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
|
# = 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.
#
module URI
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 = ";/?:@&=+$,\\[\\]"
# uric = reserved | unreserved | escaped
URIC = "(?:[#{UNRESERVED}#{RESERVED}]|#{ESCAPED})"
# uric_no_slash = unreserved | escaped | ";" | "?" | ":" | "@" |
# "&" | "=" | "+" | "$" | ","
URIC_NO_SLASH = "(?:[#{UNRESERVED};?:@&=+$,]|#{ESCAPED})"
# query = *uric
QUERY = "#{URIC}*"
# fragment = *uric
FRAGMENT = "#{URIC}*"
# domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum
DOMLABEL = "(?:[#{ALNUM}](?:[-#{ALNUM}]*[#{ALNUM}])?)"
# toplabel = alpha | alpha *( alphanum | "-" ) alphanum
TOPLABEL = "(?:[#{ALPHA}](?:[-#{ALNUM}]*[#{ALNUM}])?)"
# hostname = *( domainlabel "." ) toplabel [ "." ]
HOSTNAME = "(?:#{DOMLABEL}\\.)*#{TOPLABEL}\\.?"
# RFC 2373, APPENDIX B:
# IPv6address = hexpart [ ":" IPv4address ]
# IPv4address = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT
# hexpart = hexseq | hexseq "::" [ hexseq ] | "::" [ hexseq ]
# hexseq = hex4 *( ":" hex4)
# hex4 = 1*4HEXDIG
#
# XXX: This definition has a flaw. "::" + IPv4address must be
# allowed too. Here is a replacement.
#
# IPv4address = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT
IPV4ADDR = "\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}"
# hex4 = 1*4HEXDIG
HEX4 = "[#{HEX}]{1,4}"
# lastpart = hex4 | IPv4address
LASTPART = "(?:#{HEX4}|#{IPV4ADDR})"
# hexseq1 = *( hex4 ":" ) hex4
HEXSEQ1 = "(?:#{HEX4}:)*#{HEX4}"
# hexseq2 = *( hex4 ":" ) lastpart
HEXSEQ2 = "(?:#{HEX4}:)*#{LASTPART}"
# IPv6address = hexseq2 | [ hexseq1 ] "::" [ hexseq2 ]
IPV6ADDR = "(?:#{HEXSEQ2}|(?:#{HEXSEQ1})?::(?:#{HEXSEQ2})?)"
# IPv6prefix = ( hexseq1 | [ hexseq1 ] "::" [ hexseq1 ] ) "/" 1*2DIGIT
# unused
# ipv6reference = "[" IPv6address "]" (RFC 2732)
IPV6REF = "\\[#{IPV6ADDR}\\]"
# host = hostname | IPv4address
# host = hostname | IPv4address | IPv6reference (RFC 2732)
HOST = "(?:#{HOSTNAME}|#{IPV4ADDR}|#{IPV6REF})"
# port = *digit
PORT = '\d*'
# hostport = host [ ":" port ]
HOSTPORT = "#{HOST}(?::#{PORT})?"
# userinfo = *( unreserved | escaped |
# ";" | ":" | "&" | "=" | "+" | "$" | "," )
USERINFO = "(?:[#{UNRESERVED};:&=+$,]|#{ESCAPED})*"
# pchar = unreserved | escaped |
# ":" | "@" | "&" | "=" | "+" | "$" | ","
PCHAR = "(?:[#{UNRESERVED}:@&=+$,]|#{ESCAPED})"
# param = *pchar
PARAM = "#{PCHAR}*"
# segment = *pchar *( ";" param )
SEGMENT = "#{PCHAR}*(?:;#{PARAM})*"
# path_segments = segment *( "/" segment )
PATH_SEGMENTS = "#{SEGMENT}(?:/#{SEGMENT})*"
# server = [ [ userinfo "@" ] hostport ]
SERVER = "(?:#{USERINFO}@)?#{HOSTPORT}"
# reg_name = 1*( unreserved | escaped | "$" | "," |
# ";" | ":" | "@" | "&" | "=" | "+" )
REG_NAME = "(?:[#{UNRESERVED}$,;+@&=+]|#{ESCAPED})+"
# authority = server | reg_name
AUTHORITY = "(?:#{SERVER}|#{REG_NAME})"
# rel_segment = 1*( unreserved | escaped |
# ";" | "@" | "&" | "=" | "+" | "$" | "," )
REL_SEGMENT = "(?:[#{UNRESERVED};@&=+$,]|#{ESCAPED})+"
# scheme = alpha *( alpha | digit | "+" | "-" | "." )
SCHEME = "[#{ALPHA}][-+.#{ALPHA}\\d]*"
# abs_path = "/" path_segments
ABS_PATH = "/#{PATH_SEGMENTS}"
# rel_path = rel_segment [ abs_path ]
REL_PATH = "#{REL_SEGMENT}(?:#{ABS_PATH})?"
