# You can redistribute it and/or modify it under the same term as Ruby. +# See URI for general documentation # -=begin +require_relative "rfc2396_parser" +require_relative "rfc3986_parser" -== URI +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 + Parser.new.regexp.each_pair do |sym, str| + remove_const(sym) if const_defined?(sym, false) + const_set(sym, str) + end + end + self.parser = RFC3986_PARSER + + def self.const_missing(const) # :nodoc: + if const == :REGEXP + warn "URI::REGEXP is obsolete.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uplevel: 1 if $VERBOSE + URI::RFC2396_REGEXP + elsif value = RFC2396_PARSER.regexp[const] + warn "URI::#{const} is obsolete.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explicitly.", uplevel: 1 if $VERBOSE + value + elsif value = RFC2396_Parser.const_get(const) + warn "URI::#{const} is obsolete.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 $VERBOSE + value + else + super + end + end -module URI - module REGEXP - module PATTERN - # RFC 2396 (URI Generic Syntax) - # RFC 2732 (IPv6 Literal Addresses in URL's) - # RFC 2373 (IPv6 Addressing Architecture) - - # alpha = lowalpha | upalpha - ALPHA = "a-zA-Z" - # alphanum = alpha | digit - ALNUM = "#{ALPHA}\\d" - - # hex = digit | "A" | "B" | "C" | "D" | "E" | "F" | - # "a" | "b" | "c" | "d" | "e" | "f" - HEX = "a-fA-F\\d" - # escaped = "%" hex hex - ESCAPED = "%[#{HEX}]{2}" - # mark = "-" | "_" | "." | "!" | "~" | "*" | "'" | - # "(" | ")" - # unreserved = alphanum | mark - UNRESERVED = "-_.!~*'()#{ALNUM}" - # reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" | - # "$" | "," - # reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" | - # "$" | "," | "[" | "]" (RFC 2732) - RESERVED = ";/?:@&=+$,\\[\\]" - - # uric = reserved | unreserved | escaped - URIC = "(?:[#{UNRESERVED}#{RESERVED}]|#{ESCAPED})" - # uric_no_slash = unreserved | escaped | ";" | "?" | ":" | "@" | - # "&" | "=" | "+" | "$" | "," - URIC_NO_SLASH = "(?:[#{UNRESERVED};?:@&=+$,]|#{ESCAPED})" - # query = *uric - QUERY = "#{URIC}*" - # fragment = *uric - FRAGMENT = "#{URIC}*" - - # domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum - DOMLABEL = "(?:[#{ALNUM}](?:[-#{ALNUM}]*[#{ALNUM}])?)" - # toplabel = alpha | alpha *( alphanum | "-" ) alphanum - TOPLABEL = "(?:[#{ALPHA}](?:[-#{ALNUM}]*[#{ALNUM}])?)" - # hostname = *( domainlabel "." ) toplabel [ "." ] - HOSTNAME = "(?:#{DOMLABEL}\\.)*#{TOPLABEL}\\.?" - - # 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 - IPV4ADDR = "\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}" - # hex4 = 1*4HEXDIG - HEX4 = "[#{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 ] - IPV6ADDR = "(?:#{HEXSEQ2}|(?:#{HEXSEQ1})?::(?:#{HEXSEQ2})?)" - - # IPv6prefix = ( hexseq1 | [ hexseq1 ] "::" [ hexseq1 ] ) "/" 1*2DIGIT - # unused - - # ipv6reference = "[" IPv6address "]" (RFC 2732) - IPV6REF = "\\[#{IPV6ADDR}\\]" - - # host = hostname | IPv4address - # host = hostname | IPv4address | IPv6reference (RFC 2732) - HOST = "(?:#{HOSTNAME}|#{IPV4ADDR}|#{IPV6REF})" - # port = *digit - PORT = "\d*" - # hostport = host [ ":" port ] - HOSTPORT = "#{HOST}(?:#{PORT})?" - - # userinfo = *( unreserved | escaped | - # ";" | ":" | "&" | "=" | "+" | "$" | "," ) - USERINFO = "(?:[#{UNRESERVED};:&=+$,]|#{ESCAPED})*" - - # pchar = unreserved | escaped | - # ":" | "@" | "&" | "=" | "+" | "$" | "," - PCHAR = "(?:[#{UNRESERVED}:@&=+$,]|#{ESCAPED})" - # param = *pchar - PARAM = "#{PCHAR}*" - # segment = *pchar *( ";" param ) - SEGMENT = "#{PCHAR}*(?:;#{PARAM})*" - # path_segments = segment *( "/" segment ) - PATH_SEGMENTS = "#{SEGMENT}(?:/#{SEGMENT})*" - - # server = [ [ userinfo "@" ] hostport ] - SERVER = "(?:#{USERINFO}@)?