.github/workflows/main.yml

@@ -1,19 +0,0 @@
-name: main
-
-on:
-  push:
-    branches: [main, test-me-*]
-    tags: '*'
-  pull_request:
-
-jobs:
-  main-windows:
-    uses: asottile/workflows/.github/workflows/tox.yml@v1.8.1
-    with:
-      env: '["py310"]'
-      os: windows-latest
-  main-linux:
-    uses: asottile/workflows/.github/workflows/tox.yml@v1.8.1
-    with:
-      env: '["py310", "py311", "py312", "py313"]'
-      os: ubuntu-latest

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v6.0.0
+    rev: v4.3.0
     hooks:
     -   id: trailing-whitespace
     -   id: end-of-file-fixer
@@ -10,32 +10,34 @@ repos:
     -   id: name-tests-test
     -   id: requirements-txt-fixer
 -   repo: https://github.com/asottile/setup-cfg-fmt
-    rev: v3.2.0
+    rev: v1.20.1
     hooks:
     -   id: setup-cfg-fmt
--   repo: https://github.com/asottile/reorder-python-imports
-    rev: v3.16.0
+-   repo: https://github.com/asottile/reorder_python_imports
+    rev: v3.1.0
     hooks:
     -   id: reorder-python-imports
-        args: [--py310-plus, --add-import, 'from __future__ import annotations']
+        args: [--py37-plus, --add-import, 'from __future__ import annotations']
 -   repo: https://github.com/asottile/add-trailing-comma
-    rev: v4.0.0
+    rev: v2.2.3
     hooks:
     -   id: add-trailing-comma
+        args: [--py36-plus]
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v3.21.2
+    rev: v2.32.1
     hooks:
     -   id: pyupgrade
-        args: [--py310-plus]
--   repo: https://github.com/hhatto/autopep8
-    rev: v2.3.2
+        args: [--py37-plus]
+-   repo: https://github.com/pre-commit/mirrors-autopep8
+    rev: v1.6.0
     hooks:
     -   id: autopep8
 -   repo: https://github.com/PyCQA/flake8
-    rev: 7.3.0
+    rev: 4.0.1
     hooks:
     -   id: flake8
 -   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.19.1
+    rev: v0.960
     hooks:
     -   id: mypy
+        additional_dependencies: [types-all]

.pre-commit-hooks.yaml

@@ -3,8 +3,7 @@
     description: prevents giant files from being committed.
     entry: check-added-large-files
     language: python
-    stages: [pre-commit, pre-push, manual]
-    minimum_pre_commit_version: 3.2.0
+    stages: [commit, push, manual]
 -   id: check-ast
     name: check python ast
     description: simply checks whether the files parse as valid python.
@@ -12,9 +11,9 @@
     language: python
     types: [python]
 -   id: check-byte-order-marker
-    name: check-byte-order-marker (removed)
-    description: (removed) use fix-byte-order-marker instead.
-    entry: pre-commit-hooks-removed check-byte-order-marker fix-byte-order-marker https://github.com/pre-commit/pre-commit-hooks
+    name: 'check BOM - deprecated: use fix-byte-order-marker'
+    description: forbids files which have a utf-8 byte-order marker.
+    entry: check-byte-order-marker
     language: python
     types: [text]
 -   id: check-builtin-literals
@@ -29,7 +28,7 @@
     entry: check-case-conflict
     language: python
 -   id: check-docstring-first
-    name: check docstring is first (deprecated)
+    name: check docstring is first
     description: checks a common error of defining a docstring after code.
     entry: check-docstring-first
     language: python
@@ -40,13 +39,7 @@
     entry: check-executables-have-shebangs
     language: python
     types: [text, executable]
-    stages: [pre-commit, pre-push, manual]
-    minimum_pre_commit_version: 3.2.0
--   id: check-illegal-windows-names
-    name: check illegal windows names
-    entry: Illegal Windows filenames detected
-    language: fail
-    files: '(?i)((^|/)(CON|PRN|AUX|NUL|COM[\d¹²³]|LPT[\d¹²³])(\.|/|$)|[<>:\"\\|?*\x00-\x1F]|/[^/]*[\.\s]/|[^/]*[\.\s]$)'
+    stages: [commit, push, manual]
 -   id: check-json
     name: check json
     description: checks json files for parseable syntax.
@@ -59,8 +52,7 @@
     entry: check-shebang-scripts-are-executable
     language: python
     types: [text]
-    stages: [pre-commit, pre-push, manual]
-    minimum_pre_commit_version: 3.2.0
+    stages: [commit, push, manual]
 -   id: pretty-format-json
     name: pretty format json
     description: sets a standard for formatting json files.
@@ -115,7 +107,6 @@
     entry: destroyed-symlinks
     language: python
     types: [file]
-    stages: [pre-commit, pre-push, manual]
 -   id: detect-aws-credentials
     name: detect aws credentials
     description: detects *your* aws credentials from the aws cli credentials file.
@@ -140,8 +131,7 @@
     entry: end-of-file-fixer
     language: python
     types: [text]
-    stages: [pre-commit, pre-push, manual]
-    minimum_pre_commit_version: 3.2.0
+    stages: [commit, push, manual]
 -   id: file-contents-sorter
     name: file contents sorter
     description: sorts the lines in specified files (defaults to alphabetical). you must provide list of target files as input in your .pre-commit-config.yaml file.
@@ -155,10 +145,10 @@
     language: python
     types: [text]
 -   id: fix-encoding-pragma
-    name: fix python encoding pragma (removed)
-    description: (removed) use pyupgrade instead.
-    entry: pre-commit-hooks-removed fix-encoding-pragma pyupgrade https://github.com/asottile/pyupgrade
+    name: fix python encoding pragma
+    description: 'adds # -*- coding: utf-8 -*- to the top of python files.'
     language: python
+    entry: fix-encoding-pragma
     types: [python]
 -   id: forbid-new-submodules
     name: forbid new submodules
@@ -166,12 +156,6 @@
     language: python
     entry: forbid-new-submodules
     types: [directory]
--   id: forbid-submodules
-    name: forbid submodules
-    description: forbids any submodules in the repository
-    language: fail
-    entry: 'submodules are not allowed in this repository:'
-    types: [directory]
 -   id: mixed-line-ending
     name: mixed line ending
     description: replaces or checks mixed line ending.
@@ -195,7 +179,7 @@
     description: sorts entries in requirements.txt.
     entry: requirements-txt-fixer
     language: python
-    files: (requirements|constraints).*\.txt$
+    files: requirements.*\.txt$
 -   id: sort-simple-yaml
     name: sort simple yaml files
     description: sorts simple yaml files which consist only of top-level keys, preserving comments and blocks.
@@ -208,5 +192,4 @@
     entry: trailing-whitespace-fixer
     language: python
     types: [text]
-    stages: [pre-commit, pre-push, manual]
-    minimum_pre_commit_version: 3.2.0
+    stages: [commit, push, manual]

CHANGELOG.md

@@ -1,94 +1,3 @@
-6.0.0 - 2025-08-09
-==================
-
-## Fixes
-- `check-shebang-scripts-are-executable`: improve error message.
-    - #1115 PR by @homebysix.
-
-## Migrating
-- now requires python >= 3.9.
-    - #1098 PR by @asottile.
-- `file-contents-sorter`: disallow `--unique` and `--ignore-case` at the same
-  time.
-    - #1095 PR by @nemacysts.
-    - #794 issue by @teksturi.
-- Removed `check-byte-order-marker` and `fix-encoding-pragma`.
-    - `check-byte-order-marker`: migrate to `fix-byte-order-marker`.
-    - `fix-encoding-pragma`: migrate to `pyupgrade`.
-    - #1034 PR by @mxr.
-    - #1032 issue by @mxr.
