FIX: use identifiable instead of record

The crawler has internal checks in order to decide whether a Record can be checked for existence with the server. For this, all identifying properties need to be existent and all references of those need to be resolved or also records that can be checked themselves (so that they can be checked first).

Previously, the crawler required that ALL reference Properties can be checked or are resolved in order decide that the Record at hand can be checked.

Example: RT A with properties b and c

The registered identifiable is A with b

Record A
  b = 1234

can be checked (but the old code assumed it cannot.)

Record A
  c = 2344

cannot be checked since the identifying prop is missing.

Please consider !56 (merged)

unittests/test_tool.py

@@ -287,7 +287,6 @@ def test_crawler_update_list(crawler, ident):
 
 def test_synchronization(crawler, ident):
     insl, updl = crawler.synchronize(commit_changes=False)
-
     assert len(insl) == 0
     assert len(updl) == 0
 
@@ -506,87 +505,63 @@ def test_split_into_inserts_and_updates_with_copy_attr(crawler_mocked_identifiab
     crawler.identifiableAdapter.retrieve_identified_record_for_record.assert_called()
 
 
-def test_all_references_are_existing_already2(crawler):
-    registered_identifiables = {
-        "C": db.Record().add_parent("C").add_property("a"),
-        "D": db.Record().add_parent("D").add_property("a").add_property("b")}
-    crawler.identifiableAdapter.get_registered_identifiable = Mock(side_effect=partial(
-        basic_ident_lookup, idents=registered_identifiables))
-
-    assert crawler.all_references_are_existing_already(
-        db.Record().add_parent("C").add_property('a', 123))
-    assert crawler.all_references_are_existing_already(db.Record().add_parent("C"))
-    assert crawler.all_references_are_existing_already(db.Record().add_parent("D")
-                                                       .add_property('a', 123)
-                                                       .add_property('b', db.Record(id=123)))
-    a = db.Record(name="A").add_parent("C").add_property("a", 12311)
-    assert not crawler.all_references_are_existing_already(db.Record().add_parent("D")
-                                                           .add_property('a', 123)
-                                                           .add_property('b', a))
-    crawler.add_identified_record_to_local_cache(a)
-    assert crawler.all_references_are_existing_already(db.Record().add_parent("D")
-                                                       .add_property('a', 123)
-                                                       .add_property('b', a))
-    # if this ever fails, the mock up may be removed
-    crawler.identifiableAdapter.get_registered_identifiable.assert_called()
-
-
 def test_all_references_are_existing_already(crawler):
     # Simulate remote server content by using the names to identify records
     # There are only two known Records with name A and B
     crawler.identifiableAdapter.get_registered_identifiable = Mock(side_effect=partial(
-        basic_retrieve_by_name_mock_up, known={"A": db.Record(name="A").add_parent("C"),
-                                               "B": db.Record(name="B").add_parent("C")}))
+        basic_retrieve_by_name_mock_up, known={"C": db.Record(name="C").add_parent("C")
+                                               .add_property("d"),
+                                               "D": db.Record(name="D").add_parent("D")
+                                               .add_property("d").add_property("e"),
+                                               }))
 
