lorem_jp 0.0.1
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/Gemfile +3 -0
- data/LICENSE.txt +22 -0
- data/README.md +57 -0
- data/Rakefile +7 -0
- data/bin/lorem_jp +6 -0
- data/build/fetcher.rb +248 -0
- data/build/make_dict.rb +183 -0
- data/build/recipes/2363.rb +30 -0
- data/build/recipes/52960.rb +28 -0
- data/build/recipes/789.rb +63 -0
- data/data/dict.txt +4449 -0
- data/lib/lorem_jp.rb +223 -0
- data/lib/lorem_jp/cli.rb +40 -0
- data/lorem_jp.gemspec +37 -0
- data/test/lorem_jp_spec.rb +60 -0
- metadata +90 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 3b5ed5259d27443978984fcdee63ad7f09d004d2
|
4
|
+
data.tar.gz: 4710492f6fc10793b6722337531a70eca870d232
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 6107f68c64a7c67f7cc33b6abb272c26fa7e3330025a1c3dae5c65dfb36388bd7d3debeef4255a380e611f3bb367d9988a700fa9423aeafbc50dc0dd78e74f27
|
7
|
+
data.tar.gz: 8ed7f6edf858bf1fe1dd4d5dfd2402bcfb2a78325eee9122407b2d50d79e3d095813bdc7d7a2e156dd0c20ae6a8f83c40750b6c64595e617b8e86aa0c3cac560
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 ITO Nobuaki
|
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 +1,57 @@
|
|
1
|
+
# LoremJP
|
2
|
+
|
3
|
+
Japanese Lorem Ipsum generator.
|
4
|
+
|
5
|
+
## Usage
|
6
|
+
|
7
|
+
```ruby
|
8
|
+
# Singleton API
|
9
|
+
puts LoremJP.sentence # => output meaningless Japanese sentence
|
10
|
+
|
11
|
+
# Or create an instance and re-use it
|
12
|
+
generator = LoremJP.new
|
13
|
+
generator.sentence # => ...
|
14
|
+
generator.sentence # => ...
|
15
|
+
```
|
16
|
+
|
17
|
+
Command line tool `lorem_jp` is also available.
|
18
|
+
|
19
|
+
$ lorem_jp
|
20
|
+
blah blah blah ...
|
21
|
+
|
22
|
+
## Installation
|
23
|
+
|
24
|
+
Add this line to your application's Gemfile:
|
25
|
+
|
26
|
+
gem 'lorem_jp', :github => 'dayflower/lorem_jp'
|
27
|
+
|
28
|
+
And then execute:
|
29
|
+
|
30
|
+
$ bundle
|
31
|
+
|
32
|
+
Or install it yourself as:
|
33
|
+
|
34
|
+
$ gem install lorem_jp
|
35
|
+
|
36
|
+
## Notice
|
37
|
+
|
38
|
+
Default dictionary is assembled from out-of-copyright texts provided by [Aozora Bunko](http://www.aozora.gr.jp/index.html).
