Function read_vector

leafmap/common.py:18925–19000

Reads vector data from various formats including GeoParquet. This function dynamically determines the file type based on extension and reads it into a GeoDataFrame. It supports both local files and HTTP/HTTPS URLs. Args: source (str): Path to the vector file or URL. lay

(source, layer=None, **kwargs: Any)

def read_vector(source, layer=None, **kwargs: Any):
    """Reads vector data from various formats including GeoParquet.

    This function dynamically determines the file type based on extension
    and reads it into a GeoDataFrame. It supports both local files and HTTP/HTTPS URLs.

    Args:
        source (str): Path to the vector file or URL.
        layer (str | int, optional): String or integer specifying which layer to read from multi-layer
            files (only applicable for formats like GPKG, GeoJSON, etc.).
            Defaults to None.
        **kwargs (Any): Additional keyword arguments to pass to the underlying reader.

    Returns:
        A GeoDataFrame containing the vector data.

    Raises:
        ValueError: If the file format is not supported or source cannot be accessed.

    Examples:
        Read a local shapefile
        >>> gdf = read_vector("path/to/data.shp")
        >>>
        Read a GeoParquet file from URL
        >>> gdf = read_vector("https://example.com/data.parquet")
        >>>
        Read a specific layer from a GeoPackage
        >>> gdf = read_vector("path/to/data.gpkg", layer="layer_name")
    """

    import urllib.parse

    import fiona
    import geopandas as gpd

    # Determine if source is a URL or local file
    parsed_url = urllib.parse.urlparse(source)
    is_url = parsed_url.scheme in ["http", "https"]

    # If it's a local file, check if it exists
    if not is_url and not os.path.exists(source):
        raise ValueError(f"File does not exist: {source}")
    elif is_url and source.endswith(".parquet"):
        source = download_file(source, quiet=True, overwrite=True)

    # Get file extension
    _, ext = os.path.splitext(source)
    ext = ext.lower()

    # Handle GeoParquet files
    if ext in [".parquet", ".pq", ".geoparquet"]:
        return read_parquet(source, **kwargs)

    # Handle common vector formats
    if ext in [".shp", ".geojson", ".json", ".gpkg", ".gml", ".kml", ".gpx"]:
        # For formats that might have multiple layers
        if ext in [".gpkg", ".gml"] and layer is not None:
            return gpd.read_file(source, layer=layer, **kwargs)