www_stream: extra link to mirroring information in the footer

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

diff --git a/lib/PublicInbox/Smsg.pm b/lib/PublicInbox/Smsg.pm
index 140865389bce65102b9a00ee2c739780d4caefb5..da8ce590991a3e40522bcab2bc0c561d5aa5683f 100644 (file)
--- a/lib/PublicInbox/Smsg.pm
+++ b/lib/PublicInbox/Smsg.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2015-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # A small/skeleton/slim representation of a message.
@@ -12,7 +12,7 @@ use strict;
 use warnings;
 use base qw(Exporter);
 our @EXPORT_OK = qw(subject_normalized);
-use PublicInbox::MID qw(mids);
+use PublicInbox::MID qw(mids references);
 use PublicInbox::Address;
 use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
 
@@ -69,7 +69,27 @@ sub psgi_cull ($) {
        $self;
 }
 
-# for Import and v1 non-SQLite WWW code paths
+sub parse_references ($$$) {
+       my ($smsg, $hdr, $mids) = @_;
+       my $refs = references($hdr);
+       push(@$refs, @$mids) if scalar(@$mids) > 1;
+       return $refs if scalar(@$refs) == 0;
+
+       # prevent circular references here:
+       my %seen = ( ($smsg->{mid} // '') => 1 );
+       my @keep;
+       foreach my $ref (@$refs) {
+               if (length($ref) > PublicInbox::MID::MAX_MID_SIZE) {
+                       warn "References: <$ref> too long, ignoring\n";
+                       next;
+               }
+               $seen{$ref} //= push(@keep, $ref);
+       }
+       $smsg->{references} = '<'.join('> <', @keep).'>' if @keep;
+       \@keep;
+}
+
+# used for v2, Import and v1 non-SQLite WWW code paths
 sub populate {
        my ($self, $hdr, $sync) = @_;
        for my $f (qw(From To Cc Subject)) {
@@ -100,9 +120,7 @@ sub populate {
        $self->{-ts} = [ my @ts = msg_timestamp($hdr, $sync->{cotime}) ];
        $self->{ds} //= $ds[0]; # no zone
        $self->{ts} //= $ts[0];
-
-       # for v1 users w/o SQLite
-       $self->{mid} //= eval { mids($hdr)->[0] } // '';
+       $self->{mid} //= mids($hdr)->[0];
 }
 
 # no strftime, that is locale-dependent and not for RFC822
@@ -137,4 +155,17 @@ sub subject_normalized ($) {
        $subj;
 }
 
+# returns the number of bytes to add if given a non-CRLF arg
+sub crlf_adjust ($) {
+       if (index($_[0], "\r\n") < 0) {
+               # common case is LF-only, every \n needs an \r;
+               # so favor a cheap tr// over an expensive m//g
+               $_[0] =~ tr/\n/\n/;
+       } else { # count number of '\n' w/o '\r', expensive:
+               scalar(my @n = ($_[0] =~ m/(?<!\r)\n/g));
+       }
+}
+
+sub set_bytes { $_[0]->{bytes} = $_[2] + crlf_adjust($_[1]) }
+
 1;