|
39
|
+
|
40
|
+
* "[Chawan no yu](http://www.aozora.gr.jp/cards/000042/card2363.html)"
|
41
|
+
by "[Torahiko Terada](http://www.aozora.gr.jp/index_pages/person42.html)"
|
42
|
+
* "[Akai fune no okyaku](http://www.aozora.gr.jp/cards/001475/card52960.html)"
|
43
|
+
by "[Mimei Ogawa](http://www.aozora.gr.jp/index_pages/person1475.html)"
|
44
|
+
|
45
|
+
## TODO
|
46
|
+
|
47
|
+
* write document for usage (in README)
|
48
|
+
* write document for building custom dictionary
|
49
|
+
* write more tests
|
50
|
+
|
51
|
+
## Contributing
|
52
|
+
|
53
|
+
1. Fork it
|
54
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
55
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
56
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
57
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
data/bin/lorem_jp
ADDED
data/build/fetcher.rb
ADDED
@@ -0,0 +1,248 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
|
3
|
+
require 'fileutils'
|
4
|
+
require 'stringio'
|
5
|
+
require 'open-uri'
|
6
|
+
|
7
|
+
module TextFilter
|
8
|
+
attr_accessor :next_filter
|
9
|
+
|
10
|
+
def input(line)
|
11
|
+
raise 'must be overriden'
|
12
|
+
end
|
13
|
+
|
14
|
+
def finish
|
15
|
+
if @next_filter
|
16
|
+
@next_filter.finish
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
private
|
21
|
+
|
22
|
+
def puts(line)
|
23
|
+
@next_filter.input(line)
|
24
|
+
end
|
25
|
+
end
|
26
|
+
|
27
|
+
class ResultCatcher < Array
|
28
|
+
include TextFilter
|
29
|
+
|
30
|
+
def input(line)
|
31
|
+
self << line
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
class FileOutput
|
36
|
+
include TextFilter
|
37
|
+
|
38
|
+
def initialize(filename)
|
39
|
+
@handle = open filename, 'w:utf-8'
|
40
|
+
end
|
41
|
+
|
42
|
+
def input(line)
|
43
|
+
@handle.write line
|
44
|
+
end
|
45
|
+
|
46
|
+
def finish
|
47
|
+
@handle.close
|
48
|
+
|
49
|
+
if @next_filter
|
50
|
+
@next_filter.finish
|
51
|
+
end
|
52
|
+
end
|
53
|
+
end
|
54
|
+
|
55
|
+
class TextFilterManager < Array
|
56
|
+
def setup
|
57
|
+
last = nil
|
58
|
+
(self.size - 1).downto(0) do |i|
|
59
|
+
self[i].next_filter = last
|
60
|
+
last = self[i]
|
61
|
+
end
|
62
|
+
end
|
63
|
+
|
64
|
+
def input(line)
|
65
|
+
self.first.input line
|
66
|
+
end
|
67
|
+
|
68
|
+
def finish
|
69
|
+
self.first.finish
|
70
|
+
end
|
71
|
+
end
|
72
|
+
|
73
|
+
class UTF8Converter
|
74
|
+
include TextFilter
|
75
|
+
|
76
|
+
def input(line)
|
77
|
+
puts line.encode('UTF-8')
|
78
|
+
end
|
79
|
+
end
|
80
|
+
|
81
|
+
class BlankTrimmer
|
82
|
+
include TextFilter
|
83
|
+
|
84
|
+
def input(line)
|
85
|
+
line.sub!(%r{^ +}xmo, '')
|
86
|
+
|
87
|
+
if line !~ %r{^\s*$}xmo
|
88
|
+
puts line
|
89
|
+
end
|
90
|
+
end
|
91
|
+
end
|
92
|
+
|
93
|
+
