more consistent and defensive lower-casing of DOIs

After noticing more upper/lower ambiguity in production. In particular,
we have some old ingest requests in sandcrawler DB, which get
re-submitted/re-tried, which have capitalized DOIs in the link source id
field.

2 files changed, 6 insertions, 1 deletions

diff --git a/python/fatcat_tools/importers/ingest.py b/python/fatcat_tools/importers/ingest.py
index 483932ad..ae3e147a 100644
--- a/python/fatcat_tools/importers/ingest.py
+++ b/python/fatcat_tools/importers/ingest.py
@@ -133,6 +133,8 @@ class IngestFileResultImporter(EntityImporter):
                 extid = request['ext_ids'].get(extid_type)
                 if not extid:
                     continue
+                if extid_type == 'doi':
+                    extid = extid.lower()
                 try:
                     release = self.api.lookup_release(**{extid_type: extid})
                 except fatcat_openapi_client.rest.ApiException as err:
@@ -217,6 +219,8 @@ class IngestFileResultImporter(EntityImporter):
         if request.get('link_source') and request.get('link_source_id'):
             edit_extra['link_source'] = request['link_source']
             edit_extra['link_source_id'] = request['link_source_id']
+            if edit_extra['link_source'] == 'doi':
+                edit_extra['link_source_id'] = edit_extra['link_source_id'].lower()
 
         return edit_extra
 
diff --git a/python/fatcat_tools/importers/jalc.py b/python/fatcat_tools/importers/jalc.py
index 9bf2621c..12f5450f 100644
--- a/python/fatcat_tools/importers/jalc.py
+++ b/python/fatcat_tools/importers/jalc.py
@@ -5,6 +5,7 @@ import datetime
 from bs4 import BeautifulSoup
 
 import fatcat_openapi_client
+from fatcat_tools.normal import clean_doi
 from .common import EntityImporter, clean, is_cjk, DATE_FMT
 
 
@@ -171,7 +172,7 @@ class JalcImporter(EntityImporter):
 
         doi = None
         if record.doi:
-            doi = record.doi.string.lower().strip()
+            doi = clean_doi(record.doi.string.strip().lower())
             if doi.startswith('http://dx.doi.org/'):
                 doi = doi.replace('http://dx.doi.org/', '')
             elif doi.startswith('https://dx.doi.org/'):