Add further configuration for ATLAS projects

AUTHORS.rst

@@ -12,3 +12,8 @@ Co-Developers
 * Eleanor Smith [email protected] `@ellesmith88 <https://github.com/ellesmith88>`_
 * Carsten Ehbrecht [email protected]
 * Pascal Bourgault [email protected]
+
+Contributors
+------------
+
+* Martin Schupfner <[email protected]> `@sol1105 <https://github.com/sol1105>`_

HISTORY.rst

@@ -6,6 +6,14 @@ Next
 
 * ...
 
+
+v0.6.7 (unreleased)
+-------------------
+
+Other Changes
+^^^^^^^^^^^^^
+* Updated `roocs.ini` default values for atlas datasets for further methods of how to infer the project name (#113).
+
 v0.6.6 (2024-01-26)
 -------------------
 

roocs_utils/etc/roocs.ini

@@ -160,6 +160,34 @@ mappings =
     project:project_id
 data_node_root = https://data.mips.copernicus-climate.eu/thredds/fileServer/esg_c3s-ipcc-atlas/
 
+[project:c3s-ipcc-ar6-atlas]
+base_dir = /pool/data/c3s-ipcc-ar6-atlas
+use_inventory = True
+use_catalog = True
+is_default_for_path = True
+file_name_template = {__derive__var_id}_{source}_{experiment_id}_{frequency}{__derive__time_range}{extra}.{__derive__extension}
+attr_defaults =
+    frequency:no-freq
+    experiment_id:no-expt
+facet_rule = variable project experiment time_frequency
+mappings =
+    project:project_id
+data_node_root = https://data.mips.copernicus-climate.eu/thredds/fileServer/esg_c3s-ipcc-atlas/
+
+[project:ipcc-ar6-interactive-atlas-dataset]
+base_dir = /pool/data/c3s-ipcc-ar6-atlas
+use_inventory = True
+use_catalog = True
+is_default_for_path = True
+file_name_template = {__derive__var_id}_{source}_{experiment_id}_{frequency}{__derive__time_range}{extra}.{__derive__extension}
+attr_defaults =
+    frequency:no-freq
+    experiment_id:no-expt
+facet_rule = variable project experiment time_frequency
+mappings =
+    project:product
+data_node_root = https://data.mips.copernicus-climate.eu/thredds/fileServer/esg_c3s-ipcc-atlas/
+
 [project:c3s-cica-atlas]
 base_dir = /pool/data/c3s-cica-atlas
 use_inventory = True
@@ -174,6 +202,19 @@ mappings =
     project:project_id
 data_node_root = https://data.mips.copernicus-climate.eu/thredds/fileServer/esg_c3s-cica-atlas/
 
+[project:copernicus -interactive-climate-atlas-dataset]
+base_dir = /pool/data/c3s-cica-atlas
+use_inventory = True
+use_catalog = True
+is_default_for_path = True
+file_name_template = {__derive__var_id}_{source}_{experiment_id}_{frequency}{__derive__time_range}{extra}.{__derive__extension}
+attr_defaults =
+    frequency:no-freq
+    experiment_id:no-expt
+facet_rule = variable project experiment time_frequency
+mappings =
+    project:product
+data_node_root = https://data.mips.copernicus-climate.eu/thredds/fileServer/esg_c3s-cica-atlas/
 
 [environment]
 OMP_NUM_THREADS=1

tests/test_project_utils.py

@@ -58,11 +58,32 @@ def test_get_project_name(load_test_data):
     project = get_project_name(dset)
     assert project == "c3s-cmip6-decadal"
 
+    # TODO: This needs to be cleaned up by introducing aliases and/or multiple mapping facets.
+    #       Each project should be defined only once in the roocs.ini.
+    #       Currently, without the possibility to define aliases, this is not possible
+    #       for the ATLAS projects, because the web prefix, the project name in the DRS and the
+    #       project name in the netCDF metadata differ from one another ...
+    #
     # c3s-cica-atlas
     dset = "c3s-cica-atlas.cd.CMIP6.historical.yr"
     project = get_project_name(dset)
     assert project == "c3s-cica-atlas"
 
+    # c3s-cica-atlas 2
+    dset = "/pool/data/c3s-cica-atlas/ERA5/psl_ERA5_mon_194001-202212.nc"
+    project = get_project_name(dset)
+    assert project == "c3s-cica-atlas"
+
+    # c3s-ipcc-ar6-atlas
+    dset = "c3s-ipcc-ar6-atlas.t.CORDEX-ANT.rcp45.mon"
+    project = get_project_name(dset)
+    assert project == "c3s-ipcc-ar6-atlas"
+
+    # c3s-ipcc-ar6-atlas
+    dset = "/pool/data/c3s-ipcc-ar6-atlas/CORDEX-ANT/rcp45/pr_CORDEX-ANT_rcp45_mon_200601-210012.nc"
+    project = get_project_name(dset)
+    assert project in ["c3s-ipcc-ar6-atlas", "c3s-ipcc-atlas"]
+
 
 def test_get_project_name_badc():
     dset = "/badc/cmip5/data/cmip5/output1/MOHC/HadGEM2-ES/rcp85/mon/atmos/Amon/r1i1p1/latest/tas/*.nc"
@@ -207,6 +228,12 @@ def test_derive_dset():
 
     assert ds_id == "/pool/data/c3s-cica-atlas/cd/CMIP6/historical/yr"
 
+    # c3s-ipcc-ar6-atlas
+    dset = "c3s-ipcc-ar6-atlas.cd.CMIP6.historical.yr"
+    ds_id = derive_dset(dset)
+
+    assert ds_id == "/pool/data/c3s-ipcc-ar6-atlas/cd/CMIP6/historical/yr"
+
 
 def test_switch_dset():
     dset = "/badc/cmip6/data/CMIP6/CMIP/MIROC/MIROC6/historical/r1i1p1f1/SImon/siconc/gn/latest/*.nc"