-# Copyright (C) 2015 all contributors <meta@public-inbox.org>
-# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# Copyright (C) 2015-2018 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
#
# Read-only search interface for use by the web and NNTP interfaces
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::MIME;
use PublicInbox::MID qw/mid_clean id_compress/;
# This is English-only, everything else is non-standard and may be confused as
# 8 - remove redundant/unneeded document data
# 9 - disable Message-ID compression (SHA-1)
# 10 - optimize doc for NNTP overviews
- SCHEMA_VERSION => 10,
+ # 11 - merge threads when vivifying ghosts
+ # 12 - change YYYYMMDD value column to numeric
+ # 13 - fix threading for empty References/In-Reply-To
+ # (commit 83425ef12e4b65cdcecd11ddcb38175d4a91d5a0)
+ # 14 - fix ghost root vivification
+ SCHEMA_VERSION => 14,
# 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 = (
- path => 'XPATH',
- mid => 'Q', # uniQue id (Message-ID)
+ mid => 'XMID', # Message-ID (full/exact)
);
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 => 'XM', # 'mid:' (bool) is exact, 'm:' (prob) can do partial
+ f => 'A',
+ t => 'XTO',
+ tc => 'XTO XCC',
+ c => 'XCC',
+ tcf => 'XTO XCC A',
+ a => 'XTO XCC A',
+ b => 'XNQ XQUOT',
+ bs => 'XNQ XQUOT S',
+ n => 'XFN',
+
+ q => 'XQUOT',
+ nq => 'XNQ',
+ dfn => 'XDFN',
+ dfa => 'XDFA',
+ dfb => 'XDFB',
+ dfhh => 'XDFHH',
+ dfctx => 'XDFCTX',
+ dfpre => 'XDFPRE',
+ dfpost => 'XDFPOST',
+ dfblob => 'XDFPRE XDFPOST',
+
+ # default:
+ '' => 'XM S A XNQ XQUOT XFN',
);
-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);
-while (my ($k, $v) = each %all_pfx) {
- $PFX2TERM_RMAP{$v} = $k if $meta_pfx{$k};
-}
+# not documenting m: and mid: for now, the using the URLs works w/o Xapian
+our @HELP = (
+ 's:' => 'match within Subject e.g. s:"a quick brown fox"',
+ '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
+ 'b:' => 'match within message body, including text attachments',
+ 'nq:' => 'match non-quoted text within message body',
+ 'q:' => 'match quoted text within message body',
+ 'n:' => 'match filename of attachment(s)',
+ 't:' => 'match within the To header',
+ 'c:' => 'match within the Cc header',
+ 'f:' => 'match within the From header',
+ 'a:' => 'match within the To, Cc, and From headers',
+ 'tc:' => 'match within the To and Cc headers',
+ 'bs:' => 'match within the Subject and body',
+ 'dfn:' => 'match filename from diff',
+ 'dfa:' => 'match diff removed (-) lines',
+ 'dfb:' => 'match diff added (+) lines',
+ 'dfhh:' => 'match diff hunk header context (usually a function name)',
+ 'dfctx:' => 'match diff context lines',
+ 'dfpre:' => 'match pre-image git blob ID',
+ 'dfpost:' => 'match post-image git blob ID',
+ 'dfblob:' => 'match either pre or post-image git blob ID',
+);
+chomp @HELP;
-my $mail_query = Search::Xapian::Query->new(xpfx('type') . 'mail');
+my $mail_query = Search::Xapian::Query->new('T' . 'mail');
sub xdir {
- my (undef, $git_dir) = @_;
- "$git_dir/public-inbox/xapian" . SCHEMA_VERSION;
+ my ($self) = @_;
+ if ($self->{version} == 1) {
+ "$self->{mainrepo}/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";
+ }
}
sub new {
- my ($class, $git_dir) = @_;
- my $dir = $class->xdir($git_dir);
- my $db = Search::Xapian::Database->new($dir);
- bless { xdb => $db, git_dir => $git_dir }, $class;
+ my ($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,
+ }, $class;
+ if ($version >= 2) {
+ my $dir = "$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);
+ if ($xdb) {
+ $xdb->add_database($sub);
+ } else {
+ $xdb = $sub;
+ }
+ }
+ warn "v2 repo with $parts found in $dir\n";
+ $self->{xdb} = $xdb;
