pyproject.toml

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

[project]
name = "datajoint"
dynamic = ["version"]
dependencies = [
  "numpy",
  "pymysql>=0.7.2",
  "deepdiff",
  "pyparsing",
  "pandas",
  "tqdm",
  "networkx",
  "pydot",
  "fsspec>=2023.1.0",
  "pydantic-settings>=2.0.0",
]

requires-python = ">=3.10,<3.14"
authors = [
  {name = "Dimitri Yatsenko", email = "dimitri@datajoint.com"},
  {name = "Thinh Nguyen", email = "thinh@datajoint.com"},
  {name = "Raphael Guzman"},
  {name = "Edgar Walker"},
  {name = "DataJoint Contributors", email = "support@datajoint.com"},
]
maintainers = [
  {name = "Dimitri Yatsenko", email = "dimitri@datajoint.com"},
  {name = "DataJoint Contributors", email = "support@datajoint.com"},
]
# manually sync here: https://docs.datajoint.com/core/datajoint-python/latest/#welcome-to-datajoint-for-python
description = "DataJoint for Python is a framework for scientific workflow management based on relational principles. DataJoint is built on the foundation of the relational data model and prescribes a consistent method for organizing, populating, computing, and querying data."
readme = "README.md"
license = {file = "LICENSE"}
keywords = [
    "datajoint",
    "data-pipelines",
    "workflow-management",
    "data-engineering",
    "scientific-computing",
    "neuroscience",
    "research-software",
    "data-integrity",
    "reproducibility",
    "declarative",
    "etl",
    "object-storage",
    "schema-management",
    "data-lineage",
    "relational-model",
    "mysql",
    "postgresql",
]
# https://pypi.org/classifiers/
classifiers = [
  "Programming Language :: Python",
  "Development Status :: 5 - Production/Stable",
  "Intended Audience :: Science/Research",
  "Intended Audience :: Healthcare Industry",
  "License :: OSI Approved :: Apache Software License",
  "Topic :: Software Development :: Libraries :: Python Modules",
  "Topic :: Scientific/Engineering",
  "Topic :: Scientific/Engineering :: Bio-Informatics",
  "Topic :: Scientific/Engineering :: Artificial Intelligence",
]

[project.urls]
Homepage = "https://docs.datajoint.com/"
Documentation = "https://docs.datajoint.com/"
Repository = "https://github.com/datajoint/datajoint-python"
"Bug Tracker" = "https://github.com/datajoint/datajoint-python/issues"
"Release Notes" = "https://github.com/datajoint/datajoint-python/releases"

[project.scripts]
dj = "datajoint.cli:cli"
datajoint = "datajoint.cli:cli"

[dependency-groups]
test = [
  "pytest",
  "pytest-cov",
  "requests",
  "faker",
  "matplotlib",
  "ipython",
  "graphviz",
  "testcontainers[mysql,minio,postgres]>=4.0",
  "polars>=0.20.0",
  "pyarrow>=14.0.0",
]

[project.optional-dependencies]
s3 = ["s3fs>=2023.1.0"]
gcs = ["gcsfs>=2023.1.0"]
azure = ["adlfs>=2023.1.0"]
postgres = ["psycopg2-binary>=2.9.0"]
polars = ["polars>=0.20.0"]
arrow = ["pyarrow>=14.0.0"]
viz = ["matplotlib", "ipython"]
test = [
  "pytest",
  "pytest-cov",
  "requests",
  "faker",
  "matplotlib",
  "ipython",
  "s3fs>=2023.1.0",
  "testcontainers[mysql,minio,postgres]>=4.0",
  "psycopg2-binary>=2.9.0",
  "polars>=0.20.0",
  "pyarrow>=14.0.0",
]
dev = [
  "pre-commit",
  "ruff",
  "codespell",
  # including test
  "pytest",
  "pytest-cov",
  "polars>=0.20.0",
  "pyarrow>=14.0.0",
]

[tool.ruff]
# Equivalent to flake8 configuration
line-length = 127
target-version = "py310"

[tool.ruff.lint]
# Enable specific rule sets equivalent to flake8 configuration
select = [
    "E",  # pycodestyle errors
    "W",  # pycodestyle warnings
    "F",  # pyflakes
    "C90", # mccabe complexity
]

