addressable 2.8.1 → 2.8.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +22 -2
- data/Rakefile +2 -1
- data/addressable.gemspec +28 -0
- data/lib/addressable/idna/native.rb +8 -2
- data/lib/addressable/idna/pure.rb +10 -182
- data/lib/addressable/template.rb +9 -10
- data/lib/addressable/uri.rb +112 -96
- data/lib/addressable/version.rb +1 -1
- data/spec/addressable/idna_spec.rb +6 -5
- data/spec/addressable/template_spec.rb +60 -264
- data/spec/addressable/uri_spec.rb +56 -0
- metadata +4 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 9be949fe19003ebc13db9a486fe0bb50b488896fa1671a3dc5ac2cd62e30c875
|
4
|
+
data.tar.gz: '01824780e0172f78d7bf95857b4546e47b32a50426c2d953a07f9d1c63f37af3'
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 051d1501ab89efff21d5bcc3aed23bec2f7ff2defdf21915455142d7c1382e6b734053162dc9a19a9ba5946e9978ff6baa305035ebea5f947ba48e6241973059
|
7
|
+
data.tar.gz: 7cca09d71ccbb21e116ddb36075ab1fab39078dc5b51b9c7c34df8a88db3d90f8158c8c066692997fd551c97e983e6a9ddec3054741ee1337a9c185cca1c8a88
|
data/CHANGELOG.md
CHANGED
@@ -1,13 +1,33 @@
|
|
1
|
+
# Addressable 2.8.4
|
2
|
+
- Restore `Addressable::IDNA.unicode_normalize_kc` as a deprecated method ([#504])
|
3
|
+
|
4
|
+
[#504]: https://github.com/sporkmonger/addressable/pull/504
|
5
|
+
|
6
|
+
# Addressable 2.8.3
|
7
|
+
- Fix template expand level 2 hash support for non-string objects ([#499], [#498])
|
8
|
+
|
9
|
+
[#499]: https://github.com/sporkmonger/addressable/pull/499
|
10
|
+
[#498]: https://github.com/sporkmonger/addressable/pull/498
|
11
|
+
|
12
|
+
# Addressable 2.8.2
|
13
|
+
- Improve cache hits and JIT friendliness ([#486](https://github.com/sporkmonger/addressable/pull/486))
|
14
|
+
- Improve code style and test coverage ([#482](https://github.com/sporkmonger/addressable/pull/482))
|
15
|
+
- Ensure reset of deferred validation ([#481](https://github.com/sporkmonger/addressable/pull/481))
|
16
|
+
- Resolve normalization differences between `IDNA::Native` and `IDNA::Pure` ([#408](https://github.com/sporkmonger/addressable/issues/408), [#492])
|
17
|
+
- Remove redundant colon in `Addressable::URI::CharacterClasses::AUTHORITY` regex ([#438](https://github.com/sporkmonger/addressable/pull/438)) (accidentally reverted by [#449] merge but [added back](https://github.com/sporkmonger/addressable/pull/492#discussion_r1105125280) in [#492])
|
18
|
+
|
19
|
+
[#492]: https://github.com/sporkmonger/addressable/pull/492
|
20
|
+
|
1
21
|
# Addressable 2.8.1
|
2
22
|
- refactor `Addressable::URI.normalize_path` to address linter offenses ([#430](https://github.com/sporkmonger/addressable/pull/430))
|
3
|
-
- remove redundant colon in `Addressable::URI::CharacterClasses::AUTHORITY` regex ([#438](https://github.com/sporkmonger/addressable/pull/438))
|
4
23
|
- update gemspec to reflect supported Ruby versions ([#466], [#464], [#463])
|
5
24
|
- compatibility w/ public_suffix 5.x ([#466], [#465], [#460])
|
6
25
|
- fixes "invalid byte sequence in UTF-8" exception when unencoding URLs containing non UTF-8 characters ([#459](https://github.com/sporkmonger/addressable/pull/459))
|
7
|
-
- `Ractor` compatibility ([#449]
|
26
|
+
- `Ractor` compatibility ([#449])
|
8
27
|
- use the whole string instead of a single line for template match ([#431](https://github.com/sporkmonger/addressable/pull/431))
|
9
28
|
- force UTF-8 encoding only if needed ([#341](https://github.com/sporkmonger/addressable/pull/341))
|
10
29
|
|
30
|
+
[#449]: https://github.com/sporkmonger/addressable/pull/449
|
11
31
|
[#460]: https://github.com/sporkmonger/addressable/pull/460
|
12
32
|
[#463]: https://github.com/sporkmonger/addressable/pull/463
|
13
33
|
[#464]: https://github.com/sporkmonger/addressable/pull/464
|
data/Rakefile
CHANGED
@@ -24,7 +24,8 @@ PKG_FILES = FileList[
|
|
24
24
|
"tasks/**/*",
|
25
25
|
"[A-Z]*", "Rakefile"
|
26
26
|
].exclude(/pkg/).exclude(/database\.yml/).
