package PublicInbox::LeiImport;
use strict;
use v5.10.1;
-use parent qw(PublicInbox::IPC);
+use parent qw(PublicInbox::IPC PublicInbox::LeiInput);
use PublicInbox::Eml;
-use PublicInbox::InboxWritable qw(eml_from_path);
-use PublicInbox::PktOp;
+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 eml_cb { # used by PublicInbox::LeiInput::input_fh
+ my ($self, $eml, $vmd) = @_;
+ my $xoids = $self->{lei}->{ale}->xoids_for($eml);
+ $self->{lei}->{sto}->ipc_do('set_eml', $eml, $vmd, $xoids);
+}
+
+sub mbox_cb { # MboxReader callback used by PublicInbox::LeiInput::input_fh
+ my ($eml, $self) = @_;
+ my $vmd;
+ if ($self->{-import_kw}) {
+ my $kw = PublicInbox::MboxReader::mbox_keywords($eml);
+ $vmd = { kw => $kw } if scalar(@$kw);
+ }
+ eml_cb($self, $eml, $vmd);
}
sub import_done_wait { # dwaitpid callback
my ($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
+ my $sto = delete $lei->{sto};
+ my $wait = $sto->ipc_do('done') if $sto; # PublicInbox::LeiStore::done
$lei->dclose;
}
$imp->wq_wait_old(\&import_done_wait, $lei);
}
-sub check_fmt ($;$) {
- my ($lei, $f) = @_;
- my $fmt = $lei->{opt}->{'format'};
- if (!$fmt) {
- my $err = $f ? "regular file(s):\n@$f" : '--stdin';
- return $lei->fail("--format unset for $err");
+sub net_merge_complete { # callback used by LeiAuth
+ my ($self) = @_;
+ for my $input (@{$self->{inputs}}) {
+ $self->wq_io_do('import_path_url', [], $input);
}
- return 1 if $fmt eq 'eml';
- require PublicInbox::MboxReader;
- PublicInbox::MboxReader->can($fmt) ||
- $lei->fail( "--format=$fmt unrecognized\n");
+ $self->wq_close(1);
}
-sub do_import {
+sub import_start {
my ($lei) = @_;
- 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 $self = $lei->{imp};
- my $j = $lei->{opt}->{jobs} // scalar(@{$self->{argv}}) || 1;
- if (my $nrd = $lei->{nrd}) {
- # $j = $nrd->net_concurrency($j); TODO
+ $lei->ale; # initialize for workers to read
+ 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;
}
- $self->wq_workers_start('lei_import', $j, $lei->oldset, {lei => $lei});
- my $op = delete $lei->{pkt_op_c};
- delete $lei->{pkt_op_p};
+ 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};
- for my $x (@{$self->{argv}}) {
- $self->wq_io_do('import_path_url', [], $x);
- }
- $self->wq_close(1);
- $lei->event_step_init; # wait for shutdowns
- if ($lei->{oneshot}) {
- while ($op->{sock}) { $op->event_step }
- }
+ net_merge_complete($self) unless $lei->{auth};
+ while ($op && $op->{sock}) { $op->event_step }
}
-sub call { # the main "lei import" method
- my ($cls, $lei, @argv) = @_;
+sub lei_import { # the main "lei import" method
+ my ($lei, @inputs) = @_;
my $sto = $lei->_lei_store(1);
$sto->write_prepare($lei);
- $lei->{opt}->{kw} //= 1;
- my $self = $lei->{imp} = bless { argv => \@argv }, $cls;
- if ($lei->{opt}->{stdin}) {
- @argv and return
- $lei->fail("--stdin and locations (@argv) do not mix");
- check_fmt($lei) or return;
- $self->{0} = $lei->{0};
- } else {
- my @f;
- for my $x (@argv) {
- if (-f $x) { push @f, $x }
- elsif (-d _) { require PublicInbox::MdirReader }
- else {
- require PublicInbox::NetReader;
- $lei->{nrd} //= PublicInbox::NetReader->new;
- $lei->{nrd}->add_url($x);
- }
- }
- if (@f) { check_fmt($lei, \@f) or return }
- if ($lei->{nrd} && (my @err = $lei->{nrd}->errors)) {
- return $lei->fail(@err);
- }
- }
- do_import($lei);
+ my $self = $lei->{imp} = bless {}, __PACKAGE__;
+ $self->{-import_kw} = $lei->{opt}->{kw} // 1;
+ $self->prepare_inputs($lei, \@inputs) or return;
+ import_start($lei);
}
-sub ipc_atfork_child {
- my ($self) = @_;
- $self->{lei}->lei_atfork_child;
- $self->SUPER::ipc_atfork_child;
-}
-
-sub _import_fh {
- my ($lei, $fh, $x) = @_;
- my $set_kw = $lei->{opt}->{kw};
- my $fmt = $lei->{opt}->{'format'};
- eval {
- if ($fmt eq 'eml') {
- my $buf = do { local $/; <$fh> } //
- return $lei->child_error(1 >> 8, <<"");
-error reading $x: $!
