Merge pull request #6 from CalthorpeAnalytics/bobby-pull-from-master

Update to Latest upstream.

.coveragerc

@@ -5,11 +5,12 @@ source =
 omit =
     .tox/*
     /usr/*
-    */tmp*
     setup.py
     get-git-lfs.py
 
 [report]
+show_missing = True
+skip_covered = True
 exclude_lines =
     # Have to re-enable the standard pragma
     \#\s*pragma: no cover

.gitignore

@@ -2,6 +2,7 @@
 *.iml
 *.py[co]
 .*.sw[a-z]
+.pytest_cache
 .coverage
 .idea
 .project
@@ -11,3 +12,5 @@
 /venv*
 coverage-html
 dist
+# SublimeText project/workspace files
+*.sublime-*

.pre-commit-config.yaml

@@ -1,5 +1,6 @@
+repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    sha: v0.7.0
+    rev: v1.3.0
     hooks:
     -   id: trailing-whitespace
     -   id: end-of-file-fixer
@@ -13,12 +14,19 @@
     -   id: requirements-txt-fixer
     -   id: flake8
 -   repo: https://github.com/pre-commit/pre-commit
-    sha: v0.12.2
+    rev: v1.7.0
     hooks:
-    -   id: validate_config
     -   id: validate_manifest
 -   repo: https://github.com/asottile/reorder_python_imports
-    sha: v0.3.1
+    rev: v1.0.1
     hooks:
     -   id: reorder-python-imports
         language_version: python2.7
+-   repo: https://github.com/asottile/pyupgrade
+    rev: v1.2.0
+    hooks:
+    -   id: pyupgrade
+-   repo: https://github.com/asottile/add-trailing-comma
+    rev: v0.6.4
+    hooks:
+    -   id: add-trailing-comma

.pre-commit-hooks.yaml

@@ -3,147 +3,263 @@
     description: "Runs autopep8 over python source.  If you configure additional arguments you'll want to at least include -i."
     entry: autopep8-wrapper
     language: python
-    files: \.py$
+    types: [python]
     args: [-i]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: check-added-large-files
     name: Check for added large files
     description: Prevent giant files from being committed
     entry: check-added-large-files
     language: python
-    # Match all files
+    # for backward compatibility
     files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: check-ast
     name: Check python ast
     description: Simply check whether the files parse as valid python.
     entry: check-ast
     language: python
-    files: '\.py$'
+    types: [python]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: check-byte-order-marker
     name: Check for byte-order marker
     description: Forbid files which have a UTF-8 byte-order marker
     entry: check-byte-order-marker
     language: python
-    files: '\.py$'
+    types: [python]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
+-   id: check-builtin-literals
+    name: Check builtin type constructor use
+    description: Require literal syntax when initializing empty or zero Python builtin types.
+    entry: check-builtin-literals
+    language: python
+    types: [python]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: check-case-conflict
     name: Check for case conflicts
     description: Check for files that would conflict in case-insensitive filesystems
     entry: check-case-conflict
     language: python
-    # Match all files
+    # for backward compatibility
     files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: check-docstring-first
     name: Check docstring is first
     description: Checks a common error of defining a docstring after code.
     entry: check-docstring-first
     language: python
-    files: \.py$
+    types: [python]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
+-   id: check-executables-have-shebangs
+    name: Check that executables have shebangs
+    description: Ensures that (non-binary) executables have a shebang.
+    entry: check-executables-have-shebangs
+    language: python
+    types: [text, executable]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: check-json
     name: Check JSON
     description: This hook checks json files for parseable syntax.
     entry: check-json
     language: python
-    files: \.json$
+    types: [json]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: pretty-format-json
     name: Pretty format JSON
     description: This hook sets a standard for formatting JSON files.
     entry: pretty-format-json
     language: python
-    files: \.json$
+    types: [json]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: check-merge-conflict
     name: Check for merge conflicts
     description: Check for files that contain merge conflict strings.
     entry: check-merge-conflict
     language: python
-    # Match all files
+    types: [text]
+    # for backward compatibility
     files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: check-symlinks
     name: Check for broken symlinks
     description: Checks for symlinks which do not point to anything.
     entry: check-symlinks
     language: python
-    # Match all files
+    types: [symlink]
+    # for backward compatibility
     files: ''
+    minimum_pre_commit_version: 0.15.0
+-   id: check-vcs-permalinks
+    name: Check vcs permalinks
+    description: Ensures that links to vcs websites are permalinks.
+    entry: check-vcs-permalinks
+    language: python
+    types: [text]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: check-xml
     name: Check Xml
     description: This hook checks xml files for parseable syntax.
     entry: check-xml
     language: python
-    files: \.xml$
+    types: [xml]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: check-yaml
     name: Check Yaml
     description: This hook checks yaml files for parseable syntax.
     entry: check-yaml
     language: python
-    files: \.(yaml|yml|eyaml)$
+    types: [yaml]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: debug-statements
     name: Debug Statements (Python)
-    description: This hook checks that debug statements (pdb, ipdb, pudb) are not imported on commit.
+    description: Check for debugger imports and py37+ `breakpoint()` calls in python source.
     entry: debug-statement-hook
     language: python
-    files: \.py$
+    types: [python]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: detect-aws-credentials
     name: Detect AWS Credentials
     description: Detects *your* aws credentials from the aws cli credentials file
     entry: detect-aws-credentials
     language: python
+    types: [text]
+    # for backward compatibility
     files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: detect-private-key
     name: Detect Private Key
     description: Detects the presence of private keys
     entry: detect-private-key
     language: python
+    types: [text]
+    # for backward compatibility
     files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: double-quote-string-fixer
     name: Fix double quoted strings
     description: This hook replaces double quoted strings with single quoted strings
     entry: double-quote-string-fixer
     language: python
-    files: \.py$
+    types: [python]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: end-of-file-fixer
     name: Fix End of Files
     description: Ensures that a file is either empty, or ends with one newline.
     entry: end-of-file-fixer
     language: python
-    files: \.(asciidoc|adoc|coffee|cpp|css|c|ejs|erb|groovy|h|haml|hh|hpp|hxx|html|in|j2|jade|json|js|less|markdown|md|ml|mli|pp|py|rb|rs|R|scala|scss|sh|slim|tex|tmpl|ts|txt|yaml|yml)$
+    types: [text]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
+-   id: file-contents-sorter
+    name: File Contents Sorter
+    description: Sort the lines in specified files (defaults to alphabetical). You must provide list of target files as input in your .pre-commit-config.yaml file.
+    entry: file-contents-sorter
+    language: python
+    files: '^$'
 -   id: fix-encoding-pragma
     name: Fix python encoding pragma
     language: python
     entry: fix-encoding-pragma
     description: 'Add # -*- coding: utf-8 -*- to the top of python files'
-    files: \.py$
+    types: [python]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: flake8
     name: Flake8
     description: This hook runs flake8.
     entry: flake8
     language: python
-    files: \.py$
+    types: [python]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: forbid-new-submodules
     name: Forbid new submodules
     language: python
     entry: forbid-new-submodules
     description: Prevent addition of new git submodules
+    # for backward compatibility
     files: ''
+    minimum_pre_commit_version: 0.15.0
+-   id: mixed-line-ending
+    name: Mixed line ending
+    description: Replaces or checks mixed line ending
+    entry: mixed-line-ending
+    language: python
+    types: [text]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: name-tests-test
     name: Tests should end in _test.py
     description: This verifies that test files are named correctly
     entry: name-tests-test
     language: python
-    files: tests/.+\.py$
+    files: (^|/)tests/.+\.py$
+-   id: no-commit-to-branch
+    name: "Don't commit to branch"
+    entry: no-commit-to-branch
+    language: python
+    pass_filenames: false
+    always_run: true
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: pyflakes
     name: Pyflakes (DEPRECATED, use flake8)
     description: This hook runs pyflakes. (This is deprecated, use flake8).
     entry: pyflakes
     language: python
-    files: \.py$
+    types: [python]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: requirements-txt-fixer
     name: Fix requirements.txt
     description: Sorts entries in requirements.txt
     entry: requirements-txt-fixer
     language: python
     files: requirements.*\.txt$
+-   id: sort-simple-yaml
+    name: Sort simple YAML files
+    language: python
+    entry: sort-simple-yaml
+    description: Sorts simple YAML files which consist only of top-level keys, preserving comments and blocks.
+    files: '^$'
 -   id: trailing-whitespace
     name: Trim Trailing Whitespace
     description: This hook trims trailing whitespace.
     entry: trailing-whitespace-fixer
     language: python
-    files: \.(asciidoc|adoc|coffee|cpp|css|c|ejs|erb|groovy|h|haml|hh|hpp|hxx|html|in|j2|jade|json|js|less|markdown|md|ml|mli|pp|py|rb|rs|R|scala|scss|sh|slim|tex|tmpl|ts|txt|yaml|yml)$
+    types: [text]
+    # for backward compatibility
+    files: ''
+    minimum_pre_commit_version: 0.15.0

.travis.yml

@@ -8,8 +8,8 @@ matrix:
     -   env: TOXENV=py36
         python: 3.6
     -   env: TOXENV=pypy
-#install: pip install coveralls tox
+        python: pypy-5.7.1
-install: pip install tox
+install: pip install coveralls tox
 script: tox
 before_install:
   # Install git-lfs for a test
@@ -18,5 +18,5 @@ after_success: coveralls
 cache:
     directories:
         - $HOME/.cache/pip
-        - $HOME/.pre-commit
+        - $HOME/.cache/pre-commit
         - /tmp/git-lfs

CHANGELOG

@@ -1,86 +0,0 @@
-0.7.1
-=====
-- Don't false positive on files where trailing whitespace isn't changed.
-
-0.7.0
-=====
-- Improve search for detecting aws keys
-- Add .pre-commit-hooks.yaml for forward compatibility
-
-0.6.1
-=====
-- trailing-whitespace-hook: restore original file on catastrophic failure
-- trailing-whitespace-hook: support crlf
-- check-yaml: Use safe_load
-- check-json: allow custom key sort
-- check-json: display filename for non-utf8 files
-- New hook: forbid-new-submodules
-
-0.6.0
-=====
-- Merge conflict detection no longer crashes on binary files
-- Indentation in json may be an arbitrary separator
-- Editable requirements are properly sorted
-- Encoding pragma fixer pragma is configurable
-
-0.5.1
-=====
-- Add a --no-sort-keys to json pretty formatter
-- Add a --remove to fix-encoding-pragma
-
-0.5.0
-=====
-- Add check-byte-order-marker
-- Add check-synlinks
-- check-large-files-added understands git-lfs
-- Support older git
-- Fix regex for --django in test name checker
-- Add fix-encoding-pragma hook
-- requirements-txt-fixer now sorts like latest pip
-- Add check-ast hook
-- Add detect-aws-credentials hook
-- Allow binary files to pass private key hook
-- Add pretty-format-json hook
-
-0.4.2
-=====
-- Add --django to test name checker
-- Add check-merge-conflict hook
-- Remove dependency on plumbum
-- Add q as a debug statement
-- Don't detect markup titles as conflicts
-- Teach trailing-whitespace about markdown
-- Quickfix for pyflakes - flake8 version conflict
-
-0.4.1
-=====
-- Respect configuration when running autopep8
-- Quickfix for pep8 version conflicts
-
-0.4.0
-=====
-- Fix trailing-whitespace on OS X
-- Add check-added-large-files hook
-- Add check-docstring-first hook
-- Add requirements-txt-fixer hook
-- Add check-case-conflict hook
-- Use yaml's CLoader when available in check-yaml for more speed
-- Add check-xml hook
-- Fix end-of-file-fixer for windows
-- Add double-quote-string-fixer hook
-
-0.3.0
-=====
-- Add autopep8-wrapper hook
-
-0.2.0
-=====
-- Add check-json hook
-
-0.1.1
-=====
-- Don't crash on non-parseable files for debug-statement-hook
-
-0.1.0
-=====
-- Initial Release

CHANGELOG.md

@@ -0,0 +1,223 @@
+1.3.0
+=====
+
+### Features
+- Add an `--unsafe` argument to `check-yaml` to allow custom yaml tags
+    - #273 issue by @blackillzone.
+    - #274 PR by @asottile.
+- Automatically remove `pkg-resources==0.0.0` in `requirements-txt-fixer`
+    - #275 PR by @nvtkaszpir.
+- Detect `breakpoint()` (python3.7+) in `debug-statements` hook.
+    - #283 PR by @asottile.
+- Detect sshcom and putty hooks in `detect-private-key`
+    - #287 PR by @vin01.
+
+### Fixes
+- Open files as UTF-8 (`autopep8-wrapper`, `check-docstring-first`,
+  `double-quote-string-fixer`)
+    - #279 PR by @nvtkaszpir.
+- Fix `AttributeError` in `check-builtin-literals` for some functions
+    - #285 issue by @EgoWumpus.
+    - #286 PR by @asottile.
+
+1.2.3
+=====
+
+### Fixes
+- `trailing-whitespace` entrypoint was incorrect.
+    - f6780b9 by @asottile.
+
+1.2.2
+=====
+
+### Fixes
+- `trailing-whitespace` no longer adds a missing newline at end-of-file
+    - #270 issue by @fractos.
+    - #271 PR by @asottile.
+
+1.2.1-1
+=======
+
+(Note: this is a tag-only release as no code changes occurred)
+
+### Fixes:
+- Don't pass filenames for `no-commit-to-branch`
+    - #268 issue by @dongyuzheng.
+    - #269 PR by @asottile.
+
+1.2.1
+=====
+### Fixes:
+- `detect-aws-credentials` false positive when key was empty
+    - #258 issue by @PVSec.
+    - #260 PR by @PVSec.
+- `no-commit-to-branch` no longer crashes when not on a branch
+    - #265 issue by @hectorv.
+    - #266 PR by @asottile.
+
+1.2.0
+=====
+### Features:
+- Add new `check-builtin-literals` hook.
+    - #249 #251 PR by @benwebber.
+- `pretty-format-json` no longer depends on `simplejson`.
+    - #254 PR by @cas--.
+- `detect-private-key` now detects gcp keys.
+    - #255 issue by @SaMnCo @nicain.
+    - #256 PR by @nicain.
+
+1.1.1
+=====
+### Fixes:
+- Fix output interleaving in `check-vcs-permalinks` under python3.
+    - #245 PR by @asottile.
+
+1.1.0
+=====
+### Features:
+- `check-yaml` gains a `--allow-multiple-documents` (`-m`) argument to allow
+  linting of files using the
+  [multi document syntax](http://www.yaml.org/spec/1.2/spec.html#YAML)
+    - pre-commit/pre-commit#635 issue by @geekobi.
+    - #244 PR by @asottile.
+
+1.0.0
+=====
+### Features:
+- New hook: `check-vcs-permalinks` for ensuring permalinked github urls.
+    - #241 PR by @asottile.
+
+### Fixes:
+- Fix `trailing-whitespace` for non-utf8 files on macos
+    - #242 PR by @asottile.
+- Fix `requirements-txt-fixer` for files ending in comments
+    - #243 PR by @asottile.
+
+0.9.5
+=====
+- Fix mixed-line-endings `--fix=...` when whole file is a different ending
+
+0.9.4
+=====
+- Fix entry point for `mixed-line-ending`
+
+0.9.3
+=====
+- New hook: `mixed-line-ending`
+
+0.9.2
+=====
+- Report full python version in `check-ast`.
+- Apply a more strict regular expression for `name-tests-test`
+- Upgrade binding for `git-lfs` for `check-added-large-files`.  The oldest
+  version that is supported is 2.2.1 (2.2.0 will incorrectly refer to all
+  files as "lfs" (false negative) and earlier versions will crash.
+- `debug-statements` now works for non-utf-8 files.
+
+0.9.1
+=====
+- Add `check-executables-have-shebangs` hook.
+
+0.9.0
+=====
+- Add `sort-simple-yaml` hook
+- Fix `requirements-txt-fixer` for empty files
+- Add `file-contents-sorter` hook for sorting flat files
+- `check-merge-conflict` now recognizes rebase conflicts
+- Metadata now uses `types` (and therefore requires pre-commit 0.15.0).  This
+  allows the text processing hooks to match *all* text files (and to match
+  files which would only be classifiable by their shebangs).
+
+0.8.0
+=====
+- Add flag allowing missing keys to `detect-aws-credentials`
+- Handle django default `tests.py` in `name-tests-test`
+- Add `--no-ensure-ascii` option to `pretty-format-json`
+- Add `no-commit-to-branch` hook
+
+0.7.1
+=====
+- Don't false positive on files where trailing whitespace isn't changed.
+
+0.7.0
+=====
+- Improve search for detecting aws keys
+- Add .pre-commit-hooks.yaml for forward compatibility
+
+0.6.1
+=====
+- trailing-whitespace-hook: restore original file on catastrophic failure
+- trailing-whitespace-hook: support crlf
+- check-yaml: Use safe_load
+- check-json: allow custom key sort
+- check-json: display filename for non-utf8 files
+- New hook: forbid-new-submodules
+
+0.6.0
+=====
+- Merge conflict detection no longer crashes on binary files
+- Indentation in json may be an arbitrary separator
+- Editable requirements are properly sorted
+- Encoding pragma fixer pragma is configurable
+
+0.5.1
+=====
+- Add a --no-sort-keys to json pretty formatter
+- Add a --remove to fix-encoding-pragma
+
+0.5.0
+=====
+- Add check-byte-order-marker
+- Add check-synlinks
+- check-large-files-added understands git-lfs
+- Support older git
+- Fix regex for --django in test name checker
+- Add fix-encoding-pragma hook
+- requirements-txt-fixer now sorts like latest pip
+- Add check-ast hook
+- Add detect-aws-credentials hook
+- Allow binary files to pass private key hook
+- Add pretty-format-json hook
+
+0.4.2
+=====
+- Add --django to test name checker
+- Add check-merge-conflict hook
+- Remove dependency on plumbum
+- Add q as a debug statement
+- Don't detect markup titles as conflicts
+- Teach trailing-whitespace about markdown
+- Quickfix for pyflakes - flake8 version conflict
+
+0.4.1
+=====
+- Respect configuration when running autopep8
+- Quickfix for pep8 version conflicts
+
+0.4.0
+=====
+- Fix trailing-whitespace on OS X
+- Add check-added-large-files hook
+- Add check-docstring-first hook
+- Add requirements-txt-fixer hook
+- Add check-case-conflict hook
+- Use yaml's CLoader when available in check-yaml for more speed
+- Add check-xml hook
+- Fix end-of-file-fixer for windows
+- Add double-quote-string-fixer hook
+
+0.3.0
+=====
+- Add autopep8-wrapper hook
+
+0.2.0
+=====
+- Add check-json hook
+
+0.1.1
+=====
+- Don't crash on non-parseable files for debug-statement-hook
+
+0.1.0
+=====
+- Initial Release