+    # one reference with id -> check
     assert crawler.all_references_are_existing_already(
-        db.Record().add_property('a', 123))
-    assert crawler.all_references_are_existing_already(db.Record()
-                                                       .add_property('a', db.Record(id=123)))
-    assert crawler.all_references_are_existing_already(db.Record().add_parent("D")
-                                                       .add_property('a', 123)
+        db.Record(name="C").add_parent("C").add_property('d', 123))
+    # one ref with Entity with id -> check
+    assert crawler.all_references_are_existing_already(db.Record(name="C")
+                                                       .add_property('d', db.Record(id=123)))
+    # one ref with id one with Entity with id (mixed) -> check
+    assert crawler.all_references_are_existing_already(db.Record(name="C").add_parent("D")
+                                                       .add_property('d', 123)
                                                        .add_property('b', db.Record(id=123)))
-    a = db.Record(name="A").add_parent("C").add_property("a", 12311)
-    assert not crawler.all_references_are_existing_already(db.Record().add_parent("D")
-                                                           .add_property('a', 123)
-                                                           .add_property('b', a))
+    # entity to be referenced in the following
+    a = db.Record(name="C").add_parent("C").add_property("d", 12311)
+    # one ref with id one with Entity without id (but not identifying) -> check
+    assert crawler.all_references_are_existing_already(db.Record(name="C").add_parent("C")
+                                                       .add_property('d', 123)
+                                                       .add_property('e', a))
+
+    # one ref with id one with Entity without id (mixed) -> fail
+    assert not crawler.all_references_are_existing_already(db.Record(name="D").add_parent("D")
+                                                           .add_property('d', 123)
+                                                           .add_property('e', a))
     crawler.add_identified_record_to_local_cache(a)
-    assert crawler.all_references_are_existing_already(db.Record().add_parent("D")
-                                                       .add_property('a', 123)
-                                                       .add_property('b', a))
+    # one ref with id one with Entity without id but in cache -> check
+    assert crawler.all_references_are_existing_already(db.Record(name="D").add_parent("D")
+                                                       .add_property('d', 123)
+                                                       .add_property('e', a))
     # if this ever fails, the mock up may be removed
     crawler.identifiableAdapter.get_registered_identifiable.assert_called()
 
 
-def test_can_be_checked_externally2(crawler):
-    registered_identifiables = {
-        "C": db.Record().add_parent("C").add_property("a"),
-        "D": db.Record().add_parent("D").add_property("a").add_property("b")}
-    crawler.identifiableAdapter.get_registered_identifiable = Mock(side_effect=partial(
-        basic_ident_lookup, idents=registered_identifiables))
-    assert crawler.can_be_checked_externally(db.Record().add_parent("C").add_property('a', 123))
-    assert crawler.can_be_checked_externally(db.Record().add_parent("C")
-                                             .add_property('a', db.Record(id=123)))
-    assert crawler.can_be_checked_externally(db.Record().add_parent("D")
-                                             .add_property('a', 123)
-                                             .add_property('b', db.Record(id=123)))
-
-    assert not crawler.can_be_checked_externally(db.Record().add_parent("D")
-                                                 .add_property('a', 123)
-                                                 .add_property('b', db.Record()))
-
-
-def test_can_be_checked_externally(crawler):
+def test_can_be_checked_externally(crawler, ident):
     assert crawler.can_be_checked_externally(
-        db.Record().add_property('a', 123))
-    assert crawler.can_be_checked_externally(db.Record()
-                                             .add_property('a', db.Record(id=123)))
-    assert crawler.can_be_checked_externally(db.Record().add_parent("D")
-                                             .add_property('a', 123)
-                                             .add_property('b', db.Record(id=123)))
-
-    assert not crawler.can_be_checked_externally(db.Record().add_parent("D")
-                                                 .add_property('a', 123)
-                                                 .add_property('b', db.Record()))
+        db.Record().add_parent("Person").add_property('last_name', 123).add_property('first_name', 123))
+    # id and rec with id
+    assert crawler.can_be_checked_externally(db.Record().add_parent("Person")
+                                             .add_property('first_name', 123)
+                                             .add_property('last_name', db.Record(id=123)))
+    # id and rec with id and one unneeded prop
+    assert crawler.can_be_checked_externally(db.Record().add_parent("Person")
+                                             .add_property('first_name', 123)
+                                             .add_property('stuff', db.Record())
+                                             .add_property('last_name', db.Record(id=123)))
+
+    # one identifying prop is missing
+    assert not crawler.can_be_checked_externally(db.Record().add_parent("Person")
+                                                 .add_property('first_name', 123)
+                                                 .add_property('last_name', db.Record()))
 
 
 def test_replace_entities_with_ids(crawler):