/[Biblio-Isis]/trunk/lib/Biblio/Isis.pm
This is repository of my old source code which isn't updated any more. Go to git.rot13.org for current projects!
ViewVC logotype

Diff of /trunk/lib/Biblio/Isis.pm

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 12 by dpavlin, Wed Dec 29 20:10:11 2004 UTC revision 15 by dpavlin, Wed Dec 29 22:46:40 2004 UTC
# Line 7  use Data::Dumper; Line 7  use Data::Dumper;
7  BEGIN {  BEGIN {
8          use Exporter ();          use Exporter ();
9          use vars qw ($VERSION @ISA @EXPORT @EXPORT_OK %EXPORT_TAGS);          use vars qw ($VERSION @ISA @EXPORT @EXPORT_OK %EXPORT_TAGS);
10          $VERSION     = 0.04;          $VERSION     = 0.05;
11          @ISA         = qw (Exporter);          @ISA         = qw (Exporter);
12          #Give a hoot don't pollute, do not export more than needed by default          #Give a hoot don't pollute, do not export more than needed by default
13          @EXPORT      = qw ();          @EXPORT      = qw ();
# Line 18  BEGIN { Line 18  BEGIN {
18    
19  =head1 NAME  =head1 NAME
20    
21  IsisDB - Read CDS/ISIS database  IsisDB - Read CDS/ISIS, WinISIS and IsisMarc database
22    
23  =head1 SYNOPSIS  =head1 SYNOPSIS
24    
# Line 34  IsisDB - Read CDS/ISIS database Line 34  IsisDB - Read CDS/ISIS database
34    
35  =head1 DESCRIPTION  =head1 DESCRIPTION
36    
37  This module will read CDS/ISIS databases and create hash values out of it.  This module will read ISIS databases created by DOS CDS/ISIS, WinIsis or
38  It can be used as perl-only alternative to OpenIsis module.  IsisMarc. It can be used as perl-only alternative to OpenIsis module.
39    
40  This will module will always be slower that OpenIsis module which use C  It can create hash values from data in ISIS database (using C<to_hash>),
41  library. However, since it's written in perl, it's platform independent (so  ASCII dump (using C<to_ascii>) or just hash with field names and packed
42  you don't need C compiler), and can be easily modified.  values (like C<^asomething^belse>).
43    
44  Unique feature of this module is ability to C<include_deleted> records.  Unique feature of this module is ability to C<include_deleted> records.
45  It will also skip zero sized fields (OpenIsis has a bug in XS bindings, so  It will also skip zero sized fields (OpenIsis has a bug in XS bindings, so
46  fields which are zero sized will be filled with random junk from memory).  fields which are zero sized will be filled with random junk from memory).
47    
48    It also has support for identifiers (only if ISIS database is created by
49    IsisMarc), see C<to_hash>.
50    
51    This will module will always be slower than OpenIsis module which use C
52    library. However, since it's written in perl, it's platform independent (so
53    you don't need C compiler), and can be easily modified. I hope that it
54    creates data structures which are easier to use than ones created by
55    OpenIsis, so reduced time in other parts of the code should compensate for
56    slower performance of this module (speed of reading ISIS database is
57    rarely an issue).
58    
59  =head1 METHODS  =head1 METHODS
60    
61  =cut  =cut
# Line 65  fields which are zero sized will be fill Line 76  fields which are zero sized will be fill
76    
77  =head2 new  =head2 new
78    
79  Open CDS/ISIS database  Open ISIS database
80    
81   my $isis = new IsisDB(   my $isis = new IsisDB(
82          isisdb => './cds/cds',          isisdb => './cds/cds',
# Line 84  Options are described below: Line 95  Options are described below:
95    
96  =item isisdb  =item isisdb
97    
98  Prefix path to CDS/ISIS. It should contain full or relative path to database  This is full or relative path to ISIS database files which include
99  and common prefix of C<.FDT>, C<.MST>, C<.CNT>, C<.XRF> and C<.MST> files.  common prefix of C<.FDT>, C<.MST>, C<.CNT>, C<.XRF> and C<.MST> files.
100    
101    In this example it uses C<./cds/cds.MST> and related files.
102    
103  =item read_fdt  =item read_fdt
104    
# Line 214  sub new { Line 227  sub new {
227    
228          close(fileCNT);          close(fileCNT);
229    
230          print Dumper($self) if ($self->{debug});          print Dumper($self),"\n" if ($self->{debug});
231    
232          # open files for later          # open files for later
233          open($self->{'fileXRF'}, $self->{isisdb}.".XRF") || croak "can't open '$self->{isisdb}.XRF': $!";          open($self->{'fileXRF'}, $self->{isisdb}.".XRF") || croak "can't open '$self->{isisdb}.XRF': $!";
# Line 231  Read record with selected MFN Line 244  Read record with selected MFN
244    my $rec = $isis->fetch(55);    my $rec = $isis->fetch(55);
245    
246  Returns hash with keys which are field names and values are unpacked values  Returns hash with keys which are field names and values are unpacked values
247  for that field (like C<^asometing^bsomething else>)  for that field like this:
248    
249      $rec = {
250        '210' => [ '^aNew York^cNew York University press^dcop. 1988' ],
251        '990' => [ '2140', '88', 'HAY' ],
252      };
253    
254  =cut  =cut
255    
# Line 355  print ("Error: The MFN:".$mfn." is not f Line 373  print ("Error: The MFN:".$mfn." is not f
373          }          }
374          close(fileMST);          close(fileMST);
375    
376          print Dumper($self) if ($self->{debug});          print Dumper($self),"\n" if ($self->{debug});
377    
378          return $self->{'record'};          return $self->{'record'};
379  }  }
380    
381  =head2 to_ascii  =head2 to_ascii
382    
383  Dump ascii output of selected MFN  Dump ASCII output of record with specified MFN
384    
385    print $isis->to_ascii(55);    print $isis->to_ascii(42);
386    
