d010e270e6
* Add failing specs for hashtag and username extraction in language detector * Remove usernames and hashtags from text before language detection * Handle multiple instances of special case, and reduce whitespace
48 lines
953 B
Ruby
48 lines
953 B
Ruby
# frozen_string_literal: true
|
|
|
|
class LanguageDetector
|
|
attr_reader :text, :account
|
|
|
|
def initialize(text, account = nil)
|
|
@text = text
|
|
@account = account
|
|
@identifier = CLD3::NNetLanguageIdentifier.new(1, 2048)
|
|
end
|
|
|
|
def to_iso_s
|
|
detected_language_code || default_locale.to_sym
|
|
end
|
|
|
|
def prepared_text
|
|
simplified_text.strip
|
|
end
|
|
|
|
private
|
|
|
|
def detected_language_code
|
|
result.language.to_sym if detected_language_reliable?
|
|
end
|
|
|
|
def result
|
|
@result ||= @identifier.find_language(prepared_text)
|
|
end
|
|
|
|
def detected_language_reliable?
|
|
result.reliable?
|
|
end
|
|
|
|
def simplified_text
|
|
text.dup.tap do |new_text|
|
|
URI.extract(new_text).each do |url|
|
|
new_text.gsub!(url, '')
|
|
end
|
|
new_text.gsub!(Account::MENTION_RE, '')
|
|
new_text.gsub!(Tag::HASHTAG_RE, '')
|
|
new_text.gsub!(/\s+/, ' ')
|
|
end
|
|
end
|
|
|
|
def default_locale
|
|
account&.user_locale || I18n.default_locale
|
|
end
|
|
end
|