Class: Kotoshu::Languages::Russian
Overview
Russian language implementation.
Supports multiple dialects: ru-RU, ru-BY, ru-KZ, ru-KG, ru-MD
Full Hunspell integration with spell checking, POS tagging, and grammar rules specifically handling Russian Cyrillic script and case system.
Defined Under Namespace
Modules: GrammarRules
Classes: POSTagger, SpellChecker, Tokenizer
Constant Summary
collapse
- HUNSPELL_DICTIONARIES =
{
'ru-RU' => {
aff: 'spec/integrational/fixtures/ru_RU.aff',
dic: 'spec/integrational/fixtures/ru_RU.dic'
}
}.freeze
- VARIANT_NAMES =
{
'RU' => 'Russian',
'BY' => 'Belarusian',
'KZ' => 'Kazakh',
'KG' => 'Kyrgyz',
'MD' => 'Moldovan'
}.freeze
Instance Attribute Summary
#code, #name, #region, #variant
Instance Method Summary
collapse
#base_code, #base_language?, #compatible_with?, #encoding, #full_name, #info, instance, #matches_code?, #normalize, #normalize_word, #region_code, register, #rtl?, #tokenize, #valid_word?
Constructor Details
#initialize(code: "ru", name: "Russian", variant: nil) ⇒ Russian
Returns a new instance of Russian.
334
335
336
337
338
|
# File 'lib/kotoshu/languages/ru/language.rb', line 334
def initialize(code: "ru", name: "Russian", variant: nil)
variant ||= (code)
super(code: code, name: name, variant: variant)
@hunspell_paths = resolve_hunspell_paths(code)
end
|
Instance Method Details
#create_pos_tagger ⇒ Object
383
384
385
386
387
388
389
390
|
# File 'lib/kotoshu/languages/ru/language.rb', line 383
def create_pos_tagger
POSTagger.new(
aff_path: @hunspell_paths[:aff],
dic_path: @hunspell_paths[:dic],
script: :cyrillic,
flag_mapping: POSTagger::FLAG_TO_POS
)
end
|
#create_spell_checker ⇒ Object
371
372
373
374
375
376
377
|
# File 'lib/kotoshu/languages/ru/language.rb', line 371
def create_spell_checker
SpellChecker.new(
aff_path: @hunspell_paths[:aff],
dic_path: @hunspell_paths[:dic],
script: :cyrillic
)
end
|
#create_tokenizer ⇒ Object
379
380
381
|
# File 'lib/kotoshu/languages/ru/language.rb', line 379
def create_tokenizer
Tokenizer.new
end
|
#default_dictionary_paths ⇒ Object
358
359
360
361
362
363
364
365
|
# File 'lib/kotoshu/languages/ru/language.rb', line 358
def default_dictionary_paths
case code
when "ru-RU"
["/usr/share/dict/russian"]
else
["/usr/share/dict/words"]
end
end
|
#description ⇒ Object
340
341
342
343
344
|
# File 'lib/kotoshu/languages/ru/language.rb', line 340
def description
return name unless variant
variant_name = VARIANT_NAMES[variant] || variant
"#{name} (#{variant_name})"
end
|
#dictionary_class ⇒ Object
354
355
356
|
# File 'lib/kotoshu/languages/ru/language.rb', line 354
def dictionary_class
Dictionary::UnixWords
end
|
#normalizer ⇒ Object
350
351
352
|
# File 'lib/kotoshu/languages/ru/language.rb', line 350
def normalizer
@normalizer ||= Language::Normalizer::Base.new
end
|
#script_type ⇒ Object
367
368
369
|
# File 'lib/kotoshu/languages/ru/language.rb', line 367
def script_type
:cyrillic
end
|
#tokenizer ⇒ Object
346
347
348
|
# File 'lib/kotoshu/languages/ru/language.rb', line 346
def tokenizer
@tokenizer ||= Tokenizer.new
end
|