3 |
use warnings; |
use warnings; |
4 |
use strict; |
use strict; |
5 |
|
|
6 |
|
use blib; |
7 |
|
|
8 |
use WebPAC::Common; |
use WebPAC::Common; |
9 |
use base qw/WebPAC::Common/; |
use base qw/WebPAC::Common/; |
|
use Text::Iconv; |
|
10 |
use Data::Dumper; |
use Data::Dumper; |
11 |
|
use Encode qw/from_to/; |
12 |
|
|
13 |
=head1 NAME |
=head1 NAME |
14 |
|
|
16 |
|
|
17 |
=head1 VERSION |
=head1 VERSION |
18 |
|
|
19 |
Version 0.03 |
Version 0.11 |
20 |
|
|
21 |
=cut |
=cut |
22 |
|
|
23 |
our $VERSION = '0.03'; |
our $VERSION = '0.11'; |
24 |
|
|
25 |
=head1 SYNOPSIS |
=head1 SYNOPSIS |
26 |
|
|
39 |
|
|
40 |
Perhaps a little code snippet. |
Perhaps a little code snippet. |
41 |
|
|
42 |
use WebPAC::Input; |
use WebPAC::Input; |
43 |
|
|
44 |
my $db = WebPAC::Input->new( |
my $db = WebPAC::Input->new( |
45 |
module => 'WebPAC::Input::ISIS', |
module => 'WebPAC::Input::ISIS', |
|
config => $config, |
|
|
lookup => $lookup_obj, |
|
46 |
low_mem => 1, |
low_mem => 1, |
47 |
); |
); |
48 |
|
|
49 |
$db->open('/path/to/database'); |
$db->open( path => '/path/to/database' ); |
50 |
print "database size: ",$db->size,"\n"; |
print "database size: ",$db->size,"\n"; |
51 |
while (my $rec = $db->fetch) { |
while (my $rec = $db->fetch) { |
52 |
} |
# do something with $rec |
53 |
|
} |
54 |
|
|
55 |
|
|
56 |
|
|
62 |
|
|
63 |
my $db = new WebPAC::Input( |
my $db = new WebPAC::Input( |
64 |
module => 'WebPAC::Input::MARC', |
module => 'WebPAC::Input::MARC', |
65 |
code_page => 'ISO-8859-2', |
encoding => 'ISO-8859-2', |
66 |
low_mem => 1, |
low_mem => 1, |
67 |
|
recode => 'char pairs', |
68 |
|
no_progress_bar => 1, |
69 |
); |
); |
70 |
|
|
71 |
C<module> is low-level file format module. See L<WebPAC::Input::Isis> and |
C<module> is low-level file format module. See L<WebPAC::Input::ISIS> and |
72 |
L<WebPAC::Input::MARC>. |
L<WebPAC::Input::MARC>. |
73 |
|
|
74 |
Optional parametar C<code_page> specify application code page (which will be |
Optional parametar C<encoding> specify application code page (which will be |
75 |
used internally). This should probably be your terminal encoding, and by |
used internally). This should probably be your terminal encoding, and by |
76 |
default, it C<ISO-8859-2>. |
default, it C<ISO-8859-2>. |
77 |
|
|
78 |
Default is not to use C<low_mem> options (see L<MEMORY USAGE> below). |
Default is not to use C<low_mem> options (see L<MEMORY USAGE> below). |
79 |
|
|
80 |
|
C<recode> is optional string constisting of character or words pairs that |
81 |
|
should be replaced in input stream. |
82 |
|
|
83 |
|
C<no_progress_bar> disables progress bar output on C<STDOUT> |
84 |
|
|
85 |
This function will also call low-level C<init> if it exists with same |
This function will also call low-level C<init> if it exists with same |
86 |
parametars. |
parametars. |
87 |
|
|
94 |
|
|
95 |
my $log = $self->_get_logger; |
my $log = $self->_get_logger; |
96 |
|
|
97 |
|
$log->logconfess("code_page argument is not suppored any more. change it to encoding") if ($self->{lookup}); |
98 |
|
$log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_ref") if ($self->{lookup}); |
99 |
|
|
100 |
