fs counter handler easier to maintain

oc_meta/run/find_duplicated_entities.py

@@ -53,16 +53,31 @@ def main():
     parser = argparse.ArgumentParser(description='Run a SPARQL query and save results to CSV.')
     parser.add_argument('endpoint', type=str, help='SPARQL endpoint URL')
     parser.add_argument('csv_path', type=str, help='Path to the CSV file to save results')
+    parser.add_argument('entity_type', type=str, choices=['id', 'br', 'ra'], help='Type of entity: "id" or "br"')
     args = parser.parse_args()
 
-    sparql_query = """
-        PREFIX datacite: <http://purl.org/spar/datacite/>
-        PREFIX literal: <http://www.essepuntato.it/2010/06/literalreification/>
-        SELECT ?entity1 ?entity2 {
-            ?id ^datacite:hasIdentifier ?entity1, ?entity2.
-            FILTER(?entity1 != ?entity2 )
-        }    
-    """
+    if args.entity_type == 'id':
+        sparql_query = """
+            PREFIX datacite: <http://purl.org/spar/datacite/>
+            PREFIX literal: <http://www.essepuntato.it/2010/06/literalreification/>
+            SELECT ?entity1 ?entity2 {
+                ?id ^datacite:hasIdentifier ?entity1, ?entity2.
+                FILTER(?entity1 != ?entity2 )
+            }    
+        """
+    elif args.entity_type == 'ra':
+        sparql_query = """
+            PREFIX datacite: <http://purl.org/spar/datacite/>
+            PREFIX literal: <http://www.essepuntato.it/2010/06/literalreification/>
+            PREFIX foaf: <http://xmlns.com/foaf/0.1/>
+            SELECT ?entity1 ?entity2 {
+                ?entity1 datacite:hasIdentifier ?id;
+                        a foaf:Agent.
+                ?entity2 datacite:hasIdentifier ?id;
+                        a foaf:Agent.
+                FILTER(?entity1 != ?entity2 )
+            }    
+        """
 
     results = execute_sparql_query(args.endpoint, sparql_query)
     final_entities = find_surviving_entities(results)

oc_meta/run/upload/on_triplestore.py

@@ -82,6 +82,9 @@ def split_queries(file_path, batch_size):
     return generate_sparql_queries(quads_to_add, quads_to_remove, batch_size)
 
 def upload_sparql_updates(endpoint, folder, batch_size):
+    if not os.path.exists(folder):
+        return
+
     processed_files = load_cache()
     failed_files = []
 

pyproject.toml

@@ -28,7 +28,7 @@ oc-ds-converter = "1.0.3"
 ijson = "^3.2.3"
 internetarchive = "^3.7.0"
 zenodopy = "^0.3.0"
-oc-ocdm = "8.2.1"
+oc-ocdm = "8.2.2"
 retrying = "^1.3.4"
 
 [tool.poetry.dev-dependencies]

test/editor_test.py

@@ -159,10 +159,10 @@ def read_and_normalize_file(filepath):
         graph_storer.upload_all(endpoint)
         editor = MetaEditor(META_CONFIG, 'https://orcid.org/0000-0002-8420-0696')
         editor.merge(URIRef('https://w3id.org/oc/meta/ra/06107'), URIRef('https://w3id.org/oc/meta/ra/06205'))
-        expected_lines_0610 = ['1 \n', '1 \n', '1 \n', '1 \n', '1 \n', '1 \n', '2 \n']
+        expected_lines_0610 = ['1\n', '1\n', '1\n', '1\n', '1\n', '1\n', '2\n']
         normalized_lines_0610 = read_and_normalize_file(os.path.join(OUTPUT, 'info_dir', '0610', 'creator', 'prov_file_ra.txt'))
         self.assertEqual(normalized_lines_0610, expected_lines_0610)
-        expected_lines_0620 = ['  \n', '  \n', '  \n', '  \n', '2 \n']
+        expected_lines_0620 = ['\n', '\n', '\n', '\n', '2\n']
         normalized_lines_0620 = read_and_normalize_file(os.path.join(OUTPUT, 'info_dir', '0620', 'creator', 'prov_file_ra.txt'))
         self.assertEqual(normalized_lines_0620, expected_lines_0620)
         for filepath in [