# Copyright (C) 2020-2021 all contributors
# License: AGPL-3.0+
#
# Local storage (cache/memo) for lei(1), suitable for personal/private
# mail iff on encrypted device/FS. Based on v2, but only deduplicates
# based on git OID.
#
# for xref3, the following are constant: $eidx_key = '.', $xnum = -1
package PublicInbox::LeiStore;
use strict;
use v5.10.1;
use parent qw(PublicInbox::Lock PublicInbox::IPC);
use PublicInbox::ExtSearchIdx;
use PublicInbox::Import;
use PublicInbox::InboxWritable qw(eml_from_path);
use PublicInbox::V2Writable;
use PublicInbox::ContentHash qw(content_hash);
use PublicInbox::MID qw(mids);
use PublicInbox::LeiSearch;
use PublicInbox::MDA;
use List::Util qw(max);
sub new {
my (undef, $dir, $opt) = @_;
my $eidx = PublicInbox::ExtSearchIdx->new($dir, $opt);
my $self = bless { priv_eidx => $eidx }, __PACKAGE__;
eidx_init($self)->done if $opt->{creat};
$self;
}
sub git { $_[0]->{priv_eidx}->git } # read-only
sub packing_factor { $PublicInbox::V2Writable::PACKING_FACTOR }
sub rotate_bytes {
$_[0]->{rotate_bytes} // ((1024 * 1024 * 1024) / $_[0]->packing_factor)
}
sub git_pfx { "$_[0]->{priv_eidx}->{topdir}/local" };
sub git_epoch_max {
my ($self) = @_;
if (opendir(my $dh, $self->git_pfx)) {
max(map {
substr($_, 0, -4) + 0; # drop ".git" suffix
} grep(/\A[0-9]+\.git\z/, readdir($dh))) // 0;
} else {
$!{ENOENT} ? 0 : die("opendir ${\$self->git_pfx}: $!\n");
}
}
sub git_ident ($) {
my ($git) = @_;
chomp(my $i = $git->qx(qw(var GIT_COMMITTER_IDENT)));
warn "$git->{git_dir} GIT_COMMITTER_IDENT failed\n" if $?;
$i =~ /\A(.+) <([^>]+)> [0-9]+ [-\+]?[0-9]+$/ ? ($1, $2) :
('lei user', 'x@example.com')
}
sub importer {
my ($self) = @_;
my $max;
my $im = $self->{im};
if ($im) {
return $im if $im->{bytes_added} < $self->rotate_bytes;
delete $self->{im};
$im->done;
undef $im;
$self->checkpoint;
$max = $self->git_epoch_max + 1;
}
my $pfx = $self->git_pfx;
$max //= $self->git_epoch_max;
while (1) {
my $latest = "$pfx/$max.git";
my $old = -e $latest;
PublicInbox::Import::init_bare($latest);
my $git = PublicInbox::Git->new($latest);
$git->qx(qw(config core.sharedRepository 0600)) if !$old;
my $packed_bytes = $git->packed_bytes;
my $unpacked_bytes = $packed_bytes / $self->packing_factor;
if ($unpacked_bytes >= $self->rotate_bytes) {
$max++;
next;
}
my ($n, $e) = git_ident($git);
$self->{im} = $im = PublicInbox::Import->new($git, $n, $e);
$im->{bytes_added} = int($packed_bytes / $self->packing_factor);
$im->{lock_path} = undef;
$im->{path_type} = 'v2';
return $im;
}
}
sub search {
PublicInbox::LeiSearch->new($_[0]->{priv_eidx}->{topdir});
}
sub eidx_init {
my ($self) = @_;
my $eidx = $self->{priv_eidx};
$eidx->idx_init({-private => 1});
$eidx;
}
sub _docids_for ($$) {
my ($self, $eml) = @_;
my %docids;
my ($chash, $mids) = PublicInbox::LeiSearch::content_key($eml);
my $eidx = eidx_init($self);
my $oidx = $eidx->{oidx};
my $im = $self->{im};
for my $mid (@$mids) {
my ($id, $prev);
while (my $cur = $oidx->next_by_mid($mid, \$id, \$prev)) {
my $oid = $cur->{blob};
my $docid = $cur->{num};
my $bref = $im ? $im->cat_blob($oid) : undef;
$bref //= $eidx->git->cat_file($oid) // do {
warn "W: $oid (#$docid) <$mid> not found\n";
next;
};
local $self->{current_info} = $oid;
my $x = PublicInbox::Eml->new($bref);
$docids{$docid} = $docid if content_hash($x) eq $chash;
}
}
sort { $a <=> $b } values %docids;
}
sub set_eml_keywords {
my ($self, $eml, @kw) = @_;
my $eidx = eidx_init($self);
my @docids = _docids_for($self, $eml);
for my $docid (@docids) {
$eidx->idx_shard($docid)->ipc_do('set_keywords', $docid, @kw);
}
\@docids;
}
sub add_eml_keywords {
my ($self, $eml, @kw) = @_;
my $eidx = eidx_init($self);
my @docids = _docids_for($self, $eml);
for my $docid (@docids) {
$eidx->idx_shard($docid)->ipc_do('add_keywords', $docid, @kw);
}
\@docids;
}
sub remove_eml_keywords {
my ($self, $eml, @kw) = @_;
my $eidx = eidx_init($self);
my @docids = _docids_for($self, $eml);
for my $docid (@docids) {
$eidx->idx_shard($docid)->ipc_do('remove_keywords', $docid, @kw)
}
\@docids;
}
# cf: https://doc.dovecot.org/configuration_manual/mail_location/mbox/
my %status2kw = (F => 'flagged', A => 'answered', R => 'seen', T => 'draft');
