idgf

pipeline/download/test_places.py

@@ -9,10 +9,12 @@ from pipeline.download.places import (
     _display_city_from_tags,
     _is_dlr_station,
     _is_tram_station,
+    _london_postcode_tree,
     _naptan_dlr_stations,
     _normalize_street_name,
     _ofs_universities,
     _outcode_of_postcode,
+    _outcode_tree,
     _pois_to_places,
     _select_university_name,
     _station_display_name,
@@ -242,6 +244,42 @@ def test_pois_to_places_keeps_high_value_named_pois_only():
     assert all(place["travel_destination"] is False for place in places)
 
 
+def test_pois_to_places_keeps_distinct_same_named_pois():
+    # Two genuinely distinct POIs sharing a name, far apart (London vs Bristol).
+    pois = pl.DataFrame(
+        {
+            "name": ["Victoria Park", "Victoria Park"],
+            "category": ["leisure/park", "leisure/park"],
+            "lat": [51.54, 51.46],
+            "lng": [-0.04, -2.60],
+        }
+    )
+
+    places = _pois_to_places(pois)
+
+    assert len(places) == 2
+    assert {(place["lat"], place["lon"]) for place in places} == {
+        (51.54, -0.04),
+        (51.46, -2.60),
+    }
+
+
+def test_pois_to_places_still_dedupes_colocated():
+    # The same physical POI mapped twice a few metres apart collapses to one.
+    pois = pl.DataFrame(
+        {
+            "name": ["Victoria Park", "Victoria Park"],
+            "category": ["leisure/park", "leisure/park"],
+            "lat": [51.5400, 51.5401],
+            "lng": [-0.0400, -0.0399],
+        }
+    )
+
+    places = _pois_to_places(pois)
+
+    assert len(places) == 1
+
+
 def test_display_city_from_tags_uses_explicit_london_context():
     assert _display_city_from_tags({"is_in": "Croydon, London, UK"}) == "London"
     assert _display_city_from_tags({"is_in": "Croydon, Cambridgeshire, UK"}) is None
@@ -290,3 +328,52 @@ def test_assign_london_display_city_uses_nearest_active_postcode_admin(tmp_path)
 
     assert assigned == 2
     assert [place["display_city"] for place in places] == ["London", "London", None]
+
+
+def test_no_grid_reference_sentinel_is_excluded_from_coordinate_trees(tmp_path):
+    # ONS NSPL stores postcodes with no grid reference at the Null-Island sentinel
+    # lat=99.999999, long=0.0, whose paired BNG coords collapse to the (0, 0) origin.
+    # Such an active postcode must never enter the nearest-neighbour indexes.
+    sentinel = {
+        "pcds": "ZZ99 9ZZ",
+        "lat": 99.999999,
+        "long": 0.0,
+        "doterm": None,
+        "ctry25cd": "E92000001",
+        "east1m": 0,
+        "north1m": 0,
+        "rgn25cd": "E12000007",
+        "lad25cd": "E09000008",
+        "cty25cd": "E13000002",
+    }
+    croydon_easting, croydon_northing = WGS84_TO_BNG.transform(-0.101793, 51.371273)
+    real = {
+        "pcds": "CR0 1SZ",
+        "lat": 51.371273,
+        "long": -0.101793,
+        "doterm": None,
+        "ctry25cd": "E92000001",
+        "east1m": int(round(croydon_easting)),
+        "north1m": int(round(croydon_northing)),
+        "rgn25cd": "E12000007",
+        "lad25cd": "E09000008",
+        "cty25cd": "E13000002",
+    }
+    postcodes = tmp_path / "postcodes.parquet"
+    pl.DataFrame([sentinel, real]).write_parquet(postcodes)
+
+    # lat/long outcode tree: only the real postcode survives, so a London-area query
+    # cannot be tagged with the sentinel's (empty) outcode.
+    tree, outcodes = _outcode_tree(postcodes)
+    assert tree.n == 1
+    assert outcodes == ["CR0"]
+    _, idx = tree.query([[51.371273, -0.101793]])
+    assert outcodes[idx[0]] == "CR0"
+
+    # BNG London tree: only the real postcode survives, so the (0, 0) origin can never
+    # be the nearest neighbour of a real place.
+    bng_tree, london_flags = _london_postcode_tree(postcodes)
+    assert bng_tree.n == 1
+    assert london_flags.tolist() == [True]
+    _, bng_idx = bng_tree.query([[croydon_easting, croydon_northing]])
+    assert bng_idx[0] == 0