v2writable: warn on unseen deleted files

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

diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 605f68879ed2e2d5b0dd2e0f7920db2983ffb034..01ec98ac58c332655b0f31d38a1c551f784b21ae 100644 (file)
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -173,8 +173,7 @@ sub num_for_harder {
                        $num = $self->{skel}->{mm}->mid_insert($$mid0);
                }
        }
-       my @cur = $hdr->header_raw('Message-Id');
-       $hdr->header_set('Message-Id', "<$$mid0>", @cur);
+       PublicInbox::Import::prepend_mid($hdr, $$mid0);
        $num;
 }
 
@@ -223,6 +222,12 @@ sub remove {
        my $mm = $skel->{mm};
        my $removed;
        my $mids = mids($mime->header_obj);
+
+       # We avoid introducing new blobs into git since the raw content
+       # can be slightly different, so we do not need the user-supplied
+       # message now that we have the mids and content_id
+       $mime = undef;
+
        foreach my $mid (@$mids) {
                $srch->reopen->each_smsg_by_mid($mid, sub {
                        my ($smsg) = @_;
@@ -426,10 +431,11 @@ sub diff ($$$) {
        use File::Temp qw(tempfile);
        use PublicInbox::Spawn qw(spawn);
 
-       my ($ah, $an) = tempfile('email-cur-XXXXXXXX');
+       my ($ah, $an) = tempfile('email-cur-XXXXXXXX', TMPDIR => 1);
        print $ah $cur->as_string or die "print: $!";
        close $ah or die "close: $!";
-       my ($bh, $bn) = tempfile('email-new-XXXXXXXX');
+       my ($bh, $bn) = tempfile('email-new-XXXXXXXX', TMPDIR => 1);
+       PublicInbox::Import::drop_unwanted_headers($new);
        print $bh $new->as_string or die "print: $!";
        close $bh or die "close: $!";
        my $cmd = [ qw(diff -u), $an, $bn ];
@@ -489,7 +495,7 @@ sub mark_deleted {
        my $mids = mids($mime->header_obj);
        my $cid = content_id($mime);
        foreach my $mid (@$mids) {
-               $D->{$mid.$cid} = 1;
+               $D->{"$mid\0$cid"} = 1;
        }
 }
 
@@ -507,7 +513,7 @@ sub reindex_oid {
        my $num = -1;
        my $del = 0;
        foreach my $mid (@$mids) {
-               $del += (delete $D->{$mid.$cid} || 0);
+               $del += (delete $D->{"$mid\0$cid"} || 0);
                my $n = $mm_tmp->num_for($mid);
                if (defined $n && $n > $num) {
                        $mid0 = $mid;
@@ -627,6 +633,14 @@ sub reindex {
        }
        my ($min, $max) = $mm_tmp->minmax;
        defined $max and die "leftover article numbers at $min..$max\n";
+       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";
+               }
+       }
 }
 
 1;