use PublicInbox::IdxStack;
use Carp qw(croak);
use POSIX qw(strftime);
+use Time::Local qw(timegm);
use PublicInbox::OverIdx;
use PublicInbox::Spawn qw(spawn nodatacow_dir);
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);
+our @EXPORT_OK = qw(crlf_adjust log2stack is_ancestor check_size prepare_stack);
my $X = \%PublicInbox::Search::X;
my ($DB_CREATE_OR_OPEN, $DB_OPEN);
our $DB_NO_SYNC = 0;
my $xapianlevels = qr/\A(?:full|medium)\z/;
my $hex = '[a-f0-9]';
my $OID = $hex .'{40,}';
+our $INDEXLEVELS = qr/\A(?:full|medium|basic)\z/;
sub new {
my ($class, $ibx, $creat, $shard) = @_;
ref $ibx or die "BUG: expected PublicInbox::Inbox object: $ibx";
- my $levels = qr/\A(?:full|medium|basic)\z/;
my $inboxdir = $ibx->{inboxdir};
my $version = $ibx->version;
my $indexlevel = 'full';
$altid = [ map { PublicInbox::AltId->new($ibx, $_); } @$altid ];
}
if ($ibx->{indexlevel}) {
- if ($ibx->{indexlevel} =~ $levels) {
+ if ($ibx->{indexlevel} =~ $INDEXLEVELS) {
$indexlevel = $ibx->{indexlevel};
} else {
die("Invalid indexlevel $ibx->{indexlevel}\n");
}
eval 'require '.$X->{WritableDatabase} or die;
*sortable_serialise = $xap.'::sortable_serialise';
+ *sortable_unserialise = $xap.'::sortable_unserialise';
$DB_CREATE_OR_OPEN = eval($xap.'::DB_CREATE_OR_OPEN()');
$DB_OPEN = eval($xap.'::DB_OPEN()');
my $ver = (eval($xap.'::major_version()') << 16) |
}
}
return unless defined $flag;
- $flag |= $DB_NO_SYNC if $self->{ibx}->{-no_fsync};
+ $flag |= $DB_NO_SYNC if ($self->{ibx} // $self->{eidx})->{-no_fsync};
my $xdb = eval { ($X->{WritableDatabase})->new($dir, $flag) };
croak "Failed opening $dir: $@" if $@;
$self->{xdb} = $xdb;
}
}
+sub index_list_id ($$$) {
+ my ($self, $doc, $hdr) = @_;
+ for my $l ($hdr->header_raw('List-Id')) {
+ $l =~ /<([^>]+)>/ or next;
+ my $lid = lc $1;
+ $doc->add_boolean_term('G' . $lid);
+ index_text($self, $lid, 1, 'XL'); # probabilistic
+ }
+}
+
sub index_ids ($$$$) {
my ($self, $doc, $hdr, $mids) = @_;
for my $mid (@$mids) {
}
}
$doc->add_boolean_term('Q' . $_) for @$mids;
- for my $l ($hdr->header_raw('List-Id')) {
- $l =~ /<([^>]+)>/ or next;
- my $lid = $1;
- $doc->add_boolean_term('G' . $lid);
- index_text($self, $lid, 1, 'XL'); # probabilistic
- }
+ index_list_id($self, $doc, $hdr);
}
sub add_xapian ($$$$) {
$tg->set_document($doc);
index_headers($self, $smsg);
+ if (defined(my $eidx_key = $smsg->{eidx_key})) {
+ $doc->add_boolean_term('O'.$eidx_key);
+ }
msg_iter($eml, \&index_xapian, [ $self, $doc ]);
index_ids($self, $doc, $eml, $mids);
$smsg->{num};
}
+sub _get_doc ($$$) {
+ my ($self, $docid, $oid) = @_;
+ my $doc = eval { $self->{xdb}->get_document($docid) };
+ $doc // do {
+ warn "E: $@\n" if $@;
+ warn "E: #$docid $oid missing in Xapian\n";
+ undef;
+ }
+}
+
+sub add_eidx_info {
+ my ($self, $docid, $oid, $eidx_key, $eml) = @_;
+ begin_txn_lazy($self);
+ my $doc = _get_doc($self, $docid, $oid) or return;
+ term_generator($self)->set_document($doc);
+ $doc->add_boolean_term('O'.$eidx_key);
+ index_list_id($self, $doc, $eml);
+ $self->{xdb}->replace_document($docid, $doc);
+}
+
+sub remove_eidx_info {
+ my ($self, $docid, $oid, $eidx_key, $eml) = @_;
+ begin_txn_lazy($self);
+ my $doc = _get_doc($self, $docid, $oid) or return;
+ $doc->remove_term('O'.$eidx_key);
+ for my $l ($eml->header_raw('List-Id')) {
+ $l =~ /<([^>]+)>/ or next;
+ my $lid = lc $1;
+ $doc->remove_term('G' . $lid);
+
+ # nb: we don't remove the XL probabilistic terms
+ # since terms may overlap if cross-posted.
