some updates to website YAML names, add nci file path

.github/scripts/crosswalk_mappings.py

@@ -146,11 +146,15 @@
     #but for the website they should point to the NCI collection
     'model_setup_info.url':'foo',
     'model_setup_info.summary':'model_setup_description',
-    'model_files.url':'foo',
-    'model_files.notes':'foo',
+    'model_files.url':'model_code_inputs.url',
+    'model_files.notes':'model_code_inputs.notes',
     'model_files.file_tree':'foo',
-    "dataset.url":"model_data.url",
-    "dataset.notes":"model_data.notes",
-    "dataset.doi":"model_data.doi",
-    "dataset.notes":"model_data.notes"
+    'model_files.existing_identifier':'model_code_inputs.doi',
+    'model_files.nci_file_path':'foo',
+    'model_files.include':'include_model_code',
+    "dataset.url":"model_output_data.url",
+    "dataset.notes":"model_output_data.notes",
+    'dataset.existing_identifier':'model_output_data.doi',
+    'dataset.nci_file_path':'foo',
+    'dataset.include':'include_model_output'
 }

.github/scripts/parse_issue.py

@@ -259,6 +259,7 @@ def parse_issue(issue):
 
     # slug
     proposed_slug = data["-> slug"].strip()
+    data_dict["proposed_slug"] = proposed_slug
 
     slug, log = validate_slug(proposed_slug)
     data_dict["slug"] = slug
@@ -451,8 +452,12 @@ def parse_issue(issue):
 
     # include model output data
     model_output = data["-> include model output data?"].strip()
+    #having this outside the record
+    #anticipates that we might choose not to build the record if False
     data_dict["include_model_output"] = parse_yes_no_choice(model_output)
 
+
+
     # model output data
     model_output_record = {}
 

.github/scripts/yaml_utils.py

@@ -158,41 +158,44 @@ def ensure_path_starts_with_pattern(file_path, pattern='./graphics/'):
     return file_path
 
 def configure_yaml_output_dict(output_dict, issue_dict,
-                               image_path='./graphics/', old_yaml=True, timestamp=False):
+                               image_path='./graphics/',
+                               nci_file_path_base='/g/data/nm08/MATE/',
+                               timestamp=False):
+
+                               #nci_file_path_base
 
     #make some changes (in-place) to output_dict, to help wrangle the yaml output dict
-    #many of these simply enforce formatting that is required by the Gatsby YAML frontmatter
 
     #add in the template key for this page
     output_dict['templateKey'] = 'model'
 
+    #include_model_code
+    if issue_dict['slug']:
+        path_slug = issue_dict['slug']
+    elif issue_dict['proposed_slug']:
+            path_slug = issue_dict['proposed_slug']
+    else:
+        path_slug = 'PENDING'
+
+    ## add the NCI_file_path
+    if issue_dict["include_model_output"]:
+        data_file_path = nci_file_path_base + path_slug + '/model_output_data'
+        output_dict['dataset']['nci_file_path'] = data_file_path
+
+    if issue_dict["include_model_code"]:
+        code_file_path = nci_file_path_base + path_slug + '/model_code_inputs'
+        output_dict['model_files']['nci_file_path'] = code_file_path
+
+
     #change format of ORCiD ids if required
     for creator in output_dict['creators']:
         creator['ORCID'] = extract_orcid_id(creator['ORCID'])
 
-    #change format of ORCiD ids if required
-    #for contributor in output_dict['contributors']:
-    #    contributor['ORCID'] = extract_orcid_id(contributor['ORCID'])
-
-
 
-    ########################
-    #Now we're going to to a hotfix to sync the names with the website terminology
-    ########################
-    #if old_yaml is True:
-    #    output_dict['authors'] = copy.deepcopy(output_dict['creators']) + copy.deepcopy(output_dict['contributors'])
-    #    output_dict['contributor'] = copy.deepcopy(output_dict['submitter'])
-    #    del output_dict['contributors']
-    #    del output_dict['creators']
-    ########################
-    #... remove this when we've update website code
-    ########################
 
     # Format the datetime as specified, with milliseconds set to .000
     if timestamp:
         output_dict['date'] = timestamp
-    #
-    #
 
     #enforce list and sytax for FOR codes
     updated_codes = extract_integers(output_dict['for_codes'])