$log->logconfess("specify low-level file format module") unless ($self->{module}); |
$log->logconfess("specify low-level file format module") unless ($self->{module}); |
101 |
my $module = $self->{module}; |
my $module = $self->{module}; |
102 |
$module =~ s#::#/#g; |
$module =~ s#::#/#g; |
122 |
$self->{init}->($self, @_); |
$self->{init}->($self, @_); |
123 |
} |
} |
124 |
|
|
125 |
$self->{'code_page'} ||= 'ISO-8859-2'; |
$self->{'encoding'} ||= 'ISO-8859-2'; |
126 |
|
|
127 |
# running with low_mem flag? well, use DBM::Deep then. |
# running with low_mem flag? well, use DBM::Deep then. |
128 |
if ($self->{'low_mem'}) { |
if ($self->{'low_mem'}) { |
159 |
|
|
160 |
$input->open( |
$input->open( |
161 |
path => '/path/to/database/file', |
path => '/path/to/database/file', |
162 |
code_page => '852', |
code_page => 'cp852', |
163 |
limit => 500, |
limit => 500, |
164 |
offset => 6000, |
offset => 6000, |
165 |
lookup => $lookup_obj, |
lookup => $lookup_obj, |
166 |
|
stats => 1, |
167 |
|
lookup_ref => sub { |
168 |
|
my ($k,$v) = @_; |
169 |
|
# store lookup $k => $v |
170 |
|
}, |
171 |
|
modify_records => { |
172 |
|
900 => { '^a' => { ' : ' => '^b' } }, |
173 |
|
901 => { '*' => { '^b' => ' ; ' } }, |
174 |
|
}, |
175 |
); |
); |
176 |
|
|
177 |
By default, C<code_page> is assumed to be C<852>. |
By default, C<code_page> is assumed to be C<cp852>. |
178 |
|
|
179 |
C<offset> is optional parametar to position at some offset before reading from database. |
C<offset> is optional parametar to position at some offset before reading from database. |
180 |
|
|
181 |
C<limit> is optional parametar to read just C<limit> records from database |
C<limit> is optional parametar to read just C<limit> records from database |
182 |
|
|
183 |
|
C<stats> create optional report about usage of fields and subfields |
184 |
|
|
185 |
|
C<lookup_coderef> is closure to call when adding C<< key => 'value' >> combinations to |
186 |
|
lookup. |
187 |
|
|
188 |
|
C<modify_records> specify mapping from subfields to delimiters or from |
189 |
|
delimiters to subfields, as well as oprations on fields (if subfield is |
190 |
|
defined as C<*>. |
191 |
|
|
192 |
Returns size of database, regardless of C<offset> and C<limit> |
Returns size of database, regardless of C<offset> and C<limit> |
193 |
parametars, see also C<size>. |
parametars, see also C<size>. |
194 |
|
|
200 |
|
|
201 |
my $log = $self->_get_logger(); |
my $log = $self->_get_logger(); |
202 |
|
|
203 |
|
$log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_coderef") if ($arg->{lookup}); |
204 |
|
$log->logconfess("lookup_coderef must be CODE, not ",ref($arg->{lookup_coderef})) |
205 |
|
if ($arg->{lookup_coderef} && ref($arg->{lookup_coderef}) ne 'CODE'); |
206 |
|
|
207 |
$log->logcroak("need path") if (! $arg->{'path'}); |
$log->logcroak("need path") if (! $arg->{'path'}); |
208 |
my $code_page = $arg->{'code_page'} || '852'; |
my $code_page = $arg->{'code_page'} || 'cp852'; |
209 |
|
|
210 |
# store data in object |
# store data in object |
211 |
$self->{'input_code_page'} = $code_page; |
$self->{'input_code_page'} = $code_page; |
213 |
$self->{$v} = $arg->{$v} if ($arg->{$v}); |
$self->{$v} = $arg->{$v} if ($arg->{$v}); |