Makefile

@@ -1,24 +0,0 @@
-REBUILD_FLAG =
-
-.PHONY: all
-all: venv test
-
-.PHONY: venv
-venv: .venv.touch
-	tox -e venv $(REBUILD_FLAG)
-
-.PHONY: tests test
-tests: test
-test: .venv.touch
-	tox $(REBUILD_FLAG)
-
-.venv.touch: setup.py requirements-dev.txt
-	$(eval REBUILD_FLAG := --recreate)
-	touch .venv.touch
-
-.PHONY: clean
-clean:
-	find . -name '*.pyc' -delete
-	rm -rf .tox
-	rm -rf ./venv-*
-	rm -f .venv.touch

README.md

@@ -14,8 +14,8 @@ See also: https://github.com/pre-commit/pre-commit
 
 Add this to your `.pre-commit-config.yaml`
 
-    -   repo: git://github.com/pre-commit/pre-commit-hooks
+    -   repo: https://github.com/pre-commit/pre-commit-hooks
-        sha: v0.7.1  # Use the ref you want to point at
+        rev: v1.3.0  # Use the ref you want to point at
         hooks:
         -   id: trailing-whitespace
         # -   id: ...
@@ -25,21 +25,40 @@ Add this to your `.pre-commit-config.yaml`
 
 - `autopep8-wrapper` - Runs autopep8 over python source.
     - Ignore PEP 8 violation types with `args: ['-i', '--ignore=E000,...']` or
-      through configuration of the `[pep8]` section in setup.cfg / tox.ini.
+      through configuration of the `[pycodestyle]` section in
+      setup.cfg / tox.ini.
 - `check-added-large-files` - Prevent giant files from being committed.
     - Specify what is "too large" with `args: ['--maxkb=123']` (default=500kB).
+    - If `git-lfs` is installed, lfs files will be skipped
+      (requires `git-lfs>=2.2.1`)
 - `check-ast` - Simply check whether files parse as valid python.
+- `check-builtin-literals` - Require literal syntax when initializing empty or zero Python builtin types.
+    - Allows calling constructors with positional arguments (e.g., `list('abc')`).
+    - Allows calling constructors from the `builtins` (`__builtin__`) namespace (`builtins.list()`).
+    - Ignore this requirement for specific builtin types with `--ignore=type1,type2,…`.
+    - Forbid `dict` keyword syntax with `--no-allow-dict-kwargs`.
 - `check-byte-order-marker` - Forbid files which have a UTF-8 byte-order marker
 - `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-json` - Attempts to load all json files to verify syntax.
 - `check-merge-conflict` - Check for files that contain merge conflict strings.
 - `check-symlinks` - Checks for symlinks which do not point to anything.
+- `check-vcs-permalinks` - Ensures that links to vcs websites are permalinks.
 - `check-xml` - Attempts to load all xml files to verify syntax.
 - `check-yaml` - Attempts to load all yaml files to verify syntax.
-- `debug-statements` - Check for pdb / ipdb / pudb statements in code.
+    - `--allow-multiple-documents` - allow yaml files which use the
+      [multi-document syntax](http://www.yaml.org/spec/1.2/spec.html#YAML)
+    - `--unsafe` - Instead of loading the files, simply parse them for syntax.
+      A syntax-only check enables extensions and unsafe constructs which would
+      otherwise be forbidden.  Using this option removes all guarantees of
+      portability to other yaml implementations.
+      Implies `--allow-multiple-documents`.
+- `debug-statements` - Check for debugger imports and py37+ `breakpoint()`
+  calls in python source.
 - `detect-aws-credentials` - Checks for the existence of AWS secrets that you
   have set up with the AWS CLI.
   The following arguments are available:
@@ -52,10 +71,21 @@ Add this to your `.pre-commit-config.yaml`
 - `end-of-file-fixer` - Makes sure files end in a newline and only a newline.
 - `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 list of target files as input to it. Note that this hook WILL remove blank lines and does NOT respect any comments.
 - `flake8` - Run flake8 on your python files.
 - `forbid-new-submodules` - Prevent addition of new git submodules.
+- `mixed-line-ending` - Replaces or checks mixed line ending.
+    - `--fix={auto,crlf,lf,no}`
+        - `auto` - Replaces automatically the most frequent line ending. This is the default argument.
+        - `crlf`, `lf` - Forces to replace line ending by respectively CRLF and LF.
+        - `no` - Checks if there is any mixed line ending without modifying any file.
 - `name-tests-test` - Assert that files in tests/ end in `_test.py`.
     - Use `args: ['--django']` to match `test*.py` instead.
+- `no-commit-to-branch` - Protect specific branches from direct checkins.
+    - Use `args: [--branch <branch>]` to set the branch. `master` is the
+      default if no argument is set.
+    - `-b` / `--branch` may be specified multiple times to protect multiple
+      branches.
 - `pyflakes` - Run pyflakes on your python files.
 - `pretty-format-json` - Checks that all your JSON files are pretty.  "Pretty"
   here means that keys are sorted and indented.  You can configure this with
@@ -64,7 +94,8 @@ Add this to your `.pre-commit-config.yaml`
     - `--indent ...` - Control the indentation (either a number for a number of spaces or a string of whitespace).  Defaults to 4 spaces.
     - `--no-sort-keys` - when autofixing, retain the original key ordering (instead of sorting the keys)
     - `--top-keys comma,separated,keys` - Keys to keep at the top of mappings.
-- `requirements-txt-fixer` - Sorts entries in requirements.txt
+- `requirements-txt-fixer` - 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 keys, preserving comments and blocks.
 - `trailing-whitespace` - Trims trailing whitespace.
     - Markdown linebreak trailing spaces preserved for `.md` and`.markdown`;
       use `args: ['--markdown-linebreak-ext=txt,text']` to add other extensions,

appveyor.yml

@@ -14,4 +14,4 @@ test_script: tox
 
 cache:
   - '%LOCALAPPDATA%\pip\cache'
-  - '%USERPROFILE%\.pre-commit'
+  - '%USERPROFILE%\.cache\pre-commit'

get-git-lfs.py

@@ -8,9 +8,9 @@ from urllib.request import urlopen
 
 DOWNLOAD_PATH = (
     'https://github.com/github/git-lfs/releases/download/'
-    'v1.1.0/git-lfs-linux-amd64-1.1.0.tar.gz'
+    'v2.2.1/git-lfs-linux-amd64-2.2.1.tar.gz'
 )
-PATH_IN_TAR = 'git-lfs-1.1.0/git-lfs'
+PATH_IN_TAR = 'git-lfs-2.2.1/git-lfs'
 DEST_PATH = '/tmp/git-lfs/git-lfs'
 DEST_DIR = os.path.dirname(DEST_PATH)
 

hooks.yaml

@@ -1,149 +1,186 @@
 -   id: autopep8-wrapper
-    name: autopep8 wrapper
+    language: system
-    description: "Runs autopep8 over python source.  If you configure additional arguments you'll want to at least include -i."
+    name: upgrade-your-pre-commit-version
-    entry: autopep8-wrapper
+    entry: upgrade-your-pre-commit-version
-    language: python
+    files: ''
-    files: \.py$
+    minimum_pre_commit_version: 0.15.0
-    args: [-i]
 -   id: check-added-large-files
-    name: Check for added large files
+    language: system
-    description: Prevent giant files from being committed
+    name: upgrade-your-pre-commit-version
-    entry: check-added-large-files
+    entry: upgrade-your-pre-commit-version
-    language: python
-    # Match all files
     files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: check-ast
-    name: Check python ast
+    language: system
-    description: Simply check whether the files parse as valid python.
+    name: upgrade-your-pre-commit-version
-    entry: check-ast
+    entry: upgrade-your-pre-commit-version
-    language: python
+    files: ''
-    files: '\.py$'
+    minimum_pre_commit_version: 0.15.0
+-   id: check-builtin-literals
+    language: system
+    name: upgrade-your-pre-commit-version
+    entry: upgrade-your-pre-commit-version
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: check-byte-order-marker
-    name: Check for byte-order marker
+    language: system
-    description: Forbid files which have a UTF-8 byte-order marker
+    name: upgrade-your-pre-commit-version
-    entry: check-byte-order-marker
+    entry: upgrade-your-pre-commit-version
-    language: python
+    files: ''
-    files: '\.py$'
+    minimum_pre_commit_version: 0.15.0
 -   id: check-case-conflict
-    name: Check for case conflicts
+    language: system
-    description: Check for files that would conflict in case-insensitive filesystems
+    name: upgrade-your-pre-commit-version
-    entry: check-case-conflict
+    entry: upgrade-your-pre-commit-version
-    language: python
-    # Match all files
     files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: check-docstring-first
-    name: Check docstring is first
+    language: system
-    description: Checks a common error of defining a docstring after code.
+    name: upgrade-your-pre-commit-version
-    entry: check-docstring-first
+    entry: upgrade-your-pre-commit-version
-    language: python
+    files: ''
-    files: \.py$
+    minimum_pre_commit_version: 0.15.0
+-   id: check-executables-have-shebangs
+    language: system
+    name: upgrade-your-pre-commit-version
+    entry: upgrade-your-pre-commit-version
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: check-json
-    name: Check JSON
+    language: system
-    description: This hook checks json files for parseable syntax.
+    name: upgrade-your-pre-commit-version
-    entry: check-json
+    entry: upgrade-your-pre-commit-version
-    language: python
+    files: ''
-    files: \.json$
+    minimum_pre_commit_version: 0.15.0
 -   id: pretty-format-json
-    name: Pretty format JSON
+    language: system
-    description: This hook sets a standard for formatting JSON files.
+    name: upgrade-your-pre-commit-version
-    entry: pretty-format-json
+    entry: upgrade-your-pre-commit-version
-    language: python
+    files: ''
-    files: \.json$
+    minimum_pre_commit_version: 0.15.0
 -   id: check-merge-conflict
-    name: Check for merge conflicts
+    language: system
-    description: Check for files that contain merge conflict strings.
+    name: upgrade-your-pre-commit-version
-    entry: check-merge-conflict
+    entry: upgrade-your-pre-commit-version
-    language: python
-    # Match all files
     files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: check-symlinks
-    name: Check for broken symlinks
+    language: system
-    description: Checks for symlinks which do not point to anything.
+    name: upgrade-your-pre-commit-version
-    entry: check-symlinks
+    entry: upgrade-your-pre-commit-version
-    language: python
-    # Match all files
     files: ''
+    minimum_pre_commit_version: 0.15.0
+-   id: check-vcs-permalinks
+    language: system
+    name: upgrade-your-pre-commit-version
+    entry: upgrade-your-pre-commit-version
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: check-xml
-    name: Check Xml
+    language: system
-    description: This hook checks xml files for parseable syntax.
+    name: upgrade-your-pre-commit-version
-    entry: check-xml
+    entry: upgrade-your-pre-commit-version
-    language: python
+    files: ''
-    files: \.xml$
+    minimum_pre_commit_version: 0.15.0
 -   id: check-yaml
-    name: Check Yaml
+    language: system
-    description: This hook checks yaml files for parseable syntax.
+    name: upgrade-your-pre-commit-version
-    entry: check-yaml
+    entry: upgrade-your-pre-commit-version
-    language: python
+    files: ''
-    files: \.(yaml|yml|eyaml)$
+    minimum_pre_commit_version: 0.15.0
 -   id: debug-statements
-    name: Debug Statements (Python)
+    language: system
-    description: This hook checks that debug statements (pdb, ipdb, pudb) are not imported on commit.
+    name: upgrade-your-pre-commit-version
-    entry: debug-statement-hook
+    entry: upgrade-your-pre-commit-version
-    language: python
+    files: ''
-    files: \.py$
+    minimum_pre_commit_version: 0.15.0
 -   id: detect-aws-credentials
-    name: Detect AWS Credentials
+    language: system
-    description: Detects *your* aws credentials from the aws cli credentials file
+    name: upgrade-your-pre-commit-version
-    entry: detect-aws-credentials
+    entry: upgrade-your-pre-commit-version
-    language: python
     files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: detect-private-key
-    name: Detect Private Key
+    language: system
-    description: Detects the presence of private keys
+    name: upgrade-your-pre-commit-version
-    entry: detect-private-key
+    entry: upgrade-your-pre-commit-version
-    language: python
     files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: double-quote-string-fixer
-    name: Fix double quoted strings
+    language: system
-    description: This hook replaces double quoted strings with single quoted strings
+    name: upgrade-your-pre-commit-version
-    entry: double-quote-string-fixer
+    entry: upgrade-your-pre-commit-version
-    language: python
-    files: \.py$
--   id: end-of-file-fixer
-    name: Fix End of Files
-    description: Ensures that a file is either empty, or ends with one newline.
-    entry: end-of-file-fixer
-    language: python
-    files: \.(asciidoc|adoc|coffee|cpp|css|c|ejs|erb|groovy|h|haml|hh|hpp|hxx|html|in|j2|jade|json|js|less|markdown|md|ml|mli|pp|py|rb|rs|R|scala|scss|sh|slim|tex|tmpl|ts|txt|yaml|yml)$
--   id: fix-encoding-pragma
-    name: Fix python encoding pragma
-    language: python
-    entry: fix-encoding-pragma
-    description: 'Add # -*- coding: utf-8 -*- to the top of python files'
-    files: \.py$
--   id: flake8
-    name: Flake8
-    description: This hook runs flake8.
-    entry: flake8
-    language: python
-    files: \.py$
--   id: forbid-new-submodules
-    name: Forbid new submodules
-    language: python
-    entry: forbid-new-submodules
-    description: Prevent addition of new git submodules
     files: ''
+    minimum_pre_commit_version: 0.15.0
+-   id: end-of-file-fixer
+    language: system
+    name: upgrade-your-pre-commit-version
+    entry: upgrade-your-pre-commit-version
+    files: ''
+    minimum_pre_commit_version: 0.15.0
+-   id: file-contents-sorter
+    language: system
+    name: upgrade-your-pre-commit-version
+    entry: upgrade-your-pre-commit-version
+    files: ''
+    minimum_pre_commit_version: 0.15.0
+-   id: fix-encoding-pragma
+    language: system
+    name: upgrade-your-pre-commit-version
+    entry: upgrade-your-pre-commit-version
+    files: ''
+    minimum_pre_commit_version: 0.15.0
+-   id: flake8
+    language: system
+    name: upgrade-your-pre-commit-version
+    entry: upgrade-your-pre-commit-version
+    files: ''
+    minimum_pre_commit_version: 0.15.0
+-   id: forbid-new-submodules
+    language: system
+    name: upgrade-your-pre-commit-version
+    entry: upgrade-your-pre-commit-version
+    files: ''
+    minimum_pre_commit_version: 0.15.0
+-   id: mixed-line-ending
+    language: system
+    name: upgrade-your-pre-commit-version
+    entry: upgrade-your-pre-commit-version
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: name-tests-test
-    name: Tests should end in _test.py
+    language: system
-    description: This verifies that test files are named correctly
+    name: upgrade-your-pre-commit-version
-    entry: name-tests-test
+    entry: upgrade-your-pre-commit-version
-    language: python
+    files: ''
-    files: tests/.+\.py$
+    minimum_pre_commit_version: 0.15.0
+-   id: no-commit-to-branch
+    language: system
+    name: upgrade-your-pre-commit-version
+    entry: upgrade-your-pre-commit-version
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: pyflakes
-    name: Pyflakes (DEPRECATED, use flake8)
+    language: system
-    description: This hook runs pyflakes. (This is deprecated, use flake8).
+    name: upgrade-your-pre-commit-version
-    entry: pyflakes
+    entry: upgrade-your-pre-commit-version
-    language: python
+    files: ''
-    files: \.py$
+    minimum_pre_commit_version: 0.15.0
 -   id: requirements-txt-fixer
-    name: Fix requirements.txt
+    language: system
-    description: Sorts entries in requirements.txt
+    name: upgrade-your-pre-commit-version
-    entry: requirements-txt-fixer
+    entry: upgrade-your-pre-commit-version
-    language: python
+    files: ''
-    files: requirements.*\.txt$
+    minimum_pre_commit_version: 0.15.0
+-   id: sort-simple-yaml
+    language: system
+    name: upgrade-your-pre-commit-version
+    entry: upgrade-your-pre-commit-version
+    files: ''
+    minimum_pre_commit_version: 0.15.0
 -   id: trailing-whitespace
-    name: Trim Trailing Whitespace
+    language: system
-    description: This hook trims trailing whitespace.
+    name: upgrade-your-pre-commit-version
-    entry: trailing-whitespace-fixer
+    entry: upgrade-your-pre-commit-version
-    language: python
+    files: ''
-    files: \.(asciidoc|adoc|coffee|cpp|css|c|ejs|erb|groovy|h|haml|hh|hpp|hxx|html|in|j2|jade|json|js|less|markdown|md|ml|mli|pp|py|rb|rs|R|scala|scss|sh|slim|tex|tmpl|ts|txt|yaml|yml)$
+    minimum_pre_commit_version: 0.15.0

pre_commit_hooks/autopep8_wrapper.py

@@ -14,12 +14,12 @@ def main(argv=None):
 
     retv = 0
     for filename in args.files:
-        original_contents = io.open(filename).read()
+        original_contents = io.open(filename, encoding='UTF-8').read()
         new_contents = autopep8.fix_code(original_contents, args)
         if original_contents != new_contents:
-            print('Fixing {0}'.format(filename))
+            print('Fixing {}'.format(filename))
             retv = 1
-            with io.open(filename, 'w') as output_file:
+            with io.open(filename, 'w', encoding='UTF-8') as output_file:
                 output_file.write(new_contents)
 
     return retv

pre_commit_hooks/check_added_large_files.py

@@ -4,6 +4,7 @@ from __future__ import print_function
 from __future__ import unicode_literals
 
 import argparse
+import json
 import math
 import os
 
@@ -13,23 +14,13 @@ from pre_commit_hooks.util import cmd_output
 
 
 def lfs_files():
-    try:  # pragma: no cover (no git-lfs)
+    try:
-        lines = cmd_output('git', 'lfs', 'status', '--porcelain').splitlines()
+        # Introduced in git-lfs 2.2.0, first working in 2.2.1
+        lfs_ret = cmd_output('git', 'lfs', 'status', '--json')
     except CalledProcessError:  # pragma: no cover (with git-lfs)
-        lines = []
+        lfs_ret = '{"files":{}}'
 
