Tidy up and auto-format

spacy/cli/info.py

@@ -105,12 +105,15 @@ def info_model(model: str, *, silent: bool = True) -> Dict[str, Any]:
 
 
 def get_markdown(
-    data: Dict[str, Any], title: Optional[str] = None, exclude: Optional[List[str]] = None
+    data: Dict[str, Any],
+    title: Optional[str] = None,
+    exclude: Optional[List[str]] = None,
 ) -> str:
     """Get data in GitHub-flavoured Markdown format for issues etc.
 
-    data (dict or list of tuples): Label/value pairs.
+    data (Dict[str, Any]): Label/value pairs.
-    title (str / None): Title, will be rendered as headline 2.
+    title (str): Optional title, will be rendered as headline 2.
+    exclude (List[str]): Names of keys to exclude.
     RETURNS (str): The Markdown string.
     """
     md = MarkdownRenderer()

spacy/lang/es/__init__.py

@@ -29,7 +29,9 @@ class Spanish(Language):
     default_config={"model": None, "mode": "rule", "overwrite": False},
     default_score_weights={"lemma_acc": 1.0},
 )
-def make_lemmatizer(nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool):
+def make_lemmatizer(
+    nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool
+):
     return SpanishLemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)
 
 

spacy/lang/ky/tokenizer_exceptions.py

@@ -47,6 +47,7 @@ for exc_data in [  # "etc." abbreviations
     {ORTH: "көч.", NORM: "көчөсү"},
     {ORTH: "м-н", NORM: "менен"},
     {ORTH: "б-ча", NORM: "боюнча"},
-]:    _exc[exc_data[ORTH]] = [exc_data]
+]:
+    _exc[exc_data[ORTH]] = [exc_data]
 
 TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)

spacy/lang/mk/lemmatizer.py

@@ -9,7 +9,6 @@ class MacedonianLemmatizer(Lemmatizer):
     def rule_lemmatize(self, token: Token) -> List[str]:
         string = token.text
         univ_pos = token.pos_.lower()
-        morphology = token.morph.to_dict()
 
         if univ_pos in ("", "eol", "space"):
             return [string.lower()]

spacy/language.py

@@ -1686,7 +1686,10 @@ class Language:
         return nlp
 
     def replace_listeners(
-        self, tok2vec_name: str, pipe_name: str, listeners: Iterable[str],
+        self,
+        tok2vec_name: str,
+        pipe_name: str,
+        listeners: Iterable[str],
     ) -> None:
         """Find listener layers (connecting to a token-to-vector embedding
         component) of a given pipeline component model and replace

spacy/pipeline/attributeruler.py

@@ -135,7 +135,6 @@ class AttributeRuler(Pipe):
                 ) from None
             set_token_attrs(span[index], attrs)
 
-
     def load_from_tag_map(
         self, tag_map: Dict[str, Dict[Union[int, str], Union[int, str]]]
     ) -> None:

spacy/pipeline/entity_linker.py

@@ -217,7 +217,6 @@ class EntityLinker(TrainablePipe):
             return losses
         validate_examples(examples, "EntityLinker.update")
         sentence_docs = []
-        docs = [eg.predicted for eg in examples]
         for eg in examples:
             sentences = [s for s in eg.reference.sents]
             kb_ids = eg.get_aligned("ENT_KB_ID", as_string=True)

spacy/pipeline/functions.py

@@ -1,10 +1,9 @@
-import srsly
-from thinc.api import Config
 from typing import Dict, Any
+import srsly
+
 from ..language import Language
 from ..matcher import Matcher
 from ..tokens import Doc
-from ..util import filter_spans
 from .. import util
 
