tataki 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 +18 -0
- data/.rspec +2 -0
- data/.travis.yml +5 -0
- data/Gemfile +4 -0
- data/Guardfile +6 -0
- data/LICENSE.txt +22 -0
- data/README.md +55 -0
- data/Rakefile +6 -0
- data/data/alphabet.yml +27 -0
- data/data/jisyo/.gitignore +2 -0
- data/data/roman.yml +142 -0
- data/data/skk-jisyo.yml +24 -0
- data/lib/tataki.rb +15 -0
- data/lib/tataki/base.rb +13 -0
- data/lib/tataki/converters.rb +16 -0
- data/lib/tataki/converters/alphabet.rb +24 -0
- data/lib/tataki/converters/combine.rb +20 -0
- data/lib/tataki/converters/roman.rb +67 -0
- data/lib/tataki/converters/skk_jisyo.rb +129 -0
- data/lib/tataki/version.rb +3 -0
- data/spec/spec_helper.rb +2 -0
- data/spec/tataki/converters/alphabet_spec.rb +17 -0
- data/spec/tataki/converters/combine_spec.rb +35 -0
- data/spec/tataki/converters/roman_spec.rb +30 -0
- data/spec/tataki/converters/skk_jisyo_spec.rb +22 -0
- data/spec/tataki_spec.rb +25 -0
- data/tataki.gemspec +30 -0
- metadata +190 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: a2ee32cd3111b09f4e62781debac62e4b5685017
|
4
|
+
data.tar.gz: 90a9ae1f2b96841d50ec13cefc9740fb43f7557c
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: ba6ba513abcfbd2b1b31250cc592a094a39ab9c5dc995741dcbfa864091f7e96f1f73119ea3965f5b49ec4329589731219c62fca4c6df8096ec10b3001bfe6c1
|
7
|
+
data.tar.gz: 94070b7ba996462447f5e942c6193829ab8c01cb10687e5812d7d97954710168fcf6fe2443a6b736f79595bc7b21af29830ea4cbfec74842165a68060ea00832
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/Guardfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Sunao Komuro
|
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 +1,55 @@
|
|
1
|
+
# Tataki
|
2
|
+
|
3
|
+
Tataki is pure ruby kana converter.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'tataki'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install tataki
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
### Basic usage
|
22
|
+
```ruby
|
23
|
+
require "tataki"
|
24
|
+
|
25
|
+
"漢字をひらがなに変換".to_kana # => "かんじをひらがなにへんかん"
|
26
|
+
"X線研究者".to_kana # => "えっくすせんけんきゅうしゃ"
|
27
|
+
"肉を食べるだけの簡単なお仕事".to_kana # => "にくをたべるだけのかんたんなおしごと"
|
28
|
+
```
|
29
|
+
|
30
|
+
At first time, `require "tataki"` is slow (creating dictionary cache).
|
31
|
+
|
32
|
+
### Configure converter
|
33
|
+
```ruby
|
34
|
+
require "tataki/base"
|
35
|
+
|
36
|
+
alphabet_converter = Tataki::Converter::Alphabet.new
|
37
|
+
alphabet_converter.to_kana("abcde") # => "えーびーしーでぃーいー"
|
38
|
+
|
39
|
+
roman_alphabet_converter = Tataki::Converter::Combine.new(Tataki::Converter::Roman.new, Tataki::Converter::Alphabet.new)
|
40
|
+
roman_alphabet_converter.to_kana("robottotaisennf") # => "ろぼっとたいせんえふ"
|
41
|
+
|
42
|
+
skk_converter = Tataki::Converter::SkkJisyo.new
|
43
|
+
skk_converter.to_kana("研究者") # => "けんきゅうしゃ"
|
44
|
+
```
|
45
|
+
|
46
|
+
## TODO
|
47
|
+
