ruslat 0.1.0
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/CODE_OF_CONDUCT.md +49 -0
- data/LICENSE.txt +21 -0
- data/README.md +47 -0
- data/exe/ruslat +3 -0
- data/lib/ruslat.rb +9 -0
- data/lib/ruslat/core.rb +290 -0
- data/lib/ruslat/version.rb +3 -0
- metadata +109 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 91a568d57913415df95dbac2caaaec616b757dea
|
4
|
+
data.tar.gz: ec272ca1a3a396e5dff22673029db839dfe1aef9
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: bc734be13097122eb929786aa3771f80eefa35324dff3216b3242663ba43ddc7a721f6890b5ace3923da4f5dce042e2e18ba6ebc09b073dc3faddb2ed6dfbc53
|
7
|
+
data.tar.gz: 468a4b313f3c10b5b80207f0ad043cb1dd319107861dcb2bf15b1a6a6fd8abcffaa3c3c56a0ee58ff44d5cd166ca42435ce7eddbb86a9f128ff7343df71f5b57
|
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,49 @@
|
|
1
|
+
# Contributor Code of Conduct
|
2
|
+
|
3
|
+
As contributors and maintainers of this project, and in the interest of
|
4
|
+
fostering an open and welcoming community, we pledge to respect all people who
|
5
|
+
contribute through reporting issues, posting feature requests, updating
|
6
|
+
documentation, submitting pull requests or patches, and other activities.
|
7
|
+
|
8
|
+
We are committed to making participation in this project a harassment-free
|
9
|
+
experience for everyone, regardless of level of experience, gender, gender
|
10
|
+
identity and expression, sexual orientation, disability, personal appearance,
|
11
|
+
body size, race, ethnicity, age, religion, or nationality.
|
12
|
+
|
13
|
+
Examples of unacceptable behavior by participants include:
|
14
|
+
|
15
|
+
* The use of sexualized language or imagery
|
16
|
+
* Personal attacks
|
17
|
+
* Trolling or insulting/derogatory comments
|
18
|
+
* Public or private harassment
|
19
|
+
* Publishing other's private information, such as physical or electronic
|
20
|
+
addresses, without explicit permission
|
21
|
+
* Other unethical or unprofessional conduct
|
22
|
+
|
23
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
24
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
25
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
26
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
27
|
+
threatening, offensive, or harmful.
|
28
|
+
|
29
|
+
By adopting this Code of Conduct, project maintainers commit themselves to
|
30
|
+
fairly and consistently applying these principles to every aspect of managing
|
31
|
+
this project. Project maintainers who do not follow or enforce the Code of
|
32
|
+
Conduct may be permanently removed from the project team.
|
33
|
+
|
34
|
+
This code of conduct applies both within project spaces and in public spaces
|
35
|
+
when an individual is representing the project or its community.
|
36
|
+
|
37
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
38
|
+
reported by contacting a project maintainer at vsuhachev@yandex.ru. All
|
39
|
+
complaints will be reviewed and investigated and will result in a response that
|
40
|
+
is deemed necessary and appropriate to the circumstances. Maintainers are
|
41
|
+
obligated to maintain confidentiality with regard to the reporter of an
|
42
|
+
incident.
|
43
|
+
|
44
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage],
|
45
|
+
version 1.3.0, available at
|
46
|
+
[http://contributor-covenant.org/version/1/3/0/][version]
|
47
|
+
|
48
|
+
[homepage]: http://contributor-covenant.org
|
49
|
+
[version]: http://contributor-covenant.org/version/1/3/0/
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2016 vs
|
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 +1,47 @@
|
|
1
|
+
# Ruslat
|
2
|
+
|
3
|
+
Ruslat is library for bidirectional transliteration for russian to latin.
|
4
|
+
|
5
|
+
It is Ruby implementation of Andrey V. Lukyanov transliteration system. See http://tapemark.narod.ru/ruslat.html for more info.
