unicode-scripts 1.2.1 → 1.3.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +9 -0
- data/MIT-LICENSE.txt +1 -1
- data/README.md +21 -7
- data/data/scripts.marshal.gz +0 -0
- data/lib/unicode/scripts/constants.rb +2 -2
- data/lib/unicode/scripts/index.rb +9 -2
- 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: 4553aef6ef38f7ab727daa55ee8a3baf29848f5599f6e116f3e192bb12fecd72
|
4
|
+
data.tar.gz: 431a7deb7daab9a0651d9223cedeb0d2f4d32bd5e8e2417ca095e32251ddc0d3
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: bc8d031a9f5528608dff602cb383907c3ba26c7f54ac6e9e183b3d7dd112d8697d8e8d937531015d5a8030bbefdc4027ccbcaf0a253f73784db5795a8de3b45d
|
7
|
+
data.tar.gz: df002e70c93bdb45c9c0bf8467d497a16ffa0e840539762191eea9959daebefc36e438d53555421bb936ccc587ca4bc0bce8ea683f6c48fbb7b65686ff3fcd73
|
data/CHANGELOG.md
CHANGED
@@ -1,5 +1,14 @@
|
|
1
1
|
## CHANGELOG
|
2
2
|
|
3
|
+
### 1.3.0
|
4
|
+
|
5
|
+
* Unicode 11
|
6
|
+
* Do not depend on rubygems (only use zlib stdlib for unzipping)
|
7
|
+
|
8
|
+
### 1.2.2
|
9
|
+
|
10
|
+
* Explicitly load rubygems/util, fixes regression in 1.2.1
|
11
|
+
|
3
12
|
### 1.2.1
|
4
13
|
|
5
14
|
* Use `Gem::Util` for `gunzip`, removes deprecation warning
|
data/MIT-LICENSE.txt
CHANGED
data/README.md
CHANGED
@@ -2,7 +2,7 @@
|
|
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: **11.0.0**
|
6
6
|
|
7
7
|
Supported Rubies: **2.5**, **2.4**, **2.3**
|
8
8
|
|
@@ -28,11 +28,11 @@ Unicode::Scripts.scripts("СC", format: :short) # => ["Cyrl", "Latn"]
|
|
28
28
|
Unicode::Scripts.script("ᴦ") # => "Greek"
|
29
29
|
|
30
30
|
# Script_Extension property
|
31
|
-
Unicode::Scripts.script_extensions("॥")
|
32
|
-
|
33
|
-
|
34
|
-
|
35
|
-
|
31
|
+
Unicode::Scripts.script_extensions("॥")
|
32
|
+
# => ["Bengali", "Devanagari", "Dogra", "Grantha", "Gujarati",
|
33
|
+
"Gunjala_Gondi", "Gurmukhi", "Kannada", "Khudawadi", "Limbu",
|
34
|
+
"Mahajani", "Malayalam", "Oriya", "Sinhala", "Syloti_Nagri",
|
35
|
+
"Takri", "Tamil", "Telugu", "Tirhuta"]
|
36
36
|
```
|
37
37
|
|
38
38
|
## Hints
|
@@ -84,6 +84,7 @@ Cypriot
|
|
84
84
|
Cyrillic
|
85
85
|
Deseret
|
86
86
|
Devanagari
|
87
|
+
Dogra
|
87
88
|
Duployan
|
88
89
|
Egyptian_Hieroglyphs
|
89
90
|
Elbasan
|
@@ -94,9 +95,11 @@ Gothic
|
|
94
95
|
Grantha
|
95
96
|
Greek
|
96
97
|
Gujarati
|
98
|
+
Gunjala_Gondi
|
97
99
|
Gurmukhi
|
98
100
|
Han
|
99
101
|
Hangul
|
102
|
+
Hanifi_Rohingya
|
100
103
|
Hanunoo
|
101
104
|
Hatran
|
102
105
|
Hebrew
|
@@ -125,11 +128,13 @@ Lisu
|
|
125
128
|
Lycian
|
126
129
|
Lydian
|
127
130
|
Mahajani
|
131
|
+
Makasar
|
128
132
|
Malayalam
|
129
133
|
Mandaic
|
130
134
|
Manichaean
|
131
135
|
Marchen
|
132
136
|
Masaram_Gondi
|
137
|
+
Medefaidrin
|
133
138
|
Meetei_Mayek
|
134
139
|
Mende_Kikakui
|
135
140
|
Meroitic_Cursive
|
@@ -152,6 +157,7 @@ Old_Italic
|
|
152
