search: fix space regressions from recent changes

As of Xapian 1.0.4 (from 2007) is possible to use
Search::Xapian::QueryParser::add_prefix multiple times with the
same user field name but different term prefixes.

This brings my current git@vger mirror from 6.5GB to 2.1GB
(both sizes are after xapian-compact).

diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index f74129d5da1c382fa75dd38f8ca634916349af81..c8e297f42634a842c3b9b3ba033d21cd71353d9e 100644 (file)
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -60,20 +60,23 @@ my %bool_pfx_external = (
 my %prob_prefix = (
        # for mairix compatibility
        s => 'S',
-       m => 'Q', # 'mid' is exact, 'm' can do partial
+       m => 'XMID', # 'mid:' (bool) is exact, 'm:' (prob) can do partial
        f => 'A',
        t => 'XTO',
-       tc => 'XTC',
+       tc => 'XTO XCC',
        c => 'XCC',
-       tcf => 'XTCF',
-       b => 'XBODY',
-       bs => 'XBS',
+       tcf => 'XTO XCC A',
+       b => 'XNQ XQUOT',
+       bs => 'XNQ XQUOT S',
 
        # 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',
 );
 
 # not documenting m: and mid: for now, the using the URLs works w/o Xapian
@@ -241,7 +244,7 @@ EOF
        }
 
        while (my ($name, $prefix) = each %prob_prefix) {
-               $qp->add_prefix($name, $prefix);
+               $qp->add_prefix($name, $_) foreach split(/ /, $prefix);
        }
 
        $self->{query_parser} = $qp;

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index cd27a29459e2360d1607cc7267d910af3aa8acb4..ae890605d14e56a7386f100ee477786d45c5dc2f 100644 (file)
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -129,15 +129,9 @@ sub index_users ($$) {
 
        $tg->index_text($from, 1, 'A'); # A - author
        $tg->increase_termpos;
-
        $tg->index_text($to, 1, 'XTO') if $to ne '';
+       $tg->increase_termpos;
        $tg->index_text($cc, 1, 'XCC') if $cc ne '';
-       my $tc = join("\t", $to, $cc);
-       $tg->index_text($tc, 1, 'XTC') if $tc ne '';
-       my $tcf = join("\t", $tc, $from);
-       $tg->index_text($tcf, 1, 'XTCF') if $tcf ne '';
-
-       $tg->index_text($from);
        $tg->increase_termpos;
 }
 
@@ -173,12 +167,7 @@ sub add_message {
                my $tg = $self->term_generator;
 
                $tg->set_document($doc);
-               if ($subj) {
-                       $tg->index_text($subj, 1, 'S');
-                       $tg->index_text($subj, 1, 'XBS');
-               }
-               $tg->increase_termpos;
-               $tg->index_text($subj) if $subj;
+               $tg->index_text($subj, 1, 'S') if $subj;
                $tg->increase_termpos;
 
                index_users($tg, $smsg);
@@ -204,25 +193,19 @@ sub add_message {
                        if (@quot) {
                                my $s = join("\n", @quot);
                                @quot = ();
-                               $tg->index_text($s, 1, 'XQUOT');
-                               $tg->index_text($s, 0, 'XBS');
-                               $tg->index_text($s, 0, 'XBODY');
-                               $tg->index_text($s, 0);
+                               $tg->index_text($s, 0, 'XQUOT');
                                $tg->increase_termpos;
                        }
                        if (@orig) {
                                my $s = join("\n", @orig);
                                @orig = ();
                                $tg->index_text($s, 1, 'XNQ');
-                               $tg->index_text($s, 1, 'XBS');
-                               $tg->index_text($s, 1, 'XBODY');
-                               $tg->index_text($s);
                                $tg->increase_termpos;
                        }
                });
 
                link_message($self, $smsg, $old_tid);
-               $tg->index_text($mid, 1);
+               $tg->index_text($mid, 1, 'XMID');
                $doc->set_data($smsg->to_doc_data($blob));
 
                if (my $altid = $self->{-altid}) {