From f2003e3e52d60f9b088a5ad06536a745e1010dcd Mon Sep 17 00:00:00 2001
From: Pedro Amorim <pedro.amorim@openfifth.co.uk>
Date: Wed, 19 Aug 2026 13:10:08 +0000
Subject: [PATCH] Bug 35104: (RM follow-up) Restore StripNonXmlChars in
 TransformHtmlToMarc

Removed by 6726b1a2544 on the assumption store() strips centrally -
but TransformHtmlToMarc never calls store(), so callers like
addbiblio.pl (FindDuplicate, duplicate redisplay) see unstripped
control characters again, the same failure Bug 34549 fixed.

repair_marcxml covers more faults but works on full MARCXML and can
throw - too big a change here; left as a follow-up.

Test plan:
prove t/db_dependent/Biblio/TransformHtmlToMarc.t

Signed-off-by: Pedro Amorim <pedro.amorim@openfifth.co.uk>
---
 C4/Biblio.pm | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/C4/Biblio.pm b/C4/Biblio.pm
index c0d7baa7b9..f694a19f46 100644
--- a/C4/Biblio.pm
+++ b/C4/Biblio.pm
@@ -89,6 +89,7 @@ use C4::Charset     qw(
     nsb_clean
     SetMarcUnicodeFlag
     SetUTF8Flag
+    StripNonXmlChars
 );
 use C4::Languages;
 use C4::Linker;
@@ -2363,6 +2364,7 @@ sub TransformHtmlToMarc {
 
                     # between 001 and 009 (included)
                 } elsif ( $fval ne '' ) {
+                    $fval     = StripNonXmlChars($fval);
                     $newfield = MARC::Field->new( $tag, $fval, );
                 }
 
@@ -2387,6 +2389,7 @@ sub TransformHtmlToMarc {
                     if ( $fval ne '' && $newfield ) {
                         $newfield->add_subfields( $fkey => $fval );
                     } elsif ( $fval ne '' ) {
+                        $fval     = StripNonXmlChars($fval);
                         $newfield = MARC::Field->new( $tag, $ind1, $ind2, $fkey => $fval );
                     }
                     $j += 2;