Class: Addressable::URI

Inherits:
Object
  • Object
show all
Defined in:
lib/addressable/uri.rb

Overview

This is an implementation of a URI parser based on <a href=“RFC”>www.ietf.org/rfc/rfc3986.txt“>RFC 3986</a>, <a href=”RFC“>www.ietf.org/rfc/rfc3987.txt”>RFC 3987</a>.

Defined Under Namespace

Modules: CharacterClasses Classes: InvalidURIError

Constant Summary collapse

SLASH =
'/'
EMPTY_STR =
''
URIREGEX =
/^(([^:\/?#]+):)?(\/\/([^\/?#]*))?([^?#]*)(\?([^#]*))?(#(.*))?$/
PORT_MAPPING =
{
  "http" => 80,
  "https" => 443,
  "ftp" => 21,
  "tftp" => 69,
  "sftp" => 22,
  "ssh" => 22,
  "svn+ssh" => 22,
  "telnet" => 23,
  "nntp" => 119,
  "gopher" => 70,
  "wais" => 210,
  "ldap" => 389,
  "prospero" => 1525
}
SEQUENCE_ENCODING_TABLE =

Tables used to optimize encoding operations in `self.encode_component` and `self.normalize_component`

Hash.new do |hash, sequence|
  hash[sequence] = sequence.unpack("C*").map do |c|
    format("%02x", c)
  end.join
end
SEQUENCE_UPCASED_PERCENT_ENCODING_TABLE =
Hash.new do |hash, sequence|
  hash[sequence] = sequence.unpack("C*").map do |c|
    format("%%%02X", c)
  end.join
end
NORMPATH =
/^(?!\/)[^\/:]*:.*$/

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(options = {}) ⇒ Addressable::URI

Creates a new uri object from component parts.


808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
# File 'lib/addressable/uri.rb', line 808

def initialize(options={})
  if options.has_key?(:authority)
    if (options.keys & [:userinfo, :user, :password, :host, :port]).any?
      raise ArgumentError,
        "Cannot specify both an authority and any of the components " +
        "within the authority."
    end
  end
  if options.has_key?(:userinfo)
    if (options.keys & [:user, :password]).any?
      raise ArgumentError,
        "Cannot specify both a userinfo and either the user or password."
    end
  end

  self.defer_validation do
    # Bunch of crazy logic required because of the composite components
    # like userinfo and authority.
    self.scheme = options[:scheme] if options[:scheme]
    self.user = options[:user] if options[:user]
    self.password = options[:password] if options[:password]
    self.userinfo = options[:userinfo] if options[:userinfo]
    self.host = options[:host] if options[:host]
    self.port = options[:port] if options[:port]
    self.authority = options[:authority] if options[:authority]
    self.path = options[:path] if options[:path]
    self.query = options[:query] if options[:query]
    self.query_values = options[:query_values] if options[:query_values]
    self.fragment = options[:fragment] if options[:fragment]
  end
  self.to_s
end

Class Method Details

.convert_path(path) ⇒ Addressable::URI

Converts a path to a file scheme URI. If the path supplied is relative, it will be returned as a relative URI. If the path supplied is actually a non-file URI, it will parse the URI as if it had been parsed with Addressable::URI.parse. Handles all of the various Microsoft-specific formats for specifying paths.

Examples:

base = Addressable::URI.convert_path("/absolute/path/")
uri = Addressable::URI.convert_path("relative/path")
(base + uri).to_s
#=> "file:///absolute/path/relative/path"

Addressable::URI.convert_path(
  "c:\\windows\\My Documents 100%20\\foo.txt"
).to_s
#=> "file:///c:/windows/My%20Documents%20100%20/foo.txt"

Addressable::URI.convert_path("http://example.com/").to_s
#=> "http://example.com/"

265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
# File 'lib/addressable/uri.rb', line 265

def self.convert_path(path)
  # If we were given nil, return nil.
  return nil unless path
  # If a URI object is passed, just return itself.
  return path if path.kind_of?(self)
  if !path.respond_to?(:to_str)
    raise TypeError, "Can't convert #{path.class} into String."
  end
  # Otherwise, convert to a String
  path = path.to_str.strip

  path.sub!(/^file:\/?\/?/, EMPTY_STR) if path =~ /^file:\/?\/?/
  path = SLASH + path if path =~ /^([a-zA-Z])[\|:]/
  uri = self.parse(path)

  if uri.scheme == nil
    # Adjust windows-style uris
    uri.path.sub!(/^\/?([a-zA-Z])[\|:][\\\/]/) do
      "/#{$1.downcase}:/"
    end
    uri.path.tr!("\\", SLASH)
    if File.exist?(uri.path) &&
        File.stat(uri.path).directory?
      uri.path.chomp!(SLASH)
      uri.path = uri.path + '/'
    end

    # If the path is absolute, set the scheme and host.
    if uri.path.start_with?(SLASH)
      uri.scheme = "file"
      uri.host = EMPTY_STR
    end
    uri.normalize!
  end

  return uri
end

.encode(uri, return_type = String) ⇒ String, Addressable::URI Also known as: escape

Percent encodes any special characters in the URI.


593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
# File 'lib/addressable/uri.rb', line 593

def self.encode(uri, return_type=String)
  return nil if uri.nil?

  begin
    uri = uri.to_str
  rescue NoMethodError, TypeError
    raise TypeError, "Can't convert #{uri.class} into String."
  end if !uri.is_a? String

  if ![String, ::Addressable::URI].include?(return_type)
    raise TypeError,
      "Expected Class (String or Addressable::URI), " +
      "got #{return_type.inspect}"
  end
  uri_object = uri.kind_of?(self) ? uri : self.parse(uri)
  encoded_uri = Addressable::URI.new(
    :scheme => self.encode_component(uri_object.scheme,
      Addressable::URI::CharacterClasses::SCHEME),
    :authority => self.encode_component(uri_object.authority,
      Addressable::URI::CharacterClasses::AUTHORITY),
    :path => self.encode_component(uri_object.path,
      Addressable::URI::CharacterClasses::PATH),
    :query => self.encode_component(uri_object.query,
      Addressable::URI::CharacterClasses::QUERY),
    :fragment => self.encode_component(uri_object.fragment,
      Addressable::URI::CharacterClasses::FRAGMENT)
  )
  if return_type == String
    return encoded_uri.to_s
  elsif return_type == ::Addressable::URI
    return encoded_uri
  end
end

.form_encode(form_values, sort = false) ⇒ String

Encodes a set of key/value pairs according to the rules for the application/x-www-form-urlencoded MIME type.


718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
# File 'lib/addressable/uri.rb', line 718

def self.form_encode(form_values, sort=false)
  if form_values.respond_to?(:to_hash)
    form_values = form_values.to_hash.to_a
  elsif form_values.respond_to?(:to_ary)
    form_values = form_values.to_ary
  else
    raise TypeError, "Can't convert #{form_values.class} into Array."
  end

  form_values = form_values.inject([]) do |accu, (key, value)|
    if value.kind_of?(Array)
      value.each do |v|
        accu << [key.to_s, v.to_s]
      end
    else
      accu << [key.to_s, value.to_s]
    end
    accu
  end

  if sort
    # Useful for OAuth and optimizing caching systems
    form_values = form_values.sort
  end
  escaped_form_values = form_values.map do |(key, value)|
    # Line breaks are CRLF pairs
    [
      self.encode_component(
        key.gsub(/(\r\n|\n|\r)/, "\r\n"),
        CharacterClasses::UNRESERVED
      ).gsub("%20", "+"),
      self.encode_component(
        value.gsub(/(\r\n|\n|\r)/, "\r\n"),
        CharacterClasses::UNRESERVED
      ).gsub("%20", "+")
    ]
  end
  return escaped_form_values.map do |(key, value)|
    "#{key}=#{value}"
  end.join("&")
end

.form_unencode(encoded_value) ⇒ Array

Decodes a String according to the rules for the application/x-www-form-urlencoded MIME type.


