X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FOverIdx.pm;h=acbf2c8de6092742e10cdda77415812cbf6778d6;hb=b5bc3576af3d0ef0fa884ed32a674c7a703a19b2;hp=28e4aa9c9b3f83865d8e8c19e23d112dbd8edf40;hpb=936670cb83971bf250571a7dd9b0a0a0b33babd8;p=public-inbox.git

diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index 28e4aa9c..acbf2c8d 100644
--- a/lib/PublicInbox/OverIdx.pm
+++ b/lib/PublicInbox/OverIdx.pm
@@ -1,19 +1,26 @@
-# Copyright (C) 2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # for XOVER, OVER in NNTP, and feeds/homepage/threads in PSGI
-# Unlike Msgmap, this is an _UNSTABLE_ database which can be
+# Unlike Msgmap, this is an _UNSTABLE_ cache which can be
 # tweaked/updated over time and rebuilt.
+#
+# Ghost messages (messages which are only referenced in References/In-Reply-To)
+# are denoted by a negative NNTP article number.
 package PublicInbox::OverIdx;
 use strict;
 use warnings;
 use base qw(PublicInbox::Over);
 use IO::Handle;
 use DBI qw(:sql_types); # SQL_BLOB
+use PublicInbox::MID qw/id_compress mids_for_index references/;
+use PublicInbox::Smsg qw(subject_normalized);
+use Compress::Zlib qw(compress);
+use PublicInbox::Search;
 
 sub dbh_new {
 	my ($self) = @_;
-	my $dbh = $self->SUPER::dbh_new;
+	my $dbh = $self->SUPER::dbh_new(1);
 	$dbh->do('PRAGMA journal_mode = TRUNCATE');
 	$dbh->do('PRAGMA cache_size = 80000');
 	create_tables($dbh);
@@ -72,8 +79,15 @@ sub mid2id {
 }
 
 sub delete_by_num {
-	my ($self, $num) = @_;
+	my ($self, $num, $tid_ref) = @_;
 	my $dbh = $self->{dbh};
+	if ($tid_ref) {
+		my $sth = $dbh->prepare_cached(<<'', undef, 1);
+SELECT tid FROM over WHERE num = ? LIMIT 1
+
+		$sth->execute($num);
+		$$tid_ref = $sth->fetchrow_array; # may be undef
+	}
 	foreach (qw(over id2num)) {
 		$dbh->prepare_cached(<<"")->execute($num);
 DELETE FROM $_ WHERE num = ?
@@ -200,6 +214,54 @@ sub link_refs {
 	$tid;
 }
 
+sub parse_references ($$$) {
+	my ($smsg, $hdr, $mids) = @_;
+	my $refs = references($hdr);
+	push(@$refs, @$mids) if scalar(@$mids) > 1;
+	return $refs if scalar(@$refs) == 0;
+
+	# prevent circular references here:
+	my %seen = ( $smsg->{mid} => 1 );
+	my @keep;
+	foreach my $ref (@$refs) {
+		if (length($ref) > PublicInbox::MID::MAX_MID_SIZE) {
+			warn "References: <$ref> too long, ignoring\n";
+			next;
+		}
+		push(@keep, $ref) unless $seen{$ref}++;
+	}
+	$smsg->{references} = '<'.join('> <', @keep).'>' if @keep;
+	\@keep;
+}
+
+# normalize subjects so they are suitable as pathnames for URLs
+# XXX: consider for removal
+sub subject_path ($) {
+	my ($subj) = @_;
+	$subj = subject_normalized($subj);
+	$subj =~ s![^a-zA-Z0-9_\.~/\-]+!_!g;
+	lc($subj);
+}
+
+sub add_overview {
+	my ($self, $mime, $smsg) = @_;
+	$smsg->{lines} = $mime->body_raw =~ tr!\n!\n!;
+	$smsg->{mime} = $mime; # XXX temporary?
+	my $hdr = $mime->header_obj;
+	my $mids = mids_for_index($hdr);
+	my $refs = parse_references($smsg, $hdr, $mids);
+	my $subj = $smsg->subject;
+	my $xpath;
+	if ($subj ne '') {
+		$xpath = subject_path($subj);
+		$xpath = id_compress($xpath);
+	}
+	my $dd = $smsg->to_doc_data;
+	utf8::encode($dd);
+	$dd = compress($dd);
+	add_over($self, [ @$smsg{qw(ts ds num)}, $mids, $refs, $xpath, $dd ]);
+}
+
 sub add_over {
 	my ($self, $values) = @_;
 	my ($ts, $ds, $num, $mids, $refs, $xpath, $ddd) = @$values;
@@ -207,7 +269,7 @@ sub add_over {
 	my $vivified = 0;
 
 	$self->begin_lazy;
-	$self->delete_by_num($num);
+	$self->delete_by_num($num, \$old_tid);
 	foreach my $mid (@$mids) {
 		my $v = 0;
 		each_by_mid($self, $mid, ['tid'], sub {
@@ -249,20 +311,35 @@ INSERT INTO id2num (id, num) VALUES (?,?)
 	}
 }
 
-sub delete_articles {
-	my ($self, $nums) = @_;
-	my $dbh = $self->connect;
-	$self->delete_by_num($_) foreach @$nums;
-}
-
+# returns number of removed messages
+# $oid may be undef to match only on $mid
 sub remove_oid {
 	my ($self, $oid, $mid) = @_;
+	my $nr = 0;
 	$self->begin_lazy;
 	each_by_mid($self, $mid, ['ddd'], sub {
 		my ($smsg) = @_;
-		$self->delete_by_num($smsg->{num}) if $smsg->{blob} eq $oid;
+		if (!defined($oid) || $smsg->{blob} eq $oid) {
+			$self->delete_by_num($smsg->{num});
+			$nr++;
+		}
 		1;
 	});
+	$nr;
+}
+
+sub num_mid0_for_oid {
+	my ($self, $oid, $mid) = @_;
+	my ($num, $mid0);
+	$self->begin_lazy;
+	each_by_mid($self, $mid, ['ddd'], sub {
+		my ($smsg) = @_;
+		my $blob = $smsg->{blob};
+		return 1 if (!defined($blob) || $blob ne $oid); # continue;
+		($num, $mid0) = ($smsg->{num}, $smsg->{mid});
+		0; # done
+	});
+	($num, $mid0);
 }
 
 sub create_tables {