summaryrefslogtreecommitdiff
path: root/lib/uri/common.rb
blob: 28b5c997892106b731f751065d4caf7ff8e99ac2 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
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
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
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
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
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
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
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
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
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
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
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
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
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
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
#--
# = uri/common.rb
#
# Author:: Akira Yamada <akira@ruby-lang.org>
# Revision:: $Id$
# License::
#   You can redistribute it and/or modify it under the same term as Ruby.
#
# See URI for general documentation
#

require "uri/rfc2396_parser"
require "uri/rfc3986_parser"

module URI
  REGEXP = RFC2396_REGEXP
  Parser = RFC2396_Parser
  RFC3986_PARSER = RFC3986_Parser.new

  # 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
        klass.component[1..-1].each_index do |i|
          begin
            tmp[klass.component[i + 1]] = array_hash[i].clone
          rescue TypeError
            tmp[klass.component[i + 1]] = array_hash[i]
          end
        end

      elsif array_hash.kind_of?(Hash)
        array_hash.each do |key, value|
          begin
            tmp[key] = value.clone
          rescue TypeError
            tmp[key] = value
          end
        end
      else
        raise ArgumentError,
          "expected Array of or Hash of components of #{klass} (#{klass.component[1..-1].join(', ')})"
      end
      tmp[:scheme] = klass.to_s.sub(/\A.*::/, '').downcase

      return tmp
    end
    module_function :make_components_hash
  end

  # module for escaping unsafe characters with codes.
  module Escape
    #
    # == Synopsis
    #
    #   URI.escape(str [, unsafe])
    #
    # == Args
    #
    # +str+::
    #   String to replaces in.
    # +unsafe+::
    #   Regexp that matches all symbols that must be replaced with codes.
    #   By default uses <tt>REGEXP::UNSAFE</tt>.
    #   When this argument is a String, it represents a character set.
    #
    # == Description
    #
    # Escapes the string, replacing all unsafe characters with codes.
    #
    # == Usage
    #
    #   require 'uri'
    #
    #   enc_uri = URI.escape("http://example.com/?a=\11\15")
    #   p enc_uri
    #   # => "http://example.com/?a=%09%0D"
    #
    #   p URI.unescape(enc_uri)
    #   # => "http://example.com/?a=\t\r"
    #
    #   p URI.escape("@?@!", "!?")
    #   # => "@%3F@%21"
    #
    def escape(*arg)
      warn "#{caller(1)[0]}: warning: URI.escape is obsolete" if $VERBOSE
      DEFAULT_PARSER.escape(*arg)
    end
    alias encode escape
    #
    # == Synopsis
    #
    #   URI.unescape(str)
    #
    # == Args
    #
    # +str+::
    #   Unescapes the string.
    #
    # == Usage
    #
    #   require 'uri'
    #
    #   enc_uri = URI.escape("http://example.com/?a=\11\15")
    #   p enc_uri
    #   # => "http://example.com/?a=%09%0D"
    #
    #   p URI.unescape(enc_uri)
    #   # => "http://example.com/?a=\t\r"
    #
    def unescape(*arg)
      warn "#{caller(1)[0]}: warning: URI.unescape is obsolete" if $VERBOSE
      DEFAULT_PARSER.unescape(*arg)
    end
    alias decode unescape
  end # module Escape

  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
  #
  # Not a URI.
  #
  class InvalidURIError < Error; end
  #
  # Not a URI component.
  #
  class InvalidComponentError < Error; end
  #
  # URI is valid, bad usage is not.
  #
  class BadURIError < Error; end

  #
  # == Synopsis
  #
  #   URI::split(uri)
  #
  # == Args
  #
  # +uri+::
  #   String with URI.
  #
  # == Description
  #
  # Splits the string on following parts and returns array with result:
  #
  #   * Scheme
  #   * Userinfo
  #   * Host
  #   * Port
  #   * Registry
  #   * Path
  #   * Opaque
  #   * Query
  #   * Fragment
  #
  # == Usage
  #
  #   require 'uri'
  #
  #   p URI.split("http://www.ruby-lang.org/")
  #   # => ["http", nil, "www.ruby-lang.org", nil, nil, "/", nil, nil, nil]
  #
  def self.split(uri)
    RFC3986_PARSER.split(uri)
  end

