diff options
Diffstat (limited to 'lib/uri')
| -rw-r--r-- | lib/uri/common.rb | 1232 | ||||
| -rw-r--r-- | lib/uri/file.rb | 100 | ||||
| -rw-r--r-- | lib/uri/ftp.rb | 266 | ||||
| -rw-r--r-- | lib/uri/generic.rb | 1810 | ||||
| -rw-r--r-- | lib/uri/http.rb | 167 | ||||
| -rw-r--r-- | lib/uri/https.rb | 29 | ||||
| -rw-r--r-- | lib/uri/ldap.rb | 192 | ||||
| -rw-r--r-- | lib/uri/ldaps.rb | 22 | ||||
| -rw-r--r-- | lib/uri/mailto.rb | 351 | ||||
| -rw-r--r-- | lib/uri/rfc2396_parser.rb | 547 | ||||
| -rw-r--r-- | lib/uri/rfc3986_parser.rb | 206 | ||||
| -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, 3637 insertions, 1439 deletions
diff --git a/lib/uri/common.rb b/lib/uri/common.rb index 5d6a3b5519..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 @@ -242,183 +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 + + def register(name, klass) + unless scheme = escape(name) + raise ArgumentError, "invalid character as scheme - #{name}" + end + const_set(scheme, klass) end - end - alias encode escape - def unescape(str) - str.gsub(ESCAPED) do - $&[1,2].hex.chr + 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 = []) - urls = [] - regexp = ABS_URI_REF - unless schemes.empty? - regexp = Regexp.new('(?=' + schemes.collect{|s| - Regexp.quote(s + ':') - }.join('|') + ')' + PATTERN::X_ABS_URI, - Regexp::EXTENDED, 'N') - end - - str.scan(regexp) { - if block_given? - yield($&) - else - urls << $& - end - } - - if block_given? - return nil + 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 +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 - return urls + raise ArgumentError, + "bad argument (expected URI object or URI string)" end end - -end # URI + module_function :URI +end 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 391cd550e9..1c75e242ba 100644 --- a/lib/uri/ftp.rb +++ b/lib/uri/ftp.rb @@ -1,149 +1,267 @@ +# frozen_string_literal: false +# = uri/ftp.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 # -require 'uri/generic' +require_relative 'generic' module URI -=begin - -== URI::FTP - -=== Super Class - -((<URI::Generic>)) - -=end - - # RFC1738 section 3.2. + # + # FTP URI syntax is defined by RFC1738 section 3.2. + # + # 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. + # https://datatracker.ietf.org/doc/html/draft-hoffman-ftp-uri-04 + # class FTP < Generic + # A Default port of 21 for URI::FTP. DEFAULT_PORT = 21 + # + # An Array of the available components for URI::FTP. + # COMPONENT = [ - :scheme, + :scheme, :userinfo, :host, :port, :path, :typecode ].freeze + # + # Typecode is "a", "i", or "d". + # + # * "a" indicates a text file (the FTP command was ASCII) + # * "i" indicates a binary file (FTP command IMAGE) + # * "d" indicates the contents of a directory should be displayed + # TYPECODE = ['a', 'i', 'd'].freeze - TYPECODE_PREFIX = ';type='.freeze - -=begin -=== Class Methods - ---- URI::FTP::build - Create a new URI::FTP object from components of URI::FTP with - check. It is scheme, userinfo, host, port, path and typecode. It - provided by an Array or a Hash. typecode is "a", "i" or "d". - ---- URI::FTP::new - Create a new URI::FTP object from ``generic'' components with no - check. - -=end + # Typecode prefix ";type=". + TYPECODE_PREFIX = ';type='.freeze - def self.new2(user, password, host, port, path, - typecode = nil, arg_check = true) + def self.new2(user, password, host, port, path, + typecode = nil, arg_check = true) # :nodoc: + # Do not use this method! Not tested. [Bug #7301] + # This methods remains just for compatibility, + # Keep it undocumented until the active maintainer is assigned. typecode = nil if typecode.size == 0 if typecode && !TYPECODE.include?(typecode) - raise ArgumentError, - "bad typecode is specified: #{typecode}" + raise ArgumentError, + "bad typecode is specified: #{typecode}" end # do escape self.new('ftp', - [user, password], - host, port, nil, - typecode ? path + TYPECODE_PREFIX + typecode : path, - nil, nil, nil, arg_check) + [user, password], + host, port, nil, + typecode ? path + TYPECODE_PREFIX + typecode : path, + nil, nil, nil, arg_check) end + # + # == Description + # + # Creates a new URI::FTP object from components, with syntax checking. + # + # 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 <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: + # + # require 'uri' + # + # uri1 = URI::FTP.build(['user:password', 'ftp.example.com', nil, + # '/path/file.zip', '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'}) + # uri2.to_s # => "ftp://ftp.example.com/ruby/src" + # def self.build(args) + + # Fix the incoming path to be generic URL syntax + # FTP path -> URL path + # foo/bar /foo/bar + # /foo/bar /%2Ffoo/bar + # + if args.kind_of?(Array) + args[3] = '/' + args[3].sub(/^\//, '%2F') + else + args[:path] = '/' + args[:path].sub(/^\//, '%2F') + end + tmp = Util::make_components_hash(self, args) if tmp[:typecode] - if tmp[:typecode].size == 1 - tmp[:typecode] = TYPECODE_PREFIX + tmp[:typecode] - end - tmp[:path] << tmp[:typecode] + if tmp[:typecode].size == 1 + tmp[:typecode] = TYPECODE_PREFIX + tmp[:typecode] + end + tmp[:path] << tmp[:typecode] end return super(tmp) end - def initialize(*arg) - super(*arg) + # + # == Description + # + # Creates a new URI::FTP object from generic URL components with no + # syntax checking. + # + # Unlike build(), this method does not escape the path component as + # 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. + # + def initialize(scheme, + userinfo, host, port, registry, + path, opaque, + query, + fragment, + parser = nil, + arg_check = false) + raise InvalidURIError unless path + path = path.sub(/^\//,'') + path.sub!(/^%2F/,'/') + super(scheme, userinfo, host, port, registry, path, opaque, + query, fragment, parser, arg_check) @typecode = nil - tmp = @path.index(TYPECODE_PREFIX) - if tmp - typecode = @path[tmp + TYPECODE_PREFIX.size..-1] - self.set_path(@path[0..tmp - 1]) - - if arg[-1] - self.typecode = typecode - else - self.set_typecode(typecode) - end + if tmp = @path.index(TYPECODE_PREFIX) + typecode = @path[tmp + TYPECODE_PREFIX.size..-1] + @path = @path[0..tmp - 1] + + if arg_check + self.typecode = typecode + else + self.set_typecode(typecode) + end end end - attr_reader :typecode + # typecode accessor. # - # methods for typecode - # + # See URI::FTP::COMPONENT. + attr_reader :typecode + # Validates typecode +v+, + # returns +true+ or +false+. + # def check_typecode(v) if TYPECODE.include?(v) - return true + return true else - raise InvalidComponentError, - "bad typecode(expected #{TYPECODE.join(', ')}): #{v}" + raise InvalidComponentError, + "bad typecode(expected #{TYPECODE.join(', ')}): #{v}" end end private :check_typecode + # Private setter for the typecode +v+. + # + # See also URI::FTP.typecode=. + # def set_typecode(v) @typecode = v end protected :set_typecode + # + # == Args + # + # +v+:: + # String + # + # == Description + # + # Public setter for the typecode +v+ + # (with validation). + # + # See also URI::FTP.check_typecode. + # + # == Usage + # + # require 'uri' + # + # uri = URI.parse("ftp://john@ftp.example.com/my_file.img") + # #=> #<URI::FTP ftp://john@ftp.example.com/my_file.img> + # uri.typecode = "i" + # uri + # #=> #<URI::FTP ftp://john@ftp.example.com/my_file.img;type=i> + # def typecode=(typecode) check_typecode(typecode) set_typecode(typecode) + typecode end -=begin -=end - def merge(oth) + def merge(oth) # :nodoc: tmp = super(oth) if self != tmp - tmp.set_typecode(oth.typecode) + tmp.set_typecode(oth.typecode) end return tmp end -=begin -=end - def to_str + # Returns the path from an FTP 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: + # + # <code>ftp://ftp.example.com/pub/ruby</code> + # + # The above URI indicates that the client should connect to + # 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: + # + # <code>ftp://ftp.example.com/%2Fpub/ruby</code> + # + # This method will then return "/pub/ruby". + # + def path + return @path.sub(/^\//,'').sub(/^%2F/,'/') + end + + # 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. + def to_s save_path = nil if @typecode - save_path = @path - @path = @path + TYPECODE_PREFIX + @typecode + save_path = @path + @path = @path + TYPECODE_PREFIX + @typecode end str = super if @typecode - @path = save_path + @path = save_path end return str end - end # FTP - @@schemes['FTP'] = FTP -end # URI + end + + register_scheme 'FTP', FTP +end diff --git a/lib/uri/generic.rb b/lib/uri/generic.rb index 4a671e9ed5..6a0f638d76 100644 --- a/lib/uri/generic.rb +++ b/lib/uri/generic.rb @@ -1,140 +1,178 @@ +# frozen_string_literal: true + +# = uri/generic.