# SPDX-FileCopyrightText: 2022 James R. Barlow # SPDX-License-Identifier: MPL-2.0 [build-system] requires = ["setuptools >= 61", "setuptools_scm[toml] >= 7.0.5", "wheel"] build-backend = "setuptools.build_meta" [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 = { text = "MPL-2.0" } requires-python = ">=3.10" dependencies = [ "Pillow>=10.0.1", "deprecation>=2.1.0", "img2pdf>=0.5", "packaging>=20", "pdfminer.six>=20220319", "pikepdf>=8.10.1", "pluggy>=1", "rich>=13", ] 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", "License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)", "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" [project.optional-dependencies] docs = ["sphinx", "sphinx-issues", "sphinx-rtd-theme"] extended_test = ["PyMuPDF>=1.19.1"] test = [ "coverage[toml]>=6.2", "hypothesis>=6.36.0", "pytest>=6.2.5", "pytest-cov>=3.0.0", "pytest-xdist>=2.5.0", "python-xmp-toolkit==2.0.1", # also requires apt-get install libexempi3 "reportlab>=3.6.8", "types-Pillow", "types-humanfriendly", ] watcher = ["watchdog>=1.0.2", "typer[all]", "python-dotenv"] webservice = ["Flask>=2.0.1"] [project.scripts] ocrmypdf = "ocrmypdf.__main__:run" [tool.setuptools.package-data] ocrmypdf = ["data/sRGB.icc", "py.typed"] [tool.setuptools.packages.find] where = ["src"] namespaces = false [tool.setuptools_scm] [tool.distutils.bdist_wheel] python-tag = "py310" [tool.black] line-length = 88 target-version = ["py310", "py311", "py312"] skip-string-normalization = true include = '\.pyi?$' exclude = ''' /( \.eggs | \.git | \.hg | \.mypy_cache | \.tox | \.venv | _build | buck-out | build | dist | docs | misc | \.egg-info )/ ''' [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" norecursedirs = ["lib", ".pc", ".git", "venv", "output", "cache", "resources"] testpaths = ["tests"] addopts = "-n auto" markers = ["slow"] filterwarnings = [ "ignore:.*XMLParser.*:DeprecationWarning", 'ignore:.*ast.NameConstant.*:DeprecationWarning', ] [tool.mypy] [[tool.mypy.overrides]] module = [ 'pluggy', 'tqdm', 'coloredlogs', 'img2pdf', 'pdfminer.*', 'reportlab.*', 'fitz', 'libxmp.utils', ] ignore_missing_imports = true [tool.ruff] select = [ "D", # pydocstyle "E", # pycodestyle "W", # pycodestyle "F", # pyflakes "I001", # isort "UP", # pyupgrade ] target-version = "py310" [tool.ruff.isort] known-first-party = ["ocrmypdf"] required-imports = ["from __future__ import annotations"] [tool.ruff.pydocstyle] convention = "google" [tool.ruff.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"]