feat: added option to save geometry in the wkt format

README.md

@@ -403,6 +403,8 @@ When the `keep_all_tags` parameter is passed while filtering by OSM tags, and ad
 General schema of multiple segments that are concatenated together:
 `pbf_file_name`\_(`osm_filter_tags_hash_part`/`nofilter`)(\_`alltags`)\_(`clipping_geometry_hash_part`/`noclip`)\_(`compact`/`exploded`)(\_`filter_osm_ids_hash_part`).geoparquet
 
+> If the WKT mode is turned on, then the result file will be saved with a `parquet` extension and a `_wkt` suffix.
+
 ### Memory usage
 
 DuckDB queries requiring `JOIN`, `GROUP` and `ORDER BY` operations are very memory intensive. Because of that, some steps are divided into chunks (groups) with a set number of rows per chunk.

examples/command_line_interface.ipynb

@@ -452,6 +452,41 @@
     "    \"files/andorra_8a275d4edddd035eb6a5d8120a8b42a320b25cf93577335600faba8c2d69d85a_noclip_compact.geoparquet\"\n",
     ")"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## WKT mode\n",
+    "\n",
+    "By default, QuackOSM saves parsed files in the `GeoParquet` format with the geometry in the `WKB` format.\n",
+    "\n",
+    "There is also an option to save the file as a `Parquet` file with the geometry in the `WKT` format using `--wkt-result` (or `--wkt`) parameter."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "shellscript"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "! QuackOSM andorra.osm.pbf --wkt-result"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "duckdb.read_parquet(\n",
+    "    \"files/andorra_nofilter_noclip_compact_wkt.parquet\"\n",
+    ")"
+   ]
   }
  ],
  "metadata": {

quackosm/cli.py

@@ -500,6 +500,15 @@ def main(
             callback=_filter_osm_ids_callback,
         ),
     ] = None,
+    wkt_result: Annotated[
+        bool,
+        typer.Option(
+            "--wkt-result/",
+            "--wkt/",
+            help="Whether to save the geometry as a WKT string instead of WKB blob.",
+            show_default=False,
+        ),
+    ] = False,
     silent_mode: Annotated[
         bool,
         typer.Option(
@@ -583,6 +592,7 @@ def main(
                     else None
                 ),
                 filter_osm_ids=filter_osm_ids,  # type: ignore
+                save_as_wkt=wkt_result,
                 silent_mode=silent_mode,
             )
         else:
@@ -601,6 +611,7 @@ def main(
                     else None
                 ),
                 filter_osm_ids=filter_osm_ids,  # type: ignore
+                save_as_wkt=wkt_result,
                 silent_mode=silent_mode,
             )
     typer.secho(geoparquet_path, fg="green")

quackosm/functions.py

@@ -28,6 +28,7 @@ def convert_pbf_to_gpq(
     filter_osm_ids: Optional[list[str]] = None,
     working_directory: Union[str, Path] = "files",
     osm_way_polygon_features_config: Optional[Union[OsmWayPolygonConfig, dict[str, Any]]] = None,
+    save_as_wkt: bool = False,
     silent_mode: bool = False,
 ) -> Path:
     """
@@ -69,7 +70,10 @@ def convert_pbf_to_gpq(
             Config used to determine which closed way features are polygons.
             Modifications to this config left are left for experienced OSM users.
             Defaults to predefined "osm_way_polygon_features.json".
-        silent_mode (bool): Disable progress bars.
+        save_as_wkt (bool): Whether to save the file with geometry in the WKT form instead of WKB.
+            If `True`, it will be saved as a `.parquet` file, because it won't be in the GeoParquet
+            standard. Defaults to `False`.
+        silent_mode (bool): Disable progress bars. Defaults to `False`.
 
     Returns:
         Path: Path to the generated GeoParquet file.
@@ -229,6 +233,7 @@ def convert_pbf_to_gpq(
         explode_tags=explode_tags,
         ignore_cache=ignore_cache,
         filter_osm_ids=filter_osm_ids,
+        save_as_wkt=save_as_wkt,
     )
 
 
@@ -243,6 +248,7 @@ def convert_geometry_to_gpq(
     filter_osm_ids: Optional[list[str]] = None,
     working_directory: Union[str, Path] = "files",
     osm_way_polygon_features_config: Optional[Union[OsmWayPolygonConfig, dict[str, Any]]] = None,
+    save_as_wkt: bool = False,
     silent_mode: bool = False,
 ) -> Path:
     """
@@ -287,7 +293,10 @@ def convert_geometry_to_gpq(
             Config used to determine which closed way features are polygons.
             Modifications to this config left are left for experienced OSM users.
             Defaults to predefined "osm_way_polygon_features.json".
-        silent_mode (bool): Disable progress bars.
+        save_as_wkt (bool): Whether to save the file with geometry in the WKT form instead of WKB.
+            If `True`, it will be saved as a `.parquet` file, because it won't be in the GeoParquet
+            standard. Defaults to `False`.
+        silent_mode (bool): Disable progress bars. Defaults to `False`.
 
     Returns:
         Path: Path to the generated GeoParquet file.
@@ -399,6 +408,7 @@ def convert_geometry_to_gpq(
         explode_tags=explode_tags,
         ignore_cache=ignore_cache,
         filter_osm_ids=filter_osm_ids,
+        save_as_wkt=save_as_wkt,
     )
 
 
@@ -454,7 +464,7 @@ def get_features_gdf(
             Config used to determine which closed way features are polygons.
             Modifications to this config left are left for experienced OSM users.
             Defaults to predefined "osm_way_polygon_features.json".
-        silent_mode (bool): Disable progress bars.
+        silent_mode (bool): Disable progress bars. Defaults to `False`.
 
     Returns:
         gpd.GeoDataFrame: GeoDataFrame with OSM features.
@@ -634,7 +644,7 @@ def get_features_gdf_from_geometry(
             Config used to determine which closed way features are polygons.
             Modifications to this config left are left for experienced OSM users.
             Defaults to predefined "osm_way_polygon_features.json".
-        silent_mode (bool): Disable progress bars.
+        silent_mode (bool): Disable progress bars. Defaults to `False`.
 
     Returns:
         gpd.GeoDataFrame: GeoDataFrame with OSM features.