X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchIdx.pm;h=6e2e614c5085c7e45fa33ad06375a9137af1ee31;hb=7ffa98cbbf5bff8225fdfedb0f2b7c2beb5d0a6f;hp=3237aadc7fb355b2ce3811d050f7fac511de76b7;hpb=b6829bbfd86f5d22a8ffb80fd7bfe59299fe6b55;p=public-inbox.git

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 3237aadc..6e2e614c 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -11,6 +11,7 @@ use strict;
 use v5.10.1;
 use parent qw(PublicInbox::Search PublicInbox::Lock Exporter);
 use PublicInbox::Eml;
+use PublicInbox::Search qw(xap_terms);
 use PublicInbox::InboxWritable;
 use PublicInbox::MID qw(mids_for_index mids);
 use PublicInbox::MsgIter;
@@ -23,17 +24,23 @@ use PublicInbox::Spawn qw(spawn nodatacow_dir);
 use PublicInbox::Git qw(git_unquote);
 use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
 use PublicInbox::Address;
+use Config;
 our @EXPORT_OK = qw(log2stack is_ancestor check_size prepare_stack
 	index_text term_generator add_val is_bad_blob);
 my $X = \%PublicInbox::Search::X;
 our ($DB_CREATE_OR_OPEN, $DB_OPEN);
 our $DB_NO_SYNC = 0;
-our $BATCH_BYTES = $ENV{XAPIAN_FLUSH_THRESHOLD} ? 0x7fffffff : 1_000_000;
+our $BATCH_BYTES = $ENV{XAPIAN_FLUSH_THRESHOLD} ? 0x7fffffff :
+	# assume a typical 64-bit system has 8x more RAM than a
+	# typical 32-bit system:
+	(($Config{ptrsize} >= 8 ? 8192 : 1024) * 1024);
+
 use constant DEBUG => !!$ENV{DEBUG};
 
 my $xapianlevels = qr/\A(?:full|medium)\z/;
 my $hex = '[a-f0-9]';
 my $OID = $hex .'{40,}';
+my @VMD_MAP = (kw => 'K', L => 'L');
 our $INDEXLEVELS = qr/\A(?:full|medium|basic)\z/;
 
 sub new {
@@ -87,7 +94,7 @@ sub need_xapian ($) { $_[0]->{indexlevel} =~ $xapianlevels }
 sub idx_release {
 	my ($self, $wake) = @_;
 	if (need_xapian($self)) {
-		my $xdb = delete $self->{xdb} or croak 'not acquired';
+		my $xdb = delete $self->{xdb} or croak '{xdb} not acquired';
 		$xdb->close;
 	}
 	$self->lock_release($wake) if $self->{creat};
@@ -96,7 +103,7 @@ sub idx_release {
 
 sub load_xapian_writable () {
 	return 1 if $X->{WritableDatabase};
-	PublicInbox::Search::load_xapian() or return;
+	PublicInbox::Search::load_xapian() or die "failed to load Xapian: $@\n";
 	my $xap = $PublicInbox::Search::Xap;
 	for (qw(Document TermGenerator WritableDatabase)) {
 		$X->{$_} = $xap.'::'.$_;
@@ -252,6 +259,7 @@ sub index_diff ($$$) {
 		} elsif (m!^diff --git "?[^/]+/.+ "?[^/]+/.+\z!) {
 			# wait until "---" and "+++" to capture filenames
 			$in_diff = 1;
+			push @xnq, $_;
 		# traditional diff:
 		} elsif (m/^diff -(.+) (\S+) (\S+)$/) {
 			my ($opt, $fa, $fb) = ($1, $2, $3);
@@ -428,17 +436,25 @@ sub eml2doc ($$$;$) {
 sub add_xapian ($$$$) {
 	my ($self, $eml, $smsg, $mids) = @_;
 	begin_txn_lazy($self);
+	my $merge_vmd = delete $smsg->{-merge_vmd};
 	my $doc = eml2doc($self, $eml, $smsg, $mids);
+	if (my $old = $merge_vmd ? _get_doc($self, $smsg->{num}) : undef) {
+		my @x = @VMD_MAP;
+		while (my ($field, $pfx) = splice(@x, 0, 2)) {
+			for my $term (xap_terms($pfx, $old)) {
+				$doc->add_boolean_term($pfx.$term);
+			}
+		}
+	}
 	$self->{xdb}->replace_document($smsg->{num}, $doc);
 }
 
 sub _msgmap_init ($) {
 	my ($self) = @_;
 	die "BUG: _msgmap_init is only for v1\n" if $self->{ibx}->version != 1;
-	$self->{mm} //= eval {
+	$self->{mm} //= do {
 		require PublicInbox::Msgmap;
-		my $rw = $self->{ibx}->{-no_fsync} ? 2 : 1;
-		PublicInbox::Msgmap->new($self->{ibx}->{inboxdir}, $rw);
+		PublicInbox::Msgmap->new_file($self->{ibx}, 1);
 	};
 }
 