#{HOSTPORT}" - # reg_name = 1*( unreserved | escaped | "$" | "," | - # ";" | ":" | "@" | "&" | "=" | "+" ) - REG_NAME = "(?:[#{UNRESERVED}$,;+@&=+]|#{ESCAPED})+" - # authority = server | reg_name - AUTHORITY = "(?:#{SERVER}|#{REG_NAME})" - - # rel_segment = 1*( unreserved | escaped | - # ";" | "@" | "&" | "=" | "+" | "$" | "," ) - REL_SEGMENT = "(?:[#{UNRESERVED};@&=+$,]|#{ESCAPED})+" - - # scheme = alpha *( alpha | digit | "+" | "-" | "." ) - SCHEME = "[#{ALPHA}][-+.#{ALPHA}\\d]*" - - # abs_path = "/" path_segments - ABS_PATH = "/#{PATH_SEGMENTS}" - # rel_path = rel_segment [ abs_path ] - REL_PATH = "#{REL_SEGMENT}(?:#{ABS_PATH})?" - # net_path = "//" authority [ abs_path ] - NET_PATH = "//#{AUTHORITY}(?:#{ABS_PATH})?" - - # hier_part = ( net_path | abs_path ) [ "?" query ] - HIER_PART = "(?:#{NET_PATH}|#{ABS_PATH})(?:\\?(?:#{QUERY}))?" - # opaque_part = uric_no_slash *uric - OPAQUE_PART = "#{URIC_NO_SLASH}#{URIC}*" - - # absoluteURI = scheme ":" ( hier_part | opaque_part ) - ABS_URI = "#{SCHEME}:(?:#{HIER_PART}|#{OPAQUE_PART})" - # relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ] - REL_URI = "(?:#{NET_PATH}|#{ABS_PATH}|#{REL_PATH})(?:\\?#{QUERY})?" - - # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ] - URI_REF = "(?:#{ABS_URI}|#{REL_URI})?(?:##{FRAGMENT})?" - - # XXX: - X_ABS_URI = " - (#{PATTERN::SCHEME}): (?# 1: scheme) - (?: - (#{PATTERN::OPAQUE_PART}) (?# 2: opaque) - | - (?:(?: - //(?: - (?:(?:(#{PATTERN::USERINFO})@)? (?# 3: userinfo) - (?:(#{PATTERN::HOST})(?::(\\d*))?))?(?# 4: host, 5: port) - | - (#{PATTERN::REG_NAME}) (?# 6: registry) - ) - | - (?!//)) (?# XXX: '//' is the mark for hostport) - (#{PATTERN::ABS_PATH})? (?# 7: path) - )(?:\\?(#{PATTERN::QUERY}))? (?# 8: query) - ) - (?:\\#(#{PATTERN::FRAGMENT}))? (?# 9: fragment) - " - X_REL_URI = " - (?: - (?: - // - (?: - (?:(#{PATTERN::USERINFO})@)? (?# 1: userinfo) - (#{PATTERN::HOST})?(?::(\\d*))? (?# 2: host, 3: port) - | - (#{PATTERN::REG_NAME}) (?# 4: registry) - ) - ) - | - (#{PATTERN::REL_SEGMENT}) (?# 5: rel_segment) - )? - (#{PATTERN::ABS_PATH})? (?# 6: abs_path) - (?:\\?(#{PATTERN::QUERY}))? (?# 7: query) - (?:\\#(#{PATTERN::FRAGMENT}))? (?# 8: fragment) - " - end # PATTERN - - # for URI::split - ABS_URI = Regexp.new('^' + PATTERN::X_ABS_URI + '$', #' - Regexp::EXTENDED, 'N').freeze - REL_URI = Regexp.new('^' + PATTERN::X_REL_URI + '$', #' - Regexp::EXTENDED, 'N').freeze - - # for URI::extract - URI_REF = Regexp.new(PATTERN::URI_REF, false, 'N').freeze - ABS_URI_REF = Regexp.new(PATTERN::X_ABS_URI, Regexp::EXTENDED, 'N').freeze - REL_URI_REF = Regexp.new(PATTERN::X_REL_URI, Regexp::EXTENDED, 'N').freeze - - # for URI::escape/unescape - ESCAPED = Regexp.new(PATTERN::ESCAPED, false, 'N').freeze - UNSAFE = Regexp.new("[^#{PATTERN::UNRESERVED}#{PATTERN::RESERVED}]", - false, 'N').freeze - - # for Generic#initialize - SCHEME = Regexp.new("^#{PATTERN::SCHEME}$", false, 'N').freeze #" - USERINFO = Regexp.new("^#{PATTERN::USERINFO}$", false, 'N').freeze #" - HOST = Regexp.new("^#{PATTERN::HOST}$", false, 'N').freeze #" - PORT = Regexp.new("^#{PATTERN::PORT}$", false, 'N').freeze #" - OPAQUE = Regexp.new("^#{PATTERN::OPAQUE_PART}$", false, 'N').freeze #" - REGISTRY = Regexp.new("^#{PATTERN::REG_NAME}$", false, 'N').freeze #" - ABS_PATH = Regexp.new("^#{PATTERN::ABS_PATH}$", false, 'N').freeze #" - REL_PATH = Regexp.new("^#{PATTERN::REL_PATH}$", false, 'N').freeze #" - QUERY = Regexp.new("^#{PATTERN::QUERY}$", false, 'N').freeze #" - FRAGMENT = Regexp.new("^#{PATTERN::FRAGMENT}$", false, 'N').freeze #" - end # REGEXP - - module Util + module Util # :nodoc: def make_components_hash(klass, array_hash) tmp = {} if array_hash.kind_of?