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'ruslat'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install ruslat
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
```ruby
|
26
|
+
require 'ruslat'
|
27
|
+
|
28
|
+
extend Ruslat::Core
|
29
|
+
|
30
|
+
puts rus_to_lat('Привет Мир!')
|
31
|
+
puts lat_to_rus(rus_to_lat('Привет Мир!'))
|
32
|
+
```
|
33
|
+
|
34
|
+
## Development
|
35
|
+
|
36
|
+
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.
|
37
|
+
|
38
|
+
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).
|
39
|
+
|
40
|
+
## Contributing
|
41
|
+
|
42
|
+
Bug reports and pull requests are welcome on GitHub at [https://github.com/vsuhachev/ruslat](https://github.com/vsuhachev/ruslat). 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.
|
43
|
+
|
44
|
+
|
45
|
+
## License
|
46
|
+
|
47
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
data/exe/ruslat
ADDED
data/lib/ruslat.rb
ADDED
data/lib/ruslat/core.rb
ADDED
@@ -0,0 +1,290 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
|
3
|
+
module Ruslat
|
4
|
+
# (c) 2008 Andrey V. Lukyanov (e-mail: land@long.yar.ru)
|
5
|
+
# License: I grant anyone the right to use this program
|
6
|
+
# for any purpose, without any conditions.
|
7
|
+
#
|
8
|
+
# см. http://tapemark.narod.ru/ruslat.html
|
9
|
+
#
|
10
|
+
# Обозначения:
|
11
|
+
# * RUSLAT - #rus_to_lat
|
12
|
+
# * LATRUS - #lat_to_rus
|
13
|
+
# * CASECORRECT - #case_correct
|
14
|
+
# * LCORRECT - #typo_correct
|
15
|
+
#
|
16
|
+
# RUSLAT перекодирует кириллицу в латиницу.
|
17
|
+
#
|
18
|
+
# LATRUS перекодирует латиницу в кириллицу.
|
19
|
+
#
|
20
|
+
# Круговое преобразование RUSLAT+LATRUS восстанавливает исходный русский
|
21
|
+
# текст, причём в любом случае полностью восстанавливается также
|
22
|
+
# распределение заглавных и строчных букв.
|
23
|
+
#
|
24
|
+
# Однако преобразование LATRUS+RUSLAT не обязательно восстанавливает исходный
|
25
|
+
# текст в латинице.
|
26
|
+
#
|
27
|
+
# Скрипт RUSLAT не рассчитан на обработку текста, в котором перепутаны
|
28
|
+
# русские и латинские буквы (например: а/a, с/c, р/p, у/y и т. п.); в этом
|
29
|
+
# случае надо предварительно пропустить текст через скрипт LCORRECT.
|
30
|
+
#
|
31
|
+
# CASECORRECT исправляет в латинице регистр букв в словах, которые целиком
|
32
|
+
# должны быть написаны заглавными буквами (например, АЛЁША → ALYoShA →
|
33
|
+
# ALYOSHA). Обычно применяется преобразование RUSLAT+CASECORRECT. Следует
|
34
|
+
# учитывать, что изменяется регистр не только в том тексте, который
|
35
|
+
# изначально был написан русскими буквами, но и там, где изначально была
|
36
|
+
# латиница, поэтому CASECORRECT не следует применять к текстам программ.
|
37
|
+
# Кроме того, при круговом преобразовании RUSLAT+CASECORRECT+LATRUS исходный
|
38
|
+
# русский текст не полностью восстанавливается (состав букв будет полностью
|
39
|
+
# совпадать, но регистр букв может поменяться). CASECORRECT рассчитан на GNU
|
40
|
+
# sed, в других вариантах sed он может не работать.
|
41
|
+
#
|
42
|
+
# Если в вашей системе используется кодировка, в которой нет значка номера
|
43
|
+
# (например, КОИ-8), то надо закомментировать или удалить последнюю строку в
|
44
|
+
# RUSLAT и первую строку замены в LATRUS (т. е. те строки, где есть №/Nh).
|
45
|
+
module Core
|
46
|
+
# Russian to Latin converter
|
47
|
+
def rus_to_lat(string)
|
48
|
+
string.dup.tap do |str|
|
49