  #
  # == Synopsis
  #
  #   URI::parse(uri_str)
  #
  # == Args
  #
  # +uri_str+::
  #   String with URI.
  #
  # == Description
  #
  # Creates one of the URI's subclasses instance from the string.
  #
  # == Raises
  #
  # URI::InvalidURIError
  #   Raised if URI given is not a correct one.
  #
  # == Usage
  #
  #   require 'uri'
  #
  #   uri = URI.parse("http://www.ruby-lang.org/")
  #   p uri
  #   # => #<URI::HTTP:0x202281be URL:http://www.ruby-lang.org/>
  #   p uri.scheme
  #   # => "http"
  #   p uri.host
  #   # => "www.ruby-lang.org"
  #
  # It's recommended to first ::escape the provided +uri_str+ if there are any
  # invalid URI characters.
  #
  def self.parse(uri)
    RFC3986_PARSER.parse(uri)
  end

  #
  # == Synopsis
  #
  #   URI::join(str[, str, ...])
  #
  # == Args
  #
  # +str+::
  #   String(s) to work with, will be converted to RFC3986 URIs before merging.
  #
  # == Description
  #
  # Joins URIs.
  #
  # == Usage
  #
  #   require 'uri'
  #
  #   p URI.join("http://example.com/","main.rbx")
  #   # => #<URI::HTTP:0x2022ac02 URL:http://example.com/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)
    RFC3986_PARSER.join(*str)
  end

  #
  # == Synopsis
  #
  #   URI::extract(str[, schemes][,&blk])
  #
  # == Args
  #
  # +str+::
  #   String to extract URIs from.
  # +schemes+::
  #   Limit URI matching to a specific schemes.
  #
  # == Description
  #
  # Extracts URIs from a string. If block given, iterates through all matched URIs.
  # Returns nil if block given or array with matches.
  #
  # == Usage
  #
  #   require "uri"
  #
  #   URI.extract("text here http://foo.example.org/bla and here mailto:test@example.com and here also.")
  #   # => ["http://foo.example.com/bla", "mailto:test@example.com"]
  #
  def self.extract(str, schemes = nil, &block)
    warn "#{caller(1)[0]}: warning: URI.extract is obsolete" if $VERBOSE
    DEFAULT_PARSER.extract(str, schemes, &block)
  end

  #
  # == Synopsis
  #
  #   URI::regexp([match_schemes])
  #
  # == Args
  #
  # +match_schemes+::
  #   Array of schemes. If given, resulting regexp matches to URIs
  #   whose scheme is one of the match_schemes.
  #
  # == Description
  # Returns a Regexp object which matches to URI-like strings.
  # The Regexp object returned by this method includes arbitrary
  # number of capture group (parentheses).  Never rely on 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)
    warn "#{caller(1)[0]}: warning: URI.regexp is obsolete" if $VERBOSE
    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 = defined? Encoding::UTF_7 ? [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.
  #
  # If +enc+ is given, convert +str+ to the encoding before percent encoding.
  #
  # This is an implementation of
  # http://www.w3.org/TR/2013/CR-html5-20130806/forms.html#url-encoded-form-data
  #
  # See URI.decode_www_form_component, URI.encode_www_form
  def self.encode_www_form_component(str, enc=nil)
    str = str.to_s.dup
    if str.encoding != Encoding::ASCII_8BIT
      if enc && enc != Encoding::ASCII_8BIT
        str.encode!(Encoding::UTF_8, invalid: :replace, undef: :replace)
        str.encode!(enc, fallback: ->(x){"&#{x.ord};"})
      end
      str.force_encoding(Encoding::ASCII_8BIT)
    end
    str.gsub!(/[^*\-.0-9A-Z_a-z]/, TBLENCWWWCOMP_)
    str.force_encoding(Encoding::US_ASCII)
  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})" if /%(?!\h\h)/ =~ str
    str.b.gsub(/\+|%\h\h/, TBLDECWWWCOMP_).force_encoding(enc)
  end

