about summary refs log tree commit homepage
path: root/lib/PublicInbox/OverIdx.pm
diff options
authorEric Wong <e@80x24.org>2021-10-06 10:12:21 +0000
committerEric Wong <e@80x24.org>2021-10-06 11:23:51 +0000
commite785573c556572a675407796604e9c0a9965ea9f (patch)
tree007e58811f281de2d8d51433021c85440bbc2163 /lib/PublicInbox/OverIdx.pm
parent89193578d21f847478f844e9e85495b9cae8842b (diff)
This should bring us closer to the "Base subject" definition in
IMAP ORDEREDSUBJECT (RFC 5256 2.1).  Larger changes may cause
some breakage (until --reindex).  But for now, a reindex will
prevents the non-ASCII subjects from being normalized to the
same fuzzy "thread" in the thread view.
Diffstat (limited to 'lib/PublicInbox/OverIdx.pm')
1 files changed, 4 insertions, 3 deletions
diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index 2e3d4534..0c8a4d9e 100644
--- a/lib/PublicInbox/OverIdx.pm
+++ b/lib/PublicInbox/OverIdx.pm
@@ -243,12 +243,13 @@ sub link_refs {
-# normalize subjects so they are suitable as pathnames for URLs
-# XXX: consider for removal
+# normalize subjects somewhat, they used to be ASCII-only but now
+# we use \w for UTF-8 support.  We may still drop it entirely and
+# rely on Xapian for subject matches...
 sub subject_path ($) {
         my ($subj) = @_;
         $subj = subject_normalized($subj);
-        $subj =~ s![^a-zA-Z0-9_\.~/\-]+!_!g;
+        $subj =~ s![^\w\.~/\-]+!_!g;