wordcuta 0.3.0 → 0.4.0
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/LICENSE +503 -158
- data/README.md +11 -1
- data/wordcuta.gemspec +7 -6
- metadata +19 -10
- data/Gemfile +0 -5
- data/data/thai-dix.txt +0 -15890
data/README.md
CHANGED
@@ -5,11 +5,21 @@
|
|
5
5
|
* Install [wordcutw](https://github.com/veer66/wordcutw)
|
6
6
|
* gem install wordcuta
|
7
7
|
|
8
|
+
## Prerequisite
|
9
|
+
|
10
|
+
### Dictionaries and rules
|
11
|
+
|
12
|
+
```Shell
|
13
|
+
wget https://codeberg.org/mekong-lang/mekong-lang-data/archive/main.tar.gz -O - | tar -xzvf -
|
14
|
+
```
|
15
|
+
|
8
16
|
## Example
|
9
17
|
|
10
18
|
```Ruby
|
11
19
|
require 'wordcuta'
|
12
|
-
|
20
|
+
|
21
|
+
wc = WordcutA::Wordcut.new("mekong-lang-data/dictionaries/mixed/chamkho-dict.txt",
|
22
|
+
"mekong-lang-data/cluster-rules/thai_cluster_rules.txt")
|
13
23
|
p wc.put_delimiters('กากาก้า', '|')
|
14
24
|
p wc.into_strings('กากา')
|
15
25
|
p wc.into_ranges('กากา')
|
data/wordcuta.gemspec
CHANGED
@@ -1,12 +1,13 @@
|
|
1
1
|
Gem::Specification.new do |s|
|
2
|
-
s.name =
|
3
|
-
s.version =
|
4
|
-
s.authors = [
|
5
|
-
s.email = [
|
6
|
-
s.licenses = [
|
2
|
+
s.name = "wordcuta"
|
3
|
+
s.version = "0.4.0"
|
4
|
+
s.authors = ["Vee Satayamas"]
|
5
|
+
s.email = ["vsatayamas@gmail.com"]
|
6
|
+
s.licenses = ["BSD-2-Clause"]
|
7
7
|
s.description = "A Ruby wrapper of wordcut-engine - a word segmentation tools for ASEAN languages, i.e. Khmer, Lao, Myanmar, and Thai"
|
8
8
|
s.homepage = "https://codeberg.org/mekong/wordcuta"
|
9
9
|
s.required_ruby_version = Gem::Requirement.new(">= 2.3.0")
|
10
10
|
s.summary = "A word segmentation tools for ASEAN languages wrapper for Ruby"
|
11
|
-
s.files = %w(README.md LICENSE
|
11
|
+
s.files = %w(README.md LICENSE wordcuta.gemspec lib/wordcuta.rb)
|
12
|
+
s.add_dependency "ffi", "~> 1.15"
|
12
13
|
end
|
metadata
CHANGED
@@ -1,15 +1,28 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: wordcuta
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.4.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Vee Satayamas
|
8
|
-
autorequire:
|
9
8
|
bindir: bin
|
10
9
|
cert_chain: []
|
11
|
-
date:
|
12
|
-
dependencies:
|
10
|
+
date: 1980-01-02 00:00:00.000000000 Z
|
11
|
+
dependencies:
|
12
|
+
- !ruby/object:Gem::Dependency
|
13
|
+
name: ffi
|
14
|
+
requirement: !ruby/object:Gem::Requirement
|
15
|
+
requirements:
|
16
|
+
- - "~>"
|
17
|
+
- !ruby/object:Gem::Version
|
18
|
+
version: '1.15'
|
19
|
+
type: :runtime
|
20
|
+
prerelease: false
|
21
|
+
version_requirements: !ruby/object:Gem::Requirement
|
22
|
+
requirements:
|
23
|
+
- - "~>"
|
24
|
+
- !ruby/object:Gem::Version
|
25
|
+
version: '1.15'
|
13
26
|
description: A Ruby wrapper of wordcut-engine - a word segmentation tools for ASEAN
|
14
27
|
languages, i.e. Khmer, Lao, Myanmar, and Thai
|
15
28
|
email:
|
@@ -18,17 +31,14 @@ executables: []
|
|
18
31
|
extensions: []
|
19
32
|
extra_rdoc_files: []
|
20
33
|
files:
|
21
|
-
- Gemfile
|
22
34
|
- LICENSE
|
23
35
|
- README.md
|
24
|
-
- data/thai-dix.txt
|
25
36
|
- lib/wordcuta.rb
|
26
37
|
- wordcuta.gemspec
|
27
38
|
homepage: https://codeberg.org/mekong/wordcuta
|
28
39
|
licenses:
|
29
|
-
-
|
40
|
+
- BSD-2-Clause
|
30
41
|
metadata: {}
|
31
|
-
post_install_message:
|
32
42
|
rdoc_options: []
|
33
43
|
require_paths:
|
34
44
|
- lib
|
@@ -43,8 +53,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
43
53
|
- !ruby/object:Gem::Version
|
44
54
|
version: '0'
|
45
55
|
requirements: []
|
46
|
-
rubygems_version: 3.
|
47
|
-
signing_key:
|
56
|
+
rubygems_version: 3.7.1
|
48
57
|
specification_version: 4
|
49
58
|
summary: A word segmentation tools for ASEAN languages wrapper for Ruby
|
50
59
|
test_files: []
|