TST: add test for query and some minor changes

src/newcrawler/crawl.py

@@ -344,15 +344,23 @@ class Crawler(object):
                     if isinstance(val, db.Entity):
                         el.value[index] = val.id
 
-    def remove_unnecessary_updates(self, updateList: list[db.Record]):
+    @staticmethod
+    def remove_unnecessary_updates(updateList: list[db.Record],
+                                   identified_records: list[db.Record]):
         """
         checks whether all relevant attributes (especially Property values) are equal
+
+        Returns (in future)
+        -------
+        update list without unecessary updates
+
         """
+        if len(updateList) != len(identified_records):
+            raise RuntimeError("The lists of updates and of identified records need to be of the "
+                               "same length!")
+        # TODO this can now easily be changed to a function without side effect
         for i in reversed(range(len(updateList))):
-            record = updateList[i]
-            identifiable = self.identifiableAdapter.retrieve_identifiable(record)
-
-            comp = compare_entities(record, identifiable)
+            comp = compare_entities(updateList[i], identified_records[i])
             identical = True
             for j in range(2):
                 # TODO: should be implemented elsewhere (?)
@@ -364,7 +372,8 @@ class Crawler(object):
                     break
             for key in comp[0]["properties"]:
                 for attribute in ("datatype", "importance", "unit"):
-
+                    # only make an update for those attributes if there is a value difference and
+                    # the value in the updateList is not None
                     if attribute in comp[0]["properties"][key]:
                         attr_val = comp[0]["properties"][key][attribute]
                         other_attr_val = (comp[1]["properties"][key][attribute]
@@ -407,7 +416,9 @@ class Crawler(object):
         for el in to_be_updated:
             self.replace_entities_by_ids(el)
 
-        self.remove_unnecessary_updates(to_be_updated)
+        identified_records = [self.identifiableAdapter.retrieve_identifiable(record) for record
+                              in to_be_updated]
+        self.remove_unnecessary_updates(to_be_updated, identified_records)
 
         # TODO
         # self.execute_inserts_in_list(to_be_inserted)