use Carp;
use File::Glob qw(:globally :nocase);
-use Data::Dumper;
-
BEGIN {
use Exporter ();
use vars qw ($VERSION @ISA @EXPORT @EXPORT_OK %EXPORT_TAGS);
- $VERSION = 0.12;
+ $VERSION = 0.24_1;
@ISA = qw (Exporter);
#Give a hoot don't pollute, do not export more than needed by default
@EXPORT = qw ();
read_fdt => 1,
include_deleted => 1,
hash_filter => sub {
- my $v = shift;
+ my ($v,$field_number) = @_;
$v =~ s#foo#bar#g;
},
debug => 1,
+ join_subfields_with => ' ; ',
);
Options are described below:
=item hash_filter
-Filter code ref which will be used before data is converted to hash.
+Filter code ref which will be used before data is converted to hash. It will
+receive two arguments, whole line from current field (in C<< $_[0] >>) and
+field number (in C<< $_[1] >>).
=item debug
-Dump a B<lot> of debugging output.
+Dump a B<lot> of debugging output even at level 1. For even more increase level.
+
+=item join_subfields_with
+
+Define delimiter which will be used to join repeatable subfields. This
+option is included to support lagacy application written against version
+older than 0.21 of this module. By default, it disabled. See L</to_hash>.
+
+=item ignore_empty_subfields
+
+Remove all empty subfields while reading from ISIS file.
=back
croak "new needs database name (isisdb) as argument!" unless ({@_}->{isisdb});
- foreach my $v (qw{isisdb debug include_deleted hash_filter}) {
- $self->{$v} = {@_}->{$v};
+ foreach my $v (qw{isisdb debug include_deleted hash_filter join_subfields_with ignore_empty_subfields}) {
+ $self->{$v} = {@_}->{$v} if defined({@_}->{$v});
}
my @isis_files = grep(/\.(FDT|MST|XRF|CNT)$/i,glob($self->{isisdb}."*"));
}
}
- print STDERR "## using files: ",join(" ",@isis_files),"\n" if ($self->{debug});
+ if ($self->{debug}) {
+ print STDERR "## using files: ",join(" ",@isis_files),"\n";
+ eval "use Data::Dump";
+
+ if (! $@) {
+ *Dumper = *Data::Dump::dump;
+ } else {
+ use Data::Dumper;
+ }
+ }
# if you want to read .FDT file use read_fdt argument when creating class!
if ($self->{read_fdt} && -e $self->{fdt_file}) {
read($self->{'fileMST'}, $buff, 4) || croak "can't read NXTMFN from MST: $!";
$self->{'NXTMFN'}=unpack("V",$buff) || croak "NXTNFN is zero";
- print STDERR Dumper($self),"\n" if ($self->{debug});
+ print STDERR "## self ",Dumper($self),"\n" if ($self->{debug});
# open files for later
open($self->{'fileXRF'}, $self->{xrf_file}) || croak "can't open '$self->{xrf_file}': $!";
# read XRFMFB abd XRFMFP
read($self->{'fileXRF'}, $buff, 4);
- my $pointer=unpack("V",$buff) || croak "pointer is null";
+ my $pointer=unpack("V",$buff);
+ if (! $pointer) {
+ if ($self->{include_deleted}) {
+ return;
+ } else {
+ warn "pointer for MFN $mfn is null\n";
+ return;
+ }
+ }
# check for logically deleted record
if ($pointer & 0x80000000) {
# skip zero-sized fields
next if ($FieldLEN[$i] == 0);
- push @{$self->{record}->{$FieldTAG[$i]}}, substr($buff,$FieldPOS[$i],$FieldLEN[$i]);
+ my $v = substr($buff,$FieldPOS[$i],$FieldLEN[$i]);
+
+ if ( $self->{ignore_empty_subfields} ) {
+ $v =~ s/(\^\w)+(\^\w)/$2/g;
+ $v =~ s/\^\w$//; # last on line?
+ next if ($v eq '');
+ }
+
+ push @{$self->{record}->{$FieldTAG[$i]}}, $v;
}
$self->{'current_mfn'} = $mfn;
return $self->{'record'};
}
+=head2 mfn
+
+Returns current MFN position
+
+ my $mfn = $isis->mfn;
+
+=cut
+
+# This function should be simple return $self->{current_mfn},
+# but if new is called with _hack_mfn it becomes setter.
+# It's useful in tests when setting $isis->{record} directly
+
+sub mfn {
+ my $self = shift;
+ return $self->{current_mfn};
+};
+
+
=head2 to_ascii
Returns ASCII output of record with specified MFN
my $mfn = shift || croak "need MFN";
- my $rec = $self->fetch($mfn);
+ my $rec = $self->fetch($mfn) || return;
my $out = "0\t$mfn";
}
],
+In case there are repeatable subfields in record, this will create
+following structure:
+
+ '900' => [ {
+ 'a' => [ 'foo', 'bar', 'baz' ],
+ }]
+
+Or in more complex example of
+
+ 902 ^aa1^aa2^aa3^bb1^aa4^bb2^cc1^aa5
+
+it will create
+
+ 902 => [
+ { a => ["a1", "a2", "a3", "a4", "a5"], b => ["b1", "b2"], c => "c1" },
+ ],
+
+This behaviour can be changed using C<join_subfields_with> option to L</new>,
+in which case C<to_hash> will always create single value for each subfield.
+This will change result to:
+
+
+
This method will also create additional field C<000> with MFN.
