conv_ja_char 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +13 -0
- data/.rspec +2 -0
- data/.travis.yml +5 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +7 -0
- data/LICENSE.txt +21 -0
- data/README.md +43 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/conv_ja_char.gemspec +42 -0
- data/gemtest/Gemfile +8 -0
- data/gemtest/test.rb +3 -0
- data/lib/conv_ja_char/check_char.rb +23 -0
- data/lib/conv_ja_char/constants/katakana_romaji.rb +77 -0
- data/lib/conv_ja_char/normalization.rb +18 -0
- data/lib/conv_ja_char/version.rb +3 -0
- data/lib/conv_ja_char.rb +165 -0
- metadata +175 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 57c3fd15e6ddfbec1787f943d2e20999e4912c30
|
4
|
+
data.tar.gz: c20b412c7734f64ba05ac9a8bc4763c6b089666b
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 6848b175134d2d6cfb40d76cb80411249a8ef205f249ee028d9e3774c68d7502fdc3c861c58ed0bef3739a89f3d5f2d2bcddfa1e202d07105e2c397c360eea6d
|
7
|
+
data.tar.gz: 1aa59395f3a0ff11923bef678a9276d9feedacdb893c5ecc25aef7903e21e14018afd8e681537c831c2e943b3df446d575fe2fbe2d2f27e2dcfaa752c38fa361
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# Contributor Covenant Code of Conduct
|
2
|
+
|
3
|
+
## Our Pledge
|
4
|
+
|
5
|
+
In the interest of fostering an open and welcoming environment, we as
|
6
|
+
contributors and maintainers pledge to making participation in our project and
|
7
|
+
our community a harassment-free experience for everyone, regardless of age, body
|
8
|
+
size, disability, ethnicity, gender identity and expression, level of experience,
|
9
|
+
nationality, personal appearance, race, religion, or sexual identity and
|
10
|
+
orientation.
|
11
|
+
|
12
|
+
## Our Standards
|
13
|
+
|
14
|
+
Examples of behavior that contributes to creating a positive environment
|
15
|
+
include:
|
16
|
+
|
17
|
+
* Using welcoming and inclusive language
|
18
|
+
* Being respectful of differing viewpoints and experiences
|
19
|
+
* Gracefully accepting constructive criticism
|
20
|
+
* Focusing on what is best for the community
|
21
|
+
* Showing empathy towards other community members
|
22
|
+
|
23
|
+
Examples of unacceptable behavior by participants include:
|
24
|
+
|
25
|
+
* The use of sexualized language or imagery and unwelcome sexual attention or
|
26
|
+
advances
|
27
|
+
* Trolling, insulting/derogatory comments, and personal or political attacks
|
28
|
+
* Public or private harassment
|
29
|
+
* Publishing others' private information, such as a physical or electronic
|
30
|
+
address, without explicit permission
|
31
|
+
* Other conduct which could reasonably be considered inappropriate in a
|
32
|
+
professional setting
|
33
|
+
|
34
|
+
## Our Responsibilities
|
35
|
+
|
36
|
+
Project maintainers are responsible for clarifying the standards of acceptable
|
37
|
+
behavior and are expected to take appropriate and fair corrective action in
|
38
|
+
response to any instances of unacceptable behavior.
|
39
|
+
|
40
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
41
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
42
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
43
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
44
|
+
threatening, offensive, or harmful.
|
45
|
+
|
46
|
+
## Scope
|
47
|
+
|
48
|
+
This Code of Conduct applies both within project spaces and in public spaces
|
49
|
+
when an individual is representing the project or its community. Examples of
|
50
|
+
representing a project or community include using an official project e-mail
|
51
|
+
address, posting via an official social media account, or acting as an appointed
|
52
|
+
representative at an online or offline event. Representation of a project may be
|
53
|
+
further defined and clarified by project maintainers.
|
54
|
+
|
55
|
+
## Enforcement
|
56
|
+
|
57
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
58
|
+
reported by contacting the project team at lica@nii.ac.jp. All
|
59
|
+
complaints will be reviewed and investigated and will result in a response that
|
60
|
+
is deemed necessary and appropriate to the circumstances. The project team is
|
61
|
+
obligated to maintain confidentiality with regard to the reporter of an incident.
|
62
|
+
Further details of specific enforcement policies may be posted separately.
