#!/usr/bin/perl
-use strict;
-#use warnings; FIXME - Bug 2505
+# This file is part of Koha.
+#
+# Koha is free software; you can redistribute it and/or modify it
+# under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# Koha is distributed in the hope that it will be useful, but
+# WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with Koha; if not, see <http://www.gnu.org/licenses>.
+
+use Modern::Perl;
use C4::Context;
use Getopt::Long;
+use Fcntl qw(:flock);
use File::Temp qw/ tempdir /;
use File::Path;
use C4::Biblio;
use C4::AuthoritiesMarc;
use C4::Items;
use Koha::RecordProcessor;
+use Koha::Caches;
use XML::LibXML;
+use constant LOCK_FILENAME => 'rebuild..LCK';
+
# script that checks zebradir structure & create directories & mandatory files if needed
#
#
my $reset;
my $biblios;
my $authorities;
-my $noxml;
+my $as_xml;
my $noshadow;
-my $do_munge;
my $want_help;
-my $as_xml;
my $process_zebraqueue;
+my $process_zebraqueue_skip_deletes;
my $do_not_clear_zebraqueue;
my $length;
my $where;
my $offset;
my $run_as_root;
my $run_user = (getpwuid($<))[0];
+my $wait_for_lock = 0;
+my $use_flock;
+my $table = 'biblioitems';
+my $is_memcached = Koha::Caches->get_instance->memcached_cache;
my $verbose_logging = 0;
my $zebraidx_log_opt = " -v none,fatal,warn ";
'I|skip-index' => \$skip_index,
'nosanitize' => \$nosanitize,
'b' => \$biblios,
- 'noxml' => \$noxml,
'w' => \$noshadow,
- 'munge-config' => \$do_munge,
'a' => \$authorities,
'h|help' => \$want_help,
'x' => \$as_xml,
'y' => \$do_not_clear_zebraqueue,
'z' => \$process_zebraqueue,
- 'where:s' => \$where,
- 'length:i' => \$length,
+ 'skip-deletes' => \$process_zebraqueue_skip_deletes,
+ 'where:s' => \$where,
+ 'length:i' => \$length,
'offset:i' => \$offset,
- 'v+' => \$verbose_logging,
- 'run-as-root' => \$run_as_root,
+ 'v+' => \$verbose_logging,
+ 'run-as-root' => \$run_as_root,
+ 'wait-for-lock' => \$wait_for_lock,
+ 't|table:s' => \$table,
);
if (not $result or $want_help) {
exit 0;
}
+if ( $as_xml ) {
+ warn "Warning: You passed -x which is already the default and is now deprecated\n";
+ undef $as_xml; # Should not be used later
+}
+
if( not defined $run_as_root and $run_user eq 'root') {
my $msg = "Warning: You are running this script as the user 'root'.\n";
$msg .= "If this is intentional you must explicitly specify this using the -run-as-root switch\n";
die $msg;
}
-if (not $biblios and not $authorities) {
- my $msg = "Must specify -b or -a to reindex bibs or authorities\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";
- die $msg;
-}
-
if ($process_zebraqueue and ($skip_export or $reset)) {
my $msg = "Cannot specify -r or -s if -z is specified\n";
$msg .= "Please do '$0 --help' to see usage.\n";
die $msg;
}
-if ($reset) {
- $noshadow = 1;
-}
-
-if ($noshadow) {
- $noshadow = ' -n ';
-}
-
if ($daemon_mode) {
# incompatible flags handled above: help, reset, and do_not_clear_zebraqueue
if ($skip_export or $keep_export or $skip_index or
$msg .= "Please do '$0 --help' to see usage.\n";
die $msg;
}
+ unless ($is_memcached) {
+ warn "Warning: script running in daemon mode, without recommended caching system (memcached).\n";
+ }
$authorities = 1;
$biblios = 1;
$process_zebraqueue = 1;
}
+if (not $biblios and not $authorities) {
+ my $msg = "Must specify -b or -a to reindex bibs or authorities\n";
+ $msg .= "Please do '$0 --help' to see usage.\n";
+ die $msg;
+}
+
+our @tables_allowed_for_select = ( 'biblioitems', 'items', 'biblio', 'biblio_metadata' );
+unless ( grep { /^$table$/ } @tables_allowed_for_select ) {
+ die "Cannot specify -t|--table with value '$table'. Only "
+ . ( join ', ', @tables_allowed_for_select )
+ . " are allowed.";
+}
+
+
# -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 >= 2) {
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,$biblioitemnumbertagsubfield) = &GetMarcFromKohaField("biblioitems.biblioitemnumber","");
+my ($biblionumbertagfield,$biblionumbertagsubfield) = C4::Biblio::GetMarcFromKohaField("biblio.biblionumber","");
+my ($biblioitemnumbertagfield,$biblioitemnumbertagsubfield) = C4::Biblio::GetMarcFromKohaField("biblioitems.biblioitemnumber","");
+
+my $marcxml_open = q{<?xml version="1.0" encoding="UTF-8"?>
+<collection xmlns="http://www.loc.gov/MARC21/slim">
+};
+
+my $marcxml_close = q{
+</collection>
+};
+
+# Protect again simultaneous update of the zebra index by using a lock file.
