X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearch.pm;h=ba2392557bc5abfc42147483a65bb1f7dc10ef2a;hb=525555d14118f92f86be54c683f797089c52a78d;hp=0321ca9352944d720a0962df8e3d1097ca9de68f;hpb=2255a4ad2fa2384c1f4cec6dd267383396cbc945;p=public-inbox.git diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm index 0321ca93..ba239255 100644 --- a/lib/PublicInbox/Search.pm +++ b/lib/PublicInbox/Search.pm @@ -6,7 +6,7 @@ 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 @@ -54,11 +54,11 @@ use constant { 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 $Xap; @@ -190,38 +190,42 @@ sub xdir ($;$) { } } -sub _xdb ($) { +sub xdb_sharded { + my ($self) = @_; + opendir(my $dh, $self->{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); + my (@xdb, $slow_phrase); + for (0..$last) { + my $shard_dir = "$self->{xpfx}/$_"; + 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; + } + } + $self->{qp_flags} |= FLAG_PHRASE() if !$slow_phrase; + $self->{nshard} = scalar(@xdb); + my $xdb = shift @xdb; + $xdb->add_database($_) for @xdb; + $xdb; +} + +sub _xdb { my ($self) = @_; my $dir = xdir($self, 1); - my ($xdb, $slow_phrase); - my $qpf = \($self->{qp_flags} ||= $QP_FLAGS); + $self->{qp_flags} //= $QP_FLAGS; if ($self->{ibx_ver} >= 2) { - my @xdb; - opendir(my $dh, $dir) 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($last); - for (0..$last) { - 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; - } - } - $self->{nshard} = scalar(@xdb); - $xdb = shift @xdb; - $xdb->add_database($_) for @xdb; + xdb_sharded($self); } else { - $slow_phrase = -f "$dir/iamchert"; - $xdb = $X{Database}->new($dir); + $self->{qp_flags} |= FLAG_PHRASE() if !-f "$dir/iamchert"; + $X{Database}->new($dir); } - $$qpf |= FLAG_PHRASE() unless $slow_phrase; - $xdb; } # v2 Xapian docids don't conflict, so they're identical to @@ -241,9 +245,9 @@ sub mset_to_artnums { sub xdb ($) { my ($self) = @_; - $self->{xdb} ||= do { + $self->{xdb} //= do { load_xapian(); - _xdb($self); + $self->_xdb; }; } @@ -287,15 +291,15 @@ sub mset { } sub retry_reopen { - my ($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 $@; } # Exception: The revision being read has been discarded - @@ -315,7 +319,7 @@ sub retry_reopen { sub _do_enquire { my ($self, $query, $opts) = @_; - retry_reopen($self, \&_enquire_once, [ $self, $query, $opts ]); + retry_reopen($self, \&_enquire_once, $query, $opts); } # returns true if all docs have the THREADID value @@ -325,8 +329,11 @@ sub has_threadid ($) { } 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); + } my $enquire = $X{Enquire}->new($xdb); $enquire->set_query($query); $opts ||= {};