pyproject.toml

[project]
name = "htrflow"
version = "0.2.1"
description = "htrflow is developed at Riksarkivet's AI-lab as an open-source package to simplify HTR"
readme = "README.md"
license = {file = "LICENSE"}
authors = [{email = "ai@riksarkivet.se"}]
keywords = ["htr", "htrflow", "ocr"]
classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "Operating System :: OS Independent",
    "Programming Language :: Python :: 3.10",
    "Topic :: Software Development :: Libraries :: Python Modules",
    "Typing :: Typed",
]
requires-python = ">=3.10,<3.13"

dependencies = [
    "jinja2 >= 3.1.3",
    "numpy",
    "opencv-python >=4.6.0",
    "tqdm >=4.66.2,<5",
    "xmlschema >=3.0.2,<4",
    "typer>=0.12.0",
    "rich >=13.7.1",
    "jiwer >=3.0.4",
    "pandas",
    "pagexml-tools >=0.5.0",
    "transformers[torch] >=4.44.1",
    "huggingface-hub[cli] >=0.24.6",
    "ultralytics >=8.0.225",
    "pydantic>=2.9.2",
]


[project.urls]
Documentation = "https://ai-riksarkivet.github.io/htrflow"
Repository = "https://github.com/AI-Riksarkivet/htrflow"


[project.scripts]
htrflow = "htrflow.cli:app"


[tool.uv]
dev-dependencies = [
    "mypy >=1.8.0",
    "pre-commit >=3.6.2",
    "pytest >=8.0.1",
    "pytest-cov >=4.1.0",
    "pytest-github-actions-annotate-failures >=0.2.0",
    "python-dotenv >=1.0.1",
    "ruff >=0.6.2",
    "uv>=0.4.12",
    "lorem",
    "tox-uv>=1.13.0",
]

[project.optional-dependencies]
docs = [
    "mike >=2.1.1",
    "mkdocs-jupyter >=0.24.6",
    "mkdocs-material >=9.5.10",
    "mkdocstrings[python] >=0.20",
    "mkdocs-table-reader-plugin >=2.2.2",
    "mkdocs-git-revision-date-localized-plugin >=1.2.6",
    "termynal >=0.12.1",
    "mkdocs-swagger-ui-tag >=0.6.10"
]
teklia = [
    "pylaia==1.1.2; python_version == '3.10'"
]

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[tool.hatch.metadata]
allow-direct-references = true  

[tool.pytest.ini_options]
addopts = "-v --cov htrflow --cov-report term-missing --no-cov-on-fail"
markers = [
    "slow: marks tests as slow (deselect with '-m \"not slow\"')",
    "gpu: marks tests as gpu (deselect with '-m \"not gpu\"')",
    "openmmlab: marks tests as openmmlab (deselect with '-m \"not openmmlab\"')",
    "teklia: marks tests as teklia (deselect with '-m \"not teklia\"')"
]
pythonpath = "src"
testpaths = ["tests/unit", "tests/integration"]

[tool.coverage.run]
source = ["src/htrflow"]

[tool.coverage.report]
exclude_lines = [
    "if __name__ == .__main__.:",
    "pragma: no cover",
    "def __repr__",
    "if self\\.debug",
    "raise AssertionError",
    "raise NotImplementedError",
]

# Formatting and linting (tool.ruff)
[tool.ruff]
line-length = 119
target-version = "py310"
exclude = ["*.ipynb"]

[tool.ruff.lint]
ignore = ["C901", "E741", "W605"]
select = ["C", "E", "F", "I", "W"]

[tool.ruff.lint.per-file-ignores]
"__init__.py" = ["E402", "F401", "F403", "F811"]
# Disable line length limit in cli.py. This allows Typer CLI arguments
# and their documentation to use one line each, increasing readability.
"cli.py" = ["E501"]

[tool.ruff.lint.isort]
known-first-party = ["htrflow"]
lines-after-imports = 2

# Typing (tool.mypy)
[tool.mypy]
check_untyped_defs = true
disallow_any_generics = true
exclude = ['venv', '.venv', "tests", "docs"]
ignore_missing_imports = true
mypy_path = "src"
no_implicit_optional = true
no_implicit_reexport = true
show_error_codes = true
strict_equality = true
warn_redundant_casts = true
warn_return_any = true
warn_unreachable = true
warn_unused_configs = true