lib/uri/common.rb in rubysl-uri-1.0.0 vs lib/uri/common.rb in rubysl-uri-2.0.0

- old
+ new

@@ -1,14 +1,20 @@ +#-- # = uri/common.rb # # Author:: Akira Yamada <akira@ruby-lang.org> -# Revision:: $Id: common.rb 14178 2007-12-10 09:31:55Z matz $ -# License:: +# Revision:: $Id$ +# License:: # You can redistribute it and/or modify it under the same term as Ruby. # +# See URI for general documentation +# module URI + # + # Includes URI::REGEXP::PATTERN + # module REGEXP # # Patterns used to parse URI's # module PATTERN @@ -29,33 +35,340 @@ # escaped = "%" hex hex ESCAPED = "%[#{HEX}]{2}" # mark = "-" | "_" | "." | "!" | "~" | "*" | "'" | # "(" | ")" # unreserved = alphanum | mark - UNRESERVED = "-_.!~*'()#{ALNUM}" + UNRESERVED = "\\-_.!~*'()#{ALNUM}" # reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" | # "$" | "," - # reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" | + # reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" | # "$" | "," | "[" | "]" (RFC 2732) RESERVED = ";/?:@&=+$,\\[\\]" + # domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum + DOMLABEL = "(?:[#{ALNUM}](?:[-#{ALNUM}]*[#{ALNUM}])?)" + # toplabel = alpha | alpha *( alphanum | "-" ) alphanum + TOPLABEL = "(?:[#{ALPHA}](?:[-#{ALNUM}]*[#{ALNUM}])?)" + # hostname = *( domainlabel "." ) toplabel [ "." ] + HOSTNAME = "(?:#{DOMLABEL}\\.)*#{TOPLABEL}\\.?" + + # :startdoc: + end # PATTERN + + # :startdoc: + end # REGEXP + + # class that Parses String's into URI's + # + # It contains a Hash set of patterns and Regexp's that match and validate. + # + class Parser + include REGEXP + + # + # == Synopsis + # + # URI::Parser.new([opts]) + # + # == Args + # + # The constructor accepts a hash as options for parser. + # Keys of options are pattern names of URI components + # and values of options are pattern strings. + # The constructor generetes set of regexps for parsing URIs. + # + # You can use the following keys: + # + # * :ESCAPED (URI::PATTERN::ESCAPED in default) + # * :UNRESERVED (URI::PATTERN::UNRESERVED in default) + # * :DOMLABEL (URI::PATTERN::DOMLABEL in default) + # * :TOPLABEL (URI::PATTERN::TOPLABEL in default) + # * :HOSTNAME (URI::PATTERN::HOSTNAME in default) + # + # == Examples + # + # p = URI::Parser.new(:ESCAPED => "(?:%[a-fA-F0-9]{2}|%u[a-fA-F0-9]{4})") + # u = p.parse("http://example.jp/%uABCD") #=> #<URI::HTTP:0xb78cf4f8 URL:http://example.jp/%uABCD> + # URI.parse(u.to_s) #=> raises URI::InvalidURIError + # + # s = "http://examle.com/ABCD" + # u1 = p.parse(s) #=> #<URI::HTTP:0xb78c3220 URL:http://example.com/ABCD> + # u2 = URI.parse(s) #=> #<URI::HTTP:0xb78b6d54 URL:http://example.com/ABCD> + # u1 == u2 #=> true + # u1.eql?(u2) #=> false + # + def initialize(opts = {}) + @pattern = initialize_pattern(opts) + @pattern.each_value {|v| v.freeze} + @pattern.freeze + + @regexp = initialize_regexp(@pattern) + @regexp.each_value {|v| v.freeze} + @regexp.freeze + end + + # The Hash of patterns. + # + # see also URI::Parser.initialize_pattern + attr_reader :pattern + + # The Hash of Regexp + # + # see also URI::Parser.initialize_regexp + attr_reader :regexp + + # Returns a split URI against regexp[:ABS_URI] + def split(uri) + case uri + when '' + # null uri + + when @regexp[:ABS_URI] + scheme, opaque, userinfo, host, port, + registry, path, query, fragment = $~[1..