  # Generate URL-encoded form data from given +enum+.
  #
  # 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 refers http://url.spec.whatwg.org/#concept-urlencoded-serializer
  #
  #    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, enc=nil)
    enum.map do |k,v|
      if v.nil?
        encode_www_form_component(k, enc)
      elsif v.respond_to?(:to_ary)
        v.to_ary.map do |w|
          str = encode_www_form_component(k, enc)
          unless w.nil?
            str << '='
            str << encode_www_form_component(w, enc)
          end
        end.join('&')
      else
        str = encode_www_form_component(k, enc)
        str << '='
        str << encode_www_form_component(v, enc)
      end
    end.join('&')
  end

  # Decode URL-encoded form data from given +str+.
  #
  # This decodes application/x-www-form-urlencoded data
  # and returns array of key-value array.
  #
  # This refers http://url.spec.whatwg.org/#concept-urlencoded-parser ,
  # so this supports only &-separator, don't support ;-separator.
  #
  #    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, separator: '&', use__charset_: false, isindex: false)
    raise ArgumentError, "the input of #{self.name}.#{__method__} must be ASCII only string" unless str.ascii_only?
    ary = []
    return ary if str.empty?
    enc = Encoding.find(enc)
    str.b.each_line(separator) do |string|
      string.chomp!(separator)
      key, sep, val = string.partition('=')
      if isindex
        if sep.empty?
          val = key
          key = ''
        end
        isindex = false
      end

      if use__charset_ and key == '_charset_' and e = get_encoding(val)
        enc = e
        use__charset_ = false
      end

      key.gsub!(/\+|%\h\h/, TBLDECWWWCOMP_)
      if val
        val.gsub!(/\+|%\h\h/, TBLDECWWWCOMP_)
      else
        val = ''
      end

      ary << [key, val]
    end
    ary.each do |k, v|
      k.force_encoding(enc)
      k.scrub!
      v.force_encoding(enc)
      v.scrub!
    end
    ary
  end