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ьй([аоуАОУ])/, '\1jy\2')
|
50
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])Ьй([аоуАОУ])/, '\1Jy\2')
|
51
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ьЙ([аоуАОУ])/, '\1jY\2')
|
52
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ЬЙ([аоуАОУ])/, '\1JY\2')
|
53
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ьйе/, '\1jye')
|
54
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ьЙе/, '\1jYe')
|
55
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ьйЕ/, '\1jyE')
|
56
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ьЙЕ/, '\1jYE')
|
57
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])Ьйе/, '\1Jye')
|
58
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ЬЙе/, '\1JYe')
|
59
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ЬйЕ/, '\1JyE')
|
60
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ЬЙЕ/, '\1JYE')
|
61
|
+
|
62
|
+
str.gsub!(/([аеёийоуъыьэюяАЕЁИЙОУЪЫЬЭЮЯEe])й([аоуАОУ])/, '\1y\2')
|
63
|
+
str.gsub!(/([аеёийоуъыьэюяАЕЁИЙОУЪЫЬЭЮЯEe])й([аоуАОУ])/, '\1y\2')
|
64
|
+
str.gsub!(/([аеёийоуъыьэюяАЕЁИЙОУЪЫЬЭЮЯEe])Й([аоуАОУ])/, '\1Y\2')
|
65
|
+
str.gsub!(/([аеёийоуъыьэюяАЕЁИЙОУЪЫЬЭЮЯEe])Й([аоуАОУ])/, '\1Y\2')
|
66
|
+
|
67
|
+
str.gsub!(/([^абвгдеёжзийклмнопрстуфхцчшщъыьэюяАБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯeEyY])й([аоуАОУ])/, '\1y\2')
|
68
|
+
str.gsub!(/([^абвгдеёжзийклмнопрстуфхцчшщъыьэюяАБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯeEyY])Й([аоуАОУ])/, '\1Y\2')
|
69
|
+
str.gsub!(/^й([аоуАОУ])/, 'y\1')
|
70
|
+
str.gsub!(/^Й([аоуАОУ])/, 'Y\1')
|
71
|
+
|
72
|
+
str.gsub!(/([аеёийоуъыьэюяАЕЁИЙОУЪЫЬЭЮЯEe])йе/, '\1ye')
|
73
|
+
str.gsub!(/([аеёийоуъыьэюяАЕЁИЙОУЪЫЬЭЮЯEe])Йе/, '\1Ye')
|
74
|
+
str.gsub!(/([аеёийоуъыьэюяАЕЁИЙОУЪЫЬЭЮЯEe])йЕ/, '\1yE')
|
75
|
+
str.gsub!(/([аеёийоуъыьэюяАЕЁИЙОУЪЫЬЭЮЯEe])ЙЕ/, '\1YE')
|
76
|
+
|
77
|
+
str.gsub!(/([^абвгдеёжзийклмнопрстуфхцчшщъыьэюяАБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯeEyY])йе/, '\1ye')
|
78
|
+
str.gsub!(/([^абвгдеёжзийклмнопрстуфхцчшщъыьэюяАБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯeEyY])Йе/, '\1Ye')
|
79
|
+
str.gsub!(/([^абвгдеёжзийклмнопрстуфхцчшщъыьэюяАБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯeEyY])йЕ/, '\1yE')
|
80
|
+
str.gsub!(/([^абвгдеёжзийклмнопрстуфхцчшщъыьэюяАБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯeEyY])ЙЕ/, '\1YE')
|
81
|
+
str.gsub!(/^йе/, 'ye')
|
82
|
+
str.gsub!(/^Йе/, 'Ye')
|
83
|
+
str.gsub!(/^йЕ/, 'yE')
|
84
|
+
str.gsub!(/^ЙЕ/, 'YE')
|
85
|
+
|
86
|
+
str.gsub!(/йэ/, 'йeh')
|
87
|
+
str.gsub!(/Йэ/, 'Йeh')
|
88
|
+
str.gsub!(/йЭ/, 'йEh')
|
89
|
+
str.gsub!(/ЙЭ/, 'ЙEH')
|
90
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])й/, '\1ih')
|
91
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])Й/, '\1Ih')
|
92
|
+
|
93
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ье/, '\1je')
|
94
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])Ье/, '\1Je')
|
95
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ьЕ/, '\1jE')
|
96
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ЬЕ/, '\1JE')
|
97
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ьё/, '\1jo')
|
98
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])Ьё/, '\1Jo')
|
99
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ьЁ/, '\1jO')
|
100
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ЬЁ/, '\1JO')
|
101
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ью/, '\1ju')
