X-Git-Url: http://koha-dev.rot13.org:8081/gitweb/?a=blobdiff_plain;f=misc%2Fmigration_tools%2Fbulkmarcimport.pl;h=4a47de00c36ad847ca7a62b2ff33cbfa541d5e4c;hb=b4f4e5a71b016d10e1c374136a760648bd807105;hp=3bb9ed85d92298c7a4e4bc956b9f6c001245159b;hpb=374cdb2678866c043fa0231fbe30dd1b2ffed485;p=koha_fer diff --git a/misc/migration_tools/bulkmarcimport.pl b/misc/migration_tools/bulkmarcimport.pl index 3bb9ed85d9..4a47de00c3 100755 --- a/misc/migration_tools/bulkmarcimport.pl +++ b/misc/migration_tools/bulkmarcimport.pl @@ -24,16 +24,22 @@ use C4::Koha; use C4::Debug; use C4::Charset; use C4::Items; +use YAML; use Unicode::Normalize; use Time::HiRes qw(gettimeofday); use Getopt::Long; use IO::File; use Pod::Usage; -binmode(STDOUT, ":utf8"); +use open qw( :std :encoding(UTF-8) ); +binmode( STDOUT, ":encoding(UTF-8)" ); my ( $input_marc_file, $number, $offset) = ('',0,0); my ($version, $delete, $test_parameter, $skip_marc8_conversion, $char_encoding, $verbose, $commit, $fk_off,$format,$biblios,$authorities,$keepids,$match, $isbn_check, $logfile); -my ($sourcetag,$sourcesubfield,$idmapfl); +my ( $insert, $filters, $update, $all, $yamlfile, $authtypes, $append ); +my $cleanisbn = 1; +my ($sourcetag,$sourcesubfield,$idmapfl, $dedup_barcode); +my $framework = ''; +my $localcust; $|=1; @@ -44,29 +50,68 @@ GetOptions( 'o|offset:f' => \$offset, 'h' => \$version, 'd' => \$delete, - 't' => \$test_parameter, + 't|test' => \$test_parameter, 's' => \$skip_marc8_conversion, 'c:s' => \$char_encoding, - 'v:s' => \$verbose, + 'v:+' => \$verbose, 'fk' => \$fk_off, 'm:s' => \$format, 'l:s' => \$logfile, + 'append' => \$append, 'k|keepids:s' => \$keepids, 'b|biblios' => \$biblios, 'a|authorities' => \$authorities, + 'authtypes:s' => \$authtypes, + 'filter=s@' => \$filters, + 'insert' => \$insert, + 'update' => \$update, + 'all' => \$all, 'match=s@' => \$match, 'i|isbn' => \$isbn_check, 'x:s' => \$sourcetag, 'y:s' => \$sourcesubfield, 'idmap:s' => \$idmapfl, + 'cleanisbn!' => \$cleanisbn, + 'yaml:s' => \$yamlfile, + 'dedupbarcode' => \$dedup_barcode, + 'framework=s' => \$framework, + 'custom:s' => \$localcust, ); -$biblios=!$authorities||$biblios; +$biblios ||= !$authorities; +$insert ||= !$update; +my $writemode = ($append) ? "a" : "w"; + +if ($all) { + $insert = 1; + $update = 1; +} if ($version || ($input_marc_file eq '')) { pod2usage( -verbose => 2 ); exit; } +if(defined $localcust) { #local customize module + if(!-e $localcust) { + $localcust= $localcust||'LocalChanges'; #default name + $localcust=~ s/^.*\/([^\/]+)$/$1/; #extract file name only + $localcust=~ s/\.pm$//; #remove extension + my $fqcust= $FindBin::Bin."/$localcust.pm"; #try migration_tools dir + if(-e $fqcust) { + $localcust= $fqcust; + } + else { + print "WARNING: customize module $localcust.pm not found!\n"; + exit 1; + } + } + require $localcust if $localcust; + $localcust=\&customize if $localcust; +} + +my $dbh = C4::Context->dbh; +my $heading_fields=get_heading_fields(); + if (defined $idmapfl) { open(IDMAP,">$idmapfl") or die "cannot open $idmapfl \n"; } @@ -76,8 +121,6 @@ if ((not defined $sourcesubfield) && (not defined $sourcetag)){ $sourcesubfield="a"; } -my $dbh = C4::Context->dbh; - # save the CataloguingLog property : we don't want to log a bulkmarcimport. It will slow the import & # will create problems in the action_logs table, that can't handle more than 1 