-    modes_and_fileparts = [
+    return set(json.loads(lfs_ret)['files'])
-        (line[:3].strip(), line[3:].rpartition(' ')[0]) for line in lines
-    ]
-
-    def to_file_part(mode, filepart):  # pragma: no cover (no git-lfs)
-        assert mode in ('A', 'R')
-        return filepart if mode == 'A' else filepart.split(' -> ')[1]
-
-    return set(
-        to_file_part(mode, filepart) for mode, filepart in modes_and_fileparts
-        if mode in ('A', 'R')
-    )
 
 
 def find_large_added_files(filenames, maxkb):
@@ -41,7 +32,7 @@ def find_large_added_files(filenames, maxkb):
     for filename in filenames:
         kb = int(math.ceil(os.stat(filename).st_size / 1024))
         if kb > maxkb:
-            print('{0} ({1} KB) exceeds {2} KB.'.format(filename, kb, maxkb))
+            print('{} ({} KB) exceeds {} KB.'.format(filename, kb, maxkb))
             retv = 1
 
     return retv
@@ -51,7 +42,7 @@ def main(argv=None):
     parser = argparse.ArgumentParser()
     parser.add_argument(
         'filenames', nargs='*',
-        help='Filenames pre-commit believes are changed.'
+        help='Filenames pre-commit believes are changed.',
     )
     parser.add_argument(
         '--maxkb', type=int, default=500,

pre_commit_hooks/check_ast.py

@@ -4,7 +4,7 @@ from __future__ import unicode_literals
 
 import argparse
 import ast
-import os.path
+import platform
 import sys
 import traceback
 
@@ -14,19 +14,19 @@ def check_ast(argv=None):
     parser.add_argument('filenames', nargs='*')
     args = parser.parse_args(argv)
 
-    _, interpreter = os.path.split(sys.executable)
-
     retval = 0
     for filename in args.filenames:
 
         try:
             ast.parse(open(filename, 'rb').read(), filename=filename)
         except SyntaxError:
-            print('{0}: failed parsing with {1}:'.format(
+            print('{}: failed parsing with {} {}:'.format(
-                filename, interpreter,
+                filename,
+                platform.python_implementation(),
+                sys.version.partition(' ')[0],
             ))
-            print('\n{0}'.format(
+            print('\n{}'.format(
-                '    ' + traceback.format_exc().replace('\n', '\n    ')
+                '    ' + traceback.format_exc().replace('\n', '\n    '),
             ))
             retval = 1
     return retval

pre_commit_hooks/check_builtin_literals.py

@@ -0,0 +1,95 @@
+from __future__ import unicode_literals
+
+import argparse
+import ast
+import collections
+import sys
+
+
+BUILTIN_TYPES = {
+    'complex': '0j',
+    'dict': '{}',
+    'float': '0.0',
+    'int': '0',
+    'list': '[]',
+    'str': "''",
+    'tuple': '()',
+}
+
+
+BuiltinTypeCall = collections.namedtuple('BuiltinTypeCall', ['name', 'line', 'column'])
+
+
+class BuiltinTypeVisitor(ast.NodeVisitor):
+    def __init__(self, ignore=None, allow_dict_kwargs=True):
+        self.builtin_type_calls = []
+        self.ignore = set(ignore) if ignore else set()
+        self.allow_dict_kwargs = allow_dict_kwargs
+
+    def _check_dict_call(self, node):
+        return self.allow_dict_kwargs and (getattr(node, 'kwargs', None) or getattr(node, 'keywords', None))
+
+    def visit_Call(self, node):
+        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.
+            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(
+            BuiltinTypeCall(node.func.id, node.lineno, node.col_offset),
+        )
+
+
+def check_file_for_builtin_type_constructors(filename, ignore=None, allow_dict_kwargs=True):
+    tree = ast.parse(open(filename, 'rb').read(), filename=filename)
+    visitor = BuiltinTypeVisitor(ignore=ignore, allow_dict_kwargs=allow_dict_kwargs)
+    visitor.visit(tree)
+    return visitor.builtin_type_calls
+
+
+def parse_args(argv):
+    def parse_ignore(value):
+        return set(value.split(','))
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument('filenames', nargs='*')
+    parser.add_argument('--ignore', type=parse_ignore, default=set())
+
+    allow_dict_kwargs = parser.add_mutually_exclusive_group(required=False)
+    allow_dict_kwargs.add_argument('--allow-dict-kwargs', action='store_true')
+    allow_dict_kwargs.add_argument('--no-allow-dict-kwargs', dest='allow_dict_kwargs', action='store_false')
+    allow_dict_kwargs.set_defaults(allow_dict_kwargs=True)
+
+    return parser.parse_args(argv)
+
+
+def main(argv=None):
+    args = parse_args(argv)
+    rc = 0
+    for filename in args.filenames:
+        calls = check_file_for_builtin_type_constructors(
+            filename,
+            ignore=args.ignore,
+            allow_dict_kwargs=args.allow_dict_kwargs,
+        )
+        if calls:
+            rc = rc or 1
+        for call in calls:
+            print(
+                '{filename}:{call.line}:{call.column} - Replace {call.name}() with {replacement}'.format(
+                    filename=filename,
+                    call=call,
+                    replacement=BUILTIN_TYPES[call.name],
+                ),
+            )
+    return rc
+
+
+if __name__ == '__main__':
+    sys.exit(main())

pre_commit_hooks/check_byte_order_marker.py

@@ -16,7 +16,7 @@ def main(argv=None):
         with open(filename, 'rb') as f:
             if f.read(3) == b'\xef\xbb\xbf':
                 retv = 1
-                print('{0}: Has a byte-order marker'.format(filename))
+                print('{}: Has a byte-order marker'.format(filename))
 
     return retv
 

pre_commit_hooks/check_case_conflict.py

@@ -9,7 +9,7 @@ from pre_commit_hooks.util import cmd_output
 
 
 def lower_set(iterable):
-    return set(x.lower() for x in iterable)
+    return {x.lower() for x in iterable}
 
 
 def find_conflicting_filenames(filenames):
@@ -35,7 +35,7 @@ def find_conflicting_filenames(filenames):
             if x.lower() in conflicts
         ]
         for filename in sorted(conflicting_files):
-            print('Case-insensitivity conflict found: {0}'.format(filename))
+            print('Case-insensitivity conflict found: {}'.format(filename))
         retv = 1
 
     return retv
@@ -45,7 +45,7 @@ def main(argv=None):
     parser = argparse.ArgumentParser()
     parser.add_argument(
         'filenames', nargs='*',
-        help='Filenames pre-commit believes are changed.'
+        help='Filenames pre-commit believes are changed.',
     )
 
     args = parser.parse_args(argv)

pre_commit_hooks/check_docstring_first.py

@@ -1,4 +1,5 @@
 from __future__ import absolute_import
+from __future__ import print_function
 from __future__ import unicode_literals
 
 import argparse
@@ -27,18 +28,18 @@ def check_docstring_first(src, filename='<unknown>'):
         if tok_type == tokenize.STRING and scol == 0:
             if found_docstring_line is not None:
                 print(
-                    '{0}:{1} Multiple module docstrings '
+                    '{}:{} Multiple module docstrings '
-                    '(first docstring on line {2}).'.format(
+                    '(first docstring on line {}).'.format(
                         filename, sline, found_docstring_line,
-                    )
+                    ),
                 )
                 return 1
             elif found_code_line is not None:
                 print(
-                    '{0}:{1} Module docstring appears after code '
+                    '{}:{} Module docstring appears after code '
-                    '(code seen on line {2}).'.format(
+                    '(code seen on line {}).'.format(
                         filename, sline, found_code_line,
-                    )
+                    ),
                 )
                 return 1
             else:
@@ -57,7 +58,7 @@ def main(argv=None):
     retv = 0
 
     for filename in args.filenames:
-        contents = io.open(filename).read()
+        contents = io.open(filename, encoding='UTF-8').read()
         retv |= check_docstring_first(contents, filename=filename)
 
     return retv

pre_commit_hooks/check_executables_have_shebangs.py

@@ -0,0 +1,40 @@
+"""Check that executable text files have a shebang."""
+from __future__ import absolute_import
+from __future__ import print_function
+from __future__ import unicode_literals
+
+import argparse
+import pipes
+import sys
+
+
+def check_has_shebang(path):
+    with open(path, 'rb') as f:
+        first_bytes = f.read(2)
+
+    if first_bytes != b'#!':
+        print(
+            '{path}: marked executable but has no (or invalid) shebang!\n'
+            "  If it isn't supposed to be executable, try: chmod -x {quoted}\n"
+            '  If it is supposed to be executable, double-check its shebang.'.format(
+                path=path,
+                quoted=pipes.quote(path),
+            ),
+            file=sys.stderr,
+        )
+        return 1
+    else:
+        return 0
+
+
+def main(argv=None):
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument('filenames', nargs='*')
+    args = parser.parse_args(argv)
+
+    retv = 0
+
+    for filename in args.filenames:
+        retv |= check_has_shebang(filename)
+
+    return retv

pre_commit_hooks/check_json.py

@@ -1,10 +1,10 @@
 from __future__ import print_function
 
 import argparse
+import io
+import json
 import sys
 
-import simplejson
-
 
 def check_json(argv=None):
     parser = argparse.ArgumentParser()
@@ -14,9 +14,9 @@ def check_json(argv=None):
     retval = 0
     for filename in args.filenames:
         try:
-            simplejson.load(open(filename))
+            json.load(io.open(filename, encoding='UTF-8'))
-        except (simplejson.JSONDecodeError, UnicodeDecodeError) as exc:
+        except (ValueError, UnicodeDecodeError) as exc:
-            print('{0}: Failed to json decode ({1})'.format(filename, exc))
+            print('{}: Failed to json decode ({})'.format(filename, exc))
             retval = 1
     return retval
 

pre_commit_hooks/check_merge_conflict.py

@@ -7,7 +7,7 @@ CONFLICT_PATTERNS = [
     b'<<<<<<< ',
     b'======= ',
     b'=======\n',
-    b'>>>>>>> '
+    b'>>>>>>> ',
 ]
 WARNING_MSG = 'Merge conflict string "{0}" found in {1}:{2}'
 
@@ -15,7 +15,11 @@ WARNING_MSG = 'Merge conflict string "{0}" found in {1}:{2}'
 def is_in_merge():
     return (
         os.path.exists(os.path.join('.git', 'MERGE_MSG')) and
-        os.path.exists(os.path.join('.git', 'MERGE_HEAD'))
+        (
+            os.path.exists(os.path.join('.git', 'MERGE_HEAD')) or
+            os.path.exists(os.path.join('.git', 'rebase-apply')) or
+            os.path.exists(os.path.join('.git', 'rebase-merge'))
+        )
     )
 
 

pre_commit_hooks/check_symlinks.py

@@ -19,7 +19,7 @@ def check_symlinks(argv=None):
                 os.path.islink(filename) and
                 not os.path.exists(filename)
         ):  # pragma: no cover (symlink support required)
-            print('{0}: Broken symlink'.format(filename))
+            print('{}: Broken symlink'.format(filename))
             retv = 1
 
     return retv

pre_commit_hooks/check_vcs_permalinks.py

@@ -0,0 +1,44 @@
+from __future__ import absolute_import
+from __future__ import print_function
+from __future__ import unicode_literals
+
+import argparse
+import re
+import sys
+
+
+GITHUB_NON_PERMALINK = re.compile(
+    b'https://github.com/[^/ ]+/[^/ ]+/blob/master/[^# ]+#L\d+',
+)
+
+
+def _check_filename(filename):
+    retv = 0
+    with open(filename, 'rb') as f:
+        for i, line in enumerate(f, 1):
+            if GITHUB_NON_PERMALINK.search(line):
+                sys.stdout.write('{}:{}:'.format(filename, i))
+                sys.stdout.flush()
+                getattr(sys.stdout, 'buffer', sys.stdout).write(line)
+                retv = 1
+    return retv
+
+
+def main(argv=None):
+    parser = argparse.ArgumentParser()
+    parser.add_argument('filenames', nargs='*')
+    args = parser.parse_args(argv)
+
+    retv = 0
+    for filename in args.filenames:
+        retv |= _check_filename(filename)
+
+    if retv:
+        print()
+        print('Non-permanent github link detected.')
+        print('On any page on github press [y] to load a permalink.')
+    return retv
+
+
+if __name__ == '__main__':
+    exit(main())

pre_commit_hooks/check_xml.py

@@ -19,7 +19,7 @@ def check_xml(argv=None):
             with io.open(filename, 'rb') as xml_file:
                 xml.sax.parse(xml_file, xml.sax.ContentHandler())
         except xml.sax.SAXException as exc:
-            print('{0}: Failed to xml parse ({1})'.format(filename, exc))
+            print('{}: Failed to xml parse ({})'.format(filename, exc))
             retval = 1
     return retval
 

pre_commit_hooks/check_yaml.py

@@ -1,6 +1,7 @@
 from __future__ import print_function
 
 import argparse
+import collections
 import sys
 
 import yaml
@@ -11,21 +12,57 @@ except ImportError:  # pragma: no cover (no libyaml-dev / pypy)
     Loader = yaml.SafeLoader
 
 
+def _exhaust(gen):
+    for _ in gen:
+        pass
+
+
+def _parse_unsafe(*args, **kwargs):
+    _exhaust(yaml.parse(*args, **kwargs))
+
+
+def _load_all(*args, **kwargs):
+    _exhaust(yaml.load_all(*args, **kwargs))
+
+
+Key = collections.namedtuple('Key', ('multi', 'unsafe'))
+LOAD_FNS = {
+    Key(multi=False, unsafe=False): yaml.load,
+    Key(multi=False, unsafe=True): _parse_unsafe,
+    Key(multi=True, unsafe=False): _load_all,
+    Key(multi=True, unsafe=True): _parse_unsafe,
+}
+
+
 def check_yaml(argv=None):
     parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '-m', '--multi', '--allow-multiple-documents', action='store_true',
+    )
+    parser.add_argument(
+        '--unsafe', action='store_true',
+        help=(
+            'Instead of loading the files, simply parse them for syntax.  '
+            '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'
+        ),
+    )
     parser.add_argument('--ignore-tags', type=lambda s: s.split(','), default=[],
                         help='Custom tags to ignore.')
     parser.add_argument('filenames', nargs='*', help='Yaml filenames to check.')
     args = parser.parse_args(argv)
 
-    # Ignore custom tags by returning None
     for tag in args.ignore_tags:
         Loader.add_constructor(tag, lambda *a, **k: None)
 
+    load_fn = LOAD_FNS[Key(multi=args.multi, unsafe=args.unsafe)]
+
     retval = 0
     for filename in args.filenames:
         try:
-            yaml.load(open(filename), Loader=Loader)
+            load_fn(open(filename), Loader=Loader)
         except yaml.YAMLError as exc:
             print(exc)
             retval = 1

pre_commit_hooks/debug_statement_hook.py

@@ -7,69 +7,66 @@ import collections
 import traceback
 
 
-DEBUG_STATEMENTS = set(['pdb', 'ipdb', 'pudb', 'q', 'rdb'])
+DEBUG_STATEMENTS = {'pdb', 'ipdb', 'pudb', 'q', 'rdb'}
+Debug = collections.namedtuple('Debug', ('line', 'col', 'name', 'reason'))
 
 
-DebugStatement = collections.namedtuple(
+class DebugStatementParser(ast.NodeVisitor):
-    'DebugStatement', ['name', 'line', 'col'],
-)
-
-
-class ImportStatementParser(ast.NodeVisitor):
     def __init__(self):
-        self.debug_import_statements = []
+        self.breakpoints = []
 
     def visit_Import(self, node):
-        for node_name in node.names:
+        for name in node.names:
-            if node_name.name in DEBUG_STATEMENTS:
+            if name.name in DEBUG_STATEMENTS:
-                self.debug_import_statements.append(
+                st = Debug(node.lineno, node.col_offset, name.name, 'imported')
-                    DebugStatement(node_name.name, node.lineno, node.col_offset),
+                self.breakpoints.append(st)
-                )
 
     def visit_ImportFrom(self, node):
         if node.module in DEBUG_STATEMENTS:
-            self.debug_import_statements.append(
+            st = Debug(node.lineno, node.col_offset, node.module, 'imported')
-                DebugStatement(node.module, node.lineno, node.col_offset)
+            self.breakpoints.append(st)
-            )
+
+    def visit_Call(self, node):
+        """python3.7+ breakpoint()"""
+        if isinstance(node.func, ast.Name) and node.func.id == 'breakpoint':
+            st = Debug(node.lineno, node.col_offset, node.func.id, 'called')
+            self.breakpoints.append(st)
+        self.generic_visit(node)
 
