feat(provenance): govern source snapshots and data inputs

backend/tests/test_sprint7a_persistence_foundation.py

@@ -6,6 +6,7 @@ from uuid import uuid4
 
 import pytest
 from geoalchemy2.shape import to_shape
+from pyproj import Transformer
 
 from app.api.routes.qa import compare_candidate_with_reference
 from app.models import Dataset, Metric, Project, QualityCheck, VectorFeature
@@ -117,6 +118,54 @@ def test_vector_feature_service_normalizes_source_z_coordinates_to_canonical_2d(
     assert to_shape(persisted[0].geometry).has_z is False
 
 
+def test_vector_feature_service_transforms_declared_source_crs_before_epsg4326_storage() -> None:
+    to_lambert = Transformer.from_crs("EPSG:4326", "EPSG:31370", always_xy=True)
+    x, y = to_lambert.transform(4.7, 51.1)
+    db = FakeSession()
+
+    persisted = VectorFeatureService.persist_geojson_features(
+        db=db,
+        dataset_id=uuid4(),
+        payload={
+            "type": "FeatureCollection",
+            "features": [
+                {
+                    "type": "Feature",
+                    "id": "lambert-point",
+                    "properties": {},
+                    "geometry": {"type": "Point", "coordinates": [x, y]},
+                }
+            ],
+        },
+        source_crs="EPSG:31370",
+    )
+
+    geometry = to_shape(persisted[0].geometry)
+    assert geometry.x == pytest.approx(4.7, abs=0.000001)
+    assert geometry.y == pytest.approx(51.1, abs=0.000001)
+
+
+def test_vector_feature_service_rejects_invalid_declared_source_crs() -> None:
+    with pytest.raises(Exception) as exc_info:
+        VectorFeatureService.persist_geojson_features(
+            db=FakeSession(),
+            dataset_id=uuid4(),
+            payload={
+                "type": "FeatureCollection",
+                "features": [
+                    {
+                        "type": "Feature",
+                        "properties": {},
+                        "geometry": {"type": "Point", "coordinates": [4.7, 51.1]},
+                    }
+                ],
+            },
+            source_crs="EPSG:not-a-crs",
+        )
+
+    assert getattr(exc_info.value, "code", None) == "INVALID_DATASET_CRS"
+
+
 def test_dataset_upload_persists_vector_features(monkeypatch, tmp_path) -> None:
     project_id = uuid4()
     db = FakeSession(objects={(Project, project_id): Project(id=project_id, name="Geel")})