Change cf:parameters, osc:varibales and time axis

CHANGES.md

@@ -85,8 +85,11 @@
 - Removed redundant `via` access link from the OSC STAC collection; access is already expressed via typed assets (`zarr-data`, `zarr-consolidated-metadata`) on the STAC item.
 - `osc_project` is now omitted from `OscDatasetStacGenerator` when not provided, preserving the callee's default instead of passing `None`.
 
-## Changes in 0.2.0 (in Development)
+## Changes in 0.2.0 (in development)
 
+- Automatically derives OSC CF parameters from data variable metadata when `cf_params` is not provided.
+- Supports temporal coordinates whose names contain `time`.
+- The `osc:variables` extension field now contains the variable names used in the cube rather than the `standard_name` values from the data variable attributes.
 - Generated project collection now includes required STAC extensions (`osc`, `themes`, `contacts`) and OSC-mandatory fields (`osc:type`, `osc:status`, `themes`, `contacts`) to pass OSC catalog validation.
 - Added optional `osc_project_url` field to the dataset config; used as the `via` link in the project collection. Falls back to `documentation_link` if omitted; defaults to the existing DeepESDL project collection when neither is provided.
 - `dataset_status` now defaults to `"ongoing"` when not specified in the dataset config.

deep_code/tests/utils/test_dataset_stac_generator.py

@@ -198,6 +198,24 @@ def test_get_temporal_extent(self):
         self.assertEqual(interval[0], datetime(2023, 1, 1, 0, 0))
         self.assertEqual(interval[1], datetime(2023, 1, 2, 0, 0))
 
+    def test_get_temporal_extent_uses_all_time_coordinates(self):
+        """Temporal bounds include all coordinates whose names contain time."""
+        dataset = Dataset(
+            coords={
+                "time_start": ("time_start", [np.datetime64("2023-01-03")]),
+                "time_end": ("time_end", [np.datetime64("2023-01-05")]),
+            }
+        )
+        extent = self.generator._get_temporal_extent(dataset)
+        self.assertEqual(
+            extent.intervals[0], [datetime(2023, 1, 3), datetime(2023, 1, 5)]
+        )
+
+    def test_get_cf_params_from_data_variables(self):
+        """CF parameters are derived from variable names and attributes."""
+        params = self.generator._get_cf_params(self.mock_dataset)
+        self.assertEqual([param["name"] for param in params], ["var1", "var2"])
+
     def test_get_variables(self):
         """Test variable ID extraction."""
         vars_ = self.generator.get_variable_ids(self.mock_dataset)
@@ -1042,7 +1060,11 @@ def setUp(self):
                 "sst": (
                     ("time", "lat", "lon"),
                     np.random.rand(2, 3, 3),
-                    {"units": "K", "long_name": "Sea surface temperature"},
+                    {
+                        "units": "K",
+                        "standard_name": "sea_surface_temperature",
+                        "long_name": "Sea surface temperature",
+                    },
                 ),
                 "chl": (
                     ("time", "lat", "lon"),
@@ -1193,7 +1215,10 @@ def test_build_prr_collection(self):
         self.assertEqual(ef["osc:region"], "Global")
         self.assertCountEqual(ef["osc:variables"], ["sst", "chl"])
         self.assertEqual(ef["osc:missions"], ["sentinel-3"])
-        self.assertEqual(ef["cf:parameter"], [{"name": "prr-collection"}])
+        self.assertEqual(
+            ef["cf:parameter"],
+            [{"name": "sea_surface_temperature"}],
+        )
         self.assertIn("processing:datetime", ef)
 
         # Extensions declared.

deep_code/tools/new.py

@@ -94,9 +94,7 @@ def generate_dataset_template(output_path: str | None = None) -> str:
             ],
             "collection_title": "[OPTIONAL: title present in the collection and in the STAC browser]",
             "coord_position": "[OPTIONAL: Position of the coordinates within each grid cell. 'center' assumes coordinates represent cell centers, 'left' assumes they represent the left/bottom edge, and 'right' assumes they represent the right/top edge.]",
-            "cf_parameter": [
-                {"name": "[OPTIONAL: CF standard name]", "units": "[unit string]"}
-            ],
+            "cf_parameter": [{"name": "[OPTIONAL: CF standard name]"}],
         }
 
