💫 Tidy up and auto-format tests (explosion#2967)

* Auto-format tests with black

* Add flake8 config

* Tidy up and remove unused imports

* Fix redefinitions of test functions

* Replace orths_and_spaces with words and spaces

* Fix compatibility with pytest 4.0

* xfail test for now

Test was previously overwritten by following test due to naming conflict, so failure wasn't reported

* Unfail passing test

* Only use fixture via arguments

Fixes pytest 4.0 compatibility

.flake8

@@ -0,0 +1,4 @@
+[flake8]
+ignore = E203, E266, E501, W503
+max-line-length = 80
+select = B,C,E,F,W,T4,B9

requirements.txt

@@ -11,7 +11,7 @@ ujson>=1.35
 dill>=0.2,<0.3
 regex==2018.01.10
 requests>=2.13.0,<3.0.0
-pytest>=3.6.0,<4.0.0
+pytest>=4.0.0,<5.0.0
 pytest-timeout>=1.3.0,<2.0.0
 mock>=2.0.0,<3.0.0
 pathlib==1.0.1; python_version < "3.4"

spacy/tests/conftest.py

@@ -2,7 +2,6 @@
 from __future__ import unicode_literals
 
 import pytest
-from io import StringIO, BytesIO
 from spacy.util import get_lang_class
 
 
@@ -11,126 +10,135 @@ def pytest_addoption(parser):
 
 
 def pytest_runtest_setup(item):
-    for opt in ['slow']:
+    for opt in ["slow"]:
         if opt in item.keywords and not item.config.getoption("--%s" % opt):
             pytest.skip("need --%s option to run" % opt)
 
 
-@pytest.fixture(scope='module')
+@pytest.fixture(scope="module")
 def tokenizer():
-    return get_lang_class('xx').Defaults.create_tokenizer()
+    return get_lang_class("xx").Defaults.create_tokenizer()
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def en_tokenizer():
-    return get_lang_class('en').Defaults.create_tokenizer()
+    return get_lang_class("en").Defaults.create_tokenizer()
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def en_vocab():
-    return get_lang_class('en').Defaults.create_vocab()
+    return get_lang_class("en").Defaults.create_vocab()
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def en_parser(en_vocab):
-    nlp = get_lang_class('en')(en_vocab)
-    return nlp.create_pipe('parser')
+    nlp = get_lang_class("en")(en_vocab)
+    return nlp.create_pipe("parser")
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def es_tokenizer():
-    return get_lang_class('es').Defaults.create_tokenizer()
+    return get_lang_class("es").Defaults.create_tokenizer()
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def de_tokenizer():
-    return get_lang_class('de').Defaults.create_tokenizer()
+    return get_lang_class("de").Defaults.create_tokenizer()
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def fr_tokenizer():
-    return get_lang_class('fr').Defaults.create_tokenizer()
+    return get_lang_class("fr").Defaults.create_tokenizer()
 
 
 @pytest.fixture
 def hu_tokenizer():
-    return get_lang_class('hu').Defaults.create_tokenizer()
+    return get_lang_class("hu").Defaults.create_tokenizer()
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def fi_tokenizer():
-    return get_lang_class('fi').Defaults.create_tokenizer()
+    return get_lang_class("fi").Defaults.create_tokenizer()
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def ro_tokenizer():
-    return get_lang_class('ro').Defaults.create_tokenizer()
+    return get_lang_class("ro").Defaults.create_tokenizer()
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def id_tokenizer():
-    return get_lang_class('id').Defaults.create_tokenizer()
+    return get_lang_class("id").Defaults.create_tokenizer()
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def sv_tokenizer():
-    return get_lang_class('sv').Defaults.create_tokenizer()
+    return get_lang_class("sv").Defaults.create_tokenizer()
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def bn_tokenizer():
-    return get_lang_class('bn').Defaults.create_tokenizer()
+    return get_lang_class("bn").Defaults.create_tokenizer()
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def ga_tokenizer():
-    return get_lang_class('ga').Defaults.create_tokenizer()
+    return get_lang_class("ga").Defaults.create_tokenizer()
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def he_tokenizer():
-    return get_lang_class('he').Defaults.create_tokenizer()
+    return get_lang_class("he").Defaults.create_tokenizer()
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def nb_tokenizer():
-    return get_lang_class('nb').Defaults.create_tokenizer()
+    return get_lang_class("nb").Defaults.create_tokenizer()
 
