--- trunk/lib/WebPAC/Normalize.pm 2006/10/31 13:19:47 766 +++ trunk/lib/WebPAC/Normalize.pm 2007/04/02 17:20:01 815 @@ -9,8 +9,8 @@ tag search display marc marc_indicators marc_repeatable_subfield - marc_compose marc_leader - marc_duplicate marc_remove + marc_compose marc_leader marc_fixed + marc_duplicate marc_remove marc_count marc_original_order rec1 rec2 rec @@ -19,6 +19,9 @@ save_into_lookup split_rec_on + + get set + count /; use warnings; @@ -39,11 +42,11 @@ =head1 VERSION -Version 0.23 +Version 0.28 =cut -our $VERSION = '0.23'; +our $VERSION = '0.28'; =head1 SYNOPSIS @@ -164,7 +167,7 @@ =cut -my ($out, $marc_record, $marc_encoding, $marc_repeatable_subfield, $marc_indicators, $leader); +my ($out, $marc_record, $marc_encoding, $marc_repeatable_subfield, $marc_indicators, $marc_leader); my ($marc_record_offset, $marc_fetch_offset) = (0, 0); sub _get_ds { @@ -181,7 +184,7 @@ sub _clean_ds { my $a = {@_}; - ($out,$marc_record, $marc_encoding, $marc_repeatable_subfield, $marc_indicators, $leader) = (); + ($out,$marc_record, $marc_encoding, $marc_repeatable_subfield, $marc_indicators, $marc_leader) = (); ($marc_record_offset, $marc_fetch_offset) = (0,0); $marc_encoding = $a->{marc_encoding}; } @@ -286,13 +289,15 @@ =cut +my $fetch_pos; + sub _get_marc_fields { my $arg = {@_}; warn "### _get_marc_fields arg: ", dump($arg), $/ if ($debug > 2); - my $offset = $marc_fetch_offset; + $fetch_pos = $marc_fetch_offset; if ($arg->{offset}) { - $offset = $arg->{offset}; + $fetch_pos = $arg->{offset}; } elsif($arg->{fetch_next}) { $marc_fetch_offset++; } @@ -301,9 +306,9 @@ warn "### full marc_record = ", dump( @{ $marc_record }), $/ if ($debug > 2); - my $marc_rec = $marc_record->[ $offset ]; + my $marc_rec = $marc_record->[ $fetch_pos ]; - warn "## _get_marc_fields (at offset: $offset) -- marc_record = ", dump( @$marc_rec ), $/ if ($debug > 1); + warn "## _get_marc_fields (at offset: $fetch_pos) -- marc_record = ", dump( @$marc_rec ), $/ if ($debug > 1); return if (! $marc_rec || ref($marc_rec) ne 'ARRAY' || $#{ $marc_rec } < 0); @@ -324,7 +329,7 @@ if ($debug) { warn "## marc_repeatable_subfield = ", dump( $marc_repeatable_subfield ), $/ if ( $marc_repeatable_subfield ); - warn "## marc_record[$offset] = ", dump( $marc_rec ), $/; + warn "## marc_record[$fetch_pos] = ", dump( $marc_rec ), $/; warn "## sorted_marc_record = ", dump( \@sorted_marc_record ), $/; warn "## subfield count = ", dump( $u ), $/; } @@ -405,6 +410,19 @@ return \@m; } +=head2 _get_marc_leader + +Return leader from currently fetched record by L + + print WebPAC::Normalize::_get_marc_leader(); + +=cut + +sub _get_marc_leader { + die "no fetch_pos, did you called _get_marc_fields first?" unless ( defined( $fetch_pos ) ); + return $marc_leader->[ $fetch_pos ]; +} + =head2 _debug Change level of debug warnings @@ -487,9 +505,56 @@ my ($offset,$value) = @_; if ($offset) { - $leader->{ $offset } = $value; + $marc_leader->[ $marc_record_offset ]->{ $offset } = $value; } else { - return $leader; + + if (defined($marc_leader)) { + die "marc_leader not array = ", dump( $marc_leader ) unless (ref($marc_leader) eq 'ARRAY'); + return $marc_leader->[ $marc_record_offset ]; + } else { + return; + } + } +} + +=head2 marc_fixed + +Create control/indentifier fields with values in fixed positions + + marc_fixed('008', 00, '070402'); + marc_fixed('008', 39, '|'); + +Positions not specified will be filled with spaces (C<0x20>). + +There will be no effort to extend last specified value to full length of +field in standard. + +=cut + +sub marc_fixed { + my ($f, $pos, $val) = @_; + die "need marc(field, position, value)" unless defined($f) && defined($pos); + + my $update = 0; + + map { + if ($_->[0] eq $f) { + my $old = $_->[1]; + if (length($old) < $pos) { + $_->[1] .