.gitattributes

# Git attributes for academic repository

# PDFs - treat as binary, don't diff
*.pdf binary
*.PDF binary

# Academic document formats - treat as binary
*.doc binary
*.docx binary
*.odt binary
*.rtf binary

# Data files - treat as binary
*.xlsx binary
*.xls binary
*.ods binary
*.rda binary
*.rds binary
*.RData binary
*.pkl binary
*.pickle binary
*.h5 binary
*.hdf5 binary
*.mat binary
*.sav binary

# Image files - treat as binary
*.png binary
*.jpg binary
*.jpeg binary
*.gif binary
*.bmp binary
*.tiff binary
*.svg binary
*.eps binary

# Text-based academic formats - use text diff
*.tex text
*.bib text
*.md text
*.txt text
*.csv text
*.tsv text
*.json text
*.xml text
*.yaml text
*.yml text

# R and Python scripts
*.R text
*.r text
*.py text
*.ipynb text

# Configuration files
*.cff text
.gitignore text
.gitattributes text

# Line ending normalization for text files
* text=auto

# Markdown files - normalize to LF
*.md text eol=lf
*.markdown text eol=lf

# YAML/JSON files - normalize to LF
*.yml text eol=lf
*.yaml text eol=lf
*.json text eol=lf

# Citation and bibliography files - normalize to LF
*.bib text eol=lf
*.cff text eol=lf

# Jupyter notebooks - normalize to LF and treat as text
*.ipynb text eol=lf

# Archive files - treat as binary
*.zip binary
*.tar binary
*.gz binary
*.tgz binary
*.7z binary

# Linguist overrides for GitHub language statistics
*.md linguist-documentation
*.txt linguist-documentation
CHANGELOG.md linguist-documentation
CONTRIBUTING.md linguist-documentation
CODE_OF_CONDUCT.md linguist-documentation
LICENSE linguist-documentation

# Don't count certain files in language statistics
*.pdf linguist-generated=false linguist-documentation
supplementary/* linguist-documentation
references/* linguist-documentation
assets/* linguist-documentation