-# Copyright (C) 2015-2016 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2018 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
#
package PublicInbox::SearchMsg;
use strict;
use warnings;
-use Search::Xapian;
-use Date::Parse qw/str2time/;
-use PublicInbox::MID qw/mid_clean/;
+use PublicInbox::MID qw/mid_clean mid_mime/;
use PublicInbox::Address;
+use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
sub new {
my ($class, $mime) = @_;
my $doc = Search::Xapian::Document->new;
- $doc->add_term('T' . 'mail');
+ $doc->add_boolean_term('T' . 'mail');
bless { type => 'mail', doc => $doc, mime => $mime }, $class;
}
bless { doc => $doc, mime => undef, mid => $mid }, $class;
}
+sub get {
+ my ($class, $head, $db, $mid) = @_;
+ my $doc_id = $head->get_docid;
+ my $doc = $db->get_document($doc_id);
+ load_expand(wrap($class, $doc, $mid))
+}
+
sub get_val ($$) {
my ($doc, $col) = @_;
Search::Xapian::sortable_unserialise($doc->get_value($col));
}
-sub load_expand {
- my ($self) = @_;
- my $doc = $self->{doc};
- my $data = $doc->get_data or return;
- $self->{ts} = get_val($doc, &PublicInbox::Search::TS);
- utf8::decode($data);
- my ($subj, $from, $refs, $to, $cc, $blob) = split(/\n/, $data);
+sub load_from_data ($$) {
+ my ($self) = $_[0]; # data = $_[1]
+ my ($subj, $from, $refs, $to, $cc, $blob, $mid0) = split(/\n/, $_[1]);
$self->{subject} = $subj;
$self->{from} = $from;
$self->{references} = $refs;
+
+ # To: and Cc: are stored to optimize HDR/XHDR in NNTP since
+ # some NNTP clients will use that for message displays.
$self->{to} = $to;
$self->{cc} = $cc;
+
$self->{blob} = $blob;
+ $self->{mid} = $mid0;
+}
+
+sub load_expand {
+ my ($self) = @_;
+ my $doc = $self->{doc};
+ my $data = $doc->get_data or return;
+ $self->{ts} = get_val($doc, &PublicInbox::Search::TS);
+ $self->{ds} = get_val($doc, &PublicInbox::Search::DS);
+ utf8::decode($data);
+ load_from_data($self, $data);
$self;
}
sub load_doc {
my ($class, $doc) = @_;
- my $data = $doc->get_data or return;
- my $ts = get_val($doc, &PublicInbox::Search::TS);
- utf8::decode($data);
- my ($subj, $from, $refs, $to, $cc, $blob) = split(/\n/, $data);
- bless {
- doc => $doc,
- subject => $subj,
- ts => $ts,
- from => $from,
- references => $refs,
- to => $to,
- cc => $cc,
- blob => $blob,
- }, $class;
+ my $self = bless { doc => $doc }, $class;
+ $self->load_expand;
}
# :bytes and :lines metadata in RFC 3977
sub bytes ($) { get_val($_[0]->{doc}, &PublicInbox::Search::BYTES) }
sub lines ($) { get_val($_[0]->{doc}, &PublicInbox::Search::LINES) }
-sub num ($) { get_val($_[0]->{doc}, &PublicInbox::Search::NUM) }
+sub num ($) {
+ $_[0]->{num} ||= get_val($_[0]->{doc}, PublicInbox::Search::NUM())
+}
sub __hdr ($$) {
my ($self, $field) = @_;
sub date ($) {
my ($self) = @_;
- my $ts = $self->{ts};
- return unless defined $ts;
- my ($sec, $min, $hour, $mday, $mon, $year, $wday) = gmtime($ts);
+ my $ds = $self->{ds};
+ return unless defined $ds;
+ my ($sec, $min, $hour, $mday, $mon, $year, $wday) = gmtime($ds);
"$DoW[$wday], " . sprintf("%02d $MoY[$mon] %04d %02d:%02d:%02d +0000",
$mday, $year+1900, $hour, $min, $sec);
sub ts {
my ($self) = @_;
- $self->{ts} ||= eval { str2time($self->{mime}->header('Date')) } || 0;
+ $self->{ts} ||= eval { msg_timestamp($self->{mime}->header_obj) } || 0;
+}
+
+sub ds {
+ my ($self) = @_;
+ $self->{ds} ||= eval { msg_datestamp($self->{mime}->header_obj); } || 0;
}
sub to_doc_data {
- my ($self, $blob) = @_;
+ my ($self, $oid, $mid0) = @_;
my @rows = ($self->subject, $self->from, $self->references,
$self->to, $self->cc);
- push @rows, $blob if defined $blob;
- join("\n", @rows);
+ $oid = '' unless defined $oid;
+ join("\n", @rows, $oid, $mid0);
}
sub references {
$self->{mid} = $mid;
} elsif (my $rv = $self->{mid}) {
$rv;
+ } elsif ($self->{doc}) {
+ $self->{mid} = _get_term_val($self, 'Q', qr/\AQ/);
} else {
- $self->{mid} = _get_term_val($self, 'Q', qr/\AQ/) ||
- $self->_extract_mid;
+ $self->_extract_mid; # v1 w/o Xapian
}
}
$self->{path} = _get_term_val($self, 'XPATH', qr/\AXPATH/); # path
}
+sub type {
+ my ($self) = @_;
+ my $type = $self->{type};
+ return $type if defined $type;
+ $self->{type} = _get_term_val($self, 'T', qr/\AT/);
+}
+
1;