-# 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 mid_compress/;
-use Encode qw/find_encoding/;
-my $enc_utf8 = find_encoding('UTF-8');
-our $PFX2TERM_RE = undef;
+use PublicInbox::MID qw/mid_clean/;
+use PublicInbox::Address;
sub new {
my ($class, $mime) = @_;
my $doc = Search::Xapian::Document->new;
- $doc->add_term(PublicInbox::Search::xpfx('type') . 'mail');
+ $doc->add_term('T' . 'mail');
bless { type => 'mail', doc => $doc, mime => $mime }, $class;
}
bless { doc => $doc, mime => undef, mid => $mid }, $class;
}
+sub get_val ($$) {
+ my ($doc, $col) = @_;
+ Search::Xapian::sortable_unserialise($doc->get_value($col));
+}
+
+sub load_expand {
+ my ($self) = @_;
+ my $doc = $self->{doc};
+ my $data = $doc->get_data or return;
+ $self->{ts} = get_val($doc, &PublicInbox::Search::TS);
+ utf8::decode($data);
+ my ($subj, $from, $refs, $to, $cc, $blob) = split(/\n/, $data);
+ $self->{subject} = $subj;
+ $self->{from} = $from;
+ $self->{references} = $refs;
+ $self->{to} = $to;
+ $self->{cc} = $cc;
+ $self->{blob} = $blob;
+ $self;
+}
+
sub load_doc {
my ($class, $doc) = @_;
- my $data = $doc->get_data;
- $data = $enc_utf8->decode($data);
- my ($mid, $subj, $from, $date, $refs) = split(/\n/, $data);
+ my $data = $doc->get_data or return;
+ my $ts = get_val($doc, &PublicInbox::Search::TS);
+ utf8::decode($data);
+ my ($subj, $from, $refs, $to, $cc, $blob) = split(/\n/, $data);
bless {
doc => $doc,
- mid => $mid,
subject => $subj,
- date => $date,
- from_name => $from,
- references_sorted => $refs,
+ ts => $ts,
+ from => $from,
+ references => $refs,
+ to => $to,
+ cc => $cc,
+ blob => $blob,
}, $class;
}
-sub subject {
+# :bytes and :lines metadata in RFC 3977
+sub bytes ($) { get_val($_[0]->{doc}, &PublicInbox::Search::BYTES) }
+sub lines ($) { get_val($_[0]->{doc}, &PublicInbox::Search::LINES) }
+sub num ($) { get_val($_[0]->{doc}, &PublicInbox::Search::NUM) }
+
+sub __hdr ($$) {
+ 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($_[0], 'cc') }
+
+# no strftime, that is locale-dependent and not for RFC822
+my @DoW = qw(Sun Mon Tue Wed Thu Fri Sat);
+my @MoY = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
+
+sub date ($) {
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 $ts = $self->{ts};
+ return unless defined $ts;
+ my ($sec, $min, $hour, $mday, $mon, $year, $wday) = gmtime($ts);
+ "$DoW[$wday], " . sprintf("%02d $MoY[$mon] %04d %02d:%02d:%02d +0000",
+ $mday, $year+1900, $hour, $min, $sec);
+
}
-sub from {
+sub from ($) {
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};
+ $from;
}
sub from_name {
sub ts {
my ($self) = @_;
- my $ts = $self->{ts};
- return $ts if $ts;
- $self->{ts} = eval {
- str2time($self->date || $self->mime->header('Date'))
- } || 0;
-}
-
-sub date {
- my ($self) = @_;
- my $date = $self->{date};
- return $date if $date;
- my $ts = eval { str2time($self->mime->header('Date')) };
- $self->{date} = POSIX::strftime('%Y-%m-%d %H:%M', gmtime($ts));
+ $self->{ts} ||= eval { str2time($self->{mime}->header('Date')) } || 0;
}
sub to_doc_data {
- my ($self) = @_;
- $self->mid . "\n" .
- PublicInbox::Search::subject_summary($self->subject) . "\n" .
- $self->from_name . "\n".
- $self->date . "\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 ? $x : '';
}
-sub ensure_metadata {
- my ($self) = @_;
+sub _get_term_val ($$$) {
+ my ($self, $pfx, $re) = @_;
my $doc = $self->{doc};
my $end = $doc->termlist_end;
-
- unless (defined $PFX2TERM_RE) {
- my $or = join('|', keys %PublicInbox::Search::PFX2TERM_RMAP);
- $PFX2TERM_RE = qr/\A($or)/;
- }
-
- 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) {
- $self->{$field} = $val;
- }
- }
+ my $i = $doc->termlist_begin;
+ $i->skip_to($pfx);
+ if ($i != $end) {
+ my $val = $i->get_termname;
+ $val =~ s/$re// and return $val;
}
+ undef;
}
-# for threading only
-sub mini_mime {
- my ($self) = @_;
- $self->ensure_metadata;
- my @h = (
- Subject => $self->subject,
- 'X-PI-From' => $self->from_name,
- 'X-PI-Date' => $self->date,
- 'X-PI-TS' => $self->ts,
- 'Message-ID' => "<$self->{mid}>",
- );
-
- my $refs = $self->{references_sorted};
- my $mime = Email::MIME->create(header_str => \@h);
- $mime->header_set('References', $refs) if (defined $refs);
- $mime;
-}
-
-sub mid {
+sub mid ($;$) {
my ($self, $mid) = @_;
if (defined $mid) {
$self->{mid} = $mid;
+ } elsif (my $rv = $self->{mid}) {
+ $rv;
} else {
- $self->ensure_metadata; # needed for ghosts
- $self->{mid} ||= $self->_extract_mid;
+ $self->{mid} = _get_term_val($self, 'Q', qr/\AQ/) ||
+ $self->_extract_mid;
}
}
-sub _extract_mid {
- my ($self) = @_;
-
- my $mid = $self->mime->header('Message-ID');
- $mid ? mid_compress(mid_clean($mid)) : $mid;
-}
-
-sub mime {
- my ($self, $mime) = @_;
- if (defined $mime) {
- $self->{mime} = $mime;
- } else {
- # TODO load from git
- $self->{mime};
- }
-}
-
-sub doc_id {
- my ($self, $doc_id) = @_;
- if (defined $doc_id) {
- $self->{doc_id} = $doc_id;
- } else {
- # TODO load from xapian
- $self->{doc_id};
- }
-}
+sub _extract_mid { mid_clean(mid_mime($_[0]->{mime})) }
sub thread_id {
my ($self) = @_;
my $tid = $self->{thread};
return $tid if defined $tid;
- $self->ensure_metadata;
- $self->{thread};
+ $self->{thread} = _get_term_val($self, 'G', qr/\AG/); # *G*roup
}
+# XXX: consider removing this, we can phrase match subject
sub path {
my ($self) = @_;
my $path = $self->{path};
return $path if defined $path;
- $self->ensure_metadata;
- $self->{path};
+ $self->{path} = _get_term_val($self, 'XPATH', qr/\AXPATH/); # path
}
1;