X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FOverIdx.pm;h=acbf2c8de6092742e10cdda77415812cbf6778d6;hb=b5bc3576af3d0ef0fa884ed32a674c7a703a19b2;hp=bb3068ddcb4b190bcd30f4e24158d962bfa04751;hpb=1b7e935ab1690e28d790d8db5af2714f13c258cc;p=public-inbox.git

diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index bb3068dd..acbf2c8d 100644
--- a/lib/PublicInbox/OverIdx.pm
+++ b/lib/PublicInbox/OverIdx.pm
@@ -1,4 +1,4 @@
-# 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
@@ -13,14 +13,14 @@ use warnings;
 use base qw(PublicInbox::Over);
 use IO::Handle;
 use DBI qw(:sql_types); # SQL_BLOB
-use PublicInbox::MID qw/id_compress mids references/;
-use PublicInbox::SearchMsg;
+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);
@@ -215,51 +215,51 @@ sub link_refs {
 }
 
 sub parse_references ($$$) {
-	my ($smsg, $mid0, $mids) = @_;
-	my $mime = $smsg->{mime};
-	my $hdr = $mime->header_obj;
+	my ($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 = ( $mid0 => 1 );
+	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;
 		}
-		next if $seen{$ref}++;
-		push @keep, $ref;
+		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, $bytes, $num, $oid, $mid0) = @_;
-	my $lines = $mime->body_raw =~ tr!\n!\n!;
-	my $smsg = bless {
-		mime => $mime,
-		mid => $mid0,
-		bytes => $bytes,
-		lines => $lines,
-		blob => $oid,
-	}, 'PublicInbox::SearchMsg';
-	my $mids = mids($mime->header_obj);
-	my $refs = parse_references($smsg, $mid0, $mids);
+	my ($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 '') {
-		$xpath = PublicInbox::Search::subject_path($subj);
+		$xpath = subject_path($subj);
 		$xpath = id_compress($xpath);
 	}
-	my $dd = $smsg->to_doc_data($oid, $mid0);
+	my $dd = $smsg->to_doc_data;
 	utf8::encode($dd);
 	$dd = compress($dd);
-	my $values = [ $smsg->ts, $smsg->ds, $num, $mids, $refs, $xpath, $dd ];
-	add_over($self, $values);
+	add_over($self, [ @$smsg{qw(ts ds num)}, $mids, $refs, $xpath, $dd ]);
 }
 
 sub add_over {
@@ -311,12 +311,6 @@ 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 {
@@ -334,6 +328,20 @@ sub remove_oid {
 	$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, $mid0);
+}
+
 sub create_tables {
 	my ($dbh) = @_;