-    - #522 PR by @jgowdy.
-
-5.0.0 - 2024-10-05
-==================
-
-### Features
-- `requirements-txt-fixer`: also remove `pkg_resources==...`.
-    - #850 PR by @ericfrederich.
-    - #1030 issue by @ericfrederich.
-- `check-illegal-windows-names`: new hook!
-    - #1044 PR by @ericfrederich.
-    - #589 issue by @ericfrederich.
-    - #1049 PR by @Jeffrey-Lim.
-- `pretty-format-json`: continue processing even if a file has a json error.
-    - #1039 PR by @amarvin.
-    - #1038 issue by @amarvin.
-
-### Fixes
-- `destroyed-symlinks`: set `stages` to `[pre-commit, pre-push, manual]`
-    - PR #1085 by @AdrianDC.
-
-### Migrating
-- pre-commit-hooks now requires `pre-commit>=3.2.0`.
-- use non-deprecated names for `stages`.
-    - #1093 PR by @asottile.
-
-4.6.0 - 2024-04-06
-==================
-
-### Features
-- `requirements-txt-fixer`: remove duplicate packages.
-    - #1014 PR by @vhoulbreque-withings.
-    - #960 issue @csibe17.
-
-### Migrating
-- `fix-encoding-pragma`: deprecated -- will be removed in 5.0.0.  use
-  [pyupgrade](https://github.com/asottile/pyupgrade) or some other tool.
-    - #1033 PR by @mxr.
-    - #1032 issue by @mxr.
-
-4.5.0 - 2023-10-07
-==================
-
-### Features
-- `requirements-txt-fixer`: also sort `constraints.txt` by default.
-    - #857 PR by @lev-blit.
-    - #830 issue by @PLPeeters.
-- `debug-statements`: add `bpdb` debugger.
-    - #942 PR by @mwip.
-    - #941 issue by @mwip.
-
-### Fixes
-- `file-contents-sorter`: fix sorting an empty file.
-    - #944 PR by @RoelAdriaans.
-    - #935 issue by @paduszyk.
-- `double-quote-string-fixer`: don't rewrite inside f-strings in 3.12+.
-    - #973 PR by @asottile.
-    - #971 issue by @XuehaiPan.
-
-## Migrating
-- now requires python >= 3.8.
-    - #926 PR by @asottile.
-    - #927 PR by @asottile.
-
-4.4.0 - 2022-11-23
-==================
-
-### Features
-- `forbid-submodules`: new hook which outright bans submodules.
-    - #815 PR by @asottile.
-    - #707 issue by @ChiefGokhlayeh.
-
 4.3.0 - 2022-06-07
 ==================
 

README.md

@@ -1,4 +1,5 @@
-[![build status](https://github.com/pre-commit/pre-commit-hooks/actions/workflows/main.yml/badge.svg)](https://github.com/pre-commit/pre-commit-hooks/actions/workflows/main.yml)
+[![Build Status](https://asottile.visualstudio.com/asottile/_apis/build/status/pre-commit.pre-commit-hooks?branchName=main)](https://asottile.visualstudio.com/asottile/_build/latest?definitionId=17&branchName=main)
+[![Azure DevOps coverage](https://img.shields.io/azure-devops/coverage/asottile/asottile/17/main.svg)](https://dev.azure.com/asottile/asottile/_build/latest?definitionId=17&branchName=main)
 [![pre-commit.ci status](https://results.pre-commit.ci/badge/github/pre-commit/pre-commit-hooks/main.svg)](https://results.pre-commit.ci/latest/github/pre-commit/pre-commit-hooks/main)
 
 pre-commit-hooks
@@ -15,7 +16,7 @@ Add this to your `.pre-commit-config.yaml`
 
 ```yaml
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v6.0.0  # Use the ref you want to point at
+    rev: v4.3.0  # Use the ref you want to point at
     hooks:
     -   id: trailing-whitespace
     # -   id: ...
@@ -45,12 +46,12 @@ Require literal syntax when initializing empty or zero Python builtin types.
 #### `check-case-conflict`
 Check for files with names that would conflict on a case-insensitive filesystem like MacOS HFS+ or Windows FAT.
 
+#### `check-docstring-first`
+Checks for a common error of placing code before the docstring.
+
 #### `check-executables-have-shebangs`
 Checks that non-binary executables have a proper shebang.
 
-#### `check-illegal-windows-names`
-Check for files that cannot be created on Windows.
-
 #### `check-json`
 Attempts to load all json files to verify syntax.
 
@@ -113,28 +114,25 @@ This hook replaces double quoted strings with single quoted strings.
 #### `end-of-file-fixer`
 Makes sure files end in a newline and only a newline.
 
+#### `fix-byte-order-marker`
+removes UTF-8 byte order marker
+
+#### `fix-encoding-pragma`
+Add `# -*- coding: utf-8 -*-` to the top of python files.
+  - To remove the coding pragma pass `--remove` (useful in a python3-only codebase)
+
 #### `file-contents-sorter`
 Sort the lines in specified files (defaults to alphabetical).
-You must provide the target [`files`](https://pre-commit.com/#config-files) as input.
+You must provide list of target files as input to it.
 Note that this hook WILL remove blank lines and does NOT respect any comments.
-All newlines will be converted to line feeds (`\n`).
 
 The following arguments are available:
 - `--ignore-case` - fold lower case to upper case characters.
 - `--unique` - ensure each line is unique.
 
-#### `fix-byte-order-marker`
-removes UTF-8 byte order marker
-
 #### `forbid-new-submodules`
 Prevent addition of new git submodules.
 
-This is intended as a helper to migrate away from submodules.  If you want to
-ban them entirely use `forbid-submodules`
-
-#### `forbid-submodules`
-forbids any submodules in the repository.
-
 #### `mixed-line-ending`
 Replaces or checks mixed line ending.
   - `--fix={auto,crlf,lf,no}`
@@ -176,7 +174,7 @@ the following commandline options:
   - `--top-keys comma,separated,keys` - Keys to keep at the top of mappings.
 
 #### `requirements-txt-fixer`
-Sorts entries in requirements.txt and constraints.txt and removes incorrect entry for `pkg-resources==0.0.0`
+Sorts entries in requirements.txt and removes incorrect entry for `pkg-resources==0.0.0`
 
 #### `sort-simple-yaml`
 Sorts simple YAML files which consist only of top-level
@@ -203,9 +201,6 @@ Trims trailing whitespace.
 ### Deprecated / replaced hooks
 
 - `check-byte-order-marker`: instead use fix-byte-order-marker
-- `fix-encoding-pragma`: instead use [`pyupgrade`](https://github.com/asottile/pyupgrade)
-- `check-docstring-first`: fundamentally flawed, deprecated without replacement.
