From 80dc77cde23954150ef1ae143ed1468ee031e477 Mon Sep 17 00:00:00 2001
From: Florian Spreckelsen <f.spreckelsen@inidscale.com>
Date: Wed, 24 Jan 2024 15:40:00 +0100
Subject: [PATCH] ENH: Use merge_id_with_resolved_entity=True
---
setup.cfg | 2 +-
src/caoscrawler/crawl.py | 5 +----
2 files changed, 2 insertions(+), 5 deletions(-)
diff --git a/setup.cfg b/setup.cfg
index dc2f7378..fedee42a 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -21,7 +21,7 @@ python_requires = >=3.7
install_requires =
importlib-resources
caosadvancedtools >= 0.7.0
- linkahead >= 0.13.3
+ linkahead > 0.13.2
yaml-header-tools >= 0.2.1
pyyaml
odfpy #make optional
diff --git a/src/caoscrawler/crawl.py b/src/caoscrawler/crawl.py
index 7b05120b..70e9695e 100644
--- a/src/caoscrawler/crawl.py
+++ b/src/caoscrawler/crawl.py
@@ -601,10 +601,7 @@ class Crawler(object):
elif self.get_from_any_cache(identifiable) is not None:
# We merge the two in order to prevent loss of information
newrecord = self.get_from_any_cache(identifiable)
- try:
- merge_entities(newrecord, record)
- except EntityMergeConflictError:
- continue
+ merge_entities(newrecord, record, merge_id_with_resolved_entity=True)
Crawler.bend_references_to_new_object(
old=record, new=newrecord, entities=flat + to_be_updated + to_be_inserted)
--
GitLab