Class: Kotoshu::Languages::French
Overview
French language implementation.
Supports multiple dialects: fr-FR, fr-CA, fr-BE, fr-CH, fr-LU, fr-MC
Full Hunspell integration with spell checking, POS tagging, and grammar rules.
Defined Under Namespace
Modules: GrammarRules
Classes: POSTagger, SpellChecker, Tokenizer
Constant Summary
collapse
- HUNSPELL_DICTIONARIES =
{
'fr-FR' => {
aff: 'spec/integrational/fixtures/fr_FR.aff',
dic: 'spec/integrational/fixtures/fr_FR.dic'
},
'fr-CA' => {
aff: 'spec/integrational/fixtures/fr_CA.aff',
dic: 'spec/integrational/fixtures/fr_CA.dic'
}
}.freeze
- VARIANT_NAMES =
{
'FR' => 'France',
'CA' => 'Canadian',
'BE' => 'Belgian',
'CH' => 'Swiss',
'LU' => 'Luxembourgish',
'MC' => 'Monégasque'
}.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: "fr", name: "French", variant: nil) ⇒ French
Returns a new instance of French.
421
422
423
424
425
|
# File 'lib/kotoshu/languages/fr/language.rb', line 421
def initialize(code: "fr", name: "French", 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
472
473
474
475
476
477
478
479
|
# File 'lib/kotoshu/languages/fr/language.rb', line 472
def create_pos_tagger
POSTagger.new(
aff_path: @hunspell_paths[:aff],
dic_path: @hunspell_paths[:dic],
script: :latin,
flag_mapping: POSTagger::FLAG_TO_POS
)
end
|
#create_spell_checker ⇒ Object
460
461
462
463
464
465
466
|
# File 'lib/kotoshu/languages/fr/language.rb', line 460
def create_spell_checker
SpellChecker.new(
aff_path: @hunspell_paths[:aff],
dic_path: @hunspell_paths[:dic],
script: :latin
)
end
|
#create_tokenizer ⇒ Object
468
469
470
|
# File 'lib/kotoshu/languages/fr/language.rb', line 468
def create_tokenizer
Tokenizer.new
end
|
#default_dictionary_paths ⇒ Object
445
446
447
448
449
450
451
452
453
454
|
# File 'lib/kotoshu/languages/fr/language.rb', line 445
def default_dictionary_paths
case code
when "fr-FR"
["/usr/share/dict/french"]
when "fr-CA"
["/usr/share/dict/french-CA"]
else
["/usr/share/dict/words"]
end
end
|
#description ⇒ Object
427
428
429
430
431
|
# File 'lib/kotoshu/languages/fr/language.rb', line 427
def description
return name unless variant
variant_name = VARIANT_NAMES[variant] || variant
"#{name} (#{variant_name})"
end
|
#dictionary_class ⇒ Object
441
442
443
|
# File 'lib/kotoshu/languages/fr/language.rb', line 441
def dictionary_class
Dictionary::UnixWords
end
|
#normalizer ⇒ Object
437
438
439
|
# File 'lib/kotoshu/languages/fr/language.rb', line 437
def normalizer
@normalizer ||= Language::Normalizer::Base.new
end
|
#script_type ⇒ Object
456
457
458
|
# File 'lib/kotoshu/languages/fr/language.rb', line 456
def script_type
:latin
end
|
#tokenizer ⇒ Object
433
434
435
|
# File 'lib/kotoshu/languages/fr/language.rb', line 433
def tokenizer
@tokenizer ||= Tokenizer.new
end
|