yaroslav-yandex_inflect 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.
- data/LICENSE +20 -0
- data/README.rdoc +33 -0
- data/Rakefile +55 -0
- data/TODO +0 -0
- data/init.rb +3 -0
- data/lib/yandex_inflect.rb +75 -0
- data/lib/yandex_inflect/version.rb +9 -0
- data/spec/spec.opts +2 -0
- data/spec/spec_helper.rb +10 -0
- data/spec/yandex_inflect_spec.rb +77 -0
- metadata +73 -0
data/LICENSE
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
Copyright (c) 2008 Yaroslav Markin
|
|
2
|
+
|
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
|
4
|
+
a copy of this software and associated documentation files (the
|
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
|
9
|
+
the following conditions:
|
|
10
|
+
|
|
11
|
+
The above copyright notice and this permission notice shall be
|
|
12
|
+
included in all copies or substantial portions of the Software.
|
|
13
|
+
|
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.rdoc
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
1
|
+
= YandexInflect
|
|
2
|
+
|
|
3
|
+
Yandex.Inflect webservice client (provides Russian language pluralization)
|
|
4
|
+
|
|
5
|
+
Клиент сервиса Яндекс.Склонятор (склонение слов на русском языке)
|
|
6
|
+
|
|
7
|
+
* http://nano.yandex.ru/project/inflect/
|
|
8
|
+
* http://nano.yandex.ru/post/27/
|
|
9
|
+
|
|
10
|
+
== Установка
|
|
11
|
+
|
|
12
|
+
Установка в качестве gem с GitHub:
|
|
13
|
+
|
|
14
|
+
gem sources -a http://gems.github.com
|
|
15
|
+
gem install yaroslav-yandex_inflect
|
|
16
|
+
|
|
17
|
+
== Использование
|
|
18
|
+
|
|
19
|
+
> YandexInflect.inflections("рубин")
|
|
20
|
+
=> ["рубин", "рубина", "рубину", "рубин", "рубином", "рубине"]
|
|
21
|
+
> YandexInflect.inflections("ЭтогоСловаНетВСловаре")
|
|
22
|
+
=> ["ЭтогоСловаНетВСловаре", "ЭтогоСловаНетВСловаре", "ЭтогоСловаНетВСловаре",
|
|
23
|
+
"ЭтогоСловаНетВСловаре", "ЭтогоСловаНетВСловаре", "ЭтогоСловаНетВСловаре"]
|
|
24
|
+
|
|
25
|
+
Если во время общения с веб-сервисом произошла ошибка, возвращается массив, забитый оригинальной строкой.
|
|
26
|
+
|
|
27
|
+
Успешные ответы от веб-сервиса кешируются, кеш можно очистить с помощью
|
|
28
|
+
|
|
29
|
+
> YandexInflect.clear_cache
|
|
30
|
+
|
|
31
|
+
== Автор
|
|
32
|
+
|
|
33
|
+
* Ярослав Маркин <yaroslav@markin.net>
|
data/Rakefile
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
1
|
+
require 'rubygems'
|
|
2
|
+
require 'rake/gempackagetask'
|
|
3
|
+
require 'spec/rake/spectask'
|
|
4
|
+
require 'rubygems/specification'
|
|
5
|
+
require 'date'
|
|
6
|
+
|
|
7
|
+
GEM = "yandex_inflect"
|
|
8
|
+
GEM_VERSION = "0.0.2"