387    It outputs something like this:
388    
389      210   ^aNew York^cNew York University press^dcop. 1988
390      990   2140
391      990   88
392      990   HAY
393    
394    If C<read_fdt> is specified when calling C<new> it will display field names
395    from C<.FDT> file instead of numeric tags.
396    
397  =cut  =cut
398    
# Line 378  sub to_ascii { Line 406  sub to_ascii {
406          my $out = "0\t$mfn";          my $out = "0\t$mfn";
407    
408          foreach my $f (sort keys %{$rec}) {          foreach my $f (sort keys %{$rec}) {
409                  $out .= "\n$f\t".join("\n$f\t",@{$self->{record}->{$f}});                  my $fn = $self->tag_name($f);
410                    $out .= "\n$fn\t".join("\n$fn\t",@{$self->{record}->{$f}});
411          }          }
412    
413          $out .= "\n";          $out .= "\n";
# Line 388  sub to_ascii { Line 417  sub to_ascii {
417    
418  =head2 to_hash  =head2 to_hash
419    
420  Read mfn and convert it to hash  Read record with specified MFN and convert it to hash
421    
422    my $hash = $isis->to_hash($mfn);    my $hash = $isis->to_hash($mfn);
423    
424  It has ability to convert characters (using C<hash_filter> from ISIS  It has ability to convert characters (using C<hash_filter> from ISIS
425  database before creating structures enabling character remapping or quick  database before creating structures enabling character re-mapping or quick
426  fixup of data.  fix-up of data.
427    
428  This function returns hash which is like this:  This function returns hash which is like this:
429    
# Line 413  This function returns hash which is like Line 442  This function returns hash which is like
442               ],               ],
443    };    };
444    
445  You can later use that has to produce any output from ISIS data.  You can later use that hash to produce any output from ISIS data.
446    
447    If database is created using IsisMarc, it will also have to special fields
448    which will be used for identifiers, C<i1> and C<i2> like this:
449    
450      '200' => [
451                 {
452                   'i1' => '1',
453                   'i2' => ' '
454                   'a' => 'Goa',
455                   'f' => 'Valdo D\'Arienzo',
456                   'e' => 'tipografie e tipografi nel XVI secolo',
457                 }
458               ],
459    
460    This method will also create additional field C<000> with MFN.
461    
462  =cut  =cut
463    
# Line 422  sub to_hash { Line 466  sub to_hash {
466    
467          my $mfn = shift || confess "need mfn!";          my $mfn = shift || confess "need mfn!";
468    
469          my $rec;          # init record to include MFN as field 000
470            my $rec = { '000' => $mfn };
471    
472          my $row = $self->fetch($mfn);          my $row = $self->fetch($mfn);
473    
474          foreach my $k (keys %{$row}) {          foreach my $k (keys %{$row}) {
# Line 431  sub to_hash { Line 477  sub to_hash {
477                          # filter output                          # filter output
478                          $l = $self->{'hash_filter'}->($l) if ($self->{'hash_filter'});                          $l = $self->{'hash_filter'}->($l) if ($self->{'hash_filter'});
479    
                         # has subfields?  
480                          my $val;                          my $val;
481    
482                            # has identifiers?
483                            ($val->{'i1'},$val->{'i2'}) = ($1,$2) if ($l =~ s/^([01 #])([01 #])//);
484    
485                            # has subfields?
486                          if ($l =~ m/\^/) {                          if ($l =~ m/\^/) {
487                                  foreach my $t (split(/\^/,$l)) {                                  foreach my $t (split(/\^/,$l)) {
488                                          next if (! $t);                                          next if (! $t);
# Line 449  sub to_hash { Line 499  sub to_hash {
499          return $rec;          return $rec;
500  }  }
501    
502  #  =head2 tag_name
 # XXX porting from php left-over:  
 #  
 # do I *REALLY* need those methods, or should I use  
 # $self->{something} directly?  
 #  
 # Probably direct usage is better!  
 #  
503    
504  sub TagName {  Return name of selected tag
505          my $self = shift;  
506          return $self->{TagName};   print $isis->tag_name('200');
 }  
507    
508  sub NextMFN {  =cut
509    
510    sub tag_name {
511          my $self = shift;          my $self = shift;
512          return $self->{NXTMFN};          my $tag = shift || return;
513            return $self->{'TagName'}->{$tag} || $tag;
514  }  }
515    
516  1;  1;
# Line 481  This module has been very lightly tested Line 526  This module has been very lightly tested
526          dpavlin@rot13.org          dpavlin@rot13.org
527          http://www.rot13.org/~dpavlin/          http://www.rot13.org/~dpavlin/
528    
529  This module is based heavily on code from LIBISIS.PHP - Library to read ISIS files V0.1.1  This module is based heavily on code from C<LIBISIS.PHP> library to read ISIS files V0.1.1
530  written in php and (c) 2000 Franck Martin - <franck@sopac.org> released under LGPL.  written in php and (c) 2000 Franck Martin <franck@sopac.org> and released under LGPL.
531    
532  =head1 COPYRIGHT  =head1 COPYRIGHT
533    
# Line 495  LICENSE file included with this module. Line 540  LICENSE file included with this module.
540    
541  =head1 SEE ALSO  =head1 SEE ALSO
542    
543  L<http://www.openisis.org|OpenIsis>, perl(1).  OpenIsis web site L<http://www.openisis.org>
544    
545    perl4lib site L<http://perl4lib.perl.org>
546    

Legend:
Removed from v.12  
changed lines
  Added in v.15

  ViewVC Help
Powered by ViewVC 1.1.26