# Read-only search interface for use by the web and NNTP interfaces
package PublicInbox::Search;
use strict;
+use parent qw(Exporter);
+our @EXPORT_OK = qw(mdocid);
-# values for searching
+# values for searching, changing the numeric value breaks
+# compatibility with old indices (so don't change them it)
use constant {
TS => 0, # Received: header in Unix time (IMAP INTERNALDATE)
YYYYMMDD => 1, # Date: header for searching in the WWW UI
DT => 2, # Date: YYYYMMDDHHMMSS
+
+ # added for public-inbox 1.6.0+
BYTES => 3, # IMAP RFC822.SIZE
UID => 4, # IMAP UID == NNTP article number == Xapian docid
+
# TODO
- # REPLYCNT => 4, # IMAP ANSWERED
+ # THREADID => ?
+ # REPLYCNT => ?, # IMAP ANSWERED
+
+ # SCHEMA_VERSION history
+ # 0 - initial
+ # 1 - subject_path is lower-cased
+ # 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 (SHA-1)
+ # 10 - optimize doc for NNTP overviews
+ # 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
+ # 15 - see public-inbox-v2-format(5)
+ # further bumps likely unnecessary, we'll suggest in-place
+ # "--reindex" use for further fixes and tweaks:
+ #
+ # public-inbox v1.5.0 adds (still SCHEMA_VERSION=15):
+ # * "lid:" and "l:" for List-Id searches
+ #
+ # v1.6.0 adds BYTES and UID values
+ SCHEMA_VERSION => 15,
};
use PublicInbox::Smsg;
# a prefix common in patch emails
our $LANG = 'english';
-use constant {
- # SCHEMA_VERSION history
- # 0 - initial
- # 1 - subject_path is lower-cased
- # 2 - subject_path is id_compress in the index, only
- # 3 - message-ID is compressed if it includes '%' (hack!)
- # 4 - change "Re: " normalization, avoid circular Reference ghosts
- # 5 - subject_path drops trailing '.'
- # 6 - preserve References: order in document data
- # 7 - remove references and inreplyto terms
- # 8 - remove redundant/unneeded document data
- # 9 - disable Message-ID compression (SHA-1)
- # 10 - optimize doc for NNTP overviews
- # 11 - merge threads when vivifying ghosts
- # 12 - change YYYYMMDD value column to numeric
- # 13 - fix threading for empty References/In-Reply-To
- # (commit 83425ef12e4b65cdcecd11ddcb38175d4a91d5a0)
- # 14 - fix ghost root vivification
- # 15 - see public-inbox-v2-format(5)
- # further bumps likely unnecessary, we'll suggest in-place
- # "--reindex" use for further fixes and tweaks
- #
- # public-inbox v1.5.0 adds (still SCHEMA_VERSION=15):
- # * "lid:" and "l:" for List-Id searches
- SCHEMA_VERSION => 15,
-};
-
# note: the non-X term prefix allocations are shared with
# Xapian omega, see xapian-applications/omega/docs/termprefixes.rst
my %bool_pfx_external = (
if ($query_string eq '' && !$opts->{mset}) {
$self->{over_ro}->recent($opts);
} else {
- my $qp = qp($self);
+ my $qp = $self->{qp} //= qparse_new($self);
my $qp_flags = $self->{qp_flags};
my $query = $qp->parse_query($query_string, $qp_flags);
$opts->{relevance} = 1 unless exists $opts->{relevance};
my $limit = $opts->{limit} || 50;
my $mset = $enquire->get_mset($offset, $limit);
return $mset if $opts->{mset};
- my @msgs = map { PublicInbox::Smsg::from_mitem($_) } $mset->items;
- return \@msgs unless wantarray;
-
- ($mset->get_matches_estimated, \@msgs)
+ my $nshard = $self->{nshard} // 1;
+ my $i = 0;
+ my %order = map { mdocid($nshard, $_) => ++$i } $mset->items;
+ my @msgs = sort {
+ $order{$a->{num}} <=> $order{$b->{num}}
+ } @{$self->{over_ro}->get_all(keys %order)};
+ wantarray ? ($mset->get_matches_estimated, \@msgs) : \@msgs;
}
# read-write
sub stemmer { $X{Stem}->new($LANG) }
# read-only
-sub qp {
+sub qparse_new ($) {
my ($self) = @_;
- my $qp = $self->{query_parser};
- return $qp if $qp;
my $xdb = xdb($self);
- # new parser
- $qp = $X{QueryParser}->new;
+ my $qp = $X{QueryParser}->new;
$qp->set_default_op(OP_AND());
$qp->set_database($xdb);
- $qp->set_stemmer($self->stemmer);
+ $qp->set_stemmer(stemmer($self));
$qp->set_stemming_strategy(STEM_SOME());
$qp->set_max_wildcard_expansion(100);
my $nvrp = $X{NumberValueRangeProcessor};
while (my ($name, $prefix) = each %prob_prefix) {
$qp->add_prefix($name, $_) foreach split(/ /, $prefix);
}
-
- $self->{query_parser} = $qp;
+ $qp;
}
sub help {
my ($self) = @_;
- $self->qp; # parse altids
+ $self->{qp} //= qparse_new($self); # parse altids
my @ret = @HELP;
if (my $user_pfx = $self->{-user_pfx}) {
push @ret, @$user_pfx;