-# Copyright (C) 2015, all contributors <meta@public-inbox.org>
+# 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 PublicInbox::SearchMsg;
+
+# 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
our $LANG = 'english';
use constant {
- TS => 0,
# 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
- SCHEMA_VERSION => 6,
+ # 7 - remove references and inreplyto terms
+ # 8 - remove redundant/unneeded document data
+ # 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
QP_FLAGS => FLAG_PHRASE|FLAG_BOOLEAN|FLAG_LOVEHATE|FLAG_WILDCARD,
};
# setup prefixes
my %bool_pfx_internal = (
type => 'T', # "mail" or "ghost"
- mid => 'Q', # uniQue id (Message-ID or mid_compress)
+ thread => 'G', # newsGroup (or similar entity - e.g. a web forum name)
);
my %bool_pfx_external = (
path => 'XPATH',
- thread => 'G', # newsGroup (or similar entity - e.g. a web forum name)
- references => 'XREFS',
- inreplyto => 'XIRT',
+ 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
);
my %all_pfx = (%bool_pfx_internal, %bool_pfx_external, %prob_prefix);
sub xpfx { $all_pfx{$_[0]} }
our %PFX2TERM_RMAP;
-my %meta_pfx = (mid => 1, thread => 1, path => 1, type => 1);
+my %meta_pfx = (mid => 1, thread => 1, path => 1);
while (my ($k, $v) = each %all_pfx) {
$PFX2TERM_RMAP{$v} = $k if $meta_pfx{$k};
}
# read-only
sub query {
my ($self, $query_string, $opts) = @_;
- my $query = $self->qp->parse_query($query_string, QP_FLAGS);
+ my $query;
$opts ||= {};
- $opts->{relevance} = 1;
- $self->do_enquire($query, $opts);
-}
-
-sub get_subject_path {
- my ($self, $path, $opts) = @_;
- my $query = $self->qp->parse_query("path:".mid_compress($path), 0);
- $self->do_enquire($query, $opts);
-}
+ unless ($query_string eq '') {
+ $query = $self->qp->parse_query($query_string, QP_FLAGS);
+ $opts->{relevance} = 1 unless exists $opts->{relevance};
+ }
-# given a message ID, get followups to a message
-sub get_followups {
- my ($self, $mid, $opts) = @_;
- $mid = mid_clean($mid);
- $mid = mid_compress($mid);
- my $qp = $self->qp;
- my $irt = $qp->parse_query("inreplyto:$mid", 0);
- my $ref = $qp->parse_query("references:$mid", 0);
- my $query = Search::Xapian::Query->new(OP_OR, $irt, $ref);
- $self->do_enquire($query, $opts);
+ _do_enquire($self, $query, $opts);
}
sub get_thread {
my $smsg = eval { $self->lookup_message($mid) };
return { total => 0, msgs => [] } unless $smsg;
- my $qp = $self->qp;
- my $qtid = $qp->parse_query('thread:'.$smsg->thread_id, 0);
- my $qsub = $qp->parse_query('path:'.mid_compress($smsg->path), 0);
- my $query = Search::Xapian::Query->new(OP_OR, $qtid, $qsub);
- $self->do_enquire($query, $opts);
+ my $qtid = Search::Xapian::Query->new(xpfx('thread').$smsg->thread_id);
+ 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;
-
- $query = Search::Xapian::Query->new(OP_AND, $query, $mail_query);
+ if (defined $query) {
+ $query = Search::Xapian::Query->new(OP_AND,$query,$mail_query);
+ } else {
+ $query = $mail_query;
+ }
$enquire->set_query($query);
+ $opts ||= {};
+ my $desc = !$opts->{asc};
if ($opts->{relevance}) {
- $enquire->set_sort_by_relevance_then_value(TS, 0);
+ $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(TS, 0);
+ $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);
+ return $mset if $opts->{mset};
my @msgs = map {
PublicInbox::SearchMsg->load_doc($_->get_document);
} $mset->items;
$_[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);
- $mid = mid_compress($mid);
my $doc_id = $self->find_unique_doc_id('mid', $mid);
my $smsg;
$smsg;
}
+sub lookup_mail { # no ghosts!
+ my ($self, $mid) = @_;
+ my $smsg = lookup_message($self, $mid);
+ PublicInbox::SearchMsg->load_doc($smsg->{doc});
+}
+
sub find_unique_doc_id {
my ($self, $term, $value) = @_;
last if length($new) >= $max;
$subj = $new;
}
- if (length $subj) {
+ if ($subj ne '') {
my $r = scalar @subj ? ' ...' : '';
$subj =~ s/ \z/$r/s;
} else {
+ # subject has one REALLY long word, and NOT spam? wtf
@subj = ($l =~ /\A(.{1,72})/);
$subj = $subj[0] . ' ...';
}