Bug 31925: Add thesaurus/008 lookup and default MARC21 008 builder to Koha::Authority

AutoCreateAuthorities builds a brand-new authority record whenever a bib
subject heading (6XX) has no match, but always lets the record fall back
to C4::AuthoritiesMarc::AddAuthority()'s default 008/040, which hardcodes
008 position 11 ("Subject heading system/thesaurus") to 'a' (LCSH) no
matter what thesaurus the source heading actually uses. This is the first
step towards fixing that.

Adds two things to Koha::Authority:

- $MARC21_THESAURUS_TO_CONTROL_FIELD_008_11: a single-source-of-truth
  lookup mapping a thesaurus name (as already derived by C4::Heading from
  MARC indicator 2 / subfield $2, e.g. 'lcsh', 'mesh', or a raw $2 code
  such as 'fast') to its MARC21 authority 008/11 code, per the LOC ad008
  code list. This table previously only existed once, for a different
  purpose, in Koha::SearchEngine::Elasticsearch::QueryBuilder (used for
  building thesaurus search queries) - it's promoted here so both that
  and the authority-creation fix that follows can read from one place
  instead of two copies that can silently drift apart.

- default_marc21_008($thesaurus): builds the default 34-character body of
  a new MARC21 authority's 008 field, honouring the
  MARCAuthorityControlField008 system preference. When $thesaurus is
  given, position 11 is set from the table above instead of whatever the
  default/syspref value carries, falling back to 'z' (Other) for a
  thesaurus with no dedicated code.

AddAuthority() is refactored to build its own (thesaurus-less, LCSH
default) 008 via this new method too, replacing its previous inline copy
of the same defaulting logic - pure refactor, no behaviour change.
Nothing thesaurus-aware calls it yet.

Sponsored-by: Heythrop Library <https://heythroplibrary.co.uk/>
Signed-off-by: Clemens Gresser <cgresser@jesuit.org.uk>
Signed-off-by: Phil Ringnalda <phil@chetcolibrary.org>
Signed-off-by: David Cook <dcook@prosentient.com.au>
Signed-off-by: Pedro Amorim <pedro.amorim@openfifth.co.uk>

C4/AuthoritiesMarc.pm

@@ -620,16 +620,7 @@ sub AddAuthority {
         }
         my $date = POSIX::strftime( "%y%m%d", localtime );
         if ( !$record->field('008') ) {
-
-            # Get a valid default value for field 008
-            my $default_008 = C4::Context->preference('MARCAuthorityControlField008');
-            if ( !$default_008 or length($default_008) < 34 ) {
-                $default_008 = '|| aca||aabn           | a|a     d';
-            } else {
-                $default_008 = substr( $default_008, 0, 34 );
-            }
-
-            $record->insert_fields_ordered( MARC::Field->new( '008', $date . $default_008 ) );
+            $record->insert_fields_ordered( MARC::Field->new( '008', $date . Koha::Authority->default_marc21_008 ) );
         }
         if ( !$record->field('040') ) {
             $record->insert_fields_ordered(

Koha/Authority.pm

@@ -21,6 +21,8 @@ use Modern::Perl;
 
 use Scalar::Util qw( blessed );
 
+use C4::Context;
+
 use base qw(Koha::Object);
 
 use Koha::Authority::ControlledIndicators;
@@ -292,6 +294,77 @@ sub record_schema {
         : 'MARC21';
 }
 