|
63
|
+
|
64
|
+
Project maintainers who do not follow or enforce the Code of Conduct in good
|
65
|
+
faith may face temporary or permanent repercussions as determined by other
|
66
|
+
members of the project's leadership.
|
67
|
+
|
68
|
+
## Attribution
|
69
|
+
|
70
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
71
|
+
available at [http://contributor-covenant.org/version/1/4][version]
|
72
|
+
|
73
|
+
[homepage]: http://contributor-covenant.org
|
74
|
+
[version]: http://contributor-covenant.org/version/1/4/
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2017 Lica Okamoto
|
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 +1,43 @@
|
|
1
|
+
# ConvJaChar
|
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/conv_ja_char`. 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 'conv_ja_char'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install conv_ja_char
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
TODO: Write usage instructions here
|
26
|
+
|
27
|
+
## Development
|
28
|
+
|
29
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also 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`, which will 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
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/conv_ja_char. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
|
36
|
+
|
37
|
+
## License
|
38
|
+
|
39
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
40
|
+
|
41
|
+
## Code of Conduct
|
42
|
+
|
43
|
+
Everyone interacting in the ConvJaChar project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/conv_ja_char/blob/master/CODE_OF_CONDUCT.md).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "conv_ja_char"
|
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(__FILE__)
|
data/bin/setup
ADDED
@@ -0,0 +1,42 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path("../lib", __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require "conv_ja_char/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "conv_ja_char"
|
8
|
+
spec.version = ConvJaChar::VERSION
|
9
|
+
spec.authors = ["LicaOka"]
|
10
|
+
spec.email = ["lica.oka@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{a library to convert Japanese character, like Hiragana or Katanaka, to Romaji.}
|
13
|
+
spec.description = %q{this library converts Hiragana or Katakana (both, UTF-8 without BOM) to Romaji form (using roman alphabet).}
|
14
|
+
spec.homepage = "https://github.com/LicaOka/conv_ja_char"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
# Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
|
18
|
+
# to allow pushing to a single host or delete this section to allow pushing to any host.
|
19
|
+
if spec.respond_to?(:metadata)
|
20
|
+
# to allow pushing to any host
|
21
|
+
else
|
22