|
|
9
|
+
AUTHOR = "Yaroslav Markin"
|
|
10
|
+
EMAIL = "yaroslav@markin.net"
|
|
11
|
+
HOMEPAGE = "http://github.com/yaroslav/yandex_inflect/"
|
|
12
|
+
SUMMARY = "Yandex.Inflect webservice client (Russian language inflection)"
|
|
13
|
+
|
|
14
|
+
spec = Gem::Specification.new do |s|
|
|
15
|
+
s.name = GEM
|
|
16
|
+
s.version = GEM_VERSION
|
|
17
|
+
s.platform = Gem::Platform::RUBY
|
|
18
|
+
s.has_rdoc = true
|
|
19
|
+
s.extra_rdoc_files = ["README.rdoc", "LICENSE", 'TODO']
|
|
20
|
+
s.summary = SUMMARY
|
|
21
|
+
s.description = s.summary
|
|
22
|
+
s.author = AUTHOR
|
|
23
|
+
s.email = EMAIL
|
|
24
|
+
s.homepage = HOMEPAGE
|
|
25
|
+
|
|
26
|
+
# Uncomment this to add a dependency
|
|
27
|
+
s.add_dependency "httparty"
|
|
28
|
+
|
|
29
|
+
s.require_path = 'lib'
|
|
30
|
+
s.autorequire = GEM
|
|
31
|
+
s.files = %w(LICENSE README.rdoc Rakefile TODO init.rb) + Dir.glob("{lib,spec}/**/*")
|
|
32
|
+
end
|
|
33
|
+
|
|
34
|
+
Rake::GemPackageTask.new(spec) do |pkg|
|
|
35
|
+
pkg.gem_spec = spec
|
|
36
|
+
end
|
|
37
|
+
|
|
38
|
+
task :default => :spec
|
|
39
|
+
desc "Run specs"
|
|
40
|
+
Spec::Rake::SpecTask.new do |t|
|
|
41
|
+
t.spec_files = FileList['spec/**/*_spec.rb']
|
|
42
|
+
t.spec_opts = %w(-fs --color)
|
|
43
|
+
end
|
|
44
|
+
|
|
45
|
+
desc "install the gem locally"
|
|
46
|
+
task :install => [:package] do
|
|
47
|
+
sh %{sudo gem install pkg/#{GEM}-#{GEM_VERSION}}
|
|
48
|
+
end
|
|
49
|
+
|
|
50
|
+
desc "create a gemspec file"
|
|
51
|
+
task :make_spec do
|
|
52
|
+
File.open("#{GEM}.gemspec", "w") do |file|
|
|
53
|
+
file.puts spec.to_ruby
|
|
54
|
+
end
|
|
55
|
+
end
|
data/TODO
ADDED
|
File without changes
|
data/init.rb
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
1
|
+
$KCODE = 'u'
|
|
2
|
+
|
|
3
|
+
$:.unshift(File.dirname(__FILE__)) unless
|
|
4
|
+
$:.include?(File.dirname(__FILE__)) || $:.include?(File.expand_path(File.dirname(__FILE__)))
|
|
5
|
+
|
|
6
|
+
require 'rubygems'
|
|
7
|
+
require 'httparty'
|
|
8
|
+
|
|
9
|
+
module YandexInflect
|
|
10
|
+
# Число доступных вариантов склонений
|
|
11
|
+
INFLECTIONS_COUNT = 6
|
|
12
|
+
|
|
13
|
+
# Класс для получения данных с веб-сервиса Яндекса.
|
|
14
|
+
class Inflection
|
|
15
|
+
include HTTParty
|
|
16
|
+
base_uri 'http://export.yandex.ru/'
|
|
17
|
+
|
|
18
|
+
# Получить склонения для имени <tt>name</tt>
|
|
19
|
+
def get(name)
|
|
20
|
+
options = {}
|
|
21
|
+
options[:query] = { :name => name }
|
|
22
|
+
inflections = self.class.get("/inflect.xml", options)
|
|
23
|
+
|
|
24
|
+
return inflections["inflections"]["inflection"]
|
|
25
|
+
end
|
|
26
|
+
end
|
|
27
|
+
|
|
28
|
+
# Кеширование успешных результатов запроса к веб-сервису
|
|
29
|
+
@@cache = {}
|
|
30
|
+
|
|
31
|
+
# Возвращает массив склонений (размером <tt>INFLECTIONS_COUNT</tt>) для слова <tt>word</tt>.
|
|
32
|
+
#
|
|
33
|
+
# Если слово не найдено в словаре, будет возвращен массив размерностью <tt>INFLECTIONS_COUNT</tt>,
|
|
34
|
+
# заполненный этим словом.
|
|
35
|
+
def self.inflections(word)
|
|
36
|
+
inflections = []
|
|
37
|
+
|
|
38
|
+
# TODO ugly
|
|
39
|
+
lookup = cache_lookup(word)
|
|
40
|
+
return lookup if lookup
|
|
41
|
+
|
|
42
|
+
get = Inflection.new.get(word) rescue nil # если поднято исключение, переходим к третьему варианту и не кешируем
|
|
43
|
+
case get
|
|
44
|
+
when Array then
|
|
45
|
+
# Яндекс вернул массив склонений
|
|
46
|
+
inflections = get
|
|
47
|
+
# Кладем в кеш
|
|
48
|
+
cache_store(word, inflections)
|
|
49
|
+
when String then
|
|
50
|
+
# Яндекс не вернул массива склонений (слово не найдено в словаре),
|
|
51
|
+
# а только строку, то забиваем этой строкой весь массив
|
|
52
|
+
inflections.fill(get, 0..INFLECTIONS_COUNT-1)
|
|
53
|
+
# Кладем в кеш
|
|
54
|
+
cache_store(word, inflections)
|
|
55
|
+
else
|
|
56
|
+
# Забиваем варианты склонений оригиналом
|
|
57
|
+
inflections.fill(word, 0..INFLECTIONS_COUNT-1)
|
|
58
|
+
end
|
|
59
|
+
|
|
60
|
+
inflections
|
|
61
|
+
end
|
|
62
|
+
|
|
63
|
+
def self.clear_cache
|
|
64
|
+
@@cache.clear
|
|
65
|
+
end
|
|
66
|
+
|
|
67
|
+
private
|
|
68
|
+
def self.cache_lookup(word)
|
|
69
|
+
@@cache[word.to_s]
|
|
70
|
+
end
|
|
71
|
+
|
|
72
|
+
def self.cache_store(word, value)
|
|
73
|
+
@@cache[word.to_s] = value
|
|
74
|
+
end
|
|
75
|
+
end
|
data/spec/spec.opts
ADDED
data/spec/spec_helper.rb
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
1
|
+
require File.dirname(__FILE__) + '/spec_helper.rb'
|
|
2
|
+
|
|
3
|
+
describe YandexInflect do
|
|
4
|
+
before(:all) do
|
|
5
|
+
@sample_inflection = ["рубин", "рубина", "рубину", "рубин", "рубином", "рубине"]
|
|
6
|
+
end
|
|
7
|
+
|
|
8
|
+
before(:each) do
|
|
9
|
+
@inflection = mock(:inflection)
|
|
10
|
+
YandexInflect::clear_cache
|
|
11
|
+
end
|
|
12
|
+
|
|
13
|
+
it "should return an array of inflections when webservice returns an array" do
|
|
14
|
+
@inflection.stub!(:get).and_return(@sample_inflection)
|
|
15
|
+
YandexInflect::Inflection.should_receive(:new).and_return(@inflection)
|
|
16
|
+
YandexInflect.inflections("рубин").should == @sample_inflection
|
|
17
|
+
end
|
|
18
|
+
|
|
19
|
+
it "should return an array filled with identical strings when webservice returns a string" do
|
|
20
|
+
@inflection.stub!(:get).and_return("рубин1")
|
|
21
|
+
YandexInflect::Inflection.should_receive(:new).and_return(@inflection)
|
|
22
|
+
YandexInflect.inflections("рубин").should == %w(рубин1 рубин1 рубин1 рубин1 рубин1 рубин1)
|
|
23
|
+
end
|
|
24
|
+
|
|
25
|
+
it "should return an array filled with identical strings of original word when webservice does not return anything meaningful or throws an exception" do
|
|
26
|
+
@inflection.stub!(:get).and_return(nil)
|
|
27
|
+
YandexInflect::Inflection.should_receive(:new).and_return(@inflection)
|
|
28
|
+
YandexInflect.inflections("рубин").should == %w(рубин рубин рубин рубин рубин рубин)
|
|
29
|
+
end
|
|
30
|
+
end
|
|
31
|
+
|
|
32
|
+
describe YandexInflect, "with caching" do
|
|
33
|
+
before(:each) do
|
|
34
|
+
@inflection = mock(:inflection)
|
|
35
|
+
YandexInflect::clear_cache
|
|
36
|
+
end
|
|
37
|
+
|
|
38
|
+
it "should cache successful lookups" do
|
|
39
|
+
sample = ["рубин", "рубина", "рубину", "рубин", "рубином", "рубине"]
|
|
40
|
+
@inflection.stub!(:get).and_return(sample)
