regexp_property_values 1.2.0-java → 1.4.0-java
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/CHANGELOG.md +10 -0
- data/Rakefile +6 -0
- data/lib/aliases +5 -0
- data/lib/regexp_property_values/updater.rb +8 -21
- data/lib/regexp_property_values/version.rb +1 -1
- data/lib/values +29 -0
- metadata +3 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 9aad0c3c1f944b7c75346dd9f789dfed8d13fcc91da62631a1a3e98365f0ca8a
|
4
|
+
data.tar.gz: eda51e3a4a97d7c5101aec7b0c868b68105b30d6e06825873dfbdf0792f1910a
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 7edb359fd4aed59738212aec9ec9e2747227df4d6df057a4c0e738e2f93b181bcbfad27b6eb52bc9a37dc6f5734ef6dbba3f331bd3774c07517aff6d779694f9
|
7
|
+
data.tar.gz: 0e7bc02f520b6459928c3c84f012ca5157fceda81354c98feef5b04baeec4cb98cd44458ec67c96d93a51d0ecf312fa8a728189bbbe1dfa7a7d2490fa1fa3b1a
|
data/CHANGELOG.md
CHANGED
@@ -4,6 +4,16 @@ All notable changes to this project will be documented in this file.
|
|
4
4
|
The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
|
5
5
|
and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
|
6
6
|
|
7
|
+
## [1.4.0] - 2023-06-10
|
8
|
+
|
9
|
+
### Added
|
10
|
+
- new properties of Ruby 3.2 / Unicode 15.0
|
11
|
+
|
12
|
+
## [1.3.0] - 2022-04-07
|
13
|
+
|
14
|
+
### Added
|
15
|
+
- new properties of Ruby 3.2 / Unicode 14.0
|
16
|
+
|
7
17
|
## [1.2.0] - 2021-12-31
|
8
18
|
|
9
19
|
### Added
|
data/Rakefile
CHANGED
data/lib/aliases
CHANGED
@@ -35,6 +35,7 @@ Cn;Unassigned
|
|
35
35
|
Co;Private_Use
|
36
36
|
Combining_Mark;Mark
|
37
37
|
Copt;Coptic
|
38
|
+
Cpmn;Cypro_Minoan
|
38
39
|
Cprt;Cypriot
|
39
40
|
Cs;Surrogate
|
40
41
|
Cyrl;Cyrillic
|
@@ -132,6 +133,7 @@ Mult;Multani
|
|
132
133
|
Mymr;Myanmar
|
133
134
|
N;Number
|
134
135
|
NChar;Noncharacter_Code_Point
|
136
|
+
Nagm;Nag_Mundari
|
135
137
|
Nand;Nandinagari
|
136
138
|
Narb;Old_North_Arabian
|
137
139
|
Nbat;Nabataean
|
@@ -154,6 +156,7 @@ Orkh;Old_Turkic
|
|
154
156
|
Orya;Oriya
|
155
157
|
Osge;Osage
|
156
158
|
Osma;Osmanya
|
159
|
+
Ougr;Old_Uyghur
|
157
160
|
P;Punctuation
|
158
161
|
PCM;Prepended_Concatenation_Mark
|
159
162
|
Palm;Palmyrene
|
@@ -218,10 +221,12 @@ Tglg;Tagalog
|
|
218
221
|
Thaa;Thaana
|
219
222
|
Tibt;Tibetan
|
220
223
|
Tirh;Tirhuta
|
224
|
+
Tnsa;Tangsa
|
221
225
|
UIdeo;Unified_Ideograph
|
222
226
|
Ugar;Ugaritic
|
223
227
|
VS;Variation_Selector
|
224
228
|
Vaii;Vai
|
229
|
+
Vith;Vithkuqi
|
225
230
|
WSpace;White_Space
|
226
231
|
Wara;Warang_Citi
|
227
232
|
Wcho;Wancho
|
@@ -5,7 +5,7 @@ module RegexpPropertyValues
|
|
5
5
|
require 'fileutils'
|
6
6
|
require 'set'
|
7
7
|
|
8
|
-
BASE_URL = '
|
8
|
+
BASE_URL = 'https://www.unicode.org/Public/UCD/latest/ucd'
|
9
9
|
|
10
10
|
UCD_FILES = %w[
|
11
11
|
Blocks.txt
|
@@ -38,26 +38,11 @@ module RegexpPropertyValues
|
|
38
38
|
end
|
39
39
|
|
40
40
|
def download_ucd_files(ucd_path: nil, emoji_path: nil)
|
41
|
-
|
42
|
-
|
43
|
-
|
44
|
-
ucd_path ||= ENV['RPV_UCD_PATH']
|
45
|
-
emoji_path ||= ENV['RPV_EMOJI_PATH']
|
46
|
-
|
47
|
-
if ucd_path.nil? && emoji_path.nil?
