summaryrefslogtreecommitdiff
path: root/lib/uri/common.rb
blob: 10f77caecbc32f5013eae84b945d43a4bbc170a0 (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
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
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
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
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
#--
# = 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
#

module URI
  #
  # Includes URI::REGEXP::PATTERN
  #
  module REGEXP
    #
    # Patterns used to parse URI's
    #
    module PATTERN
      # :stopdoc:

      # RFC 2396 (URI Generic Syntax)
      # RFC 2732 (IPv6 Literal Addresses in URL's)
      # RFC 2373 (IPv6 Addressing Architecture)

      # alpha         = lowalpha | upalpha
      ALPHA = "a-zA-Z"
      # alphanum      = alpha | digit
      ALNUM = "#{ALPHA}\\d"

      # hex           = digit | "A" | "B" | "C" | "D" | "E" | "F" |
      #                         "a" | "b" | "c" | "d" | "e" | "f"
      HEX     = "a-fA-F\\d"
      # escaped       = "%" hex hex
      ESCAPED = "%[#{HEX}]{2}"
      # mark          = "-" | "_" | "." | "!" | "~" | "*" | "'" |
      #                 "(" | ")"
      # unreserved    = alphanum | mark
      UNRESERVED = "\\-_.!~*'()#{ALNUM}"
      # reserved      = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" |
      #                 "$" | ","
      # reserved      = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" |
      #                 "$" | "," | "[" | "]" (RFC 2732)
      RESERVED = ";/?:@&=+$,\\[\\]"

      # domainlabel   = alphanum | alphanum *( alphanum | "-" ) alphanum
      DOMLABEL = "(?:[#{ALNUM}](?:[-#{ALNUM}]*[#{ALNUM}])?)"
      # toplabel      = alpha | alpha *( alphanum | "-" ) alphanum
      TOPLABEL = "(?:[#{ALPHA}](?:[-#{ALNUM}]*[#{ALNUM}])?)"
      # hostname      = *( domainlabel "." ) toplabel [ "." ]
      HOSTNAME = "(?:#{DOMLABEL}\\.)*#{TOPLABEL}\\.?"

      # :startdoc:
    end # PATTERN

    # :startdoc:
  end # REGEXP

  # class that Parses String's into URI's
  #
  # It contains a Hash set of patterns and Regexp's that match and validate.
  #
  class 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:
    #
    #   * <tt>:ESCAPED</tt> (URI::PATTERN::ESCAPED in default)
    #   * <tt>:UNRESERVED</tt> (URI::PATTERN::UNRESERVED in default)
    #   * <tt>:DOMLABEL</tt> (URI::PATTERN::DOMLABEL in default)
    #   * <tt>:TOPLABEL</tt> (URI::PATTERN::TOPLABEL in default)
    #   * <tt>:HOSTNAME</tt> (URI::PATTERN::HOSTNAME in default)
    #
    # == Examples
    #
    #   p = URI::Parser.new(:ESCPAED => "(?:%[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] = URI(uris[0], self)
      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, &block)
      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
      ret[:URIC] = uric = "(?:[#{unreserved}#{reserved}]|#{escaped})"
      # uric_no_slash = unreserved | escaped | ";" | "?" | ":" | "@" |
      #                 "&" | "=" | "+" | "$" | ","
      ret[:URIC_NO_SLASH] = uric_no_slash = "(?:[#{unreserved};?:@&=+$,]|#{escaped})"
      # query         = *uric
      ret[:QUERY] = query = "#{uric}*"
      # fragment      = *uric
      ret[:FRAGMENT] = fragment = "#{uric}*"

      # hostname      = *( domainlabel "." ) toplabel [ "." ]
      # reg-name      = *( unreserved / pct-encoded / sub-delims ) # RFC3986
      unless hostname
        ret[:HOSTNAME] = hostname = "(?:[a-zA-Z0-9\\-.]|%\\h\\h)+"
      end

      # RFC 2373, APPENDIX B:
      # IPv6address = hexpart [ ":" IPv4address ]
      # IPv4address   = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT
      # hexpart = hexseq | hexseq "::" [ hexseq ] | "::" [ hexseq ]
      # hexseq  = hex4 *( ":" hex4)
      # hex4    = 1*4HEXDIG
      #
      # XXX: This definition has a flaw. "::" + IPv4address must be
      # allowed too.  Here is a replacement.
      #
      # IPv4address = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT
      ret[:IPV4ADDR] = ipv4addr = "\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}"
      # hex4     = 1*4HEXDIG
      hex4 = "[#{PATTERN::HEX}]{1,4}"
      # lastpart = hex4 | IPv4address
      lastpart = "(?:#{hex4}|#{ipv4addr})"
      # hexseq1  = *( hex4 ":" ) hex4
      hexseq1 = "(?:#{hex4}:)*#{hex4}"
      # hexseq2  = *( hex4 ":" ) lastpart
      hexseq2 = "(?:#{hex4}:)*#{lastpart}"
      # IPv6address = hexseq2 | [ hexseq1 ] "::" [ hexseq2 ]
      ret[:IPV6ADDR] = ipv6addr = "(?:#{hexseq2}|(?:#{hexseq1})?::(?:#{hexseq2})?)"