-1] + + # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ] + + # absoluteURI = scheme ":" ( hier_part | opaque_part ) + # hier_part = ( net_path | abs_path ) [ "?" query ] + # opaque_part = uric_no_slash *uric + + # abs_path = "/" path_segments + # net_path = "//" authority [ abs_path ] + + # authority = server | reg_name + # server = [ [ userinfo "@" ] hostport ] + + if !scheme + raise InvalidURIError, + "bad URI(absolute but no scheme): #{uri}" + end + if !opaque && (!path && (!host && !registry)) + raise InvalidURIError, + "bad URI(absolute but no path): #{uri}" + end + + when @regexp[:REL_URI] + scheme = nil + opaque = nil + + userinfo, host, port, registry, + rel_segment, abs_path, query, fragment = $~[1..-1] + if rel_segment && abs_path + path = rel_segment + abs_path + elsif rel_segment + path = rel_segment + elsif abs_path + path = abs_path + end + + # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ] + + # relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ] + + # net_path = "//" authority [ abs_path ] + # abs_path = "/" path_segments + # rel_path = rel_segment [ abs_path ] + + # authority = server | reg_name + # server = [ [ userinfo "@" ] hostport ] + + else + raise InvalidURIError, "bad URI(is not URI?): #{uri}" + end + + path = '' if !path && !opaque # (see RFC2396 Section 5.2) + ret = [ + scheme, + userinfo, host, port, # X + registry, # X + path, # Y + opaque, # Y + query, + fragment + ] + return ret + end + + # + # == Args + # + # +uri+:: + # String + # + # == Description + # + # parses +uri+ and constructs either matching URI scheme object + # (FTP, HTTP, HTTPS, LDAP, LDAPS, or MailTo) or URI::Generic + # + # == Usage + # + # p = URI::Parser.new + # p.parse("ldap://ldap.example.com/dc=example?user=john") + # #=> #<URI::LDAP:0x00000000b9e7e8 URL:ldap://ldap.example.com/dc=example?user=john> + # + def parse(uri) + scheme, userinfo, host, port, + registry, path, opaque, query, fragment = self.split(uri) + + if scheme && URI.scheme_list.include?(scheme.upcase) + URI.scheme_list[scheme.upcase].new(scheme, userinfo, host, port, + registry, path, opaque, query, + fragment, self) + else + Generic.new(scheme, userinfo, host, port, + registry, path, opaque, query, + fragment, self) + end + end + + + # + # == Args + # + # +uris+:: + # an Array of Strings + # + # == Description + # + # Attempts to parse and merge a set of URIs + # + def join(*uris) + uris[0] = convert_to_uri(uris[0]) + uris.inject :merge + end + + # + # :call-seq: + # extract( str ) + # extract( str, schemes ) + # extract( str, schemes ) {|item| block } + # + # == Args + # + # +str+:: + # String to search + # +schemes+:: + # Patterns to apply to +str+ + # + # == Description + # + # Attempts to parse and merge a set of URIs + # If no +block+ given , then returns the result, + # else it calls +block+ for each element in result. + # + # see also URI::Parser.make_regexp + # + def extract(str, schemes = nil) + if block_given? + str.scan(make_regexp(schemes)) { yield $& } + nil + else + result = [] + str.scan(make_regexp(schemes)) { result.push $& } + result + end + end + + # returns Regexp that is default self.regexp[:ABS_URI_REF], + # unless +schemes+ is provided. Then it is a Regexp.union with self.pattern[:X_ABS_URI] + def make_regexp(schemes = nil) + unless schemes + @regexp[:ABS_URI_REF] + else + /(?