- Support more configurable
|
48
|
+
|
49
|
+
## Contributing
|
50
|
+
|
51
|
+
1. Fork it
|
52
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
53
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
54
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
55
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
data/data/alphabet.yml
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
table:
|
2
|
+
"a": えー
|
3
|
+
"b": びー
|
4
|
+
"c": しー
|
5
|
+
"d": でぃー
|
6
|
+
"e": いー
|
7
|
+
"f": えふ
|
8
|
+
"g": じー
|
9
|
+
"h": えいち
|
10
|
+
"i": あい
|
11
|
+
"j": じぇい
|
12
|
+
"k": けー
|
13
|
+
"l": える
|
14
|
+
"m": えむ
|
15
|
+
"n": えぬ
|
16
|
+
"o": おー
|
17
|
+
"p": ぴー
|
18
|
+
"q": きゅー
|
19
|
+
"r": あーる
|
20
|
+
"s": えす
|
21
|
+
"t": てぃー
|
22
|
+
"u": ゆー
|
23
|
+
"v": ぶい
|
24
|
+
"w": だぶりゅー
|
25
|
+
"x": えっくす
|
26
|
+
"y": わい
|
27
|
+
"z": ぜっと
|
data/data/roman.yml
ADDED
@@ -0,0 +1,142 @@
|
|
1
|
+
table:
|
2
|
+
"a": あ
|
3
|
+
"i": い
|
4
|
+
"u": う
|
5
|
+
"e": え
|
6
|
+
"o": お
|
7
|
+
"ka": か
|
8
|
+
"ki": き
|
9
|
+
"ku": く
|
10
|
+
"ke": け
|
11
|
+
"ko": こ
|
12
|
+
"ga": が
|
13
|
+
"gi": ぎ
|
14
|
+
"gu": ぐ
|
15
|
+
"ge": げ
|
16
|
+
"go": ご
|
17
|
+
"sa": さ
|
18
|
+
"si": し
|
19
|
+
"shi": し
|
20
|
+
"su": す
|
21
|
+
"se": せ
|
22
|
+
"so": そ
|
23
|
+
"za": ざ
|
24
|
+
"zi": じ
|
25
|
+
"ji": じ
|
26
|
+
"zu": ず
|
27
|
+
"ze": ぜ
|
28
|
+
"zo": ぞ
|
29
|
+
"ta": た
|
30
|
+
"ti": ち
|
31
|
+
"chi": ち
|
32
|
+
"tu": つ
|
33
|
+
"tsu": つ
|
34
|
+
"te": て
|
35
|
+
"to": と
|
36
|
+
"da": だ
|
37
|
+
"di": ぢ
|
38
|
+
"du": づ
|
39
|
+
"de": で
|
40
|
+
"do": ど
|
41
|
+
"na": な
|
42
|
+
"ni": に
|
43
|
+
"nu": ぬ
|
44
|
+
"ne": ね
|
45
|
+
"no": の
|
46
|
+
"ha": は
|
47
|
+
"hi": ひ
|
48
|
+
"hu": ふ
|
49
|
+
"fu": ふ
|
50
|
+
"he": へ
|
51
|
+
"ho": ほ
|
52
|
+
"ba": ば
|
53
|
+
"bi": び
|
54
|
+
"bu": ぶ
|
55
|
+
"be": べ
|
56
|
+
"bo": ぼ
|
57
|
+
"pa": ぱ
|
58
|
+
"pi": ぴ
|
59
|
+
"pu": ぷ
|
60
|
+
"pe": ぺ
|
61
|
+
"po": ぽ
|
62
|
+
"ma": ま
|
63
|
+
"mi": み
|
64
|
+
"mu": む
|
65
|
+
"me": め
|
66
|
+
"mo": も
|
67
|
+
"ya": や
|
68
|
+
"yu": ゆ
|
69
|
+
"yo": よ
|
70
|
+
"ra": ら
|
71
|
+
"ri": り
|
72
|
+
"ru": る
|
73
|
+
"re": れ
|
74
|
+
"ro": ろ
|
75
|
+
"wa": わ
|
76
|
+
"wo": を
|
77
|
+
"n": ん
|
78
|
+
"nn": ん
|
79
|
+
"xa": ぁ
|
80
|
+
"la": ぁ
|
81
|
+
"xi": ぃ
|
82
|
+
"li": ぃ
|
83
|
+
"xu": ぅ
|
84
|
+
"lu": ぅ
|
85
|
+
"xe": ぇ
|
86
|
+
"le": ぇ
|
87
|
+
"xo": ぉ
|
88
|
+
"lo": ぉ
|
89
|
+
"kya": きゃ
|
90
|
+
"kyu": きゅ
|
91
|
+
"kyo": きょ
|
92
|
+
"gya": ぎゃ
|
93
|
+
"gyu": ぎゅ
|
94
|
+
"gyo": ぎょ
|
95
|
+
"zya": じゃ
|
96
|
+
"sya": しゃ
|
97
|
+
"sha": しゃ
|
98
|
+
"syu": しゅ
|
99
|
+
"shu": しゅ
|
100
|
+
"syo": しょ
|
101
|
+
"sho": しょ
|
102
|
+
"ja": じゃ
|
103
|
+
"zyu": じゅ
|
104
|
+
"ju": じゅ
|
105
|
+
"zyo": じょ
|
106
|
+
"jo": じょ
|
107
|
+
"tya": ちゃ
|
108
|
+
"cha": ちゃ
|
109
|
+
"tyu": ちゅ
|
110
|
+
"chu": ちゅ
|
111
|
+
"tyo": ちょ
|
112
|
+
"cho": ちょ
|
113
|
+
"dya": ぢゃ
|
114
|
+
"dyu": ぢゅ
|