-
 
 ### As a standalone package
 

azure-pipelines.yml

@@ -0,0 +1,23 @@
+trigger:
+  branches:
+    include: [main, test-me-*]
+  tags:
+    include: ['*']
+
+resources:
+  repositories:
+    - repository: asottile
+      type: github
+      endpoint: github
+      name: asottile/azure-pipeline-templates
+      ref: refs/tags/v2.4.0
+
+jobs:
+- template: job--python-tox.yml@asottile
+  parameters:
+    toxenvs: [py38]
+    os: windows
+- template: job--python-tox.yml@asottile
+  parameters:
+    toxenvs: [py37, py38, py39, py310]
+    os: linux

pre_commit_hooks/check_added_large_files.py

@@ -4,7 +4,7 @@ import argparse
 import math
 import os
 import subprocess
-from collections.abc import Sequence
+from typing import Sequence
 
 from pre_commit_hooks.util import added_files
 from pre_commit_hooks.util import zsplit
@@ -46,7 +46,7 @@ def find_large_added_files(
         filenames_filtered &= added_files()
 
     for filename in filenames_filtered:
-        kb = math.ceil(os.stat(filename).st_size / 1024)
+        kb = int(math.ceil(os.stat(filename).st_size / 1024))
         if kb > maxkb:
             print(f'{filename} ({kb} KB) exceeds {maxkb} KB.')
             retv = 1

pre_commit_hooks/check_ast.py

@@ -5,7 +5,7 @@ import ast
 import platform
 import sys
 import traceback
-from collections.abc import Sequence
+from typing import Sequence
 
 
 def main(argv: Sequence[str] | None = None) -> int:

pre_commit_hooks/check_builtin_literals.py

@@ -2,8 +2,8 @@ from __future__ import annotations
 
 import argparse
 import ast
-from collections.abc import Sequence
 from typing import NamedTuple
+from typing import Sequence
 
 
 BUILTIN_TYPES = {
@@ -26,37 +26,36 @@ class Call(NamedTuple):
 class Visitor(ast.NodeVisitor):
     def __init__(
             self,
-            ignore: set[str],
+            ignore: Sequence[str] | None = None,
             allow_dict_kwargs: bool = True,
     ) -> None:
         self.builtin_type_calls: list[Call] = []
+        self.ignore = set(ignore) if ignore else set()
         self.allow_dict_kwargs = allow_dict_kwargs
-        self._disallowed = BUILTIN_TYPES.keys() - ignore
 
     def _check_dict_call(self, node: ast.Call) -> bool:
         return self.allow_dict_kwargs and bool(node.keywords)
 
     def visit_Call(self, node: ast.Call) -> None:
-        if (
+        if not isinstance(node.func, ast.Name):
             # Ignore functions that are object attributes (`foo.bar()`).
             # Assume that if the user calls `builtins.list()`, they know what
             # they're doing.
-            isinstance(node.func, ast.Name) and
-            node.func.id in self._disallowed and
-            (node.func.id != 'dict' or not self._check_dict_call(node)) and
-            not node.args
-        ):
-            self.builtin_type_calls.append(
-                Call(node.func.id, node.lineno, node.col_offset),
-            )
-
-        self.generic_visit(node)
+            return
+        if node.func.id not in set(BUILTIN_TYPES).difference(self.ignore):
+            return
+        if node.func.id == 'dict' and self._check_dict_call(node):
+            return
+        elif node.args:
+            return
+        self.builtin_type_calls.append(
+            Call(node.func.id, node.lineno, node.col_offset),
+        )
 
 
 def check_file(
         filename: str,
-        *,
-        ignore: set[str],
+        ignore: Sequence[str] | None = None,
         allow_dict_kwargs: bool = True,
 ) -> list[Call]:
     with open(filename, 'rb') as f:

pre_commit_hooks/check_byte_order_marker.py

@@ -0,0 +1,24 @@
+from __future__ import annotations
+
+import argparse
+from typing import Sequence
+
+
+def main(argv: Sequence[str] | None = None) -> int:
+    parser = argparse.ArgumentParser()
+    parser.add_argument('filenames', nargs='*', help='Filenames to check')
+    args = parser.parse_args(argv)
+
+    retv = 0
+
+    for filename in args.filenames:
+        with open(filename, 'rb') as f:
+            if f.read(3) == b'\xef\xbb\xbf':
+                retv = 1
+                print(f'{filename}: Has a byte-order marker')
+
+    return retv
+
+
+if __name__ == '__main__':
+    raise SystemExit(main())

pre_commit_hooks/check_case_conflict.py

@@ -1,9 +1,9 @@
 from __future__ import annotations
 
 import argparse
-from collections.abc import Iterable
-from collections.abc import Iterator
-from collections.abc import Sequence
+from typing import Iterable
+from typing import Iterator
+from typing import Sequence
 
 from pre_commit_hooks.util import added_files
 from pre_commit_hooks.util import cmd_output

pre_commit_hooks/check_docstring_first.py

@@ -3,8 +3,8 @@ from __future__ import annotations
 import argparse
 import io
 import tokenize
-from collections.abc import Sequence
 from tokenize import tokenize as tokenize_tokenize
+from typing import Sequence
 
 NON_CODE_TOKENS = frozenset((
     tokenize.COMMENT, tokenize.ENDMARKER, tokenize.NEWLINE, tokenize.NL,

pre_commit_hooks/check_executables_have_shebangs.py

@@ -4,9 +4,9 @@ from __future__ import annotations
 import argparse
 import shlex
 import sys
-from collections.abc import Generator
-from collections.abc import Sequence
+from typing import Generator
 from typing import NamedTuple
+from typing import Sequence
 
 from pre_commit_hooks.util import cmd_output
 from pre_commit_hooks.util import zsplit
@@ -35,7 +35,7 @@ class GitLsFile(NamedTuple):
     filename: str
 
 
-def git_ls_files(paths: Sequence[str]) -> Generator[GitLsFile]:
+def git_ls_files(paths: Sequence[str]) -> Generator[GitLsFile, None, None]:
     outs = cmd_output('git', 'ls-files', '-z', '--stage', '--', *paths)
     for out in zsplit(outs):
         metadata, filename = out.split('\t')

pre_commit_hooks/check_json.py

@@ -2,8 +2,8 @@ from __future__ import annotations
 
 import argparse
 import json
-from collections.abc import Sequence
 from typing import Any
+from typing import Sequence
 
 
 def raise_duplicate_keys(

pre_commit_hooks/check_merge_conflict.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import argparse
 import os.path
-from collections.abc import Sequence
+from typing import Sequence
 
 from pre_commit_hooks.util import cmd_output
 

pre_commit_hooks/check_shebang_scripts_are_executable.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 import argparse
 import shlex
 import sys
-from collections.abc import Sequence
+from typing import Sequence
 
 from pre_commit_hooks.check_executables_have_shebangs import EXECUTABLE_VALUES
 from pre_commit_hooks.check_executables_have_shebangs import git_ls_files
@@ -36,7 +36,7 @@ def _message(path: str) -> None:
         f'`chmod +x {shlex.quote(path)}`\n'
         f'  If on Windows, you may also need to: '
         f'`git add --chmod=+x {shlex.quote(path)}`\n'
-        f'  If it is not supposed to be executable, double-check its shebang '
+        f'  If it not supposed to be executable, double-check its shebang '
         f'is wanted.\n',
         file=sys.stderr,
     )

pre_commit_hooks/check_symlinks.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import argparse
 import os.path
-from collections.abc import Sequence
+from typing import Sequence
 
 
 def main(argv: Sequence[str] | None = None) -> int:

pre_commit_hooks/check_toml.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import argparse
 import sys
-from collections.abc import Sequence
+from typing import Sequence
 
 if sys.version_info >= (3, 11):  # pragma: >=3.11 cover
     import tomllib

pre_commit_hooks/check_vcs_permalinks.py

@@ -3,8 +3,8 @@ from __future__ import annotations
 import argparse
 import re
 import sys
-from collections.abc import Sequence