= ' ' x ( $pos - length($old) ) . $val; + warn "## marc_fixed($f,$pos,'$val') append '$old' -> '$_->[1]'\n"; + } else { + $_->[1] = substr($old, 0, $pos) . $val . substr($old, $pos + length($val)); + warn "## marc_fixed($f,$pos,'$val') update '$old' -> '$_->[1]'\n"; + } + $update++; + } + } @{ $marc_record->[ $marc_record_offset ] }; + + if (! $update) { + my $v = ' ' x $pos . $val; + push @{ $marc_record->[ $marc_record_offset ] }, [ $f, $v ]; + warn "## marc_fixed($f,$pos,'val') created '$v'\n"; } } @@ -621,9 +686,11 @@ my $m = $marc_record->[ -1 ]; die "can't duplicate record which isn't defined" unless ($m); push @{ $marc_record }, dclone( $m ); - warn "## marc_duplicate = ", dump(@$marc_record), $/ if ($debug > 1); + push @{ $marc_leader }, dclone( marc_leader() ); + warn "## marc_duplicate = ", dump(@$marc_leader, @$marc_record), $/ if ($debug > 1); $marc_record_offset = $#{ $marc_record }; warn "## marc_record_offset = $marc_record_offset", $/ if ($debug > 1); + } =head2 marc_remove @@ -635,6 +702,10 @@ This will erase field C<200> or C<200^a> from current MARC record. + marc_remove('*'); + +Will remove all fields in current MARC record. + This is useful after calling C or on it's own (but, you should probably just remove that subfield definition if you are not using C). @@ -652,39 +723,47 @@ warn "### marc_remove before = ", dump( $marc ), $/ if ($debug > 2); - my $i = 0; - foreach ( 0 .. $#{ $marc } ) { - last unless (defined $marc->[$i]); - warn "#### working on ",dump( @{ $marc->[$i] }), $/ if ($debug > 3); - if ($marc->[$i]->[0] eq $f) { - if (! defined $sf) { - # remove whole field - splice @$marc, $i, 1; - warn "#### slice \@\$marc, $i, 1 = ",dump( @{ $marc }), $/ if ($debug > 3); - $i--; - } else { - foreach my $j ( 0 .. (( $#{ $marc->[$i] } - 3 ) / 2) ) { - my $o = ($j * 2) + 3; - if ($marc->[$i]->[$o] eq $sf) { - # remove subfield - splice @{$marc->[$i]}, $o, 2; - warn "#### slice \@{\$marc->[$i]}, $o, 2 = ", dump( @{ $marc }), $/ if ($debug > 3); - # is record now empty? - if ($#{ $marc->[$i] } == 2) { - splice @$marc, $i, 1; - warn "#### slice \@\$marc, $i, 1 = ", dump( @{ $marc }), $/ if ($debug > 3); - $i--; - }; + if ($f eq '*') { + + delete( $marc_record->[ $marc_record_offset ] ); + warn "## full marc_record = ", dump( @{ $marc_record }), $/ if ($debug > 1); + + } else { + + my $i = 0; + foreach ( 0 .. $#{ $marc } ) { + last unless (defined $marc->[$i]); + warn "#### working on ",dump( @{ $marc->[$i] }), $/ if ($debug > 3); + if ($marc->[$i]->[0] eq $f) { + if (! defined $sf) { + # remove whole field + splice @$marc, $i, 1; + warn "#### slice \@\$marc, $i, 1 = ",dump( @{ $marc }), $/ if ($debug > 3); + $i--; + } else { + foreach my $j ( 0 .. (( $#{ $marc->[$i] } - 3 ) / 2) ) { + my $o = ($j * 2) + 3; + if ($marc->[$i]->[$o] eq $sf) { + # remove subfield + splice @{$marc->[$i]}, $o, 2; + warn "#### slice \@{\$marc->[$i]}, $o, 2 = ", dump( @{ $marc }), $/ if ($debug > 3); + # is record now empty? + if ($#{ $marc->[$i] } == 2) { + splice @$marc, $i, 1; + warn "#### slice \@\$marc, $i, 1 = ", dump( @{ $marc }), $/ if ($debug > 3); + $i--; + }; + } } } } + $i++; } - $i++; - } - warn "### marc_remove($f", $sf ? ",$sf" : "", ") after = ", dump( $marc ), $/ if ($debug > 2); + warn "### marc_remove($f", $sf ? ",$sf" : "", ") after = ", dump( $marc ), $/ if ($debug > 2); - $marc_record->[ $marc_record_offset ] = $marc; + $marc_record->[ $marc_record_offset ] = $marc; + } warn "## full marc_record = ", dump( @{ $marc_record }), $/ if ($debug > 1); } @@ -759,6 +838,18 @@ warn "## marc_record = ", dump( $marc_record ),$/ if ($debug > 1); } +=head2 marc_count + +Return number of MARC records created using L. + + print "created ", marc_count(), " records"; + +=cut + +sub marc_count { + return $#{ $marc_record }; +} + =head1 Functions to extract data from input @@ -1248,5 +1339,45 @@ } } +my $hash; + +=head2 set + + set( key => 'value' ); + +=cut + +sub set { + my ($k,$v) = @_; + warn "## set ( $k => ", dump($v), " )", $/ if ( $debug ); + $hash->{$k} = $v; +}; + +=head2 get + + get( 'key' ); + +=cut + +sub get { + my $k = shift || return; + my $v = $hash->{$k}; + warn "## get $k = ", dump( $v ), $/ if ( $debug ); + return $v; +} + +=head2 count + + if ( count( @result ) == 1 ) { + # do something if only 1 result is there + } + +=cut + +sub count { + warn "## count ",dump(@_),$/ if ( $debug ); + return @_ . ''; +} + # END 1;