 
-def check_file_for_debug_statements(filename):
+def check_file(filename):
     try:
-        ast_obj = ast.parse(open(filename).read(), filename=filename)
+        ast_obj = ast.parse(open(filename, 'rb').read(), filename=filename)
     except SyntaxError:
-        print('{0} - Could not parse ast'.format(filename))
+        print('{} - Could not parse ast'.format(filename))
         print()
         print('\t' + traceback.format_exc().replace('\n', '\n\t'))
         print()
         return 1
-    visitor = ImportStatementParser()
+
+    visitor = DebugStatementParser()
     visitor.visit(ast_obj)
-    if visitor.debug_import_statements:
+
-        for debug_statement in visitor.debug_import_statements:
+    for bp in visitor.breakpoints:
-            print(
+        print(
-                '{0}:{1}:{2} - {3} imported'.format(
+            '{}:{}:{} - {} {}'.format(
-                    filename,
+                filename, bp.line, bp.col, bp.name, bp.reason,
-                    debug_statement.line,
+            ),
-                    debug_statement.col,
+        )
-                    debug_statement.name,
+
-                )
+    return int(bool(visitor.breakpoints))
-            )
-        return 1
-    else:
-        return 0
 
 
-def debug_statement_hook(argv=None):
+def main(argv=None):
     parser = argparse.ArgumentParser()
     parser.add_argument('filenames', nargs='*', help='Filenames to run')
     args = parser.parse_args(argv)
 
     retv = 0
     for filename in args.filenames:
-        retv |= check_file_for_debug_statements(filename)
+        retv |= check_file(filename)
-
     return retv
 
 
 if __name__ == '__main__':
-    exit(debug_statement_hook())
+    exit(main())

pre_commit_hooks/detect_aws_credentials.py

@@ -12,7 +12,7 @@ def get_aws_credential_files_from_env():
     files = set()
     for env_var in (
         'AWS_CONFIG_FILE', 'AWS_CREDENTIAL_FILE', 'AWS_SHARED_CREDENTIALS_FILE',
-        'BOTO_CONFIG'
+        'BOTO_CONFIG',
     ):
         if env_var in os.environ:
             files.add(os.environ[env_var])
@@ -23,7 +23,7 @@ def get_aws_secrets_from_env():
     """Extract AWS secrets from environment variables."""
     keys = set()
     for env_var in (
-        'AWS_SECRET_ACCESS_KEY', 'AWS_SECURITY_TOKEN', 'AWS_SESSION_TOKEN'
+        'AWS_SECRET_ACCESS_KEY', 'AWS_SECURITY_TOKEN', 'AWS_SESSION_TOKEN',
     ):
         if env_var in os.environ:
             keys.add(os.environ[env_var])
@@ -50,10 +50,12 @@ def get_aws_secrets_from_file(credentials_file):
     for section in parser.sections():
         for var in (
             'aws_secret_access_key', 'aws_security_token',
-            'aws_session_token'
+            'aws_session_token',
         ):
             try:
-                keys.add(parser.get(section, var))
+                key = parser.get(section, var).strip()
+                if key:
+                    keys.add(key)
             except configparser.NoOptionError:
                 pass
     return keys
@@ -93,13 +95,13 @@ def main(argv=None):
         help=(
             'Location of additional AWS credential files from which to get '
             'secret keys from'
-        )
+        ),
     )
     parser.add_argument(
         '--allow-missing-credentials',
         dest='allow_missing_credentials',
         action='store_true',
-        help='Allow hook to pass when no credentials are detected.'
+        help='Allow hook to pass when no credentials are detected.',
     )
     args = parser.parse_args(argv)
 
@@ -124,7 +126,7 @@ def main(argv=None):
         print(
             'No AWS keys were found in the configured credential files and '
             'environment variables.\nPlease ensure you have the correct '
-            'setting for --credentials-file'
+            'setting for --credentials-file',
         )
         return 2
 

pre_commit_hooks/detect_private_key.py

@@ -8,6 +8,9 @@ BLACKLIST = [
     b'BEGIN DSA PRIVATE KEY',
     b'BEGIN EC PRIVATE KEY',
     b'BEGIN OPENSSH PRIVATE KEY',
+    b'BEGIN PRIVATE KEY',
+    b'PuTTY-User-Key-File-2',
+    b'BEGIN SSH2 ENCRYPTED PRIVATE KEY',
 ]
 
 
@@ -26,7 +29,7 @@ def detect_private_key(argv=None):
 
     if private_key_files:
         for private_key_file in private_key_files:
-            print('Private key found: {0}'.format(private_key_file))
+            print('Private key found: {}'.format(private_key_file))
         return 1
     else:
         return 0

pre_commit_hooks/end_of_file_fixer.py

@@ -58,7 +58,7 @@ def end_of_file_fixer(argv=None):
         with open(filename, 'rb+') as file_obj:
             ret_for_file = fix_file(file_obj)
             if ret_for_file:
-                print('Fixing {0}'.format(filename))
+                print('Fixing {}'.format(filename))
             retv |= ret_for_file
 
     return retv

pre_commit_hooks/file_contents_sorter.py

@@ -0,0 +1,52 @@
+"""
+A very simple pre-commit hook that, when passed one or more filenames
+as arguments, will sort the lines in those files.
+
+An example use case for this: you have a deploy-whitelist.txt file
+in a repo that contains a list of filenames that is used to specify
+files to be included in a docker container. This file has one filename
+per line. Various users are adding/removing lines from this file; using
+this hook on that file should reduce the instances of git merge
+conflicts and keep the file nicely ordered.
+"""
+from __future__ import print_function
+
+import argparse
+
+PASS = 0
+FAIL = 1
+
+
+def sort_file_contents(f):
+    before = list(f)
+    after = sorted([line.strip(b'\n\r') for line in before if line.strip()])
+
+    before_string = b''.join(before)
+    after_string = b'\n'.join(after) + b'\n'
+
+    if before_string == after_string:
+        return PASS
+    else:
+        f.seek(0)
+        f.write(after_string)
+        f.truncate()
+        return FAIL
+
+
+def main(argv=None):
+    parser = argparse.ArgumentParser()
+    parser.add_argument('filenames', nargs='+', help='Files to sort')
+    args = parser.parse_args(argv)
+
+    retv = PASS
+
+    for arg in args.filenames:
+        with open(arg, 'rb+') as file_obj:
+            ret_for_file = sort_file_contents(file_obj)
+
+            if ret_for_file:
+                print('Sorting {}'.format(arg))
+
+            retv |= ret_for_file
+
+    return retv

pre_commit_hooks/mixed_line_ending.py

@@ -0,0 +1,84 @@
+from __future__ import absolute_import
+from __future__ import print_function
+from __future__ import unicode_literals
+
+import argparse
+import collections
+
+
+CRLF = b'\r\n'
+LF = b'\n'
+CR = b'\r'
+# Prefer LF to CRLF to CR, but detect CRLF before LF
+ALL_ENDINGS = (CR, CRLF, LF)
+FIX_TO_LINE_ENDING = {'cr': CR, 'crlf': CRLF, 'lf': LF}
+
+
+def _fix(filename, contents, ending):
+    new_contents = b''.join(
+        line.rstrip(b'\r\n') + ending for line in contents.splitlines(True)
+    )
+    with open(filename, 'wb') as f:
+        f.write(new_contents)
+
+
+def fix_filename(filename, fix):
+    with open(filename, 'rb') as f:
+        contents = f.read()
+
+    counts = collections.defaultdict(int)
+
+    for line in contents.splitlines(True):
+        for ending in ALL_ENDINGS:
+            if line.endswith(ending):
+                counts[ending] += 1
+                break
+
+    # Some amount of mixed line endings
+    mixed = sum(bool(x) for x in counts.values()) > 1
+
+    if fix == 'no' or (fix == 'auto' and not mixed):
+        return mixed
+
+    if fix == 'auto':
+        max_ending = LF
+        max_lines = 0
+        # ordering is important here such that lf > crlf > cr
+        for ending_type in ALL_ENDINGS:
+            # also important, using >= to find a max that prefers the last
+            if counts[ending_type] >= max_lines:
+                max_ending = ending_type
+                max_lines = counts[ending_type]
+
+        _fix(filename, contents, max_ending)
+        return 1
+    else:
+        target_ending = FIX_TO_LINE_ENDING[fix]
+        # find if there are lines with *other* endings
+        # It's possible there's no line endings of the target type
+        counts.pop(target_ending, None)
+        other_endings = bool(sum(counts.values()))
+        if other_endings:
+            _fix(filename, contents, target_ending)
+        return other_endings
+
+
+def main(argv=None):
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '-f', '--fix',
+        choices=('auto', 'no') + tuple(FIX_TO_LINE_ENDING),
+        default='auto',
+        help='Replace line ending with the specified. Default is "auto"',
+    )
+    parser.add_argument('filenames', nargs='*', help='Filenames to fix')
+    args = parser.parse_args(argv)
+
+    retv = 0
+    for filename in args.filenames:
+        retv |= fix_filename(filename, args.fix)
+    return retv
+
+
+if __name__ == '__main__':
+    exit(main())

pre_commit_hooks/no_commit_to_branch.py

@@ -0,0 +1,31 @@
+from __future__ import print_function
+
+import argparse
+
+from pre_commit_hooks.util import CalledProcessError
+from pre_commit_hooks.util import cmd_output
+
+
+def is_on_branch(protected):
+    try:
+        branch = cmd_output('git', 'symbolic-ref', 'HEAD')
+    except CalledProcessError:
+        return False
+    chunks = branch.strip().split('/')
+    return '/'.join(chunks[2:]) in protected
+
+
+def main(argv=None):
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '-b', '--branch', action='append',
+        help='branch to disallow commits to, may be specified multiple times',
+    )
+    args = parser.parse_args(argv)
+
+    protected = set(args.branch or ('master',))
+    return int(is_on_branch(protected))
+
+
+if __name__ == '__main__':
+    exit(main())

pre_commit_hooks/pretty_format_json.py

@@ -1,13 +1,15 @@
 from __future__ import print_function
 
 import argparse
+import io
+import json
 import sys
 from collections import OrderedDict
 
-import simplejson
+from six import text_type
 
 
-def _get_pretty_format(contents, indent, sort_keys=True, top_keys=[]):
+def _get_pretty_format(contents, indent, ensure_ascii=True, sort_keys=True, top_keys=[]):
     def pairs_first(pairs):
         before = [pair for pair in pairs if pair[0] in top_keys]
         before = sorted(before, key=lambda x: top_keys.index(x[0]))
@@ -15,39 +17,28 @@ def _get_pretty_format(contents, indent, sort_keys=True, top_keys=[]):
         if sort_keys:
             after = sorted(after, key=lambda x: x[0])
         return OrderedDict(before + after)
-    return simplejson.dumps(
+    json_pretty = json.dumps(
-        simplejson.loads(
+        json.loads(contents, object_pairs_hook=pairs_first),
-            contents,
+        indent=indent,
-            object_pairs_hook=pairs_first,
+        ensure_ascii=ensure_ascii,
-        ),
+        separators=(',', ': '),  # Workaround for https://bugs.python.org/issue16333
-        indent=indent
+    )
-    ) + "\n"  # dumps don't end with a newline
+    # Ensure unicode (Py2) and add the newline that dumps does not end with.
+    return text_type(json_pretty) + '\n'
 
 
 def _autofix(filename, new_contents):
-    print("Fixing file {0}".format(filename))
+    print('Fixing file {}'.format(filename))
-    with open(filename, 'w') as f:
+    with io.open(filename, 'w', encoding='UTF-8') as f:
         f.write(new_contents)
 
 
-def parse_indent(s):
+def parse_num_to_int(s):
-    # type: (str) -> str
+    """Convert string numbers to int, leaving strings as is."""
     try:
-        int_indentation_spec = int(s)
+        return int(s)
     except ValueError:
-        if not s.strip():
+        return s
-            return s
-        else:
-            raise ValueError(
-                'Non-whitespace JSON indentation delimiter supplied. ',
-            )
-    else:
-        if int_indentation_spec >= 0:
-            return int_indentation_spec * ' '
-        else:
-            raise ValueError(
-                'Negative integer supplied to construct JSON indentation delimiter. ',
-            )
 
 
 def parse_topkeys(s):
@@ -65,9 +56,19 @@ def pretty_format_json(argv=None):
     )
     parser.add_argument(
         '--indent',
-        type=parse_indent,
+        type=parse_num_to_int,
-        default='  ',
+        default='2',
-        help='String used as delimiter for one indentation level',
+        help=(
+            'The number of indent spaces or a string to be used as delimiter'
+            ' for indentation level e.g. 4 or "\t" (Default: 2)'
+        ),
+    )
+    parser.add_argument(
+        '--no-ensure-ascii',
+        action='store_true',
+        dest='no_ensure_ascii',
+        default=False,
+        help='Do NOT convert non-ASCII characters to Unicode escape sequences (\\uXXXX)',
     )
     parser.add_argument(
         '--no-sort-keys',
@@ -90,27 +91,26 @@ def pretty_format_json(argv=None):
     status = 0
 
     for json_file in args.filenames:
-        with open(json_file) as f:
+        with io.open(json_file, encoding='UTF-8') as f:
             contents = f.read()
 
         try:
             pretty_contents = _get_pretty_format(
-                contents, args.indent, sort_keys=not args.no_sort_keys,
+                contents, args.indent, ensure_ascii=not args.no_ensure_ascii,
-                top_keys=args.top_keys
+                sort_keys=not args.no_sort_keys, top_keys=args.top_keys,
             )
 
             if contents != pretty_contents:
-                print("File {0} is not pretty-formatted".format(json_file))
+                print('File {} is not pretty-formatted'.format(json_file))
 
                 if args.autofix:
                     _autofix(json_file, pretty_contents)
 
                 status = 1
-
+        except ValueError:
-        except simplejson.JSONDecodeError:
             print(
-                "Input File {0} is not a valid JSON, consider using check-json"
+                'Input File {} is not a valid JSON, consider using check-json'
-                .format(json_file)
+                .format(json_file),
             )
             return 1
 

pre_commit_hooks/requirements_txt_fixer.py

@@ -3,6 +3,10 @@ from __future__ import print_function
 import argparse
 
 
+PASS = 0
+FAIL = 1
+
+
 class Requirement(object):
 
     def __init__(self):
@@ -30,21 +34,25 @@ class Requirement(object):
 
 def fix_requirements(f):
     requirements = []
-    before = []
+    before = tuple(f)
     after = []
 
-    for line in f:
+    before_string = b''.join(before)
-        before.append(line)
 
-        # If the most recent requirement object has a value, then it's time to
+    # If the file is empty (i.e. only whitespace/newlines) exit early
-        # start building the next requirement object.
+    if before_string.strip() == b'':
+        return PASS
+
+    for line in before:
+        # If the most recent requirement object has a value, then it's
+        # time to start building the next requirement object.
         if not len(requirements) or requirements[-1].value is not None:
             requirements.append(Requirement())
 
         requirement = requirements[-1]
 
-        # If we see a newline before any requirements, then this is a top of
+        # If we see a newline before any requirements, then this is a
-        # file comment.
+        # top of file comment.
         if len(requirements) == 1 and line.strip() == b'':
             if len(requirement.comments) and requirement.comments[0].startswith(b'#'):
                 requirement.value = b'\n'
@@ -55,21 +63,33 @@ def fix_requirements(f):
         else:
             requirement.value = line
 
-    for requirement in sorted(requirements):
+    # if a file ends in a comment, preserve it at the end
-        for comment in requirement.comments:
+    if requirements[-1].value is None:
-            after.append(comment)
+        rest = requirements.pop().comments
-        after.append(requirement.value)
+    else:
+        rest = []
+
+    # find and remove pkg-resources==0.0.0
+    # which is automatically added by broken pip package under Debian
+    requirements = [
+        req for req in requirements
+        if req.value != b'pkg-resources==0.0.0\n'
+    ]
+
+    for requirement in sorted(requirements):
+        after.extend(requirement.comments)
+        after.append(requirement.value)
+    after.extend(rest)
 
-    before_string = b''.join(before)
     after_string = b''.join(after)
 
     if before_string == after_string:
-        return 0
+        return PASS
     else:
         f.seek(0)
         f.write(after_string)
         f.truncate()
-        return 1
+        return FAIL
 
 
 def fix_requirements_txt(argv=None):
@@ -77,14 +97,14 @@ def fix_requirements_txt(argv=None):
     parser.add_argument('filenames', nargs='*', help='Filenames to fix')
     args = parser.parse_args(argv)
 