@@ -502,6 +518,12 @@ sub add_eidx_info {
 	$self->{xdb}->replace_document($docid, $doc);
 }
 
+sub get_terms {
+	my ($self, $pfx, $docid) = @_;
+	begin_txn_lazy($self);
+	xap_terms($pfx, $self->{xdb}, $docid);
+}
+
 sub remove_eidx_info {
 	my ($self, $docid, $eidx_key, $eml) = @_;
 	begin_txn_lazy($self);
@@ -531,8 +553,6 @@ sub remove_eidx_info {
 	$self->{xdb}->replace_document($docid, $doc);
 }
 
-my @VMD_MAP = (kw => 'K', label => 'L');
-
 sub set_vmd {
 	my ($self, $docid, $vmd) = @_;
 	begin_txn_lazy($self);
@@ -559,16 +579,39 @@ sub set_vmd {
 	$self->{xdb}->replace_document($docid, $doc);
 }
 
+sub apply_vmd_mod ($$) {
+	my ($doc, $vmd_mod) = @_;
+	my $updated = 0;
+	my @x = @VMD_MAP;
+	while (my ($field, $pfx) = splice(@x, 0, 2)) {
+		# field: "L" or "kw"
+		for my $val (@{$vmd_mod->{"-$field"} // []}) {
+			eval {
+				$doc->remove_term($pfx . $val);
+				++$updated;
+			};
+		}
+		for my $val (@{$vmd_mod->{"+$field"} // []}) {
+			$doc->add_boolean_term($pfx . $val);
+			++$updated;
+		}
+	}
+	$updated;
+}
+
 sub add_vmd {
 	my ($self, $docid, $vmd) = @_;
 	begin_txn_lazy($self);
 	my $doc = _get_doc($self, $docid) or return;
 	my @x = @VMD_MAP;
+	my $updated = 0;
 	while (my ($field, $pfx) = splice(@x, 0, 2)) {
 		my $add = $vmd->{$field} // next;
 		$doc->add_boolean_term($pfx . $_) for @$add;
+		$updated += scalar(@$add);
 	}
-	$self->{xdb}->replace_document($docid, $doc);
+	$updated += apply_vmd_mod($doc, $vmd);
+	$self->{xdb}->replace_document($docid, $doc) if $updated;
 }
 
 sub remove_vmd {
@@ -589,16 +632,35 @@ sub remove_vmd {
 	$self->{xdb}->replace_document($docid, $doc) if $replace;
 }
 
+sub update_vmd {
+	my ($self, $docid, $vmd_mod) = @_;
+	begin_txn_lazy($self);
+	my $doc = _get_doc($self, $docid) or return;
+	my $updated = apply_vmd_mod($doc, $vmd_mod);
+	$self->{xdb}->replace_document($docid, $doc) if $updated;
+	$updated;
+}
+
 sub xdb_remove {
 	my ($self, @docids) = @_;
-	$self->begin_txn_lazy;
-	my $xdb = $self->{xdb} or return;
+	begin_txn_lazy($self);
+	my $xdb = $self->{xdb} // die 'BUG: missing {xdb}';
 	for my $docid (@docids) {
 		eval { $xdb->delete_document($docid) };
 		warn "E: #$docid not in in Xapian? $@\n" if $@;
 	}
 }
 
+sub xdb_remove_quiet {
+	my ($self, $docid) = @_;
+	begin_txn_lazy($self);
+	my $xdb = $self->{xdb} // die 'BUG: missing {xdb}';
+	eval { $xdb->delete_document($docid) };
+	++$self->{-quiet_rm} unless $@;
+}
+
+sub nr_quiet_rm { delete($_[0]->{-quiet_rm}) // 0 }
+
 sub index_git_blob_id {
 	my ($doc, $pfx, $objid) = @_;
 