class AozoraTrimmer
|
94
|
+
include TextFilter
|
95
|
+
|
96
|
+
def input(line)
|
97
|
+
puts line.gsub(%r{|(\S+?)《.*?》}xmo, '\\1') \
|
98
|
+
.gsub(%r{《.*?》}xmo, '') \
|
99
|
+
.gsub(%r{[#.*?]}xmo, '')
|
100
|
+
end
|
101
|
+
end
|
102
|
+
|
103
|
+
class AozoraTrimHeader
|
104
|
+
include TextFilter
|
105
|
+
|
106
|
+
def initialize
|
107
|
+
@state = 0
|
108
|
+
end
|
109
|
+
|
110
|
+
def input(line)
|
111
|
+
case @state
|
112
|
+
when 2
|
113
|
+
puts line
|
114
|
+
when 0, 1
|
115
|
+
if line =~ %r{^----------}
|
116
|
+
@state += 1
|
117
|
+
end
|
118
|
+
end
|
119
|
+
end
|
120
|
+
end
|
121
|
+
|
122
|
+
class AozoraTrimTrailer
|
123
|
+
include TextFilter
|
124
|
+
|
125
|
+
def initialize
|
126
|
+
@state = 0
|
127
|
+
end
|
128
|
+
|
129
|
+
def input(line)
|
130
|
+
case @state
|
131
|
+
when 1
|
132
|
+
# pass
|
133
|
+
when 0
|
134
|
+
if line =~ %r{^底本:}
|
135
|
+
@state = 1
|
136
|
+
else
|
137
|
+
puts line
|
138
|
+
end
|
139
|
+
end
|
140
|
+
end
|
141
|
+
end
|
142
|
+
|
143
|
+
class StandardFetcher
|
144
|
+
class << self
|
145
|
+
DOWNLOAD_DIR = File.absolute_path('../download/', __FILE__)
|
146
|
+
|
147
|
+
def fetch(filename, url, options = {})
|
148
|
+
force = options[:force]
|
149
|
+
|
150
|
+
output_file = File.join(DOWNLOAD_DIR, filename)
|
151
|
+
if File.exists?(output_file) && ! force
|
152
|
+
return output_file
|
153
|
+
end
|
154
|
+
|
155
|
+
unless Dir.exists?(DOWNLOAD_DIR)
|
156
|
+
FileUtils.makedirs(DOWNLOAD_DIR)
|
157
|
+
end
|
158
|
+
|
159
|
+
begin
|
160
|
+
Kernel.open output_file, 'wb:ASCII-8BIT' do |file|
|
161
|
+
Kernel.open url, 'rb' do |net|
|
162
|
+
begin
|
163
|
+
loop do
|
164
|
+
buf = net.sysread(4096)
|
165
|
+
len = file.write buf
|
166
|
+
end
|
167
|
+
rescue EOFError
|
168
|
+
# pass
|
169
|
+
end
|
170
|
+
end
|
171
|
+
end
|
172
|
+
|
173
|
+
rescue
|
174
|
+
File.unlink output_file rescue nil
|
175
|
+
raise
|
176
|
+
end
|
177
|
+
|
178
|
+
return output_file
|
179
|
+
end
|
180
|
+
|
181
|
+
def extract(archive, target, options = { :external_encoding => 'CP932' })
|
182
|
+
if ! File.exists?(archive)
|
183
|
+
raise
|
184
|
+
end
|
185
|
+
|
186
|
+
cmdline = "unzip -xqc #{archive} #{target} 2>/dev/null"
|
187
|
+
result = StringIO.new
|
188
|
+
|
189
|
+
IO.popen(cmdline, 'r', options) { |io|
|
190
|
+
loop do
|
191
|
+
line = io.gets
|
192
|
+
break if line.nil?
|
193
|
+
result.write line
|
194
|
+
end
|
195
|
+
}
|
196
|
+
if $?.exitstatus !=0
|
197
|
+
raise "#{$?}"
|
198
|
+
end
|
199
|
+
|
200
|
+
result.rewind
|
201
|
+
|
202
|
+
return result
|
203
|
+
end
|
204
|
+
end
|
205
|
+
end
|
206
|
+
|
207
|
+
class AozoraFetcher < StandardFetcher
|
208
|
+
class << self
|
209
|
+
TEXT_DIR = File.absolute_path('../text/', __FILE__)
|
