hval: only perform one substitution when obfuscating

[public-inbox.git] / lib / PublicInbox / Hval.pm

diff --git a/lib/PublicInbox/Hval.pm b/lib/PublicInbox/Hval.pm
index 72496065d59fc49dba282428fee6885b1438dc2d..8d36fc2ba6a38189193360e0059647688346eabf 100644 (file)
--- a/lib/PublicInbox/Hval.pm
+++ b/lib/PublicInbox/Hval.pm
@@ -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/;
 
 # 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 +86,24 @@ sub prurl {
        index($u, '//') == 0 ? "$env->{'psgi.url_scheme'}:$u" : $u;
 }
 
+# for misguided people who believe in this stuff, give them a
+# substitution for '.'
+# ․ · 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 ($$) {
+       my $ibx = $_[0];
+       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, $2);
+               if ($addrs->{$addr} || ((defined $re && $domain =~ $re))) {
+                       $addr;
+               } else {
+                       $addr =~ s!([^\.]+)\.!$1•!;
+                       $addr
+               }
+               /sge;
+}
+
 1;