-# Copyright (C) 2015-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2019 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 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);
bless { mid => $mid }, $class;
}
-sub get {
- my ($class, $head, $db, $mid) = @_;
- my $doc_id = $head->get_docid;
- load_expand(wrap($class, $mid), $db->get_document($doc_id));
-}
-
sub get_val ($$) {
my ($doc, $col) = @_;
Search::Xapian::sortable_unserialise($doc->get_value($col));
$self;
}
+sub psgi_cull ($) {
+ 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;
- my $smsg = load_expand($self, $doc);
-
- from_name($smsg); # 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 @$smsg{qw(from ts to cc bytes lines)};
- $smsg;
+ psgi_cull(load_expand($self, $doc));
}
# :bytes and :lines metadata in RFC 3977
sub _extract_mid { mid_clean(mid_mime($_[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;