/[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 17 by dpavlin, Thu Jun 21 10:24:12 2007 UTC revision 31 by dpavlin, Thu Feb 4 17:09:49 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     = 0.07;          $VERSION     = 0.09;
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( $mfn );
32      }
33    
34    For longer example with command line options look at L<scripts/dump_fastmarc.pl>
35    
36  =head1 DESCRIPTION  =head1 DESCRIPTION
37    
38  This is very fast alternative to C<MARC> and C<MARC::Record> modules.  This is very fast alternative to C<MARC> and C<MARC::Record> modules.
39    
40  It's is also very sutable for random access to MARC records (as opposed to  It's is also very subtable for random access to MARC records (as opposed to
41  sequential one).  sequential one).
42    
43  =head1 METHODS  =head1 METHODS
# Line 79  sub new { Line 88  sub new {
88    
89                  if ($len < 24) {                  if ($len < 24) {
90                          carp "short read of leader, aborting\n";                          carp "short read of leader, aborting\n";
91                            $self->{count}--;
92                          last;                          last;
93                  }                  }
94    
# Line 111  sub new { Line 121  sub new {
121                  print STDERR "REC ",$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                  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 145  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 234  sub fetch { Line 253  sub fetch {
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  =head2 to_hash
277    
278  Read record with specified MFN and convert it to hash  Read record with specified MFN and convert it to hash
279    
280    my $hash = $marc->to_hash($mfn);    my $hash = $marc->to_hash( $mfn, include_subfields => 1, );
281    
282  It has ability to convert characters (using C<hash_filter>) from MARC  It has ability to convert characters (using C<hash_filter>) from MARC
283  database before creating structures enabling character re-mapping or quick  database before creating structures enabling character re-mapping or quick
# Line 265  sub to_hash { Line 304  sub to_hash {
304    
305          my $mfn = shift || confess "need mfn!";          my $mfn = shift || confess "need mfn!";
306    
307            my $args = {@_};
308    
309          # init record to include MFN as field 000          # init record to include MFN as field 000
310          my $rec = { '000' => [ $mfn ] };          my $rec = { '000' => [ $mfn ] };
311    
# Line 284  sub to_hash { Line 325  sub to_hash {
325                          # has identifiers?                          # has identifiers?
326                          ($val->{'i1'},$val->{'i2'}) = ($1,$2) if ($l =~ s/^([01 #])([01 #])\x1F/\x1F/);                          ($val->{'i1'},$val->{'i2'}) = ($1,$2) if ($l =~ s/^([01 #])([01 #])\x1F/\x1F/);
327    
328                            my $sf_usage;
329                            my @subfields;
330    
331                          # has subfields?                          # has subfields?
332                          if ($l =~ m/\x1F/) {                          if ($l =~ m/\x1F/) {
333                                  foreach my $t (split(/\x1F/,$l)) {                                  foreach my $t (split(/\x1F/,$l)) {
334                                          next if (! $t);                                          next if (! $t);
335                                          my $f = substr($t,0,1);                                          my $f = substr($t,0,1);
336                                          # repeatable subfileds. When we hit first one,  
337                                          # store CURRENT (up to that) in first repetition                                          push @subfields, ( $f, $sf_usage->{$f}++ || 0 );
338                                          # of this record. Then, new record with same  
339                                          # identifiers will be created.                                          # repeatable subfiled -- convert it to array
340                                          if ($val->{$f}) {                                          if ($val->{$f}) {
341                                                  push @{$rec->{$rec_nr}}, $val;                                                  if ( ref($val->{$f}) ne 'ARRAY' ) {
342                                                  $val = {                                                          $val->{$f} = [ $val->{$f}, $val ];
343                                                          i1 => $val->{i1},                                                  } else {
344                                                          i2 => $val->{i2},                                                          push @{$val->{$f}}, $val;
345                                                  };                                                  }
346                                          }                                          }
347                                          $val->{substr($t,0,1)} = substr($t,1);                                          $val->{substr($t,0,1)} = substr($t,1);
348                                  }                                  }
349                                    $val->{subfields} = [ @subfields ] if $args->{include_subfields};
350                          } else {                          } else {
351                                  $val = $l;                                  $val = $l;
352                          }                          }
# Line 340  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.17  
changed lines
  Added in v.31

  ViewVC Help
Powered by ViewVC 1.1.26