214 |
} |
} |
215 |
|
|
216 |
# create Text::Iconv object |
my $filter_ref; |
217 |
$self->{iconv} = Text::Iconv->new($code_page,$self->{'code_page'}); |
my $recode_regex; |
218 |
|
my $recode_map; |
219 |
|
|
220 |
|
if ($self->{recode}) { |
221 |
|
my @r = split(/\s/, $self->{recode}); |
222 |
|
if ($#r % 2 != 1) { |
223 |
|
$log->logwarn("recode needs even number of elements (some number of valid pairs)"); |
224 |
|
} else { |
225 |
|
while (@r) { |
226 |
|
my $from = shift @r; |
227 |
|
my $to = shift @r; |
228 |
|
$recode_map->{$from} = $to; |
229 |
|
} |
230 |
|
|
231 |
|
$recode_regex = join '|' => keys %{ $recode_map }; |
232 |
|
|
233 |
|
$log->debug("using recode regex: $recode_regex"); |
234 |
|
} |
235 |
|
|
236 |
|
} |
237 |
|
|
238 |
|
my $rec_regex = $self->modify_record_regexps(%{ $arg->{modify_records} }); |
239 |
|
$log->debug("rec_regex: ", Dumper($rec_regex)); |
240 |
|
|
241 |
my ($db, $size) = $self->{open_db}->( $self, |
my ($db, $size) = $self->{open_db}->( $self, |
242 |
path => $arg->{path}, |
path => $arg->{path}, |
243 |
|
# filter => sub { |
244 |
|
# my ($l,$f_nr) = @_; |
245 |
|
# return unless defined($l); |
246 |
|
# from_to($l, $code_page, $self->{'encoding'}); |
247 |
|
# $l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map); |
248 |
|
# return $l; |
249 |
|
# }, |
250 |
|
%{ $arg }, |
251 |
); |
); |
252 |
|
|
253 |
unless ($db) { |
unless (defined($db)) { |
254 |
$log->logwarn("can't open database $arg->{path}, skipping..."); |
$log->logwarn("can't open database $arg->{path}, skipping..."); |
255 |
return; |
return; |
256 |
} |
} |
260 |
return; |
return; |
261 |
} |
} |
262 |
|
|
263 |
my $offset = 1; |
my $from_rec = 1; |
264 |
my $limit = $size; |
my $to_rec = $size; |
265 |
|
|
266 |
if (my $s = $self->{offset}) { |
if (my $s = $self->{offset}) { |
267 |
$log->info("skipping to MFN $s"); |
$log->debug("skipping to MFN $s"); |
268 |
$offset = $s; |
$from_rec = $s; |
269 |
} else { |
} else { |
270 |
$self->{offset} = $offset; |
$self->{offset} = $from_rec; |
271 |
} |
} |
272 |
|
|
273 |
if ($self->{limit}) { |
if ($self->{limit}) { |
274 |
$log->debug("limiting to ",$self->{limit}," records"); |
$log->debug("limiting to ",$self->{limit}," records"); |
275 |
$limit = $offset + $self->{limit} - 1; |
$to_rec = $from_rec + $self->{limit} - 1; |
276 |
$limit = $size if ($limit > $size); |
$to_rec = $size if ($to_rec > $size); |
277 |
} |
} |
278 |
|
|
279 |
# store size for later |
# store size for later |
280 |
$self->{size} = ($limit - $offset) ? ($limit - $offset + 1) : 0; |
$self->{size} = ($to_rec - $from_rec) ? ($to_rec - $from_rec + 1) : 0; |
281 |
|
|
282 |
$log->info("processing $self->{size} records in $code_page, convert to $self->{code_page}"); |
$log->info("processing $self->{size}/$size records [$from_rec-$to_rec] convert $code_page -> $self->{encoding}", $self->{stats} ? ' [stats]' : ''); |
283 |
|
|
284 |
# read database |
# read database |
285 |
for (my $pos = $offset; $pos <= $limit; $pos++) { |
for (my $pos = $from_rec; $pos <= $to_rec; $pos++) { |
286 |
|
|
287 |
$log->debug("position: $pos\n"); |
$log->debug("position: $pos\n"); |
288 |
|
|
289 |
