kokugo_tagger 0.0.2
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 +7 -0
- data/.gitignore +15 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +31 -0
- data/Rakefile +2 -0
- data/bin/kokugo_tagger +6 -0
- data/kokugo_tagger.gemspec +23 -0
- data/lib/kokugo_tagger/parser.rb +46 -0
- data/lib/kokugo_tagger/tagger.rb +114 -0
- data/lib/kokugo_tagger/version.rb +3 -0
- data/lib/kokugo_tagger.rb +7 -0
- metadata +84 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: b609be62c8aea30eda82811044d1d7ecc6eeb1b4
|
4
|
+
data.tar.gz: 733d6a86cea778492416df55f6e79de5c072a4c3
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 02a682b673b2103320ced6836cb3784c8b9543628840d9aec1033de7a509869449818be930c6c2f06b22ccbfeb4748a2172916a2e849db836dd51b74837ad46d
|
7
|
+
data.tar.gz: b2ba4fe4e4aeeeb83d9a709243479c70298426e86ab771a19eaa28420ddd8dee6b18dcafcedf3b4c5e648a513b7b06cbbeff97352b13b1a0c7b09cb0361eafec
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 Mizuho IMADA
|
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 +1,31 @@
|
|
1
|
+
# KokugoTagger
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'kokugo_tagger'
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install kokugo_tagger
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
TODO: Write usage instructions here
|
24
|
+
|
25
|
+
## Contributing
|
26
|
+
|
27
|
+
1. Fork it ( https://github.com/[my-github-username]/kokugo_tagger/fork )
|
28
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
29
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
30
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
31
|
+
5. Create a new Pull Request
|
data/Rakefile
ADDED
data/bin/kokugo_tagger
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'kokugo_tagger/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "kokugo_tagger"
|
8
|
+
spec.version = KokugoTagger::VERSION
|
9
|
+
spec.authors = ["Mizuho IMADA"]
|
10
|
+
spec.email = ["imadamizuho@gmail.com"]
|
11
|
+
spec.summary = %q{Write a short summary. Required.}
|
12
|
+
spec.description = %q{Write a longer description. Optional.}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0")
|
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
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.7"
|
22
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
23
|
+
end
|
@@ -0,0 +1,46 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
require 'csv'
|
3
|
+
|
4
|
+
module CabochaParser
|
5
|
+
def parse(line)
|
6
|
+
case line.chomp
|
7
|
+
when /^#/
|
8
|
+
return parse_excab(line)
|
9
|
+
when /^\*/
|
10
|
+
return parse_chunk(line)
|
11
|
+
when 'EOS'
|
12
|
+
return {type: 'EOS'}
|
13
|
+
when ''
|
14
|
+
return nil
|
15
|
+
else
|
16
|
+
return parse_token(line)
|
17
|
+
end
|
18
|
+
end
|
19
|
+
def parse_excab(line)
|
20
|
+
null, type, *data = CSV.parse_line(line.chomp, col_sep:' ')
|
21
|
+
case type
|
22
|
+
when 'SEGMENT', 'SEGMENT_S', 'LINK', 'LINK_S'
|
23
|
+
excab = {type: type, name: data[0], start: data[1].to_i, end: data[2].to_i, comment: data[3]}
|
24
|
+
when 'GROUP', 'GROUP_S'
|
25
|
+
excab = {type: type, name: data[0], member: data[1..-2], comment: data[-1]}
|
26
|
+
when 'ATTR'
|
27
|
+