      # IPv6prefix  = ( hexseq1 | [ hexseq1 ] "::" [ hexseq1 ] ) "/" 1*2DIGIT
      # unused

      # ipv6reference = "[" IPv6address "]" (RFC 2732)
      ret[:IPV6REF] = ipv6ref = "\\[#{ipv6addr}\\]"

      # host          = hostname | IPv4address
      # host          = hostname | IPv4address | IPv6reference (RFC 2732)
      ret[:HOST] = host = "(?:#{hostname}|#{ipv4addr}|#{ipv6ref})"
      # port          = *digit
      port = '\d*'
      # hostport      = host [ ":" port ]
      ret[:HOSTPORT] = hostport = "#{host}(?::#{port})?"

      # userinfo      = *( unreserved | escaped |
      #                    ";" | ":" | "&" | "=" | "+" | "$" | "," )
      ret[:USERINFO] = userinfo = "(?:[#{unreserved};:&=+$,]|#{escaped})*"

      # pchar         = unreserved | escaped |
      #                 ":" | "@" | "&" | "=" | "+" | "$" | ","
      pchar = "(?:[#{unreserved}:@&=+$,]|#{escaped})"
      # param         = *pchar
      param = "#{pchar}*"
      # segment       = *pchar *( ";" param )
      segment = "#{pchar}*(?:;#{param})*"
      # path_segments = segment *( "/" segment )
      ret[:PATH_SEGMENTS] = path_segments = "#{segment}(?:/#{segment})*"

      # server        = [ [ userinfo "@" ] hostport ]
      server = "(?:#{userinfo}@)?#{hostport}"
      # reg_name      = 1*( unreserved | escaped | "$" | "," |
      #                     ";" | ":" | "@" | "&" | "=" | "+" )
      ret[:REG_NAME] = reg_name = "(?:[#{unreserved}$,;:@&=+]|#{escaped})+"
      # authority     = server | reg_name
      authority = "(?:#{server}|#{reg_name})"

      # rel_segment   = 1*( unreserved | escaped |
      #                     ";" | "@" | "&" | "=" | "+" | "$" | "," )
      ret[:REL_SEGMENT] = rel_segment = "(?:[#{unreserved};@&=+$,]|#{escaped})+"

      # scheme        = alpha *( alpha | digit | "+" | "-" | "." )
      ret[:SCHEME] = scheme = "[#{PATTERN::ALPHA}][\\-+.#{PATTERN::ALPHA}\\d]*"

      # abs_path      = "/"  path_segments
      ret[:ABS_PATH] = abs_path = "/#{path_segments}"
      # rel_path      = rel_segment [ abs_path ]
      ret[:REL_PATH] = rel_path = "#{rel_segment}(?:#{abs_path})?"
      # net_path      = "//" authority [ abs_path ]
      ret[:NET_PATH] = net_path = "//#{authority}(?:#{abs_path})?"

      # hier_part     = ( net_path | abs_path ) [ "?" query ]
      ret[:HIER_PART] = hier_part = "(?:#{net_path}|#{abs_path})(?:\\?(?:#{query}))?"
      # opaque_part   = uric_no_slash *uric
      ret[:OPAQUE_PART] = opaque_part = "#{uric_no_slash}#{uric}*"

      # absoluteURI   = scheme ":" ( hier_part | opaque_part )
      ret[:ABS_URI] = abs_uri = "#{scheme}:(?:#{hier_part}|#{opaque_part})"
      # relativeURI   = ( net_path | abs_path | rel_path ) [ "?" query ]
      ret[:REL_URI] = rel_uri = "(?:#{net_path}|#{abs_path}|#{rel_path})(?:\\?#{query})?"

      # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
      ret[:URI_REF] = "(?:#{abs_uri}|#{rel_uri})?(?:##{fragment})?"

      ret[:X_ABS_URI] = "
        (#{scheme}):                           (?# 1: scheme)
        (?:
           (#{opaque_part})                    (?# 2: opaque)
        |
           (?:(?:
             //(?:
                 (?:(?:(#{userinfo})@)?        (?# 3: userinfo)
                   (?:(#{host})(?::(\\d*))?))? (?# 4: host, 5: port)
               |
                 (#{reg_name})                 (?# 6: registry)
               )
             |
             (?!//))                           (?# XXX: '//' is the mark for hostport)
             (#{abs_path})?                    (?# 7: path)
           )(?:\\?(#{query}))?                 (?# 8: query)
        )
        (?:\\#(#{fragment}))?                  (?# 9: fragment)
      "

