fix: make vector ingestion canonical and atomic

backend/tests/test_sprint7a_persistence_foundation.py

@@ -5,6 +5,7 @@ from pathlib import Path
 from uuid import uuid4
 
 import pytest
+from geoalchemy2.shape import to_shape
 
 from app.api.routes.qa import compare_candidate_with_reference
 from app.models import Dataset, Metric, Project, QualityCheck, VectorFeature
@@ -22,6 +23,7 @@ class FakeSession:
         self.commits = 0
         self.refreshes = []
         self.flushes = 0
+        self.rollbacks = 0
 
     def get(self, model, item_id):
         return self.objects.get((model, item_id))
@@ -38,6 +40,9 @@ class FakeSession:
     def refresh(self, item) -> None:
         self.refreshes.append(item)
 
+    def rollback(self) -> None:
+        self.rollbacks += 1
+
 
 def test_vector_feature_service_persists_geojson_features_with_properties() -> None:
     db = FakeSession()
@@ -84,6 +89,34 @@ def test_vector_feature_service_persists_geojson_features_with_properties() -> N
     assert db.refreshes == []
 
 
+def test_vector_feature_service_normalizes_source_z_coordinates_to_canonical_2d() -> None:
+    db = FakeSession()
+    persisted = VectorFeatureService.persist_geojson_features(
+        db=db,
+        dataset_id=uuid4(),
+        payload={
+            "type": "FeatureCollection",
+            "features": [
+                {
+                    "type": "Feature",
+                    "id": "sector-3d",
+                    "properties": {"population_total": 100},
+                    "geometry": {
+                        "type": "Polygon",
+                        "coordinates": [
+                            [[5.0, 51.0, 0.0], [5.1, 51.0, 0.0], [5.1, 51.1, 0.0], [5.0, 51.0, 0.0]]
+                        ],
+                    },
+                }
+            ],
+        },
+        feature_class="population",
+    )
+
+    assert len(persisted) == 1
+    assert to_shape(persisted[0].geometry).has_z is False
+
+
 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")})
@@ -141,6 +174,53 @@ def test_dataset_upload_persists_vector_features(monkeypatch, tmp_path) -> None:
     assert result.source_name == "manual"
     assert len(persisted_features) == 1
     assert persisted_features[0].dataset_id == result.id
+    assert db.commits == 1
+
+
+def test_dataset_upload_rolls_back_dataset_and_file_when_vector_indexing_fails(monkeypatch, tmp_path) -> None:
+    project_id = uuid4()
+    db = FakeSession(objects={(Project, project_id): Project(id=project_id, name="Mol")})
+    storage_path = tmp_path / "invalid.geojson"
+    storage_path.write_text("{}", encoding="utf-8")
+
+    class Upload:
+        filename = "invalid.geojson"
+        content_type = "application/geo+json"
+
+        async def read(self) -> bytes:
+            return b'{"type":"FeatureCollection","features":[]}'
+
+    monkeypatch.setattr(
+        "app.services.dataset_service.StorageService.persist_dataset_file",
+        lambda **_kwargs: {
+            "storage_path": str(storage_path),
+            "original_filename": "invalid.geojson",
+            "stored_filename": "invalid.geojson",
+            "content_type": "application/geo+json",
+            "size_bytes": 2,
+            "checksum_sha256": "0" * 64,
+        },
+    )
+    monkeypatch.setattr(
+        VectorFeatureService,
+        "persist_geojson_features",
+        lambda **_kwargs: (_ for _ in ()).throw(RuntimeError("PostGIS indexing failed")),
+    )
+
+    with pytest.raises(RuntimeError, match="PostGIS indexing failed"):
+        asyncio.run(
+            DatasetService.upload_dataset(
+                db=db,
+                project_id=project_id,
+                file=Upload(),
+                dataset_type="vector",
+                source="user_upload",
+            )
+        )
+
+    assert db.commits == 0
+    assert db.rollbacks == 1
+    assert storage_path.exists() is False
 
 
 def test_quality_service_persists_quality_check_and_metrics() -> None: