Issue #424 Add DataCube.apply_polygon

Author: soxofaan

CHANGELOG.md

@@ -14,6 +14,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   ([#310](https://github.com/Open-EO/openeo-python-client/issues/310))
 - Add `collection_property()` helper to easily build collection metadata property filters for `Connection.load_collection()`
   ([#331](https://github.com/Open-EO/openeo-python-client/pull/331))
+- Add `DataCube.apply_polygon()` (standardized version of experimental `chunk_polygon`) ([#424](https://github.com/Open-EO/openeo-python-client/issues/424))
 
 ### Changed
 

openeo/rest/datacube.py

@@ -1193,11 +1193,11 @@ def reduce_spatial(
             metadata=self.metadata.reduce_spatial(),
         )
 
-    # @openeo_process
+    @deprecated("Use :py:meth:`apply_polygon`.", version="0.26.0")
     def chunk_polygon(
         self,
         chunks: Union[shapely.geometry.base.BaseGeometry, dict, str, pathlib.Path, Parameter, VectorCube],
-        process: Union[str, PGNode, typing.Callable],
+        process: Union[str, PGNode, typing.Callable, UDF],
         mask_value: float = None,
         context: Optional[dict] = None,
     ) -> DataCube:
@@ -1237,6 +1237,45 @@ def chunk_polygon(
             ),
         )
 
+    @openeo_process
+    def apply_polygon(
+        self,
+        polygons: Union[shapely.geometry.base.BaseGeometry, dict, str, pathlib.Path, Parameter, VectorCube],
+        process: Union[str, PGNode, typing.Callable, UDF],
+        mask_value: Optional[float] = None,
+        context: Optional[dict] = None,
+    ) -> DataCube:
+        """
+        Apply a process to segments of the data cube that are defined by the given polygons.
+        For each polygon provided, all pixels for which the point at the pixel center intersects
+        with the polygon (as defined in the Simple Features standard by the OGC) are collected into sub data cubes.
+        If a pixel is part of multiple of the provided polygons (e.g., when the polygons overlap),
+        the GeometriesOverlap exception is thrown.
+        Each sub data cube is passed individually to the given process.
+
+        .. warning:: experimental process: not generally supported, API subject to change.
+
+        :param polygons: Polygons, provided as a shapely geometry, a GeoJSON-style dictionary,
+            a public GeoJSON URL, or a path (that is valid for the back-end) to a GeoJSON file.
+        :param process: "child callback" function, see :ref:`callbackfunctions`
+        :param mask_value: The value used for pixels outside the polygon.
+        :param context: Additional data to be passed to the process.
+        """
+        process = build_child_callback(process, parent_parameters=["data"], connection=self.connection)
+        valid_geojson_types = ["Polygon", "MultiPolygon", "Feature", "FeatureCollection"]
+        polygons = self._get_geometry_argument(polygons, valid_geojson_types=valid_geojson_types)
+        mask_value = float(mask_value) if mask_value is not None else None
+        return self.process(
+            process_id="apply_polygon",
+            data=THIS,
+            polygons=polygons,
+            process=process,
+            arguments=dict_no_none(
+                mask_value=mask_value,
+                context=context,
+            ),
+        )
+
     def reduce_bands(self, reducer: Union[str, PGNode, typing.Callable, UDF]) -> DataCube:
         """
         Shortcut for :py:meth:`reduce_dimension` along the band dimension

tests/rest/__init__.py

@@ -5,13 +5,15 @@
 from openeo.rest.datacube import DataCube
 
 
-def get_download_graph(cube: DataCube, drop_save_result: bool = False) -> dict:
+def get_download_graph(cube: DataCube, *, drop_save_result: bool = False, drop_load_collection: bool = False) -> dict:
     """
     Do fake download of a cube and intercept the process graph
     :param cube: cube to download
-    :param connection: connection object
+    :param drop_save_result: whether to drop the save_result node
+    :param drop_load_collection: whether to drop the load_collection node
     :return:
     """
+    # TODO: move this to a testing utility module
     with mock.patch.object(cube.connection, 'download') as download:
         cube.download("out.geotiff", format="GTIFF")
         download.assert_called_once()
@@ -21,6 +23,8 @@ def get_download_graph(cube: DataCube, drop_save_result: bool = False) -> dict:
         save_results_nodes = [k for k, v in actual_graph.items() if v["process_id"] == "save_result"]
         assert len(save_results_nodes) == 1
         del actual_graph[save_results_nodes[0]]
+    if drop_load_collection:
+        actual_graph = {k: v for (k, v) in actual_graph.items() if v["process_id"] != "load_collection"}
     return actual_graph
 
 

tests/rest/datacube/test_datacube.py

@@ -65,6 +65,7 @@ def test_min_time(s2cube, api_version):
 
 def _get_leaf_node(cube, force_flat=True) -> dict:
     """Get leaf node (node with result=True), supporting old and new style of graph building."""
+    # TODO: replace this with get_download_graph
     if isinstance(cube, DataCube):
         if force_flat:
             flat_graph = cube.flat_graph()