chore: add project configuration files including .gitattributes, .gitignore, and pre-commit setup

.gitattributes

@@ -0,0 +1,386 @@
+# Project specific .gitattributes here
+
+
+
+# ================================
+# gitattributes tempaltes from https://github.com/gitattributes/gitattributes
+# Common.gitattributes
+# Markdown.gitattributes
+# Python.gitattributes
+# Vim.gitattributes
+# Web.gitattributes
+# VisualStudioCode.gitattributes
+
+# ================ Common
+
+# Common settings that generally should always be used with your language specific settings
+
+# Auto detect text files and perform LF normalization
+*          text=auto
+
+#
+# The above will handle all files NOT found below
+#
+
+# Documents
+*.bibtex   text diff=bibtex
+*.doc      diff=astextplain
+*.DOC      diff=astextplain
+*.docx     diff=astextplain
+*.DOCX     diff=astextplain
+*.dot      diff=astextplain
+*.DOT      diff=astextplain
+*.pdf      diff=astextplain
+*.PDF      diff=astextplain
+*.rtf      diff=astextplain
+*.RTF      diff=astextplain
+*.md       text diff=markdown
+*.mdx      text diff=markdown
+*.tex      text diff=tex
+*.adoc     text
+*.textile  text
+*.mustache text
+*.csv      text eol=crlf
+*.tab      text
+*.tsv      text
+*.txt      text
+*.sql      text
+*.epub     diff=astextplain
+
+# Graphics
+*.png      binary
+*.jpg      binary
+*.jpeg     binary
+*.gif      binary
+*.tif      binary
+*.tiff     binary
+*.ico      binary
+# SVG treated as text by default.
+*.svg      text
+# If you want to treat it as binary,
+# use the following line instead.
+# *.svg    binary
+*.eps      binary
+
+# Scripts
+*.bash     text eol=lf
+*.fish     text eol=lf
+*.ksh      text eol=lf
+*.sh       text eol=lf
+*.zsh      text eol=lf
+# These are explicitly windows files and should use crlf
+*.bat      text eol=crlf
+*.cmd      text eol=crlf
+*.ps1      text eol=crlf
+
+# Serialisation
+*.json     text
+*.toml     text
+*.xml      text
+*.yaml     text
+*.yml      text
+
+# Archives
+*.7z       binary
+*.bz       binary
+*.bz2      binary
+*.bzip2    binary
+*.gz       binary
+*.lz       binary
+*.lzma     binary
+*.rar      binary
+*.tar      binary
+*.taz      binary
+*.tbz      binary
+*.tbz2     binary
+*.tgz      binary
+*.tlz      binary
+*.txz      binary
+*.xz       binary
+*.Z        binary
+*.zip      binary
+*.zst      binary
+
+# Text files where line endings should be preserved
+*.patch    -text
+
+#
+# Exclude files from exporting
+#
+
+.gitattributes export-ignore
+.gitignore     export-ignore
+.gitkeep       export-ignore
+
+# ================ Markdown
+
+# Apply override to all files in the directory
+*.md linguist-detectable
+
+# ================ Python
+
+# Basic .gitattributes for a python repo.
+
+# Source files
+# ============
+*.pxd    text diff=python
+*.py     text diff=python
+*.py3    text diff=python
+*.pyw    text diff=python
+*.pyx    text diff=python
+*.pyz    text diff=python
+*.pyi    text diff=python
+
+# Binary files
+# ============
+*.db     binary
+*.p      binary
+*.pkl    binary
+*.pickle binary
+*.pyc    binary export-ignore
+*.pyo    binary export-ignore
+*.pyd    binary
+
+# Jupyter notebook
+*.ipynb  text eol=lf
+
+# Note: .db, .p, and .pkl files are associated
+# with the python modules ``pickle``, ``dbm.*``,
+# ``shelve``, ``marshal``, ``anydbm``, & ``bsddb``
+# (among others).
+
+# ================ Vim
+
+# Basic .gitattributes for a Vim repo.
+# Vim on Linux works with LF only, Vim on Windows works with both LF and CRLF
+
+# Source files
+# ============
+*.vim text eol=lf
+.vimrc text eol=lf
+.gvimrc text eol=lf
+
+# ================ Web
+
+## GITATTRIBUTES FOR WEB PROJECTS
+#
+# These settings are for any web project.
+#
+# Details per file setting:
+#   text    These files should be normalized (i.e. convert CRLF to LF).
+#   binary  These files are binary and should be left untouched.
+#
+# Note that binary is a macro for -text -diff.
+######################################################################
+
+# Auto detect
+##   Handle line endings automatically for files detected as
+##   text and leave all files detected as binary untouched.
+##   This will handle all files NOT defined below.
+*                 text=auto
+
+# Source code
+*.bash            text eol=lf
+*.bat             text eol=crlf
+*.cmd             text eol=crlf
+*.coffee          text
+*.css             text diff=css
+*.htm             text diff=html
+*.html            text diff=html
+*.inc             text
+*.ini             text
+*.js              text
+*.mjs             text
+*.cjs             text
+*.json            text
+*.jsx             text
+*.less            text
