# Copyright (C) 2015 all contributors <meta@public-inbox.org>
# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
# based on notmuch, but with no concept of folders, files or flags
+#
+# Read-only search interface for use by the web and NNTP interfaces
package PublicInbox::Search;
use strict;
use warnings;
-use constant TS => 0;
+
+# values for searching
+use constant TS => 0; # timestamp
+use constant NUM => 1; # NNTP article number
+use constant BYTES => 2; # :bytes as defined in RFC 3977
+use constant LINES => 3; # :lines as defined in RFC 3977
+
use Search::Xapian qw/:standard/;
use PublicInbox::SearchMsg;
use Email::MIME;
-use PublicInbox::MID qw/mid_clean mid_compress/;
+use PublicInbox::MID qw/mid_clean id_compress/;
# This is English-only, everything else is non-standard and may be confused as
# a prefix common in patch emails
# SCHEMA_VERSION history
# 0 - initial
# 1 - subject_path is lower-cased
- # 2 - subject_path is mid_compress in the index, only
+ # 2 - subject_path is id_compress in the index, only
# 3 - message-ID is compressed if it includes '%' (hack!)
# 4 - change "Re: " normalization, avoid circular Reference ghosts
# 5 - subject_path drops trailing '.'
# 6 - preserve References: order in document data
# 7 - remove references and inreplyto terms
# 8 - remove redundant/unneeded document data
- # 9 - disable Message-ID compression
- SCHEMA_VERSION => 9,
+ # 9 - disable Message-ID compression (SHA-1)
+ # 10 - optimize doc for NNTP overviews
+ # 11 - merge threads when vivifying ghosts
+ SCHEMA_VERSION => 11,
# n.b. FLAG_PURE_NOT is expensive not suitable for a public website
# as it could become a denial-of-service vector
}
sub new {
- my ($class, $git_dir) = @_;
+ my ($class, $git_dir, $altid) = @_;
my $dir = $class->xdir($git_dir);
my $db = Search::Xapian::Database->new($dir);
- bless { xdb => $db, git_dir => $git_dir }, $class;
+ bless { xdb => $db, git_dir => $git_dir, altid => $altid }, $class;
}
sub reopen { $_[0]->{xdb}->reopen }
$opts->{relevance} = 1 unless exists $opts->{relevance};
}
- $self->do_enquire($query, $opts);
+ _do_enquire($self, $query, $opts);
}
sub get_thread {
return { total => 0, msgs => [] } unless $smsg;
my $qtid = Search::Xapian::Query->new(xpfx('thread').$smsg->thread_id);
- my $path = mid_compress($smsg->path);
- my $qsub = Search::Xapian::Query->new(xpfx('path').$path);
- my $query = Search::Xapian::Query->new(OP_OR, $qtid, $qsub);
- $self->do_enquire($query, $opts);
+ my $path = $smsg->path;
+ if (defined $path && $path ne '') {
+ my $path = id_compress($smsg->path);
+ my $qsub = Search::Xapian::Query->new(xpfx('path').$path);
+ $qtid = Search::Xapian::Query->new(OP_OR, $qtid, $qsub);
+ }
+ $opts ||= {};
+ $opts->{limit} ||= 1000;
+ _do_enquire($self, $qtid, $opts);
}
-sub do_enquire {
+sub _do_enquire {
+ my ($self, $query, $opts) = @_;
+ my $ret;
+ for (1..10) {
+ eval { $ret = _enquire_once($self, $query, $opts) };
+ return $ret unless $@;
+ # Exception: The revision being read has been discarded -
+ # you should call Xapian::Database::reopen()
+ if (index($@, 'Xapian::Database::reopen') >= 0) {
+ reopen($self);
+ } else {
+ die $@;
+ }
+ }
+}
+
+sub _enquire_once {
my ($self, $query, $opts) = @_;
my $enquire = $self->enquire;
if (defined $query) {
my $desc = !$opts->{asc};
if ($opts->{relevance}) {
$enquire->set_sort_by_relevance_then_value(TS, $desc);
+ } elsif ($opts->{num}) {
+ $enquire->set_sort_by_value(NUM, 0);
} else {
$enquire->set_sort_by_value_then_relevance(TS, $desc);
}
$qp->add_boolean_prefix($name, $prefix);
}
+ # we do not actually create AltId objects,
+ # just parse the spec to avoid the extra DB handles for now.
+ if (my $altid = $self->{altid}) {
+ for (@$altid) {
+ # $_ = 'serial:gmane:/path/to/gmane.msgmap.sqlite3'
+ /\Aserial:(\w+):/ or next;
+ my $pfx = $1;
+ # gmane => XGMANE
+ $qp->add_boolean_prefix($pfx, 'X'.uc($pfx));
+ }
+ }
+
while (my ($name, $prefix) = each %prob_prefix) {
$qp->add_prefix($name, $prefix);
}
$_[0]->{drp} ||= Search::Xapian::DateValueRangeProcessor->new(TS);
}
+sub num_range_processor {
+ $_[0]->{nrp} ||= Search::Xapian::NumberValueRangeProcessor->new(NUM);
+}
+
+# only used for NNTP server
+sub query_xover {
+ my ($self, $beg, $end, $offset) = @_;
+ my $qp = Search::Xapian::QueryParser->new;
+ $qp->set_database($self->{xdb});
+ $qp->add_valuerangeprocessor($self->num_range_processor);
+ my $query = $qp->parse_query("$beg..$end", QP_FLAGS);
+
+ _do_enquire($self, $query, {num => 1, limit => 200, offset => $offset});
+}
+
sub lookup_message {
my ($self, $mid) = @_;
$mid = mid_clean($mid);
$smsg;
}
+sub lookup_mail { # no ghosts!
+ my ($self, $mid) = @_;
+ my $smsg = lookup_message($self, $mid);
+ PublicInbox::SearchMsg->load_doc($smsg->{doc});
+}
+
sub find_unique_doc_id {
my ($self, $term, $value) = @_;