Merge pull request #51 from crim-ca/datacube-fixes

Fixes to datacube extension helper

STACpopulator/api_requests.py

@@ -93,14 +93,16 @@ def post_stac_item(
     item_url = os.path.join(stac_host, f"collections/{collection_id}/items")
     r = session.post(item_url, json=json_data)
 
+    extra_log_info = {"item_id": item_id, "item_url": os.path.join(item_url, item_id)}
+
     if r.status_code == 200:
-        LOGGER.info(f"Item {item_name} successfully added")
+        LOGGER.info(f"Item {item_name} successfully added", extra=extra_log_info)
     elif r.status_code == 409:
         if update:
-            LOGGER.info(f"Item {item_id} already exists. Updating.")
+            LOGGER.info(f"Item {item_id} already exists. Updating.", extra=extra_log_info)
             r = session.put(os.path.join(stac_host, f"collections/{collection_id}/items/{item_id}"), json=json_data)
             r.raise_for_status()
         else:
-            LOGGER.warn(f"Item {item_id} already exists.")
+            LOGGER.warn(f"Item {item_id} already exists.", extra=extra_log_info)
     else:
         r.raise_for_status()

STACpopulator/extensions/datacube.py

@@ -169,10 +169,8 @@ def dimensions(self) -> dict[str, Dimension]:
                             properties = dict(
                                 type=type_.value,
                                 extent=extent,
-                                description=v.get(
-                                    "description",
-                                    v.get("long_name", criteria["standard_name"][0])
-                                ) or "",
+                                description=v.get("description", v.get("long_name", criteria["standard_name"][0]))
+                                or "",
                             )
                             if type_ == DimensionType.SPATIAL:
                                 properties["axis"] = axis
@@ -191,7 +189,11 @@ def variables(self) -> dict[str, Variable]:
             if name in self.attrs["dimensions"]:
                 continue
 
-            attrs = meta["attributes"]
+            # Some variables like "time_bnds" in some model files do not have any attributes.
+            attrs = meta.get("attributes", {})
+
+            self._infer_variable_units_description(name, attrs)
+
             variables[name] = Variable(
                 properties=dict(
                     dimensions=meta["shape"],
@@ -202,8 +204,32 @@ def variables(self) -> dict[str, Variable]:
             )
         return variables
 
+    def _infer_variable_units_description(self, name, attrs):
+        """Try to infer the units and description of some simple coordinate variables."""
+        if name == "time_bnds":
+            related_variable = "time"
+            attrs["description"] = "bounds for the time coordinate"
+        elif name == "lat_bnds":
+            related_variable = "lat"
+            attrs["description"] = "bounds for the latitude coordinate"
+        elif name == "lon_bnds":
+            related_variable = "lon"
+            attrs["description"] = "bounds for the longitude coordinate"
+        else:
+            return
+
+        try:
+            attrs["units"] = self.attrs["variables"][related_variable]["attributes"]["units"]
+        except KeyError:
+            pass
+
     def is_coordinate(self, attrs: MutableMapping[str, Any]) -> bool:
         """Return whether variable is a coordinate."""
+
+        if (desc := attrs.get("description", None)) is not None:
+            if "bounds for" in desc:
+                return True
+
         for key, criteria in self.coordinate_criteria.items():
             for criterion, expected in criteria.items():
                 if attrs.get(criterion, None) in expected: