v2: support incremental indexing + purge

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

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index b2aae9a7a800c8dbc0d738a8ef63eeea6e2f104d..2529798fe4b7adc40424dad7b32341ccd9597ac0 100644 (file)
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -192,6 +192,7 @@ sub get_mark {
        my ($r, $w) = $self->gfi_start;
        print $w "get-mark $mark\n" or wfail;
        defined(my $oid = <$r>) or die "get-mark failed, need git 2.6.0+\n";
+       chomp($oid);
        $oid;
 }
 
@@ -379,7 +380,7 @@ sub add {
 
        # v2: we need this for Xapian
        if ($self->{want_object_info}) {
-               chomp(my $oid = $self->get_mark(":$blob"));
+               my $oid = $self->get_mark(":$blob");
                $self->{last_object} = [ $oid, $n, \$str ];
        }
        my $ref = $self->{ref};
@@ -476,6 +477,7 @@ sub purge_oids {
        my @buf;
        my $npurge = 0;
        my @oids;
+       my ($done, $mark);
        my $tree = $self->{-tree};
        while (<$rd>) {
                if (/^reset (?:.+)/) {
@@ -506,14 +508,20 @@ sub purge_oids {
                        my $path = $1;
                        push @buf, $_ if $tree->{$path};
                } elsif ($_ eq "\n") {
-                       my $out = join('', @buf);
-                       $out =~ s/^/# /sgm;
-                       warn "purge rewriting\n", $out, "\n";
-                       clean_purge_buffer(\@oids, \@buf);
-                       $out = join('', @buf);
+                       if (@oids) {
+                               my $out = join('', @buf);
+                               $out =~ s/^/# /sgm;
+                               warn "purge rewriting\n", $out, "\n";
+                               clean_purge_buffer(\@oids, \@buf);
+                               $npurge++;
+                       }
                        $w->print(@buf, "\n") or wfail;
                        @buf = ();
-                       $npurge++;
+               } elsif ($_ eq "done\n") {
+                       $done = 1;
+               } elsif (/^mark :(\d+)$/) {
+                       push @buf, $_;
+                       $mark = $1;
                } else {
                        push @buf, $_;
                }
@@ -521,7 +529,9 @@ sub purge_oids {
        if (@buf) {
                $w->print(@buf) or wfail;
        }
-       $w = $r = undef;
+       die 'done\n not seen from fast-export' unless $done;
+       chomp(my $cmt = $self->get_mark(":$mark")) if $npurge;
+       $self->{nchg} = 0; # prevent _update_git_info until update-ref:
        $self->done;
        my @git = ('git', "--git-dir=$git->{git_dir}");
 
@@ -540,7 +550,9 @@ sub purge_oids {
                        $err++;
                }
        }
+       _update_git_info($self, 0);
        die "Failed to purge $err object(s)\n" if $err;
+       $cmt;
 }
 
 1;