115
|
+
"dyo": ぢょ
|
116
|
+
"nya": にゃ
|
117
|
+
"nyu": にゅ
|
118
|
+
"nyo": にょ
|
119
|
+
"hya": ひゃ
|
120
|
+
"hyu": ひゅ
|
121
|
+
"hyo": ひょ
|
122
|
+
"bya": びゃ
|
123
|
+
"byu": びゅ
|
124
|
+
"byo": びょ
|
125
|
+
"pya": ぴゃ
|
126
|
+
"pyu": ぴゅ
|
127
|
+
"pyo": ぴょ
|
128
|
+
"mya": みゃ
|
129
|
+
"myu": みゅ
|
130
|
+
"myo": みょ
|
131
|
+
"xya": ゃ
|
132
|
+
"lya": ゃ
|
133
|
+
"xyu": ゅ
|
134
|
+
"lyu": ゅ
|
135
|
+
"xyo": ょ
|
136
|
+
"lyo": ょ
|
137
|
+
"rya": りゃ
|
138
|
+
"ryu": りゅ
|
139
|
+
"ryo": りょ
|
140
|
+
"xwa": ゎ
|
141
|
+
"lwa": ゎ
|
142
|
+
consonant: [k, g, s, j, t, c, d, n, h, f, b, p, m, y, r, w, x, l]
|
data/data/skk-jisyo.yml
ADDED
@@ -0,0 +1,24 @@
|
|
1
|
+
roman_table:
|
2
|
+
"i": [い]
|
3
|
+
"u": [う]
|
4
|
+
"e": [え]
|
5
|
+
"o": [お]
|
6
|
+
"k": [か, き, く, け, こ]
|
7
|
+
"g": [が, ぎ, ぐ, げ, ご]
|
8
|
+
"s": [さ, し, す, せ, そ]
|
9
|
+
"z": [ざ, じ, ず, ぜ, ぞ]
|
10
|
+
"j": [じ]
|
11
|
+
"t": [た, ち, つ, て, と]
|
12
|
+
"c": [ち]
|
13
|
+
"d": [だ, ぢ, づ, で, ど]
|
14
|
+
"n": [な, に, ぬ, ね, の]
|
15
|
+
"h": [は, ひ, ふ, へ, ほ]
|
16
|
+
"f": [ふ]
|
17
|
+
"b": [ば, び, ぶ, べ, ぼ]
|
18
|
+
"p": [ぱ, ぴ, ぷ, ぺ, ぽ]
|
19
|
+
"m": [ま, み, む, め, も]
|
20
|
+
"y": [や, ゆ, よ]
|
21
|
+
"r": [ら, り, る, れ, ろ]
|
22
|
+
"w": [わ]
|
23
|
+
ignore_kana:
|
24
|
+
- きごう
|
data/lib/tataki.rb
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
require "tataki/base"
|
3
|
+
|
4
|
+
module Tataki
|
5
|
+
EASY_CONVERTER = Tataki::Converter::Combine.new(
|
6
|
+
Tataki::Converter::SkkJisyo.new,
|
7
|
+
Tataki::Converter::Alphabet.new,
|
8
|
+
).freeze
|
9
|
+
|
10
|
+
String.class_eval do
|
11
|
+
def to_kana
|
12
|
+
EASY_CONVERTER.to_kana(self)
|
13
|
+
end
|
14
|
+
end
|
15
|
+
end
|
data/lib/tataki/base.rb
ADDED
@@ -0,0 +1,16 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
module Tataki
|
3
|
+
CONVERTERS = []
|
4
|
+
|
5
|
+
module Converter
|
6
|
+
class Base
|
7
|
+
def to_kana(sentence)
|
8
|
+
raise "TODO: implement .to_kana"
|
9
|
+
end
|
10
|
+
end
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
Dir[File.expand_path("../converters", __FILE__) + "/*.rb"].each do |file|
|
15
|
+
require file
|
16
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
require "yaml"
|
3
|
+
|
4
|
+
module Tataki
|
5
|
+
module Converter
|
6
|
+
class Alphabet < Base
|
7
|
+
def initialize
|
8
|
+
alphabet_file = File.expand_path("../../../../data/alphabet.yml", __FILE__)
|
9
|
+
alphabet_data = YAML.load_file(alphabet_file)
|
10
|
+
@table = alphabet_data["table"]
|
11
|
+
end
|
12
|
+
|
13
|
+
def to_kana(sentence)
|
14
|
+
kana = ""
|
15
|
+
sentence.downcase.each_char do |ch|
|
16
|
+
kana << (@table[ch] || ch)
|
17
|
+
end
|
18
|
+
kana
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
Tataki::CONVERTERS << Converter::Alphabet
|
24
|
+
end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
module Tataki
|
3
|
+
module Converter
|
4
|
+
class Combine < Base
|
5
|
+
def initialize(*converters)
