Change language detector threshold from 140 characters to 4 words (#10376)

Add `lang` attribute to statuses in web UI
This commit is contained in:
Eugen Rochko
2019-03-26 01:23:59 +01:00
committed by GitHub
parent 94e5e834f2
commit e6cfa7ab89
2 changed files with 6 additions and 4 deletions

View File

@ -3,7 +3,7 @@
class LanguageDetector
include Singleton
CHARACTER_THRESHOLD = 140
WORDS_THRESHOLD = 4
RELIABLE_CHARACTERS_RE = /[\p{Hebrew}\p{Arabic}\p{Syriac}\p{Thaana}\p{Nko}\p{Han}\p{Katakana}\p{Hiragana}\p{Hangul}]+/m
def initialize
@ -37,7 +37,7 @@ class LanguageDetector
end
def sufficient_text_length?(text)
text.size >= CHARACTER_THRESHOLD
text.split(/\s+/).size >= WORDS_THRESHOLD
end
def language_specific_character_set?(text)