cab2xml 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/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +39 -0
- data/Rakefile +2 -0
- data/bin/cab2xml +5 -0
- data/bin/console +14 -0
- data/bin/setup +7 -0
- data/cab2xml.gemspec +32 -0
- data/lib/cab2xml/converter.rb +134 -0
- data/lib/cab2xml/version.rb +3 -0
- data/lib/cab2xml.rb +6 -0
- metadata +99 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 746106cafaf3c1f9241df12fe24e73bb4583d8b6
|
4
|
+
data.tar.gz: b4dfe536cb85cf531092fe9053f2b563c1fa4114
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 23f643b1a499bc6b3b49c2fec603825e2eee6ebf09da77c2310d6c3c5cf1c607bce616166212337172c1f3ff4c9617a3fbafd3afc4c5d802952ca64bfd6db8a0
|
7
|
+
data.tar.gz: 2c989bd371b647056b79f1a25338097fdab688f47a9a582cc4fdc8e975c21e8bbcaaf5460c32c4f857fa53c66fe6a84852b55a637dc96052ca0f2988dbf598b5
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2015 Mizuho IMADA
|
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 +1,39 @@
|
|
1
|
+
# Cab2xml
|
2
|
+
|
3
|
+
Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/cab2xml`. To experiment with that code, run `bin/console` for an interactive prompt.
|
4
|
+
|
5
|
+
TODO: Delete this and the text above, and describe your gem
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'cab2xml'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install cab2xml
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
$ cab2xml your.cabocha > your.xml
|
26
|
+
|
27
|
+
## Development
|
28
|
+
|
29
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `bin/console` for an interactive prompt that will allow you to experiment.
|
30
|
+
|
31
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release` to create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
32
|
+
|
33
|
+
## Contributing
|
34
|
+
|
35
|
+
1. Fork it ( https://github.com/[my-github-username]/cab2xml/fork )
|
36
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
37
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
38
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
39
|
+
5. Create a new Pull Request
|
data/Rakefile
ADDED
data/bin/cab2xml
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "cab2xml"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start
|
data/bin/setup
ADDED
data/cab2xml.gemspec
ADDED
@@ -0,0 +1,32 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'cab2xml/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "cab2xml"
|
8
|
+
spec.version = Cab2xml::VERSION
|
9
|
+
spec.authors = ["Mizuho IMADA"]
|
10
|
+
spec.email = ["imadamizuho@gmail.com"]
|
11
|
+
|
12
|
+
if spec.respond_to?(:metadata)
|
13
|
+
spec.metadata['allowed_push_host'] = "https://rubygems.org"
|
14
|
+
end
|
15
|
+
|
16
|
+
spec.summary = %q{Cabocha to XML.}
|
17
|
+
spec.description = %q{Cabocha to XML.}
|
18
|
+
spec.homepage = ""
|
19
|
+
spec.license = "MIT"
|
20
|
+
|
21
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
22
|
+
# spec.bindir = "exe"
|
23
|
+
# spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
24
|
+
spec.bindir = "lib"
|
25
|
+
spec.executables = ["cab2xml"]
|
26
|
+
spec.require_paths = ["lib"]
|
27
|
+
|
28
|
+
spec.add_dependency "nokogiri"
|
29
|
+
|
30
|
+
spec.add_development_dependency "bundler", "~> 1.8"
|
31
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
32
|
+
end
|
@@ -0,0 +1,134 @@
|
|
1
|
+
require "nokogiri"
|
2
|
+
require "csv"
|
3
|
+
|
4
|
+
module Cab2xml
|
5
|
+
class Converter
|
6
|
+
attr_accessor :attr_mode, :token_format
|
7
|
+
def initialize
|
8
|
+
@attr_mode = :attr
|
9
|
+
@token_format = :mecab_unidic
|
10
|
+
end
|
11
|
+
def parse(file)
|
12
|
+
@xml, @sen, @senid = nil
|
13
|
+
file.set_encoding 'UTF-8'
|
14
|
+
file.each_line do |line|
|
15
|
+
line.chomp!