771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
# File 'lib/addressable/uri.rb', line 771

def self.form_unencode(encoded_value)
  if !encoded_value.respond_to?(:to_str)
    raise TypeError, "Can't convert #{encoded_value.class} into String."
  end
  encoded_value = encoded_value.to_str
  split_values = encoded_value.split("&").map do |pair|
    pair.split("=", 2)
  end
  return split_values.map do |(key, value)|
    [
      key ? self.unencode_component(
        key.gsub("+", "%20")).gsub(/(\r\n|\n|\r)/, "\n") : nil,
      value ? (self.unencode_component(
        value.gsub("+", "%20")).gsub(/(\r\n|\n|\r)/, "\n")) : nil
    ]
  end
end

.heuristic_parse(uri, hints = {}) ⇒ Addressable::URI

Converts an input to a URI. The input does not have to be a valid URI — the method will use heuristics to guess what URI was intended. This is not standards-compliant, merely user-friendly.


164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
# File 'lib/addressable/uri.rb', line 164

def self.heuristic_parse(uri, hints={})
  # If we were given nil, return nil.
  return nil unless uri
  # If a URI object is passed, just return itself.
  return uri.dup if uri.kind_of?(self)

  # If a URI object of the Ruby standard library variety is passed,
  # convert it to a string, then parse the string.
  # We do the check this way because we don't want to accidentally
  # cause a missing constant exception to be thrown.
  if uri.class.name =~ /^URI\b/
    uri = uri.to_s
  end

  if !uri.respond_to?(:to_str)
    raise TypeError, "Can't convert #{uri.class} into String."
  end
  # Otherwise, convert to a String
  uri = uri.to_str.dup.strip
  hints = {
    :scheme => "http"
  }.merge(hints)
  case uri
  when /^http:\//i
    uri.sub!(/^http:\/+/i, "http://")
  when /^https:\//i
    uri.sub!(/^https:\/+/i, "https://")
  when /^feed:\/+http:\//i
    uri.sub!(/^feed:\/+http:\/+/i, "feed:http://")
  when /^feed:\//i
    uri.sub!(/^feed:\/+/i, "feed://")
  when %r[^file:/{4}]i
    uri.sub!(%r[^file:/+]i, "file:////")
  when %r[^file://localhost/]i
    uri.sub!(%r[^file://localhost/+]i, "file:///")
  when %r[^file:/+]i
    uri.sub!(%r[^file:/+]i, "file:///")
  when /^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}/
    uri.sub!(/^/, hints[:scheme] + "://")
  when /\A\d+\..*:\d+\z/
    uri = "#{hints[:scheme]}://#{uri}"
  end
  match = uri.match(URIREGEX)
  fragments = match.captures
  authority = fragments[3]
  if authority && authority.length > 0
    new_authority = authority.tr("\\", "/").gsub(" ", "%20")
    # NOTE: We want offset 4, not 3!
    offset = match.offset(4)
    uri = uri.dup
    uri[offset[0]...offset[1]] = new_authority
  end
  parsed = self.parse(uri)
  if parsed.scheme =~ /^[^\/?#\.]+\.[^\/?#]+$/
    parsed = self.parse(hints[:scheme] + "://" + uri)
  end
  if parsed.path.include?(".")
    if parsed.path[/\[email protected]\b/]
      parsed.scheme = "mailto" unless parsed.scheme
    elsif new_host = parsed.path[/^([^\/]+\.[^\/]*)/, 1]
      parsed.defer_validation do
        new_path = parsed.path.sub(
          Regexp.new("^" + Regexp.escape(new_host)), EMPTY_STR)
        parsed.host = new_host
        parsed.path = new_path
        parsed.scheme = hints[:scheme] unless parsed.scheme
      end
    end
  end
  return parsed
end

.ip_based_schemesObject

Returns an array of known ip-based schemes. These schemes typically use a similar URI form: //<user>:<password>@<host>:<port>/<url-path>


1358
1359
1360
# File 'lib/addressable/uri.rb', line 1358

def self.ip_based_schemes
  return self.port_mapping.keys
end

.join(*uris) ⇒ Addressable::URI

Joins several URIs together.

Examples:

base = "http://example.com/"
uri = Addressable::URI.parse("relative/path")
Addressable::URI.join(base, uri)
#=> #<Addressable::URI:0xcab390 URI:http://example.com/relative/path>

316
317
318
319
320
321
322
323
324
325
326
327
328
# File 'lib/addressable/uri.rb', line 316

def self.join(*uris)
  uri_objects = uris.collect do |uri|
    if !uri.respond_to?(:to_str)
      raise TypeError, "Can't convert #{uri.class} into String."
    end
    uri.kind_of?(self) ? uri : self.parse(uri.to_str)
  end
  result = uri_objects.shift.dup
  for uri in uri_objects
    result.join!(uri)
  end
  return result
end

.normalize_component(component, character_class = CharacterClasses::RESERVED + CharacterClasses::UNRESERVED, leave_encoded = '') ⇒ String

Normalizes the encoding of a URI component.

Examples:

Addressable::URI.normalize_component("simpl%65/%65xampl%65", "b-zB-Z")
=> "simple%2Fex%61mple"
Addressable::URI.normalize_component(
  "simpl%65/%65xampl%65", /[^b-zB-Z]/
)
=> "simple%2Fex%61mple"
Addressable::URI.normalize_component(
  "simpl%65/%65xampl%65",
  Addressable::URI::CharacterClasses::UNRESERVED
)
=> "simple%2Fexample"
Addressable::URI.normalize_component(
  "one%20two%2fthree%26four",
  "0-9a-zA-Z &/",
  "/"
)
=> "one two%2Fthree&four"

532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
# File 'lib/addressable/uri.rb', line 532

def self.normalize_component(component, character_class=
    CharacterClasses::RESERVED + CharacterClasses::UNRESERVED,
    leave_encoded='')
  return nil if component.nil?

  begin
    component = component.to_str
  rescue NoMethodError, TypeError
    raise TypeError, "Can't convert #{component.class} into String."
  end if !component.is_a? String

  if ![String, Regexp].include?(character_class.class)
    raise TypeError,
      "Expected String or Regexp, got #{character_class.inspect}"
  end
  if character_class.kind_of?(String)
    leave_re = if leave_encoded.length > 0
      character_class = "#{character_class}%" unless character_class.include?('%')

      "|%(?!#{leave_encoded.chars.map do |char|
        seq = SEQUENCE_ENCODING_TABLE[char]
        [seq.upcase, seq.downcase]
      end.flatten.join('|')})"
    end

    character_class = /[^#{character_class}]#{leave_re}/
  end
  # We can't perform regexps on invalid UTF sequences, but
  # here we need to, so switch to ASCII.
  component = component.dup
  component.force_encoding(Encoding::ASCII_8BIT)
  unencoded = self.unencode_component(component, String, leave_encoded)
  begin
    encoded = self.encode_component(
      Addressable::IDNA.unicode_normalize_kc(unencoded),
      character_class,
      leave_encoded
    )
  rescue ArgumentError
    encoded = self.encode_component(unencoded)
  end
  encoded.force_encoding(Encoding::UTF_8)
  return encoded
end

.normalized_encode(uri, return_type = String) ⇒ String, Addressable::URI

Normalizes the encoding of a URI. Characters within a hostname are not percent encoded to allow for internationalized domain names.


648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
# File 'lib/addressable/uri.rb', line 648

def self.normalized_encode(uri, return_type=String)
  begin
    uri = uri.to_str
  rescue NoMethodError, TypeError
    raise TypeError, "Can't convert #{uri.class} into String."
  end if !uri.is_a? String

  if ![String, ::Addressable::URI].include?(return_type)
    raise TypeError,
      "Expected Class (String or Addressable::URI), " +
      "got #{return_type.inspect}"
  end
  uri_object = uri.kind_of?(self) ? uri : self.parse(uri)
  components = {
    :scheme => self.unencode_component(uri_object.scheme),
    :user => self.unencode_component(uri_object.user),
    :password => self.unencode_component(uri_object.password),
    :host => self.unencode_component(uri_object.host),
    :port => (uri_object.port.nil? ? nil : uri_object.port.to_s),
    :path => self.unencode_component(uri_object.path),
    :query => self.unencode_component(uri_object.query),
    :fragment => self.unencode_component(uri_object.fragment)
  }
  components.each do |key, value|
    if value != nil
      begin
        components[key] =
          Addressable::IDNA.unicode_normalize_kc(value.to_str)
      rescue ArgumentError
        # Likely a malformed UTF-8 character, skip unicode normalization
        components[key] = value.to_str
      end
    end
  end
  encoded_uri = Addressable::URI.new(
    :scheme => self.encode_component(components[:scheme],
      Addressable::URI::CharacterClasses::SCHEME),
    :user => self.encode_component(components[:user],
      Addressable::URI::CharacterClasses::UNRESERVED),
    :password => self.encode_component(components[:password],
      Addressable::URI::CharacterClasses::UNRESERVED),
    :host => components[:host],
    :port => components[:port],
    :path => self.encode_component(components[:path],
      Addressable::URI::CharacterClasses::PATH),
    :query => self.encode_component(components[:query],
      Addressable::URI::CharacterClasses::QUERY),
    :fragment => self.encode_component(components[:fragment],
      Addressable::URI::CharacterClasses::FRAGMENT)
  )
  if return_type == String
    return encoded_uri.to_s
  elsif return_type == ::Addressable::URI
    return encoded_uri
  end
end

.parse(uri) ⇒ Addressable::URI

Returns a URI object based on the parsed string.