|
102
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])Ью/, '\1Ju')
|
103
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ьЮ/, '\1jU')
|
104
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ЬЮ/, '\1JU')
|
105
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ья/, '\1ja')
|
106
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])Ья/, '\1Ja')
|
107
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ьЯ/, '\1jA')
|
108
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ЬЯ/, '\1JA')
|
109
|
+
|
110
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ь([бвгджзийклмнпрстфхцчшщБВГДЖЗИЙКЛМНПРСТФХЦЧШЩ])/, '\1j\2')
|
111
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])Ь([бвгджзийклмнпрстфхцчшщБВГДЖЗИЙКЛМНПРСТФХЦЧШЩ])/, '\1J\2')
|
112
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ь$/, '\1j')
|
113
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])Ь$/, '\1J')
|
114
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ь([^абвгдеёжзийклмнопрстуфхцчшщъыьэюяАБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯeEyY])/, '\1j\2')
|
115
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])Ь([^абвгдеёжзийклмнопрстуфхцчшщъыьэюяАБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯeEyY])/, '\1J\2')
|
116
|
+
str.gsub!(/ь/, 'jh')
|
117
|
+
str.gsub!(/Ь/, 'Jh')
|
118
|
+
|
119
|
+
str.gsub!(/й/, 'j')
|
120
|
+
str.gsub!(/Й/, 'J')
|
121
|
+
|
122
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])е/, '\1e')
|
123
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])Е/, '\1E')
|
124
|
+
str.gsub!(/е/, 'je')
|
125
|
+
str.gsub!(/Е/, 'Je')
|
126
|
+
|
127
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ё/, '\1yo')
|
128
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])Ё/, '\1Yo')
|
129
|
+
str.gsub!(/ё/, 'jo')
|
130
|
+
str.gsub!(/Ё/, 'Jo')
|
131
|
+
|
132
|
+
str.gsub!(/ы([аоуэАОУЭ])/, 'yh\1')
|
133
|
+
str.gsub!(/Ы([аоуэАОУЭ])/, 'Yh\1')
|
134
|
+
str.gsub!(/ы/, 'y')
|
135
|
+
str.gsub!(/Ы/, 'Y')
|
136
|
+
|
137
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])э/, '\1eh')
|
138
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])Э/, '\1Eh')
|
139
|
+
str.gsub!(/э/, 'e')
|
140
|
+
str.gsub!(/Э/, 'E')
|
141
|
+
|
142
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])ю/, '\1yu')
|
143
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])Ю/, '\1Yu')
|
144
|
+
str.gsub!(/ю/, 'ju')
|
145
|
+
str.gsub!(/Ю/, 'Ju')
|
146
|
+
|
147
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])я/, '\1ya')
|
148
|
+
str.gsub!(/([бвгджзклмнпрстфхцчшщБВГДЖЗКЛМНПРСТФХЦЧШЩ])Я/, '\1Ya')
|
149
|
+
str.gsub!(/я/, 'ja')
|
150
|
+
str.gsub!(/Я/, 'Ja')
|
151
|
+
|
152
|
+
str.gsub!(/ж/, 'zh')
|
153
|
+
str.gsub!(/ч/, 'ch')
|
154
|
+
str.gsub!(/ш/, 'sh')
|
155
|
+
str.gsub!(/щ/, 'xh')
|
156
|
+
str.gsub!(/Ж/, 'Zh')
|
157
|
+
str.gsub!(/Ч/, 'Ch')
|
158
|
+
str.gsub!(/Ш/, 'Sh')
|
159
|
+
str.gsub!(/Щ/, 'Xh')
|
160
|
+
|
161
|
+
str.tr!('абвгдзиклмнопрстуфхцъАБВГДЗИКЛМНОПРСТУФХЦЪ', 'abvgdziklmnoprstufxcqABVGDZIKLMNOPRSTUFXCQ')
|
162
|
+
|
163
|
+
str.gsub!(/№/, 'Nh')
|
164
|
+
end
|
165
|
+
end
|
166
|
+
|
167
|
+
# Latin to Russian converter
|
168
|
+
def lat_to_rus(string)
|
169
|
+
string.dup.tap do |str|
|
170
|
+
str.gsub!(/[nN][hH]/, '№')
|
171
|
+
str.gsub!(/e[hH]/, 'э')
|
172
|
+
str.gsub!(/E[hH]/, 'Э')
|
173
|
+
str.gsub!(/i[hH]/, 'й')
|
174
|
+
str.gsub!(/I[hH]/, 'Й')
|
175
|
+
str.gsub!(/j[hH]/, 'ь')
|
176
|
+
str.gsub!(/J[hH]/, 'Ь')
|
