Update conftest to lazy load languages

spacy/tests/conftest.py

@@ -1,98 +1,85 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from ..en import English
-from ..de import German
-from ..es import Spanish
-from ..it import Italian
-from ..fr import French
-from ..pt import Portuguese
-from ..nl import Dutch
-from ..sv import Swedish
-from ..hu import Hungarian
-from ..fi import Finnish
-from ..bn import Bengali
-from ..he import Hebrew
-from ..nb import Norwegian
-
-
 from ..tokens import Doc
 from ..strings import StringStore
 from ..lemmatizer import Lemmatizer
 from ..attrs import ORTH, TAG, HEAD, DEP
+from .. import util
 
 from io import StringIO, BytesIO
 from pathlib import Path
-import os
 import pytest
 
 
-LANGUAGES = [English, German, Spanish, Italian, French, Portuguese, Dutch,
-             Swedish, Hungarian, Finnish, Bengali, Norwegian]
+_languages = ['bn', 'de', 'en', 'es', 'fi', 'fr', 'he', 'hu', 'it', 'nb', 'nl',
+              'pt', 'sv']
 
 
-@pytest.fixture(params=LANGUAGES)
+@pytest.fixture(params=_languages)
 def tokenizer(request):
-    lang = request.param
+    lang = util.load_lang_class(request.param)
     return lang.Defaults.create_tokenizer()
 
 
 @pytest.fixture
 def en_tokenizer():
-    return English.Defaults.create_tokenizer()
+    return util.load_lang_class('en').Defaults.create_tokenizer()
 
 
 @pytest.fixture
 def en_vocab():
-    return English.Defaults.create_vocab()
+    return util.load_lang_class('en').Defaults.create_vocab()
 
 
 @pytest.fixture
 def en_parser():
-    return English.Defaults.create_parser()
+    return util.load_lang_class('en').Defaults.create_parser()
+
 
 @pytest.fixture
 def es_tokenizer():
-    return Spanish.Defaults.create_tokenizer()
+    return util.load_lang_class('es').Defaults.create_tokenizer()
 
 
 @pytest.fixture
 def de_tokenizer():
-    return German.Defaults.create_tokenizer()
+    return util.load_lang_class('de').Defaults.create_tokenizer()
 
 
 @pytest.fixture(scope='module')
 def fr_tokenizer():
-    return French.Defaults.create_tokenizer()
+    return util.load_lang_class('fr').Defaults.create_tokenizer()
 
 
 @pytest.fixture
 def hu_tokenizer():
-    return Hungarian.Defaults.create_tokenizer()
+    return util.load_lang_class('hu').Defaults.create_tokenizer()
 
 
 @pytest.fixture
 def fi_tokenizer():
-    return Finnish.Defaults.create_tokenizer()
+    return util.load_lang_class('fi').Defaults.create_tokenizer()
 
 
 @pytest.fixture
 def sv_tokenizer():
-    return Swedish.Defaults.create_tokenizer()
+    return util.load_lang_class('sv').Defaults.create_tokenizer()
 
 
 @pytest.fixture
 def bn_tokenizer():
-    return Bengali.Defaults.create_tokenizer()
+    return util.load_lang_class('bn').Defaults.create_tokenizer()
 
 
 @pytest.fixture
 def he_tokenizer():
-    return Hebrew.Defaults.create_tokenizer()
+    return util.load_lang_class('he').Defaults.create_tokenizer()
 
 @pytest.fixture
 def nb_tokenizer():
-    return Norwegian.Defaults.create_tokenizer()
+    return util.load_lang_class('nb').Defaults.create_tokenizer()
+
 
 @pytest.fixture
 def stringstore():
@@ -101,12 +88,12 @@ def stringstore():
 
 @pytest.fixture
 def en_entityrecognizer():
-     return English.Defaults.create_entity()
+     return util.load_lang_class('en').Defaults.create_entity()
 
 
 @pytest.fixture
 def lemmatizer():
-    return English.Defaults.create_lemmatizer()
+    return util.load_lang_class('en').Defaults.create_lemmatizer()
 
 
 @pytest.fixture