# SPDX-FileCopyrightText: 2022 James R. Barlow
# SPDX-License-Identifier: MPL-2.0
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[project]
name = "ocrmypdf"
version = "17.8.1"
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 = ">=3.11"
dependencies = [
  "fpdf2>=2.8.0",
  "img2pdf>=0.5",
  "packaging>=20",
  "pdfminer.six>=20260107",  # fixes parsing of tokens split across the read buffer/streams (gh #1361)
  "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",
  "typing-extensions>=4.12; python_version < '3.13'",
  "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/tree/main/docs/releasenotes"

[project.optional-dependencies]
# User-installable features - use `uv sync --extra <name>` or `pip install ocrmypdf[name]`
watcher = ["watchdog>=1.0.2", "cyclopts>=3", "python-dotenv"]
webservice = ["streamlit>=1.41.0"]

[project.scripts]
ocrmypdf = "ocrmypdf.__main__:run"

[tool.distutils.bdist_wheel]
python-tag = "py311"

[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]
check_untyped_defs = true

[[tool.mypy.overrides]]
module = [
  'img2pdf',
  'pdfminer.*',
  'reportlab.*',
  'fitz',
  'libxmp.utils',
  'pypdfium2',
  'uharfbuzz',
  'pi_heif',
]
ignore_missing_imports = true

[[tool.mypy.overrides]]
# Test functions are not required to annotate their return type (almost
# always None); it's a low-value hint that would just be noise here.
module = 'tests.*'
disallow_untyped_defs = false
disallow_incomplete_defs = false

[tool.ruff]
target-version = "py311"
exclude = ["src/ocrmypdf/_version.py"] # Autogenerated

[tool.ruff.lint]
"select" = [
  "D",   # pydocstyle
  "E",   # pycodestyle
  "W",   # pycodestyle
  "F",   # pyflakes
  "I",   # isort
  "UP",  # pyupgrade
  "SIM", # simplify
  "B",   # flake8-bugbear
  "ICN", # flake8-import-conventions
  "PTH", # flake8-use-pathlib
]
ignore = [
  "B028", # warning with no explicit stacklevel
  # rule is key in dict instead of key in dict.keys(); but pikepdf semantics differ
  "SIM118",
]

[tool.ruff.lint.isort]
known-first-party = ["ocrmypdf"]
required-imports = ["from __future__ import annotations"]

[tool.ruff.lint.flake8-import-conventions]
# Prohibit explicit imports from the 'datetime' module
banned-from = ["datetime"]
# Optionally, suggest an alias for 'import datetime' (e.g., as dt)
extend-aliases = { "datetime" = "dt" }

[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", "E501"]
"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>`
dev = [
    "mypy>=1.13.0",
    "ruff>=0.14.11",
    "prek>=0.4.8",
    "ipykernel>=6.29.5",
    "reportlab>=4.4.4",
    "cyclopts>=4.5.1",
    "pygithub>=2.9.1",
]
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-humanfriendly",
  # Extended test capabilities (merged from extended_test)
  "pymupdf>=1.24.14",
]
docs = [
  "myst-parser>=4.0.1",
  "sphinx",
  "sphinx-issues",
  "sphinx-reredirects",
  "sphinx-rtd-theme",
  "sphinxcontrib-mermaid",
]
streamlit-dev = ["streamlit>=1.40.2", "streamlit-pdf-viewer>=0.0.19"]