light-mecab 0.0.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +47 -0
- data/Rakefile +1 -0
- data/lib/light-mecab/version.rb +3 -0
- data/lib/light-mecab.rb +63 -0
- data/lib/locale/morpheme.yml +9 -0
- data/light-mecab.gemspec +20 -0
- data/test/test_morpheme.rb +56 -0
- metadata +55 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: f71e38a8bffc439780889b8159cc4eb0edfb4ddc
|
4
|
+
data.tar.gz: c2b6da744a3da6bf59838437cf9af4d7919d3107
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 5ba527248b849472c1e4d3ea9d3070c2df322e6a605c43ea40181e14b9e7f427f994d09b00134959f8b88665002dcb1f6bb792d99c8c9386eb03991caf43a9f9
|
7
|
+
data.tar.gz: 3439477c732e5c94bfe65cc1409c75e0d81765c973bff8c809374ee2563a406ba11e36c89d44476d87121961747ef3455c45c1d33e5d85bc9d05dd11d7e6a9d5
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Kei Tsuchiya
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,47 @@
|
|
1
|
+
# LightMecab
|
2
|
+
|
3
|
+
LightMecabは,mecab-rubyをラッピングすることで,より簡単に形態素解析を行うgemである.
|
4
|
+
|
5
|
+
## Environment
|
6
|
+
|
7
|
+
MeCabおよびmecab-rubyが動作する環境が必要.
|
8
|
+
|
9
|
+
## Installation
|
10
|
+
|
11
|
+
Gemfileに以下を記述する.
|
12
|
+
|
13
|
+
gem 'light-mecab'
|
14
|
+
|
15
|
+
その後,
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
を実行.
|
20
|
+
|
21
|
+
以下のコマンドでもインストール可能.
|
22
|
+
|
23
|
+
$ gem install light-mecab
|
24
|
+
|
25
|
+
## Usage
|
26
|
+
例えば「太郎はこの本を二郎を見た女性に渡した。」という文に含まれる名詞は,
|
27
|
+
|
28
|
+
```ruby
|
29
|
+
require 'light-mecab'
|
30
|
+
sentence = '太郎はこの本を二郎を見た女性に渡した。'
|
31
|
+
LightMecab::Morpheme.new(sentence).noun
|
32
|
+
```
|
33
|
+
によって取得できる(返り値はString型の配列).
|
34
|
+
|
35
|
+
その他の品詞(形態素)を取得するメソッド名は,以下を参照.
|
36
|
+
|
37
|
+
lib/locale/morpheme.yml
|
38
|
+
|
39
|
+
|
40
|
+
|
41
|
+
## Contributing
|
42
|
+
|
43
|
+
1. Fork it
|
44
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
45
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
46
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
47
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/lib/light-mecab.rb
ADDED
@@ -0,0 +1,63 @@
|
|
1
|
+
require 'light-mecab/version'
|
2
|
+
require 'MeCab'
|
3
|
+
require 'yaml'
|
4
|
+
|
5
|
+
module LightMecab
|
6
|
+
class Morpheme
|
7
|
+
@@i18n = ::YAML.load_file(File.expand_path(File.join(__FILE__, '..', 'locale', 'morpheme.yml')))
|
8
|
+
|
9
|
+
class << self
|
10
|
+
# @param text [String]
|
11
|
+
# @return [Array <MeCab::Node>]
|
12
|
+
def analyze(text)
|
13
|
+
nodes = []
|
14
|
+
node = ::MeCab::Tagger.new.parseToNode(text)
|
15
|
+
while node
|
16
|
+
nodes << node
|
17
|
+
node = node.next
|
18
|
+
end
|
19
|
+
nodes.shift
|
20
|
+
nodes.pop
|
21
|
+
nodes
|
22
|
+
end
|
23
|
+
|
24
|
+
# @param key [String or Symbol]
|
25
|
+
# @return [String]
|
26
|
+
def i18n(key)
|
27
|
+
key.is_a?(Symbol) ? @@i18n[key.to_s] : @@i18n[key]
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
# @param text [String]
|
32
|
+
def initialize(text)
|
33
|
+
@nodes = self.class.analyze(text)
|
34
|
+
end
|
35
|
+
|
36
|
+
# @return [Integer]
|
37
|
+
def count
|
38
|
+
@nodes.size
|
39
|
+
end
|
40
|
+
|
41
|
+
# @param method_name [Symbol]
|
42
|
+
def method_missing(method_name)
|
43
|
+
if !self.class.i18n(method_name)
|
44
|
+
raise NoMethodError
|
45
|
+
end
|
46
|
+
extract(self.class.i18n(method_name))
|
47
|
+
end
|
48
|
+
|
49
|
+
private
|
50
|
+
|
51
|
+
# @param name [String]
|
52
|
+
# @return [Array <String>]
|
53
|
+
def extract(name)
|
54
|
+
morpheme = []
|
55
|
+
@nodes.each do |node|
|
56
|
+
if name == node.feature.split(',').first.force_encoding('UTF-8')
|
57
|
+
morpheme << node.surface.force_encoding('UTF-8')
|
58
|
+
end
|
59
|
+
end
|
60
|
+
morpheme
|
61
|
+
end
|
62
|
+
end
|
63
|
+
end
|
data/light-mecab.gemspec
