mid: id_compress requires ASCII-clean words

[public-inbox.git] / lib / PublicInbox / MID.pm

diff --git a/lib/PublicInbox/MID.pm b/lib/PublicInbox/MID.pm
index 7f1ab15ea731db8f0f70304662afe338754b5c6c..6904d61a0303bb0edd2b17b479c85e6bd13e76ff 100644 (file)
--- a/lib/PublicInbox/MID.pm
+++ b/lib/PublicInbox/MID.pm
@@ -26,11 +26,11 @@ sub mid_clean {
        $mid;
 }
 
-# this is idempotent
+# this is idempotent, used for HTML anchor/ids and such
 sub id_compress {
        my ($id, $force) = @_;
 
-       if ($force || $id =~ /[^\w\-]/ || length($id) > MID_MAX) {
+       if ($force || $id =~ /[^a-zA-Z0-9_\-]/ || length($id) > MID_MAX) {
                utf8::encode($id);
                return sha1_hex($id);
        }