Files
OCRmyPDF/pyproject.toml
T
James R. Barlow bf76c8270c Rationalize optional dependencies vs dependency groups
Establish clear separation between user-facing optional dependencies
and developer-only dependency groups:

**Optional Dependencies (user features):**
- watcher: File watching service for batch processing
- webservice: Streamlit-based web UI
- Installable via: uv sync --extra <name> or pip install ocrmypdf[name]

**Dependency Groups (developer tools):**
- test: Testing infrastructure (merged from test + extended_test)
- docs: Documentation building tools
- streamlit-dev: Enhanced Streamlit development tools
- dev: General development tools (mypy, ipykernel)
- Installable via: uv sync --group <name> (uv only, NOT pip)

Breaking changes for developers:
- pip install -e .[test] no longer works → use uv sync --group test
- pip install -e .[docs] no longer works → use uv sync --group docs
- pip install -e .[extended_test] removed → merged into test group

No breaking changes for end users:
- pip install ocrmypdf[watcher] still works
- pip install ocrmypdf[webservice] still works

Updated:
- CI/CD workflows to use uv sync --group test
- Docker images to exclude test dependencies
- Documentation to recommend uv with pip as fallback
- pyproject.toml with clear comments explaining both systems
2026-01-13 00:34:55 -08:00

179 lines
4.4 KiB
TOML

# SPDX-FileCopyrightText: 2022 James R. Barlow
# SPDX-License-Identifier: MPL-2.0
[build-system]
requires = ["hatchling", "hatch-vcs"]
build-backend = "hatchling.build"
[project]
name = "ocrmypdf"
dynamic = ["version"]
description = "OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched"
readme = "README.md"
license = "MPL-2.0"
requires-python = ">=3.10"
dependencies = [
"deprecation>=2.1.0",
"fpdf2>=2.8.0",
"img2pdf>=0.5",
"packaging>=20",
"pdfminer.six>=20220319",
"pi-heif", # Heif image format - maintainers: if this is removed, it will NOT break
"pikepdf>=10",
"Pillow>=10.0.1",
"pluggy>=1",
"pydantic>=2.12.5",
"pypdfium2>=5.0.0",
"rich>=13",
"uharfbuzz>=0.53.2",
]
authors = [{ name = "James R. Barlow", email = "james@purplerock.ca" }]
classifiers = [
"Development Status :: 5 - Production/Stable",
"Environment :: Console",
"Intended Audience :: End Users/Desktop",
"Intended Audience :: Science/Research",
"Intended Audience :: System Administrators",
"Operating System :: MacOS",
"Operating System :: Microsoft :: Windows",
"Operating System :: POSIX",
"Operating System :: POSIX :: BSD",
"Operating System :: POSIX :: Linux",
"Programming Language :: Python :: 3",
"Topic :: Scientific/Engineering :: Image Recognition",
"Topic :: Text Processing :: Indexing",
"Topic :: Text Processing :: Linguistic",
]
keywords = ["PDF", "OCR", "optical character recognition", "PDF/A", "scanning"]
[project.urls]
Documentation = "https://ocrmypdf.readthedocs.io/"
Source = "https://github.com/ocrmypdf/OCRmyPDF"
Tracker = "https://github.com/ocrmypdf/OCRmyPDF/issues"
Changelog = "https://github.com/ocrmypdf/OCRmyPDF/docs/release_notes.md"
[project.optional-dependencies]
# User-installable features - use `uv sync --extra <name>` or `pip install ocrmypdf[name]`
watcher = ["watchdog>=1.0.2", "typer-slim[standard]", "python-dotenv"]
webservice = ["streamlit>=1.41.0"]
[project.scripts]
ocrmypdf = "ocrmypdf.__main__:run"
[tool.hatch.version]
source = "vcs"
[tool.hatch.build.hooks.vcs]
version-file = "src/ocrmypdf/_version.py"
[tool.distutils.bdist_wheel]
python-tag = "py310"
[tool.coverage.run]
branch = true
parallel = true
concurrency = ["multiprocessing", "thread"]
sigterm = true
[tool.coverage.paths]
source = ["src/ocrmypdf"]
[tool.coverage.report]
# Regexes for lines to exclude from consideration
exclude_lines = [
# Have to re-enable the standard pragma
"pragma: no cover",
# Don't complain if tests don't hit defensive assertion code:
"raise AssertionError",
"raise NotImplementedError",
# Don't complain if non-runnable code isn't run:
"if 0:",
"if False:",
"if __name__ == .__main__.:",
"if TYPE_CHECKING:",
]
[tool.pytest.ini_options]
minversion = "6.0"
testpaths = ["tests"]
addopts = "-n auto"
markers = ["slow"]
filterwarnings = [
"ignore:.*XMLParser.*:DeprecationWarning",
"ignore:.*ast.NameConstant.*:DeprecationWarning:reportlab",
"ignore:.*distutils.*:DeprecationWarning:libxmp",
]
[tool.mypy]
[[tool.mypy.overrides]]
module = [
'pluggy',
'img2pdf',
'pdfminer.*',
'reportlab.*',
'fitz',
'libxmp.utils',
]
ignore_missing_imports = true
[tool.ruff]
target-version = "py310"
[tool.ruff.lint]
"select" = [
"D", # pydocstyle
"E", # pycodestyle
"W", # pycodestyle
"F", # pyflakes
"I001", # isort
"UP", # pyupgrade
]
[tool.ruff.lint.isort]
known-first-party = ["ocrmypdf"]
[tool.ruff.lint.pydocstyle]
convention = "google"
[tool.ruff.lint.per-file-ignores]
"docs/conf.py" = ["D100", "D101", "D105"]
"tests/*.py" = ["D100", "D101", "D102", "D103", "D105"]
"misc/*.py" = ["D103", "D101", "D102"]
"src/ocrmypdf/builtin_plugins/*.py" = ["D103", "D102", "D105"]
[tool.ruff.format]
quote-style = "preserve"
[dependency-groups]
# Developer-only tools - use `uv sync --group <name>` (NOT pip-installable)
dev = [
"mypy>=1.13.0",
"ipykernel>=6.29.5",
]
test = [
# Core testing framework
"coverage[toml]>=6.2",
"hypothesis>=6.36.0",
"pytest>=6.2.5",
"pytest-cov>=3.0.0",
"pytest-xdist>=2.5.0",
# Test dependencies
"python-xmp-toolkit==2.0.1", # also requires apt-get install libexempi3
"reportlab>=3.6.8",
# Type stubs for testing
"types-Pillow",
"types-humanfriendly",
# Extended test capabilities (merged from extended_test)
"pymupdf>=1.24.14",
]
docs = [
"myst-parser>=4.0.1",
"sphinx",
"sphinx-issues",
"sphinx-rtd-theme",
]
streamlit-dev = [
"streamlit>=1.40.2",
"streamlit-pdf-viewer>=0.0.19",
]