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 # -require 'uri/common' +require_relative 'common' +autoload :IPSocket, 'socket' +autoload :IPAddr, 'ipaddr' module URI -=begin - -== URI::Generic - -=== Super Class - -Object - -=end - + # + # Base class for all URI classes. + # Implements generic URI syntax as per RFC 2396. + # class Generic include URI - include REGEXP - -=begin - -=== Class Methods ---- URI::Generic::default_port - -=end + # + # A Default port of nil for URI::Generic. + # DEFAULT_PORT = nil + # + # Returns default port. + # def self.default_port self::DEFAULT_PORT end + # + # Returns default port. + # def default_port self.class.default_port end -=begin ---- URI::Generic::component -=end + # + # An Array of the available components for URI::Generic. + # COMPONENT = [ - :scheme, - :userinfo, :host, :port, :registry, - :path, :opaque, - :query, + :scheme, + :userinfo, :host, :port, :registry, + :path, :opaque, + :query, :fragment ].freeze + # + # Components of the URI in the order. + # def self.component self::COMPONENT end -=begin ---- URI::Generic::use_registry -=end - USE_REGISTRY = false + USE_REGISTRY = false # :nodoc: - def self.use_registry + def self.use_registry # :nodoc: self::USE_REGISTRY end -=begin - ---- URI::Generic::build2 - At first, try to create a new URI::Generic object using - URI::Generic::build. But, if you get a exception - URI::InvalidComponentError, then re-try to create an object with - escaped components. - ---- URI::Generic::build - Create a new URI::Generic object from components of URI::Generic - with check. It is scheme, userinfo, host, port, registry, path, - opaque, query and fragment. It provided by an Array of a Hash. - ---- URI::Generic::new - Create new URI::Generic object from ``generic'' components with no - check. - -=end + # + # == Synopsis + # + # 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 does URI::RFC2396_PARSER.escape all URI components and tries again. + # def self.build2(args) begin - return self.build(args) + return self.build(args) rescue InvalidComponentError - if args.kind_of?(Array) - return self.build(args.collect{|x| - if x - URI.escape(x) - else - x - end - }) - elsif args.kind_of?(Hash) - tmp = {} - args.each do |key, value| - tmp[key] = if value - URI.escape(value) - else - value - end - end - return self.build(tmp) - end + if args.kind_of?(Array) + return self.build(args.collect{|x| + if x.is_a?(String) + URI::RFC2396_PARSER.escape(x) + else + x + end + }) + elsif args.kind_of?(Hash) + tmp = {} + args.each do |key, value| + tmp[key] = if value + URI::RFC2396_PARSER.escape(value) + else + value + end + end + return self.build(tmp) + end end end + # + # == Synopsis + # + # 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. + # def self.build(args) if args.kind_of?(Array) && - args.size == ::URI::Generic::COMPONENT.size - tmp = args + args.size == ::URI::Generic::COMPONENT.size + tmp = args.dup elsif args.kind_of?(Hash) - tmp = ::URI::Generic::COMPONENT.collect do |c| - if args.include?(c) - args[c] - else - nil - end - end + tmp = ::URI::Generic::COMPONENT.collect do |c| + if args.include?(c) + args[c] + else + nil + end + end else - raise ArgumentError, - "expected Array of or Hash of components of #{self.class} (#{self.class.component.join(', ')})" + component = self.component rescue ::URI::Generic::COMPONENT + raise ArgumentError, + "expected Array of or Hash of components of #{self} (#{component.join(', ')})" end + tmp << nil tmp << true return self.new(*tmp) end - def initialize(scheme, - userinfo, host, port, registry, - path, opaque, - query, - fragment, - arg_check = false) + # + # == Args + # + # +scheme+:: + # Protocol scheme, i.e. 'http','ftp','mailto' and so on. + # +userinfo+:: + # User name and password, i.e. 'sdmitry:bla'. + # +host+:: + # Server host name. + # +port+:: + # Server port. + # +registry+:: + # Registry of naming authorities. + # +path+:: + # Path on server. + # +opaque+:: + # Opaque part. + # +query+:: + # Query data. + # +fragment+:: + # Part of the URI after '#' character. + # +parser+:: + # Parser for internal use [URI::DEFAULT_PARSER by default]. + # +arg_check+:: + # Check arguments [false by default]. + # + # == Description + # + # Creates a new URI::Generic instance from ``generic'' components without check. + # + def initialize(scheme, + userinfo, host, port, registry, + path, opaque, + query, + fragment, + parser = DEFAULT_PARSER, + arg_check = false) @scheme = nil @user = nil @password = nil @@ -143,1004 +181,1412 @@ Object @path = nil @query = nil @opaque = nil - @registry = nil @fragment = nil + @parser = parser == DEFAULT_PARSER ? nil : parser if arg_check - self.scheme = scheme - self.userinfo = userinfo - self.host = host - self.port = port - self.path = path - self.query = query - self.opaque = opaque - self.registry = registry - self.fragment = fragment + self.scheme = scheme + 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_path(path) - self.set_query(query) - self.set_opaque(opaque) - self.set_registry(registry) - self.set_fragment(fragment) + self.set_scheme(scheme) + self.set_host(host) + self.set_port(port) + self.set_userinfo(userinfo) + self.set_path(path) + self.query = query + self.set_opaque(opaque) + self.fragment=(fragment) end - if @registry && !self.class.use_registry - raise InvalidURIError, "the scheme #{@scheme} does not accept registry part: #{@registry} (or bad hostname?)" + if registry + raise InvalidURIError, + "the scheme #{@scheme} does not accept registry part: #{registry} (or bad hostname?)" end - - @scheme.freeze if @scheme + + @scheme&.freeze self.set_path('') if !@path && !@opaque # (see RFC2396 Section 5.2) self.set_port(self.default_port) if self.default_port && !@port end + + # + # Returns the scheme component of the URI. + # + # URI("http://foo/bar/baz").scheme #=> "http" + # attr_reader :scheme + + # Returns the host component of the URI. + # + # URI("http://foo/bar/baz").host #=> "foo" + # + # It returns nil if no host component exists. + # + # URI("mailto:foo@example.org").host #=> nil + # + # The component does not contain the port number. + # + # URI("http://foo:8080/bar/baz").host #=> "foo" + # + # 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").hostname #=> "::1" + # attr_reader :host + + # Returns the port component of the URI. + # + # URI("http://foo/bar/baz").port #=> 80 + # URI("http://foo:8080/bar/baz").port #=> 8080 + # attr_reader :port - attr_reader :registry + + def registry # :nodoc: + nil + end + + # 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. + # + # URI("http://foo/bar/baz?search=FooBar").query #=> "search=FooBar" + # attr_reader :query + + # Returns the opaque part of the URI. + # + # URI("mailto:foo@example.org").opaque #=> "foo@example.org" + # URI("http://foo/bar/baz").opaque #=> nil + # + # 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. + # + # URI("http://foo/bar/baz?search=FooBar#ponies").fragment #=> "ponies" + # attr_reader :fragment - # replace self by other URI object + # Returns the parser to be used. + # + # Unless the +parser+ is defined, DEFAULT_PARSER is used. + # + def parser + if !defined?(@parser) || !@parser + DEFAULT_PARSER + else + @parser || DEFAULT_PARSER + end + end + + # Replaces self by other URI object. + # def replace!(oth) if self.class != oth.class - raise ArgumentError, "expected #{self.class} object" + raise ArgumentError, "expected #{self.class} object" end component.each do |c| - self.__send__("#{c}=", oth.__send__(c)) + self.__send__("#{c}=", oth.__send__(c)) end end private :replace! -=begin - -=== Instance Methods - -=end - -=begin - ---- URI::Generic#component - -=end + # + # Components of the URI in the order. + # def component self.class.component end - # set_XXX method sets value to @XXX instance variable with no check, - # so be careful if you use these methods. or, you use these method - # with check_XXX method, or you use XXX= methods. - -=begin - ---- URI::Generic#scheme - ---- URI::Generic#scheme=(v) - -=end # - # methods for scheme + # Checks the scheme +v+ component against the +parser+ Regexp for :SCHEME. # def check_scheme(v) - if v && SCHEME !~ v - raise InvalidComponentError, - "bad component(expected scheme component): #{v}" + if v && parser.regexp[:SCHEME] !~ v + raise InvalidComponentError, + "bad component(expected scheme component): #{v}" end return true end private :check_scheme + # Protected setter for the scheme component +v+. + # + # See also URI::Generic.scheme=. + # def set_scheme(v) - @scheme = v + @scheme = v&.downcase end protected :set_scheme + # + # == Args + # + # +v+:: + # String + # + # == Description + # + # Public setter for the scheme component +v+ + # (with validation). + # + # See also URI::Generic.check_scheme. + # + # == Usage + # + # require 'uri' + # + # uri = URI.parse("http://my.example.com") + # uri.scheme = "https" + # uri.to_s #=> "https://my.example.com" + # def scheme=(v) check_scheme(v) set_scheme(v) + v end -=begin - ---- URI::Generic#userinfo - ---- URI::Generic#userinfo=(v) - ---- URI::Generic#user - ---- URI::Generic#user=(v) - ---- URI::Generic#password - ---- URI::Generic#password=(v) - -=end # - # methods for userinfo + # 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. # def check_userinfo(user, password = nil) - if (user || password) && - (@registry || @opaque) - raise InvalidURIError, - "can not set userinfo with registry or opaque" - end - if !password - user, password = split_userinfo(user) + user, password = split_userinfo(user) end check_user(user) - check_password(password) + check_password(password, user) return true end private :check_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. + # def check_user(v) + if @opaque + raise InvalidURIError, + "cannot set user with opaque" + end + return v unless v - if USERINFO !