X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiImport.pm;h=13e817d0b7a54b9fc2057f1f6c7502616da3d730;hb=9d1d7c2b505454fba331666a951e0f7997500b3c;hp=2c7cbf2bc96bb8bac87cdce6ed4b8cb5a4df3638;hpb=618c5d7767a3611d70f78825156d5ddac7ce9427;p=public-inbox.git

diff --git a/lib/PublicInbox/LeiImport.pm b/lib/PublicInbox/LeiImport.pm
index 2c7cbf2b..13e817d0 100644
--- a/lib/PublicInbox/LeiImport.pm
+++ b/lib/PublicInbox/LeiImport.pm
@@ -6,101 +6,194 @@ package PublicInbox::LeiImport;
 use strict;
 use v5.10.1;
 use parent qw(PublicInbox::IPC);
-use PublicInbox::MboxReader;
 use PublicInbox::Eml;
+use PublicInbox::PktOp qw(pkt_do);
 
 sub _import_eml { # MboxReader callback
 	my ($eml, $sto, $set_kw) = @_;
 	$sto->ipc_do('set_eml', $eml, $set_kw ? $sto->mbox_keywords($eml) : ());
 }
 
+sub import_done_wait { # dwaitpid callback
+	my ($arg, $pid) = @_;
+	my ($imp, $lei) = @$arg;
+	$lei->child_error($?, 'non-fatal errors during import') if $?;
+	my $ign = $lei->{sto}->ipc_do('done'); # PublicInbox::LeiStore::done
+	$lei->dclose;
+}
+
 sub import_done { # EOF callback for main daemon
 	my ($lei) = @_;
-	my $imp = delete $lei->{imp};
-	$imp->wq_wait_old($lei) if $imp;
-	my $wait = $lei->{sto}->ipc_do('done');
-	$lei->dclose;
+	my $imp = delete $lei->{imp} or return;
+	$imp->wq_wait_old(\&import_done_wait, $lei);
+}
+
+sub net_merge_complete { # callback used by LeiAuth
+	my ($self) = @_;
+	for my $input (@{$self->{inputs}}) {
+		$self->wq_io_do('import_path_url', [], $input);
+	}
+	$self->wq_close(1);
+}
+
+sub import_start {
+	my ($lei) = @_;
+	my $self = $lei->{imp};
+	my $j = $lei->{opt}->{jobs} // scalar(@{$self->{inputs}}) || 1;
+	if (my $net = $lei->{net}) {
+		# $j = $net->net_concurrency($j); TODO
+	} else {
+		my $nproc = $self->detect_nproc;
+		$j = $nproc if $j > $nproc;
+	}
+	my $ops = { '' => [ \&import_done, $lei ] };
+	$lei->{auth}->op_merge($ops, $self) if $lei->{auth};
+	$self->{-wq_nr_workers} = $j // 1; # locked
+	my $op = $lei->workers_start($self, 'lei_import', undef, $ops);
+	$self->wq_io_do('import_stdin', []) if $self->{0};
+	net_merge_complete($self) unless $lei->{auth};
+	while ($op && $op->{sock}) { $op->event_step }
 }
 
 sub call { # the main "lei import" method
-	my ($cls, $lei, @argv) = @_;
+	my ($cls, $lei, @inputs) = @_;
 	my $sto = $lei->_lei_store(1);
 	$sto->write_prepare($lei);
+	my ($net, @f, @d);
 	$lei->{opt}->{kw} //= 1;
+	my $self = $lei->{imp} = bless { inputs => \@inputs }, $cls;
+	if ($lei->{opt}->{stdin}) {
+		@inputs and return $lei->fail("--stdin and @inputs do not mix");
+		$lei->check_input_format or return;
+		$self->{0} = $lei->{0};
+	}
+
+	# TODO: do we need --format for non-stdin?
 	my $fmt = $lei->{opt}->{'format'};
-	my $self = $lei->{imp} = bless {}, $cls;
-	return $lei->fail('--format unspecified') if !$fmt;
-	$self->{0} = $lei->{0} if $lei->{opt}->{stdin};
-	my $ops = {
-		'!' => [ $lei->can('fail_handler'), $lei ],
-		'x_it' => [ $lei->can('x_it'), $lei ],
-		'child_error' => [ $lei->can('child_error'), $lei ],
-		'' => [ \&import_done, $lei ],
-	};
-	($lei->{pkt_op_c}, $lei->{pkt_op_p}) = PublicInbox::PktOp->pair($ops);
-	my $j = $lei->{opt}->{jobs} // scalar(@argv) || 1;
-	my $nproc = $self->detect_nproc;
-	$j = $nproc if $j > $nproc;
-	$self->wq_workers_start('lei_import', $j, $lei->oldset, {lei => $lei});
-	my $op = delete $lei->{pkt_op_c};
-	delete $lei->{pkt_op_p};
-	$self->wq_do('import_stdin', []) if $self->{0};
-	for my $x (@argv) {
-		$self->wq_do('import_path_url', [], $x);
+	# e.g. Maildir:/home/user/Mail/ or imaps://example.com/INBOX
+	for my $input (@inputs) {
+		my $input_path = $input;
+		if ($input =~ m!\A(?:imaps?|nntps?|s?news)://!i) {
+			require PublicInbox::NetReader;
+			$net //= PublicInbox::NetReader->new;
+			$net->add_url($input);
+		} elsif ($input_path =~ s/\A([a-z0-9]+)://is) {
+			my $ifmt = lc $1;
+			if (($fmt // $ifmt) ne $ifmt) {
+				return $lei->fail(<<"");
+--format=$fmt and `$ifmt:' conflict
+
+			}
+			if (-f $input_path) {
+				require PublicInbox::MboxReader;
+				PublicInbox::MboxReader->can($ifmt) or return
+					$lei->fail("$ifmt not supported");
+			} elsif (-d _) {
+				require PublicInbox::MdirReader;
+				$ifmt eq 'maildir' or return
+					$lei->fail("$ifmt not supported");
+			} else {
+				return $lei->fail("Unable to handle $input");
+			}
+		} elsif (-f $input) { push @f, $input
+		} elsif (-d _) { push @d, $input
+		} else { return $lei->fail("Unable to handle $input") }
 	}
-	$self->wq_close(1);
-	$lei->event_step_init; # wait for shutdowns
-	if ($lei->{oneshot}) {
-		while ($op->{sock}) { $op->event_step }
+	if (@f) { $lei->check_input_format(\@f) or return }
+	if (@d) { # TODO: check for MH vs Maildir, here
+		require PublicInbox::MdirReader;
 	}
+	$self->{inputs} = \@inputs;
+	if ($net) {
+		if (my $err = $net->errors) {
+			return $lei->fail($err);
+		}
+		$net->{quiet} = $lei->{opt}->{quiet};
+		$lei->{net} = $net;
+		require PublicInbox::LeiAuth;
+		$lei->{auth} = PublicInbox::LeiAuth->new;
+	}
+	import_start($lei);
 }
 
