Improve data pipeline

pipeline/transform/postcode_boundaries/test_postcode_boundaries.py

@@ -893,3 +893,54 @@ class TestSubtractGreenspace:
         result = subtract_greenspace(postcode, tree, geoms)
         # 80% < 90% cap, so subtraction should happen
         assert result.area == pytest.approx(2000, rel=0.01)
+
+
+class TestToWgs84GeojsonValidity:
+    """to_wgs84_geojson must emit GeoJSON that round-trips to a valid geometry."""
+
+    def test_geojson_round_trips_to_valid_geometry(self):
+        from shapely.geometry import shape
+
+        geojson = to_wgs84_geojson(box(530000, 180000, 530100, 180100))
+        assert geojson is not None
+        rt = shape(geojson)
+        assert not rt.is_empty
+        assert rt.is_valid
+
+    def test_written_district_features_are_all_valid(self, tmp_path):
+        from shapely.geometry import shape
+
+        postcodes = {
+            "AA1 1AA": box(530000, 180000, 530100, 180100),
+            "AA1 1AB": MultiPolygon(
+                [
+                    box(530200, 180000, 530250, 180050),
+                    box(530200, 180060, 530250, 180110),
+                ]
+            ),
+        }
+        assert write_district_geojson(postcodes, tmp_path) == 1
+        collection = json.loads((tmp_path / "units" / "AA1.geojson").read_text())
+        for feature in collection["features"]:
+            geom = shape(feature["geometry"])
+            assert geom.is_valid
+            assert not geom.is_empty
+
+
+class TestGreenspaceHolePreserved:
+    """Interior holes carved by greenspace subtraction must survive merge_fragments
+    (the post-subtraction _fill_holes that previously negated them was removed)."""
+
+    def test_interior_lake_hole_survives_merge_fragments(self):
+        from shapely.strtree import STRtree
+
+        postcode = box(0, 0, 100, 100)  # 10000 sqm
+        lake = box(30, 30, 70, 70)  # 1600 sqm fully-interior hole (16% removal)
+        result = merge_fragments(
+            [("TEST1", postcode)],
+            greenspace_tree=STRtree([lake]),
+            greenspace_geoms=[lake],
+        )
+        merged = result["TEST1"]
+        assert len(list(merged.interiors)) == 1
+        assert merged.area == pytest.approx(10000 - 1600, rel=0.05)