         # Fields used only by `deep-code generate-prr-collection` to build a

deep_code/utils/dataset_stac_generator.py

@@ -250,17 +250,31 @@ def _get_spatial_extent(
     @staticmethod
     def _get_temporal_extent(dataset: xr.Dataset) -> TemporalExtent:
         """Extract temporal extent from the dataset."""
-        dataset = dataset
-        if "time" in dataset.coords:
+        time_coords = [name for name in dataset.coords if "time" in name]
+        if time_coords:
             try:
-                # Convert the time bounds to datetime objects
-                time_min = pd.to_datetime(dataset.time.min().values).to_pydatetime()
-                time_max = pd.to_datetime(dataset.time.max().values).to_pydatetime()
+                time_min = min(
+                    pd.to_datetime(dataset[name].min().values) for name in time_coords
+                ).to_pydatetime()
+                time_max = max(
+                    pd.to_datetime(dataset[name].max().values) for name in time_coords
+                ).to_pydatetime()
                 return TemporalExtent([[time_min, time_max]])
             except Exception as e:
                 raise ValueError(f"Failed to parse temporal extent: {e}")
         else:
-            raise ValueError("Dataset does not have a 'time' coordinate.")
+            raise ValueError("Dataset does not have a '*time*' coordinate.")
+
+    @staticmethod
+    def _get_cf_params(dataset: xr.Dataset) -> list:
+        params = []
+
+        for var_name, data_var in dataset.data_vars.items():
+            attrs = data_var.attrs
+            if "standard_name" in attrs:
+                params.append({"name": attrs["standard_name"]})
+
+        return params
 
     @staticmethod
     def _normalize_name(name: str | None) -> str | None:
@@ -357,13 +371,12 @@ def extract_metadata_for_variable(self, variable_data) -> dict:
         """Extract metadata for a single variable."""
         long_name = variable_data.attrs.get("long_name")
         standard_name = variable_data.attrs.get("standard_name", "unknown")
-        variable_id = (
-            variable_data.name if standard_name == "unknown" else standard_name
-        )
+        variable_id = variable_data.name
         description = variable_data.attrs.get("description", long_name)
         gcmd_keyword_url = variable_data.attrs.get("gcmd_keyword_url")
         return {
-            "variable_id": self._normalize_name(variable_id),
+            "variable_id": variable_id,
+            "standard_name": standard_name,
             "description": description,
             "gcmd_keyword_url": gcmd_keyword_url,
         }
@@ -386,7 +399,7 @@ def get_variable_ids(
         #  Remove 'crs' and 'spatial_ref' from the list if they exist, note that
         #  spatial_ref will be normalized to spatial-ref in variable_ids and skipped.
         return [
-            var_id for var_id in variable_ids if var_id not in ["crs", "spatial-ref"]
+            var_id for var_id in variable_ids if var_id not in ["crs", "spatial_ref"]
         ]
 
     def get_variables_metadata(self, dataset: xr.Dataset) -> dict[str, dict]:
@@ -1186,7 +1199,10 @@ def build_prr_collection(self) -> Collection:
         osc_extension.osc_region = self.osc_region
         osc_extension.osc_variables = variables
         osc_extension.osc_missions = self.osc_missions
-        osc_extension.cf_parameter = self.cf_params or [{"name": self.collection_id}]
+        if self.cf_params:
+            osc_extension.cf_parameter = self.cf_params
+        else:
+            osc_extension.cf_parameter = self._get_cf_params(dataset_ref)
 
         now_iso = datetime.now(timezone.utc).isoformat()
         collection.extra_fields["created"] = now_iso
@@ -1399,7 +1415,7 @@ def build_dataset_stac_collection(
         if self.cf_params:
             osc_extension.cf_parameter = self.cf_params
         else:
-            osc_extension.cf_parameter = [{"name": self.collection_id}]
+            osc_extension.cf_parameter = self._get_cf_params(dataset)
 
         # Add creation and update timestamps for the collection
         now_iso = datetime.now(timezone.utc).isoformat()

docs/cli.md

@@ -85,7 +85,9 @@ The output conforms to the
 [PRR collection specification](https://eoresults.esa.int/prr_collection_specifications.html)
 when the PRR fields are set in the config. If any required field is missing, the command
 still runs but logs a warning listing what is needed for full conformance. See
-[PRR collection fields](configuration.md#prr-collection-fields).
+[PRR collection fields](configuration.md#prr-collection-fields). Before sending the collection JSON to the PRR team, 
+you can validate the generated collection using the [PRR STAC Collection Editor](https://eoresults.esa.int/prr_collection_editor.html).
+
 
 Options: