/[webpac2]/trunk/lib/WebPAC/Normalize.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/WebPAC/Normalize.pm

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

revision 538 by dpavlin, Thu Jun 29 15:29:19 2006 UTC revision 551 by dpavlin, Fri Jun 30 20:43:09 2006 UTC
# Line 5  use Exporter 'import'; Line 5  use Exporter 'import';
5          _get_ds _clean_ds          _get_ds _clean_ds
6    
7          tag search display          tag search display
8            marc marc_indicators marc_repeatable_subfield
9    
10          rec1 rec2 rec          rec1 rec2 rec
11          regex prefix suffix surround          regex prefix suffix surround
12          first lookup join_with          first lookup join_with
# Line 14  use warnings; Line 16  use warnings;
16  use strict;  use strict;
17    
18  #use base qw/WebPAC::Common/;  #use base qw/WebPAC::Common/;
19  use Data::Dumper;  use Data::Dump qw/dump/;
20    use Encode qw/from_to/;
21    
22    # debugging warn(s)
23    my $debug = 0;
24    
25    
26  =head1 NAME  =head1 NAME
27    
# Line 22  WebPAC::Normalize - describe normalisato Line 29  WebPAC::Normalize - describe normalisato
29    
30  =head1 VERSION  =head1 VERSION
31    
32  Version 0.05  Version 0.06
33    
34  =cut  =cut
35    
36  our $VERSION = '0.05';  our $VERSION = '0.06';
37    
38  =head1 SYNOPSIS  =head1 SYNOPSIS
39    
# Line 39  means that you check it's validity befor Line 46  means that you check it's validity befor
46  C<perl -c normalize.pl>.  C<perl -c normalize.pl>.
47    
48  Normalisation can generate multiple output normalized data. For now, supported output  Normalisation can generate multiple output normalized data. For now, supported output
49  types (on the left side of definition) are: C<tag>, C<display> and C<search>.  types (on the left side of definition) are: C<tag>, C<display>, C<search> and
50    C<marc>.
51    
52  =head1 FUNCTIONS  =head1 FUNCTIONS
53    
# Line 54  Return data structure Line 62  Return data structure
62          lookup => $lookup->lookup_hash,          lookup => $lookup->lookup_hash,
63          row => $row,          row => $row,
64          rules => $normalize_pl_config,          rules => $normalize_pl_config,
65            marc_encoding => 'utf-8',
66    );    );
67    
68    Options C<lookup>, C<row>, C<rules> and C<log> are mandatory while all
69    other are optional.
70    
71  This function will B<die> if normalizastion can't be evaled.  This function will B<die> if normalizastion can't be evaled.
72    
73  Since this function isn't exported you have to call it with  Since this function isn't exported you have to call it with
# Line 72  sub data_structure { Line 84  sub data_structure {
84          no strict 'subs';          no strict 'subs';
85          _set_lookup( $arg->{lookup} );          _set_lookup( $arg->{lookup} );
86          _set_rec( $arg->{row} );          _set_rec( $arg->{row} );
87          _clean_ds();          _clean_ds( %{ $arg } );
88          eval "$arg->{rules}";          eval "$arg->{rules}";
89          die "error evaling $arg->{rules}: $@\n" if ($@);          die "error evaling $arg->{rules}: $@\n" if ($@);
90    
91          return _get_ds();          return _get_ds();
92  }  }
93    
# Line 100  Return hash formatted as data structure Line 113  Return hash formatted as data structure
113    
114  =cut  =cut
115    
116  my $out;  my ($out,$marc_record, $marc_encoding, $marc_repeatable_subfield, $marc_indicators);
117    
118  sub _get_ds {  sub _get_ds {
119          return $out;          return $out;
# Line 115  Clean data structure hash for next recor Line 128  Clean data structure hash for next recor
128  =cut  =cut
129    
130  sub _clean_ds {  sub _clean_ds {
131          $out = undef;          my $a = {@_};
132            ($out,$marc_record, $marc_encoding, $marc_repeatable_subfield, $marc_indicators) = ();
133            $marc_encoding = $a->{marc_encoding};
134  }  }
135    
136  =head2 _set_lookup  =head2 _set_lookup
# Line 132  sub _set_lookup { Line 147  sub _set_lookup {
147          $lookup = shift;          $lookup = shift;
148  }  }
149    
150    =head2 _get_marc_fields
151    
152    Get all fields defined by calls to C<marc>
153    
154            $marc->add_fields( WebPAC::Normalize:_get_marc_fields() );
155    
156    
157    
158    We are using I<magic> which detect repeatable fields only from
159    sequence of field/subfield data generated by normalization.
160    
161    Repeatable field is created if there is second occurence of same subfield or
162    if any of indicators are different. This is sane for most cases except for
163    non-repeatable fields with repeatable subfields.
164    
165    You can change behaviour of that using C<marc_repeatable_subfield>.
166    
167    =cut
168    
169    sub _get_marc_fields {
170    
171            return if (! $marc_record || ref($marc_record) ne 'ARRAY' || $#{ $marc_record } < 0);
172    
173            # first, sort all existing fields
174            # XXX might not be needed, but modern perl might randomize elements in hash
175            my @sorted_marc_record = sort {
176                    $a->[0] . $a->[3] cmp $b->[0] . $b->[3]
177            } @{ $marc_record };
178    
179            # output marc fields
180            my @m;
181    
182            # count unique field-subfields (used for offset when walking to next subfield)
183            my $u;
184            map { $u->{ $_->[0] . $_->[3]  }++ } @sorted_marc_record;
185    
186            if ($debug) {
187                    warn "## marc_repeatable_subfield ", dump( $marc_repeatable_subfield ), $/;
188                    warn "## marc_record ", dump( $marc_record ), $/;
189                    warn "## sorted_marc_record ", dump( \@sorted_marc_record ), $/;
190                    warn "## subfield count ", dump( $u ), $/;
191            }
192    
193            my $len = $#sorted_marc_record;
194            my $visited;
195            my $i = 0;
196            my $field;
197    
198            foreach ( 0 .. $len ) {
199    
200                    # find next element which isn't visited
201                    while ($visited->{$i}) {
202                            $i = ($i + 1) % ($len + 1);
203                    }
204    
205                    # mark it visited
206                    $visited->{$i}++;
207    
208                    my $row = $sorted_marc_record[$i];
209    
210                    # field and subfield which is key for
211                    # marc_repeatable_subfield and u
212                    my $fsf = $row->[0] . $row->[3];
213    
214                    if ($debug > 1) {
215    
216                            print "### field so far [", $#$field, "] : ", dump( $field ), " ", $field ? 'T' : 'F', $/;
217                            print "### this [$i]: ", dump( $row ),$/;
218                            print "### sf: ", $row->[3], " vs ", $field->[3],
219                                    $marc_repeatable_subfield->{ $row->[0] . $row->[3] } ? ' (repeatable)' : '', $/,
220                                    if ($#$field >= 0);
221    
222                    }
223    
224                    # if field exists
225                    if ( $#$field >= 0 ) {
226                            if (
227                                    $row->[0] ne $field->[0] ||             # field
228                                    $row->[1] ne $field->[1] ||             # i1
229                                    $row->[2] ne $field->[2]                # i2
230                            ) {
231                                    push @m, $field;
232                                    warn "## saved/1 ", dump( $field ),$/ if ($debug);
233                                    $field = $row;
234    
235                            } elsif (
236                                    ( $row->[3] lt $field->[-2] )           # subfield which is not next (e.g. a after c)
237                                    ||
238                                    ( $row->[3] eq $field->[-2] &&          # same subfield, but not repeatable
239                                            ! $marc_repeatable_subfield->{ $fsf }
240                                    )
241                            ) {
242                                    push @m, $field;
243                                    warn "## saved/2 ", dump( $field ),$/ if ($debug);
244                                    $field = $row;
245    
246                            } else {
247                                    # append new subfields to existing field
248                                    push @$field, ( $row->[3], $row->[4] );
249                            }
250                    } else {
251                            # insert first field
252                            $field = $row;
253                    }
254    
255                    if (! $marc_repeatable_subfield->{ $fsf }) {
256                            # make step to next subfield
257                            $i = ($i + $u->{ $fsf } ) % ($len + 1);
258                    }
259            }
260    
261            if ($#$field >= 0) {
262                    push @m, $field;
263                    warn "## saved/3 ", dump( $field ),$/ if ($debug);
264            }
265    
266            return @m;
