Bug 29333: Fix encoding of imported UNIMARC authorities

MARC::Record and MARC::File::* modules sometimes use the position 09 of
the leader to detect encoding. A blank character means 'MARC-8' while an
'a' means 'UTF-8'.

In a UNIMARC authority this position is used to store the authority type
(see https://www.transition-bibliographique.fr/wp-content/uploads/2021/02/AIntroLabel-2004.pdf [FR]).
In this case, 'a' means 'Personal Name'.

The result is that the import will succeed for a Personal Name
authority, but it will fail for all other authority types.

Steps to reproduce:
0. Be sure to have a Koha UNIMARC instance.
1. Download the MARCXML for "Honoré de Balzac"
   curl -o balzac.marcxml https://www.idref.fr/02670305X.xml
2. Verify that it's encoded in UTF-8
   file balzac.marcxml
   (should output "balzac.marcxml: XML 1.0 document, UTF-8 Unicode
   text")
3. Go to Tools » Stage MARC for import and import balzac.marcxml with
   the following settings:
   Record type: Authority
   Character encoding: UTF-8
   Format: MARCXML
   Do not touch the other settings
4. Once imported, go to the staged MARC management tool and find your
   batch. Click on the authority title "Balzac Honoré de 1799-1850" to
   show the MARC inside a modal window. There should be no encoding
   issue.
5. Write down the imported record id (the number in column '#') and go
   to the MARC authority editor. Replace all URL parameters by
   'breedingid=THE_ID_YOU_WROTE_DOWN'
   The URL should look like this:
   /cgi-bin/koha/authorities/authorities.pl?breedingid=198
   You should see no encoding issues. Do not save the record.
6. Import the batch into the catalog. Verify that the authority record
   has no encoding issue.
7. Now download the MARCXML for "Athènes (Grèce)"
   curl -o athènes.marcxml https://www.idref.fr/027290530.xml
8. Repeat steps 2 to 6 using athènes.marcxml file. At steps 4 and 5 you
   should see encoding issues and that the position 9 of the leader was
   rewritten from 'c' to 'a'. Strangely, importing this batch fix the
   encoding issue, but we still lose the information in position 09 of
   the leader

This patch makes use of the MARCXML representation of the record instead
of the ISO2709 representation, because, unlike
MARC::Record::new_from_usmarc, MARC::Record::new_from_xml allows us to
pass directly the encoding and the format, which prevents data to be
double encoded when position 09 of the leader is different that 'a'

Test plan:
- Follow the "steps to reproduce" above and verify that you have no
  encoding issues.

Signed-off-by: David Nind <david@davidnind.com>
Signed-off-by: Martin Renvoize <martin.renvoize@ptfs-europe.com>
Signed-off-by: Tomas Cohen Arazi <tomascohen@theke.io>
(cherry picked from commit 01d78e1ec7)

Signed-off-by: Lucas Gass <lucas@bywatersolutions.com>
This commit is contained in:
Julian Maurice 2021-10-27 12:00:23 +02:00 committed by Lucas Gass
parent e9153d7f15
commit 76e980bb1a
6 changed files with 164 additions and 103 deletions

View file

@ -46,8 +46,6 @@ BEGIN {
GetZ3950BatchId
GetWebserviceBatchId
GetImportRecordMarc
GetImportRecordMarcXML
GetRecordFromImportBiblio
AddImportBatch
GetImportBatch
AddAuthToBatch
@ -191,17 +189,6 @@ sub GetImportRecordMarc {
return $marc, $encoding;
}
sub GetRecordFromImportBiblio {
my ( $import_record_id, $embed_items ) = @_;
my ($marc) = GetImportRecordMarc($import_record_id);
my $record = MARC::Record->new_from_usmarc($marc);
EmbedItemsInImportBiblio( $record, $import_record_id ) if $embed_items;
return $record;
}
sub EmbedItemsInImportBiblio {
my ( $record, $import_record_id ) = @_;
my ( $itemtag, $itemsubfield ) = GetMarcFromKohaField( "items.itemnumber" );
@ -220,24 +207,6 @@ sub EmbedItemsInImportBiblio {
return $record;
}
=head2 GetImportRecordMarcXML
my $marcxml = GetImportRecordMarcXML($import_record_id);
=cut
sub GetImportRecordMarcXML {
my ($import_record_id) = @_;
my $dbh = C4::Context->dbh;
my $sth = $dbh->prepare("SELECT marcxml FROM import_records WHERE import_record_id = ?");
$sth->execute($import_record_id);
my ($marcxml) = $sth->fetchrow();
$sth->finish();
return $marcxml;
}
=head2 AddImportBatch
my $batch_id = AddImportBatch($params_hash);

