X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearch.pm;h=b7db2b9f7fcc91aacc317ef3e439b6349934083c;hb=b714ab45d30d6f0298d73ef4281c1d0263a02493;hp=7f901125057275376041a59ecf5ec69eba6206b0;hpb=95bdac7f09c69036efed537a4d03d5bdd2ae4eb6;p=public-inbox.git

diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 7f901125..b7db2b9f 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -12,7 +12,7 @@ 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 PublicInbox::SearchMsg;
+use PublicInbox::Smsg;
 use PublicInbox::Over;
 my $QP_FLAGS;
 our %X = map { $_ => 0 } qw(BoolWeight Database Enquire
@@ -36,8 +36,8 @@ sub load_xapian () {
 		$ENQ_ASCENDING = $x eq 'Xapian' ?
 				1 : Search::Xapian::ENQ_ASCENDING();
 
-		# for SearchMsg:
-		*PublicInbox::SearchMsg::sortable_unserialise =
+		# for Smsg:
+		*PublicInbox::Smsg::sortable_unserialise =
 						$Xap.'::sortable_unserialise';
 		# n.b. FLAG_PURE_NOT is expensive not suitable for a public
 		# website as it could become a denial-of-service vector
@@ -77,11 +77,17 @@ use constant {
 	# 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',
@@ -92,6 +98,7 @@ my %prob_prefix = (
 	# 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',
@@ -134,6 +141,8 @@ 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',
 	'bs:' => 'match within the Subject and body',
 	'dfn:' => 'match filename from diff',
 	'dfa:' => 'match diff removed (-) lines',
@@ -279,7 +288,7 @@ sub _enquire_once { # retry_reopen callback
 	my $limit = $opts->{limit} || 50;
 	my $mset = $enquire->get_mset($offset, $limit);
 	return $mset if $opts->{mset};
-	my @msgs = map { PublicInbox::SearchMsg::from_mitem($_) } $mset->items;
+	my @msgs = map { PublicInbox::Smsg::from_mitem($_) } $mset->items;
 	return \@msgs unless wantarray;
 
 	($mset->get_matches_estimated, \@msgs)
@@ -313,9 +322,11 @@ sub qp {
 	# 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;