v2writable: reindex handles 3-headered monsters

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

diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index cc9bd7d483650d138b8f388193345c229b2b977c..64277342a15e809f31ac1d12565c8f6d135c3d04 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) 2018-2019 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
@@ -14,7 +14,7 @@ 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::SearchMsg qw(subject_normalized);
 use Compress::Zlib qw(compress);
 use PublicInbox::Search;
 
@@ -237,6 +237,15 @@ sub parse_references ($$$) {
        \@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!;
@@ -252,7 +261,7 @@ sub add_overview {
        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);
@@ -317,14 +326,35 @@ sub delete_articles {
        $self->delete_by_num($_) 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 {