Attachment 134457 Details for Bug 15187 – Bug 15187: Index 880 in Zebra the same as Elasticsearch

[patch] Bug 15187: Index 880 in Zebra the same as Elasticsearch

Bug-15187-Index-880-in-Zebra-the-same-as-Elasticse.patch (text/plain), 4.53 KB, created by David Cook on 2022-05-02 07:40:37 UTC

(hide)

Description:

Filename:

MIME Type:

Creator: David Cook

Created: 2022-05-02 07:40:37 UTC

Size: 4.53 KB

patch

obsolete

>From b972a35515cbdc9c89e11d0a78f1f4cdeb53c33c Mon Sep 17 00:00:00 2001
>From: David Cook <dcook@prosentient.com.au>
>Date: Mon, 2 May 2022 07:34:34 +0000
>Subject: [PATCH] Bug 15187: Index 880 in Zebra the same as Elasticsearch
>MIME-Version: 1.0
>Content-Type: text/plain; charset=UTF-8
>Content-Transfer-Encoding: 8bit
>
>This patch modifies the MARC21 export to Zebra, so that 880 fields
>are rewritten as their linked fields, in the same way that we
>already do with Elasticsearch, so that the alternate graphic
>representation of fields are indexed accordingly. (ie 880 $6245-01
>Chinese titles will be indexed into the title index using the 245 rules)
>
>Test plan:
>0. Apply patch
>1. Turn on ICU indexing
>1b. vi /etc/koha/zebradb/etc/default.idx
>1c. Replace charmap word-phrase-utf.chr with icuchain words-icu.xml
>1d. Replace charmap word-phrase-utf.chr with icuchain phrases-icu.xml
>1e. Restart Zebra server
>1f. Re-index Zebra
>2. Add record with a 880 $6 245-01 $a æç§æ¸ä¿¡ field.
>3. Search for this record using a title index with the Chinese title
>4. Note that the record is correctly retrieved
>
>(Note: This test probably works better using author or series as they
> present as links on the detail page which makes the fix more obviously
> useful.)
>---
> Koha/Filter/MARC/Index880InZebra.pm   | 88 +++++++++++++++++++++++++++
> misc/migration_tools/rebuild_zebra.pl |  1 +
> 2 files changed, 89 insertions(+)
> create mode 100644 Koha/Filter/MARC/Index880InZebra.pm
>
>diff --git a/Koha/Filter/MARC/Index880InZebra.pm b/Koha/Filter/MARC/Index880InZebra.pm
>new file mode 100644
>index 0000000000..0cff55c117
>--- /dev/null
>+++ b/Koha/Filter/MARC/Index880InZebra.pm
>@@ -0,0 +1,88 @@
>+package Koha::Filter::MARC::Index880InZebra;
>+
>+# 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>.
>+
>+=head1 NAME
>+
>+Koha::Filter::MARC::Index880InZebra - replace 880 with its linked field number
>+so that the alternate graphic representation gets indexed appropriately
>+(see Koha::SearchEngine::Elasticsearch for the ES version)
>+
>+=head1 SYNOPSIS
>+
>+my $processor = Koha::RecordProcessor->new({ filters => ('Index880InZebra') });
>+
>+=head1 DESCRIPTION
>+
>+Filter to rewrite 880 to linked field
>+
>+=cut
>+
>+use Modern::Perl;
>+
>+use C4::Context;
>+
>+use base qw(Koha::RecordProcessor::Base);
>+our $NAME = 'Index880InZebra';
>+
>+our $marcflavour = lc C4::Context->preference('marcflavour');
>+
>+=head2 filter
>+
>+    my $newrecord = $filter->filter($record);
>+    my $newrecords = $filter->filter(\@records);
>+
>+=cut
>+
>+sub filter {
>+    my $self = shift;
>+    my $record = shift;
>+    my $newrecord;
>+
>+    return unless defined $record;
>+
>+    if (ref $record eq 'ARRAY') {
>+        my @recarray;
>+        foreach my $thisrec (@$record) {
>+            push @recarray, _processrecord($thisrec);
>+        }
>+        $newrecord = \@recarray;
>+    } elsif (ref $record eq 'MARC::Record') {
>+        $newrecord = _processrecord($record);
>+    }
>+
>+    return $newrecord;
>+}
>+
>+sub _processrecord {
>+
>+    my $record = shift;
>+    if ($marcflavour && $marcflavour eq 'marc21'){
>+        my @fields = $record->field('880');
>+        foreach my $field (@fields){
>+            my $sub6 = $field->subfield('6');
>+            if ($sub6 =~ /^(...)-\d+/) {
>+                my $tag = $1;
>+                if ($tag){
>+                    $field->set_tag($tag);
>+                }
>+            }
>+        }
>+    }
>+    return $record;
>+}
>+
>+1;
>diff --git a/misc/migration_tools/rebuild_zebra.pl b/misc/migration_tools/rebuild_zebra.pl
>index 718c30533d..2263bfd0f9 100755
>--- a/misc/migration_tools/rebuild_zebra.pl
>+++ b/misc/migration_tools/rebuild_zebra.pl
>@@ -661,6 +661,7 @@ sub get_corrected_marc_record {
>             push @filters, 'EmbedItemsAvailability';
>             push @filters, 'EmbedSeeFromHeadings'
>                 if C4::Context->preference('IncludeSeeFromInSearches');
>+            push @filters, 'Index880InZebra';
> 
>             my $normalizer = Koha::RecordProcessor->new( { filters => \@filters } );
>             $marc = $normalizer->process($marc);
>-- 
>2.30.2

Actions: View | Diff | Splinter Review

Attachments on bug 15187: 44850 | 44876 | 134457 | 137050 | 137207 | 137208 | 137233 | 137234