excab = {type: type, name: data[0], value: data[1]}
|
28
|
+
end
|
29
|
+
return excab
|
30
|
+
end
|
31
|
+
def parse_chunk(line)
|
32
|
+
null, id, rel, part, score = line.chomp.split("\s")
|
33
|
+
link, dep = rel[0..-2], rel[-1]
|
34
|
+
head, func = part.split('/')
|
35
|
+
chunk = {type: 'CHUNK', id: id, link: link, dep: dep, head: head, func: func, score: score}
|
36
|
+
return chunk
|
37
|
+
end
|
38
|
+
def parse_token(line)
|
39
|
+
text, attrs, ne = line.chomp.split("\t")
|
40
|
+
attrs = CSV.parse_line(attrs, col_sep:',')
|
41
|
+
pos = attrs[0, 4].delete_if{|item| item.empty?}.join('-')
|
42
|
+
token = {type: 'TOKEN', text: text, ne: ne, pos: pos, ctype: attrs[4], cform: attrs[5]}
|
43
|
+
return token
|
44
|
+
end
|
45
|
+
module_function :parse, :parse_excab, :parse_chunk, :parse_token
|
46
|
+
end
|
@@ -0,0 +1,114 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
require 'csv'
|
3
|
+
|
4
|
+
module KokugoTagger
|
5
|
+
module_function
|
6
|
+
def annotate(file)
|
7
|
+
file.each_line do |line|
|
8
|
+
next unless data = CabochaParser.parse(line)
|
9
|
+
method_name = data[:type].downcase.to_sym
|
10
|
+
method(method_name).call(data) if methods.include?(method_name)
|
11
|
+
puts line
|
12
|
+
end
|
13
|
+
end
|
14
|
+
def chunk(data)
|
15
|
+
@chunks ||= []
|
16
|
+
@chunks << @chunk = data
|
17
|
+
@lpos ||= 0
|
18
|
+
@chunk.update start:@lpos, end:@lpos, text:'', pos:nil, pred:nil, conj:nil
|
19
|
+
end
|
20
|
+
def token(data)
|
21
|
+
@lpos += data[:text].size
|
22
|
+
@chunk[:end] = @lpos
|
23
|
+
@chunk[:text] += data[:text]
|
24
|
+
pos data
|
25
|
+
cform data
|
26
|
+
end
|
27
|
+
def segment_s(data)
|
28
|
+
end
|
29
|
+
def attr(data)
|
30
|
+
end
|
31
|
+
def eos(data)
|
32
|
+
before_eos
|
33
|
+
@chunks.each do |chunk|
|
34
|
+
puts '#! SEGMENT_S bccwj-kok:Bnst %d %d "%s"' % [chunk[:start], chunk[:end], chunk[:text]]
|
35
|
+
puts '#! ATTR bccwj-kok:pred "%s述語"' % chunk[:pos] if chunk[:pred]
|
36
|
+
puts '#! ATTR bccwj-kok:conj "%s"' % chunk[:conj] if chunk[:conj]
|
37
|
+
end
|
38
|
+
@chunks, @chunk, @lpos, @segments = nil
|
39
|
+
end
|
40
|
+
def pos(token)
|
41
|
+
case token[:pos]
|
42
|
+
when /^(名詞|代名詞|接尾辞-名詞的)/
|
43
|
+
@chunk.update pos:'名詞', pred:nil, conj:nil
|
44
|
+
when /^(形状詞|接尾辞-形状詞的)/
|
45
|
+
@chunk.update pos:'形状詞', pred:nil, conj:nil
|
46
|
+
when /^連体詞/
|
47
|
+
@chunk.update pos:'連体詞', pred:nil, conj:'修飾(連体)'
|
48
|
+
when /^副詞/
|
49
|
+
@chunk.update pos:'副詞', pred:nil, conj:'修飾(連用)'
|
50
|
+
when /^接続詞/
|
51
|
+
@chunk.update pos:'接続詞', pred:nil, conj:'接続'
|
52
|
+
when /^感動詞/
|
53
|
+
@chunk.update pos:'感動詞', pred:nil, conj:'独立'
|
54
|
+
when /^(動詞|接尾辞-動詞的)/
|
55
|
+
@chunk.update pos:'動詞', pred:true, conj:nil
|
56
|
+
when /^(形容詞|接尾辞-形容詞的)/
|
57
|
+
@chunk.update pos:'形容詞', pred:true, conj:nil
|
58
|
+
when /^助動詞/
|
59
|
+
@chunk.update pred:true, conj:nil
|
60
|
+
when /^助詞-格助詞/
|
61
|
+
case token[:text]
|
62
|
+
when 'が'
|
63
|
+
@chunk.update conj:'主語'
|
64
|
+
when 'の', 'との', 'という', 'といった'
|
65
|
+
@chunk.update conj:'修飾(連体)'
|
66
|
+
else
|
67
|
+
@chunk.update conj:'補語'
|
68
|
+
end
|
69
|
+
when /^(助詞-副助詞|助詞-係助詞)/
|
70
|
+
@chunk.update conj:'修飾(連用)'
|
71
|
+
