# Ignore generated docs but keep GitHub Pages content
/project/docs/
/tmp/

# Track GitHub Pages content in docs/
# (Generated markdown/html files from LinkML are ignored, but D4D examples are tracked)
docs/*
!docs/*.md
!docs/*.css
!docs/html_output/
!docs/yaml_output/

# 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/
pip-wheel-metadata/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST

# 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
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/

# Translations
*.mo
*.pot

# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal

# Flask stuff:
instance/
.webassets-cache

# Scrapy stuff:
.scrapy

# Sphinx documentation
docs/_build/

# PyBuilder
target/

# Jupyter Notebook
.ipynb_checkpoints

# IPython
profile_default/
ipython_config.py

# pyenv
.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

# PEP 582; used by e.g. github.com/David-OConnor/pyflow
__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/
.DS_Store

# RO-Crate packages: keep the upstream archive (raw/), not the extracted tree.
# CM4AI's extracted crate is ~47 MB, almost entirely per-file listing HTML
# (ro-crate-preview.html up to 11.8 MB each).
#
# Re-extract from raw/cm4ai_release_metadata.zip, named rather than globbed:
# raw/ now holds two unrelated archives and `raw/*.zip` matches both. The other
# is cm4ai_images_untreated.zip, 3.2 GB of immunofluorescence JPEGs under
# untreated/ — 15,911 files that are not a crate and will not rebuild one.
data/ro-crate_packages/*/crate/

# ...but "keep the upstream archive" holds for a 1.1 MB metadata zip and stops
# holding at 3.19 GB. CM4AI's image archives are gigabytes; committing one would
# push it to a repository that is 60 MB today, and no later `git rm` would get
# it back out of history.
#
# This is not hypothetical. One such archive was staged and then unstaged, which
# left a 3.19 GB unreferenced blob in .git/objects — invisible to every ordinary
# git command, never pushed, and 96% of the local repository.
#
# Allowlist rather than a pattern per treatment condition: the archive names are
# upstream's to choose, so anything new in raw/ is ignored until someone decides
# otherwise. The one zip already tracked is named explicitly.
#
# Every archive extension and any depth, because the next one will not be named
# like the last one — .tar.gz and raw/images/foo.zip both slipped past a plain
# raw/*.zip when tested. This still only guards archives under raw/; a general
# "no large file anywhere" check needs a size threshold, which .gitignore cannot
# express. See #262.
#
# Compression suffixes are spelled out rather than written `*.tar.*`, which also
# swallowed images.tar.md5 and manifest.tar.sha256. A tracked checksum beside an
# untracked archive is the only way anyone verifies the copy in their raw/ is
# the right one, so ignoring it defeats the reason the archive is untracked.
data/ro-crate_packages/*/raw/**/*.zip
data/ro-crate_packages/*/raw/**/*.tar
data/ro-crate_packages/*/raw/**/*.tar.gz
data/ro-crate_packages/*/raw/**/*.tar.bz2
data/ro-crate_packages/*/raw/**/*.tar.xz
data/ro-crate_packages/*/raw/**/*.tar.zst
data/ro-crate_packages/*/raw/**/*.tgz
data/ro-crate_packages/*/raw/**/*.7z
data/ro-crate_packages/*/raw/**/*.zip.[0-9][0-9][0-9]
!data/ro-crate_packages/CM4AI/raw/cm4ai_release_metadata.zip

# Poster/slide artifacts are kept local-only and never committed to this repo.
data/poster_assets/

# Resume scaffolding for `d4d api` runs — deleted on success, never a record.
*_api_progress.json

# Run locks for in-flight API sweeps (#513) — process state, not artifacts
data/.run_locks/
