Cyrillizer 0.1.1
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.
- data/README.rdoc +45 -0
- data/Rakefile +41 -0
- data/lib/cyrillizer.rb +8 -0
- data/lib/cyrillizer/converter.rb +29 -0
- data/spec/converter_spec.rb +35 -0
- metadata +59 -0
data/README.rdoc
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
= cyrillizer
|
2
|
+
|
3
|
+
* http://github.com/vasil/cyrillizer
|
4
|
+
|
5
|
+
== DESCRIPTION:
|
6
|
+
|
7
|
+
Character conversion from latin alphabet to Macedonian cyrillic alphabet
|
8
|
+
|
9
|
+
== SYNOPSIS:
|
10
|
+
|
11
|
+
require 'rubygems'
|
12
|
+
require 'cyrillizer'
|
13
|
+
puts 'Konvertiraj go ova na kirilica'.to_cyr
|
14
|
+
|
15
|
+
== INSTALL:
|
16
|
+
|
17
|
+
$ git clone git://github.com/vasil/cyrillizer.git
|
18
|
+
$ cd cyrillizer
|
19
|
+
$ rage gem
|
20
|
+
$ sudo gem install pkg/Cyrillizer-0.1.1.gem
|
21
|
+
|
22
|
+
== LICENSE:
|
23
|
+
|
24
|
+
(The MIT License)
|
25
|
+
|
26
|
+
Copyright (c) 2009 Dalibor Nasevic
|
27
|
+
|
28
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
29
|
+
a copy of this software and associated documentation files (the
|
30
|
+
'Software'), to deal in the Software without restriction, including
|
31
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
32
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
33
|
+
permit persons to whom the Software is furnished to do so, subject to
|
34
|
+
the following conditions:
|
35
|
+
|
36
|
+
The above copyright notice and this permission notice shall be
|
37
|
+
included in all copies or substantial portions of the Software.
|
38
|
+
|
39
|
+
THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
|
40
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
41
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
42
|
+
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
|
43
|
+
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
44
|
+
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
45
|
+
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/Rakefile
ADDED
@@ -0,0 +1,41 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
require 'rake/clean'
|
4
|
+
require 'rake/gempackagetask'
|
5
|
+
require 'rake/rdoctask'
|
6
|
+
require 'rake/testtask'
|
7
|
+
require 'spec/rake/spectask'
|
8
|
+
|
9
|
+
spec = Gem::Specification.new do |s|
|
10
|
+
s.name = 'Cyrillizer'
|
11
|
+
s.version = '0.1.1'
|
12
|
+
s.has_rdoc = true
|
13
|
+
s.extra_rdoc_files = ['README.rdoc']
|
14
|
+
s.summary = 'Converts (macedonian) text from latin transcript to cyrillic'
|
15
|
+
s.homepage = 'http://github.com/vasil/cyrillizer'
|
16
|
+
s.description = 'Character conversion from latin alphabet to Macedonian cyrillic alphabet'
|
17
|
+
s.author = 'Vasil Taneski'
|
18
|
+
s.email = 'vasil.taneski@gmail.com'
|
19
|
+
s.files = %w(README.rdoc Rakefile) + Dir.glob("{bin,lib,spec}/**/*")
|
20
|
+
s.require_path = "lib"
|
21
|
+
s.bindir = "bin"
|
22
|
+
end
|
23
|
+
|
24
|
+
Rake::GemPackageTask.new(spec) do |p|
|
25
|
+
p.gem_spec = spec
|
26
|
+
p.need_tar = true
|
27
|
+
p.need_zip = true
|
28
|
+
end
|
29
|
+
|
30
|
+
Rake::RDocTask.new do |rdoc|
|
31
|
+
files =['README.rdoc', 'lib/**/*.rb']
|
32
|
+
rdoc.rdoc_files.add(files)
|
33
|
+
rdoc.main = "README.rdoc"
|
34
|
+
rdoc.title = "Cyrillizer Docs"
|
35
|
+
rdoc.rdoc_dir = 'doc/rdoc'
|
36
|
+
rdoc.options << '--line-numbers'
|
37
|
+
end
|
38
|
+
|
39
|
+
Spec::Rake::SpecTask.new do |t|
|
40
|
+
t.spec_files = FileList['spec/**/*.rb']
|
41
|
+
end
|
data/lib/cyrillizer.rb
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
module Cyrillizer
|
3
|
+
module Converter
|
4
|
+
|
5
|
+
