DataBeak

[build-system] requires = ["hatchling>=1.26.0"] build-backend = "hatchling.build" [project] name = "databeak" version = "0.1.2" description = "DataBeak: MCP server for comprehensive CSV file operations with pandas-based tools" readme = "README.md" requires-python = ">=3.12" license = {text = "Apache-2.0"} authors = [ {name = "Jonathan Springer", email = "jps@s390x.com"}, ] maintainers = [ {name = "Jonathan Springer", email = "jps@s390x.com"}, ] keywords = [ "csv", "mcp", "model-context-protocol", "data-analysis", "data-manipulation", "pandas", "fastmcp", "data-validation", "data-quality", "data-profiling", "outlier-detection", ] classifiers = [ "Development Status :: 4 - Beta", "Intended Audience :: Developers", "Intended Audience :: Science/Research", "Intended Audience :: Financial and Insurance Industry", "License :: OSI Approved :: Apache Software License", "Operating System :: OS Independent", "Programming Language :: Python", "Programming Language :: Python :: 3", "Programming Language :: Python :: 3.12", "Programming Language :: Python :: 3.13", "Topic :: Scientific/Engineering :: Information Analysis", "Topic :: Software Development :: Libraries :: Python Modules", "Topic :: Office/Business :: Financial :: Spreadsheet", "Topic :: Utilities", "Typing :: Typed", "Framework :: AsyncIO", ] dependencies = [ "pandas>=2.2.3", "numpy>=2.1.3", "pydantic>=2.10.4", "aiofiles>=24.1.0", "python-dateutil>=2.9.0", "httpx>=0.27.0", "openpyxl>=3.1.5", "pyarrow>=17.0.0", "tabulate>=0.9.0", "pytz>=2024.2", "pydantic-settings>=2.10.1", "psutil>=7.0.0", "scipy>=1.16.1", "simpleeval>=1.0.3", "pandera>=0.26.1", "fastapi>=0.117.1", "uvicorn>=0.36.0", "fastmcp>=2.12.4", "smithery>=0.4.2", ] [project.urls] Homepage = "https://github.com/jonpspri/databeak" Documentation = "https://github.com/jonpspri/databeak#readme" Repository = "https://github.com/jonpspri/databeak" Issues = "https://github.com/jonpspri/databeak/issues" Changelog = "https://github.com/jonpspri/databeak/blob/main/CHANGELOG.md" "Release Notes" = "https://github.com/jonpspri/databeak/releases" [project.scripts] databeak = "databeak.server:main" csv = "databeak.server:main" # Legacy alias sync-versions = "scripts.sync_versions:main" # Version synchronization utility # Note: We use uv for environment and dependency management # Hatchling is used only as the build backend for packaging [tool.hatch.build.targets.sdist] include = [ "/src", "/tests", "/examples", "README.md", "LICENSE", "NOTICE", "CHANGELOG.md", "pyproject.toml", ] exclude = [ "*.pyc", "__pycache__", ".git", ".github", ".venv", ".env", ".DS_Store", "*.egg-info", ".pytest_cache", ".mypy_cache", ".ruff_cache", "htmlcov", ".coverage", ] [tool.hatch.build.targets.wheel] packages = ["src/databeak"] [tool.ruff] line-length = 100 fix = true output-format = "grouped" show-fixes = true [tool.ruff.lint] select = [ "A", # flake8-builtins "ARG", # flake8-unused-arguments "ASYNC",# flake8-async "B", # flake8-bugbear "C4", # flake8-comprehensions "COM", # flake8-commas "D", # pydocstyle "DTZ", # flake8-datetimez "E", # pycodestyle errors "EM", # flake8-errmsg "F", # pyflakes "FA", # flake8-future-annotations "FBT", # flake8-boolean-trap "FIX", # flake8-fixme "FLY", # flynt "FURB", # refurb "G", # flake8-logging-format "I", # isort "ICN", # flake8-import-conventions "ISC", # flake8-implicit-str-concat "LOG", # flake8-logging "N", # pep8-naming "NPY", # NumPy-specific rules "PD", # pandas-vet "PGH", # pygrep-hooks "PERF", # Perflint "PIE", # flake8-pie "PL", # Pylint "PT", # flake8-pytest-style "PTH", # flake8-use-pathlib "Q", # flake8-quotes "RET", # flake8-return "RSE", # flake8-raise "RUF", # Ruff-specific rules "S", # flake8-bandit "SIM", # flake8-simplify "SLF", # flake8-self "T20", # flake8-print "TID", # flake8-tidy-imports "TRY", # tryceratops "UP", # pyupgrade "W", # pycodestyle warnings ] ignore = [ "D203", # Incompatible with formatter "D211", "D213", # Incompatible with D203, D212 "E501", # line too long (handled by ruff format) "COM812", # Missing trailing comma (handled by ruff format) "RET501", # Copilot and Clyde Code PR reviewers prefer 'return None' to 'return' "SIM105", # contextlib.suppress is slower that try-except-pass "SIM108", # Ternary operator - preference # TODO: Work on bringing these into play "PLR0911", "PLR0912", "PLR0913", "PLR0915", # Complexity findings that make the AI cry ] [tool.ruff.lint.per-file-ignores] # Allow unused arguments, naive datetime, temp files, binding all interfaces, blocking file ops, and assert in tests "tests/*" = ["ARG", "DTZ", "S108", "S104", "ASYNC230", "S101", "SLF001", "D", # Docstring requirements (tests don't need comprehensive documentation) "PLC0415", # Local import "PLR2004", # Magic numbers are a HUGE part of testing "RUF043", # Regex in asserts in tests "RUF059", # Unused unpacked variable "PT011", # TODO: Revisit post v0.1.0 "TRY300", # TODO: Revisit post v0.1.0 ] "examples/*" = ["T201", "T203", "PL"] # Allow print() in examples "scripts/*" = [ "T201", "T203", # Allow print() in scripts "TRY300", # TODO: Revisit post v0.1.0 ] [tool.ruff.lint.isort] known-first-party = ["src", "databeak"] section-order = ["future", "standard-library", "third-party", "first-party", "local-folder"] [tool.ruff.format] quote-style = "double" indent-style = "space" skip-magic-trailing-comma = false [tool.mypy] python_version = "3.12" mypy_path = "./src" namespace_packages = false explicit_package_bases = false warn_return_any = true warn_unused_configs = true disallow_untyped_defs = true disallow_any_unimported = false disallow_any_explicit = false disallow_any_generics = true # From pydantic recommendation no_implicit_optional = true no_implicit_reexport = true # From pydantic recommendation check_untyped_defs = true warn_redundant_casts = true warn_unused_ignores = true warn_no_return = true show_error_codes = true strict_equality = true pretty = true show_column_numbers = true show_error_context = true follow_imports = "silent" # From pydantic recommendation exclude = ["examples/"] plugins = [ "pydantic.mypy", # "pandera.mypy", # TODO: Enable when pre-commit environment supports pandera ] [tool.pydantic-mypy] init_forbid_extra = true init_typed = false # Too many Enums gumming up the works warn_required_dynamic_aliases = true [tool.pandera.mypy] # Enable enhanced DataFrame type checking with Pandera warn_untyped_dataframes = true warn_untyped_fields = true [[tool.mypy.overrides]] module = [ "fastmcp", "tabulate", "openpyxl", "pyarrow", "numexpr", "bottleneck", "fastparquet", "pytest", "simpleeval", "smithery", ] ignore_missing_imports = true [[tool.mypy.overrides]] module = ["tests.*", "tests.unit.*", "tests.integration.*", "tests.security.*"] disallow_untyped_defs = true disallow_any_explicit = true #disable_error_code = ["arg-type", "no-untyped-def"] check_untyped_defs = true [[tool.mypy.overrides]] module = "examples.*" ignore_errors = true [[tool.mypy.overrides]] module = "src.databeak.models.pandera_schemas" ignore_errors = true # Complex Pandera/FastMCP type compatibility - TODO: resolve in future PR [[tool.mypy.overrides]] module = "tests.unit.models.test_pandera_schemas" ignore_errors = true # Pandera not available in pre-commit environment [tool.pytest.ini_options] minversion = "8.0" testpaths = ["./tests"] pythonpath = ["./src"] asyncio_mode = "auto" asyncio_default_fixture_loop_scope = "module" asyncio_default_test_loop_scope = "module" addopts = [ "--strict-markers", "--tb=short", "--verbose", "--color=yes", "-ra", ] markers = [ "slow: marks tests as slow (deselect with '-m \"not slow\"')", "integration: marks tests as integration tests", "unit: marks tests as unit tests", "asyncio: marks tests as async", ] filterwarnings = [ "ignore::DeprecationWarning", "ignore::PendingDeprecationWarning", ] [tool.coverage.run] source = ["src"] branch = true parallel = true omit = [ "*/tests/*", "*/__pycache__/*", "*/site-packages/*", "src/databeak/__main__.py", ] [tool.coverage.report] exclude_lines = [ "pragma: no cover", "def __repr__", "def __str__", "raise AssertionError", "raise NotImplementedError", "if __name__ == .__main__.:", "if TYPE_CHECKING:", "pass", "@abstractmethod", "@abc.abstractmethod", ] precision = 2 show_missing = true skip_covered = false skip_empty = true sort = "Cover" fail_under = 80 [tool.coverage.html] directory = "htmlcov" title = "DataBeak Coverage Report" [tool.coverage.json] output = "coverage.json" pretty_print = true # Markdown formatting [tool.mdformat] wrap = 80 number = true end_of_line = "lf" # Documentation [tool.mkdocs] site_name = "DataBeak" site_description = "Comprehensive CSV manipulation and analysis via Model Context Protocol" site_author = "Santosh Ray" repo_url = "https://github.com/jonpspri/databeak" repo_name = "databeak" [tool.smithery] server = "databeak.server:create_server" [dependency-groups] dev = [ "mdformat>=0.7.22", "mdformat-frontmatter>=2.0.8", "mdformat-gfm>=0.4.1", "mdformat-ruff>=0.1.3", "mkdocs>=1.6.1", "mkdocs-material>=9.6.18", "mkdocs-mermaid2-plugin>=1.2.2", "mkdocstrings[python]>=0.30.0", "mypy>=1.17.1", "pandas-stubs>=2.3.0", "pre-commit>=4.3.0", "pymarkdownlnt>=0.9.32", "pytest>=8.4.2", "pytest-asyncio>=1.1.0", "pytest-cov>=6.2.1", "pytest-xdist>=3.8.0", "ruff>=0.12.10", "twine>=6.1.0", "ty>=0.0.1a21", "types-aiofiles>=24.1.0.20250822", "types-jsonschema>=4.25.1.20250822", "types-psutil>=7.0.0.20250822", "types-pytz>=2025.2.0.20250809", "types-tabulate>=0.9.0.20241207", ] # Pre-commit hooks configuration (for reference) # Create .pre-commit-config.yaml separately