X-Git-Url: http://git.rot13.org/?a=blobdiff_plain;f=misc%2Fmigration_tools%2Fbulkmarcimport.pl;h=a9fee95d1489bb3230f9a6a8174eea4ac4d683ab;hb=b2b16fb8cf4bf89862eba6fc14d507dc79de4db7;hp=2f18d5266e1a2159ea29f289cb11191c3dd1ee6f;hpb=12ac5e3d8908254d0b4c1d4399b895722821ea19;p=koha.git

diff --git a/misc/migration_tools/bulkmarcimport.pl b/misc/migration_tools/bulkmarcimport.pl
index 2f18d5266e..a9fee95d14 100755
--- a/misc/migration_tools/bulkmarcimport.pl
+++ b/misc/migration_tools/bulkmarcimport.pl
@@ -30,10 +30,11 @@ use Getopt::Long;
 use IO::File;
 use Pod::Usage;
 
-binmode(STDOUT, ":utf8");
+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 $cleanisbn = 1;
+my ($sourcetag,$sourcesubfield,$idmapfl, $dedup_barcode);
 
 $|=1;
 
@@ -59,6 +60,8 @@ GetOptions(
     'x:s' => \$sourcetag,
     'y:s' => \$sourcesubfield,
     'idmap:s' => \$idmapfl,
+    'cleanisbn!'     => \$cleanisbn,
+    'dedupbarcode' => \$dedup_barcode,
 );
 $biblios=!$authorities||$biblios;
 
@@ -176,7 +179,6 @@ 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
@@ -197,19 +199,13 @@ RECORD: while (  ) {
     }
     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')) {
-                $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 $id;
@@ -221,15 +217,15 @@ RECORD: while (  ) {
        my ($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(@$results)==1){
+       if ( @{$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 $query";
+       elsif  ( @{$results} > 1){
+           $debug && warn "more than one match for $query";
        } 
        else {
-       $debug && warn "nomatch for $query";
+           $debug && warn "nomatch for $query";
        }
     }
 	my $originalid;
@@ -323,18 +319,67 @@ RECORD: while (  ) {
 				printlog({id=>$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, '' );
+            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', '');
+                # 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, $biblionumber, '' );
+                    next RECORD;
+                } else {
+                    printlog({id=>$id||$originalid||$biblionumber, op=>"insert",status=>"ok"}) if ($logfile);
+                }
+                push @$errors_ref, @{ $more_errors };
+            }
+            if ($#{ $errors_ref } > -1) {
                 report_item_errors($biblionumber, $errors_ref);
             }
         }
@@ -405,6 +450,7 @@ sub report_item_errors {
     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;
@@ -518,6 +564,11 @@ 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<TAG>
 
 Source bib I<TAG> for reporting the source bib number
@@ -536,6 +587,13 @@ 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.)
+
 =back
 
 =cut