/[MARC-Fast]/trunk/lib/MARC/Fast.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/MARC/Fast.pm

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

revision 24 by dpavlin, Tue Nov 6 20:06:07 2007 UTC revision 36 by dpavlin, Thu Sep 23 12:24:38 2010 UTC
# Line 2  package MARC::Fast; Line 2  package MARC::Fast;
2    
3  use strict;  use strict;
4  use Carp;  use Carp;
5  use Data::Dumper;  use Data::Dump qw/dump/;
6    
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     = 0.09;          $VERSION     = 0.10;
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 87  sub new { Line 87  sub new {
87                  my $len = read($self->{fh}, $leader, 24);                  my $len = read($self->{fh}, $leader, 24);
88    
89                  if ($len < 24) {                  if ($len < 24) {
90                          carp "short read of leader, aborting\n";                          warn "short read of leader, aborting\n";
91                            $self->{count}--;
92                          last;                          last;
93                  }                  }
94    
# Line 124  sub new { Line 125  sub new {
125    
126                  # skip to next record                  # skip to next record
127                  my $o = substr($leader,0,5);                  my $o = substr($leader,0,5);
128                    warn "# in record ", $self->{count}," record length isn't number but: ",dump($o),"\n" unless $o =~ m/^\d+$/;
129                  if ($o > 24) {                  if ($o > 24) {
130                          seek($self->{fh},$o-24,1) if ($o);                          seek($self->{fh},$o-24,1) if ($o);
131                  } else {                  } else {
# Line 309  sub to_hash { Line 311  sub to_hash {
311    
312          my $row = $self->fetch($mfn) || return;          my $row = $self->fetch($mfn) || return;
313    
314          foreach my $rec_nr (keys %{$row}) {          foreach my $tag (keys %{$row}) {
315                  foreach my $l (@{$row->{$rec_nr}}) {                  foreach my $l (@{$row->{$tag}}) {
316    
317                          # remove end marker                          # remove end marker
318                          $l =~ s/\x1E$//;                          $l =~ s/\x1E$//;
319    
320                          # filter output                          # filter output
321                          $l = $self->{'hash_filter'}->($l, $rec_nr) if ($self->{'hash_filter'});                          $l = $self->{'hash_filter'}->($l, $tag) if ($self->{'hash_filter'});
322    
323                          my $val;                          my $val;
324    
# Line 349  sub to_hash { Line 351  sub to_hash {
351                                  $val = $l;                                  $val = $l;
352                          }                          }
353    
354                          push @{$rec->{$rec_nr}}, $val;                          push @{$rec->{$tag}}, $val;
355                  }                  }
356          }          }
357    
# Line 383  sub to_ascii { Line 385  sub to_ascii {
385  1;  1;
386  __END__  __END__
387    
388    =head1 UTF-8 ENCODING
389    
390    This module does nothing with encoding. But, since MARC format is byte
391    oriented even when using UTF-8 which has variable number of bytes for each
392    character, file is opened in binary mode.
393    
394    As a result, all scalars recturned to perl don't have utf-8 flag. Solution is
395    to use C<hash_filter> and L<Encode> to decode utf-8 encoding like this:
396    
397      use Encode;
398    
399      my $marc = new MARC::Fast(
400            marcdb => 'utf8.marc',
401            hash_filter => sub {
402                    Encode::decode( 'utf-8', $_[0] );
403            },
404      );
405    
406    This will affect C<to_hash>, but C<fetch> will still return binary representation
407    since it doesn't support C<hash_filter>.
408    
409  =head1 AUTHOR  =head1 AUTHOR
410    
411          Dobrica Pavlinusic          Dobrica Pavlinusic
Legend:
Removed from v.24  
changed lines
  Added in v.36
  ViewVC Help
Powered by ViewVC 1.1.26