~ v - raise InvalidComponentError, - "bad component(expected userinfo component or user component): #{v}" + if parser.regexp[:USERINFO] !~ v + raise InvalidComponentError, + "bad component(expected userinfo component or user component): #{v}" end return true end private :check_user - def check_password(v) + # + # 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. + # + def check_password(v, user = @user) + if @opaque + raise InvalidURIError, + "cannot set password with opaque" + end return v unless v - if !@password - raise InvalidURIError, - "password component depends user component" + if !user + raise InvalidURIError, + "password component depends user component" end - if USERINFO !~ v - raise InvalidComponentError, - "bad component(expected user component): #{v}" + if parser.regexp[:USERINFO] !~ v + raise InvalidComponentError, + "bad password component" end return true end private :check_password + # + # Sets userinfo, argument is string like 'name:pass'. + # def userinfo=(userinfo) if userinfo.nil? - return nil + return nil end check_userinfo(*userinfo) set_userinfo(*userinfo) + # returns userinfo end + # + # == Args + # + # +v+:: + # String + # + # == Description + # + # Public setter for the +user+ component + # (with validation). + # + # See also URI::Generic.check_user. + # + # == Usage + # + # require 'uri' + # + # uri = URI.parse("http://john:S3nsit1ve@my.example.com") + # uri.user = "sam" + # uri.to_s #=> "http://sam@my.example.com" + # def user=(user) check_user(user) set_user(user) + # returns user end + # + # == Args + # + # +v+:: + # String + # + # == Description + # + # Public setter for the +password+ component + # (with validation). + # + # See also URI::Generic.check_password. + # + # == Usage + # + # require 'uri' + # + # uri = URI.parse("http://john:S3nsit1ve@my.example.com") + # uri.password = "V3ry_S3nsit1ve" + # uri.to_s #=> "http://john:V3ry_S3nsit1ve@my.example.com" + # def password=(password) check_password(password) set_password(password) + # returns password end + # Protected setter for the +user+ component, and +password+ if available + # (with validation). + # + # See also URI::Generic.userinfo=. + # def set_userinfo(user, password = nil) - unless password - user, password = split_userinfo(user) + 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+. + # + # 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+. + # + # See also URI::Generic.password=. + # def set_password(v) - set_userinfo(@user, v) - v + @password = v + # returns v end protected :set_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 - tmp = ui.index(':') - if tmp - user = ui[0..tmp - 1] - password = ui[tmp + 1..-1] - else - user = ui - password = nil - end + user, password = ui.split(':', 2) return user, password end private :split_userinfo + # Escapes 'user:password' +v+ based on RFC 1738 section 3.1. def escape_userpass(v) - v = URI.escape(v, /[@:\/]/o) # RFC 1738 section 3.1 #/ + parser.escape(v, /[@:\/]/o) # RFC 1738 section 3.1 #/ end private :escape_userpass + # Returns the userinfo, either as 'user' or 'user:password'. def userinfo - if !@password - @user + if @user.nil? + nil + elsif @password.nil? + @user else - @user + ':' + @password + @user + ':' + @password end end + # Returns the user component (without URI decoding). def user @user end + # Returns the password component (without URI decoding). def password @password end -=begin + # 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 ---- URI::Generic#host + # Returns the user component after URI decoding. + def decoded_user + URI.decode_uri_component(@user) if @user + end ---- URI::Generic#host=(v) + # Returns the password component after URI decoding. + def decoded_password + URI.decode_uri_component(@password) if @password + end -=end # - # methods 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. # - def check_host(v) return v unless v - if @registry || @opaque - raise InvalidURIError, - "can not set host with registry or opaque" - elsif HOST !~ v - raise InvalidComponentError, - "bad component(expected host component): #{v}" + if @opaque + raise InvalidURIError, + "cannot set host with registry or opaque" + elsif parser.regexp[:HOST] !~ v + raise InvalidComponentError, + "bad component(expected host component): #{v}" end return true end private :check_host + # Protected setter for the host component +v+. + # + # 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 + # + # +v+:: + # String + # + # == Description + # + # Public setter for the host component +v+ + # (with validation). + # + # See also URI::Generic.check_host. + # + # == Usage + # + # require 'uri' + # + # uri = URI.parse("http://my.example.com") + # uri.host = "foo.com" + # uri.to_s #=> "http://foo.com" + # def host=(v) check_host(v) set_host(v) + set_userinfo(nil) + v end -=begin - ---- URI::Generic#port - ---- URI::Generic#port=(v) + # Extract the host part of the URI and unwrap brackets for IPv6 addresses. + # + # This method is the same as URI::Generic#host except + # brackets for IPv6 (and future IP) addresses are removed. + # + # uri = URI("http://[::1]/bar") + # uri.hostname #=> "::1" + # uri.host #=> "[::1]" + # + def hostname + v = self.host + v&.start_with?('[') && v.end_with?(']') ? v[1..-2] : v + end -=end + # Sets the host part of the URI as the argument with brackets for IPv6 addresses. + # + # This method is the same as URI::Generic#host= except + # the argument can be a bare IPv6 address. + # + # uri = URI("http://foo/bar") + # uri.hostname = "::1" + # uri.to_s #=> "http://[::1]/bar" # - # methods for port + # If the argument seems to be an IPv6 address, + # it is wrapped with brackets. # + def hostname=(v) + v = "[#{v}]" if !(v&.start_with?('[') && v&.end_with?(']')) && v&.index(':') + self.host = v + end + # + # 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. + # def check_port(v) return v unless v - if @registry || @opaque - raise InvalidURIError, - "can not set port with registry or opaque" - elsif !v.kind_of?(Fixnum) && PORT !~ v - raise InvalidComponentError, - "bad component(expected port component): #{v}" + if @opaque + raise InvalidURIError, + "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}" end return true end private :check_port + # Protected setter for the port component +v+. + # + # See also URI::Generic.port=. + # def set_port(v) - unless !v || v.kind_of?(Fixnum) - if v.empty? - v = nil - else - v = v.to_i - end - end + v = v.empty? ? nil : v.to_i unless !v || v.kind_of?(Integer) @port = v end protected :set_port + # + # == Args + # + # +v+:: + # String + # + # == Description + # + # Public setter for the port component +v+ + # (with validation). + # + # See also URI::Generic.check_port. + # + # == Usage + # + # require 'uri' + # + # uri = URI.parse("http://my.example.com") + # uri.port = 8080 + # uri.to_s #=> "http://my.example.com:8080" + # def port=(v) check_port(v) set_port(v) + set_userinfo(nil) + port end -=begin - ---- URI::Generic#registry - ---- URI::Generic#registry=(v) - -=end - # - # methods for registry - # - - def check_registry(v) - return v unless v - - # raise if both server and registry are not nil, because: - # authority = server | reg_name - # server = [ [ userinfo "@" ] hostport ] - if @host || @port || @user # userinfo = @user + ':' + @password - raise InvalidURIError, - "can not set registry with host, port, or userinfo" - elsif v && REGISTRY !~ v - raise InvalidComponentError, - "bad component(expected registry component): #{v}" - end - - return true + def check_registry(v) # :nodoc: + raise InvalidURIError, "cannot set registry" end private :check_registry - def set_registry(v) - @registry = v + def set_registry(v) # :nodoc: + raise InvalidURIError, "cannot set registry" end protected :set_registry - def registry=(v) - check_registry(v) - set_registry(v) + def registry=(v) # :nodoc: + raise InvalidURIError, "cannot set registry" end -=begin - ---- URI::Generic#path - ---- URI::Generic#path=(v) - -=end # - # methods for 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. # - def check_path(v) # raise if both hier and opaque are not nil, because: # absoluteURI = scheme ":" ( hier_part | opaque_part ) # hier_part = ( net_path | abs_path ) [ "?" query ] if v && @opaque - raise InvalidURIError, - "path conflicts with opaque" + raise InvalidURIError, + "path conflicts with opaque" end - if @scheme - if v && v != '' && ABS_PATH !~ v - raise InvalidComponentError, - "bad component(expected absolute path component): #{v}" - end + # If scheme is ftp, path may be relative. + # See RFC 1738 section 3.2.2, and RFC 2396. + if @scheme && @scheme != "ftp" + if v && v != '' && parser.regexp[:ABS_PATH] !~ v + raise InvalidComponentError, + "bad component(expected absolute path component): #{v}" + end else - if v && v != '' && ABS_PATH !~ v && REL_PATH !~ v - raise InvalidComponentError, - "bad component(expected relative path component): #{v}" - end + if v && v != '' && parser.regexp[:ABS_PATH] !~ v && + parser.regexp[:REL_PATH] !