use warnings;
# 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 constant TS => 0; # Received: header in Unix time
+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/mid_clean id_compress/;
+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
-our $REPLY_RE = qr/^re:\s+/i;
our $LANG = 'english';
use constant {
# 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
- QP_FLAGS => FLAG_PHRASE|FLAG_BOOLEAN|FLAG_LOVEHATE|FLAG_WILDCARD,
+ SCHEMA_VERSION => 15,
};
-# setup prefixes
-my %bool_pfx_internal = (
- type => 'T', # "mail" or "ghost"
- thread => 'G', # newsGroup (or similar entity - e.g. a web forum name)
-);
-
my %bool_pfx_external = (
- mid => 'XMID', # Message-ID (full/exact)
+ mid => 'Q', # Message-ID (full/exact), this is mostly uniQue
+ dfpre => 'XDFPRE',
+ dfpost => 'XDFPOST',
+ dfblob => 'XDFPRE XDFPOST',
);
+my $non_quoted_body = 'XNQ XDFN XDFA XDFB XDFHH XDFCTX XDFPRE XDFPOST';
my %prob_prefix = (
# for mairix compatibility
s => 'S',
c => 'XCC',
tcf => 'XTO XCC A',
a => 'XTO XCC A',
- b => 'XNQ XQUOT',
- bs => 'XNQ XQUOT S',
+ b => $non_quoted_body . ' XQUOT',
+ bs => $non_quoted_body . ' XQUOT S',
n => 'XFN',
q => 'XQUOT',
- nq => 'XNQ',
+ nq => $non_quoted_body,
dfn => 'XDFN',
dfa => 'XDFA',
dfb => 'XDFB',
dfhh => 'XDFHH',
dfctx => 'XDFCTX',
- dfpre => 'XDFPRE',
- dfpost => 'XDFPOST',
- dfblob => 'XDFPRE XDFPOST',
# default:
- '' => 'XM S A XNQ XQUOT XFN',
+ '' => 'XM S A XQUOT XFN ' . $non_quoted_body,
);
# not documenting m: and mid: for now, the using the URLs works w/o Xapian
date range as YYYYMMDD e.g. d:19931002..20101002
Open-ended ranges such as d:19931002.. and d:..20101002
are also supported
+EOF
+ 'dt:' => <<EOF,
+date-time range as YYYYMMDDhhmmss (e.g. dt:19931002011000..19931002011200)
EOF
'b:' => 'match within message body, including text attachments',
'nq:' => 'match non-quoted text within message body',
);
chomp @HELP;
-my $mail_query = Search::Xapian::Query->new('T' . 'mail');
-
-sub xdir {
- my ($self) = @_;
+sub xdir ($;$) {
+ my ($self, $rdonly) = @_;
if ($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";
+ 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 = $ibx->{mainrepo};
+sub _xdb ($) {
+ 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";
+ }
+ } else {
+ $slow_phrase = -f "$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 {
- mainrepo => $mainrepo,
- altid => $altid,
- version => $version,
+ mainrepo => $ibx->{mainrepo},
+ altid => $ibx->{altid},
+ version => $ibx->{version} // 1,
}, $class;
- $self->{xdb} = Search::Xapian::Database->new($self->xdir);
+ my $dir = xdir($self, 1);
+ $self->{over_ro} = PublicInbox::Over->new("$dir/over.sqlite3");
$self;
}
-sub reopen { $_[0]->{xdb}->reopen }
+sub reopen {
+ my ($self) = @_;
+ if (my $xdb = $self->{xdb}) {
+ $xdb->reopen;
+ }
+ $self; # make chaining easier
+}
# read-only
sub query {
my ($self, $query_string, $opts) = @_;
- my $query;
-
$opts ||= {};
- unless ($query_string eq '') {
- $query = $self->qp->parse_query($query_string, QP_FLAGS);
+ if ($query_string eq '' && !$opts->{mset}) {
+ $self->{over_ro}->recent($opts);
+ } else {
+ 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, $opts);
}
-
- _do_enquire($self, $query, $opts);
-}
-
-sub get_thread {
- my ($self, $mid, $opts) = @_;
- my $smsg = eval { $self->lookup_message($mid) };
-
- return { total => 0, msgs => [] } unless $smsg;
- 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;
-
- # always sort threads by timestamp, this makes life easier
- # for the threading algorithm (in SearchThread.pm)
- $opts->{asc} = 1;
-
