/[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

trunk/Fast.pm revision 1 by dpavlin, Tue Jan 4 10:26:07 2005 UTC trunk/lib/MARC/Fast.pm revision 39 by dpavlin, Thu Sep 23 12:55:35 2010 UTC
# Line 1  Line 1 
   
1  package MARC::Fast;  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     = 0.01;          $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 23  MARC::Fast - Very fast implementation of Line 23  MARC::Fast - Very fast implementation of
23    
24    use MARC::Fast;    use MARC::Fast;
25    
26      my $marc = new MARC::Fast(
27            marcdb => 'unimarc.iso',
28      );
29    
30      foreach my $mfn ( 1 .. $marc->count ) {
31            print $marc->to_ascii( $mfn );
32      }
33    
34    For longer example with command line options look at L<scripts/dump_fastmarc.pl>
35    
36  =head1 DESCRIPTION  =head1 DESCRIPTION
37    
38  This is very fast alternative to C<MARC> and C<MARC::Record> modules.  This is very fast alternative to C<MARC> and C<MARC::Record> modules.
39    
40  It's is also very sutable for random access to MARC records (as opposed to  It's is also very subtable for random access to MARC records (as opposed to
41  sequential one).  sequential one).
42    
43  =head1 METHODS  =head1 METHODS
# Line 42  Read MARC database Line 51  Read MARC database
51          quiet => 0,          quiet => 0,
52          debug => 0,          debug => 0,
53          assert => 0,          assert => 0,
54            hash_filter => sub {
55                    my ($t, $record_number) = @_;
56                    $t =~ s/foo/bar/;
57                    return $t;
58            },
59    );    );
60    
61  =cut  =cut
# Line 59  sub new { Line 73  sub new {
73          print STDERR "# opening ",$self->{marcdb},"\n" if ($self->{debug});          print STDERR "# opening ",$self->{marcdb},"\n" if ($self->{debug});
74    
75          open($self->{fh}, $self->{marcdb}) || croak "can't open ",$self->{marcdb},": $!";          open($self->{fh}, $self->{marcdb}) || croak "can't open ",$self->{marcdb},": $!";
76            binmode($self->{fh});
77    
78          $self->{count} = 0;          $self->{count} = 0;
79    
# Line 69  sub new { Line 84  sub new {
84                  push @{$self->{fh_offset}}, tell($self->{fh});                  push @{$self->{fh_offset}}, tell($self->{fh});
85    
86                  my $leader;                  my $leader;
87                  read($self->{fh}, $leader, 24);                  my $len = read($self->{fh}, $leader, 24);
88    
89                    if ($len < 24) {
90                            warn "short read of leader, aborting\n";
91                            $self->{count}--;
92                            last;
93                    }
94    
95                  # Byte        Name                  # Byte        Name
96                  # ----        ----                  # ----        ----
# Line 100  sub new { Line 121  sub new {
121                  print STDERR "REC ",$self->{count},": $leader\n" if ($self->{debug});                  print STDERR "REC ",$self->{count},": $leader\n" if ($self->{debug});
122    
123                  # store leader for later                  # store leader for later
124                  push @{$self->{leaders}}, $leader;                  push @{$self->{leader}}, $leader;
125    
126                  # skip to next record                  # skip to next record
127                  seek($self->{fh},substr($leader,0,5)-24,1);                  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 ($o > 24) {
130                            seek($self->{fh},$o-24,1) if ($o);
131                    } else {
132                            last;
133                    }
134    
135          }          }
136    
# Line 129  Fetch record from database Line 156  Fetch record from database
156    
157    my $hash = $marc->fetch(42);    my $hash = $marc->fetch(42);
158    
159    First record number is C<1>
160    
161  =cut  =cut
162    
163  sub fetch {  sub fetch {
164          my $self = shift;          my $self = shift;
165    
166          my $rec_nr = shift || return;          my $rec_nr = shift;
167    
168            if ( ! $rec_nr ) {
169                    $self->{last_leader} = undef;
170                    return;
171            }
172    
173          my $leader = $self->{leaders}->[$rec_nr - 1];          my $leader = $self->{leader}->[$rec_nr - 1];
174            $self->{last_leader} = $leader;
175          unless ($leader) {          unless ($leader) {
176                  carp "can't find record $rec_nr";                  carp "can't find record $rec_nr";
177                  return;                  return;
# Line 196  sub fetch { Line 231  sub fetch {
231                  my $f = substr($fields,$addr,$len);                  my $f = substr($fields,$addr,$len);
232                  print STDERR "tag/len/addr $tag [$len] $addr: '$f'\n" if ($self->{debug});                  print STDERR "tag/len/addr $tag [$len] $addr: '$f'\n" if ($self->{debug});
233    
234                  $row->{$tag} = $f;                  push @{ $row->{$tag} }, $f;
235    