210
|
+
|
211
|
+
def run(args = {})
|
212
|
+
@output_file = File.join(TEXT_DIR, args[:output])
|
213
|
+
if File.exists?(@output_file) && ! args[:force]
|
214
|
+
return @output_file
|
215
|
+
end
|
216
|
+
|
217
|
+
archive = fetch(args[:archive_name], args[:url])
|
218
|
+
|
219
|
+
unless Dir.exists?(TEXT_DIR)
|
220
|
+
FileUtils.makedirs(TEXT_DIR)
|
221
|
+
end
|
222
|
+
|
223
|
+
manager = create_manager
|
224
|
+
|
225
|
+
source = extract(archive, args[:source])
|
226
|
+
source.each do |line|
|
227
|
+
manager.input line
|
228
|
+
end
|
229
|
+
|
230
|
+
manager.finish
|
231
|
+
|
232
|
+
return @output_file
|
233
|
+
end
|
234
|
+
|
235
|
+
def create_manager
|
236
|
+
manager = TextFilterManager.new
|
237
|
+
manager << UTF8Converter.new
|
238
|
+
manager << AozoraTrimHeader.new
|
239
|
+
manager << AozoraTrimTrailer.new
|
240
|
+
manager << BlankTrimmer.new
|
241
|
+
manager << AozoraTrimmer.new
|
242
|
+
manager << FileOutput.new(@output_file)
|
243
|
+
manager.setup
|
244
|
+
|
245
|
+
return manager
|
246
|
+
end
|
247
|
+
end
|
248
|
+
end
|
data/build/make_dict.rb
ADDED
@@ -0,0 +1,183 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
require 'open3'
|
3
|
+
require 'optparse'
|
4
|
+
|
5
|
+
class MarkovCalculator
|
6
|
+
def initialize(options = {})
|
7
|
+
@chain = options[:chain] || 1
|
8
|
+
@ignore_type = options[:ignore_type]
|
9
|
+
|
10
|
+
# word dictionary
|
11
|
+
@dict = { '' => { :id => 0, :word => '', :next => [] } }
|
12
|
+
@word_id = 1
|
13
|
+
|
14
|
+
# probability (candidates)
|
15
|
+
@tree = {}
|
16
|
+
|
17
|
+
clear_stack
|
18
|
+
end
|
19
|
+
|
20
|
+
def input_line(line)
|
21
|
+
line = line.chomp
|
22
|
+
return if line == 'EOS'
|
23
|
+
|
24
|
+
word, type = line.split(%r{\s+})
|
25
|
+
|
26
|
+
if word == '」'
|
27
|
+
sentence_is_terminated
|
28
|
+
return
|
29
|
+
end
|
30
|
+
|
31
|
+
return if word == '「' || word == '」'
|
32
|
+
|
33
|
+
if @ignore_type
|
34
|
+
line = word
|
35
|
+
end
|
36
|
+
|
37
|
+
# register word to dictionary
|
38
|
+
if @dict.has_key?(line)
|
39
|
+
id = @dict[line][:id]
|
40
|
+
else
|
41
|
+
id = @word_id
|
42
|
+
@word_id += 1
|
43
|
+
@dict[line] = { :id => id, :word => word }
|
44
|
+
end
|
45
|
+
|
46
|
+
# add to candidates
|
47
|
+
add_word_to_candidate id
|
48
|
+
|
49
|
+
@stack.shift
|
50
|
+
@stack << id
|
51
|
+
|
52
|
+
# termination
|
53
|
+
if %w[ 。 ? ! ].include?(word)
|
54
|
+
sentence_is_terminated
|
55
|
+
end
|
56
|
+
|
57
|
+
return
|
58
|
+
end
|
59
|
+
|
60
|
+
def input(lines)
|
61
|
+
lines.each do |line|
|
62
|
+
input_line(line.chomp)
|
63
|
+
end
|
64
|
+
end
|
65
|
+
|
66
|
+
def output_dictionary(handle)
|
67
|
+
# chains
|
68
|
+
handle.puts @chain.to_s
|
69
|
+
|
70
|
+
# word dictionary
|
71
