X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FImport.pm;h=572e9bb9899fc464671510dc26275d51d6b7ce8c;hb=55b707d788ce13696e4411389583e720ea6dab01;hp=2c8fe848fc606c0461b5b5d349015daeb239d55b;hpb=cfff674918e8fc3e0763ac4818c07e0ba7fa716e;p=public-inbox.git

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index 2c8fe848..572e9bb9 100644
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -10,7 +10,7 @@ use strict;
 use warnings;
 use base qw(PublicInbox::Lock);
 use PublicInbox::Spawn qw(spawn);
-use PublicInbox::MID qw(mids mid_mime mid2path);
+use PublicInbox::MID qw(mids mid2path);
 use PublicInbox::Address;
 use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
 use PublicInbox::ContentId qw(content_digest);
@@ -66,7 +66,7 @@ sub gfi_start {
 	my $git_dir = $git->{git_dir};
 	my @cmd = ('git', "--git-dir=$git_dir", qw(fast-import
 			--quiet --done --date-format=raw));
-	my $rdr = { 0 => fileno($out_r), 1 => fileno($in_w) };
+	my $rdr = { 0 => $out_r, 1 => $in_w };
 	my $pid = spawn(\@cmd, undef, $rdr);
 	die "spawn fast-import failed: $!" unless defined $pid;
 	$out_w->autoflush(1);
@@ -178,14 +178,14 @@ sub _update_git_info ($$) {
 		my $env = { GIT_INDEX_FILE => $index };
 		run_die([@cmd, qw(read-tree -m -v -i), $self->{ref}], $env);
 	}
-	run_die([@cmd, 'update-server-info'], undef);
-	($self->{path_type} eq '2/38') and eval {
+	run_die([@cmd, 'update-server-info']);
+	my $ibx = $self->{-inbox};
+	($ibx && $self->{path_type} eq '2/38') and eval {
 		require PublicInbox::SearchIdx;
-		my $ibx = $self->{-inbox} || $git_dir;
 		my $s = PublicInbox::SearchIdx->new($ibx);
 		$s->index_sync({ ref => $self->{ref} });
 	};
-	eval { run_die([@cmd, qw(gc --auto)], undef) } if $do_gc;
+	eval { run_die([@cmd, qw(gc --auto)]) } if $do_gc;
 }
 
 sub barrier {
@@ -394,16 +394,16 @@ sub add {
 	}
 
 	my $blob = $self->{mark}++;
-	my $str = $mime->as_string;
-	my $n = length($str);
+	my $raw_email = $mime->{-public_inbox_raw} // $mime->as_string;
+	my $n = length($raw_email);
 	$self->{bytes_added} += $n;
 	print $w "blob\nmark :$blob\ndata ", $n, "\n" or wfail;
-	print $w $str, "\n" or wfail;
+	print $w $raw_email, "\n" or wfail;
 
 	# v2: we need this for Xapian
 	if ($self->{want_object_info}) {
 		my $oid = $self->get_mark(":$blob");
-		$self->{last_object} = [ $oid, $n, \$str ];
+		$self->{last_object} = [ $oid, $n, \$raw_email ];
 	}
 	my $ref = $self->{ref};
 	my $commit = $self->{mark}++;
@@ -484,26 +484,38 @@ sub digest2mid ($$) {
 	"$dt.$b64" . '@z';
 }
 
-sub clean_purge_buffer {
-	my ($oids, $buf) = @_;
-	my $cmt_msg = 'purged '.join(' ',@$oids)."\n";
+sub rewrite_commit ($$$$) {
+	my ($self, $oids, $buf, $mime) = @_;
+	my ($name, $email, $at, $ct, $subject);
+	if ($mime) {
+		($name, $email, $at, $ct, $subject) = extract_cmt_info($mime);
+	} else {
+		$name = $email = '';
+		$subject = 'purged '.join(' ', @$oids);
+	}
 	@$oids = ();
-
+	$subject .= "\n";
 	foreach my $i (0..$#$buf) {
 		my $l = $buf->[$i];
 		if ($l =~ /^author .* ([0-9]+ [\+-]?[0-9]+)$/) {
-			$buf->[$i] = "author <> $1\n";
+			$at //= $1;
+			$buf->[$i] = "author $name <$email> $at\n";
+		} elsif ($l =~ /^committer .* ([0-9]+ [\+-]?[0-9]+)$/) {
+			$ct //= $1;
+			$buf->[$i] = "committer $self->{ident} $ct\n";
 		} elsif ($l =~ /^data ([0-9]+)/) {
-			$buf->[$i++] = "data " . length($cmt_msg) . "\n";
-			$buf->[$i] = $cmt_msg;
+			$buf->[$i++] = "data " . length($subject) . "\n";
+			$buf->[$i] = $subject;
 			last;
 		}
 	}
 }
 
+# returns the new commit OID if a replacement was done
+# returns undef if nothing was done
 sub replace_oids {
-	my ($self, $replace) = @_; # oid => raw string
-	my $tmp = "refs/heads/replace-".((keys %$replace)[0]);
+	my ($self, $mime, $replace_map) = @_; # oid => raw string
+	my $tmp = "refs/heads/replace-".((keys %$replace_map)[0]);
 	my $old = $self->{'ref'};
 	my $git = $self->{git};
 	my @export = (qw(fast-export --no-data --use-done-feature), $old);
@@ -533,7 +545,7 @@ sub replace_oids {
 		} elsif (/^M 100644 ([a-f0-9]+) (\w+)/) {
 			my ($oid, $path) = ($1, $2);
 			$tree->{$path} = 1;
-			my $sref = $replace->{$oid};
+			my $sref = $replace_map->{$oid};
 			if (defined $sref) {
 				push @oids, $oid;
 				my $n = length($$sref);
@@ -548,10 +560,12 @@ sub replace_oids {
 			push @buf, $_ if $tree->{$path};
 		} elsif ($_ eq "\n") {
 			if (@oids) {
-				my $out = join('', @buf);
-				$out =~ s/^/# /sgm;
-				warn "purge rewriting\n", $out, "\n";
-				clean_purge_buffer(\@oids, \@buf);
+				if (!$mime) {
+					my $out = join('', @buf);
+					$out =~ s/^/# /sgm;
+					warn "purge rewriting\n", $out, "\n";
+				}
+				rewrite_commit($self, \@oids, \@buf, $mime);
 				$nreplace++;
 			}
 			$w->print(@buf, "\n") or wfail;
@@ -581,11 +595,11 @@ sub replace_oids {
 
 	return if $nreplace == 0;
 
-	run_die([@git, qw(-c gc.reflogExpire=now gc --prune=all)]);
+	run_die([@git, qw(-c gc.reflogExpire=now gc --prune=all --quiet)]);
 
 	# check that old OIDs are gone
 	my $err = 0;
-	foreach my $oid (keys %$replace) {
+	foreach my $oid (keys %$replace_map) {
 		my @info = $git->check($oid);
 		if (@info) {
 			warn "$oid not replaced\n";
@@ -609,7 +623,7 @@ PublicInbox::Import - message importer for public-inbox v1 inboxes
 
 version 1.0
 
-=head1 SYNOPSYS
+=head1 SYNOPSIS
 
 	use Email::MIME;
 	use PublicInbox::Git;