|
+
raise "RubyGems 2.0 or newer is required to protect against " \
|
23
|
+
"public gem pushes."
|
24
|
+
end
|
25
|
+
|
26
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
27
|
+
f.match(%r{^(test|spec|features)/})
|
28
|
+
end
|
29
|
+
spec.bindir = "exe"
|
30
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
31
|
+
spec.require_paths = ["lib"]
|
32
|
+
|
33
|
+
spec.add_development_dependency "bundler", "~> 1.14"
|
34
|
+
spec.add_development_dependency "rake", "~> 12.0"
|
35
|
+
spec.add_development_dependency "rspec", "~> 3"
|
36
|
+
|
37
|
+
spec.add_development_dependency "rubocop", "~> 0.49.1"
|
38
|
+
spec.add_development_dependency "onkcop", "~> 0.49.1"
|
39
|
+
spec.add_development_dependency "pry", "~> 0.10"
|
40
|
+
spec.add_development_dependency "pry-byebug", "~> 3.4"
|
41
|
+
spec.add_development_dependency "debase", "~> 0.2.1"
|
42
|
+
end
|
data/gemtest/Gemfile
ADDED
data/gemtest/test.rb
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
|
3
|
+
require 'conv_ja_char/version'
|
4
|
+
|
5
|
+
module ConvJaChar
|
6
|
+
class CharTypeCheck
|
7
|
+
def self.kanji?(str)
|
8
|
+
return nil unless str
|
9
|
+
|
10
|
+
regexp_kanji = /[一-龠々]+/
|
11
|
+
|
12
|
+
str =~ regexp_kanji # nil: not match, not nil: the position number that the matched char starts
|
13
|
+
end
|
14
|
+
|
15
|
+
def self.symbol?(str)
|
16
|
+
return nil unless str
|
17
|
+
|
18
|
+
regexp_symbol = /[!"#%&()*+,.\/:;<=>?@^_`{|}~]+/ # without white space, dollar sign($), single quotation(') and hyphen(-)
|
19
|
+
|
20
|
+
str =~ regexp_symbol # nil: not match, not nil: the position number that the matched char starts
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
@@ -0,0 +1,77 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
|
3
|
+
module ConvJaChar
|
4
|
+
KATANA_TO_HEBON_FORM = {
|
5
|
+
'ア' => 'a', 'イ' => 'i', 'ウ' => 'u', 'エ' => 'e', 'オ' => 'o',
|
6
|
+
'カ' => 'ka', 'キ' => 'ki', 'ク' => 'ku', 'ケ' => 'ke', 'コ' => 'ko',
|
7
|
+
'サ' => 'sa', 'シ' => 'shi', 'ス' => 'su', 'セ' => 'se', 'ソ' => 'so',
|
8
|
+
'タ' => 'ta', 'チ' => 'chi', 'ツ' => 'tsu', 'テ' => 'te', 'ト' => 'to',
|
9
|
+
'ナ' => 'na', 'ニ' => 'ni', 'ヌ' => 'nu', 'ネ' => 'ne', 'ノ' => 'no',
|
10
|
+
'ハ' => 'ha', 'ヒ' => 'hi', 'フ' => 'fu', 'ヘ' => 'he', 'ホ' => 'ho',
|
11
|
+
'マ' => 'ma', 'ミ' => 'mi', 'ム' => 'mu', 'メ' => 'me', 'モ' => 'mo',
|
12
|
+
'ヤ' => 'ya', 'ユ' => 'yu', 'ヨ' => 'yo',
|
13
|
+
'ラ' => 'ra', 'リ' => 'ri', 'ル' => 'ru', 'レ' => 're', 'ロ' => 'ro',
|
14
|
+
'ワ' => 'wa', 'ヰ' => 'wi', 'ヱ' => 'we', 'ヲ' => 'wo', 'ー' => '-',
|
15
|
+
'ガ' => 'ga', 'ギ' => 'gi', 'グ' => 'gu', 'ゲ' => 'ge', 'ゴ' => 'go',
|
16
|
+
'ザ' => 'za', 'ジ' => 'ji', 'ズ' => 'zu', 'ゼ' => 'ze', 'ゾ' => 'zo',
|
17
|
+
'ダ' => 'da', 'ヂ' => 'di', 'ヅ' => 'du', 'デ' => 'de', 'ド' => 'do',
|
18
|
+
