X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FImport.pm;h=2cb4896af5a83a08ca45cb7340f5c1e548ed1e42;hb=e5d32fe689dd0922eaf206e2371fc8040ad85247;hp=07a4951871375674b442c1a0c5bd7710013e608f;hpb=0faddbbfecaa784c584d3a625628c288fe9316c7;p=public-inbox.git

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index 07a49518..2cb4896a 100644
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -106,7 +106,7 @@ sub _cat_blob ($$$) {
 	local $/ = "\n";
 	my $info = <$r>;
 	defined $info or die "EOF from fast-import / cat-blob: $!";
-	$info =~ /\A[a-f0-9]{40} blob ([0-9]+)\n\z/ or return;
+	$info =~ /\A[a-f0-9]{40,} blob ([0-9]+)\n\z/ or return;
 	my $left = $1;
 	my $offset = 0;
 	my $buf = '';
@@ -137,7 +137,7 @@ sub check_remove_v1 {
 	my ($r, $w, $tip, $path, $mime) = @_;
 
 	my $info = _check_path($r, $w, $tip, $path) or return ('MISSING',undef);
-	$info =~ m!\A100644 blob ([a-f0-9]{40})\t!s or die "not blob: $info";
+	$info =~ m!\A100644 blob ([a-f0-9]{40,})\t!s or die "not blob: $info";
 	my $oid = $1;
 	my $msg = _cat_blob($r, $w, $oid) or die "BUG: cat-blob $1 failed";
 	my $cur = PublicInbox::Eml->new($msg);
@@ -285,15 +285,14 @@ sub extract_cmt_info ($;$) {
 	# $mime is PublicInbox::Eml, but remains Email::MIME-compatible
 	$smsg //= bless {}, 'PublicInbox::Smsg';
 
-	my $hdr = $mime->header_obj;
-	$smsg->populate($hdr);
+	$smsg->populate($mime);
 
 	my $sender = '';
 	my $from = delete($smsg->{From}) // '';
 	my ($email) = PublicInbox::Address::emails($from);
 	my ($name) = PublicInbox::Address::names($from);
 	if (!defined($name) || !defined($email)) {
-		$sender = $hdr->header('Sender') // '';
+		$sender = $mime->header('Sender') // '';
 		$name //= (PublicInbox::Address::names($sender))[0];
 		$email //= (PublicInbox::Address::emails($sender))[0];
 	}
@@ -329,11 +328,13 @@ sub extract_cmt_info ($;$) {
 }
 
 # kill potentially confusing/misleading headers
+our @UNWANTED_HEADERS = (qw(Bytes Lines Content-Length),
+			qw(Status X-Status));
 sub drop_unwanted_headers ($) {
-	my ($mime) = @_;
-
-	$mime->header_set($_) for qw(Bytes Lines Content-Length Status);
-	$mime->header_set($_) for @PublicInbox::MDA::BAD_HEADERS;
+	my ($eml) = @_;
+	for (@UNWANTED_HEADERS, @PublicInbox::MDA::BAD_HEADERS) {
+		$eml->header_set($_);
+	}
 }
 
 # used by V2Writable, too
@@ -346,13 +347,12 @@ sub append_mid ($$) {
 }
 
 sub v1_mid0 ($) {
-	my ($mime) = @_;
-	my $hdr = $mime->header_obj;
-	my $mids = mids($hdr);
+	my ($eml) = @_;
+	my $mids = mids($eml);
 
 	if (!scalar(@$mids)) { # spam often has no Message-ID
-		my $mid0 = digest2mid(content_digest($mime), $hdr);
-		append_mid($hdr, $mid0);
+		my $mid0 = digest2mid(content_digest($eml), $eml);
+		append_mid($eml, $mid0);
 		return $mid0;
 	}
 	$mids->[0];
@@ -463,6 +463,9 @@ sub init_bare {
 	}
 }
 
+# true if locked and active
+sub active { !!$_[0]->{out} }
+
 sub done {
 	my ($self) = @_;
 	my $w = delete $self->{out} or return;
@@ -671,8 +674,7 @@ version 1.0
 	my $parsed = PublicInbox::Eml->new($message);
 	my $ret = $im->add($parsed);
 	if (!defined $ret) {
-		warn "duplicate: ",
-			$parsed->header_obj->header_raw('Message-ID'), "\n";
+		warn "duplicate: ", $parsed->header_raw('Message-ID'), "\n";
 	} else {
 		print "imported at mark $ret\n";
 	}