 
@@ -64,7 +63,7 @@ def merge_subtokens(doc: Doc, label: str = "subtok") -> Doc:
     merger = Matcher(doc.vocab)
     merger.add("SUBTOK", [[{"DEP": label, "op": "+"}]])
     matches = merger(doc)
-    spans = filter_spans([doc[start : end + 1] for _, start, end in matches])
+    spans = util.filter_spans([doc[start : end + 1] for _, start, end in matches])
     with doc.retokenize() as retokenizer:
         for span in spans:
             retokenizer.merge(span)
@@ -77,15 +76,9 @@ def merge_subtokens(doc: Doc, label: str = "subtok") -> Doc:
     retokenizes=True,
 )
 def make_token_splitter(
-    nlp: Language,
+    nlp: Language, name: str, *, min_length=0, split_length=0,
-    name: str,
-    *,
-    min_length=0,
-    split_length=0,
 ):
-    return TokenSplitter(
+    return TokenSplitter(min_length=min_length, split_length=split_length)
-        min_length=min_length, split_length=split_length
-    )
 
 
 class TokenSplitter:

spacy/pipeline/lemmatizer.py

@@ -1,5 +1,4 @@
-from typing import Optional, List, Dict, Any, Callable, Iterable, Iterator, Union
+from typing import Optional, List, Dict, Any, Callable, Iterable, Union, Tuple
-from typing import Tuple
 from thinc.api import Model
 from pathlib import Path
 

spacy/tests/doc/test_doc_api.py

@@ -641,7 +641,8 @@ def test_doc_noun_chunks_not_implemented():
     nlp = MultiLanguage()
     doc = nlp(text)
     with pytest.raises(NotImplementedError):
-        chunks = list(doc.noun_chunks)
+        _ = list(doc.noun_chunks)  # noqa: F841
+
 
 def test_span_groups(en_tokenizer):
     doc = en_tokenizer("Some text about Colombia and the Czech Republic")

spacy/tests/lang/ky/test_tokenizer.py

@@ -18,9 +18,7 @@ PUNC_INSIDE_WORDS_TESTS = [
     ('То"кой', 'То " кой'.split()),
 ]
 
-MIXED_ORDINAL_NUMS_TESTS = [
+MIXED_ORDINAL_NUMS_TESTS = [("Эртең 22-январь...", "Эртең 22 - январь ...".split())]
-    ("Эртең 22-январь...", "Эртең 22 - январь ...".split())
-]
 
 ABBREV_TESTS = [
     ("Маселе б-ча эртең келет", "Маселе б-ча эртең келет".split()),

spacy/tests/matcher/test_dependency_matcher.py

@@ -2,7 +2,6 @@ import pytest
 import pickle
 import re
 import copy
-import logging
 from mock import Mock
 from spacy.matcher import DependencyMatcher
 from spacy.tokens import Doc
@@ -343,6 +342,5 @@ def test_dependency_matcher_long_matches(en_vocab, doc):
     ]
 
     matcher = DependencyMatcher(en_vocab)
-    logger = logging.getLogger("spacy")
     with pytest.raises(ValueError):
         matcher.add("pattern", [pattern])

spacy/tests/matcher/test_phrase_matcher.py

@@ -322,4 +322,4 @@ def test_phrase_matcher_deprecated(en_vocab):
 
 @pytest.mark.parametrize("attr", ["SENT_START", "IS_SENT_START"])
 def test_phrase_matcher_sent_start(en_vocab, attr):
-    matcher = PhraseMatcher(en_vocab, attr=attr)
+    _ = PhraseMatcher(en_vocab, attr=attr)  # noqa: F841

spacy/tests/pipeline/test_tok2vec.py

@@ -6,7 +6,6 @@ from spacy.pipeline.tok2vec import Tok2Vec, Tok2VecListener
 from spacy.vocab import Vocab
 from spacy.tokens import Doc
 from spacy.training import Example
-from spacy.training.initialize import init_nlp
 from spacy import util
 from spacy.lang.en import English
 from thinc.api import Config

