X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FHval.pm;h=d65ab3217c915a18db892e226a87af7594a2fe53;hb=7ee391533b51f37e949e31a26c2ad93b935c3d03;hp=8d36fc2ba6a38189193360e0059647688346eabf;hpb=cfb0a03a8966c71820e4536eaf31265ea79397e6;p=public-inbox.git

diff --git a/lib/PublicInbox/Hval.pm b/lib/PublicInbox/Hval.pm
index 8d36fc2b..d65ab321 100644
--- 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 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
@@ -91,19 +91,30 @@ sub prurl {
 # ․ · 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•!;
-			$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;