# 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;
# 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 = (
mid => 'Q', # Message-ID (full/exact), this is mostly uniQue
+ lid => 'G', # newsGroup (or similar entity), just inside <>
dfpre => 'XDFPRE',
dfpost => 'XDFPOST',
dfblob => 'XDFPRE XDFPOST',
# for mairix compatibility
s => 'S',
m => 'XM', # 'mid:' (bool) is exact, 'm:' (prob) can do partial
+ l => 'XL', # 'lid:' (bool) is exact, 'l:' (prob) can do partial
f => 'A',
t => 'XTO',
tc => 'XTO XCC',
);
# 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,
'f:' => 'match within the From header',
'a:' => 'match within the To, Cc, and From headers',
'tc:' => 'match within the To and Cc headers',
+ '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',
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);
$xdb = $sub;
}
$slow_phrase ||= -f "$shard/iamchert";
+ ++$n;
}
+ $self->{nshard} = $n;
} else {
$slow_phrase = -f "$dir/iamchert";
$xdb = $X{Database}->new($dir);
$xdb;
}
+# v2 Xapian docids don't conflict, so they're identical to
+# NNTP article numbers and IMAP UIDs.
+# https://trac.xapian.org/wiki/FAQ/MultiDatabaseDocumentID
+sub mdocid {
+ my ($nshard, $mitem) = @_;
+ my $docid = $mitem->get_docid;
+ int(($docid - 1) / $nshard) + 1;
+}
+
sub xdb ($) {
my ($self) = @_;
$self->{xdb} ||= do {
$enquire->set_query($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}) {
$qp->add_valuerangeprocessor($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);
}
# 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} ||= [];
+ my $user_pfx = $self->{-user_pfx} = [];
for (@$altid) {
# $_ = 'serial:gmane:/path/to/gmane.msgmap.sqlite3'
+ # note: Xapian supports multibyte UTF-8, /^[0-9]+$/,
+ # and '_' with prefixes matching \w+
/\Aserial:(\w+):/ or next;
my $pfx = $1;
push @$user_pfx, "$pfx:", <<EOF;