+# Create our own lock directory if it is missing. This should be created
+# by koha-zebra-ctl.sh or at system installation. If the desired directory
+# does not exist and cannot be created, we fall back on /tmp - which will
+# always work.
+
+my ($lockfile, $LockFH);
+foreach (
+ C4::Context->config("zebra_lockdir"),
+ '/var/lock/zebra_' . C4::Context->config('database'),
+ '/tmp/zebra_' . C4::Context->config('database')
+) {
+ #we try three possibilities (we really want to lock :)
+ next if !$_;
+ ($LockFH, $lockfile) = _create_lockfile($_.'/rebuild');
+ last if defined $LockFH;
+}
+if( !defined $LockFH ) {
+ print "WARNING: Could not create lock file $lockfile: $!\n";
+ print "Please check your koha-conf.xml for ZEBRA_LOCKDIR.\n";
+ print "Verify file permissions for it too.\n";
+ $use_flock = 0; # we disable file locking now and will continue
+ # without it
+ # note that this mimics old behavior (before we used
+ # the lockfile)
+};
if ( $verbose_logging ) {
print "Zebra configuration information\n";
print "Zebra biblio directory = $biblioserverdir\n";
print "Zebra authorities directory = $authorityserverdir\n";
print "Koha directory = $kohadir\n";
+ print "Lockfile = $lockfile\n" if $lockfile;
print "BIBLIONUMBER in : $biblionumbertagfield\$$biblionumbertagsubfield\n";
print "BIBLIOITEMNUMBER in : $biblioitemnumbertagfield\$$biblioitemnumbertagsubfield\n";
print "================================\n";
}
-if ($do_munge) {
- munge_config();
-}
-
my $tester = XML::LibXML->new();
-
+my $dbh;
+
+# The main work is done here by calling do_one_pass(). We have added locking
+# avoid race conditions between full rebuilds and incremental updates either from
+# daemon mode or periodic invocation from cron. The race can lead to an updated
+# record being overwritten by a rebuild if the update is applied after the export
+# by the rebuild and before the rebuild finishes (more likely to affect large
+# catalogs).
+#
+# We have chosen to exit immediately by default if we cannot obtain the lock
+# to prevent the potential for a infinite backlog from cron invocations, but an
+# option (wait-for-lock) is provided to let the program wait for the lock.
+# See http://bugs.koha-community.org/bugzilla3/show_bug.cgi?id=11078 for details.
if ($daemon_mode) {
while (1) {
- do_one_pass() if ( zebraqueue_not_empty() );
+ # For incremental updates, skip the update if the updates are locked
+ if (_flock($LockFH, LOCK_EX|LOCK_NB)) {
+ eval {
+ $dbh = C4::Context->dbh;
+ if( zebraqueue_not_empty() ) {
+ Koha::Caches->flush_L1_caches() if $is_memcached;
+ do_one_pass();
+ }
+ };
+ if ($@ && $verbose_logging) {
+ warn "Warning : $@\n";
+ }
+ _flock($LockFH, LOCK_UN);
+ }
sleep $daemon_sleep;
}
} else {
- do_one_pass();
+ # all one-off invocations
+ my $lock_mode = ($wait_for_lock) ? LOCK_EX : LOCK_EX|LOCK_NB;
+ if (_flock($LockFH, $lock_mode)) {
+ $dbh = C4::Context->dbh;
+ do_one_pass();
+ _flock($LockFH, LOCK_UN);
+ } else {
+ print "Skipping rebuild/update because flock failed on $lockfile: $!\n";
+ }
}
print "parameter";
}
print "\n";
- print "if you just want to rebuild zebra after changing the record.abs\n";
- print "or another zebra config file\n";
+ print "if you just want to rebuild zebra after changing zebra config files\n";
} else {
unless ($use_tempdir) {
# if we're using a temporary directory
sub do_one_pass {
if ($authorities) {
- index_records('authority', $directory, $skip_export, $skip_index, $process_zebraqueue, $as_xml, $noxml, $nosanitize, $do_not_clear_zebraqueue, $verbose_logging, $zebraidx_log_opt, $authorityserverdir);
+ index_records('authority', $directory, $skip_export, $skip_index, $process_zebraqueue, $nosanitize, $do_not_clear_zebraqueue, $verbose_logging, $zebraidx_log_opt, $authorityserverdir);
} else {
print "skipping authorities\n" if ( $verbose_logging );
}
if ($biblios) {
- index_records('biblio', $directory, $skip_export, $skip_index, $process_zebraqueue, $as_xml, $noxml, $nosanitize, $do_not_clear_zebraqueue, $verbose_logging, $zebraidx_log_opt, $biblioserverdir);
