-# Copyright (C) 2015-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2019 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
#
use constant YYYYMMDD => 1; # Date: header for searching in the WWW UI
use constant DT => 2; # Date: YYYYMMDDHHMMSS
-use Search::Xapian qw/:standard/;
use PublicInbox::SearchMsg;
use PublicInbox::MIME;
use PublicInbox::MID qw/id_compress/;
use PublicInbox::Over;
+my $QP_FLAGS;
+sub load_xapian () {
+ $QP_FLAGS ||= eval {
+ require Search::Xapian;
+ Search::Xapian->import(qw(:standard));
+
+ # n.b. FLAG_PURE_NOT is expensive not suitable for a public
+ # website as it could become a denial-of-service vector
+ # FLAG_PHRASE also seems to cause performance problems chert
+ # (and probably earlier Xapian DBs). glass seems fine...
+ # TODO: make this an option, maybe?
+ # or make indexlevel=medium as default
+ FLAG_PHRASE()|FLAG_BOOLEAN()|FLAG_LOVEHATE()|FLAG_WILDCARD();
+ };
+};
# This is English-only, everything else is non-standard and may be confused as
# a prefix common in patch emails
# (commit 83425ef12e4b65cdcecd11ddcb38175d4a91d5a0)
# 14 - fix ghost root vivification
SCHEMA_VERSION => 15,
-
- # n.b. FLAG_PURE_NOT is expensive not suitable for a public website
- # as it could become a denial-of-service vector
- QP_FLAGS => FLAG_PHRASE|FLAG_BOOLEAN|FLAG_LOVEHATE|FLAG_WILDCARD,
};
my %bool_pfx_external = (
);
chomp @HELP;
-sub xdir {
- my ($self) = @_;
+sub xdir ($;$) {
+ my ($self, $rdonly) = @_;
if ($self->{version} == 1) {
- "$self->{mainrepo}/public-inbox/xapian" . SCHEMA_VERSION;
+ "$self->{inboxdir}/public-inbox/xapian" . SCHEMA_VERSION;
} else {
- my $dir = "$self->{mainrepo}/xap" . SCHEMA_VERSION;
- my $part = $self->{partition};
- defined $part or die "partition not given";
- $dir .= "/$part";
+ my $dir = "$self->{inboxdir}/xap" . SCHEMA_VERSION;
+ return $dir if $rdonly;
+
+ my $shard = $self->{shard};
+ defined $shard or die "shard not given";
+ $dir .= "/$shard";
}
}
-sub new {
- my ($class, $mainrepo, $altid) = @_;
- my $version = 1;
- my $ibx = $mainrepo;
- if (ref $ibx) {
- $version = $ibx->{version} || 1;
- $mainrepo = $ibx->{mainrepo};
- }
- my $self = bless {
- mainrepo => $mainrepo,
- altid => $altid,
- version => $version,
- }, $class;
- my $dir;
- if ($version >= 2) {
- $dir = "$self->{mainrepo}/xap" . SCHEMA_VERSION;
- my $xdb;
- my $parts = 0;
- foreach my $part (<$dir/*>) {
- -d $part && $part =~ m!/\d+\z! or next;
- $parts++;
- my $sub = Search::Xapian::Database->new($part);
+sub _xdb ($) {
+ my ($self) = @_;
+ my $dir = xdir($self, 1);
+ my ($xdb, $slow_phrase);
+ my $qpf = \($self->{qp_flags} ||= $QP_FLAGS);
+ if ($self->{version} >= 2) {
+ foreach my $shard (<$dir/*>) {
+ -d $shard && $shard =~ m!/[0-9]+\z! or next;
+ my $sub = Search::Xapian::Database->new($shard);
if ($xdb) {
$xdb->add_database($sub);
} else {
$xdb = $sub;
}
+ $slow_phrase ||= -f "$shard/iamchert";
}
- $self->{xdb} = $xdb;
} else {
- $dir = $self->xdir;
- $self->{xdb} = Search::Xapian::Database->new($dir);
+ $slow_phrase = -f "$dir/iamchert";
+ $xdb = Search::Xapian::Database->new($dir);
}
+ $$qpf |= FLAG_PHRASE() unless $slow_phrase;
+ $xdb;
+}
+
+sub xdb ($) {
+ my ($self) = @_;
+ $self->{xdb} ||= do {
+ load_xapian();
+ _xdb($self);
+ };
+}
+
+sub new {
+ my ($class, $ibx) = @_;
+ ref $ibx or die "BUG: expected PublicInbox::Inbox object: $ibx";
+ my $self = bless {
+ inboxdir => $ibx->{inboxdir},
+ altid => $ibx->{altid},
+ version => $ibx->{version} // 1,
+ }, $class;
+ my $dir = xdir($self, 1);
$self->{over_ro} = PublicInbox::Over->new("$dir/over.sqlite3");
$self;
}
sub reopen {
my ($self) = @_;
- $self->{xdb}->reopen;
+ if (my $xdb = $self->{xdb}) {
+ $xdb->reopen;
+ }
$self; # make chaining easier
}
if ($query_string eq '' && !$opts->{mset}) {
$self->{over_ro}->recent($opts);
} else {
- my $query = $self->qp->parse_query($query_string, QP_FLAGS);
+ my $qp = qp($self);
+ my $qp_flags = $self->{qp_flags};
+ my $query = $qp->parse_query($query_string, $qp_flags);
$opts->{relevance} = 1 unless exists $opts->{relevance};
_do_enquire($self, $query, $opts);
}
warn "reopen try #$i on $@\n";
reopen($self);
} else {
- warn "ref: ", ref($@), "\n";
+ # let caller decide how to spew, because ExtMsg queries
+ # get wonky and trigger:
+ # "something terrible happened at .../Xapian/Enquire.pm"
die;
}
}
sub _enquire_once {
my ($self, $query, $opts) = @_;
- my $enquire = Search::Xapian::Enquire->new($self->{xdb});
+ my $xdb = xdb($self);
+ my $enquire = Search::Xapian::Enquire->new($xdb);
$enquire->set_query($query);
$opts ||= {};
my $desc = !$opts->{asc};
my $qp = $self->{query_parser};
return $qp if $qp;
-
+ my $xdb = xdb($self);
# new parser
$qp = Search::Xapian::QueryParser->new;
- $qp->set_default_op(OP_AND);
- $qp->set_database($self->{xdb});
+ $qp->set_default_op(OP_AND());
+ $qp->set_database($xdb);
$qp->set_stemmer($self->stemmer);
- $qp->set_stemming_strategy(STEM_SOME);
+ $qp->set_stemming_strategy(STEM_SOME());
$qp->set_max_wildcard_expansion(100);
$qp->add_valuerangeprocessor(
Search::Xapian::NumberValueRangeProcessor->new(YYYYMMDD, 'd:'));