mirror of
https://github.com/lunaisnotaboy/mastodon.git
synced 2024-11-17 20:32:56 +00:00
Fix Thai being skipped from language detection (#13989)
Thai does not separate words by spaces, so I figured out it should be in 'reliable characters regexp' that denotes languages that do the same. Related #13891.
This commit is contained in:
parent
f7bdfec5bb
commit
f5cea4d2ea
|
@ -4,7 +4,7 @@ class LanguageDetector
|
||||||
include Singleton
|
include Singleton
|
||||||
|
|
||||||
WORDS_THRESHOLD = 4
|
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
|
RELIABLE_CHARACTERS_RE = /[\p{Hebrew}\p{Arabic}\p{Syriac}\p{Thaana}\p{Nko}\p{Han}\p{Katakana}\p{Hiragana}\p{Hangul}\p{Thai}]+/m
|
||||||
|
|
||||||
def initialize
|
def initialize
|
||||||
@identifier = CLD3::NNetLanguageIdentifier.new(1, 2048)
|
@identifier = CLD3::NNetLanguageIdentifier.new(1, 2048)
|
||||||
|
|
Loading…
Reference in a new issue