X-Git-Url: http://koha-dev.rot13.org:8081/gitweb/?a=blobdiff_plain;f=misc%2Fmigration_tools%2Frebuild_zebra.pl;h=b72ab2c16d0399696378722ca90682efe0db0b7d;hb=c27a9818561698a04bbf8ac553d8448686efbddd;hp=fbfd3af0606d570bcfd49152c125ca47b6843679;hpb=c0234dd9b9649063acf2617fecf5c6efda38a532;p=srvgit diff --git a/misc/migration_tools/rebuild_zebra.pl b/misc/migration_tools/rebuild_zebra.pl index fbfd3af060..b72ab2c16d 100755 --- a/misc/migration_tools/rebuild_zebra.pl +++ b/misc/migration_tools/rebuild_zebra.pl @@ -10,6 +10,7 @@ use File::Path; use C4::Biblio; use C4::AuthoritiesMarc; use C4::Items; +use Koha::RecordProcessor; # # script that checks zebradir structure & create directories & mandatory files if needed @@ -24,6 +25,7 @@ my $directory; my $nosanitize; my $skip_export; my $keep_export; +my $skip_index; my $reset; my $biblios; my $authorities; @@ -34,13 +36,17 @@ my $want_help; 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, 'r|reset' => \$reset, 's' => \$skip_export, 'k' => \$keep_export, + 'I|skip-index' => \$skip_index, 'nosanitize' => \$nosanitize, 'b' => \$biblios, 'noxml' => \$noxml, @@ -51,7 +57,10 @@ my $result = GetOptions( '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, ); @@ -66,12 +75,6 @@ if (not $biblios and not $authorities) { die $msg; } -if ($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 '$0 --help' to see usage.\n"; @@ -90,14 +93,18 @@ if ($process_zebraqueue and $do_not_clear_zebraqueue) { die $msg; } +if ($reset) { + $noshadow = 1; +} + if ($noshadow) { $noshadow = ' -n '; } # -v is for verbose, which seems backwards here because of how logging is set # on the CLI of zebraidx. It works this way. The default is to not log much -if ($verbose_logging) { - $zebraidx_log_opt = ''; +if ($verbose_logging >= 2) { + $zebraidx_log_opt = '-v none,fatal,warn,all'; } my $use_tempdir = 0; @@ -111,6 +118,9 @@ my $biblioserverdir = C4::Context->zebraconfig('biblioserver')->{directory}; 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,$biblioitemnumbertagsubfield) = &GetMarcFromKohaField("biblioitems.biblioitemnumber",""); @@ -131,13 +141,13 @@ if ($do_munge) { } if ($authorities) { - index_records('authority', $directory, $skip_export, $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, $as_xml, $noxml, $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, $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, $as_xml, $noxml, $nosanitize, $do_not_clear_zebraqueue, $verbose_logging, $zebraidx_log_opt, $biblioserverdir); } else { print "skipping biblios\n" if ( $verbose_logging ); } @@ -188,7 +198,7 @@ sub check_zebra_dirs { } # ---------- end of subroutine check_zebra_dirs ---------- sub index_records { - my ($record_type, $directory, $skip_export, $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, $as_xml, $noxml, $nosanitize, $do_not_clear_zebraqueue, $verbose_logging, $zebraidx_log_opt, $server_dir) = @_; my $num_records_exported = 0; my $records_deleted; @@ -227,24 +237,32 @@ sub index_records { } } } - + # # and reindexing everything # - if ( $verbose_logging ) { - print "====================\n"; - print "REINDEXING zebra\n"; - print "====================\n"; - } - my $record_fmt = ($as_xml) ? 'marcxml' : 'iso2709' ; - if ($process_zebraqueue) { - do_indexing($record_type, 'delete', "$directory/del_$record_type", $reset, $noshadow, $record_fmt, $zebraidx_log_opt) - if %$records_deleted; - do_indexing($record_type, 'update', "$directory/upd_$record_type", $reset, $noshadow, $record_fmt, $zebraidx_log_opt) - if $num_records_exported; + if ($skip_index) { + if ($verbose_logging) { + print "====================\n"; + print "SKIPPING $record_type indexing\n"; + print "====================\n"; + } } else { - do_indexing($record_type, 'update', "$directory/$record_type", $reset, $noshadow, $record_fmt, $zebraidx_log_opt) - if ($num_records_exported or $skip_export); + if ( $verbose_logging ) { + print "====================\n"; + print "REINDEXING zebra\n"; + print "====================\n"; + } + my $record_fmt = ($as_xml) ? 'marcxml' : 'iso2709' ; + if ($process_zebraqueue) { + do_indexing($record_type, 'adelete', "$directory/del_$record_type", $reset, $noshadow, $record_fmt, $zebraidx_log_opt) + if %$records_deleted; + do_indexing($record_type, 'update', "$directory/upd_$record_type", $reset, $noshadow, $record_fmt, $zebraidx_log_opt) + if $num_records_exported; + } else { + do_indexing($record_type, 'update', "$directory/$record_type", $reset, $noshadow, $record_fmt, $zebraidx_log_opt) + if ($num_records_exported or $skip_export); + } } } @@ -294,22 +312,45 @@ sub select_all_records { } 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; } +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 $num_exported = 0; - open (OUT, ">:utf8 ", "$directory/exported_records") or die $!; + 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} ''; + } my $i = 0; my ( $itemtag, $itemsubfield ) = GetMarcFromKohaField("items.itemnumber",''); while (my ($record_number) = $sth->fetchrow_array) { @@ -337,20 +378,22 @@ sub export_marc_records_from_sth { } } if ( $marcxml ) { - print OUT $marcxml if $marcxml; + print {$fh} $marcxml if $marcxml; $num_exported++; } next; } my ($marc) = get_corrected_marc_record($record_type, $record_number, $noxml); if (defined $marc) { - # FIXME - when more than one record is exported and $as_xml is true, - # the output file is not valid XML - it's just multiple elements - # strung together with no single root element. zebraidx doesn't seem - # to care, though, at least if you're using the GRS-1 filter. It does - # care if you're using the DOM filter, which requires valid XML file(s). eval { - print OUT ($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; $num_exported++; }; if ($@) { @@ -359,7 +402,8 @@ sub export_marc_records_from_sth { } } print "\nRecords exported: $num_exported\n" if ( $verbose_logging ); - close OUT; + print {$fh} '' if (include_xml_wrapper($as_xml, $record_type)); + close $fh; return $num_exported; } @@ -367,7 +411,11 @@ sub export_marc_records_from_list { my ($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 $!; + if (include_xml_wrapper($as_xml, $record_type)) { + # include XML declaration and root element + print {$fh} ''; + } my $i = 0; # Skip any deleted records. We check for this anyway, but this reduces error spam @@ -379,17 +427,26 @@ sub export_marc_records_from_list { print "\r$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 $as_xml is true, - # the output file is not valid XML - it's just multiple elements - # strung together with no single root element. zebraidx doesn't seem - # to care, though, at least if you're using the GRS-1 filter. It does - # care if you're using the DOM filter, which requires valid XML file(s). - print OUT ($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 ( $verbose_logging ); - close OUT; + print {$fh} '' if (include_xml_wrapper($as_xml, $record_type)); + close $fh; return $num_exported; } @@ -397,7 +454,11 @@ sub generate_deleted_marc_records { my ($record_type, $entries, $directory, $as_xml) = @_; my $records_deleted = {}; - open (OUT, ">:utf8 ", "$directory/exported_records") or die $!; + 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} ''; + } my $i = 0; foreach my $record_number (map { $_->{biblio_auth_number} } @$entries ) { print "\r$i" unless ($i++ %100 or !$verbose_logging); @@ -413,12 +474,20 @@ sub generate_deleted_marc_records { fix_unimarc_100($marc); } - print OUT ($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 ( $verbose_logging ); - close OUT; + print {$fh} '' if (include_xml_wrapper($as_xml, $record_type)); + close $fh; return $records_deleted; @@ -433,6 +502,9 @@ sub get_corrected_marc_record { fix_leader($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' } ); + $marc = $normalizer->process($marc); } if (C4::Context->preference("marcflavour") eq "UNIMARC") { fix_unimarc_100($marc); @@ -548,7 +620,7 @@ sub fix_unimarc_100 { my $marc = shift; my $string; - if ( length($marc->subfield( 100, "a" )) == 35 ) { + if ( length($marc->subfield( 100, "a" )) == 36 ) { $string = $marc->subfield( 100, "a" ); my $f100 = $marc->field(100); $marc->delete_field($f100); @@ -559,7 +631,7 @@ sub fix_unimarc_100 { $string = sprintf( "%-*s", 35, $string ); } substr( $string, 22, 6, "frey50" ); - unless ( length($marc->subfield( 100, "a" )) == 35 ) { + unless ( length($marc->subfield( 100, "a" )) == 36 ) { $marc->delete_field($marc->field(100)); $marc->insert_grouped_field(MARC::Field->new( 100, "", "", "a" => $string )); } @@ -599,7 +671,7 @@ Parameters: or -s. -r clear Zebra index before - adding records to index + adding records to index. Implies -w. -d Temporary directory for indexing. If not specified, one is automatically @@ -637,8 +709,16 @@ Parameters: -v increase the amount of logging. Normally only warnings and errors from the indexing are shown. + Use log level 2 (-v -v) to include all Zebra logs. + + --length 1234 how many biblio you want to export + --offset 1243 offset you want to start to + example: --offset 500 --length=500 will result in a LIMIT 500,1000 (exporting 1000 records, starting by the 500th one) + note that the numbers are NOT related to biblionumber, that's the intended behaviour. + --where let you specify a WHERE query, like itemtype='BOOK' + or something like that - -munge-config Deprecated option to try + --munge-config Deprecated option to try to fix Zebra config files. --help or -h show this message. _USAGE_ @@ -823,8 +903,8 @@ if ($authorities) { # 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/ @@ -968,8 +1048,8 @@ if ($biblios) { # 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/