about summary refs log tree commit diff
diff options
context:
space:
mode:
authorSasha Sorokin <dafri.nochiterov8@gmail.com>2020-06-26 03:45:01 +0700
committerGitHub <noreply@github.com>2020-06-25 22:45:01 +0200
commitf5cea4d2ea314a78d44ef013c6dabda32ad96df1 (patch)
tree061b13f1f2d96ca6365e03ffdf8991c464b8d8f4
parentf7bdfec5bba683f25dd9cf497f84d202ca5267c2 (diff)
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.
-rw-r--r--app/lib/language_detector.rb2
1 files changed, 1 insertions, 1 deletions
diff --git a/app/lib/language_detector.rb b/app/lib/language_detector.rb
index 05a06726d..2cc8ac615 100644
--- a/app/lib/language_detector.rb
+++ b/app/lib/language_detector.rb
@@ -4,7 +4,7 @@ class LanguageDetector
   include Singleton
 
   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
     @identifier = CLD3::NNetLanguageIdentifier.new(1, 2048)