+ $self->{skel} = Search::Xapian::Database->new("$dir/all");
+ } else {
+ $self->{xdb} = Search::Xapian::Database->new($self->xdir);
+ }
+ $self;
}
-sub reopen { $_[0]->{xdb}->reopen }
+sub reopen {
+ my ($self) = @_;
+ $self->{xdb}->reopen;
+ if (my $skel = $self->{skel}) {
+ $skel->reopen;
+ }
+}
# read-only
sub query {
sub get_thread {
my ($self, $mid, $opts) = @_;
- my $smsg = eval { $self->lookup_message($mid) };
+ my $smsg = retry_reopen($self, sub { lookup_skeleton($self, $mid) });
return { total => 0, msgs => [] } unless $smsg;
- my $qtid = Search::Xapian::Query->new(xpfx('thread').$smsg->thread_id);
- my $path = id_compress($smsg->path);
- my $qsub = Search::Xapian::Query->new(xpfx('path').$path);
- my $query = Search::Xapian::Query->new(OP_OR, $qtid, $qsub);
+ my $qtid = Search::Xapian::Query->new('G' . $smsg->thread_id);
+ my $path = $smsg->path;
+ if (defined $path && $path ne '') {
+ my $path = id_compress($smsg->path);
+ my $qsub = Search::Xapian::Query->new('XPATH' . $path);
+ $qtid = Search::Xapian::Query->new(OP_OR, $qtid, $qsub);
+ }
$opts ||= {};
$opts->{limit} ||= 1000;
- _do_enquire($self, $query, $opts);
+
+ # always sort threads by timestamp, this makes life easier
+ # for the threading algorithm (in SearchThread.pm)
+ $opts->{asc} = 1;
+ $opts->{enquire} = enquire_skel($self);
+ _do_enquire($self, $qtid, $opts);
}
-sub _do_enquire {
- my ($self, $query, $opts) = @_;
+sub retry_reopen {
+ my ($self, $cb) = @_;
my $ret;
for (1..10) {
- eval { $ret = _enquire_once($self, $query, $opts) };
+ eval { $ret = $cb->() };
return $ret unless $@;
# Exception: The revision being read has been discarded -
# you should call Xapian::Database::reopen()
- if (index($@, 'Xapian::Database::reopen') >= 0) {
+ if (ref($@) eq 'Search::Xapian::DatabaseModifiedError') {
reopen($self);
} else {
- die $@;
+ warn "ref: ", ref($@), "\n";
+ die;
}
}
}
+sub _do_enquire {
+ my ($self, $query, $opts) = @_;
+ retry_reopen($self, sub { _enquire_once($self, $query, $opts) });
+}
+
sub _enquire_once {
my ($self, $query, $opts) = @_;
- my $enquire = $self->enquire;
+ my $enquire = $opts->{enquire} || enquire($self);
if (defined $query) {
$query = Search::Xapian::Query->new(OP_AND,$query,$mail_query);
} else {
$qp->set_database($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 (boolean)
+EOF
+ # gmane => XGMANE
+ $qp->add_boolean_prefix($pfx, 'X'.uc($pfx));
+ }
+ chomp @$user_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 date_range_processor {
- $_[0]->{drp} ||= Search::Xapian::DateValueRangeProcessor->new(TS);
-}
-
sub num_range_processor {
$_[0]->{nrp} ||= Search::Xapian::NumberValueRangeProcessor->new(NUM);
}
_do_enquire($self, $query, {num => 1, limit => 200, offset => $offset});
}
+sub lookup_skeleton {
+ my ($self, $mid) = @_;
+ my $skel = $self->{skel} or return lookup_message($self, $mid);
+ $mid = mid_clean($mid);
+ my $term = 'XMID' . $mid;
+ my $smsg;
+ my $beg = $skel->postlist_begin($term);
+ if ($beg != $skel->postlist_end($term)) {
+ my $doc_id = $beg->get_docid;
+ if (defined $doc_id) {
+ # raises on error:
+ my $doc = $skel->get_document($doc_id);
+ $smsg = PublicInbox::SearchMsg->wrap($doc, $mid);
+ $smsg->{doc_id} = $doc_id;
+ }
+ }
+ $smsg;
+}
+
sub lookup_message {
my ($self, $mid) = @_;
$mid = mid_clean($mid);
- my $doc_id = $self->find_unique_doc_id('mid', $mid);
+ my $doc_id = $self->find_first_doc_id('XMID' . $mid);
my $smsg;
if (defined $doc_id) {
# raises on error:
my $doc = $self->{xdb}->get_document($doc_id);
$smsg = PublicInbox::SearchMsg->wrap($doc, $mid);
- $smsg->doc_id($doc_id);
+ $smsg->{doc_id} = $doc_id;
}
$smsg;
}
+sub lookup_mail { # no ghosts!