87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
# File 'lib/addressable/uri.rb', line 87

def self.parse(uri)
  # If we were given nil, return nil.
  return nil unless uri
  # If a URI object is passed, just return itself.
  return uri.dup if uri.kind_of?(self)

  # If a URI object of the Ruby standard library variety is passed,
  # convert it to a string, then parse the string.
  # We do the check this way because we don't want to accidentally
  # cause a missing constant exception to be thrown.
  if uri.class.name =~ /^URI\b/
    uri = uri.to_s
  end

  # Otherwise, convert to a String
  begin
    uri = uri.to_str
  rescue TypeError, NoMethodError
    raise TypeError, "Can't convert #{uri.class} into String."
  end if not uri.is_a? String

  # This Regexp supplied as an example in RFC 3986, and it works great.
  scan = uri.scan(URIREGEX)
  fragments = scan[0]
  scheme = fragments[1]
  authority = fragments[3]
  path = fragments[4]
  query = fragments[6]
  fragment = fragments[8]
  user = nil
  password = nil
  host = nil
  port = nil
  if authority != nil
    # The Regexp above doesn't split apart the authority.
    userinfo = authority[/^([^\[\]]*)@/, 1]
    if userinfo != nil
      user = userinfo.strip[/^([^:]*):?/, 1]
      password = userinfo.strip[/:(.*)$/, 1]
    end
    host = authority.sub(
      /^([^\[\]]*)@/, EMPTY_STR
    ).sub(
      /:([^:@\[\]]*?)$/, EMPTY_STR
    )
    port = authority[/:([^:@\[\]]*?)$/, 1]
  end
  if port == EMPTY_STR
    port = nil
  end

  return new(
    :scheme => scheme,
    :user => user,
    :password => password,
    :host => host,
    :port => port,
    :path => path,
    :query => query,
    :fragment => fragment
  )
end

.port_mappingObject

Returns a hash of common IP-based schemes and their default port numbers. Adding new schemes to this hash, as necessary, will allow for better URI normalization.


1365
1366
1367
# File 'lib/addressable/uri.rb', line 1365

def self.port_mapping
  PORT_MAPPING
end

.unencode(uri, return_type = String, leave_encoded = '') ⇒ String, Addressable::URI Also known as: unescape, unencode_component, unescape_component

Unencodes any percent encoded characters within a URI component. This method may be used for unencoding either components or full URIs, however, it is recommended to use the unencode_component alias when unencoding components.


450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
# File 'lib/addressable/uri.rb', line 450

def self.unencode(uri, return_type=String, leave_encoded='')
  return nil if uri.nil?

  begin
    uri = uri.to_str
  rescue NoMethodError, TypeError
    raise TypeError, "Can't convert #{uri.class} into String."
  end if !uri.is_a? String
  if ![String, ::Addressable::URI].include?(return_type)
    raise TypeError,
      "Expected Class (String or Addressable::URI), " +
      "got #{return_type.inspect}"
  end
  uri = uri.dup
  # Seriously, only use UTF-8. I'm really not kidding!
  uri.force_encoding("utf-8")
  leave_encoded = leave_encoded.dup.force_encoding("utf-8")
  result = uri.gsub(/%[0-9a-f]{2}/iu) do |sequence|
    c = sequence[1..3].to_i(16).chr
    c.force_encoding("utf-8")
    leave_encoded.include?(c) ? sequence : c
  end
  result.force_encoding("utf-8")
  if return_type == String
    return result
  elsif return_type == ::Addressable::URI
    return ::Addressable::URI.parse(result)
  end
end

Instance Method Details

#==(uri) ⇒ TrueClass, FalseClass

Returns true if the URI objects are equal. This method normalizes both URIs before doing the comparison.


2232
2233
2234
2235
# File 'lib/addressable/uri.rb', line 2232

def ==(uri)
  return false unless uri.kind_of?(URI)
  return self.normalize.to_s == uri.normalize.to_s
end

#===(uri) ⇒ TrueClass, FalseClass

Returns true if the URI objects are equal. This method normalizes both URIs before doing the comparison, and allows comparison against Strings.


2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
# File 'lib/addressable/uri.rb', line 2210

def ===(uri)
  if uri.respond_to?(:normalize)
    uri_string = uri.normalize.to_s
  else
    begin
      uri_string = ::Addressable::URI.parse(uri).normalize.to_s
    rescue InvalidURIError, TypeError
      return false
    end
  end
  return self.normalize.to_s == uri_string
end

#absolute?TrueClass, FalseClass

Determines if the URI is absolute.


1872
1873
1874
# File 'lib/addressable/uri.rb', line 1872

def absolute?
  return !relative?
end

#authorityString

The authority component for this URI. Combines the user, password, host, and port components.


1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
# File 'lib/addressable/uri.rb', line 1221

def authority
  self.host && @authority ||= begin
    authority = String.new
    if self.userinfo != nil
      authority << "#{self.userinfo}@"
    end
    authority << self.host
    if self.port != nil
      authority << ":#{self.port}"
    end
    authority
  end
end

#authority=(new_authority) ⇒ Object

Sets the authority component for this URI.


1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
# File 'lib/addressable/uri.rb', line 1263

def authority=(new_authority)
  if new_authority
    if !new_authority.respond_to?(:to_str)
      raise TypeError, "Can't convert #{new_authority.class} into String."
    end
    new_authority = new_authority.to_str
    new_userinfo = new_authority[/^([^\[\]]*)@/, 1]
    if new_userinfo
      new_user = new_userinfo.strip[/^([^:]*):?/, 1]
      new_password = new_userinfo.strip[/:(.*)$/, 1]
    end
    new_host = new_authority.sub(
      /^([^\[\]]*)@/, EMPTY_STR
    ).sub(
      /:([^:@\[\]]*?)$/, EMPTY_STR
    )
    new_port =
      new_authority[/:([^:@\[\]]*?)$/, 1]
  end

  # Password assigned first to ensure validity in case of nil
  self.password = defined?(new_password) ? new_password : nil
  self.user = defined?(new_user) ? new_user : nil
  self.host = defined?(new_host) ? new_host : nil
  self.port = defined?(new_port) ? new_port : nil

  # Reset dependent values
  remove_instance_variable(:@userinfo) if defined?(@userinfo)
  remove_instance_variable(:@normalized_userinfo) if defined?(@normalized_userinfo)
  remove_composite_values

  # Ensure we haven't created an invalid URI
  validate()
end

#basenameString

The basename, if any, of the file in the path component.


1581
1582
1583
1584
# File 'lib/addressable/uri.rb', line 1581

def basename
  # Path cannot be nil
  return File.basename(self.path).sub(/;[^\/]*$/, EMPTY_STR)
end

#default_portInteger

The default port for this URI's scheme. This method will always returns the default port for the URI's scheme regardless of the presence of an explicit port in the URI.


1445
1446
1447
# File 'lib/addressable/uri.rb', line 1445

def default_port
  URI.port_mapping[self.scheme.strip.downcase] if self.scheme
end

#defer_validationObject

This method allows you to make several changes to a URI simultaneously, which separately would cause validation errors, but in conjunction, are valid. The URI will be revalidated as soon as the entire block has been executed.