~ v + raise InvalidComponentError, + "bad component(expected relative path component): #{v}" + end end return true end private :check_path + # Protected setter for the path component +v+. + # + # See also URI::Generic.path=. + # def set_path(v) @path = v end protected :set_path + # + # == Args + # + # +v+:: + # String + # + # == Description + # + # Public setter for the path component +v+ + # (with validation). + # + # See also URI::Generic.check_path. + # + # == Usage + # + # require 'uri' + # + # uri = URI.parse("http://my.example.com/pub/files") + # uri.path = "/faq/" + # uri.to_s #=> "http://my.example.com/faq/" + # def path=(v) check_path(v) set_path(v) + v end -=begin - ---- URI::Generic#query - ---- URI::Generic#query=(v) - -=end # - # methods for query + # == Args + # + # +v+:: + # String + # + # == Description + # + # Public setter for the query component +v+. + # + # == Usage + # + # require 'uri' + # + # uri = URI.parse("http://my.example.com/?id=25") + # uri.query = "id=1" + # uri.to_s #=> "http://my.example.com/?id=1" # - - def check_query(v) - return v unless v - - # raise if both hier and opaque are not nil, because: - # absoluteURI = scheme ":" ( hier_part | opaque_part ) - # hier_part = ( net_path | abs_path ) [ "?" query ] - if @opaque - raise InvalidURIError, - "query conflicts with opaque" - end - - if v && v != '' && QUERY !~ v - raise InvalidComponentError, - "bad component(expected query component): #{v}" - end - - return true - end - private :check_query - - def set_query(v) - @query = v - end - protected :set_query - def query=(v) - check_query(v) - set_query(v) + return @query = nil unless v + raise InvalidURIError, "query conflicts with opaque" if @opaque + + x = v.to_str + v = x.dup if x.equal? v + 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 -=begin - ---- URI::Generic#opaque - ---- URI::Generic#opaque=(v) - -=end # - # methods 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, + # with an opaque component defined. # - def check_opaque(v) return v unless v # raise if both hier and opaque are not nil, because: # absoluteURI = scheme ":" ( hier_part | opaque_part ) # hier_part = ( net_path | abs_path ) [ "?" query ] - if @host || @port || @usr || @path # userinfo = @user + ':' + @password - raise InvalidURIError, - "can not set opaque with host, port, userinfo or path" - elsif v && OPAQUE !~ v - raise InvalidComponentError, - "bad component(expected opaque component): #{v}" + if @host || @port || @user || @path # userinfo = @user + ':' + @password + raise InvalidURIError, + "cannot set opaque with host, port, userinfo or path" + elsif v && parser.regexp[:OPAQUE] !~ v + raise InvalidComponentError, + "bad component(expected opaque component): #{v}" end return true end private :check_opaque + # Protected setter for the opaque component +v+. + # + # See also URI::Generic.opaque=. + # def set_opaque(v) @opaque = v end protected :set_opaque + # + # == Args + # + # +v+:: + # String + # + # == Description + # + # Public setter for the opaque component +v+ + # (with validation). + # + # See also URI::Generic.check_opaque. + # def opaque=(v) check_opaque(v) set_opaque(v) + v end -=begin - ---- URI::Generic#fragment - ---- URI::Generic#fragment=(v) - -=end # - # methods for fragment + # Checks the fragment +v+ component against the +parser+ Regexp for :FRAGMENT. + # + # + # == Args + # + # +v+:: + # String + # + # == Description + # + # Public setter for the fragment component +v+ + # (with validation). + # + # == Usage + # + # require 'uri' + # + # uri = URI.parse("http://my.example.com/?id=25#time=1305212049") + # uri.fragment = "time=1305212086" + # uri.to_s #=> "http://my.example.com/?id=25#time=1305212086" # - - def check_fragment(v) - return v unless v - - if v && v != '' && FRAGMENT !~ v - raise InvalidComponentError, - "bad component(expected fragment component): #{v}" - end - - return true - end - private :check_fragment - - def set_fragment(v) - @fragment = v - end - protected :set_fragment - def fragment=(v) - check_fragment(v) - set_fragment(v) + return @fragment = nil unless v + + x = v.to_str + v = x.dup if x.equal? v + v.encode!(Encoding::UTF_8) rescue nil + v.delete!("\t\r\n") + v.force_encoding(Encoding::ASCII_8BIT) + v.gsub!(/(?!%\h\h|[!-~])./n){'%%%02X' % $&.ord} + v.force_encoding(Encoding::US_ASCII) + @fragment = v end -=begin - ---- URI::Generic#hierarchical? - -=end + # + # 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 - true + true else - false + false end end -=begin - ---- URI::Generic#absolute? - -=end + # + # Returns true if URI has a scheme (e.g. http:// or https://) specified. + # def absolute? if @scheme - true + true else - false + false end end alias absolute absolute? -=begin - ---- URI::Generic#relative? - -=end + # + # Returns true if URI does not have a scheme (e.g. http:// or https://) specified. + # def relative? !absolute? end -=begin - ---- URI::Generic#merge(rel) ---- URI::Generic#merge!(rel) ---- URI::Generic#+(rel) - -=end + # + # Returns an Array of the path split on '/'. + # def split_path(path) - path.split(%r{/+}, -1) + path.split("/", -1) end private :split_path + # + # Merges a base path +base+, with relative path +rel+, + # returns a modified base path. + # def merge_path(base, rel) + # RFC2396, Section 5.2, 5) - if rel[0] == ?/ #/ - # RFC2396, Section 5.2, 5) - return rel + # RFC2396, Section 5.2, 6) + base_path = split_path(base) + rel_path = split_path(rel) + + # RFC2396, Section 5.2, 6), a) + base_path << '' if base_path.last == '..' + while i = base_path.index('..') + base_path.slice!(i - 1, 2) + end - else - # RFC2396, Section 5.2, 6) - base_path = split_path(base) - rel_path = split_path(rel) - - if base_path.empty? - base_path = [''] # XXX - end - - # RFC2396, Section 5.2, 6), a) - base_path.pop unless base_path.size == 1 - - # RFC2396, Section 5.2, 6), c) - # RFC2396, Section 5.2, 6), d) - rel_path.push('') if rel_path.last == '.' - rel_path.delete('.') - - # RFC2396, Section 5.2, 6), e) - tmp = [] - rel_path.each do |x| - if x == '..' && - !(tmp.empty? || tmp.last == '..') - tmp.pop - else - tmp << x - end - end - - add_trailer_slash = true - while x = tmp.shift - if x == '..' && base_path.size > 1 - # RFC2396, Section 4 - # a .. or . in an absolute path has no special meaning - base_path.pop - else - # if x == '..' - # valid absolute (but abnormal) path "/../..." - # else - # valid absolute path - # end - base_path << x - tmp.each {|t| base_path << t} - add_trailer_slash = false - break - end - end - base_path.push('') if add_trailer_slash - - return base_path.join('/') + if (first = rel_path.first) and first.empty? + base_path.clear + rel_path.shift end + + # RFC2396, Section 5.2, 6), c) + # RFC2396, Section 5.2, 6), d) + rel_path.push('') if rel_path.last == '.' || rel_path.last == '..' + rel_path.delete('.') + + # RFC2396, Section 5.2, 6), e) + tmp = [] + rel_path.each do |x| + if x == '..' && + !(tmp.empty? || tmp.last == '..') + tmp.pop + else + tmp << x + end + end + + add_trailer_slash = !tmp.empty? + if base_path.empty? + base_path = [''] # keep '/' for root directory + elsif add_trailer_slash + base_path.pop + end + while x = tmp.shift + if x == '..' + # RFC2396, Section 4 + # a .. or . in an absolute path has no special meaning + base_path.pop if base_path.size > 1 + else + # if x == '..' + # valid absolute (but abnormal) path "/../..." + # else + # valid absolute path + # end + base_path << x + tmp.each {|t| base_path << t} + add_trailer_slash = false + break + end + end + base_path.push('') if add_trailer_slash + + return base_path.join('/') end private :merge_path + # + # == Args + # + # +oth+:: + # URI or String + # + # == Description + # + # Destructive form of #merge. + # + # == Usage + # + # require 'uri' + # + # uri = URI.parse("http://my.example.com") + # uri.merge!("/main.rbx?page=1") + # uri.to_s # => "http://my.example.com/main.rbx?page=1" + # def merge!(oth) t = merge(oth) if self == t - nil + nil else - replace!(t) - self + replace!(t) + self end end - # abs(self) + rel(oth) => abs(new) + # + # == Args + # + # +oth+:: + # URI or String + # + # == Description + # + # Merges two URIs. + # + # == Usage + # + # require 'uri' + # + # uri = URI.parse("http://my.example.com") + # uri.merge("/main.rbx?page=1") + # # => "http://my.example.com/main.rbx?page=1" + # def merge(oth) - base, rel = merge0(oth) - if base == rel - return base + rel = parser.__send__(:convert_to_uri, oth) + + if rel.absolute? + #raise BadURIError, "both URI are absolute" if absolute? + # hmm... should return oth for usability? + return rel + end + + unless self.absolute? + raise BadURIError, "both URI are relative" end - authority = rel.userinfo || rel.host || rel.port + base = self.dup + + authority = rel.authority # RFC2396, Section 5.2, 2) - if rel.path.empty? && !authority && !rel.query - base.set_fragment(rel.fragment) if rel.fragment - return base + if (rel.path.nil? || rel.path.empty?) && !authority && !rel.query + base.fragment=(rel.fragment) if rel.fragment + return base end - base.set_query(nil) - base.set_fragment(nil) + base.query = nil + base.fragment=(nil) # RFC2396, Section 5.2, 4) - if !authority - base.set_path(merge_path(base.path, rel.path)) - else - # RFC2396, Section 5.2, 4) - base.set_path(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.set_query(rel.query) if rel.query - base.set_fragment(rel.fragment) if rel.fragment + base.query = rel.query if rel.query + base.fragment=(rel.fragment) if rel.fragment return base end # merge alias + merge - # return base and rel. - # you can modify `base', but can not `rel'. - def merge0(oth) - case oth - when Generic - when String - oth = URI.parse(oth) - else - raise ArgumentError, - "bad argument(expected URI object or URI string)" - end - - if self.relative? && oth.relative? - raise BadURIError, - "both URI are relative" - end - - if self.absolute? && oth.absolute? - #raise BadURIError, - # "both URI are absolute" - # hmm... should return oth for usability? - return oth, oth - end - - if !self.hierarchical? - raise BadURIError, - "not hierarchical URI: #{self}" - elsif !oth.hierarchical? - raise BadURIError, - "not hierarchical URI: #{oth}" - end - - if self.absolute? - return self.dup, oth - else - return oth, oth - end - end - private :merge0 - -=begin - ---- URI::Generic#route_from(src) ---- URI::Generic#-(src) - -=end + # :stopdoc: def route_from_path(src, dst) - # RFC2396, Section 4.2 - return '' if src == dst - - src_path = split_path(src) - dst_path = split_path(dst) - - # hmm... dst has abnormal absolute path, - # like "/./", "/../", "/x/../", ... - if dst_path.include?