entry per second per user. my $CataloguingLog = C4::Context->preference('CataloguingLog'); @@ -137,7 +180,7 @@ $batch->warnings_off(); $batch->strict_off(); my $i=0; my $commitnum = $commit ? $commit : 50; - +my $yamlhash; # Skip file offset if ( $offset ) { @@ -151,7 +194,7 @@ if ($authorities){ } else { ( $tagid, $subfieldid ) = - GetMarcFromKohaField( "biblio.biblionumber", '' ); + GetMarcFromKohaField( "biblio.biblionumber", $framework ); $tagid||="001"; } @@ -161,7 +204,7 @@ my $sth_isbn = $dbh->prepare("SELECT biblionumber,biblioitemnumber FROM biblioit $dbh->{AutoCommit} = 0; my $loghandle; if ($logfile){ - $loghandle= IO::File->new($logfile,"w") ; + $loghandle= IO::File->new($logfile, $writemode) ; print $loghandle "id;operation;status\n"; } RECORD: while ( ) { @@ -176,15 +219,15 @@ RECORD: while ( ) { # from because we don't have access to the original blob. Note # that the staging import can deal with this condition (via # C4::Charset::MarcToUTF8Record) because it doesn't use MARC::Batch. - $i++; next; } # skip if we get an empty record (that is MARC valid, but will result in AddBiblio failure last unless ( $record ); $i++; - print "."; - print "\r$i" unless $i % 100; - + if( ($verbose//1)==1 ) { #no dot for verbose==2 + print "." . ( $i % 100==0 ? "\n$i" : '' ); + } + # transcode the record to UTF8 if needed & applicable. if ($record->encoding() eq 'MARC-8' and not $skip_marc8_conversion) { # FIXME update condition @@ -195,65 +238,93 @@ RECORD: while ( ) { next RECORD; } } + SetUTF8Flag($record); + &$localcust($record) if $localcust; my $isbn; # remove trailing - in isbn (only for biblios, of course) - if ($biblios) { - if ($marcFlavour eq 'UNIMARC') { - if (my $f010 = $record->field('010')) { - $isbn = $f010->subfield('a'); - $isbn =~ s/-//g; - $f010->update('a' => $isbn); - } - } else { - if (my $f020 = $record->field('020')) { - if ($isbn = $f020->subfield('a')) { - $isbn =~ s/-//g; - $f020->update('a' => $isbn); - } - } + if ($biblios && $cleanisbn) { + my $tag = $marcFlavour eq 'UNIMARC' ? '010' : '020'; + my $field = $record->field($tag); + my $isbn = $field && $field->subfield('a'); + if ( $isbn ) { + $isbn =~ s/-//g; + $field->update('a' => $isbn); } } my $id; # search for duplicates (based on Local-number) - if ($match){ - require C4::Search; - my $query=build_query($match,$record); - my $server=($authorities?'authorityserver':'biblioserver'); - my ($error, $results,$totalhits)=C4::Search::SimpleSearch( $query, 0, 3, [$server] ); - die "unable to search the database for duplicates : $error" if (defined $error); - #warn "$query $server : $totalhits"; - if ($results && scalar(@$results)==1){ - my $marcrecord = MARC::File::USMARC::decode($results->[0]); - $id=GetRecordId($marcrecord,$tagid,$subfieldid); - } - elsif ($results && scalar(@$results)>1){ - $debug && warn "more than one match for $query"; - } - else { - $debug && warn "nomatch for $query"; - } + my $originalid; + $originalid = GetRecordId( $record, $tagid, $subfieldid ); + if ($match) { + require C4::Search; + my $query = build_query( $match, $record ); + my $server = ( $authorities ? 'authorityserver' : 'biblioserver' ); + $debug && warn $query; + my ( $error, $results, $totalhits ) = C4::Search::SimpleSearch( $query, 0, 3, [$server] ); + die "unable to search the database for duplicates : $error" if ( defined $error ); + $debug && warn "$query $server : $totalhits"; + if ( $results && scalar(@$results) == 1 ) { + my $marcrecord = C4::Search::new_record_from_zebra( $server, $results->[0] ); + SetUTF8Flag($marcrecord); + $id = GetRecordId( $marcrecord, $tagid, $subfieldid ); + if ( $authorities && $marcFlavour ) { + #Skip if authority in database is the same as the on in database + if ( $marcrecord->field('005') && $record->field('005') && + $marcrecord->field('005')->data && $record->field('005')->data && + $marcrecord->field('005')->data >= $record->field('005')->data ) { + if ($yamlfile) { + $yamlhash->{$originalid}->{'authid'} = $id; + + # we recover all subfields of the heading authorities + my @subfields; + foreach my $field ( $marcrecord->field("2..") ) { + push @subfields, map { ( $_->[0] =~ /[a-z]/ ? $_->[1] : () ) } $field->subfields(); + } + $yamlhash->{$originalid}->{'subfields'} = \@subfields; + } + next; + } + } + } elsif ( $results && scalar(@$results) > 1 ) { + $debug && warn "more than one match for $query"; + } else { + $debug && warn "nomatch for $query"; + } + } + if ($keepids && $originalid) { + my $storeidfield; + if ( length($keepids) == 3 ) { + $storeidfield = MARC::Field->new( $keepids, $originalid ); + } else { + $storeidfield = MARC::Field->new( substr( $keepids, 0, 3 ), "", "", substr( $keepids, 3, 1 ), $originalid ); + } + $record->insert_fields_ordered($storeidfield); + $record->delete_field( $record->field($tagid) ); } - my $originalid; - if ($keepids){ - $originalid=GetRecordId($record,$tagid,$subfieldid); - if ($originalid){ - my $storeidfield; - if (length($keepids)==3){ - $storeidfield=MARC::Field->new($keepids,$originalid); - } - else { - $storeidfield=MARC::Field->new(substr($keepids,0,3),"","",substr($keepids,3,1),$originalid); - } - $record->insert_fields_ordered($storeidfield); - $record->delete_field($record->field($tagid)); - } + foreach my $stringfilter (@$filters) { + if ( length($stringfilter) == 3 ) { + foreach my $field ( $record->field($stringfilter) ) { + $record->delete_field($field); + $debug && warn "removed : ", $field->as_string; + } + } elsif ($stringfilter =~ /([0-9]{3})([a-z0-9])(.*)/) { + my $removetag = $1; + my $removesubfield = $2; + my $removematch = $3; + if ( ( $removetag > "010" ) && $removesubfield ) { + foreach my $field ( $record->field($removetag) ) { + $field->delete_subfield( code => "$removesubfield", match => $removematch ); + $debug && warn "Potentially removed : ", $field->subfield($removesubfield); + } + } + } } unless ($test_parameter) { if ($authorities){ use C4::AuthoritiesMarc; - my $authtypecode=GuessAuthTypeCode($record); + my $authtypecode=GuessAuthTypeCode($record, $heading_fields); my $authid= ($id?$id:GuessAuthId($record)); - if ($authid && GetAuthority($authid)){ + if ($authid && GetAuthority($authid) && $update ){ ## Authority has an id and is in database : Replace eval { ( $authid ) = ModAuthority($authid,$record, $authtypecode) }; if ($@){ @@ -286,6 +357,14 @@ RECORD: while ( ) { printlog({id=>$originalid||$id||$authid, op=>"insert",status=>"ok"}) if ($logfile); } } + if ($yamlfile) { + $yamlhash->{$originalid}->{'authid'} = $authid; + my @subfields; + foreach my $field ( $record->field("2..") ) { + push @subfields, map { ( $_->[0] =~ /[a-z]/ ? $_->[1] : () ) } $field->subfields(); + } + $yamlhash->{$originalid}->{'subfields'} = \@subfields; + } } else { my ( $biblionumber, $biblioitemnumber, $itemnumbers_ref, $errors_ref ); @@ -309,42 +388,106 @@ RECORD: while ( ) { } # create biblio, unless we already have it ( either match or isbn ) if ($biblionumber) { - eval{$biblioitemnumber=GetBiblioData($biblionumber)->{biblioitemnumber};} - } - else - { - eval { ( $biblionumber, $biblioitemnumber ) = AddBiblio($record, '', { defer_marc_save => 1 }) }; + eval{$biblioitemnumber=GetBiblioData($biblionumber)->{biblioitemnumber};}; + if ($update) { + eval { ( $biblionumber, $biblioitemnumber ) = ModBiblio( $record, $biblionumber, GetFrameworkcode($biblionumber) ) }; + if ($@) { + warn "ERROR: Edit biblio $biblionumber failed: $@\n"; + printlog( { id => $id || $originalid || $biblionumber, op => "update", status => "ERROR" } ) if ($logfile); + next RECORD; + } else { + printlog( { id => $id || $originalid || $biblionumber, op => "update", status => "ok" } ) if ($logfile); + } + } else { + printlog( { id => $id || $originalid || $biblionumber, op => "insert", status => "warning : already in database" } ) if ($logfile); + } + } else { + if ($insert) { + eval { ( $biblionumber, $biblioitemnumber ) = AddBiblio( $record, '', { defer_marc_save => 1 } ) }; + if ($@) { + warn "ERROR: Adding biblio $biblionumber failed: $@\n"; + printlog( { id => $id || $originalid || $biblionumber, op => "insert", status => "ERROR" } ) if ($logfile); + next RECORD; + } else { + printlog( { id => $id || $originalid || $biblionumber, op => "insert", status => "ok" } ) if ($logfile); + } + } else { + printlog( { id => $id || $originalid || $biblionumber, op => "update", status => "warning : not in database" } ) if ($logfile); + } } - if ( $@ ) { - warn "ERROR: Adding biblio $biblionumber failed: $@\n"; - printlog({id=>$id||$originalid||$biblionumber, op=>"insert",status=>"ERROR"}) if ($logfile); - next RECORD; - } - else{ - printlog({id=>$id||$originalid||$biblionumber, op=>"insert",status=>"ok"}) if ($logfile); - } eval { ( $itemnumbers_ref, $errors_ref ) = AddItemBatchFromMarc( $record, $biblionumber, $biblioitemnumber, '' ); }; - if ( $@ ) { - warn "ERROR: Adding items to bib $biblionumber failed: $@\n"; + my $error_adding = $@; + # Work on a clone so that if there are real errors, we can maybe + # fix them up later. + my $clone_record = $record->clone(); + C4::Biblio::_strip_item_fields($clone_record, ''); + # This sets the marc fields if there was an error, and also calls + # defer_marc_save. + ModBiblioMarc( $clone_record, $biblionumber, $framework ); + if ( $error_adding ) { + warn "ERROR: Adding items to bib $biblionumber failed: $error_adding"; printlog({id=>$id||$originalid||$biblionumber, op=>"insertitem",status=>"ERROR"}) if ($logfile); # if we failed because of an exception, assume that # the MARC columns in biblioitems were not set. - ModBiblioMarc( $record, $biblionumber, '' ); next RECORD; - } + } else{ printlog({id=>$id||$originalid||$biblionumber, op=>"insert",status=>"ok"}) if ($logfile); } - if ($#{ $errors_ref } > -1) { + if ($dedup_barcode && grep { exists $_->{error_code} && $_->{error_code} eq 'duplicate_barcode' } @$errors_ref) { + # Find the record called 'barcode' + my ($tag, $sub) = C4::Biblio::GetMarcFromKohaField('items.barcode', $framework); + # Now remove any items that didn't have a duplicate_barcode error, + # erase the barcodes on items that did, and re-add those items. + my %dupes; + foreach my $i (0 .. $#{$errors_ref}) { + my $ref = $errors_ref->[$i]; + if ($ref && ($ref->{error_code} eq 'duplicate_barcode')) { + $dupes{$ref->{item_sequence}} = 1; + # Delete the error message because we're going to + # retry this one. + delete $errors_ref->[$i]; + } + } + my $seq = 0; + foreach my $field ($record->field($tag)) { + $seq++; + if ($dupes{$seq}) { + # Here we remove the barcode + $field->delete_subfield(code => $sub); + } else { + # otherwise we delete the field because we don't want + # two of them + $record->delete_fields($field); + } + } + # Now re-add the record as before, adding errors to the prev list + my $more_errors; + eval { ( $itemnumbers_ref, $more_errors ) = AddItemBatchFromMarc( $record, $biblionumber, $biblioitemnumber, '' ); }; + if ( $@ ) { + warn "ERROR: Adding items to bib $biblionumber failed: $@\n"; + printlog({id=>$id||$originalid||$biblionumber, op=>"insertitem",status=>"ERROR"}) if ($logfile); + # if we failed because of an exception, assume that + # the MARC columns in biblioitems were not set. + ModBiblioMarc( $record, $biblionumber, $framework ); + next RECORD; + } else { + printlog({id=>$id||$originalid||$biblionumber, op=>"insert",status=>"ok"}) if ($logfile); + } + push @$errors_ref, @{ $more_errors }; + } + if ($#{ $errors_ref } > -1) { report_item_errors($biblionumber, $errors_ref); } + $yamlhash->{$originalid} = $biblionumber if ($yamlfile); } $dbh->commit() if (0 == $i % $commitnum); } + print $record->as_formatted()."\n" if ($verbose//0)==2; last if $i == $number; } $dbh->commit(); - +$dbh->{AutoCommit} = 1; if ($fk_off) { @@ -361,6 +504,10 @@ if ($logfile){ print $loghandle "$i MARC records done in $timeneeded seconds\n"; $loghandle->close; } +if ($yamlfile) { + open my $yamlfileout, q{>}, "$yamlfile" or die "cannot open $yamlfile \n"; + print $yamlfileout Dump($yamlhash); +} exit 0; sub GetRecordId{ @@ -386,26 +533,45 @@ sub build_query { my $string = build_simplequery($matchingpoint,$record); push @searchstrings,$string if (length($string)>0); } - return join(" and ",@searchstrings); + my $QParser; + $QParser = C4::Context->queryparser if (C4::Context->preference('UseQueryParser')); + my $op; + if ($QParser) { + $op = '&&'; + } else { + $op = 'and'; + } + return join(" $op ",@searchstrings); } sub build_simplequery { my $element=shift; my $record=shift; - my ($index,$recorddata)=split /,/,$element; - my ($tag,$subfields) =($1,$2) if ($recorddata=~/(\d{3})(.*)/); - my @searchstrings; + my @searchstrings; + my ($index,$recorddata)=split /,/,$element; + if ($recorddata=~/(\d{3})(.*)/) { + my ($tag,$subfields) =($1,$2); foreach my $field ($record->field($tag)){ if (length($field->as_string("$subfields"))>0){ - push @searchstrings,"$index,wrdl=\"".$field->as_string("$subfields")."\""; + push @searchstrings,"$index:\"".$field->as_string("$subfields")."\""; } } - return join(" and ",@searchstrings); + } + my $QParser; + $QParser = C4::Context->queryparser if (C4::Context->preference('UseQueryParser')); + my $op; + if ($QParser) { + $op = '&&'; + } else { + $op = 'and'; + } + return join(" $op ",@searchstrings); } sub report_item_errors { my $biblionumber = shift; my $errors_ref = shift; foreach my $error (@{ $errors_ref }) { + next if !$error; my $msg = "Item not added (bib $biblionumber, item tag #$error->{'item_sequence'}, barcode $error->{'item_barcode'}): "; my $error_code = $error->{'error_code'}; $error_code =~ s/_/ /g; @@ -415,9 +581,21 @@ sub report_item_errors { } sub printlog{ my $logelements=shift; - print $loghandle join (";",@$logelements{qw}),"\n"; + print $loghandle join( ";", map { defined $_ ? $_ : "" } @$logelements{qw} ), "\n"; +} +sub get_heading_fields{ + my $headingfields; + if ($authtypes){ + $headingfields=YAML::LoadFile($authtypes); + $headingfields={C4::Context->preference('marcflavour')=>$headingfields}; + $debug && warn YAML::Dump($headingfields); + } + unless ($headingfields){ + $headingfields=$dbh->selectall_hashref("SELECT auth_tag_to_report, authtypecode from auth_types",'auth_tag_to_report',{Slice=>{}}); + $headingfields={C4::Context->preference('marcflavour')=>$headingfields}; + } + return $headingfields; } - =head1 NAME @@ -479,7 +657,11 @@ The I of records to wait before performing a 'commit' operation File logs actions done for each record and their status into file -=item B<-t> +=item B<-append> + +If specified, data will be appended to the logfile. If not, the logfile will be erased for each execution. + +=item B<-t, -test> Test mode: parses the file, saying what he would do, but doing nothing. @@ -502,6 +684,32 @@ biblioitems, items Input file I: I or I (defaults to ISO2709) +=item B<-authtypes> + +file yamlfile with authoritiesTypes and distinguishable record field in order +to store the correct authtype + +=item B<-yaml> + +yaml file format a yaml file with ids + +=item B<-filter> + +list of fields that will not be imported. Can be any from 000 to 999 or field, +subfield and subfield's matching value such as 200avalue + +=item B<-insert> + +if set, only insert when possible + +=item B<-update> + +if set, only updates (any biblio should have a matching record) + +=item B<-all> + +if set, do whatever is required + =item B<-k, -keepids>= Field store ids in I (usefull for authorities, where 001 contains the @@ -519,6 +727,11 @@ If set, a search will be done on isbn, and, if the same isbn is found, the biblio is not added. It's another method to deduplicate. B<-match> & B<-isbn> can be both set. +=item B<-cleanisbn> + +Clean ISBN fields from entering biblio records, ie removes hyphens. By default, +ISBN are cleaned. --nocleanisbn will keep ISBN unchanged. + =item B<-x>=I Source bib I for reporting the source bib number @@ -537,6 +750,27 @@ Store ids in 009 (usefull for authorities, where 001 contains the authid for Koha, that can contain a very valuable info for authorities coming from LOC or BNF. useless for biblios probably) +=item B<-dedupbarcode> + +If set, whenever a duplicate barcode is detected, it is removed and the attempt +to add the record is retried, thereby giving the record a blank barcode. This +is useful when something has set barcodes to be a biblio ID, or similar +(usually other software.) + +=item B<-framework> + +This is the code for the framework that the requested records will have attached +to them when they are created. If not specified, then the default framework +will be used. + +=item B<-custom>=I + +This parameter allows you to use a local module with a customize subroutine +that is called for each MARC record. +If no filename is passed, LocalChanges.pm is assumed to be in the +migration_tools subdirectory. You may pass an absolute file name or a file name +from the migration_tools directory. + =back =cut