From 9c0e5d714ea9fedeca64f1ceb5b47f67438629af Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Tue, 23 Jun 2020 18:38:33 -0700
Subject: strip control characters from titles (issn_meta)

---
 chocula/util.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/chocula/util.py b/chocula/util.py
index 894af98..c2466cd 100644
--- a/chocula/util.py
+++ b/chocula/util.py
@@ -279,6 +279,10 @@ def clean_str(s: Optional[str]) -> Optional[str]:
     if not s:
         return None
     s = unquote(ftfy.fix_text(s))
+    # these unicode characters are used by, eg, ISSN portal to mare prefixes as
+    # non-sorting
+    s.replace("\u02dc", "")
+    s.replace("\u0153", "")
     return s or None
 
 
-- 
cgit v1.2.3