|
27
|
-
exclude(/Gemfile\.lock/).exclude(/[_\.]git$/)
|
27
|
+
exclude(/Gemfile\.lock/).exclude(/[_\.]git$/).
|
28
|
+
exclude(/coverage/)
|
28
29
|
|
29
30
|
task :default => "spec"
|
30
31
|
|
data/addressable.gemspec
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
# stub: addressable 2.8.4 ruby lib
|
3
|
+
|
4
|
+
Gem::Specification.new do |s|
|
5
|
+
s.name = "addressable".freeze
|
6
|
+
s.version = "2.8.4"
|
7
|
+
|
8
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0".freeze) if s.respond_to? :required_rubygems_version=
|
9
|
+
s.metadata = { "changelog_uri" => "https://github.com/sporkmonger/addressable/blob/main/CHANGELOG.md" } if s.respond_to? :metadata=
|
10
|
+
s.require_paths = ["lib".freeze]
|
11
|
+
s.authors = ["Bob Aman".freeze]
|
12
|
+
s.date = "2023-04-09"
|
13
|
+
s.description = "Addressable is an alternative implementation to the URI implementation that is\npart of Ruby's standard library. It is flexible, offers heuristic parsing, and\nadditionally provides extensive support for IRIs and URI templates.\n".freeze
|
14
|
+
s.email = "bob@sporkmonger.com".freeze
|
15
|
+
s.extra_rdoc_files = ["README.md".freeze]
|
16
|
+
s.files = ["CHANGELOG.md".freeze, "Gemfile".freeze, "LICENSE.txt".freeze, "README.md".freeze, "Rakefile".freeze, "addressable.gemspec".freeze, "data/unicode.data".freeze, "lib/addressable.rb".freeze, "lib/addressable/idna.rb".freeze, "lib/addressable/idna/native.rb".freeze, "lib/addressable/idna/pure.rb".freeze, "lib/addressable/template.rb".freeze, "lib/addressable/uri.rb".freeze, "lib/addressable/version.rb".freeze, "spec/addressable/idna_spec.rb".freeze, "spec/addressable/net_http_compat_spec.rb".freeze, "spec/addressable/security_spec.rb".freeze, "spec/addressable/template_spec.rb".freeze, "spec/addressable/uri_spec.rb".freeze, "spec/spec_helper.rb".freeze, "tasks/clobber.rake".freeze, "tasks/gem.rake".freeze, "tasks/git.rake".freeze, "tasks/metrics.rake".freeze, "tasks/profile.rake".freeze, "tasks/rspec.rake".freeze, "tasks/yard.rake".freeze]
|
17
|
+
s.homepage = "https://github.com/sporkmonger/addressable".freeze
|
18
|
+
s.licenses = ["Apache-2.0".freeze]
|
19
|
+
s.rdoc_options = ["--main".freeze, "README.md".freeze]
|
20
|
+
s.required_ruby_version = Gem::Requirement.new(">= 2.2".freeze)
|
21
|
+
s.rubygems_version = "3.4.10".freeze
|
22
|
+
s.summary = "URI Implementation".freeze
|
23
|
+
|
24
|
+
s.specification_version = 4
|
25
|
+
|
26
|
+
s.add_runtime_dependency(%q<public_suffix>.freeze, [">= 2.0.2", "< 6.0"])
|
27
|
+
s.add_development_dependency(%q<bundler>.freeze, [">= 1.0", "< 3.0"])
|
28
|
+
end
|
@@ -29,8 +29,14 @@ module Addressable
|
|
29
29
|
IDN::Punycode.decode(value.to_s)
|
30
30
|
end
|
31
31
|
|
32
|
-
|
33
|
-
|
32
|
+
class << self
|
33
|
+
# @deprecated Use {String#unicode_normalize(:nfkc)} instead
|
34
|
+
def unicode_normalize_kc(value)
|
35
|
+
value.to_s.unicode_normalize(:nfkc)
|
36
|
+
end
|
37
|
+
|
38
|
+
extend Gem::Deprecate
|
39
|
+
deprecate :unicode_normalize_kc, "String#unicode_normalize(:nfkc)", 2023, 4
|
34
40
|
end
|
35
41
|
|
36
42
|
def self.to_ascii(value)