(Array) && - array_hash.size == klass.component.size - 1 - klass.component[1..-1].each_index do |i| - begin - tmp[klass.component[i + 1]] = array_hash[i].clone - rescue TypeError - tmp[klass.component[i + 1]] = array_hash[i] - end - end + array_hash.size == klass.component.size - 1 + klass.component[1..-1].each_index do |i| + begin + tmp[klass.component[i + 1]] = array_hash[i].clone + rescue TypeError + tmp[klass.component[i + 1]] = array_hash[i] + end + end elsif array_hash.kind_of?(Hash) - array_hash.each do |key, value| - begin - tmp[key] = value.clone - rescue TypeError - tmp[key] = value - end - end + array_hash.each do |key, value| + begin + tmp[key] = value.clone + rescue TypeError + tmp[key] = value + end + end else - raise ArgumentError, - "expected Array of or Hash of components of #{klass.to_s} (#{klass.component[1..-1].join(', ')})" + raise ArgumentError, + "expected Array of or Hash of components of #{klass} (#{klass.component[1..-1].join(', ')})" end tmp[:scheme] = klass.to_s.sub(/\A.*::/, '').downcase @@ -242,201 +94,829 @@ module URI module_function :make_components_hash end - module Escape - include REGEXP + 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 escape(str, unsafe = UNSAFE) - unless unsafe.kind_of?(Regexp) - # perhaps unsafe is String object - unsafe = Regexp.new(Regexp.quote(unsafe), false, 'N') + def unescape(name) + name.tr(EscapedChars, ReservedChars).encode(Encoding::US_ASCII).upcase end - str.gsub(unsafe) do |us| - tmp = '' - us.each_byte do |uc| - tmp << sprintf('%%%02X', uc) - end - tmp + + def find(name) + const_get(name, false) if name and const_defined?(name, false) end - end - alias encode escape - def unescape(str) - str.gsub(ESCAPED) do - $&[1,2].hex.chr + 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 + private_constant :Schemes + + # Registers the given +klass+ as the class to be instantiated + # when parsing a \URI with the given +scheme+: + # + # URI.register_scheme('MS_SEARCH', URI::Generic) # => URI::Generic + # URI.scheme_list['MS_SEARCH'] # => URI::Generic + # + # Note that after calling String#upcase on +scheme+, it must be a valid + # constant name. + def self.register_scheme(scheme, klass) + Schemes.register(scheme, klass) end - include REGEXP - extend Escape + # 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.list + end - @@schemes = {} + # :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 + # + # Base class for all URI exceptions. + # class Error < StandardError; end - class InvalidURIError < Error; end # it is not URI. - class InvalidComponentError < Error; end # it is not component of URI. - class BadURIError < Error; end # the URI is valid but it is bad for the position. - -=begin - -=== Methods - ---- URI::split(uri) - -=end - + # + # Not a URI. + # + class InvalidURIError < Error; end + # + # Not a URI component. + # + class InvalidComponentError < Error; end + # + # URI is valid, bad usage is not. + # + class BadURIError < Error; end + + # 