Raises:

  • (LocalJumpError)

2389
2390
2391
2392
2393
2394
2395
2396
# File 'lib/addressable/uri.rb', line 2389

def defer_validation
  raise LocalJumpError, "No block given." unless block_given?
  @validation_deferred = true
  yield
  @validation_deferred = false
  validate
  return nil
end

#display_uriAddressable::URI

Creates a URI suitable for display to users. If semantic attacks are likely, the application should try to detect these and warn the user. See <a href=“RFC”>www.ietf.org/rfc/rfc3986.txt“>RFC 3986</a>, section 7.6 for more information.


2194
2195
2196
2197
2198
# File 'lib/addressable/uri.rb', line 2194

def display_uri
  display_uri = self.normalize
  display_uri.host = ::Addressable::IDNA.to_unicode(display_uri.host)
  return display_uri
end

#domainObject

Returns the public suffix domain for this host.

Examples:

Addressable::URI.parse("http://www.example.co.uk").domain # => "example.co.uk"

1212
1213
1214
# File 'lib/addressable/uri.rb', line 1212

def domain
  PublicSuffix.domain(self.host, ignore_private: true)
end

#dupAddressable::URI

Clones the URI object.


2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
# File 'lib/addressable/uri.rb', line 2264

def dup
  duplicated_uri = self.class.new(
    :scheme => self.scheme ? self.scheme.dup : nil,
    :user => self.user ? self.user.dup : nil,
    :password => self.password ? self.password.dup : nil,
    :host => self.host ? self.host.dup : nil,
    :port => self.port,
    :path => self.path ? self.path.dup : nil,
    :query => self.query ? self.query.dup : nil,
    :fragment => self.fragment ? self.fragment.dup : nil
  )
  return duplicated_uri
end

#empty?TrueClass, FalseClass

Determines if the URI is an empty string.


2326
2327
2328
# File 'lib/addressable/uri.rb', line 2326

def empty?
  return self.to_s.empty?
end

#eql?(uri) ⇒ TrueClass, FalseClass

Returns true if the URI objects are equal. This method does NOT normalize either URI before doing the comparison.


2246
2247
2248
2249
# File 'lib/addressable/uri.rb', line 2246

def eql?(uri)
  return false unless uri.kind_of?(URI)
  return self.to_s == uri.to_s
end

#extnameString

The extname, if any, of the file in the path component. Empty string if there is no extension.


1591
1592
1593
1594
# File 'lib/addressable/uri.rb', line 1591

def extname
  return nil unless self.path
  return File.extname(self.basename)
end

#fragmentString

The fragment component for this URI.


1799
1800
1801
# File 'lib/addressable/uri.rb', line 1799

def fragment
  return defined?(@fragment) ? @fragment : nil
end

#fragment=(new_fragment) ⇒ Object

Sets the fragment component for this URI.


1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
# File 'lib/addressable/uri.rb', line 1828

def fragment=(new_fragment)
  if new_fragment && !new_fragment.respond_to?(:to_str)
    raise TypeError, "Can't convert #{new_fragment.class} into String."
  end
  @fragment = new_fragment ? new_fragment.to_str : nil

  # Reset dependent values
  remove_instance_variable(:@normalized_fragment) if defined?(@normalized_fragment)
  remove_composite_values

  # Ensure we haven't created an invalid URI
  validate()
end

#freezeAddressable::URI

Freeze URI, initializing instance variables.


845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
# File 'lib/addressable/uri.rb', line 845

def freeze
  self.normalized_scheme
  self.normalized_user
  self.normalized_password
  self.normalized_userinfo
  self.normalized_host
  self.normalized_port
  self.normalized_authority
  self.normalized_site
  self.normalized_path
  self.normalized_query
  self.normalized_fragment
  self.hash
  super
end

#hashInteger

A hash value that will make a URI equivalent to its normalized form.


2256
2257
2258
# File 'lib/addressable/uri.rb', line 2256

def hash
  @hash ||= self.to_s.hash * -1
end

#hostString

The host component for this URI.


1107
1108
1109
# File 'lib/addressable/uri.rb', line 1107

def host
  return defined?(@host) ? @host : nil
end

#host=(new_host) ⇒ Object

Sets the host component for this URI.


1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
# File 'lib/addressable/uri.rb', line 1143

def host=(new_host)
  if new_host && !new_host.respond_to?(:to_str)
    raise TypeError, "Can't convert #{new_host.class} into String."
  end
  @host = new_host ? new_host.to_str : nil

  # Reset dependent values
  remove_instance_variable(:@authority) if defined?(@authority)
  remove_instance_variable(:@normalized_host) if defined?(@normalized_host)
  remove_composite_values

  # Ensure we haven't created an invalid URI
  validate()
end

#hostnameString

This method is same as URI::Generic#host except brackets for IPv6 (and 'IPvFuture') addresses are removed.

See Also:


1165
1166
1167
1168
# File 'lib/addressable/uri.rb', line 1165

def hostname
  v = self.host
  /\A\[(.*)\]\z/ =~ v ? $1 : v
end

#hostname=(new_hostname) ⇒ Object

This method is same as URI::Generic#host= except the argument can be a bare IPv6 address (or 'IPvFuture').

See Also:


1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
# File 'lib/addressable/uri.rb', line 1177

def hostname=(new_hostname)
  if new_hostname &&
      (new_hostname.respond_to?(:ipv4?) || new_hostname.respond_to?(:ipv6?))
    new_hostname = new_hostname.to_s
  elsif new_hostname && !new_hostname.respond_to?(:to_str)
    raise TypeError, "Can't convert #{new_hostname.class} into String."
  end
  v = new_hostname ? new_hostname.to_str : nil
  v = "[#{v}]" if /\A\[.*\]\z/ !~ v && /:/ =~ v
  self.host = v
end

#inferred_portInteger

The inferred port component for this URI. This method will normalize to the default port for the URI's scheme if the port isn't explicitly specified in the URI.


1431
1432
1433
1434
1435
1436
1437
# File 'lib/addressable/uri.rb', line 1431

def inferred_port
  if self.port.to_i == 0
    self.default_port
  else
    self.port.to_i
  end
end

#inspectString

Returns a String representation of the URI object's state.


2377
2378
2379
# File 'lib/addressable/uri.rb', line 2377

def inspect
  sprintf("#<%s:%#0x URI:%s>", URI.to_s, self.object_id, self.to_s)
end

#ip_based?TrueClass, FalseClass

Determines if the scheme indicates an IP-based protocol.


1848
1849
1850
1851
1852
1853
1854
# File 'lib/addressable/uri.rb', line 1848

def ip_based?
  if self.scheme
    return URI.ip_based_schemes.include?(
      self.scheme.strip.downcase)
  end
  return false
end

#join(uri) ⇒ Addressable::URI Also known as: +

Joins two URIs together.


1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
# File 'lib/addressable/uri.rb', line 1882

def join(uri)
  if !uri.respond_to?(:to_str)
    raise TypeError, "Can't convert #{uri.class} into String."
  end
  if !uri.kind_of?(URI)
    # Otherwise, convert to a String, then parse.
    uri = URI.parse(uri.to_str)
  end
  if uri.to_s.empty?
    return self.dup
  end

  joined_scheme = nil
  joined_user = nil
  joined_password = nil
  joined_host = nil
  joined_port = nil
  joined_path = nil
  joined_query = nil
  joined_fragment = nil

  # Section 5.2.2 of RFC 3986
  if uri.scheme != nil
    joined_scheme = uri.scheme
    joined_user = uri.user
    joined_password = uri.password
    joined_host = uri.host
    joined_port = uri.port
    joined_path = URI.normalize_path(uri.path)
    joined_query = uri.query
  else
    if uri.authority != nil
      joined_user = uri.user
      joined_password = uri.password
      joined_host = uri.host
      joined_port = uri.port
      joined_path = URI.normalize_path(uri.path)
      joined_query = uri.query
    else
      if uri.path == nil || uri.path.empty?
        joined_path = self.path
        if uri.query != nil
          joined_query = uri.query
        else
          joined_query = self.query
        end
      else
        if uri.path[0..0] == SLASH
          joined_path = URI.normalize_path(uri.path)
        else
          base_path = self.path.dup
          base_path = EMPTY_STR if base_path == nil
          base_path = URI.normalize_path(base_path)

          # Section 5.2.3 of RFC 3986
          #
          # Removes the right-most path segment from the base path.
          if base_path.include?(SLASH)
            base_path.sub!(/\/[^\/]+$/, SLASH)
          else
            base_path = EMPTY_STR
          end

          # If the base path is empty and an authority segment has been
          # defined, use a base path of SLASH
          if base_path.empty? && self.authority != nil
            base_path = SLASH
          end

          joined_path = URI.normalize_path(base_path + uri.path)
        end
        joined_query = uri.query
      end
      joined_user = self.user
      joined_password = self.password
      joined_host = self.host
      joined_port = self.port
    end
    joined_scheme = self.scheme
  end
  joined_fragment = uri.fragment

  return self.class.new(
    :scheme => joined_scheme,
    :user => joined_user,
    :password => joined_password,
    :host => joined_host,
    :port => joined_port,
    :path => joined_path,
    :query => joined_query,
    :fragment => joined_fragment
  )
end

#join!(uri) ⇒ Addressable::URI

Destructive form of join.