+ index_records('biblio', $directory, $skip_export, $skip_index, $process_zebraqueue, $nosanitize, $do_not_clear_zebraqueue, $verbose_logging, $zebraidx_log_opt, $biblioserverdir);
} else {
print "skipping biblios\n" if ( $verbose_logging );
}
$where_str = 'server = "authorityserver" AND done = 0;';
}
my $query =
- $dbh->prepare( 'SELECT COUNT(*) FROM zebraqueue WHERE ' . $where_str );
+ $dbh->prepare('SELECT COUNT(*) FROM zebraqueue WHERE ' . $where_str );
$query->execute;
my $count = $query->fetchrow_arrayref->[0];
} # ---------- end of subroutine check_zebra_dirs ----------
sub index_records {
- my ($record_type, $directory, $skip_export, $skip_index, $process_zebraqueue, $as_xml, $noxml, $nosanitize, $do_not_clear_zebraqueue, $verbose_logging, $zebraidx_log_opt, $server_dir) = @_;
+ my ($record_type, $directory, $skip_export, $skip_index, $process_zebraqueue, $nosanitize, $do_not_clear_zebraqueue, $verbose_logging, $zebraidx_log_opt, $server_dir) = @_;
my $num_records_exported = 0;
- my $records_deleted;
+ my $records_deleted = {};
my $need_reset = check_zebra_dirs($server_dir);
if ($need_reset) {
print "$0: found broken zebra server directories: forcing a rebuild\n";
mkdir "$directory" unless (-d $directory);
mkdir "$directory/$record_type" unless (-d "$directory/$record_type");
if ($process_zebraqueue) {
- my $entries = select_zebraqueue_records($record_type, 'deleted');
- mkdir "$directory/del_$record_type" unless (-d "$directory/del_$record_type");
- $records_deleted = generate_deleted_marc_records($record_type, $entries, "$directory/del_$record_type", $as_xml);
- mark_zebraqueue_batch_done($entries);
+ my $entries;
+
+ unless ( $process_zebraqueue_skip_deletes ) {
+ $entries = select_zebraqueue_records($record_type, 'deleted');
+ mkdir "$directory/del_$record_type" unless (-d "$directory/del_$record_type");
+ $records_deleted = generate_deleted_marc_records($record_type, $entries, "$directory/del_$record_type");
+ mark_zebraqueue_batch_done($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, $records_deleted);
+ $num_records_exported = export_marc_records_from_list($record_type,$entries, "$directory/upd_$record_type", $records_deleted);
mark_zebraqueue_batch_done($entries);
+
} else {
my $sth = select_all_records($record_type);
- $num_records_exported = export_marc_records_from_sth($record_type, $sth, "$directory/$record_type", $as_xml, $noxml, $nosanitize);
+ $num_records_exported = export_marc_records_from_sth($record_type, $sth, "$directory/$record_type", $nosanitize);
unless ($do_not_clear_zebraqueue) {
mark_all_zebraqueue_done($record_type);
}
print "REINDEXING zebra\n";
print "====================\n";
}
- my $record_fmt = ($as_xml) ? 'marcxml' : 'iso2709' ;
+ my $record_fmt = 'marcxml';
if ($process_zebraqueue) {
do_indexing($record_type, 'adelete', "$directory/del_$record_type", $reset, $noshadow, $record_fmt, $zebraidx_log_opt)
if %$records_deleted;
}
sub select_all_biblios {
- my $strsth = qq{ SELECT biblionumber FROM biblioitems };
+ $table = 'biblioitems'
+ unless grep { /^$table$/ } @tables_allowed_for_select;
+ my $strsth = qq{ SELECT DISTINCT biblionumber FROM $table };
$strsth.=qq{ WHERE $where } if ($where);
$strsth.=qq{ LIMIT $length } if ($length && !$offset);
$strsth.=qq{ LIMIT $offset,$length } if ($offset);
return $sth;
}
-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, $nosanitize) = @_;
+ my ($record_type, $sth, $directory, $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>';
- }
+
+ print {$fh} $marcxml_open;
+
my $i = 0;
- my ( $itemtag, $itemsubfield ) = GetMarcFromKohaField("items.itemnumber",'');
+ my ( $itemtag, $itemsubfield ) = C4::Biblio::GetMarcFromKohaField("items.itemnumber",'');
while (my ($record_number) = $sth->fetchrow_array) {
print "." if ( $verbose_logging );
print "\r$i" unless ($i++ %100 or !$verbose_logging);
}
next;
}
- my ($marc) = get_corrected_marc_record($record_type, $record_number, $noxml);
+ my ($marc) = get_corrected_marc_record($record_type, $record_number);
if (defined $marc) {
eval {
- my $rec;
- if ($as_xml) {
- $rec = $marc->as_xml_record(C4::Context->preference('marcflavour'));
- eval {
- my $doc = $tester->parse_string($rec);
- };
- if ($@) {
- die "invalid XML: $@";
- }
- $rec =~ s!<\?xml version="1.0" encoding="UTF-8"\?>\n!!;
- } else {
- $rec = $marc->as_usmarc();
+ my $rec = $marc->as_xml_record(C4::Context->preference('marcflavour'));
+ eval {
+ my $doc = $tester->parse_string($rec);
+ };
+ if ($@) {
+ die "invalid XML: $@";
}
+ $rec =~ s!<\?xml version="1.0" encoding="UTF-8"\?>\n!!;
print {$fh} $rec;
$num_exported++;
};
if ($@) {
- warn "Error exporting record $record_number ($record_type) ".($noxml ? "not XML" : "XML");
+ warn "Error exporting record $record_number ($record_type) XML";
warn "... specific error is $@" if $verbose_logging;
}
}
}
print "\nRecords exported: $num_exported\n" if ( $verbose_logging );
- print {$fh} '</collection>' if (include_xml_wrapper($as_xml, $record_type));
+ print {$fh} $marcxml_close;
+
close $fh;
return $num_exported;
}
sub export_marc_records_from_list {
- my ($record_type, $entries, $directory, $as_xml, $noxml, $records_deleted) = @_;
+ my ($record_type, $entries, $directory, $records_deleted) = @_;
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>';
- }
+
+ print {$fh} $marcxml_open;
+
my $i = 0;
# Skip any deleted records. We check for this anyway, but this reduces error spam
@$entries ) {
print "." if ( $verbose_logging );
print "\r$i" unless ($i++ %100 or !$verbose_logging);
- my ($marc) = get_corrected_marc_record($record_type, $record_number, $noxml);
+ my ($marc) = get_corrected_marc_record($record_type, $record_number);
if (defined $marc) {
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();
- }
+ my $rec = $marc->as_xml_record(C4::Context->preference('marcflavour'));
+ $rec =~ s!<\?xml version="1.0" encoding="UTF-8"\?>\n!!;
print {$fh} $rec;
$num_exported++;
};
if ($@) {
- warn "Error exporting record $record_number ($record_type) ".($noxml ? "not XML" : "XML");
+ warn "Error exporting record $record_number ($record_type) XML";
}
}
}
print "\nRecords exported: $num_exported\n" if ( $verbose_logging );
- print {$fh} '</collection>' if (include_xml_wrapper($as_xml, $record_type));
+
+ print {$fh} $marcxml_close;
+
close $fh;
return $num_exported;
}
sub generate_deleted_marc_records {
- my ($record_type, $entries, $directory, $as_xml) = @_;
+
+ my ($record_type, $entries, $directory) = @_;
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>';
- }
+
+ print {$fh} $marcxml_open;
+
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);
}
- 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();
- }
+ my $rec = $marc->as_xml_record(C4::Context->preference('marcflavour'));
+ # Remove the record's XML header
+ $rec =~ s!<\?xml version="1.0" encoding="UTF-8"\?>\n!!;
print {$fh} $rec;
$records_deleted->{$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 $records_deleted;
+ print {$fh} $marcxml_close;
+ close $fh;
+ return $records_deleted;
}
sub get_corrected_marc_record {
- my ($record_type, $record_number, $noxml) = @_;
+ my ( $record_type, $record_number ) = @_;
- my $marc = get_raw_marc_record($record_type, $record_number, $noxml);
+ my $marc = get_raw_marc_record( $record_type, $record_number );
- if (defined $marc) {
+ if ( defined $marc ) {
fix_leader($marc);
- if ($record_type eq 'authority') {
- fix_authority_id($marc, $record_number);
- } elsif ($record_type eq 'biblio' && C4::Context->preference('IncludeSeeFromInSearches')) {
- my $normalizer = Koha::RecordProcessor->new( { filters => 'EmbedSeeFromHeadings' } );
+ if ( $record_type eq 'authority' ) {
+ fix_authority_id( $marc, $record_number );
+ }
+ elsif ( $record_type eq 'biblio' ) {
+
+ my @filters;
+ push @filters, 'EmbedItemsAvailability';
+ push @filters, 'EmbedSeeFromHeadings'
+ if C4::Context->preference('IncludeSeeFromInSearches');
+
+ my $normalizer = Koha::RecordProcessor->new( { filters => \@filters } );
$marc = $normalizer->process($marc);
}
- if (C4::Context->preference("marcflavour") eq "UNIMARC") {
+ if ( C4::Context->preference("marcflavour") eq "UNIMARC" ) {
fix_unimarc_100($marc);
}
}
}
sub get_raw_marc_record {
- my ($record_type, $record_number, $noxml) = @_;
+ my ($record_type, $record_number) = @_;
my $marc;
if ($record_type eq 'biblio') {
- if ($noxml) {
- my $fetch_sth = $dbh->prepare_cached("SELECT marc FROM biblioitems WHERE biblionumber = ?");
- $fetch_sth->execute($record_number);
- if (my ($blob) = $fetch_sth->fetchrow_array) {
- $marc = MARC::Record->new_from_usmarc($blob);
- 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, 1); };
- if ($@ || !$marc) {
- # here we do warn since catching an exception
- # means that the bib was found but failed
- # to be parsed
- warn "error retrieving biblio $record_number";
- return;
- }
+ eval { $marc = C4::Biblio::GetMarcBiblio({ biblionumber => $record_number, embed_items => 1 }); };
+ if ($@ || !$marc) {
+ # here we do warn since catching an exception
+ # means that the bib was found but failed
+ # to be parsed
+ warn "error retrieving biblio $record_number";
+ return;
}
} else {
eval { $marc = GetAuthority($record_number); };
my $marc = shift;
my $string;
- if ( length($marc->subfield( 100, "a" )) == 36 ) {
+ my $length_100a = length($marc->subfield( 100, "a" ));
+ if ( $length_100a and $length_100a == 36 ) {
$string = $marc->subfield( 100, "a" );
my $f100 = $marc->field(100);
$marc->delete_field($f100);
$string = sprintf( "%-*s", 35, $string );
}
substr( $string, 22, 6, "frey50" );
- unless ( length($marc->subfield( 100, "a" )) == 36 ) {
+ $length_100a = length($marc->subfield( 100, "a" ));
+ unless ( $length_100a and $length_100a == 36 ) {
$marc->delete_field($marc->field(100));
$marc->insert_grouped_field(MARC::Field->new( 100, "", "", "a" => $string ));
}
my $zebra_config = C4::Context->zebraconfig($zebra_server)->{'config'};
my $zebra_db_dir = C4::Context->zebraconfig($zebra_server)->{'directory'};
+ $noshadow //= '';
+
+ if ($noshadow or $reset_index) {
+ $noshadow = '-n';
+ }
+
system("zebraidx -c $zebra_config $zebraidx_log_opt -g $record_format -d $zebra_db_name init") if $reset_index;
system("zebraidx -c $zebra_config $zebraidx_log_opt $noshadow -g $record_format -d $zebra_db_name $op $record_dir");
system("zebraidx -c $zebra_config $zebraidx_log_opt -g $record_format -d $zebra_db_name commit") unless $noshadow;
+}
+
+sub _flock {
+ # test if flock is present; if so, use it; if not, return true
+ # op refers to the official flock operations including LOCK_EX,
+ # LOCK_UN, etc.
+ # combining LOCK_EX with LOCK_NB returns immediately
+ my ($fh, $op)= @_;
+ if( !defined($use_flock) ) {
+ #check if flock is present; if not, you will have a fatal error
+ my $lock_acquired = eval { flock($fh, $op) };
+ # assuming that $fh and $op are fine(..), an undef $lock_acquired
+ # means no flock
+ $use_flock = defined($lock_acquired) ? 1 : 0;
+ print "Warning: flock could not be used!\n" if $verbose_logging && !$use_flock;
+ return 1 if !$use_flock;
+ return $lock_acquired;
+ } else {
+ return 1 if !$use_flock;
+ return flock($fh, $op);
+ }
+}
+sub _create_lockfile { #returns undef on failure
+ my $dir= shift;
+ unless (-d $dir) {
+ eval { mkpath($dir, 0, oct(755)) };
+ return if $@;
+ }
+ return if !open my $fh, q{>}, $dir.'/'.LOCK_FILENAME;
+ return ( $fh, $dir.'/'.LOCK_FILENAME );
}
sub print_usage {
table. Cannot be used with -r
or -s.
+ --skip-deletes only select record updates, not record
+ deletions, to avoid potential excessive
+ I/O when zebraidx processes deletions.
+ If this option is used for normal indexing,
+ a cronjob should be set up to run
+ rebuild_zebra.pl -z without --skip-deletes
+ during off hours.
+ Only effective with -z.
+
-r clear Zebra index before
adding records to index. Implies -w.
already exported the records
in a previous run.
- -noxml index from ISO MARC blob
- instead of MARC XML. This
- option is recommended only
- for advanced user.
-
- -x export and index as xml instead of is02709 (biblios only).
- use this if you might have records > 99,999 chars,
-
-nosanitize export biblio/authority records directly from DB marcxml
field without sanitizing records. It speed up
dump process but could fail if DB contains badly
--where let you specify a WHERE query, like itemtype='BOOK'
or something like that
- --munge-config Deprecated option to try
- to fix Zebra config files.
