ar-stemmer 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/.travis.yml +4 -0
- data/CODE_OF_CONDUCT.md +49 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +33 -0
- data/Rakefile +10 -0
- data/ar-stemmer.gemspec +25 -0
- data/lib/ar-stemmer.rb +1 -0
- data/lib/ar_stemmer.rb +86 -0
- metadata +110 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 00e718669bea040030d76fd7255a4100cf723b04
|
4
|
+
data.tar.gz: 29b082c0c16c487a3b4de412f4aa23a11ddd43e6
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: d88e6f82ce53bf77093885bc6b7b5b8539eee14db8206e6a535baf6139afab1084cbeba92ac61f5cce74e09ecd3efe3b0018f5f2235ce1e35ced94c4f597bf3e
|
7
|
+
data.tar.gz: 830e35dcae938f5c8f1a678df5b1ab3eaeb7edf7d4f071acd376e2cf373d285174983a055a7e4aed4dfb70ce5bb0a9e0b97c136e8cd651d69bb276a0444c7571
|
data/.gitignore
ADDED
data/.travis.yml
ADDED
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,49 @@
|
|
1
|
+
# Contributor Code of Conduct
|
2
|
+
|
3
|
+
As contributors and maintainers of this project, and in the interest of
|
4
|
+
fostering an open and welcoming community, we pledge to respect all people who
|
5
|
+
contribute through reporting issues, posting feature requests, updating
|
6
|
+
documentation, submitting pull requests or patches, and other activities.
|
7
|
+
|
8
|
+
We are committed to making participation in this project a harassment-free
|
9
|
+
experience for everyone, regardless of level of experience, gender, gender
|
10
|
+
identity and expression, sexual orientation, disability, personal appearance,
|
11
|
+
body size, race, ethnicity, age, religion, or nationality.
|
12
|
+
|
13
|
+
Examples of unacceptable behavior by participants include:
|
14
|
+
|
15
|
+
* The use of sexualized language or imagery
|
16
|
+
* Personal attacks
|
17
|
+
* Trolling or insulting/derogatory comments
|
18
|
+
* Public or private harassment
|
19
|
+
* Publishing other's private information, such as physical or electronic
|
20
|
+
addresses, without explicit permission
|
21
|
+
* Other unethical or unprofessional conduct
|
22
|
+
|
23
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
24
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
25
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
26
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
27
|
+
threatening, offensive, or harmful.
|
28
|
+
|
29
|
+
By adopting this Code of Conduct, project maintainers commit themselves to
|
30
|
+
fairly and consistently applying these principles to every aspect of managing
|
31
|
+
this project. Project maintainers who do not follow or enforce the Code of
|
32
|
+
Conduct may be permanently removed from the project team.
|
33
|
+
|
34
|
+
This code of conduct applies both within project spaces and in public spaces
|
35
|
+
when an individual is representing the project or its community.
|
36
|
+
|
37
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
38
|
+
reported by contacting a project maintainer at tomoya@cookpad.com. All
|
39
|
+
complaints will be reviewed and investigated and will result in a response that
|
40
|
+
is deemed necessary and appropriate to the circumstances. Maintainers are
|
41
|
+
obligated to maintain confidentiality with regard to the reporter of an
|
42
|
+
incident.
|
43
|
+
|
44
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage],
|
45
|
+
version 1.3.0, available at
|
46
|
+
[http://contributor-covenant.org/version/1/3/0/][version]
|
47
|
+
|
48
|
+
[homepage]: http://contributor-covenant.org
|
49
|
+
[version]: http://contributor-covenant.org/version/1/3/0/
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2016 Tomoya Hirano
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,33 @@
|
|
1
|
+
# Ar-Stemmer
|
2
|
+
|
3
|
+
Ar-Stemmer is pure Ruby port of ArabicStemmer Java class from Lucene.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'ar-stemmer'
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install ar-stemmer
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
```
|
24
|
+
require 'ar-stemmer'
|
25
|
+
|
26
|
+
ArStemmer.stem("الدونات")
|
27
|
+
# =>
|
28
|
+
"دونات"
|
29
|
+
```
|
30
|
+
|
31
|
+
## License
|
32
|
+
|
33
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
data/Rakefile
ADDED
data/ar-stemmer.gemspec
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
|
5
|
+
Gem::Specification.new do |spec|
|
6
|
+
spec.name = "ar-stemmer"
|
7
|
+
spec.version = "0.1.0"
|
8
|
+
spec.authors = ["Tomoya Hirano"]
|
9
|
+
spec.email = ["hiranotomoya@gmail.com"]
|
10
|
+
|
11
|
+
spec.summary = "Ar-Stemmer is pure Ruby port of ArabicStemmer Java class from Lucene."
|
12
|
+
spec.description = "Ar-Stemmer is pure Ruby port of ArabicStemmer Java class from Lucene."
