From e38fed98b8a95be2dea65759e99fac9ff322428d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Henrik=20tom=20W=C3=B6rden?= <h.tomwoerden@indiscale.com>
Date: Mon, 17 Oct 2022 10:01:11 +0200
Subject: [PATCH] MAINT: doc and rename test
---
src/caoscrawler/crawl.py | 13 +++++++------
unittests/test_tool.py | 2 +-
2 files changed, 8 insertions(+), 7 deletions(-)
diff --git a/src/caoscrawler/crawl.py b/src/caoscrawler/crawl.py
index a117aeb2..03a856c1 100644
--- a/src/caoscrawler/crawl.py
+++ b/src/caoscrawler/crawl.py
@@ -193,8 +193,9 @@ class Crawler(object):
Please use SecurityMode Enum
"""
- # TODO: check if this feature is really needed
-
+ # The following caches store records, where we checked whether they exist on the remote
+ # server. Since, it is important to know whether they exist or not, we store them into two
+ # different caches.
self.remote_existing_cache = IdentifiedCache()
self.remote_missing_cache = IdentifiedCache()
self.recordStore = RecordStore()
@@ -525,10 +526,10 @@ class Crawler(object):
def has_missing_object_in_references(self, record: db.Record):
"""
- returns False if any property value is a db.Entity object that does not have an ID and also
- is not contained in the local cache. For example, if it was checked before whether such an
- db.Entity object existed remotely and it was not found, it would have been added to the
- local cache.
+ returns False if any property value is a db.Entity object that
+ is contained in the `remote_missing_cache`. If the record has such an object in the
+ reference properties, it means that it references another Entity, where we checked
+ whether it exists remotely and it was not found.
"""
for p in record.properties:
# if (is_reference(p)
diff --git a/unittests/test_tool.py b/unittests/test_tool.py
index 7eba03fe..5ffb9a45 100755
--- a/unittests/test_tool.py
+++ b/unittests/test_tool.py
@@ -498,7 +498,7 @@ def test_split_into_inserts_and_updates_with_copy_attr(crawler_mocked_identifiab
crawler.identifiableAdapter.retrieve_identified_record_for_record.assert_called()
-def test_no_uncached_entity_object_in_references(crawler):
+def test_has_missing_object_in_references(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(
--
GitLab