-
--run-as-root explicitily allow script to run as 'root' user
- --help or -h show this message.
-_USAGE_
-}
-
-# FIXME: the following routines are deprecated and
-# will be removed once it is determined whether
-# a script to fix Zebra configuration files is
-# actually needed.
-sub munge_config {
-#
-# creating zebra-biblios.cfg depending on system
-#
-
-# getting zebraidx directory
-my $zebraidxdir;
-foreach (qw(/usr/local/bin/zebraidx
- /opt/bin/zebraidx
- /usr/bin/zebraidx
- )) {
- if ( -f $_ ) {
- $zebraidxdir=$_;
- }
-}
-
-unless ($zebraidxdir) {
- print qq|
- ERROR: could not find zebraidx directory
- ERROR: Either zebra is not installed,
- ERROR: or it's in a directory I don't checked.
- ERROR: do a which zebraidx and edit this file to add the result you get
-|;
- exit;
-}
-$zebraidxdir =~ s/\/bin\/.*//;
-print "Info : zebra is in $zebraidxdir \n";
-
-# getting modules directory
-my $modulesdir;
-foreach (qw(/usr/local/lib/idzebra-2.0/modules/mod-grs-xml.so
- /usr/local/lib/idzebra/modules/mod-grs-xml.so
- /usr/lib/idzebra/modules/mod-grs-xml.so
- /usr/lib/idzebra-2.0/modules/mod-grs-xml.so
- )) {
- if ( -f $_ ) {
- $modulesdir=$_;
- }
-}
-
-unless ($modulesdir) {
- print qq|
- ERROR: could not find mod-grs-xml.so directory
- ERROR: Either zebra is not properly compiled (libxml2 is not setup and you don t have mod-grs-xml.so,
- ERROR: or it's in a directory I don't checked.
- ERROR: find where mod-grs-xml.so is and edit this file to add the result you get
-|;
- exit;
-}
-$modulesdir =~ s/\/modules\/.*//;
-print "Info: zebra modules dir : $modulesdir\n";
-
-# getting tab directory
-my $tabdir;
-foreach (qw(/usr/local/share/idzebra/tab/explain.att
- /usr/local/share/idzebra-2.0/tab/explain.att
- /usr/share/idzebra/tab/explain.att
- /usr/share/idzebra-2.0/tab/explain.att
- )) {
- if ( -f $_ ) {
- $tabdir=$_;
- }
-}
-
-unless ($tabdir) {
- print qq|
- ERROR: could not find explain.att directory
- ERROR: Either zebra is not properly compiled,
- ERROR: or it's in a directory I don't checked.
- ERROR: find where explain.att is and edit this file to add the result you get
-|;
- exit;
-}
-$tabdir =~ s/\/tab\/.*//;
-print "Info: tab dir : $tabdir\n";
-
-#
-# AUTHORITIES creating directory structure
-#
-my $created_dir_or_file = 0;
-if ($authorities) {
- if ( $verbose_logging ) {
- print "====================\n";
- print "checking directories & files for authorities\n";
- print "====================\n";
- }
- unless (-d "$authorityserverdir") {
- system("mkdir -p $authorityserverdir");
- print "Info: created $authorityserverdir\n";
- $created_dir_or_file++;
- }
- unless (-d "$authorityserverdir/lock") {
- mkdir "$authorityserverdir/lock";
- print "Info: created $authorityserverdir/lock\n";
- $created_dir_or_file++;
- }
- unless (-d "$authorityserverdir/register") {
- mkdir "$authorityserverdir/register";
- print "Info: created $authorityserverdir/register\n";
- $created_dir_or_file++;
- }
- unless (-d "$authorityserverdir/shadow") {
- mkdir "$authorityserverdir/shadow";
- print "Info: created $authorityserverdir/shadow\n";
- $created_dir_or_file++;
- }
- unless (-d "$authorityserverdir/tab") {
- mkdir "$authorityserverdir/tab";
- print "Info: created $authorityserverdir/tab\n";
- $created_dir_or_file++;
- }
- unless (-d "$authorityserverdir/key") {
- mkdir "$authorityserverdir/key";
- print "Info: created $authorityserverdir/key\n";
- $created_dir_or_file++;
- }
-
- unless (-d "$authorityserverdir/etc") {
- mkdir "$authorityserverdir/etc";
- print "Info: created $authorityserverdir/etc\n";
- $created_dir_or_file++;
- }
+ --wait-for-lock when not running in daemon mode, the default
+ behavior is to abort a rebuild if the rebuild
+ lock is busy. This option will cause the program
+ to wait for the lock to free and then continue
+ processing the rebuild request,
- #
- # AUTHORITIES : copying mandatory files
- #
- # the record model, depending on marc flavour
