[pre-commit.ci] pre-commit autoupdate (#431)

* [pre-commit.ci] pre-commit autoupdate

updates:
- [github.com/astral-sh/ruff-pre-commit: v0.2.2 → v0.3.2](astral-sh/ruff-pre-commit@v0.2.2...v0.3.2)

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix lint errors; format docstrings with ruff

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Steven Loria <sloria1@gmail.com>

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
 - repo: https://github.com/astral-sh/ruff-pre-commit
-  rev: v0.2.2
+  rev: v0.3.2
   hooks:
     - id: ruff
     - id: ruff-format

pyproject.toml

@@ -75,6 +75,9 @@ exclude = [
   "src/textblob/_text.py",
 ]
 
+[tool.ruff.format]
+docstring-code-format = true
+
 [tool.ruff.lint]
 select = [
   "B",  # flake8-bugbear

src/textblob/base.py

@@ -4,6 +4,7 @@
 .. versionchanged:: 0.7.0
     All base classes are defined in the same module, ``textblob.base``.
 """
+
 from abc import ABCMeta, abstractmethod
 
 import nltk

src/textblob/blob.py

@@ -19,6 +19,7 @@
 .. versionchanged:: 0.8.0
     These classes are now imported from ``textblob`` rather than ``text.blob``.
 """  # noqa: E501
+
 import json
 import sys
 from collections import defaultdict
@@ -65,7 +66,6 @@ def _penn_to_wordnet(tag):
 
 
 class Word(str):
-
     """A simple word representation. Includes methods for inflection,
     and WordNet integration.
     """
@@ -486,8 +486,14 @@ def pos_tags(self):
         Example:
         ::
 
-            [('At', 'IN'), ('eight', 'CD'), ("o'clock", 'JJ'), ('on', 'IN'),
-                    ('Thursday', 'NNP'), ('morning', 'NN')]
+            [
+                ("At", "IN"),
+                ("eight", "CD"),
+                ("o'clock", "JJ"),
+                ("on", "IN"),
+                ("Thursday", "NNP"),
+                ("morning", "NN"),
+            ]
 
         :rtype: list of tuples
         """
@@ -775,15 +781,12 @@ def __repr__(self):
             self.classifier.__class__.__name__ + "()" if self.classifier else "None"
         )
         return (
-            "Blobber(tokenizer={}(), pos_tagger={}(), "
-            "np_extractor={}(), analyzer={}(), parser={}(), classifier={})"
-        ).format(
-            self.tokenizer.__class__.__name__,
-            self.pos_tagger.__class__.__name__,
-            self.np_extractor.__class__.__name__,
-            self.analyzer.__class__.__name__,
-            self.parser.__class__.__name__,
-            classifier_name,
+            f"Blobber(tokenizer={self.tokenizer.__class__.__name__}(), "
+            f"pos_tagger={self.pos_tagger.__class__.__name__}(), "
+            f"np_extractor={self.np_extractor.__class__.__name__}(), "
+            f"analyzer={self.analyzer.__class__.__name__}(), "
+            f"parser={self.parser.__class__.__name__}(), "
+            f"classifier={classifier_name})"
         )
 
     __str__ = __repr__

src/textblob/classifiers.py

@@ -30,6 +30,7 @@
 
 .. versionadded:: 0.6.0
 """  # noqa: E501
+
 from itertools import chain
 
 import nltk

src/textblob/download_corpora.py

@@ -11,6 +11,7 @@
     $ python -m textblob.download_corpora lite
 
 """
+
 import sys
 
 import nltk

src/textblob/formats.py

@@ -5,19 +5,22 @@
 
     from textblob import formats
 
+
     class PipeDelimitedFormat(formats.DelimitedFormat):
-        delimiter = '|'
+        delimiter = "|"
+
 
-    formats.register('psv', PipeDelimitedFormat)
+    formats.register("psv", PipeDelimitedFormat)
 
