From c6707778dd12536ef2655c844555710dd1e5bdcc Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal@gmail.com>
Date: Mon, 13 Apr 2015 22:28:59 +0200
Subject: [PATCH] * Fix Issue #51: Handle non-ascii lemmas correctly

---
 spacy/en/pos.pyx | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/spacy/en/pos.pyx b/spacy/en/pos.pyx
index c5d7e126d..8b4e0730e 100644
--- a/spacy/en/pos.pyx
+++ b/spacy/en/pos.pyx
@@ -331,7 +331,8 @@ cdef class EnPosTagger:
         cdef unicode lemma_string
         lemma_strings = self.lemmatizer(py_string, pos)
         lemma_string = sorted(lemma_strings)[0]
-        lemma = self.strings.intern(lemma_string.encode('utf8'), len(lemma_string)).i
+        bytes_string = lemma_string.encode('utf8')
+        lemma = self.strings.intern(bytes_string, len(bytes_string)).i
         return lemma
 
     def load_morph_exceptions(self, dict exc):