From 3402506dd3a5013c3e37a3c2230818ea9e462cf3 Mon Sep 17 00:00:00 2001
From: Alina Saalfeld <alina.saalfeld@ymail.com>
Date: Tue, 29 Sep 2015 16:52:46 +0200
Subject: [PATCH] Fix utf-8 in keywords

---
 lib/twitter_ebooks/nlp.rb | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/twitter_ebooks/nlp.rb b/lib/twitter_ebooks/nlp.rb
index b65e162..3fb9ea3 100644
--- a/lib/twitter_ebooks/nlp.rb
+++ b/lib/twitter_ebooks/nlp.rb
@@ -99,7 +99,7 @@ module Ebooks
         #set :vowels, 1                     # => default: 0 = not considered
         #set :consonants, 5                 # => default: 0 = not considered
         #set :ignore_case, true             # => default: false
-        set :word_pattern, /(?<!@)(?<=\s)[\w']+/           # => default: /\w+/
+        set :word_pattern, /(?<!@)(?<=\s)[\p{Word}']+/           # => default: /\w+/
         #set :stemming, true                # => default: false
       end