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) - case uri - when '' - # null uri - - when 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 + PARSER.split(uri) + end - # abs_path = "/" path_segments - # net_path = "//" authority [ abs_path ] + # Returns a new \URI object constructed from the given string +uri+: + # + # URI.parse('https://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top') + # # => #<URI::HTTPS https://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top> + # URI.parse('http://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top') + # # => #<URI::HTTP http://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top> + # + # It's recommended to first URI::RFC2396_PARSER.escape string +uri+ + # if it may contain invalid URI characters. + # + def self.parse(uri) + PARSER.parse(uri) + end - # authority = server | reg_name - # server = [ [ userinfo "@" ] hostport ] + # Merges the given URI strings +str+ + # per {RFC 2396}[https://www.rfc-editor.org/rfc/rfc2396.html]. + # + # Each string in +str+ is converted to an + # {RFC3986 URI}[https://www.rfc-editor.org/rfc/rfc3986.html] before being merged. + # + # Examples: + # + # URI.join("http://example.com/","main.rbx") + # # => #<URI::HTTP http://example.com/main.rbx> + # + # URI.join('http://example.com', 'foo') + # # => #<URI::HTTP http://example.com/foo> + # + # 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/bar> + # + # URI.join('http://example.com', '/foo/', 'bar') + # # => #<URI::HTTP http://example.com/foo/bar> + # + def self.join(*str) + PARSER.join(*str) + end - 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 + # + # == Synopsis + # + # URI::extract(str[, schemes][,&blk]) + # + # == Args + # + # +str+:: + # String to extract URIs from. + # +schemes+:: + # Limit URI matching to specific schemes. + # + # == Description + # + # Extracts URIs from a string. If block given, iterates through all matched URIs. + # Returns nil if block given or array with matches. + # + # == Usage + # + # require "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) # :nodoc: + warn "URI.extract is obsolete", uplevel: 1 if $VERBOSE + PARSER.extract(str, schemes, &block) + end - when 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 + # + # == Synopsis + # + # URI::regexp([match_schemes]) + # + # == Args + # + # +match_schemes+:: + # Array of schemes. If given, resulting regexp matches to URIs + # 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 its number. + # + # == Usage + # + # require 'uri' + # + # # extract first URI from html_string + # html_string.slice(URI.regexp) + # + # # remove ftp URIs + # 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)# :nodoc: + warn "URI.regexp is obsolete", uplevel: 1 if $VERBOSE + PARSER.make_regexp(schemes) + end - # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ] + TBLENCWWWCOMP_ = {} # :nodoc: + 256.times do |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 + end + TBLDECWWWCOMP_['+'] = ' ' + TBLDECWWWCOMP_.freeze + + # Returns a URL-encoded string derived from the given string +str+. + # + # The returned string: + # + # - Preserves: + # + # - Characters <tt>'*'</tt>, <tt>'.'</tt>, <tt>'-'</tt>, and <tt>'_'</tt>. + # - Character in ranges <tt>'a'..'z'</tt>, <tt>'A'..'Z'</tt>, + # and <tt>'0'..'9'</tt>. + # + # Example: + # + # URI.encode_www_form_component('*.-_azAZ09') + # # => "*.