-    retv = 0
+    retv = PASS
 
     for arg in args.filenames:
         with open(arg, 'rb+') as file_obj:
             ret_for_file = fix_requirements(file_obj)
 
             if ret_for_file:
-                print('Sorting {0}'.format(arg))
+                print('Sorting {}'.format(arg))
 
             retv |= ret_for_file
 

pre_commit_hooks/sort_simple_yaml.py

@@ -0,0 +1,123 @@
+#!/usr/bin/env python
+"""Sort a simple YAML file, keeping blocks of comments and definitions
+together.
+
+We assume a strict subset of YAML that looks like:
+
+    # block of header comments
+    # here that should always
+    # be at the top of the file
+
+    # optional comments
+    # can go here
+    key: value
+    key: value
+
+    key: value
+
+In other words, we don't sort deeper than the top layer, and might corrupt
+complicated YAML files.
+"""
+from __future__ import print_function
+
+import argparse
+
+
+QUOTES = ["'", '"']
+
+
+def sort(lines):
+    """Sort a YAML file in alphabetical order, keeping blocks together.
+
+    :param lines: array of strings (without newlines)
+    :return: sorted array of strings
+    """
+    # make a copy of lines since we will clobber it
+    lines = list(lines)
+    new_lines = parse_block(lines, header=True)
+
+    for block in sorted(parse_blocks(lines), key=first_key):
+        if new_lines:
+            new_lines.append('')
+        new_lines.extend(block)
+
+    return new_lines
+
+
+def parse_block(lines, header=False):
+    """Parse and return a single block, popping off the start of `lines`.
+
+    If parsing a header block, we stop after we reach a line that is not a
+    comment. Otherwise, we stop after reaching an empty line.
+
+    :param lines: list of lines
+    :param header: whether we are parsing a header block
+    :return: list of lines that form the single block
+    """
+    block_lines = []
+    while lines and lines[0] and (not header or lines[0].startswith('#')):
+        block_lines.append(lines.pop(0))
+    return block_lines
+
+
+def parse_blocks(lines):
+    """Parse and return all possible blocks, popping off the start of `lines`.
+
+    :param lines: list of lines
+    :return: list of blocks, where each block is a list of lines
+    """
+    blocks = []
+
+    while lines:
+        if lines[0] == '':
+            lines.pop(0)
+        else:
+            blocks.append(parse_block(lines))
+
+    return blocks
+
+
+def first_key(lines):
+    """Returns a string representing the sort key of a block.
+
+    The sort key is the first YAML key we encounter, ignoring comments, and
+    stripping leading quotes.
+
+    >>> print(test)
+    # some comment
+    'foo': true
+    >>> first_key(test)
+    'foo'
+    """
+    for line in lines:
+        if line.startswith('#'):
+            continue
+        if any(line.startswith(quote) for quote in QUOTES):
+            return line[1:]
+        return line
+
+
+def main(argv=None):
+    parser = argparse.ArgumentParser()
+    parser.add_argument('filenames', nargs='*', help='Filenames to fix')
+    args = parser.parse_args(argv)
+
+    retval = 0
+
+    for filename in args.filenames:
+        with open(filename, 'r+') as f:
+            lines = [line.rstrip() for line in f.readlines()]
+            new_lines = sort(lines)
+
+            if lines != new_lines:
+                print("Fixing file `{filename}`".format(filename=filename))
+                f.seek(0)
+                f.write("\n".join(new_lines) + "\n")
+                f.truncate()
+                retval = 1
+
+    return retval
+
+
+if __name__ == '__main__':
+    exit(main())

pre_commit_hooks/string_fixer.py

@@ -32,7 +32,7 @@ def get_line_offsets_by_line_no(src):
 
 
 def fix_strings(filename):
-    contents = io.open(filename).read()
+    contents = io.open(filename, encoding='UTF-8').read()
     line_offsets = get_line_offsets_by_line_no(contents)
 
     # Basically a mutable string
@@ -52,7 +52,7 @@ def fix_strings(filename):
 
     new_contents = ''.join(splitcontents)
     if contents != new_contents:
-        with io.open(filename, 'w') as write_handle:
+        with io.open(filename, 'w', encoding='UTF-8') as write_handle:
             write_handle.write(new_contents)
         return 1
     else:
@@ -69,7 +69,7 @@ def main(argv=None):
     for filename in args.filenames:
         return_value = fix_strings(filename)
         if return_value != 0:
-            print('Fixing strings in {0}'.format(filename))
+            print('Fixing strings in {}'.format(filename))
         retv |= return_value
 
     return retv

pre_commit_hooks/tests_should_end_in_test.py

@@ -11,12 +11,12 @@ def validate_files(argv=None):
     parser.add_argument('filenames', nargs='*')
     parser.add_argument(
         '--django', default=False, action='store_true',
-        help='Use Django-style test naming pattern (test*.py)'
+        help='Use Django-style test naming pattern (test*.py)',
     )
     args = parser.parse_args(argv)
 
     retcode = 0
-    test_name_pattern = 'test_.*.py' if args.django else '.*_test.py'
+    test_name_pattern = 'test.*.py' if args.django else '.*_test.py'
     for filename in args.filenames:
         base = basename(filename)
         if (
@@ -26,9 +26,9 @@ def validate_files(argv=None):
         ):
             retcode = 1
             print(
-                '{0} does not match pattern "{1}"'.format(
+                '{} does not match pattern "{}"'.format(
-                    filename, test_name_pattern
+                    filename, test_name_pattern,
-                )
+                ),
             )
 
     return retcode

pre_commit_hooks/trailing_whitespace_fixer.py

@@ -4,8 +4,6 @@ import argparse
 import os
 import sys
 
-from pre_commit_hooks.util import cmd_output
-
 
 def _fix_file(filename, is_markdown):
     with open(filename, mode='rb') as file_processed:
@@ -21,14 +19,19 @@ def _fix_file(filename, is_markdown):
 
 
 def _process_line(line, is_markdown):
+    if line[-2:] == b'\r\n':
+        eol = b'\r\n'
+    elif line[-1:] == b'\n':
+        eol = b'\n'
+    else:
+        eol = b''
     # preserve trailing two-space for non-blank lines in markdown files
-    eol = b'\r\n' if line[-2:] == b'\r\n' else b'\n'
     if is_markdown and (not line.isspace()) and line.endswith(b'  ' + eol):
         return line.rstrip() + b'  ' + eol
     return line.rstrip() + eol
 
 
-def fix_trailing_whitespace(argv=None):
+def main(argv=None):
     parser = argparse.ArgumentParser()
     parser.add_argument(
         '--no-markdown-linebreak-ext',
@@ -36,7 +39,7 @@ def fix_trailing_whitespace(argv=None):
         const=[],
         default=argparse.SUPPRESS,
         dest='markdown_linebreak_ext',
-        help='Do not preserve linebreak spaces in Markdown'
+        help='Do not preserve linebreak spaces in Markdown',
     )
     parser.add_argument(
         '--markdown-linebreak-ext',
@@ -45,15 +48,11 @@ def fix_trailing_whitespace(argv=None):
         default=['md,markdown'],
         metavar='*|EXT[,EXT,...]',
         nargs='?',
-        help='Markdown extensions (or *) for linebreak spaces'
+        help='Markdown extensions (or *) for linebreak spaces',
     )
     parser.add_argument('filenames', nargs='*', help='Filenames to fix')
     args = parser.parse_args(argv)
 
-    bad_whitespace_files = cmd_output(
-        'grep', '-l', '[[:space:]]$', *args.filenames, retcode=None
-    ).strip().splitlines()
-
     md_args = args.markdown_linebreak_ext
     if '' in md_args:
         parser.error('--markdown-linebreak-ext requires a non-empty argument')
@@ -67,20 +66,20 @@ def fix_trailing_whitespace(argv=None):
     for ext in md_exts:
         if any(c in ext[1:] for c in r'./\:'):
             parser.error(
-                "bad --markdown-linebreak-ext extension '{0}' (has . / \\ :)\n"
+                "bad --markdown-linebreak-ext extension '{}' (has . / \\ :)\n"
                 "  (probably filename; use '--markdown-linebreak-ext=EXT')"
-                .format(ext)
+                .format(ext),
             )
 
     return_code = 0
-    for bad_whitespace_file in bad_whitespace_files:
+    for filename in args.filenames:
-        _, extension = os.path.splitext(bad_whitespace_file.lower())
+        _, extension = os.path.splitext(filename.lower())
         md = all_markdown or extension in md_exts
-        if _fix_file(bad_whitespace_file, md):
+        if _fix_file(filename, md):
-            print('Fixing {}'.format(bad_whitespace_file))
+            print('Fixing {}'.format(filename))
             return_code = 1
     return return_code
 
 
 if __name__ == '__main__':
-    sys.exit(fix_trailing_whitespace())
+    sys.exit(main())

setup.cfg

@@ -1,2 +1,2 @@
-[wheel]
+[bdist_wheel]
 universal = True

setup.py

@@ -6,7 +6,7 @@ setup(
     name='pre_commit_hooks',
     description='Some out-of-the-box hooks for pre-commit.',
     url='https://github.com/pre-commit/pre-commit-hooks',
-    version='0.7.1',
+    version='1.3.0',
 
     author='Anthony Sottile',
     author_email='asottile@umich.edu',
@@ -24,37 +24,44 @@ setup(
 
     packages=find_packages(exclude=('tests*', 'testing*')),
     install_requires=[
-        # quickfix to prevent pep8 conflicts
+        # quickfix to prevent pycodestyle conflicts
-        'flake8==3.3.0',
+        'flake8==3.5.0',
-        'autopep8==1.2.4',
+        'autopep8==1.3.5',
+        'pycodestyle==2.3.1',
         'pyyaml==3.12',
-        'simplejson==3.10.0',
+        'six==1.11.0',
-        'six==1.10.0',
     ],
     entry_points={
         'console_scripts': [
             'autopep8-wrapper = pre_commit_hooks.autopep8_wrapper:main',
             'check-added-large-files = pre_commit_hooks.check_added_large_files:main',
             'check-ast = pre_commit_hooks.check_ast:check_ast',
+            '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-json = pre_commit_hooks.check_json:check_json',
+            'check-executables-have-shebangs = pre_commit_hooks.check_executables_have_shebangs:main',
+            'check-json = pre_commit_check.hooks_json:check_json',
             'check-merge-conflict = pre_commit_hooks.check_merge_conflict:detect_merge_conflict',
             'check-symlinks = pre_commit_hooks.check_symlinks:check_symlinks',
+            'check-vcs-permalinks = pre_commit_hooks.check_vcs_permalinks:main',
             'check-xml = pre_commit_hooks.check_xml:check_xml',
             'check-yaml = pre_commit_hooks.check_yaml:check_yaml',
-            'debug-statement-hook = pre_commit_hooks.debug_statement_hook:debug_statement_hook',
+            'debug-statement-hook = pre_commit_hooks.debug_statement_hook:main',
             'detect-aws-credentials = pre_commit_hooks.detect_aws_credentials:main',
             'detect-private-key = pre_commit_hooks.detect_private_key:detect_private_key',
             'double-quote-string-fixer = pre_commit_hooks.string_fixer:main',
             'end-of-file-fixer = pre_commit_hooks.end_of_file_fixer:end_of_file_fixer',
+            'file-contents-sorter = pre_commit_hooks.file_contents_sorter: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:validate_files',
+            'no-commit-to-branch = pre_commit_hooks.no_commit_to_branch:main',
             'pretty-format-json = pre_commit_hooks.pretty_format_json:pretty_format_json',
             'requirements-txt-fixer = pre_commit_hooks.requirements_txt_fixer:fix_requirements_txt',
-            'trailing-whitespace-fixer = pre_commit_hooks.trailing_whitespace_fixer:fix_trailing_whitespace',
+            'sort-simple-yaml = pre_commit_hooks.sort_simple_yaml:main',
+            'trailing-whitespace-fixer = pre_commit_hooks.trailing_whitespace_fixer:main',
         ],
     },
 )

testing/resources/aws_config_without_secrets_with_spaces.ini

@@ -0,0 +1,4 @@
+# file with an AWS access key id but no valid AWS secret access key only space characters
+[production]
+aws_access_key_id = AKIASLARTARGENTINA86
+aws_secret_access_key =

testing/resources/broken_symlink

@@ -1 +0,0 @@
-does_not_exist

testing/resources/builtin_constructors.py

@@ -0,0 +1,17 @@
+from six.moves import builtins
+
+c1 = complex()
+d1 = dict()
+f1 = float()
+i1 = int()
+l1 = list()
+s1 = str()
+t1 = tuple()
+
+c2 = builtins.complex()
+d2 = builtins.dict()
+f2 = builtins.float()
+i2 = builtins.int()
+l2 = builtins.list()
+s2 = builtins.str()
+t2 = builtins.tuple()

testing/resources/builtin_literals.py

@@ -0,0 +1,7 @@
+c1 = 0j
+d1 = {}
+f1 = 0.0
+i1 = 0
+l1 = []
+s1 = ''
+t1 = ()

testing/resources/file_with_debug.notpy

@@ -1,5 +0,0 @@
-
-def foo(obj):
-    import pdb; pdb.set_trace()
-
-    return 5

testing/resources/non_ascii_pretty_formatted_json.json

@@ -0,0 +1,10 @@
+{
+  "alist": [
+    2,
+    34,
+    234
+  ],
+  "blah": null,
+  "foo": "bar",
+  "non_ascii": "中文にほんご한국어"
+}

testing/resources/working_symlink

@@ -1 +0,0 @@
-does_exist

testing/util.py

@@ -1,7 +1,6 @@
 from __future__ import absolute_import
 from __future__ import unicode_literals
 
-import io
 import os.path
 
 
@@ -10,9 +9,3 @@ TESTING_DIR = os.path.abspath(os.path.dirname(__file__))
 
 def get_resource_path(path):
     return os.path.join(TESTING_DIR, 'resources', path)
-
-
-def write_file(filename, contents):
-    """Hax because coveragepy chokes on nested context managers."""
-    with io.open(filename, 'w', newline='') as file_obj:
-        file_obj.write(contents)

tests/autopep8_wrapper_test.py

@@ -23,6 +23,6 @@ def test_main_failing(tmpdir, input_src, expected_ret, output_src):
 
 def test_respects_config_file(tmpdir):
     with tmpdir.as_cwd():
-        tmpdir.join('setup.cfg').write('[pep8]\nignore=E221')
+        tmpdir.join('setup.cfg').write('[pycodestyle]\nignore=E221')
         tmpdir.join('test.py').write('print(1    + 2)\n')
         assert main(['test.py', '-i', '-v']) == 0

tests/check_added_large_files_test.py

@@ -79,15 +79,6 @@ xfailif_no_gitlfs = pytest.mark.xfail(
 @xfailif_no_gitlfs
 def test_allows_gitlfs(temp_git_dir):  # pragma: no cover
     with temp_git_dir.as_cwd():
-        # Work around https://github.com/github/git-lfs/issues/913
-        cmd_output(
-            'git',
-            'commit',
-            '--no-gpg-sign',
-            '--allow-empty',
-            '-m',
-            'foo',
-        )
         cmd_output('git', 'lfs', 'install')
         temp_git_dir.join('f.py').write('a' * 10000)
         cmd_output('git', 'lfs', 'track', 'f.py')

tests/check_builtin_literals_test.py

@@ -0,0 +1,116 @@
+import ast
+
+import pytest
+
+from pre_commit_hooks.check_builtin_literals import BuiltinTypeCall
+from pre_commit_hooks.check_builtin_literals import BuiltinTypeVisitor
+from pre_commit_hooks.check_builtin_literals import main
+from testing.util import get_resource_path
+
+
+@pytest.fixture
+def visitor():
+    return BuiltinTypeVisitor()
+
+
+@pytest.mark.parametrize(
+    ('expression', 'calls'),
+    [
+        # see #285
+        ('x[0]()', []),
+        # complex
+        ("0j", []),
+        ("complex()", [BuiltinTypeCall('complex', 1, 0)]),
+        ("complex(0, 0)", []),
+        ("complex('0+0j')", []),
+        ('builtins.complex()', []),
+        # float
+        ("0.0", []),
+        ("float()", [BuiltinTypeCall('float', 1, 0)]),
+        ("float('0.0')", []),
+        ('builtins.float()', []),
+        # int
+        ("0", []),
+        ("int()", [BuiltinTypeCall('int', 1, 0)]),
+        ("int('0')", []),
+        ('builtins.int()', []),
+        # list
+        ("[]", []),
+        ("list()", [BuiltinTypeCall('list', 1, 0)]),
+        ("list('abc')", []),
+        ("list([c for c in 'abc'])", []),
+        ("list(c for c in 'abc')", []),
+        ('builtins.list()', []),
+        # str
+        ("''", []),
+        ("str()", [BuiltinTypeCall('str', 1, 0)]),
+        ("str('0')", []),
+        ('builtins.str()', []),
+        # tuple
+        ("()", []),
+        ("tuple()", [BuiltinTypeCall('tuple', 1, 0)]),
+        ("tuple('abc')", []),
+        ("tuple([c for c in 'abc'])", []),
+        ("tuple(c for c in 'abc')", []),
+        ('builtins.tuple()', []),
+    ],
+)
+def test_non_dict_exprs(visitor, expression, calls):
+    visitor.visit(ast.parse(expression))
+    assert visitor.builtin_type_calls == calls
+
+
+@pytest.mark.parametrize(
+    ('expression', 'calls'),
+    [
+        ("{}", []),
+        ("dict()", [BuiltinTypeCall('dict', 1, 0)]),
+        ("dict(a=1, b=2, c=3)", []),
+        ("dict(**{'a': 1, 'b': 2, 'c': 3})", []),
+        ("dict([(k, v) for k, v in [('a', 1), ('b', 2), ('c', 3)]])", []),
+        ("dict((k, v) for k, v in [('a', 1), ('b', 2), ('c', 3)])", []),
+        ('builtins.dict()', []),
+    ],
+)
+def test_dict_allow_kwargs_exprs(visitor, expression, calls):
+    visitor.visit(ast.parse(expression))
+    assert visitor.builtin_type_calls == calls
+
+
+@pytest.mark.parametrize(
+    ('expression', 'calls'),
+    [
+        ("dict()", [BuiltinTypeCall('dict', 1, 0)]),
+        ("dict(a=1, b=2, c=3)", [BuiltinTypeCall('dict', 1, 0)]),
+        ("dict(**{'a': 1, 'b': 2, 'c': 3})", [BuiltinTypeCall('dict', 1, 0)]),
+        ('builtins.dict()', []),
+    ],
+)
+def test_dict_no_allow_kwargs_exprs(expression, calls):
+    visitor = BuiltinTypeVisitor(allow_dict_kwargs=False)
+    visitor.visit(ast.parse(expression))
+    assert visitor.builtin_type_calls == calls
+
+
+def test_ignore_constructors():
+    visitor = BuiltinTypeVisitor(ignore=('complex', 'dict', 'float', 'int', 'list', 'str', 'tuple'))
+    visitor.visit(ast.parse(open(get_resource_path('builtin_constructors.py'), 'rb').read(), 'builtin_constructors.py'))
+    assert visitor.builtin_type_calls == []
+
+
+def test_failing_file():
+    rc = main([get_resource_path('builtin_constructors.py')])
+    assert rc == 1
+
+
+def test_passing_file():
+    rc = main([get_resource_path('builtin_literals.py')])
+    assert rc == 0
+
+
+def test_failing_file_ignore_all():
+    rc = main([
+        '--ignore=complex,dict,float,int,list,str,tuple',
+        get_resource_path('builtin_constructors.py'),
+    ])
+    assert rc == 0

