geointel/backend/tests/test_sprint201_semantic_selection_metrics.py

from __future__ import annotations

from pathlib import Path
from uuid import uuid4

from app.models import Dataset
from app.schemas.operations import VectorSelectionSummary
from app.services.vector_feature_service import VectorFeatureService


ROOT = Path(__file__).parents[2]
BBOX = {"min_x": 5.0, "min_y": 51.1, "max_x": 5.2, "max_y": 51.3, "crs": "EPSG:4326"}


class ScalarQuery:
    def __init__(self, value: float):
        self.value = value

    def filter(self, *args):  # noqa: ANN002, ARG002
        return self

    def scalar(self):
        return self.value


class SequenceScalarSession:
    """Answers scalar queries in the order the summary issues them.

    The first query is the fully-covered feature count that produces the
    selection-edge disclosure; ``covered_count`` defaults to the full
    population, i.e. a selection that cuts nothing.
    """

    def __init__(self, values: list[float], covered_count: float | None = None):
        self.values = iter(([covered_count] if covered_count is not None else []) + values)

    def query(self, *args):  # noqa: ANN002, ARG002
        return ScalarQuery(next(self.values))


def themed_dataset(theme: str, *, method: str = "feature_count") -> Dataset:
    return Dataset(
        id=uuid4(),
        project_id=uuid4(),
        name=f"regional-{theme}.geojson",
        dataset_type="vector",
        dataset_role="reference",
        source_name="grb",
        reference_layer_name=theme,
        source_metadata={
            "theme": theme,
            "selection_aggregation": {
                "method": method,
                "label": theme.title(),
                "unit": "objecten",
            },
        },
    )


def test_building_selection_promotes_footprint_area_and_retains_object_count() -> None:
    result = VectorFeatureService.summarize_features_by_bbox(
        SequenceScalarSession([125_000.0], covered_count=40),
        dataset=themed_dataset("buildings"),
        bbox=BBOX,
        total_feature_count=40,
    )

    assert result["primary_metric_key"] == "footprint_area"
    assert result["metric_label"] == "Bebouwde grondoppervlakte"
    assert result["metric_value"] == 12.5
    assert result["metric_unit"] == "ha"
    assert [(item["metric_key"], item["metric_value"]) for item in result["metrics"]] == [
        ("footprint_area", 12.5),
        ("feature_count", 40.0),
    ]
    assert "niet de totale vloeroppervlakte" in result["warning"]
    VectorSelectionSummary(**result)


def test_water_selection_reports_surface_length_and_honest_volume_limitation() -> None:
    result = VectorFeatureService.summarize_features_by_bbox(
        SequenceScalarSession([52_500.0, 12_750.0], covered_count=23),
        dataset=themed_dataset("water"),
        bbox=BBOX,
        total_feature_count=23,
    )

    assert result["metric_value"] == 5.25
    assert result["metric_unit"] == "ha"
    assert [(item["metric_key"], item["metric_value"], item["metric_unit"]) for item in result["metrics"]] == [
        ("water_area", 5.25, "ha"),
        ("watercourse_length", 12.75, "km"),
        ("feature_count", 23.0, "objecten"),
    ]
    assert "Watervolume is niet berekenbaar" in result["warning"]


def test_population_keeps_configured_metric_and_adds_sector_count() -> None:
    dataset = themed_dataset("population", method="sum")
    dataset.source_metadata["selection_aggregation"].update(
        {"metric_key": "population", "property": "population_total", "label": "Inwoners", "unit": "inwoners"}
    )
    result = VectorFeatureService.summarize_features_by_bbox(
        SequenceScalarSession([86_458.0], covered_count=733),
        dataset=dataset,
        bbox=BBOX,
        total_feature_count=733,
    )

    assert result["primary_metric_key"] == "population"
    assert result["metric_value"] == 86_458.0
    assert result["metrics"][1] == {
        "metric_key": "feature_count",
        "metric_label": "Statistische sectoren",
        "metric_value": 733.0,
        "metric_unit": "objecten",
        "aggregation_method": "feature_count",
        "is_estimate": False,
        "warning": None,
    }


def test_station_measurement_uses_numeric_mean_without_area_extrapolation() -> None:
    dataset = themed_dataset("water", method="mean")
    dataset.source_name = "waterinfo"
    dataset.source_metadata.update(
        {
            "semantic_metrics": False,
            "selection_aggregation": {
                "metric_key": "water_level",
                "method": "mean",
                "property": "annual_mean_water_level_m",
                "label": "Jaargemiddelde waterstand",
                "unit": "m",
                "warning": "Puntmeting; geen gebiedsdekkend watervolume.",
            },
        }
    )

    result = VectorFeatureService.summarize_features_by_bbox(
        SequenceScalarSession([30.455], covered_count=1),
        dataset=dataset,
        bbox=BBOX,
        total_feature_count=1,
    )

    assert result["metric_value"] == 30.455
    assert result["aggregation_method"] == "mean"
    assert result["metric_unit"] == "m"
    assert result["warning"] == "Puntmeting; geen gebiedsdekkend watervolume."


def test_regional_historical_polygons_do_not_emit_irrelevant_line_metrics() -> None:
    dataset = themed_dataset("water", method="intersection_area")
    dataset.source_metadata["selection_aggregation"].update(
        {"metric_key": "water_area", "label": "Historische wateroppervlakte", "unit": "ha"}
    )
    dataset.provenance_metadata = {"operator_tool": "provision_regional_historical_landuse.py"}

    result = VectorFeatureService.summarize_features_by_bbox(
        SequenceScalarSession([52_500.0], covered_count=23),
        dataset=dataset,
        bbox=BBOX,
        total_feature_count=23,
    )

    assert [(item["metric_key"], item["metric_unit"]) for item in result["metrics"]] == [
        ("water_area", "ha"),
        ("feature_count", "objecten"),
    ]


def test_future_regional_imports_persist_semantic_aggregation_configuration() -> None:
    buildings = (ROOT / "scripts/provision_regional_grb_buildings.py").read_text(encoding="utf-8")
    context = (ROOT / "scripts/provision_regional_grb_context.py").read_text(encoding="utf-8")
    frontend = (ROOT / "frontend/src/components/map/MapWorkspace.tsx").read_text(encoding="utf-8")

    assert '"method": "intersection_area"' in buildings
    assert '"label": "Bebouwde grondoppervlakte"' in buildings
    assert 'metric_method="intersection_length"' in context
    assert 'metric_label="Wateroppervlakte"' in context
    assert 'metric_label="Perceeloppervlakte"' in context
    assert 'aria-label="Aanvullende gebiedsmetingen"' in frontend
    assert "activeSelectionResult.summary.warning" in frontend