Koha/C4/Linker/Default.pm
Frank Hansen 8c7230b802
Bug 30280: Add support for subject headings from different thesaurus when using Elasticsearch
This patch allows subject headings from different thesaurus to co-exist in Koha.

Test plan:
1. Enable Elasticsearch as the search engine (SearchEngine system preference =
Elasticsearch) and reindex (koha-elasticsearch --rebuild -d -b -a kohadev).
2. Load sample authority records attached to the bug (in this case the
authorities.mrc file was saved in the koha directory - adjust file location as
appropriate):
   misc/migration_tools/bulkmarcimport.pl -v -a -file authorities.mrc -insert
-c=MARC21
3. Load the sample bibliographic record attached to the bug:
   misc/migration_tools/bulkmarcimport.pl -v -b -file biblios.mrc -insert
-c=MARC21
4. Search for ISBN 0704328623 and verify that the subject terms are not linked
to any authority records (if you hover over the link terms, all links should
look like ../cgi-bin/koha/catalogue/search.pl?q=su:"subjectterm" - none should
have any ?q=an:XXX (where XXX = authority record ids) in the link).
5. Apply the patches.
6. Reset the Elasticsearch mappings (Administration > Catalog > Search engine
configuration (Elasticsearch)).
7. Reindex: koha-elasticsearch --rebuild -d -b -a kohadev
8. Link bibliographic records to authority records:
misc/link_bibs_to_authorities.pl -v -l
9. Repeat the search in step 4 (or refresh the record details page) and verify
that the first three Feminism headings[1] are linked to an authority record
(should have ?q=an:XXX (where XXX = different authority record IDs for the
various feminism authority records linked to a specific thesaurus)).
10. Reindex: koha-elasticsearch --rebuild -d -b -a kohadev

[1] Links for subject terms for step 9 in order are (the authority ids may be
different depending on how ou are testing):

    Subject(s:) Feminism | feminism | Feminism | Feminism | Idéhistoria |
Litteratur

    http://127.0.0.1:8081/cgi-bin/koha/catalogue/search.pl?q=an:1709
    http://127.0.0.1:8081/cgi-bin/koha/catalogue/search.pl?q=an:1710
    http://127.0.0.1:8081/cgi-bin/koha/catalogue/search.pl?q=an:1708
    http://127.0.0.1:8081/cgi-bin/koha/catalogue/search.pl?q=su:"Feminism"
    http://127.0.0.1:8081/cgi-bin/koha/catalogue/search.pl?q=su:"Idéhistoria"
    http://127.0.0.1:8081/cgi-bin/koha/catalogue/search.pl?q=su:"Litteratur"

    MARC info:

    650 #7 - SUBJECT ADDED ENTRY--TOPICAL TERM
      a Topical term or geographic name entry element Feminism
      0 Authority record control number or standard number
https://id.kb.se/term/sao/Feminism
      2 Source of heading or term sao
    650 #7 - SUBJECT ADDED ENTRY--TOPICAL TERM
      a Topical term or geographic name entry element feminism
      2 Source of heading or term bnb
    650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM
      a Topical term or geographic name entry element Feminism
    650 #4 - SUBJECT ADDED ENTRY--TOPICAL TERM
      a Topical term or geographic name entry element Feminism
    650 #4 - SUBJECT ADDED ENTRY--TOPICAL TERM
      a Topical term or geographic name entry element Idéhistoria
    650 #4 - SUBJECT ADDED ENTRY--TOPICAL TERM
      a Topical term or geographic name entry element Litteratur

   Note: The fourth Feminism term has second indicator 4 which means "Source
not specified". So this term is only a local term and does not belong to any
specific thesaurus and thus not linked. To specify a source of a term, the
second indicator must be set as 7. The source of heading is then specified in
subfield 2.