-_azAZ09" + # + # - Converts: + # + # - Character <tt>' '</tt> to character <tt>'+'</tt>. + # - Any other character to "percent notation"; + # the percent notation for character <i>c</i> is <tt>'%%%X' % c.ord</tt>. + # + # Example: + # + # 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 - # relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ] + # 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 - # net_path = "//" authority [ abs_path ] - # abs_path = "/" path_segments - # rel_path = rel_segment [ abs_path ] + # 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 - # authority = server | reg_name - # server = [ [ userinfo "@" ] hostport ] + # 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 - else - raise InvalidURIError, "bad URI(is not URI?): #{uri}" + # 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};"}) + end + str.force_encoding(Encoding::ASCII_8BIT) end + str.gsub!(regexp, table) + str.force_encoding(Encoding::US_ASCII) + end + private_class_method :_encode_uri_component - 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 + # 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 + + # 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) + # + # 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" + # + def self.encode_www_form(enum, enc=nil) + enum.map do |k,v| + if v.nil? + encode_www_form_component(k, enc) + elsif v.respond_to?(:to_ary) + v.to_ary.map do |w| + str = encode_www_form_component(k, enc) + unless w.nil? + str << '=' + str << encode_www_form_component(w, enc) + end + end.join('&') + else + str = encode_www_form_component(k, enc) + str << '=' + str << encode_www_form_component(v, enc) + end + end.join('&') end -=begin + # 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", "@"]] + # + # 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", ""]] + # + 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 = [] + return ary if str.empty? + enc = Encoding.find(enc) + str.b.each_line(separator) do |string| + string.chomp!(separator) + key, sep, val = string.partition('=') + if isindex + if sep.empty? + val = key + key = +'' + end + isindex = false + end ---- URI::parse(uri_str) + if use__charset_ and key == '_charset_' and e = get_encoding(val) + enc = e + use__charset_ = false + end -=end - def self.parse(uri) - scheme, userinfo, host, port, - registry, path, opaque, query, fragment = self.split(uri) + key.gsub!(/\+|%\h\h/, TBLDECWWWCOMP_) + if val + val.gsub!(/\+|%\h\h/, TBLDECWWWCOMP_) + else + val = +'' + end - if scheme && @@schemes.include?(scheme.upcase) - @@schemes[scheme.upcase].new(scheme, userinfo, host, port, - registry, path, opaque, query, - fragment) - else - Generic.new(scheme, userinfo, host, port, - registry, path, opaque, query, - fragment) + ary << [key, val] end - end - -=begin - ---- URI::join(str[, str, ...]) - -=end - def self.join(*str) - u = self.parse(str[0]) - str[1 .. -1].each do |x| - u = u.merge(x) + ary.each do |k, v| + k.force_encoding(enc) + k.scrub! + v.force_encoding(enc) + v.scrub! end - u + ary end -=begin - ---- URI::extract(str[, schemes]) - + private +=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 - def self.extract(str, schemes = nil, &block) - if block_given? - str.scan(regexp(schemes)) { yield $& } - nil - else - result = [] - str.scan(regexp(schemes)) { result.push $& } - result - end + WEB_ENCODINGS_ = { + "unicode-1-1-utf-8"=>"utf-8", + "utf-8"=>"utf-8", + "utf8"=>"utf-8", + "866"=>"ibm866", + "cp866"=>"ibm866", + "csibm866"=>"ibm866", + "ibm866"=>"ibm866", + "csisolatin2"=>"iso-8859-2", + "iso-8859-2"=>"iso-8859-2", + "iso-ir-101"=>"iso-8859-2", + "iso8859-2"=>"iso-8859-2", + "iso88592"=>"iso-8859-2", + "iso_8859-2"=>"iso-8859-2", + "iso_8859-2:1987"=>"iso-8859-2", + "l2"=>"iso-8859-2", + "latin2"=>"iso-8859-2", + "csisolatin3"=>"iso-8859-3", + "iso-8859-3"=>"iso-8859-3", + "iso-ir-109"=>"iso-8859-3", + "iso8859-3"=>"iso-8859-3", + "iso88593"=>"iso-8859-3", + "iso_8859-3"=>"iso-8859-3", + "iso_8859-3:1988"=>"iso-8859-3", + "l3"=>"iso-8859-3", + "latin3"=>"iso-8859-3", + "csisolatin4"=>"iso-8859-4", + "iso-8859-4"=>"iso-8859-4", + "iso-ir-110"=>"iso-8859-4", + "iso8859-4"=>"iso-8859-4", + "iso88594"=>"iso-8859-4", + "iso_8859-4"=>"iso-8859-4", + "iso_8859-4:1988"=>"iso-8859-4", + "l4"=>"iso-8859-4", + "latin4"=>"iso-8859-4", + "csisolatincyrillic"=>"iso-8859-5", + "cyrillic"=>"iso-8859-5", + "iso-8859-5"=>"iso-8859-5", + "iso-ir-144"=>"iso-8859-5", + "iso8859-5"=>"iso-8859-5", + "iso88595"=>"iso-8859-5", + "iso_8859-5"=>"iso-8859-5", + "iso_8859-5:1988"=>"iso-8859-5", + "arabic"=>"iso-8859-6", + "asmo-708"=>"iso-8859-6", + "csiso88596e"=>"iso-8859-6", + "csiso88596i"=>"iso-8859-6", + "csisolatinarabic"=>"iso-8859-6", + "ecma-114"=>"iso-8859-6", + "iso-8859-6"=>"iso-8859-6", + "iso-8859-6-e"=>"iso-8859-6", + "iso-8859-6-i"=>"iso-8859-6", + "iso-ir-127"=>"iso-8859-6", + "iso8859-6"=>"iso-8859-6", + "iso88596"=>"iso-8859-6", + "iso_8859-6"=>"iso-8859-6", + "iso_8859-6:1987"=>"iso-8859-6", + "csisolatingreek"=>"iso-8859-7", + "ecma-118"=>"iso-8859-7", + "elot_928"=>"iso-8859-7", + "greek"=>"iso-8859-7", + "greek8"=>"iso-8859-7", + "iso-8859-7"=>"iso-8859-7", + "iso-ir-126"=>"iso-8859-7", + "iso8859-7"=>"iso-8859-7", + "iso88597"=>"iso-8859-7", + "iso_8859-7"=>"iso-8859-7", + "iso_8859-7:1987"=>"iso-8859-7", + "sun_eu_greek"=>"iso-8859-7", + "csiso88598e"=>"iso-8859-8", + "csisolatinhebrew"=>"iso-8859-8", + "hebrew"=>"iso-8859-8", + "iso-8859-8"=>"iso-8859-8", + "iso-8859-8-e"=>"iso-8859-8", + "iso-ir-138"=>"iso-8859-8", + "iso8859-8"=>"iso-8859-8", + "iso88598"=>"iso-8859-8", + "iso_8859-8"=>"iso-8859-8", + "iso_8859-8:1988"=>"iso-8859-8", + "visual"=>"iso-8859-8", + "csisolatin6"=>"iso-8859-10", + "iso-8859-10"=>"iso-8859-10", + "iso-ir-157"=>"iso-8859-10", + "iso8859-10"=>"iso-8859-10", + "iso885910"=>"iso-8859-10", + "l6"=>"iso-8859-10", + "latin6"=>"iso-8859-10", + "iso-8859-13"=>"iso-8859-13", + "iso8859-13"=>"iso-8859-13", + "iso885913"=>"iso-8859-13", + "iso-8859-14"=>"iso-8859-14", + "iso8859-14"=>"iso-8859-14", + "iso885914"=>"iso-8859-14", + "csisolatin9"=>"iso-8859-15", + "iso-8859-15"=>"iso-8859-15", + "iso8859-15"=>"iso-8859-15", + "iso885915"=>"iso-8859-15", + "iso_8859-15"=>"iso-8859-15", + "l9"=>"iso-8859-15", + "iso-8859-16"=>"iso-8859-16", + "cskoi8r"=>"koi8-r", + "koi"=>"koi8-r", + "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", + "iso8859-11"=>"windows-874", + "iso885911"=>"windows-874", + "tis-620"=>"windows-874", + "windows-874"=>"windows-874", + "cp1250"=>"windows-1250", + "windows-1250"=>"windows-1250", + "x-cp1250"=>"windows-1250", + "cp1251"=>"windows-1251", + "windows-1251"=>"windows-1251", + "x-cp1251"=>"windows-1251", + "ansi_x3.4-1968"=>"windows-1252", + "ascii"=>"windows-1252", + "cp1252"=>"windows-1252", + "cp819"=>"windows-1252", + "csisolatin1"=>"windows-1252", + "ibm819"=>"windows-1252", + "iso-8859-1"=>"windows-1252", + "iso-ir-100"=>"windows-1252", + "iso8859-1"=>"windows-1252", + "iso88591