|
13
|
+
spec.homepage = "https://github.com/tomoya55/ar-stemmer"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
17
|
+
spec.bindir = "exe"
|
18
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.11"
|
22
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
23
|
+
spec.add_development_dependency "minitest", "~> 5.0"
|
24
|
+
spec.add_development_dependency "pry"
|
25
|
+
end
|
data/lib/ar-stemmer.rb
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "ar_stemmer"
|
data/lib/ar_stemmer.rb
ADDED
@@ -0,0 +1,86 @@
|
|
1
|
+
# ArStemmer is a pure ruby port of Lucene's ArabicStemmer class
|
2
|
+
#
|
3
|
+
# https://github.com/apache/lucene-solr/blob/master/lucene/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicStemmer.java
|
4
|
+
class ArStemmer
|
5
|
+
|
6
|
+
ALEF = "\u0627"
|
7
|
+
BEH = "\u0628"
|
8
|
+
TEH_MARBUTA = "\u0629"
|
9
|
+
TEH = "\u062A"
|
10
|
+
FEH = "\u0641"
|
11
|
+
KAF = "\u0643"
|
12
|
+
LAM = "\u0644"
|
13
|
+
NOON = "\u0646"
|
14
|
+
HEH = "\u0647"
|
15
|
+
WAW = "\u0648"
|
16
|
+
YEH = "\u064A"
|
17
|
+
|
18
|
+
PREFIXES = [
|
19
|
+
ALEF + LAM,
|
20
|
+
WAW + ALEF + LAM,
|
21
|
+
BEH + ALEF + LAM,
|
22
|
+
KAF + ALEF + LAM,
|
23
|
+
FEH + ALEF + LAM,
|
24
|
+
LAM + LAM,
|
25
|
+
WAW
|
26
|
+
]
|
27
|
+
|
28
|
+
SUFFIXES = [
|
29
|
+
HEH + ALEF,
|
30
|
+
ALEF + NOON,
|
31
|
+
ALEF + TEH,
|
32
|
+
WAW + NOON,
|
33
|
+
YEH + NOON,
|
34
|
+
YEH + HEH,
|
35
|
+
YEH + TEH_MARBUTA,
|
36
|
+
HEH,
|
37
|
+
TEH_MARBUTA,
|
38
|
+
YEH
|
39
|
+
]
|
40
|
+
|
41
|
+
def self.stem(word)
|
42
|
+
new(word).stem
|
43
|
+
end
|
44
|
+
|
45
|
+
attr_reader :word
|
46
|
+
|
47
|
+
def initialize(word)
|
48
|
+
@word = word.dup
|
49
|
+
end
|
50
|
+
|
51
|
+
def stem
|
52
|
+
stem_prefix
|
53
|
+
stem_suffix
|
54
|
+
word
|
55
|
+
end
|
56
|
+
|
57
|
+
def stem_prefix
|
58
|
+
PREFIXES.each do |prefix|
|
59
|
+
@word = word[prefix.length .. -1] if starts_with_check_length(word, prefix)
|
60
|
+
end
|
61
|
+
end
|
62
|
+
|
63
|
+
def stem_suffix
|
64
|
+
SUFFIXES.each do |suffix|
|
65
|
+
@word = word[0 .. -(suffix.length + 1)] if ends_with_check_length(word, suffix)
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
69
|
+
def starts_with_check_length(word, prefix)
|
70
|
+
if prefix.length == 1 && word.length < 4 # wa- prefix requires at least 3 characters
|
71
|
+
false
|
72
|
+
elsif word.length < prefix.length + 2
|
73
|
+
false
|
74
|
+
else
|
75
|
+
word.start_with?(prefix)
|
76
|
+
end
|
77
|
+
end
|
78
|
+
|
79
|
+
def ends_with_check_length(word, suffix)
|
80
|
+
if word.length < suffix.length + 2
|
81
|
+
false
|
82
|
+
else
|
83
|
+
word.end_with?(suffix)
|
84
|
+
end
|
85
|
+
end
|
86
|
+
end
|
metadata
ADDED
@@ -0,0 +1,110 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: ar-stemmer
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Tomoya Hirano
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-02-08 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.11'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.11'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: minitest
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '5.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '5.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: pry
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
description: Ar-Stemmer is pure Ruby port of ArabicStemmer Java class from Lucene.
|
70
|
+
email:
|
71
|
+
- hiranotomoya@gmail.com
|
72
|
+
executables: []
|
73
|
+
extensions: []
|
74
|
+
extra_rdoc_files: []
|
75
|
+
files:
|
76
|
+
- ".gitignore"
|
77
|
+
- ".travis.yml"
|
78
|
+
- CODE_OF_CONDUCT.md
|
79
|
+
- Gemfile
|
80
|
+
- LICENSE.txt
|
81
|
+
- README.md
|
82
|
+
- Rakefile
|
83
|
+
- ar-stemmer.gemspec
|
84
|
+
- lib/ar-stemmer.rb
|
85
|
+
- lib/ar_stemmer.rb
|
86
|
+
homepage: https://github.com/tomoya55/ar-stemmer
|
87
|
+
licenses:
|
88
|
+
- MIT
|
89
|
+
metadata: {}
|
90
|
+
post_install_message:
|
91
|
+
rdoc_options: []
|
92
|
+
require_paths:
|
93
|
+
- lib
|
94
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
95
|
+
requirements:
|
96
|
+
- - ">="
|
97
|
+
- !ruby/object:Gem::Version
|
98
|
+
version: '0'
|
99
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - ">="
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '0'
|
104
|
+
requirements: []
|
105
|
+
rubyforge_project:
|
106
|
+
rubygems_version: 2.4.5
|
107
|
+
signing_key:
|
108
|
+
specification_version: 4
|
109
|
+
summary: Ar-Stemmer is pure Ruby port of ArabicStemmer Java class from Lucene.
|
110
|
+
test_files: []
|