See Also:


1985
1986
1987
# File 'lib/addressable/uri.rb', line 1985

def join!(uri)
  replace_self(self.join(uri))
end

#merge(hash) ⇒ Addressable::URI

Merges a URI with a Hash of components. This method has different behavior from join. Any components present in the hash parameter will override the original components. The path component is not treated specially.

See Also:

  • Hash#merge

2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
# File 'lib/addressable/uri.rb', line 2000

def merge(hash)
  if !hash.respond_to?(:to_hash)
    raise TypeError, "Can't convert #{hash.class} into Hash."
  end
  hash = hash.to_hash

  if hash.has_key?(:authority)
    if (hash.keys & [:userinfo, :user, :password, :host, :port]).any?
      raise ArgumentError,
        "Cannot specify both an authority and any of the components " +
        "within the authority."
    end
  end
  if hash.has_key?(:userinfo)
    if (hash.keys & [:user, :password]).any?
      raise ArgumentError,
        "Cannot specify both a userinfo and either the user or password."
    end
  end

  uri = self.class.new
  uri.defer_validation do
    # Bunch of crazy logic required because of the composite components
    # like userinfo and authority.
    uri.scheme =
      hash.has_key?(:scheme) ? hash[:scheme] : self.scheme
    if hash.has_key?(:authority)
      uri.authority =
        hash.has_key?(:authority) ? hash[:authority] : self.authority
    end
    if hash.has_key?(:userinfo)
      uri.userinfo =
        hash.has_key?(:userinfo) ? hash[:userinfo] : self.userinfo
    end
    if !hash.has_key?(:userinfo) && !hash.has_key?(:authority)
      uri.user =
        hash.has_key?(:user) ? hash[:user] : self.user
      uri.password =
        hash.has_key?(:password) ? hash[:password] : self.password
    end
    if !hash.has_key?(:authority)
      uri.host =
        hash.has_key?(:host) ? hash[:host] : self.host
      uri.port =
        hash.has_key?(:port) ? hash[:port] : self.port
    end
    uri.path =
      hash.has_key?(:path) ? hash[:path] : self.path
    uri.query =
      hash.has_key?(:query) ? hash[:query] : self.query
    uri.fragment =
      hash.has_key?(:fragment) ? hash[:fragment] : self.fragment
  end

  return uri
end

#merge!(uri) ⇒ Addressable::URI

Destructive form of merge.

See Also:


2065
2066
2067
# File 'lib/addressable/uri.rb', line 2065

def merge!(uri)
  replace_self(self.merge(uri))
end

#normalizeAddressable::URI

Returns a normalized URI object.

NOTE: This method does not attempt to fully conform to specifications. It exists largely to correct other people's failures to read the specifications, and also to deal with caching issues since several different URIs may represent the same resource and should not be cached multiple times.


2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
# File 'lib/addressable/uri.rb', line 2157

def normalize
  # This is a special exception for the frequently misused feed
  # URI scheme.
  if normalized_scheme == "feed"
    if self.to_s =~ /^feed:\/*http:\/*/
      return URI.parse(
        self.to_s[/^feed:\/*(http:\/*.*)/, 1]
      ).normalize
    end
  end

  return self.class.new(
    :scheme => normalized_scheme,
    :authority => normalized_authority,
    :path => normalized_path,
    :query => normalized_query,
    :fragment => normalized_fragment
  )
end

#normalize!Addressable::URI

Destructively normalizes this URI object.

See Also:


2183
2184
2185
# File 'lib/addressable/uri.rb', line 2183

def normalize!
  replace_self(self.normalize)
end

#normalized_authorityString

The authority component for this URI, normalized.


1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
# File 'lib/addressable/uri.rb', line 1239

def normalized_authority
  return nil unless self.authority
  @normalized_authority ||= begin
    authority = String.new
    if self.normalized_userinfo != nil
      authority << "#{self.normalized_userinfo}@"
    end
    authority << self.normalized_host
    if self.normalized_port != nil
      authority << ":#{self.normalized_port}"
    end
    authority
  end
  # All normalized values should be UTF-8
  if @normalized_authority
    @normalized_authority.force_encoding(Encoding::UTF_8)
  end
  @normalized_authority
end

#normalized_fragmentString

The fragment component for this URI, normalized.


1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
# File 'lib/addressable/uri.rb', line 1807

def normalized_fragment
  return nil unless self.fragment
  return @normalized_fragment if defined?(@normalized_fragment)
  @normalized_fragment ||= begin
    component = Addressable::URI.normalize_component(
      self.fragment,
      Addressable::URI::CharacterClasses::FRAGMENT
    )
    component == "" ? nil : component
  end
  # All normalized values should be UTF-8
  if @normalized_fragment
    @normalized_fragment.force_encoding(Encoding::UTF_8)
  end
  @normalized_fragment
end

#normalized_hostString

The host component for this URI, normalized.


1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
# File 'lib/addressable/uri.rb', line 1115

def normalized_host
  return nil unless self.host
  @normalized_host ||= begin
    if !self.host.strip.empty?
      result = ::Addressable::IDNA.to_ascii(
        URI.unencode_component(self.host.strip.downcase)
      )
      if result =~ /[^\.]\.$/
        # Single trailing dots are unnecessary.
        result = result[0...-1]
      end
      result = Addressable::URI.normalize_component(
        result,
        CharacterClasses::HOST)
      result
    else
      EMPTY_STR.dup
    end
  end
  # All normalized values should be UTF-8
  @normalized_host.force_encoding(Encoding::UTF_8) if @normalized_host
  @normalized_host
end

#normalized_passwordString

The password component for this URI, normalized.


983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
# File 'lib/addressable/uri.rb', line 983

def normalized_password
  return nil unless self.password
  return @normalized_password if defined?(@normalized_password)
  @normalized_password ||= begin
    if self.normalized_scheme =~ /https?/ && self.password.strip.empty? &&
        (!self.user || self.user.strip.empty?)
      nil
    else
      Addressable::URI.normalize_component(
        self.password.strip,
        Addressable::URI::CharacterClasses::UNRESERVED
      )
    end
  end
  # All normalized values should be UTF-8
  if @normalized_password
    @normalized_password.force_encoding(Encoding::UTF_8)
  end
  @normalized_password
end

#normalized_pathString

The path component for this URI, normalized.


1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
# File 'lib/addressable/uri.rb', line 1528

def normalized_path
  @normalized_path ||= begin
    path = self.path.to_s
    if self.scheme == nil && path =~ NORMPATH
      # Relative paths with colons in the first segment are ambiguous.
      path = path.sub(":", "%2F")
    end
    # String#split(delimeter, -1) uses the more strict splitting behavior
    # found by default in Python.
    result = path.strip.split(SLASH, -1).map do |segment|
      Addressable::URI.normalize_component(
        segment,
        Addressable::URI::CharacterClasses::PCHAR
      )
    end.join(SLASH)

    result = URI.normalize_path(result)
    if result.empty? &&
        ["http", "https", "ftp", "tftp"].include?(self.normalized_scheme)
      result = SLASH.dup
    end
    result
  end
  # All normalized values should be UTF-8
  @normalized_path.force_encoding(Encoding::UTF_8) if @normalized_path
  @normalized_path
end

#normalized_portInteger

The port component for this URI, normalized.


