From ca811ace8629e0e87fe75a681a4667600fcac2f7 Mon Sep 17 00:00:00 2001 From: Ere Maijala Date: Mon, 19 Feb 2018 16:54:39 +0200 Subject: [PATCH] Bug 20248 - Improve Elasticsearch mappings UI and rebuild_elastic_search.pl. Improvements: 1) Mappings UI now has button that allows one to reset the mappings. 2) Mappings UI displays the items in alphabetical order. 3) Indexing script drops and recreates the index right away, which helps prevent ES from autocreating a bad index if someone does something while the first batch of records is being processed. 4) Indexing script has nicer output. To test: 1) Change mappings.yaml file 2) Reset mappings in UI in mappings.pl 3) Verify the mappings have been changed in UI 4) The field order is alphabetical 5) Rebuild script has clean output 6) Run test t/db_dependent/Koha_Elasticsearch_Indexer.t Signed-off-by: Nicolas Legrand Signed-off-by: Alex Arnaud --- Koha/SearchEngine/Elasticsearch/Indexer.pm | 25 +++++++++++++++- admin/searchengine/elasticsearch/mappings.pl | 17 ++++++----- .../admin/searchengine/elasticsearch/mappings.tt | 25 ++++++++++++++-- misc/search_tools/rebuild_elastic_search.pl | 20 ++++++++----- t/db_dependent/Koha_Elasticsearch_Indexer.t | 34 ++++++++++++++++++++-- 5 files changed, 100 insertions(+), 21 deletions(-) diff --git a/Koha/SearchEngine/Elasticsearch/Indexer.pm b/Koha/SearchEngine/Elasticsearch/Indexer.pm index e5babee..ad0e4ca 100644 --- a/Koha/SearchEngine/Elasticsearch/Indexer.pm +++ b/Koha/SearchEngine/Elasticsearch/Indexer.pm @@ -139,6 +139,28 @@ sub delete_index_background { $self->delete_index(@_); } +=head2 $indexer->create_index(); + +Create an index on the Elasticsearch server. + +=cut + +sub create_index { + my ($self) = @_; + + if (!$self->store) { + my $params = $self->get_elasticsearch_params(); + $self->store( + Catmandu::Store::ElasticSearch->new( + %$params, + index_settings => $self->get_elasticsearch_settings(), + index_mappings => $self->get_elasticsearch_mappings(), + ) + ); + } + $self->store->bag->commit; +} + =head2 $indexer->drop_index(); Drops the index from the elasticsearch server. Calling C @@ -161,8 +183,9 @@ sub drop_index { ) ); } - $self->store->drop(); + my $store = $self->store; $self->store(undef); + $store->drop(); } sub _sanitise_records { diff --git a/admin/searchengine/elasticsearch/mappings.pl b/admin/searchengine/elasticsearch/mappings.pl index 7d63002..12219d3 100755 --- a/admin/searchengine/elasticsearch/mappings.pl +++ b/admin/searchengine/elasticsearch/mappings.pl @@ -97,15 +97,17 @@ if ( $op eq 'edit' ) { $schema->storage->txn_commit; } } -elsif( $op eq 'reset' ) { - # TODO Move this feature to the interface - my $sure = $input->param('i_know_what_i_am_doing'); - if ( $sure ) { - Koha::SearchMarcMaps->search->delete; - Koha::SearchEngine::Elasticsearch->reset_elasticsearch_mappings; - } +elsif( $op eq 'reset' || $op eq 'reset_confirmed' ) { + Koha::SearchMarcMaps->delete; + Koha::SearchFields->delete; + Koha::SearchEngine::Elasticsearch->reset_elasticsearch_mappings; + push @messages, { type => 'message', code => 'success_on_reset' }; +} +elsif( $op eq 'reset_confirm' ) { + $template->param( reset_confirm => 1 ); } + my @indexes; for my $index_name (qw| biblios authorities |) { @@ -114,6 +116,7 @@ for my $index_name (qw| biblios authorities |) { { join => { search_marc_to_fields => 'search_marc_map' }, '+select' => [ 'search_marc_to_fields.facet', 'search_marc_to_fields.suggestible', 'search_marc_to_fields.sort', 'search_marc_map.marc_field' ], '+as' => [ 'facet', 'suggestible', 'sort', 'marc_field' ], + order_by => { -asc => [qw/name marc_field/] } } ); diff --git a/koha-tmpl/intranet-tmpl/prog/en/modules/admin/searchengine/elasticsearch/mappings.tt b/koha-tmpl/intranet-tmpl/prog/en/modules/admin/searchengine/elasticsearch/mappings.tt index 24327c5..6765c4e 100644 --- a/koha-tmpl/intranet-tmpl/prog/en/modules/admin/searchengine/elasticsearch/mappings.tt +++ b/koha-tmpl/intranet-tmpl/prog/en/modules/admin/searchengine/elasticsearch/mappings.tt @@ -79,7 +79,9 @@ a.add, a.delete { An error occurred when deleting the existing mappings. Nothing has been changed! (search field [% m.values.field_name %] with mapping [% m.values.marc_field %].) [% CASE 'success_on_update' %] - Mapping updated successfully. + Mappings updated successfully. + [% CASE 'success_on_reset' %] + Mappings have been reset successfully. [% CASE %] [% m.code %] [% END %] @@ -88,7 +90,7 @@ a.add, a.delete {

