feat: Modify guid from the identifier that is in shape of <id>

ckanext/dcatapchharvest/harvesters.py

@@ -190,33 +190,19 @@ def _derive_flat_title(title_dict):
 
 
 class SwissDCATI14YRDFHarvester(SwissDCATRDFHarvester):
-    p.implements(IDCATRDFHarvester, inherit=True)
 
     def info(self):
-        # call the parent class SwissDCATRDFHarvester
-        # to get the default info dictionary
-        info = super(SwissDCATRDFHarvester, self).info()
-        # source_config = super(SwissDCATRDFHarvester, self).validate_config(source_config)  # noqa
+        info = super(SwissDCATI14YRDFHarvester, self).info()
 
         info['name'] = 'dcat_ch_i14y_rdf'
         info['title'] = 'DCAT-AP Switzerland I14Y RDF Harvester'
         info['description'] = 'Harvester for DCAT-AP Switzerland datasets from an RDF graph desighned for I14Y'  # noqa
 
         return info
 
-    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)
-         * 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
+    def _get_guid(self, dataset_dict, source_url=None):
+        guid = super(SwissDCATI14YRDFHarvester, self)._get_guid(dataset_dict, source_url)
+
         # get organization name
         try:
             dataset_organization = get_action('organization_show')(
@@ -227,63 +213,19 @@ def _get_guid(self, dataset_dict, source_url=None):  # noqa
 
         except NotFound:
             raise ValueError(
-                _('The selected organization was not found.')  # noqa
+                _('The selected organization was not found.')
             )
 
-        if dataset_dict.get('identifier'):
-            guid = dataset_dict['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)
-                    if not org:
-                        error_msg = (
-                            'The organization in the dataset identifier (%s) '
-                            'does not not exist. ' % org_name
-                        )
-                        log.error(error_msg)
-                        self._save_gather_error(error_msg, self.harvest_job)
-                        return None
-
-                    if org.id != dataset_dict['owner_org']:
-                        error_msg = (
-                            'The organization in the dataset identifier (%s) '
-                            'does not match the organization in the harvester '
-                            'config (%s)' % (org.id, dataset_dict['owner_org'])
-                        )
-                        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
-            return dataset_dict['identifier']
-
-        for extra in dataset_dict.get('extras', []):
-            if extra['key'] == 'uri' and extra['value']:
-                return extra['value']
-
-        if dataset_dict.get('uri'):
-            return dataset_dict['uri']
-
-        for extra in dataset_dict.get('extras', []):
-            if extra['key'] == 'identifier' and extra['value']:
-                return extra['value']
-
-        for extra in dataset_dict.get('extras', []):
-            if extra['key'] == 'dcat_identifier' and extra['value']:
-                return extra['value']
-
-        if dataset_dict.get('name'):
-            guid = dataset_dict['name']
-            if source_url:
-                guid = source_url.rstrip('/') + '/' + guid
-
-        return guid
+        # identifier that has form of <id>,
+        # should be changed to the form <id>@<slug>,
+        # where slug is an organization name
+        if (dataset_dict.get('identifier')
+                and dataset_dict['identifier'] == guid
+                and '@' not in guid):
+            dataset_dict['identifier_i14y'] =\
+                dataset_dict['identifier']
+            dataset_dict['identifier'] =\
+                dataset_dict['identifier'] + '@'\
+                + dataset_organization_name
+
+        return dataset_dict['identifier']