my $rec = $self->{fetch_rec}->($self, $db, $pos ); |
my $rec = $self->{fetch_rec}->($self, $db, $pos, sub { |
290 |
|
my ($l,$f_nr) = @_; |
291 |
|
# return unless defined($l); |
292 |
|
# return $l unless ($rec_regex && $f_nr); |
293 |
|
|
294 |
|
warn "## --> $f_nr ## $l\n"; |
295 |
|
# codepage conversion and recode_regex |
296 |
|
# from_to($l, $code_page, $self->{'encoding'}); |
297 |
|
from_to($l, $code_page, 'utf-8'); |
298 |
|
$l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map); |
299 |
|
|
300 |
|
# apply regexps |
301 |
|
if ($rec_regex && defined($rec_regex->{$f_nr})) { |
302 |
|
$log->logconfess("regexps->{$f_nr} must be ARRAY") if (ref($rec_regex->{$f_nr}) ne 'ARRAY'); |
303 |
|
my $c = 0; |
304 |
|
foreach my $r (@{ $rec_regex->{$f_nr} }) { |
305 |
|
#$log->debug("\$l = $l\neval \$l =~ $r"); |
306 |
|
eval '$l =~ ' . $r; |
307 |
|
$log->error("error applying regex: $r") if ($@); |
308 |
|
} |
309 |
|
} |
310 |
|
|
311 |
|
warn "## <-- $f_nr ## $l\n"; |
312 |
|
return $l; |
313 |
|
}); |
314 |
|
|
315 |
$log->debug(sub { Dumper($rec) }); |
$log->debug(sub { Dumper($rec) }); |
316 |
|
|
327 |
} |
} |
328 |
|
|
329 |
# create lookup |
# create lookup |
330 |
$self->{'lookup'}->add( $rec ) if ($rec && $self->{'lookup'}); |
$arg->{'lookup_coderef'}->( $rec ) if ($rec && $arg->{'lookup_coderef'}); |
331 |
|
|
332 |
|
# update counters for statistics |
333 |
|
if ($self->{stats}) { |
334 |
|
|
335 |
|
# fetch clean record with regexpes applied for statistics |
336 |
|
my $rec = $self->{fetch_rec}->($self, $db, $pos); |
337 |
|
|
338 |
|
foreach my $fld (keys %{ $rec }) { |
339 |
|
$self->{_stats}->{fld}->{ $fld }++; |
340 |
|
|
341 |
|
$log->logdie("invalid record fild $fld, not ARRAY") |
342 |
|
unless (ref($rec->{ $fld }) eq 'ARRAY'); |
343 |
|
|
344 |
|
foreach my $row (@{ $rec->{$fld} }) { |
345 |
|
|
346 |
|
if (ref($row) eq 'HASH') { |
347 |
|
|
348 |
|
foreach my $sf (keys %{ $row }) { |
349 |
|
next if ($sf eq 'subfields'); |
350 |
|
$self->{_stats}->{sf}->{ $fld }->{ $sf }->{count}++; |
351 |
|
$self->{_stats}->{sf}->{ $fld }->{ $sf }->{repeatable}++ |
352 |
|
if (ref($row->{$sf}) eq 'ARRAY'); |
353 |
|
} |
354 |
|
|
355 |
|
} else { |
356 |
|
$self->{_stats}->{repeatable}->{ $fld }++; |
357 |
|
} |
358 |
|
} |
359 |
|
} |
360 |
|
} |
361 |
|
|
362 |
$self->progress_bar($pos,$limit); |
$self->progress_bar($pos,$to_rec) unless ($self->{no_progress_bar}); |
363 |
|
|
364 |
} |
} |
365 |
|
|
367 |
$self->{last_pcnt} = 0; |
$self->{last_pcnt} = 0; |
368 |
|
|
369 |
# store max mfn and return it. |
# store max mfn and return it. |
370 |
$self->{max_pos} = $limit; |
$self->{max_pos} = $to_rec; |
371 |
$log->debug("max_pos: $limit"); |
$log->debug("max_pos: $to_rec"); |
372 |
|
|
373 |
return $size; |
return $size; |
374 |
} |
} |
405 |
return; |
return; |
406 |
} |
} |
407 |
|
|
408 |
$self->progress_bar($mfn,$self->{max_pos}); |
$self->progress_bar($mfn,$self->{max_pos}) unless ($self->{no_progress_bar}); |
409 |
|
|
410 |
my $rec; |
my $rec; |
411 |
|
|
480 |
return $self->{pos} = (($pos - 1) || -1); |
return $self->{pos} = (($pos - 1) || -1); |
481 |
} |
} |
482 |
|
|
483 |
|
=head2 stats |
484 |
|
|
485 |
|