tests/check_docstring_first_test.py

@@ -19,7 +19,7 @@ TESTS = (
         '"foo"\n',
         1,
         '{filename}:2 Module docstring appears after code '
-        '(code seen on line 1).\n'
+        '(code seen on line 1).\n',
     ),
     # Test double docstring
     (
@@ -28,7 +28,7 @@ TESTS = (
         '"fake docstring"\n',
         1,
         '{filename}:3 Multiple module docstrings '
-        '(first docstring on line 1).\n'
+        '(first docstring on line 1).\n',
     ),
     # Test multiple lines of code above
     (

tests/check_executables_have_shebangs_test.py

@@ -0,0 +1,39 @@
+# -*- coding: utf-8 -*-
+from __future__ import absolute_import
+from __future__ import unicode_literals
+
+import pytest
+
+from pre_commit_hooks.check_executables_have_shebangs import main
+
+
+@pytest.mark.parametrize(
+    'content', (
+        b'#!/bin/bash\nhello world\n',
+        b'#!/usr/bin/env python3.6',
+        b'#!python',
+        '#!☃'.encode('UTF-8'),
+    ),
+)
+def test_has_shebang(content, tmpdir):
+    path = tmpdir.join('path')
+    path.write(content, 'wb')
+    assert main((path.strpath,)) == 0
+
+
+@pytest.mark.parametrize(
+    'content', (
+        b'',
+        b' #!python\n',
+        b'\n#!python\n',
+        b'python\n',
+        '☃'.encode('UTF-8'),
+
+    ),
+)
+def test_bad_shebang(content, tmpdir, capsys):
+    path = tmpdir.join('path')
+    path.write(content, 'wb')
+    assert main((path.strpath,)) == 1
+    _, stderr = capsys.readouterr()
+    assert stderr.startswith('{}: marked executable but'.format(path.strpath))

tests/check_json_test.py

@@ -4,11 +4,13 @@ from pre_commit_hooks.check_json import check_json
 from testing.util import get_resource_path
 
 
-@pytest.mark.parametrize(('filename', 'expected_retval'), (
+@pytest.mark.parametrize(
-    ('bad_json.notjson', 1),
+    ('filename', 'expected_retval'), (
-    ('bad_json_latin1.nonjson', 1),
+        ('bad_json.notjson', 1),
-    ('ok_json.json', 0),
+        ('bad_json_latin1.nonjson', 1),
-))
+        ('ok_json.json', 0),
+    ),
+)
 def test_check_json(capsys, filename, expected_retval):
     ret = check_json([get_resource_path(filename)])
     assert ret == expected_retval

tests/check_merge_conflict_test.py

@@ -9,10 +9,9 @@ import pytest
 from pre_commit_hooks.check_merge_conflict import detect_merge_conflict
 from pre_commit_hooks.util import cmd_output
 from testing.util import get_resource_path
-from testing.util import write_file
 
 
-@pytest.yield_fixture
+@pytest.fixture
 def f1_is_a_conflict_file(tmpdir):
     # Make a merge conflict
     repo1 = tmpdir.join('repo1')
@@ -37,7 +36,7 @@ def f1_is_a_conflict_file(tmpdir):
     with repo2.as_cwd():
         repo2_f1.write('child\n')
         cmd_output('git', 'commit', '--no-gpg-sign', '-am', 'clone commit2')
-        cmd_output('git', 'pull', retcode=None)
+        cmd_output('git', 'pull', '--no-rebase', retcode=None)
         # We should end up in a merge conflict!
         f1 = repo2_f1.read()
         assert f1.startswith(
@@ -45,7 +44,7 @@ def f1_is_a_conflict_file(tmpdir):
             'child\n'
             '=======\n'
             'parent\n'
-            '>>>>>>>'
+            '>>>>>>>',
         ) or f1.startswith(
             '<<<<<<< HEAD\n'
             'child\n'
@@ -53,14 +52,22 @@ def f1_is_a_conflict_file(tmpdir):
             '||||||| merged common ancestors\n'
             '=======\n'
             'parent\n'
-            '>>>>>>>'
+            '>>>>>>>',
+        ) or f1.startswith(
+            # .gitconfig with [pull] rebase = preserve causes a rebase which
+            # flips parent / child
+            '<<<<<<< HEAD\n'
+            'parent\n'
+            '=======\n'
+            'child\n'
+            '>>>>>>>',
         )
         assert os.path.exists(os.path.join('.git', 'MERGE_MSG'))
-        yield
+        yield repo2
 
 
-@pytest.yield_fixture
+@pytest.fixture
-def repository_is_pending_merge(tmpdir):
+def repository_pending_merge(tmpdir):
     # Make a (non-conflicting) merge
     repo1 = tmpdir.join('repo1')
     repo1_f1 = repo1.join('f1')
@@ -85,12 +92,12 @@ def repository_is_pending_merge(tmpdir):
         repo2_f2.write('child\n')
         cmd_output('git', 'add', '--', repo2_f2.strpath)
         cmd_output('git', 'commit', '--no-gpg-sign', '-m', 'clone commit2')
-        cmd_output('git', 'pull', '--no-commit')
+        cmd_output('git', 'pull', '--no-commit', '--no-rebase')
         # We should end up in a pending merge
         assert repo2_f1.read() == 'parent\n'
         assert repo2_f2.read() == 'child\n'
         assert os.path.exists(os.path.join('.git', 'MERGE_HEAD'))
-        yield
+        yield repo2
 
 
 @pytest.mark.usefixtures('f1_is_a_conflict_file')
@@ -99,20 +106,18 @@ def test_merge_conflicts_git():
 
 
 @pytest.mark.parametrize(
-    'failing_contents', ('<<<<<<< HEAD\n', '=======\n', '>>>>>>> master\n'),
+    'contents', (b'<<<<<<< HEAD\n', b'=======\n', b'>>>>>>> master\n'),
 )
-@pytest.mark.usefixtures('repository_is_pending_merge')
+def test_merge_conflicts_failing(contents, repository_pending_merge):
-def test_merge_conflicts_failing(failing_contents):
+    repository_pending_merge.join('f2').write_binary(contents)
-    write_file('f2', failing_contents)
     assert detect_merge_conflict(['f2']) == 1
 
 
 @pytest.mark.parametrize(
-    'ok_contents', ('# <<<<<<< HEAD\n', '# =======\n', 'import my_module', ''),
+    'contents', (b'# <<<<<<< HEAD\n', b'# =======\n', b'import mod', b''),
 )
-@pytest.mark.usefixtures('f1_is_a_conflict_file')
+def test_merge_conflicts_ok(contents, f1_is_a_conflict_file):
-def test_merge_conflicts_ok(ok_contents):
+    f1_is_a_conflict_file.join('f1').write_binary(contents)
-    write_file('f1', ok_contents)
     assert detect_merge_conflict(['f1']) == 0
 
 

tests/check_symlinks_test.py

@@ -3,14 +3,21 @@ import os
 import pytest
 
 from pre_commit_hooks.check_symlinks import check_symlinks
-from testing.util import get_resource_path
 
 
-@pytest.mark.xfail(os.name == 'nt', reason='No symlink support on windows')
+xfail_symlink = pytest.mark.xfail(os.name == 'nt', reason='No symlink support')
-@pytest.mark.parametrize(('filename', 'expected_retval'), (
+
-    ('broken_symlink', 1),
+
-    ('working_symlink', 0),
+@xfail_symlink
-))
+@pytest.mark.parametrize(
-def test_check_symlinks(filename, expected_retval):
+    ('dest', 'expected'), (('exists', 0), ('does-not-exist', 1)),
-    ret = check_symlinks([get_resource_path(filename)])
+)
-    assert ret == expected_retval
+def test_check_symlinks(tmpdir, dest, expected):  # pragma: no cover (symlinks)
+    tmpdir.join('exists').ensure()
+    symlink = tmpdir.join('symlink')
+    symlink.mksymlinkto(tmpdir.join(dest))
+    assert check_symlinks((symlink.strpath,)) == expected
+
+
+def test_check_symlinks_normal_file(tmpdir):
+    assert check_symlinks((tmpdir.join('f').ensure().strpath,)) == 0

tests/check_vcs_permalinks_test.py

@@ -0,0 +1,38 @@
+from __future__ import absolute_import
+from __future__ import unicode_literals
+
+from pre_commit_hooks.check_vcs_permalinks import main
+
+
+def test_trivial(tmpdir):
+    f = tmpdir.join('f.txt').ensure()
+    assert not main((f.strpath,))
+
+
+def test_passing(tmpdir):
+    f = tmpdir.join('f.txt')
+    f.write_binary(
+        # permalinks are ok
+        b'https://github.com/asottile/test/blob/649e6/foo%20bar#L1\n'
+        # links to files but not line numbers are ok
+        b'https://github.com/asottile/test/blob/master/foo%20bar\n'
+        # regression test for overly-greedy regex
+        b'https://github.com/ yes / no ? /blob/master/foo#L1\n',
+    )
+    assert not main((f.strpath,))
+
+
+def test_failing(tmpdir, capsys):
+    with tmpdir.as_cwd():
+        tmpdir.join('f.txt').write_binary(
+            b'https://github.com/asottile/test/blob/master/foo#L1\n',
+        )
+
+        assert main(('f.txt',))
+        out, _ = capsys.readouterr()
+        assert out == (
+            'f.txt:1:https://github.com/asottile/test/blob/master/foo#L1\n'
+            '\n'
+            'Non-permanent github link detected.\n'
+            'On any page on github press [y] to load a permalink.\n'
+        )

tests/check_xml_test.py

@@ -4,10 +4,12 @@ from pre_commit_hooks.check_xml import check_xml
 from testing.util import get_resource_path
 
 
-@pytest.mark.parametrize(('filename', 'expected_retval'), (
+@pytest.mark.parametrize(
-    ('bad_xml.notxml', 1),
+    ('filename', 'expected_retval'), (
-    ('ok_xml.xml', 0),
+        ('bad_xml.notxml', 1),
-))
+        ('ok_xml.xml', 0),
+    ),
+)
 def test_check_xml(filename, expected_retval):
     ret = check_xml([get_resource_path(filename)])
     assert ret == expected_retval

tests/check_yaml_test.py

@@ -1,13 +1,54 @@
+from __future__ import absolute_import
+from __future__ import unicode_literals
+
 import pytest
 
 from pre_commit_hooks.check_yaml import check_yaml
 from testing.util import get_resource_path
 
 
-@pytest.mark.parametrize(('filename', 'expected_retval'), (
+@pytest.mark.parametrize(
-    ('bad_yaml.notyaml', 1),
+    ('filename', 'expected_retval'), (
-    ('ok_yaml.yaml', 0),
+        ('bad_yaml.notyaml', 1),
-))
+        ('ok_yaml.yaml', 0),
+    ),
+)
 def test_check_yaml(filename, expected_retval):
     ret = check_yaml([get_resource_path(filename)])
     assert ret == expected_retval
+
+
+def test_check_yaml_allow_multiple_documents(tmpdir):
+    f = tmpdir.join('test.yaml')
+    f.write('---\nfoo\n---\nbar\n')
+
+    # should fail without the setting
+    assert check_yaml((f.strpath,))
+
+    # should pass when we allow multiple documents
+    assert not check_yaml(('--allow-multiple-documents', f.strpath))
+
+
+def test_fails_even_with_allow_multiple_documents(tmpdir):
+    f = tmpdir.join('test.yaml')
+    f.write('[')
+    assert check_yaml(('--allow-multiple-documents', f.strpath))
+
+
+def test_check_yaml_unsafe(tmpdir):
+    f = tmpdir.join('test.yaml')
+    f.write(
+        'some_foo: !vault |\n'
+        '    $ANSIBLE_VAULT;1.1;AES256\n'
+        '    deadbeefdeadbeefdeadbeef\n',
+    )
+    # should fail "safe" check
+    assert check_yaml((f.strpath,))
+    # should pass when we allow unsafe documents
+    assert not check_yaml(('--unsafe', f.strpath))
+
+
+def test_check_yaml_unsafe_still_fails_on_syntax_errors(tmpdir):
+    f = tmpdir.join('test.yaml')
+    f.write('[')
+    assert check_yaml(('--unsafe', f.strpath))

tests/conftest.py

@@ -7,7 +7,7 @@ import pytest
 from pre_commit_hooks.util import cmd_output
 
 
-@pytest.yield_fixture
+@pytest.fixture
 def temp_git_dir(tmpdir):
     git_dir = tmpdir.join('gits')
     cmd_output('git', 'init', '--', git_dir.strpath)

tests/debug_statement_hook_test.py

@@ -1,73 +1,63 @@
+# -*- coding: utf-8 -*-
+from __future__ import absolute_import
+from __future__ import unicode_literals
+
 import ast
 
-import pytest
+from pre_commit_hooks.debug_statement_hook import Debug
-
+from pre_commit_hooks.debug_statement_hook import DebugStatementParser
-from pre_commit_hooks.debug_statement_hook import debug_statement_hook
+from pre_commit_hooks.debug_statement_hook import main
-from pre_commit_hooks.debug_statement_hook import DebugStatement
-from pre_commit_hooks.debug_statement_hook import ImportStatementParser
 from testing.util import get_resource_path
 
 
-@pytest.fixture
+def test_no_breakpoints():
-def ast_with_no_debug_imports():
+    visitor = DebugStatementParser()
-    return ast.parse("""
+    visitor.visit(ast.parse('import os\nfrom foo import bar\n'))
-import foo
+    assert visitor.breakpoints == []
-import bar
-import baz
-from foo import bar
-""")
 
 
-@pytest.fixture
+def test_finds_debug_import_attribute_access():
-def ast_with_debug_import_form_1():
+    visitor = DebugStatementParser()
-    return ast.parse("""
+    visitor.visit(ast.parse('import ipdb; ipdb.set_trace()'))
-
+    assert visitor.breakpoints == [Debug(1, 0, 'ipdb', 'imported')]
-import ipdb; ipdb.set_trace()
-
-""")
 
 
-@pytest.fixture
+def test_finds_debug_import_from_import():
-def ast_with_debug_import_form_2():
+    visitor = DebugStatementParser()
-    return ast.parse("""
+    visitor.visit(ast.parse('from pudb import set_trace; set_trace()'))
-
+    assert visitor.breakpoints == [Debug(1, 0, 'pudb', 'imported')]
-from pudb import set_trace; set_trace()
-
-""")
 
 
-def test_returns_no_debug_statements(ast_with_no_debug_imports):
+def test_finds_breakpoint():
-    visitor = ImportStatementParser()
+    visitor = DebugStatementParser()
-    visitor.visit(ast_with_no_debug_imports)
+    visitor.visit(ast.parse('breakpoint()'))
-    assert visitor.debug_import_statements == []
+    assert visitor.breakpoints == [Debug(1, 0, 'breakpoint', 'called')]
 
