From 1629b33082f34fc60d5de9f47e565cec50f56619 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal@gmail.com>
Date: Sun, 12 Apr 2015 04:45:31 +0200
Subject: [PATCH] * Fix copying of tokenizer data in init_model

---
 bin/init_model.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/bin/init_model.py b/bin/init_model.py
index e9c6b8477..69e7b9cde 100644
--- a/bin/init_model.py
+++ b/bin/init_model.py
@@ -19,6 +19,7 @@ import plac
 from pathlib import Path
 
 from shutil import copyfile
+from shutil import copytree
 import codecs
 
 from spacy.en import get_lex_props
@@ -35,7 +36,7 @@ def setup_tokenizer(lang_data_dir, tok_dir):
         src = lang_data_dir / filename
         dst = tok_dir / filename
         if not dst.exists():
-            copyfile(src, dst)
+            copyfile(str(src), str(dst))
 
 
 def _read_clusters(loc):