package PublicInbox::LeiImport;
use strict;
use v5.10.1;
-use parent qw(PublicInbox::IPC);
-use PublicInbox::Eml;
-use PublicInbox::InboxWritable qw(eml_from_path);
-use PublicInbox::PktOp;
+use parent qw(PublicInbox::IPC PublicInbox::LeiInput);
-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
- $lei->dclose;
-}
+# /^input_/ subs are used by (or override) PublicInbox::LeiInput superclass
-sub import_done { # EOF callback for main daemon
- my ($lei) = @_;
- my $imp = delete $lei->{imp} or return;
- $imp->wq_wait_old(\&import_done_wait, $lei);
+sub input_eml_cb { # used by PublicInbox::LeiInput::input_fh
+ my ($self, $eml, $vmd) = @_;
+ my $xoids = $self->{lei}->{ale}->xoids_for($eml);
+ if (my $all_vmd = $self->{all_vmd}) {
+ @$vmd{keys %$all_vmd} = values %$all_vmd;
+ }
+ $self->{lei}->{sto}->ipc_do('set_eml', $eml, $vmd, $xoids);
}
-sub call { # the main "lei import" method
- my ($cls, $lei, @argv) = @_;
- my $sto = $lei->_lei_store(1);
- $sto->write_prepare($lei);
- $lei->{opt}->{kw} //= 1;
- my $fmt = $lei->{opt}->{'format'};
- my $self = $lei->{imp} = bless {}, $cls;
- my @f;
- for my $x (@argv) {
- if (-f $x) { push @f, $x }
- elsif (-d _) { require PublicInbox::MdirReader }
- }
- (@f && !$fmt) and
- return $lei->fail("--format unset for regular file(s):\n@f");
- if (@f && $fmt ne 'eml') {
- require PublicInbox::MboxReader;
- PublicInbox::MboxReader->can($fmt) or
- return $lei->fail( "--format=$fmt unrecognized\n");
- }
- $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_io_do('import_stdin', []) if $self->{0};
- for my $x (@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}) { $op->event_step }
+sub input_mbox_cb { # MboxReader callback
+ my ($eml, $self) = @_;
+ my $vmd;
+ if ($self->{-import_kw}) {
+ my $kw = PublicInbox::MboxReader::mbox_keywords($eml);
+ $vmd = { kw => $kw } if scalar(@$kw);
}
+ input_eml_cb($self, $eml, $vmd);
}
-sub ipc_atfork_child {
- my ($self) = @_;
- $self->{lei}->lei_atfork_child;
- $self->SUPER::ipc_atfork_child;
+sub input_maildir_cb { # maildir_each_eml cb
+ my ($f, $kw, $eml, $self) = @_;
+ my $vmd = $self->{-import_kw} ? { kw => $kw } : undef;
+ if ($self->{-mail_sync}) {
+ if ($f =~ m!\A(.+?)/(?:new|cur)/([^/]+)\z!) { # ugh...
+ $vmd->{sync_info} = [ "maildir:$1", \(my $n = $2) ];
+ } else {
+ warn "E: $f was not from a Maildir?\n";
+ }
+ }
+ input_eml_cb($self, $eml, $vmd);
}
-sub _import_fh {
- my ($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 $@;
+sub input_net_cb { # imap_each / nntp_each
+ my ($url, $uid, $kw, $eml, $self) = @_;
+ my $vmd = $self->{-import_kw} ? { kw => $kw } : undef;
+ $vmd->{sync_info} = [ $url, $uid ] if $self->{-mail_sync};
+ input_eml_cb($self, $eml, $vmd);
}
-sub _import_maildir { # maildir_each_file cb
- my ($f, $sto, $set_kw) = @_;
- $sto->ipc_do('set_eml_from_maildir', $f, $set_kw);
+sub net_merge_complete { # callback used by LeiAuth
+ my ($self) = @_;
+ $self->wq_io_do('process_inputs');
+ $self->wq_close(1);
}
-sub import_path_url {
- my ($self, $x) = @_;
- my $lei = $self->{lei};
- # TODO auto-detect?
- if (-f $x) {
- open my $fh, '<', $x or return $lei->child_error(1 >> 8, <<"");
-unable to open $x: $!
+sub lei_import { # the main "lei import" method
+ my ($lei, @inputs) = @_;
+ my $sto = $lei->_lei_store(1);
+ $sto->write_prepare($lei);
+ my $self = bless {}, __PACKAGE__;
+ $self->{-import_kw} = $lei->{opt}->{kw} // 1;
+ my $vmd_mod = $self->vmd_mod_extract(\@inputs);
+ return $lei->fail(join("\n", @{$vmd_mod->{err}})) if $vmd_mod->{err};
+ $self->{all_vmd} = $vmd_mod if scalar keys %$vmd_mod;
+ $self->prepare_inputs($lei, \@inputs) or return;
+ $self->{-mail_sync} = $lei->{opt}->{'mail-sync'} // 1;
- _import_fh($lei, $fh, $x);
- } elsif (-d _ && (-d "$x/cur" || -d "$x/new")) {
- PublicInbox::MdirReader::maildir_each_file($x,
- \&_import_maildir,
- $lei->{sto}, $lei->{opt}->{kw});
+ $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
+ if ($lei->{opt}->{incremental} // 1) {
+ $net->{incremental} = 1;
+ $net->{-lms_ro} = $lei->_lei_store->search->lms // 0;
+ }
} else {
- $lei->fail("$x unsupported (TODO)");
+ my $nproc = $self->detect_nproc;
+ $j = $nproc if $j > $nproc;
}
+ my $ops = {};
+ $lei->{auth}->op_merge($ops, $self) if $lei->{auth};
+ $self->{-wq_nr_workers} = $j // 1; # locked
+ $lei->{-eml_noisy} = 1;
+ (my $op_c, $ops) = $lei->workers_start($self, 'lei-import', $j, $ops);
+ $lei->{wq1} = $self;
+ $lei->{-err_type} = 'non-fatal';
+ net_merge_complete($self) unless $lei->{auth};
+ $op_c->op_wait_event($ops);
}
-sub import_stdin {
- my ($self) = @_;
- _import_fh($self->{lei}, $self->{0}, '<stdin>');
+sub _complete_import {
+ my ($lei, @argv) = @_;
+ my $sto = $lei->_lei_store or return;
+ my $lms = $sto->search->lms or return;
+ my $match_cb = $lei->complete_url_prepare(\@argv);
+ map { $match_cb->($_) } $lms->folders;
}
+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;