'バ' => 'ba', 'ビ' => 'bi', 'ブ' => 'bu', 'ベ' => 'be', 'ボ' => 'bo',
|
19
|
+
'パ' => 'pa', 'ピ' => 'pi', 'プ' => 'pu', 'ペ' => 'pe', 'ポ' => 'po',
|
20
|
+
'ウィ' => 'wi','ウェ' => 'we', 'クヮ' => 'kwa', 'グヮ' => 'gwa', 'ン' => 'n',
|
21
|
+
'キャ' => 'kya', 'キィ' => 'kyi', 'キュ' => 'kyu', 'キェ' => 'kye', 'キョ' => 'kyo',
|
22
|
+
'ギャ' => 'gya', 'ギィ' => 'gyi', 'ギュ' => 'gyu', 'ギェ' => 'gye', 'ギョ' => 'gyo',
|
23
|
+
'シャ' => 'sha', 'シィ' => 'syi', 'シュ' => 'shu', 'シェ' => 'she', 'ショ' => 'sho',
|
24
|
+
'ジャ' => 'ja', 'ジィ' => 'jyi', 'ジュ' => 'ju', 'ジェ' => 'je', 'ジョ' => 'jo',
|
25
|
+
'チャ' => 'cha', 'チィ' => 'cyi', 'チュ' => 'chu', 'チェ' => 'che', 'チョ' => 'cho',
|
26
|
+
'ヂャ' => 'dya', 'ヂィ' => 'dyi', 'ヂュ' => 'dyu', 'ヂェ' => 'dye', 'ヂョ' => 'dyo',
|
27
|
+
'テャ' => 'tha', 'ティ' => 'thi', 'テュ' => 'thu', 'テェ' => 'the', 'テョ' => 'tho',
|
28
|
+
'デャ' => 'dha', 'ディ' => 'dhi', 'デュ' => 'dhu', 'デェ' => 'dhe', 'デョ' => 'dho',
|
29
|
+
'ニャ' => 'nya', 'ニィ' => 'nyi', 'ニュ' => 'nyu', 'ニェ' => 'nye', 'ニョ' => 'nyo',
|
30
|
+
'ヒャ' => 'hya', 'ヒィ' => 'hyi', 'ヒュ' => 'hyu', 'ヒェ' => 'hye', 'ヒョ' => 'hyo',
|
31
|
+
'ビャ' => 'bya', 'ビィ' => 'byi', 'ビュ' => 'byu', 'ビェ' => 'bye', 'ビョ' => 'byo',
|
32
|
+
'ピャ' => 'pya', 'ピィ' => 'pyi', 'ピュ' => 'pyu', 'ピェ' => 'pye', 'ピョ' => 'pyo',
|
33
|
+
'ファ' => 'fa', 'フィ' => 'fi', 'フュ' => 'fyu', 'フェ' => 'fe', 'フォ' => 'fo',
|
34
|
+
'ミャ' => 'mya', 'ミィ' => 'myi', 'ミュ' => 'myu', 'ミェ' => 'mye', 'ミョ' => 'myo',
|
35
|
+
'リャ' => 'rya', 'リィ' => 'ryi', 'リュ' => 'ryu', 'リェ' => 'rye', 'リョ' => 'ryo',
|
36
|
+
'ヴァ' => 'va', 'ヴィ' => 'vi', 'ヴ' => 'vu', 'ヴェ' => 've', 'ヴォ' => 'vo'
|
37
|
+
}.freeze
|
38
|
+
|
39
|
+
KATANA_TO_KUNREI_FORM = {
|
40
|
+
'ア' => 'a', 'イ' => 'i', 'ウ' => 'u', 'エ' => 'e', 'オ' => 'o',
|
41
|
+
'カ' => 'ka', 'キ' => 'ki', 'ク' => 'ku', 'ケ' => 'ke', 'コ' => 'ko',
|
42
|
+
'サ' => 'sa', 'シ' => 'si', 'ス' => 'su', 'セ' => 'se', 'ソ' => 'so',
|
43
|
+
'タ' => 'ta', 'チ' => 'ti', 'ツ' => 'tu', 'テ' => 'te', 'ト' => 'to',
|
44
|
+
'ナ' => 'na', 'ニ' => 'ni', 'ヌ' => 'nu', 'ネ' => 'ne', 'ノ' => 'no',
|
45
|
+
'ハ' => 'ha', 'ヒ' => 'hi', 'フ' => 'fu', 'ヘ' => 'he', 'ホ' => 'ho',
|
46
|
+
'マ' => 'ma', 'ミ' => 'mi', 'ム' => 'mu', 'メ' => 'me', 'モ' => 'mo',
|
47
|
+
'ヤ' => 'ya', 'ユ' => 'yu', 'ヨ' => 'yo',
|
48
|
+
'ラ' => 'ra', 'リ' => 'ri', 'ル' => 'ru', 'レ' => 're', 'ロ' => 'ro',
|
49
|
+
'ワ' => 'wa', 'ヰ' => 'wi', 'ヱ' => 'we', 'ヲ' => 'wo', 'ー' => '-',
|
50
|
+
'ガ' => 'ga', 'ギ' => 'gi', 'グ' => 'gu', 'ゲ' => 'ge', 'ゴ' => 'go',
|
51
|
+
'ザ' => 'za', 'ジ' => 'zi', 'ズ' => 'zu', 'ゼ' => 'ze', 'ゾ' => 'zo',
|
52
|
+
'ダ' => 'da', 'ヂ' => 'zi', 'ヅ' => 'zu', 'デ' => 'de', 'ド' => 'do',
|
53
|
+
'バ' => 'ba', 'ビ' => 'bi', 'ブ' => 'bu', 'ベ' => 'be', 'ボ' => 'bo',
|
54
|
+
'パ' => 'pa', 'ピ' => 'pi', 'プ' => 'pu', 'ペ' => 'pe', 'ポ' => 'po',
|
55
|
+
'ウィ' => 'wi', 'ウェ' => 'we', 'クヮ' => 'kwa', 'グヮ' => 'gwa', 'ン' => 'n',
|
56
|
+
