use File::Path;
use C4::Biblio;
use C4::AuthoritiesMarc;
+use C4::Items;
#
# script that checks zebradir structure & create directories & mandatory files if needed
my $as_xml;
my $process_zebraqueue;
my $do_not_clear_zebraqueue;
-my $verbose_logging;
+my $length;
+my $where;
+my $offset;
+my $verbose_logging = 0;
my $zebraidx_log_opt = " -v none,fatal,warn ";
my $result = GetOptions(
'd:s' => \$directory,
- 'reset' => \$reset,
+ 'r|reset' => \$reset,
's' => \$skip_export,
'k' => \$keep_export,
'nosanitize' => \$nosanitize,
'x' => \$as_xml,
'y' => \$do_not_clear_zebraqueue,
'z' => \$process_zebraqueue,
- 'v' => \$verbose_logging,
+ 'where:s' => \$where,
+ 'length:i' => \$length,
+ 'offset:i' => \$offset,
+ 'v+' => \$verbose_logging,
);
# -v is for verbose, which seems backwards here because of how logging is set
# on the CLI of zebraidx. It works this way. The default is to not log much
-if ($verbose_logging) {
- $zebraidx_log_opt = '';
+if ($verbose_logging >= 2) {
+ $zebraidx_log_opt = '-v none,fatal,warn,all';
}
my $use_tempdir = 0;
sub check_zebra_dirs {
my ($base) = shift() . '/';
my $needed_repairing = 0;
- my @dirs = ( '', 'key', 'register', 'shadow' );
+ my @dirs = ( '', 'key', 'register', 'shadow', 'tmp' );
foreach my $dir (@dirs) {
my $bdir = $base . $dir;
if (! -d $bdir) {
my ($record_type, $directory, $skip_export, $process_zebraqueue, $as_xml, $noxml, $nosanitize, $do_not_clear_zebraqueue, $verbose_logging, $zebraidx_log_opt, $server_dir) = @_;
my $num_records_exported = 0;
- my $num_records_deleted = 0;
+ my $records_deleted;
my $need_reset = check_zebra_dirs($server_dir);
if ($need_reset) {
print "$0: found broken zebra server directories: forcing a rebuild\n";
if ($process_zebraqueue) {
my $entries = select_zebraqueue_records($record_type, 'deleted');
mkdir "$directory/del_$record_type" unless (-d "$directory/del_$record_type");
- $num_records_deleted = generate_deleted_marc_records($record_type, $entries, "$directory/del_$record_type", $as_xml);
+ $records_deleted = generate_deleted_marc_records($record_type, $entries, "$directory/del_$record_type", $as_xml);
mark_zebraqueue_batch_done($entries);
$entries = select_zebraqueue_records($record_type, 'updated');
mkdir "$directory/upd_$record_type" unless (-d "$directory/upd_$record_type");
$num_records_exported = export_marc_records_from_list($record_type,
- $entries, "$directory/upd_$record_type", $as_xml, $noxml);
+ $entries, "$directory/upd_$record_type", $as_xml, $noxml, $records_deleted);
mark_zebraqueue_batch_done($entries);
} else {
my $sth = select_all_records($record_type);
my $record_fmt = ($as_xml) ? 'marcxml' : 'iso2709' ;
if ($process_zebraqueue) {
do_indexing($record_type, 'delete', "$directory/del_$record_type", $reset, $noshadow, $record_fmt, $zebraidx_log_opt)
- if $num_records_deleted;
+ if %$records_deleted;
do_indexing($record_type, 'update', "$directory/upd_$record_type", $reset, $noshadow, $record_fmt, $zebraidx_log_opt)
if $num_records_exported;
} else {
}
sub select_all_authorities {
- my $sth = $dbh->prepare("SELECT authid FROM auth_header");
+ my $strsth=qq{SELECT authid FROM auth_header};
+ $strsth.=qq{ WHERE $where } if ($where);
+ $strsth.=qq{ LIMIT $length } if ($length && !$offset);
+ $strsth.=qq{ LIMIT $offset,$length } if ($length && $offset);
+ my $sth = $dbh->prepare($strsth);
$sth->execute();
return $sth;
}