1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
# File 'lib/addressable/uri.rb', line 1383

def normalized_port
  return nil unless self.port
  return @normalized_port if defined?(@normalized_port)
  @normalized_port ||= begin
    if URI.port_mapping[self.normalized_scheme] == self.port
      nil
    else
      self.port
    end
  end
end

#normalized_query(*flags) ⇒ String

The query component for this URI, normalized.


1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
# File 'lib/addressable/uri.rb', line 1608

def normalized_query(*flags)
  return nil unless self.query
  return @normalized_query if defined?(@normalized_query)
  @normalized_query ||= begin
    modified_query_class = Addressable::URI::CharacterClasses::QUERY.dup
    # Make sure possible key-value pair delimiters are escaped.
    modified_query_class.sub!("\\&", "").sub!("\\;", "")
    pairs = (self.query || "").split("&", -1)
    pairs.delete_if(&:empty?) if flags.include?(:compacted)
    pairs.sort! if flags.include?(:sorted)
    component = pairs.map do |pair|
      Addressable::URI.normalize_component(pair, modified_query_class, "+")
    end.join("&")
    component == "" ? nil : component
  end
  # All normalized values should be UTF-8
  @normalized_query.force_encoding(Encoding::UTF_8) if @normalized_query
  @normalized_query
end

#normalized_schemeString

The scheme component for this URI, normalized.


873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
# File 'lib/addressable/uri.rb', line 873

def normalized_scheme
  return nil unless self.scheme
  @normalized_scheme ||= begin
    if self.scheme =~ /^\s*ssh\+svn\s*$/i
      "svn+ssh".dup
    else
      Addressable::URI.normalize_component(
        self.scheme.strip.downcase,
        Addressable::URI::CharacterClasses::SCHEME
      )
    end
  end
  # All normalized values should be UTF-8
  @normalized_scheme.force_encoding(Encoding::UTF_8) if @normalized_scheme
  @normalized_scheme
end

#normalized_siteString

The normalized combination of components that represent a site. Combines the scheme, user, password, host, and port components. Primarily useful for HTTP and HTTPS.

For example, "http://example.com/path?query" would have a site value of "http://example.com".


1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
# File 'lib/addressable/uri.rb', line 1476

def normalized_site
  return nil unless self.site
  @normalized_site ||= begin
    site_string = "".dup
    if self.normalized_scheme != nil
      site_string << "#{self.normalized_scheme}:"
    end
    if self.normalized_authority != nil
      site_string << "//#{self.normalized_authority}"
    end
    site_string
  end
  # All normalized values should be UTF-8
  @normalized_site.force_encoding(Encoding::UTF_8) if @normalized_site
  @normalized_site
end

#normalized_userString

The user component for this URI, normalized.


926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
# File 'lib/addressable/uri.rb', line 926

def normalized_user
  return nil unless self.user
  return @normalized_user if defined?(@normalized_user)
  @normalized_user ||= begin
    if normalized_scheme =~ /https?/ && self.user.strip.empty? &&
        (!self.password || self.password.strip.empty?)
      nil
    else
      Addressable::URI.normalize_component(
        self.user.strip,
        Addressable::URI::CharacterClasses::UNRESERVED
      )
    end
  end
  # All normalized values should be UTF-8
  @normalized_user.force_encoding(Encoding::UTF_8) if @normalized_user
  @normalized_user
end

#normalized_userinfoString

The userinfo component for this URI, normalized.


1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
# File 'lib/addressable/uri.rb', line 1053

def normalized_userinfo
  return nil unless self.userinfo
  return @normalized_userinfo if defined?(@normalized_userinfo)
  @normalized_userinfo ||= begin
    current_user = self.normalized_user
    current_password = self.normalized_password
    if !current_user && !current_password
      nil
    elsif current_user && current_password
      "#{current_user}:#{current_password}".dup
    elsif current_user && !current_password
      "#{current_user}".dup
    end
  end
  # All normalized values should be UTF-8
  if @normalized_userinfo
    @normalized_userinfo.force_encoding(Encoding::UTF_8)
  end
  @normalized_userinfo
end

#omit(*components) ⇒ Addressable::URI

Omits components from a URI.

Examples:

uri = Addressable::URI.parse("http://example.com/path?query")
#=> #<Addressable::URI:0xcc5e7a URI:http://example.com/path?query>
uri.omit(:scheme, :authority)
#=> #<Addressable::URI:0xcc4d86 URI:/path?query>

2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
# File 'lib/addressable/uri.rb', line 2290

def omit(*components)
  invalid_components = components - [
    :scheme, :user, :password, :userinfo, :host, :port, :authority,
    :path, :query, :fragment
  ]
  unless invalid_components.empty?
    raise ArgumentError,
      "Invalid component names: #{invalid_components.inspect}."
  end
  duplicated_uri = self.dup
  duplicated_uri.defer_validation do
    components.each do |component|
      duplicated_uri.send((component.to_s + "=").to_sym, nil)
    end
    duplicated_uri.user = duplicated_uri.normalized_user
  end
  duplicated_uri
end

#omit!(*components) ⇒ Addressable::URI

Destructive form of omit.

See Also:


2317
2318
2319
# File 'lib/addressable/uri.rb', line 2317

def omit!(*components)
  replace_self(self.omit(*components))
end

#originString

The origin for this URI, serialized to ASCII, as per RFC 6454, section 6.2.


1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
# File 'lib/addressable/uri.rb', line 1303

def origin
  if self.scheme && self.authority
    if self.normalized_port
      "#{self.normalized_scheme}://#{self.normalized_host}" +
      ":#{self.normalized_port}"
    else
      "#{self.normalized_scheme}://#{self.normalized_host}"
    end
  else
    "null"
  end
end

#origin=(new_origin) ⇒ Object

Sets the origin for this URI, serialized to ASCII, as per RFC 6454, section 6.2. This assignment will reset the `userinfo` component.


1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
# File 'lib/addressable/uri.rb', line 1322

def origin=(new_origin)
  if new_origin
    if !new_origin.respond_to?(:to_str)
      raise TypeError, "Can't convert #{new_origin.class} into String."
    end
    new_origin = new_origin.to_str
    new_scheme = new_origin[/^([^:\/?#]+):\/\//, 1]
    unless new_scheme
      raise InvalidURIError, 'An origin cannot omit the scheme.'
    end
    new_host = new_origin[/:\/\/([^\/?#:]+)/, 1]
    unless new_host
      raise InvalidURIError, 'An origin cannot omit the host.'
    end
    new_port = new_origin[/:([^:@\[\]\/]*?)$/, 1]
  end

  self.scheme = defined?(new_scheme) ? new_scheme : nil
  self.host = defined?(new_host) ? new_host : nil
  self.port = defined?(new_port) ? new_port : nil
  self.userinfo = nil

  # Reset dependent values
  remove_instance_variable(:@userinfo) if defined?(@userinfo)
  remove_instance_variable(:@normalized_userinfo) if defined?(@normalized_userinfo)
  remove_instance_variable(:@authority) if defined?(@authority)
  remove_instance_variable(:@normalized_authority) if defined?(@normalized_authority)
  remove_composite_values

  # Ensure we haven't created an invalid URI
  validate()
end

#passwordString

The password component for this URI.


975
976
977
# File 'lib/addressable/uri.rb', line 975

def password
  return defined?(@password) ? @password : nil
end

#password=(new_password) ⇒ Object

Sets the password component for this URI.


1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
# File 'lib/addressable/uri.rb', line 1008

def password=(new_password)
  if new_password && !new_password.respond_to?(:to_str)
    raise TypeError, "Can't convert #{new_password.class} into String."
  end
  @password = new_password ? new_password.to_str : nil

  # You can't have a nil user with a non-nil password
  @password ||= nil
  @user ||= nil
  if @password != nil
    @user = EMPTY_STR if @user.nil?
  end

  # Reset dependent values
  remove_instance_variable(:@userinfo) if defined?(@userinfo)
  remove_instance_variable(:@normalized_userinfo) if defined?(@normalized_userinfo)
  remove_instance_variable(:@authority) if defined?(@authority)
  remove_instance_variable(:@normalized_password) if defined?(@normalized_password)
  remove_composite_values

  # Ensure we haven't created an invalid URI
  validate()
end

#pathString

The path component for this URI.


1519
1520
1521
# File 'lib/addressable/uri.rb', line 1519

def path
  return defined?(@path) ? @path : EMPTY_STR
end

#path=(new_path) ⇒ Object

Sets the path component for this URI.