177
|
+
str.gsub!(/y[hH]/, 'ы')
|
178
|
+
str.gsub!(/Y[hH]/, 'Ы')
|
179
|
+
|
180
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])ja/, '\1ья')
|
181
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])jA/, '\1ьЯ')
|
182
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])Ja/, '\1Ья')
|
183
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])JA/, '\1ЬЯ')
|
184
|
+
str.gsub!(/j[aA]/, 'я')
|
185
|
+
str.gsub!(/J[aA]/, 'Я')
|
186
|
+
|
187
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])je/, '\1ье')
|
188
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])jE/, '\1ьЕ')
|
189
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])Je/, '\1Ье')
|
190
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])JE/, '\1ЬЕ')
|
191
|
+
str.gsub!(/j[eE]/, 'е')
|
192
|
+
str.gsub!(/J[eE]/, 'Е')
|
193
|
+
|
194
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])ji/, '\1ьи')
|
195
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])jI/, '\1ьИ')
|
196
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])Ji/, '\1Ьи')
|
197
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])JI/, '\1ЬИ')
|
198
|
+
str.gsub!(/ji/, 'йи')
|
199
|
+
str.gsub!(/jI/, 'йИ')
|
200
|
+
str.gsub!(/Ji/, 'Йи')
|
201
|
+
str.gsub!(/JI/, 'ЙИ')
|
202
|
+
|
203
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])jo/, '\1ьё')
|
204
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])jO/, '\1ьЁ')
|
205
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])Jo/, '\1Ьё')
|
206
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])JO/, '\1ЬЁ')
|
207
|
+
str.gsub!(/j[oO]/, 'ё')
|
208
|
+
str.gsub!(/J[oO]/, 'Ё')
|
209
|
+
|
210
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])ju/, '\1ью')
|
211
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])jU/, '\1ьЮ')
|
212
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])Ju/, '\1Ью')
|
213
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])JU/, '\1ЬЮ')
|
214
|
+
str.gsub!(/j[uU]/, 'ю')
|
215
|
+
str.gsub!(/J[uU]/, 'Ю')
|
216
|
+
|
217
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])y[aA]/, '\1я')
|
218
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])Y[aA]/, '\1Я')
|
219
|
+
str.gsub!(/ya/, 'йа')
|
220
|
+
str.gsub!(/yA/, 'йА')
|
221
|
+
str.gsub!(/Ya/, 'Йа')
|
222
|
+
str.gsub!(/YA/, 'ЙА')
|
223
|
+
|
224
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])y[eE]/, '\1е')
|
225
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])Y[eE]/, '\1Е')
|
226
|
+
str.gsub!(/ye/, 'йе')
|
227
|
+
str.gsub!(/yE/, 'йЕ')
|
228
|
+
str.gsub!(/Ye/, 'Йе')
|
229
|
+
str.gsub!(/YE/, 'ЙЕ')
|
230
|
+
|
231
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])y[oO]/, '\1ё')
|
232
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])Y[oO]/, '\1Ё')
|
233
|
+
str.gsub!(/yo/, 'йо')
|
234
|
+
str.gsub!(/yO/, 'йО')
|
235
|
+
str.gsub!(/Yo/, 'Йо')
|
236
|
+
str.gsub!(/YO/, 'ЙО')
|
237
|
+
|
238
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])y[uU]/, '\1ю')
|
239
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])Y[uU]/, '\1Ю')
|
240
|
+
str.gsub!(/yu/, 'йу')
|
241
|
+
str.gsub!(/yU/, 'йУ')
|
242
|
+
str.gsub!(/Yu/, 'Йу')
|
243
|
+
str.gsub!(/YU/, 'ЙУ')
|
244
|
+
|
245
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])e/, '\1е')
|
246
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])E/, '\1Е')
|
247
|
+
str.gsub!(/e/, 'э')
|
248
|
+
str.gsub!(/E/, 'Э')
|
249
|
+
|
250
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])j/, '\1ь')