|
6
|
+
@converters = converters
|
7
|
+
end
|
8
|
+
|
9
|
+
def to_kana(sentence)
|
10
|
+
kana = sentence
|
11
|
+
@converters.each do |converter|
|
12
|
+
kana = converter.to_kana(kana)
|
13
|
+
end
|
14
|
+
kana
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
Tataki::CONVERTERS << Converter::Combine
|
20
|
+
end
|
@@ -0,0 +1,67 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
require "trie"
|
3
|
+
require "yaml"
|
4
|
+
|
5
|
+
module Tataki
|
6
|
+
module Converter
|
7
|
+
class Roman < Base
|
8
|
+
SOKUON = "っ"
|
9
|
+
|
10
|
+
def initialize
|
11
|
+
@trie = Trie.new
|
12
|
+
roman_file = File.expand_path("../../../../data/roman.yml", __FILE__)
|
13
|
+
roman_data = YAML.load_file(roman_file)
|
14
|
+
roman_data["table"].each do |roman, kana|
|
15
|
+
@trie.insert(roman, kana)
|
16
|
+
end
|
17
|
+
@consonant = roman_data["consonant"]
|
18
|
+
@trie.freeze
|
19
|
+
end
|
20
|
+
|
21
|
+
def to_kana(sentence)
|
22
|
+
_to_kana(sentence.downcase, "", "", @trie)
|
23
|
+
end
|
24
|
+
|
25
|
+
private
|
26
|
+
|
27
|
+
def _to_kana(sentence, kana, prefix, trie, through_alphabet = true)
|
28
|
+
return if trie.empty?
|
29
|
+
return kana if sentence.empty?
|
30
|
+
|
31
|
+
next_ch = sentence[0]
|
32
|
+
next_sentence = sentence[1..-1]
|
33
|
+
next_trie = trie.find_prefix(next_ch)
|
34
|
+
next_set = next_trie.find([])
|
35
|
+
if next_set.size > 0 && next_set.size == next_trie.size
|
36
|
+
return _to_kana(next_sentence, kana + next_set.values.first, "", @trie)
|
37
|
+
end
|
38
|
+
|
39
|
+
if next_sentence.empty?
|
40
|
+
if next_set.size > 0
|
41
|
+
return kana + prefix + next_set.values.first
|
42
|
+
else
|
43
|
+
return kana + prefix + next_ch
|
44
|
+
end
|
45
|
+
end
|
46
|
+
|
47
|
+
next_kana = _to_kana(next_sentence, kana, prefix + next_ch, next_trie, false)
|
48
|
+
|
49
|
+
if next_kana
|
50
|
+
return next_kana
|
51
|
+
end
|
52
|
+
|
53
|
+
if next_set.size > 0
|
54
|
+
return _to_kana(next_sentence, kana + next_set.values.first, "", @trie)
|
55
|
+
elsif @consonant.include?(next_ch) && next_sentence.start_with?(next_ch)
|
56
|
+
return _to_kana(next_sentence, kana + SOKUON, "", @trie)
|
57
|
+
elsif through_alphabet
|
58
|
+
return _to_kana(next_sentence, kana + prefix + next_ch, "", @trie)
|
59
|
+
else
|
60
|
+
return nil
|
61
|
+
end
|
62
|
+
end
|
63
|
+
end
|
64
|
+
end
|
65
|
+
|
66
|
+
Tataki::CONVERTERS << Converter::Roman
|
67
|
+
end
|
@@ -0,0 +1,129 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
require "yaml"
|
3
|
+
require "time"
|
4
|
+
require "skk/jisyo"
|
5
|
+
require "trie"
|
6
|
+
|
7
|
+
module Tataki
|
8
|
+
module Converter
|
9
|
+
class SkkJisyo < Base
|
10
|
+
DEFAULT_JISYO_SUFFIXES = %w[M]
|
11
|
+
|
12
|
+
def initialize(options = {})
|
13
|
+
options = {
|
14
|
+
:jisyo_paths => DEFAULT_JISYO_SUFFIXES.map{|suffix| Skk::Jisyo.path(suffix) },
|
15
|
+