|
16
|
+
case line
|
17
|
+
when ''
|
18
|
+
# ignore
|
19
|
+
when /^##/
|
20
|
+
# comment line
|
21
|
+
when /^#!/
|
22
|
+
parse_extended_tag line
|
23
|
+
else
|
24
|
+
parse_cabocha_tag line
|
25
|
+
end
|
26
|
+
end
|
27
|
+
return @xml
|
28
|
+
end
|
29
|
+
def create_xml(mode)
|
30
|
+
# mode = {:corpora|:document}
|
31
|
+
@xml = Nokogiri::XML("<#{mode}/>")
|
32
|
+
@xml.encoding = 'UTF-8'
|
33
|
+
@corpora = @xml.root if mode == :corpora
|
34
|
+
@doc = @xml.root if mode == :document
|
35
|
+
end
|
36
|
+
def add_node(parent, format, data)
|
37
|
+
parent << (format % data)
|
38
|
+
@last = parent.children.last
|
39
|
+
return @last
|
40
|
+
end
|
41
|
+
def check_namespace(key)
|
42
|
+
return unless key =~ /:/
|
43
|
+
namespace, key = key.split(':', 2)
|
44
|
+
@namespaces ||= {}
|
45
|
+
return if @namespaces[namespace]
|
46
|
+
@namespaces[namespace] = true
|
47
|
+
@doc.add_namespace namespace, 'http://www.ninjal.ac.jp/corpus_center/bccwj/' + namespace
|
48
|
+
end
|
49
|
+
def parse_extended_tag(line)
|
50
|
+
null, label, *data = CSV.parse_line(line, :col_sep => "\s")
|
51
|
+
data.map!{|item| item.encode(:xml => :text)}
|
52
|
+
case label
|
53
|
+
when 'DOCID'
|
54
|
+
create_xml(:corpora) unless @xml
|
55
|
+
format = '<DOCID id=%d>%s</DOCID>'
|
56
|
+
@docid = add_node(@corpora, format, data)
|
57
|
+
when 'SENTENCETAGID'
|
58
|
+
format = '<SENTENCETAGID id=%d>%s</SENTENCETAGID>'
|
59
|
+
@sentencetagid = add_node(@corpora, format, data)
|
60
|
+
when 'DOC'
|
61
|
+
format = '<document id="%d"/>'
|
62
|
+
@doc = add_node(@corpora, format, data)
|
63
|
+
@senid = 0
|
64
|
+
when 'ATTR'
|
65
|
+
case @attr_mode
|
66
|
+
when :node
|
67
|
+
format = '<ATTR Key="%s" Value="%s"/>'
|
68
|
+
@attr = add_node(@last, format, data)
|
69
|
+
when :attr
|
70
|
+
key, value = data
|
71
|
+
check_namespace key
|
72
|
+
@last[key] = value
|
73
|
+
end
|
74
|
+
when 'SEGMENT'
|
75
|
+
format = '<SEGMENT TagName="%s" StartGPos="%s" EndGPos="%s" Comments="%s"/>'
|
76
|
+
@seg = add_node(@doc, format, data)
|
77
|
+
when 'SEGMENT_S'
|
78
|
+
format = '<SEGMENT_S TagName="%s" StartLPos="%s" EndLPos="%s" Comments="%s"/>'
|
79
|
+
@seg = add_node(@sen, format, data)
|
80
|
+
when 'LINK'
|
81
|
+
format = '<LINK TagName="%s" FromSegNo="%s" EndSegNo="%s" Comments="%s"/>'
|
82
|
+
@link = add_node(@doc, format, data)
|
83
|
+
when 'LINK_S'
|
84
|
+
format = '<LINK_S TagName="%s" FromSegSNo="%s" EndSegSNo="%s" Comments="%s"/>'
|
85
|
+
@link = add_node(@sen, format, data)
|
86
|
+
when 'GROUP'
|
87
|
+
format = '<GROUP TagName="%s" SegNo="%s" Comments="%s"/>'
|
88
|
+
data = [data[0], data[1..-2].join(','), data[-1]]
|
89
|
+
@group = add_node(@doc, format, data)
|
90
|
+
when 'GROUP_S'
|
91
|
+
format = '<GROUP_S TagName="%s" SegSNo="%s" Comments="%s"/>'
|
92
|
+
data = [data[0], data[1..-2].join(','), data[-1]]
|
93
|
+
@group = add_node(@sen, format, data)
|
94
|
+
end
|
95
|
+
end
|
96
|
+
def parse_cabocha_tag(line)
|
97
|
+
case line
|
98
|
+
when /^\*/
|
99
|
+
create_xml(:document) unless @xml
|
100
|
+
unless @sen
|
101
|
+
@sen = add_node(@doc, '<sentence id="%d"/>', @senid ||= 0)
|