=#{Regexp.union(*schemes)}:)#{@pattern[:X_ABS_URI]}/x + end + end + + # + # :call-seq: + # escape( str ) + # escape( str, unsafe ) + # + # == Args + # + # +str+:: + # String to make safe + # +unsafe+:: + # Regexp to apply. Defaults to self.regexp[:UNSAFE] + # + # == Description + # + # constructs a safe String from +str+, removing unsafe characters, + # replacing them with codes. + # + def escape(str, unsafe = @regexp[:UNSAFE]) + unless unsafe.kind_of?(Regexp) + # perhaps unsafe is String object + unsafe = Regexp.new("[#{Regexp.quote(unsafe)}]", false) + end + str.gsub(unsafe) do + us = $& + tmp = '' + us.each_byte do |uc| + tmp << sprintf('%%%02X', uc) + end + tmp + end.force_encoding(Encoding::US_ASCII) + end + + # + # :call-seq: + # unescape( str ) + # unescape( str, unsafe ) + # + # == Args + # + # +str+:: + # String to remove escapes from + # +unsafe+:: + # Regexp to apply. Defaults to self.regexp[:ESCAPED] + # + # == Description + # + # Removes escapes from +str+ + # + def unescape(str, escaped = @regexp[:ESCAPED]) + str.gsub(escaped) { [$&[1, 2].hex].pack('C') }.force_encoding(str.encoding) + end + + @@to_s = Kernel.instance_method(:to_s) + def inspect + @@to_s.bind(self).call + end + + private + + # Constructs the default Hash of patterns + def initialize_pattern(opts = {}) + ret = {} + ret[:ESCAPED] = escaped = (opts.delete(:ESCAPED) || PATTERN::ESCAPED) + ret[:UNRESERVED] = unreserved = opts.delete(:UNRESERVED) || PATTERN::UNRESERVED + ret[:RESERVED] = reserved = opts.delete(:RESERVED) || PATTERN::RESERVED + ret[:DOMLABEL] = opts.delete(:DOMLABEL) || PATTERN::DOMLABEL + ret[:TOPLABEL] = opts.delete(:TOPLABEL) || PATTERN::TOPLABEL + ret[:HOSTNAME] = hostname = opts.delete(:HOSTNAME) + + # RFC 2396 (URI Generic Syntax) + # RFC 2732 (IPv6 Literal Addresses in URL's) + # RFC 2373 (IPv6 Addressing Architecture) + # uric = reserved | unreserved | escaped - URIC = "(?:[#{UNRESERVED}#{RESERVED}]|#{ESCAPED})" + ret[:URIC] = uric = "(?:[#{unreserved}#{reserved}]|#{escaped})" # uric_no_slash = unreserved | escaped | ";" | "?" | ":" | "@" | # "&" | "=" | "+" | "$" | "," - URIC_NO_SLASH = "(?:[#{UNRESERVED};?:@&=+$,]|#{ESCAPED})" + ret[:URIC_NO_SLASH] = uric_no_slash = "(?:[#{unreserved};?:@&=+$,]|#{escaped})" # query = *uric - QUERY = "#{URIC}*" + ret[:QUERY] = query = "#{uric}*" # fragment = *uric - FRAGMENT = "#{URIC}*" + ret[:FRAGMENT] = 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}\\.?" + # 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 ] @@ -64,158 +377,183 @@ # # 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}" + ret[:IPV4ADDR] = ipv4addr = "\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}" # hex4 = 1*4HEXDIG - HEX4 = "[#{HEX}]{1,4}" + hex4 = "[#{PATTERN::HEX}]{1,4}" # lastpart = hex4 | IPv4address - LASTPART = "(?:#{HEX4}|#{IPV4ADDR})" + lastpart = "(?:#{hex4}|#{ipv4addr})" # hexseq1 = *( hex4 ":" ) hex4 - HEXSEQ1 = "(?:#{HEX4}:)*#{HEX4}" + hexseq1 = "(?:#{hex4}:)*#{hex4}" # hexseq2 = *( hex4 ":" ) lastpart - HEXSEQ2 = "(?:#{HEX4}:)*#{LASTPART}" + hexseq2 = "(?:#{hex4}:)*#{lastpart}" # IPv6address = hexseq2 | [ hexseq1 ] "::" [ hexseq2 ] - IPV6ADDR = "(?:#{HEXSEQ2}|(?:#{HEXSEQ1})?::(?:#{HEXSEQ2})?)" + ret[:IPV6ADDR] = ipv6addr = "(?:#{hexseq2}|(?:#{hexseq1})?::(?:#{hexseq2})?)" # IPv6prefix = ( hexseq1 | [ hexseq1 ] "::" [ hexseq1 ] ) "/" 1*2DIGIT # unused # ipv6reference = "[" IPv6address "]" (RFC 2732) - IPV6REF = "\\[#{IPV6ADDR}\\]" + ret[:IPV6REF] = ipv6ref = "\\[#{ipv6addr}\\]" # host = hostname | IPv4address # host = hostname | IPv4address | IPv6reference (RFC 2732) - HOST = "(?:#{HOSTNAME}|#{IPV4ADDR}|#{IPV6REF})" + ret[:HOST] = host = "(?:#{hostname}|#{ipv4addr}|#{ipv6ref})" # port = *digit - PORT = '\d*' + port = '\d*' # hostport = host [ ":" port ] - HOSTPORT = "#{HOST}(?::#{PORT})?" + ret[:HOSTPORT] = hostport = "#{host}(?::#{port})?" # userinfo = *( unreserved | escaped | # ";" | ":" | "&" | "=" | "+" | "$" | "," ) - USERINFO = "(?:[#{UNRESERVED};:&=+$,]|#{ESCAPED})*" + ret[:USERINFO] = userinfo = "(?:[#{unreserved};:&=+$,]|#{escaped})*" # pchar = unreserved | escaped | # ":" | "@" | "&" | "=" | "+" | "$" | "," - PCHAR = "(?:[#{UNRESERVED}:@&=+$,]|#{ESCAPED})" + pchar = "(?:[#{unreserved}:@&=+$,]|#{escaped})" # param = *pchar - PARAM = "#{PCHAR}*" + param = "#{pchar}*" # segment = *pchar *( ";" param ) - SEGMENT = "#{PCHAR}*(?:;#{PARAM})*" + segment = "#{pchar}*(?:;#{param})*" # path_segments = segment *( "/" segment ) - PATH_SEGMENTS = "#{SEGMENT}(?:/#{SEGMENT})*" + ret[:PATH_SEGMENTS] = path_segments = "#{segment}(?:/#{segment})*" # server = [ [ userinfo "@" ] hostport ] - SERVER = "(?:#{USERINFO}@)?#{HOSTPORT}" + server = "(?:#{userinfo}@)?#{hostport}" # reg_name = 1*( unreserved | escaped | "$" | "," | # ";" | ":" | "@" | "&" | "=" | "+" ) - REG_NAME = "(?:[#{UNRESERVED}$,;:@&=+]|#{ESCAPED})+" + ret[:REG_NAME] = reg_name = "(?:[#{unreserved}$,;:@&=+]|#{escaped})+" # authority = server | reg_name - AUTHORITY = "(?:#{SERVER}|#{REG_NAME})" + authority = "(?:#{server}|#{reg_name})" # rel_segment = 1*( unreserved | escaped | # ";" | "@" | "&" | "=" | "+" | "$" | "," ) - REL_SEGMENT = "(?:[#{UNRESERVED};@&=+$,]|#{ESCAPED})+" + ret[:REL_SEGMENT] = rel_segment = "(?:[#{unreserved};@&=+$,]|#{escaped})+" # scheme = alpha *( alpha | digit | "+" | "-" | "." ) - SCHEME = "[#{ALPHA}][-+.#{ALPHA}\\d]*" + ret[:SCHEME] = scheme = "[#{PATTERN::ALPHA}][\\-+.#{PATTERN::ALPHA}\\d]*" # abs_path = "/" path_segments - ABS_PATH = "/#{PATH_SEGMENTS}" + ret[:ABS_PATH] = abs_path = "/#{path_segments}" # rel_path = rel_segment [ abs_path ] - REL_PATH = "#{REL_SEGMENT}(?:#{ABS_PATH})?" + ret[:REL_PATH] = rel_path = "#{rel_segment}(?:#{abs_path})?" # net_path = "//" authority [ abs_path ] - NET_PATH = "//#{AUTHORITY}(?:#{ABS_PATH})?" + ret[:NET_PATH] = net_path = "//#{authority}(?:#{abs_path})?" # hier_part = ( net_path | abs_path ) [ "?" query ] - HIER_PART = "(?:#{NET_PATH}|#{ABS_PATH})(?:\\?(?:#{QUERY}))?" + ret[:HIER_PART] = hier_part = "(?:#{net_path}|#{abs_path})(?:\\?(?:#{query}))?" # opaque_part = uric_no_slash *uric - OPAQUE_PART = "#{URIC_NO_SLASH}#{URIC}*" + ret[:OPAQUE_PART] = opaque_part = "#{uric_no_slash}#{uric}*" # absoluteURI = scheme ":" ( hier_part | opaque_part ) - ABS_URI = "#{SCHEME}:(?:#{HIER_PART}|#{OPAQUE_PART})" + ret[:ABS_URI] = abs_uri = "#{scheme}:(?:#{hier_part}|#{opaque_part})" # relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ] - REL_URI = "(?:#{NET_PATH}|#{ABS_PATH}|#{REL_PATH})(?:\\?#{QUERY})?" + ret[:REL_URI] = rel_uri = "(?:#{net_path}|#{abs_path}|#{rel_path})(?:\\?#{query})?" # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ] - URI_REF = "(?:#{ABS_URI}|#{REL_URI})?(?:##{FRAGMENT})?" + ret[:URI_REF] = "(?:#{abs_uri}|#{rel_uri})?