-from re import Pattern
+from typing import Pattern
+from typing import Sequence
 
 
 def _get_pattern(domain: str) -> Pattern[bytes]:

pre_commit_hooks/check_xml.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import argparse
 import xml.sax.handler
-from collections.abc import Sequence
+from typing import Sequence
 
 
 def main(argv: Sequence[str] | None = None) -> int:

pre_commit_hooks/check_yaml.py

@@ -1,17 +1,17 @@
 from __future__ import annotations
 
 import argparse
-from collections.abc import Generator
-from collections.abc import Sequence
 from typing import Any
+from typing import Generator
 from typing import NamedTuple
+from typing import Sequence
 
 import ruamel.yaml
 
 yaml = ruamel.yaml.YAML(typ='safe')
 
 
-def _exhaust(gen: Generator[str]) -> None:
+def _exhaust(gen: Generator[str, None, None]) -> None:
     for _ in gen:
         pass
 
@@ -46,7 +46,7 @@ def main(argv: Sequence[str] | None = None) -> int:
         '--unsafe', action='store_true',
         help=(
             'Instead of loading the files, simply parse them for syntax.  '
-            'A syntax-only check enables extensions and unsafe constructs '
+            'A syntax-only check enables extensions and unsafe contstructs '
             'which would otherwise be forbidden.  Using this option removes '
             'all guarantees of portability to other yaml implementations.  '
             'Implies --allow-multiple-documents'

pre_commit_hooks/debug_statement_hook.py

@@ -3,12 +3,11 @@ from __future__ import annotations
 import argparse
 import ast
 import traceback
-from collections.abc import Sequence
 from typing import NamedTuple
+from typing import Sequence
 
 
 DEBUG_STATEMENTS = {
-    'bpdb',
     'ipdb',
     'pdb',
     'pdbr',

pre_commit_hooks/destroyed_symlinks.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 import argparse
 import shlex
 import subprocess
-from collections.abc import Sequence
+from typing import Sequence
 
 from pre_commit_hooks.util import cmd_output
 from pre_commit_hooks.util import zsplit
@@ -76,7 +76,11 @@ def main(argv: Sequence[str] | None = None) -> int:
         for destroyed_link in destroyed_links:
             print(f'- {destroyed_link}')
         print('You should unstage affected files:')
-        print(f'\tgit reset HEAD -- {shlex.join(destroyed_links)}')
+        print(
+            '\tgit reset HEAD -- {}'.format(
+                ' '.join(shlex.quote(link) for link in destroyed_links),
+            ),
+        )
         print(
             'And retry commit. As a long term solution '
             'you may try to explicitly tell git that your '

pre_commit_hooks/detect_aws_credentials.py

@@ -3,8 +3,8 @@ from __future__ import annotations
 import argparse
 import configparser
 import os
-from collections.abc import Sequence
 from typing import NamedTuple
+from typing import Sequence
 
 
 class BadFile(NamedTuple):

pre_commit_hooks/detect_private_key.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import argparse
-from collections.abc import Sequence
+from typing import Sequence
 
 BLACKLIST = [
     b'BEGIN RSA PRIVATE KEY',

pre_commit_hooks/end_of_file_fixer.py

@@ -2,8 +2,8 @@ from __future__ import annotations
 
 import argparse
 import os
-from collections.abc import Sequence
 from typing import IO
+from typing import Sequence
 
 
 def fix_file(file_obj: IO[bytes]) -> int:

pre_commit_hooks/file_contents_sorter.py

@@ -12,11 +12,11 @@ conflicts and keep the file nicely ordered.
 from __future__ import annotations
 
 import argparse
-from collections.abc import Callable
-from collections.abc import Iterable
-from collections.abc import Sequence
 from typing import Any
+from typing import Callable
 from typing import IO
+from typing import Iterable
+from typing import Sequence
 
 PASS = 0
 FAIL = 1
@@ -37,10 +37,7 @@ def sort_file_contents(
     after = sorted(lines, key=key)
 
     before_string = b''.join(before)
-    after_string = b'\n'.join(after)
-
-    if after_string:
-        after_string += b'\n'
+    after_string = b'\n'.join(after) + b'\n'
 
     if before_string == after_string:
         return PASS
@@ -54,21 +51,18 @@ def sort_file_contents(
 def main(argv: Sequence[str] | None = None) -> int:
     parser = argparse.ArgumentParser()
     parser.add_argument('filenames', nargs='+', help='Files to sort')
-
-    mutex = parser.add_mutually_exclusive_group(required=False)
-    mutex.add_argument(
+    parser.add_argument(
         '--ignore-case',
         action='store_const',
         const=bytes.lower,
         default=None,
         help='fold lower case to upper case characters',
     )
-    mutex.add_argument(
+    parser.add_argument(
         '--unique',
         action='store_true',
         help='ensure each line is unique',
     )
-
     args = parser.parse_args(argv)
 
     retv = PASS

pre_commit_hooks/fix_byte_order_marker.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import argparse
-from collections.abc import Sequence
+from typing import Sequence
 
 
 def main(argv: Sequence[str] | None = None) -> int:

pre_commit_hooks/fix_encoding_pragma.py

@@ -0,0 +1,149 @@
+from __future__ import annotations
+
+import argparse
+from typing import IO
+from typing import NamedTuple
+from typing import Sequence
+
+DEFAULT_PRAGMA = b'# -*- coding: utf-8 -*-'
+
+
+def has_coding(line: bytes) -> bool:
+    if not line.strip():
+        return False
+    return (
+        line.lstrip()[:1] == b'#' and (
+            b'unicode' in line or
+            b'encoding' in line or
+            b'coding:' in line or
+            b'coding=' in line
+        )
+    )
+
+
+class ExpectedContents(NamedTuple):
+    shebang: bytes
+    rest: bytes
+    # True: has exactly the coding pragma expected
+    # False: missing coding pragma entirely
+    # None: has a coding pragma, but it does not match
+    pragma_status: bool | None
+    ending: bytes
+
+    @property
+    def has_any_pragma(self) -> bool:
+        return self.pragma_status is not False
+
+    def is_expected_pragma(self, remove: bool) -> bool:
+        expected_pragma_status = not remove
+        return self.pragma_status is expected_pragma_status
+
+
+def _get_expected_contents(
+        first_line: bytes,
+        second_line: bytes,
+        rest: bytes,
+        expected_pragma: bytes,
+) -> ExpectedContents:
+    ending = b'\r\n' if first_line.endswith(b'\r\n') else b'\n'
+
+    if first_line.startswith(b'#!'):
+        shebang = first_line
+        potential_coding = second_line
+    else:
+        shebang = b''
+        potential_coding = first_line
+        rest = second_line + rest
+
+    if potential_coding.rstrip(b'\r\n') == expected_pragma:
+        pragma_status: bool | None = True
+    elif has_coding(potential_coding):
+        pragma_status = None
+    else:
+        pragma_status = False
+        rest = potential_coding + rest
+
+    return ExpectedContents(
+        shebang=shebang, rest=rest, pragma_status=pragma_status, ending=ending,
+    )
+
+
+def fix_encoding_pragma(
+        f: IO[bytes],
+        remove: bool = False,
+        expected_pragma: bytes = DEFAULT_PRAGMA,
+) -> int:
+    expected = _get_expected_contents(
+        f.readline(), f.readline(), f.read(), expected_pragma,
+    )
+
+    # Special cases for empty files
+    if not expected.rest.strip():
+        # If a file only has a shebang or a coding pragma, remove it
+        if expected.has_any_pragma or expected.shebang:
+            f.seek(0)
+            f.truncate()
+            f.write(b'')
+            return 1
+        else:
+            return 0
+
+    if expected.is_expected_pragma(remove):
+        return 0
+