1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
# File 'lib/addressable/uri.rb', line 1560

def path=(new_path)
  if new_path && !new_path.respond_to?(:to_str)
    raise TypeError, "Can't convert #{new_path.class} into String."
  end
  @path = (new_path || EMPTY_STR).to_str
  if !@path.empty? && @path[0..0] != SLASH && host != nil
    @path = "/#{@path}"
  end

  # Reset dependent values
  remove_instance_variable(:@normalized_path) if defined?(@normalized_path)
  remove_composite_values

  # Ensure we haven't created an invalid URI
  validate()
end

#portInteger

The port component for this URI. This is the port number actually given in the URI. This does not infer port numbers from default values.


1375
1376
1377
# File 'lib/addressable/uri.rb', line 1375

def port
  return defined?(@port) ? @port : nil
end

#port=(new_port) ⇒ Object

Sets the port component for this URI.


1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
# File 'lib/addressable/uri.rb', line 1399

def port=(new_port)
  if new_port != nil && new_port.respond_to?(:to_str)
    new_port = Addressable::URI.unencode_component(new_port.to_str)
  end

  if new_port.respond_to?(:valid_encoding?) && !new_port.valid_encoding?
    raise InvalidURIError, "Invalid encoding in port"
  end

  if new_port != nil && !(new_port.to_s =~ /^\d+$/)
    raise InvalidURIError,
      "Invalid port number: #{new_port.inspect}"
  end

  @port = new_port.to_s.to_i
  @port = nil if @port == 0

  # Reset dependent values
  remove_instance_variable(:@authority) if defined?(@authority)
  remove_instance_variable(:@normalized_port) if defined?(@normalized_port)
  remove_composite_values

  # Ensure we haven't created an invalid URI
  validate()
end

#queryString

The query component for this URI.


1600
1601
1602
# File 'lib/addressable/uri.rb', line 1600

def query
  return defined?(@query) ? @query : nil
end

#query=(new_query) ⇒ Object

Sets the query component for this URI.


1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
# File 'lib/addressable/uri.rb', line 1632

def query=(new_query)
  if new_query && !new_query.respond_to?(:to_str)
    raise TypeError, "Can't convert #{new_query.class} into String."
  end
  @query = new_query ? new_query.to_str : nil

  # Reset dependent values
  remove_instance_variable(:@normalized_query) if defined?(@normalized_query)
  remove_composite_values
end

#query_values(return_type = Hash) ⇒ Hash, ...

Converts the query component to a Hash value.

Examples:

Addressable::URI.parse("?one=1&two=2&three=3").query_values
#=> {"one" => "1", "two" => "2", "three" => "3"}
Addressable::URI.parse("?one=two&one=three").query_values(Array)
#=> [["one", "two"], ["one", "three"]]
Addressable::URI.parse("?one=two&one=three").query_values(Hash)
#=> {"one" => "three"}
Addressable::URI.parse("?").query_values
#=> {}
Addressable::URI.parse("").query_values
#=> nil

1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
# File 'lib/addressable/uri.rb', line 1663

def query_values(return_type=Hash)
  empty_accumulator = Array == return_type ? [] : {}
  if return_type != Hash && return_type != Array
    raise ArgumentError, "Invalid return type. Must be Hash or Array."
  end
  return nil if self.query == nil
  split_query = self.query.split("&").map do |pair|
    pair.split("=", 2) if pair && !pair.empty?
  end.compact
  return split_query.inject(empty_accumulator.dup) do |accu, pair|
    # I'd rather use key/value identifiers instead of array lookups,
    # but in this case I really want to maintain the exact pair structure,
    # so it's best to make all changes in-place.
    pair[0] = URI.unencode_component(pair[0])
    if pair[1].respond_to?(:to_str)
      # I loathe the fact that I have to do this. Stupid HTML 4.01.
      # Treating '+' as a space was just an unbelievably bad idea.
      # There was nothing wrong with '%20'!
      # If it ain't broke, don't fix it!
      pair[1] = URI.unencode_component(pair[1].to_str.tr("+", " "))
    end
    if return_type == Hash
      accu[pair[0]] = pair[1]
    else
      accu << pair
    end
    accu
  end
end

#query_values=(new_query_values) ⇒ Object

Sets the query component for this URI from a Hash object. An empty Hash or Array will result in an empty query string.

Examples:

uri.query_values = {:a => "a", :b => ["c", "d", "e"]}
uri.query
# => "a=a&b=c&b=d&b=e"
uri.query_values = [['a', 'a'], ['b', 'c'], ['b', 'd'], ['b', 'e']]
uri.query
# => "a=a&b=c&b=d&b=e"
uri.query_values = [['a', 'a'], ['b', ['c', 'd', 'e']]]
uri.query
# => "a=a&b=c&b=d&b=e"
uri.query_values = [['flag'], ['key', 'value']]
uri.query
# => "flag&key=value"

1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
# File 'lib/addressable/uri.rb', line 1712

def query_values=(new_query_values)
  if new_query_values == nil
    self.query = nil
    return nil
  end

  if !new_query_values.is_a?(Array)
    if !new_query_values.respond_to?(:to_hash)
      raise TypeError,
        "Can't convert #{new_query_values.class} into Hash."
    end
    new_query_values = new_query_values.to_hash
    new_query_values = new_query_values.map do |key, value|
      key = key.to_s if key.kind_of?(Symbol)
      [key, value]
    end
    # Useful default for OAuth and caching.
    # Only to be used for non-Array inputs. Arrays should preserve order.
    new_query_values.sort!
  end

  # new_query_values have form [['key1', 'value1'], ['key2', 'value2']]
  buffer = "".dup
  new_query_values.each do |key, value|
    encoded_key = URI.encode_component(
      key, CharacterClasses::UNRESERVED
    )
    if value == nil
      buffer << "#{encoded_key}&"
    elsif value.kind_of?(Array)
      value.each do |sub_value|
        encoded_value = URI.encode_component(
          sub_value, CharacterClasses::UNRESERVED
        )
        buffer << "#{encoded_key}=#{encoded_value}&"
      end
    else
      encoded_value = URI.encode_component(
        value, CharacterClasses::UNRESERVED
      )
      buffer << "#{encoded_key}=#{encoded_value}&"
    end
  end
  self.query = buffer.chop
end

#relative?TrueClass, FalseClass

Determines if the URI is relative.


1862
1863
1864
# File 'lib/addressable/uri.rb', line 1862

def relative?
  return self.scheme.nil?
end

#request_uriString

The HTTP request URI for this URI. This is the path and the query string.


1763
1764
1765
1766
1767
1768
1769
# File 'lib/addressable/uri.rb', line 1763

def request_uri
  return nil if self.absolute? && self.scheme !~ /^https?$/i
  return (
    (!self.path.empty? ? self.path : SLASH) +
    (self.query ? "?#{self.query}" : EMPTY_STR)
  )
end

#request_uri=(new_request_uri) ⇒ Object

Sets the HTTP request URI for this URI.


1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
# File 'lib/addressable/uri.rb', line 1775

def request_uri=(new_request_uri)
  if !new_request_uri.respond_to?(:to_str)
    raise TypeError, "Can't convert #{new_request_uri.class} into String."
  end
  if self.absolute? && self.scheme !~ /^https?$/i
    raise InvalidURIError,
      "Cannot set an HTTP request URI for a non-HTTP URI."
  end
  new_request_uri = new_request_uri.to_str
  path_component = new_request_uri[/^([^\?]*)\??(?:.*)$/, 1]
  query_component = new_request_uri[/^(?:[^\?]*)\?(.*)$/, 1]
  path_component = path_component.to_s
  path_component = (!path_component.empty? ? path_component : SLASH)
  self.path = path_component
  self.query = query_component

  # Reset dependent values
  remove_composite_values
end

#route_from(uri) ⇒ Addressable::URI

Returns the shortest normalized relative form of this URI that uses the supplied URI as a base for resolution. Returns an absolute URI if necessary. This is effectively the opposite of route_to.


