Auto-format [ci skip]

spacy/lang/uk/__init__.py

@@ -26,7 +26,9 @@ class Ukrainian(Language):
     default_config={"model": None, "mode": "pymorphy2"},
     default_score_weights={"lemma_acc": 1.0},
 )
-def make_lemmatizer(nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool = False,):
+def make_lemmatizer(
+    nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool = False
+):
     return UkrainianLemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)
 
 

spacy/lang/zh/__init__.py

@@ -54,9 +54,7 @@ def create_chinese_tokenizer(segmenter: Segmenter = Segmenter.char):
 
 
 class ChineseTokenizer(DummyTokenizer):
-    def __init__(
+    def __init__(self, nlp: Language, segmenter: Segmenter = Segmenter.char):
-        self, nlp: Language, segmenter: Segmenter = Segmenter.char,
-    ):
         self.vocab = nlp.vocab
         if isinstance(segmenter, Segmenter):
             segmenter = segmenter.value
@@ -87,7 +85,7 @@ class ChineseTokenizer(DummyTokenizer):
             if pkuseg_user_dict is None:
                 pkuseg_user_dict = pkuseg_model
             self.pkuseg_seg = try_pkuseg_import(
-                pkuseg_model=pkuseg_model, pkuseg_user_dict=pkuseg_user_dict,
+                pkuseg_model=pkuseg_model, pkuseg_user_dict=pkuseg_user_dict
             )
 
     def __call__(self, text: str) -> Doc:

spacy/tests/doc/test_retokenize_split.py

@@ -209,9 +209,13 @@ def test_doc_retokenizer_split_norm(en_vocab):
     # Retokenize to split out the words in the token at doc[2].
     token = doc[2]
     with doc.retokenize() as retokenizer:
-      retokenizer.split(token, ["brown", "fox", "jumps", "over", "the"], heads=[(token, idx) for idx in range(5)])
+        retokenizer.split(
+            token,
+            ["brown", "fox", "jumps", "over", "the"],
+            heads=[(token, idx) for idx in range(5)],
+        )
 
-    assert doc[9].text  == "w/"
+    assert doc[9].text == "w/"
     assert doc[9].norm_ == "with"
-    assert doc[5].text  == "over"
+    assert doc[5].text == "over"
     assert doc[5].norm_ == "over"

spacy/tests/pipeline/test_pipe_methods.py

@@ -350,7 +350,7 @@ def test_pipe_methods_frozen():
 
 
 @pytest.mark.parametrize(
-    "pipe", ["tagger", "parser", "ner", "textcat", "morphologizer"],
+    "pipe", ["tagger", "parser", "ner", "textcat", "morphologizer"]
 )
 def test_pipe_label_data_exports_labels(pipe):
     nlp = Language()

spacy/tests/test_models.py

@@ -64,7 +64,7 @@ def get_tok2vec_kwargs():
             width=32,
             rows=[500, 500, 500],
             attrs=["NORM", "PREFIX", "SHAPE"],
-            include_static_vectors=False
+            include_static_vectors=False,
         ),
         "encode": MaxoutWindowEncoder(
             width=32, depth=2, maxout_pieces=2, window_size=1
@@ -81,7 +81,7 @@ def test_multi_hash_embed():
         width=32,
         rows=[500, 500, 500],
         attrs=["NORM", "PREFIX", "SHAPE"],
-        include_static_vectors=False
+        include_static_vectors=False,
     )
     hash_embeds = [node for node in embed.walk() if node.name == "hashembed"]
     assert len(hash_embeds) == 3
@@ -96,7 +96,7 @@ def test_multi_hash_embed():
         width=32,
         rows=[1000, 50, 250],
         attrs=["NORM", "PREFIX", "SHAPE"],
-        include_static_vectors=False
+        include_static_vectors=False,
     )
     hash_embeds = [node for node in embed.walk() if node.name == "hashembed"]
     assert [he.get_dim("nV") for he in hash_embeds] == [1000, 50, 250]

spacy/training/augment.py

@@ -64,7 +64,7 @@ def dont_augment(nlp: "Language", example: Example) -> Iterator[Example]:
 
 
 def lower_casing_augmenter(
-    nlp: "Language", example: Example, *, level: float,
+    nlp: "Language", example: Example, *, level: float
 ) -> Iterator[Example]:
     if random.random() >= level:
         yield example