package PublicInbox::Search;
use strict;
use parent qw(Exporter);
-our @EXPORT_OK = qw(mdocid);
+our @EXPORT_OK = qw(retry_reopen);
use List::Util qw(max);
# values for searching, changing the numeric value breaks
use PublicInbox::Smsg;
use PublicInbox::Over;
-my $QP_FLAGS;
-our %X = map { $_ => 0 } qw(BoolWeight Database Enquire QueryParser Stem);
+our $QP_FLAGS;
+our %X = map { $_ => 0 } qw(BoolWeight Database Enquire QueryParser Stem Query);
our $Xap; # 'Search::Xapian' or 'Xapian'
-my $NVRP; # '$Xap::'.('NumberValueRangeProcessor' or 'NumberRangeProcessor')
-my $ENQ_ASCENDING;
+our $NVRP; # '$Xap::'.('NumberValueRangeProcessor' or 'NumberRangeProcessor')
+our $ENQ_ASCENDING;
sub load_xapian () {
return 1 if defined $Xap;
$ENQ_ASCENDING = $x eq 'Xapian' ?
1 : Search::Xapian::ENQ_ASCENDING();
+ *sortable_serialise = $x.'::sortable_serialise';
# n.b. FLAG_PURE_NOT is expensive not suitable for a public
# website as it could become a denial-of-service vector
# FLAG_PHRASE also seems to cause performance problems chert
}
}
-sub _xdb_sharded {
- my ($self, $xpfx) = @_;
- opendir(my $dh, $xpfx) or return; # not initialized yet
-
- # We need numeric sorting so shard[0] is first for reading
- # Xapian metadata, if needed
- my $last = max(grep(/\A[0-9]+\z/, readdir($dh)));
- return if !defined($last);
+# returns all shards as separate Xapian::Database objects w/o combining
+sub xdb_shards_flat ($) {
+ my ($self) = @_;
+ my $xpfx = $self->{xpfx};
my (@xdb, $slow_phrase);
- for (0..$last) {
- my $shard_dir = "$xpfx/$_";
- if (-d $shard_dir && -r _) {
+ if ($xpfx =~ m/xapian${\SCHEMA_VERSION}\z/) {
+ @xdb = ($X{Database}->new($xpfx));
+ $self->{qp_flags} |= FLAG_PHRASE() if !-f "$xpfx/iamchert";
+ } else {
+ opendir(my $dh, $xpfx) or return (); # not initialized yet
+ # We need numeric sorting so shard[0] is first for reading
+ # Xapian metadata, if needed
+ my $last = max(grep(/\A[0-9]+\z/, readdir($dh))) // return ();
+ for (0..$last) {
+ my $shard_dir = "$self->{xpfx}/$_";
push @xdb, $X{Database}->new($shard_dir);
$slow_phrase ||= -f "$shard_dir/iamchert";
- } else { # gaps from missing epochs throw off mdocid()
- warn "E: $shard_dir missing or unreadable\n";
- return;
}
+ $self->{qp_flags} |= FLAG_PHRASE() if !$slow_phrase;
}
- $self->{qp_flags} |= FLAG_PHRASE() if !$slow_phrase;
- $self->{nshard} = scalar(@xdb);
- my $xdb = shift @xdb;
- $xdb->add_database($_) for @xdb;
- $xdb;
+ @xdb;
}
sub _xdb {
my ($self) = @_;
- my $dir = xdir($self, 1);
$self->{qp_flags} //= $QP_FLAGS;
- if ($self->{ibx_ver} >= 2) {
- _xdb_sharded($self, $dir);
- } else {
- $self->{qp_flags} |= FLAG_PHRASE() if !-f "$dir/iamchert";
- $X{Database}->new($dir);
- }
+ my @xdb = xdb_shards_flat($self) or return;
+ $self->{nshard} = scalar(@xdb);
+ my $xdb = shift @xdb;
+ $xdb->add_database($_) for @xdb;
+ $xdb;
}
# v2 Xapian docids don't conflict, so they're identical to
sub mset_to_artnums {
my ($self, $mset) = @_;
- my $nshard = $self->{nshard} // 1;
+ my $nshard = $self->{nshard};
[ map { mdocid($nshard, $_) } $mset->items ];
}
sub xdb ($) {
my ($self) = @_;
- $self->{xdb} ||= do {
+ $self->{xdb} //= do {
load_xapian();
- _xdb($self);
+ $self->_xdb;
};
}
-sub xpfx_init ($) {
- my ($self) = @_;
- if ($self->{ibx_ver} == 1) {
- $self->{xpfx} .= '/public-inbox/xapian' . SCHEMA_VERSION;
- } else {
- $self->{xpfx} .= '/xap'.SCHEMA_VERSION;
- }
-}
-
sub new {
my ($class, $ibx) = @_;
ref $ibx or die "BUG: expected PublicInbox::Inbox object: $ibx";
- my $self = bless {
- xpfx => $ibx->{inboxdir}, # for xpfx_init
+ my $xap = $ibx->version > 1 ? 'xap' : 'public-inbox/xapian';
+ bless {
+ xpfx => "$ibx->{inboxdir}/$xap" . SCHEMA_VERSION,
altid => $ibx->{altid},
- ibx_ver => $ibx->version,
}, $class;
- xpfx_init($self);
- $self;
}
sub reopen {
}
sub retry_reopen {
- my ($self, $cb, $arg) = @_;
+ my ($self, $cb, @arg) = @_;
for my $i (1..10) {
if (wantarray) {
my @ret;
- eval { @ret = $cb->($arg) };
+ eval { @ret = $cb->($self, @arg) };
return @ret unless $@;
} else {
my $ret;
- eval { $ret = $cb->($arg) };
+ eval { $ret = $cb->($self, @arg) };
return $ret unless $@;
}
# Exception: The revision being read has been discarded -
sub _do_enquire {
my ($self, $query, $opts) = @_;
- retry_reopen($self, \&_enquire_once, [ $self, $query, $opts ]);
+ retry_reopen($self, \&_enquire_once, $query, $opts);
}
# returns true if all docs have the THREADID value
}
sub _enquire_once { # retry_reopen callback
- my ($self, $query, $opts) = @{$_[0]};
+ my ($self, $query, $opts) = @_;
my $xdb = xdb($self);
+ if (defined(my $eidx_key = $opts->{eidx_key})) {
+ $query = $X{Query}->new(OP_FILTER(), $query, 'O'.$eidx_key);
+ }
+ if (defined(my $uid_range = $opts->{uid_range})) {
+ my $range = $X{Query}->new(OP_VALUE_RANGE(), UID,
+ sortable_serialise($uid_range->[0]),
+ sortable_serialise($uid_range->[1]));
+ $query = $X{Query}->new(OP_FILTER(), $query, $range);
+ }
my $enquire = $X{Enquire}->new($xdb);
$enquire->set_query($query);
$opts ||= {};
sub mset_to_smsg {
my ($self, $ibx, $mset) = @_;
- my $nshard = $self->{nshard} // 1;
+ my $nshard = $self->{nshard};
my $i = 0;
my %order = map { mdocid($nshard, $_) => ++$i } $mset->items;
my @msgs = sort {