aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@robocracy.org>2019-12-24 14:03:07 -0800
committerBryan Newbold <bnewbold@robocracy.org>2019-12-24 14:03:07 -0800
commit7222131f172ef26eebf964e8b17b024d7ccebb24 (patch)
tree8d7c6f1d0de941dc4201c1ff56602045662c0de2
parent19bbc2f1959f19b8ec8e7f0609442d67509e49a8 (diff)
downloadfatcat-7222131f172ef26eebf964e8b17b024d7ccebb24.tar.gz
fatcat-7222131f172ef26eebf964e8b17b024d7ccebb24.zip
make chocula URL updates more conservative
-rw-r--r--python/fatcat_tools/importers/chocula.py10
1 files changed, 5 insertions, 5 deletions
diff --git a/python/fatcat_tools/importers/chocula.py b/python/fatcat_tools/importers/chocula.py
index 6915ba98..eea50314 100644
--- a/python/fatcat_tools/importers/chocula.py
+++ b/python/fatcat_tools/importers/chocula.py
@@ -128,15 +128,15 @@ class ChoculaImporter(EntityImporter):
existing.publisher = ce.publisher
existing.container_type = existing.container_type or ce.container_type
for k in ('urls', 'webarchive_urls'):
- # update, or clobber/remove any existing values. often
- # want/need to remove dead URLs
+ # update, which might clobber, but won't remove
if ce.extra.get(k):
existing.extra[k] = ce.extra.get(k, [])
- elif k in existing.extra.keys():
- existing.extra.pop(k)
+ # note: in some cases we might *want* to clobber existing (if
+ # all URLs found to be bad), but being conservative for now so
+ # we don't clobber human edits
for k in ('issne', 'issnp', 'country', 'sherpa_romeo', 'ezb',
'szczepanski', 'doaj'):
- # update, but don't remove any existing value
+ # update/overwrite, but don't remove any existing value
if ce.extra.get(k):
existing.extra[k] = ce.extra[k]
if ce.extra.get('languages'):