sub select_all_biblios {
- my $sth = $dbh->prepare("SELECT biblionumber FROM biblioitems ORDER BY biblionumber");
+ my $strsth = qq{ SELECT biblionumber FROM biblioitems };
+ $strsth.=qq{ WHERE $where } if ($where);
+ $strsth.=qq{ LIMIT $length } if ($length && !$offset);
+ $strsth.=qq{ LIMIT $offset,$length } if ($offset);
+ my $sth = $dbh->prepare($strsth);
$sth->execute();
return $sth;
}
my ($record_type, $sth, $directory, $as_xml, $noxml, $nosanitize) = @_;
my $num_exported = 0;
- open (OUT, ">:utf8 ", "$directory/exported_records") or die $!;
+ open my $fh, '>:encoding(UTF-8) ', "$directory/exported_records" or die $!;
my $i = 0;
+ my ( $itemtag, $itemsubfield ) = GetMarcFromKohaField("items.itemnumber",'');
while (my ($record_number) = $sth->fetchrow_array) {
print "." if ( $verbose_logging );
print "\r$i" unless ($i++ %100 or !$verbose_logging);
my $marcxml = $record_type eq 'biblio'
? GetXmlBiblio( $record_number )
: GetAuthorityXML( $record_number );
+ if ($record_type eq 'biblio'){
+ my @items = GetItemsInfo($record_number);
+ if (@items){
+ my $record = MARC::Record->new;
+ $record->encoding('UTF-8');
+ my @itemsrecord;
+ foreach my $item (@items){
+ my $record = Item2Marc($item, $record_number);
+ push @itemsrecord, $record->field($itemtag);
+ }
+ $record->insert_fields_ordered(@itemsrecord);
+ my $itemsxml = $record->as_xml_record();
+ $marcxml =
+ substr($marcxml, 0, length($marcxml)-10) .
+ substr($itemsxml, index($itemsxml, "</leader>\n", 0) + 10);
+ }
+ }
if ( $marcxml ) {
- print OUT $marcxml if $marcxml;
+ print {$fh} $marcxml if $marcxml;
$num_exported++;
}
next;
# strung together with no single root element. zebraidx doesn't seem
# to care, though, at least if you're using the GRS-1 filter. It does
# care if you're using the DOM filter, which requires valid XML file(s).
- print OUT ($as_xml) ? $marc->as_xml_record() : $marc->as_usmarc();
- $num_exported++;
+ eval {
+ print {$fh} ($as_xml) ? $marc->as_xml_record(C4::Context->preference('marcflavour')) : $marc->as_usmarc();
+ $num_exported++;
+ };
+ if ($@) {
+ warn "Error exporting record $record_number ($record_type) ".($noxml ? "not XML" : "XML");
+ }
}
}
print "\nRecords exported: $num_exported\n" if ( $verbose_logging );
- close OUT;
+ close $fh;
return $num_exported;
}
sub export_marc_records_from_list {
- my ($record_type, $entries, $directory, $as_xml, $noxml) = @_;
+ my ($record_type, $entries, $directory, $as_xml, $noxml, $records_deleted) = @_;
my $num_exported = 0;
- open (OUT, ">:utf8 ", "$directory/exported_records") or die $!;
+ open my $fh, '>:encoding(UTF-8)', "$directory/exported_records" or die $!;
my $i = 0;
- my %found = ();
+
+ # Skip any deleted records. We check for this anyway, but this reduces error spam
+ my %found = %$records_deleted;
foreach my $record_number ( map { $_->{biblio_auth_number} }
grep { !$found{ $_->{biblio_auth_number} }++ }
@$entries ) {
# 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 OUT ($as_xml) ? $marc->as_xml_record() : $marc->as_usmarc();
+ print {$fh} ($as_xml) ? $marc->as_xml_record(C4::Context->preference('marcflavour')) : $marc->as_usmarc();
$num_exported++;
}
}
print "\nRecords exported: $num_exported\n" if ( $verbose_logging );
- close OUT;
+ close $fh;
return $num_exported;
}
sub generate_deleted_marc_records {
my ($record_type, $entries, $directory, $as_xml) = @_;
