# large threads in our WWW UI and the NNTP range responses.
package PublicInbox::Smsg;
use strict;
-use warnings;
-use base qw(Exporter);
+use v5.10.1;
+use parent 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);
+sub oidbin { pack('H*', $_[0]->{blob}) }
+
sub to_doc_data {
my ($self) = @_;
join("\n",
sub psgi_cull ($) {
my ($self) = @_;
- # ghosts don't have ->{from}
- my $from = delete($self->{from}) // '';
- my @n = PublicInbox::Address::names($from);
- $self->{from_name} = join(', ', @n);
-
# drop NNTP-only fields which aren't relevant to PSGI results:
# saves ~80K on a 200 item search result:
# TODO: we may need to keep some of these for JMAP...
- delete @$self{qw(tid to cc bytes lines)};
+ my ($f) = delete @$self{qw(from tid to cc bytes lines)};
+ # ghosts don't have ->{from}
+ $self->{from_name} = join(', ', PublicInbox::Address::names($f // ''));
$self;
}
+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) = @_;
our $REPLY_RE = qr/^re:\s+/i;
+# TODO: see RFC 5256 sec 2.1 "Base Subject" and evaluate compatibility
+# w/ existing indices...
sub subject_normalized ($) {
my ($subj) = @_;
$subj =~ s/\A\s+//s; # no leading space
$subj;
}
+# returns the number of bytes to add if given a non-CRLF arg
+sub crlf_adjust ($) {
+ 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;