X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearch.pm;h=b739faf1a50c7eae1ae781078a0621fa71e648c4;hb=6e0659d2ae455fb28d433fd8c71b563210a3997a;hp=4e08aed7acbf0697ccdd9593325080b63e8e637d;hpb=298c806d51f31796caa65da70ab6bfa310db614a;p=public-inbox.git

diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 4e08aed7..b739faf1 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -5,34 +5,82 @@
 # 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
+	THREADID => 5, # RFC 8474, RFC 8621
+
 	# TODO
-	# REPLYCNT => 4, # IMAP ANSWERED
+	# 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, UID and THREADID values
+	SCHEMA_VERSION => 15,
 };
 
 use PublicInbox::Smsg;
 use PublicInbox::Over;
 my $QP_FLAGS;
-our %X = map { $_ => 0 } qw(BoolWeight Database Enquire
-			NumberValueRangeProcessor QueryParser Stem);
+our %X = map { $_ => 0 } qw(BoolWeight Database Enquire QueryParser Stem);
 our $Xap; # 'Search::Xapian' or 'Xapian'
+my $NVRP; # '$Xap::'.('NumberValueRangeProcessor' or 'NumberRangeProcessor')
 my $ENQ_ASCENDING;
 
 sub load_xapian () {
 	return 1 if defined $Xap;
-	for my $x (qw(Search::Xapian Xapian)) {
+	# n.b. PI_XAPIAN is intended for development use only.  We still
+	# favor Search::Xapian since that's what's available in current
+	# Debian stable (10.x) and derived distros.
+	for my $x (($ENV{PI_XAPIAN} // 'Search::Xapian'), 'Xapian') {
 		eval "require $x";
 		next if $@;
 
 		$x->import(qw(:standard));
 		$Xap = $x;
+
+		# `version_string' was added in Xapian 1.1
+		my $xver = eval('v'.eval($x.'::version_string()')) //
+				eval('v'.eval($x.'::xapian_version_string()'));
+
+		# NumberRangeProcessor was added in Xapian 1.3.6,
+		# NumberValueRangeProcessor was removed for 1.5.0+,
+		# favor the older /Value/ variant since that's what our
+		# (currently) preferred Search::Xapian supports
+		$NVRP = $x.'::'.($x eq 'Xapian' && $xver ge v1.5 ?
+			'NumberRangeProcessor' : 'NumberValueRangeProcessor');
 		$X{$_} = $Xap.'::'.$_ for (keys %X);
 
 		# ENQ_ASCENDING doesn't seem exported by SWIG Xapian.pm,
@@ -61,33 +109,6 @@ sub load_xapian () {
 # 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 = (
@@ -177,19 +198,24 @@ 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);
-			if ($xdb) {
-				$xdb->add_database($sub);
-			} else {
-				$xdb = $sub;
+		my @xdb;
+		opendir(my $dh, $dir) or return; # not initialized yet
+
+		# We need numeric sorting so shard[0] is first for reading
+		# Xapian metadata, if needed
+		for (sort { $a <=> $b } grep(/\A[0-9]+\z/, readdir($dh))) {
+			my $shard_dir = "$dir/$_";
+			if (-d $shard_dir && -r _) {
+				push @xdb, $X{Database}->new($shard_dir);
+				$slow_phrase ||= -f "$shard_dir/iamchert";
+			} else { # gaps from missing epochs throw off mdocid()
+				warn "E: $shard_dir missing or unreadable\n";
+				return;
 			}
-			$slow_phrase ||= -f "$shard/iamchert";
-			++$n;
 		}
-		$self->{nshard} = $n;
+		$self->{nshard} = scalar(@xdb);
+		$xdb = shift @xdb;
+		$xdb->add_database($_) for @xdb;
 	} else {
 		$slow_phrase = -f "$dir/iamchert";
 		$xdb = $X{Database}->new($dir);
@@ -207,6 +233,12 @@ sub mdocid {
 	int(($docid - 1) / $nshard) + 1;
 }
 
+sub mset_to_artnums {
+	my ($self, $mset) = @_;
+	my $nshard = $self->{nshard} // 1;
+	[ map { mdocid($nshard, $_) } $mset->items ];
+}
+
 sub xdb ($) {
 	my ($self) = @_;
 	$self->{xdb} ||= do {
@@ -253,7 +285,7 @@ sub query {
 	if ($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 $opts->{relevance};
@@ -293,6 +325,12 @@ sub _do_enquire {
 	retry_reopen($self, \&_enquire_once, [ $self, $query, $opts ]);
 }
 
+# returns true if all docs have the THREADID value
+sub has_threadid ($) {
+	my ($self) = @_;
+	(xdb($self)->get_metadata('has_threadid') // '') eq '1';
+}
+
 sub _enquire_once { # retry_reopen callback
 	my ($self, $query, $opts) = @{$_[0]};
 	my $xdb = xdb($self);
@@ -308,41 +346,50 @@ sub _enquire_once { # retry_reopen callback
 	} else {
 		$enquire->set_sort_by_value_then_relevance(TS, $desc);
 	}
+
+	# `mairix -t / --threads' or JMAP collapseThreads
+	if ($opts->{thread} && has_threadid($self)) {
+		$enquire->set_collapse_key(THREADID);
+	}
+
 	my $offset = $opts->{offset} || 0;
 	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};
-	$qp->add_valuerangeprocessor($nvrp->new(YYYYMMDD, 'd:'));
-	$qp->add_valuerangeprocessor($nvrp->new(DT, 'dt:'));
+	my $cb = $qp->can('set_max_wildcard_expansion') //
+		$qp->can('set_max_expansion'); # Xapian 1.5.0+
+	$cb->($qp, 100);
+	$cb = $qp->can('add_valuerangeprocessor') //
+		$qp->can('add_rangeprocessor'); # Xapian 1.5.0+
+	$cb->($qp, $NVRP->new(YYYYMMDD, 'd:'));
+	$cb->($qp, $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:'));
+	$cb->($qp, $NVRP->new(BYTES, 'bytes:'));
+	$cb->($qp, $NVRP->new(TS, 'ts:'));
+	$cb->($qp, $NVRP->new(UID, 'uid:'));
 
 	while (my ($name, $prefix) = each %bool_pfx_external) {
 		$qp->add_boolean_prefix($name, $_) foreach split(/ /, $prefix);
@@ -370,13 +417,12 @@ EOF
 	while (my ($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;