pyproject.toml

[project]
name = "tablassert"
version = "17.0.0"
description = "Extract knowledge assertions from tabular data into NCATS Translator-compliant KGX NDJSON — declaratively, with entity resolution and quality control built in."
authors = [
    { name = "Skye Lane Goetz", email = "sgoetz@isbscience.org" }
]
keywords = [
    "knowledge graph",
    "kgx",
    "ncats translator",
    "biolink",
    "bioinformatics",
    "biomedical data",
    "entity resolution",
    "tabular data",
    "yaml configuration",
    "declarative pipeline",
    "quality control",
    "llm agent",
]
readme = "README.md"
license = "Apache-2.0"
license-files = ["LICENSE"]
classifiers = [
    "License :: OSI Approved :: Apache Software License",
    "Development Status :: 5 - Production/Stable",
    "Intended Audience :: Science/Research",
    "Intended Audience :: Healthcare Industry",
    "Intended Audience :: Developers",
    "Topic :: Scientific/Engineering :: Bio-Informatics",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: Scientific/Engineering :: Information Analysis",
    "Topic :: Database",
    "Topic :: Software Development :: Libraries :: Python Modules",
    "Programming Language :: Python :: 3 :: Only",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: 3.13",
    "Programming Language :: Python :: 3.14",
    "Programming Language :: Python :: Implementation :: CPython",
    "Programming Language :: Rust",
    "Framework :: Pydantic :: 2",
    "Operating System :: POSIX :: Linux",
    "Operating System :: MacOS :: MacOS X",
    "Environment :: Console",
]
requires-python = ">=3.11"
dependencies = [
    "biolink-model>=4.4.4",
    "polars>=1.39.0",
    "rapidfuzz>=3.14.3",
    "pydantic>=2.12.5",
    "pyyaml>=6.0.3",
    "cyclopts>=1.0.0",
    "rich>=13.0.0",
    "fastexcel>=0.20.2",
]

[project.urls]
Homepage = "https://github.com/SkyeAv/Tablassert"
Source = "https://github.com/SkyeAv/Tablassert"
Documentation = "https://skyeav.github.io/Tablassert/"

[build-system]
requires = ["maturin>=1.10,<2.0"]
build-backend = "maturin"

[tool.maturin]
python-source = "src"
module-name = "tablassert.rs"
bindings = "pyo3"
manifest-path = "rust/Cargo.toml"
features = ["extension-module"]

[project.scripts]
tablassert = "tablassert.cli:APP"

[project.optional-dependencies]
rt = [
    "polars[rtcompat]>=1.40.1",
]
# PyPI distribution "aria2" exposes import module "aria2c" with a bundled aria2c binary.
aria2 = [
    "aria2==0.0.1b0",
]
qc = [
    "scikit-learn>=1.8.0",
    "sentence-transformers>=5.3.0",
]
agent = [
    "smolagents>=1.26.0",
    "litellm>=1.93.0",
]
optimize = [
    "dspy>=3.2.1",
]
distill = [
    "datasets>=3.0.0",
]
log = [
    "loguru>=0.7.3",
]

[dependency-groups]
test = [
    "maturin>=1.10,<2.0",
    # Direct test import (excel fixtures); was only transitive via linkml 1.10,
    # which biolink-model 4.4.4's linkml 1.11 bump no longer pulls.
    "openpyxl>=3.1",
    "pytest>=9.0.2",
    "pytest-cov>=7.1.0",
    "pytest-xdist>=3.8.0",
]
typecheck = [
    "pyright>=1.1.411",
]
docs = [
    "mkdocs>=1.6.1",
    "mkdocs-material>=9.6.0",
]
# The EXACT set both CI Python jobs install. Keeping `python-type` and `python-test` on one
# identical sync is deliberate: `astral-sh/setup-uv` keys its cache on the lockfile, so jobs
# with different dependency sets race to save a cache the others then restore and miss on.
# One shared set means one genuinely warm cache. Excludes docs/pre-commit/ruff, which no CI
# job that syncs needs (lint runs ruff standalone; docs uses `--group docs`).
ci = [
    { include-group = "test" },
    { include-group = "typecheck" },
]
# Superset for local development, so `make setup` still installs everything.
dev = [
    { include-group = "ci" },
    { include-group = "docs" },
    "pre-commit>=4.5.1",
    "ruff>=0.15.6",
]

[tool.pytest.ini_options]
testpaths = ["tests"]
# Parallel by default via pytest-xdist (~7x faster full suite, identical coverage).
# Disable for a single serial run with `-n 0` (e.g. debugging one test).
addopts = "--cov=tablassert --cov-report=term-missing -n auto"
markers = ["network: requires internet"]

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

[tool.ruff]
line-length = 150
indent-width = 4
target-version = "py311"

[tool.ruff.lint]
select = [
    "E4", # pycodestyle E4xx
    "E7", # pycodestyle E7xx
    "E9", # pycodestyle E9xx
    "F", # pyflakes
    "RUF100", # stale noqa
    "B", # flake8-bugbear
    "SIM", # flake8-simplify
    "C4", # flake8-comprehensions
    "PT", # flake8-pytest-style
    "RUF", # ruff-specific
    "TID", # flake8-tidy-imports
    "I", # isort
    "PIE", # flake8-pie
    "RET", # flake8-return
    "UP", # pyupgrade
]
ignore = [
    "UP042", # keep enum/str-conversion behavior as-is
]

[tool.ruff.lint.isort]
# Align isort with `format.skip-magic-trailing-comma = true` (avoids the ruff incompatibility warning).
split-on-trailing-comma = false

[tool.ruff.format]
quote-style = "double"
indent-style = "space"
skip-magic-trailing-comma = true

[tool.pyright]
include = ["src", "tests"]
pythonVersion = "3.11"
strictListInference = true
strictDictionaryInference = true
strictSetInference = true
reportMissingTypeStubs = false
reportUnusedImport = true
reportUnusedVariable = true
reportDuplicateImport = true