|
48
|
-
puts <<-EOS.gsub(/\n */, ' ')
|
49
|
-
This try will load ucd and emoji data for the CURRENT RUBY (
|
50
|
-
(#{RUBY_VERSION} - ucd #{unicode_version}, emoji #{emoji_version}).
|
51
|
-
Run this on the latest Ruby version you want to support.
|
52
|
-
Unicode directory structure changes sometimes, so you might need to
|
53
|
-
pass the right path(s) as keyword args or ENV vars. Continue? [y/n]'
|
54
|
-
EOS
|
55
|
-
|
56
|
-
return puts 'download skipped.' unless $stdin.gets =~ /^y/i
|
57
|
-
end
|
41
|
+
puts 'This will try to load the latest UCD data. Continue? [y/n]'
|
42
|
+
return puts 'download skipped.' unless $stdin.gets =~ /^y/i
|
58
43
|
|
59
|
-
ucd_path ||=
|
60
|
-
emoji_path ||= "#{BASE_URL}/emoji
|
44
|
+
ucd_path ||= ENV['RPV_UCD_PATH'] || BASE_URL
|
45
|
+
emoji_path ||= ENV['RPV_EMOJI_PATH'] || "#{BASE_URL}/emoji/"
|
61
46
|
|
62
47
|
Dir.chdir(TMP_DIR) do
|
63
48
|
UCD_FILES.each { |f| `wget #{ucd_path}/#{f}` }
|
@@ -76,7 +61,9 @@ module RegexpPropertyValues
|
|
76
61
|
]
|
77
62
|
|
78
63
|
# special properties
|
79
|
-
@values += %w[
|
64
|
+
@values += %w[
|
65
|
+
Any Assigned Extended_Pictographic In_No_Block Unknown
|
66
|
+
]
|
80
67
|
|
81
68
|
# legacy properties
|
82
69
|
@values += %w[Newline]
|
data/lib/values
CHANGED
@@ -7,6 +7,8 @@ Age=11.0
|
|
7
7
|
Age=12.0
|
8
8
|
Age=12.1
|
9
9
|
Age=13.0
|
10
|
+
Age=14.0
|
11
|
+
Age=15.0
|
10
12
|
Age=2.0
|
11
13
|
Age=2.1
|
12
14
|
Age=3.0
|
@@ -71,6 +73,7 @@ Coptic
|
|
71
73
|
Cuneiform
|
72
74
|
Currency_Symbol
|
73
75
|
Cypriot
|
76
|
+
Cypro_Minoan
|
74
77
|
Cyrillic
|
75
78
|
Dash
|
76
79
|
Dash_Punctuation
|
@@ -94,6 +97,7 @@ Emoji_Modifier_Base
|
|
94
97
|
Emoji_Presentation
|
95
98
|
Enclosing_Mark
|
96
99
|
Ethiopic
|
100
|
+
Extended_Pictographic
|
97
101
|
Extender
|
98
102
|
Final_Punctuation
|
99
103
|
Format
|
@@ -135,6 +139,8 @@ In_Ancient_Greek_Numbers
|
|
135
139
|
In_Ancient_Symbols
|
136
140
|
In_Arabic
|
137
141
|
In_Arabic_Extended_A
|
142
|
+
In_Arabic_Extended_B
|
143
|
+
In_Arabic_Extended_C
|
138
144
|
In_Arabic_Mathematical_Alphabetic_Symbols
|
139
145
|
In_Arabic_Presentation_Forms_A
|
140
146
|
In_Arabic_Presentation_Forms_B
|
@@ -174,6 +180,7 @@ In_CJK_Unified_Ideographs_Extension_D
|
|
174
180
|
In_CJK_Unified_Ideographs_Extension_E
|
175
181
|
In_CJK_Unified_Ideographs_Extension_F
|
176
182
|
In_CJK_Unified_Ideographs_Extension_G
|
183
|
+
In_CJK_Unified_Ideographs_Extension_H
|
177
184
|
In_Carian
|
178
185
|
In_Caucasian_Albanian
|
179
186
|
In_Chakma
|
