1
0
mirror of https://github.com/mastodon/mastodon synced 2024-12-25 12:08:13 +09:00
mastodon/app/lib/language_detector.rb
Eugen Rochko e1fcad34a9 Fix length validator counting things that look like URIs like URLs (#4462)
URI.extract is too strong, not limited to URLs, matched real text.
Same issue was present in language detector.
2017-07-31 05:06:20 +02:00

47 lines
914 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
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|
new_text.gsub!(FetchLinkCardService::URL_PATTERN, '')
new_text.gsub!(Account::MENTION_RE, '')
new_text.gsub!(Tag::HASHTAG_RE, '')
new_text.gsub!(/\s+/, ' ')
end
end
def default_locale
account&.user_locale&.to_sym || nil
end
end