Changes

pipeline/download/places.py

@@ -1,6 +1,7 @@
-"""Extract place=* nodes from OSM PBF → data/places.parquet.
+"""Extract place=* nodes and railway stations from OSM PBF → data/places.parquet.
 
-Extracts named place nodes (cities, towns, suburbs, etc.) for typeahead search.
+Extracts named place nodes (cities, towns, suburbs, etc.) and railway stations
+(tube, national rail, DLR, etc.) for typeahead search.
 Reuses the same great-britain-latest.osm.pbf as pois.py.
 """
 
@@ -18,13 +19,54 @@ PLACE_TYPES = {
     "borough",
     "town",
     "suburb",
+    "quarter",
     "neighbourhood",
     "village",
     "hamlet",
     "locality",
+    "island",
     "isolated_dwelling",
 }
 
+# Suffixes to strip from raw station names before appending the typed suffix.
+_STATION_STRIP = (
+    " tube station",
+    " underground station",
+    " railway station",
+    " dlr station",
+    " overground station",
+    " tram stop",
+    " station",
+)
+
+
+def _station_display_name(name: str, tags: dict[str, str]) -> str:
+    """Build a descriptive station name like 'Bank tube station'."""
+    station_tag = tags.get("station", "")
+    network = tags.get("network", "").lower()
+
+    if station_tag == "subway" or "underground" in network:
+        suffix = "tube station"
+    elif "docklands" in network or "dlr" in network:
+        suffix = "DLR station"
+    elif "overground" in network:
+        suffix = "overground station"
+    elif "elizabeth" in network:
+        suffix = "Elizabeth line station"
+    elif station_tag == "light_rail" or "tramlink" in network or "tram" in network:
+        suffix = "tram stop"
+    else:
+        suffix = "railway station"
+
+    # Strip any existing station suffix from the raw name
+    lower = name.lower()
+    for s in _STATION_STRIP:
+        if lower.endswith(s):
+            name = name[: len(name) - len(s)].rstrip()
+            break
+
+    return f"{name} {suffix}"
+
 
 class PlaceHandler(osmium.SimpleHandler):
     def __init__(self, progress: tqdm) -> None:
@@ -32,6 +74,12 @@ class PlaceHandler(osmium.SimpleHandler):
         self._progress = progress
         self.places: list[dict] = []
 
+    def _add(self, name: str, place_type: str, lat: float, lon: float, population: int) -> None:
+        self.places.append(
+            {"name": name, "place_type": place_type, "lat": lat, "lon": lon, "population": population}
+        )
+        self._progress.set_postfix(places=f"{len(self.places):,}", refresh=False)
+
     def node(self, n: osmium.osm.Node) -> None:
         self._progress.update(1)
         if not n.location.valid:
@@ -39,16 +87,28 @@ class PlaceHandler(osmium.SimpleHandler):
         lat, lon = n.location.lat, n.location.lon
         if not (UK_BBOX_SOUTH <= lat <= UK_BBOX_NORTH and UK_BBOX_WEST <= lon <= UK_BBOX_EAST):
             return
-        place_type = n.tags.get("place")
-        if place_type not in PLACE_TYPES:
-            return
+
         name = n.tags.get("name:en", n.tags.get("name", ""))
         if not name:
             return
-        self.places.append(
-            {"name": name, "place_type": place_type, "lat": lat, "lon": lon}
-        )
-        self._progress.set_postfix(places=f"{len(self.places):,}", refresh=False)
+
+        pop_str = n.tags.get("population", "")
+        try:
+            population = int(pop_str)
+        except ValueError:
+            population = 0
+
+        # place=* nodes (cities, towns, suburbs, etc.)
+        place_type = n.tags.get("place")
+        if place_type in PLACE_TYPES:
+            self._add(name, place_type, lat, lon, population)
+            return
+
+        # railway=station nodes (tube, national rail, DLR, tram, etc.)
+        if n.tags.get("railway") == "station":
+            display_name = _station_display_name(name, dict(n.tags))
+            self._add(display_name, "station", lat, lon, population)
+            return
 
 
 def main() -> None:
@@ -73,7 +133,7 @@ def main() -> None:
         else:
             print(f"Using cached PBF: {pbf_file}")
 
-    print(f"Extracting place nodes: {sorted(PLACE_TYPES)}")
+    print(f"Extracting place nodes: {sorted(PLACE_TYPES)} + railway=station")
     with tqdm(
         unit=" elements",
         unit_scale=True,