Latin = "AaBbVvGgDdEeZzIiJjKkLlMmNnOoPpRrSsTtUuFfHhCc"
|
6
|
+
Cyrillic = "АаБбВвГгДдЕеЗзИиЈјКкЛлМмНнОоПпРрСсТтУуФфХхЦц"
|
7
|
+
|
8
|
+
Latin_a = %w(DZH Dzh dzh GJ Gj gj ZH Zh zh DZ Dz dz LJ Lj lj NJ Nj nj KJ Kj kj CH Ch ch SH Sh sh)
|
9
|
+
Cyrillic_a = %w(Џ Џ џ Ѓ Ѓ ѓ Ж Ж ж Ѕ Ѕ ѕ Љ Љ љ Њ Њ њ Ќ Ќ ќ Ч Ч ч Ш Ш ш )
|
10
|
+
|
11
|
+
def to_cyr
|
12
|
+
self.tr_group(Latin_a, Cyrillic_a).tr(Latin, Cyrillic)
|
13
|
+
end
|
14
|
+
|
15
|
+
protected
|
16
|
+
def tr_group(from, to)
|
17
|
+
text = clone
|
18
|
+
from.each_with_index { |latin, i|
|
19
|
+
text.gsub!(latin, to[i])
|
20
|
+
}
|
21
|
+
return text
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
25
|
+
|
26
|
+
# Add to_cyr method to all Strings
|
27
|
+
class String
|
28
|
+
include Cyrillizer::Converter
|
29
|
+
end
|
@@ -0,0 +1,35 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
require File.join(File.dirname(__FILE__), *%w(.. lib cyrillizer converter))
|
3
|
+
|
4
|
+
describe Cyrillizer::Converter do
|
5
|
+
|
6
|
+
latin = Cyrillizer::Converter::Latin
|
7
|
+
latin_a = Cyrillizer::Converter::Latin_a
|
8
|
+
|
9
|
+
cyrillic = Cyrillizer::Converter::Cyrillic
|
10
|
+
cyrillic_a = Cyrillizer::Converter::Cyrillic_a
|
11
|
+
|
12
|
+
it "should return empty string for given empty string" do
|
13
|
+
"".to_cyr.should == ""
|
14
|
+
end
|
15
|
+
|
16
|
+
it "should return the same string for given cyrillic patterns" do
|
17
|
+
cyrillic.to_cyr.should == cyrillic
|
18
|
+
cyrillic_a.join.to_cyr.should == cyrillic_a.join
|
19
|
+
end
|
20
|
+
|
21
|
+
it "should return the cyrillic patterns for given latin ones" do
|
22
|
+
latin.to_cyr.should == cyrillic
|
23
|
+
latin_a.join.to_cyr.should == cyrillic_a.join
|
24
|
+
end
|
25
|
+
|
26
|
+
it "should be ok for UPCASE SENTENCES" do
|
27
|
+
"DZHABE RABOTI, DZHABE NE SEDI".to_cyr.should == "ЏАБЕ РАБОТИ, ЏАБЕ НЕ СЕДИ"
|
28
|
+
end
|
29
|
+
|
30
|
+
it "should be ok for Capitalized sentences" do
|
31
|
+
"Dzhabe raboti, dzhabe ne sedi".to_cyr.should == "Џабе работи, џабе не седи"
|
32
|
+
end
|
33
|
+
|
34
|
+
end
|
35
|
+
|
metadata
ADDED
@@ -0,0 +1,59 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: Cyrillizer
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Vasil Taneski
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2009-10-25 01:00:00 +02:00
|
13
|
+
default_executable:
|
14
|
+
dependencies: []
|
15
|
+
|
16
|
+
description: Character conversion from latin alphabet to Macedonian cyrillic alphabet
|
17
|
+
email: vasil.taneski@gmail.com
|
18
|
+
executables: []
|
19
|
+
|
20
|
+
extensions: []
|
21
|
+
|
22
|
+
extra_rdoc_files:
|
23
|
+
- README.rdoc
|
24
|
+
files:
|
25
|
+
- README.rdoc
|
26
|
+
- Rakefile
|
27
|
+
- lib/cyrillizer.rb
|
28
|
+
- lib/cyrillizer/converter.rb
|
29
|
+
- spec/converter_spec.rb
|
30
|
+
has_rdoc: true
|
31
|
+
homepage: http://github.com/vasil/cyrillizer
|
32
|
+
licenses: []
|
33
|
+
|
34
|
+
post_install_message:
|
35
|
+
rdoc_options: []
|
36
|
+
|
37
|
+
require_paths:
|
38
|
+
- lib
|
39
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
40
|
+
requirements:
|
41
|
+
- - ">="
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
version: "0"
|
44
|
+
version:
|
45
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
46
|
+
requirements:
|
47
|
+
- - ">="
|
48
|
+
- !ruby/object:Gem::Version
|
49
|
+
version: "0"
|
50
|
+
version:
|
51
|
+
requirements: []
|
52
|
+
|
53
|
+
rubyforge_project:
|
54
|
+
rubygems_version: 1.3.5
|
55
|
+
signing_key:
|
56
|
+
specification_version: 3
|
57
|
+
summary: Converts (macedonian) text from latin transcript to cyrillic
|
58
|
+
test_files: []
|
59
|
+
|