✅ Review Round 11 COMPLETE: Official CMIP7 File Naming

Implemented per DOI: 10.5281/zenodo.17250297

FILENAME FORMAT (CORRECT):
tos_tavg-u-hxy-sea_mon_glb_gn_AWI-ESM3-VEG-LR_piControl_r1i1p1f1_135001-135012.nc

Components:
- variable_id: tos
- branding_suffix: tavg-u-hxy-sea (time-avg, undefined-vert, horiz-xy, sea)
- frequency: mon (NOT table_id!)
- region: glb (global)
- grid_label: gn/gr
- source_id: AWI-ESM3-VEG-LR
- experiment_id: piControl
- variant_label: r1i1p1f1
- timeRange: 135001-135012

DIRECTORY STRUCTURE (CORRECT):
MIP-DRS7/CMIP7/CMIP/AWI/AWI-ESM3-VEG-LR/piControl/r1i1p1f1/glb/mon/tos/tavg-u-hxy-sea/gn/v20260313/

Changes:
1. Config: Added CMIP7 params (activity_id, institution_id, region, branding_suffix)
2. files.py: Rewrote CMIP7 create_filepath() with correct component order
3. global_attributes.py: Rewrote CMIP7 subdir_path() with MIP-DRS7 structure
4. Enabled output_subdirs for proper directory nesting

Note: gn and gr must be processed separately (pycmor limitation)

Author: JanStreffing

cmorize_sst.yaml

@@ -15,6 +15,7 @@ pycmor:
   enable_dask: False
   xarray_open_mfdataset_parallel: False
   pipeline_workflow_orchestrator: "native"
+  enable_output_subdirs: True
 
 pipelines:
   - name: default
@@ -52,6 +53,11 @@ rules:
     model_component: ocean
     grid_label: gn
     grid_file: /work/ab0246/a270092/input/fesom2/dars2/mesh.nc
+    # CMIP7 required parameters
+    activity_id: CMIP
+    institution_id: AWI
+    region: glb
+    branding_suffix: "tavg-u-hxy-sea"
     pipelines:
       - default
     inputs:
@@ -72,6 +78,11 @@ rules:
     mesh_path: /work/ab0246/a270092/input/fesom2/dars2
     box: "-180, 180, -90, 90"
     target_resolution: "0.25"
+    # CMIP7 required parameters
+    activity_id: CMIP
+    institution_id: AWI
+    region: glb
+    branding_suffix: "tavg-u-hxy-sea"
     pipelines:
       - regridded
     inputs:

src/pycmor/std_lib/files.py

@@ -217,16 +217,37 @@ def create_filepath(ds, rule):
     frequency_str = rule.data_request_variable.frequency
 
     if mip_era == "CMIP7":
-        # CMIP7: No institution prefix, simpler format
-        if frequency_str == "fx" or not time_range:
+        # CMIP7 format per official specification (DOI: 10.5281/zenodo.17250297):
+        # <variable_id>_<branding_suffix>_<frequency>_<region>_<grid_label>_
+        # <source_id>_<experiment_id>_<variant_label>[_<timeRange>].nc
+        
+        # Get branding suffix from rule or data request
+        branding_suffix = getattr(rule, 'branding_suffix', None)
+        if not branding_suffix:
+            branding_suffix = getattr(
+                rule.data_request_variable, 'branding_suffix', 'unknown-u-hxy-u'
+            )
+        branding_suffix = _sanitize_component(branding_suffix)
+        
+        # Get region from rule (default to global)
+        region = getattr(rule, 'region', 'glb')
+        region = _sanitize_component(region)
+        
+        # Use frequency, not table_id
+        frequency = _sanitize_component(frequency_str)
+        
+        # Build CMIP7 filename
+        if frequency == "fx" or not time_range:
+            # Fixed (time-independent) variable - no timeRange
             filepath = (
-                f"{out_dir}/{name}_{table_id}_{source_id}_"
-                f"{experiment_id}_{label}_{grid}{clim_suffix}.nc"
+                f"{out_dir}/{name}_{branding_suffix}_{frequency}_{region}_{grid}_"
+                f"{source_id}_{experiment_id}_{label}{clim_suffix}.nc"
             )
         else:
+            # Time-dependent variable - include timeRange
             filepath = (
-                f"{out_dir}/{name}_{table_id}_{source_id}_"
-                f"{experiment_id}_{label}_{grid}_{time_range}{clim_suffix}.nc"
+                f"{out_dir}/{name}_{branding_suffix}_{frequency}_{region}_{grid}_"
+                f"{source_id}_{experiment_id}_{label}_{time_range}{clim_suffix}.nc"
             )
     else:
         # CMIP6: Include institution prefix

src/pycmor/std_lib/global_attributes.py

@@ -46,16 +46,42 @@ def global_attributes(self):
         }
 
     def subdir_path(self):
-        """Return subdirectory path for CMIP7 output"""
+        """Return subdirectory path for CMIP7 output per official specification
+        
+        Template (DOI: 10.5281/zenodo.17250297):
+        <drs_specs>/<mip_era>/<activity_id>/<institution_id>/<source_id>/
+        <experiment_id>/<variant_label>/<region>/<frequency>/<variable_id>/
+        <branding_suffix>/<grid_label>/<directoryDate>
+        """
+        drs_specs = "MIP-DRS7"
         mip_era = "CMIP7"
+        activity_id = self.rule_dict.get("activity_id", "CMIP")
+        institution_id = self.rule_dict.get("institution_id", "AWI")
         source_id = self.rule_dict.get("source_id", "")
         experiment_id = self.rule_dict.get("experiment_id", "")
         variant_label = self.rule_dict.get("variant_label", "")
-        table_id = self.drv.table_header.table_id if hasattr(self.drv, 'table_header') else "Omon"
+        region = self.rule_dict.get("region", "glb")
+        
+        # Get frequency from data request (NOT table_id!)
+        frequency = self.drv.frequency if hasattr(self.drv, 'frequency') else "mon"
+        
         variable_id = self.rule_dict.get("cmor_variable", "")
+        
+        # Get branding suffix from rule or data request
+        branding_suffix = self.rule_dict.get('branding_suffix')
+        if branding_suffix is None:
+            branding_suffix = getattr(self.drv, 'branding_suffix', 'unknown-u-hxy-u')
+        
         grid_label = self.rule_dict.get("grid_label", "")
         version = f"v{datetime.datetime.today().strftime('%Y%m%d')}"
-        directory_path = f"{mip_era}/{source_id}/{experiment_id}/{variant_label}/{table_id}/{variable_id}/{grid_label}/{version}"
+        
+        directory_path = (
+            f"{drs_specs}/{mip_era}/{activity_id}/{institution_id}/"
+            f"{source_id}/{experiment_id}/{variant_label}/"
+            f"{region}/{frequency}/{variable_id}/{branding_suffix}/"
+            f"{grid_label}/{version}"
+        )
+        
         return directory_path
 
     def get_tracking_id(self):