:trie_cache_path => trie_cache_path(DEFAULT_JISYO_SUFFIXES.join("_")),
|
16
|
+
}.merge(options)
|
17
|
+
config_file = File.expand_path("../../../../data/skk-jisyo.yml", __FILE__)
|
18
|
+
config_data = YAML.load_file(config_file)
|
19
|
+
@roman_data = config_data["roman_table"]
|
20
|
+
@ignore_kana = config_data["ignore_kana"]
|
21
|
+
@trie = setup_jisyo(options).freeze
|
22
|
+
end
|
23
|
+
|
24
|
+
def setup_jisyo(options)
|
25
|
+
if File.exist?(options[:trie_cache_path])
|
26
|
+
trie = Marshal.load(File.read(options[:trie_cache_path]))
|
27
|
+
else
|
28
|
+
trie = Trie.new
|
29
|
+
options[:jisyo_paths].each do |jisyo_path|
|
30
|
+
add_jisyo(trie, jisyo_path)
|
31
|
+
end
|
32
|
+
File.binwrite(options[:trie_cache_path], Marshal.dump(trie))
|
33
|
+
File.write("#{options[:trie_cache_path]}.timestamp", Time.now.to_s)
|
34
|
+
end
|
35
|
+
trie
|
36
|
+
end
|
37
|
+
|
38
|
+
def add_jisyo(trie, jisyo_path)
|
39
|
+
File.open(jisyo_path, "rb:euc-jp") do |jisyo_file|
|
40
|
+
jisyo_file.each_line do |line|
|
41
|
+
next if line.empty? || line[0] == ";" || line.include?("#")
|
42
|
+
kana, kanji_part = line.encode("utf-8").split(" ")
|
43
|
+
next unless kana && kanji_part
|
44
|
+
kana.gsub!(/[^ぁ-んa-z]/, "")
|
45
|
+
next if kana.empty? || !(kana =~ /^[ぁ-ん]+[a-z]?/) || @ignore_kana.include?(kana)
|
46
|
+
kanji_part.gsub!(/^\/|;.+|\/$/, "")
|
47
|
+
kanji_part.split("/").each do |kanji|
|
48
|
+
trie.insert(kanji, kana)
|
49
|
+
end
|
50
|
+
end
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
def jisyo_path
|
55
|
+
File.expand_path("../../../../data/jisyo", __FILE__)
|
56
|
+
end
|
57
|
+
|
58
|
+
def trie_cache_path(name)
|
59
|
+
File.join(jisyo_path, "SKK-JISYO.#{name}.trie.cache")
|
60
|
+
end
|
61
|
+
|
62
|
+
def jisyo_timestamp(path)
|
63
|
+
Time.parse(File.read("#{path}.timestamp"))
|
64
|
+
end
|
65
|
+
|
66
|
+
def to_kana(sentence)
|
67
|
+
_to_kana(sentence, "", "", @trie)
|
68
|
+
end
|
69
|
+
|
70
|
+
private
|
71
|
+
|
72
|
+
def _to_kana(sentence, kana, prefix, trie, through_alphabet = true)
|
73
|
+
return if trie.empty?
|
74
|
+
return kana if sentence.empty?
|
75
|
+
|
76
|
+
next_ch = sentence[0]
|
77
|
+
next_sentence = sentence[1..-1]
|
78
|
+
next_trie = trie.find_prefix(next_ch)
|
79
|
+
next_trie_values = next_trie.values
|
80
|
+
next_trie_values.reject!{|value| value =~ /[a-z]/ }
|
81
|
+
next_set = next_trie.find([])
|
82
|
+
next_set_values = next_set.values
|
83
|
+
okurigana = find_okurigana(next_set_values, next_sentence)
|
84
|
+
next_set_values.reject!{|value| value =~ /[a-z]/ }
|
85
|
+
if okurigana
|
86
|
+
return _to_kana(next_sentence, kana + okurigana, "", @trie)
|
87
|
+
elsif next_set_values.size > 0 && next_set_values.size == next_trie_values.size
|
88
|
+
return _to_kana(next_sentence, kana + next_set_values.sample, "", @trie)
|
89
|
+
end
|
90
|
+
|
91
|
+
if next_sentence.empty?
|
92
|
+
if next_set_values.size > 0
|
93
|
+
return kana + next_set_values.sample
|
94
|
+
elsif through_alphabet
|
95
|
+
return kana + prefix + next_ch
|
96
|
+
end
|
97
|
+
end
|
98
|
+
|
99
|
+
next_kana = _to_kana(next_sentence, kana, prefix + next_ch, next_trie, false)
|
100
|
+
|
101
|
+
if next_kana
|
102
|
+
return next_kana
|
103
|
+
end
|
104
|
+
|
105
|
+
if next_set_values.size > 0
|
106
|
+
return _to_kana(next_sentence, kana + next_set_values.sample, "", @trie)
|
107
|
+
elsif through_alphabet
|
108
|
+
return _to_kana(next_sentence, kana + prefix + next_ch, "", @trie)
|
109
|
+
else
|
110
|
+
return nil
|
111
|
+
end
|
112
|
+
end
|
113
|
+
|
114
|
+
def find_okurigana(yomi_candidates, next_sentence)
|
115
|
+
yomi_candidates.each do |yomi|
|
116
|
+
next unless yomi =~ /.+([a-z])$/
|
117
|
+
okurigana_yomi = @roman_data[$1]
|
118
|
+
next unless okurigana_yomi
|
119
|
+
okurigana_yomi.each do |okurigana|
|
120
|
+
return yomi.gsub(/[a-z]$/, "") if next_sentence.start_with?(okurigana)
|
121
|
+
end
|
122
|
+
end
|
123
|
+
nil
|
124
|
+
end
|
125
|
+
end
|
126
|
+
end
|
127
|
+
|
128
|
+
Tataki::CONVERTERS << Converter::SkkJisyo
|
129
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
require "spec_helper"
|
3
|
+
|
4
|
+
describe Tataki::Converter::Alphabet do
|
5
|
+
let(:converter) { Tataki::Converter::Alphabet.new }
|
6
|
+
|
7
|
+
describe ".to_kana" do
|
8
|
+
shared_examples "converts_kana" do |sentence, kana|
|
9
|
+
it "converts #{sentence.inspect} to #{kana.inspect}" do
|
10
|
+
expect(converter.to_kana(sentence)).to eq(kana)
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
include_examples "converts_kana", "", ""
|
15
|
+
include_examples "converts_kana", "hoge!", "えいちおーじーいー!"
|
16
|
+
end
|
17
|
+
end
|
@@ -0,0 +1,35 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
require "spec_helper"
|
3
|
+
|
4
|
+
describe Tataki::Converter::Combine do
|
5
|
+
let(:skk_converter) { Tataki::Converter::SkkJisyo.new }
|
6
|
+
let(:roman_converter) { Tataki::Converter::Roman.new }
|
7
|
+
let(:alphabet_converter) { Tataki::Converter::Alphabet.new }
|
8
|
+
|
9
|
+
describe ".to_kana" do
|
10
|
+
shared_examples "converts_kana" do |sentence, kana|
|
11
|
+
it "converts #{sentence.inspect} to #{kana.inspect}" do
|
12
|
+
expect(converter.to_kana(sentence)).to eq(kana)
|
13
|
+
end
|
14
|
+
end
|
15
|
+
|
16
|
+
context "when roman + alphabet" do
|
17
|
+
let(:converter) do
|
18
|
+
Tataki::Converter::Combine.new(roman_converter, alphabet_converter)
|
19
|
+
end
|
20
|
+
|
21
|
+
include_examples "converts_kana", "robottotaisennf", "ろぼっとたいせんえふ"
|
22
|
+
end
|
23
|
+
|
24
|
+
context "when skk-jisyo + alphabet" do
|
25
|
+
let(:converter) do
|
26
|
+
Tataki::Converter::Combine.new(skk_converter, alphabet_converter)
|
27
|
+
end
|
28
|
+
|
29
|
+
include_examples "converts_kana", "X線の研究をしています", "えっくすせんのけんきゅうをしています"
|
30
|
+
include_examples "converts_kana", "X線研究者", "えっくすせんけんきゅうしゃ"
|
31
|
+
include_examples "converts_kana", "電気通信大学X線研究", "でんきつうしんだいがくえっくすせんけんきゅう"
|
32
|
+
include_examples "converts_kana", "DNAは螺旋状の構造らしい", "でぃーえぬえーはらせんじょうのこうぞうらしい"
|
33
|
+
end
|
34
|
+
end
|
35
|
+
end
|
@@ -0,0 +1,30 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
require "spec_helper"
|
3
|
+
|
4
|
+
describe Tataki::Converter::Roman do
|
5
|
+
let(:converter) { Tataki::Converter::Roman.new }
|
6
|
+
|
7
|
+
describe ".to_kana" do
|
8
|
+
shared_examples "converts_kana" do |sentence, kana|
|
9
|
+
it "converts #{sentence.inspect} to #{kana.inspect}" do
|
10
|
+
expect(converter.to_kana(sentence)).to eq(kana)
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
include_examples "converts_kana", "", ""
|
15
|
+
include_examples "converts_kana", "hoge", "ほげ"
|
16
|
+
include_examples "converts_kana", "hogelog", "ほげぉg"
|
17
|
+
include_examples "converts_kana", "hogge", "ほっげ"
|
18
|
+
include_examples "converts_kana", "hogs", "ほgs"
|
19
|
+
include_examples "converts_kana", "nanka", "なんか"
|
20
|
+
include_examples "converts_kana", "nannnan", "なんなん"
|
21
|
+
include_examples "converts_kana", "nannnann", "なんなん"
|
22
|
+
include_examples "converts_kana", "nannnannsei", "なんなんせい"
|
23
|
+
include_examples "converts_kana", "kukkingu", "くっきんぐ"
|
24
|
+
include_examples "converts_kana", "kukkingu papa", "くっきんぐ ぱぱ"
|
25
|
+
include_examples "converts_kana", "toukyoutokkyokyokakyoku", "とうきょうとっきょきょかきょく"
|
26
|
+
|
27
|
+
include_examples "converts_kana", "kku", "っく"
|
28
|
+
include_examples "converts_kana", ",,", ",,"
|
29
|
+
end
|
30
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
require "spec_helper"
|
3
|
+
|
4
|
+
describe Tataki::Converter::SkkJisyo do
|
5
|
+
let(:converter) { Tataki::Converter::SkkJisyo.new }
|
6
|
+
|
7
|
+
describe ".to_kana" do
|
8
|
+
shared_examples "converts_kana" do |sentence, kana|
|
9
|
+
it "converts #{sentence.inspect} to #{kana.inspect}" do
|
10
|
+
expect(converter.to_kana(sentence)).to eq(kana)
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
include_examples "converts_kana", "", ""
|
15
|
+
include_examples "converts_kana", "漢字", "かんじ"
|
16
|
+
include_examples "converts_kana", "漢字変換する", "かんじへんかんする"
|
17
|
+
include_examples "converts_kana", "隣りの", "となりの"
|
18
|
+
include_examples "converts_kana", "隣りはよく柿食う", "となりはよくかきくう"
|
19
|
+
include_examples "converts_kana", "安心安全", "あんしんあんぜん"
|
20
|
+
include_examples "converts_kana", "毎朝新聞配達をしています", "まいあさしんぶんはいたつをしています"
|
21
|
+
end
|
22
|
+
end
|
data/spec/tataki_spec.rb
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
require "spec_helper"
|
3
|
+
|
4
|
+
describe Tataki do
|
5
|
+
it "has a version number" do
|
6
|
+
Tataki::VERSION.should_not be_nil
|
7
|
+
end
|
8
|
+
|
9
|
+
describe ".converters" do
|
10
|
+
it "returns converters" do
|
11
|
+
expect(Tataki.converters).to match_array([
|
12
|
+
Tataki::Converter::Roman,
|
13
|
+
Tataki::Converter::Alphabet,
|
14
|
+
Tataki::Converter::Combine,
|
15
|
+
Tataki::Converter::SkkJisyo,
|
16
|
+
])
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
describe "String.to_kana" do
|
21
|
+
it "converts to kana" do
|
22
|
+
expect("X線研究者".to_kana).to eq("えっくすせんけんきゅうしゃ")
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
data/tataki.gemspec
ADDED
@@ -0,0 +1,30 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'tataki/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "tataki"
|
8
|
+
spec.version = Tataki::VERSION
|
9
|
+
spec.authors = ["hogelog"]
|
10
|
+
spec.email = ["konbu.komuro@gmail.com"]
|
11
|
+
spec.description = %q{Kanji to Kana converter}
|
12
|
+
spec.summary = %q{Tataki is pure ruby Kanji to Kana converter.}
|
13
|
+
spec.homepage = "https://github.com/hogelog/tataki"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
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
|
+
|
21
|
+
spec.add_dependency "skk-jisyo", "~> 0.0.5"
|
22
|
+
spec.add_dependency "trie"
|
23
|
+
|
24
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
25
|
+
spec.add_development_dependency "rake"
|
26
|
+
spec.add_development_dependency "rspec"
|
27
|
+
spec.add_development_dependency "pry"
|
28
|
+
spec.add_development_dependency "guard-rspec"
|
29
|
+
spec.add_development_dependency "spring"
|
30
|
+
end
|
metadata
ADDED
@@ -0,0 +1,190 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: tataki
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.2
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- hogelog
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-10-17 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: skk-jisyo
