One consequence is that the -x and -a options are no longer
mutually exclusive.
Also, because of the way that the GRS-1 SGML filter works, if you're
indexing multiple documents, you can't just wrap them in a document
element, but the DOM filter *requires* it. Consequently, two
new config settings in koha-conf.xml are added to indicate the
Zebra filter in use so that the -x option of rebuild_zebra.pl
knows whether to wrap the exported records or not:
- bib_index_mode (defaults to 'grs1' if not specified)
- auth_index_mode (defaults to 'dom')
Signed-off-by: Galen Charlton <gmc@esilibrary.com>
Signed-off-by: Jared Camins-Esakov <jcamins@cpbibliography.com>
Signed-off-by: Paul Poulain <paul.poulain@biblibre.com>
<pazpar2url>http://__PAZPAR2_HOST__:__PAZPAR2_PORT__/search.pz2</pazpar2url>
<install_log>__MISC_DIR__/koha-install-log</install_log>
<useldapserver>0</useldapserver><!-- see C4::Auth_with_ldap for extra configs you must add if you want to turn this on -->
<pazpar2url>http://__PAZPAR2_HOST__:__PAZPAR2_PORT__/search.pz2</pazpar2url>
<install_log>__MISC_DIR__/koha-install-log</install_log>
<useldapserver>0</useldapserver><!-- see C4::Auth_with_ldap for extra configs you must add if you want to turn this on -->
+ <zebra_bib_index_mode>__BIB_INDEX_MODE__</zebra_bib_index_mode>
+ <zebra_auth_index_mode>__AUTH_INDEX_MODE__</zebra_auth_index_mode>
<xslt stylesheet="authority-zebra-indexdefs.xsl"/>
</retrieve>
<input>
<xslt stylesheet="authority-zebra-indexdefs.xsl"/>
</retrieve>
<input>
<xslt stylesheet="biblio-zebra-indexdefs.xsl"/>
</retrieve>
<input>
<xslt stylesheet="biblio-zebra-indexdefs.xsl"/>
</retrieve>
<input>
-if ($authorities and $as_xml) {
- my $msg = "Cannot specify both -a and -x\n";
- $msg .= "Please do '$0 --help' to see usage.\n";
- die $msg;
-}
-
if ( !$as_xml and $nosanitize ) {
my $msg = "Cannot specify both -no_xml and -nosanitize\n";
$msg .= "Please do '$0 --help' to see usage.\n";
if ( !$as_xml and $nosanitize ) {
my $msg = "Cannot specify both -no_xml and -nosanitize\n";
$msg .= "Please do '$0 --help' to see usage.\n";
my $authorityserverdir = C4::Context->zebraconfig('authorityserver')->{directory};
my $kohadir = C4::Context->config('intranetdir');
my $authorityserverdir = C4::Context->zebraconfig('authorityserver')->{directory};
my $kohadir = C4::Context->config('intranetdir');
+my $bib_index_mode = C4::Context->config('zebra_bib_index_mode') || 'grs1';
+my $auth_index_mode = C4::Context->config('zebra_auth_index_mode') || 'dom';
+
my $dbh = C4::Context->dbh;
my ($biblionumbertagfield,$biblionumbertagsubfield) = &GetMarcFromKohaField("biblio.biblionumber","");
my ($biblioitemnumbertagfield,$biblioitemnumbertagsubfield) = &GetMarcFromKohaField("biblioitems.biblioitemnumber","");
my $dbh = C4::Context->dbh;
my ($biblionumbertagfield,$biblionumbertagsubfield) = &GetMarcFromKohaField("biblio.biblionumber","");
my ($biblioitemnumbertagfield,$biblioitemnumbertagsubfield) = &GetMarcFromKohaField("biblioitems.biblioitemnumber","");
+sub include_xml_wrapper {
+ my $as_xml = shift;
+ my $record_type = shift;
+
+ return 0 unless $as_xml;
+ return 1 if $record_type eq 'biblio' and $bib_index_mode eq 'dom';
+ return 1 if $record_type eq 'authority' and $auth_index_mode eq 'dom';
+ return 0;
+
+}
+
sub export_marc_records_from_sth {
my ($record_type, $sth, $directory, $as_xml, $noxml, $nosanitize) = @_;
my $num_exported = 0;
open my $fh, '>:encoding(UTF-8) ', "$directory/exported_records" or die $!;
sub export_marc_records_from_sth {
my ($record_type, $sth, $directory, $as_xml, $noxml, $nosanitize) = @_;
my $num_exported = 0;
open my $fh, '>:encoding(UTF-8) ', "$directory/exported_records" or die $!;
+ if (include_xml_wrapper($as_xml, $record_type)) {
+ # include XML declaration and root element
+ print {$fh} '<?xml version="1.0" encoding="UTF-8"?><collection>';
+ }
my $i = 0;
my ( $itemtag, $itemsubfield ) = GetMarcFromKohaField("items.itemnumber",'');
while (my ($record_number) = $sth->fetchrow_array) {
my $i = 0;
my ( $itemtag, $itemsubfield ) = GetMarcFromKohaField("items.itemnumber",'');
while (my ($record_number) = $sth->fetchrow_array) {
}
my ($marc) = get_corrected_marc_record($record_type, $record_number, $noxml);
if (defined $marc) {
}
my ($marc) = get_corrected_marc_record($record_type, $record_number, $noxml);
if (defined $marc) {
- # FIXME - when more than one record is exported and $as_xml is true,
- # the output file is not valid XML - it's just multiple <record> elements
- # strung together with no single root element. zebraidx doesn't seem
- # to care, though, at least if you're using the GRS-1 filter. It does
- # care if you're using the DOM filter, which requires valid XML file(s).
