unicode_script_detector 0.0.7 → 0.0.8
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/README.md +3 -2
- data/lib/unicode_script_detector/scripts.rb +13 -3
- data/lib/unicode_script_detector/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: b560b59ec3054c3af1a1a91e4c5584ac42b0e1210515b5987657e199200d9ece
|
|
4
|
+
data.tar.gz: c06e00816247f4b2f5899132b9f6a73faceaa3f53e6783f8672ee4d0471cfc25
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: bf6649c6d8b2e1aa2b8aadc33a6b78d8135045182a816bc71e74601c1dd0ced24b95ce69595fc43ca2603912fe1094525ce7ca7c0c8c86f399575c4d5c651845
|
|
7
|
+
data.tar.gz: 8663594198a08c6d6d00c584885e14b077cc12f834fcc10d6b5affc03b738056cfebe7a96ec9877b6ec3fee57dda9a623fc8bbb0137704369a83b055009d7655
|
data/README.md
CHANGED
|
@@ -17,7 +17,7 @@ $ gem install unicode_script_detector
|
|
|
17
17
|
|
|
18
18
|
## Detect all the characters of a string
|
|
19
19
|
```ruby
|
|
20
|
-
UnicodeScriptDetector.detect_characters "Hel6
|
|
20
|
+
UnicodeScriptDetector.detect_characters "Hel6б\t"
|
|
21
21
|
|
|
22
22
|
#Output:
|
|
23
23
|
[
|
|
@@ -25,7 +25,8 @@ UnicodeScriptDetector.detect_characters "Hel6б"
|
|
|
25
25
|
#<UnicodeScriptDetector::Character:0x00007768fefdea10 @char="e", @name="Latin", @script=:Latin>,
|
|
26
26
|
#<UnicodeScriptDetector::Character:0x00007768fefde970 @char="l", @name="Latin", @script=:Latin>,
|
|
27
27
|
#<UnicodeScriptDetector::Character:0x00007768fefde8d0 @char="6", @name="Digit", @script=:Digit>,
|
|
28
|
-
#<UnicodeScriptDetector::Character:0x00007768fefde830 @char="б", @name="Cyrillic", @script=:Cyrillic
|
|
28
|
+
#<UnicodeScriptDetector::Character:0x00007768fefde830 @char="б", @name="Cyrillic", @script=:Cyrillic>,
|
|
29
|
+
#<UnicodeScriptDetector::Character:0x00007768fefde830 @char="\t", @name="Tab", @script=:Tab>
|
|
29
30
|
]
|
|
30
31
|
```
|
|
31
32
|
|
|
@@ -868,15 +868,25 @@ module UnicodeScriptDetector
|
|
|
868
868
|
},
|
|
869
869
|
|
|
870
870
|
#Special characters
|
|
871
|
+
{
|
|
872
|
+
script: :New_Line,
|
|
873
|
+
name: "New Line",
|
|
874
|
+
regex: /\n/,
|
|
875
|
+
},
|
|
876
|
+
{
|
|
877
|
+
script: :Tab,
|
|
878
|
+
name: "Tab",
|
|
879
|
+
regex: /\t/,
|
|
880
|
+
},
|
|
871
881
|
{
|
|
872
882
|
script: :Whitespace,
|
|
873
883
|
name: "Whitespace",
|
|
874
|
-
regex: /\s
|
|
884
|
+
regex: /\s/,
|
|
875
885
|
},
|
|
876
886
|
{
|
|
877
887
|
script: :Digit,
|
|
878
888
|
name: "Digit",
|
|
879
|
-
regex: /\d
|
|
889
|
+
regex: /\d/,
|
|
880
890
|
},
|
|
881
891
|
{
|
|
882
892
|
script: :Emoji,
|
|
@@ -886,7 +896,7 @@ module UnicodeScriptDetector
|
|
|
886
896
|
{
|
|
887
897
|
script: :Punctuation,
|
|
888
898
|
name: "Punctuation",
|
|
889
|
-
regex: /[[:punct:]]
|
|
899
|
+
regex: /[[:punct:]]/,
|
|
890
900
|
},
|
|
891
901
|
{
|
|
892
902
|
script: :Common,
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: unicode_script_detector
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.8
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- David Arendsen
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2026-01-
|
|
11
|
+
date: 2026-01-05 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: zeitwerk
|