From 85d249d451d4791e5e188f0bcecbfdcc1cbff0f7 Mon Sep 17 00:00:00 2001
From: ines <ines@ines.io>
Date: Thu, 16 Feb 2017 23:26:21 +0100
Subject: [PATCH] Revert "Revert "Merge pull request #836 from
 raphael0202/load_vectors (closes #834)""

This reverts commit ea05f7866020faf9de40fe4c731655f0ab793886.
---
 spacy/tests/regression/test_issue834.py | 15 +++++++++++++++
 spacy/vocab.pyx                         | 13 +++++--------
 2 files changed, 20 insertions(+), 8 deletions(-)
 create mode 100644 spacy/tests/regression/test_issue834.py

diff --git a/spacy/tests/regression/test_issue834.py b/spacy/tests/regression/test_issue834.py
new file mode 100644
index 000000000..00b227f28
--- /dev/null
+++ b/spacy/tests/regression/test_issue834.py
@@ -0,0 +1,15 @@
+# coding: utf-8
+
+from __future__ import unicode_literals
+from io import StringIO
+
+word2vec_str = """, -0.046107 -0.035951 -0.560418
+de -0.648927 -0.400976 -0.527124
+. 0.113685 0.439990 -0.634510
+  -1.499184 -0.184280 -0.598371"""
+
+
+def test_issue834(en_vocab):
+    f = StringIO(word2vec_str)
+    vector_length = en_vocab.load_vectors(f)
+    assert vector_length == 3
diff --git a/spacy/vocab.pyx b/spacy/vocab.pyx
index cd2b18f81..ab023c3b4 100644
--- a/spacy/vocab.pyx
+++ b/spacy/vocab.pyx
@@ -1,22 +1,17 @@
 from __future__ import unicode_literals
 
-from libc.stdio cimport fopen, fclose, fread, fwrite, FILE
 from libc.string cimport memset
 from libc.stdint cimport int32_t
-from libc.stdint cimport uint64_t
 from libc.math cimport sqrt
 
 from pathlib import Path
 import bz2
-import io
-import math
 import ujson as json
-import tempfile
+import re
 
 from .lexeme cimport EMPTY_LEXEME
 from .lexeme cimport Lexeme
 from .strings cimport hash_string
-from .orth cimport word_shape
 from .typedefs cimport attr_t
 from .cfile cimport CFile
 from .lemmatizer import Lemmatizer
@@ -29,7 +24,6 @@ from . import symbols
 from cymem.cymem cimport Address
 from .serialize.packer cimport Packer
 from .attrs cimport PROB, LANG
-from . import deprecated
 from . import util
 
 
@@ -477,9 +471,12 @@ cdef class Vocab:
         cdef attr_t orth
         cdef int32_t vec_len = -1
         cdef double norm = 0.0
+
+        whitespace_pattern = re.compile(r'\s')
+
         for line_num, line in enumerate(file_):
             pieces = line.split()
-            word_str = " " if line.startswith(" ") else pieces.pop(0)
+            word_str = " " if whitespace_pattern.match(line) else pieces.pop(0)
             if vec_len == -1:
                 vec_len = len(pieces)
             elif vec_len != len(pieces):