+    # Otherwise, write out the new file
+    f.seek(0)
+    f.truncate()
+    f.write(expected.shebang)
+    if not remove:
+        f.write(expected_pragma + expected.ending)
+    f.write(expected.rest)
+
+    return 1
+
+
+def _normalize_pragma(pragma: str) -> bytes:
+    return pragma.encode().rstrip()
+
+
+def main(argv: Sequence[str] | None = None) -> int:
+    parser = argparse.ArgumentParser(
+        'Fixes the encoding pragma of python files',
+    )
+    parser.add_argument('filenames', nargs='*', help='Filenames to fix')
+    parser.add_argument(
+        '--pragma', default=DEFAULT_PRAGMA, type=_normalize_pragma,
+        help=(
+            f'The encoding pragma to use.  '
+            f'Default: {DEFAULT_PRAGMA.decode()}'
+        ),
+    )
+    parser.add_argument(
+        '--remove', action='store_true',
+        help='Remove the encoding pragma (Useful in a python3-only codebase)',
+    )
+    args = parser.parse_args(argv)
+
+    retv = 0
+
+    if args.remove:
+        fmt = 'Removed encoding pragma from {filename}'
+    else:
+        fmt = 'Added `{pragma}` to {filename}'
+
+    for filename in args.filenames:
+        with open(filename, 'r+b') as f:
+            file_ret = fix_encoding_pragma(
+                f, remove=args.remove, expected_pragma=args.pragma,
+            )
+            retv |= file_ret
+            if file_ret:
+                print(
+                    fmt.format(pragma=args.pragma.decode(), filename=filename),
+                )
+
+    return retv
+
+
+if __name__ == '__main__':
+    raise SystemExit(main())

pre_commit_hooks/forbid_new_submodules.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import argparse
 import os
-from collections.abc import Sequence
+from typing import Sequence
 
 from pre_commit_hooks.util import cmd_output
 

pre_commit_hooks/mixed_line_ending.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import argparse
 import collections
-from collections.abc import Sequence
+from typing import Sequence
 
 
 CRLF = b'\r\n'

pre_commit_hooks/no_commit_to_branch.py

@@ -2,8 +2,8 @@ from __future__ import annotations
 
 import argparse
 import re
-from collections.abc import Sequence
 from typing import AbstractSet
+from typing import Sequence
 
 from pre_commit_hooks.util import CalledProcessError
 from pre_commit_hooks.util import cmd_output

pre_commit_hooks/pretty_format_json.py

@@ -3,9 +3,9 @@ from __future__ import annotations
 import argparse
 import json
 import sys
-from collections.abc import Mapping
-from collections.abc import Sequence
 from difflib import unified_diff
+from typing import Mapping
+from typing import Sequence
 
 
 def _get_pretty_format(
@@ -115,20 +115,16 @@ def main(argv: Sequence[str] | None = None) -> int:
                 f'Input File {json_file} is not a valid JSON, consider using '
                 f'check-json',
             )
-            status = 1
-        else:
-            if contents != pretty_contents:
-                if args.autofix:
-                    _autofix(json_file, pretty_contents)
-                else:
-                    diff_output = get_diff(
-                        contents,
-                        pretty_contents,
-                        json_file,
-                    )
-                    sys.stdout.buffer.write(diff_output.encode())
+            return 1
 
-                status = 1
+        if contents != pretty_contents:
+            if args.autofix:
+                _autofix(json_file, pretty_contents)
+            else:
+                diff_output = get_diff(contents, pretty_contents, json_file)
+                sys.stdout.buffer.write(diff_output.encode())
+
+            status = 1
 
     return status
 

pre_commit_hooks/removed.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import sys
-from collections.abc import Sequence
+from typing import Sequence
 
 
 def main(argv: Sequence[str] | None = None) -> int:

pre_commit_hooks/requirements_txt_fixer.py

@@ -2,8 +2,8 @@ from __future__ import annotations
 
 import argparse
 import re
-from collections.abc import Sequence
 from typing import IO
+from typing import Sequence
 
 
 PASS = 0
@@ -45,11 +45,6 @@ class Requirement:
         elif requirement.value == b'\n':
             return False
         else:
-            # if 2 requirements have the same name, the one with comments
-            # needs to go first (so that when removing duplicates, the one
-            # with comments is kept)
-            if self.name == requirement.name:
-                return bool(self.comments) > bool(requirement.comments)
             return self.name < requirement.name
 
     def is_complete(self) -> bool:
@@ -115,20 +110,13 @@ def fix_requirements(f: IO[bytes]) -> int:
     # which is automatically added by broken pip package under Debian
     requirements = [
         req for req in requirements
-        if req.value not in [
-            b'pkg-resources==0.0.0\n',
-            b'pkg_resources==0.0.0\n',
-        ]
+        if req.value != b'pkg-resources==0.0.0\n'
     ]
 
-    # sort the requirements and remove duplicates
-    prev = None
     for requirement in sorted(requirements):
         after.extend(requirement.comments)
         assert requirement.value, requirement.value
-        if prev is None or requirement.value != prev.value:
-            after.append(requirement.value)
-            prev = requirement
+        after.append(requirement.value)
     after.extend(rest)
 
     after_string = b''.join(after)

pre_commit_hooks/sort_simple_yaml.py

@@ -20,7 +20,7 @@ complicated YAML files.
 from __future__ import annotations
 
 import argparse
-from collections.abc import Sequence
+from typing import Sequence
 
 
 QUOTES = ["'", '"']

pre_commit_hooks/string_fixer.py

@@ -3,15 +3,8 @@ from __future__ import annotations
 import argparse
 import io
 import re
-import sys
 import tokenize
-from collections.abc import Sequence
-
-if sys.version_info >= (3, 12):  # pragma: >=3.12 cover
-    FSTRING_START = tokenize.FSTRING_START
-    FSTRING_END = tokenize.FSTRING_END
-else:  # pragma: <3.12 cover
-    FSTRING_START = FSTRING_END = -1
+from typing import Sequence
 
 START_QUOTE_RE = re.compile('^[a-zA-Z]*"')
 
@@ -47,17 +40,11 @@ def fix_strings(filename: str) -> int:
     # Basically a mutable string
     splitcontents = list(contents)
 
-    fstring_depth = 0
-
     # Iterate in reverse so the offsets are always correct
     tokens_l = list(tokenize.generate_tokens(io.StringIO(contents).readline))
     tokens = reversed(tokens_l)
     for token_type, token_text, (srow, scol), (erow, ecol), _ in tokens:
-        if token_type == FSTRING_START:  # pragma: >=3.12 cover
-            fstring_depth += 1
-        elif token_type == FSTRING_END:  # pragma: >=3.12 cover
-            fstring_depth -= 1
-        elif fstring_depth == 0 and token_type == tokenize.STRING:
+        if token_type == tokenize.STRING:
             new_text = handle_match(token_text)
             splitcontents[
                 line_offsets[srow] + scol:

pre_commit_hooks/tests_should_end_in_test.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 import argparse
 import os.path
 import re
-from collections.abc import Sequence
+from typing import Sequence
 
 
 def main(argv: Sequence[str] | None = None) -> int:

pre_commit_hooks/trailing_whitespace_fixer.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import argparse
 import os
-from collections.abc import Sequence
+from typing import Sequence
 
 
 def _fix_file(

setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = pre_commit_hooks
-version = 6.0.0
+version = 4.3.0
 description = Some out-of-the-box hooks for pre-commit.
