pyproject.toml

[build-system]
requires = ["setuptools>=68"]
build-backend = "setuptools.build_meta"

[project]
name = "EEADataLakehouse"
version = "0.1.7"
description = "Data preparation and validation utilities for the EEA data lakehouse pipeline."
readme = "README.md"
requires-python = ">=3.11"
license = { text = "EUPL-1.2" }
authors = [{ name = "EEA Data Hub" }]
dependencies = [
    "pandas>=3",
    "pyarrow>=25",               # parquet writer + the Arrow types the ingest lane expects
    "openpyxl>=3.1,<4",          # .xlsx reader — handles sparse cells correctly (see bathing_water/README.md)
    "xlrd>=2.0,<3",              # legacy .xls, some older SDI deliveries
    "lxml>=5.2,<7",              # ISO 19115-3 metadata records
    "duckdb>=1.1,<2",            # validate parquet with SQL before it ever leaves the machine
    # geometry: source encoding in, WKB out (see CLAUDE.md). shapely 2.x only —
    # the from_wkt/from_geojson/to_wkb vectorised API the prepare step uses
    # does not exist in 1.x. No GDAL/geopandas: reading a GeoPackage or GDB
    # companion is a separate, heavier problem, and nothing here needs it yet.
    "shapely>=2.0,<3",
    "pyproj>=3.6,<4",            # only where a reprojection is a deliberate, documented step
    "requests>=2.32,<3",
    "httpx>=0.28,<1",            # also the dds_ingest dependency
    "beautifulsoup4>=4.12,<5",   # SDI "direct download" is an HTML landing page, not a file
    "tqdm>=4.66,<5",
]

[project.optional-dependencies]
dev = [
    "pytest>=7",
    "ruff>=0.15",
    "mypy>=2.1",
    "respx>=0.23",       # mocks httpx for the ingestion test suite
    "types-tqdm",
    "ipykernel>=6.29",   # run/debug notebooks against this environment
]

[project.urls]
Repository = "https://github.com/eeadata/EEALakeHouse.python"

[tool.setuptools.packages.find]
where = ["src"]

[tool.ruff]
target-version = "py311"
line-length = 100
src = ["src", "tests"]

[tool.ruff.lint]
select = ["E", "F", "I", "UP", "B", "C4", "SIM"]

[tool.mypy]
python_version = "3.11"
strict = true
warn_return_any = false

[[tool.mypy.overrides]]
module = ["respx.*"]
ignore_missing_imports = true

[tool.pytest.ini_options]
testpaths = ["tests"]
addopts = "-q"
filterwarnings = ["ignore::DeprecationWarning"]