102
|
+
@senid += 1
|
103
|
+
@tokid = 0
|
104
|
+
end
|
105
|
+
null, id, dep, headfunc, score = line.split(' ')
|
106
|
+
link, rel = dep[0..-2], dep[-1]
|
107
|
+
head, func = headfunc.split('/')
|
108
|
+
data = [id, link, rel, head, func, score]
|
109
|
+
format = '<chunk id="%d" link="%d" rel="%s" head="%d" func="%d" score="%s"/>'
|
110
|
+
@chunk = add_node(@sen, format, data)
|
111
|
+
when 'EOS'
|
112
|
+
@sen = nil
|
113
|
+
else
|
114
|
+
case token_format
|
115
|
+
when :chasen
|
116
|
+
data = line.split(/\s/)
|
117
|
+
data = [@tokid, *data[1..5], data[0]]
|
118
|
+
format = '<tok id="%d" read="%s" base="%s" pos="%s" cype="%s" cform="%s">%s</tok>'
|
119
|
+
@tok = add_node(@chunk, format, data)
|
120
|
+
@tokid += 1
|
121
|
+
when :mecab_unidic
|
122
|
+
text, data = line.split(/\s/, 2)
|
123
|
+
data = data.split(',').map{|item| item == '*' ? nil : item }
|
124
|
+
pos = data[0, 4].compact.join('-')
|
125
|
+
ctype, cform, lemmaForm, lemma = data[4, 4]
|
126
|
+
data = [@tokid, pos, ctype, cform, lemmaForm, lemma, text]
|
127
|
+
format = '<tok id="%d" pos="%s" cype="%s" cform="%s" lemmaForm="%s" lemma="%s">%s</tok>'
|
128
|
+
@tok = add_node(@chunk, format, data)
|
129
|
+
@tokid += 1
|
130
|
+
end
|
131
|
+
end
|
132
|
+
end
|
133
|
+
end
|
134
|
+
end
|
data/lib/cab2xml.rb
ADDED
metadata
ADDED
@@ -0,0 +1,99 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: cab2xml
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Mizuho IMADA
|
8
|
+
autorequire:
|
9
|
+
bindir: lib
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-02-25 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: nokogiri
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: bundler
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.8'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.8'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '10.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '10.0'
|
55
|
+
description: Cabocha to XML.
|
56
|
+
email:
|
57
|
+
- imadamizuho@gmail.com
|
58
|
+
executables: []
|
59
|
+
extensions: []
|
60
|
+
extra_rdoc_files: []
|
61
|
+
files:
|
62
|
+
- ".gitignore"
|
63
|
+
- Gemfile
|
64
|
+
- LICENSE.txt
|
65
|
+
- README.md
|
66
|
+
- Rakefile
|
67
|
+
- bin/cab2xml
|
68
|
+
- bin/console
|
69
|
+
- bin/setup
|
70
|
+
- cab2xml.gemspec
|
71
|
+
- lib/cab2xml.rb
|
72
|
+
- lib/cab2xml/converter.rb
|
73
|
+
- lib/cab2xml/version.rb
|
74
|
+
homepage: ''
|
75
|
+
licenses:
|
76
|
+
- MIT
|
77
|
+
metadata:
|
78
|
+
allowed_push_host: https://rubygems.org
|
79
|
+
post_install_message:
|
80
|
+
rdoc_options: []
|
81
|
+
require_paths:
|
82
|
+
- lib
|
83
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
84
|
+
requirements:
|
85
|
+
- - ">="
|
86
|
+
- !ruby/object:Gem::Version
|
87
|
+
version: '0'
|
88
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
89
|
+
requirements:
|
90
|
+
- - ">="
|
91
|
+
- !ruby/object:Gem::Version
|
92
|
+
version: '0'
|
93
|
+
requirements: []
|
94
|
+
rubyforge_project:
|
95
|
+
rubygems_version: 2.4.6
|
96
|
+
signing_key:
|
97
|
+
specification_version: 4
|
98
|
+
summary: Cabocha to XML.
|
99
|
+
test_files: []
|