Dump statistics about field and subfield usage |
486 |
|
|
487 |
|
print $input->stats; |
488 |
|
|
489 |
|
=cut |
490 |
|
|
491 |
|
sub stats { |
492 |
|
my $self = shift; |
493 |
|
|
494 |
|
my $log = $self->_get_logger(); |
495 |
|
|
496 |
|
my $s = $self->{_stats}; |
497 |
|
if (! $s) { |
498 |
|
$log->warn("called stats, but there is no statistics collected"); |
499 |
|
return; |
500 |
|
} |
501 |
|
|
502 |
|
my $max_fld = 0; |
503 |
|
|
504 |
|
my $out = join("\n", |
505 |
|
map { |
506 |
|
my $f = $_ || die "no field"; |
507 |
|
my $v = $s->{fld}->{$f} || die "no s->{fld}->{$f}"; |
508 |
|
$max_fld = $v if ($v > $max_fld); |
509 |
|
|
510 |
|
my $o = sprintf("%4s %d ~", $f, $v); |
511 |
|
|
512 |
|
if (defined($s->{sf}->{$f})) { |
513 |
|
map { |
514 |
|
$o .= sprintf(" %s:%d%s", $_, |
515 |
|
$s->{sf}->{$f}->{$_}->{count}, |
516 |
|
$s->{sf}->{$f}->{$_}->{repeatable} ? '*' : '', |
517 |
|
); |
518 |
|
} sort keys %{ $s->{sf}->{$f} }; |
519 |
|
} |
520 |
|
|
521 |
|
if (my $v_r = $s->{repeatable}->{$f}) { |
522 |
|
$o .= " ($v_r)" if ($v_r != $v); |
523 |
|
} |
524 |
|
|
525 |
|
$o; |
526 |
|
} sort { $a cmp $b } keys %{ $s->{fld} } |
527 |
|
); |
528 |
|
|
529 |
|
$log->debug( sub { Dumper($s) } ); |
530 |
|
|
531 |
|
return $out; |
532 |
|
} |
533 |
|
|
534 |
|
=head2 modify_record_regexps |
535 |
|
|
536 |
|
Generate hash with regexpes to be applied using L<filter>. |
537 |
|
|
538 |
|
my $regexpes = $input->modify_record_regexps( |
539 |
|
900 => { '^a' => { ' : ' => '^b' } }, |
540 |
|
901 => { '*' => { '^b' => ' ; ' } }, |
541 |
|
); |
542 |
|
|
543 |
|
=cut |
544 |
|
|
545 |
|
sub modify_record_regexps { |
546 |
|
my $self = shift; |
547 |
|
my $modify_record = {@_}; |
548 |
|
|
549 |
|
my $regexpes; |
550 |
|
|
551 |
|
foreach my $f (keys %$modify_record) { |
552 |
|
warn "--- f: $f\n"; |
553 |
|
foreach my $sf (keys %{ $modify_record->{$f} }) { |
554 |
|
warn "---- sf: $sf\n"; |
555 |
|
foreach my $from (keys %{ $modify_record->{$f}->{$sf} }) { |
556 |
|
my $to = $modify_record->{$f}->{$sf}->{$from}; |
557 |
|
#die "no field?" unless defined($to); |
558 |
|
warn "----- transform: |$from| -> |$to|\n"; |
559 |
|
|
560 |
|
if ($sf =~ /^\^/) { |
561 |
|
my $regex = |
562 |
|
's/\Q'. $sf .'\E([^\^]+)\Q'. $from .'\E([^\^]+)/'. $sf .'$1'. $to .'$2/g'; |
563 |
|
push @{ $regexpes->{$f} }, $regex; |
564 |
|
warn ">>>>> $regex [sf]\n"; |
565 |
|
} else { |
566 |
|
my $regex = |
567 |
|
's/\Q'. $from .'\E/'. $to .'/g'; |
568 |
|
push @{ $regexpes->{$f} }, $regex; |
569 |
|
warn ">>>>> $regex [global]\n"; |
570 |
|
} |
571 |
|
|
572 |
|
} |
573 |
|
} |
574 |
|
} |
575 |
|
|
576 |
|
return $regexpes; |
577 |
|
} |
578 |
|
|
579 |
=head1 MEMORY USAGE |
=head1 MEMORY USAGE |
580 |
|
|
613 |
|
|
614 |
=head1 COPYRIGHT & LICENSE |
=head1 COPYRIGHT & LICENSE |
615 |
|
|
616 |
Copyright 2005 Dobrica Pavlinusic, All Rights Reserved. |
Copyright 2005-2006 Dobrica Pavlinusic, All Rights Reserved. |
617 |
|
|
618 |
This program is free software; you can redistribute it and/or modify it |
This program is free software; you can redistribute it and/or modify it |
619 |
under the same terms as Perl itself. |
under the same terms as Perl itself. |