X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FHval.pm;h=c47057fc5f82cfea7c15ffa79d21dd5cc4106058;hb=3d41aa23f35501ca92aab8aa42980fa73f7fa74f;hp=72496065d59fc49dba282428fee6885b1438dc2d;hpb=9d1e5fadd7d18f4c96ab0509d673040e34225a04;p=public-inbox.git

diff --git a/lib/PublicInbox/Hval.pm b/lib/PublicInbox/Hval.pm
index 72496065..c47057fc 100644
--- a/lib/PublicInbox/Hval.pm
+++ b/lib/PublicInbox/Hval.pm
@@ -1,5 +1,5 @@
-# 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)
@@ -9,7 +9,7 @@ use warnings;
 use Encode qw(find_encoding);
 use PublicInbox::MID qw/mid_clean mid_escape/;
 use base qw/Exporter/;
-our @EXPORT_OK = qw/ascii_html/;
+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
@@ -31,7 +31,6 @@ sub new {
 
 sub new_msgid {
 	my ($class, $msgid) = @_;
-	$msgid = mid_clean($msgid);
 	$class->new($msgid, mid_escape($msgid));
 }
 
@@ -87,4 +86,35 @@ sub prurl {
 	index($u, '//') == 0 ? "$env->{'psgi.url_scheme'}:$u" : $u;
 }
 
+# for misguided people who believe in this stuff, give them a
+# substitution for '.'
+# &#8228; &#183; and &#890; were also candidates:
+#   https://public-inbox.org/meta/20170615015250.GA6484@starla/
+# However, &#8226; was chosen to make copy+paste errors more obvious
+sub obfuscate_addrs ($$;$) {
+	my $ibx = $_[0];
+	my $repl = $_[2] || '&#8226;';
+	my $re = $ibx->{-no_obfuscate_re}; # regex of domains
+	my $addrs = $ibx->{-no_obfuscate}; # { adddress => 1 }
+	$_[1] =~ s/(([\w\.\+=\-]+)\@([\w\-]+\.[\w\.\-]+))/
+		my ($addr, $user, $domain) = ($1, $2, $3);
+		if ($addrs->{$addr} || ((defined $re && $domain =~ $re))) {
+			$addr;
+		} else {
+			$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;