"=>"windows-1252", + "iso_8859-1"=>"windows-1252", + "iso_8859-1:1987"=>"windows-1252", + "l1"=>"windows-1252", + "latin1"=>"windows-1252", + "us-ascii"=>"windows-1252", + "windows-1252"=>"windows-1252", + "x-cp1252"=>"windows-1252", + "cp1253"=>"windows-1253", + "windows-1253"=>"windows-1253", + "x-cp1253"=>"windows-1253", + "cp1254"=>"windows-1254", + "csisolatin5"=>"windows-1254", + "iso-8859-9"=>"windows-1254", + "iso-ir-148"=>"windows-1254", + "iso8859-9"=>"windows-1254", + "iso88599"=>"windows-1254", + "iso_8859-9"=>"windows-1254", + "iso_8859-9:1989"=>"windows-1254", + "l5"=>"windows-1254", + "latin5"=>"windows-1254", + "windows-1254"=>"windows-1254", + "x-cp1254"=>"windows-1254", + "cp1255"=>"windows-1255", + "windows-1255"=>"windows-1255", + "x-cp1255"=>"windows-1255", + "cp1256"=>"windows-1256", + "windows-1256"=>"windows-1256", + "x-cp1256"=>"windows-1256", + "cp1257"=>"windows-1257", + "windows-1257"=>"windows-1257", + "x-cp1257"=>"windows-1257", + "cp1258"=>"windows-1258", + "windows-1258"=>"windows-1258", + "x-cp1258"=>"windows-1258", + "x-mac-cyrillic"=>"macCyrillic", + "x-mac-ukrainian"=>"macCyrillic", + "chinese"=>"gbk", + "csgb2312"=>"gbk", + "csiso58gb231280"=>"gbk", + "gb2312"=>"gbk", + "gb_2312"=>"gbk", + "gb_2312-80"=>"gbk", + "gbk"=>"gbk", + "iso-ir-58"=>"gbk", + "x-gbk"=>"gbk", + "gb18030"=>"gb18030", + "big5"=>"big5", + "big5-hkscs"=>"big5", + "cn-big5"=>"big5", + "csbig5"=>"big5", + "x-x-big5"=>"big5", + "cseucpkdfmtjapanese"=>"cp51932", + "euc-jp"=>"cp51932", + "x-euc-jp"=>"cp51932", + "csiso2022jp"=>"cp50221", + "iso-2022-jp"=>"cp50221", + "csshiftjis"=>"Windows-31J", + "ms932"=>"Windows-31J", + "ms_kanji"=>"Windows-31J", + "shift-jis"=>"Windows-31J", + "shift_jis"=>"Windows-31J", + "sjis"=>"Windows-31J", + "windows-31j"=>"Windows-31J", + "x-sjis"=>"Windows-31J", + "cseuckr"=>"euc-kr", + "csksc56011987"=>"euc-kr", + "euc-kr"=>"euc-kr", + "iso-ir-149"=>"euc-kr", + "korean"=>"euc-kr", + "ks_c_5601-1987"=>"euc-kr", + "ks_c_5601-1989"=>"euc-kr", + "ksc5601"=>"euc-kr", + "ksc_5601"=>"euc-kr", + "windows-949"=>"euc-kr", + "utf-16be"=>"utf-16be", + "utf-16"=>"utf-16le", + "utf-16le"=>"utf-16le", + } # :nodoc: + Ractor.make_shareable(WEB_ENCODINGS_) if defined?(Ractor) + + # :nodoc: + # return encoding or nil + # http://encoding.spec.whatwg.org/#concept-encoding-get + def self.get_encoding(label) + Encoding.find(WEB_ENCODINGS_[label.to_str.strip.downcase]) rescue nil end - -=begin - ---- URI::regexp([match_schemes]) - - Returns a Regexp object which matches to URI-like strings. - If MATCH_SCHEMES given, resulting regexp matches to URIs - whose scheme is one of the MATCH_SCHEMES. - - The Regexp object returned by this method includes arbitrary - number of capture group (parentheses). Never rely on its - number. - - # extract first URI from html_string - html_string.slice(URI.regexp) - - # remove ftp URIs - html_string.sub(URI.regexp(['ftp']) - - # You should not rely on the number of parentheses - html_string.scan(URI.regexp) do |*matches| - p $& - end - -=end - def self.regexp(schemes = nil) - unless schemes - ABS_URI_REF +end # module URI + +module Kernel + + # + # 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) + uri + elsif uri = String.try_convert(uri) + URI.parse(uri) else - /(?=#{Regexp.union(*schemes)}:)#{PATTERN::X_ABS_URI}/xn + raise ArgumentError, + "bad argument (expected URI object or URI string)" end end - -end # URI + module_function :URI +end |