X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FImport.pm;h=27f36a7e486b84337e1e4e4586ab9ec5251e4c65;hb=2c69f7bc34a2b12dc7f55e2bb24fa28565f24f03;hp=1f52a0cc80f9eddd40a8e16f7b44496a4085b005;hpb=1f89e15a29cd63335f40902f1de7944e2efe91fa;p=public-inbox.git

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index 1f52a0cc..27f36a7e 100644
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -8,7 +8,6 @@ package PublicInbox::Import;
 use strict;
 use warnings;
 use Fcntl qw(:flock :DEFAULT);
-use Email::Address;
 use PublicInbox::Spawn qw(spawn);
 use PublicInbox::MID qw(mid_mime mid2path);
 
@@ -51,6 +50,7 @@ sub gfi_start {
 	$self->{out} = $out_w;
 	$self->{lockfh} = $lockfh;
 	$self->{pid} = $pid;
+	$self->{nchg} = 0;
 	($in_r, $out_w);
 }
 
@@ -112,8 +112,11 @@ sub remove {
 	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);
-	if ($cur->header('Subject') ne $mime->header('Subject') ||
-			norm_body($cur) ne norm_body($mime)) {
+	my $cur_s = $cur->header('Subject');
+	$cur_s = '' unless defined $cur_s;
+	my $cur_m = $mime->header('Subject');
+	$cur_m = '' unless defined $cur_m;
+	if ($cur_s ne $cur_m || norm_body($cur) ne norm_body($mime)) {
 		return ('MISMATCH', $cur);
 	}
 
@@ -131,29 +134,30 @@ sub remove {
 		"data 3\nrm\n\n",
 		'from ', ($parent ? $parent : $tip), "\n" or wfail;
 	print $w "D $path\n\n" or wfail;
+	$self->{nchg}++;
 	(($self->{tip} = ":$commit"), $cur);
 }
 
 # returns undef on duplicate
 sub add {
-	my ($self, $mime) = @_; # mime = Email::MIME
+	my ($self, $mime, $check_cb) = @_; # mime = Email::MIME
 
 	my $from = $mime->header('From');
-	my @from = Email::Address->parse($from);
-	my $name = $from[0]->name;
-	my $email = $from[0]->address;
+	my ($email) = ($from =~ /([^<\s]+\@[^>\s]+)/g);
+	my $name = $from;
+	$name =~ s/\s*\S+\@\S+\s*\z//;
+	# git gets confused with:
+	#  "'A U Thor <u@example.com>' via foo" <foo@example.com>
+	# ref:
+	# <CAD0k6qSUYANxbjjbE4jTW4EeVwOYgBD=bXkSu=akiYC_CB7Ffw@mail.gmail.com>
+	$name =~ tr/<>// and $name = $email;
+
 	my $date = $mime->header('Date');
 	my $subject = $mime->header('Subject');
 	$subject = '(no subject)' unless defined $subject;
 	my $mid = mid_mime($mime);
 	my $path = mid2path($mid);
 
-	# git gets confused with:
-	#  "'A U Thor <u@example.com>' via foo" <foo@example.com>
-	# ref:
-	# <CAD0k6qSUYANxbjjbE4jTW4EeVwOYgBD=bXkSu=akiYC_CB7Ffw@mail.gmail.com>
-	$name =~ s/<([^>]+)>/($1)/g;
-
 	my ($r, $w) = $self->gfi_start;
 	my $tip = $self->{tip};
 	if ($tip ne '') {
@@ -166,6 +170,10 @@ sub add {
 
 	# kill potentially confusing/misleading headers
 	$mime->header_set($_) for qw(bytes lines content-length status);
+	if ($check_cb) {
+		$mime = $check_cb->($mime) or return;
+	}
+
 	$mime = $mime->as_string;
 	my $blob = $self->{mark}++;
 	print $w "blob\nmark :$blob\ndata ", length($mime), "\n" or wfail;
@@ -191,6 +199,7 @@ sub add {
 		print $w 'from ', ($parent ? $parent : $tip), "\n" or wfail;
 	}
 	print $w "M 100644 :$blob $path\n\n" or wfail;
+	$self->{nchg}++;
 	$self->{tip} = ":$commit";
 }
 
@@ -202,14 +211,15 @@ sub done {
 	my $pid = delete $self->{pid} or die 'BUG: missing {pid} when done';
 	waitpid($pid, 0) == $pid or die 'fast-import did not finish';
 	$? == 0 or die "fast-import failed: $?";
+	my $nchg = delete $self->{nchg};
 
 	# for compatibility with existing ssoma installations
 	# we can probably remove this entirely by 2020
 	my $git_dir = $self->{git}->{git_dir};
-	my $index = "$git_dir/ssoma.index";
 	# XXX: change the following scope to: if (-e $index) # in 2018 or so..
 	my @cmd = ('git', "--git-dir=$git_dir");
-	unless ($ENV{FAST}) {
+	if ($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, $env, undef);
@@ -217,11 +227,18 @@ sub done {
 		waitpid($pid, 0) == $pid or die 'read-tree did not finish';
 		$? == 0 or die "failed to update $git_dir/ssoma.index: $?\n";
 	}
-
-	$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: $?\n";
+	if ($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: $?\n";
+
+		eval {
+			require PublicInbox::SearchIdx;
+			PublicInbox::SearchIdx->new($git_dir, 2)->index_sync;
+		};
+	}
 
 	my $lockfh = delete $self->{lockfh} or die "BUG: not locked: $!";
 	flock($lockfh, LOCK_UN) or die "unlock failed: $!";