      ret[:X_REL_URI] = "
        (?:
          (?:
            //
            (?:
              (?:(#{userinfo})@)?       (?# 1: userinfo)
                (#{host})?(?::(\\d*))?  (?# 2: host, 3: port)
            |
              (#{reg_name})             (?# 4: registry)
            )
          )
        |
          (#{rel_segment})              (?# 5: rel_segment)
        )?
        (#{abs_path})?                  (?# 6: abs_path)
        (?:\\?(#{query}))?              (?# 7: query)
        (?:\\#(#{fragment}))?           (?# 8: fragment)
      "

      ret
    end

    # Constructs the default Hash of Regexp's
    def initialize_regexp(pattern)
      ret = {}

      # for URI::split
      ret[:ABS_URI] = Regexp.new('\A\s*' + pattern[:X_ABS_URI] + '\s*\z', Regexp::EXTENDED)
      ret[:REL_URI] = Regexp.new('\A\s*' + pattern[:X_REL_URI] + '\s*\z', Regexp::EXTENDED)

      # for URI::extract
      ret[:URI_REF]     = Regexp.new(pattern[:URI_REF])
      ret[:ABS_URI_REF] = Regexp.new(pattern[:X_ABS_URI], Regexp::EXTENDED)
      ret[:REL_URI_REF] = Regexp.new(pattern[:X_REL_URI], Regexp::EXTENDED)

      # for URI::escape/unescape
      ret[:ESCAPED] = Regexp.new(pattern[:ESCAPED])
      ret[:UNSAFE]  = Regexp.new("[^#{pattern[:UNRESERVED]}#{pattern[:RESERVED]}]")

      # for Generic#initialize
      ret[:SCHEME]   = Regexp.new("^#{pattern[:SCHEME]}$")
      ret[:USERINFO] = Regexp.new("^#{pattern[:USERINFO]}$")
      ret[:HOST]     = Regexp.new("^#{pattern[:HOST]}$")
      ret[:PORT]     = Regexp.new("^#{pattern[:PORT]}$")
      ret[:OPAQUE]   = Regexp.new("^#{pattern[:OPAQUE_PART]}$")
      ret[:REGISTRY] = Regexp.new("^#{pattern[:REG_NAME]}$")
      ret[:ABS_PATH] = Regexp.new("^#{pattern[:ABS_PATH]}$")
      ret[:REL_PATH] = Regexp.new("^#{pattern[:REL_PATH]}$")
      ret[:QUERY]    = Regexp.new("^#{pattern[:QUERY]}$")
      ret[:FRAGMENT] = Regexp.new("^#{pattern[:FRAGMENT]}$")

      ret
    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
        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.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
    #
    # == 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)
    DEFAULT_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"
  #
  def self.parse(uri)
    DEFAULT_PARSER.parse(uri)
  end

  #
  # == Synopsis
  #
  #   URI::join(str[, str, ...])
  #
  # == Args
  #
  # +str+::
  #   String(s) to work with
  #
  # == Description
  #
  # Joins URIs.
  #
  # == Usage
  #
  #   require 'uri'
  #
  #   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)
    DEFAULT_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)
    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)
    DEFAULT_PARSER.make_regexp(schemes)
  end

  TBLENCWWWCOMP_ = {} # :nodoc:
  TBLDECWWWCOMP_ = {} # :nodoc:
  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/forms.html#url-encoded-form-data
  #
  # See URI.decode_www_form_component, URI.encode_www_form
  def self.encode_www_form_component(str)
    if TBLENCWWWCOMP_.empty?
      tbl = {}
      256.times do |i|
        tbl[i.chr] = '%%%02X' % i
      end
      tbl[' '] = '+'
      begin
        TBLENCWWWCOMP_.replace(tbl)
        TBLENCWWWCOMP_.freeze
      rescue
      end
    end
    str = str.to_s
    if HTML5ASCIIINCOMPAT.include?(str.encoding)
      str = str.encode(Encoding::UTF_8)
    else
      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

  # Decode given +str+ of URL-encoded form data.
  #
  # This decods + to SP.
  #
  # See URI.encode_www_form_component, URI.decode_www_form
  def self.decode_www_form_component(str, enc=Encoding::UTF_8)
    if TBLDECWWWCOMP_.empty?
      tbl = {}
      256.times do |i|
        h, l = i>>4, i&15
        tbl['%%%X%X' % [h, l]] = i.chr
        tbl['%%%x%X' % [h, l]] = i.chr
        tbl['%%%X%x' % [h, l]] = i.chr
        tbl['%%%x%x' % [h, l]] = i.chr
      end
      tbl['+'] = ' '
      begin
        TBLDECWWWCOMP_.replace(tbl)
        TBLDECWWWCOMP_.freeze
      rescue
      end
    end
    raise ArgumentError, "invalid %-encoding (#{str})" unless /\A(?:%\h\h|[^%]+)*\z/ =~ str
    str.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 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

  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, parser = URI::DEFAULT_PARSER)
    if uri.is_a?(URI::Generic)
      uri
    elsif uri = String.try_convert(uri)
      parser.parse(uri)
    else
      raise ArgumentError,
        "bad argument (expected URI object or URI string)"
    end
  end
  module_function :URI
end