-# 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 Email::Simple 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');
+use PublicInbox::Address;
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 ($$) {
+ my ($doc, $col) = @_;
+ Search::Xapian::sortable_unserialise($doc->get_value($col));
+}
+
sub load_doc {
my ($class, $doc) = @_;
- my $data = $doc->get_data;
- my $ts = eval {
- no strict 'subs';
- $doc->get_value(PublicInbox::Search::TS);
- };
- $ts = Search::Xapian::sortable_unserialise($ts);
- $data = $enc_utf8->decode($data);
- my ($subj, $from, $refs) = split(/\n/, $data);
+ my $data = $doc->get_data or return;
+ my $ts = get_val($doc, &PublicInbox::Search::TS);
+ utf8::decode($data);
+ my ($subj, $from, $refs, $to, $cc, $blob) = split(/\n/, $data);
bless {
doc => $doc,
subject => $subj,
ts => $ts,
- from_name => $from,
- references_sorted => $refs,
+ from => $from,
+ references => $refs,
+ to => $to,
+ cc => $cc,
+ blob => $blob,
}, $class;
}
-sub subject {
+# :bytes and :lines metadata in RFC 3977
+sub bytes ($) { get_val($_[0]->{doc}, &PublicInbox::Search::BYTES) }
+sub lines ($) { get_val($_[0]->{doc}, &PublicInbox::Search::LINES) }
+sub num ($) { get_val($_[0]->{doc}, &PublicInbox::Search::NUM) }
+
+sub __hdr ($$) {
+ 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/\n/ /;
+ $val =~ tr/\r//d;
+ $self->{$field} = $val;
+}
+
+sub subject ($) { __hdr($_[0], 'subject') }
+sub to ($) { __hdr($_[0], 'to') }
+sub cc ($) { __hdr($_[0], 'cc') }
+
+sub date ($) {
my ($self) = @_;
- my $subj = $self->{subject};
- return $subj if defined $subj;
- $subj = $self->{mime}->header('Subject');
- $subj = '' unless defined $subj;
- $subj =~ tr/\n/ /;
- $self->{subject} = $subj;
+ my $date = __hdr($self, 'date');
+ return $date if defined $date;
+ my $ts = $self->{ts};
+ return unless defined $ts;
+ $self->{date} = strftime('%a, %d %b %Y %T +0000', gmtime($ts));
}
-sub from {
+sub from ($) {
my ($self) = @_;
- my $from = $self->mime->header('From') || '';
- my @from;
-
- if ($from) {
- $from =~ tr/\n/ /;
- @from = Email::Address->parse($from);
- $self->{from} = $from[0];
- $from = $from[0]->name;
+ my $from = __hdr($self, 'from');
+ if (defined $from && !defined $self->{from_name}) {
+ my @n = PublicInbox::Address::names($from);
+ $self->{from_name} = join(', ', @n);
}
- $self->{from_name} = $from;
- $self->{from};
+ $from;
}
sub from_name {
}
sub to_doc_data {
- my ($self) = @_;
- PublicInbox::Search::subject_summary($self->subject) . "\n" .
- $self->from_name . "\n".
- $self->references_sorted;
+ my ($self, $blob) = @_;
+ my @rows = ($self->subject, $self->from, $self->references,
+ $self->to, $self->cc);
+ push @rows, $blob if defined $blob;
+ join("\n", @rows);
}
-sub references_sorted {
+sub references {
my ($self) = @_;
- my $x = $self->{references_sorted};
+ my $x = $self->{references};
defined $x ? $x : '';
}
}
}
-# for threading only
-sub mini_mime {
- my ($self) = @_;
- $self->ensure_metadata;
- my @h = (
- Subject => $self->subject,
- 'X-PI-From' => $self->from_name,
- 'X-PI-TS' => $self->ts,
- 'Message-ID' => "<$self->{mid}>",
-
- # 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,
- );
-
- my $refs = $self->{references_sorted};
- my $mime = Email::MIME->create(header_str => \@h);
- my $h = $mime->header_obj;
- $h->header_set('References', $refs) if (defined $refs);
-
- # drop useless headers Email::MIME set for us
- $h->header_set('Date');
- $h->header_set('MIME-Version');
- $mime;
-}
-
-sub mid {
+sub mid ($;$) {
my ($self, $mid) = @_;
if (defined $mid) {
}
}
-sub _extract_mid {
- my ($self) = @_;
+sub _extract_mid { mid_clean(mid_mime($_[0]->mime)) }
- my $mid = $self->mime->header('Message-ID');
- defined $mid ? mid_clean($mid) : $mid;
+sub blob {
+ my ($self, $x40) = @_;
+ if (defined $x40) {
+ $self->{blob} = $x40;
+ } else {
+ $self->{blob};
+ }
}
sub mime {