-# Copyright (C) 2014-2015 all contributors <meta@public-inbox.org>
-# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# Copyright (C) 2014-2018 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
#
# represents a header value in various forms. Used for HTML generation
# in our web interface(s)
use Encode qw(find_encoding);
use PublicInbox::MID qw/mid_clean mid_escape/;
use base qw/Exporter/;
-our @EXPORT_OK = qw/ascii_html obfuscate_addrs/;
+our @EXPORT_OK = qw/ascii_html obfuscate_addrs to_filename/;
# for user-generated content (UGC) which may have excessively long lines
# and screw up rendering on some browsers. This is the only CSS style
# ․ · and ͺ were also candidates:
# https://public-inbox.org/meta/20170615015250.GA6484@starla/
# However, • was chosen to make copy+paste errors more obvious
-sub obfuscate_addrs ($$) {
+sub obfuscate_addrs ($$;$) {
my $ibx = $_[0];
+ my $repl = $_[2] || '•';
my $re = $ibx->{-no_obfuscate_re}; # regex of domains
my $addrs = $ibx->{-no_obfuscate}; # { adddress => 1 }
- $_[1] =~ s/([\w\.\+=\-]+\@([\w\-]+\.[\w\.\-]+))/
- my ($addr, $domain) = ($1, $2);
+ $_[1] =~ s/(([\w\.\+=\-]+)\@([\w\-]+\.[\w\.\-]+))/
+ my ($addr, $user, $domain) = ($1, $2, $3);
if ($addrs->{$addr} || ((defined $re && $domain =~ $re))) {
$addr;
} else {
- $addr =~ s!([^\.]+)\.!$1•!g;
- $addr
+ $domain =~ s!([^\.]+)\.!$1$repl!;
+ $user . '@' . $domain
}
/sge;
}
+# like format_sanitized_subject in git.git pretty.c with '%f' format string
+sub to_filename ($) {
+ my ($s, undef) = split(/\n/, $_[0]);
+ $s =~ s/[^A-Za-z0-9_\.]+/-/g;
+ $s =~ tr/././s;
+ $s =~ s/[\.\-]+\z//;
+ $s =~ s/\A[\.\-]+//;
+ $s
+}
+
1;