Drop six and related hacks as a dependency

requirements.txt

@@ -6,7 +6,6 @@ preshed>=1.0.0,<2.0.0
 thinc>=6.10.1,<6.11.0
 murmurhash>=0.28,<0.29
 plac<1.0.0,>=0.9.6
-six
 ujson>=1.35
 dill>=0.2,<0.3
 requests>=2.13.0,<3.0.0
@@ -16,4 +15,3 @@ pytest>=3.0.6,<4.0.0
 mock>=2.0.0,<3.0.0
 msgpack-python
 msgpack-numpy==0.4.1
-html5lib==1.0b8

setup.py

@@ -191,8 +191,6 @@ def setup_package():
                 'preshed>=1.0.0,<2.0.0',
                 'thinc>=6.10.1,<6.11.0',
                 'plac<1.0.0,>=0.9.6',
-                'six',
-                'html5lib==1.0b8',
                 'pathlib',
                 'ujson>=1.35',
                 'dill>=0.2,<0.3',

spacy/compat.py

@@ -1,7 +1,6 @@
 # coding: utf8
 from __future__ import unicode_literals
 
-import six
 import ftfy
 import sys
 import ujson
@@ -47,9 +46,10 @@ is_windows = sys.platform.startswith('win')
 is_linux = sys.platform.startswith('linux')
 is_osx = sys.platform == 'darwin'
 
-is_python2 = six.PY2
-is_python3 = six.PY3
-is_python_pre_3_5 = is_python2 or (is_python3 and sys.version_info[1]<5)
+# See: https://github.com/benjaminp/six/blob/master/six.py
+is_python2 = sys.version_info[0] == 2
+is_python3 = sys.version_info[0] == 3
+is_python_pre_3_5 = is_python2 or (is_python3 and sys.version_info[1] < 5)
 
 if is_python2:
     bytes_ = str

spacy/tests/lang/en/test_tagger.py

@@ -2,9 +2,9 @@
 from __future__ import unicode_literals
 
 from ....parts_of_speech import SPACE
+from ....compat import unicode_
 from ...util import get_doc
 
-import six
 import pytest
 
 
@@ -24,8 +24,8 @@ def test_tag_names(EN):
     text = "I ate pizzas with anchovies."
     doc = EN(text, disable=['parser'])
     assert type(doc[2].pos) == int
-    assert isinstance(doc[2].pos_, six.text_type)
-    assert isinstance(doc[2].dep_, six.text_type)
+    assert isinstance(doc[2].pos_, unicode_)
+    assert isinstance(doc[2].dep_, unicode_)
     assert doc[2].tag_ == u'NNS'