Fix data pipelines once and for all

pipeline/transform/postcode_boundaries/test_postcode_boundaries.py

@@ -921,6 +921,49 @@ class TestToWgs84Geojson:
         area_m2 = transform_geometry(to_bng.transform, shape(result)).area
         assert area_m2 > 100, f"point footprint only {area_m2:.1f} m^2"
 
+    def test_snappable_pointlike_polygon_still_gets_building_scale_footprint(self):
+        """A collapsed-but-snappable footprint (e.g. EC2A 2FJ: 181 properties on
+        0.86 m²) must NOT ship as-is just because it survives precision snapping;
+        pointlike inputs are rescued to a ~201 m² disc unconditionally."""
+        import pyproj
+        from shapely.geometry import shape
+        from shapely.ops import transform as transform_geometry
+
+        to_bng = pyproj.Transformer.from_crs(
+            "EPSG:4326", "EPSG:27700", always_xy=True
+        )
+        # 0.9m x 0.9m square: area 0.81 m², perimeter 3.6 m — pointlike, yet
+        # large enough (~8 output-grid cells) to survive the 1e-6 deg snap.
+        tiny = box(530000, 180000, 530000.9, 180000.9)
+        from .output import _snap_to_wgs84_geojson
+
+        assert _snap_to_wgs84_geojson(tiny) is not None, (
+            "precondition: this polygon must be snappable, otherwise the test "
+            "exercises the old snap-fails path instead of the new one"
+        )
+        result = to_wgs84_geojson(tiny)
+        assert result is not None
+        area_m2 = transform_geometry(to_bng.transform, shape(result)).area
+        assert 150 < area_m2 < 300, (
+            f"pointlike snappable footprint shipped at {area_m2:.2f} m^2 "
+            "instead of a building-scale (~201 m^2) disc"
+        )
+
+    def test_normal_polygon_area_unchanged(self):
+        """A normal polygon must pass through without rescue inflation."""
+        import pyproj
+        from shapely.geometry import shape
+        from shapely.ops import transform as transform_geometry
+
+        to_bng = pyproj.Transformer.from_crs(
+            "EPSG:4326", "EPSG:27700", always_xy=True
+        )
+        poly = box(530000, 180000, 530100, 180100)  # 10,000 m²
+        result = to_wgs84_geojson(poly)
+        assert result is not None
+        area_m2 = transform_geometry(to_bng.transform, shape(result)).area
+        assert area_m2 == pytest.approx(10_000, rel=0.01)
+
     def test_thin_sliver_keeps_minimal_buffer(self):
         """A genuine elongated sliver still carries length, so it is NOT inflated
         to building scale — only truly pointlike inputs are."""
@@ -1132,6 +1175,26 @@ class TestSubtractGreenspace:
         # 80% < 90% cap, so subtraction should happen
         assert result.area == pytest.approx(2000, rel=0.01)
 
+    def test_load_greenspace_repairs_invalid_and_drops_empty(self, tmp_path):
+        """An invalid (bow-tie) park polygon in the parquet must be repaired on
+        load: it would otherwise make the per-postcode intersects/difference
+        liable to raise hours into a merge."""
+        from .greenspace import load_greenspace
+
+        bowtie = Polygon([(0, 0), (10, 10), (10, 0), (0, 10)])  # self-intersects
+        assert not bowtie.is_valid
+        valid = box(20, 20, 30, 30)
+        path = tmp_path / "greenspace.parquet"
+        pl.DataFrame({"geometry": [bowtie.wkb, valid.wkb]}).write_parquet(path)
+
+        tree, geoms = load_greenspace(path)
+        assert len(geoms) == 2
+        assert all(g.is_valid and not g.is_empty for g in geoms)
+        # The repaired bow-tie must still subtract cleanly.
+        result = subtract_greenspace(box(0, 0, 100, 100), tree, geoms)
+        assert result.is_valid
+        assert result.area < 10_000
+
 
 class TestToWgs84GeojsonValidity:
     """to_wgs84_geojson must emit GeoJSON that round-trips to a valid geometry."""