[pre-commit] Add codespell, and fix some existing typos (#9912)

Pierre-Sassoulas · web-flow · commit 09509163baab · 2024-09-19T11:33:41.000+02:00
* Add the spellchecker codespell to the pre-commit configuration
* Make the dict name generic now that it's used by multiple tools
* Fix existing typos
* Sort the custom dict
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -7,6 +7,9 @@ repos:
     hooks:
       - id: trailing-whitespace
         exclude: tests(/\w*)*/functional/t/trailing_whitespaces.py|tests/pyreverse/data/.*.html|doc/data/messages/t/trailing-whitespace/bad.py
+      #      - id: file-contents-sorter # commented out because it does not preserve comments order
+      #        args: ["--ignore-case", "--unique"]
+      #        files: "custom_dict.txt"
       - id: end-of-file-fixer
         exclude: |
           (?x)^(
@@ -173,3 +176,10 @@ repos:
       - id: bandit
         args: ["-r", "-lll"]
         exclude: *fixtures
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.3.0
+    hooks:
+      - id: codespell
+        args: ["--toml=pyproject.toml"]
+        additional_dependencies:
+          - tomli
diff --git a/custom_dict.txt b/custom_dict.txt
@@ -13,10 +13,11 @@ argumentparser
 argumentsparser
 argv
 ascii
+asend
 assignattr
 assignname
-ast
 AST
+ast
 astroid
 async
 asynccontextmanager
@@ -67,8 +68,8 @@ contextlib
 contextmanager
 contravariance
 contravariant
-cpython
 CPython
+cpython
 csv
 CVE
 cwd
@@ -126,8 +127,8 @@ formfeed
 fromlineno
 fullname
 func
-functiøn
 functiondef
+functiøn
 functools
 genexpr
 getattr
@@ -160,10 +161,11 @@ isfile
 isinstance
 isort
 iter
-itered
 iterable
 iterables
+itered
 iteritems
+iTerm
 jn
 jpg
 json
@@ -206,10 +208,10 @@ monkeypatch
 mro
 # Used so much that we need the abbreviation
 msg
+msg-template
 msgid
 msgids
 msgs
-msg-template
 mult
 multiline
 multiset
@@ -250,8 +252,8 @@ parens
 passthru
 pathlib
 patternerror
-positionals
 png
+positionals
 pragma
 pragma's
 pragmas
@@ -264,9 +266,9 @@ pyenchant
 pyfile
 pyi
 pylint
+pylint's
 pylintdict
 pylintrc
-pylint's
 pyproject
 pypy
 pyreverse
@@ -275,6 +277,7 @@ qname
 rawcheckers
 rc
 rcfile
+re-usable
 readlines
 recognise
 recurse
@@ -345,9 +348,9 @@ tomlkit
 toplevel
 towncrier
 tp
+truthey
 truthness
 truthy
-truthey
 tryexcept
 txt
 typecheck
@@ -362,8 +365,8 @@ unary
 unflattens
 unhandled
 unicode
-Uninferable
 uninferable
+Uninferable
 unittest
 unraisablehook
 untriggered
diff --git a/doc/development_guide/contributor_guide/profiling.rst b/doc/development_guide/contributor_guide/profiling.rst
@@ -90,7 +90,7 @@ and thus is displayed as being 0.
 
 Often you are more interested in the cumulative time (per call). This refers to the time spent within the function
 and any of the functions it called or the functions they called (etc.). In our example, the ``visit_importfrom``
-method and all of its child-functions took a little over 8 seconds to exectute, with an execution time of
+method and all of its child-functions took a little over 8 seconds to execute, with an execution time of
 0.013 ms per call.
 
 You can also search the ``profiler_stats`` for an individual function you want to check. For example
diff --git a/doc/development_guide/contributor_guide/tests/writing_test.rst b/doc/development_guide/contributor_guide/tests/writing_test.rst
@@ -21,7 +21,7 @@ Unittest tests
 
 Most other tests reside in the '/pylint/test' directory. These unittests can be used to test
 almost all functionality within Pylint. A good step before writing any new unittests is to look
-at some tests that test a similar funcitionality. This can often help write new tests.
+at some tests that test a similar functionality. This can often help write new tests.
 
