From f5bcc021276bc483fb26df205a52e020d8ecd3a8 Mon Sep 17 00:00:00 2001
From: David Cook <dcook@prosentient.com.au>
Date: Mon, 11 Nov 2024 04:30:06 +0000
Subject: [PATCH] Bug 38416: Failover to MARCXML if cannot roundtrip USMARC
 during indexing

This change failsover to MARCXML from USMARC if there are any
warnings generated by MARC::File::USMARC::decode when trying to
roundtrip the record.

Test plan:
0. Apply the patch
1. Setup your koha-testing-docker to use Elasticsearch
2. Create a new record with 15,000 characters in the 500$a field
3. Index that record
(e.g. perl misc/search_tools/rebuild_elasticsearch.pl --biblios -v -v)
4. Note that a warning saying the following appears:
"Warnings encountered while roundtripping a MARC record to/from USMARC.
Failing over to MARCXML"
5. View the "Elasticsearch record" on the detail page and note that the
marc_format is MARCXML
6. Perform a search for the record (the keyword should be something that
brings up other results too)
7. Note that the record appears correctly in the search results
---
 Koha/SearchEngine/Elasticsearch.pm | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/Koha/SearchEngine/Elasticsearch.pm b/Koha/SearchEngine/Elasticsearch.pm
index 5ef5235720..13541d0849 100644
--- a/Koha/SearchEngine/Elasticsearch.pm
+++ b/Koha/SearchEngine/Elasticsearch.pm
@@ -815,7 +815,19 @@ sub marc_records_to_documents {
                 local $SIG{__WARN__} = sub {
                     push @warnings, $_[0];
                 };
-                $record_document->{'marc_data'} = encode_base64(encode('UTF-8', $record->as_usmarc()));
+                my $usmarc_record = $record->as_usmarc();
+
+                #NOTE: Try to round-trip the record to prove it will work for retrieval after searching
+                my $decoded_usmarc_record = MARC::Record->new_from_usmarc($usmarc_record);
+                if ($decoded_usmarc_record->warnings()){
+                    #NOTE: We override the warnings since they're many and misleading
+                    @warnings = (
+                        "Warnings encountered while roundtripping a MARC record to/from USMARC. Failing over to MARCXML.",
+                    );
+                }
+
+                my $marc_data = encode_base64(encode('UTF-8', $usmarc_record));
+                $record_document->{'marc_data'} = $marc_data;
             }
             if (@warnings) {
                 # Suppress warnings if record length exceeded
-- 
2.39.5