View file

@ -18,7 +18,9 @@ package Koha::Import::Record;
use Modern::Perl;
use Carp;
use MARC::Record;
use C4::Context;
use Koha::Database;
use base qw(Koha::Object);
@ -29,6 +31,39 @@ Koha::Import::Record - Koha Import Record Object class
=head1 API
=head2 Public methods
=head3 get_marc_record
Returns a MARC::Record object
my $marc_record = $import_record->get_marc_record({ embed_items => $embed_items })
If $embed_items is true then items from import_items are embedded into the
MARC::Record returned
=cut
sub get_marc_record {
my ($self, $args) = @_;
my $marcflavour = C4::Context->preference('marcflavour');
my $format = $marcflavour eq 'UNIMARC' ? 'UNIMARC' : 'USMARC';
if ($marcflavour eq 'UNIMARC' && $self->record_type eq 'auth') {
$format = 'UNIMARCAUTH';
}
my $record = MARC::Record->new_from_xml($self->marcxml, $self->encoding, $format);
if ($self->record_type eq 'biblio' && $args->{embed_items}) {
require C4::ImportBatch;
C4::ImportBatch::EmbedItemsInImportBiblio($record, $self->id);
}
return $record;
}
=head2 Internal methods
=head3 _type

View file

@ -24,13 +24,13 @@ use CGI qw ( -utf8 );
use C4::Auth qw( get_template_and_user );
use C4::Output qw( output_html_with_http_headers );
use C4::AuthoritiesMarc qw( AddAuthority ModAuthority GetAuthority GetTagsLabels GetAuthMARCFromKohaField FindDuplicateAuthority );
use C4::ImportBatch qw( GetImportRecordMarc );
use C4::Context;
use Date::Calc qw( Today );
use MARC::File::USMARC;
use MARC::File::XML;
use C4::Biblio qw( TransformHtmlToMarc );
use Koha::Authority::Types;
use Koha::Import::Records;
use Koha::ItemTypes;
use vars qw( $tagslib);
use vars qw( $authorised_values_sth);
@ -48,21 +48,6 @@ builds list, depending on authorised value...
=cut
sub MARCfindbreeding_auth {
my ( $id ) = @_;
my ($marc, $encoding) = GetImportRecordMarc($id);
if ($marc) {
my $record = MARC::Record->new_from_usmarc($marc);
if ( !defined(ref($record)) ) {
return -1;
} else {
return $record, $encoding;
}
} else {
return -1;
}
}
sub build_authorized_values_list {
my ( $tag, $subfield, $value, $dbh, $authorised_values_sth,$index_tag,$index_subfield ) = @_;
@ -329,7 +314,7 @@ sub GetMandatoryFieldZ3950 {
}
sub build_tabs {
my ( $template, $record, $dbh, $encoding,$input ) = @_;
my ( $template, $record, $dbh, $input ) = @_;
# fill arrays
my @loop_data = ();
@ -365,7 +350,7 @@ sub build_tabs {
# if MARC::Record is not empty =>use it as master loop, then add missing subfields that should be in the tab.
# if MARC::Record is empty => use tab as master loop.
if ( $record != -1 && ( $record->field($tag) || $tag eq '000' ) ) {
if ( $record && ( $record->field($tag) || $tag eq '000' ) ) {
my @fields;
if ( $tag ne '000' ) {
@fields = $record->field($tag);
@ -571,13 +556,14 @@ $template->param(nonav => $nonav,index=>$myindex,authtypecode=>$authtypecode,b
$tagslib = GetTagsLabels(1,$authtypecode);
$mandatory_z3950 = GetMandatoryFieldZ3950($authtypecode);
my $record=-1;
my $encoding="";
if (($authid) && !($breedingid)){
$record = GetAuthority($authid);
}
my $record;
if ($breedingid) {
( $record, $encoding ) = MARCfindbreeding_auth( $breedingid );
my $import_record = Koha::Import::Records->find($breedingid);
if ($import_record) {
$record = $import_record->get_marc_record();
}
} elsif ($authid) {
$record = GetAuthority($authid);
}
my ($oldauthnumtagfield,$oldauthnumtagsubfield);
@ -619,7 +605,7 @@ if ($op eq "add") {
exit;
} else {
# it may be a duplicate, warn the user and do nothing
build_tabs($template, $record, $dbh, $encoding,$input);
build_tabs($template, $record, $dbh, $input);
build_hidden_data;
$template->param(authid =>$authid,
duplicateauthid => $duplicateauthid,
@ -640,7 +626,7 @@ if ($op eq "duplicate")
{
$authid = "";
}
build_tabs ($template, $record, $dbh,$encoding,$input);
build_tabs ($template, $record, $dbh, $input);
build_hidden_data;
$template->param(oldauthtypetagfield=>$oldauthtypetagfield, oldauthtypetagsubfield=>$oldauthtypetagsubfield,
oldauthnumtagfield=>$oldauthnumtagfield, oldauthnumtagsubfield=>$oldauthnumtagsubfield,

