# 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);
# 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]);
$self;
}
+sub psgi_cull ($) {
+ 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 {}, $class;
- load_expand($self, $doc);
+ psgi_cull(load_expand($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;