Fix data pipelines once and for all

pipeline/transform/postcode_boundaries/greenspace.py

@@ -3,7 +3,7 @@
 from pathlib import Path
 
 import polars as pl
-from shapely import wkb
+from shapely import make_valid, wkb
 from shapely.geometry import MultiPolygon, Polygon
 from shapely.strtree import STRtree
 
@@ -13,12 +13,23 @@ from .geometry import safe_difference, safe_union
 def load_greenspace(path: Path) -> tuple[STRtree, list]:
     """Load greenspace parquet and build an STRtree spatial index.
 
+    Geometries are repaired with ``make_valid`` on load: an invalid park/lake
+    polygon would make the per-postcode ``intersects`` predicate (and the exact
+    difference path) liable to raise mid-merge, hours into a build. Empty
+    geometries are dropped.
+
     Returns:
         (tree, geoms) where tree is a Shapely STRtree and geoms is
         the list of geometries indexed by the tree.
     """
     df = pl.read_parquet(path)
-    geoms = [wkb.loads(g) for g in df["geometry"].to_list()]
+    geoms = []
+    for raw in df["geometry"].to_list():
+        geom = wkb.loads(raw)
+        if not geom.is_valid:
+            geom = make_valid(geom)
+        if not geom.is_empty:
+            geoms.append(geom)
     tree = STRtree(geoms)
     return tree, geoms