From a877a02f812c0161205379b4ab58b38c86247d99 Mon Sep 17 00:00:00 2001
From: Katalin Pajkossy <pajkossy@info.ilab.sztaki.hu>
Date: Fri, 27 May 2016 09:41:10 +0200
Subject: [PATCH] num_replacement encoding

---
 hunvec/datasets/tools.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/hunvec/datasets/tools.py b/hunvec/datasets/tools.py
index 593d15b..a1a19ea 100644
--- a/hunvec/datasets/tools.py
+++ b/hunvec/datasets/tools.py
@@ -11,7 +11,7 @@ def replace_numerals(w):
         i += 1
         begin = w[:len(matched.groups()[0])]
         end = w[len(matched.groups()[0]) + len(matched.groups()[1]):]
-        w = '{}__num__{}'.format(begin, end)
+        w = u'{}__num__{}'.format(begin, end)
         matched = num_pattern.match(w)
     return w