-# 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.
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);
-use Time::Local qw(timegm);
-
-sub get_val ($$) {
- my ($doc, $col) = @_;
- # sortable_unserialise is defined by PublicInbox::Search::load_xapian()
- sortable_unserialise($doc->get_value($col));
-}
sub to_doc_data {
my ($self) = @_;
) = split(/\n/, $_[1]);
}
-sub load_expand {
- my ($self, $doc) = @_;
- my $data = $doc->get_data or return;
- $self->{ts} = get_val($doc, PublicInbox::Search::TS());
- my $dt = get_val($doc, PublicInbox::Search::DT());
- my ($yyyy, $mon, $dd, $hh, $mm, $ss) = unpack('A4A2A2A2A2A2', $dt);
- $self->{ds} = timegm($ss, $mm, $hh, $dd, $mon - 1, $yyyy);
- load_from_data($self, $data);
- $self;
-}
-
sub psgi_cull ($) {
my ($self) = @_;
# drop NNTP-only fields which aren't relevant to PSGI results:
# saves ~80K on a 200 item search result:
# TODO: we may need to keep some of these for JMAP...
- delete @$self{qw(ts tid to cc bytes lines)};
+ delete @$self{qw(tid to cc bytes lines)};
$self;
}
-# for Import and v1 non-SQLite WWW code paths
+sub parse_references ($$$) {
+ 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)) {
$self->{-ts} = [ my @ts = msg_timestamp($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
$subj;
}
+# returns the number of bytes to add if given a non-CRLF arg
+sub crlf_adjust ($) {
+ 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;