@@ -704,7 +766,8 @@ sub index_sync {
 	my ($self, $opt) = @_;
 	delete $self->{lock_path} if $opt->{-skip_lock};
 	$self->with_umask(\&_index_sync, $self, $opt);
-	if ($opt->{reindex} && !$opt->{quit}) {
+	if ($opt->{reindex} && !$opt->{quit} &&
+			!grep(defined, @$opt{qw(since until)})) {
 		my %again = %$opt;
 		delete @again{qw(rethread reindex)};
 		index_sync($self, \%again);
@@ -729,18 +792,19 @@ sub v1_checkpoint ($$;$) {
 	# $newest may be undef
 	my $newest = $stk ? $stk->{latest_cmt} : ${$sync->{latest_cmt}};
 	if (defined($newest)) {
-		my $cur = $self->{mm}->last_commit || '';
-		if (need_update($self, $cur, $newest)) {
+		my $cur = $self->{mm}->last_commit;
+		if (need_update($self, $sync, $cur, $newest)) {
 			$self->{mm}->last_commit($newest);
 		}
 	}
 	${$sync->{max}} = $self->{batch_bytes};
 
 	$self->{mm}->{dbh}->commit;
-	my $xdb = need_xapian($self) ? $self->{xdb} : undef;
+	eval { $self->{mm}->{dbh}->do('PRAGMA optimize') };
+	my $xdb = $self->{xdb};
 	if ($newest && $xdb) {
 		my $cur = $xdb->get_metadata('last_commit');
-		if (need_update($self, $cur, $newest)) {
+		if (need_update($self, $sync, $cur, $newest)) {
 			$xdb->set_metadata('last_commit', $newest);
 		}
 	}
@@ -824,9 +888,14 @@ sub log2stack ($$$) {
 
 	# Count the new files so they can be added newest to oldest
 	# and still have numbers increasing from oldest to newest
-	my $fh = $git->popen(qw(log --raw -r --pretty=tformat:%at-%ct-%H
-				--no-notes --no-color --no-renames --no-abbrev),
-				$range);
+	my @cmd = qw(log --raw -r --pretty=tformat:%at-%ct-%H
+			--no-notes --no-color --no-renames --no-abbrev);
+	for my $k (qw(since until)) {
+		my $v = $sync->{-opt}->{$k} // next;
+		next if !$sync->{-opt}->{reindex};
+		push @cmd, "--$k=$v";
+	}
+	my $fh = $git->popen(@cmd, $range);
 	my ($at, $ct, $stk, $cmt);
 	while (<$fh>) {
 		return if $sync->{quit};
@@ -882,10 +951,17 @@ sub is_ancestor ($$$) {
 	$? == 0;
 }
 
-sub need_update ($$$) {
-	my ($self, $cur, $new) = @_;
+sub need_update ($$$$) {
+	my ($self, $sync, $cur, $new) = @_;
 	my $git = $self->{ibx}->git;
-	return 1 if $cur && !is_ancestor($git, $cur, $new);
+	$cur //= ''; # XS Search::Xapian ->get_metadata doesn't give undef
+
+	# don't rewind if --{since,until,before,after} are in use
+	return if $cur ne '' &&
+		grep(defined, @{$sync->{-opt}}{qw(since until)}) &&
+		is_ancestor($git, $new, $cur);
+
+	return 1 if $cur ne '' && !is_ancestor($git, $cur, $new);
 	my $range = $cur eq '' ? $new : "$cur..$new";
 	chomp(my $n = $git->qx(qw(rev-list --count), $range));
 	($n eq '' || $n > 0);
@@ -1039,25 +1115,4 @@ sub eidx_shard_new {
 	$self;
 }
 
-# ensure there's no stale Xapian docs by treating $over as canonical
-sub over_check {
-	my ($self, $over) = @_;
-	begin_txn_lazy($self);
-	my $sth = $over->dbh->prepare(<<'');
-SELECT COUNT(*) FROM over WHERE num = ?
-
-	my $xdb = $self->{xdb};
-	my $cur = $xdb->postlist_begin('');
-	my $end = $xdb->postlist_end('');
-	my $xdir = $self->xdir;
-	for (; $cur != $end; $cur++) {
-		my $docid = $cur->get_docid;
-		$sth->execute($docid);
-		my $x = $sth->fetchrow_array;
-		next if $x > 0;
-		warn "I: removing $xdir #$docid, not in `over'\n";
-		$xdb->delete_document($docid);
-	}
-}
-
 1;