Merge pull request #1212 from yambottle/DEV-861-pre-commit

Dev 861 pre commit

Author: drewyangdev

.coveragerc

@@ -3,4 +3,4 @@ branch = False
 source = datajoint
 
 [report]
-show_missing = True
+show_missing = True

.devcontainer/devcontainer.json

@@ -47,4 +47,4 @@
 	}
 	// Uncomment to connect as an existing user other than the container default. More info: https://aka.ms/dev-containers-non-root.
 	// "remoteUser": "devcontainer"
-}
+}

.devcontainer/docker-compose.yml

@@ -29,4 +29,3 @@ services:
 
     # Overrides default command so things don't shut down after the process ends.
     command: /bin/sh -c "while sleep 1000; do :; done"
-

.dockerignore

@@ -3,4 +3,4 @@ build
 *.egg-info
 dist
 .vscode
-__pycache__
+__pycache__

.github/workflows/docs.yaml

@@ -16,4 +16,4 @@ jobs:
           export UPSTREAM_REPO=https://github.com/${GITHUB_REPOSITORY}.git
           export HOST_UID=$(id -u)
           docker compose -f docs/docker-compose.yaml up --exit-code-from docs --build
-          git push origin gh-pages
+          git push origin gh-pages

.gitignore

@@ -1,35 +1,187 @@
-.ipynb_checkpoints/
-*.json
-*/.*.swp
-*/.*.swo
-*/*.pyc
-.DS_Store
-__*__
-.idea/
-*.pyc
-.python-version
-*.egg-info/
+# https://github.com/github/gitignore/blob/main/Python.gitignore
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
 dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
 MANIFEST
-.vagrant/
-dj_local_conf.json
-build/
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
 .coverage
-./tests/.coverage
-./tests/dj-store/*
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
 *.log
-*.env
-docker-compose.yml
-notebook
-__main__.py
-jupyter_custom.js
-.eggs
-*.code-workspace
-docs/site
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
 
+# Flask stuff:
+instance/
+.webassets-cache
 
-!.vscode/settings.json
-!.vscode/launch.json
-!.devcontainer/devcontainer.json
-!.devcontainer/docker-compose.yml
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
 
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+# VS Code
+.vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+######################
+
+# Mac OS
+.DS_Store
+
+# Datajoint related files
+dj_local_conf.json
+*.env
+!.vscode/launch.json

.pre-commit-config.yaml

@@ -0,0 +1,50 @@
+# pip install datajoint[test]
+# pre-commit install
+# pre-commit run --all-files
+# pre-commit autoupdate
+# SKIP=flake8 git commit -m "foo"
+
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v5.0.0
+  hooks:
+  - id: check-yaml
+    exclude: 'docs/mkdocs.yaml' # exclude mkdocs.yaml since pymdownx.emoji !! usage
+  - id: check-json
+    exclude: '(.vscode|.devcontainer)' # exclude these since // was used for comments
+  - id: check-toml
+  - id: trailing-whitespace
+  - id: end-of-file-fixer
+  - id: check-added-large-files
+- repo: https://github.com/codespell-project/codespell
+  rev: v2.4.1
+  hooks:
+    - id: codespell
+- repo: https://github.com/pycqa/isort
+  rev: 5.12.0  # Use the latest stable version
+  hooks:
+    - id: isort
+      args:
+        - --profile=black  # Optional, makes isort compatible with Black
+- repo: https://github.com/psf/black
+  rev: 24.2.0 # matching versions in pyproject.toml and github actions
+  hooks:
+  - id: black
+    args: ["--check", "-v", "datajoint", "tests", "--diff"] # --required-version is conflicting with pre-commit
+- repo: https://github.com/PyCQA/flake8
+  rev: 7.1.2
+  hooks:
+  - id: flake8
+    args:
+      - --ignore=E203,E722,W503
+      - --count
+      - --max-complexity=62
+      - --max-line-length=127
+      - --statistics
+      - --per-file-ignores=datajoint/diagram.py:C901
+    files: datajoint # a lot of files in tests are not compliant
+
+## Suggest to add pytest hook that runs unit test | Prerequisite: split unit/integration test
+## https://github.com/datajoint/datajoint-python/issues/1211

.vscode/launch.json

@@ -13,4 +13,4 @@
             "justMyCode": false
         }
     ]
-}
+}

.vscode/settings.json

@@ -17,5 +17,5 @@
     "[dockercompose]": {
         "editor.defaultFormatter": "disable"
     },
-    "files.autoSave": "off"
-}
+    //"files.autoSave": "off"
+}

README.md

@@ -5,17 +5,17 @@
 
 # Welcome to DataJoint for Python!
 
-DataJoint for Python is a framework for scientific workflow management based on 
-relational principles. DataJoint is built on the foundation of the relational data 
-model and prescribes a consistent method for organizing, populating, computing, and 
+DataJoint for Python is a framework for scientific workflow management based on
+relational principles. DataJoint is built on the foundation of the relational data
+model and prescribes a consistent method for organizing, populating, computing, and
 querying data.
 
-DataJoint was initially developed in 2009 by Dimitri Yatsenko in Andreas Tolias' Lab at 
-Baylor College of Medicine for the distributed processing and management of large 
-volumes of data streaming from regular experiments. Starting in 2011, DataJoint has 
-been available as an open-source project adopted by other labs and improved through 
+DataJoint was initially developed in 2009 by Dimitri Yatsenko in Andreas Tolias' Lab at
+Baylor College of Medicine for the distributed processing and management of large
+volumes of data streaming from regular experiments. Starting in 2011, DataJoint has
+been available as an open-source project adopted by other labs and improved through
 contributions from several developers.
-Presently, the primary developer of DataJoint open-source software is the company 
+Presently, the primary developer of DataJoint open-source software is the company
 DataJoint (https://datajoint.com).
 
 ## Data Pipeline Example