unicode-scripts 1.9.0 → 1.10.0
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 +4 -0
- data/Gemfile.lock +1 -1
- data/MIT-LICENSE.txt +1 -1
- data/README.md +21 -8
- data/data/scripts.marshal.gz +0 -0
- data/lib/unicode/scripts/constants.rb +2 -2
- data/spec/unicode_scripts_spec.rb +4 -0
- metadata +7 -7
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 619c8f5ddc697b93bff330edd8dae275a9684f0410272237284de4f829779803
|
|
4
|
+
data.tar.gz: d0468aeae3dac7525f1f8a79816fde9eb450dccf8b984e685d0a8b8409acb81f
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 98f89704fd77edeea1079eb26011c23c29c8fb36eb0b078848d097069a935771adbbd8946a4289031d5575056065cf1c641a0e6a3248fdf017ed72de0efbfff4
|
|
7
|
+
data.tar.gz: d374cba93bd2e84ac064f4583bca2df4e66029cb5dd3d21fee4d52689f6c4de738c926eb93b1c67e4f8ae149b6a58ffb8cb67e5ee8f66ba9cea2227553e59fc5
|
data/CHANGELOG.md
CHANGED
data/Gemfile.lock
CHANGED
data/MIT-LICENSE.txt
CHANGED
data/README.md
CHANGED
|
@@ -2,11 +2,11 @@
|
|
|
2
2
|
|
|
3
3
|
Retrieve the [Unicode script(s)](https://en.wikipedia.org/wiki/Script_%28Unicode%29) a string belongs to. Can also return the *Script_Extension* property which is defined as characters which are "commonly used with more than one script, but with a limited number of scripts".
|
|
4
4
|
|
|
5
|
-
Unicode version: **
|
|
5
|
+
Unicode version: **16.0.0** (September 2024)
|
|
6
6
|
|
|
7
|
-
Supported Rubies: **3.2**, **3.1**, **3.0**
|
|
7
|
+
Supported Rubies: **3.3**, **3.2**, **3.1**, **3.0**
|
|
8
8
|
|
|
9
|
-
Old Rubies that might still work: **2.X**
|
|
9
|
+
Old Rubies that might still work: **2.7**, **2.6**, **2.5**, **2.4**, **2.3**, **2.X**
|
|
10
10
|
|
|
11
11
|
## Gemfile
|
|
12
12
|
|
|
@@ -29,9 +29,9 @@ Unicode::Scripts.script("ᴦ") # => "Greek"
|
|
|
29
29
|
|
|
30
30
|
# Script_Extension property
|
|
31
31
|
Unicode::Scripts.script_extensions("॥")
|
|
32
|
-
# => ["Bengali", "Devanagari", "Dogra", "Grantha", "Gujarati","Gunjala_Gondi", "Gurmukhi",
|
|
33
|
-
"Khudawadi",
|
|
34
|
-
"Syloti_Nagri", "Takri", "Tamil", "Telugu", "Tirhuta"]
|
|
32
|
+
# => ["Bengali", "Devanagari", "Dogra", "Grantha", "Gujarati", "Gunjala_Gondi", "Gurmukhi","Gurung_Khema",
|
|
33
|
+
"Kannada","Khudawadi", "Limbu", "Mahajani", "Malayalam", "Masaram_Gondi", "Nandinagari", "Ol_Onal",
|
|
34
|
+
"Oriya", "Sinhala", "Syloti_Nagri", "Takri", "Tamil", "Telugu", "Tirhuta"]
|
|
35
35
|
```
|
|
36
36
|
|
|
37
37
|
## Hints
|
|
@@ -94,6 +94,7 @@ Egyptian_Hieroglyphs
|
|
|
94
94
|
Elbasan
|
|
95
95
|
Elymaic
|
|
96
96
|
Ethiopic
|
|
97
|
+
Garay
|
|
97
98
|
Georgian
|
|
98
99
|
Glagolitic
