From: Eric W. Biederman <ebiederm@xmission.com>
Date: Wed, 18 Jul 2018 16:53:25 +0000 (-0500)
Subject: SearchIdx: Allow the amount of indexing be configured
X-Git-Tag: v1.2.0~482
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=cd196679300c54f840e7569dba97005c449f99ab;p=thirdparty%2Fpublic-inbox.git

SearchIdx: Allow the amount of indexing be configured

This adds a new inbox configuration option 'indexlevel' that can take
the values 'full', 'medium', and 'basic'.

When set to 'full' everything is indexed including the positions
of all terms.

When set to 'medium' everything except the positions of terms is
indexed.

When set to 'basic' terms and positions are not indexed.  Just the
Overview database for NNTP is created.  Which is still quite good and
allows searching for messages by Message-ID.  But there are no indexes to support
searching inside the email messages themselves.

Update the reindex tests to exercise the full medium and basic code paths

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---

diff --git a/lib/PublicInbox/Config.pm b/lib/PublicInbox/Config.pm
index 289c36a6c..78586560c 100644
--- a/lib/PublicInbox/Config.pm
+++ b/lib/PublicInbox/Config.pm
@@ -158,7 +158,7 @@ sub _fill {
 
 	foreach my $k (qw(mainrepo filter url newsgroup
 			infourl watch watchheader httpbackendmax
-			replyto feedmax nntpserver)) {
+			replyto feedmax nntpserver indexlevel)) {
 		my $v = $self->{"$pfx.$k"};
 		$rv->{$k} = $v if defined $v;
 	}
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 8978914ab..04e853069 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -47,6 +47,7 @@ sub git_unquote ($) {
 
 sub new {
 	my ($class, $ibx, $creat, $part) = @_;
+	my $levels = qr/\A(?:full|medium|basic)\z/;
 	my $mainrepo = $ibx; # for "public-inbox-index" w/o entry in config
 	my $git_dir = $mainrepo;
 	my ($altid, $git);
@@ -62,6 +63,13 @@ sub new {
 				PublicInbox::AltId->new($ibx, $_);
 			} @$altid ];
 		}
+		if ($ibx->{indexlevel}) {
+			if ($ibx->{indexlevel} =~ $levels) {
+				$indexlevel = $ibx->{indexlevel};
+			} else {
+				die("Invalid indexlevel $ibx->{indexlevel}\n");
+			}
+		}
 	} else { # v1
 		$ibx = { mainrepo => $git_dir, version => 1 };
 	}
diff --git a/t/v1reindex.t b/t/v1reindex.t
index 0df36d3fe..ff32750fc 100644
--- a/t/v1reindex.t
+++ b/t/v1reindex.t
@@ -20,6 +20,7 @@ my $ibx_config = {
 	mainrepo => $mainrepo,
 	name => 'test-v1reindex',
 	-primary_address => 'test@example.com',
+	indexlevel => 'full',
 };
 my $ibx = PublicInbox::Inbox->new($ibx_config);
 my $mime = PublicInbox::MIME->create(
@@ -74,15 +75,32 @@ is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
 
 ok(unlink "$mainrepo/public-inbox/msgmap.sqlite3", 'remove msgmap');
 remove_tree($xap);
+ok(!-d $xap, 'Xapian directories removed again');
+
 $rw = PublicInbox::SearchIdx->new($ibx, 1);
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	eval { $rw->index_sync({reindex => 1}) };
+	is($@, '', 'no error from reindexing without msgmap');
+	is(scalar(@warn), 0, 'no warnings from reindexing');
+	$im->done;
+	ok(-d $xap, 'Xapian directories recreated');
+	delete $ibx->{mm};
+	is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
+}
 
