Bug 24094: Strip trailing spaces and punctuation from authority headings

Both when searching for and creating new authorities we need to remove
punctuation that exists in the bibliographic record but does not belong in
the authority record.

For example, a series with a volume contains a semicolon in the bib record,
however, this should not be passed to the authority as the volume is not
included in the authority record.

To test:
 1 - Set AutoCreateAuthorities to 'generate'
 2 - Set BiblioAddsAuthorities to 'true'
 3 - Set CatalogModuleRelink to 'Do'
 4 - Find or create a record with:
    a 100 field with a subfield e preceded by a comma: 100 $aBoring, M. Eugene M ,$e author
    an 830 field with a volume preceded by a semicolon: 650$aLord of the rings ;$v 3.
 5 - Save the records and check the links
 6 - Note punctuation is passed through
 7 - Save again, auth records are created again
 8 - Apply patch
 9 - Save again, new auth records are created again
10 - Check the records, punctuation has been removed
11 - Save again, no more records created.

Signed-off-by: Myka Kennedy Stephens <mkstephens@lancasterseminary.edu>
Signed-off-by: Martin Renvoize <martin.renvoize@ptfs-europe.com>

diff --git a/C4/Biblio.pm b/C4/Biblio.pm
index aa401d5..da58af2 100644 (file)
--- a/C4/Biblio.pm
+++ b/C4/Biblio.pm
@@ -542,16 +542,22 @@ sub LinkBibHeadingsToAuthorities {
                     }
                     $field->delete_subfield( code => '9' )
                       if defined $current_link;
-                    my $authfield =
-                      MARC::Field->new( $authority_type->auth_tag_to_report,
-                        '', '', "a" => "" . $field->subfield('a') );
-                    map {
-                        $authfield->add_subfields( $_->[0] => $_->[1] )
-                          if ( $_->[0] =~ /[A-z]/ && $_->[0] ne "a"
+                    my @auth_subfields;
+                    foreach my $subfield ( $field->subfields() ){
+                        if ( $subfield->[0] =~ /[A-z]/
                             && C4::Heading::valid_bib_heading_subfield(
-                                $field->tag, $_->[0] )
-                            );
-                    } $field->subfields();
+                                $field->tag, $subfield->[0] )
+                           ){
+                            push @auth_subfields, $subfield->[0] => $subfield->[1];
+                        }
+                    }
+                    # Bib headings contain some ending punctuation that should NOT
+                    # be included in the authority record. Strip those before creation
+                    next unless @auth_subfields; # Don't try to create a record if we have no fields;
+                    my $last_sub = pop @auth_subfields;
+                    $last_sub =~ s/[\s]*[,.:=;!%\/][\s]*$//;
+                    push @auth_subfields, $last_sub;
+                    my $authfield = MARC::Field->new( $authority_type->auth_tag_to_report, '', '', @auth_subfields );
                     $marcrecordauth->insert_fields_ordered($authfield);
 
 # bug 2317: ensure new authority knows it's using UTF-8; currently

diff --git a/C4/Heading/MARC21.pm b/C4/Heading/MARC21.pm
index fc4d576..0fc3374 100644 (file)
--- a/C4/Heading/MARC21.pm
+++ b/C4/Heading/MARC21.pm
@@ -256,7 +256,7 @@ sub _get_search_heading {
         my $code    = $subfields[$i]->[0];
         my $code_re = quotemeta $code;
         my $value   = $subfields[$i]->[1];
-        $value =~ s/[-,.:=;!%\/]$//;
+        $value =~ s/[\s]*[-,.:=;!%\/][\s]*$//;
         next unless $subfields =~ qr/$code_re/;
         if ($first) {
             $first   = 0;