# 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 constant YYYYMMDD => 4; # for searching in the WWW UI
+
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
+ # 12 - change YYYYMMDD value column to numeric
+ SCHEMA_VERSION => 12,
# n.b. FLAG_PURE_NOT is expensive not suitable for a public website
# as it could become a denial-of-service vector
);
my %bool_pfx_external = (
+ # do we still need these? probably not..
path => 'XPATH',
mid => 'Q', # uniQue id (Message-ID)
);
my %prob_prefix = (
- subject => 'S',
- s => 'S', # for mairix compatibility
- m => 'Q', # 'mid' is exact, 'm' can do partial
+ # for mairix compatibility
+ s => 'S',
+ m => 'XMID', # 'mid:' (bool) is exact, 'm:' (prob) can do partial
+ f => 'A',
+ t => 'XTO',
+ tc => 'XTO XCC',
+ c => 'XCC',
+ tcf => 'XTO XCC A',
+ b => 'XNQ XQUOT',
+ bs => 'XNQ XQUOT S',
+ n => 'XFN',
+
+ # n.b.: leaving out "a:" alias for "tcf:" even though
+ # mairix supports it. It is only mentioned in passing in mairix(1)
+ # and the extra two letters are not significantly longer.
+ q => 'XQUOT',
+ nq => 'XNQ',
+
+ # default:
+ '' => 'XMID S A XNQ XQUOT XFN',
+);
+
+# not documenting m: and mid: for now, the using the URLs works w/o Xapian
+our @HELP = (
+ 's:' => <<EOF,
+match within Subject only e.g. s:"a quick brown fox"
+This is a probabilistic search with support for stemming
+and wildcards '*'
+EOF
+ 'd:' => <<EOF,
+date range as YYYYMMDD e.g. d:19931002..20101002
+Open-ended ranges such as d:19931002.. and d:..20101002
+are also supported.
+EOF
);
+# TODO: (from mairix, some of these are maybe)
+# b (body), f (From:), c (Cc:), n (attachment), t (To:)
+# tc (To:+Cc:), bs (body + Subject), tcf (To: +Cc: +From:)
+#
+# Non-mairix:
+# df (filenames from diff)
+# nq (non-quoted body)
+# da (diff a/ removed lines)
+# db (diff b/ added lines)
my %all_pfx = (%bool_pfx_internal, %bool_pfx_external, %prob_prefix);
}
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, $opts);
-}
-
-sub get_subject_path {
- my ($self, $path, $opts) = @_;
- my $q = Search::Xapian::Query->new(xpfx("path").mid_compress($path));
- $self->do_enquire($q, $opts);
+ _do_enquire($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, $opts);
}
-# private subs below
+sub _do_enquire {
+ my ($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 $@;
+ }
+ }
+}
-sub do_enquire {
+sub _enquire_once {
my ($self, $query, $opts) = @_;
my $enquire = $self->enquire;
if (defined $query) {
$query = $mail_query;
}
$enquire->set_query($query);
+ $opts ||= {};
+ my $desc = !$opts->{asc};
if ($opts->{relevance}) {
- $enquire->set_sort_by_relevance_then_value(TS, 1);
+ $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, 1);
+ $enquire->set_sort_by_value_then_relevance(TS, $desc);
}
- $opts ||= {};
my $offset = $opts->{offset} || 0;
my $limit = $opts->{limit} || 50;
my $mset = $enquire->get_mset($offset, $limit);
$qp->set_database($self->{xdb});
$qp->set_stemmer($self->stemmer);
$qp->set_stemming_strategy(STEM_SOME);
- $qp->add_valuerangeprocessor($self->ts_range_processor);
- $qp->add_valuerangeprocessor($self->date_range_processor);
+ $qp->add_valuerangeprocessor(
+ Search::Xapian::NumberValueRangeProcessor->new(YYYYMMDD, 'd:'));
while (my ($name, $prefix) = each %bool_pfx_external) {
$qp->add_boolean_prefix($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}) {
+ my $user_pfx = $self->{-user_pfx} ||= [];
+ for (@$altid) {
+ # $_ = 'serial:gmane:/path/to/gmane.msgmap.sqlite3'
+ /\Aserial:(\w+):/ or next;
+ my $pfx = $1;
+ push @$user_pfx, "$pfx:", <<EOF;
+alternate serial number e.g. $pfx:12345
+EOF
+ # gmane => XGMANE
+ $qp->add_boolean_prefix($pfx, 'X'.uc($pfx));
+ }
+ }
+
while (my ($name, $prefix) = each %prob_prefix) {
- $qp->add_prefix($name, $prefix);
+ $qp->add_prefix($name, $_) foreach split(/ /, $prefix);
}
$self->{query_parser} = $qp;
}
-sub ts_range_processor {
- $_[0]->{tsrp} ||= Search::Xapian::NumberValueRangeProcessor->new(TS);
+sub num_range_processor {
+ $_[0]->{nrp} ||= Search::Xapian::NumberValueRangeProcessor->new(NUM);
}
-sub date_range_processor {
- $_[0]->{drp} ||= Search::Xapian::DateValueRangeProcessor->new(TS);
+# only used for NNTP server
+sub query_xover {
+ my ($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 {
$smsg;
}
+sub lookup_mail { # no ghosts!
+ my ($self, $mid) = @_;
+ my $smsg = lookup_message($self, $mid) or return;
+ PublicInbox::SearchMsg->load_doc($smsg->{doc});
+}
+
sub find_unique_doc_id {
my ($self, $term, $value) = @_;
$self->{enquire} ||= Search::Xapian::Enquire->new($self->{xdb});
}
+sub help {
+ my ($self) = @_;
+ $self->qp; # parse altids
+ my @ret = @HELP;
+ if (my $user_pfx = $self->{-user_pfx}) {
+ push @ret, @$user_pfx;
+ }
+ \@ret;
+}
+
1;