hval: only allow domain obfuscation in address

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

diff --git a/lib/PublicInbox/Hval.pm b/lib/PublicInbox/Hval.pm
index 77acecda0dc39aa7ca3bedf675b6ce32078009f8..0e199025adcec36d72d55e139900e1bf03f26edc 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 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
@@ -86,4 +86,34 @@ 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, $user, $domain) = ($1, $2, $3);
+               if ($addrs->{$addr} || ((defined $re && $domain =~ $re))) {
+                       $addr;
+               } else {
+                       $domain =~ s!([^\.]+)\.!$1•!;
+                       $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;