spacy/tests/regression/test_issue6001-6500.py

@@ -1,6 +1,21 @@
-import pytest
+from spacy.util import filter_spans
 from pydantic import ValidationError
 from spacy.schemas import TokenPattern, TokenPatternSchema
+import pytest
+
+
+def test_issue6207(en_tokenizer):
+    doc = en_tokenizer("zero one two three four five six")
+
+    # Make spans
+    s1 = doc[:4]
+    s2 = doc[3:6]  # overlaps with s1
+    s3 = doc[5:7]  # overlaps with s2, not s1
+
+    result = filter_spans((s1, s2, s3))
+    assert s1 in result
+    assert s2 not in result
+    assert s3 in result
 
 
 def test_issue6258():

spacy/tests/regression/test_issue6207.py

@@ -1,15 +0,0 @@
-from spacy.util import filter_spans
-
-
-def test_issue6207(en_tokenizer):
-    doc = en_tokenizer("zero one two three four five six")
-
-    # Make spans
-    s1 = doc[:4]
-    s2 = doc[3:6]  # overlaps with s1
-    s3 = doc[5:7]  # overlaps with s2, not s1
-
-    result = filter_spans((s1, s2, s3))
-    assert s1 in result
-    assert s2 not in result
-    assert s3 in result

spacy/tests/regression/test_issue6815.py

@@ -4,9 +4,8 @@ import numpy as np
 
 
 @pytest.mark.parametrize(
-    "sentence, start_idx,end_idx,label", [
+    "sentence, start_idx,end_idx,label",
-        ('Welcome to Mumbai, my friend',11,17,'GPE')
+    [("Welcome to Mumbai, my friend", 11, 17, "GPE")],
-    ]
 )
 def test_char_span_label(sentence, start_idx, end_idx, label):
     nlp = English()
@@ -14,10 +13,9 @@ def test_char_span_label(sentence, start_idx, end_idx, label):
     span = doc[:].char_span(start_idx, end_idx, label=label)
     assert span.label_ == label
 
+
 @pytest.mark.parametrize(
-    "sentence, start_idx,end_idx,kb_id", [
+    "sentence, start_idx,end_idx,kb_id", [("Welcome to Mumbai, my friend", 11, 17, 5)]
-        ('Welcome to Mumbai, my friend',11,17,5)
-    ]
 )
 def test_char_span_kb_id(sentence, start_idx, end_idx, kb_id):
     nlp = English()
@@ -25,10 +23,10 @@ def test_char_span_kb_id(sentence, start_idx, end_idx, kb_id):
     span = doc[:].char_span(start_idx, end_idx, kb_id=kb_id)
     assert span.kb_id == kb_id
 
+
 @pytest.mark.parametrize(
-    "sentence, start_idx,end_idx,vector", [
+    "sentence, start_idx,end_idx,vector",
-        ('Welcome to Mumbai, my friend',11,17,np.array([0.1,0.2,0.3]))
+    [("Welcome to Mumbai, my friend", 11, 17, np.array([0.1, 0.2, 0.3]))],
-    ]
 )
 def test_char_span_vector(sentence, start_idx, end_idx, vector):
     nlp = English()

spacy/tests/test_language.py

@@ -186,6 +186,7 @@ def test_language_pipe_error_handler():
 
 def test_language_pipe_error_handler_custom(en_vocab):
     """Test the error handling of a custom component that has no pipe method"""
+
     @Language.component("my_evil_component")
     def evil_component(doc):
         if "2" in doc.text:
@@ -194,6 +195,7 @@ def test_language_pipe_error_handler_custom(en_vocab):
 
     def warn_error(proc_name, proc, docs, e):
         from spacy.util import logger
+
         logger.warning(f"Trouble with component {proc_name}.")
 
     nlp = English()
@@ -217,6 +219,7 @@ def test_language_pipe_error_handler_custom(en_vocab):
 
 def test_language_pipe_error_handler_pipe(en_vocab):
     """Test the error handling of a component's pipe method"""
+
     @Language.component("my_sentences")
     def perhaps_set_sentences(doc):
         if not doc.text.startswith("4"):