X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FHval.pm;h=0e199025adcec36d72d55e139900e1bf03f26edc;hb=24a309bd1221a24ac673ece463f765f7a92921ff;hp=f262073767807cfbd37919f442001d181c77e355;hpb=1d0ce406b75fc174bee51e77efe5f10c61fb6098;p=public-inbox.git

diff --git a/lib/PublicInbox/Hval.pm b/lib/PublicInbox/Hval.pm
index f2620737..0e199025 100644
--- a/lib/PublicInbox/Hval.pm
+++ b/lib/PublicInbox/Hval.pm
@@ -7,10 +7,9 @@ package PublicInbox::Hval;
 use strict;
 use warnings;
 use Encode qw(find_encoding);
-use URI::Escape qw(uri_escape_utf8);
-use PublicInbox::MID qw/mid_clean/;
+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
@@ -32,8 +31,7 @@ sub new {
 
 sub new_msgid {
 	my ($class, $msgid) = @_;
-	$msgid = mid_clean($msgid);
-	$class->new($msgid, $msgid);
+	$class->new($msgid, mid_escape($msgid));
 }
 
 sub new_oneline {
@@ -74,7 +72,6 @@ sub ascii_html {
 }
 
 sub as_html { ascii_html($_[0]->{raw}) }
-sub as_href { ascii_html(uri_escape_utf8($_[0]->{href})) }
 
 sub raw {
 	if (defined $_[1]) {
@@ -89,4 +86,34 @@ sub prurl {
 	index($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;