View file

@ -31,9 +31,10 @@ use C4::Context;
use C4::Output qw( output_html_with_http_headers );
use C4::Auth qw( get_template_and_user );
use C4::Biblio qw( GetMarcBiblio GetXmlBiblio );
use C4::ImportBatch qw( GetRecordFromImportBiblio );
use C4::XSLT;
use Koha::Import::Records;
my $input= CGI->new;
my ( $template, $loggedinuser, $cookie ) = get_template_and_user(
{
@ -48,9 +49,20 @@ my $biblionumber= $input->param('id');
my $importid= $input->param('importid');
my $view= $input->param('viewas')||'';
my $marcflavour = C4::Context->preference('marcflavour');
my $record;
my $record_type = 'biblio';
my $format = $marcflavour eq 'UNIMARC' ? 'UNIMARC' : 'USMARC';
if ($importid) {
$record = C4::ImportBatch::GetRecordFromImportBiblio( $importid, 'embed_items' );
my $import_record = Koha::Import::Records->find($importid);
if ($import_record) {
if ($marcflavour eq 'UNIMARC' && $import_record->record_type eq 'auth') {
$format = 'UNIMARCAUTH';
}
$record = $import_record->get_marc_record({ embed_items => 1 });
}
}
else {
$record =GetMarcBiblio({ biblionumber => $biblionumber });
@ -61,11 +73,10 @@ if(!ref $record) {
}
if($view eq 'card' || $view eq 'html') {
my $xml = $importid ? $record->as_xml(): GetXmlBiblio($biblionumber);
my $xml = $importid ? $record->as_xml($format): GetXmlBiblio($biblionumber);
my $xsl;
if ( $view eq 'card' ){
$xsl = C4::Context->preference('marcflavour') eq 'UNIMARC'
? 'UNIMARC_compact.xsl' : 'compact.xsl';
$xsl = $marcflavour eq 'UNIMARC' ? 'UNIMARC_compact.xsl' : 'compact.xsl';
}
else {
$xsl = 'plainMARC.xsl';

