from pathlib import Path

DATA_DIR = Path("./data_sources")
GB_PBF_FILE = DATA_DIR / "great-britain-latest.osm.pbf"
OUTPUT_FILE = DATA_DIR / "uk_pois.parquet"


BATCH_SIZE = 50_000

MIN_OCCURENCE_COUNT = 20

GEOFABRIK_GB_URL = (
    "https://download.geofabrik.de/europe/great-britain-latest.osm.pbf"
)

UK_BBOX_WEST = -7.57
UK_BBOX_SOUTH = 49.96
UK_BBOX_EAST = 1.68
UK_BBOX_NORTH = 58.64

POI_TAG_KEYS: list[str] = [
    "amenity",
    "building",
    "craft",
    "emergency",
    "healthcare",
    "leisure",
    "office",
    "shop",
    "tourism",
    "public_transport",
]