X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FImport.pm;h=29c482f9b4339b09089421723f3991b24e57f553;hb=cf35d38e7f845393659dfce0249a76d529a2c92c;hp=b25427ee552628237bc094225f2daf24e98dcdac;hpb=cfb8d16578e7f2f2e300f9f436205e4a8fc7f322;p=public-inbox.git

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index b25427ee..29c482f9 100644
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2016-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2019 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # git fast-import-based ssoma-mda MDA replacement
@@ -278,10 +278,12 @@ sub extract_author_info ($) {
 
 	my $sender = '';
 	my $from = $mime->header('From');
+	$from ||= '';
 	my ($email) = PublicInbox::Address::emails($from);
 	my ($name) = PublicInbox::Address::names($from);
 	if (!defined($name) || !defined($email)) {
 		$sender = $mime->header('Sender');
+		$sender ||= '';
 		if (!defined($name)) {
 			($name) = PublicInbox::Address::names($sender);
 		}
@@ -405,6 +407,8 @@ sub add {
 		print $w "reset $ref\n" or wfail;
 	}
 
+	# Mime decoding can create nulls replace them with spaces to protect git
+	$subject =~ tr/\0/ /;
 	utf8::encode($subject);
 	print $w "commit $ref\nmark :$commit\n",
 		"author $name <$email> $author_time_raw\n",
@@ -440,11 +444,14 @@ sub done {
 	_update_git_info($self, 1) if delete $self->{nchg};
 
 	$self->lock_release;
+
+	$self->{git}->cleanup;
 }
 
 sub atfork_child {
 	my ($self) = @_;
 	foreach my $f (qw(in out)) {
+		next unless defined($self->{$f});
 		close $self->{$f} or die "failed to close import[$f]: $!\n";
 	}
 }
@@ -512,11 +519,12 @@ sub purge_oids {
 			push @buf, $buf;
 		} elsif (/^M 100644 ([a-f0-9]+) (\w+)/) {
 			my ($oid, $path) = ($1, $2);
+			$tree->{$path} = 1;
 			if ($purge->{$oid}) {
 				push @oids, $oid;
-				delete $tree->{$path};
+				my $cmd = "M 100644 inline $path\ndata 0\n\n";
+				push @buf, $cmd;
 			} else {
-				$tree->{$path} = 1;
 				push @buf, $_;
 			}
 		} elsif (/^D (\w+)/) {
@@ -627,8 +635,8 @@ version 1.0
 =head1 DESCRIPTION
 
 An importer and remover for public-inboxes which takes L<Email::MIME>
-messages as input and stores them in a ssoma repository as
-documented in L<https://ssoma.public-inbox.org/ssoma_repository.txt>,
+messages as input and stores them in a git repository as
+documented in L<https://public-inbox.org/public-inbox-v1-format.txt>,
 except it does not allow duplicate Message-IDs.
 
 It requires L<git(1)> and L<git-fast-import(1)> to be installed.