- unless (-f "$authorityserverdir/tab/record.abs") {
- if (C4::Context->preference("marcflavour") eq "UNIMARC") {
- system("cp -f $kohadir/etc/zebradb/marc_defs/unimarc/authorities/record.abs $authorityserverdir/tab/record.abs");
- print "Info: copied record.abs for UNIMARC\n";
- } else {
- system("cp -f $kohadir/etc/zebradb/marc_defs/marc21/authorities/record.abs $authorityserverdir/tab/record.abs");
- print "Info: copied record.abs for USMARC\n";
- }
- $created_dir_or_file++;
- }
- unless (-f "$authorityserverdir/tab/sort-string-utf.chr") {
- system("cp -f $kohadir/etc/zebradb/lang_defs/fr/sort-string-utf.chr $authorityserverdir/tab/sort-string-utf.chr");
- print "Info: copied sort-string-utf.chr\n";
- $created_dir_or_file++;
- }
- unless (-f "$authorityserverdir/tab/word-phrase-utf.chr") {
- system("cp -f $kohadir/etc/zebradb/lang_defs/fr/sort-string-utf.chr $authorityserverdir/tab/word-phrase-utf.chr");
- print "Info: copied word-phase-utf.chr\n";
- $created_dir_or_file++;
- }
- unless (-f "$authorityserverdir/tab/auth1.att") {
- system("cp -f $kohadir/etc/zebradb/authorities/etc/bib1.att $authorityserverdir/tab/auth1.att");
- print "Info: copied auth1.att\n";
- $created_dir_or_file++;
- }
- unless (-f "$authorityserverdir/tab/default.idx") {
- system("cp -f $kohadir/etc/zebradb/etc/default.idx $authorityserverdir/tab/default.idx");
- print "Info: copied default.idx\n";
- $created_dir_or_file++;
- }
+ --table specify a table (can be items, biblioitems, biblio, biblio_metadata) to retrieve biblionumber to index.
+ biblioitems is the default value.
- unless (-f "$authorityserverdir/etc/ccl.properties") {
-# system("cp -f $kohadir/etc/zebradb/ccl.properties ".C4::Context->zebraconfig('authorityserver')->{ccl2rpn});
- system("cp -f $kohadir/etc/zebradb/ccl.properties $authorityserverdir/etc/ccl.properties");
- print "Info: copied ccl.properties\n";
- $created_dir_or_file++;
- }
- unless (-f "$authorityserverdir/etc/pqf.properties") {
-# system("cp -f $kohadir/etc/zebradb/pqf.properties ".C4::Context->zebraconfig('authorityserver')->{ccl2rpn});
- system("cp -f $kohadir/etc/zebradb/pqf.properties $authorityserverdir/etc/pqf.properties");
- print "Info: copied pqf.properties\n";
- $created_dir_or_file++;
- }
-
- #
- # AUTHORITIES : copying mandatory files
- #
- unless (-f C4::Context->zebraconfig('authorityserver')->{config}) {
- 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/
-
-encoding: UTF-8
-# Files that describe the attribute sets supported.
-attset: auth1.att
-attset: explain.att
-attset: gils.att
-
-modulePath:$modulesdir/modules/
-# Specify record type
-iso2709.recordType:grs.marcxml.record
-recordType:grs.xml
-recordId: (auth1,Local-Number)
-storeKeys:1
-storeData:1
-
-
-# Lock File Area
-lockDir: $authorityserverdir/lock
-perm.anonymous:r
-perm.kohaadmin:rw
-register: $authorityserverdir/register:4G
-shadow: $authorityserverdir/shadow:4G
-
-# Temp File area for result sets
-setTmpDir: $authorityserverdir/tmp
-
-# Temp File area for index program
-keyTmpDir: $authorityserverdir/key
-
-# Approx. Memory usage during indexing
-memMax: 40M
-rank:rank-1
- ";
- print "Info: creating zebra-authorities.cfg\n";
- $created_dir_or_file++;
- }
-
- if ($created_dir_or_file) {
- print "Info: created : $created_dir_or_file directories & files\n";
- } else {
- print "Info: file & directories OK\n";
- }
-
-}
-if ($biblios) {
- if ( $verbose_logging ) {
- print "====================\n";
- print "checking directories & files for biblios\n";
- print "====================\n";
- }
-
- #
- # BIBLIOS : creating directory structure
- #
- unless (-d "$biblioserverdir") {
- system("mkdir -p $biblioserverdir");
- print "Info: created $biblioserverdir\n";
- $created_dir_or_file++;
- }
- unless (-d "$biblioserverdir/lock") {
- mkdir "$biblioserverdir/lock";
- print "Info: created $biblioserverdir/lock\n";
- $created_dir_or_file++;
- }
- unless (-d "$biblioserverdir/register") {
- mkdir "$biblioserverdir/register";
