OneStop4All-Indexer 2.8.0.dev20__tar.gz → 2.8.0rc2__tar.gz

{onestop4all_indexer-2.8.0.dev20 → onestop4all_indexer-2.8.0rc2/OneStop4All_Indexer.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: OneStop4All-Indexer
-Version: 2.8.0.dev20
+Version: 2.8.0rc2
 Summary: Library to harvest data from NFDI4Earth-KnowledgeHub to OneStop4All-Index
 Author: Markus Konkol, Arne Vogt, Tom Niers, Ralf Klammer
 Author-email: m.konkol@52north.org, a.vogt@52north.org, tom.niers@tu-dresden.de, ralf.klammer@tu-dresden.de

{onestop4all_indexer-2.8.0.dev20/OneStop4All_Indexer.egg-info → onestop4all_indexer-2.8.0rc2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: OneStop4All-Indexer
-Version: 2.8.0.dev20
+Version: 2.8.0rc2
 Summary: Library to harvest data from NFDI4Earth-KnowledgeHub to OneStop4All-Index
 Author: Markus Konkol, Arne Vogt, Tom Niers, Ralf Klammer
 Author-email: m.konkol@52north.org, a.vogt@52north.org, tom.niers@tu-dresden.de, ralf.klammer@tu-dresden.de

{onestop4all_indexer-2.8.0.dev20 → onestop4all_indexer-2.8.0rc2}/harvesters/harvester_dataservice.py

@@ -511,7 +511,11 @@ class DataService_HarvesterBatched(DataService_Harvester):
         hits = sparql.execute_query(self.sparql_endpoint, query)
         return hits
 
-    def harvest(self, records, batch_size=10):
+    def harvest(self, records=None, batch_size=10):
+
+        if records is None:
+            records = self.get_all_ids()
+
         services = {}
         # dsh_batched.parse_response(triples, services)
         while True:

{onestop4all_indexer-2.8.0.dev20 → onestop4all_indexer-2.8.0rc2}/harvesters/harvester_organization.py

@@ -173,7 +173,6 @@ class Organization_Harvester(Harvester):
             "http://www.w3.org/2004/02/skos/core#altLabel": "altLabel",
             "http://www.w3.org/1999/02/22-rdf-syntax-ns#type": "type",
             "http://nfdi4earth.de/ontology/sourceSystemURL": "sourceSystemURL",
-            "http://nfdi4earth.de/ontology/hasSignedCommitment": "hasSignedCommitment",
             "http://nfdi4earth.de/ontology/sourceSystemID": "sourceSystem" + self.flatten_separator + "id"
         }
 
@@ -250,6 +249,15 @@ class Organization_Harvester(Harvester):
                         dict=organizations[subject],
                         attribute=attribute,
                         value=object)
+            
+            elif (predicate == "http://nfdi4earth.de/ontology/hasSignedCommitment"
+                  and not self.does_object_exist(object, "hasSignedCommitment", organizations[subject])
+                  and int(object[0])):
+                self.addValue(
+                        dict=organizations[subject],
+                        attribute="hasSignedCommitment",
+                        value=object)
+
             elif (
                 predicate == "http://www.w3.org/ns/org#subOrganizationOf"
                 and (subject, object) not in issuborganization

{onestop4all_indexer-2.8.0.dev20 → onestop4all_indexer-2.8.0rc2}/setup.py

@@ -2,7 +2,7 @@ from setuptools import find_packages, setup
 
 setup(
     name="OneStop4All-Indexer",
-    version="2.8.0.dev20",
+    version="2.8.0.rc2",
     description="Library to harvest data from NFDI4Earth-KnowledgeHub to OneStop4All-Index",
     author="Markus Konkol, Arne Vogt, Tom Niers, Ralf Klammer",
     author_email="m.konkol@52north.org, a.vogt@52north.org, tom.niers@tu-dresden.de, ralf.klammer@tu-dresden.de",

{onestop4all_indexer-2.8.0.dev20 → onestop4all_indexer-2.8.0rc2}/utils/cli.py

@@ -2,8 +2,11 @@ import logging
 
 import click
 
+from data_repositories import RepositoryPerson, RepositoryTheme
+from harvesters.harvester_dataservice import DataService_HarvesterBatched
 from utils import cli_startup, config, run as run_harvesting, Solr
 
+
 log = logging.getLogger(__name__)
 
 
@@ -129,12 +132,6 @@ def dataservices(**options):
 
 @debug.command()
 def dataservices_batched():
-    from utils import config
-    from harvesters.harvester_dataservice import DataService_HarvesterBatched
-    from data_repositories import RepositoryPerson, RepositoryTheme
-
-    print("und los")
-    print(config)
     persons_repo = RepositoryPerson()
     themes_repo = RepositoryTheme()
     dsh_batched = DataService_HarvesterBatched(
@@ -148,7 +145,7 @@ def dataservices_batched():
         # print(f"Batch {i//batch_size}: IDs {i} to {i+batch_size}")
         ids_batched = ids[i : i + batch_size]
         print(f"Batch {i//batch_size}: IDs {ids_batched}")
-        triples = dsh_batched.get_triples_for_subjects(ids_batched)
+        triples = dsh_batched.harvest(ids_batched)
         print(f"Batch {i//batch_size}: Triples {len(triples)}")