Update mock up for validation data/optional data api

Author: msschwartz21

src/geff/geff_reader.py

@@ -190,6 +190,8 @@ def read_to_dict(
     validate: bool = True,
     node_props: list[str] | None = None,
     edge_props: list[str] | None = None,
+    validate_data: bool = False,
+    validate_optional_data: utils.ValidationConfig | None = None,
 ) -> GraphDict:
     """
     Read a GEFF zarr file to a dictionary representation.
@@ -200,9 +202,13 @@ def read_to_dict(
     Args:
         source (str | Path | zarr store): Either a path to the root of the geff zarr
             (where the .attrs contains the geff metadata), or a zarr store object
-        validate (bool, optional): Flag indicating whether to perform validation on the
-            geff file before loading into memory. If set to False and there are
-            format issues, will likely fail with a cryptic error. Defaults to True.
+        validate (bool, optional): Flag indicating whether to perform metadata/structure
+            validation on the geff file before loading into memory. If set to False and
+            there are format issues, will likely fail with a cryptic error. Defaults to True.
+        validate_data (bool, optional): Flag indicating whether to perform validation on the
+            underlying data of the geff, e.g. edges. Defaults to False.
+        validate_optional_data (ValidationConfig, optional): Optional configuration for which
+            optional properties to validate. Defaults to None and validation does not occur.
         node_props (list of str, optional): The names of the node properties to load,
             if None all properties will be loaded, defaults to None.
         edge_props (list of str, optional): The names of the edge properties to load,
@@ -218,4 +224,11 @@ def read_to_dict(
     file_reader.read_edge_props(edge_props)
 
     graph_dict = file_reader.build()
+
+    if validate_data:
+        utils.validate_zarr_data(graph_dict)
+
+    if validate_optional_data is not None:
+        utils.validate_optional_data(config=validate_optional_data, graph_dict=graph_dict)
+
     return graph_dict

src/geff/utils.py

@@ -6,6 +6,7 @@
 
 import numpy as np
 import zarr
+from pydantic import BaseModel
 
 if TYPE_CHECKING:
     from zarr.storage import StoreLike
@@ -102,9 +103,35 @@ def validate_zarr_data(graph_dict: GraphDict):
         graph_dict (GraphDict): A graphdict object which contains metadata and
             dictionaries of node/edge property arrays
     """
-    graph_dict["metadata"]
+    # TODO add edge validation
+    pass
 
-    # TODO: Test various properties based on what is present in the metadata
+
+class ValidationConfig(BaseModel):
+    sphere: bool = False
+    ellipsoid: bool = False
+    lineage: bool = False
+    tracklet: bool = False
+
+
+def validate_optional_data(config: ValidationConfig, graph_dict: GraphDict):
+    """Run data validation on optional data types based on the input
+
+    Args:
+        config (ValidationConfig): Configuration for which validation to run
+        graph_dict (GraphDict): A graphdict object which contains metadata and
+            dictionaries of node/edge property arrays
+    """
+    meta = graph_dict["metadata"]
+    if config.sphere and meta.sphere is not None:
+        pass
+    if config.ellipsoid and meta.ellipsoid is not None:
+        pass
+    if meta.track_node_props is not None:
+        if config.lineage and "lineage" in meta.track_node_props:
+            pass
+        if config.lineage and "tracklet" in meta.track_node_props:
+            pass
 
 
 def validate_graph_group(group: zarr.Group, type: Literal["node", "edge"]):