From 53ce683625bb6f26515f342b5ee191842d2f5d5d Mon Sep 17 00:00:00 2001
From: florian <f.spreckelsen@inidscale.com>
Date: Wed, 2 Nov 2022 14:54:53 +0100
Subject: [PATCH] FIX: Use force merge with a deepcopy
---
src/caoscrawler/crawl.py | 12 +++++++++---
1 file changed, 9 insertions(+), 3 deletions(-)
diff --git a/src/caoscrawler/crawl.py b/src/caoscrawler/crawl.py
index 0952d645..0883ca8f 100644
--- a/src/caoscrawler/crawl.py
+++ b/src/caoscrawler/crawl.py
@@ -745,9 +745,15 @@ class Crawler(object):
record._size = identified_record._size
record._checksum = identified_record._checksum
- merge_entities(record, identified_record)
- to_be_updated.append(record)
- self.add_to_remote_existing_cache(record)
+ # Create a temporary copy since the merge will be conducted in place
+ tmp = deepcopy(identified_record)
+ # A force merge will overwrite any properties that both
+ # the identified and the crawled record have with the
+ # values of the crawled record while keeping existing
+ # properties intact.
+ merge_entities(tmp, record, force=True)
+ to_be_updated.append(tmp)
+ self.add_to_remote_existing_cache(tmp)
del flat[i]
resolved_references = True
--
GitLab