-# Copyright (C) 2015, all contributors <meta@public-inbox.org>
-# License: GPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# Copyright (C) 2015-2016 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# based on notmuch, but with no concept of folders, files or flags
+#
+# Wraps a document inside our Xapian search index.
package PublicInbox::SearchMsg;
use strict;
use warnings;
use Search::Xapian;
+use Email::Address qw//;
+use POSIX qw//;
+use Date::Parse qw/str2time/;
+use PublicInbox::MID qw/mid_clean/;
+use Encode qw/find_encoding/;
+my $enc_utf8 = find_encoding('UTF-8');
our $PFX2TERM_RE = undef;
+use constant EPOCH_822 => 'Thu, 01 Jan 1970 00:00:00 +0000';
+use POSIX qw(strftime);
sub new {
my ($class, $mime) = @_;
bless { doc => $doc, mime => undef, mid => $mid }, $class;
}
+sub get_val ($$) {
+ my ($doc, $col) = @_;
+ Search::Xapian::sortable_unserialise($doc->get_value($col));
+}
+
+sub load_doc {
+ my ($class, $doc) = @_;
+ my $data = $doc->get_data;
+ my $ts = get_val($doc, &PublicInbox::Search::TS);
+ $data = $enc_utf8->decode($data);
+ my ($subj, $from, $refs, $to, $cc) = split(/\n/, $data);
+ bless {
+ doc => $doc,
+ subject => $subj,
+ ts => $ts,
+ from => $from,
+ references => $refs,
+ to => $to,
+ cc => $cc,
+ }, $class;
+}
+
+# :bytes and :lines metadata in RFC 3977
+sub bytes ($) { get_val($_[0]->{doc}, &PublicInbox::Search::BYTES) }
+sub lines ($) { get_val($_[0]->{doc}, &PublicInbox::Search::LINES) }
+sub num ($) { get_val($_[0]->{doc}, &PublicInbox::Search::NUM) }
+
+sub __hdr ($$) {
+ my ($self, $field) = @_;
+ my $val = $self->{$field};
+ return $val if defined $val;
+
+ my $mime = $self->{mime} or return;
+ $val = $mime->header($field);
+ $val = '' unless defined $val;
+ $val =~ tr/\t\r\n/ /;
+ $self->{$field} = $val;
+}
+
+sub subject ($) { __hdr($_[0], 'subject') }
+sub to ($) { __hdr($_[0], 'to') }
+sub cc ($) { __hdr($_[0], 'cc') }
+
+sub date ($) {
+ my ($self) = @_;
+ my $date = __hdr($self, 'date');
+ return $date if defined $date;
+ my $ts = $self->{ts};
+ return unless defined $ts;
+ $self->{date} = strftime('%a, %d %b %Y %T %z', gmtime($ts));
+}
+
+sub from ($) {
+ my ($self) = @_;
+ my $from = __hdr($self, 'from');
+ if (defined $from && !defined $self->{from_name}) {
+ $from =~ tr/\t\r\n/ /;
+ my @from = Email::Address->parse($from);
+ $self->{from_name} = $from[0]->name;
+ }
+ $from;
+}
+
+sub from_name {
+ my ($self) = @_;
+ my $from_name = $self->{from_name};
+ return $from_name if defined $from_name;
+ $self->from;
+ $self->{from_name};
+}
+
+sub ts {
+ my ($self) = @_;
+ $self->{ts} ||= eval { str2time($self->mime->header('Date')) } || 0;
+}
+
+sub to_doc_data {
+ my ($self) = @_;
+ join("\n", $self->subject, $self->from, $self->references,
+ $self->to, $self->cc);
+}
+
+sub references {
+ my ($self) = @_;
+ my $x = $self->{references};
+ defined $x ? $x : '';
+}
+
sub ensure_metadata {
my ($self) = @_;
my $doc = $self->{doc};
- my $i = $doc->termlist_begin;
my $end = $doc->termlist_end;
unless (defined $PFX2TERM_RE) {
$PFX2TERM_RE = qr/\A($or)/;
}
- for (; $i != $end; $i->inc) {
- my $val = $i->get_termname;
+ while (my ($pfx, $field) = each %PublicInbox::Search::PFX2TERM_RMAP) {
+ # ideally we'd move this out of the loop:
+ my $i = $doc->termlist_begin;
+
+ $i->skip_to($pfx);
+ if ($i != $end) {
+ my $val = $i->get_termname;
- if ($val =~ s/$PFX2TERM_RE//o) {
- my $field = $PublicInbox::Search::PFX2TERM_RMAP{$1};
- if ($field eq 'references') {
- my $refs = $self->{references} ||= [];
- push @$refs, $val;
- } else {
+ if ($val =~ s/$PFX2TERM_RE//o) {
$self->{$field} = $val;
}
}
}
}
-sub mid {
+# for threading only
+sub mini_mime {
+ my ($self) = @_;
+ $self->ensure_metadata;
+ my @hs = (
+ 'Subject' => $self->subject,
+ 'X-PI-From' => $self->from_name,
+ );
+
+ my @h = (
+ # prevent Email::Simple::Creator from running,
+ # this header is useless for threading as we use X-PI-TS
+ # for sorting and display:
+ 'Date' => EPOCH_822,
+ 'Message-ID' => "<$self->{mid}>",
+ 'X-PI-TS' => $self->ts,
+ );
+ if (my $refs = $self->{references}) {
+ push @h, References => $refs;
+ }
+ my $mime = Email::MIME->create(header_str => \@hs, header => \@h);
+ my $h = $mime->header_obj;
+
+ # set these headers manually since Encode::encode('MIME-Q', ...)
+ # will add spaces to long values when using header_str above.
+
+ # drop useless headers Email::MIME set for us
+ $h->header_set('Date');
+ $h->header_set('MIME-Version');
+ $mime;
+}
+
+sub mid ($;$) {
my ($self, $mid) = @_;
if (defined $mid) {
- $self->{mid} = $mid;
+ $self->{mid} = $mid;
+ } elsif (my $rv = $self->{mid}) {
+ $rv;
} else {
- $self->{mid} ||= $self->_extract_mid;
+ $self->ensure_metadata; # needed for ghosts
+ $self->{mid} ||= $self->_extract_mid;
}
}
-sub _extract_mid {
- my ($self) = @_;
-
- my $mid = $self->mime->header('Message-ID');
- if ($mid && $mid =~ /<([^>]+)>/) {
- return $1;
- }
- return $mid;
-}
+sub _extract_mid { mid_clean(mid_mime($_[0]->mime)) }
sub mime {
my ($self, $mime) = @_;