-# Copyright (C) 2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2020-2021 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
package PublicInbox::LeiStore;
use strict;
use v5.10.1;
-use parent qw(PublicInbox::Lock);
+use parent qw(PublicInbox::Lock PublicInbox::IPC);
use PublicInbox::SearchIdx qw(crlf_adjust);
use PublicInbox::ExtSearchIdx;
use PublicInbox::Import;
use PublicInbox::InboxWritable;
use PublicInbox::V2Writable;
-use PublicInbox::ContentHash qw(content_hash);
-use PublicInbox::MID qw(mids);
+use PublicInbox::ContentHash qw(content_hash content_digest);
+use PublicInbox::MID qw(mids mids_in);
use PublicInbox::LeiSearch;
+use List::Util qw(max);
sub new {
my (undef, $dir, $opt) = @_;
my $eidx = PublicInbox::ExtSearchIdx->new($dir, $opt);
- bless { priv_eidx => $eidx }, __PACKAGE__;
+ my $self = bless { priv_eidx => $eidx }, __PACKAGE__;
+ if ($opt->{creat}) {
+ PublicInbox::SearchIdx::load_xapian_writable();
+ eidx_init($self);
+ }
+ $self;
}
sub git { $_[0]->{priv_eidx}->git } # read-only
sub git_epoch_max {
my ($self) = @_;
- my $pfx = $self->git_pfx;
- my $max = 0;
- return $max unless -d $pfx ;
- opendir my $dh, $pfx or die "opendir $pfx: $!\n";
- while (defined(my $git_dir = readdir($dh))) {
- $git_dir =~ m!\A([0-9]+)\.git\z! or next;
- $max = $1 + 0 if $1 > $max;
+ 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");
}
- $max;
+}
+
+sub git_ident ($) {
+ 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 {
while (1) {
my $latest = "$pfx/$max.git";
my $old = -e $latest;
+ PublicInbox::Import::init_bare($latest);
my $git = PublicInbox::Git->new($latest);
- PublicInbox::Import::init_bare({ git => $git });
$git->qx(qw(config core.sharedRepository 0600)) if !$old;
my $packed_bytes = $git->packed_bytes;
my $unpacked_bytes = $packed_bytes / $self->packing_factor;
$max++;
next;
}
- chomp(my $i = $git->qx(qw(var GIT_COMMITTER_IDENT)));
- die "$git->{git_dir} GIT_COMMITTER_IDENT failed\n" if $?;
- my ($n, $e) = ($i =~ /\A(.+) <([^>]+)> [0-9]+ [-\+]?[0-9]+$/g)
- or die "could not extract name/email from `$i'\n";
+ 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;
$eidx;
}
+# when a message has no Message-IDs at all, this is needed for
+# unsent Draft messages, at least
+sub _fake_mid_for ($$) {
+ my ($eml, $dig) = @_;
+ my $mids = mids_in($eml, qw(X-Alt-Message-ID Resent-Message-ID));
+ $eml->{-lei_fake_mid} =
+ $mids->[0] // PublicInbox::Import::digest2mid($dig, $eml);
+}
+
sub _docids_for ($$) {
my ($self, $eml) = @_;
my %docids;
- my $chash = content_hash($eml);
+ my $dig = content_digest($eml);
+ my $chash = $dig->clone->digest;
my $eidx = eidx_init($self);
my $oidx = $eidx->{oidx};
my $im = $self->{im};
- for my $mid (@{mids($eml)}) {
+ my $mids = mids($eml);
+ $mids->[0] //= _fake_mid_for($eml, $dig);
+ for my $mid (@$mids) {
my ($id, $prev);
while (my $cur = $oidx->next_by_mid($mid, \$id, \$prev)) {
my $oid = $cur->{blob};
\@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);
+}
+
+# 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, $eml) = @_;
+ my ($self, $eml, @kw) = @_;
my $eidx = eidx_init($self);
my $oidx = $eidx->{oidx};
my $smsg = bless { -oidx => $oidx }, 'PublicInbox::Smsg';
my $idx = $eidx->idx_shard($docid);
$oidx->add_xref3($docid, -1, $smsg->{blob}, '.');
$idx->shard_add_eidx_info($docid, '.', $eml); # List-Id
+ $idx->shard_add_keywords($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});
$idx->index_raw($msgref, $eml, $smsg);
+ $idx->shard_add_keywords($smsg->{num}, @kw) if @kw;
+ $smsg;
}
- $smsg->{blob}
+}
+
+sub set_eml {
+ my ($self, $eml, @kw) = @_;
+ add_eml($self, $eml, @kw) // set_eml_keywords($self, $eml, @kw);
}
sub done {