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 0.0.5
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 0.0.5
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: trie
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: bundler
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ~>
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '1.3'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ~>
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '1.3'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rake
|
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
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: rspec
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - '>='
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - '>='
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: pry
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - '>='
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - '>='
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: guard-rspec
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - '>='
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '0'
|
104
|
+
type: :development
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - '>='
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '0'
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: spring
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - '>='
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '0'
|
118
|
+
type: :development
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - '>='
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: '0'
|
125
|
+
description: Kanji to Kana converter
|
126
|
+
email:
|
127
|
+
- konbu.komuro@gmail.com
|
128
|
+
executables: []
|
129
|
+
extensions: []
|
130
|
+
extra_rdoc_files: []
|
131
|
+
files:
|
132
|
+
- .gitignore
|
133
|
+
- .rspec
|
134
|
+
- .travis.yml
|
135
|
+
- Gemfile
|
136
|
+
- Guardfile
|
137
|
+
- LICENSE.txt
|
138
|
+
- README.md
|
139
|
+
- Rakefile
|
140
|
+
- data/alphabet.yml
|
141
|
+
- data/jisyo/.gitignore
|
142
|
+
- data/roman.yml
|
143
|
+
- data/skk-jisyo.yml
|
144
|
+
- lib/tataki.rb
|
145
|
+
- lib/tataki/base.rb
|
146
|
+
- lib/tataki/converters.rb
|
147
|
+
- lib/tataki/converters/alphabet.rb
|
148
|
+
- lib/tataki/converters/combine.rb
|
149
|
+
- lib/tataki/converters/roman.rb
|
150
|
+
- lib/tataki/converters/skk_jisyo.rb
|
151
|
+
- lib/tataki/version.rb
|
152
|
+
- spec/spec_helper.rb
|
153
|
+
- spec/tataki/converters/alphabet_spec.rb
|
154
|
+
- spec/tataki/converters/combine_spec.rb
|
155
|
+
- spec/tataki/converters/roman_spec.rb
|
156
|
+
- spec/tataki/converters/skk_jisyo_spec.rb
|
157
|
+
- spec/tataki_spec.rb
|
158
|
+
- tataki.gemspec
|
159
|
+
homepage: https://github.com/hogelog/tataki
|
160
|
+
licenses:
|
161
|
+
- MIT
|
162
|
+
metadata: {}
|
163
|
+
post_install_message:
|
164
|
+
rdoc_options: []
|
165
|
+
require_paths:
|
166
|
+
- lib
|
167
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
168
|
+
requirements:
|
169
|
+
- - '>='
|
170
|
+
- !ruby/object:Gem::Version
|
171
|
+
version: '0'
|
172
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
173
|
+
requirements:
|
174
|
+
- - '>='
|
175
|
+
- !ruby/object:Gem::Version
|
176
|
+
version: '0'
|
177
|
+
requirements: []
|
178
|
+
rubyforge_project:
|
179
|
+
rubygems_version: 2.0.3
|
180
|
+
signing_key:
|
181
|
+
specification_version: 4
|
182
|
+
summary: Tataki is pure ruby Kanji to Kana converter.
|
183
|
+
test_files:
|
184
|
+
- spec/spec_helper.rb
|
185
|
+
- spec/tataki/converters/alphabet_spec.rb
|
186
|
+
- spec/tataki/converters/combine_spec.rb
|
187
|
+
- spec/tataki/converters/roman_spec.rb
|
188
|
+
- spec/tataki/converters/skk_jisyo_spec.rb
|
189
|
+
- spec/tataki_spec.rb
|
190
|
+
has_rdoc:
|