Files
geointel/backend/tests/test_sprint214_dov_soil_map.py
T
JensandClaude Opus 5 39c12822bc extract the map workspace's domain layer out of the component
MapWorkspace.tsx opened with ~590 lines of theme catalogue, dataset matching
and label formatting above a 3.200-line component. None of it is React, all of
it is independently testable, and both render paths read from it, so it belongs
beside the pure helpers that already live in mapWorkspaceUtils.

The contract tests that read MapWorkspace.tsx would have gone red for a move
that changes no behaviour at all — 24 of them. That is the brittleness the
frontend_contract helper exists to remove, so it gains read_map_workspace():
the workspace is one feature spread over several modules, and a contract
belongs to the feature rather than to whichever file currently holds it.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-22 18:49:06 +02:00

185 lines
6.3 KiB
Python

from __future__ import annotations
import importlib.util
from pathlib import Path
from uuid import uuid4
import pytest
from shapely.geometry import box, mapping, shape
from shapely.ops import transform as transform_geometry
from app.models import Dataset
from app.services.vector_feature_service import VectorFeatureService
from tests.frontend_contract import read_map_workspace
ROOT = Path(__file__).resolve().parents[2]
def load_operator():
path = ROOT / "scripts" / "provision_mol_soil_map.py"
spec = importlib.util.spec_from_file_location("dov_soil_map_operator", path)
assert spec and spec.loader
module = importlib.util.module_from_spec(spec)
spec.loader.exec_module(module)
return module
class FakeResponse:
def __init__(self, payload: dict, url: str):
self._payload = payload
self.url = url
self.content = b'{"type":"FeatureCollection"}'
def raise_for_status(self) -> None:
return None
def json(self) -> dict:
return self._payload
class FakeSession:
def __init__(self, pages: list[dict]):
self.pages = pages
self.calls: list[dict] = []
def get(self, _url: str, *, params: dict, timeout: int):
self.calls.append({"params": dict(params), "timeout": timeout})
return FakeResponse(self.pages[len(self.calls) - 1], f"https://example.test/page/{len(self.calls)}")
def soil_feature(module, feature_id: str = "bodemtypes.1") -> dict:
return {
"type": "Feature",
"id": feature_id,
"geometry": mapping(box(5.0, 51.0, 5.02, 51.02)),
"properties": {
"gid": 1,
"id_kaartvlak": 10,
"Bodemtype": "Zeg",
"Unibodemtype": "Zeg",
"Bodemserie": "Zeg",
"Beknopte_omschrijving_bodemserie": "Natte zandbodem",
"Gegeneraliseerde_legende": "Nat zand",
"Textuurklasse_code": "Z",
"Textuurklasse": "zand",
"Drainageklasse_code": "e",
"Drainageklasse": "nat",
"Profielontwikkelingsgroep_code": "g",
"Profielontwikkelingsgroep": "humus B horizont",
"Eenduidige_legende_titel": "bodemserie Zeg",
},
}
def test_wfs_pagination_is_bounded_complete_and_deterministic() -> None:
module = load_operator()
feature = soil_feature(module)
pages = [
{
"type": "FeatureCollection",
"numberMatched": 3,
"numberReturned": 2,
"features": [feature, {**feature, "id": "bodemtypes.2"}],
},
{
"type": "FeatureCollection",
"numberMatched": 3,
"numberReturned": 1,
"features": [{**feature, "id": "bodemtypes.3"}],
},
]
session = FakeSession(pages)
result = list(
module.iter_wfs_pages(
session,
(196000.0, 205000.0, 211000.0, 224000.0),
page_limit=2,
timeout=30,
)
)
assert len(result) == 2
assert [call["params"]["startIndex"] for call in session.calls] == ["0", "2"]
assert all(call["params"]["typeNames"] == "bodemkaart:bodemtypes" for call in session.calls)
assert all(call["params"]["bbox"].endswith("EPSG:31370") for call in session.calls)
assert all(call["params"]["sortBy"] == "gid" for call in session.calls)
def test_soil_feature_is_exactly_clipped_and_keeps_governed_properties() -> None:
module = load_operator()
boundary_wgs84 = box(5.005, 51.005, 5.015, 51.015)
boundary_lambert72 = transform_geometry(module.TO_LAMBERT72.transform, boundary_wgs84)
normalized, was_clipped = module.normalize_feature(soil_feature(module), boundary_lambert72)
assert normalized is not None and was_clipped is True
persisted_geometry = shape(normalized["geometry"])
assert persisted_geometry.within(boundary_wgs84.buffer(1e-7))
properties = normalized["properties"]
assert properties["source_name"] == "dov_soil_map"
assert properties["soil_texture_class"] == "zand"
assert properties["soil_drainage_class"] == "nat"
assert properties["survey_period"] == "1949-1971"
assert properties["clipped_area_ha"] > 0
assert "may differ today" in properties["historical_drainage_limitation"]
def test_soil_map_uses_existing_semantic_selection_architecture() -> None:
dataset = Dataset(
id=uuid4(),
project_id=uuid4(),
name="dov_soil_map_mol.geojson",
dataset_type="vector",
source="operator_official_import",
source_name="dov_soil_map",
reference_layer_name="soil",
source_metadata={
"theme": "soil",
"selection_aggregation": {
"method": "intersection_area",
"label": "Bodemkaartoppervlakte",
"unit": "ha",
},
},
status="ready",
)
assert VectorFeatureService._dataset_theme(dataset) == "soil"
assert VectorFeatureService.supports_selection_summary(dataset) is True
assert VectorFeatureService.can_use_full_area_fast_path(dataset, None) is False
def test_soil_operator_contract_has_no_direct_persistence_and_is_packaged() -> None:
operator = (ROOT / "scripts" / "provision_mol_soil_map.py").read_text(encoding="utf-8")
dockerfile = (ROOT / "deploy" / "unraid" / "Dockerfile.all-in-one").read_text(encoding="utf-8")
readiness = (ROOT / "scripts" / "run_readiness_check.sh").read_text(encoding="utf-8")
map_workspace = read_map_workspace()
assert "/datasets/upload" in operator
assert "vector_features" in operator
assert "does not write directly" in " ".join(operator.split())
assert "SessionLocal" not in operator and "INSERT INTO" not in operator
assert "COPY scripts/provision_mol_soil_map.py" in dockerfile
assert "py_compile scripts/provision_mol_soil_map.py" in readiness
assert "id: 'soil'" in map_workspace
assert "dataset.source_name === 'dov_soil_map'" in map_workspace
def test_incomplete_wfs_pagination_fails_closed() -> None:
module = load_operator()
session = FakeSession(
[
{
"type": "FeatureCollection",
"numberMatched": 2,
"numberReturned": 0,
"features": [],
}
]
)
with pytest.raises(RuntimeError, match="returned 0 of 2"):
list(module.iter_wfs_pages(session, (0.0, 0.0, 1.0, 1.0), page_limit=100, timeout=30))