wwwstream: reduce blob fetch paths for ->getline

[public-inbox.git] / lib / PublicInbox / Search.pm

diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index b7db2b9f7fcc91aacc317ef3e439b6349934083c..55eee41ca4a88c43594e9e0899c3dba25e77771e 100644 (file)
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -5,12 +5,17 @@
 # Read-only search interface for use by the web and NNTP interfaces
 package PublicInbox::Search;
 use strict;
-use warnings;
 
 # values for searching
-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 constant {
+       TS => 0, # Received: header in Unix time (IMAP INTERNALDATE)
+       YYYYMMDD => 1, # Date: header for searching in the WWW UI
+       DT => 2, # Date: YYYYMMDDHHMMSS
+       BYTES => 3, # IMAP RFC822.SIZE
+       UID => 4, # IMAP UID == NNTP article number == Xapian docid
+       # TODO
+       # REPLYCNT => 4, # IMAP ANSWERED
+};
 
 use PublicInbox::Smsg;
 use PublicInbox::Over;
@@ -122,6 +127,9 @@ my %prob_prefix = (
 );
 
 # not documenting m: and mid: for now, the using the URLs works w/o Xapian
+# not documenting lid: for now, either, it is probably redundant with l:,
+# especially since we don't offer boolean searches for To/Cc/From
+# headers, either
 our @HELP = (
        's:' => 'match within Subject  e.g. s:"a quick brown fox"',
        'd:' => <<EOF,
@@ -141,8 +149,7 @@ EOF
        'f:' => 'match within the From header',
        'a:' => 'match within the To, Cc, and From headers',
        'tc:' => 'match within the To and Cc headers',
-       'lid:' => 'exact contents of the List-Id',
-       'l:' => 'partial match contents of the List-Id header',
+       'l:' => 'match contents of the List-Id header',
        'bs:' => 'match within the Subject and body',
        'dfn:' => 'match filename from diff',
        'dfa:' => 'match diff removed (-) lines',
@@ -175,6 +182,7 @@ sub _xdb ($) {
        my ($xdb, $slow_phrase);
        my $qpf = \($self->{qp_flags} ||= $QP_FLAGS);
        if ($self->{ibx_ver} >= 2) {
+               my $n = 0;
                foreach my $shard (<$dir/*>) {
                        -d $shard && $shard =~ m!/[0-9]+\z! or next;
                        my $sub = $X{Database}->new($shard);
@@ -184,7 +192,9 @@ sub _xdb ($) {
                                $xdb = $sub;
                        }
                        $slow_phrase ||= -f "$shard/iamchert";
+                       ++$n;
                }
+               $self->{nshard} = $n;
        } else {
                $slow_phrase = -f "$dir/iamchert";
                $xdb = $X{Database}->new($dir);
@@ -193,6 +203,15 @@ sub _xdb ($) {
        $xdb;
 }
 
+# v2 Xapian docids don't conflict, so they're identical to
+# NNTP article numbers and IMAP UIDs.
+# https://trac.xapian.org/wiki/FAQ/MultiDatabaseDocumentID
+sub mdocid {
+       my ($nshard, $mitem) = @_;
+       my $docid = $mitem->get_docid;
+       int(($docid - 1) / $nshard) + 1;
+}
+
 sub xdb ($) {
        my ($self) = @_;
        $self->{xdb} ||= do {
@@ -276,7 +295,7 @@ sub _enquire_once { # retry_reopen callback
        $enquire->set_query($query);
        $opts ||= {};
         my $desc = !$opts->{asc};
-       if (($opts->{mset} || 0) == 2) {
+       if (($opts->{mset} || 0) == 2) { # mset == 2: ORDER BY docid/UID
                $enquire->set_docid_order($ENQ_ASCENDING);
                $enquire->set_weighting_scheme($X{BoolWeight}->new);
        } elsif ($opts->{relevance}) {
@@ -315,6 +334,11 @@ sub qp {
        $qp->add_valuerangeprocessor($nvrp->new(YYYYMMDD, 'd:'));
        $qp->add_valuerangeprocessor($nvrp->new(DT, 'dt:'));
 
+       # for IMAP, undocumented for WWW and may be split off go away
+       $qp->add_valuerangeprocessor($nvrp->new(BYTES, 'bytes:'));
+       $qp->add_valuerangeprocessor($nvrp->new(TS, 'ts:'));
+       $qp->add_valuerangeprocessor($nvrp->new(UID, 'uid:'));
+
        while (my ($name, $prefix) = each %bool_pfx_external) {
                $qp->add_boolean_prefix($name, $_) foreach split(/ /, $prefix);
        }