|
|
99
100
|
Gothic
|
|
@@ -102,6 +103,7 @@ Greek
|
|
|
102
103
|
Gujarati
|
|
103
104
|
Gunjala_Gondi
|
|
104
105
|
Gurmukhi
|
|
106
|
+
Gurung_Khema
|
|
105
107
|
Han
|
|
106
108
|
Hangul
|
|
107
109
|
Hanifi_Rohingya
|
|
@@ -125,6 +127,7 @@ Khitan_Small_Script
|
|
|
125
127
|
Khmer
|
|
126
128
|
Khojki
|
|
127
129
|
Khudawadi
|
|
130
|
+
Kirat_Rai
|
|
128
131
|
Lao
|
|
129
132
|
Latin
|
|
130
133
|
Lepcha
|
|
@@ -162,6 +165,7 @@ Nushu
|
|
|
162
165
|
Nyiakeng_Puachue_Hmong
|
|
163
166
|
Ogham
|
|
164
167
|
Ol_Chiki
|
|
168
|
+
Ol_Onal
|
|
165
169
|
Old_Hungarian
|
|
166
170
|
Old_Italic
|
|
167
171
|
Old_North_Arabian
|
|
@@ -193,6 +197,7 @@ Sogdian
|
|
|
193
197
|
Sora_Sompeng
|
|
194
198
|
Soyombo
|
|
195
199
|
Sundanese
|
|
200
|
+
Sunuwar
|
|
196
201
|
Syloti_Nagri
|
|
197
202
|
Syriac
|
|
198
203
|
Tagalog
|
|
@@ -210,7 +215,9 @@ Thai
|
|
|
210
215
|
Tibetan
|
|
211
216
|
Tifinagh
|
|
212
217
|
Tirhuta
|
|
218
|
+
Todhri
|
|
213
219
|
Toto
|
|
220
|
+
Tulu_Tigalari
|
|
214
221
|
Ugaritic
|
|
215
222
|
Unknown
|
|
216
223
|
Vai
|
|
@@ -223,7 +230,6 @@ Zanabazar_Square
|
|
|
223
230
|
```
|
|
224
231
|
|
|
225
232
|
### Short Script Names
|
|
226
|
-
|
|
227
233
|
You can extract all 4 letter script names from the gem like this:
|
|
228
234
|
|
|
229
235
|
```ruby
|
|
@@ -269,6 +275,7 @@ Egyp
|
|
|
269
275
|
Elba
|
|
270
276
|
Elym
|
|
271
277
|
Ethi
|
|
278
|
+
Gara
|
|
272
279
|
Geor
|
|
273
280
|
Glag
|
|
274
281
|
Gong
|
|
@@ -277,6 +284,7 @@ Goth
|
|
|
277
284
|
Gran
|
|
278
285
|
Grek
|
|
279
286
|
Gujr
|
|
287
|
+
Gukh
|
|
280
288
|
Guru
|
|
281
289
|
Hang
|
|
282
290
|
Hani
|
|
@@ -299,6 +307,7 @@ Khmr
|
|
|
299
307
|
Khoj
|
|
300
308
|
Kits
|
|
301
309
|
Knda
|
|
310
|
+
Krai
|
|
302
311
|
Kthi
|
|
303
312
|
Lana
|
|
304
313
|
Laoo
|
|
@@ -335,6 +344,7 @@ Nkoo
|
|
|
335
344
|
Nshu
|
|
336
345
|
Ogam
|
|
337
346
|
Olck
|
|
347
|
+
Onao
|
|
338
348
|
Orkh
|
|
339
349
|
Orya
|
|
340
350
|
Osge
|
|
@@ -368,6 +378,7 @@ Sogo
|
|
|
368
378
|
Sora
|
|
369
379
|
Soyo
|
|
370
380
|
Sund
|
|
381
|
+
Sunu
|
|
371
382
|
Sylo
|
|
372
383
|
Syrc
|
|
373
384
|
Tagb
|
|
@@ -385,7 +396,9 @@ Thai
|
|
|
385
396
|
Tibt
|
|
386
397
|
Tirh
|
|
387
398
|
Tnsa
|
|
399
|
+
Todr
|
|
388
400
|
Toto
|
|
401
|
+
Tutg
|
|
389
402
|
Ugar
|
|
390
403
|
Vaii
|
|
391
404
|
Vith
|
|
@@ -405,5 +418,5 @@ See [unicode-x](https://github.com/janlelis/unicode-x) for more Unicode related
|
|
|
405
418
|
|
|
406
419
|
## MIT License
|
|
407
420
|
|
|
408
|
-
- Copyright (C) 2016-
|
|
421
|
+
- Copyright (C) 2016-2024 Jan Lelis <https://janlelis.com>. Released under the MIT license.