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'light-mecab/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = 'light-mecab'
|
8
|
+
spec.version = LightMecab::VERSION
|
9
|
+
spec.authors = ['Kei Tsuchiya']
|
10
|
+
spec.email = ['kei.tsuchiya86@gmail.com']
|
11
|
+
spec.description = %q{Execute morphological analysis by MeCab}
|
12
|
+
spec.summary = %q{Wrapping mecab-ruby to execute morphological analysis easlily}
|
13
|
+
spec.homepage = 'https://github.com/kei500/light-mecab'
|
14
|
+
spec.license = 'MIT'
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ['lib']
|
20
|
+
end
|
@@ -0,0 +1,56 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
$: << File.expand_path(File.join(__FILE__, '..', '..', 'lib'))
|
3
|
+
|
4
|
+
require 'test-unit'
|
5
|
+
require 'light-mecab'
|
6
|
+
|
7
|
+
class TC_LightMecab_Morpheme < Test::Unit::TestCase
|
8
|
+
def setup
|
9
|
+
@sentence = 'そして太郎はこの本を二郎を見た美しい女性に渡した。'
|
10
|
+
@morpheme = LightMecab::Morpheme.new(@sentence)
|
11
|
+
end
|
12
|
+
|
13
|
+
def test_count
|
14
|
+
assert_equal(17, @morpheme.count)
|
15
|
+
end
|
16
|
+
|
17
|
+
def test_method_missing_noun
|
18
|
+
assert_equal(['太郎', '本', '二', '郎', '女性'], @morpheme.noun)
|
19
|
+
end
|
20
|
+
|
21
|
+
def test_method_missing_verb
|
22
|
+
assert_equal(['見', '渡し'], @morpheme.verb)
|
23
|
+
end
|
24
|
+
|
25
|
+
def test_method_missing_aux_verb
|
26
|
+
assert_equal(['た', 'た'], @morpheme.aux_verb)
|
27
|
+
end
|
28
|
+
|
29
|
+
def test_method_missing_adjective
|
30
|
+
assert_equal(['美しい'], @morpheme.adjective)
|
31
|
+
end
|
32
|
+
|
33
|
+
def test_method_missing_conjunction
|
34
|
+
assert_equal(['そして'], @morpheme.conjunction)
|
35
|
+
end
|
36
|
+
|
37
|
+
def test_method_missing_interjection
|
38
|
+
assert_equal([], @morpheme.interjection)
|
39
|
+
end
|
40
|
+
|
41
|
+
def test_method_missing_particle
|
42
|
+
assert_equal(['は', 'を', 'を', 'に'], @morpheme.particle)
|
43
|
+
end
|
44
|
+
|
45
|
+
def test_method_missing_ad_adjective
|
46
|
+
assert_equal(['この'], @morpheme.ad_adjective)
|
47
|
+
end
|
48
|
+
|
49
|
+
def test_method_missing_symbol
|
50
|
+
assert_equal(['。'], @morpheme.symbol)
|
51
|
+
end
|
52
|
+
|
53
|
+
def test_method_missing_hoge
|
54
|
+
assert_raise{@morpheme.hoge}
|
55
|
+
end
|
56
|
+
end
|
metadata
ADDED
@@ -0,0 +1,55 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: light-mecab
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.2
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Kei Tsuchiya
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-10-03 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description: Execute morphological analysis by MeCab
|
14
|
+
email:
|
15
|
+
- kei.tsuchiya86@gmail.com
|
16
|
+
executables: []
|
17
|
+
extensions: []
|
18
|
+
extra_rdoc_files: []
|
19
|
+
files:
|
20
|
+
- .gitignore
|
21
|
+
- Gemfile
|
22
|
+
- LICENSE.txt
|
23
|
+
- README.md
|
24
|
+
- Rakefile
|
25
|
+
- lib/light-mecab.rb
|
26
|
+
- lib/light-mecab/version.rb
|
27
|
+
- lib/locale/morpheme.yml
|
28
|
+
- light-mecab.gemspec
|
29
|
+
- test/test_morpheme.rb
|
30
|
+
homepage: https://github.com/kei500/light-mecab
|
31
|
+
licenses:
|
32
|
+
- MIT
|
33
|
+
metadata: {}
|
34
|
+
post_install_message:
|
35
|
+
rdoc_options: []
|
36
|
+
require_paths:
|
37
|
+
- lib
|
38
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
39
|
+
requirements:
|
40
|
+
- - '>='
|
41
|
+
- !ruby/object:Gem::Version
|
42
|
+
version: '0'
|
43
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
requirements: []
|
49
|
+
rubyforge_project:
|
50
|
+
rubygems_version: 2.0.2
|
51
|
+
signing_key:
|
52
|
+
specification_version: 4
|
53
|
+
summary: Wrapping mecab-ruby to execute morphological analysis easlily
|
54
|
+
test_files:
|
55
|
+
- test/test_morpheme.rb
|