View file

@ -10,6 +10,7 @@ use t::lib::Mocks;
use t::lib::TestBuilder;
use Koha::Database;
use Koha::Import::Records;
BEGIN {
# Mock pluginsdir before loading Plugins module
@ -17,7 +18,7 @@ BEGIN {
t::lib::Mocks::mock_config( 'pluginsdir', $path );
use_ok('Koha::Plugins');
use_ok('C4::ImportBatch', qw( AddImportBatch GetImportBatch AddBiblioToBatch AddItemsToImportBiblio GetRecordFromImportBiblio SetMatchedBiblionumber GetImportBiblios GetItemNumbersFromImportBatch CleanBatch DeleteBatch RecordsFromMarcPlugin ));
use_ok('C4::ImportBatch', qw( AddImportBatch GetImportBatch AddBiblioToBatch AddItemsToImportBiblio SetMatchedBiblionumber GetImportBiblios GetItemNumbersFromImportBatch CleanBatch DeleteBatch RecordsFromMarcPlugin ));
}
# Start transaction
@ -93,47 +94,83 @@ my $original_record = MARC::Record->new;
$record->leader('03174nam a2200445 a 4500');
$original_record->leader('03174nam a2200445 a 4500');
my ($item_tag, $item_subfield) = C4::Biblio::GetMarcFromKohaField( 'items.itemnumber' );
my @fields = (
MARC::Field->new(
100, '1', ' ',
a => 'Knuth, Donald Ervin',
d => '1938',
),
MARC::Field->new(
245, '1', '4',
a => 'The art of computer programming',
c => 'Donald E. Knuth.',
),
MARC::Field->new(
650, ' ', '0',
a => 'Computer programming.',
9 => '462',
),
MARC::Field->new(
$item_tag, ' ', ' ',
e => 'my edition ❤',
i => 'my item part',
),
MARC::Field->new(
$item_tag, ' ', ' ',
e => 'my edition 2',
i => 'my item part 2',
),
);
my @fields;
if (C4::Context->preference('marcflavour') eq 'UNIMARC') {
@fields = (
MARC::Field->new(
100, ' ', ' ',
a => '20220520d u||y0frey50 ba',
),
MARC::Field->new(
700, ' ', ' ',
a => 'Knuth, Donald Ervin',
f => '1938',
),
MARC::Field->new(
200, ' ', ' ',
a => 'The art of computer programming',
f => 'Donald E. Knuth.',
),
MARC::Field->new(
650, ' ', '0',
a => 'Computer programming.',
9 => '462',
),
MARC::Field->new(
$item_tag, ' ', ' ',
e => 'my edition ❤',
i => 'my item part',
),
MARC::Field->new(
$item_tag, ' ', ' ',
e => 'my edition 2',
i => 'my item part 2',
),
);
} else {
@fields = (
MARC::Field->new(
100, '1', ' ',
a => 'Knuth, Donald Ervin',
d => '1938',
),
MARC::Field->new(
245, '1', '4',
a => 'The art of computer programming',
c => 'Donald E. Knuth.',
),
MARC::Field->new(
650, ' ', '0',
a => 'Computer programming.',
9 => '462',
),
MARC::Field->new(
$item_tag, ' ', ' ',
e => 'my edition ❤',
i => 'my item part',
),
MARC::Field->new(
$item_tag, ' ', ' ',
e => 'my edition 2',
i => 'my item part 2',
),
);
}
$record->append_fields(@fields);
$original_record->append_fields(@fields);
my $import_record_id = AddBiblioToBatch( $id_import_batch1, 0, $record, 'utf8', int(rand(99999)), 0 );
AddItemsToImportBiblio( $id_import_batch1, $import_record_id, $record, 0 );
my $record_from_import_biblio_with_items = C4::ImportBatch::GetRecordFromImportBiblio( $import_record_id, 'embed_items' );
my $import_record = Koha::Import::Records->find($import_record_id);
my $record_from_import_biblio_with_items = $import_record->get_marc_record({ embed_items => 1 });
$original_record->leader($record_from_import_biblio_with_items->leader());
is_deeply( $record_from_import_biblio_with_items, $original_record, 'GetRecordFromImportBiblio should return the record with items if specified' );
is_deeply( $record_from_import_biblio_with_items, $original_record, 'Koha::Import::Record::get_marc_record should return the record with items if specified' );
my $utf8_field = $record_from_import_biblio_with_items->subfield($item_tag, 'e');
is($utf8_field, 'my edition ❤');
$original_record->delete_fields($original_record->field($item_tag)); #Remove items fields
