-# Copyright (C) 2020-2021 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>
#
# Local storage (cache/memo) for lei(1), suitable for personal/private
use IO::Handle (); # ->autoflush
use Sys::Syslog qw(syslog openlog);
use Errno qw(EEXIST ENOENT);
+use PublicInbox::Syscall qw(rename_noreplace);
sub new {
my (undef, $dir, $opt) = @_;
my $dst = "$mdir/cur/$bn";
for my $d (@try) {
my $src = "$mdir/$d/$orig";
- if (link($src, $dst)) {
- if (!unlink($src) and $! != ENOENT) {
- syslog('warning', "unlink($src): $!");
- }
+ if (rename_noreplace($src, $dst)) {
# TODO: verify oidbin?
$self->{lms}->mv_src("maildir:$mdir",
$oidbin, \$orig, $bn);
} elsif ($! == EEXIST) { # lost race with "lei export-kw"?
return;
} elsif ($! != ENOENT) {
- syslog('warning', "link($src -> $dst): $!");
+ syslog('warning', "rename_noreplace($src -> $dst): $!");
}
}
for (@try) { return if -e "$mdir/$_/$orig" };
sub _lms_rw ($) { # it is important to have eidx processes open before lms
my ($self) = @_;
- my ($eidx, $tl) = eidx_init($self);
- $self->{lms} //= do {
+ $self->{lms} // do {
require PublicInbox::LeiMailSync;
+ my ($eidx, $tl) = eidx_init($self);
my $f = "$self->{priv_eidx}->{topdir}/mail_sync.sqlite3";
my $lms = PublicInbox::LeiMailSync->new($f);
$lms->lms_write_prepare;
- $lms;
+ $self->{lms} = $lms;
};
}
-sub set_sync_info {
- my ($self, $oidhex, $folder, $id) = @_;
- _lms_rw($self)->set_src(pack('H*', $oidhex), $folder, $id);
-}
-
sub _remove_if_local { # git->cat_async arg
my ($bref, $oidhex, $type, $size, $self) = @_;
$self->{im}->remove($bref) if $bref;
my ($self, @docids) = @_;
my $eidx = eidx_init($self);
for my $docid (@docids) {
- $eidx->idx_shard($docid)->ipc_do('xdb_remove', $docid);
- $eidx->{oidx}->delete_by_num($docid);
+ $eidx->remove_doc($docid);
$eidx->{oidx}->{dbh}->do(<<EOF, undef, $docid);
DELETE FROM xref3 WHERE docid = ?
EOF
$git->cat_async($oidhex, \&_remove_if_local, $self);
}
}
- $git->cat_async_wait;
+ $git->async_wait_all;
remove_docids($self, @docids);
\@docids;
}
sto_export_kw($self, $docid, $vmd);
}
+sub _docids_and_maybe_kw ($$) {
+ my ($self, $docids) = @_;
+ return $docids unless wantarray;
+ my $kw = {};
+ for my $num (@$docids) { # likely only 1, unless ContentHash changes
+ # can't use ->search->msg_keywords on uncommitted docs
+ my $idx = $self->{priv_eidx}->idx_shard($num);
+ my $tmp = eval { $idx->ipc_do('get_terms', 'K', $num) };
+ if ($@) { warn "#$num get_terms: $@" }
+ else { @$kw{keys %$tmp} = values(%$tmp) };
+ }
+ ($docids, [ sort keys %$kw ]);
+}
+
+sub _reindex_1 { # git->cat_async callback
+ my ($bref, $hex, $type, $size, $smsg) = @_;
+ my $self = delete $smsg->{-sto};
+ my ($eidx, $tl) = eidx_init($self);
+ $bref //= _lms_rw($self)->local_blob($hex, 1);
+ if ($bref) {
+ my $eml = PublicInbox::Eml->new($bref);
+ $smsg->{-merge_vmd} = 1; # preserve existing keywords
+ $eidx->idx_shard($smsg->{num})->index_eml($eml, $smsg);
+ } elsif ($type eq 'missing') {
+ # pre-release/buggy lei may've indexed external-only msgs,
+ # try to correct that, here
+ warn("E: missing $hex, culling (ancient lei artifact?)\n");
+ $smsg->{to} = $smsg->{cc} = $smsg->{from} = '';
