Merge pull request #55 from aradhakrishnanGFDL/template

updating template. time_range, modeling_realm, standard_name

configs/config-template.yaml

@@ -1,29 +1,41 @@
-#The headerlist contains expected column names in your catalog/csv file. This is usually determined by the users in conjuction
-#with the ESM collection specification standards and the appropriate workflows.
+#what kind of directory structure to expect? 
+#For a directory structure like /archive/am5/am5/am5f3b1r0/c96L65_am5f3b1r0_pdclim1850F/gfdl.ncrc5-deploy-prod-openmp/pp
+# the output_path_template is set as follows.
+#We have NA in those values that do not match up with any of the expected headerlist (CSV columns), otherwise we
+#simply specify the associated header name in the appropriate place. E.g. The third directory in the PP path example
+#above is the model (source_id), so the third list value in output_path_template is set to 'source_id'. We make sure
+#this is a valid value in headerlist as well.
+#The fourth directory is am5f3b1r0 which does not map to an existing header value. So we simply NA in output_path_template
+#for the fourth value.
 
-headerlist: ["activity_id", "institution_id", "source_id", "experiment_id", "frequency", "realm", "table_id","member_id",
-            "grid_label", "variable_id", "time_range", "chunk_freq","grid_label","platform","dimensions","cell_methods","path"]
+#catalog headers
+#The headerlist is expected column names in your catalog/csv file. This is usually determined by the users in conjuction
+#with the ESM collection specification standards and the appropriate workflows.
 
+headerlist: ["activity_id", "institution_id", "source_id", "experiment_id",
+                  "frequency", "realm", "table_id",
+                  "member_id", "grid_label", "variable_id",
+                  "time_range", "chunk_freq","platform","dimensions","cell_methods","standard_name","path"]
 
 #what kind of directory structure to expect?
+#For a directory structure like /archive/am5/am5/am5f3b1r0/c96L65_am5f3b1r0_pdclim1850F/gfdl.ncrc5-deploy-prod-openmp/pp
+# the output_path_template is set as follows.
 #We have NA in those values that do not match up with any of the expected headerlist (CSV columns), otherwise we
 #simply specify the associated header name in the appropriate place. E.g. The third directory in the PP path example
 #above is the model (source_id), so the third list value in output_path_template is set to 'source_id'. We make sure
 #this is a valid value in headerlist as well.
 #The fourth directory is am5f3b1r0 which does not map to an existing header value. So we simply NA in output_path_template
 #for the fourth value.
 
-
-output_path_template: ['NA','NA','source_id','NA','experiment_id','platform','custom_pp','modeling_realm','cell_methods','frequency','chunk_freq']
+output_path_template: ['NA','NA','source_id','NA','experiment_id','platform','custom_pp','realm','cell_methods','frequency','chunk_freq']
 
 output_file_template: ['realm','time_range','variable_id']
 
+#OUTPUT FILE INFO is currently passed as command-line argument.
+#We will revisit adding a csvfile, jsonfile and logfile configuration to the builder configuration file in the future.
+#csvfile =  #jsonfile =  #logfile =
 
-#ENTER INPUT PATH HERE (ex: /Users/ar46/archive/am5/am5/am5f3b1r0/c96L65_am5f3b1r0_pdclim1850F/gfdl.ncrc5-deploy-prod-openmp/pp/)
-
-input_path: ""
-
-#ENTER NAME OF THE CSV AND JSON, WITHOUT THE SUFFIX. (ex: catalog) The builder then generates catalog.csv and catalog.json. This can also be an absolute path)
-
-output_path: ""
+#######################################################
 
+input_path: "/archive/am5/am5/am5f7b12r0/c96L65_am5f7b12r0_amip/gfdl.ncrc5-deploy-prod-openmp/pp/"
+output_path: "/home/a1r/github/noaa-gfdl/catalogs/c96L65_am5f7b10r0_amip30_0821" # ENTER NAME OF THE CSV AND JSON, THE SUFFIX ALONE. e.g catalog (the builder then generates catalog.csv and catalog.json. This can also be an absolute path)