- print "Info: created $biblioserverdir/register\n";
- $created_dir_or_file++;
- }
- unless (-d "$biblioserverdir/shadow") {
- mkdir "$biblioserverdir/shadow";
- print "Info: created $biblioserverdir/shadow\n";
- $created_dir_or_file++;
- }
- unless (-d "$biblioserverdir/tab") {
- mkdir "$biblioserverdir/tab";
- print "Info: created $biblioserverdir/tab\n";
- $created_dir_or_file++;
- }
- unless (-d "$biblioserverdir/key") {
- mkdir "$biblioserverdir/key";
- print "Info: created $biblioserverdir/key\n";
- $created_dir_or_file++;
- }
- unless (-d "$biblioserverdir/etc") {
- mkdir "$biblioserverdir/etc";
- print "Info: created $biblioserverdir/etc\n";
- $created_dir_or_file++;
- }
-
- #
- # BIBLIOS : copying mandatory files
- #
- # the record model, depending on marc flavour
- unless (-f "$biblioserverdir/tab/record.abs") {
- if (C4::Context->preference("marcflavour") eq "UNIMARC") {
- system("cp -f $kohadir/etc/zebradb/marc_defs/unimarc/biblios/record.abs $biblioserverdir/tab/record.abs");
- print "Info: copied record.abs for UNIMARC\n";
- } else {
- system("cp -f $kohadir/etc/zebradb/marc_defs/marc21/biblios/record.abs $biblioserverdir/tab/record.abs");
- print "Info: copied record.abs for USMARC\n";
- }
- $created_dir_or_file++;
- }
- unless (-f "$biblioserverdir/tab/sort-string-utf.chr") {
- system("cp -f $kohadir/etc/zebradb/lang_defs/fr/sort-string-utf.chr $biblioserverdir/tab/sort-string-utf.chr");
- print "Info: copied sort-string-utf.chr\n";
- $created_dir_or_file++;
- }
- unless (-f "$biblioserverdir/tab/word-phrase-utf.chr") {
- system("cp -f $kohadir/etc/zebradb/lang_defs/fr/sort-string-utf.chr $biblioserverdir/tab/word-phrase-utf.chr");
- print "Info: copied word-phase-utf.chr\n";
- $created_dir_or_file++;
- }
- unless (-f "$biblioserverdir/tab/bib1.att") {
- system("cp -f $kohadir/etc/zebradb/biblios/etc/bib1.att $biblioserverdir/tab/bib1.att");
- print "Info: copied bib1.att\n";
- $created_dir_or_file++;
- }
- unless (-f "$biblioserverdir/tab/default.idx") {
- system("cp -f $kohadir/etc/zebradb/etc/default.idx $biblioserverdir/tab/default.idx");
- print "Info: copied default.idx\n";
- $created_dir_or_file++;
- }
- unless (-f "$biblioserverdir/etc/ccl.properties") {
-# system("cp -f $kohadir/etc/zebradb/ccl.properties ".C4::Context->zebraconfig('biblioserver')->{ccl2rpn});
- system("cp -f $kohadir/etc/zebradb/ccl.properties $biblioserverdir/etc/ccl.properties");
- print "Info: copied ccl.properties\n";
- $created_dir_or_file++;
- }
- unless (-f "$biblioserverdir/etc/pqf.properties") {
-# system("cp -f $kohadir/etc/zebradb/pqf.properties ".C4::Context->zebraconfig('biblioserver')->{ccl2rpn});
- system("cp -f $kohadir/etc/zebradb/pqf.properties $biblioserverdir/etc/pqf.properties");
- print "Info: copied pqf.properties\n";
- $created_dir_or_file++;
- }
-
- #
- # BIBLIOS : copying mandatory files
- #
- unless (-f C4::Context->zebraconfig('biblioserver')->{config}) {
- 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/
-
-encoding: UTF-8
-# Files that describe the attribute sets supported.
-attset:bib1.att
-attset:explain.att
-attset:gils.att
-
-modulePath:$modulesdir/modules/
-# Specify record type
-iso2709.recordType:grs.marcxml.record
-recordType:grs.xml
-recordId: (bib1,Local-Number)
-storeKeys:1
-storeData:1
-
-
-# Lock File Area
-lockDir: $biblioserverdir/lock
-perm.anonymous:r
-perm.kohaadmin:rw
-register: $biblioserverdir/register:4G
-shadow: $biblioserverdir/shadow:4G
-
-# Temp File area for result sets
-setTmpDir: $biblioserverdir/tmp
-
-# Temp File area for index program
-keyTmpDir: $biblioserverdir/key
-
-# Approx. Memory usage during indexing
-memMax: 40M
-rank:rank-1
- ";
- print "Info: creating zebra-biblios.cfg\n";
- $created_dir_or_file++;
- }
-
- if ($created_dir_or_file) {
- print "Info: created : $created_dir_or_file directories & files\n";
- } else {
- print "Info: file & directories OK\n";
- }
-
-}
+ --help or -h show this message.
+_USAGE_
}