Test changes

pipeline/download/test_places.py

@@ -0,0 +1,81 @@
+import polars as pl
+
+from pipeline.download.places import (
+    _is_dlr_station,
+    _is_tram_station,
+    _naptan_dlr_stations,
+    _station_display_name,
+)
+
+
+def test_dlr_light_rail_is_not_treated_as_tram():
+    dlr_tags = {
+        "name": "Lewisham DLR",
+        "railway": "station",
+        "station": "light_rail",
+        "network": "Docklands Light Railway",
+    }
+
+    assert _is_dlr_station(dlr_tags)
+    assert not _is_tram_station(dlr_tags)
+    assert _station_display_name("Lewisham DLR", dlr_tags) == "Lewisham DLR station"
+    assert (
+        _station_display_name("Tower Gateway Station DLR", dlr_tags)
+        == "Tower Gateway DLR station"
+    )
+
+
+def test_tram_light_rail_is_still_excluded():
+    tram_tags = {
+        "name": "East Croydon",
+        "railway": "station",
+        "station": "light_rail",
+        "network": "London Trams",
+    }
+
+    assert not _is_dlr_station(tram_tags)
+    assert _is_tram_station(tram_tags)
+
+
+def test_naptan_dlr_stations_are_deduplicated_by_atco_code(tmp_path):
+    naptan = tmp_path / "naptan.parquet"
+    pl.DataFrame(
+        {
+            "id": [
+                "4900ZZDLSHA3",
+                "9400ZZDLSHA",
+                "4900ZZDLGRE1",
+                "490002076RV",
+                "4900ZZLUBNK",
+            ],
+            "name": [
+                "Shadwell DLR",
+                "Shadwell DLR Station",
+                "Greenwich Station",
+                "Tower Gateway Station DLR",
+                "Bank",
+            ],
+            "category": [
+                "Tube station",
+                "Tube station",
+                "Rail station",
+                "Bus stop",
+                "Tube station",
+            ],
+            "lat": [51.51156, 51.511693, 51.47794, 51.510575, 51.5131],
+            "lng": [-0.055595, -0.056643, -0.01442, -0.07514, -0.0894],
+        }
+    ).write_parquet(naptan)
+
+    stations = _naptan_dlr_stations(naptan)
+
+    assert [station["name"] for station in stations] == [
+        "Greenwich DLR station",
+        "Shadwell DLR station",
+    ]
+    shadwell = next(
+        station for station in stations if station["name"].startswith("Shadwell")
+    )
+    assert shadwell["lat"] == (51.51156 + 51.511693) / 2
+    assert shadwell["place_type"] == "station"
+    assert shadwell["travel_destination"] is True