'キャ' => 'kya', 'キィ' => 'kyi', 'キュ' => 'kyu', 'キェ' => 'kye', 'キョ' => 'kyo',
|
57
|
+
'ギャ' => 'gya', 'ギィ' => 'gyi', 'ギュ' => 'gyu', 'ギェ' => 'gye', 'ギョ' => 'gyo',
|
58
|
+
'シャ' => 'sya', 'シィ' => 'syi', 'シュ' => 'syu', 'シェ' => 'sye', 'ショ' => 'syo',
|
59
|
+
'ジャ' => 'zya', 'ジィ' => 'zyi', 'ジュ' => 'zyu', 'ジェ' => 'zye', 'ジョ' => 'zyo',
|
60
|
+
'チャ' => 'tya', 'チィ' => 'tyi', 'チュ' => 'tyu', 'チェ' => 'tye', 'チョ' => 'tyo',
|
61
|
+
'ヂャ' => 'zya', 'ヂィ' => 'zyi', 'ヂュ' => 'zyu', 'ヂェ' => 'zye', 'ヂョ' => 'zyo',
|
62
|
+
'テャ' => 'tha', 'ティ' => 'thi', 'テュ' => 'thu', 'テェ' => 'the', 'テョ' => 'tho',
|
63
|
+
'デャ' => 'dha', 'ディ' => 'dhi', 'デュ' => 'dhu', 'デェ' => 'dhe', 'デョ' => 'dho',
|
64
|
+
'ニャ' => 'nya', 'ニィ' => 'nyi', 'ニュ' => 'nyu', 'ニェ' => 'nye', 'ニョ' => 'nyo',
|
65
|
+
'ヒャ' => 'hya', 'ヒィ' => 'hyi', 'ヒュ' => 'hyu', 'ヒェ' => 'hye', 'ヒョ' => 'hyo',
|
66
|
+
'ビャ' => 'bya', 'ビィ' => 'byi', 'ビュ' => 'byu', 'ビェ' => 'bye', 'ビョ' => 'byo',
|
67
|
+
'ピャ' => 'pya', 'ピィ' => 'pyi', 'ピュ' => 'pyu', 'ピェ' => 'pye', 'ピョ' => 'pyo',
|
68
|
+
'ファ' => 'fa', 'フィ' => 'fi', 'フュ' => 'fyu', 'フェ' => 'fe', 'フォ' => 'fo',
|
69
|
+
'ミャ' => 'mya', 'ミィ' => 'myi', 'ミュ' => 'myu', 'ミェ' => 'mye', 'ミョ' => 'myo',
|
70
|
+
'リャ' => 'rya', 'リィ' => 'ryi', 'リュ' => 'ryu', 'リェ' => 'rye', 'リョ' => 'ryo',
|
71
|
+
'ヴァ' => 'va', 'ヴィ' => 'vi', 'ヴ' => 'vu', 'ヴェ' => 've', 'ヴォ' => 'vo'
|
72
|
+
}.freeze
|
73
|
+
|
74
|
+
SMALL_KANA_FOR_CONTRACTED_SOUND = %w(ァ ィ ェ ォ ャ ュ ョ ヮ).freeze
|
75
|
+
|
76
|
+
DOUBLE_CONSONANT_SOUND = 'ッ'.freeze
|
77
|
+
end
|
@@ -0,0 +1,18 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
|
3
|
+
require 'nkf'
|
4
|
+
require 'conv_ja_char/version'
|
5
|
+
|
6
|
+
module ConvJaChar
|
7
|
+
class Normalization
|
8
|
+
def self.kana(str)
|
9
|
+
return '' unless str
|
10
|
+
# -Z1 : convert from X0208 white sapce to ASCII white space
|
11
|
+
# -X : convert from X0201 half-size katanaka to X0208 full-size katakana
|
12
|
+
# -w : output UTF-8 without BOM
|
13
|
+
# --katakana : convert from hiragana to katakana
|
14
|
+
NKF.nkf('-Z1 -X -w --katakana', "#{str}").downcase
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
data/lib/conv_ja_char.rb
ADDED
@@ -0,0 +1,165 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
|
3
|
+
require 'nkf'
|
4
|
+
require 'conv_ja_char/version'
|
5
|
+
require 'conv_ja_char/constants/katakana_romaji'
|
6
|
+
require 'conv_ja_char/normalization'
|
7
|
+
require 'conv_ja_char/check_char'
|
8
|
+
|
9
|
+
# conv_ja_char return value
|
10
|
+
# something romaji string : when ConvJaChar.to_romaji successes
|
11
|
+
# nil : when ConvJaChar.to_romaji has some errors
|
12
|
+
|
13
|
+
# conv_ja_char does not accept Kanji char currently.
|
14
|
+
|
15
|
+
module ConvJaChar
|
16
|
+
class << self
|
17
|
+
def to_romaji(str, option)
|
18
|
+
return str unless str.nil?