267    }
268    
269    =head1 Functions to create C<data_structure>
270    
271    Those functions generally have to first in your normalization file.
272    
273  =head2 tag  =head2 tag
274    
275  Define new tag for I<search> and I<display>.  Define new tag for I<search> and I<display>.
# Line 182  sub search { Line 320  sub search {
320          $out->{$name}->{search} = \@o;          $out->{$name}->{search} = \@o;
321  }  }
322    
323    =head2 marc
324    
325    Save value for MARC field
326    
327      marc('900','a', rec('200','a') );
328    
329    =cut
330    
331    sub marc {
332            my $f = shift or die "marc needs field";
333            die "marc field must be numer" unless ($f =~ /^\d+$/);
334    
335            my $sf = shift or die "marc needs subfield";
336    
337            foreach (@_) {
338                    my $v = $_;             # make var read-write for Encode
339                    next unless (defined($v) && $v !~ /^\s*$/);
340                    from_to($v, 'iso-8859-2', $marc_encoding) if ($marc_encoding);
341                    my ($i1,$i2) = defined($marc_indicators->{$f}) ? @{ $marc_indicators->{$f} } : (' ',' ');
342                    push @{ $marc_record }, [ $f, $i1, $i2, $sf => $v ];
343            }
344    }
345    
346    =head2 marc_repeatable_subfield
347    
348    Save values for MARC repetable subfield
349    
350      marc_repeatable_subfield('910', 'z', rec('909') );
351    
352    =cut
353    
354    sub marc_repeatable_subfield {
355            my ($f,$sf) = @_;
356            die "marc_repeatable_subfield need field and subfield!\n" unless ($f && $sf);
357            $marc_repeatable_subfield->{ $f . $sf }++;
358            marc(@_);
359    }
360    
361    =head2 marc_indicators
362    
363    Set both indicators for MARC field
364    
365      marc_indicators('900', ' ', 1);
366    
367    Any indicator value other than C<0-9> will be treated as undefined.
368    
369    =cut
370    
371    sub marc_indicators {
372            my $f = shift || die "marc_indicators need field!\n";
373            my ($i1,$i2) = @_;
374            die "marc_indicators($f, ...) need i1!\n" unless(defined($i1));
375            die "marc_indicators($f, $i1, ...) need i2!\n" unless(defined($i2));
376    
377            $i1 = ' ' if ($i1 !~ /^\d$/);
378            $i2 = ' ' if ($i2 !~ /^\d$/);
379            @{ $marc_indicators->{$f} } = ($i1,$i2);
380    }
381    
382    
383    =head1 Functions to extract data from input
384    
385    This function should be used inside functions to create C<data_structure> described
386    above.
387    
388  =head2 rec1  =head2 rec1
389    
390  Return all values in some field  Return all values in some field
# Line 251  Apply regex to some or all values Line 454  Apply regex to some or all values
454  sub regex {  sub regex {
455          my $r = shift;          my $r = shift;
456          my @out;          my @out;
457          #warn "r: $r\n",Dumper(\@_);          #warn "r: $r\n", dump(\@_);
458          foreach my $t (@_) {          foreach my $t (@_) {
459                  next unless ($t);                  next unless ($t);
460                  eval "\$t =~ $r";                  eval "\$t =~ $r";
Legend:
Removed from v.538  
changed lines
  Added in v.551
  ViewVC Help
Powered by ViewVC 1.1.26