 If your new test requires any additional files you can put those in the
 ``/pylint/test/regrtest_data`` directory. This is the directory we use to store any data needed for
diff --git a/doc/user_guide/checkers/features.rst b/doc/user_guide/checkers/features.rst
@@ -918,16 +918,16 @@ Refactoring checker Messages
   Emitted when a single "return" or "return None" statement is found at the end
   of function or method definition. This statement can safely be removed
   because Python will implicitly return None
-:use-implicit-booleaness-not-comparison-to-string (C1804): *"%s" can be simplified to "%s", if it is striclty a string, as an empty string is falsey*
-  Empty string are considered false in a boolean context. Following this check
-  blindly in weakly typed code base can create hard to debug issues. If the
-  value can be something else that is falsey but not a string (for example
-  ``None``, an empty sequence, or ``0``) the code will not be equivalent.
 :use-implicit-booleaness-not-comparison (C1803): *"%s" can be simplified to "%s", if it is strictly a sequence, as an empty %s is falsey*
   Empty sequences are considered false in a boolean context. Following this
   check blindly in weakly typed code base can create hard to debug issues. If
   the value can be something else that is falsey but not a sequence (for
   example ``None``, an empty string, or ``0``) the code will not be equivalent.
+:use-implicit-booleaness-not-comparison-to-string (C1804): *"%s" can be simplified to "%s", if it is strictly a string, as an empty string is falsey*
+  Empty string are considered false in a boolean context. Following this check
+  blindly in weakly typed code base can create hard to debug issues. If the
+  value can be something else that is falsey but not a string (for example
+  ``None``, an empty sequence, or ``0``) the code will not be equivalent.
 :use-implicit-booleaness-not-comparison-to-zero (C1805): *"%s" can be simplified to "%s", if it is strictly an int, as 0 is falsey*
   0 is considered false in a boolean context. Following this check blindly in
   weakly typed code base can create hard to debug issues. If the value can be
diff --git a/doc/whatsnew/0/0.x.rst b/doc/whatsnew/0/0.x.rst
@@ -1001,7 +1001,7 @@ Release date: 2004-10-19
 * avoid importing analyzed modules !
 
 * new Refactor and Convention message categories. Some Warnings have been
-  remaped into those new categories
+  remapped into those new categories
 
 * added "similar", a tool to find copied and pasted lines of code,
   both using a specific command line tool and integrated as a
diff --git a/doc/whatsnew/1/1.5.rst b/doc/whatsnew/1/1.5.rst
@@ -435,7 +435,7 @@ Release date: 2015-11-29
 * astroid.utils.LocalsVisitor was moved to pylint.pyreverse.LocalsVisitor.
 
 * pylint.checkers.utils.excepts_import_error was removed.
-  Use pylint.chekcers.utils.error_of_type instead.
+  Use pylint.checkers.utils.error_of_type instead.
 
 * Don't emit undefined-all-variables for nodes which can't be
   inferred (YES nodes).
diff --git a/doc/whatsnew/2/2.0/summary.rst b/doc/whatsnew/2/2.0/summary.rst
@@ -221,7 +221,7 @@ Other Changes
   ``pylint`` should be a bit faster as well.
 
   We added a new flag, ``max_inferable_values`` on ``astroid.MANAGER`` for
-  limitting the maximum amount of values that ``astroid`` can infer when inferring
+  limiting the maximum amount of values that ``astroid`` can infer when inferring
   values. This change should improve the performance when dealing with large frameworks
   such as ``django``.
   You can also control this behaviour with ``pylint --limit-inference-results``
diff --git a/doc/whatsnew/2/2.13/summary.rst b/doc/whatsnew/2/2.13/summary.rst
@@ -81,7 +81,7 @@ New checkers
   creates memory leaks by never letting the instance get garbage collected.
 
   Closes #5670
-  Clsoes #6180
+  Closes #6180
 
 Removed checkers
 ================
diff --git a/doc/whatsnew/2/2.4/full.rst b/doc/whatsnew/2/2.4/full.rst
@@ -137,7 +137,7 @@ Release date: 2019-09-24
   Closes #2925
 
 * ``useless-suppression`` check now ignores ``cyclic-import`` suppressions,
-  which could lead to false postiives due to incomplete context at the time
+  which could lead to false positives due to incomplete context at the time
   of the check.
 
   Closes #3064
diff --git a/doc/whatsnew/2/2.6/full.rst b/doc/whatsnew/2/2.6/full.rst
@@ -54,7 +54,7 @@ Release date: 2020-08-20
 
 * Add ``raise-missing-from`` check for exceptions that should have a cause.
 
-* Support both isort 4 and isort 5. If you have pinned isort 4 in your projet requirements, nothing changes. If you use isort 5, though, note that the ``known-standard-library`` option is not interpreted the same in isort 4 and isort 5 (see the migration guide in isort documentation for further details). For compatibility's sake for most pylint users, the ``known-standard-library`` option in pylint now maps to ``extra-standard-library`` in isort 5. If you really want what ``known-standard-library`` now means in isort 5, you must disable the ``wrong-import-order`` check in pylint and run isort manually with a proper isort configuration file.
+* Support both isort 4 and isort 5. If you have pinned isort 4 in your project requirements, nothing changes. If you use isort 5, though, note that the ``known-standard-library`` option is not interpreted the same in isort 4 and isort 5 (see the migration guide in isort documentation for further details). For compatibility's sake for most pylint users, the ``known-standard-library`` option in pylint now maps to ``extra-standard-library`` in isort 5. If you really want what ``known-standard-library`` now means in isort 5, you must disable the ``wrong-import-order`` check in pylint and run isort manually with a proper isort configuration file.
 
   Closes #3722
 
diff --git a/doc/whatsnew/2/2.6/summary.rst b/doc/whatsnew/2/2.6/summary.rst
@@ -25,4 +25,4 @@ Other Changes
 
 * Fix superfluous-parens false-positive for the walrus operator
 
-* Add support for both isort 4 and isort 5. If you have pinned isort 4 in your projet requirements, nothing changes. If you use isort 5, though, note that the ``known-standard-library`` option is not interpreted the same in isort 4 and isort 5 (see `the migration guide in isort documentation` (no longer available) for further details). For compatibility's sake for most pylint users, the ``known-standard-library`` option in pylint now maps to ``extra-standard-library`` in isort 5. If you really want what ``known-standard-library`` now means in isort 5, you must disable the ``wrong-import-order`` check in pylint and run isort manually with a proper isort configuration file.
+* Add support for both isort 4 and isort 5. If you have pinned isort 4 in your project requirements, nothing changes. If you use isort 5, though, note that the ``known-standard-library`` option is not interpreted the same in isort 4 and isort 5 (see `the migration guide in isort documentation` (no longer available) for further details). For compatibility's sake for most pylint users, the ``known-standard-library`` option in pylint now maps to ``extra-standard-library`` in isort 5. If you really want what ``known-standard-library`` now means in isort 5, you must disable the ``wrong-import-order`` check in pylint and run isort manually with a proper isort configuration file.
diff --git a/doc/whatsnew/3/3.1/index.rst b/doc/whatsnew/3/3.1/index.rst
@@ -118,7 +118,7 @@ Other Bug Fixes
   The message will report imports as follows:
   For "import X", it will report "(standard/third party/first party/local) import X"
   For "import X.Y" and "from X import Y", it will report "(standard/third party/first party/local) import X.Y"
-  The import category is specified to provide explanation as to why pylint has issued the message and guidence to the developer on how to fix the problem.
+  The import category is specified to provide explanation as to why pylint has issued the message and guidance to the developer on how to fix the problem.
 
   Closes #8808 (`#8808 <https://github.com/pylint-dev/pylint/issues/8808>`_)
 
diff --git a/pylint/checkers/base/function_checker.py b/pylint/checkers/base/function_checker.py
@@ -45,7 +45,7 @@ def _check_contextmanager_generator_missing_cleanup(
         :param node: FunctionDef node to check
         :type node: nodes.FunctionDef
         """
-        # if function does not use a Yield statement, it cant be a generator
+        # if function does not use a Yield statement, it can't be a generator
         with_nodes = list(node.nodes_of_class(nodes.With))
         if not with_nodes:
             return
diff --git a/pylint/checkers/refactoring/implicit_booleaness_checker.py b/pylint/checkers/refactoring/implicit_booleaness_checker.py
@@ -81,7 +81,7 @@ class ImplicitBooleanessChecker(checkers.BaseChecker):
             "equivalent.",
         ),
         "C1804": (
-            '"%s" can be simplified to "%s", if it is striclty a string, as an empty string is falsey',
+            '"%s" can be simplified to "%s", if it is strictly a string, as an empty string is falsey',
             "use-implicit-booleaness-not-comparison-to-string",
             "Empty string are considered false in a boolean context. Following this"
             " check blindly in weakly typed code base can create hard to debug issues."
diff --git a/pylintrc b/pylintrc
@@ -400,7 +400,7 @@ spelling-ignore-words=
 spelling-ignore-comment-directives=fmt: on,fmt: off,noqa:,noqa,nosec,isort:skip,mypy:,pragma:,# noinspection
 
 # A path to a file that contains private dictionary; one word per line.
-spelling-private-dict-file=.pyenchant_pylint_custom_dict.txt
+spelling-private-dict-file=custom_dict.txt
 
