-# Copyright (C) 2015, all contributors <meta@public-inbox.org>
-# License: GPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# Copyright (C) 2015-2018 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
+#
+# Wraps a document inside our Xapian search index.
+# There may be many of these objects loaded in memory at once
+# for large threads in our WWW UI.
package PublicInbox::SearchMsg;
use strict;
use warnings;
-use Search::Xapian;
-our $PFX2TERM_RE = undef;
+use base qw(Exporter);
+our @EXPORT_OK = qw(subject_normalized);
+use PublicInbox::MID qw/mid_clean mid_mime/;
+use PublicInbox::Address;
+use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
+use Time::Local qw(timegm);
sub new {
my ($class, $mime) = @_;
- my $doc = Search::Xapian::Document->new;
- $doc->add_term(PublicInbox::Search::xpfx('type') . 'mail');
-
- bless { type => 'mail', doc => $doc, mime => $mime }, $class;
+ bless { mime => $mime }, $class;
}
sub wrap {
- my ($class, $doc, $mid) = @_;
- bless { doc => $doc, mime => undef, mid => $mid }, $class;
+ my ($class, $mid) = @_;
+ bless { mid => $mid }, $class;
}
-sub ensure_metadata {
- my ($self) = @_;
- my $doc = $self->{doc};
- my $i = $doc->termlist_begin;
- my $end = $doc->termlist_end;
+sub get_val ($$) {
+ my ($doc, $col) = @_;
+ Search::Xapian::sortable_unserialise($doc->get_value($col));
+}
- unless (defined $PFX2TERM_RE) {
- my $or = join('|', keys %PublicInbox::Search::PFX2TERM_RMAP);
- $PFX2TERM_RE = qr/\A($or)/;
- }
+sub to_doc_data {
+ my ($self, $oid, $mid0) = @_;
+ $oid = '' unless defined $oid;
+ join("\n",
+ $self->subject,
+ $self->from,
+ $self->references,
+ $self->to,
+ $self->cc,
+ $oid,
+ $mid0,
+ $self->{bytes} || '',
+ $self->{lines} || ''
+ );
+}
- for (; $i != $end; $i->inc) {
- my $val = $i->get_termname;
-
- if ($val =~ s/$PFX2TERM_RE//o) {
- my $field = $PublicInbox::Search::PFX2TERM_RMAP{$1};
- if ($field eq 'references') {
- my $refs = $self->{references} ||= [];
- push @$refs, $val;
- } else {
- $self->{$field} = $val;
- }
- }
- }
+sub load_from_data ($$) {
+ my ($self) = $_[0]; # data = $_[1]
+ (
+ $self->{subject},
+ $self->{from},
+ $self->{references},
+
+ # To: and Cc: are stored to optimize HDR/XHDR in NNTP since
+ # some NNTP clients will use that for message displays.
+ # NNTP only, and only stored in Over(view), not Xapian
+ $self->{to},
+ $self->{cc},
+
+ $self->{blob},
+ $self->{mid},
+
+ # NNTP only
+ $self->{bytes},
+ $self->{lines}
+ ) = split(/\n/, $_[1]);
}
-sub mid {
- my ($self, $mid) = @_;
+sub load_expand {
+ my ($self, $doc) = @_;
+ my $data = $doc->get_data or return;
+ $self->{ts} = get_val($doc, PublicInbox::Search::TS());
+ my $dt = get_val($doc, PublicInbox::Search::DT());
+ my ($yyyy, $mon, $dd, $hh, $mm, $ss) = unpack('A4A2A2A2A2A2', $dt);
+ $self->{ds} = timegm($ss, $mm, $hh, $dd, $mon - 1, $yyyy);
+ utf8::decode($data);
+ load_from_data($self, $data);
+ $self;
+}
- if (defined $mid) {
- $self->{mid} = $mid;
- } else {
- $self->{mid} ||= $self->_extract_mid;
- }
+sub psgi_cull ($) {
+ my ($self) = @_;
+ from_name($self); # fill in {from_name} so we can delete {from}
+
+ # drop NNTP-only fields which aren't relevant to PSGI results:
+ # saves ~80K on a 200 item search result:
+ delete @$self{qw(from ts to cc bytes lines)};
+ $self;
+}
+
+# Only called by PSGI interface, not NNTP
+sub load_doc {
+ my ($class, $doc) = @_;
+ my $self = bless {}, $class;
+ psgi_cull(load_expand($self, $doc));
}
-sub _extract_mid {
+# :bytes and :lines metadata in RFC 3977
+sub bytes ($) { $_[0]->{bytes} }
+sub lines ($) { $_[0]->{lines} }
+
+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\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 $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);
- my $mid = $self->mime->header('Message-ID');
- if ($mid && $mid =~ /<([^>]+)>/) {
- return $1;
- }
- return $mid;
}
-sub mime {
- my ($self, $mime) = @_;
- if (defined $mime) {
- $self->{mime} = $mime;
- } else {
- # TODO load from git
- $self->{mime};
+sub from ($) {
+ my ($self) = @_;
+ my $from = __hdr($self, 'from');
+ if (defined $from && !defined $self->{from_name}) {
+ my @n = PublicInbox::Address::names($from);
+ $self->{from_name} = join(', ', @n);
}
+ $from;
}
-sub doc_id {
- my ($self, $doc_id) = @_;
- if (defined $doc_id) {
- $self->{doc_id} = $doc_id;
- } else {
- # TODO load from xapian
- $self->{doc_id};
- }
+sub from_name {
+ my ($self) = @_;
+ my $from_name = $self->{from_name};
+ return $from_name if defined $from_name;
+ $self->from;
+ $self->{from_name};
}
-sub thread_id {
+sub ts {
my ($self) = @_;
- my $tid = $self->{thread};
- return $tid if defined $tid;
- $self->ensure_metadata;
- $self->{thread};
+ $self->{ts} ||= eval { msg_timestamp($self->{mime}->header_obj) } || 0;
}
-sub path {
+sub ds {
my ($self) = @_;
- my $path = $self->{path};
- return $path if defined $path;
- $self->ensure_metadata;
- $self->{path};
+ $self->{ds} ||= eval { msg_datestamp($self->{mime}->header_obj); } || 0;
+}
+
+sub references {
+ my ($self) = @_;
+ my $x = $self->{references};
+ defined $x ? $x : '';
+}
+
+sub mid ($;$) {
+ my ($self, $mid) = @_;
+
+ if (defined $mid) {
+ $self->{mid} = $mid;
+ } elsif (defined(my $rv = $self->{mid})) {
+ $rv;
+ } else {
+ die "NO {mime} for mid\n" unless $self->{mime};
+ $self->_extract_mid; # v1 w/o Xapian
+ }
+}
+
+sub _extract_mid { mid_clean(mid_mime($_[0]->{mime})) }
+
+our $REPLY_RE = qr/^re:\s+/i;
+
+sub subject_normalized ($) {
+ my ($subj) = @_;
+ $subj =~ s/\A\s+//s; # no leading space
+ $subj =~ s/\s+\z//s; # no trailing space
+ $subj =~ s/\s+/ /gs; # no redundant spaces
+ $subj =~ s/\.+\z//; # no trailing '.'
+ $subj =~ s/$REPLY_RE//igo; # remove reply prefix
+ $subj;
}
1;