- _do_enquire($self, $qtid, $opts);
}
sub retry_reopen {
my ($self, $cb) = @_;
- my $ret;
- for (1..10) {
- eval { $ret = $cb->() };
- return $ret unless $@;
+ for my $i (1..10) {
+ if (wantarray) {
+ my @ret;
+ eval { @ret = $cb->() };
+ return @ret unless $@;
+ } else {
+ my $ret;
+ eval { $ret = $cb->() };
+ return $ret unless $@;
+ }
# Exception: The revision being read has been discarded -
# you should call Xapian::Database::reopen()
if (ref($@) eq 'Search::Xapian::DatabaseModifiedError') {
+ warn "reopen try #$i on $@\n";
reopen($self);
} else {
+ # let caller decide how to spew, because ExtMsg queries
+ # get wonky and trigger:
+ # "something terrible happened at .../Xapian/Enquire.pm"
die;
}
}
+ die "Too many Xapian database modifications in progress\n";
}
sub _do_enquire {
sub _enquire_once {
my ($self, $query, $opts) = @_;
- my $enquire = $self->enquire;
- if (defined $query) {
- $query = Search::Xapian::Query->new(OP_AND,$query,$mail_query);
- } else {
- $query = $mail_query;
- }
+ my $xdb = xdb($self);
+ my $enquire = Search::Xapian::Enquire->new($xdb);
$enquire->set_query($query);
$opts ||= {};
my $desc = !$opts->{asc};
- if ($opts->{relevance}) {
+ if (($opts->{mset} || 0) == 2) {
+ $enquire->set_docid_order(Search::Xapian::ENQ_ASCENDING());
+ $enquire->set_weighting_scheme(Search::Xapian::BoolWeight->new);
+ } elsif ($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, $desc);
}
my @msgs = map {
PublicInbox::SearchMsg->load_doc($_->get_document);
} $mset->items;
+ return \@msgs unless wantarray;
- { total => $mset->get_matches_estimated, msgs => \@msgs }
+ ($mset->get_matches_estimated, \@msgs)
}
# read-write
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:'));
+ $qp->add_valuerangeprocessor(
+ Search::Xapian::NumberValueRangeProcessor->new(DT, 'dt:'));
while (my ($name, $prefix) = each %bool_pfx_external) {
- $qp->add_boolean_prefix($name, $prefix);
+ $qp->add_boolean_prefix($name, $_) foreach split(/ /, $prefix);
}
# we do not actually create AltId objects,
$self->{query_parser} = $qp;
}
-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);
-
- 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;
- }
- $smsg;
-}
-
-sub lookup_mail { # no ghosts!
- my ($self, $mid) = @_;
- retry_reopen($self, sub {
- my $smsg = lookup_message($self, $mid) or return;
- $smsg->load_expand;
- });
-}
-
-sub find_unique_doc_id {
- my ($self, $termval) = @_;
-
- my ($begin, $end) = $self->find_doc_ids($termval);
-
- return undef if $begin->equal($end); # not found
-
- my $rv = $begin->get_docid;
-
- # sanity check
- $begin->inc;
- $begin->equal($end) or die "Term '$termval' is not unique\n";
- $rv;
-}
-
-# returns begin and end PostingIterator
-sub find_doc_ids {
- my ($self, $termval) = @_;
- my $db = $self->{xdb};
-
- ($db->postlist_begin($termval), $db->postlist_end($termval));
-}
-
-sub find_first_doc_id {
- my ($self, $termval) = @_;
-
- my ($begin, $end) = $self->find_doc_ids($termval);
-
- return undef if $begin->equal($end); # not found
-
- $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);
- $subj =~ s![^a-zA-Z0-9_\.~/\-]+!_!g;
- lc($subj);
-}
-
-sub subject_normalized {
- my $subj = pop;
- $subj =~ s/\A\s+//s; # no leading space
- $subj =~ s/\s+\z//s; # no trailing space
- $subj =~ s/\s+/ /gs; # no redundant spaces
- $subj =~ s/\.+\z//; # no trailing '.'
- $subj =~ s/$REPLY_RE//igo; # remove reply prefix
- $subj;
-}
-
-sub enquire {
- my ($self) = @_;
- $self->{enquire} ||= Search::Xapian::Enquire->new($self->{xdb});
+sub lookup_article {
+ my ($self, $num) = @_;
+ $self->{over_ro}->get_art($num);
}
sub help {