 # Tells whether to store unknown words to indicated private dictionary in
 # --spelling-private-dict-file option instead of raising a message.
diff --git a/pyproject.toml b/pyproject.toml
@@ -200,3 +200,32 @@ ignore = [
 
 [tool.ruff.lint.pydocstyle]
 convention = "pep257"
+
+[tool.codespell]
+ignore-words = ["custom_dict.txt"]
+
+# Disabled the spelling files for obvious reason, but also,
+# the test file with typing extension imported as 'te' and:
+# tests/functional/i/implicit/implicit_str_concat_latin1.py:
+#   - bad encoding
+# pylint/pyreverse/diagrams.py and tests/pyreverse/test_diagrams.py:
+#   - An API from pyreverse use 'classe', and would need to be deprecated
+# pylint/checkers/imports.py:
+#   - 'THIRDPARTY' is a value from isort that would need to be handled even
+#   if isort fix the typo in newer versions
+# tests/functional/m/member/member_checks.py:
+#   - typos are voluntary to create credible 'no-member'
+
+skip = """
+tests/checkers/unittest_spelling.py,\
+CODE_OF_CONDUCT.md,\
+CONTRIBUTORS.txt,\
+pylint/checkers/imports.py,\
+pylint/pyreverse/diagrams.py,\
+tests/pyreverse/test_diagrams.py,\
+tests/functional/i/implicit/implicit_str_concat_latin1.py,\
+tests/functional/m/member/member_checks.py,\
+tests/functional/t/type/typevar_naming_style_rgx.py,\
+tests/functional/t/type/typevar_naming_style_default.py,\
+tests/functional/m/member/member_checks_async.py,\
+"""
diff --git a/tests/checkers/unittest_misc.py b/tests/checkers/unittest_misc.py
@@ -40,7 +40,7 @@ def test_xxx_without_space(self) -> None:
 
     def test_xxx_middle(self) -> None:
         code = """a = 1
-                # midle XXX
+                # middle XXX
                 """
         with self.assertNoMessages():
             self.checker.process_tokens(_tokenize_str(code))
diff --git a/tests/config/functional/toml/unknown_msgid/enable_unknown_msgid.toml b/tests/config/functional/toml/unknown_msgid/enable_unknown_msgid.toml
@@ -1,4 +1,4 @@
-# Check the behavior for unkonwn symbol/msgid
+# Check the behavior for unknown symbol/msgid
 # (Originally) reported in https://github.com/pylint-dev/pylint/pull/6293
 
 [tool.pylint."messages control"]
diff --git a/tests/data/a_script b/tests/data/a_script
diff --git a/tests/functional/a/arguments_differ.py b/tests/functional/a/arguments_differ.py
@@ -280,7 +280,7 @@ class ChildT3(ParentT3):
     def func(self, user_input: FooT1) -> None:
         pass
 
-# Keyword and positional overriddes
+# Keyword and positional overrides
 class AbstractFoo:
 
     def kwonly_1(self, first, *, second, third):
diff --git a/tests/functional/c/consider/consider_using_get.py b/tests/functional/c/consider/consider_using_get.py
@@ -16,10 +16,10 @@
 if 'key' in dictionary:  # not accessing the dictionary in assignment
     variable = "string"
 
-if 'key' in dictionary:  # is a match, but not obvious and we ignore it for now
+if 'key' in dictionary:  # is a match, but not obvious, and we ignore it for now
     variable = dictionary[key]
 
-if 'key1' in dictionary:  # dictionary querried for wrong key
+if 'key1' in dictionary:  # dictionary queried for wrong key
     variable = dictionary['key2']
 
 if 'key' in dictionary:  # body is not pure
diff --git a/tests/functional/i/inconsistent/inconsistent_quotes_fstring_py312.py b/tests/functional/i/inconsistent/inconsistent_quotes_fstring_py312.py
@@ -1,5 +1,5 @@
 # pylint: disable=missing-module-docstring
 
 dictionary = {'0': 0}
-# quotes are inconsistent when targetting Python 3.12 (use single quotes)
+# quotes are inconsistent when targeting Python 3.12 (use single quotes)
 F_STRING = f'{dictionary["0"]}'  # [inconsistent-quotes]
diff --git a/tests/functional/i/inconsistent/inconsistent_quotes_fstring_py312_311.py b/tests/functional/i/inconsistent/inconsistent_quotes_fstring_py312_311.py
@@ -1,5 +1,5 @@
 # pylint: disable=missing-module-docstring
 
