Can't even keep track anymore

pipeline/download/places.py

@@ -0,0 +1,99 @@
+"""Extract place=* nodes from OSM PBF → data/places.parquet.
+
+Extracts named place nodes (cities, towns, suburbs, etc.) for typeahead search.
+Reuses the same great-britain-latest.osm.pbf as pois.py.
+"""
+
+import argparse
+from pathlib import Path
+
+import osmium
+import polars as pl
+from tqdm import tqdm
+
+from .pois import UK_BBOX_EAST, UK_BBOX_NORTH, UK_BBOX_SOUTH, UK_BBOX_WEST, download_pbf
+
+PLACE_TYPES = {
+    "city",
+    "borough",
+    "town",
+    "suburb",
+    "neighbourhood",
+    "village",
+    "hamlet",
+    "locality",
+    "isolated_dwelling",
+}
+
+
+class PlaceHandler(osmium.SimpleHandler):
+    def __init__(self, progress: tqdm) -> None:
+        super().__init__()
+        self._progress = progress
+        self.places: list[dict] = []
+
+    def node(self, n: osmium.osm.Node) -> None:
+        self._progress.update(1)
+        if not n.location.valid:
+            return
+        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)
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Extract place names from OSM PBF"
+    )
+    parser.add_argument(
+        "--output", type=Path, required=True, help="Output parquet file path"
+    )
+    parser.add_argument(
+        "--pbf", type=Path, default=None, help="Path to existing PBF file (skips download)"
+    )
+    args = parser.parse_args()
+
+    if args.pbf and args.pbf.exists():
+        pbf_file = args.pbf
+        print(f"Using existing PBF: {pbf_file}")
+    else:
+        pbf_file = Path("data/great-britain-latest.osm.pbf")
+        if not pbf_file.exists():
+            download_pbf(pbf_file)
+        else:
+            print(f"Using cached PBF: {pbf_file}")
+
+    print(f"Extracting place nodes: {sorted(PLACE_TYPES)}")
+    with tqdm(
+        unit=" elements",
+        unit_scale=True,
+        desc="Streaming",
+        smoothing=0.05,
+        mininterval=1.0,
+    ) as progress:
+        handler = PlaceHandler(progress)
+        handler.apply_file(str(pbf_file), locations=True)
+
+    print(f"Extracted {len(handler.places):,} place nodes")
+
+    if handler.places:
+        df = pl.DataFrame(handler.places)
+        args.output.parent.mkdir(parents=True, exist_ok=True)
+        df.write_parquet(args.output)
+        print(f"Saved to {args.output}")
+    else:
+        print("No places found — skipping output")
+
+
+if __name__ == "__main__":
+    main()