# O (old/non-recent), and D (deleted) aren't in JMAP,
# so probably won't be supported by us.
sub mbox_keywords {
my $eml = $_[-1];
my $s = "@{[$eml->header_raw('X-Status'),$eml->header_raw('Status')]}";
my %kw;
$s =~ s/([FART])/$kw{$status2kw{$1}} = 1/sge;
sort(keys %kw);
}
# TODO: move this to MdirReader, maybe...
# cf: https://cr.yp.to/proto/maildir.html
my %c2kw = ('D' => 'draft', F => 'flagged', R => 'answered', S => 'seen');
sub maildir_keywords {
$_[-1] =~ /:2,([A-Z]+)\z/i ?
sort(map { $c2kw{$_} // () } split(//, $1)) : ();
}
sub add_eml {
my ($self, $eml, @kw) = @_;
my $im = $self->importer; # may create new epoch
my $eidx = eidx_init($self); # writes ALL.git/objects/info/alternates
my $oidx = $eidx->{oidx};
my $smsg = bless { -oidx => $oidx }, 'PublicInbox::Smsg';
$im->add($eml, undef, $smsg) or return; # duplicate returns undef
local $self->{current_info} = $smsg->{blob};
if (my @docids = _docids_for($self, $eml)) {
for my $docid (@docids) {
my $idx = $eidx->idx_shard($docid);
$oidx->add_xref3($docid, -1, $smsg->{blob}, '.');
# add_eidx_info for List-Id
$idx->ipc_do('add_eidx_info', $docid, '.', $eml);
$idx->ipc_do('add_keywords', $docid, @kw) if @kw;
}
\@docids;
} else {
$smsg->{num} = $oidx->adj_counter('eidx_docid', '+');
$oidx->add_overview($eml, $smsg);
$oidx->add_xref3($smsg->{num}, -1, $smsg->{blob}, '.');
my $idx = $eidx->idx_shard($smsg->{num});
$idx->index_eml($eml, $smsg);
$idx->ipc_do('add_keywords', $smsg->{num}, @kw) if @kw;
$smsg;
}
}
sub set_eml {
my ($self, $eml, @kw) = @_;
add_eml($self, $eml, @kw) // set_eml_keywords($self, $eml, @kw);
}
sub set_eml_from_maildir {
my ($self, $f, $set_kw) = @_;
my $eml = eml_from_path($f) or return;
set_eml($self, $eml, $set_kw ? maildir_keywords($f) : ());
}
sub checkpoint {
my ($self, $wait) = @_;
if (my $im = $self->{im}) {
$wait ? $im->barrier : $im->checkpoint;
}
$self->{priv_eidx}->checkpoint($wait);
}
sub done {
my ($self) = @_;
my $err = '';
if (my $im = delete($self->{im})) {
eval { $im->done };
if ($@) {
$err .= "import done: $@\n";
warn $err;
}
}
$self->{priv_eidx}->done;
die $err if $err;
}
sub ipc_atfork_child {
my ($self) = @_;
my $lei = delete $self->{lei};
$lei->lei_atfork_child(1) if $lei;
$self->SUPER::ipc_atfork_child;
}
sub write_prepare {
my ($self, $lei) = @_;
$self->ipc_lock_init;
# 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->ipc_worker_spawn('lei_store', $lei->oldset, { lei => $lei });
$lei->{sto} = $self;
}
1;