 sub ipc_atfork_child {
 	my ($self) = @_;
-	$self->{lei}->lei_atfork_child;
+	my $lei = $self->{lei};
+	delete $lei->{imp}; # drop circular ref
+	$lei->lei_atfork_child;
 	$self->SUPER::ipc_atfork_child;
+	$lei->{auth}->do_auth_atfork($self) if $lei->{auth};
+	undef;
 }
 
 sub _import_fh {
-	my ($lei, $fh, $x) = @_;
+	my ($lei, $fh, $input, $ifmt) = @_;
 	my $set_kw = $lei->{opt}->{kw};
-	my $fmt = $lei->{opt}->{'format'};
 	eval {
-		if ($fmt eq 'eml') {
+		if ($ifmt eq 'eml') {
 			my $buf = do { local $/; <$fh> } //
-				return $lei->child_error(1 >> 8, <<"");
-		error reading $x: $!
+				return $lei->child_error(1 << 8, <<"");
+error reading $input: $!
 
 			my $eml = PublicInbox::Eml->new(\$buf);
 			_import_eml($eml, $lei->{sto}, $set_kw);
-		} else { # some mbox
-			my $cb = PublicInbox::MboxReader->can($fmt);
-			$cb or return $lei->child_error(1 >> 8, <<"");
-	--format $fmt unsupported for $x
-
+		} else { # some mbox (->can already checked in call);
+			my $cb = PublicInbox::MboxReader->can($ifmt) //
+				die "BUG: bad fmt=$ifmt";
 			$cb->(undef, $fh, \&_import_eml, $lei->{sto}, $set_kw);
 		}
 	};
-	$lei->child_error(1 >> 8, "<stdin>: $@") if $@;
+	$lei->child_error(1 << 8, "<stdin>: $@") if $@;
+}
+
+sub _import_maildir { # maildir_each_file cb
+	my ($f, $sto, $set_kw) = @_;
+	$sto->ipc_do('set_eml_from_maildir', $f, $set_kw);
+}
+
+sub _import_net { # imap_each, nntp_each cb
+	my ($url, $uid, $kw, $eml, $sto, $set_kw) = @_;
+	$sto->ipc_do('set_eml', $eml, $set_kw ? @$kw : ());
 }
 
 sub import_path_url {
-	my ($self, $x) = @_;
+	my ($self, $input) = @_;
 	my $lei = $self->{lei};
+	my $ifmt = lc($lei->{opt}->{'format'} // '');
 	# TODO auto-detect?
-	if (-f $x) {
-		open my $fh, '<', $x or return $lei->child_error(1 >> 8, <<"");
-unable to open $x: $!
+	if ($input =~ m!\Aimaps?://!i) {
+		$lei->{net}->imap_each($input, \&_import_net, $lei->{sto},
+					$lei->{opt}->{kw});
+		return;
+	} elsif ($input =~ m!\A(?:nntps?|s?news)://!i) {
+		$lei->{net}->nntp_each($input, \&_import_net, $lei->{sto}, 0);
+		return;
+	} elsif ($input =~ s!\A([a-z0-9]+):!!i) {
+		$ifmt = lc $1;
+	}
+	if (-f $input) {
+		open my $fh, '<', $input or return $lei->child_error(1 << 8, <<"");
+unable to open $input: $!
 
-		_import_fh($lei, $fh, $x);
+		_import_fh($lei, $fh, $input, $ifmt);
+	} elsif (-d _ && (-d "$input/cur" || -d "$input/new")) {
+		return $lei->fail(<<EOM) if $ifmt && $ifmt ne 'maildir';
+$input appears to a be a maildir, not $ifmt
+EOM
+		PublicInbox::MdirReader::maildir_each_file($input,
+					\&_import_maildir,
+					$lei->{sto}, $lei->{opt}->{kw});
 	} else {
-		$lei->fail("$x unsupported (TODO)");
+		$lei->fail("$input unsupported (TODO)");
 	}
 }
 
 sub import_stdin {
 	my ($self) = @_;
-	_import_fh($self->{lei}, $self->{0}, '<stdin>');
+	my $lei = $self->{lei};
+	_import_fh($lei, delete $self->{0}, '<stdin>', $lei->{opt}->{'format'});
 }
 
+no warnings 'once'; # the following works even when LeiAuth is lazy-loaded
+*net_merge_all = \&PublicInbox::LeiAuth::net_merge_all;
 1;