- my $num_exported = 0;
- open (OUT, ">:utf8 ", "$directory/exported_records") or die $!;
+ my $records_deleted = {};
+ open my $fh, '>:encoding(UTF-8)', "$directory/exported_records" or die $!;
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);
}
- print OUT ($as_xml) ? $marc->as_xml_record() : $marc->as_usmarc();
- $num_exported++;
+ print {$fh} ($as_xml) ? $marc->as_xml_record(C4::Context->preference("marcflavour")) : $marc->as_usmarc();
+
+ $records_deleted->{$record_number} = 1;
}
- print "\nRecords exported: $num_exported\n" if ( $verbose_logging );
- close OUT;
- return $num_exported;
+ print "\nRecords exported: $i\n" if ( $verbose_logging );
+ close $fh;
+ return $records_deleted;
}
if (defined $marc) {
fix_leader($marc);
- if ($record_type eq 'biblio') {
- my $succeeded = fix_biblio_ids($marc, $record_number);
- return unless $succeeded;
- } else {
+ if ($record_type eq 'authority') {
fix_authority_id($marc, $record_number);
}
if (C4::Context->preference("marcflavour") eq "UNIMARC") {
$fetch_sth->execute($record_number);
if (my ($blob) = $fetch_sth->fetchrow_array) {
$marc = MARC::Record->new_from_usmarc($blob);
- $fetch_sth->finish();
- } else {
- return; # failure to find a bib is not a problem -
- # a delete could have been done before
- # trying to process a record update
+ unless ($marc) {
+ warn "error creating MARC::Record from $blob";
+ }
}
+ # failure to find a bib is not a problem -
+ # a delete could have been done before
+ # trying to process a record update
+
+ $fetch_sth->finish();
+ return unless $marc;
} else {
- eval { $marc = GetMarcBiblio($record_number); };
- if ($@) {
+ eval { $marc = GetMarcBiblio($record_number, 1); };
+ if ($@ || !$marc) {
# here we do warn since catching an exception
# means that the bib was found but failed
# to be parsed
-v increase the amount of logging. Normally only
warnings and errors from the indexing are shown.
+ Use log level 2 (-v -v) to include all Zebra logs.
+
+ --length 1234 how many biblio you want to export
+ --offset 1243 offset you want to start to
+ example: --offset 500 --length=500 will result in a LIMIT 500,1000 (exporting 1000 records, starting by the 500th one)
+ note that the numbers are NOT related to biblionumber, that's the intended behaviour.
+ --where let you specify a WHERE query, like itemtype='BOOK'
+ or something like that
- -munge-config Deprecated option to try
+ --munge-config Deprecated option to try
to fix Zebra config files.
--help or -h show this message.
_USAGE_
# AUTHORITIES : copying mandatory files
#
unless (-f C4::Context->zebraconfig('authorityserver')->{config}) {
- open ZD,">:utf8 ",C4::Context->zebraconfig('authorityserver')->{config};
- print ZD "
+ open my $zd, '>:encoding(UTF-8)' ,C4::Context->zebraconfig('authorityserver')->{config};
+ print {$zd} "
# generated by KOHA/misc/migration_tools/rebuild_zebra.pl
profilePath:\${srcdir:-.}:$authorityserverdir/tab/:$tabdir/tab/:\${srcdir:-.}/tab/
# BIBLIOS : copying mandatory files
#
unless (-f C4::Context->zebraconfig('biblioserver')->{config}) {
- open ZD,">:utf8 ",C4::Context->zebraconfig('biblioserver')->{config};
- print ZD "
+ open my $zd, '>:encoding(UTF-8)', C4::Context->zebraconfig('biblioserver')->{config};
+ print {$zd} "
# generated by KOHA/misc/migrtion_tools/rebuild_zebra.pl
profilePath:\${srcdir:-.}:$biblioserverdir/tab/:$tabdir/tab/:\${srcdir:-.}/tab/