-@pytest.fixture(scope='session')
+
+@pytest.fixture(scope="session")
 def da_tokenizer():
-    return get_lang_class('da').Defaults.create_tokenizer()
+    return get_lang_class("da").Defaults.create_tokenizer()
+
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def ja_tokenizer():
     mecab = pytest.importorskip("MeCab")
-    return get_lang_class('ja').Defaults.create_tokenizer()
+    return get_lang_class("ja").Defaults.create_tokenizer()
+
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def th_tokenizer():
     pythainlp = pytest.importorskip("pythainlp")
-    return get_lang_class('th').Defaults.create_tokenizer()
+    return get_lang_class("th").Defaults.create_tokenizer()
 
-@pytest.fixture(scope='session')
+
+@pytest.fixture(scope="session")
 def tr_tokenizer():
-    return get_lang_class('tr').Defaults.create_tokenizer()
+    return get_lang_class("tr").Defaults.create_tokenizer()
+
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def tt_tokenizer():
-    return get_lang_class('tt').Defaults.create_tokenizer()
+    return get_lang_class("tt").Defaults.create_tokenizer()
 
-@pytest.fixture(scope='session')
+
+@pytest.fixture(scope="session")
 def el_tokenizer():
-    return get_lang_class('el').Defaults.create_tokenizer()
+    return get_lang_class("el").Defaults.create_tokenizer()
+
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def ar_tokenizer():
-    return get_lang_class('ar').Defaults.create_tokenizer()
+    return get_lang_class("ar").Defaults.create_tokenizer()
 
-@pytest.fixture(scope='session')
+
+@pytest.fixture(scope="session")
 def ur_tokenizer():
-    return get_lang_class('ur').Defaults.create_tokenizer()
+    return get_lang_class("ur").Defaults.create_tokenizer()
+
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def ru_tokenizer():
-    pymorphy = pytest.importorskip('pymorphy2')
-    return get_lang_class('ru').Defaults.create_tokenizer()
+    pymorphy = pytest.importorskip("pymorphy2")
+    return get_lang_class("ru").Defaults.create_tokenizer()

spacy/tests/doc/test_array.py

@@ -38,7 +38,7 @@ def test_doc_scalar_attr_of_token(en_tokenizer, en_vocab):
 
 def test_doc_array_tag(en_tokenizer):
     text = "A nice sentence."
-    pos = ['DET', 'ADJ', 'NOUN', 'PUNCT']
+    pos = ["DET", "ADJ", "NOUN", "PUNCT"]
     tokens = en_tokenizer(text)
     doc = get_doc(tokens.vocab, words=[t.text for t in tokens], pos=pos)
     assert doc[0].pos != doc[1].pos != doc[2].pos != doc[3].pos
@@ -51,7 +51,7 @@ def test_doc_array_tag(en_tokenizer):
 
 def test_doc_array_dep(en_tokenizer):
     text = "A nice sentence."
-    deps = ['det', 'amod', 'ROOT', 'punct']
+    deps = ["det", "amod", "ROOT", "punct"]
     tokens = en_tokenizer(text)
     doc = get_doc(tokens.vocab, words=[t.text for t in tokens], deps=deps)
     feats_array = doc.to_array((ORTH, DEP))

spacy/tests/doc/test_creation.py

@@ -9,7 +9,7 @@
 
 @pytest.fixture
 def lemmatizer():
-    return Lemmatizer(lookup={'dogs': 'dog', 'boxen': 'box', 'mice': 'mouse'})
+    return Lemmatizer(lookup={"dogs": "dog", "boxen": "box", "mice": "mouse"})
 
 
 @pytest.fixture
@@ -23,15 +23,15 @@ def test_empty_doc(vocab):
 
 
 def test_single_word(vocab):
-    doc = Doc(vocab, words=['a'])
-    assert doc.text == 'a '
-    doc = Doc(vocab, words=['a'], spaces=[False])
-    assert doc.text == 'a'
+    doc = Doc(vocab, words=["a"])
+    assert doc.text == "a "
+    doc = Doc(vocab, words=["a"], spaces=[False])
+    assert doc.text == "a"
 
 
 def test_lookup_lemmatization(vocab):
-    doc = Doc(vocab, words=['dogs', 'dogses'])
-    assert doc[0].text == 'dogs'
-    assert doc[0].lemma_ == 'dog'
-    assert doc[1].text == 'dogses'
-    assert doc[1].lemma_ == 'dogses'
+    doc = Doc(vocab, words=["dogs", "dogses"])
+    assert doc[0].text == "dogs"
+    assert doc[0].lemma_ == "dog"
+    assert doc[1].text == "dogses"
+    assert doc[1].lemma_ == "dogses"