|
|
409
422
|
- Unicode data: https://www.unicode.org/copyright.html#Exhibit1
|
data/data/scripts.marshal.gz
CHANGED
|
Binary file
|
|
@@ -2,8 +2,8 @@
|
|
|
2
2
|
|
|
3
3
|
module Unicode
|
|
4
4
|
module Scripts
|
|
5
|
-
VERSION = "1.
|
|
6
|
-
UNICODE_VERSION = "
|
|
5
|
+
VERSION = "1.10.0"
|
|
6
|
+
UNICODE_VERSION = "16.0.0"
|
|
7
7
|
DATA_DIRECTORY = File.expand_path(File.dirname(__FILE__) + "/../../../data/").freeze
|
|
8
8
|
INDEX_FILENAME = (DATA_DIRECTORY + "/scripts.marshal.gz").freeze
|
|
9
9
|
end
|
|
@@ -63,6 +63,7 @@ describe Unicode::Scripts do
|
|
|
63
63
|
"Gujarati",
|
|
64
64
|
"Gunjala_Gondi",
|
|
65
65
|
"Gurmukhi",
|
|
66
|
+
"Gurung_Khema",
|
|
66
67
|
"Kannada",
|
|
67
68
|
"Khudawadi",
|
|
68
69
|
"Limbu",
|
|
@@ -70,6 +71,7 @@ describe Unicode::Scripts do
|
|
|
70
71
|
"Malayalam",
|
|
71
72
|
"Masaram_Gondi",
|
|
72
73
|
"Nandinagari",
|
|
74
|
+
"Ol_Onal",
|
|
73
75
|
"Oriya",
|
|
74
76
|
"Sinhala",
|
|
75
77
|
"Syloti_Nagri",
|
|
@@ -89,12 +91,14 @@ describe Unicode::Scripts do
|
|
|
89
91
|
"Gonm",
|
|
90
92
|
"Gran",
|
|
91
93
|
"Gujr",
|
|
94
|
+
"Gukh",
|
|
92
95
|
"Guru",
|
|
93
96
|
"Knda",
|
|
94
97
|
"Limb",
|
|
95
98
|
"Mahj",
|
|
96
99
|
"Mlym",
|
|
97
100
|
"Nand",
|
|
101
|
+
"Onao",
|
|
98
102
|
"Orya",
|
|
99
103
|
"Sind",
|
|
100
104
|
"Sinh",
|
metadata
CHANGED
|
@@ -1,16 +1,16 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: unicode-scripts
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 1.
|
|
4
|
+
version: 1.10.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Jan Lelis
|
|
8
|
-
autorequire:
|
|
8
|
+
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date:
|
|
11
|
+
date: 2024-09-12 00:00:00.000000000 Z
|
|
12
12
|
dependencies: []
|
|
13
|
-
description: "[Unicode
|
|
13
|
+
description: "[Unicode 16.0.0] Retrieve the Unicode script(s) a string belongs to.
|
|
14
14
|
Can also return the Script_Extension property which is defined as characters which
|
|
15
15
|
are 'commonly used with more than one script, but with a limited number of scripts'. "
|
|
16
16
|
email:
|
|
@@ -39,7 +39,7 @@ licenses:
|
|
|
39
39
|
- MIT
|
|
40
40
|
metadata:
|
|
41
41
|
rubygems_mfa_required: 'true'
|
|
42
|
-
post_install_message:
|
|
42
|
+
post_install_message:
|
|
43
43
|
rdoc_options: []
|
|
44
44
|
require_paths:
|
|
45
45
|
- lib
|
|
@@ -54,8 +54,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
54
54
|
- !ruby/object:Gem::Version
|
|
55
55
|
version: '0'
|
|
56
56
|
requirements: []
|
|
57
|
-
rubygems_version: 3.
|
|
58
|
-
signing_key:
|
|
57
|
+
rubygems_version: 3.5.9
|
|
58
|
+
signing_key:
|
|
59
59
|
specification_version: 4
|
|
60
60
|
summary: Which script(s) does a Unicode string belong to?
|
|
61
61
|
test_files:
|