('..') || - dst_path.include?('.') - return dst.dup + case dst + when src + # RFC2396, Section 4.2 + return '' + when %r{(?:\A|/)\.\.?(?:/|\z)} + # dst has abnormal absolute path, + # like "/./", "/../", "/x/../", ... + return dst.dup end - src_path.pop + src_path = src.scan(%r{[^/]*/}) + dst_path = dst.scan(%r{[^/]*/?}) # discard same parts - while dst_path.first == src_path.first - break if dst_path.empty? - - src_path.shift - dst_path.shift + while !dst_path.empty? && dst_path.first == src_path.first + src_path.shift + dst_path.shift end - tmp = dst_path.join('/') + tmp = dst_path.join # calculate if src_path.empty? - if tmp.empty? - return './' - elsif dst_path.first.include?(':') # (see RFC2396 Section 5) - return './' + tmp - else - return tmp - end + if tmp.empty? + return './' + elsif dst_path.first.include?(':') # (see RFC2396 Section 5) + return './' + tmp + else + return tmp + end end return '../' * src_path.size + tmp end private :route_from_path + # :startdoc: + # :stopdoc: def route_from0(oth) - case oth - when Generic - when String - oth = URI.parse(oth) - else - raise ArgumentError, - "bad argument(expected URI object or URI string)" - end - + oth = parser.__send__(:convert_to_uri, oth) if self.relative? - raise BadURIError, - "relative URI: #{self}" + raise BadURIError, + "relative URI: #{self}" end if oth.relative? - raise BadURIError, - "relative URI: #{oth}" - end - - if !self.hierarchical? || !oth.hierarchical? - return self, self.dup + raise BadURIError, + "relative URI: #{oth}" end if self.scheme != oth.scheme - return oth, oth.dup + return self, self.dup end rel = URI::Generic.new(nil, # it is relative URI - self.userinfo, self.host, self.port, - self.registry, self.path, self.opaque, - self.query, self.fragment) + self.userinfo, self.host, self.port, + nil, self.path, self.opaque, + self.query, self.fragment, parser) if rel.userinfo != oth.userinfo || - rel.host != oth.host || - rel.port != oth.port - rel.set_port(nil) if rel.port == oth.default_port - return rel, rel + rel.host.to_s.downcase != oth.host.to_s.downcase || + rel.port != oth.port + + if self.userinfo.nil? && self.host.nil? + return self, self.dup + end + + rel.set_port(nil) if rel.port == oth.default_port + return rel, rel end rel.set_userinfo(nil) rel.set_host(nil) rel.set_port(nil) - if rel.path == oth.path - rel.set_path('') - rel.set_query(nil) if rel.query == oth.query - return rel, rel + if rel.path && rel.path == oth.path + rel.set_path('') + rel.query = nil if rel.query == oth.query + return rel, rel + elsif rel.opaque && rel.opaque == oth.opaque + rel.set_opaque('') + rel.query = nil if rel.query == oth.query + 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 + # :startdoc: - # calculate relative path from oth to self + # + # == Args + # + # +oth+:: + # URI or String + # + # == Description + # + # Calculates relative path from oth to self. + # + # == Usage + # + # require 'uri' + # + # uri = URI.parse('http://my.example.com/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'. - oth, rel = route_from0(oth) + # you can modify `rel', but cannot `oth'. + begin + oth, rel = route_from0(oth) + rescue + raise $!.class, $!.message + end if oth == rel - return rel + return rel end rel.set_path(route_from_path(oth.path, self.path)) if rel.path == './' && self.query - # "./?foo" -> "?foo" - rel.set_path('') + # "./?foo" -> "?foo" + rel.set_path('') end return rel end - # abs1 - abs2 => relative_path_to_abs1_from_abs2 - # (see http://www.nikonet.or.jp/spring/what_v/what_v_4.htm :-) - alias - route_from -=begin - ---- URI::Generic#route_to(dst) + alias - route_from -=end - # calculate relative path to oth from self + # + # == Args + # + # +oth+:: + # URI or String + # + # == Description + # + # Calculates relative path to oth from self. + # + # == Usage + # + # require 'uri' + # + # uri = URI.parse('http://my.example.com') + # uri.route_to('http://my.example.com/main.rbx?page=1') + # #=> #<URI::Generic /main.rbx?page=1> + # def route_to(oth) - case oth - when Generic - when String - oth = URI.parse(oth) - else - raise ArgumentError, - "bad argument(expected URI object or URI string)" - end - - oth.route_from(self) + parser.__send__(:convert_to_uri, oth).route_from(self) end -=begin - ---- URI::Generic#normalize ---- URI::Generic#normalize! - -=end + # + # 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 uri.normalize! uri end + # + # Destructive version of #normalize. + # def normalize! - if path && path == '' - set_path('/') + if path&.empty? + set_path('/') + end + if scheme && scheme != scheme.downcase + set_scheme(self.scheme.downcase) end if host && host != host.downcase - set_host(self.host.downcase) - end - end - -=begin - ---- URI::Generic#to_s - -=end - def path_query - str = @path - if @query - str += '?' + @query + set_host(self.host.downcase) end - str end - private :path_query - def to_str - str = '' + # + # Constructs String from URI. + # + def to_s + str = ''.dup if @scheme - str << @scheme - str << ':' + str << @scheme + str << ':' end if @opaque - str << @opaque - + str << @opaque else - if @registry - str << @registry - else - if @host - str << '//' - end - if self.userinfo - str << self.userinfo - str << '@' - end - if @host - str << @host - end - if @port && @port != self.default_port - str << ':' - str << @port.to_s - end - end - - str << path_query + if @host || %w[file postgres].include?(@scheme) + str << '//' + end + if self.userinfo + str << self.userinfo + str << '@' + end + if @host + str << @host + end + if @port && @port != self.default_port + str << ':' + str << @port.to_s + end + if (@host || @port) && !@path.empty? && !@path.start_with?('/') + str << '/' + end + str << @path + if @query + str << '?' + str << @query + end end - if @fragment - str << '#' - str << @fragment + str << '#' + str << @fragment end - str end + alias to_str to_s - def to_s - to_str - end - -=begin - ---- URI::Generic#==(oth) - -=end + # + # Compares two URIs. + # def ==(oth) - if oth.kind_of?(String) - oth = URI.parse(oth) - end - if self.class == oth.class - self.normalize.component_ary == oth.normalize.component_ary + self.normalize.component_ary == oth.normalize.component_ary else - false + false end end -=begin - ---- URI::Generic#===(oth) + # Returns the hash value. + def hash + self.component_ary.hash + end -=end -# def ===(oth) -# raise NotImplementedError -# 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 -=end + # 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 -=begin ---- URI::Generic#select(*components) -=end + # == Args + # + # +components+:: + # Multiple Symbol arguments defined in URI::HTTP. + # + # == Description + # + # Selects specified components from URI. + # + # == Usage + # + # require 'uri' + # + # uri = URI.parse('http://myuser:mypass@my.example.com/test.rbx') + # 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) - else - raise ArgumentError, - "expected of components of #{self.class} (#{self.class.component.join(', ')})" - end + if component.include?(c) + self.__send__(c) + else + raise ArgumentError, + "expected of components of #{self.class} (#{self.class.component.join(', ')})" + end end end -=begin -=end - def inspect - sprintf("#<%s:0x%x URL:%s>", self.class.to_s, self.object_id, self.to_s) + def inspect # :nodoc: + "#<#{self.class} #{self}>" end -=begin -=end + # + # == Args + # + # +v+:: + # URI or String + # + # == Description + # + # Attempts to parse other URI +oth+, + # returns [parsed_oth, self]. + # + # == Usage + # + # require 'uri' + # + # uri = URI.parse("http://my.example.com") + # uri.coerce("http://foo.com") + # #=> [#<URI::HTTP http://foo.com>, #<URI::HTTP http://my.example.com>] + # def coerce(oth) case oth when String - oth = URI.parse(oth) + oth = parser.parse(oth) else - super + super end return oth, self end - end # Generic -end # 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. + # + # Note that capitalized variables (HTTP_PROXY, FTP_PROXY, NO_PROXY, etc.) + # 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. + # So HTTP_PROXY is not used. + # http_proxy is not used too if the variable is case insensitive. + # CGI_HTTP_PROXY can be used instead. + def find_proxy(env=ENV) + raise BadURIError, "relative URI: #{self}" if self.relative? + name = self.scheme.downcase + '_proxy' + proxy_uri = nil + if name == 'http_proxy' && env.include?