+=head3 $MARC21_THESAURUS_TO_CONTROL_FIELD_008_11
+
+    my $code = $Koha::Authority::MARC21_THESAURUS_TO_CONTROL_FIELD_008_11->{$thesaurus};
+
+The mapping of a subject heading's thesaurus name (as derived by
+C4::Heading from MARC indicator 2 / subfield $2, e.g. 'lcsh', 'mesh', or a
+raw $2 code such as 'fast') to its MARC21 authority 008/11 code ("Subject
+heading system/thesaurus"), per
+L<https://www.loc.gov/marc/authority/ad008.html>.
+
+Note that C<sears> and C<aat> map to 008/11 values here but never appear
+as a thesaurus name derived by C4::Heading, because they don't have their
+own MARC21 indicator 2 value (see the LOC list linked above).
+
+=cut
+
+our $MARC21_THESAURUS_TO_CONTROL_FIELD_008_11 = {
+    lcsh          => 'a',
+    lcac          => 'b',
+    mesh          => 'c',
+    nal           => 'd',
+    notapplicable => 'n',
+    cash          => 'k',
+    rvm           => 'v',
+    aat           => 'r',
+    sears         => 's',
+    notdefined    => 'z',
+    notspecified  => '|',
+};
+
+=head3 default_marc21_008
+
+    my $default_008 = Koha::Authority->default_marc21_008;
+    my $default_008 = Koha::Authority->default_marc21_008($thesaurus);
+
+Returns the default 34-character body (i.e. everything after the
+6-character date) to use for a new MARC21 authority record's 008 field,
+honouring the I<MARCAuthorityControlField008> system preference and
+falling back to Koha's hardcoded default when it isn't set to a valid (at
+least 34 character) value.
+
+If C<$thesaurus> is passed, position 11 ("Subject heading
+system/thesaurus") is set from
+L<$MARC21_THESAURUS_TO_CONTROL_FIELD_008_11> instead of whatever the
+default/syspref value carries, falling back to 'z' (Other) for a
+thesaurus with no dedicated code -- consistent with how Elasticsearch
+indexing already reconciles 008/11 vs 040$f (see
+Koha::SearchEngine::Elasticsearch::_process_mappings, where a 'z' is
+dropped in favour of a genuine 040$f value).
+
+=cut
+
+sub default_marc21_008 {
+    my ( $class, $thesaurus ) = @_;
+
+    my $default_008 = C4::Context->preference('MARCAuthorityControlField008');
+    if ( !$default_008 or length($default_008) < 34 ) {
+        $default_008 = '|| aca||aabn           | a|a     d';
+    } else {
+        $default_008 = substr( $default_008, 0, 34 );
+    }
+
+    if ( defined $thesaurus ) {
+
+        # Position 11 is absolute (over date + body); within the 34-char body alone that's index 11 - 6 = 5.
+        substr( $default_008, 5, 1, $MARC21_THESAURUS_TO_CONTROL_FIELD_008_11->{$thesaurus} // 'z' );
+    }
+
+    return $default_008;
+}
+
 =head3 to_api_mapping
 
 This method returns the mapping for representing a Koha::Authority object

t/db_dependent/Koha/Authority.t

@@ -20,7 +20,7 @@
 use Modern::Perl;
 
 use Test::MockModule;
-use Test::More tests => 2;
+use Test::More tests => 3;
 use Test::NoWarnings;
 
 use C4::AuthoritiesMarc;
@@ -116,3 +116,41 @@ subtest 'move_to_deleted' => sub {
 
     $schema->storage->txn_rollback;
 };
+
+subtest 'default_marc21_008 tests (bug 31925)' => sub {
+    plan tests => 7;
+
+    is(
+        substr( Koha::Authority->default_marc21_008('lcsh'), 5, 1 ), 'a',
+        'lcsh maps to 008/11 code a'
+    );
+    is(
+        substr( Koha::Authority->default_marc21_008('mesh'), 5, 1 ), 'c',
+        'mesh maps to 008/11 code c'
+    );
+    is(
+        substr( Koha::Authority->default_marc21_008('rvm'), 5, 1 ), 'v',
+        'rvm maps to 008/11 code v'
+    );
+    is(
+        substr( Koha::Authority->default_marc21_008('fast'), 5, 1 ), 'z',
+        'Unrecognized raw $2 code (e.g. fast, from an ind2=7 heading) maps to 008/11 code z (Other)'
+    );
+
+    t::lib::Mocks::mock_preference( 'MARCAuthorityControlField008', '' );
+    is(
+        Koha::Authority->default_marc21_008, '|| aca||aabn           | a|a     d',
+        'Falls back to the hardcoded default when the syspref is unset, and thesaurus is not passed'
+    );
+    is(
+        substr( Koha::Authority->default_marc21_008('fast'), 5, 1 ), 'z',
+        'Thesaurus code is still applied on top of the hardcoded default'
+    );
+
+    my $custom = '||caaa||aabn           | a|a     d##padding';
+    t::lib::Mocks::mock_preference( 'MARCAuthorityControlField008', $custom );
+    is(
+        Koha::Authority->default_marc21_008, substr( $custom, 0, 34 ),
+        'Uses the syspref value, truncated to 34 characters, when valid'
+    );
+};