Improve data

pipeline/transform/postcode_boundaries/output.py

@@ -53,6 +53,18 @@ _OUTPUT_PRECISION_DEG = 0.000001
 # tolerance), we fatten it just enough to survive snapping rather than drop it.
 _MIN_FOOTPRINT_BUFFER_M = 0.5
 
+# Building-scale buffer for POINTLIKE inputs that carry no real extent. Multi-
+# dwelling (tower-block) postcodes have every UPRN geocoded to a single shared
+# coordinate, so the boundary collapses to a point; a 0.5 m buffer then yields an
+# invisible ~0.8 m² dot covering hundreds of homes. Such inputs get a ~200 m²
+# building-scale footprint instead. (Genuine thin slivers, which still carry
+# length, keep the minimal buffer.) _resolve_overlaps runs afterwards, so any
+# overlap this introduces is trimmed; a postcode shaved back to sub-grid still
+# falls through to the tiny _grid_footprint, so this can only improve the result.
+_POINT_RESCUE_BUFFER_M = 8.0
+_POINTLIKE_AREA_M2 = 1.0
+_POINTLIKE_PERIMETER_M = 4.0
+
 
 def _snap_to_wgs84_geojson(geom_bng: Polygon | MultiPolygon) -> dict | None:
     """Transform a BNG polygon to WGS84, snap to output precision, validate.
@@ -90,8 +102,23 @@ def _snap_to_wgs84_geojson(geom_bng: Polygon | MultiPolygon) -> dict | None:
 
 
 def _rescue_footprint(geom_bng) -> dict | None:
-    """Fatten a degenerate BNG geometry into a representable footprint and snap."""
-    footprint = _largest_polygonal(geom_bng.buffer(_MIN_FOOTPRINT_BUFFER_M))
+    """Fatten a degenerate BNG geometry into a representable footprint and snap.
+
+    A POINTLIKE input (a point, or a near-zero-area/short-perimeter polygon — the
+    signature of a tower-block postcode whose UPRNs all share one coordinate)
+    gets a building-scale buffer so it is not reduced to an invisible sub-metre
+    dot; thin slivers that still carry length keep the minimal buffer.
+    """
+    buffer_m = _MIN_FOOTPRINT_BUFFER_M
+    try:
+        if (
+            geom_bng.area < _POINTLIKE_AREA_M2
+            and geom_bng.length < _POINTLIKE_PERIMETER_M
+        ):
+            buffer_m = _POINT_RESCUE_BUFFER_M
+    except GEOSException:
+        pass
+    footprint = _largest_polygonal(geom_bng.buffer(buffer_m))
     if footprint is None:
         return None
     return _snap_to_wgs84_geojson(footprint)

pipeline/transform/postcode_boundaries/test_postcode_boundaries.py

@@ -906,6 +906,37 @@ class TestToWgs84Geojson:
         assert result is not None
         assert result["type"] == "Polygon"
 
+    def test_pointlike_input_gets_building_scale_footprint(self):
+        """A tower-block postcode (all UPRNs at one point) must not collapse to a
+        sub-metre dot; it gets a building-scale footprint instead."""
+        import pyproj
+        from shapely.geometry import Point, shape
+        from shapely.ops import transform as transform_geometry
+
+        to_bng = pyproj.Transformer.from_crs(
+            "EPSG:4326", "EPSG:27700", always_xy=True
+        )
+        result = to_wgs84_geojson(Point(360000, 170000))
+        assert result is not None
+        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_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."""
+        import pyproj
+        from shapely.geometry import LineString, shape
+        from shapely.ops import transform as transform_geometry
+
+        to_bng = pyproj.Transformer.from_crs(
+            "EPSG:4326", "EPSG:27700", always_xy=True
+        )
+        sliver = LineString([(360000, 170000), (360040, 170000)]).buffer(0.05)
+        result = to_wgs84_geojson(sliver)
+        assert result is not None
+        area_m2 = transform_geometry(to_bng.transform, shape(result)).area
+        assert area_m2 < 100, f"sliver inflated to {area_m2:.1f} m^2"
+
     def test_coordinates_have_limited_precision(self):
         """GeoJSON coordinates should be rounded to 6 decimal places."""
         import json