('REQUEST_METHOD') # CGI? + # HTTP_PROXY conflicts with *_proxy for proxy settings and + # HTTP_* for header information in CGI. + # So it should be careful to use it. + pairs = env.reject {|k, v| /\Ahttp_proxy\z/i !~ k } + case pairs.length + when 0 # no proxy setting anyway. + proxy_uri = nil + when 1 + k, _ = pairs.shift + if k == 'http_proxy' && env[k.upcase] == nil + # http_proxy is safe to use because ENV is case sensitive. + proxy_uri = env[name] + else + proxy_uri = nil + end + else # http_proxy is safe to use because ENV is case sensitive. + proxy_uri = env.to_hash[name] + end + if !proxy_uri + # Use CGI_HTTP_PROXY. cf. libwww-perl. + proxy_uri = env["CGI_#{name.upcase}"] + end + elsif name == '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 + proxy_uri = env[name] || env[name.upcase] + end + + if proxy_uri.nil? || proxy_uri.empty? + return nil + end + + if self.hostname + begin + addr = IPSocket.getaddress(self.hostname) + return nil if /\A127\.|\A::1\z/ =~ addr + rescue SocketError + end + end + + name = 'no_proxy' + if no_proxy = env[name] || env[name.upcase] + 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 3e5b209d49..3c41cd4e93 100644 --- a/lib/uri/http.rb +++ b/lib/uri/http.rb @@ -1,76 +1,137 @@ +# frozen_string_literal: false +# = uri/http.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 # -require 'uri/generic' +require_relative 'generic' module URI -=begin - -== URI::HTTP - -=== Super Class - -((<URI::Generic>)) - -=end - - # RFC1738 section 3.3. + # + # The syntax of HTTP URIs is defined in RFC1738 section 3.3. + # + # Note that the Ruby URI library allows HTTP 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 HTTP < Generic + # A Default port of 80 for URI::HTTP. DEFAULT_PORT = 80 - COMPONENT = [ - :scheme, - :userinfo, :host, :port, - :path, - :query, - :fragment + # An Array of the available components for URI::HTTP. + COMPONENT = %i[ + scheme + userinfo host port + path + query + fragment ].freeze -=begin - -=== Class Methods - ---- URI::HTTP::build - Create a new URI::HTTP object from components of URI::HTTP with - check. It is scheme, userinfo, host, port, path, query and - fragment. It provided by an Array of a Hash. - ---- URI::HTTP::new - Create a new URI::HTTP object from ``generic'' components with no - check. - -=end - + # + # == Description + # + # Creates a new URI::HTTP object from components, with syntax checking. + # + # 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 <code>[userinfo, host, port, path, query, fragment]</code>. + # + # Example: + # + # uri = URI::HTTP.build(host: 'www.example.com', path: '/foo/bar') + # + # uri = URI::HTTP.build([nil, "www.example.com", nil, "/path", + # "query", 'fragment']) + # + # Currently, if passed userinfo components this method generates + # invalid HTTP URIs as per RFC 1738. + # def self.build(args) - tmp = Util::make_components_hash(self, args) - return super(tmp) - end - - def initialize(*arg) - super(*arg) + tmp = Util.make_components_hash(self, args) + super(tmp) end -=begin + # Do not allow empty host names, as they are not allowed by RFC 3986. + def check_host(v) + ret = super -=== Instance Methods + if ret && v.empty? + raise InvalidComponentError, + "bad component(expected host component): #{v}" + end ---- URI::HTTP#request_uri + ret + end -=end + # + # == Description + # + # Returns the full path for an HTTP request, 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::HTTP.build(path: '/foo/bar', query: 'test=true') + # uri.request_uri # => "/foo/bar?test=true" + # def request_uri - r = path_query - if r[0] != ?/ - r = '/' + r + return unless @path + + url = @query ? "#@path?#@query" : @path.dup + url.start_with?(?/.freeze) ? url : ?/ + url + end + + # + # == Description + # + # Returns the authority for an HTTP uri, as defined in + # https://www.rfc-editor.org/rfc/rfc3986#section-3.2. + # + # + # Example: + # + # URI::HTTP.build(host: 'www.example.com', path: '/foo/bar').authority #=> "www.example.com" + # URI::HTTP.build(host: 'www.example.com', port: 8000, path: '/foo/bar').authority #=> "www.example.com:8000" + # URI::HTTP.build(host: 'www.example.com', port: 80, path: '/foo/bar').authority #=> "www.example.com" + # + def authority + if port == default_port + host + else + "#{host}:#{port}" end + end - r + # + # == Description + # + # Returns the origin for an HTTP uri, as defined in + # https://www.rfc-editor.org/rfc/rfc6454. + # + # + # Example: + # + # URI::HTTP.build(host: 'www.example.com', path: '/foo/bar').origin #=> "http://www.example.com" + # URI::HTTP.build(host: 'www.example.com', port: 8000, path: '/foo/bar').origin #=> "http://www.example.com:8000" + # URI::HTTP.build(host: 'www.example.com', port: 80, path: '/foo/bar').origin #=> "http://www.example.com" + # URI::HTTPS.build(host: 'www.example.com', path: '/foo/bar').origin #=> "https://www.example.com" + # + def origin + "#{scheme}://#{authority}" end - end # HTTP + end - @@schemes['HTTP'] = HTTP -end # URI + register_scheme 'HTTP', HTTP +end diff --git a/lib/uri/https.rb b/lib/uri/https.rb index 691198fafa..50a5cabaf8 100644 --- a/lib/uri/https.rb +++ b/lib/uri/https.rb @@ -1,26 +1,23 @@ +# frozen_string_literal: false +# = uri/https.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 # -require 'uri/http' +require_relative 'http' module URI -=begin - -== URI::HTTPS - -=== Super Class - -((<URI::HTTP>)) - -=end - + # The default port for HTTPS URIs is 443, and the scheme is 'https:' rather + # than 'http:'. Other than that, HTTPS URIs are identical to HTTP URIs; + # see URI::HTTP. class HTTPS < HTTP + # A Default port of 443 for URI::HTTPS DEFAULT_PORT = 443 end - @@schemes['HTTPS'] = HTTPS -end # URI + + register_scheme 'HTTPS', HTTPS +end diff --git a/lib/uri/ldap.rb b/lib/uri/ldap.rb index 2911aa5738..4544349f18 100644 --- a/lib/uri/ldap.rb +++ b/lib/uri/ldap.rb @@ -1,33 +1,31 @@ +# frozen_string_literal: false +# = uri/ldap.rb # -# $Id$ +# Author:: +# Takaaki Tateishi <ttate@jaist.ac.jp> +# Akira Yamada <akira@ruby-lang.org> +# 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. +# +# See URI for general documentation # -require 'uri/generic' +require_relative 'generic' module URI -=begin - -== URI::LDAP - -URI::LDAP is copyrighted free software by Takaaki Tateishi and akira yamada. - - Copyright (c) 2001 Takaaki Tateishi <ttate@jaist.ac.jp> and - akira yamada <akira@ruby-lang.org>. - You can redistribute it and/or modify it under the same term as Ruby. - -=== Super Class - -((<URI::Generic>)) - -=end - - # 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. DEFAULT_PORT = 389 - + + # An Array of the available components for URI::LDAP. COMPONENT = [ :scheme, :host, :port, @@ -38,33 +36,52 @@ URI::LDAP is copyrighted free software by Takaaki Tateishi and akira yamada. :extensions, ].freeze + # Scopes available for the starting point. + # + # * 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 - subtrees, all entries at all levels + # SCOPE = [ SCOPE_ONE = 'one', SCOPE_SUB = 'sub', SCOPE_BASE = 'base', ].freeze -=begin - -=== Class Methods - ---- URI::LDAP::build - ---- URI::LDAP::new - -=end - + # + # == Description + # + # Creates a new URI::LDAP object from components, with syntax checking. + # + # The components accepted are host, port, dn, attributes, + # scope, filter, and extensions. + # + # 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, port, dn, attributes, scope, filter, extensions]</code>. + # + # Example: + # + # uri = URI::LDAP.build({:host => 'ldap.example.com', + # :dn => '/dc=example'}) + # + # uri = URI::LDAP.build(["ldap.example.com", nil, + # "/dc=example;dc=com", "query", nil, nil, nil]) + # def self.build(args) tmp = Util::make_components_hash(self, args) if tmp[:dn] - tmp[:path] = tmp[:dn] + tmp[:path] = tmp[:dn] end query = [] [:extensions, :filter, :scope, :attributes].collect do |x| - next if !tmp[x] && query.size == 0 - query.unshift(tmp[x]) + next if !tmp[x] && query.size == 0 + query.unshift(tmp[x]) end tmp[:query] = query.join('?') @@ -72,22 +89,42 @@ URI::LDAP is copyrighted free software by Takaaki Tateishi and akira yamada. return super(tmp) end + # + # == Description + # + # 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. + # + # Example: + # + # uri = URI::LDAP.new("ldap", nil, "ldap.example.com", nil, nil, + # "/dc=example;dc=com", nil, "query", nil) + # + # See also URI::Generic.new. + # def initialize(*arg) super(*arg) if @fragment - raise InvalidURIError, 'bad LDAP URL' + raise InvalidURIError, 'bad LDAP URL' end parse_dn parse_query end + # 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. def parse_query @attributes = nil @scope = nil @@ -95,42 +132,35 @@ URI::LDAP is copyrighted free software by Takaaki Tateishi and akira yamada. @extensions = nil if @query - attrs, scope, filter, extensions = @query.split('?') + attrs, scope, filter, extensions = @query.split('?') - @attributes = attrs if attrs && attrs.size > 0 - @scope = scope if scope && scope.size > 0 - @filter = filter if filter && filter.size > 0 - @extensions = extensions if extensions && extensions.size > 0 + @attributes = attrs if