From cb2aa9dbb09248000d2f7c2d061ef1cf51e1220c Mon Sep 17 00:00:00 2001
From: Nick Clemens <nick@bywatersolutions.com>
Date: Thu, 25 Jul 2024 16:37:17 +0000
Subject: [PATCH] Bug 37478: Add strict mode to bulkmarcimport

This patch adds a conversion from MARC -> XML -> MARC to catch any parsing errors.
If errors are found, we then lint the record to catch any problems, output the
warnings, and skip the record.

To test:
1 - Download the sample records from this bug report
2 - perl misc/migration_tools/bulkmarcimport.pl -b --file=520_nosubfield.mrc -v
    fails!
3 - perl misc/migration_tools/bulkmarcimport.pl -b --file=003_subfielda.mrc -v
    fails!
4 - Apply patch
5 - Repeat 2 & 3 - no change
6 - Add -st switch to the commands:
    perl misc/migration_tools/bulkmarcimport.pl -b --file=520_nosubfield.mrc -v -st
    perl misc/migration_tools/bulkmarcimport.pl -b --file=003_subfielda.mrc -v -st
7 - The records are now skipped, and the script completes
8 - Confirm the warnings generated are useful
9 - Sign off!

Signed-off-by: David Nind <david@davidnind.com>
Signed-off-by: Martin Renvoize <martin.renvoize@ptfs-europe.com>
---
 misc/migration_tools/bulkmarcimport.pl | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/misc/migration_tools/bulkmarcimport.pl b/misc/migration_tools/bulkmarcimport.pl
index efcac9589f4..691e9c9e363 100755
--- a/misc/migration_tools/bulkmarcimport.pl
+++ b/misc/migration_tools/bulkmarcimport.pl
@@ -9,6 +9,7 @@ use Modern::Perl;
 use MARC::File::USMARC;
 use MARC::File::XML;
 use MARC::Batch;
+use MARC::Lint;
 use Encode;
 
 use Koha::Script;
@@ -76,6 +77,7 @@ my $localcust;
 my $marc_mod_template    = '';
 my $marc_mod_template_id = -1;
 my $skip_indexing        = 0;
+my $strict_mode;
 $| = 1;
 
 GetOptions(
@@ -113,6 +115,7 @@ GetOptions(
     'custom:s'          => \$localcust,
     'marcmodtemplate:s' => \$marc_mod_template,
     'si|skip_indexing'  => \$skip_indexing,
+    'st|strict'         => \$strict_mode,
 );
 
 $biblios ||= !$authorities;
@@ -320,6 +323,7 @@ my $record_number = 0;
 my $logger        = Koha::Logger->get;
 my $schema        = Koha::Database->schema;
 my $marc_records  = [];
+my $lint          = MARC::Lint->new;
 RECORD: while () {
     my $record;
     $record_number++;
@@ -339,6 +343,19 @@ RECORD: while () {
     }
     if ($record) {
 
+        if ($strict_mode) {
+            my $xml = $record->as_xml_record();
+            eval { MARC::Record::new_from_xml( $xml, 'UTF-8', "MARC21" ); };
+            if ($@) {
+                print "Record $record_number generated invalid xml:\n";
+                $lint->check_record($record);
+                foreach my $warning ( $lint->warnings ) {
+                    print "    " . $warning . "\n";
+                }
+                print "    Record skipped!";
+                next;
+            }
+        }
         # transcode the record to UTF8 if needed & applicable.
         if ( $record->encoding() eq 'MARC-8' and not $skip_marc8_conversion ) {
             my ( $guessed_charset, $charset_errors );
-- 
2.47.0