pyproject.toml

[tool.poetry]
name = "sec-parser"
version = "0.58.1"
description = "Parse SEC EDGAR HTML documents into a tree of elements that correspond to the visual structure of the document."
authors = ["Alphanome.AI <info@alphanome.ai>"]
readme = "README.md"
repository = "https://github.com/alphanome-ai/sec-parser"
license = "MIT"
classifiers = [
    "Topic :: Text Processing :: Markup :: HTML",
    "Topic :: Office/Business :: Financial",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: Scientific/Engineering :: Information Analysis",
    "Topic :: Software Development :: Libraries :: Python Modules",
    # NOTE: After changing Development Status here, also change it in the README.md badge
    "Development Status :: 4 - Beta",
    "Natural Language :: English",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "Intended Audience :: Financial and Insurance Industry",
    "Operating System :: OS Independent",
]


[tool.poetry.dependencies]
python = ">=3.9,<3.9.7 || >3.9.7,<4.0"
frozendict = "^2.4.4"
beautifulsoup4 = "^4.12.3"
lxml = "^5.2.2"
cssutils = "^2.11.1"
xxhash = "^3.4.1"
loguru = "^0.7.2"
tabulate = "^0.9.0"
pandas = "^2.2.2"
sec-downloader = "^0.11.1"


[tool.poetry.group.dev.dependencies]
pytest = "^8.2.2"
mypy = "^1.10.0"
commitizen = "^3.27.0"
pre-commit = "^3.7.1"
ruff = "^0.1.6"
pytest-cov = "^5.0.0"
types-requests = "^2.32.0.20240602"
types-beautifulsoup4 = "^4.12.0.20240511"
streamlit = "1.33.0"
watchdog = "^4.0.1"
streamlit-nested-layout = "^0.1.1"
millify = "^0.1.1"
streamlit-extras = "^0.3.5"
ipykernel = "^6.29.4"
pytest-watch = "^4.2.0"
click = "^8.1.7"
rich = "^13.7.1"
hypothesis = "^6.103.1"
execnb = "^0.1.5"
pyyaml = "^6.0.1"
pytest-xdist = "^3.6.1"
sec-api-io = "^0.0.17"
pyinstrument = "^4.6.2"
pandas-stubs = "^2.2.2.240603"
tiktoken = "^0.5.1"
streamlit-antd-components = "^0.2.3"
notebook = "^7.2.1"


[tool.poetry.group.doc.dependencies]
sphinx = "^7.3.7"
sphinx-autobuild = "^2024.4.16"
myst-parser = "^3.0.1"
nbsphinx = "^0.9.3"
sphinx-autoapi = "^3.1.1"
sphinx-rtd-theme = "^2.0.0"
jupyter-black = "^0.3.4"
aiohttp = "^3.9.5"


[tool.commitizen]
name = "cz_conventional_commits"
tag_format = "$version"
version_scheme = "pep440"
version_provider = "poetry"
update_changelog_on_bump = false
major_version_zero = true


[build-system]
requires = ["poetry-core"]
build-backend = "poetry.core.masonry.api"


[tool.coverage.run]
source = ["sec_parser"]


[tool.ruff]
select = ["ALL"]
ignore = [
    "D100",    # Missing docstring in public module
    "D101",    # Missing docstring in public class
    "D102",    # Missing docstring in public method
    "D103",    # Missing docstring in public function
    "D104",    # Missing docstring in public package
    "D105",    # Missing docstring in magic method
    "D107",    # Missing docstring in __init__
    "D203",    # 1 blank line required before class docstring
    "D205",    # 1 blank line required between summary line and description
    "D212",    # Multi-line docstring summary should start at the first line
    "ANN101",  # Missing type annotation for self in method
    "ANN102",  # Missing type annotation for cls in classmethod
    "PLR0913", # Too many arguments to function call (> 5)
    "E501",    # Line too long
    "C901",    # Function is too complex
    "PLR0912", # Too many branches (>= 12)
    ]


# Allow autofix for all enabled rules (when `--fix`) is provided.
fixable = ["ALL"]
unfixable = []

# Exclude a variety of commonly ignored directories.
exclude = [
    ".bzr",
    ".direnv",
    ".eggs",
    ".git",
    ".git-rewrite",
    ".hg",
    ".mypy_cache",
    ".nox",
    ".pants.d",
    ".pytype",
    ".ruff_cache",
    ".svn",
    ".tox",
    ".venv",
    "__pypackages__",
    "_build",
    "buck-out",
    "build",
    "dist",
    "node_modules",
    "venv",
    ]

# Same as Black.
line-length = 88

# Allow unused variables when underscore-prefixed.
dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"

# Python 3.9 is the minimum supported version.
target-version = "py39"


[tool.ruff.per-file-ignores]
"tests/**/*.py" = [
    "S101", # Allow asserts in tests
    "ARG", # Unused function args are functionally relevant due to fixtures
    "FBT", # Positional booleans in tests are acceptable, e.g. via @pytest.mark.parametrize()
    "PLR2004", # Allow magic values in tests
]


[tool.ruff.mccabe]
# Unlike Flake8, default to a complexity level of 10.
max-complexity = 10