|
19
|
+
if str == ''
|
20
|
+
return str
|
21
|
+
end
|
22
|
+
|
23
|
+
@opt = ''
|
24
|
+
set_option(option)
|
25
|
+
|
26
|
+
binding.pry
|
27
|
+
|
28
|
+
if ConvJaChar::CharTypeCheck::kanji?(str) != nil
|
29
|
+
p "there seems to be Kanji char in #{str}. conv_ja_char does not accept Kanji char currently."
|
30
|
+
return str
|
31
|
+
end
|
32
|
+
|
33
|
+
binding.pry
|
34
|
+
|
35
|
+
@t = set_char_table(@opt)
|
36
|
+
|
37
|
+
@chars = ConvJaChar::Normalization.kana(str).split(//u)
|
38
|
+
|
39
|
+
@romaji = ''
|
40
|
+
@pos = 0
|
41
|
+
while @pos < @chars.size
|
42
|
+
@c = @chars[@pos]
|
43
|
+
|
44
|
+
if @c == (' ' || '$' || '-' || '\'')
|
45
|
+
@romaji += @c
|
46
|
+
@pos += 1
|
47
|
+
next
|
48
|
+
end
|
49
|
+
|
50
|
+
if ConvJaChar::CharTypeCheck::symbol?(@c) != nil
|
51
|
+
@romaji += @c
|
52
|
+
@pos += 1
|
53
|
+
next
|
54
|
+
end
|
55
|
+
|
56
|
+
@c_next = ''
|
57
|
+
set_next_char
|
58
|
+
|
59
|
+
case @c
|
60
|
+
when 'ン'
|
61
|
+
process_nasal_sound_change
|
62
|
+
next
|
63
|
+
when 'ッ'
|
64
|
+
process_sound_change_to_double_consonant
|
65
|
+
next
|
66
|
+
when 'ウ','キ','ギ','ク','グ','シ','ジ','チ','ヂ','テ','デ','ニ','ヒ','ビ','ピ','フ','ミ','リ','ヴ'
|
67
|
+
if @c_next.nil?
|
68
|
+
process_normal_char
|
69
|
+
next
|
70
|
+
end
|
71
|
+
if SMALL_KANA_FOR_CONTRACTED_SOUND.include?(@c_next)
|
72
|
+
process_contracted_sound
|
73
|
+
next
|
74
|
+
else
|
75
|
+
process_normal_char
|
76
|
+
next
|
77
|
+
end
|
78
|
+
else
|
79
|
+
process_normal_char
|
80
|
+
end
|
81
|
+
end
|
82
|
+
|
83
|
+
@romaji
|
84
|
+
end
|
85
|
+
|
86
|
+
private
|
87
|
+
|
88
|
+
def set_option(option)
|
89
|
+
case option
|
90
|
+
when 'Kunrei'
|
91
|
+
@opt = 'Kunrei'
|
92
|
+
when 'Hebon'
|
93
|
+
@opt = 'Hebon'
|
94
|
+
else
|
95
|
+
@opt = 'Kunrei'
|
96
|
+
end
|
97
|
+
end
|
98
|
+
|
99
|
+
def set_next_char
|
100
|
+
if (@pos + 1) < @chars.size
|
101
|
+
@c_next = @chars[@pos+1]
|
102
|
+
else
|
103
|
+
@c_next = nil
|
104
|
+
end
|
105
|
+
end
|
106
|
+
|
107
|
+
def set_char_table(op)
|
108
|
+
case op
|
109
|
+
when 'Hebon'
|
110
|
+
ConvJaChar::KATANA_TO_HEBON_FORM
|
111
|
+
when 'Kunrei'
|
112
|
+
ConvJaChar::KATANA_TO_KUNREI_FORM
|
113
|
+
else
|
114
|
+
ConvJaChar::KATANA_TO_KUNREI_FORM
|
115
|
+
end
|
116
|
+
end
|
117
|
+
|
118
|
+
def process_normal_char
|
119
|
+
@romaji += @t[@c]
|
120
|
+
@pos += 1
|
121
|
+
end
|
122
|
+
|
123
|
+
def process_nasal_sound_change(op) # ex.:'ン'
|
124
|
+
s = @t[@c_next]
|
125
|
+
|
126
|
+
case op
|
127
|
+
when 'Hebon'
|
128
|
+
if ['p','b','m'].include?(s[0])
|
129
|
+
@romaji += 'm'
|
130
|
+
else
|
131
|
+
@romaji += @t[@c]
|
132
|
+
if ['a','i','u','e','o','y','n'].include?(s[0])
|
133
|
+
@romaji += '\''
|
134
|
+
end
|
135
|
+
end
|
136
|
+
when 'Kunrei'
|
137
|
+
@romaji += @t[@c]
|
138
|
+
if ['a','i','u','e','o','y','n'].include?(s[0])
|
139
|
+
@romaji += '\''
|
140
|
+
end
|
141
|
+
end
|
142
|
+
|
143
|
+
@pos += 1
|
144
|
+
end
|
145
|
+
|
146
|
+
def process_sound_change_to_double_consonant # ex.:'ッ'
|
147
|
+
r = @t[@c_next]
|
148
|
+
if @c_next == DOUBLE_CONSONANT_SOUND || ['a','i','u','e','o','n',nil].include?(r[0]) || r.nil?