+ my ($self, $mid) = @_;
+ retry_reopen($self, sub {
+ my $smsg = lookup_message($self, $mid) or return;
+ $smsg->load_expand;
+ });
+}
+
sub find_unique_doc_id {
- my ($self, $term, $value) = @_;
+ my ($self, $termval) = @_;
- my ($begin, $end) = $self->find_doc_ids($term, $value);
+ my ($begin, $end) = $self->find_doc_ids($termval);
return undef if $begin->equal($end); # not found
# sanity check
$begin->inc;
- $begin->equal($end) or die "Term '$term:$value' is not unique\n";
+ $begin->equal($end) or die "Term '$termval' is not unique\n";
$rv;
}
# returns begin and end PostingIterator
sub find_doc_ids {
- my ($self, $term, $value) = @_;
+ my ($self, $termval) = @_;
+ my $db = $self->{xdb};
- $self->find_doc_ids_for_term(xpfx($term) . $value);
+ ($db->postlist_begin($termval), $db->postlist_end($termval));
}
-# returns begin and end PostingIterator
-sub find_doc_ids_for_term {
- my ($self, $term) = @_;
- my $db = $self->{xdb};
+sub find_first_doc_id {
+ my ($self, $termval) = @_;
+
+ my ($begin, $end) = $self->find_doc_ids($termval);
+
+ return undef if $begin->equal($end); # not found
- ($db->postlist_begin($term), $db->postlist_end($term));
+ $begin->get_docid;
}
# normalize subjects so they are suitable as pathnames for URLs
+# XXX: consider for removal
sub subject_path {
my $subj = pop;
$subj = subject_normalized($subj);
$subj;
}
-# for doc data
-sub subject_summary {
- my $subj = pop;
- my $max = 68;
- if (length($subj) > $max) {
- my @subj = split(/\s+/, $subj);
- $subj = '';
- my $l;
-
- while ($l = shift @subj) {
- my $new = $subj . $l . ' ';
- last if length($new) >= $max;
- $subj = $new;
- }
- if ($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 = $subj[0] . ' ...';
- }
+sub enquire {
+ my ($self) = @_;
+ $self->{enquire} ||= Search::Xapian::Enquire->new($self->{xdb});
+}
+
+sub enquire_skel {
+ my ($self) = @_;
+ if (my $skel = $self->{skel}) {
+ $self->{enquire_skel} ||= Search::Xapian::Enquire->new($skel);
+ } else {
+ enquire($self);
}
- $subj;
}
-sub enquire {
+sub help {
my ($self) = @_;
- $self->{enquire} ||= Search::Xapian::Enquire->new($self->{xdb});
+ $self->qp; # parse altids
+ my @ret = @HELP;
+ if (my $user_pfx = $self->{-user_pfx}) {
+ push @ret, @$user_pfx;
+ }
+ \@ret;
}
1;