|
|
41
|
+
YandexInflect::Inflection.should_receive(:new).once.and_return(@inflection)
|
|
42
|
+
|
|
43
|
+
2.times { YandexInflect.inflections("рубин") }
|
|
44
|
+
end
|
|
45
|
+
|
|
46
|
+
it "should NOT cache unseccussful lookups" do
|
|
47
|
+
sample = nil
|
|
48
|
+
@inflection.stub!(:get).and_return(sample)
|
|
49
|
+
YandexInflect::Inflection.should_receive(:new).twice.and_return(@inflection)
|
|
50
|
+
|
|
51
|
+
2.times { YandexInflect.inflections("рубин") }
|
|
52
|
+
end
|
|
53
|
+
|
|
54
|
+
it "should allow to clear cache" do
|
|
55
|
+
sample = "рубин"
|
|
56
|
+
@inflection.stub!(:get).and_return(sample)
|
|
57
|
+
YandexInflect::Inflection.should_receive(:new).twice.and_return(@inflection)
|
|
58
|
+
|
|
59
|
+
YandexInflect.inflections("рубин")
|
|
60
|
+
YandexInflect.clear_cache
|
|
61
|
+
YandexInflect.inflections("рубин")
|
|
62
|
+
end
|
|
63
|
+
end
|
|
64
|
+
|
|
65
|
+
describe YandexInflect::Inflection do
|
|
66
|
+
before(:all) do
|
|
67
|
+
@sample_answer = {
|
|
68
|
+
"inflections"=>{"inflection"=>["рубин", "рубина", "рубину", "рубин", "рубином", "рубине"], "original"=>"рубин"}
|
|
69
|
+
}
|
|
70
|
+
@sample_inflection = ["рубин", "рубина", "рубину", "рубин", "рубином", "рубине"]
|
|
71
|
+
end
|
|
72
|
+
|
|
73
|
+
it "should get inflections for a word" do
|
|
74
|
+
YandexInflect::Inflection.should_receive(:get).and_return(@sample_answer)
|
|
75
|
+
YandexInflect::Inflection.new.get("рубин").should == @sample_inflection
|
|
76
|
+
end
|
|
77
|
+
end
|
metadata
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: yaroslav-yandex_inflect
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.0.2
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Yaroslav Markin
|
|
8
|
+
autorequire: yandex_inflect
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
|
|
12
|
+
date: 2008-09-09 00:00:00 -07:00
|
|
13
|
+
default_executable:
|
|
14
|
+
dependencies:
|
|
15
|
+
- !ruby/object:Gem::Dependency
|
|
16
|
+
name: httparty
|
|
17
|
+
version_requirement:
|
|
18
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
19
|
+
requirements:
|
|
20
|
+
- - ">="
|
|
21
|
+
- !ruby/object:Gem::Version
|
|
22
|
+
version: "0"
|
|
23
|
+
version:
|
|
24
|
+
description: Yandex.Inflect webservice client (Russian language inflection)
|
|
25
|
+
email: yaroslav@markin.net
|
|
26
|
+
executables: []
|
|
27
|
+
|
|
28
|
+
extensions: []
|
|
29
|
+
|
|
30
|
+
extra_rdoc_files:
|
|
31
|
+
- README.rdoc
|
|
32
|
+
- LICENSE
|
|
33
|
+
- TODO
|
|
34
|
+
files:
|
|
35
|
+
- LICENSE
|
|
36
|
+
- README.rdoc
|
|
37
|
+
- Rakefile
|
|
38
|
+
- TODO
|
|
39
|
+
- init.rb
|
|
40
|
+
- lib/yandex_inflect
|
|
41
|
+
- lib/yandex_inflect/version.rb
|
|
42
|
+
- lib/yandex_inflect.rb
|
|
43
|
+
- spec/spec.opts
|
|
44
|
+
- spec/spec_helper.rb
|
|
45
|
+
- spec/yandex_inflect_spec.rb
|
|
46
|
+
has_rdoc: true
|
|
47
|
+
homepage: http://github.com/yaroslav/yandex_inflect/
|
|
48
|
+
post_install_message:
|
|
49
|
+
rdoc_options: []
|
|
50
|
+
|
|
51
|
+
require_paths:
|
|
52
|
+
- lib
|
|
53
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
54
|
+
requirements:
|
|
55
|
+
- - ">="
|
|
56
|
+
- !ruby/object:Gem::Version
|
|
57
|
+
version: "0"
|
|
58
|
+
version:
|
|
59
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
60
|
+
requirements:
|
|
61
|
+
- - ">="
|
|
62
|
+
- !ruby/object:Gem::Version
|
|
63
|
+
version: "0"
|
|
64
|
+
version:
|
|
65
|
+
requirements: []
|
|
66
|
+
|
|
67
|
+
rubyforge_project:
|
|
68
|
+
rubygems_version: 1.2.0
|
|
69
|
+
signing_key:
|
|
70
|
+
specification_version: 2
|
|
71
|
+
summary: Yandex.Inflect webservice client (Russian language inflection)
|
|
72
|
+
test_files: []
|
|
73
|
+
|