# Ignore specific rules (equivalent to flake8 --ignore)
ignore = [
    "E203",  # whitespace before ':'
    "E722",  # bare except
]

# Per-file ignores (equivalent to flake8 --per-file-ignores)
[tool.ruff.lint.per-file-ignores]
"datajoint/diagram.py" = ["C901"]  # function too complex
"tests/integration/test_blob_matlab.py" = ["E501"]  # SQL hex strings cannot be broken across lines

[tool.ruff.lint.mccabe]
# Maximum complexity (equivalent to flake8 --max-complexity)
max-complexity = 62

[tool.ruff.format]
# Use black-compatible formatting
quote-style = "double"
indent-style = "space"
line-ending = "auto"

[tool.mypy]
python_version = "3.10"
ignore_missing_imports = true
# Start with lenient settings, gradually enable stricter checks
warn_return_any = false
warn_unused_ignores = false
disallow_untyped_defs = false
disallow_incomplete_defs = false
check_untyped_defs = true

# Modules with complete type coverage - strict checking enabled
[[tool.mypy.overrides]]
module = [
    "datajoint.hash_registry",
    "datajoint.errors",
    "datajoint.hash",
]
disallow_untyped_defs = true
disallow_incomplete_defs = true
warn_return_any = true

# Modules excluded from type checking until fully typed
[[tool.mypy.overrides]]
module = [
    "datajoint.admin",
    "datajoint.autopopulate",
    "datajoint.blob",
    "datajoint.builtin_codecs",
    "datajoint.cli",
    "datajoint.codecs",
    "datajoint.condition",
    "datajoint.connection",
    "datajoint.declare",
    "datajoint.dependencies",
    "datajoint.diagram",
    "datajoint.expression",
    "datajoint.gc",
    "datajoint.heading",
    "datajoint.jobs",
    "datajoint.lineage",
    "datajoint.logging",
    "datajoint.migrate",
    "datajoint.objectref",
    "datajoint.preview",
    "datajoint.schemas",
    "datajoint.settings",
    "datajoint.staged_insert",
    "datajoint.storage",
    "datajoint.table",
    "datajoint.user_tables",
    "datajoint.utils",
]
ignore_errors = true

[tool.hatch.version]
path = "src/datajoint/version.py"

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

[tool.codespell]
skip = ".git,*.pdf,*.svg,*.csv,*.ipynb,*.drawio"
# Rever -- nobody knows
# numer -- numerator variable
# astroid -- Python library name (not "asteroid")
ignore-words-list = "rever,numer,astroid"

[tool.pytest.ini_options]
markers = [
    "requires_mysql: marks tests as requiring MySQL database (deselect with '-m \"not requires_mysql\"')",
    "requires_minio: marks tests as requiring MinIO object storage (deselect with '-m \"not requires_minio\"')",
    "mysql: marks tests that run on MySQL backend (select with '-m mysql')",
    "postgresql: marks tests that run on PostgreSQL backend (select with '-m postgresql')",
    "backend_agnostic: marks tests that should pass on all backends (auto-marked for parameterized tests)",
]


[tool.pixi.workspace]
channels = ["conda-forge"]
platforms = ["linux-64", "osx-arm64", "linux-aarch64"]

[tool.pixi.pypi-dependencies]
datajoint = { path = ".", editable = true }

[tool.pixi.feature.test.pypi-dependencies]
datajoint = { path = ".", editable = true, extras = ["test"] }

[tool.pixi.feature.dev.pypi-dependencies]
datajoint = { path = ".", editable = true, extras = ["dev", "test"] }

[tool.pixi.environments]
default = { solve-group = "default" }
dev = { features = ["dev"], solve-group = "default" }
test = { features = ["test"], solve-group = "default" }

[tool.pixi.tasks]
# Tests use testcontainers - no manual setup required
test = "pytest tests/"
test-cov = "pytest --cov-report term-missing --cov=datajoint tests/"
# Optional: use external containers (docker-compose) instead of testcontainers
services-up = "docker compose up -d db minio"
services-down = "docker compose down"
test-external = { cmd = "DJ_USE_EXTERNAL_CONTAINERS=1 pytest tests/", depends-on = ["services-up"] }

[tool.pixi.dependencies]
python = ">=3.10,<3.14"
graphviz = ">=13.1.2,<14"

[tool.pixi.activation]
scripts=["activate.sh"]