  private
  # curl http://encoding.spec.whatwg.org/encodings.json|rb -rpp -rjson -e'H={};h={"shift_jis"=>"Windows-31J","euc-jp"=>"cp51932","iso-2022-jp"=>"cp50221","x-mac-cyrillic"=>"macCyrillic"};JSON($<.read).map{|x|x["encodings"]}.flatten.each{|x|Encoding.find(n=h.fetch(n=x["name"],n))rescue next;x["labels"].each{|y|H[y]=n}};pp H'
  WEB_ENCODINGS_ = {
    "unicode-1-1-utf-8"=>"utf-8",
    "utf-8"=>"utf-8",
    "utf8"=>"utf-8",
    "866"=>"ibm866",
    "cp866"=>"ibm866",
    "csibm866"=>"ibm866",
    "ibm866"=>"ibm866",
    "csisolatin2"=>"iso-8859-2",
    "iso-8859-2"=>"iso-8859-2",
    "iso-ir-101"=>"iso-8859-2",
    "iso8859-2"=>"iso-8859-2",
    "iso88592"=>"iso-8859-2",
    "iso_8859-2"=>"iso-8859-2",
    "iso_8859-2:1987"=>"iso-8859-2",
    "l2"=>"iso-8859-2",
    "latin2"=>"iso-8859-2",
    "csisolatin3"=>"iso-8859-3",
    "iso-8859-3"=>"iso-8859-3",
    "iso-ir-109"=>"iso-8859-3",
    "iso8859-3"=>"iso-8859-3",
    "iso88593"=>"iso-8859-3",
    "iso_8859-3"=>"iso-8859-3",
    "iso_8859-3:1988"=>"iso-8859-3",
    "l3"=>"iso-8859-3",
    "latin3"=>"iso-8859-3",
    "csisolatin4"=>"iso-8859-4",
    "iso-8859-4"=>"iso-8859-4",
    "iso-ir-110"=>"iso-8859-4",
    "iso8859-4"=>"iso-8859-4",
    "iso88594"=>"iso-8859-4",
    "iso_8859-4"=>"iso-8859-4",
    "iso_8859-4:1988"=>"iso-8859-4",
    "l4"=>"iso-8859-4",
    "latin4"=>"iso-8859-4",
    "csisolatincyrillic"=>"iso-8859-5",
    "cyrillic"=>"iso-8859-5",
    "iso-8859-5"=>"iso-8859-5",
    "iso-ir-144"=>"iso-8859-5",
    "iso8859-5"=>"iso-8859-5",
    "iso88595"=>"iso-8859-5",
    "iso_8859-5"=>"iso-8859-5",
    "iso_8859-5:1988"=>"iso-8859-5",
    "arabic"=>"iso-8859-6",
    "asmo-708"=>"iso-8859-6",
    "csiso88596e"=>"iso-8859-6",
    "csiso88596i"=>"iso-8859-6",
    "csisolatinarabic"=>"iso-8859-6",
    "ecma-114"=>"iso-8859-6",
    "iso-8859-6"=>"iso-8859-6",
    "iso-8859-6-e"=>"iso-8859-6",
    "iso-8859-6-i"=>"iso-8859-6",
    "iso-ir-127"=>"iso-8859-6",
    "iso8859-6"=>"iso-8859-6",
    "iso88596"=>"iso-8859-6",
    "iso_8859-6"=>"iso-8859-6",
    "iso_8859-6:1987"=>"iso-8859-6",
    "csisolatingreek"=>"iso-8859-7",
    "ecma-118"=>"iso-8859-7",
    "elot_928"=>"iso-8859-7",
    "greek"=>"iso-8859-7",
    "greek8"=>"iso-8859-7",
    "iso-8859-7"=>"iso-8859-7",
    "iso-ir-126"=>"iso-8859-7",
    "iso8859-7"=>"iso-8859-7",
    "iso88597"=>"iso-8859-7",
    "iso_8859-7"=>"iso-8859-7",
    "iso_8859-7:1987"=>"iso-8859-7",
    "sun_eu_greek"=>"iso-8859-7",
    "csiso88598e"=>"iso-8859-8",
    "csisolatinhebrew"=>"iso-8859-8",
    "hebrew"=>"iso-8859-8",
    "iso-8859-8"=>"iso-8859-8",
    "iso-8859-8-e"=>"iso-8859-8",
    "iso-ir-138"=>"iso-8859-8",
    "iso8859-8"=>"iso-8859-8",
    "iso88598"=>"iso-8859-8",
    "iso_8859-8"=>"iso-8859-8",
    "iso_8859-8:1988"=>"iso-8859-8",
    "visual"=>"iso-8859-8",
    "csisolatin6"=>"iso-8859-10",
    "iso-8859-10"=>"iso-8859-10",
    "iso-ir-157"=>"iso-8859-10",
    "iso8859-10"=>"iso-8859-10",
    "iso885910"=>"iso-8859-10",
    "l6"=>"iso-8859-10",
    "latin6"=>"iso-8859-10",
    "iso-8859-13"=>"iso-8859-13",
    "iso8859-13"=>"iso-8859-13",
    "iso885913"=>"iso-8859-13",
    "iso-8859-14"=>"iso-8859-14",
    "iso8859-14"=>"iso-8859-14",
    "iso885914"=>"iso-8859-14",
    "csisolatin9"=>"iso-8859-15",
    "iso-8859-15"=>"iso-8859-15",
    "iso8859-15"=>"iso-8859-15",
    "iso885915"=>"iso-8859-15",
    "iso_8859-15"=>"iso-8859-15",
    "l9"=>"iso-8859-15",
    "iso-8859-16"=>"iso-8859-16",