 dictionary = {'0': 0}
-# quotes are consistent when targetting 3.11 and earlier (cannot use single quotes here)
+# quotes are consistent when targeting 3.11 and earlier (cannot use single quotes here)
 F_STRING = f'{dictionary["0"]}'
diff --git a/tests/functional/m/misplaced_format_function.py b/tests/functional/m/misplaced_format_function.py
@@ -6,7 +6,7 @@
 print("value: {}").format(123)  # [misplaced-format-function]
 print('value: {}'.format(123))
 print('{} Come Forth!'.format('Lazarus'))
-print('Der Hem ist mein Licht und mein Heil, vor wem sollte ich mich furchten? => {}'.format('Psalm 27, 1'))
+print('He is my light and my salvation, of whom should I be afraid? => {}'.format('Psalm 27, 1'))
 print('123')
 print()
 s = 'value: {}'.format(123)
diff --git a/tests/functional/n/names_in__all__.py b/tests/functional/n/names_in__all__.py
@@ -1,7 +1,7 @@
 # pylint: disable=too-few-public-methods, import-error, unnecessary-pass
 """Test Pylint's use of __all__.
 
-* NonExistant is not defined in this module, and it is listed in
+* NonExistent is not defined in this module, and it is listed in
   __all__. An error is expected.
 
 * This module imports path and republished it in __all__. No errors
@@ -16,7 +16,7 @@
     '', # [undefined-all-variable]
     Missing,
     SomeUndefined, # [undefined-variable]
-    'NonExistant',  # [undefined-all-variable]
+    'NonExistent',  # [undefined-all-variable]
     'path',
     'func',  # [undefined-all-variable]
     'inner',  # [undefined-all-variable]
diff --git a/tests/functional/n/names_in__all__.txt b/tests/functional/n/names_in__all__.txt
@@ -1,6 +1,6 @@
 undefined-all-variable:16:4:16:6::Undefined variable name '' in __all__:UNDEFINED
 undefined-variable:18:4:18:17::Undefined variable 'SomeUndefined':UNDEFINED
-undefined-all-variable:19:4:19:17::Undefined variable name 'NonExistant' in __all__:UNDEFINED
+undefined-all-variable:19:4:19:17::Undefined variable name 'NonExistent' in __all__:UNDEFINED
 undefined-all-variable:21:4:21:10::Undefined variable name 'func' in __all__:UNDEFINED
 undefined-all-variable:22:4:22:11::Undefined variable name 'inner' in __all__:UNDEFINED
 undefined-all-variable:23:4:23:16::Undefined variable name 'InnerKlass' in __all__:UNDEFINED
diff --git a/tests/functional/n/no/no_name_in_module.py b/tests/functional/n/no/no_name_in_module.py
@@ -7,8 +7,8 @@
 toto.yo()
 
 from xml.etree import ElementTree
-ElementTree.nonexistant_function()  # [no-member]
-ElementTree.another.nonexistant.function()  # [no-member]
+ElementTree.nonexistent_function()  # [no-member]
+ElementTree.another.nonexistent.function()  # [no-member]
 
 
 import sys
diff --git a/tests/functional/n/no/no_name_in_module.txt b/tests/functional/n/no/no_name_in_module.txt
diff --git a/tests/functional/n/non/non_init_parent_called.py b/tests/functional/n/non/non_init_parent_called.py
diff --git a/tests/functional/n/non/non_init_parent_called.txt b/tests/functional/n/non/non_init_parent_called.txt
diff --git a/tests/functional/n/non_ascii_name/non_ascii_name_assignment_expressions.py b/tests/functional/n/non_ascii_name/non_ascii_name_assignment_expressions.py
diff --git a/tests/functional/n/non_ascii_name_class/non_ascii_name_class.py b/tests/functional/n/non_ascii_name_class/non_ascii_name_class.py
diff --git a/tests/functional/n/not_async_context_manager_py37.py b/tests/functional/n/not_async_context_manager_py37.py
diff --git a/tests/functional/u/uninferable_all_object.py b/tests/functional/u/uninferable_all_object.py
diff --git a/tests/functional/u/use/use_implicit_booleaness_not_comparison_to_string.txt b/tests/functional/u/use/use_implicit_booleaness_not_comparison_to_string.txt
diff --git a/tests/lint/unittest_lint.py b/tests/lint/unittest_lint.py
diff --git a/tests/test_self.py b/tests/test_self.py
diff --git a/tests/test_similar.py b/tests/test_similar.py
