X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchMsg.pm;h=adadf92ed097e8a1b23d11068faa8cebf0237783;hb=9bd675d33ad1e49bd2ebe12a1d216216e61380de;hp=5a2ca83bd1f67fcff365b8b986c8300bbde614a0;hpb=bbb8c7788ebaa7f3679d387725ee1998f0b2f615;p=public-inbox.git

diff --git a/lib/PublicInbox/SearchMsg.pm b/lib/PublicInbox/SearchMsg.pm
index 5a2ca83b..adadf92e 100644
--- a/lib/PublicInbox/SearchMsg.pm
+++ b/lib/PublicInbox/SearchMsg.pm
@@ -1,11 +1,15 @@
-# 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);
@@ -13,20 +17,12 @@ use Time::Local qw(timegm);
 
 sub new {
 	my ($class, $mime) = @_;
-	my $doc = Search::Xapian::Document->new;
-	bless { doc => $doc, mime => $mime }, $class;
+	bless { mime => $mime }, $class;
 }
 
 sub wrap {
-	my ($class, $doc, $mid) = @_;
-	bless { doc => $doc, mime => undef, mid => $mid }, $class;
-}
-
-sub get {
-	my ($class, $head, $db, $mid) = @_;
-	my $doc_id = $head->get_docid;
-	my $doc = $db->get_document($doc_id);
-	load_expand(wrap($class, $doc, $mid))
+	my ($class, $mid) = @_;
+	bless { mid => $mid }, $class;
 }
 
 sub get_val ($$) {
@@ -59,19 +55,21 @@ sub load_from_data ($$) {
 
 		# 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 load_expand {
-	my ($self) = @_;
-	my $doc = $self->{doc};
+	my ($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());
@@ -82,10 +80,21 @@ sub load_expand {
 	$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 { doc => $doc }, $class;
-	$self->load_expand;
+	my $self = bless {}, $class;
+	psgi_cull(load_expand($self, $doc));
 }
 
 # :bytes and :lines metadata in RFC 3977
@@ -164,8 +173,6 @@ sub mid ($;$) {
 		$self->{mid} = $mid;
 	} elsif (defined(my $rv = $self->{mid})) {
 		$rv;
-	} elsif ($self->{doc}) {
-		die "SHOULD NOT HAPPEN\n";
 	} else {
 		die "NO {mime} for mid\n" unless $self->{mime};
 		$self->_extract_mid; # v1 w/o Xapian
@@ -174,4 +181,16 @@ sub mid ($;$) {
 
 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;