v2: one file, really

[public-inbox.git] / lib / PublicInbox / V2Writable.pm

diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 6394d300fa2eb8e8d6f0287eaa7935c9233194f2..c8869bda3cf669b1de9428a570ce6ea0c5f6e2f0 100644 (file)
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -50,6 +50,7 @@ sub new {
        }
        $nparts = nproc() if ($nparts == 0);
 
+       $v2ibx = PublicInbox::InboxWritable->new($v2ibx);
        my $self = {
                -inbox => $v2ibx,
                im => undef, #  PublicInbox::Import
@@ -137,7 +138,7 @@ sub num_for {
                warn "<$mid> reused for mismatched content\n";
 
                # try the rest of the mids
-               foreach my $i (1..$#$mids) {
+               for(my $i = $#$mids; $i >= 1; $i--) {
                        my $m = $mids->[$i];
                        $num = $self->{skel}->{mm}->mid_insert($m);
                        if (defined $num) {
@@ -193,20 +194,23 @@ sub idx_init {
        # frequently activated.
        delete $ibx->{$_} foreach (qw(git mm search));
 
-       $self->lock_acquire;
+       $ibx->umask_prepare;
+       $ibx->with_umask(sub {
+               $self->lock_acquire;
 
-       # first time initialization, first we create the skeleton pipe:
-       my $skel = $self->{skel} = PublicInbox::SearchIdxSkeleton->new($self);
+               # first time initialization, first we create the skeleton pipe:
+               my $skel = PublicInbox::SearchIdxSkeleton->new($self);
+               $self->{skel} = $skel;
 
-       # need to create all parts before initializing msgmap FD
-       my $max = $self->{partitions} - 1;
-       my $idx = $self->{idx_parts} = [];
-       for my $i (0..$max) {
-               push @$idx, PublicInbox::SearchIdxPart->new($self, $i, $skel);
-       }
+               # need to create all parts before initializing msgmap FD
+               my $max = $self->{partitions} - 1;
+               @{$self->{idx_parts}} = map {
+                       PublicInbox::SearchIdxPart->new($self, $_, $skel);
+               } (0..$max);
 
-       # Now that all subprocesses are up, we can open the FD for SQLite:
-       $skel->_msgmap_init->{dbh}->begin_work;
+               # Now that all subprocesses are up, we can open the FD for SQLite:
+               $skel->_msgmap_init->{dbh}->begin_work;
+       });
 }
 
 sub purge_oids {
@@ -552,7 +556,7 @@ sub reindex_oid {
                $num = $$regen--;
                die "BUG: ran out of article numbers\n" if $num <= 0;
                my $mm = $self->{skel}->{mm};
-               foreach my $mid (@$mids) {
+               foreach my $mid (reverse @$mids) {
                        if ($mm->mid_set($num, $mid) == 1) {
                                $mid0 = $mid;
                                last;
@@ -560,7 +564,11 @@ sub reindex_oid {
                }
                if (!defined($mid0)) {
                        my $id = '<' . join('> <', @$mids) . '>';
-                       warn "Message-Id $id unusable for $num\n";
+                       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";
+                       }
                }
        }
 
@@ -626,15 +634,19 @@ sub reindex {
                        -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);
+
+                       # can't use 'rev-list --count' if we use --diff-filter
+                       my $fh = $git->popen(qw(log --pretty=tformat:%h
+                                       --no-notes --no-color --no-renames
+                                       --diff-filter=AM), $h, '--', 'm');
+                       ++$regen_max while <$fh>;
                }
                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);
+                       --no-notes --no-color --no-abbrev --no-renames);
 
        # if we are regenerating, we must not use a newer tip commit than what
        # the regeneration counter used:
@@ -655,14 +667,23 @@ sub reindex {
                        } 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) {
+                       } elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\td$/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;
-       defined $max and die "leftover article numbers at $min..$max\n";
+       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";