|
251
|
+
str.gsub!(/([bcdfghklmnprstvwxzBCDFGHKLMNPRSTVWXZ])J/, '\1Ь')
|
252
|
+
str.gsub!(/j/, 'й')
|
253
|
+
str.gsub!(/J/, 'Й')
|
254
|
+
|
255
|
+
str.gsub!(/c[hH]/, 'ч')
|
256
|
+
str.gsub!(/s[hH]/, 'ш')
|
257
|
+
str.gsub!(/x[hH]/, 'щ')
|
258
|
+
str.gsub!(/z[hH]/, 'ж')
|
259
|
+
|
260
|
+
str.gsub!(/C[hH]/, 'Ч')
|
261
|
+
str.gsub!(/S[hH]/, 'Ш')
|
262
|
+
str.gsub!(/X[hH]/, 'Щ')
|
263
|
+
str.gsub!(/Z[hH]/, 'Ж')
|
264
|
+
|
265
|
+
str.tr!('abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ', 'абцдэфгхийклмнопърстуввхызАБЦДЭФГХИЙКЛМНОПЪРСТУВВХЫЗ')
|
266
|
+
end
|
267
|
+
end
|
268
|
+
|
269
|
+
# Case correct, example: АЛЁША (rus_to_lat)→ ALYoShA (case_correct)→ ALYOSHA
|
270
|
+
def case_correct(string)
|
271
|
+
string.dup.tap do |str|
|
272
|
+
str.gsub!(/([A-Z])h([A-Z])/) { |s| s.upcase }
|
273
|
+
str.gsub!(/J([aeou])([A-Z])/) { |s| s.upcase }
|
274
|
+
|
275
|
+
str.gsub!(/([A-Z])([A-Z])h/) { |s| s.upcase }
|
276
|
+
str.gsub!(/([A-Z])J([aeou])/) { |s| s.upcase }
|
277
|
+
str.gsub!(/([BCDFGHKLMNPRSTVWXZ])Y([aeou])/) { |s| s.upcase }
|
278
|
+
|
279
|
+
str.gsub!(/([A-Z])h\s+([A-Z][A-Z])/) { |s| s.upcase }
|
280
|
+
str.gsub!(/J([aeou])\s+([A-Z][A-Z])/) { |s| s.upcase }
|
281
|
+
str.gsub!(/([BCDFGHKLMNPRSTVWXZ])Y([aeou])\s+([A-Z][A-Z])/) { |s| s.upcase }
|
282
|
+
end
|
283
|
+
end
|
284
|
+
|
285
|
+
# Typo correct replaces 'cyrillic-look-like' latin symbols to cyrillic ones
|
286
|
+
def typo_correct(string)
|
287
|
+
string.tr('acekopuxyABCEHKMOPTXY', 'асекорихуАВСЕНКМОРТХУ')
|
288
|
+
end
|
289
|
+
end
|
290
|
+
end
|
metadata
ADDED
@@ -0,0 +1,109 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: ruslat
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Vasiliy Sukhachev
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-12-11 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: '1.12'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.12'
|
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
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '3.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '3.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rubocop
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0.44'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0.44'
|
69
|
+
description:
|
70
|
+
email:
|
71
|
+
- vsuhachev@yandex.ru
|
72
|
+
executables:
|
73
|
+
- ruslat
|
74
|
+
extensions: []
|
75
|
+
extra_rdoc_files: []
|
76
|
+
files:
|
77
|
+
- CODE_OF_CONDUCT.md
|
78
|
+
- LICENSE.txt
|
79
|
+
- README.md
|
80
|
+
- exe/ruslat
|
81
|
+
- lib/ruslat.rb
|
82
|
+
- lib/ruslat/core.rb
|
83
|
+
- lib/ruslat/version.rb
|
84
|
+
homepage: https://github.com/vsuhachev/ruslat
|
85
|
+
licenses:
|
86
|
+
- MIT
|
87
|
+
metadata:
|
88
|
+
allowed_push_host: https://rubygems.org
|
89
|
+
post_install_message:
|
90
|
+
rdoc_options: []
|
91
|
+
require_paths:
|
92
|
+
- lib
|
93
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
94
|
+
requirements:
|
95
|
+
- - ">="
|
96
|
+
- !ruby/object:Gem::Version
|
97
|
+
version: '0'
|
98
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
99
|
+
requirements:
|
100
|
+
- - ">="
|
101
|
+
- !ruby/object:Gem::Version
|
102
|
+
version: '0'
|
103
|
+
requirements: []
|
104
|
+
rubyforge_project:
|
105
|
+
rubygems_version: 2.5.1
|
106
|
+
signing_key:
|
107
|
+
specification_version: 4
|
108
|
+
summary: Bidirectional russian transliteration library
|
109
|
+
test_files: []
|