 long_description = file: README.md
 long_description_content_type = text/markdown
@@ -8,10 +8,15 @@ url = https://github.com/pre-commit/pre-commit-hooks
 author = Anthony Sottile
 author_email = asottile@umich.edu
 license = MIT
-license_files = LICENSE
+license_file = LICENSE
 classifiers =
+    License :: OSI Approved :: MIT License
     Programming Language :: Python :: 3
     Programming Language :: Python :: 3 :: Only
+    Programming Language :: Python :: 3.7
+    Programming Language :: Python :: 3.8
+    Programming Language :: Python :: 3.9
+    Programming Language :: Python :: 3.10
     Programming Language :: Python :: Implementation :: CPython
     Programming Language :: Python :: Implementation :: PyPy
 
@@ -20,7 +25,7 @@ packages = find:
 install_requires =
     ruamel.yaml>=0.15
     tomli>=1.1.0;python_version<"3.11"
-python_requires = >=3.10
+python_requires = >=3.7
 
 [options.packages.find]
 exclude =
@@ -32,6 +37,7 @@ console_scripts =
     check-added-large-files = pre_commit_hooks.check_added_large_files:main
     check-ast = pre_commit_hooks.check_ast:main
     check-builtin-literals = pre_commit_hooks.check_builtin_literals:main
+    check-byte-order-marker = pre_commit_hooks.check_byte_order_marker:main
     check-case-conflict = pre_commit_hooks.check_case_conflict:main
     check-docstring-first = pre_commit_hooks.check_docstring_first:main
     check-executables-have-shebangs = pre_commit_hooks.check_executables_have_shebangs:main
@@ -51,6 +57,7 @@ console_scripts =
     end-of-file-fixer = pre_commit_hooks.end_of_file_fixer:main
     file-contents-sorter = pre_commit_hooks.file_contents_sorter:main
     fix-byte-order-marker = pre_commit_hooks.fix_byte_order_marker:main
+    fix-encoding-pragma = pre_commit_hooks.fix_encoding_pragma:main
     forbid-new-submodules = pre_commit_hooks.forbid_new_submodules:main
     mixed-line-ending = pre_commit_hooks.mixed_line_ending:main
     name-tests-test = pre_commit_hooks.tests_should_end_in_test:main
@@ -72,6 +79,7 @@ check_untyped_defs = true
 disallow_any_generics = true
 disallow_incomplete_defs = true
 disallow_untyped_defs = true
+no_implicit_optional = true
 warn_redundant_casts = true
 warn_unused_ignores = true
 

tests/check_builtin_literals_test.py

@@ -38,6 +38,11 @@ t1 = ()
 '''
 
 
+@pytest.fixture
+def visitor():
+    return Visitor()
+
+
 @pytest.mark.parametrize(
     ('expression', 'calls'),
     [
@@ -80,8 +85,7 @@ t1 = ()
         ('builtins.tuple()', []),
     ],
 )
-def test_non_dict_exprs(expression, calls):
-    visitor = Visitor(ignore=set())
+def test_non_dict_exprs(visitor, expression, calls):
     visitor.visit(ast.parse(expression))
     assert visitor.builtin_type_calls == calls
 
@@ -98,8 +102,7 @@ def test_non_dict_exprs(expression, calls):
         ('builtins.dict()', []),
     ],
 )
-def test_dict_allow_kwargs_exprs(expression, calls):
-    visitor = Visitor(ignore=set())
+def test_dict_allow_kwargs_exprs(visitor, expression, calls):
     visitor.visit(ast.parse(expression))
     assert visitor.builtin_type_calls == calls
 
@@ -111,18 +114,17 @@ def test_dict_allow_kwargs_exprs(expression, calls):
         ('dict(a=1, b=2, c=3)', [Call('dict', 1, 0)]),
         ("dict(**{'a': 1, 'b': 2, 'c': 3})", [Call('dict', 1, 0)]),
         ('builtins.dict()', []),
-        pytest.param('f(dict())', [Call('dict', 1, 2)], id='nested'),
     ],
 )
 def test_dict_no_allow_kwargs_exprs(expression, calls):
-    visitor = Visitor(ignore=set(), allow_dict_kwargs=False)
+    visitor = Visitor(allow_dict_kwargs=False)
     visitor.visit(ast.parse(expression))
     assert visitor.builtin_type_calls == calls
 
 
 def test_ignore_constructors():
     visitor = Visitor(
-        ignore={'complex', 'dict', 'float', 'int', 'list', 'str', 'tuple'},
+        ignore=('complex', 'dict', 'float', 'int', 'list', 'str', 'tuple'),
     )
     visitor.visit(ast.parse(BUILTIN_CONSTRUCTORS))
     assert visitor.builtin_type_calls == []

tests/check_byte_order_marker_test.py

@@ -0,0 +1,15 @@
+from __future__ import annotations
+
+from pre_commit_hooks import check_byte_order_marker
+
+
+def test_failure(tmpdir):
+    f = tmpdir.join('f.txt')
+    f.write_text('ohai', encoding='utf-8-sig')
+    assert check_byte_order_marker.main((str(f),)) == 1
+
+
+def test_success(tmpdir):
+    f = tmpdir.join('f.txt')
+    f.write_text('ohai', encoding='utf-8')
+    assert check_byte_order_marker.main((str(f),)) == 0

tests/check_illegal_windows_names_test.py

@@ -1,63 +0,0 @@
-from __future__ import annotations
-
-import os.path
-import re
-
-import pytest
-
-from pre_commit_hooks.check_yaml import yaml
-
-
-@pytest.fixture(scope='module')
-def hook_re():
-    here = os.path.dirname(__file__)
-    with open(os.path.join(here, '..', '.pre-commit-hooks.yaml')) as f:
-        hook_defs = yaml.load(f)
-    hook, = (
-        hook
-        for hook in hook_defs
-        if hook['id'] == 'check-illegal-windows-names'
-    )
-    yield re.compile(hook['files'])
-
-
-@pytest.mark.parametrize(
-    's',
-    (
-        pytest.param('aux.txt', id='with ext'),
-        pytest.param('aux', id='without ext'),
-        pytest.param('AuX.tXt', id='capitals'),
-        pytest.param('com7.dat', id='com with digit'),
-        pytest.param(':', id='bare colon'),
-        pytest.param('file:Zone.Identifier', id='mid colon'),
-        pytest.param('path/COM¹.json', id='com with superscript'),
-        pytest.param('dir/LPT³.toml', id='lpt with superscript'),
-        pytest.param('with < less than', id='with less than'),
-        pytest.param('Fast or Slow?.md', id='with question mark'),
-        pytest.param('with "double" quotes', id='with double quotes'),
-        pytest.param('with_null\x00byte', id='with null byte'),
-        pytest.param('ends_with.', id='ends with period'),
-        pytest.param('ends_with ', id='ends with space'),
-        pytest.param('ends_with\t', id='ends with tab'),
-        pytest.param('dir/ends./with.txt', id='directory ends with period'),
-        pytest.param('dir/ends /with.txt', id='directory ends with space'),
-    ),
-)
-def test_check_illegal_windows_names_matches(hook_re, s):
-    assert hook_re.search(s)
-
-
-@pytest.mark.parametrize(
-    's',
-    (
-        pytest.param('README.md', id='standard file'),
-        pytest.param('foo.aux', id='as ext'),
-        pytest.param('com.dat', id='com without digit'),
-        pytest.param('.python-version', id='starts with period'),
-        pytest.param(' pseudo nan', id='with spaces'),
-        pytest.param('!@#$%^&;=≤\'~`¡¿€🤗', id='with allowed characters'),
-        pytest.param('path.to/file.py', id='standard path'),
-    ),
-)
-def test_check_illegal_windows_names_does_not_match(hook_re, s):
