# Copyright (C) 2015-2020 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
-# based on notmuch, but with no concept of folders, files or flags
+# based on notmuch, but with no concept of folders, files
#
# Indexes mail with Xapian and our (SQLite-based) ::Msgmap for use
# with the web and NNTP interfaces. This index maintains thread
use PublicInbox::MID qw(mids_for_index mids);
use PublicInbox::MsgIter;
use PublicInbox::IdxStack;
-use Carp qw(croak);
+use Carp qw(croak carp);
use POSIX qw(strftime);
use Time::Local qw(timegm);
use PublicInbox::OverIdx;
use PublicInbox::Git qw(git_unquote);
use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
our @EXPORT_OK = qw(crlf_adjust log2stack is_ancestor check_size prepare_stack
- index_text term_generator add_val);
+ index_text term_generator add_val is_bad_blob);
my $X = \%PublicInbox::Search::X;
our ($DB_CREATE_OR_OPEN, $DB_OPEN);
our $DB_NO_SYNC = 0;
index_list_id($self, $doc, $hdr);
}
-sub add_xapian ($$$$) {
+sub eml2doc ($$$;$) {
my ($self, $eml, $smsg, $mids) = @_;
+ $mids //= mids_for_index($eml);
my $doc = $X->{Document}->new;
add_val($doc, PublicInbox::Search::TS(), $smsg->{ts});
my @ds = gmtime($smsg->{ds});
index_headers($self, $smsg);
if (defined(my $eidx_key = $smsg->{eidx_key})) {
- $doc->add_boolean_term('O'.$eidx_key);
+ $doc->add_boolean_term('O'.$eidx_key) if $eidx_key ne '.';
}
msg_iter($eml, \&index_xapian, [ $self, $doc ]);
index_ids($self, $doc, $eml, $mids);
}
}
}
+ $doc;
+}
+
+sub add_xapian ($$$$) {
+ my ($self, $eml, $smsg, $mids) = @_;
+ my $doc = eml2doc($self, $eml, $smsg, $mids);
$self->{xdb}->replace_document($smsg->{num}, $doc);
}
begin_txn_lazy($self);
my $doc = _get_doc($self, $docid) or return;
term_generator($self)->set_document($doc);
- $doc->add_boolean_term('O'.$eidx_key);
+ $doc->add_boolean_term('O'.$eidx_key) if $eidx_key ne '.';
index_list_id($self, $doc, $eml);
$self->{xdb}->replace_document($docid, $doc);
}
$self->{xdb}->replace_document($docid, $doc);
}
+sub set_keywords {
+ my ($self, $docid, @kw) = @_;
+ begin_txn_lazy($self);
+ my $doc = _get_doc($self, $docid) or return;
+ my %keep = map { $_ => 1 } @kw;
+ my %add = %keep;
+ my @rm;
+ my $end = $doc->termlist_end;
+ for (my $cur = $doc->termlist_begin; $cur != $end; $cur++) {
+ $cur->skip_to('K');
+ last if $cur == $end;
+ my $kw = $cur->get_termname;
+ $kw =~ s/\AK//s or next;
+ $keep{$kw} ? delete($add{$kw}) : push(@rm, $kw);
+ }
+ return unless (scalar(@rm) + scalar(keys %add));
+ $doc->remove_term('K'.$_) for @rm;
+ $doc->add_boolean_term('K'.$_) for (keys %add);
+ $self->{xdb}->replace_document($docid, $doc);
+}
+
+sub add_keywords {
+ my ($self, $docid, @kw) = @_;
+ begin_txn_lazy($self);
+ my $doc = _get_doc($self, $docid) or return;
+ $doc->add_boolean_term('K'.$_) for @kw;
+ $self->{xdb}->replace_document($docid, $doc);
+}
+
+sub remove_keywords {
+ my ($self, $docid, @kw) = @_;
+ begin_txn_lazy($self);
+ my $doc = _get_doc($self, $docid) or return;
+ my $replace;
+ eval {
+ $doc->remove_term('K'.$_);
+ $replace = 1
+ } for @kw;
+ $self->{xdb}->replace_document($docid, $doc) if $replace;
+}
+
sub get_val ($$) {
my ($doc, $col) = @_;
sortable_unserialise($doc->get_value($col));
}
}
+sub is_bad_blob ($$$$) {
+ my ($oid, $type, $size, $expect_oid) = @_;
+ if ($type ne 'blob') {
+ carp "W: $expect_oid is not a blob (type=$type)";
+ return 1;
+ }
+ croak "BUG: $oid != $expect_oid" if $oid ne $expect_oid;
+ $size == 0 ? 1 : 0; # size == 0 means purged
+}
+
sub index_both { # git->cat_async callback
my ($bref, $oid, $type, $size, $sync) = @_;
+ return if is_bad_blob($oid, $type, $size, $sync->{oid});
my ($nr, $max) = @$sync{qw(nr max)};
++$$nr;
$$max -= $size;
$size += crlf_adjust($$bref);
my $smsg = bless { bytes => $size, blob => $oid }, 'PublicInbox::Smsg';
my $self = $sync->{sidx};
+ local $self->{current_info} = "$self->{current_info}: $oid";
my $eml = PublicInbox::Eml->new($bref);
$smsg->{num} = index_mm($self, $eml, $oid, $sync) or
die "E: could not generate NNTP article number for $oid";
sub unindex_both { # git->cat_async callback
my ($bref, $oid, $type, $size, $sync) = @_;
- unindex_eml($sync->{sidx}, $oid, PublicInbox::Eml->new($bref));
+ return if is_bad_blob($oid, $type, $size, $sync->{oid});
+ my $self = $sync->{sidx};
+ local $self->{current_info} = "$self->{current_info}: $oid";
+ unindex_eml($self, $oid, PublicInbox::Eml->new($bref));
# may be undef if leftover
if (defined(my $cur_cmt = $sync->{cur_cmt})) {
${$sync->{latest_cmt}} = $cur_cmt;
$sync->{index_oid} = \&index_both;
}
while (my ($f, $at, $ct, $oid, $cur_cmt) = $stk->pop_rec) {
- my $arg = { %$sync, cur_cmt => $cur_cmt };
+ my $arg = { %$sync, cur_cmt => $cur_cmt, oid => $oid };
last if $sync->{quit};
if ($f eq 'm') {
$arg->{autime} = $at;
my ($self, $opt) = @_;
my $tip = $opt->{ref} || 'HEAD';
my $ibx = $self->{ibx};
+ local $self->{current_info} = "$ibx->{inboxdir}";
$self->{batch_bytes} = $opt->{batch_size} // $BATCH_BYTES;
$ibx->git->batch_prepare;
my $pr = $opt->{-progress};
sub _commit_txn {
my ($self) = @_;
+ if (my $eidx = $self->{eidx}) {
+ $eidx->git->async_wait_all;
+ $eidx->{transact_bytes} = 0;
+ }
if (my $xdb = $self->{xdb}) {
set_metadata_once($self);
$xdb->commit_transaction;