@@ -196,14 +203,17 @@ In_Cuneiform
|
|
196
203
|
In_Cuneiform_Numbers_and_Punctuation
|
197
204
|
In_Currency_Symbols
|
198
205
|
In_Cypriot_Syllabary
|
206
|
+
In_Cypro_Minoan
|
199
207
|
In_Cyrillic
|
200
208
|
In_Cyrillic_Extended_A
|
201
209
|
In_Cyrillic_Extended_B
|
202
210
|
In_Cyrillic_Extended_C
|
211
|
+
In_Cyrillic_Extended_D
|
203
212
|
In_Cyrillic_Supplement
|
204
213
|
In_Deseret
|
205
214
|
In_Devanagari
|
206
215
|
In_Devanagari_Extended
|
216
|
+
In_Devanagari_Extended_A
|
207
217
|
In_Dingbats
|
208
218
|
In_Dives_Akuru
|
209
219
|
In_Dogra
|
@@ -222,6 +232,7 @@ In_Enclosed_Ideographic_Supplement
|
|
222
232
|
In_Ethiopic
|
223
233
|
In_Ethiopic_Extended
|
224
234
|
In_Ethiopic_Extended_A
|
235
|
+
In_Ethiopic_Extended_B
|
225
236
|
In_Ethiopic_Supplement
|
226
237
|
In_General_Punctuation
|
227
238
|
In_Geometric_Shapes
|
@@ -260,13 +271,16 @@ In_Inscriptional_Pahlavi
|
|
260
271
|
In_Inscriptional_Parthian
|
261
272
|
In_Javanese
|
262
273
|
In_Kaithi
|
274
|
+
In_Kaktovik_Numerals
|
263
275
|
In_Kana_Extended_A
|
276
|
+
In_Kana_Extended_B
|
264
277
|
In_Kana_Supplement
|
265
278
|
In_Kanbun
|
266
279
|
In_Kangxi_Radicals
|
267
280
|
In_Kannada
|
268
281
|
In_Katakana
|
269
282
|
In_Katakana_Phonetic_Extensions
|
283
|
+
In_Kawi
|
270
284
|
In_Kayah_Li
|
271
285
|
In_Kharoshthi
|
272
286
|
In_Khitan_Small_Script
|
@@ -282,6 +296,8 @@ In_Latin_Extended_B
|
|
282
296
|
In_Latin_Extended_C
|
283
297
|
In_Latin_Extended_D
|
284
298
|
In_Latin_Extended_E
|
299
|
+
In_Latin_Extended_F
|
300
|
+
In_Latin_Extended_G
|
285
301
|
In_Lepcha
|
286
302
|
In_Letterlike_Symbols
|
287
303
|
In_Limbu
|
@@ -329,6 +345,7 @@ In_Myanmar_Extended_A
|
|
329
345
|
In_Myanmar_Extended_B
|
330
346
|
In_NKo
|
331
347
|
In_Nabataean
|
348
|
+
In_Nag_Mundari
|
332
349
|
In_Nandinagari
|
333
350
|
In_New_Tai_Lue
|
334
351
|
In_Newa
|
@@ -346,6 +363,7 @@ In_Old_Persian
|
|
346
363
|
In_Old_Sogdian
|
347
364
|
In_Old_South_Arabian
|
348
365
|
In_Old_Turkic
|
366
|
+
In_Old_Uyghur
|
349
367
|
In_Optical_Character_Recognition
|
350
368
|
In_Oriya
|
351
369
|
In_Ornamental_Dingbats
|
@@ -408,6 +426,7 @@ In_Tai_Xuan_Jing_Symbols
|
|
408
426
|
In_Takri
|
409
427
|
In_Tamil
|
410
428
|
In_Tamil_Supplement
|
429
|
+
In_Tangsa
|
411
430
|
In_Tangut
|
412
431
|
In_Tangut_Components
|
413
432
|
In_Tangut_Supplement
|
@@ -417,15 +436,18 @@ In_Thai
|
|
417
436
|
In_Tibetan
|
418
437
|
In_Tifinagh
|
419
438
|
In_Tirhuta
|
439
|
+
In_Toto
|
420
440
|
In_Transport_and_Map_Symbols
|
421
441
|
In_Ugaritic
|
422
442
|
