# 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", "img2pdf>=0.5", "packaging>=20", "pdfminer.six>=20220319", "pi-heif", # Heif image format - maintainers: if this is removed, it will NOT break "pikepdf>=8.10.1,!=9.8.0", "Pillow>=10.0.1", "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", "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.rst" [project.optional-dependencies] docs = ["myst-parser>=4.0.1", "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-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] dev = [ "mypy>=1.13.0", "pymupdf>=1.24.14", "streamlit-pdf-viewer>=0.0.19", "streamlit>=1.40.2", "ipykernel>=6.29.5", ]