|
@@ -66,7 +66,7 @@ module Addressable
|
|
66
66
|
# domain name as described in RFC 3490.
|
67
67
|
def self.to_ascii(input)
|
68
68
|
input = input.to_s unless input.is_a?(String)
|
69
|
-
input = input.dup
|
69
|
+
input = input.dup.force_encoding(Encoding::UTF_8).unicode_normalize(:nfkc)
|
70
70
|
if input.respond_to?(:force_encoding)
|
71
71
|
input.force_encoding(Encoding::ASCII_8BIT)
|
72
72
|
end
|
@@ -77,7 +77,7 @@ module Addressable
|
|
77
77
|
part.force_encoding(Encoding::ASCII_8BIT)
|
78
78
|
end
|
79
79
|
if part =~ UTF8_REGEX && part =~ UTF8_REGEX_MULTIBYTE
|
80
|
-
ACE_PREFIX + punycode_encode(
|
80
|
+
ACE_PREFIX + punycode_encode(part)
|
81
81
|
else
|
82
82
|
part
|
83
83
|
end
|
@@ -112,13 +112,14 @@ module Addressable
|
|
112
112
|
output
|
113
113
|
end
|
114
114
|
|
115
|
-
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
|
120
|
-
|
121
|
-
|
115
|
+
class << self
|
116
|
+
# @deprecated Use {String#unicode_normalize(:nfkc)} instead
|
117
|
+
def unicode_normalize_kc(value)
|
118
|
+
value.to_s.unicode_normalize(:nfkc)
|
119
|
+
end
|
120
|
+
|
121
|
+
extend Gem::Deprecate
|
122
|
+
deprecate :unicode_normalize_kc, "String#unicode_normalize(:nfkc)", 2023, 4
|
122
123
|
end
|
123
124
|
|
124
125
|
##
|
@@ -136,164 +137,6 @@ module Addressable
|
|
136
137
|
end
|
137
138
|
private_class_method :unicode_downcase
|
138
139
|
|
139
|
-
def self.unicode_compose(unpacked)
|
140
|
-
unpacked_result = []
|
141
|
-
length = unpacked.length
|
142
|
-
|
143
|
-
return unpacked if length == 0
|
144
|
-
|
145
|
-
starter = unpacked[0]
|
146
|
-
starter_cc = lookup_unicode_combining_class(starter)
|
147
|
-
starter_cc = 256 if starter_cc != 0
|
148
|
-
for i in 1...length
|
149
|
-
ch = unpacked[i]
|
150
|
-
|
151
|
-
if (starter_cc == 0 &&
|
152
|
-
(composite = unicode_compose_pair(starter, ch)) != nil)
|
153
|
-
starter = composite
|
154
|
-
else
|
155
|
-
unpacked_result << starter
|
156
|
-
starter = ch
|
157
|
-
end
|
158
|
-
end
|
159
|
-
unpacked_result << starter
|
160
|
-
return unpacked_result
|
161
|
-
end
|
162
|
-
private_class_method :unicode_compose
|
163
|
-
|
164
|
-
def self.unicode_compose_pair(ch_one, ch_two)
|
165
|
-
if ch_one >= HANGUL_LBASE && ch_one < HANGUL_LBASE + HANGUL_LCOUNT &&
|
166
|
-
ch_two >= HANGUL_VBASE && ch_two < HANGUL_VBASE + HANGUL_VCOUNT
|
167
|
-
# Hangul L + V
|
168
|
-
return HANGUL_SBASE + (
|
169
|
-
(ch_one - HANGUL_LBASE) * HANGUL_VCOUNT + (ch_two - HANGUL_VBASE)
|
170
|
-
) * HANGUL_TCOUNT
|
171
|
-
elsif ch_one >= HANGUL_SBASE &&
|
172
|
-
ch_one < HANGUL_SBASE + HANGUL_SCOUNT &&
|
173
|
-
(ch_one - HANGUL_SBASE) % HANGUL_TCOUNT == 0 &&
|
174
|
-
ch_two >= HANGUL_TBASE && ch_two < HANGUL_TBASE + HANGUL_TCOUNT
|
175
|
-
# Hangul LV + T
|
176
|
-
return ch_one + (ch_two - HANGUL_TBASE)
|
177
|
-
end
|
178
|
-
|
179
|
-
p = []
|
180
|
-
|
181
|
-
ucs4_to_utf8(ch_one, p)
|
182
|
-
ucs4_to_utf8(ch_two, p)
|
183
|
-
|
184
|
-
return lookup_unicode_composition(p)
|
185
|
-
end
|
186
|
-
private_class_method :unicode_compose_pair
|
187
|
-
|
188
|
-
def self.ucs4_to_utf8(char, buffer)
|
189
|
-
if char < 128
|
190
|
-
buffer << char