 Once a format has been registered, classifiers will be able to read data files with
 that format. ::
 
     from textblob.classifiers import NaiveBayesAnalyzer
 
-    with open('training_data.psv', 'r') as fp:
-        cl = NaiveBayesAnalyzer(fp, format='psv')
+    with open("training_data.psv", "r") as fp:
+        cl = NaiveBayesAnalyzer(fp, format="psv")
 """
+
 import csv
 import json
 from collections import OrderedDict
@@ -105,7 +108,7 @@ class JSON(BaseFormat):
 
         [
             {"text": "Today is a good day.", "label": "pos"},
-            {"text": "I hate this car.", "label": "neg"}
+            {"text": "I hate this car.", "label": "neg"},
         ]
     """
 

src/textblob/inflect.py

@@ -7,6 +7,7 @@
 
     >>> from textblob.en.inflect import singularize
 """
+
 from textblob.en.inflect import pluralize, singularize
 
 __all__ = [

src/textblob/mixins.py

@@ -2,7 +2,6 @@
 
 
 class ComparableMixin:
-
     """Implements rich operators for an object."""
 
     def _compare(self, other, method):
@@ -33,7 +32,6 @@ def __ne__(self, other):
 
 
 class BlobComparableMixin(ComparableMixin):
-
     """Allow blob objects to be comparable with both strings and blobs."""
 
     def _compare(self, other, method):
@@ -44,7 +42,6 @@ def _compare(self, other, method):
 
 
 class StringlikeMixin:
-
     """Make blob objects behave like Python strings.
 
     Expects that classes that use this mixin to have a _strkey() method that

src/textblob/np_extractors.py

@@ -7,6 +7,7 @@
 
 >>> from textblob.en.np_extractors import ConllExtractor
 """
+
 from textblob.base import BaseNPExtractor
 from textblob.en.np_extractors import ConllExtractor, FastNPExtractor
 

src/textblob/parsers.py

@@ -6,6 +6,7 @@
 
 >>> from textblob.en.parsers import PatternParser
 """
+
 from textblob.base import BaseParser
 from textblob.en.parsers import PatternParser
 

src/textblob/sentiments.py

@@ -7,6 +7,7 @@
 
 >>> from textblob.en.sentiments import PatternAnalyzer
 """
+
 from textblob.base import BaseSentimentAnalyzer
 from textblob.en.sentiments import (
     CONTINUOUS,

src/textblob/taggers.py

@@ -7,6 +7,7 @@
 
 >>> from textblob.en.taggers import NLTKTagger
 """
+
 from textblob.base import BaseTagger
 from textblob.en.taggers import NLTKTagger, PatternTagger
 

src/textblob/tokenizers.py

@@ -2,6 +2,7 @@
 
 .. versionadded:: 0.4.0
 """
+
 from itertools import chain
 
 import nltk

src/textblob/wordnet.py

@@ -4,6 +4,7 @@
 .. versionadded:: 0.7.0
 
 """
+
 import nltk
 
 #: wordnet module from nltk

tests/test_blob.py

@@ -1,6 +1,7 @@
 """
 Tests for the text processor.
 """
+
 import json
 from datetime import datetime
 from unittest import TestCase

tests/test_classifiers.py

@@ -47,7 +47,6 @@
 
 
 class BadNLTKClassifier(NLTKClassifier):
-
     """An NLTK classifier without ``nltk_class`` defined. Oops!"""
 
     pass
@@ -329,9 +328,7 @@ def test_accuracy(self):
     def test_repr(self):
         assert (
             repr(self.classifier)
-            == "<PositiveNaiveBayesClassifier trained on {} labeled and {} unlabeled instances>".format(  # noqa: E501
-                len(self.classifier.positive_set), len(self.classifier.unlabeled_set)
-            )
+            == f"<PositiveNaiveBayesClassifier trained on {len(self.classifier.positive_set)} labeled and {len(self.classifier.unlabeled_set)} unlabeled instances>"  # noqa: E501
         )