From: Eric Wong <e@80x24.org>
Date: Tue, 4 Jun 2019 02:04:23 +0000 (+0000)
Subject: mid: id_compress requires ASCII-clean words
X-Git-Tag: v1.2.0~196^2~20
X-Git-Url: http://www.git.stargrave.org/?a=commitdiff_plain;h=1f8065599d934b2af7d24773bb7d6901f9586945;p=public-inbox.git

mid: id_compress requires ASCII-clean words

Its result is used for HTML anchors and such.
---

diff --git a/lib/PublicInbox/MID.pm b/lib/PublicInbox/MID.pm
index 7f1ab15e..6904d61a 100644
--- 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);
 	}