-    assert hook_re.search(s) is None

tests/check_merge_conflict_test.py

@@ -27,10 +27,10 @@ def f1_is_a_conflict_file(tmpdir):
 
     cmd_output('git', 'clone', str(repo1), str(repo2))
 
-    # Commit in mainline
+    # Commit in master
     with repo1.as_cwd():
         repo1_f1.write('parent\n')
-        git_commit('-am', 'mainline commit2')
+        git_commit('-am', 'master commit2')
 
     # Commit in clone and pull
     with repo2.as_cwd():
@@ -82,10 +82,10 @@ def repository_pending_merge(tmpdir):
 
     cmd_output('git', 'clone', str(repo1), str(repo2))
 
-    # Commit in mainline
+    # Commit in master
     with repo1.as_cwd():
         repo1_f1.write('parent\n')
-        git_commit('-am', 'mainline commit2')
+        git_commit('-am', 'master commit2')
 
     # Commit in clone and pull without committing
     with repo2.as_cwd():
@@ -112,7 +112,7 @@ def test_merge_conflicts_git(capsys):
 
 
 @pytest.mark.parametrize(
-    'contents', (b'<<<<<<< HEAD\n', b'=======\n', b'>>>>>>> main\n'),
+    'contents', (b'<<<<<<< HEAD\n', b'=======\n', b'>>>>>>> master\n'),
 )
 def test_merge_conflicts_failing(contents, repository_pending_merge):
     repository_pending_merge.join('f2').write_binary(contents)
@@ -150,7 +150,7 @@ def test_worktree_merge_conflicts(f1_is_a_conflict_file, tmpdir, capsys):
     cmd_output('git', 'worktree', 'add', str(worktree))
     with worktree.as_cwd():
         cmd_output(
-            'git', 'pull', '--no-rebase', 'origin', 'HEAD', retcode=None,
+            'git', 'pull', '--no-rebase', 'origin', 'master', retcode=None,
         )
         msg = f1_is_a_conflict_file.join('.git/worktrees/worktree/MERGE_MSG')
         assert msg.exists()

tests/check_vcs_permalinks_test.py

@@ -16,9 +16,9 @@ def test_passing(tmpdir):
         # tags are ok
         b'https://github.com/asottile/test/blob/1.0.0/foo%20bar#L1\n'
         # links to files but not line numbers are ok
-        b'https://github.com/asottile/test/blob/main/foo%20bar\n'
+        b'https://github.com/asottile/test/blob/master/foo%20bar\n'
         # regression test for overly-greedy regex
-        b'https://github.com/ yes / no ? /blob/main/foo#L1\n',
+        b'https://github.com/ yes / no ? /blob/master/foo#L1\n',
     )
     assert not main((str(f),))
 
@@ -26,15 +26,17 @@ def test_passing(tmpdir):
 def test_failing(tmpdir, capsys):
     with tmpdir.as_cwd():
         tmpdir.join('f.txt').write_binary(
-            b'https://github.com/asottile/test/blob/main/foo#L1\n'
+            b'https://github.com/asottile/test/blob/master/foo#L1\n'
+            b'https://example.com/asottile/test/blob/master/foo#L1\n'
             b'https://example.com/asottile/test/blob/main/foo#L1\n',
         )
 
         assert main(('f.txt', '--additional-github-domain', 'example.com'))
         out, _ = capsys.readouterr()
         assert out == (
-            'f.txt:1:https://github.com/asottile/test/blob/main/foo#L1\n'
-            'f.txt:2:https://example.com/asottile/test/blob/main/foo#L1\n'
+            'f.txt:1:https://github.com/asottile/test/blob/master/foo#L1\n'
+            'f.txt:2:https://example.com/asottile/test/blob/master/foo#L1\n'
+            'f.txt:3:https://example.com/asottile/test/blob/main/foo#L1\n'
             '\n'
             'Non-permanent github link detected.\n'
             'On any page on github press [y] to load a permalink.\n'

tests/file_contents_sorter_test.py

@@ -10,9 +10,7 @@ from pre_commit_hooks.file_contents_sorter import PASS
 @pytest.mark.parametrize(
     ('input_s', 'argv', 'expected_retval', 'output'),
     (
-        (b'', [], PASS, b''),
-        (b'\n', [], FAIL, b''),
-        (b'\n\n', [], FAIL, b''),
+        (b'', [], FAIL, b'\n'),
         (b'lonesome\n', [], PASS, b'lonesome\n'),
         (b'missing_newline', [], FAIL, b'missing_newline\n'),
         (b'newline\nmissing', [], FAIL, b'missing\nnewline\n'),
@@ -67,6 +65,18 @@ from pre_commit_hooks.file_contents_sorter import PASS
             FAIL,
             b'Fie\nFoe\nfee\nfum\n',
         ),
+        (
+            b'fee\nFie\nFoe\nfum\n',
+            ['--unique', '--ignore-case'],
+            PASS,
+            b'fee\nFie\nFoe\nfum\n',
+        ),
+        (
+            b'fee\nfee\nFie\nFoe\nfum\n',
+            ['--unique', '--ignore-case'],
+            FAIL,
+            b'fee\nFie\nFoe\nfum\n',
+        ),
     ),
 )
 def test_integration(input_s, argv, expected_retval, output, tmpdir):
@@ -77,24 +87,3 @@ def test_integration(input_s, argv, expected_retval, output, tmpdir):
 
     assert path.read_binary() == output
     assert output_retval == expected_retval
-
-
-@pytest.mark.parametrize(
-    ('input_s', 'argv'),
-    (
-        (
-            b'fee\nFie\nFoe\nfum\n',
-            ['--unique', '--ignore-case'],
-        ),
-        (
-            b'fee\nfee\nFie\nFoe\nfum\n',
-            ['--unique', '--ignore-case'],
-        ),
-    ),
-)
-def test_integration_invalid_args(input_s, argv, tmpdir):
-    path = tmpdir.join('file.txt')
-    path.write_binary(input_s)
-
-    with pytest.raises(SystemExit):
-        main([str(path)] + argv)

tests/fix_encoding_pragma_test.py

@@ -0,0 +1,161 @@
+from __future__ import annotations
+
+import io
+
+import pytest
+
+from pre_commit_hooks.fix_encoding_pragma import _normalize_pragma
+from pre_commit_hooks.fix_encoding_pragma import fix_encoding_pragma
+from pre_commit_hooks.fix_encoding_pragma import main
+
+
+def test_integration_inserting_pragma(tmpdir):
+    path = tmpdir.join('foo.py')
+    path.write_binary(b'import httplib\n')
+
+    assert main((str(path),)) == 1
+
+    assert path.read_binary() == (
+        b'# -*- coding: utf-8 -*-\n'
+        b'import httplib\n'
+    )
+
+
+def test_integration_ok(tmpdir):
+    path = tmpdir.join('foo.py')
+    path.write_binary(b'# -*- coding: utf-8 -*-\nx = 1\n')
+    assert main((str(path),)) == 0
+
+
+def test_integration_remove(tmpdir):
+    path = tmpdir.join('foo.py')
+    path.write_binary(b'# -*- coding: utf-8 -*-\nx = 1\n')
+
+    assert main((str(path), '--remove')) == 1
+
+    assert path.read_binary() == b'x = 1\n'
+
+
+def test_integration_remove_ok(tmpdir):
+    path = tmpdir.join('foo.py')
+    path.write_binary(b'x = 1\n')
+    assert main((str(path), '--remove')) == 0
+
+
+@pytest.mark.parametrize(
+    'input_str',
+    (
+        b'',
+        (
+            b'# -*- coding: utf-8 -*-\n'
+            b'x = 1\n'
+        ),
+        (
+            b'#!/usr/bin/env python\n'
+            b'# -*- coding: utf-8 -*-\n'
+            b'foo = "bar"\n'
+        ),
+    ),
+)
+def test_ok_inputs(input_str):
+    bytesio = io.BytesIO(input_str)
+    assert fix_encoding_pragma(bytesio) == 0
+    bytesio.seek(0)