 
-def test_returns_one_form_1(ast_with_debug_import_form_1):
+def test_returns_one_for_failing_file(tmpdir):
-    visitor = ImportStatementParser()
+    f_py = tmpdir.join('f.py')
-    visitor.visit(ast_with_debug_import_form_1)
+    f_py.write('def f():\n    import pdb; pdb.set_trace()')
-    assert visitor.debug_import_statements == [
+    ret = main([f_py.strpath])
-        DebugStatement('ipdb', 3, 0)
-    ]
-
-
-def test_returns_one_form_2(ast_with_debug_import_form_2):
-    visitor = ImportStatementParser()
-    visitor.visit(ast_with_debug_import_form_2)
-    assert visitor.debug_import_statements == [
-        DebugStatement('pudb', 3, 0)
-    ]
-
-
-def test_returns_one_for_failing_file():
-    ret = debug_statement_hook([get_resource_path('file_with_debug.notpy')])
     assert ret == 1
 
 
 def test_returns_zero_for_passing_file():
-    ret = debug_statement_hook([__file__])
+    ret = main([__file__])
     assert ret == 0
 
 
 def test_syntaxerror_file():
-    ret = debug_statement_hook([get_resource_path('cannot_parse_ast.notpy')])
+    ret = main([get_resource_path('cannot_parse_ast.notpy')])
     assert ret == 1
+
+
+def test_non_utf8_file(tmpdir):
+    f_py = tmpdir.join('f.py')
+    f_py.write_binary('# -*- coding: cp1252 -*-\nx = "€"\n'.encode('cp1252'))
+    assert main((f_py.strpath,)) == 0
+
+
+def test_py37_breakpoint(tmpdir):
+    f_py = tmpdir.join('f.py')
+    f_py.write('def f():\n    breakpoint()\n')
+    assert main((f_py.strpath,)) == 1

tests/detect_aws_credentials_test.py

@@ -21,16 +21,16 @@ from testing.util import get_resource_path
         (
             {
                 'AWS_DUMMY_KEY': '/foo', 'AWS_CONFIG_FILE': '/bar',
-                'AWS_CREDENTIAL_FILE': '/baz'
+                'AWS_CREDENTIAL_FILE': '/baz',
             },
-            {'/bar', '/baz'}
+            {'/bar', '/baz'},
         ),
         (
             {
                 'AWS_CONFIG_FILE': '/foo', 'AWS_CREDENTIAL_FILE': '/bar',
-                'AWS_SHARED_CREDENTIALS_FILE': '/baz'
+                'AWS_SHARED_CREDENTIALS_FILE': '/baz',
             },
-            {'/foo', '/bar', '/baz'}
+            {'/foo', '/bar', '/baz'},
         ),
     ),
 )
@@ -51,7 +51,7 @@ def test_get_aws_credentials_file_from_env(env_vars, values):
         ({'AWS_DUMMY_KEY': 'foo', 'AWS_SECRET_ACCESS_KEY': 'bar'}, {'bar'}),
         (
             {'AWS_SECRET_ACCESS_KEY': 'foo', 'AWS_SECURITY_TOKEN': 'bar'},
-            {'foo', 'bar'}
+            {'foo', 'bar'},
         ),
     ),
 )
@@ -66,21 +66,24 @@ def test_get_aws_secrets_from_env(env_vars, values):
     (
         (
             'aws_config_with_secret.ini',
-            {'z2rpgs5uit782eapz5l1z0y2lurtsyyk6hcfozlb'}
+            {'z2rpgs5uit782eapz5l1z0y2lurtsyyk6hcfozlb'},
         ),
         ('aws_config_with_session_token.ini', {'foo'}),
-        ('aws_config_with_secret_and_session_token.ini',
+        (
-         {'z2rpgs5uit782eapz5l1z0y2lurtsyyk6hcfozlb', 'foo'}),
+            'aws_config_with_secret_and_session_token.ini',
+            {'z2rpgs5uit782eapz5l1z0y2lurtsyyk6hcfozlb', 'foo'},
+        ),
         (
             'aws_config_with_multiple_sections.ini',
             {
                 '7xebzorgm5143ouge9gvepxb2z70bsb2rtrh099e',
                 'z2rpgs5uit782eapz5l1z0y2lurtsyyk6hcfozlb',
                 'ixswosj8gz3wuik405jl9k3vdajsnxfhnpui38ez',
-                'foo'
+                'foo',
-            }
+            },
         ),
         ('aws_config_without_secrets.ini', set()),
+        ('aws_config_without_secrets_with_spaces.ini', set()),
         ('nonsense.txt', set()),
         ('ok_json.json', set()),
     ),
@@ -98,6 +101,7 @@ def test_get_aws_secrets_from_file(filename, expected_keys):
         ('aws_config_with_session_token.ini', 1),
         ('aws_config_with_multiple_sections.ini', 1),
         ('aws_config_without_secrets.ini', 0),
+        ('aws_config_without_secrets_with_spaces.ini', 0),
         ('nonsense.txt', 0),
         ('ok_json.json', 0),
     ),
@@ -121,7 +125,7 @@ def test_non_existent_credentials(mock_secrets_env, mock_secrets_file, capsys):
     mock_secrets_file.return_value = set()
     ret = main((
         get_resource_path('aws_config_without_secrets.ini'),
-        "--credentials-file=testing/resources/credentailsfilethatdoesntexist"
+        "--credentials-file=testing/resources/credentailsfilethatdoesntexist",
     ))
     assert ret == 2
     out, _ = capsys.readouterr()
@@ -141,6 +145,6 @@ def test_non_existent_credentials_with_allow_flag(mock_secrets_env, mock_secrets
     ret = main((
         get_resource_path('aws_config_without_secrets.ini'),
         "--credentials-file=testing/resources/credentailsfilethatdoesntexist",
-        "--allow-missing-credentials"
+        "--allow-missing-credentials",
     ))
     assert ret == 0

tests/detect_private_key_test.py

@@ -8,6 +8,8 @@ TESTS = (
     (b'-----BEGIN DSA PRIVATE KEY-----', 1),
     (b'-----BEGIN EC PRIVATE KEY-----', 1),
     (b'-----BEGIN OPENSSH PRIVATE KEY-----', 1),
+    (b'PuTTY-User-Key-File-2: ssh-rsa', 1),
+    (b'---- BEGIN SSH2 ENCRYPTED PRIVATE KEY ----', 1),
     (b'ssh-rsa DATA', 0),
     (b'ssh-dsa DATA', 0),
     # Some arbitrary binary data

tests/file_contents_sorter_test.py

@@ -0,0 +1,33 @@
+import pytest
+
+from pre_commit_hooks.file_contents_sorter import FAIL
+from pre_commit_hooks.file_contents_sorter import main
+from pre_commit_hooks.file_contents_sorter import PASS
+
+
+@pytest.mark.parametrize(
+    ('input_s', 'expected_retval', 'output'),
+    (
+        (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'),
+        (b'missing\nnewline', FAIL, b'missing\nnewline\n'),
+        (b'alpha\nbeta\n', PASS, b'alpha\nbeta\n'),
+        (b'beta\nalpha\n', FAIL, b'alpha\nbeta\n'),
+        (b'C\nc\n', PASS, b'C\nc\n'),
+        (b'c\nC\n', FAIL, b'C\nc\n'),
+        (b'mag ical \n tre vor\n', FAIL, b' tre vor\nmag ical \n'),
+        (b'@\n-\n_\n#\n', FAIL, b'#\n-\n@\n_\n'),
+        (b'extra\n\n\nwhitespace\n', FAIL, b'extra\nwhitespace\n'),
+        (b'whitespace\n\n\nextra\n', FAIL, b'extra\nwhitespace\n'),
+    ),
+)
+def test_integration(input_s, expected_retval, output, tmpdir):
+    path = tmpdir.join('file.txt')
+    path.write_binary(input_s)
+
+    output_retval = main([path.strpath])
+
+    assert path.read_binary() == output
+    assert output_retval == expected_retval

tests/fix_encoding_pragma_test.py

@@ -56,7 +56,7 @@ def test_integration_remove_ok(tmpdir):
             b'# -*- coding: utf-8 -*-\n'
             b'foo = "bar"\n'
         ),
-    )
+    ),
 )
 def test_ok_inputs(input_str):
     bytesio = io.BytesIO(input_str)
@@ -100,7 +100,7 @@ def test_ok_inputs(input_str):
         (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)

tests/forbid_new_submodules_test.py

@@ -6,14 +6,18 @@ from pre_commit.util import cmd_output
 from pre_commit_hooks.forbid_new_submodules import main
 
 
-@pytest.yield_fixture
+@pytest.fixture
 def git_dir_with_git_dir(tmpdir):
     with tmpdir.as_cwd():
         cmd_output('git', 'init', '.')
-        cmd_output('git', 'commit', '-m', 'init', '--allow-empty')
+        cmd_output(
+            'git', 'commit', '-m', 'init', '--allow-empty', '--no-gpg-sign',
+        )
         cmd_output('git', 'init', 'foo')
-        with tmpdir.join('foo').as_cwd():
+        cmd_output(
-            cmd_output('git', 'commit', '-m', 'init', '--allow-empty')
+            'git', 'commit', '-m', 'init', '--allow-empty', '--no-gpg-sign',
+            cwd=tmpdir.join('foo').strpath,
+        )
         yield
 
 

tests/meta_test.py

@@ -1,7 +1,43 @@
+from __future__ import absolute_import
+from __future__ import unicode_literals
+
 import io
 
+import yaml
 
-def test_hooks_yaml_same_contents():
+
-    legacy_contents = io.open('hooks.yaml').read()
+def _assert_parseable_in_old_pre_commit(hooks):
-    contents = io.open('.pre-commit-hooks.yaml').read()
+    for hook in hooks:
-    assert legacy_contents == contents
+        assert {'id', 'name', 'entry', 'files', 'language'} <= set(hook)
+
+
+def test_legacy_hooks():
+    with io.open('hooks.yaml', encoding='UTF-8') as legacy_file:
+        legacy = yaml.load(legacy_file.read())
+    with io.open('.pre-commit-hooks.yaml', encoding='UTF-8') as hooks_file:
+        hooks = yaml.load(hooks_file.read())
+
+    # The same set of hooks should be defined in both files
+    new_hook_ids = {hook['id'] for hook in hooks}
+    legacy_hook_ids = {hook['id'] for hook in legacy}
+    assert new_hook_ids == legacy_hook_ids
+
+    # Both files should be parseable by pre-commit<0.15.0
+    _assert_parseable_in_old_pre_commit(legacy)
+    _assert_parseable_in_old_pre_commit(hooks)
+
+    # The legacy file should force upgrading
+    for hook in legacy:
+        del hook['id']
+        assert hook == {
+            'language': 'system',
+            'name': 'upgrade-your-pre-commit-version',
+            'entry': 'upgrade-your-pre-commit-version',
+            'files': '',
+            'minimum_pre_commit_version': '0.15.0',
+        }
+
+    # Each hook should require a new version if it uses types
+    for hook in hooks:
+        if 'types' in hook:
+            assert hook['minimum_pre_commit_version'] == '0.15.0'

tests/mixed_line_ending_test.py

@@ -0,0 +1,113 @@
+from __future__ import absolute_import
+from __future__ import unicode_literals
+
+import pytest
+
+from pre_commit_hooks.mixed_line_ending import main
+
+
+@pytest.mark.parametrize(
+    ('input_s', 'output'),
+    (
+        # mixed with majority of 'LF'
+        (b'foo\r\nbar\nbaz\n', b'foo\nbar\nbaz\n'),
+        # mixed with majority of 'CRLF'
+        (b'foo\r\nbar\nbaz\r\n', b'foo\r\nbar\r\nbaz\r\n'),
+        # mixed with majority of 'CR'
+        (b'foo\rbar\nbaz\r', b'foo\rbar\rbaz\r'),
+        # mixed with as much 'LF' as 'CRLF'
+        (b'foo\r\nbar\n', b'foo\nbar\n'),
+        # mixed with as much 'LF' as 'CR'
+        (b'foo\rbar\n', b'foo\nbar\n'),
+        # mixed with as much 'CRLF' as 'CR'
+        (b'foo\r\nbar\r', b'foo\r\nbar\r\n'),
+        # mixed with as much 'CRLF' as 'LF' as 'CR'
+        (b'foo\r\nbar\nbaz\r', b'foo\nbar\nbaz\n'),
+    ),
+)
+def test_mixed_line_ending_fixes_auto(input_s, output, tmpdir):
+    path = tmpdir.join('file.txt')
+    path.write_binary(input_s)
+    ret = main((path.strpath,))
+
+    assert ret == 1
+    assert path.read_binary() == output
+
+
+def test_non_mixed_no_newline_end_of_file(tmpdir):
+    path = tmpdir.join('f.txt')
+    path.write_binary(b'foo\nbar\nbaz')
+    assert not main((path.strpath,))
+    # the hook *could* fix the end of the file, but leaves it alone
+    # this is mostly to document the current behaviour
+    assert path.read_binary() == b'foo\nbar\nbaz'
+
+
+def test_mixed_no_newline_end_of_file(tmpdir):
+    path = tmpdir.join('f.txt')
+    path.write_binary(b'foo\r\nbar\nbaz')
+    assert main((path.strpath,))
+    # the hook rewrites the end of the file, this is slightly inconsistent
+    # with the non-mixed case but I think this is the better behaviour
+    # this is mostly to document the current behaviour
+    assert path.read_binary() == b'foo\nbar\nbaz\n'
+
+
+@pytest.mark.parametrize(
+    ('fix_option', 'input_s'),
+    (
+        # All --fix=auto with uniform line endings should be ok
+        ('--fix=auto', b'foo\r\nbar\r\nbaz\r\n'),
+        ('--fix=auto', b'foo\rbar\rbaz\r'),
+        ('--fix=auto', b'foo\nbar\nbaz\n'),
+        # --fix=crlf with crlf endings
+        ('--fix=crlf', b'foo\r\nbar\r\nbaz\r\n'),
+        # --fix=lf with lf endings
+        ('--fix=lf', b'foo\nbar\nbaz\n'),
+    ),
+)
+def test_line_endings_ok(fix_option, input_s, tmpdir):
+    path = tmpdir.join('input.txt')
+    path.write_binary(input_s)
+    ret = main((fix_option, path.strpath))
+
+    assert ret == 0
+    assert path.read_binary() == input_s
+
+
+def test_no_fix_does_not_modify(tmpdir):
+    path = tmpdir.join('input.txt')
+    contents = b'foo\r\nbar\rbaz\nwomp\n'
+    path.write_binary(contents)
+    ret = main(('--fix=no', path.strpath))
+
+    assert ret == 1
+    assert path.read_binary() == contents
+
+
+def test_fix_lf(tmpdir):
+    path = tmpdir.join('input.txt')
+    path.write_binary(b'foo\r\nbar\rbaz\n')
+    ret = main(('--fix=lf', path.strpath))
+
+    assert ret == 1
+    assert path.read_binary() == b'foo\nbar\nbaz\n'
+
+
+def test_fix_crlf(tmpdir):
+    path = tmpdir.join('input.txt')
+    path.write_binary(b'foo\r\nbar\rbaz\n')
+    ret = main(('--fix=crlf', path.strpath))
+
+    assert ret == 1
+    assert path.read_binary() == b'foo\r\nbar\r\nbaz\r\n'
+
+
+def test_fix_lf_all_crlf(tmpdir):
+    """Regression test for #239"""
+    path = tmpdir.join('input.txt')
+    path.write_binary(b'foo\r\nbar\r\n')
+    ret = main(('--fix=lf', path.strpath))
+
+    assert ret == 1
+    assert path.read_binary() == b'foo\nbar\n'

tests/no_commit_to_branch_test.py

@@ -0,0 +1,59 @@
+from __future__ import absolute_import
+from __future__ import unicode_literals
+
+import pytest
+
+from pre_commit_hooks.no_commit_to_branch import is_on_branch
+from pre_commit_hooks.no_commit_to_branch import main
+from pre_commit_hooks.util import cmd_output
+
+
+def test_other_branch(temp_git_dir):
+    with temp_git_dir.as_cwd():
+        cmd_output('git', 'checkout', '-b', 'anotherbranch')
+        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(('master',)) is False
+
+
+def test_multi_branch_fail(temp_git_dir):
+    with temp_git_dir.as_cwd():
+        cmd_output('git', 'checkout', '-b', 'another/branch')
+        assert is_on_branch(('another/branch',)) is True
+
+
+def test_master_branch(temp_git_dir):
+    with temp_git_dir.as_cwd():
+        assert is_on_branch(('master',)) is True
+
+
+def test_main_branch_call(temp_git_dir):
+    with temp_git_dir.as_cwd():
+        cmd_output('git', 'checkout', '-b', 'other')
+        assert main(('--branch', 'other')) == 1
+
+
+@pytest.mark.parametrize('branch_name', ('b1', 'b2'))
+def test_forbid_multiple_branches(temp_git_dir, branch_name):
+    with temp_git_dir.as_cwd():
+        cmd_output('git', 'checkout', '-b', branch_name)
+        assert main(('--branch', 'b1', '--branch', 'b2'))
+
+
+def test_main_default_call(temp_git_dir):
+    with temp_git_dir.as_cwd():
+        cmd_output('git', 'checkout', '-b', 'anotherbranch')
+        assert main(()) == 0
+
+
+def test_not_on_a_branch(temp_git_dir):
+    with temp_git_dir.as_cwd():
+        cmd_output('git', 'commit', '--no-gpg-sign', '--allow-empty', '-m1')
+        head = cmd_output('git', 'rev-parse', 'HEAD').strip()
+        cmd_output('git', 'checkout', head)
+        # we're not on a branch!
+        assert main(()) == 0

tests/pretty_format_json_test.py

@@ -1,53 +1,66 @@
 import shutil
 
 import pytest
+from six import PY2
 
-from pre_commit_hooks.pretty_format_json import parse_indent
+from pre_commit_hooks.pretty_format_json import parse_num_to_int
 from pre_commit_hooks.pretty_format_json import pretty_format_json
 from testing.util import get_resource_path
 
 
-def test_parse_indent():
+def test_parse_num_to_int():
-    assert parse_indent('0') == ''
+    assert parse_num_to_int('0') == 0
-    assert parse_indent('2') == '  '
+    assert parse_num_to_int('2') == 2
-    assert parse_indent('\t') == '\t'
+    assert parse_num_to_int('\t') == '\t'
-    with pytest.raises(ValueError):
+    assert parse_num_to_int('  ') == '  '
-        parse_indent('a')
-    with pytest.raises(ValueError):
-        parse_indent('-2')
 
 
-@pytest.mark.parametrize(('filename', 'expected_retval'), (
+@pytest.mark.parametrize(
-    ('not_pretty_formatted_json.json', 1),
+    ('filename', 'expected_retval'), (
-    ('unsorted_pretty_formatted_json.json', 1),
+        ('not_pretty_formatted_json.json', 1),
-    ('pretty_formatted_json.json', 0),
+        ('unsorted_pretty_formatted_json.json', 1),
-))
+        ('non_ascii_pretty_formatted_json.json', 1),
+        ('pretty_formatted_json.json', 0),
+    ),
+)
 def test_pretty_format_json(filename, expected_retval):
     ret = pretty_format_json([get_resource_path(filename)])
     assert ret == expected_retval
 
 
-@pytest.mark.parametrize(('filename', 'expected_retval'), (
+@pytest.mark.parametrize(
-    ('not_pretty_formatted_json.json', 1),
+    ('filename', 'expected_retval'), (
-    ('unsorted_pretty_formatted_json.json', 0),
+        ('not_pretty_formatted_json.json', 1),
-    ('pretty_formatted_json.json', 0),
+        ('unsorted_pretty_formatted_json.json', 0),
-))
+        ('non_ascii_pretty_formatted_json.json', 1),
+        ('pretty_formatted_json.json', 0),
+    ),
+)
 def test_unsorted_pretty_format_json(filename, expected_retval):
     ret = pretty_format_json(['--no-sort-keys', get_resource_path(filename)])
     assert ret == expected_retval
 
 
-@pytest.mark.parametrize(('filename', 'expected_retval'), (
+@pytest.mark.skipif(PY2, reason="Requires Python3")
-    ('not_pretty_formatted_json.json', 1),
+@pytest.mark.parametrize(
-    ('unsorted_pretty_formatted_json.json', 1),
+    ('filename', 'expected_retval'), (
-    ('pretty_formatted_json.json', 1),
+        ('not_pretty_formatted_json.json', 1),
-    ('tab_pretty_formatted_json.json', 0),
+        ('unsorted_pretty_formatted_json.json', 1),
-))
+        ('non_ascii_pretty_formatted_json.json', 1),
-def test_tab_pretty_format_json(filename, expected_retval):
+        ('pretty_formatted_json.json', 1),
+        ('tab_pretty_formatted_json.json', 0),
+    ),
+)
+def test_tab_pretty_format_json(filename, expected_retval):  # pragma: no cover
     ret = pretty_format_json(['--indent', '\t', get_resource_path(filename)])
     assert ret == expected_retval
 
 
+def test_non_ascii_pretty_format_json():
+    ret = pretty_format_json(['--no-ensure-ascii', get_resource_path('non_ascii_pretty_formatted_json.json')])
+    assert ret == 0
+
+
 def test_autofix_pretty_format_json(tmpdir):
     srcfile = tmpdir.join('to_be_json_formatted.json')
     shutil.copyfile(

tests/readme_test.py

@@ -7,7 +7,9 @@ import yaml
 
 
 def test_readme_contains_all_hooks():
-    readme_contents = io.open('README.md').read()
+    with io.open('README.md', encoding='UTF-8') as f:
-    hooks = yaml.load(io.open('hooks.yaml').read())
+        readme_contents = f.read()
+    with io.open('.pre-commit-hooks.yaml', encoding='UTF-8') as f:
+        hooks = yaml.load(f)
     for hook in hooks:
-        assert '`{0}`'.format(hook['id']) in readme_contents
+        assert '`{}`'.format(hook['id']) in readme_contents

tests/requirements_txt_fixer_test.py

@@ -1,31 +1,45 @@
 import pytest
 
+from pre_commit_hooks.requirements_txt_fixer import FAIL
 from pre_commit_hooks.requirements_txt_fixer import fix_requirements_txt
+from pre_commit_hooks.requirements_txt_fixer import PASS
 from pre_commit_hooks.requirements_txt_fixer import Requirement
 
-# Input, expected return value, expected output
+
-TESTS = (
+@pytest.mark.parametrize(
-    (b'foo\nbar\n', 1, b'bar\nfoo\n'),
+    ('input_s', 'expected_retval', 'output'),
-    (b'bar\nfoo\n', 0, b'bar\nfoo\n'),
+    (
-    (b'#comment1\nfoo\n#comment2\nbar\n', 1, b'#comment2\nbar\n#comment1\nfoo\n'),
+        (b'', PASS, b''),
-    (b'#comment1\nbar\n#comment2\nfoo\n', 0, b'#comment1\nbar\n#comment2\nfoo\n'),
+        (b'\n', PASS, b'\n'),
-    (b'#comment\n\nfoo\nbar\n', 1, b'#comment\n\nbar\nfoo\n'),
+        (b'# intentionally empty\n', PASS, b'# intentionally empty\n'),
-    (b'#comment\n\nbar\nfoo\n', 0, b'#comment\n\nbar\nfoo\n'),
+        (b'foo\n# comment at end\n', PASS, b'foo\n# comment at end\n'),
-    (b'\nfoo\nbar\n', 1, b'bar\n\nfoo\n'),
+        (b'foo\nbar\n', FAIL, b'bar\nfoo\n'),
-    (b'\nbar\nfoo\n', 0, b'\nbar\nfoo\n'),
+        (b'bar\nfoo\n', PASS, b'bar\nfoo\n'),
-    (b'pyramid==1\npyramid-foo==2\n', 0, b'pyramid==1\npyramid-foo==2\n'),
+        (b'#comment1\nfoo\n#comment2\nbar\n', FAIL, b'#comment2\nbar\n#comment1\nfoo\n'),
-    (b'ocflib\nDjango\nPyMySQL\n', 1, b'Django\nocflib\nPyMySQL\n'),
+        (b'#comment1\nbar\n#comment2\nfoo\n', PASS, b'#comment1\nbar\n#comment2\nfoo\n'),
-    (b'-e git+ssh://git_url@tag#egg=ocflib\nDjango\nPyMySQL\n', 1, b'Django\n-e git+ssh://git_url@tag#egg=ocflib\nPyMySQL\n'),
+        (b'#comment\n\nfoo\nbar\n', FAIL, b'#comment\n\nbar\nfoo\n'),
+        (b'#comment\n\nbar\nfoo\n', PASS, b'#comment\n\nbar\nfoo\n'),
+        (b'\nfoo\nbar\n', FAIL, b'bar\n\nfoo\n'),
+        (b'\nbar\nfoo\n', PASS, b'\nbar\nfoo\n'),
+        (b'pyramid==1\npyramid-foo==2\n', PASS, b'pyramid==1\npyramid-foo==2\n'),
+        (b'ocflib\nDjango\nPyMySQL\n', FAIL, b'Django\nocflib\nPyMySQL\n'),
+        (
+            b'-e git+ssh://git_url@tag#egg=ocflib\nDjango\nPyMySQL\n',
+            FAIL,
+            b'Django\n-e git+ssh://git_url@tag#egg=ocflib\nPyMySQL\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'),
+    ),
 )
-
-
-@pytest.mark.parametrize(('input_s', 'expected_retval', 'output'), TESTS)
 def test_integration(input_s, expected_retval, output, tmpdir):
     path = tmpdir.join('file.txt')
     path.write_binary(input_s)
 
-    assert fix_requirements_txt([path.strpath]) == expected_retval
+    output_retval = fix_requirements_txt([path.strpath])
+
     assert path.read_binary() == output
+    assert output_retval == expected_retval
 
 
 def test_requirement_object():

tests/sort_simple_yaml_test.py

@@ -0,0 +1,120 @@
+from __future__ import absolute_import
+from __future__ import unicode_literals
+
+import os
+
+import pytest
+
+from pre_commit_hooks.sort_simple_yaml import first_key
+from pre_commit_hooks.sort_simple_yaml import main
+from pre_commit_hooks.sort_simple_yaml import parse_block
+from pre_commit_hooks.sort_simple_yaml import parse_blocks
+from pre_commit_hooks.sort_simple_yaml import sort
+
+RETVAL_GOOD = 0
+RETVAL_BAD = 1
+TEST_SORTS = [
+    (
+        ['c: true', '', 'b: 42', 'a: 19'],
+        ['b: 42', 'a: 19', '', 'c: true'],
+        RETVAL_BAD,
+    ),
+
+    (
+        ['# i am', '# a header', '', 'c: true', '', 'b: 42', 'a: 19'],
+        ['# i am', '# a header', '', 'b: 42', 'a: 19', '', 'c: true'],
+        RETVAL_BAD,
+    ),
+
+    (
+        ['# i am', '# a header', '', 'already: sorted', '', 'yup: i am'],
+        ['# i am', '# a header', '', 'already: sorted', '', 'yup: i am'],
+        RETVAL_GOOD,
+    ),
+
+    (
+        ['# i am', '# a header'],
+        ['# i am', '# a header'],
+        RETVAL_GOOD,
+    ),
+]
+
+
+@pytest.mark.parametrize('bad_lines,good_lines,retval', TEST_SORTS)
+def test_integration_good_bad_lines(tmpdir, bad_lines, good_lines, retval):
+    file_path = os.path.join(tmpdir.strpath, 'foo.yaml')
+
+    with open(file_path, 'w') as f:
+        f.write("\n".join(bad_lines) + "\n")
+
+    assert main([file_path]) == retval
+
+    with open(file_path, 'r') as f:
+        assert [line.rstrip() for line in f.readlines()] == good_lines
+
+
+def test_parse_header():
+    lines = ['# some header', '# is here', '', 'this is not a header']
+    assert parse_block(lines, header=True) == ['# some header', '# is here']
+    assert lines == ['', 'this is not a header']
+
+    lines = ['this is not a header']
+    assert parse_block(lines, header=True) == []
+    assert lines == ['this is not a header']
+
+
+def test_parse_block():
+    # a normal block
+    lines = ['a: 42', 'b: 17', '', 'c: 19']
+    assert parse_block(lines) == ['a: 42', 'b: 17']
+    assert lines == ['', 'c: 19']
+
+    # a block at the end
+    lines = ['c: 19']
+    assert parse_block(lines) == ['c: 19']
+    assert lines == []
+
+    # no block
+    lines = []
+    assert parse_block(lines) == []
+    assert lines == []
+
+
+def test_parse_blocks():
+    # normal blocks
+    lines = ['a: 42', 'b: 17', '', 'c: 19']
+    assert parse_blocks(lines) == [['a: 42', 'b: 17'], ['c: 19']]
+    assert lines == []
+
+    # a single block
+    lines = ['a: 42', 'b: 17']
+    assert parse_blocks(lines) == [['a: 42', 'b: 17']]
+    assert lines == []
+
+    # no blocks
+    lines = []
+    assert parse_blocks(lines) == []
+    assert lines == []
+
+
+def test_first_key():
+    # first line
+    lines = ['a: 42', 'b: 17', '', 'c: 19']
+    assert first_key(lines) == 'a: 42'
+
+    # second line
+    lines = ['# some comment', 'a: 42', 'b: 17', '', 'c: 19']
+    assert first_key(lines) == 'a: 42'
+
+    # second line with quotes
+    lines = ['# some comment', '"a": 42', 'b: 17', '', 'c: 19']
+    assert first_key(lines) == 'a": 42'
+
+    # no lines
+    lines = []
+    assert first_key(lines) is None
+
+
+@pytest.mark.parametrize('bad_lines,good_lines,_', TEST_SORTS)
+def test_sort(bad_lines, good_lines, _):
+    assert sort(bad_lines) == good_lines

tests/string_fixer_test.py

@@ -22,16 +22,20 @@ TESTS = (
     # Docstring
     ('""" Foo """', '""" Foo """', 0),
     (
-        textwrap.dedent("""
+        textwrap.dedent(
+            """
         x = " \\
         foo \\
         "\n
-        """),
+        """,
-        textwrap.dedent("""
+        ),
+        textwrap.dedent(
+            """
         x = ' \\
         foo \\
         '\n
-        """),
+        """,
+        ),
         1,
     ),
     ('"foo""bar"', "'foo''bar'", 1),

tests/tests_should_end_in_test_test.py

@@ -12,7 +12,7 @@ def test_validate_files_one_fails():
 
 
 def test_validate_files_django_all_pass():
-    ret = validate_files(['--django', 'test_foo.py', 'test_bar.py', 'tests/test_baz.py'])
+    ret = validate_files(['--django', 'tests.py', 'test_foo.py', 'test_bar.py', 'tests/test_baz.py'])
     assert ret == 0
 
 

tests/trailing_whitespace_fixer_test.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 
 import pytest
 
-from pre_commit_hooks.trailing_whitespace_fixer import fix_trailing_whitespace
+from pre_commit_hooks.trailing_whitespace_fixer import main
 
 
 @pytest.mark.parametrize(
@@ -16,14 +16,22 @@ from pre_commit_hooks.trailing_whitespace_fixer import fix_trailing_whitespace
 def test_fixes_trailing_whitespace(input_s, expected, tmpdir):
     path = tmpdir.join('file.txt')
     path.write(input_s)
-    assert fix_trailing_whitespace((path.strpath,)) == 1
+    assert main((path.strpath,)) == 1
     assert path.read() == expected
 
 
+def test_ok_no_newline_end_of_file(tmpdir):
+    filename = tmpdir.join('f')
+    filename.write_binary(b'foo\nbar')
+    ret = main((filename.strpath,))
+    assert filename.read_binary() == b'foo\nbar'
+    assert ret == 0
+
+
 def test_ok_with_dos_line_endings(tmpdir):
     filename = tmpdir.join('f')
     filename.write_binary(b'foo\r\nbar\r\nbaz\r\n')
-    ret = fix_trailing_whitespace((filename.strpath,))
+    ret = main((filename.strpath,))
     assert filename.read_binary() == b'foo\r\nbar\r\nbaz\r\n'
     assert ret == 0
 
@@ -31,14 +39,14 @@ def test_ok_with_dos_line_endings(tmpdir):
 def test_markdown_ok(tmpdir):
     filename = tmpdir.join('foo.md')
     filename.write_binary(b'foo  \n')
-    ret = fix_trailing_whitespace((filename.strpath,))
+    ret = main((filename.strpath,))
     assert filename.read_binary() == b'foo  \n'
     assert ret == 0
 
 
 # filename, expected input, expected output
 MD_TESTS_1 = (
-    ('foo.md', 'foo  \nbar \n  ', 'foo  \nbar\n\n'),
+    ('foo.md', 'foo  \nbar \n  ', 'foo  \nbar\n'),
     ('bar.Markdown', 'bar   \nbaz\t\n\t\n', 'bar  \nbaz\n\n'),
     ('.md', 'baz   \nquux  \t\n\t\n', 'baz\nquux\n\n'),
     ('txt', 'foo   \nbaz \n\t\n', 'foo\nbaz\n\n'),
@@ -49,7 +57,7 @@ MD_TESTS_1 = (
 def test_fixes_trailing_markdown_whitespace(filename, input_s, output, tmpdir):
     path = tmpdir.join(filename)
     path.write(input_s)
-    ret = fix_trailing_whitespace([path.strpath])
+    ret = main([path.strpath])
     assert ret == 1
     assert path.read() == output
 
@@ -68,16 +76,14 @@ MD_TESTS_2 = (
 def test_markdown_linebreak_ext_opt(filename, input_s, output, tmpdir):
     path = tmpdir.join(filename)
     path.write(input_s)
-    ret = fix_trailing_whitespace((
+    ret = main(('--markdown-linebreak-ext=TxT', path.strpath))
-        '--markdown-linebreak-ext=TxT', path.strpath
-    ))
     assert ret == 1
     assert path.read() == output
 
 
 # filename, expected input, expected output
 MD_TESTS_3 = (
-    ('foo.baz', 'foo  \nbar \n  ', 'foo  \nbar\n\n'),
+    ('foo.baz', 'foo  \nbar \n  ', 'foo  \nbar\n'),
     ('bar', 'bar   \nbaz\t\n\t\n', 'bar  \nbaz\n\n'),
 )
 
@@ -87,9 +93,7 @@ def test_markdown_linebreak_ext_opt_all(filename, input_s, output, tmpdir):
     path = tmpdir.join(filename)
     path.write(input_s)
     # need to make sure filename is not treated as argument to option
-    ret = fix_trailing_whitespace([
+    ret = main(('--markdown-linebreak-ext=*', path.strpath))
-        '--markdown-linebreak-ext=*', path.strpath,
-    ])
     assert ret == 1
     assert path.read() == output
 
@@ -97,7 +101,7 @@ def test_markdown_linebreak_ext_opt_all(filename, input_s, output, tmpdir):
 @pytest.mark.parametrize(('arg'), ('--', 'a.b', 'a/b'))
 def test_markdown_linebreak_ext_badopt(arg):
     with pytest.raises(SystemExit) as excinfo:
-        fix_trailing_whitespace(['--markdown-linebreak-ext', arg])
+        main(['--markdown-linebreak-ext', arg])
     assert excinfo.value.code == 2
 
 
@@ -112,19 +116,15 @@ MD_TESTS_4 = (
 def test_no_markdown_linebreak_ext_opt(filename, input_s, output, tmpdir):
     path = tmpdir.join(filename)
     path.write(input_s)
-    ret = fix_trailing_whitespace(['--no-markdown-linebreak-ext', path.strpath])
+    ret = main(['--no-markdown-linebreak-ext', path.strpath])
     assert ret == 1
     assert path.read() == output
 
 
-def test_returns_zero_for_no_changes():
-    assert fix_trailing_whitespace([__file__]) == 0
-
-
 def test_preserve_non_utf8_file(tmpdir):
     non_utf8_bytes_content = b'<a>\xe9 \n</a>\n'
     path = tmpdir.join('file.txt')
     path.write_binary(non_utf8_bytes_content)
-    ret = fix_trailing_whitespace([path.strpath])
+    ret = main([path.strpath])
     assert ret == 1
     assert path.size() == (len(non_utf8_bytes_content) - 1)

tox.ini

@@ -1,7 +1,6 @@
 [tox]
-project = pre_commit_hooks
 # These should match the travis env list
-envlist = py27,py34,py35,pypy
+envlist = py27,py35,py36,pypy
 
 [testenv]
 deps = -rrequirements-dev.txt
@@ -12,18 +11,14 @@ setenv =
     GIT_AUTHOR_EMAIL = "test@example.com"
     GIT_COMMITTER_EMAIL = "test@example.com"
 commands =
-    # coverage erase
+    coverage erase
-    # coverage run -m pytest {posargs:tests}
+    coverage run -m pytest {posargs:tests}
-    # coverage report --show-missing --fail-under 100
+    coverage report --fail-under 100
     pre-commit install -f --install-hooks
     pre-commit run --all-files
 
-[testenv:venv]
-envdir = venv-{[tox]project}
-commands =
-
 [flake8]
 max-line-length=131
 
 [pep8]
-ignore=E265,E309,E501
+ignore=E265,E501