+There is also more elaborative way to call C<to_hash> like this:
+
+ my $hash = $isis->to_hash({
+ mfn => 42,
+ include_subfields => 1,
+ });
+
+Each option controll creation of hash:
+
+=over 4
+
+=item mfn
+
+Specify MFN number of record
+
+=item include_subfields
+
+This option will create additional key in hash called C<subfields> which will
+have original record subfield order and index to that subfield like this:
+
+ 902 => [ {
+ a => ["a1", "a2", "a3", "a4", "a5"],
+ b => ["b1", "b2"],
+ c => "c1",
+ subfields => ["a", 0, "a", 1, "a", 2, "b", 0, "a", 3, "b", 1, "c", 0, "a", 4],
+ } ],
+
+=item join_subfields_with
+
+Define delimiter which will be used to join repeatable subfields. You can
+specify option here instead in L</new> if you want to have per-record control.
+
+=item hash_filter
+
+You can override C<hash_filter> defined in L</new> using this option.
+
+=back
+
=cut
sub to_hash {
my $self = shift;
+
my $mfn = shift || confess "need mfn!";
+ my $arg;
+
+ my $hash_filter = $self->{hash_filter};
+
+ if (ref($mfn) eq 'HASH') {
+ $arg = $mfn;
+ $mfn = $arg->{mfn} || confess "need mfn in arguments";
+ $hash_filter = $arg->{hash_filter} if ($arg->{hash_filter});
+ }
# init record to include MFN as field 000
my $rec = { '000' => [ $mfn ] };
- my $row = $self->fetch($mfn);
+ my $row = $self->fetch($mfn) || return;
+
+ my $j_rs = $arg->{join_subfields_with} || $self->{join_subfields_with};
+ $j_rs = $self->{join_subfields_with} unless(defined($j_rs));
+ my $i_sf = $arg->{include_subfields};
- foreach my $k (keys %{$row}) {
- foreach my $l (@{$row->{$k}}) {
+ foreach my $f_nr (keys %{$row}) {
+ foreach my $l (@{$row->{$f_nr}}) {
# filter output
- $l = $self->{'hash_filter'}->($l) if ($self->{'hash_filter'});
+ $l = $hash_filter->($l, $f_nr) if ($hash_filter);
+ next unless defined($l);
my $val;
+ my $r_sf; # repeatable subfields in this record
# has identifiers?
($val->{'i1'},$val->{'i2'}) = ($1,$2) if ($l =~ s/^([01 #])([01 #])\^/\^/);
if ($l =~ m/\^/) {
foreach my $t (split(/\^/,$l)) {
next if (! $t);
- $val->{substr($t,0,1)} = substr($t,1);
+ my ($sf,$v) = (substr($t,0,1), substr($t,1));
+ # XXX this might be option, but why?
+ next unless (defined($v) && $v ne '');
+# warn "### $f_nr^$sf:$v",$/ if ($self->{debug} > 1);
+
+ if (ref( $val->{$sf} ) eq 'ARRAY') {
+
+ push @{ $val->{$sf} }, $v;
+
+ # record repeatable subfield it it's offset
+ push @{ $val->{subfields} }, ( $sf, $#{ $val->{$sf} } ) if (! $j_rs && $i_sf);
+ $r_sf->{$sf}++;
+
+ } elsif (defined( $val->{$sf} )) {
+
+ # convert scalar field to array
+ $val->{$sf} = [ $val->{$sf}, $v ];
+
+ push @{ $val->{subfields} }, ( $sf, 1 ) if (! $j_rs && $i_sf);
+ $r_sf->{$sf}++;
+
+ } else {
+ $val->{$sf} = $v;
+ push @{ $val->{subfields} }, ( $sf, 0 ) if ($i_sf);
+ }
}
} else {
$val = $l;
}
- push @{$rec->{$k}}, $val;
+ if ($j_rs) {
+ map {
+ $val->{$_} = join($j_rs, @{ $val->{$_} });
+ } keys %$r_sf
+ }
+
+ push @{$rec->{$f_nr}}, $val;
}
}
tested this against ouput of one C<isis.dll>-based application, but I don't
know any details about it's version.
+=head1 VERSIONS
+
+As this is young module, new features are added in subsequent version. It's
+a good idea to specify version when using this module like this:
+
+ use Biblio::Isis 0.23
+
+Below is list of changes in specific version of module (so you can target
+older versions if you really have to):
+
+=over 8
+
+=item 0.24
+
+Added C<ignore_empty_subfields>
+
+=item 0.23
+
+Added C<hash_filter> to L</to_hash>
+
+Fixed bug with documented C<join_subfields_with> in L</new> which wasn't
+implemented
+
+=item 0.22
+
+Added field number when calling C<hash_filter>
+
+=item 0.21
+
+Added C<join_subfields_with> to L</new> and L</to_hash>.
+
+Added C<include_subfields> to L</to_hash>.
+
+=item 0.20
+
+Added C<< $isis->mfn >>, support for repeatable subfields and
+C<< $isis->to_hash({ mfn => 42, ... }) >> calling convention
+
+=back
+
=head1 AUTHOR
Dobrica Pavlinusic
=head1 SEE ALSO
+L<Biblio::Isis::Manual> for CDS/ISIS manual appendix F, G and H which describe file format
+
OpenIsis web site L<http://www.openisis.org>
perl4lib site L<http://perl4lib.perl.org>