    "cskoi8r"=>"koi8-r",
    "koi"=>"koi8-r",
    "koi8"=>"koi8-r",
    "koi8-r"=>"koi8-r",
    "koi8_r"=>"koi8-r",
    "koi8-u"=>"koi8-u",
    "dos-874"=>"windows-874",
    "iso-8859-11"=>"windows-874",
    "iso8859-11"=>"windows-874",
    "iso885911"=>"windows-874",
    "tis-620"=>"windows-874",
    "windows-874"=>"windows-874",
    "cp1250"=>"windows-1250",
    "windows-1250"=>"windows-1250",
    "x-cp1250"=>"windows-1250",
    "cp1251"=>"windows-1251",
    "windows-1251"=>"windows-1251",
    "x-cp1251"=>"windows-1251",
    "ansi_x3.4-1968"=>"windows-1252",
    "ascii"=>"windows-1252",
    "cp1252"=>"windows-1252",
    "cp819"=>"windows-1252",
    "csisolatin1"=>"windows-1252",
    "ibm819"=>"windows-1252",
    "iso-8859-1"=>"windows-1252",
    "iso-ir-100"=>"windows-1252",
    "iso8859-1"=>"windows-1252",
    "iso88591"=>"windows-1252",
    "iso_8859-1"=>"windows-1252",
    "iso_8859-1:1987"=>"windows-1252",
    "l1"=>"windows-1252",
    "latin1"=>"windows-1252",
    "us-ascii"=>"windows-1252",
    "windows-1252"=>"windows-1252",
    "x-cp1252"=>"windows-1252",
    "cp1253"=>"windows-1253",
    "windows-1253"=>"windows-1253",
    "x-cp1253"=>"windows-1253",
    "cp1254"=>"windows-1254",
    "csisolatin5"=>"windows-1254",
    "iso-8859-9"=>"windows-1254",
    "iso-ir-148"=>"windows-1254",
    "iso8859-9"=>"windows-1254",
    "iso88599"=>"windows-1254",
    "iso_8859-9"=>"windows-1254",
    "iso_8859-9:1989"=>"windows-1254",
    "l5"=>"windows-1254",
    "latin5"=>"windows-1254",
    "windows-1254"=>"windows-1254",
    "x-cp1254"=>"windows-1254",
    "cp1255"=>"windows-1255",
    "windows-1255"=>"windows-1255",
    "x-cp1255"=>"windows-1255",
    "cp1256"=>"windows-1256",
    "windows-1256"=>"windows-1256",
    "x-cp1256"=>"windows-1256",
    "cp1257"=>"windows-1257",
    "windows-1257"=>"windows-1257",
    "x-cp1257"=>"windows-1257",
    "cp1258"=>"windows-1258",
    "windows-1258"=>"windows-1258",
    "x-cp1258"=>"windows-1258",
    "x-mac-cyrillic"=>"macCyrillic",
    "x-mac-ukrainian"=>"macCyrillic",
    "chinese"=>"gbk",
    "csgb2312"=>"gbk",
    "csiso58gb231280"=>"gbk",
    "gb2312"=>"gbk",
    "gb_2312"=>"gbk",
    "gb_2312-80"=>"gbk",
    "gbk"=>"gbk",
    "iso-ir-58"=>"gbk",
    "x-gbk"=>"gbk",
    "gb18030"=>"gb18030",
    "big5"=>"big5",
    "big5-hkscs"=>"big5",
    "cn-big5"=>"big5",
    "csbig5"=>"big5",
    "x-x-big5"=>"big5",
    "cseucpkdfmtjapanese"=>"cp51932",
    "euc-jp"=>"cp51932",
    "x-euc-jp"=>"cp51932",
    "csiso2022jp"=>"cp50221",
    "iso-2022-jp"=>"cp50221",
    "csshiftjis"=>"Windows-31J",
    "ms_kanji"=>"Windows-31J",
    "shift-jis"=>"Windows-31J",
    "shift_jis"=>"Windows-31J",
    "sjis"=>"Windows-31J",
    "windows-31j"=>"Windows-31J",
    "x-sjis"=>"Windows-31J",
    "cseuckr"=>"euc-kr",
    "csksc56011987"=>"euc-kr",
    "euc-kr"=>"euc-kr",
    "iso-ir-149"=>"euc-kr",
    "korean"=>"euc-kr",
    "ks_c_5601-1987"=>"euc-kr",
    "ks_c_5601-1989"=>"euc-kr",
    "ksc5601"=>"euc-kr",
    "ksc_5601"=>"euc-kr",
    "windows-949"=>"euc-kr",
    "utf-16be"=>"utf-16be",
    "utf-16"=>"utf-16le",
    "utf-16le"=>"utf-16le"
  } # :nodoc:

  # :nodoc:
  # return encoding or nil
  # http://encoding.spec.whatwg.org/#concept-encoding-get
  def self.get_encoding(label)
    Encoding.find(WEB_ENCODINGS_[label.to_str.strip.downcase]) rescue nil
  end
end # module URI

module Kernel

  #
  # Returns +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