perf: optimize trusted full-area analysis

backend/tests/test_sprint194_regional_timeseries.py

@@ -7,11 +7,16 @@ import json
 from pathlib import Path
 import sys
 import zipfile
+from types import SimpleNamespace
+from uuid import uuid4
 
 import numpy as np
 import rasterio
 from rasterio.transform import from_origin
 
+from app.models import Dataset
+from app.services.vector_feature_service import VectorFeatureService
+
 
 ROOT = Path(__file__).resolve().parents[2]
 SCRIPTS = ROOT / "scripts"
@@ -184,3 +189,94 @@ def test_end_user_dataset_sources_are_human_readable() -> None:
     assert "statbel: 'Statbel'" in display
     assert "getDatasetSourceDisplayName(activeThemeDataset)" in workspace
     assert "dataset ? getDatasetSourceDisplayName(dataset)" in workspace
+
+
+def test_full_area_fast_path_requires_matching_area_and_clipped_operator_provenance() -> None:
+    project_id = uuid4()
+    area_id = uuid4()
+    trusted = Dataset(
+        id=uuid4(),
+        project_id=project_id,
+        area_id=area_id,
+        name="Regional forest",
+        dataset_type="vector",
+        source="operator_official_import",
+        provenance_metadata={"operator_tool": "provision_official_landuse_timeseries.py"},
+    )
+    explicit = Dataset(
+        id=uuid4(),
+        project_id=project_id,
+        area_id=area_id,
+        name="Clipped vector",
+        dataset_type="vector",
+        source="manual",
+        source_metadata={"geometry_clipped_to_area": True},
+    )
+    untrusted = Dataset(
+        id=uuid4(),
+        project_id=project_id,
+        area_id=area_id,
+        name="Assigned only",
+        dataset_type="vector",
+        source="manual",
+    )
+
+    assert VectorFeatureService.can_use_full_area_fast_path(trusted, area_id) is True
+    assert VectorFeatureService.can_use_full_area_fast_path(explicit, area_id) is True
+    assert VectorFeatureService.can_use_full_area_fast_path(untrusted, area_id) is False
+    assert VectorFeatureService.can_use_full_area_fast_path(trusted, uuid4()) is False
+    assert VectorFeatureService.can_use_full_area_fast_path(trusted, None) is False
+
+
+def test_full_area_summary_uses_exact_stored_values_without_partial_intersection() -> None:
+    class ScalarQuery:
+        def __init__(self, value: float) -> None:
+            self.value = value
+
+        def filter(self, *_args):
+            return self
+
+        def scalar(self):
+            return self.value
+
+    class ScalarSession:
+        def __init__(self, value: float) -> None:
+            self.value = value
+            self.query_count = 0
+
+        def query(self, *_args):
+            self.query_count += 1
+            return ScalarQuery(self.value)
+
+    dataset = Dataset(
+        id=uuid4(),
+        project_id=uuid4(),
+        name="Population",
+        dataset_type="vector",
+        source="operator_official_import",
+        source_metadata={
+            "selection_aggregation": {
+                "method": "area_weighted_sum",
+                "property": "population_total",
+                "label": "Inwoners",
+                "unit": "inwoners",
+                "warning_only_when_estimate": True,
+                "warning": "Partial-sector estimate",
+            }
+        },
+    )
+    session = ScalarSession(506_473.0)
+
+    result = VectorFeatureService.summarize_features_by_bbox(
+        session,
+        dataset=dataset,
+        bbox={"min_x": 4.5, "min_y": 51.0, "max_x": 5.3, "max_y": 51.6, "crs": "EPSG:4326"},
+        total_feature_count=733,
+        selection_geometry=SimpleNamespace(),
+        full_dataset_area=True,
+    )
+
+    assert result["metric_value"] == 506_473.0
+    assert result["is_estimate"] is False
+    assert result["warning"] is None
+    assert session.query_count == 1