In_Unified_Canadian_Aboriginal_Syllabics
|
423
443
|
In_Unified_Canadian_Aboriginal_Syllabics_Extended
|
444
|
+
In_Unified_Canadian_Aboriginal_Syllabics_Extended_A
|
424
445
|
In_Vai
|
425
446
|
In_Variation_Selectors
|
426
447
|
In_Variation_Selectors_Supplement
|
427
448
|
In_Vedic_Extensions
|
428
449
|
In_Vertical_Forms
|
450
|
+
In_Vithkuqi
|
429
451
|
In_Wancho
|
430
452
|
In_Warang_Citi
|
431
453
|
In_Yezidi
|
@@ -433,6 +455,7 @@ In_Yi_Radicals
|
|
433
455
|
In_Yi_Syllables
|
434
456
|
In_Yijing_Hexagram_Symbols
|
435
457
|
In_Zanabazar_Square
|
458
|
+
In_Znamenny_Musical_Notation
|
436
459
|
Inherited
|
437
460
|
Initial_Punctuation
|
438
461
|
Inscriptional_Pahlavi
|
@@ -442,6 +465,7 @@ Join_Control
|
|
442
465
|
Kaithi
|
443
466
|
Kannada
|
444
467
|
Katakana
|
468
|
+
Kawi
|
445
469
|
Kayah_Li
|
446
470
|
Kharoshthi
|
447
471
|
Khitan_Small_Script
|
@@ -488,6 +512,7 @@ Mro
|
|
488
512
|
Multani
|
489
513
|
Myanmar
|
490
514
|
Nabataean
|
515
|
+
Nag_Mundari
|
491
516
|
Nandinagari
|
492
517
|
New_Tai_Lue
|
493
518
|
Newa
|
@@ -508,6 +533,7 @@ Old_Persian
|
|
508
533
|
Old_Sogdian
|
509
534
|
Old_South_Arabian
|
510
535
|
Old_Turkic
|
536
|
+
Old_Uyghur
|
511
537
|
Open_Punctuation
|
512
538
|
Oriya
|
513
539
|
Osage
|
@@ -572,6 +598,7 @@ Tai_Tham
|
|
572
598
|
Tai_Viet
|
573
599
|
Takri
|
574
600
|
Tamil
|
601
|
+
Tangsa
|
575
602
|
Tangut
|
576
603
|
Telugu
|
577
604
|
Terminal_Punctuation
|
@@ -581,6 +608,7 @@ Tibetan
|
|
581
608
|
Tifinagh
|
582
609
|
Tirhuta
|
583
610
|
Titlecase_Letter
|
611
|
+
Toto
|
584
612
|
Ugaritic
|
585
613
|
Unassigned
|
586
614
|
Unified_Ideograph
|
@@ -590,6 +618,7 @@ Uppercase
|
|
590
618
|
Uppercase_Letter
|
591
619
|
Vai
|
592
620
|
Variation_Selector
|
621
|
+
Vithkuqi
|
593
622
|
Wancho
|
594
623
|
Warang_Citi
|
595
624
|
White_Space
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: regexp_property_values
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.
|
4
|
+
version: 1.4.0
|
5
5
|
platform: java
|
6
6
|
authors:
|
7
7
|
- Janosch Müller
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2023-06-10 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: range_compressor
|
@@ -74,7 +74,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
74
74
|
- !ruby/object:Gem::Version
|
75
75
|
version: '0'
|
76
76
|
requirements: []
|
77
|
-
rubygems_version: 3.
|
77
|
+
rubygems_version: 3.4.10
|
78
78
|
signing_key:
|
79
79
|
specification_version: 4
|
80
80
|
summary: Inspect property values supported by Ruby's regex engine
|