2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
# File 'lib/addressable/uri.rb', line 2078

def route_from(uri)
  uri = URI.parse(uri).normalize
  normalized_self = self.normalize
  if normalized_self.relative?
    raise ArgumentError, "Expected absolute URI, got: #{self.to_s}"
  end
  if uri.relative?
    raise ArgumentError, "Expected absolute URI, got: #{uri.to_s}"
  end
  if normalized_self == uri
    return Addressable::URI.parse("##{normalized_self.fragment}")
  end
  components = normalized_self.to_hash
  if normalized_self.scheme == uri.scheme
    components[:scheme] = nil
    if normalized_self.authority == uri.authority
      components[:user] = nil
      components[:password] = nil
      components[:host] = nil
      components[:port] = nil
      if normalized_self.path == uri.path
        components[:path] = nil
        if normalized_self.query == uri.query
          components[:query] = nil
        end
      else
        if uri.path != SLASH and components[:path]
          self_splitted_path = split_path(components[:path])
          uri_splitted_path = split_path(uri.path)
          self_dir = self_splitted_path.shift
          uri_dir = uri_splitted_path.shift
          while !self_splitted_path.empty? && !uri_splitted_path.empty? and self_dir == uri_dir
            self_dir = self_splitted_path.shift
            uri_dir = uri_splitted_path.shift
          end
          components[:path] = (uri_splitted_path.fill('..') + [self_dir] + self_splitted_path).join(SLASH)
        end
      end
    end
  end
  # Avoid network-path references.
  if components[:host] != nil
    components[:scheme] = normalized_self.scheme
  end
  return Addressable::URI.new(
    :scheme => components[:scheme],
    :user => components[:user],
    :password => components[:password],
    :host => components[:host],
    :port => components[:port],
    :path => components[:path],
    :query => components[:query],
    :fragment => components[:fragment]
  )
end

#route_to(uri) ⇒ Addressable::URI

Returns the shortest normalized relative form of the supplied URI that uses this URI as a base for resolution. Returns an absolute URI if necessary. This is effectively the opposite of route_from.


2143
2144
2145
# File 'lib/addressable/uri.rb', line 2143

def route_to(uri)
  return URI.parse(uri).route_from(self)
end

#schemeString

The scheme component for this URI.


865
866
867
# File 'lib/addressable/uri.rb', line 865

def scheme
  return defined?(@scheme) ? @scheme : nil
end

#scheme=(new_scheme) ⇒ Object

Sets the scheme component for this URI.


894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
# File 'lib/addressable/uri.rb', line 894

def scheme=(new_scheme)
  if new_scheme && !new_scheme.respond_to?(:to_str)
    raise TypeError, "Can't convert #{new_scheme.class} into String."
  elsif new_scheme
    new_scheme = new_scheme.to_str
  end
  if new_scheme && new_scheme !~ /\A[a-z][a-z0-9\.\+\-]*\z/i
    raise InvalidURIError, "Invalid scheme format: #{new_scheme}"
  end
  @scheme = new_scheme
  @scheme = nil if @scheme.to_s.strip.empty?

  # Reset dependent values
  remove_instance_variable(:@normalized_scheme) if defined?(@normalized_scheme)
  remove_composite_values

  # Ensure we haven't created an invalid URI
  validate()
end

#siteString

The combination of components that represent a site. Combines the scheme, user, password, host, and port components. Primarily useful for HTTP and HTTPS.

For example, "http://example.com/path?query" would have a site value of "http://example.com".


1458
1459
1460
1461
1462
1463
1464
1465
# File 'lib/addressable/uri.rb', line 1458

def site
  (self.scheme || self.authority) && @site ||= begin
    site_string = "".dup
    site_string << "#{self.scheme}:" if self.scheme != nil
    site_string << "//#{self.authority}" if self.authority != nil
    site_string
  end
end

#site=(new_site) ⇒ Object

Sets the site value for this URI.


1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
# File 'lib/addressable/uri.rb', line 1497

def site=(new_site)
  if new_site
    if !new_site.respond_to?(:to_str)
      raise TypeError, "Can't convert #{new_site.class} into String."
    end
    new_site = new_site.to_str
    # These two regular expressions derived from the primary parsing
    # expression
    self.scheme = new_site[/^(?:([^:\/?#]+):)?(?:\/\/(?:[^\/?#]*))?$/, 1]
    self.authority = new_site[
      /^(?:(?:[^:\/?#]+):)?(?:\/\/([^\/?#]*))?$/, 1
    ]
  else
    self.scheme = nil
    self.authority = nil
  end
end

#tldObject

Returns the top-level domain for this host.

Examples:

Addressable::URI.parse("http://www.example.co.uk").tld # => "co.uk"

1194
1195
1196
# File 'lib/addressable/uri.rb', line 1194

def tld
  PublicSuffix.parse(self.host, ignore_private: true).tld
end

#tld=(new_tld) ⇒ Object

Sets the top-level domain for this URI.


1202
1203
1204
1205
# File 'lib/addressable/uri.rb', line 1202

def tld=(new_tld)
  replaced_tld = host.sub(/#{tld}\z/, new_tld)
  self.host = PublicSuffix::Domain.new(replaced_tld).to_s
end

#to_hashHash

Returns a Hash of the URI components.


2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
# File 'lib/addressable/uri.rb', line 2360

def to_hash
  return {
    :scheme => self.scheme,
    :user => self.user,
    :password => self.password,
    :host => self.host,
    :port => self.port,
    :path => self.path,
    :query => self.query,
    :fragment => self.fragment
  }
end

#to_sString Also known as: to_str

Converts the URI to a String.


2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
# File 'lib/addressable/uri.rb', line 2334

def to_s
  if self.scheme == nil && self.path != nil && !self.path.empty? &&
      self.path =~ NORMPATH
    raise InvalidURIError,
      "Cannot assemble URI string with ambiguous path: '#{self.path}'"
  end
  @uri_string ||= begin
    uri_string = String.new
    uri_string << "#{self.scheme}:" if self.scheme != nil
    uri_string << "//#{self.authority}" if self.authority != nil
    uri_string << self.path.to_s
    uri_string << "?#{self.query}" if self.query != nil
    uri_string << "##{self.fragment}" if self.fragment != nil
    uri_string.force_encoding(Encoding::UTF_8)
    uri_string
  end
end

#userString

The user component for this URI.


918
919
920
# File 'lib/addressable/uri.rb', line 918

def user
  return defined?(@user) ? @user : nil
end

#user=(new_user) ⇒ Object

Sets the user component for this URI.


949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
# File 'lib/addressable/uri.rb', line 949

def user=(new_user)
  if new_user && !new_user.respond_to?(:to_str)
    raise TypeError, "Can't convert #{new_user.class} into String."
  end
  @user = new_user ? new_user.to_str : nil

  # You can't have a nil user with a non-nil password
  if password != nil
    @user = EMPTY_STR if @user.nil?
  end

  # Reset dependent values
  remove_instance_variable(:@userinfo) if defined?(@userinfo)
  remove_instance_variable(:@normalized_userinfo) if defined?(@normalized_userinfo)
  remove_instance_variable(:@authority) if defined?(@authority)
  remove_instance_variable(:@normalized_user) if defined?(@normalized_user)
  remove_composite_values

  # Ensure we haven't created an invalid URI
  validate()
end

#userinfoString

The userinfo component for this URI. Combines the user and password components.


1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
# File 'lib/addressable/uri.rb', line 1037

def userinfo
  current_user = self.user
  current_password = self.password
  (current_user || current_password) && @userinfo ||= begin
    if current_user && current_password
      "#{current_user}:#{current_password}"
    elsif current_user && !current_password
      "#{current_user}"
    end
  end
end

#userinfo=(new_userinfo) ⇒ Object

Sets the userinfo component for this URI.


1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
# File 'lib/addressable/uri.rb', line 1078

def userinfo=(new_userinfo)
  if new_userinfo && !new_userinfo.respond_to?(:to_str)
    raise TypeError, "Can't convert #{new_userinfo.class} into String."
  end
  new_user, new_password = if new_userinfo
    [
      new_userinfo.to_str.strip[/^(.*):/, 1],
      new_userinfo.to_str.strip[/:(.*)$/, 1]
    ]
  else
    [nil, nil]
  end

  # Password assigned first to ensure validity in case of nil
  self.password = new_password
  self.user = new_user

  # Reset dependent values
  remove_instance_variable(:@authority) if defined?(@authority)
  remove_composite_values

  # Ensure we haven't created an invalid URI
  validate()
end