From 9b3f8f9ec3c98c94581694060cfb60be0b8bf2f3 Mon Sep 17 00:00:00 2001
From: ines <ines@ines.io>
Date: Sat, 14 Oct 2017 13:11:18 +0200
Subject: [PATCH] Fix formatting and add comment on languages

---
 spacy/tests/conftest.py | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/spacy/tests/conftest.py b/spacy/tests/conftest.py
index 28b5f4ab9..5f3fea342 100644
--- a/spacy/tests/conftest.py
+++ b/spacy/tests/conftest.py
@@ -11,8 +11,12 @@ from ..strings import StringStore
 from .. import util
 
 
+# These languages are used for generic tokenizer tests – only add a language
+# here if it's using spaCy's tokenizer (not a different library)
+# TODO: re-implement generic tokenizer tests
 _languages = ['bn', 'da', 'de', 'en', 'es', 'fi', 'fr', 'he', 'hu', 'id',
-              'it', 'nb', 'nl', 'pl', 'pt', 'sv', 'th','xx']
+              'it', 'nb', 'nl', 'pl', 'pt', 'sv', 'xx']
+
 _models = {'en': ['en_core_web_sm'],
            'de': ['de_core_news_md'],
            'fr': ['fr_depvec_web_lg'],
@@ -42,6 +46,7 @@ def FR(request):
     #lang = util.get_lang_class(request.param)
     #return lang.Defaults.create_tokenizer()
 
+
 @pytest.fixture
 def tokenizer():
     return util.get_lang_class('xx').Defaults.create_tokenizer()
@@ -87,10 +92,12 @@ def hu_tokenizer():
 def fi_tokenizer():
     return util.get_lang_class('fi').Defaults.create_tokenizer()
 
+
 @pytest.fixture
 def id_tokenizer():
     return util.get_lang_class('id').Defaults.create_tokenizer()
 
+
 @pytest.fixture
 def sv_tokenizer():
     return util.get_lang_class('sv').Defaults.create_tokenizer()
@@ -105,6 +112,7 @@ def bn_tokenizer():
 def he_tokenizer():
     return util.get_lang_class('he').Defaults.create_tokenizer()
 
+
 @pytest.fixture
 def nb_tokenizer():
     return util.get_lang_class('nb').Defaults.create_tokenizer()
@@ -129,6 +137,7 @@ def en_entityrecognizer():
 def text_file():
     return StringIO()
 
+
 @pytest.fixture
 def text_file_b():
     return BytesIO()