236                  my $del = substr($fields,$addr+$len-1,1);                  my $del = substr($fields,$addr+$len-1,1);
237    
# Line 217  sub fetch { Line 252  sub fetch {
252          return $row;          return $row;
253  }  }
254    
255    
256    =head2 last_leader
257    
258    Returns leader of last record L<fetch>ed
259    
260      print $marc->last_leader;
261    
262    Added in version 0.08 of this module, so if you need it use:
263    
264      use MARC::Fast 0.08;
265    
266    to be sure that it's supported.
267    
268    =cut
269    
270    sub last_leader {
271            my $self = shift;
272            return $self->{last_leader};
273    }
274    
275    
276    =head2 to_hash
277    
278    Read record with specified MFN and convert it to hash
279    
280      my $hash = $marc->to_hash( $mfn, include_subfields => 1, );
281    
282    It has ability to convert characters (using C<hash_filter>) from MARC
283    database before creating structures enabling character re-mapping or quick
284    fix-up of data.
285    
286    This function returns hash which is like this:
287    
288      '200' => [
289                 {
290                   'i1' => '1',
291                   'i2' => ' '
292                   'a' => 'Goa',
293                   'f' => 'Valdo D\'Arienzo',
294                   'e' => 'tipografie e tipografi nel XVI secolo',
295                 }
296               ],
297    
298    This method will also create additional field C<000> with MFN.
299    
300    =cut
301    
302    sub to_hash {
303            my $self = shift;
304    
305            my $mfn = shift || confess "need mfn!";
306    
307            my $args = {@_};
308    
309            # init record to include MFN as field 000
310            my $rec = { '000' => [ $mfn ] };
311    
312            my $row = $self->fetch($mfn) || return;
313    
314            foreach my $tag (keys %{$row}) {
315                    foreach my $l (@{$row->{$tag}}) {
316    
317                            # remove end marker
318                            $l =~ s/\x1E$//;
319    
320                            # filter output
321                            $l = $self->{'hash_filter'}->($l, $tag) if ($self->{'hash_filter'});
322    
323                            my $val;
324    
325                            # has identifiers?
326                            ($val->{'i1'},$val->{'i2'}) = ($1,$2) if ($l =~ s/^([01 #])([01 #])\x1F/\x1F/);
327    
328                            my $sf_usage;
329                            my @subfields;
330    
331                            # has subfields?
332                            if ($l =~ m/\x1F/) {
333                                    foreach my $t (split(/\x1F/,$l)) {
334                                            next if (! $t);
335                                            my $f = substr($t,0,1);
336    
337                                            push @subfields, ( $f, $sf_usage->{$f}++ || 0 );
338    
339                                            # repeatable subfiled -- convert it to array
340                                            if ($val->{$f}) {
341                                                    if ( ref($val->{$f}) ne 'ARRAY' ) {
342                                                            $val->{$f} = [ $val->{$f}, $val ];
343                                                    } else {
344                                                            push @{$val->{$f}}, $val;
345                                                    }
346                                            }
347                                            $val->{substr($t,0,1)} = substr($t,1);
348                                    }
349                                    $val->{subfields} = [ @subfields ] if $args->{include_subfields};
350                            } else {
351                                    $val = $l;
352                            }
353    
354                            push @{$rec->{$tag}}, $val;
355                    }
356            }
357    
358            return $rec;
359    }
360    
361    =head2 to_ascii
362    
363      print $marc->to_ascii( 42 );
364    
365    =cut
366    
367    sub to_ascii {
368            my $self = shift;
369    
370            my $mfn = shift || confess "need mfn";
371            my $row = $self->fetch($mfn) || return;
372    
373            my $out;
374    
375            foreach my $f (sort keys %{$row}) {
376                    my $dump = join('', @{ $row->{$f} });
377                    $dump =~ s/\x1e$//;
378                    $dump =~ s/\x1f/\$/g;
379                    $out .= "$f\t$dump\n";
380            }
381    
382            return $out;
383    }
384    
385  1;  1;
386  __END__  __END__
387    
388  =head1 BUGS  =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  =head1 SUPPORT    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    
# Line 246  LICENSE file included with this module. Line 424  LICENSE file included with this module.
424    
425  =head1 SEE ALSO  =head1 SEE ALSO
426    
427  perl(1).  L<Biblio::Isis>, perl(1).
428    
429  =cut  =cut

Legend:
Removed from v.1  
changed lines
  Added in v.39

  ViewVC Help
Powered by ViewVC 1.1.26