Sponsored-by: Lund University Library, Sweden

Signed-off-by: David Nind <david@davidnind.com>

Signed-off-by: Katrin Fischer <katrin.fischer.83@web.de>
Signed-off-by: Tomas Cohen Arazi <tomascohen@theke.io>
2022-10-03 10:00:04 -03:00

115 lines
3.9 KiB
Perl

package C4::Linker::Default;
# Copyright 2011 C & P Bibliography Services
#
# This file is part of Koha.
#
# Koha is free software; you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3 of the License, or
# (at your option) any later version.
#
# Koha is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with Koha; if not, see <http://www.gnu.org/licenses>.
use strict;
use warnings;
use MARC::Field;
use C4::Heading;
use base qw(C4::Linker);
sub get_link {
my $self = shift;
my $heading = shift;
my $behavior = shift || 'default';
my $search_form = $heading->search_form();
my $auth_type = $heading->auth_type();
my $thesaurus = $heading->{thesaurus} || 'notdefined';
my $authid;
my $fuzzy = 0;
my $match_count;
if ( $self->{'cache'}->{$search_form.$auth_type.$thesaurus}->{'cached'} ) {
$authid = $self->{'cache'}->{$search_form.$auth_type.$thesaurus}->{'authid'};
$fuzzy = $self->{'cache'}->{$search_form.$auth_type.$thesaurus}->{'fuzzy'};
$match_count = $self->{'cache'}->{$search_form.$auth_type.$thesaurus}->{'match_count'};
}
else {
# look for matching authorities
my $authorities = $heading->authorities(1); # $skipmetadata = true
$match_count = scalar @$authorities;
if ( $behavior eq 'default' && $#{$authorities} == 0 ) {
$authid = $authorities->[0]->{'authid'};
}
elsif ( $behavior eq 'first' && $#{$authorities} >= 0 ) {
$authid = $authorities->[0]->{'authid'};
$fuzzy = $#{$authorities} > 0;
}
elsif ( $behavior eq 'last' && $#{$authorities} >= 0 ) {
$authid = $authorities->[ $#{$authorities} ]->{'authid'};
$fuzzy = $#{$authorities} > 0;
}
if ( !defined $authid && $self->{'broader_headings'} ) {
my $field = $heading->field();
my @subfields = grep { $_->[0] ne '9' } $field->subfields();
if ( scalar @subfields > 1 ) {
pop @subfields;
$field =
MARC::Field->new(
$field->tag,
$field->indicator(1),
$field->indicator(2),
map { $_->[0] => $_->[1] } @subfields
);
( $authid, $fuzzy ) =
$self->get_link( C4::Heading->new_from_field($field),
$behavior );
}
}
$self->{'cache'}->{$search_form.$auth_type.$thesaurus}->{'cached'} = 1;
$self->{'cache'}->{$search_form.$auth_type.$thesaurus}->{'authid'} = $authid;
$self->{'cache'}->{$search_form.$auth_type.$thesaurus}->{'fuzzy'} = $fuzzy;
$self->{'cache'}->{$search_form.$auth_type.$thesaurus}->{'match_count'} = $match_count;
}
return $self->SUPER::_handle_auth_limit($authid), $fuzzy, $match_count;
}
sub update_cache {
my $self = shift;
my $heading = shift;
my $authid = shift;
my $search_form = $heading->search_form();
my $auth_type = $heading->auth_type();
my $thesaurus = $heading->{thesaurus} || 'notdefined';
my $fuzzy = 0;
$self->{'cache'}->{$search_form.$auth_type.$thesaurus}->{'cached'} = 1;
$self->{'cache'}->{$search_form.$auth_type.$thesaurus}->{'authid'} = $authid;
$self->{'cache'}->{$search_form.$auth_type.$thesaurus}->{'fuzzy'} = $fuzzy;
}
sub flip_heading {
my $self = shift;
my $heading = shift;
# TODO: implement
}
1;
__END__
=head1 NAME
C4::Linker::Default - match only if there is a single matching auth
=cut