+ok(unlink "$mainrepo/public-inbox/msgmap.sqlite3", 'remove msgmap');
+remove_tree($xap);
 ok(!-d $xap, 'Xapian directories removed again');
+
+$rw = PublicInbox::SearchIdx->new($ibx, 1);
 {
 	my @warn;
 	local $SIG{__WARN__} = sub { push @warn, @_ };
 	eval { $rw->index_sync({reindex => 1}) };
 	is($@, '', 'no error from reindexing without msgmap');
-	is(scalar(@warn), 0, 'no warnings from reindexing');
+	is_deeply(\@warn, [], 'no warnings');
 	$im->done;
 	ok(-d $xap, 'Xapian directories recreated');
 	delete $ibx->{mm};
@@ -91,9 +109,31 @@ ok(!-d $xap, 'Xapian directories removed again');
 
 ok(unlink "$mainrepo/public-inbox/msgmap.sqlite3", 'remove msgmap');
 remove_tree($xap);
+ok(!-d $xap, 'Xapian directories removed again');
+
+$ibx_config->{index_level} = 'medium';
+$ibx = PublicInbox::Inbox->new($ibx_config);
 $rw = PublicInbox::SearchIdx->new($ibx, 1);
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	eval { $rw->index_sync({reindex => 1}) };
+	is($@, '', 'no error from reindexing without msgmap');
+	is_deeply(\@warn, [], 'no warnings');
+	$im->done;
+	ok(-d $xap, 'Xapian directories recreated');
+	delete $ibx->{mm};
+	is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
+}
 
+
+ok(unlink "$mainrepo/public-inbox/msgmap.sqlite3", 'remove msgmap');
+remove_tree($xap);
 ok(!-d $xap, 'Xapian directories removed again');
+
+$ibx_config->{index_level} = 'basic';
+$ibx = PublicInbox::Inbox->new($ibx_config);
+$rw = PublicInbox::SearchIdx->new($ibx, 1);
 {
 	my @warn;
 	local $SIG{__WARN__} = sub { push @warn, @_ };
@@ -106,4 +146,5 @@ ok(!-d $xap, 'Xapian directories removed again');
 	is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
 }
 
+
 done_testing();
diff --git a/t/v2reindex.t b/t/v2reindex.t
index 8af30991f..20903967b 100644
--- a/t/v2reindex.t
+++ b/t/v2reindex.t
@@ -19,6 +19,7 @@ my $ibx_config = {
 	name => 'test-v2writable',
 	version => 2,
 	-primary_address => 'test@example.com',
+	indexlevel => 'full',
 };
 my $ibx = PublicInbox::Inbox->new($ibx_config);
 my $mime = PublicInbox::MIME->create(
@@ -95,4 +96,43 @@ ok(!-d $xap, 'Xapian directories removed again');
 	is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
 }
 
+ok(unlink "$mainrepo/msgmap.sqlite3", 'remove msgmap');
+remove_tree($xap);
+ok(!-d $xap, 'Xapian directories removed again');
+
+$ibx_config->{index_level} = 'medium';
+$ibx = PublicInbox::Inbox->new($ibx_config);
+$im = PublicInbox::V2Writable->new($ibx);
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	eval { $im->index_sync({reindex => 1}) };
+	is($@, '', 'no error from reindexing without msgmap');
+	is_deeply(\@warn, [], 'no warnings');
+	$im->done;
+	ok(-d $xap, 'Xapian directories recreated');
+	delete $ibx->{mm};
+	is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
+}
+
+
+ok(unlink "$mainrepo/msgmap.sqlite3", 'remove msgmap');
+remove_tree($xap);
+ok(!-d $xap, 'Xapian directories removed again');
+
+$ibx_config->{index_level} = 'basic';
+$ibx = PublicInbox::Inbox->new($ibx_config);
+$im = PublicInbox::V2Writable->new($ibx);
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	eval { $im->index_sync({reindex => 1}) };
+	is($@, '', 'no error from reindexing without msgmap');
+	is_deeply(\@warn, [], 'no warnings');
+	$im->done;
+	ok(-d $xap, 'Xapian directories recreated');
+	delete $ibx->{mm};
+	is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
+}
+
 done_testing();