treewide: run update-copyrights from gnulib for 2019

[public-inbox.git] / lib / PublicInbox / SearchMsg.pm

diff --git a/lib/PublicInbox/SearchMsg.pm b/lib/PublicInbox/SearchMsg.pm
index 722a1b9428fba760591452f67a044a1af8ba812d..42384936b923364bb17fc515bd6b39c0d83bc35e 100644 (file)
--- 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) 2015-2020 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);
@@ -21,15 +25,10 @@ sub wrap {
        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($col));
+       # sortable_unserialise is defined by PublicInbox::Search::load_xapian()
+       sortable_unserialise($doc->get_value($col));
 }
 
 sub to_doc_data {
@@ -93,10 +92,11 @@ sub psgi_cull ($) {
 }
 
 # Only called by PSGI interface, not NNTP
-sub load_doc {
-       my ($class, $doc) = @_;
-       my $self = bless {}, $class;
-       psgi_cull(load_expand($self, $doc));
+sub from_mitem {
+       my ($mitem, $srch) = @_;
+       return $srch->retry_reopen(\&from_mitem, $mitem) if $srch;
+       my $self = bless {}, __PACKAGE__;
+       psgi_cull(load_expand($self, $mitem->get_document));
 }
 
 # :bytes and :lines metadata in RFC 3977
@@ -109,8 +109,8 @@ sub __hdr ($$) {
        return $val if defined $val;
 
        my $mime = $self->{mime} or return;
-       $val = $mime->header($field);
-       $val = '' unless defined $val;
+       my @raw = $mime->header($field);
+       $val = join(', ', @raw);
        $val =~ tr/\t\n/  /;
        $val =~ tr/\r//d;
        $self->{$field} = $val;
@@ -183,4 +183,16 @@ sub mid ($;$) {
 
 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;