my $record_from_import_biblio_without_items = C4::ImportBatch::GetRecordFromImportBiblio( $import_record_id );
my $record_from_import_biblio_without_items = $import_record->get_marc_record();
$original_record->leader($record_from_import_biblio_without_items->leader());
is_deeply( $record_from_import_biblio_without_items, $original_record, 'GetRecordFromImportBiblio should return the record without items by default' );
is_deeply( $record_from_import_biblio_without_items, $original_record, 'Koha::Import::Record::get_marc_record should return the record without items by default' );
my $another_biblio = $builder->build_sample_biblio;
C4::ImportBatch::SetMatchedBiblionumber( $import_record_id, $another_biblio->biblionumber );
@ -175,7 +212,7 @@ my $id_import_batch3 = C4::ImportBatch::AddImportBatch($sample_import_batch3);
# Test CleanBatch
C4::ImportBatch::CleanBatch( $id_import_batch3 );
my $import_record = get_import_record( $id_import_batch3 );
$import_record = get_import_record( $id_import_batch3 );
is( $import_record, "0E0", "Batch 3 has been cleaned" );
# Test DeleteBatch
@ -221,7 +258,20 @@ subtest "RecordsFromMarcPlugin" => sub {
# Create a test file
my ( $fh, $name ) = tempfile();
print $fh q|
if (C4::Context->preference('marcflavour') eq 'UNIMARC') {
print $fh q{
003 = NLAmRIJ
100,a = 20220520d u||y0frey50 ba
700,a = Author
200,ind2 = 0
200,a = Silence in the library
500 , a= Some note
700,a = Another
245,a = Noise in the library};
close $fh;
} else {
print $fh q|
003 = NLAmRIJ
100,a = Author
245,ind2 = 0
@ -230,7 +280,8 @@ subtest "RecordsFromMarcPlugin" => sub {
100,a = Another
245,a = Noise in the library|;
close $fh;
close $fh;
}
t::lib::Mocks::mock_config( 'enable_plugins', 1 );
@ -241,10 +292,17 @@ subtest "RecordsFromMarcPlugin" => sub {
my $records = C4::ImportBatch::RecordsFromMarcPlugin( $name, ref $plugin, 'UTF-8' );
is( @$records, 2, 'Two results returned' );
is( ref $records->[0], 'MARC::Record', 'Returned MARC::Record object' );
is( $records->[0]->subfield('245', 'a'), 'Silence in the library',
'Checked one field in first record' );
is( $records->[1]->subfield('100', 'a'), 'Another',
'Checked one field in second record' );
if (C4::Context->preference('marcflavour') eq 'UNIMARC') {
is( $records->[0]->subfield('200', 'a'), 'Silence in the library',
'Checked one field in first record' );
is( $records->[1]->subfield('700', 'a'), 'Another',
'Checked one field in second record' );
} else {
is( $records->[0]->subfield('245', 'a'), 'Silence in the library',
'Checked one field in first record' );
is( $records->[1]->subfield('100', 'a'), 'Another',
'Checked one field in second record' );
}
};
subtest "_get_commit_action" => sub {

View file

@ -30,10 +30,11 @@ use C4::Output qw( output_html_with_http_headers );
use C4::Auth qw( get_template_and_user );
use C4::Biblio qw( GetMarcBiblio );
use C4::Auth qw( get_template_and_user );
use C4::ImportBatch qw( GetRecordFromImportBiblio GetImportBiblios );
use C4::ImportBatch qw( GetImportBiblios );
use C4::AuthoritiesMarc qw( GetAuthority );
use Koha::Biblios;
use Koha::Import::Records;
# Input params
my $input = CGI->new;
@ -79,7 +80,8 @@ if( $record ) {
}
if( $importid ) {
$recordImportid = C4::ImportBatch::GetRecordFromImportBiblio( $importid, 'embed_items' );
my $import_record = Koha::Import::Records->find($importid);
my $recordImportid = $import_record->get_marc_record({ embed_items => 1 });
$formatted2 = $recordImportid->as_formatted;
my $biblio = GetImportBiblios($importid);
$importTitle = $biblio->[0]->{'title'};