-# Copyright (C) 2015-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2021 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
#
package PublicInbox::Search;
use strict;
use parent qw(Exporter);
-our @EXPORT_OK = qw(mdocid);
+our @EXPORT_OK = qw(retry_reopen int_val get_pct xap_terms);
+use List::Util qw(max);
# values for searching, changing the numeric value breaks
# compatibility with old indices (so don't change them it)
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')
+
+# ENQ_DESCENDING and ENQ_ASCENDING weren't in SWIG Xapian.pm prior to 1.4.16,
+# let's hope the ABI is stable
+our $ENQ_DESCENDING = 0;
+our $ENQ_ASCENDING = 1;
sub load_xapian () {
return 1 if defined $Xap;
'NumberRangeProcessor' : 'NumberValueRangeProcessor');
$X{$_} = $Xap.'::'.$_ for (keys %X);
- # ENQ_ASCENDING doesn't seem exported by SWIG Xapian.pm,
- # so lets hope this part of the ABI is stable because it's
- # just an integer:
- $ENQ_ASCENDING = $x eq 'Xapian' ?
- 1 : Search::Xapian::ENQ_ASCENDING();
-
- # for Smsg:
- *PublicInbox::Smsg::sortable_unserialise =
- $Xap.'::sortable_unserialise';
+ *sortable_serialise = $x.'::sortable_serialise';
+ *sortable_unserialise = $x.'::sortable_unserialise';
# n.b. FLAG_PURE_NOT is expensive not suitable for a public
# website as it could become a denial-of-service vector
# FLAG_PHRASE also seems to cause performance problems chert
}
}
-sub _xdb ($) {
+# returns all shards as separate Xapian::Database objects w/o combining
+sub xdb_shards_flat ($) {
my ($self) = @_;
- my $dir = xdir($self, 1);
- my ($xdb, $slow_phrase);
- my $qpf = \($self->{qp_flags} ||= $QP_FLAGS);
- if ($self->{ibx_ver} >= 2) {
- my @xdb;
- opendir(my $dh, $dir) or return; # not initialized yet
-
+ my $xpfx = $self->{xpfx};
+ my (@xdb, $slow_phrase);
+ load_xapian();
+ $self->{qp_flags} //= $QP_FLAGS;
+ if ($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
- for (sort { $a <=> $b } grep(/\A[0-9]+\z/, readdir($dh))) {
- my $shard_dir = "$dir/$_";
- if (-d $shard_dir && -r _) {
- 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;
- }
+ 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";
}
- $self->{nshard} = scalar(@xdb);
- $xdb = shift @xdb;
- $xdb->add_database($_) for @xdb;
- } else {
- $slow_phrase = -f "$dir/iamchert";
- $xdb = $X{Database}->new($dir);
+ $self->{qp_flags} |= FLAG_PHRASE() if !$slow_phrase;
}
- $$qpf |= FLAG_PHRASE() unless $slow_phrase;
- $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 {
- load_xapian();
- _xdb($self);
+ $self->{xdb} //= do {
+ my @xdb = $self->xdb_shards_flat or return;
+ $self->{nshard} = scalar(@xdb);
+ my $xdb = shift @xdb;
+ $xdb->add_database($_) for @xdb;
+ $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 {
$opts ||= {};
my $qp = $self->{qp} //= qparse_new($self);
my $query = $qp->parse_query($query_string, $self->{qp_flags});
- $opts->{relevance} = 1 unless exists $opts->{relevance};
_do_enquire($self, $query, $opts);
}
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 ||= {};
my $desc = !$opts->{asc};
- if (($opts->{mset} || 0) == 2) { # mset == 2: ORDER BY docid/UID
+ my $rel = $opts->{relevance} // 0;
+ if ($rel == -1) { # ORDER BY docid/UID
+ $enquire->set_weighting_scheme($X{BoolWeight}->new);
$enquire->set_docid_order($ENQ_ASCENDING);
+ } elsif ($rel == 0) {
+ $enquire->set_sort_by_value_then_relevance(TS, $desc);
+ } elsif ($rel == -2) {
$enquire->set_weighting_scheme($X{BoolWeight}->new);
- } elsif ($opts->{relevance}) {
+ $enquire->set_docid_order($ENQ_DESCENDING);
+ } else { # rel > 0
$enquire->set_sort_by_relevance_then_value(TS, $desc);
- } else {
- $enquire->set_sort_by_value_then_relevance(TS, $desc);
}
# `mairix -t / --threads' or JMAP collapseThreads
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 {
# for IMAP, undocumented for WWW and may be split off go away
$cb->($qp, $NVRP->new(BYTES, 'bytes:'));
- $cb->($qp, $NVRP->new(TS, 'ts:'));
+ $cb->($qp, $NVRP->new(TS, 'rt:'));
$cb->($qp, $NVRP->new(UID, 'uid:'));
while (my ($name, $prefix) = each %bool_pfx_external) {
\@ret;
}
+sub int_val ($$) {
+ my ($doc, $col) = @_;
+ my $val = $doc->get_value($col) or return; # undefined is '' in Xapian
+ sortable_unserialise($val) + 0; # PV => IV conversion
+}
+
+sub get_pct ($) { # mset item
+ # Capped at "99%" since "100%" takes an extra column in the
+ # thread skeleton view. <xapian/mset.h> says the value isn't
+ # very meaningful, anyways.
+ my $n = $_[0]->get_percent;
+ $n > 99 ? 99 : $n;
+}
+
+sub xap_terms ($$;@) {
+ my ($pfx, $xdb_or_doc, @docid) = @_; # @docid may be empty ()
+ my %ret;
+ eval {
+ my $end = $xdb_or_doc->termlist_end(@docid);
+ my $cur = $xdb_or_doc->termlist_begin(@docid);
+ for (; $cur != $end; $cur++) {
+ $cur->skip_to($pfx);
+ last if $cur == $end;
+ my $tn = $cur->get_termname;
+ if (index($tn, $pfx) == 0) {
+ $ret{substr($tn, length($pfx))} = undef;
+ }
+ }
+ };
+ \%ret;
+}
+
1;