|
+
output_words handle
|
72
|
+
|
73
|
+
# separator
|
74
|
+
handle.puts
|
75
|
+
|
76
|
+
# probabilities
|
77
|
+
output_tree handle
|
78
|
+
end
|
79
|
+
|
80
|
+
def output_words(handle)
|
81
|
+
@dict.values.sort_by { |item| item[:id] }.each do |item|
|
82
|
+
handle.puts item[:word]
|
83
|
+
end
|
84
|
+
end
|
85
|
+
|
86
|
+
def output_tree(handle)
|
87
|
+
output_tree_node(handle, @tree, 0)
|
88
|
+
end
|
89
|
+
|
90
|
+
private
|
91
|
+
|
92
|
+
def output_tree_node(handle, node, depth)
|
93
|
+
node.keys.sort.each do |key|
|
94
|
+
child = node[key]
|
95
|
+
|
96
|
+
handle.write %q{ } * depth
|
97
|
+
handle.write key
|
98
|
+
|
99
|
+
if child.has_key?(:cands)
|
100
|
+
handle.write "="
|
101
|
+
|
102
|
+
cands = child[:cands].sort
|
103
|
+
first = cands[0]
|
104
|
+
if cands.all? { |v| v == first }
|
105
|
+
cands = [ first ]
|
106
|
+
end
|
107
|
+
|
108
|
+
handle.puts cands.join(",")
|
109
|
+
else
|
110
|
+
handle.write "\n"
|
111
|
+
|
112
|
+
output_tree_node(handle, child, depth + 1)
|
113
|
+
end
|
114
|
+
end
|
115
|
+
end
|
116
|
+
|
117
|
+
def sentence_is_terminated
|
118
|
+
while @stack[0] != -1
|
119
|
+
add_word_to_candidate -1 # EOS
|
120
|
+
|
121
|
+
@stack.shift
|
122
|
+
@stack << -1
|
123
|
+
end
|
124
|
+
|
125
|
+
clear_stack
|
126
|
+
end
|
127
|
+
|
128
|
+
def add_word_to_candidate(word_id)
|
129
|
+
node = @tree
|
130
|
+
s = @stack.dup
|
131
|
+
while s.length > 0
|
132
|
+
wid = s.shift
|
133
|
+
node[wid] ||= {}
|
134
|
+
node = node[wid]
|
135
|
+
end
|
136
|
+
|
137
|
+
node[:cands] ||= []
|
138
|
+
node[:cands] << word_id
|
139
|
+
end
|
140
|
+
|
141
|
+
def clear_stack
|
142
|
+
@stack = [ 0 ] * @chain
|
143
|
+
end
|
144
|
+
|
145
|
+
class CLI
|
146
|
+
def self.main
|
147
|
+
chain = 1
|
148
|
+
ignore_type = false
|
149
|
+
|
150
|
+
opt = OptionParser.new
|
151
|
+
|
152
|
+
opt.on('-c CHAIN', 'chain of precedences (default: 1)') {
|
153
|
+
|v| chain = v.to_i
|
154
|
+
}
|
155
|
+
opt.on('-n', 'ignore a part of speech') {
|
156
|
+
|v| ignore_type = v
|
157
|
+
}
|
158
|
+
|
159
|
+
opt.parse! ARGV
|
160
|
+
|
161
|
+
calculator = MarkovCalculator.new(:chain => chain,
|
162
|
+
:ignore_type => ignore_type)
|
163
|
+
|
164
|
+
Open3.popen3('mecab -O simple') { |stdin, stdout, stderr, wait_thr|
|
165
|
+
Thread.fork {
|
166
|
+
ARGF.set_encoding 'utf-8:utf-8'
|
167
|
+
ARGF.each do |line|
|
168
|
+
stdin.puts line.gsub(%r{(?: ^ [\s ]+ | [\s ]+ $ )}xmo, '')
|
169
|
+
end
|
170
|
+
stdin.close
|
171
|
+
}
|
172
|
+
|
173
|
+
calculator.input(stdout)
|
174
|
+
}
|
175
|
+
|
176
|
+
calculator.output_dictionary(STDOUT)
|
177
|
+
end
|
178
|
+
end
|
179
|
+
end
|
180
|
+
|
181
|
+
if __FILE__ == $0
|
182
|
+
MarkovCalculator::CLI.main
|
183
|
+
end
|