+ #
+ # IOW, a message which has both <foo.example.com>
+ # and <bar.example.com> would have overlapping
+ # "XLexample" and "XLcom" as terms and which we
+ # wouldn't know if they're safe to remove if we just
+ # unindex <foo.example.com> while preserving
+ # <bar.example.com>.
+ #
+ # In any case, this entire sub is will likely never
+ # be needed and users using the "l:" prefix are probably
+ # rarer.
+ }
+ $self->{xdb}->replace_document($docid, $doc);
+}
+
+sub get_val ($$) {
+ my ($doc, $col) = @_;
+ sortable_unserialise($doc->get_value($col));
+}
+
+sub smsg_from_doc ($) {
+ my ($doc) = @_;
+ my $data = $doc->get_data or return;
+ my $smsg = bless {}, 'PublicInbox::Smsg';
+ $smsg->{ts} = get_val($doc, PublicInbox::Search::TS());
+ my $dt = get_val($doc, PublicInbox::Search::DT());
+ my ($yyyy, $mon, $dd, $hh, $mm, $ss) = unpack('A4A2A2A2A2A2', $dt);
+ $smsg->{ds} = timegm($ss, $mm, $hh, $dd, $mon - 1, $yyyy);
+ $smsg->load_from_data($data);
+ $smsg;
+}
+
sub xdb_remove {
my ($self, $oid, @removed) = @_;
my $xdb = $self->{xdb} or return;
for my $num (@removed) {
- my $doc = eval { $xdb->get_document($num) };
- unless ($doc) {
- warn "E: $@\n" if $@;
- warn "E: #$num $oid missing in Xapian\n";
- next;
- }
- my $smsg = bless {}, 'PublicInbox::Smsg';
- $smsg->load_expand($doc);
- my $blob = $smsg->{blob} // '(unset)';
- if ($blob eq $oid) {
+ my $doc = _get_doc($self, $num, $oid) or next;
+ my $smsg = smsg_from_doc($doc);
+ my $blob = $smsg->{blob}; # may be undef if --skip-docdata
+ if (!defined($blob) || $blob eq $oid) {
$xdb->delete_document($num);
} else {
warn "E: #$num $oid != $blob in Xapian\n";
unindex_eml($self, $oid, PublicInbox::Eml->new($bref));
}
+sub with_umask {
+ my $self = shift;
+ ($self->{ibx} // $self->{eidx})->with_umask(@_);
+}
+
# called by public-inbox-index
sub index_sync {
my ($self, $opt) = @_;
delete $self->{lock_path} if $opt->{-skip_lock};
- $self->{ibx}->with_umask(\&_index_sync, $self, $opt);
+ $self->with_umask(\&_index_sync, $self, $opt);
if ($opt->{reindex}) {
my %again = %$opt;
delete @again{qw(rethread reindex)};
sub v1_checkpoint ($$;$) {
my ($self, $sync, $stk) = @_;
- $self->{ibx}->git->check_async_wait;
- $self->{ibx}->git->cat_async_wait;
+ $self->{ibx}->git->async_wait_all;
# latest_cmt may be undef
my $newest = $stk ? $stk->{latest_cmt} : undef;
$self->{oidx}->rethread_done($sync->{-opt}) if $newest; # all done
commit_txn_lazy($self);
- $self->{ibx}->git->cleanup;
+ $sync->{ibx}->git->cleanup;
my $nr = ${$sync->{nr}};
idx_release($self, $nr);
