deploy: 18eba15

Author: pancetta

bin/arxiv_to_publications_correct.py

@@ -36,16 +36,28 @@
             id = data['author'][0]['family'] + 'EtAl' + str(data['issued']['date-parts'][0][0])
         else:
             id = data['author'][0]['family'] + str(data['issued']['date-parts'][0][0])
-        if id != id_db:
-            print(f'Note: ID generated with new DOI ({id}) differs from the original in database ({id_db}). Keeping original ID.')
+        id = id.replace(" ", "_")
 
         entries = db.get_entry_dict()
         assert entries[id_db]["ENTRYTYPE"] == 'unpublished', "original entry in bib file was NOT unpublished !"
         db.entries.remove(entries[id_db])
 
+        # Check for duplicate keys in the remaining database and add letter suffixes if needed
+        remaining = db.get_entry_dict()
+        id_orig = id
+        letters = 'bcdefghijklmnopqrstuvwxyz'
+        i = 0
+        while id in remaining:
+            print(f'Key {id} already exists, augmenting with letter suffix.')
+            id = id_orig + letters[i]
+            i += 1
+
+        if id != id_db:
+            print(f'Note: ID updated from {id_db} to {id} to reflect the publication year.')
+
         bType, *rest1 = bib.split("{")
         oldID, *rest2 = rest1[0].split(",")
-        bib = "{".join([bType] + [','.join([id_db]+rest2)] + rest1[1:])
+        bib = "{".join([bType] + [','.join([id]+rest2)] + rest1[1:])
         bib_db = bibtexparser.loads(bib)
         db.entries.extend(bib_db.get_entry_list())