pyproject.toml

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

[project]
name = "dqv"
version = "0.1.1"  # Bumped to force Docker cache invalidation
description = "Data Quality Validation Agent - gate + artifact generator for tabular datasets"
readme = "README.md"
requires-python = ">=3.11"
license = "MIT"
authors = [
    { name = "Nimblemind", email = "dev@nimblemind.io" }
]
classifiers = [
    "Development Status :: 3 - Alpha",
    "Intended Audience :: Developers",
    "License :: OSI Approved :: MIT License",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Typing :: Typed",
]

dependencies = [
    "pydantic>=2.0,<3.0",
    "PyYAML>=6.0,<7.0",
    "pandas>=1.0,<2.0",  # TFDV requires pandas<2
    "pyarrow>=14.0,<18.0",  # Compatible with TFDV and pandas<2
    "tensorflow-data-validation>=1.15.0,<2.0",
    "dftest>=0.4.0",
    "fsspec>=2024.0.0",
    "opentelemetry-api>=1.20.0",
    "opentelemetry-sdk>=1.20.0",
    "structlog>=24.0.0",
]

[project.optional-dependencies]
dev = [
    "pytest>=8.0,<9.0",
    "pytest-cov>=4.0,<6.0",
    "hypothesis>=6.100,<7.0",
    "mypy>=1.10,<2.0",
    "ruff>=0.4,<1.0",
    "types-requests",
    "pandas-stubs<2.0",  # Match pandas<2 constraint
]
# MDPT is installed as an editable path dependency (see tool.hatch.envs below)

[project.urls]
Homepage = "https://github.com/nimblemind/nimblemind-agents"
Repository = "https://github.com/nimblemind/nimblemind-agents"

[tool.hatch.build.targets.wheel]
packages = ["src"]

[tool.hatch.envs.default]
features = ["dev"]
# Install mdpt-main as editable path dependency
extra-dependencies = [
    "mdpt @ file://./mdpt-main",
]

[tool.hatch.envs.default.scripts]
test = "pytest -q --cov=src --cov-fail-under=90 {args}"
test-external = "pytest -m external -q {args}"
lint = "ruff check ."
format = "ruff format ."
format-check = "ruff format --check ."
typecheck = "mypy --strict src"
all = ["lint", "format-check", "typecheck", "test"]

[tool.pytest.ini_options]
testpaths = ["tests"]
python_files = ["test_*.py"]
python_functions = ["test_*"]
markers = [
    "external: marks tests that require external APIs (Azure/Bing) and secrets",
    "integration: marks integration tests",
    "e2e: marks end-to-end tests",
]
filterwarnings = [
    "ignore::DeprecationWarning",
]

[tool.coverage.run]
source = ["src"]
branch = true
omit = ["*/tests/*", "*/__pycache__/*"]

[tool.coverage.report]
exclude_lines = [
    "pragma: no cover",
    "if TYPE_CHECKING:",
    "raise NotImplementedError",
    "@abstractmethod",
]

[tool.mypy]
python_version = "3.11"
strict = true
warn_return_any = true
warn_unused_configs = true
disallow_untyped_defs = true
disallow_incomplete_defs = true
check_untyped_defs = true
disallow_untyped_decorators = true
no_implicit_optional = true
warn_redundant_casts = true
warn_unused_ignores = true
warn_no_return = true
follow_imports = "normal"
show_error_codes = true

[[tool.mypy.overrides]]
module = [
    "tensorflow_data_validation.*",
    "dftest.*",
    "mdpt.*",
    "apache_beam.*",
    "tensorflow.*",
    "tensorflow_metadata.*",
]
ignore_missing_imports = true

[tool.ruff]
target-version = "py311"
line-length = 100
exclude = [
    ".git",
    ".mypy_cache",
    ".ruff_cache",
    "__pycache__",
    "mdpt-main",
    "build",
    "dist",
]

[tool.ruff.lint]
select = [
    "E",      # pycodestyle errors
    "W",      # pycodestyle warnings
    "F",      # Pyflakes
    "I",      # isort
    "B",      # flake8-bugbear
    "C4",     # flake8-comprehensions
    "UP",     # pyupgrade
    "ARG",    # flake8-unused-arguments
    "SIM",    # flake8-simplify
    "TCH",    # flake8-type-checking
    "PTH",    # flake8-use-pathlib
    "RUF",    # Ruff-specific rules
]
ignore = [
    "E501",   # line too long (handled by formatter)
    "B008",   # do not perform function calls in argument defaults
]

[tool.ruff.lint.isort]
known-first-party = ["src"]