Merge branch 'charclass'

* charclass: (24 commits)
  www: require ASCII word characters for CSS filenames
  www: require ASCII range for mbox downloads
  githttpbackend: require ASCII in path
  require ASCII digits for local FS items
  www: require ASCII digit for git epoch
  solver|viewdiff: restrict digit matches to ASCII
  inbox: require ASCII digits for feedmax var
  filter/rubylang: require ASCII digit for mailcount
  msgtime: require ASCII digits for parsing dates
  searchview: do not allow non-ASCII offsets and limits
  githttpbackend: require Range:, Status: to be ASCII digits
  view: require YYYYmmDD(HHMMSS) timestamps to be ASCII
  newswww: only accept ASCII digits as article numbers
  config: do not accept non-ASCII digits in cgitrc params
  www: require ASCII filenames in git blob downloads
  www: only emit ASCII chars in attachment filenames
  wwwattach: only pass the charset through if ASCII
  wwwlisting: require ASCII digit for port number
  http: require SERVER_PORT to be ASCII digit
  feed: only accept ASCII digits for ref~$N
  ...

1 files changed, 3 insertions, 2 deletions

diff --git a/lib/PublicInbox/Linkify.pm b/lib/PublicInbox/Linkify.pm
index d4778e7d..84960a98 100644
--- a/lib/PublicInbox/Linkify.pm
+++ b/lib/PublicInbox/Linkify.pm
@@ -13,6 +13,7 @@ package PublicInbox::Linkify;
 use strict;
 use warnings;
 use Digest::SHA qw/sha1_hex/;
+use PublicInbox::Hval qw(ascii_html);
 
 my $SALT = rand;
 my $LINK_RE = qr{([\('!])?\b((?:ftps?|https?|nntps?|gopher)://
@@ -61,12 +62,12 @@ sub linkify_1 {
                         $end = ')';
                 }
 
+                $url = ascii_html($url); # for IDN
+
                 # salt this, as this could be exploited to show
                 # links in the HTML which don't show up in the raw mail.
                 my $key = sha1_hex($url . $SALT);
 
-                # only escape ampersands, others do not match LINK_RE
-                $url =~ s/&/&/g;
                 $_[0]->{$key} = $url;
                 $beg . 'PI-LINK-'. $key . $end;
         ^ge;