attrs && attrs.size > 0 + @scope = scope if scope && scope.size > 0 + @filter = filter if filter && filter.size > 0 + @extensions = extensions if extensions && extensions.size > 0 end end private :parse_query + # Private method to assemble +query+ from +attributes+, +scope+, +filter+, and +extensions+. def build_path_query @path = '/' + @dn query = [] [@extensions, @filter, @scope, @attributes].each do |x| - next if !x && query.size == 0 - query.unshift(x) + next if !x && query.size == 0 + query.unshift(x) end @query = query.join('?') end private :build_path_query -=begin - -=== Instance Methods - ---- URI::LDAP#dn - ---- URI::LDAP#dn=(v) - -=end - + # Returns dn. def dn @dn end + # Private setter for dn +val+. def set_dn(val) @dn = val build_path_query @@ -138,22 +168,18 @@ URI::LDAP is copyrighted free software by Takaaki Tateishi and akira yamada. end protected :set_dn + # Setter for dn +val+. def dn=(val) set_dn(val) + val end -=begin - ---- URI::LDAP#attributes - ---- URI::LDAP#attributes=(v) - -=end - + # Returns attributes. def attributes @attributes end + # Private setter for attributes +val+. def set_attributes(val) @attributes = val build_path_query @@ -161,22 +187,18 @@ URI::LDAP is copyrighted free software by Takaaki Tateishi and akira yamada. end protected :set_attributes + # Setter for attributes +val+. def attributes=(val) set_attributes(val) + val end -=begin - ---- URI::LDAP#scope - ---- URI::LDAP#scope=(v) - -=end - + # Returns scope. def scope @scope end + # Private setter for scope +val+. def set_scope(val) @scope = val build_path_query @@ -184,22 +206,18 @@ URI::LDAP is copyrighted free software by Takaaki Tateishi and akira yamada. end protected :set_scope + # Setter for scope +val+. def scope=(val) set_scope(val) + val end -=begin - ---- URI::LDAP#filter - ---- URI::LDAP#filter=(v) - -=end - + # Returns filter. def filter @filter end + # Private setter for filter +val+. def set_filter(val) @filter = val build_path_query @@ -207,22 +225,18 @@ URI::LDAP is copyrighted free software by Takaaki Tateishi and akira yamada. end protected :set_filter + # Setter for filter +val+. def filter=(val) set_filter(val) + val end -=begin - ---- URI::LDAP#extensions - ---- URI::LDAP#extensions=(v) - -=end - + # Returns extensions. def extensions @extensions end + # Private setter for extensions +val+. def set_extensions(val) @extensions = val build_path_query @@ -230,14 +244,18 @@ URI::LDAP is copyrighted free software by Takaaki Tateishi and akira yamada. end protected :set_extensions + # Setter for extensions +val+. def extensions=(val) set_extensions(val) + val end - end - def hierarchical? - 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 new file mode 100644 index 0000000000..58228f5894 --- /dev/null +++ b/lib/uri/ldaps.rb @@ -0,0 +1,22 @@ +# frozen_string_literal: false +# = uri/ldap.rb +# +# License:: You can redistribute it and/or modify it under the same term as Ruby. +# +# See URI for general documentation +# + +require_relative 'ldap' + +module URI + + # The default port for LDAPS URIs is 636, and the scheme is 'ldaps:' rather + # than 'ldap:'. Other than that, LDAPS URIs are identical to LDAP URIs; + # see URI::LDAP. + class LDAPS < LDAP + # A Default port of 636 for URI::LDAPS + DEFAULT_PORT = 636 + end + + register_scheme 'LDAPS', LDAPS +end diff --git a/lib/uri/mailto.rb b/lib/uri/mailto.rb index d50d2b792f..cb8024f301 100644 --- a/lib/uri/mailto.rb +++ b/lib/uri/mailto.rb @@ -1,35 +1,29 @@ +# frozen_string_literal: false +# = uri/mailto.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 # -require 'uri/generic' +require_relative 'generic' module URI -=begin - -== URI::MailTo - -=== Super Class - -((<URI::Generic>)) - -=end - - # RFC2368, 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. DEFAULT_PORT = nil - COMPONENT = [ - :scheme, - :to, :headers - ].freeze + # An Array of the available components for URI::MailTo. + COMPONENT = [ :scheme, :to, :headers ].freeze + # :stopdoc: # "hname" and "hvalue" are encodings of an RFC 822 header name and # value, respectively. As with "to", all URL reserved characters must # be encoded. @@ -43,220 +37,257 @@ module URI # # Within mailto URLs, the characters "?", "=", "&" are reserved. - # hname = *urlc - # hvalue = *urlc - # header = hname "=" hvalue - HEADER_PATTERN = "(?:[^?=&]*=[^?=&]*)".freeze - HEADER_REGEXP = Regexp.new(HEADER_PATTERN, 'N').freeze - # headers = "?" header *( "&" header ) - # to = #mailbox - # mailtoURL = "mailto:" [ to ] [ headers ] - MAILBOX_PATTERN = "(?:#{PATTERN::ESCAPED}|[^(),%?=&])".freeze - MAILTO_REGEXP = Regexp.new(" - \\A - (#{MAILBOX_PATTERN}*?) (?# 1: to) - (?: - \\? - (#{HEADER_PATTERN}(?:\\&#{HEADER_PATTERN})*) (?# 2: headers) - )? - \\z - ", Regexp::EXTENDED, 'N').freeze - -=begin - -=== Class Methods - ---- URI::MailTo::build - Create a new URI::MailTo object from components of URI::MailTo - with check. It is to and headers. It provided by an Array of a - Hash. You can provide headers as an String like - "subject=subscribe&cc=addr" or an Array like [["subject", - "subscribe"], ["cc", "addr"]] - ---- URI::MailTo::new - Create a new URI::MailTo object from ``generic'' components with - no check. Because, this method is usually called from URI::parse - and the method checks validity of each components. - -=end + # ; RFC 6068 + # hfields = "?" hfield *( "&" hfield ) + # hfield = hfname "=" hfvalue + # hfname = *qchar + # hfvalue = *qchar + # qchar = unreserved / pct-encoded / some-delims + # some-delims = "!" / "$" / "'" / "(" / ")" / "*" + # / "+" / "," / ";" / ":" / "@" + # + # ; RFC3986 + # unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~" + # pct-encoded = "%" HEXDIG HEXDIG + HEADER_REGEXP = /\A(?<hfield>(?:%\h\h|[!$'-.0-;@-Z_a-z~])*=(?:%\h\h|[!$'-.0-;@-Z_a-z~])*)(?:&\g<hfield>)*\z/ + # practical regexp for email address + # https://html.spec.whatwg.org/multipage/input.html#valid-e-mail-address + EMAIL_REGEXP = /\A[a-zA-Z0-9.!\#$%&'*+\/=?^_`{|}~-]+@[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: + # + # == Description + # + # 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 <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 + # <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']) + # m1.to_s # => "mailto:joe@example.com?subject=Ruby" + # + # m2 = URI::MailTo.build(['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']]}) + # m3.to_s # => "mailto:listman@example.com?subject=subscribe" + # def self.build(args) - tmp = Util::make_components_hash(self, args) + tmp = Util.make_components_hash(self, args) - if tmp[:to] - tmp[:opaque] = tmp[:to] + case tmp[:to] + when Array + tmp[:opaque] = tmp[:to].join(',') + when String + tmp[:opaque] = tmp[:to].dup else - tmp[:opaque] = '' + tmp[:opaque] = '' end if tmp[:headers] - tmp[:opaque] << '?' - - if tmp[:headers].kind_of?(Array) - tmp[:opaque] << tmp[:headers].collect { |x| - if x.kind_of?(Array) - x[0] + '=' + x[1..-1].to_s - else - x.to_s - end - }.join('&') - - elsif tmp[:headers].kind_of?(Hash) - tmp[:opaque] << tmp[:headers].collect { |h,v| - h + '=' + v - }.join('&') - - else - tmp[:opaque] << tmp[:headers].to_s - end + query = + case tmp[:headers] + when Array + tmp[:headers].collect { |x| + if x.kind_of?(Array) + x[0] + '=' + x[1..-1].join + else + x.to_s + end + }.join('&') + when Hash + tmp[:headers].collect { |h,v| + h + '=' + v + }.join('&') + else + tmp[:headers].to_s + end + unless query.empty? + tmp[:opaque] << '?' << query + end end - return super(tmp) + super(tmp) end + # + # == Description + # + # Creates a new URI::MailTo object from generic URL components with + # no syntax checking. + # + # This method is usually called from URI::parse, which checks + # the validity of each component. + # def initialize(*arg) super(*arg) @to = nil @headers = [] - if MAILTO_REGEXP =~ @opaque - if arg[-1] - self.to = $1 - self.headers = $2 - else - set_to($1) - set_headers($2) - end + # The RFC3986 parser does not normally populate opaque + @opaque = "?#{@query}" if @query && !@opaque + + unless @opaque + raise InvalidComponentError, + "missing opaque part for mailto URL" + end + to, header = @opaque.split('?', 2) + # allow semicolon as a addr-spec separator + # http://support.microsoft.com/kb/820868 + unless /\A(?:[^@,;]+@[^@,;]+(?:\z|[,;]))*\z/ =~ to + raise InvalidComponentError, + "unrecognised opaque part for mailtoURL: #{@opaque}" + end + if arg[10] # arg_check + self.to = to + self.headers = header else - raise InvalidComponentError, - "unrecognised opaque part for mailtoURL: #{@opaque}" + set_to(to) + set_headers(header) end end - attr_reader :to - attr_reader :headers - -=begin - -=== Instance Methods - ---- URI::MailTo#to - ---- URI::MailTo#to=(v) -=end + # The primary e-mail address of the URL, as a String. + attr_reader :to - # - # methods for to - # + # E-mail headers set by the URL, as an Array of Arrays. + attr_reader :headers + # Checks the to +v+ component. def check_to(v) return true unless v return true if v.size == 0 - if OPAQUE !~ v || /\A#{MAILBOX_PATTERN}*\z/o !~ v - raise InvalidComponentError, - "bad component(expected opaque component): #{v}" + v.split(/[,;]/).each do |addr| + # check url safety as path-rootless + if /\A(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*\z/ !