|
149
|
+
@romaji += 'xtsu'
|
150
|
+
else
|
151
|
+
@romaji += r[0].slice(0,1)
|
152
|
+
end
|
153
|
+
@pos += 1
|
154
|
+
end
|
155
|
+
|
156
|
+
def process_contracted_sound # ex.:'キャ'
|
157
|
+
s = @c + @c_next
|
158
|
+
@romaji += @t[s]
|
159
|
+
@pos += 2
|
160
|
+
end
|
161
|
+
end
|
162
|
+
|
163
|
+
# class Romaji TODO: to be implemented
|
164
|
+
# class Kanji TODO: to be implemented
|
165
|
+
end
|
metadata
ADDED
@@ -0,0 +1,175 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: conv_ja_char
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- LicaOka
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2017-08-03 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: '1.14'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.14'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '12.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '12.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '3'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '3'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rubocop
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 0.49.1
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: 0.49.1
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: onkcop
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: 0.49.1
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: 0.49.1
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: pry
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0.10'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0.10'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: pry-byebug
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - "~>"
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '3.4'
|
104
|
+
type: :development
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - "~>"
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '3.4'
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: debase
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - "~>"
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: 0.2.1
|
118
|
+
type: :development
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - "~>"
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: 0.2.1
|
125
|
+
description: this library converts Hiragana or Katakana (both, UTF-8 without BOM)
|
126
|
+
to Romaji form (using roman alphabet).
|
127
|
+
email:
|
128
|
+
- lica.oka@gmail.com
|
129
|
+
executables: []
|
130
|
+
extensions: []
|
131
|
+
extra_rdoc_files: []
|
132
|
+
files:
|
133
|
+
- ".gitignore"
|
134
|
+
- ".rspec"
|
135
|
+
- ".travis.yml"
|
136
|
+
- CODE_OF_CONDUCT.md
|
137
|
+
- Gemfile
|
138
|
+
- LICENSE.txt
|
139
|
+
- README.md
|
140
|
+
- Rakefile
|
141
|
+
- bin/console
|
142
|
+
- bin/setup
|
143
|
+
- conv_ja_char.gemspec
|
144
|
+
- gemtest/Gemfile
|
145
|
+
- gemtest/test.rb
|
146
|
+
- lib/conv_ja_char.rb
|
147
|
+
- lib/conv_ja_char/check_char.rb
|
148
|
+
- lib/conv_ja_char/constants/katakana_romaji.rb
|
149
|
+
- lib/conv_ja_char/normalization.rb
|
150
|
+
- lib/conv_ja_char/version.rb
|
151
|
+
homepage: https://github.com/LicaOka/conv_ja_char
|
152
|
+
licenses:
|
153
|
+
- MIT
|
154
|
+
metadata: {}
|
155
|
+
post_install_message:
|
156
|
+
rdoc_options: []
|
157
|
+
require_paths:
|
158
|
+
- lib
|
159
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
160
|
+
requirements:
|
161
|
+
- - ">="
|
162
|
+
- !ruby/object:Gem::Version
|
163
|
+
version: '0'
|
164
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
165
|
+
requirements:
|
166
|
+
- - ">="
|
167
|
+
- !ruby/object:Gem::Version
|
168
|
+
version: '0'
|
169
|
+
requirements: []
|
170
|
+
rubyforge_project:
|
171
|
+
rubygems_version: 2.5.1
|
172
|
+
signing_key:
|
173
|
+
specification_version: 4
|
174
|
+
summary: a library to convert Japanese character, like Hiragana or Katanaka, to Romaji.
|
175
|
+
test_files: []
|