- print {$fh} ($as_xml) ? $marc->as_xml_record(C4::Context->preference('marcflavour')) : $marc->as_usmarc();
+ my $rec;
+ if ($as_xml) {
+ $rec = $marc->as_xml_record(C4::Context->preference('marcflavour'));
+ $rec =~ s!<\?xml version="1.0" encoding="UTF-8"\?>\n!!;
+ } else {
+ $rec = $marc->as_usmarc();
+ }
+ print {$fh} $rec;
$num_exported++;
};
if ($@) {
$num_exported++;
};
if ($@) {
}
}
print "\nRecords exported: $num_exported\n" if ( $verbose_logging );
}
}
print "\nRecords exported: $num_exported\n" if ( $verbose_logging );
+ print {$fh} '</collection>' if (include_xml_wrapper($as_xml, $record_type));
close $fh;
return $num_exported;
}
close $fh;
return $num_exported;
}
my $num_exported = 0;
open my $fh, '>:encoding(UTF-8)', "$directory/exported_records" or die $!;
my $num_exported = 0;
open my $fh, '>:encoding(UTF-8)', "$directory/exported_records" or die $!;
+ if (include_xml_wrapper($as_xml, $record_type)) {
+ # include XML declaration and root element
+ print {$fh} '<?xml version="1.0" encoding="UTF-8"?><collection>';
+ }
my $i = 0;
# Skip any deleted records. We check for this anyway, but this reduces error spam
my $i = 0;
# Skip any deleted records. We check for this anyway, but this reduces error spam
print "\r$i" unless ($i++ %100 or !$verbose_logging);
my ($marc) = get_corrected_marc_record($record_type, $record_number, $noxml);
if (defined $marc) {
print "\r$i" unless ($i++ %100 or !$verbose_logging);
my ($marc) = get_corrected_marc_record($record_type, $record_number, $noxml);
if (defined $marc) {
- # FIXME - when more than one record is exported and $as_xml is true,
- # the output file is not valid XML - it's just multiple <record> elements
- # strung together with no single root element. zebraidx doesn't seem
- # to care, though, at least if you're using the GRS-1 filter. It does
- # care if you're using the DOM filter, which requires valid XML file(s).
- print {$fh} ($as_xml) ? $marc->as_xml_record(C4::Context->preference('marcflavour')) : $marc->as_usmarc();
+ eval {
+ my $rec;
+ if ($as_xml) {
+ $rec = $marc->as_xml_record(C4::Context->preference('marcflavour'));
+ $rec =~ s!<\?xml version="1.0" encoding="UTF-8"\?>\n!!;
+ } else {
+ $rec = $marc->as_usmarc();
+ }
+ print {$fh} $rec;
+ $num_exported++;
+ };
+ if ($@) {
+ warn "Error exporting record $record_number ($record_type) ".($noxml ? "not XML" : "XML");
+ }
$num_exported++;
}
}
print "\nRecords exported: $num_exported\n" if ( $verbose_logging );
$num_exported++;
}
}
print "\nRecords exported: $num_exported\n" if ( $verbose_logging );
+ print {$fh} '</collection>' if (include_xml_wrapper($as_xml, $record_type));
close $fh;
return $num_exported;
}
close $fh;
return $num_exported;
}
my $records_deleted = {};
open my $fh, '>:encoding(UTF-8)', "$directory/exported_records" or die $!;
my $records_deleted = {};
open my $fh, '>:encoding(UTF-8)', "$directory/exported_records" or die $!;
+ if (include_xml_wrapper($as_xml, $record_type)) {
+ # include XML declaration and root element
+ print {$fh} '<?xml version="1.0" encoding="UTF-8"?><collection>';
+ }
my $i = 0;
foreach my $record_number (map { $_->{biblio_auth_number} } @$entries ) {
print "\r$i" unless ($i++ %100 or !$verbose_logging);
my $i = 0;
foreach my $record_number (map { $_->{biblio_auth_number} } @$entries ) {
print "\r$i" unless ($i++ %100 or !$verbose_logging);
fix_unimarc_100($marc);
}
fix_unimarc_100($marc);
}
- print {$fh} ($as_xml) ? $marc->as_xml_record(C4::Context->preference("marcflavour")) : $marc->as_usmarc();
+ my $rec;
+ if ($as_xml) {
+ $rec = $marc->as_xml_record(C4::Context->preference('marcflavour'));
+ $rec =~ s!<\?xml version="1.0" encoding="UTF-8"\?>\n!!;
+ } else {
+ $rec = $marc->as_usmarc();
+ }
+ print {$fh} $rec;
$records_deleted->{$record_number} = 1;
}
print "\nRecords exported: $i\n" if ( $verbose_logging );
$records_deleted->{$record_number} = 1;
}
print "\nRecords exported: $i\n" if ( $verbose_logging );
+ print {$fh} '</collection>' if (include_xml_wrapper($as_xml, $record_type));
close $fh;
return $records_deleted;
close $fh;
return $records_deleted;