# let another process do some work...
# only for v1
sub process_stack {
my ($self, $sync, $stk) = @_;
- my $git = $self->{ibx}->git;
+ my $git = $sync->{ibx}->git;
my $max = $self->{batch_bytes};
my $nr = 0;
$sync->{nr} = \$nr;
v1_checkpoint($self, $sync, $stk);
}
-sub log2stack ($$$$) {
- my ($sync, $git, $range, $ibx) = @_;
+sub log2stack ($$$) {
+ my ($sync, $git, $range) = @_;
my $D = $sync->{D}; # OID_BIN => NR (if reindexing, undef otherwise)
my ($add, $del);
- if ($ibx->version == 1) {
+ if ($sync->{ibx}->version == 1) {
my $path = $hex.'{2}/'.$hex.'{38}';
$add = qr!\A:000000 100644 \S+ ($OID) A\t$path$!;
$del = qr!\A:100644 000000 ($OID) \S+ D\t$path$!;
$stk->read_prepare;
}
-sub prepare_stack ($$$) {
- my ($self, $sync, $range) = @_;
- my $git = $self->{ibx}->git;
+sub prepare_stack ($$) {
+ my ($sync, $range) = @_;
+ my $git = $sync->{ibx}->git;
if (index($range, '..') < 0) {
# don't show annoying git errors to users who run -index
return PublicInbox::IdxStack->new->read_prepare if $?;
}
$sync->{D} = $sync->{reindex} ? {} : undef; # OID_BIN => NR
- log2stack($sync, $git, $range, $self->{ibx});
+ log2stack($sync, $git, $range);
}
# --is-ancestor requires git 1.8.0+
sub _index_sync {
my ($self, $opt) = @_;
my $tip = $opt->{ref} || 'HEAD';
- my $git = $self->{ibx}->git;
+ my $ibx = $self->{ibx};
$self->{batch_bytes} = $opt->{batch_size} // $BATCH_BYTES;
- $git->batch_prepare;
+ $ibx->git->batch_prepare;
my $pr = $opt->{-progress};
- my $sync = { reindex => $opt->{reindex}, -opt => $opt };
+ my $sync = { reindex => $opt->{reindex}, -opt => $opt, ibx => $ibx };
my $xdb = $self->begin_txn_lazy;
$self->{oidx}->rethread_prepare($opt);
my $mm = _msgmap_init($self);
my $lx = reindex_from($sync->{reindex}, $last_commit);
my $range = $lx eq '' ? $tip : "$lx..$tip";
$pr->("counting changes\n\t$range ... ") if $pr;
- my $stk = prepare_stack($self, $sync, $range);
+ my $stk = prepare_stack($sync, $range);
$sync->{ntodo} = $stk ? $stk->num_records : 0;
$pr->("$sync->{ntodo}\n") if $pr; # continue previous line
process_stack($self, $sync, $stk);
sub begin_txn_lazy {
my ($self) = @_;
- $self->{ibx}->with_umask(\&_begin_txn, $self) if !$self->{txn};
+ $self->with_umask(\&_begin_txn, $self) if !$self->{txn};
}
# store 'indexlevel=medium' in v2 shard=0 and v1 (only one shard)
sub commit_txn_lazy {
my ($self) = @_;
delete($self->{txn}) and
- $self->{ibx}->with_umask(\&_commit_txn, $self);
+ $self->with_umask(\&_commit_txn, $self);
}
sub worker_done {
die "$$ $0 still in transaction\n" if $self->{txn};
}
+sub eidx_shard_new {
+ my ($class, $eidx, $shard) = @_;
+ my $self = bless {
+ eidx => $eidx,
+ xpfx => $eidx->{xpfx},
+ indexlevel => $eidx->{indexlevel},
+ -skip_docdata => 1,
+ shard => $shard,
+ creat => 1,
+ }, $class;
+ $self->{-set_indexlevel_once} = 1 if $self->{indexlevel} eq 'medium';
+ $self;
+}
+
1;