# net_path = "//" authority [ abs_path ]
NET_PATH = "//#{AUTHORITY}(?:#{ABS_PATH})?"
# hier_part = ( net_path | abs_path ) [ "?" query ]
HIER_PART = "(?:#{NET_PATH}|#{ABS_PATH})(?:\\?(?:#{QUERY}))?"
# opaque_part = uric_no_slash *uric
OPAQUE_PART = "#{URIC_NO_SLASH}#{URIC}*"
# absoluteURI = scheme ":" ( hier_part | opaque_part )
ABS_URI = "#{SCHEME}:(?:#{HIER_PART}|#{OPAQUE_PART})"
# relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ]
REL_URI = "(?:#{NET_PATH}|#{ABS_PATH}|#{REL_PATH})(?:\\?#{QUERY})?"
# URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
URI_REF = "(?:#{ABS_URI}|#{REL_URI})?(?:##{FRAGMENT})?"
# XXX:
X_ABS_URI = "
(#{PATTERN::SCHEME}): (?# 1: scheme)
(?:
(#{PATTERN::OPAQUE_PART}) (?# 2: opaque)
|
(?:(?:
//(?:
(?:(?:(#{PATTERN::USERINFO})@)? (?# 3: userinfo)
(?:(#{PATTERN::HOST})(?::(\\d*))?))?(?# 4: host, 5: port)
|
(#{PATTERN::REG_NAME}) (?# 6: registry)
)
|
(?!//)) (?# XXX: '//' is the mark for hostport)
(#{PATTERN::ABS_PATH})? (?# 7: path)
)(?:\\?(#{PATTERN::QUERY}))? (?# 8: query)
)
(?:\\#(#{PATTERN::FRAGMENT}))? (?# 9: fragment)
"
X_REL_URI = "
(?:
(?:
//
(?:
(?:(#{PATTERN::USERINFO})@)? (?# 1: userinfo)
(#{PATTERN::HOST})?(?::(\\d*))? (?# 2: host, 3: port)
|
(#{PATTERN::REG_NAME}) (?# 4: registry)
)
)
|
(#{PATTERN::REL_SEGMENT}) (?# 5: rel_segment)
)?
(#{PATTERN::ABS_PATH})? (?# 6: abs_path)
(?:\\?(#{PATTERN::QUERY}))? (?# 7: query)
(?:\\#(#{PATTERN::FRAGMENT}))? (?# 8: fragment)
"
# :startdoc:
end # PATTERN
# :stopdoc:
# for URI::split
ABS_URI = Regexp.new('^' + PATTERN::X_ABS_URI + '$', #'
Regexp::EXTENDED, 'N').freeze
REL_URI = Regexp.new('^' + PATTERN::X_REL_URI + '$', #'
Regexp::EXTENDED, 'N').freeze
# for URI::extract
URI_REF = Regexp.new(PATTERN::URI_REF, false, 'N').freeze
ABS_URI_REF = Regexp.new(PATTERN::X_ABS_URI, Regexp::EXTENDED, 'N').freeze
REL_URI_REF = Regexp.new(PATTERN::X_REL_URI, Regexp::EXTENDED, 'N').freeze
# for URI::escape/unescape
ESCAPED = Regexp.new(PATTERN::ESCAPED, false, 'N').freeze
UNSAFE = Regexp.new("[^#{PATTERN::UNRESERVED}#{PATTERN::RESERVED}]",
false, 'N').freeze
# for Generic#initialize
SCHEME = Regexp.new("^#{PATTERN::SCHEME}$", false, 'N').freeze #"
USERINFO = Regexp.new("^#{PATTERN::USERINFO}$", false, 'N').freeze #"
HOST = Regexp.new("^#{PATTERN::HOST}$", false, 'N').freeze #"
PORT = Regexp.new("^#{PATTERN::PORT}$", false, 'N').freeze #"
OPAQUE = Regexp.new("^#{PATTERN::OPAQUE_PART}$", false, 'N').freeze #"
REGISTRY = Regexp.new("^#{PATTERN::REG_NAME}$", false, 'N').freeze #"
ABS_PATH = Regexp.new("^#{PATTERN::ABS_PATH}$", false, 'N').freeze #"
REL_PATH = Regexp.new("^#{PATTERN::REL_PATH}$", false, 'N').freeze #"
QUERY = Regexp.new("^#{PATTERN::QUERY}$", false, 'N').freeze #"
FRAGMENT = Regexp.new("^#{PATTERN::FRAGMENT}$", false, 'N').freeze #"
