From c5621af43e9c7cb1ff0565aa61a1d8fced55a23b Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Tue, 4 Jun 2019 02:04:28 +0000 Subject: www: only emit ASCII chars in attachment filenames We don't want to emit funky URLs which can be lost in translation or cause problems with non-Unicode-aware clients. Then, don't accept non-ASCII filenames in URLs, since a manually-generated URL/filename in attachment downloads could be used for Unicode homographs to confuse folks who down the attachment. --- lib/PublicInbox/Hval.pm | 3 +++ 1 file changed, 3 insertions(+) (limited to 'lib/PublicInbox/Hval.pm') diff --git a/lib/PublicInbox/Hval.pm b/lib/PublicInbox/Hval.pm index 95a0f709..2b443970 100644 --- a/lib/PublicInbox/Hval.pm +++ b/lib/PublicInbox/Hval.pm @@ -13,6 +13,9 @@ our @EXPORT_OK = qw/ascii_html obfuscate_addrs to_filename src_escape to_attr from_attr/; my $enc_ascii = find_encoding('us-ascii'); +# safe-ish acceptable filename pattern for portability +our $FN = '[a-zA-Z0-9][a-zA-Z0-9_\-\.]+[a-zA-Z0-9]'; # needs \z anchor + sub new { my ($class, $raw, $href) = @_; -- cgit v1.2.3-24-ge0c7