+*.ls              text
+*.map             text -diff
+*.od              text
+*.onlydata        text
+*.php             text diff=php
+*.pl              text
+*.ps1             text eol=crlf
+*.py              text diff=python
+*.rb              text diff=ruby
+*.sass            text
+*.scm             text
+*.scss            text diff=css
+*.sh              text eol=lf
+.husky/*          text eol=lf
+*.sql             text
+*.styl            text
+*.tag             text
+*.ts              text
+*.tsx             text
+*.xml             text
+*.xhtml           text diff=html
+
+# Docker
+Dockerfile        text
+
+# Documentation
+*.ipynb           text eol=lf
+*.markdown        text diff=markdown
+*.md              text diff=markdown
+*.mdwn            text diff=markdown
+*.mdown           text diff=markdown
+*.mkd             text diff=markdown
+*.mkdn            text diff=markdown
+*.mdtxt           text
+*.mdtext          text
+*.txt             text
+AUTHORS           text
+CHANGELOG         text
+CHANGES           text
+CONTRIBUTING      text
+COPYING           text
+copyright         text
+*COPYRIGHT*       text
+INSTALL           text
+license           text
+LICENSE           text
+NEWS              text
+readme            text
+*README*          text
+TODO              text
+
+# Templates
+*.dot             text
+*.ejs             text
+*.erb             text
+*.haml            text
+*.handlebars      text
+*.hbs             text
+*.hbt             text
+*.jade            text
+*.latte           text
+*.mustache        text
+*.njk             text
+*.phtml           text
+*.svelte          text
+*.tmpl            text
+*.tpl             text
+*.twig            text
+*.vue             text
+
+# Configs
+*.cnf             text
+*.conf            text
+*.config          text
+.editorconfig     text
+*.env             text
+.gitattributes    text
+.gitconfig        text
+.htaccess         text
+*.lock            text -diff
+package.json      text eol=lf
+package-lock.json text eol=lf -diff
+pnpm-lock.yaml    text eol=lf -diff
+.prettierrc       text
+yarn.lock         text -diff
+*.toml            text
+*.yaml            text
+*.yml             text
+browserslist      text
+Makefile          text
+makefile          text
+# Fixes syntax highlighting on GitHub to allow comments
+tsconfig.json     linguist-language=JSON-with-Comments
+
+# Heroku
+Procfile          text
+
+# Graphics
+*.ai              binary
+*.bmp             binary
+*.eps             binary
+*.gif             binary
+*.gifv            binary
+*.ico             binary
+*.jng             binary
+*.jp2             binary
+*.jpg             binary
+*.jpeg            binary
+*.jpx             binary
+*.jxr             binary
+*.pdf             binary
+*.png             binary
+*.psb             binary
+*.psd             binary
+# SVG treated as an asset (binary) by default.
+*.svg             text
+# If you want to treat it as binary,
+# use the following line instead.
+# *.svg           binary
+*.svgz            binary
+*.tif             binary
+*.tiff            binary
+*.wbmp            binary
+*.webp            binary
+
+# Audio
+*.kar             binary
+*.m4a             binary
+*.mid             binary
+*.midi            binary
+*.mp3             binary
+*.ogg             binary
+*.ra              binary
+
+# Video
+*.3gpp            binary
+*.3gp             binary
+*.as              binary
+*.asf             binary
+*.asx             binary
+*.avi             binary
+*.fla             binary
+*.flv             binary
+*.m4v             binary
+*.mng             binary
+*.mov             binary
+*.mp4             binary
+*.mpeg            binary
+*.mpg             binary
+*.ogv             binary
+*.swc             binary
+*.swf             binary
+*.webm            binary
+
+# Archives
+*.7z              binary
+*.gz              binary
+*.jar             binary
+*.rar             binary
+*.tar             binary
+*.zip             binary
+
+# Fonts
+*.ttf             binary
+*.eot             binary
+*.otf             binary
+*.woff            binary
+*.woff2           binary
+
+# Executables
+*.exe             binary
+*.pyc             binary
+# Prevents massive diffs caused by vendored, minified files
+**/.yarn/releases/**   binary
+**/.yarn/plugins/**    binary
+
+# RC files (like .babelrc or .eslintrc)
+*.*rc             text
+
+# Ignore files (like .npmignore or .gitignore)
+*.*ignore         text
+
+# Prevents massive diffs from built files
+dist/**           binary
+
+# ================ VisualStudioCode
+
+# Fix syntax highlighting on GitHub to allow comments
+.vscode/*.json linguist-language=JSON-with-Comments

