feat: For I14Y harvester adapt the identifier

ckanext/dcatapchharvest/harvesters_i14y.py

@@ -2,6 +2,7 @@
 
 import ckan.plugins as p
 import ckan.model as model
+from ckan.logic import NotFound, get_action
 
 from ckanext.dcat.harvesters.rdf import DCATRDFHarvester
 from ckanext.dcat.interfaces import IDCATRDFHarvester
@@ -73,19 +74,31 @@ def _get_guid(self, dataset_dict, source_url=None):  # noqa
         Try to get a unique identifier for a harvested dataset
         It will be the first found of:
          * URI (rdf:about)
-         * dcat:identifier
+         * dct:identifier
          * Source URL + Dataset name
          * Dataset name
          The last two are obviously not optimal, as depend on title, which
          might change.
          Returns None if no guid could be decided.
         '''
         guid = None
+        # get organization name
+        try:
+            dataset_organization = get_action('organization_show')(
+                {},
+                {'id': dataset_dict['owner_org']}
+            )
+            dataset_organization_name = dataset_organization['name']
+
+        except NotFound:
+            raise ValueError(
+                _('The selected organization was not found.')  # noqa
+            )
 
         if dataset_dict.get('identifier'):
             guid = dataset_dict['identifier']
-            # check if the owner_org matches the identifier
             try:
+                # check if the owner_org matches the identifier
                 if '@' in guid:
                     org_name = guid.split('@')[-1]  # get last element
                     org = model.Group.by_name(org_name)
@@ -107,6 +120,13 @@ def _get_guid(self, dataset_dict, source_url=None):  # noqa
                         log.error(error_msg)
                         self._save_gather_error(error_msg, self.harvest_job)
                         return None
+                else:
+                    # save original I14Y identifier and create a new identifier of the form <id>@<slug>,# noqa
+                    # where slug is an organization name
+                    dataset_dict['identifier_i14y'] = dataset_dict['identifier']  # noqa
+                    dataset_dict['identifier'] = \
+                        dataset_dict['identifier'] + '@' + dataset_organization_name  # noqa
+
             except Exception as e:
                 log.exception("Error when getting identifier: %s" % e)
                 return None