(?:##{fragment})?" - # XXX: - X_ABS_URI = " - (#{PATTERN::SCHEME}): (?# 1: scheme) + ret[:X_ABS_URI] = " + (#{scheme}): (?# 1: scheme) (?: - (#{PATTERN::OPAQUE_PART}) (?# 2: opaque) + (#{opaque_part}) (?# 2: opaque) | (?:(?: //(?: - (?:(?:(#{PATTERN::USERINFO})@)? (?# 3: userinfo) - (?:(#{PATTERN::HOST})(?::(\\d*))?))?(?# 4: host, 5: port) + (?:(?:(#{userinfo})@)? (?# 3: userinfo) + (?:(#{host})(?::(\\d*))?))? (?# 4: host, 5: port) | - (#{PATTERN::REG_NAME}) (?# 6: registry) + (#{reg_name}) (?# 6: registry) ) | - (?!//)) (?# XXX: '//' is the mark for hostport) - (#{PATTERN::ABS_PATH})? (?# 7: path) - )(?:\\?(#{PATTERN::QUERY}))? (?# 8: query) + (?!//)) (?# XXX: '//' is the mark for hostport) + (#{abs_path})? (?# 7: path) + )(?:\\?(#{query}))? (?# 8: query) ) - (?:\\#(#{PATTERN::FRAGMENT}))? (?# 9: fragment) + (?:\\#(#{fragment}))? (?# 9: fragment) " - X_REL_URI = " + + ret[:X_REL_URI] = " (?: (?: // (?: - (?:(#{PATTERN::USERINFO})@)? (?# 1: userinfo) - (#{PATTERN::HOST})?(?::(\\d*))? (?# 2: host, 3: port) + (?:(#{userinfo})@)? (?# 1: userinfo) + (#{host})?(?::(\\d*))? (?# 2: host, 3: port) | - (#{PATTERN::REG_NAME}) (?# 4: registry) + (#{reg_name}) (?# 4: registry) ) ) | - (#{PATTERN::REL_SEGMENT}) (?# 5: rel_segment) + (#{rel_segment}) (?# 5: rel_segment) )? - (#{PATTERN::ABS_PATH})? (?# 6: abs_path) - (?:\\?(#{PATTERN::QUERY}))? (?# 7: query) - (?:\\#(#{PATTERN::FRAGMENT}))? (?# 8: fragment) + (#{abs_path})? (?# 6: abs_path) + (?:\\?(#{query}))? (?# 7: query) + (?:\\#(#{fragment}))? (?# 8: fragment) " - # :startdoc: - end # PATTERN - # :stopdoc: + ret + end - # for URI::split - ABS_URI = Regexp.new('^' + PATTERN::X_ABS_URI + '$', #' - Regexp::EXTENDED, 'N').freeze - REL_URI = Regexp.new('^' + PATTERN::X_REL_URI + '$', #' - Regexp::EXTENDED, 'N').freeze + # Constructs the default Hash of Regexp's + def initialize_regexp(pattern) + ret = {} - # for URI::extract - URI_REF = Regexp.new(PATTERN::URI_REF, false, 'N').freeze - ABS_URI_REF = Regexp.new(PATTERN::X_ABS_URI, Regexp::EXTENDED, 'N').freeze - REL_URI_REF = Regexp.new(PATTERN::X_REL_URI, Regexp::EXTENDED, 'N').freeze + # for URI::split + ret[:ABS_URI] = Regexp.new('\A\s*' + pattern[:X_ABS_URI] + '\s*\z', Regexp::EXTENDED) + ret[:REL_URI] = Regexp.new('\A\s*' + pattern[:X_REL_URI] + '\s*\z', Regexp::EXTENDED) - # for URI::escape/unescape - ESCAPED = Regexp.new(PATTERN::ESCAPED, false, 'N').freeze - UNSAFE = Regexp.new("[^#{PATTERN::UNRESERVED}#{PATTERN::RESERVED}]", - false, 'N').freeze + # for URI::extract + ret[:URI_REF] = Regexp.new(pattern[:URI_REF]) + ret[:ABS_URI_REF] = Regexp.new(pattern[:X_ABS_URI], Regexp::EXTENDED) + ret[:REL_URI_REF] = Regexp.new(pattern[:X_REL_URI], Regexp::EXTENDED) - # for Generic#initialize - SCHEME = Regexp.new("^#{PATTERN::SCHEME}$", 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 #" - # :startdoc: - end # REGEXP + # for URI::escape/unescape + ret[:ESCAPED] = Regexp.new(pattern[:ESCAPED]) + ret[:UNSAFE] = Regexp.new("[^#{pattern[:UNRESERVED]}#{pattern[:RESERVED]}]") + # for Generic#initialize + ret[:SCHEME] = Regexp.new("\\A#{pattern[:SCHEME]}\\z") + ret[:USERINFO] = Regexp.new("\\A#{pattern[:USERINFO]}\\z") + ret[:HOST] = Regexp.new("\\A#{pattern[:HOST]}\\z") + ret[:PORT] = Regexp.new("\\A#{pattern[:PORT]}\\z") + ret[:OPAQUE] = Regexp.new("\\A#{pattern[:OPAQUE_PART]}\\z") + ret[:REGISTRY] = Regexp.new("\\A#{pattern[:REG_NAME]}\\z") + ret[:ABS_PATH] = Regexp.new("\\A#{pattern[:ABS_PATH]}\\z") + ret[:REL_PATH] = Regexp.new("\\A#{pattern[:REL_PATH]}\\z") + ret[:QUERY] = Regexp.new("\\A#{pattern[:QUERY]}\\z") + ret[:FRAGMENT] = Regexp.new("\\A#{pattern[:FRAGMENT]}\\z") + + ret + end + + def convert_to_uri(uri) + if uri.is_a?(URI::Generic) + uri + elsif uri = String.try_convert(uri) + parse(uri) + else + raise ArgumentError, + "bad argument (expected URI object or URI string)" + end + end + + end # class Parser + + # URI::Parser.new + DEFAULT_PARSER = Parser.new + DEFAULT_PARSER.pattern.each_pair do |sym, str| + unless REGEXP::PATTERN.const_defined?(sym) + REGEXP::PATTERN.const_set(sym, str) + end + end + DEFAULT_PARSER.regexp.each_pair do |sym, str| + const_set(sym, str) + end + module Util # :nodoc: def make_components_hash(klass, array_hash) tmp = {} if array_hash.kind_of?(Array) && array_hash.size == klass.component.size - 1 @@ -234,23 +572,22 @@ rescue TypeError tmp[key] = value end end else - raise ArgumentError, + raise ArgumentError, "expected Array of or Hash of components of #{klass.to_s} (#{klass.component[1..-1].join(', ')})" end tmp[:scheme] = klass.to_s.sub(/\A.*::/, '').downcase return tmp end module_function :make_components_hash end + # module for escaping unsafe characters with codes. module Escape - include REGEXP - # # == Synopsis # # URI.escape(str [, unsafe]) # @@ -279,22 +616,13 @@ # # => "http://example.com/?a=\t\r" # # p URI.escape("@?@!", "!?") # # => "@%3F@%21" # - def escape(str, unsafe = UNSAFE) - unless unsafe.kind_of?(Regexp) - # perhaps unsafe is String object - unsafe = Regexp.new("[#{Regexp.quote(unsafe)}]", false, 'N') - end - str.gsub(unsafe) do |us| - tmp = '' - us.each_byte do |uc| - tmp << sprintf('%%%02X', uc) - end - tmp - end + def escape(*arg) + warn "#{caller(1)[0]}: warning: URI.escape is obsolete" if $VERBOSE + DEFAULT_PARSER.escape(*arg) end alias encode escape # # == Synopsis # @@ -314,23 +642,26 @@ # # => "http://example.com/?a=%09%0D" # # p URI.unescape(enc_uri) # # => "http://example.com/?a=\t\r" # - def unescape(str) - str.gsub(ESCAPED) do - $&[1,2].hex.chr - end + def unescape(*arg) + warn "#{caller(1)[0]}: warning: URI.unescape is obsolete" if $VERBOSE + DEFAULT_PARSER.unescape(*arg) end alias decode unescape - end + end # module Escape - include REGEXP extend Escape + include REGEXP @@schemes = {} - + # Returns a Hash of the defined schemes + def self.scheme_list + @@schemes + end + # # Base class for all URI exceptions. # class Error < StandardError; end # @@ -367,88 +698,20 @@ # * Registry # * Path # * Opaque # * Query # * Fragment - # + # # == Usage # # require 'uri' # # p URI.split("http://www.ruby-lang.org/") # # => ["http", nil, "www.ruby-lang.org", nil, nil, "/", nil, nil, nil] # 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 - - # 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 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 + DEFAULT_PARSER.split(uri) end # # == Synopsis # @@ -460,11 +723,11 @@ # String with URI. # # == Description # # Creates one of the URI's subclasses instance from the string. - # + # # == Raises # # URI::InvalidURIError # Raised if URI given is not a correct one. # @@ -473,28 +736,17 @@ # require 'uri' # # uri = URI.parse("http://www.ruby-lang.org/") # p uri # # => #<URI::HTTP:0x202281be URL:http://www.ruby-lang.org/> - # p uri.scheme - # # => "http" - # p uri.host - # # => "www.ruby-lang.org" - # + # p uri.scheme + # # => "http" + # p uri.host + # # => "www.ruby-lang.org" + # def self.parse(uri) - scheme, userinfo, host, port, - registry, path, opaque, query, fragment = self.split(uri) - - 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) - end + DEFAULT_PARSER.parse(uri) end # # == Synopsis # @@ -511,29 +763,38 @@ # # == Usage # # require 'uri' # - # p URI.join("http://localhost/","main.rbx") + # p URI.join("http://example.com/","main.rbx") # # => #<URI::HTTP:0x2022ac02 URL:http://localhost/main.rbx> # + # p URI.join('http://example.com', 'foo') + # # => #<URI::HTTP:0x01ab80a0 URL:http://example.com/foo> + # + # p URI.join('http://example.com', '/foo', '/bar') + # # => #<URI::HTTP:0x01aaf0b0 URL:http://example.com/bar> + # + # p URI.join('http://example.com', '/foo', 'bar') + # # => #<URI::HTTP:0x801a92af0 URL:http://example.com/bar> + # + # p URI.join('http://example.com', '/foo/', 'bar') + # # => #<URI::HTTP:0x80135a3a0 URL:http://example.com/foo/bar> + # + # def self.join(*str) - u = self.parse(str[0]) - str[1 .. -1].each do |x| - u = u.merge(x) - end - u + DEFAULT_PARSER.join(*str) end # # == Synopsis # # URI::extract(str[, schemes][,&blk]) # # == Args # - # +str+:: + # +str+:: # String to extract URIs from. # +schemes+:: # Limit URI matching to a specific schemes. # # == Description @@ -547,67 +808,194 @@ # # 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) - if block_given? - str.scan(regexp(schemes)) { yield $& } - nil - else - result = [] - str.scan(regexp(schemes)) { result.push $& } - result - end + DEFAULT_PARSER.extract(str, schemes, &block) end # # == Synopsis # # URI::regexp([match_schemes]) # # == Args # - # +match_schemes+:: + # +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 it's 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) - unless schemes - ABS_URI_REF + DEFAULT_PARSER.make_regexp(schemes) + end + + TBLENCWWWCOMP_ = {} # :nodoc: + 256.times do |i| + TBLENCWWWCOMP_[i.chr] = '%%%02X' % i + end + 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 + + HTML5ASCIIINCOMPAT = [Encoding::UTF_7, Encoding::UTF_16BE, Encoding::UTF_16LE, + Encoding::UTF_32BE, Encoding::UTF_32LE] # :nodoc: + + # Encode given +str+ to URL-encoded form data. + # + # This method doesn't convert *, -, ., 0-9, A-Z, _, a-z, but does convert SP + # (ASCII space) to + and converts others to %XX. + # + # This is an implementation of + # http://www.w3.org/TR/html5/association-of-controls-and-forms.html#url-encoded-form-data + # + # See URI.decode_www_form_component, URI.encode_www_form + def self.encode_www_form_component(str) + str = str.to_s + if HTML5ASCIIINCOMPAT.include?(str.encoding) + str = str.encode(Encoding::UTF_8) else - /(?=#{Regexp.union(*schemes)}:)#{PATTERN::X_ABS_URI}/xn + str = str.dup end + str.force_encoding(Encoding::ASCII_8BIT) + str.gsub!