.gitignore

# M³GIM Project .gitignore

# ==========================================
# Python
# ==========================================
__pycache__/
*.py[cod]
*$py.class
*.so
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST

# Virtual environments
venv/
env/
ENV/
.venv/
.ENV/

# PyCharm
.idea/

# VS Code
.vscode/

# Jupyter Notebook
.ipynb_checkpoints/
*.ipynb

# pytest
.pytest_cache/
.coverage
htmlcov/
.tox/

# mypy
.mypy_cache/
.dmypy.json
dmypy.json

# ==========================================
# Data Files
# ==========================================
# Large data files (use Git LFS or external storage)
*.xlsx
*.xls
*.csv
!data/source/*.xlsx        # Keep source Excel spreadsheet for reproducibility
!data/vocabularies/*.json  # Keep vocabulary files

# PDF scans (too large for Git)
*.pdf

# Compressed archives
*.zip
*.tar.gz
*.rar
*.7z

# Temporary data files
data/raw_sheets_export.json
data/*_temp.json
data/*_backup_*.json

# Pipeline-generated view JSONs (copies live in docs/data/)
data/output/views/

# ==========================================
# Credentials & Secrets
# ==========================================
.env
.env.local
.env.*.local
secrets.json
credentials.json
service_account.json
*.key
*.pem

# Google OAuth tokens
token.pickle
token.json

# ==========================================
# Claude Code IDE
# ==========================================
.claude/

# ==========================================
# Operating Systems
# ==========================================
# macOS
.DS_Store
.AppleDouble
.LSOverride
Icon
._*
.DocumentRevisions-V100
.fseventsd
.Spotlight-V100
.TemporaryItems
.Trashes
.VolumeIcon.icns
.com.apple.timemachine.donotpresent
.AppleDB
.AppleDesktop
Network Trash Folder
Temporary Items
.apdisk

# Windows
Thumbs.db
Thumbs.db:encryptable
ehthumbs.db
ehthumbs_vista.db
*.stackdump
[Dd]esktop.ini
$RECYCLE.BIN/
*.cab
*.msi
*.msix
*.msm
*.msp
*.lnk

# Linux
*~
.fuse_hidden*
.directory
.Trash-*
.nfs*

# ==========================================
# Logs & Temporary Files
# ==========================================
*.log
logs/
*.tmp
*.bak
*.swp
*.swo
*~.nib
*.orig
*.rej

# ==========================================
# Knowledge Base
# ==========================================
# knowledge/ is tracked — contains destilled project knowledge

# Source documents (DSGVO: live in Obsidian vault, not in public repo)
antrag.md
handreichung.md

# ==========================================
# IDE & Editor Files
# ==========================================
# Sublime Text
*.sublime-workspace
*.sublime-project

# Atom
.atom/

# Emacs
*~
\#*\#
/.emacs.desktop
/.emacs.desktop.lock
*.elc
auto-save-list
tramp
.\#*

# Vim
[._]*.s[a-v][a-z]
[._]*.sw[a-p]
[._]s[a-rt-v][a-z]
[._]ss[a-gi-z]
[._]sw[a-p]
Session.vim
Sessionx.vim
.netrwhist

# ==========================================
# Build & Distribution
# ==========================================
node_modules/
package-lock.json
yarn.lock

# ==========================================
# GitHub Actions
# ==========================================
# GitHub Actions artifacts (don't ignore workflows)
!.github/workflows/

# ==========================================
# Project-Specific
# ==========================================
# Old prototype files (if moved out of archive_development/)
# Uncomment if cleanup removes these from tracking
# archive_development/

# Testing outputs
tests/outputs/
tests/*.html

# ==========================================
# Comments & Notes
# ==========================================
# This .gitignore is designed for the M³GIM project
#
# What we DO track:
# - All Python scripts (preprocessing/, scripts/)
# - All documentation (docs/, *.md)
# - Processed JSON data (data/*.json)
# - HTML catalog (archive_catalog.html)
# - Templates (templates/)
# - Tests (tests/)
# - GitHub Actions workflows (.github/workflows/)
# - Controlled vocabularies (data/vocabularies/*.json)
#
# What we DON'T track:
# - Large source files (*.xlsx, *.pdf)
# - Generated files (__pycache__, *.pyc)
# - Credentials (.env, secrets.json)
# - IDE settings (.vscode/, .idea/)
# - OS files (.DS_Store, Thumbs.db)
# - Virtual environments (venv/)
#
# For sensitive data:
# - Source Excel file should remain on Google Sheets
# - PDF scans hosted externally (university server)
# - Credentials stored in GitHub Secrets
#
# See STRUCTURE.md for full folder organization