|
191
|
-
elsif char < 2048
|
192
|
-
buffer << (char >> 6 | 192)
|
193
|
-
buffer << (char & 63 | 128)
|
194
|
-
elsif char < 0x10000
|
195
|
-
buffer << (char >> 12 | 224)
|
196
|
-
buffer << (char >> 6 & 63 | 128)
|
197
|
-
buffer << (char & 63 | 128)
|
198
|
-
elsif char < 0x200000
|
199
|
-
buffer << (char >> 18 | 240)
|
200
|
-
buffer << (char >> 12 & 63 | 128)
|
201
|
-
buffer << (char >> 6 & 63 | 128)
|
202
|
-
buffer << (char & 63 | 128)
|
203
|
-
elsif char < 0x4000000
|
204
|
-
buffer << (char >> 24 | 248)
|
205
|
-
buffer << (char >> 18 & 63 | 128)
|
206
|
-
buffer << (char >> 12 & 63 | 128)
|
207
|
-
buffer << (char >> 6 & 63 | 128)
|
208
|
-
buffer << (char & 63 | 128)
|
209
|
-
elsif char < 0x80000000
|
210
|
-
buffer << (char >> 30 | 252)
|
211
|
-
buffer << (char >> 24 & 63 | 128)
|
212
|
-
buffer << (char >> 18 & 63 | 128)
|
213
|
-
buffer << (char >> 12 & 63 | 128)
|
214
|
-
buffer << (char >> 6 & 63 | 128)
|
215
|
-
buffer << (char & 63 | 128)
|
216
|
-
end
|
217
|
-
end
|
218
|
-
private_class_method :ucs4_to_utf8
|
219
|
-
|
220
|
-
def self.unicode_sort_canonical(unpacked)
|
221
|
-
unpacked = unpacked.dup
|
222
|
-
i = 1
|
223
|
-
length = unpacked.length
|
224
|
-
|
225
|
-
return unpacked if length < 2
|
226
|
-
|
227
|
-
while i < length
|
228
|
-
last = unpacked[i-1]
|
229
|
-
ch = unpacked[i]
|
230
|
-
last_cc = lookup_unicode_combining_class(last)
|
231
|
-
cc = lookup_unicode_combining_class(ch)
|
232
|
-
if cc != 0 && last_cc != 0 && last_cc > cc
|
233
|
-
unpacked[i] = last
|
234
|
-
unpacked[i-1] = ch
|
235
|
-
i -= 1 if i > 1
|
236
|
-
else
|
237
|
-
i += 1
|
238
|
-
end
|
239
|
-
end
|
240
|
-
return unpacked
|
241
|
-
end
|
242
|
-
private_class_method :unicode_sort_canonical
|
243
|
-
|
244
|
-
def self.unicode_decompose(unpacked)
|
245
|
-
unpacked_result = []
|
246
|
-
for cp in unpacked
|
247
|
-
if cp >= HANGUL_SBASE && cp < HANGUL_SBASE + HANGUL_SCOUNT
|
248
|
-
l, v, t = unicode_decompose_hangul(cp)
|
249
|
-
unpacked_result << l
|
250
|
-
unpacked_result << v if v
|
251
|
-
unpacked_result << t if t
|
252
|
-
else
|
253
|
-
dc = lookup_unicode_compatibility(cp)
|
254
|
-
unless dc
|
255
|
-
unpacked_result << cp
|
256
|
-
else
|
257
|
-
unpacked_result.concat(unicode_decompose(dc.unpack("U*")))
|
258
|
-
end
|
259
|
-
end
|
260
|
-
end
|
261
|
-
return unpacked_result
|
262
|
-
end
|
263
|
-
private_class_method :unicode_decompose
|
264
|
-
|
265
|
-
def self.unicode_decompose_hangul(codepoint)
|
266
|
-
sindex = codepoint - HANGUL_SBASE;
|
267
|
-
if sindex < 0 || sindex >= HANGUL_SCOUNT
|
268
|
-
l = codepoint
|
269
|
-
v = t = nil
|
270
|
-
return l, v, t
|
271
|
-
end
|
272
|
-
l = HANGUL_LBASE + sindex / HANGUL_NCOUNT
|
273
|
-
v = HANGUL_VBASE + (sindex % HANGUL_NCOUNT) / HANGUL_TCOUNT
|
274
|
-
t = HANGUL_TBASE + sindex % HANGUL_TCOUNT
|
275
|
-
if t == HANGUL_TBASE
|
276
|
-
t = nil
|
277
|
-
end
|
278
|
-
return l, v, t
|
279
|
-
end
|
280
|
-
private_class_method :unicode_decompose_hangul
|
281
|
-
|
282
|
-
def self.lookup_unicode_combining_class(codepoint)
|
283
|
-
codepoint_data = UNICODE_DATA[codepoint]
|
284
|
-
(codepoint_data ?
