X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiImport.pm;h=2d91e4c4aa25e1d428a595712efc1bd6a0cb1256;hb=71eb48442e0f5403e9a5c3f0ccf8257600efe392;hp=2efd4935ab7d3d63d1c36460d054513205fed4c7;hpb=bdecd7ed8e0dcf0b45491b947cd737ba8cfe38a3;p=public-inbox.git

diff --git a/lib/PublicInbox/LeiImport.pm b/lib/PublicInbox/LeiImport.pm
index 2efd4935..2d91e4c4 100644
--- a/lib/PublicInbox/LeiImport.pm
+++ b/lib/PublicInbox/LeiImport.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2021 all contributors <meta@public-inbox.org>
+# Copyright (C) all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # front-end for the "lei import" sub-command
@@ -6,6 +6,7 @@ package PublicInbox::LeiImport;
 use strict;
 use v5.10.1;
 use parent qw(PublicInbox::IPC PublicInbox::LeiInput);
+use PublicInbox::InboxWritable qw(eml_from_path);
 
 # /^input_/ subs are used by (or override) PublicInbox::LeiInput superclass
 
@@ -15,7 +16,7 @@ sub input_eml_cb { # used by PublicInbox::LeiInput::input_fh
 	if (my $all_vmd = $self->{all_vmd}) {
 		@$vmd{keys %$all_vmd} = values %$all_vmd;
 	}
-	$self->{lei}->{sto}->ipc_do('set_eml', $eml, $vmd, $xoids);
+	$self->{lei}->{sto}->wq_do('set_eml', $eml, $vmd, $xoids);
 }
 
 sub input_mbox_cb { # MboxReader callback
@@ -28,17 +29,28 @@ sub input_mbox_cb { # MboxReader callback
 	input_eml_cb($self, $eml, $vmd);
 }
 
-sub input_maildir_cb { # maildir_each_eml cb
-	my ($f, $kw, $eml, $self) = @_;
+sub pmdir_cb { # called via wq_io_do from LeiPmdir->each_mdir_fn
+	my ($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 => $kw } : undef;
-	if ($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";
-		}
+	if (scalar @docids) {
+		$lse->kw_changed(undef, $kw, \@docids) or return;
+	}
+	if (my $eml = eml_from_path($f)) {
+		$vmd->{sync_info} = [ $folder, \$bn ] if $self->{-mail_sync};
+		$self->input_eml_cb($eml, $vmd);
 	}
-	$self->input_eml_cb($eml, $vmd);
 }
 
 sub input_net_cb { # imap_each / nntp_each
@@ -62,18 +74,22 @@ sub do_import_index ($$@) {
 	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;
+	$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;
 
-	$lei->ale; # initialize for workers to read
-	my $j = $lei->{opt}->{jobs} // scalar(@{$self->{inputs}}) || 1;
+	my $j = $lei->{opt}->{jobs} // 0;
+	$j =~ /\A([0-9]+),[0-9]+\z/ and $j = $1 + 0;
+	$j ||= scalar(@{$self->{inputs}}) || 1;
 	my $ikw;
-	if (my $net = $lei->{net}) {
+	my $net = $lei->{net};
+	if ($net) {
 		# $j = $net->net_concurrency($j); TODO
 		if ($lei->{opt}->{incremental} // 1) {
 			$net->{incremental} = 1;
-			$net->{-lms_ro} = $sto->search->lms // 0;
-			if ($self->{-import_kw} && $net->{-lms_ro} &&
+			$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);
@@ -84,16 +100,11 @@ sub do_import_index ($$@) {
 		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->{opt}->{'new-only'} && (!$net || !$net->{imap_order})) and
+		warn "# --new-only is only for IMAP\n";
 	$lei->{-eml_noisy} = 1;
-	(my $op_c, $ops) = $lei->workers_start($self, $j, $ops);
-	$lei->{wq1} = $self;
 	$lei->{-err_type} = 'non-fatal';
-	$ikw->wq_close(1) if $ikw;
-	net_merge_all_done($self) unless $lei->{auth};
-	$op_c->op_wait_event($ops);
+	$lei->wq1_start($self, $j);
 }
 
 sub lei_import { # the main "lei import" method
@@ -104,16 +115,22 @@ sub lei_import { # the main "lei import" method
 
 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 { $match_cb->($_) } $lms->folders;
+	my ($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;
 }
 
 no warnings 'once';
 *ipc_atfork_child = \&PublicInbox::LeiInput::input_only_atfork_child;
 *net_merge_all_done = \&PublicInbox::LeiInput::input_only_net_merge_all_done;
 
-# the following works even when LeiAuth is lazy-loaded
-*net_merge_all = \&PublicInbox::LeiAuth::net_merge_all;
 1;