From 9b8081376c4c9788766c3a356a9151e554353e85 Mon Sep 17 00:00:00 2001
From: Nick Clemens <nick@bywatersolutions.com>
Date: Thu, 22 Jun 2023 11:22:18 +0000
Subject: [PATCH] Bug 33270: Warn errors but catch exceptions when encountering
 record issues in OAI-PMH

This patch alters the OAI code to attempt to load a badly encoded record by removing non XML characters. OAI harvests are used to keep external catalogs or display layers in sync with Koha. We should not break this connection when there is a bad record, but should allow the harvest to complete - warn the errors, and rely on Koha warnings/errors/tools to idnetify and fix the problem on the Koha side

Test plan, assumes using KTD default data - otherwise you need to find and import a record with encoding issues:
1 - Enable OAI-PMH system preference
2 - Browse to:
    http://localhost:8080/cgi-bin/koha/oai.pl?verb=ListRecords&resumptionToken=marcxml/350////0/0/352
3 - 500 error:
    Invalid data, cannot decode metadata object (biblio_metadata.id=368, biblionumber=369, format=marcxml, schema=MARC21, decoding_error=':8: parser error : PCDATA invalid Char value 31...
4 - Apply patch, restart all
5 - Reload the page
6 - It loads!
7 - Click 'Metadata' for record 369 - it succeeds!
8 - Check the logs - confirm you see a warning of the record problem

Signed-off-by: Sam Lau <samalau@gmail.com>
---
 Koha/OAI/Server/Repository.pm | 29 ++++++++++++++++++++++++++---
 1 file changed, 26 insertions(+), 3 deletions(-)

diff --git a/Koha/OAI/Server/Repository.pm b/Koha/OAI/Server/Repository.pm
index 0cd0df5dcf..16ceec411f 100644
--- a/Koha/OAI/Server/Repository.pm
+++ b/Koha/OAI/Server/Repository.pm
@@ -37,9 +37,12 @@ use YAML::XS;
 use CGI qw/:standard -oldstyle_urls/;
 use C4::Context;
 use C4::Biblio qw( GetFrameworkCode );
+use C4::Charset qw( StripNonXmlChars );
 use Koha::XSLT::Base;
 use Koha::Biblios;
 
+use MARC::Record;
+
 =head1 NAME
 
 Koha::OAI::Server::Repository - Handles OAI-PMH requests for a Koha database.
@@ -178,8 +181,29 @@ sub get_biblio_marcxml {
     }
 
     my $biblio = Koha::Biblios->find($biblionumber);
-    my $record = $biblio->metadata->record({ embed_items => $with_items, opac => 1 });
-    if ( $expanded_avs ) {
+    my $record;
+    # Koha::Biblio::Metadata->record throws an exception on bad encoding,
+    # we don't want OAI harvests to die, so we catch and warn, and try to clean the record
+    eval { $record = $biblio->metadata->record({ embed_items => $with_items, opac => 1 }); };
+    if ($@) {
+        my $marcxml_error = $@;
+        chomp $marcxml_error;
+        warn $marcxml_error;
+        eval {
+            $record = MARC::Record->new_from_xml(
+                StripNonXmlChars( $biblio->metadata->metadata ), 'UTF-8',
+                $biblio->metadata->schema
+            );
+        };
+        # If the record still cannot be built, we will warn and return undef
+        # and record will be reported as deleted
+        if( $@ ){
+            $marcxml_error = $@;
+            chomp $marcxml_error;
+            warn $marcxml_error;
+        }
+    }
+    if ( $record && $expanded_avs ) {
         my $frameworkcode = GetFrameworkCode($biblionumber) || '';
         my $record_processor = Koha::RecordProcessor->new(
             {
@@ -192,7 +216,6 @@ sub get_biblio_marcxml {
         );
         $record_processor->process($record);
     }
-
     return $record ? $record->as_xml_record() : undef;
 }
 
-- 
2.30.2