+    assert bytesio.read() == input_str
+
+
+@pytest.mark.parametrize(
+    ('input_str', 'output'),
+    (
+        (
+            b'import httplib\n',
+            b'# -*- coding: utf-8 -*-\n'
+            b'import httplib\n',
+        ),
+        (
+            b'#!/usr/bin/env python\n'
+            b'x = 1\n',
+            b'#!/usr/bin/env python\n'
+            b'# -*- coding: utf-8 -*-\n'
+            b'x = 1\n',
+        ),
+        (
+            b'#coding=utf-8\n'
+            b'x = 1\n',
+            b'# -*- coding: utf-8 -*-\n'
+            b'x = 1\n',
+        ),
+        (
+            b'#!/usr/bin/env python\n'
+            b'#coding=utf8\n'
+            b'x = 1\n',
+            b'#!/usr/bin/env python\n'
+            b'# -*- coding: utf-8 -*-\n'
+            b'x = 1\n',
+        ),
+        # These should each get truncated
+        (b'#coding: utf-8\n', b''),
+        (b'# -*- coding: utf-8 -*-\n', b''),
+        (b'#!/usr/bin/env python\n', b''),
+        (b'#!/usr/bin/env python\n#coding: utf8\n', b''),
+        (b'#!/usr/bin/env python\n# -*- coding: utf-8 -*-\n', b''),
+    ),
+)
+def test_not_ok_inputs(input_str, output):
+    bytesio = io.BytesIO(input_str)
+    assert fix_encoding_pragma(bytesio) == 1
+    bytesio.seek(0)
+    assert bytesio.read() == output
+
+
+def test_ok_input_alternate_pragma():
+    input_s = b'# coding: utf-8\nx = 1\n'
+    bytesio = io.BytesIO(input_s)
+    ret = fix_encoding_pragma(bytesio, expected_pragma=b'# coding: utf-8')
+    assert ret == 0
+    bytesio.seek(0)
+    assert bytesio.read() == input_s
+
+
+def test_not_ok_input_alternate_pragma():
+    bytesio = io.BytesIO(b'x = 1\n')
+    ret = fix_encoding_pragma(bytesio, expected_pragma=b'# coding: utf-8')
+    assert ret == 1
+    bytesio.seek(0)
+    assert bytesio.read() == b'# coding: utf-8\nx = 1\n'
+
+
+@pytest.mark.parametrize(
+    ('input_s', 'expected'),
+    (
+        ('# coding: utf-8', b'# coding: utf-8'),
+        # trailing whitespace
+        ('# coding: utf-8\n', b'# coding: utf-8'),
+    ),
+)
+def test_normalize_pragma(input_s, expected):
+    assert _normalize_pragma(input_s) == expected
+
+
+def test_integration_alternate_pragma(tmpdir, capsys):
+    f = tmpdir.join('f.py')
+    f.write('x = 1\n')
+
+    pragma = '# coding: utf-8'
+    assert main((str(f), '--pragma', pragma)) == 1
+    assert f.read() == '# coding: utf-8\nx = 1\n'
+    out, _ = capsys.readouterr()
+    assert out == f'Added `# coding: utf-8` to {str(f)}\n'
+
+
+def test_crlf_ok(tmpdir):
+    f = tmpdir.join('f.py')
+    f.write_binary(b'# -*- coding: utf-8 -*-\r\nx = 1\r\n')
+    assert not main((str(f),))
+
+
+def test_crfl_adds(tmpdir):
+    f = tmpdir.join('f.py')
+    f.write_binary(b'x = 1\r\n')
+    assert main((str(f),))
+    assert f.read_binary() == b'# -*- coding: utf-8 -*-\r\nx = 1\r\n'

tests/no_commit_to_branch_test.py

@@ -11,13 +11,13 @@ from testing.util import git_commit
 def test_other_branch(temp_git_dir):
     with temp_git_dir.as_cwd():
         cmd_output('git', 'checkout', '-b', 'anotherbranch')
-        assert is_on_branch({'placeholder'}) is False
+        assert is_on_branch({'master'}) is False
 
 
 def test_multi_branch(temp_git_dir):
     with temp_git_dir.as_cwd():
         cmd_output('git', 'checkout', '-b', 'another/branch')
-        assert is_on_branch({'placeholder'}) is False
+        assert is_on_branch({'master'}) is False
 
 
 def test_multi_branch_fail(temp_git_dir):
@@ -26,10 +26,9 @@ def test_multi_branch_fail(temp_git_dir):
         assert is_on_branch({'another/branch'}) is True
 
 
-def test_exact_branch(temp_git_dir):
+def test_master_branch(temp_git_dir):
     with temp_git_dir.as_cwd():
-        cmd_output('git', 'checkout', '-b', 'branchname')
-        assert is_on_branch({'branchname'}) is True
+        assert is_on_branch({'master'}) is True
 
 
 def test_main_branch_call(temp_git_dir):
@@ -51,11 +50,11 @@ def test_branch_pattern_fail(temp_git_dir):
         assert is_on_branch(set(), {'another/.*'}) is True
 
 
-@pytest.mark.parametrize('branch_name', ('somebranch', 'another/branch'))
+@pytest.mark.parametrize('branch_name', ('master', 'another/branch'))
 def test_branch_pattern_multiple_branches_fail(temp_git_dir, branch_name):
     with temp_git_dir.as_cwd():
         cmd_output('git', 'checkout', '-b', branch_name)
-        assert main(('--branch', 'somebranch', '--pattern', 'another/.*'))
+        assert main(('--branch', 'master', '--pattern', 'another/.*'))
 
 
 def test_main_default_call(temp_git_dir):

tests/pretty_format_json_test.py

@@ -82,24 +82,6 @@ def test_autofix_main(tmpdir):
     assert ret == 0
 
 
-def test_invalid_main(tmpdir):
-    srcfile1 = tmpdir.join('not_valid_json.json')
-    srcfile1.write(
-        '{\n'
-        '  // not json\n'
-        '  "a": "b"\n'
-        '}',
-    )
-    srcfile2 = tmpdir.join('to_be_json_formatted.json')
-    srcfile2.write('{ "a": "b" }')
-
-    # it should have skipped the first file and formatted the second one
-    assert main(['--autofix', str(srcfile1), str(srcfile2)]) == 1
-
-    # confirm second file was formatted (shouldn't trigger linter again)
-    assert main([str(srcfile2)]) == 0
-
-
 def test_orderfile_get_pretty_format():
     ret = main((
         '--top-keys=alist', get_resource_path('pretty_formatted_json.json'),

tests/requirements_txt_fixer_test.py

@@ -68,12 +68,6 @@ from pre_commit_hooks.requirements_txt_fixer import Requirement
             b'f<=2\n'
             b'g<2\n',
         ),
-        (b'a==1\nb==1\na==1\n', FAIL, b'a==1\nb==1\n'),
-        (
-            b'a==1\nb==1\n#comment about a\na==1\n',
-            FAIL,
-            b'#comment about a\na==1\nb==1\n',
-        ),
         (b'ocflib\nDjango\nPyMySQL\n', FAIL, b'Django\nocflib\nPyMySQL\n'),
         (
             b'-e git+ssh://git_url@tag#egg=ocflib\nDjango\nPyMySQL\n',
@@ -82,8 +76,6 @@ from pre_commit_hooks.requirements_txt_fixer import Requirement
         ),
         (b'bar\npkg-resources==0.0.0\nfoo\n', FAIL, b'bar\nfoo\n'),
         (b'foo\npkg-resources==0.0.0\nbar\n', FAIL, b'bar\nfoo\n'),
-        (b'bar\npkg_resources==0.0.0\nfoo\n', FAIL, b'bar\nfoo\n'),
-        (b'foo\npkg_resources==0.0.0\nbar\n', FAIL, b'bar\nfoo\n'),
         (
             b'git+ssh://git_url@tag#egg=ocflib\nDjango\nijk\n',
             FAIL,

tests/string_fixer_test.py

@@ -37,12 +37,6 @@ TESTS = (
         1,
     ),
     ('"foo""bar"', "'foo''bar'", 1),
-    pytest.param(
-        "f'hello{\"world\"}'",
-        "f'hello{\"world\"}'",
-        0,
-        id='ignore nested fstrings',
-    ),
 )
 
 

tox.ini

@@ -1,5 +1,5 @@
 [tox]
-envlist = py,pre-commit
+envlist = py37,py38,pypy3,pre-commit
 
 [testenv]
 deps = -rrequirements-dev.txt