+sub mark_deleted {
+ my ($self, $D, $git, $oid) = @_;
+ my $msgref = $git->cat_file($oid);
+ my $mime = PublicInbox::MIME->new($$msgref);
+ my $mids = mids($mime->header_obj);
+ my $cid = content_id($mime);
+ foreach my $mid (@$mids) {
+ $D->{"$mid\0$cid"} = 1;
+ }
+}
+
+sub reindex_oid {
+ my ($self, $mm_tmp, $D, $git, $oid, $regen) = @_;
+ my $len;
+ my $msgref = $git->cat_file($oid, \$len);
+ my $mime = PublicInbox::MIME->new($$msgref);
+ my $mids = mids($mime->header_obj);
+ my $cid = content_id($mime);
+
+ # get the NNTP article number we used before, highest number wins
+ # and gets deleted from mm_tmp;
+ my $mid0;
+ my $num = -1;
+ my $del = 0;
+ foreach my $mid (@$mids) {
+ $del += (delete $D->{"$mid\0$cid"} || 0);
+ my $n = $mm_tmp->num_for($mid);
+ if (defined $n && $n > $num) {
+ $mid0 = $mid;
+ $num = $n;
+ }
+ }
+ if (!defined($mid0) && $regen && !$del) {
+ $num = $$regen--;
+ die "BUG: ran out of article numbers\n" if $num <= 0;
+ my $mm = $self->{skel}->{mm};
+ foreach my $mid (reverse @$mids) {
+ if ($mm->mid_set($num, $mid) == 1) {
+ $mid0 = $mid;
+ last;
+ }
+ }
+ if (!defined($mid0)) {
+ my $id = '<' . join('> <', @$mids) . '>';
+ warn "Message-ID $id unusable for $num\n";
+ foreach my $mid (@$mids) {
+ defined(my $n = $mm->num_for($mid)) or next;
+ warn "#$n previously mapped for <$mid>\n";
+ }
+ }
+ }
+
+ if (!defined($mid0) || $del) {
+ if (!defined($mid0) && $del) { # expected for deletes
+ $$regen--;
+ return
+ }
+
+ my $id = '<' . join('> <', @$mids) . '>';
+ defined($mid0) or
+ warn "Skipping $id, no article number found\n";
+ if ($del && defined($mid0)) {
+ warn "$id was deleted $del " .
+ "time(s) but mapped to article #$num\n";
+ }
+ return;
+
+ }
+ $mm_tmp->mid_delete($mid0) or
+ die "failed to delete <$mid0> for article #$num\n";
+
+ my $nparts = $self->{partitions};
+ my $part = $num % $nparts;
+ my $idx = $self->idx_part($part);
+ $idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime);
+ my $n = $self->{transact_bytes} += $len;
+ if ($n > (PublicInbox::SearchIdx::BATCH_BYTES * $nparts)) {
+ $git->cleanup;
+ $mm_tmp->atfork_prepare;
+ $self->done; # release lock
+ # allow -watch or -mda to write...
+ $self->idx_init; # reacquire lock
+ $mm_tmp->atfork_parent;
+ }
+}
+
+sub reindex {
+ my ($self, $regen) = @_;
+ my $ibx = $self->{-inbox};
+ my $pfx = "$ibx->{mainrepo}/git";
+ my $max_git;
+ my $latest = git_dir_latest($self, \$max_git);
+ return unless defined $latest;
+ my $head = $ibx->{ref_head} || 'refs/heads/master';
+ $self->idx_init; # acquire lock
+ my $x40 = qr/[a-f0-9]{40}/;
+ my $mm_tmp = $self->{skel}->{mm}->tmp_clone;
+ if (!$regen) {
+ my (undef, $max) = $mm_tmp->minmax;
+ unless (defined $max) {
+ $regen = 1;
+ warn
+"empty msgmap.sqlite3, regenerating article numbers\n";
+ }
+ }
+ my $tip; # latest commit out of all git repos
+ if ($regen) {
+ my $regen_max = 0;
+ for (my $cur = $max_git; $cur >= 0; $cur--) {
+ die "already reindexing!\n" if $self->{reindex_pipe};
+ my $git = PublicInbox::Git->new("$pfx/$cur.git");
+ -d $git->{git_dir} or next; # missing parts are fine
+ chomp($tip = $git->qx('rev-parse', $head)) unless $tip;
+ my $h = $cur == $max_git ? $tip : $head;
+ my @count = ('rev-list', '--count', $h, '--', 'm');
+ $regen_max += $git->qx(@count);
+ }
+ die "No messages found in $pfx/*.git, bug?\n" unless $regen_max;
+ $regen = \$regen_max;
+ }
+ my $D = {};
+ my @cmd = qw(log --raw -r --pretty=tformat:%h
+ --no-notes --no-color --no-abbrev);
+
+ # if we are regenerating, we must not use a newer tip commit than what
+ # the regeneration counter used:
+ $tip ||= $head;
+
+ # work backwards through history
+ for (my $cur = $max_git; $cur >= 0; $cur--) {
+ die "already reindexing!\n" if delete $self->{reindex_pipe};
+ my $cmt;
+ my $git_dir = "$pfx/$cur.git";
+ -d $git_dir or next; # missing parts are fine
+ my $git = PublicInbox::Git->new($git_dir);
+ my $h = $cur == $max_git ? $tip : $head;
+ my $fh = $self->{reindex_pipe} = $git->popen(@cmd, $h);
+ while (<$fh>) {
+ if (/\A$x40$/o) {
+ chomp($cmt = $_);
+ } elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\tm$/o) {
+ $self->reindex_oid($mm_tmp, $D, $git, $1,
+ $regen);
+ } elsif (m!\A:\d{6} 100644 $x40 ($x40) [AM]\t_/D$!o) {
+ $self->mark_deleted($D, $git, $1);
+ }
+ }
+ delete $self->{reindex_pipe};
+ }
+ my $gaps;
+ if ($regen && $$regen != 0) {
+ warn "W: leftover article number ($$regen)\n";
+ $gaps = 1;
+ }
+ my ($min, $max) = $mm_tmp->minmax;
+ if (defined $max) {
+ warn "W: leftover article numbers at $min..$max\n";
+ $gaps = 1;
+ }
+ warn "W: were old git partitions deleted?\n" if $gaps;
+ my @d = sort keys %$D;
+ if (@d) {
+ warn "BUG: ", scalar(@d)," unseen deleted messages marked\n";
+ foreach (@d) {
+ my ($mid, undef) = split(/\0/, $_, 2);
+ warn "<$mid>\n";
+ }
+ }
+}
+