-
- my $eml = PublicInbox::Eml->new(\$buf);
- _import_eml($eml, $lei->{sto}, $set_kw);
- } else { # some mbox (->can already checked in call);
- my $cb = PublicInbox::MboxReader->can($fmt) //
- die "BUG: bad fmt=$fmt";
- $cb->(undef, $fh, \&_import_eml, $lei->{sto}, $set_kw);
- }
- };
- $lei->child_error(1 >> 8, "<stdin>: $@") if $@;
+sub _import_maildir { # maildir_each_eml cb
+ my ($f, $kw, $eml, $sto, $set_kw) = @_;
+ $sto->ipc_do('set_eml', $eml, $set_kw ? { kw => $kw }: ());
}
-sub _import_maildir { # maildir_each_file cb
- my ($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 => $kw } : ());
}
sub import_path_url {
- my ($self, $x) = @_;
+ my ($self, $input) = @_;
my $lei = $self->{lei};
+ my $ifmt = lc($lei->{opt}->{'in-format'} // '');
# TODO auto-detect?
- if (-f $x) {
- open my $fh, '<', $x or return $lei->child_error(1 >> 8, <<"");
-unable to open $x: $!
-
- _import_fh($lei, $fh, $x);
- } elsif (-d _ && (-d "$x/cur" || -d "$x/new")) {
- PublicInbox::MdirReader::maildir_each_file($x,
+ if ($input =~ m!\Aimaps?://!i) {
+ $lei->{net}->imap_each($input, \&_import_net, $lei->{sto},
+ $self->{-import_kw});
+ return;
+ } elsif ($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) {
+ my $m = $lei->{opt}->{'lock'} // ($ifmt eq 'eml' ? ['none'] :
+ PublicInbox::MboxLock->defaults);
+ my $mbl = PublicInbox::MboxLock->acq($input, 0, $m);
+ $self->input_fh($ifmt, $mbl->{fh}, $input);
+ } elsif (-d _ && (-d "$input/cur" || -d "$input/new")) {
+ return $lei->fail(<<EOM) if $ifmt && $ifmt ne 'maildir';
+$input appears to a be a maildir, not $ifmt
+EOM
+ PublicInbox::MdirReader::maildir_each_eml($input,
\&_import_maildir,
- $lei->{sto}, $lei->{opt}->{kw});
+ $lei->{sto}, $self->{-import_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};
+ my $in = delete $self->{0};
+ $self->input_fh($lei->{opt}->{'in-format'}, $in, '<stdin>');
}
+no warnings 'once';
+*ipc_atfork_child = \&PublicInbox::LeiInput::input_only_atfork_child;
+
+# the following works even when LeiAuth is lazy-loaded
+*net_merge_all = \&PublicInbox::LeiAuth::net_merge_all;
1;