X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiImport.pm;h=2d91e4c4aa25e1d428a595712efc1bd6a0cb1256;hb=71eb48442e0f5403e9a5c3f0ccf8257600efe392;hp=3a99570e3767c9b0ec9261f81d66fb2c16b0227a;hpb=757652fd1ad6843c984610263a2a0b336c974111;p=public-inbox.git diff --git a/lib/PublicInbox/LeiImport.pm b/lib/PublicInbox/LeiImport.pm index 3a99570e..2d91e4c4 100644 --- a/lib/PublicInbox/LeiImport.pm +++ b/lib/PublicInbox/LeiImport.pm @@ -1,106 +1,136 @@ -# Copyright (C) 2021 all contributors +# Copyright (C) all contributors # License: AGPL-3.0+ # front-end for the "lei import" sub-command package PublicInbox::LeiImport; use strict; use v5.10.1; -use parent qw(PublicInbox::IPC); -use PublicInbox::MboxReader; -use PublicInbox::Eml; +use parent qw(PublicInbox::IPC PublicInbox::LeiInput); +use PublicInbox::InboxWritable qw(eml_from_path); -sub _import_eml { # MboxReader callback - my ($eml, $sto, $set_kw) = @_; - $sto->ipc_do('set_eml', $eml, $set_kw ? $sto->mbox_keywords($eml) : ()); +# /^input_/ subs are used by (or override) PublicInbox::LeiInput superclass + +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}->wq_do('set_eml', $eml, $vmd, $xoids); } -sub import_done { # EOF callback for main daemon - my ($lei) = @_; - my $imp = delete $lei->{imp}; - $imp->wq_wait_old($lei) if $imp; - my $wait = $lei->{sto}->ipc_do('done'); - $lei->dclose; +sub input_mbox_cb { # MboxReader callback + my ($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, $vmd); } -sub call { # the main "lei import" method - my ($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; - 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_io_do('import_stdin', []) if $self->{0}; - for my $x (@argv) { - $self->wq_io_do('import_path_url', [], $x); +sub pmdir_cb { # called via wq_io_do from LeiPmdir->each_mdir_fn + my ($self, $f, $fl) = @_; + my ($folder, $bn) = ($f =~ m!\A(.+?)/(?:new|cur)/([^/]+)\z!) or + die "BUG: $f was not from a Maildir?\n"; + my $kw = PublicInbox::MdirReader::flags2kw($fl); + substr($folder, 0, 0) = 'maildir:'; # add prefix + my $lse = $self->{lse} //= $self->{lei}->{sto}->search; + my $lms = $self->{-lms_rw} //= $self->{lei}->lms; # may be 0 or undef + my @oidbin = $lms ? $lms->name_oidbin($folder, $bn) : (); + @oidbin > 1 and warn("W: $folder/*/$$bn not unique:\n", + map { "\t".unpack('H*', $_)."\n" } @oidbin); + my %seen; + my @docids = sort { $a <=> $b } grep { !$seen{$_}++ } + map { $lse->over->oidbin_exists($_) } @oidbin; + my $vmd = $self->{-import_kw} ? { kw => $kw } : undef; + if (scalar @docids) { + $lse->kw_changed(undef, $kw, \@docids) or return; } - $self->wq_close(1); - $lei->event_step_init; # wait for shutdowns - if ($lei->{oneshot}) { - while ($op->{sock}) { $op->event_step } + if (my $eml = eml_from_path($f)) { + $vmd->{sync_info} = [ $folder, \$bn ] if $self->{-mail_sync}; + $self->input_eml_cb($eml, $vmd); } } -sub ipc_atfork_child { - my ($self) = @_; - $self->{lei}->lei_atfork_child; - $self->SUPER::ipc_atfork_child; +sub input_net_cb { # imap_each / nntp_each + my ($uri, $uid, $kw, $eml, $self) = @_; + if (defined $eml) { + my $vmd = $self->{-import_kw} ? { kw => $kw } : undef; + $vmd->{sync_info} = [ $$uri, $uid ] if $self->{-mail_sync}; + $self->input_eml_cb($eml, $vmd); + } elsif (my $ikw = $self->{lei}->{ikw}) { # old message, kw only + # we send $uri as a bare SCALAR and not a URIimap ref to + # reduce socket traffic: + $ikw->wq_io_do('ck_update_kw', [], $$uri, $uid, $kw); + } } -sub _import_fh { - my ($lei, $fh, $x) = @_; - my $set_kw = $lei->{opt}->{kw}; - my $fmt = $lei->{opt}->{'format'}; - eval { - if ($fmt eq 'eml') { - my $buf = do { local $/; <$fh> } // - return $lei->child_error(1 >> 8, <<""); - error reading $x: $! - - my $eml = PublicInbox::Eml->new(\$buf); - _import_eml($eml, $lei->{sto}, $set_kw); - } else { # some mbox - my $cb = PublicInbox::MboxReader->can($fmt); - $cb or return $lei->child_error(1 >> 8, <<""); - --format $fmt unsupported for $x +sub do_import_index ($$@) { + my ($self, $lei, @inputs) = @_; + my $sto = $lei->_lei_store(1); + $sto->write_prepare($lei); + $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; + $lei->ale; # initialize for workers to read (before LeiPmdir->new) + $self->{-mail_sync} = $lei->{opt}->{'mail-sync'} // 1; + $self->prepare_inputs($lei, \@inputs) or return; - $cb->(undef, $fh, \&_import_eml, $lei->{sto}, $set_kw); + my $j = $lei->{opt}->{jobs} // 0; + $j =~ /\A([0-9]+),[0-9]+\z/ and $j = $1 + 0; + $j ||= scalar(@{$self->{inputs}}) || 1; + my $ikw; + my $net = $lei->{net}; + if ($net) { + # $j = $net->net_concurrency($j); TODO + if ($lei->{opt}->{incremental} // 1) { + $net->{incremental} = 1; + $net->{-lms_rw} = $lei->lms // 0; + if ($self->{-import_kw} && $net->{-lms_rw} && + !$lei->{opt}->{'new-only'} && + $net->{imap_order}) { + require PublicInbox::LeiImportKw; + $ikw = PublicInbox::LeiImportKw->new($lei); + $net->{each_old} = 1; + } } - }; - $lei->child_error(1 >> 8, ": $@") if $@; + } else { + my $nproc = $self->detect_nproc; + $j = $nproc if $j > $nproc; + } + ($lei->{opt}->{'new-only'} && (!$net || !$net->{imap_order})) and + warn "# --new-only is only for IMAP\n"; + $lei->{-eml_noisy} = 1; + $lei->{-err_type} = 'non-fatal'; + $lei->wq1_start($self, $j); } -sub import_path_url { - my ($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 $self = bless {}, __PACKAGE__; + do_import_index($self, $lei, @inputs); +} - _import_fh($lei, $fh, $x); - } else { - $lei->fail("$x unsupported (TODO)"); +sub _complete_import { + my ($lei, @argv) = @_; + my ($re, $cur, $match_cb) = $lei->complete_url_prepare(\@argv); + my @k = $lei->url_folder_cache->keys($argv[-1] // undef, 1); + my @L = eval { $lei->_lei_store->search->all_terms('L') }; + push(@k, map { "+L:$_" } @L); + my @m = map { $match_cb->($_) } @k; + my %f = map { $_ => 1 } (@m ? @m : @k); + if (my $lms = $lei->lms) { + @k = $lms->folders($argv[-1] // undef, 1); + @m = map { $match_cb->($_) } @k; + if (@m) { @f{@m} = @m } else { @f{@k} = @k } } + keys %f; } -sub import_stdin { - my ($self) = @_; - _import_fh($self->{lei}, $self->{0}, ''); -} +no warnings 'once'; +*ipc_atfork_child = \&PublicInbox::LeiInput::input_only_atfork_child; +*net_merge_all_done = \&PublicInbox::LeiInput::input_only_net_merge_all_done; 1;