when /^助詞-接続詞/
|
72
|
+
@chunk.update pred:true, conj:'接続'
|
73
|
+
when /^助詞-終助詞/
|
74
|
+
@chunk.update pred:true, conj:nil
|
75
|
+
when /^助詞-準体助詞/
|
76
|
+
@chunk.update conj:nil
|
77
|
+
end
|
78
|
+
end
|
79
|
+
def cform(token)
|
80
|
+
case token[:cform]
|
81
|
+
when /^語幹/
|
82
|
+
when /^(未然形|連用形|仮定形|已然形)/
|
83
|
+
@chunk.update conj:'接続'
|
84
|
+
when /^(意志推量形|連体形)/
|
85
|
+
@chunk.update conj:'修飾(連体)'
|
86
|
+
when /^(終止形|命令形)/
|
87
|
+
@chunk.update conj:nil
|
88
|
+
end
|
89
|
+
end
|
90
|
+
def before_eos
|
91
|
+
# 属性を付与できなかった文節に対して、係り受けを利用して属性を補完
|
92
|
+
# 連用成分を受ける文節を述語とみなす
|
93
|
+
@chunks.each do |chunk|
|
94
|
+
chunk[:pred] ||= @chunks.any?{|_chunk| _chunk[:link] == chunk[:id] && _chunk[:conj] =~ /^(主語|補語|修飾\(連用\)|接続)$/}
|
95
|
+
end
|
96
|
+
# 述語にかかる文節を修飾(連用)とみなす
|
97
|
+
@chunks.each do |chunk|
|
98
|
+
chunk[:conj] = '修飾(連用)' if chunk[:conj] == nil && @chunks.any?{|_chunk| _chunk[:id] == chunk[:link] && _chunk[:pred]}
|
99
|
+
end
|
100
|
+
# 述語項構造が付与されている文節を補語にする
|
101
|
+
@chunks.each do |chunk|
|
102
|
+
next if chunk[:link] == '-1' || chunk[:arg] == nil
|
103
|
+
next unless chunk[:conj] == nil || chunk[:conj] == '修飾(連用)'
|
104
|
+
pred = @chunks[chunk[:link].to_i]
|
105
|
+
if chunk[:arg] == 'Ga' and pred[:passive] == nil
|
106
|
+
chunk[:conj] = '主語'
|
107
|
+
elsif chunk[:arg] == 'O' and pred[:passive] == '直接'
|
108
|
+
chunk[:conj] = '主語'
|
109
|
+
else
|
110
|
+
chunk[:conj] = '補語'
|
111
|
+
end
|
112
|
+
end
|
113
|
+
end
|
114
|
+
end
|
metadata
ADDED
@@ -0,0 +1,84 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: kokugo_tagger
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.2
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Mizuho IMADA
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-11-17 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: '1.7'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.7'
|
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
|
+
description: Write a longer description. Optional.
|
42
|
+
email:
|
43
|
+
- imadamizuho@gmail.com
|
44
|
+
executables:
|
45
|
+
- kokugo_tagger
|
46
|
+
extensions: []
|
47
|
+
extra_rdoc_files: []
|
48
|
+
files:
|
49
|
+
- ".gitignore"
|
50
|
+
- Gemfile
|
51
|
+
- LICENSE.txt
|
52
|
+
- README.md
|
53
|
+
- Rakefile
|
54
|
+
- bin/kokugo_tagger
|
55
|
+
- kokugo_tagger.gemspec
|
56
|
+
- lib/kokugo_tagger.rb
|
57
|
+
- lib/kokugo_tagger/parser.rb
|
58
|
+
- lib/kokugo_tagger/tagger.rb
|
59
|
+
- lib/kokugo_tagger/version.rb
|
60
|
+
homepage: ''
|
61
|
+
licenses:
|
62
|
+
- MIT
|
63
|
+
metadata: {}
|
64
|
+
post_install_message:
|
65
|
+
rdoc_options: []
|
66
|
+
require_paths:
|
67
|
+
- lib
|
68
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
69
|
+
requirements:
|
70
|
+
- - ">="
|
71
|
+
- !ruby/object:Gem::Version
|
72
|
+
version: '0'
|
73
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
74
|
+
requirements:
|
75
|
+
- - ">="
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '0'
|
78
|
+
requirements: []
|
79
|
+
rubyforge_project:
|
80
|
+
rubygems_version: 2.4.3
|
81
|
+
signing_key:
|
82
|
+
specification_version: 4
|
83
|
+
summary: Write a short summary. Required.
|
84
|
+
test_files: []
|