-# 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 $PFX2TERM_RE = undef;
use constant EPOCH_822 => 'Thu, 01 Jan 1970 00:00:00 +0000';
use POSIX qw(strftime);
sub load_doc {
my ($class, $doc) = @_;
- my $data = $doc->get_data;
+ my $data = $doc->get_data or return;
my $ts = get_val($doc, &PublicInbox::Search::TS);
- $data = $enc_utf8->decode($data);
- my ($subj, $from, $refs, $to, $cc) = split(/\n/, $data);
+ utf8::decode($data);
+ my ($subj, $from, $refs, $to, $cc, $blob) = split(/\n/, $data);
bless {
doc => $doc,
subject => $subj,
references => $refs,
to => $to,
cc => $cc,
+ blob => $blob,
}, $class;
}
my $mime = $self->{mime} or return;
$val = $mime->header($field);
$val = '' unless defined $val;
- $val =~ tr/\t\r\n/ /;
+ $val =~ tr/\n/ /;
+ $val =~ tr/\r//d;
$self->{$field} = $val;
}
return $date if defined $date;
my $ts = $self->{ts};
return unless defined $ts;
- $self->{date} = strftime('%a, %d %b %Y %T %z', gmtime($ts));
+ $self->{date} = strftime('%a, %d %b %Y %T +0000', gmtime($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} = $from[0]->name;
+ my @n = PublicInbox::Address::names($from);
+ $self->{from_name} = join(', ', @n);
}
$from;
}
}
sub to_doc_data {
- my ($self) = @_;
- join("\n", $self->subject, $self->from, $self->references,
- $self->to, $self->cc);
+ my ($self, $blob) = @_;
+ my @rows = ($self->subject, $self->from, $self->references,
+ $self->to, $self->cc);
+ push @rows, $blob if defined $blob;
+ join("\n", @rows);
}
sub references {
}
}
-# for threading only
-sub mini_mime {
- my ($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, $mid) = @_;
}
}
-sub _extract_mid {
- my ($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 {