Fix data pipelines once and for all

pipeline/transform/postcode_boundaries/output.py

@@ -101,6 +101,21 @@ def _snap_to_wgs84_geojson(geom_bng: Polygon | MultiPolygon) -> dict | None:
     return geojson_dict
 
 
+def _is_pointlike(geom_bng) -> bool:
+    """True if a BNG geometry carries no real extent (tower-block signature).
+
+    Near-zero area AND short perimeter together distinguish a collapsed point
+    from a genuine thin sliver, which still carries length.
+    """
+    try:
+        return (
+            geom_bng.area < _POINTLIKE_AREA_M2
+            and geom_bng.length < _POINTLIKE_PERIMETER_M
+        )
+    except GEOSException:
+        return False
+
+
 def _rescue_footprint(geom_bng) -> dict | None:
     """Fatten a degenerate BNG geometry into a representable footprint and snap.
 
@@ -109,15 +124,9 @@ def _rescue_footprint(geom_bng) -> dict | None:
     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
+    buffer_m = (
+        _POINT_RESCUE_BUFFER_M if _is_pointlike(geom_bng) else _MIN_FOOTPRINT_BUFFER_M
+    )
     footprint = _largest_polygonal(geom_bng.buffer(buffer_m))
     if footprint is None:
         return None
@@ -147,10 +156,16 @@ def to_wgs84_geojson(
         )
         if simplified is None:
             simplified = cleaned
-        # Normal path; if snapping erases a thin sliver, fatten its real shape.
-        result = _snap_to_wgs84_geojson(simplified)
-        if result is None:
+        if _is_pointlike(simplified):
+            # A POINTLIKE footprint is rescued to building scale even when it
+            # would survive snapping: a 0.1-1 m² polygon serializes fine but
+            # ships as an invisible dot covering a whole tower block.
             result = _rescue_footprint(simplified)
+        else:
+            # Normal path; if snapping erases a thin sliver, fatten its real shape.
+            result = _snap_to_wgs84_geojson(simplified)
+            if result is None:
+                result = _rescue_footprint(simplified)
         if result is not None:
             return result
 
@@ -229,6 +244,10 @@ def merge_fragments(
         greenspace_tree: Optional STRtree of park/water polygons.
         greenspace_geoms: Optional list of park/water geometries (indexed by tree).
     """
+    subtract = greenspace_tree is not None and greenspace_geoms is not None
+    if subtract:
+        from .greenspace import subtract_greenspace
+
     by_postcode: dict[str, list] = defaultdict(list)
     for pc, geom in all_fragments:
         by_postcode[pc].append(geom)
@@ -256,9 +275,7 @@ def merge_fragments(
         # Remove artifact interior holes from INSPIRE+Voronoi+make_valid chain
         combined = _fill_holes(combined)
         # Subtract parks/water if provided
-        if greenspace_tree is not None and greenspace_geoms is not None:
-            from .greenspace import subtract_greenspace
-
+        if subtract:
             pre_green = combined
             combined = subtract_greenspace(combined, greenspace_tree, greenspace_geoms)
             combined = _keep_polygon_parts(combined)