.github/workflow/pre-commit.yml

@@ -0,0 +1,20 @@
+name: pre-commit
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - uses: actions/setup-python@v5
+      with:
+        python-version: "3.12"
+    - uses: actions/cache@v4
+      with:
+        path: ~/.cache/pre-commit
+        key: pre-commit-4|${{ env.pythonLocation }}|${{ hashFiles('.pre-commit-config.yaml') }}
+    - uses: pre-commit/action@v3.0.1

.gitignore

@@ -1,3 +1,243 @@
+# Project specific gitignore here
+
+# Cache
+**/data_cache/
+
+# ================================
+# gitignore tempaltes from https://github.com/github/gitignore
+# Cursor.gitignore
+# JetBrains.gitignore
+# Vim.gitignore
+# VirtualEnv.gitignore
+# VisualStudioCode.gitignore
+# macOS.gitignore
+# Linux.gitignore
+# Windows.gitignore
+# Python.gitignore
+
+# ================ Cursor
+
+.cursorignore
+.cursorindexingignore
+
+# ================ JetBrains
+
+# Covers JetBrains IDEs: IntelliJ, GoLand, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# AWS User-specific
+.idea/**/aws.xml
+
+# Generated files
+.idea/**/contentModel.xml
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/artifacts
+# .idea/compiler.xml
+# .idea/jarRepositories.xml
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+# *.iml
+# *.ipr
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# SonarLint plugin
+.idea/sonarlint/
+.idea/sonarlint.xml # see https://community.sonarsource.com/t/is-the-file-idea-idea-idea-sonarlint-xml-intended-to-be-under-source-control/121119
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based HTTP Client
+.idea/httpRequests
+http-client.private.env.json
+
+# Android studio 3.1+ serialized cache file
+.idea/caches/build_file_checksums.ser
+
+# Apifox Helper cache
+.idea/.cache/.Apifox_Helper
+.idea/ApifoxUploaderProjectSetting.xml
+
+# Github Copilot persisted session migrations, see: https://github.com/microsoft/copilot-intellij-feedback/issues/712#issuecomment-3322062215
+.idea/**/copilot.data.migration.*.xml
+
+# ================ Vim
+
+# Swap
+[._]*.s[a-v][a-z]
+# comment out the next line if you don't need vector files
+!*.svg
+[._]*.sw[a-p]
+[._]s[a-rt-v][a-z]
+[._]ss[a-gi-z]
+[._]sw[a-p]
+
+# Session
+Session.vim
+Sessionx.vim
+
+# Temporary
+.netrwhist
+*~
+# Auto-generated tag files
+tags
+# Persistent undo
+[._]*.un~
+
+# ================ VirtualEnv
+
+# Virtualenv
+# https://realpython.com/python-virtual-environments-a-primer/#the-virtualenv-project
+.Python
+[Bb]in
+[Ii]nclude
+[Ll]ib
+[Ll]ib64
+[Ll]ocal
+[Ss]cripts
+pyvenv.cfg
+.venv
+pip-selfcheck.json
+
+# ================ VisualStudioCode
+
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+!*.code-workspace
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+# ================ macOS
+
+# General
+.DS_Store
+.localized
+__MACOSX/
+.AppleDouble
+.LSOverride
+Icon[
+]
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+# ================ Linux
+
+*~
+
+# temporary files which can be created if a process still has a handle open of a deleted file
+.fuse_hidden*
+
+# Metadata left by Dolphin file manager, which comes with KDE Plasma
+.directory
+
+# Linux trash folder which might appear on any partition or disk
+.Trash-*
+
+# .nfs files are created when an open file is removed but is still being accessed
+.nfs*
+
+# Log files created by default by the nohup command
+nohup.out
+
+# ================ Windows
+
+# Windows thumbnail cache files
+Thumbs.db
+Thumbs.db:encryptable
+ehthumbs.db
+ehthumbs_vista.db
+
+# Dump file
+*.stackdump
+
+# Folder config file
+[Dd]esktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Windows Installer files
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
+
+# Windows shortcuts
+*.lnk
+
+# ================ Python
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[codz]
@@ -195,9 +435,9 @@ cython_debug/
 .abstra/
 
 # Visual Studio Code
-#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
 #   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
-#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   and can be added to the global gitignore or merged into this file. However, if you prefer,
 #   you could uncomment the following to ignore the entire vscode folder
 # .vscode/
 
@@ -214,6 +454,3 @@ __marimo__/
 
 # Streamlit
 .streamlit/secrets.toml
-
-# Cache
-**/data_cache/

.pre-commit-config.yaml

@@ -0,0 +1,33 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
+    hooks:
+      - id: trailing-whitespace
+      - id: detect-private-key
+      - id: end-of-file-fixer
+      - id: check-json
+      - id: check-toml
+      - id: check-xml
+      - id: check-yaml
+      - id: debug-statements
+      - id: name-tests-test
+      - id: requirements-txt-fixer
+
+  - repo: https://github.com/shellcheck-py/shellcheck-py
+    rev: v0.11.0.1
+    hooks:
+      - id: shellcheck
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.15.10
+    hooks:
+      # Run the linter.
+      - id: ruff-check
+        args: [--fix]
+      # Run the formatter.
+      - id: ruff-format
+
+  - repo: https://github.com/commit-check/commit-check
+    rev: v2.5.0
+    hooks:
+      - id: check-message