treewide: run update-copyrights from gnulib for 2019

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

diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index cc9bd7d483650d138b8f388193345c229b2b977c..0549c68b6c88d253595efab25faca47c375b325f 100644 (file)
--- 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::SearchMsg 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);
@@ -230,13 +230,21 @@ sub parse_references ($$$) {
                        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!;
@@ -247,12 +255,12 @@ sub add_overview {
                lines => $lines,
                blob => $oid,
        }, 'PublicInbox::SearchMsg';
-       my $mids = mids($mime->header_obj);
+       my $mids = mids_for_index($mime->header_obj);
        my $refs = parse_references($smsg, $mid0, $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);
@@ -311,20 +319,35 @@ 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 {