learn: use "spam" as subject for removal commits

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

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index 09dd38d02d3f9f9c31e937fc7c0893773edb6719..8c9d1cbad526a7d1e5dd3813f390685a0cd3713b 100644 (file)
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -54,6 +54,8 @@ sub gfi_start {
        $self->{lockfh} = $lockfh;
        $self->{pid} = $pid;
        $self->{nchg} = 0;
+       binmode $out_w, ':raw' or die "binmode :raw failed: $!";
+       binmode $in_r, ':raw' or die "binmode :raw failed: $!";
        ($in_r, $out_w);
 }
 
@@ -88,7 +90,7 @@ sub _check_path ($$$$) {
 # ('MISMATCH', msg) on mismatch
 # (:MARK, msg) on success
 sub remove {
-       my ($self, $mime) = @_; # mime = Email::MIME
+       my ($self, $mime, $msg) = @_; # mime = Email::MIME
 
        my $mid = mid_mime($mime);
        my $path = mid2path($mid);
@@ -119,7 +121,7 @@ sub remove {
        $n = read($r, my $lf, 1);
        defined($n) or die "read final byte of cat-blob failed: $!";
        die "bad read on final byte: <$lf>" if $lf ne "\n";
-       my $cur = Email::MIME->new($buf);
+       my $cur = PublicInbox::MIME->new($buf);
        my $cur_s = $cur->header('Subject');
        $cur_s = '' unless defined $cur_s;
        my $cur_m = $mime->header('Subject');
@@ -136,10 +138,12 @@ sub remove {
        }
        my $ident = $self->{ident};
        my $now = now2822();
+       $msg ||= 'rm';
+       my $len = length($msg) + 1;
        print $w "commit $ref\nmark :$commit\n",
                "author $ident $now\n",
                "committer $ident $now\n",
-               "data 3\nrm\n\n",
+               "data $len\n$msg\n\n",
                'from ', ($parent ? $parent : $tip), "\n" or wfail;
        print $w "D $path\n\n" or wfail;
        $self->{nchg}++;
@@ -187,15 +191,15 @@ sub add {
                print $w "reset $ref\n" or wfail;
        }
 
+       utf8::encode($email);
+       utf8::encode($name);
+       utf8::encode($subject);
        # quiet down wide character warnings:
-       binmode $w, ':utf8' or die "binmode :utf8 failed: $!";
        print $w "commit $ref\nmark :$commit\n",
                "author $name <$email> $date\n",
-               "committer $self->{ident} ", now2822(), "\n",
-               "data ", (bytes::length($subject) + 1), "\n",
+               "committer $self->{ident} ", now2822(), "\n" or wfail;
+       print $w "data ", (length($subject) + 1), "\n",
                $subject, "\n\n" or wfail;
-       binmode $w, ':raw' or die "binmode :raw failed: $!";
-
        if ($tip ne '') {
                print $w 'from ', ($parent ? $parent : $tip), "\n" or wfail;
        }
@@ -204,6 +208,14 @@ sub add {
        $self->{tip} = ":$commit";
 }
 
+sub run_die ($$) {
+       my ($cmd, $env) = @_;
+       my $pid = spawn($cmd, $env, undef);
+       defined $pid or die "spawning ".join(' ', @$cmd)." failed: $!";
+       waitpid($pid, 0) == $pid or die join(' ', @$cmd) .' did not finish';
+       $? == 0 or die join(' ', @$cmd) . " failed: $?\n";
+}
+
 sub done {
        my ($self) = @_;
        my $w = delete $self->{out} or return;
@@ -222,25 +234,18 @@ sub done {
        if ($nchg && !$ENV{FAST}) {
                my $index = "$git_dir/ssoma.index";
                my $env = { GIT_INDEX_FILE => $index };
-               my @rt = (@cmd, qw(read-tree -m -v -i), $self->{ref});
-               $pid = spawn(\@rt, $env, undef);
-               defined $pid or die "spawn read-tree failed: $!";
-               waitpid($pid, 0) == $pid or die 'read-tree did not finish';
-               $? == 0 or die "failed to update $git_dir/ssoma.index: $?\n";
+               run_die([@cmd, qw(read-tree -m -v -i), $self->{ref}], $env);
        }
        if ($nchg) {
-               $pid = spawn([@cmd, 'update-server-info'], undef, undef);
-               defined $pid or die "spawn update-server-info failed: $!\n";
-               waitpid($pid, 0) == $pid or
-                       die 'update-server-info did not finish';
-               $? == 0 or die "failed to update-server-info: $?\n";
-
+               run_die([@cmd, 'update-server-info'], undef);
                eval {
                        require PublicInbox::SearchIdx;
                        my $inbox = $self->{inbox} || $git_dir;
                        my $s = PublicInbox::SearchIdx->new($inbox);
                        $s->index_sync({ ref => $self->{ref} });
                };
+
+               eval { run_die([@cmd, qw(gc --auto)], undef) };
        }
 
        my $lockfh = delete $self->{lockfh} or die "BUG: not locked: $!";