Search engine configuration

- Warning: Any modification in these configurations will need a total reindexation to be fully taken into account ! + Warning: Any modification of this configuration requires a complete index rebuild to be fully taken into account!
[% IF errors %]
@@ -107,6 +109,19 @@ a.add, a.delete {
[% END %] + [% IF reset_confirm %] +
+

The current mappings you seen on the screen will be erased and replaced by the mappings in the mappings.yaml file.

+
+ + +
+
+
+ +
+
+ [% ELSE %]
@@ -286,8 +301,12 @@ a.add, a.delete {
[% END %] -

+

+ + Reset Mappings +

+ [% END %] diff --git a/misc/search_tools/rebuild_elastic_search.pl b/misc/search_tools/rebuild_elastic_search.pl index 6faa32c..63065ca 100755 --- a/misc/search_tools/rebuild_elastic_search.pl +++ b/misc/search_tools/rebuild_elastic_search.pl @@ -92,14 +92,14 @@ use MARC::Record; use Modern::Perl; use Pod::Usage; -use Data::Dumper; # TODO remove - my $verbose = 0; my $commit = 5000; my ($delete, $help, $man); my ($index_biblios, $index_authorities); my (@biblionumbers); +$|=1; # flushes output + GetOptions( 'c|commit=i' => \$commit, 'd|delete' => \$delete, @@ -161,10 +161,8 @@ sub do_reindex { my $indexer = Koha::SearchEngine::Elasticsearch::Indexer->new( { index => $index_name } ); if ($delete) { - - # We know it's safe to not recreate the indexer because update_index - # hasn't been called yet. $indexer->drop_index(); + $indexer->create_index(); } my $count = 0; @@ -173,23 +171,29 @@ sub do_reindex { while ( my $record = $next->() ) { my $id = $record->id; my $record = $record->record; - _log( 1, "$id\n" ); $count++; + if ( $verbose == 1 ) { + _log( 1, "$count records processed\n" ) if ( $count % 1000 == 0); + } else { + _log( 2, "$id\n" ); + } push @id_buffer, $id; push @commit_buffer, $record; if ( !( --$commit_count ) ) { - _log( 2, "Committing...\n" ); + _log( 1, "Committing $commit records..." ); $indexer->update_index( \@id_buffer, \@commit_buffer ); $commit_count = $commit; @id_buffer = (); @commit_buffer = (); + _log( 1, " done\n" ); } } # There are probably uncommitted records + _log( 1, "Committing final records...\n" ); $indexer->update_index( \@id_buffer, \@commit_buffer ); - _log( 1, "$count records indexed.\n" ); + _log( 1, "Total $count records indexed\n" ); } # Checks some basic stuff to ensure that it's sane before we start. diff --git a/t/db_dependent/Koha_Elasticsearch_Indexer.t b/t/db_dependent/Koha_Elasticsearch_Indexer.t index 9a525bf..bded587 100644 --- a/t/db_dependent/Koha_Elasticsearch_Indexer.t +++ b/t/db_dependent/Koha_Elasticsearch_Indexer.t @@ -17,7 +17,7 @@ use Modern::Perl; -use Test::More tests => 6; +use Test::More tests => 7; use Test::MockModule; use t::lib::Mocks; @@ -52,12 +52,42 @@ SKIP: { eval { $indexer->get_elasticsearch_params; }; - skip 'ElasticSeatch configuration not available', 1 + skip 'Elasticsearch configuration not available', 1 if $@; ok( $indexer->update_index(undef,$records), 'Update Index' ); } +subtest 'create_index() tests' => sub { + + plan tests => 3; + + my $se = Test::MockModule->new( 'Koha::SearchEngine::Elasticsearch' ); + $se->mock( 'get_elasticsearch_params', sub { + my ($self, $sub ) = @_; + + my $method = $se->original( 'get_elasticsearch_params' ); + my $params = $method->( $self ); + $params->{index_name} .= '__test'; + return $params; + }); + + my $indexer; + ok( + $indexer = Koha::SearchEngine::Elasticsearch::Indexer->new({ 'index' => 'biblios' }), + 'Creating a new indexer object' + ); + ok( + $indexer->create_index(), + 'Creating an index' + ); + $indexer->drop_index(); + ok( + $indexer->drop_index(), + 'Dropping the index' + ); +}; + subtest '_convert_marc_to_json() tests' => sub { plan tests => 2; -- 2.7.4