~ addr + raise InvalidComponentError, + "an address in 'to' is invalid as URI #{addr.dump}" + end + + # check addr-spec + # don't s/\+/ /g + addr.gsub!(/%\h\h/, URI::TBLDECWWWCOMP_) + if EMAIL_REGEXP !~ addr + raise InvalidComponentError, + "an address in 'to' is invalid as uri-escaped addr-spec #{addr.dump}" + end end - return true + true end private :check_to + # Private setter for to +v+. def set_to(v) @to = v end protected :set_to + # Setter for to +v+. def to=(v) check_to(v) set_to(v) + v end -=begin - ---- URI::MailTo#headers - ---- URI::MailTo#headers=(v) - -=end - - # - # methods for headers - # - + # Checks the headers +v+ component against either + # * HEADER_REGEXP def check_headers(v) return true unless v return true if v.size == 0 - - if OPAQUE !~ v || - /\A(#{HEADER_PATTERN}(?:\&#{HEADER_PATTERN})*)\z/o !~ v - raise InvalidComponentError, - "bad component(expected opaque component): #{v}" + if HEADER_REGEXP !~ v + raise InvalidComponentError, + "bad component(expected opaque component): #{v}" end - return true + true end private :check_headers + # Private setter for headers +v+. def set_headers(v) @headers = [] if v - v.scan(HEADER_REGEXP) do |x| - @headers << x.split(/=/o, 2) - end + v.split('&').each do |x| + @headers << x.split(/=/, 2) + end end end protected :set_headers + # Setter for headers +v+. def headers=(v) check_headers(v) set_headers(v) + v end - def to_str - @scheme + ':' + - if @to - @to - else - '' - end + - if @headers.size > 0 - '?' + @headers.collect{|x| x.join('=')}.join('&') - else - '' - end + # Constructs String from URI. + def to_s + @scheme + ':' + + if @to + @to + else + '' + end + + if @headers.size > 0 + '?' + @headers.collect{|x| x.join('=')}.join('&') + else + '' + end + + if @fragment + '#' + @fragment + else + '' + end end -=begin - ---- URI::MailTo#to_mailtext - -=end + # Returns the RFC822 e-mail text equivalent of the URL, as a String. + # + # Example: + # + # require 'uri' + # + # uri = URI.parse("mailto:ruby-list@ruby-lang.org?Subject=subscribe&cc=myaddr") + # uri.to_mailtext + # # => "To: ruby-list@ruby-lang.org\nSubject: subscribe\nCc: myaddr\n\n\n" + # def to_mailtext - to = URI::unescape(@to) + to = URI.decode_www_form_component(@to) head = '' body = '' @headers.each do |x| - case x[0] - when 'body' - body = URI::unescape(x[1]) - when 'to' - to << ', ' + URI::unescape(x[1]) - else - head << URI::unescape(x[0]).capitalize + ': ' + - URI::unescape(x[1]) + "\n" - end + case x[0] + when 'body' + body = URI.decode_www_form_component(x[1]) + when 'to' + to << ', ' + URI.decode_www_form_component(x[1]) + else + head << URI.decode_www_form_component(x[0]).capitalize + ': ' + + URI.decode_www_form_component(x[1]) + "\n" + end end - return "To: #{to} + "To: #{to} #{head} #{body} " end alias to_rfc822text to_mailtext - end # MailTo + end - @@schemes['MAILTO'] = MailTo -end # URI + register_scheme 'MAILTO', MailTo +end diff --git a/lib/uri/rfc2396_parser.rb b/lib/uri/rfc2396_parser.rb new file mode 100644 index 0000000000..cefd126cc6 --- /dev/null +++ b/lib/uri/rfc2396_parser.rb @@ -0,0 +1,547 @@ +# frozen_string_literal: false +#-- +# = uri/common.rb +# +# Author:: Akira Yamada <akira@ruby-lang.org> +# 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 RFC2396_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 RFC2396_Parser + include RFC2396_REGEXP + + # + # == Synopsis + # + # URI::RFC2396_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::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 http://example.com/ABCD> + # u2 = URI.parse(s) #=> #<URI::HTTP http://example.com/ABCD> + # u1 == u2 #=> true + # u1.eql?(u2) #=> false + # + def initialize(opts = {}) + @pattern = initialize_pattern(opts) + @pattern.each_value(&:freeze) + @pattern.freeze + + @regexp = initialize_regexp(@pattern) + @regexp.each_value(&:freeze) + @regexp.freeze + end + + # The Hash of patterns. + # + # See also #initialize_pattern. + attr_reader :pattern + + # The Hash of Regexp. + # + # See also #initialize_regexp. + attr_reader :regexp + + # Returns a split URI against +regexp[:ABS_URI]+. + def split(uri) + case uri + when '' + # null uri + + when @regexp[:ABS_URI] + scheme, opaque, userinfo, host, port, + registry, path, query, fragment = $~[1..-1] + + # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ] + + # absoluteURI = scheme ":" ( hier_part | opaque_part ) + # hier_part = ( net_path | abs_path ) [ "?" query ] + # opaque_part = uric_no_slash *uric + + # abs_path = "/" path_segments + # net_path = "//" authority [ abs_path ] + + # authority = server | reg_name + # server = [ [ userinfo "@" ] hostport ] + + if !scheme + raise InvalidURIError, + "bad URI (absolute but no scheme): #{uri}" + end + if !opaque && (!path && (!host && !registry)) + raise InvalidURIError, + "bad URI (absolute but no path): #{uri}" + end + + when @regexp[:REL_URI] + scheme = nil + opaque = nil + + userinfo, host, port, registry, + rel_segment, abs_path, query, fragment = $~[1..-1] + if rel_segment && abs_path + path = rel_segment + abs_path + elsif rel_segment + path = rel_segment + elsif abs_path + path = abs_path + end + + # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ] + + # relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ] + + # net_path = "//" authority [ abs_path ] + # abs_path = "/" path_segments + # rel_path = rel_segment [ abs_path ] + + # authority = server | reg_name + # server = [ [ userinfo "@" ] hostport ] + + else + raise InvalidURIError, "bad URI (is not URI?): #{uri}" + end + + 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 + # (File, FTP, HTTP, HTTPS, LDAP, LDAPS, or MailTo) or URI::Generic. + # + # == Usage + # + # 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) + URI.for(*self.split(uri), self) + 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 #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 + /(?=(?i:#{Regexp.union(*schemes).source}):)#{@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 = $& + tmp = '' + us.each_byte do |uc| + tmp << sprintf('%%%02X', uc) + end + tmp + end.force_encoding(Encoding::US_ASCII) + end + + # + # :call-seq: + # unescape( str ) + # unescape( str, escaped ) + # + # == Args + # + # +str+:: + # String to remove escapes from + # +escaped+:: + # Regexp to apply. Defaults to +self.regexp[:ESCAPED]+ + # + # == Description + # + # Removes escapes from +str+. + # + def unescape(str, escaped = @regexp[:ESCAPED]) + enc = str.encoding + enc = Encoding::UTF_8 if enc == Encoding::US_ASCII + str.gsub(escaped) { [$&[1, 2]].pack('H2').force_encoding(enc) } + end + + TO_S = Kernel.instance_method(:to_s) # :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. + 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 + ret[:PORT] = 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 + + # 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 + elsif uri = String.try_convert(uri) + parse(uri) + else + raise ArgumentError, + "bad argument (expected URI object or URI string)" + end + 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 new file mode 100644 index 0000000000..0b5f0c4488 --- /dev/null +++ b/lib/uri/rfc3986_parser.rb @@ -0,0 +1,206 @@ +# frozen_string_literal: true +module URI + class RFC3986_Parser # :nodoc: + # URI defined in RFC3986 + 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 + @regexp = default_regexp.each_value(&:freeze).freeze + end + + def split(uri) #:nodoc: + begin + uri = uri.to_str + rescue NoMethodError + 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"] + scheme = m["scheme"] + opaque = m["path-rootless"] + if opaque + opaque << "?#{query}" if query + [ scheme, + nil, # userinfo + nil, # host + nil, # port + nil, # registry + nil, # path + opaque, + nil, # query + m["fragment"] + ] + else # normal + [ scheme, + m["userinfo"], + m["host"], + m["port"], + nil, # registry + (m["path-abempty"] || + m["path-absolute"] || + m["path-empty"]), + nil, # opaque + query, + m["fragment"] + ] + end + elsif m = RFC3986_relative_ref.match(uri) + [ nil, # scheme + m["userinfo"], + m["host"], + m["port"], + nil, # registry, + (m["path-abempty"] || + m["path-absolute"] || + m["path-noscheme"] || + m["path-empty"]), + nil, # opaque + m["query"], + m["fragment"] + ] + else + raise InvalidURIError, "bad URI (is not URI?): #{uri.inspect}" + end + end + + def parse(uri) # :nodoc: + 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 $VERBOSE + escaped ? RFC2396_PARSER.unescape(str, escaped) : RFC2396_PARSER.unescape(str) + end + + @@to_s = Kernel.instance_method(:to_s) + if @@to_s.respond_to?(:bind_call) + def inspect + @@to_s.bind_call(self) + end + else + def inspect + @@to_s.bind(self).call + end + end + + private + + def default_regexp # :nodoc: + { + SCHEME: %r[\A#{SCHEME}\z]o, + USERINFO: %r[\A#{USERINFO}\z]o, + HOST: %r[\A#{HOST}\z]o, + ABS_PATH: %r[\A/#{SEG}*+\z]o, + REL_PATH: %r[\A(?!/)#{SEG}++\z]o, + QUERY: %r[\A(?:%\h\h|[!$&-.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 + + def convert_to_uri(uri) + if uri.is_a?(URI::Generic) + uri + elsif uri = String.try_convert(uri) + parse(uri) + else + raise ArgumentError, + "bad argument (expected URI object or URI string)" + end + end + + end # class Parser +end # module URI 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 |