+ $smsg->{bytes} = 0;
+ $eidx->{oidx}->update_blob($smsg, '');
+ my $eml = PublicInbox::Eml->new("\r\n\r\n");
+ $eidx->idx_shard($smsg->{num})->index_eml($eml, $smsg);
+ } else {
+ warn("E: $type $hex\n");
+ }
+}
+
+sub reindex_art {
+ my ($self, $art) = @_;
+ my ($eidx, $tl) = eidx_init($self);
+ my $smsg = $eidx->{oidx}->get_art($art) // return;
+ return if $smsg->{bytes} == 0; # external-only message
+ $smsg->{-sto} = $self;
+ $eidx->git->cat_async($smsg->{blob} // die("no blob (#$art)"),
+ \&_reindex_1, $smsg);
+}
+
+sub reindex_done {
+ my ($self) = @_;
+ my ($eidx, $tl) = eidx_init($self);
+ $eidx->git->async_wait_all;
+ # ->done to be called via sto_done_request
+}
+
sub add_eml {
my ($self, $eml, $vmd, $xoids) = @_;
my $im = $self->{-fake_im} // $self->importer; # may create new epoch
$smsg->{-eidx_git} = $eidx->git if !$self->{-fake_im};
my $im_mark = $im->add($eml, undef, $smsg);
if ($vmd && $vmd->{sync_info}) {
- set_sync_info($self, $smsg->{blob}, @{$vmd->{sync_info}});
+ _lms_rw($self)->set_src($smsg->oidbin, @{$vmd->{sync_info}});
+ }
+ unless ($im_mark) { # duplicate blob returns undef
+ return unless wantarray;
+ my @docids = $oidx->blob_exists($smsg->{blob});
+ return _docids_and_maybe_kw $self, \@docids;
}
- $im_mark or return; # duplicate blob returns undef
local $self->{current_info} = $smsg->{blob};
my $vivify_xvmd = delete($smsg->{-vivify_xvmd}) // []; # exact matches
}
_add_vmd($self, $idx, $docid, $vmd) if $vmd;
}
- $vivify_xvmd;
+ _docids_and_maybe_kw $self, $vivify_xvmd;
} elsif (my @docids = _docids_for($self, $eml)) {
# fuzzy match from within lei/store
for my $docid (@docids) {
$idx->ipc_do('add_eidx_info', $docid, '.', $eml);
_add_vmd($self, $idx, $docid, $vmd) if $vmd;
}
- \@docids;
- } else { # totally new message
+ _docids_and_maybe_kw $self, \@docids;
+ } else { # totally new message, no keywords
delete $smsg->{-oidx}; # for IPC-friendliness
$smsg->{num} = $oidx->adj_counter('eidx_docid', '+');
$oidx->add_overview($eml, $smsg);
my $idx = $eidx->idx_shard($smsg->{num});
$idx->index_eml($eml, $smsg);
_add_vmd($self, $idx, $smsg->{num}, $vmd) if $vmd;
- $smsg;
+ wantarray ? ($smsg, []) : $smsg;
}
}
return unless -e $dir;
my $old = delete $self->{-tmp_err};
my $pfx = POSIX::strftime('%Y%m%d%H%M%S', gmtime(time));
- my $err = File::Temp->new(TEMPLATE => "$pfx.$$.lei_storeXXXX",
+ my $err = File::Temp->new(TEMPLATE => "$pfx.$$.err-XXXX",
SUFFIX => '.err', DIR => $dir);
open STDERR, '>>', $err->filename or die "dup2: $!";
STDERR->autoflush(1); # shared with shard subprocesses
$self->SUPER::recv_and_run(@args);
}
+sub _sto_atexit { # awaitpid cb (via awaitpid_init)
+ my ($pid, $sto) = @_;
+ warn "lei/store PID:$pid died \$?=$?\n" if $?;
+}
+
sub write_prepare {
my ($self, $lei) = @_;
$lei // die 'BUG: $lei not passed';
# Mail we import into lei are private, so headers filtered out
# by -mda for public mail are not appropriate
local @PublicInbox::MDA::BAD_HEADERS = ();
- $self->{-wq_no_bcast} = 1;
+ $self->awaitpid_init(\&_sto_atexit); # outlives $lei
$self->wq_workers_start("lei/store $dir", 1, $lei->oldset, {
lei => $lei,
-err_wr => $w,