|
285
|
-
(codepoint_data[UNICODE_DATA_COMBINING_CLASS] || 0) :
|
286
|
-
0)
|
287
|
-
end
|
288
|
-
private_class_method :lookup_unicode_combining_class
|
289
|
-
|
290
|
-
def self.lookup_unicode_compatibility(codepoint)
|
291
|
-
codepoint_data = UNICODE_DATA[codepoint]
|
292
|
-
(codepoint_data ?
|
293
|
-
codepoint_data[UNICODE_DATA_COMPATIBILITY] : nil)
|
294
|
-
end
|
295
|
-
private_class_method :lookup_unicode_compatibility
|
296
|
-
|
297
140
|
def self.lookup_unicode_lowercase(codepoint)
|
298
141
|
codepoint_data = UNICODE_DATA[codepoint]
|
299
142
|
(codepoint_data ?
|
@@ -302,21 +145,6 @@ module Addressable
|
|
302
145
|
end
|
303
146
|
private_class_method :lookup_unicode_lowercase
|
304
147
|
|
305
|
-
def self.lookup_unicode_composition(unpacked)
|
306
|
-
return COMPOSITION_TABLE[unpacked]
|
307
|
-
end
|
308
|
-
private_class_method :lookup_unicode_composition
|
309
|
-
|
310
|
-
HANGUL_SBASE = 0xac00
|
311
|
-
HANGUL_LBASE = 0x1100
|
312
|
-
HANGUL_LCOUNT = 19
|
313
|
-
HANGUL_VBASE = 0x1161
|
314
|
-
HANGUL_VCOUNT = 21
|
315
|
-
HANGUL_TBASE = 0x11a7
|
316
|
-
HANGUL_TCOUNT = 28
|
317
|
-
HANGUL_NCOUNT = HANGUL_VCOUNT * HANGUL_TCOUNT # 588
|
318
|
-
HANGUL_SCOUNT = HANGUL_LCOUNT * HANGUL_NCOUNT # 11172
|
319
|
-
|
320
148
|
UNICODE_DATA_COMBINING_CLASS = 0
|
321
149
|
UNICODE_DATA_EXCLUSION = 1
|
322
150
|
UNICODE_DATA_CANONICAL = 2
|
data/lib/addressable/template.rb
CHANGED
@@ -892,25 +892,24 @@ module Addressable
|
|
892
892
|
# operator.
|
893
893
|
#
|
894
894
|
# @param [Hash, Array, String] value
|
895
|
-
# Normalizes keys and values with
|
895
|
+
# Normalizes unicode keys and values with String#unicode_normalize (NFC)
|
896
896
|
#
|
897
897
|
# @return [Hash, Array, String] The normalized values
|
898
898
|
def normalize_value(value)
|
899
|
-
unless value.is_a?(Hash)
|
900
|
-
value = value.respond_to?(:to_ary) ? value.to_ary : value.to_str
|
901
|
-
end
|
902
|
-
|
903
899
|
# Handle unicode normalization
|
904
|
-
if value.
|
905
|
-
value.map! { |val|
|
900
|
+
if value.respond_to?(:to_ary)
|
901
|
+
value.to_ary.map! { |val| normalize_value(val) }
|
906
902
|
elsif value.kind_of?(Hash)
|
907
903
|
value = value.inject({}) { |acc, (k, v)|
|
908
|
-
acc[
|
909
|
-
Addressable::IDNA.unicode_normalize_kc(v)
|
904
|
+
acc[normalize_value(k)] = normalize_value(v)
|
910
905
|
acc
|
911
906
|
}
|
912
907
|
else
|
913
|
-
value =
|
908
|
+
value = value.to_s if !value.kind_of?(String)
|
909
|
+
if value.encoding != Encoding::UTF_8
|
910
|
+
value = value.dup.force_encoding(Encoding::UTF_8)
|
911
|
+
end
|
912
|
+
value = value.unicode_normalize(:nfc)
|
914
913
|
end
|
915
914
|
value
|
916
915
|
end
|