# :startdoc:
end # REGEXP
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 Escape
include REGEXP
#
# == 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>.
#
# == Description
#
# Escapes the string, replacing all unsafe characters with codes.
#
# == Usage
#
# require 'uri'
#
# enc_uri = URI.escape("http://foobar.com/?a=\11\15")
# p enc_uri
# # => "http://foobar.com/?a=%09%0D"
#
# p URI.unescape(enc_uri)
# # => "http://foobar.com/?a=\t\r"
#
def escape(str, unsafe = UNSAFE)
unless unsafe.kind_of?(Regexp)
# perhaps unsafe is String object
unsafe = Regexp.new(Regexp.quote(unsafe), false, 'N')
end
str.gsub(unsafe) do |us|
tmp = ''
us.each_byte do |uc|
tmp << sprintf('%%%02X', uc)
end
tmp
end
end
alias encode escape
#
# == Synopsis
#
# URI.unescape(str)
#
# == Args
#
# +str+::
# Unescapes the string.
#
# == Usage
#
# require 'uri'
#
# enc_uri = URI.escape("http://foobar.com/?a=\11\15")
# p enc_uri
# # => "http://foobar.com/?a=%09%0D"
#
# p URI.unescape(enc_uri)
# # => "http://foobar.com/?a=\t\r"
#
def unescape(str)
str.gsub(ESCAPED) do
$&[1,2].hex.chr
end
end
alias decode unescape
end
include REGEXP
extend Escape
@@schemes = {}
#
# 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)
case uri
when ''
# null uri
when ABS_URI
scheme, opaque, userinfo, host, port,
registry, path, query, fragment = $~[1..-1]
# URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
# absoluteURI = scheme ":" ( hier_part | opaque_part )
# hier_part = ( net_path | abs_path ) [ "?" query ]
# opaque_part = uric_no_slash *uric
# abs_path = "/" path_segments
# net_path = "//" authority [ abs_path ]
# authority = server | reg_name
# server = [ [ userinfo "@" ] hostport ]
if !scheme
raise InvalidURIError,
"bad URI(absolute but no scheme): #{uri}"
end
if !opaque && (!path && (!host && !registry))
raise InvalidURIError,
"bad URI(absolute but no path): #{uri}"
end
when REL_URI
scheme = nil
opaque = nil
userinfo, host, port, registry,
rel_segment, abs_path, query, fragment = $~[1..-1]
if rel_segment && abs_path
path = rel_segment + abs_path
elsif rel_segment
path = rel_segment
elsif abs_path
path = abs_path
end
# URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
# relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ]
# net_path = "//" authority [ abs_path ]
# abs_path = "/" path_segments
# rel_path = rel_segment [ abs_path ]
# authority = server | reg_name
# server = [ [ userinfo "@" ] hostport ]
else
raise InvalidURIError, "bad URI(is not URI?): #{uri}"
end
path = '' if !path && !opaque # (see RFC2396 Section 5.2)
ret = [
scheme,
userinfo, host, port, # X
registry, # X
path, # Y
opaque, # Y
query,
fragment
]
return ret
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)
scheme, userinfo, host, port,
registry, path, opaque, query, fragment = self.split(uri)
if scheme && @@schemes.include?(scheme.upcase)
@@schemes[scheme.upcase].new(scheme, userinfo, host, port,
registry, path, opaque, query,
fragment)
else
Generic.new(scheme, userinfo, host, port,
registry, path, opaque, query,
fragment)
end
end
#
# == Synopsis
#
# URI::join(str[, str, ...])
#
# == Args
#
# +str+::
# String(s) to work with
#
# == Description
#
# Joins URIs.
#
# == Usage
#
# require 'uri'
#
# p URI.join("http:/localhost/","main.rbx")
# # => #<URI::HTTP:0x2022ac02 URL:http:/localhost/main.php>
#
def self.join(*str)
u = self.parse(str[0])
str[1 .. -1].each do |x|
u = u.merge(x)
end
u
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)
if block_given?
str.scan(regexp(schemes)) { yield $& }
nil
else
result = []
str.scan(regexp(schemes)) { result.push $& }
result
end
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)
unless schemes
ABS_URI_REF
else
/(?=#{Regexp.union(*schemes)}:)#{PATTERN::X_ABS_URI}/xn
end
end
end
module Kernel
# alias for URI.parse.
#
# This method is introduced at 1.8.2.
def URI(uri_str) # :doc:
URI.parse(uri_str)
end
module_function :URI
end
|