157
|
Old_North_Arabian
|
153
158
|
Old_Permic
|
154
159
|
Old_Persian
|
160
|
+
Old_Sogdian
|
155
161
|
Old_South_Arabian
|
156
162
|
Old_Turkic
|
157
163
|
Oriya
|
@@ -172,6 +178,7 @@ Shavian
|
|
172
178
|
Siddham
|
173
179
|
SignWriting
|
174
180
|
Sinhala
|
181
|
+
Sogdian
|
175
182
|
Sora_Sompeng
|
176
183
|
Soyombo
|
177
184
|
Sundanese
|
@@ -236,6 +243,7 @@ Copt
|
|
236
243
|
Cprt
|
237
244
|
Cyrl
|
238
245
|
Deva
|
246
|
+
Dogr
|
239
247
|
Dsrt
|
240
248
|
Dupl
|
241
249
|
Egyp
|
@@ -243,6 +251,7 @@ Elba
|
|
243
251
|
Ethi
|
244
252
|
Geor
|
245
253
|
Glag
|
254
|
+
Gong
|
246
255
|
Gonm
|
247
256
|
Goth
|
248
257
|
Gran
|
@@ -279,9 +288,11 @@ Lisu
|
|
279
288
|
Lyci
|
280
289
|
Lydi
|
281
290
|
Mahj
|
291
|
+
Maka
|
282
292
|
Mand
|
283
293
|
Mani
|
284
294
|
Marc
|
295
|
+
Medf
|
285
296
|
Mend
|
286
297
|
Merc
|
287
298
|
Mero
|
@@ -315,6 +326,7 @@ Prti
|
|
315
326
|
Qaac
|
316
327
|
Qaai
|
317
328
|
Rjng
|
329
|
+
Rohg
|
318
330
|
Runr
|
319
331
|
Samr
|
320
332
|
Sarb
|
@@ -325,6 +337,8 @@ Shrd
|
|
325
337
|
Sidd
|
326
338
|
Sind
|
327
339
|
Sinh
|
340
|
+
Sogd
|
341
|
+
Sogo
|
328
342
|
Sora
|
329
343
|
Soyo
|
330
344
|
Sund
|
@@ -360,5 +374,5 @@ See [unicode-x](https://github.com/janlelis/unicode-x) for more Unicode related
|
|
360
374
|
|
361
375
|
## MIT License
|
362
376
|
|
363
|
-
- Copyright (C) 2016 Jan Lelis <http://janlelis.com>. Released under the MIT license.
|
377
|
+
- Copyright (C) 2016-2018 Jan Lelis <http://janlelis.com>. Released under the MIT license.
|
364
378
|
- Unicode data: http://www.unicode.org/copyright.html#Exhibit1
|
data/data/scripts.marshal.gz
CHANGED
Binary file
|
@@ -1,7 +1,7 @@
|
|
1
1
|
module Unicode
|
2
2
|
module Scripts
|
3
|
-
VERSION = "1.
|
4
|
-
UNICODE_VERSION = "
|
3
|
+
VERSION = "1.3.0".freeze
|
4
|
+
UNICODE_VERSION = "11.0.0".freeze
|
5
5
|
DATA_DIRECTORY = File.expand_path(File.dirname(__FILE__) + '/../../../data/').freeze
|
6
6
|
INDEX_FILENAME = (DATA_DIRECTORY + '/scripts.marshal.gz').freeze
|
7
7
|
end
|
@@ -1,7 +1,14 @@
|
|
1
|
-
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "zlib"
|
4
|
+
require_relative "constants"
|
2
5
|
|
3
6
|
module Unicode
|
4
7
|
module Scripts
|
5
|
-
|
8
|
+
File.open(INDEX_FILENAME, "rb") do |file|
|
9
|
+
serialized_data = Zlib::GzipReader.new(file).read
|
10
|
+
serialized_data.force_encoding Encoding::BINARY
|
11
|
+
INDEX = Marshal.load(serialized_data)
|
12
|
+
end
|
6
13
|
end
|
7
14
|
end
|
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: 1.3.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Jan Lelis
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2018-
|
11
|
+
date: 2018-06-05 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
|
-
description: "[Unicode
|
13
|
+
description: "[Unicode 11.0.0] 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:
|