dblp: flesh out update code path (especially to add container_id linkage)

1 files changed, 6 insertions, 2 deletions

diff --git a/python/fatcat_tools/importers/dblp_release.py b/python/fatcat_tools/importers/dblp_release.py
index 6cf7037b..9cebcdc2 100644
--- a/python/fatcat_tools/importers/dblp_release.py
+++ b/python/fatcat_tools/importers/dblp_release.py
@@ -338,15 +338,19 @@ class DblpReleaseImporter(EntityImporter):
                 self.counts["exists-fuzzy"] += 1
                 return False
 
-        # create entity
+        # if no existing, then create entity
         if not existing:
             return True
 
-        # other logic could go here about skipping updates
         if not self.do_updates or existing.ext_ids.dblp:
             self.counts['exists'] += 1
             return False
 
+        # logic for whether to do update or skip
+        if (existing.container_id and existing.release_type and existing.release_stage) or existing.ext_ids.arxiv_id:
+            self.counts['skip-update'] += 1
+            return False
+
         # fields to copy over for update
         # TODO: granular contrib metadata
         existing.contribs = existing.contribs or re.contribs