(/[^*\-.0-9A-Z_a-z]/, TBLENCWWWCOMP_) + str.force_encoding(Encoding::US_ASCII) end -end + # Decode given +str+ of URL-encoded form data. + # + # This decodes + to SP. + # + # See URI.encode_www_form_component, URI.decode_www_form + def self.decode_www_form_component(str, enc=Encoding::UTF_8) + raise ArgumentError, "invalid %-encoding (#{str})" unless /\A[^%]*(?:%\h\h[^%]*)*\z/ =~ str + str.gsub(/\+|%\h\h/, TBLDECWWWCOMP_).force_encoding(enc) + end -module Kernel - # alias for URI.parse. + # Generate URL-encoded form data from given +enum+. # - # This method is introduced at 1.8.2. - def URI(uri_str) # :doc: - return uri_str if uri_str.is_a? URI + # This generates application/x-www-form-urlencoded data defined in HTML5 + # from given an Enumerable object. + # + # This internally uses URI.encode_www_form_component(str). + # + # This method doesn't convert the encoding of given items, so convert them + # before call this method if you want to send data as other than original + # encoding or mixed encoding data. (Strings which are encoded in an HTML5 + # ASCII incompatible encoding are converted to UTF-8.) + # + # This method doesn't handle files. When you send a file, use + # multipart/form-data. + # + # This is an implementation of + # http://www.w3.org/TR/html5/forms.html#url-encoded-form-data + # + # URI.encode_www_form([["q", "ruby"], ["lang", "en"]]) + # #=> "q=ruby&lang=en" + # URI.encode_www_form("q" => "ruby", "lang" => "en") + # #=> "q=ruby&lang=en" + # URI.encode_www_form("q" => ["ruby", "perl"], "lang" => "en") + # #=> "q=ruby&q=perl&lang=en" + # URI.encode_www_form([["q", "ruby"], ["q", "perl"], ["lang", "en"]]) + # #=> "q=ruby&q=perl&lang=en" + # + # See URI.encode_www_form_component, URI.decode_www_form + def self.encode_www_form(enum) + enum.map do |k,v| + if v.nil? + encode_www_form_component(k) + elsif v.respond_to?(:to_ary) + v.to_ary.map do |w| + str = encode_www_form_component(k) + unless w.nil? + str << '=' + str << encode_www_form_component(w) + end + end.join('&') + else + str = encode_www_form_component(k) + str << '=' + str << encode_www_form_component(v) + end + end.join('&') + end - URI.parse(uri_str) + WFKV_ = '(?:[^%#=;&]*(?:%\h\h[^%#=;&]*)*)' # :nodoc: + + # Decode URL-encoded form data from given +str+. + # + # This decodes application/x-www-form-urlencoded data + # and returns array of key-value array. + # This internally uses URI.decode_www_form_component. + # + # _charset_ hack is not supported now because the mapping from given charset + # to Ruby's encoding is not clear yet. + # see also http://www.w3.org/TR/html5/syntax.html#character-encodings-0 + # + # This refers http://www.w3.org/TR/html5/forms.html#url-encoded-form-data + # + # ary = URI.decode_www_form("a=1&a=2&b=3") + # p ary #=> [['a', '1'], ['a', '2'], ['b', '3']] + # p ary.assoc('a').last #=> '1' + # p ary.assoc('b').last #=> '3' + # p ary.rassoc('a').last #=> '2' + # p Hash[ary] # => {"a"=>"2", "b"=>"3"} + # + # See URI.decode_www_form_component, URI.encode_www_form + def self.decode_www_form(str, enc=Encoding::UTF_8) + return [] if str.empty? + unless /\A#{WFKV_}=#{WFKV_}(?:[;&]#{WFKV_}=#{WFKV_})*\z/o =~ str + raise ArgumentError, "invalid data of application/x-www-form-urlencoded (#{str})" + end + ary = [] + $&.scan(/([^=;&]+)=([^;&]*)/) do + ary << [decode_www_form_component($1, enc), decode_www_form_component($2, enc)] + end + ary + end +end # module URI + +module Kernel + + # + # Returns +uri+ converted to a URI object. + # + def URI(uri) + if uri.is_a?(URI::Generic) + uri + elsif uri = String.try_convert(uri) + URI.parse(uri) + else + raise ArgumentError, + "bad argument (expected URI object or URI string)" + end end module_function :URI end