3 |
use warnings; |
use warnings; |
4 |
use strict; |
use strict; |
5 |
|
|
6 |
|
use blib; |
7 |
|
|
8 |
|
use WebPAC::Common; |
9 |
|
use base qw/WebPAC::Common/; |
10 |
|
use Text::Iconv; |
11 |
|
use Data::Dumper; |
12 |
|
|
13 |
=head1 NAME |
=head1 NAME |
14 |
|
|
15 |
WebPAC::Input - core module for input file format |
WebPAC::Input - read different file formats into WebPAC |
16 |
|
|
17 |
=head1 VERSION |
=head1 VERSION |
18 |
|
|
19 |
Version 0.01 |
Version 0.08 |
20 |
|
|
21 |
=cut |
=cut |
22 |
|
|
23 |
our $VERSION = '0.01'; |
our $VERSION = '0.08'; |
24 |
|
|
25 |
=head1 SYNOPSIS |
=head1 SYNOPSIS |
26 |
|
|
27 |
This module will load particular loader module and execute it's functions. |
This module implements input as database which have fixed and known |
28 |
|
I<size> while indexing and single unique numeric identifier for database |
29 |
|
position ranging from 1 to I<size>. |
30 |
|
|
31 |
|
Simply, something that is indexed by unmber from 1 .. I<size>. |
32 |
|
|
33 |
|
Examples of such databases are CDS/ISIS files, MARC files, lines in |
34 |
|
text file, and so on. |
35 |
|
|
36 |
|
Specific file formats are implemented using low-level interface modules, |
37 |
|
located in C<WebPAC::Input::*> namespace which export C<open_db>, |
38 |
|
C<fetch_rec> and optional C<init> functions. |
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( |
45 |
|
module => 'WebPAC::Input::ISIS', |
46 |
|
low_mem => 1, |
47 |
|
); |
48 |
|
|
49 |
|
$db->open( path => '/path/to/database' ); |
50 |
|
print "database size: ",$db->size,"\n"; |
51 |
|
while (my $rec = $db->fetch) { |
52 |
|
# do something with $rec |
53 |
|
} |
54 |
|
|
|
my $db = WebPAC::Input->new( |
|
|
format => 'NULL', |
|
|
config => $config, |
|
|
lookup => $lookup_obj, |
|
|
low_mem => 1, |
|
|
); |
|
55 |
|
|
|
$db->open('/path/to/database'); |
|
|
print "database size: ",$db->size,"\n"; |
|
|
while (my $row = $db->fetch) { |
|
|
... |
|
|
} |
|
|
$db->close; |
|
56 |
|
|
57 |
=head1 FUNCTIONS |
=head1 FUNCTIONS |
58 |
|
|
61 |
Create new input database object. |
Create new input database object. |
62 |
|
|
63 |
my $db = new WebPAC::Input( |
my $db = new WebPAC::Input( |
64 |
format => 'NULL' |
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 |
Optional parametar C<code_page> specify application code page (which will be |
C<module> is low-level file format module. See L<WebPAC::Input::ISIS> and |
72 |
|
L<WebPAC::Input::MARC>. |
73 |
|
|
74 |
|
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 |
86 |
|
parametars. |
87 |
|
|
88 |
=cut |
=cut |
89 |
|
|
90 |
sub new { |
sub new { |
91 |
my $class = shift; |
my $class = shift; |
92 |
my $self = {@_}; |
my $self = {@_}; |
93 |
bless($self, $class); |
bless($self, $class); |
94 |
|
|
|
$self->{'code_page'} ||= 'ISO-8859-2'; |
|
|
|
|
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}); |
101 |
|
my $module = $self->{module}; |
102 |
|
$module =~ s#::#/#g; |
103 |
|
$module .= '.pm'; |
104 |
|
$log->debug("require low-level module $self->{module} from $module"); |
105 |
|
|
106 |
|
require $module; |
107 |
|
#eval $self->{module} .'->import'; |
108 |
|
|
109 |
|
# check if required subclasses are implemented |
110 |
|
foreach my $subclass (qw/open_db fetch_rec init/) { |
111 |
|
my $n = $self->{module} . '::' . $subclass; |
112 |
|
if (! defined &{ $n }) { |
113 |
|
my $missing = "missing $subclass in $self->{module}"; |
114 |
|
$self->{$subclass} = sub { $log->logwarn($missing) }; |
115 |
|
} else { |
116 |
|
$self->{$subclass} = \&{ $n }; |
117 |
|
} |
118 |
|
} |
119 |
|
|
120 |
|
if ($self->{init}) { |
121 |
|
$log->debug("calling init"); |
122 |
|
$self->{init}->($self, @_); |
123 |
|
} |
124 |
|
|
125 |
|
$self->{'encoding'} ||= 'ISO-8859-2'; |
126 |
|
|
127 |
# running with low_mem flag? well, use DBM::Deep then. |
# running with low_mem flag? well, use DBM::Deep then. |
128 |
if ($self->{'low_mem'}) { |
if ($self->{'low_mem'}) { |
129 |
$log->info("running with low_mem which impacts performance (<32 Mb memory usage)"); |
$log->info("running with low_mem which impacts performance (<32 Mb memory usage)"); |
153 |
$self ? return $self : return undef; |
$self ? return $self : return undef; |
154 |
} |
} |
155 |
|
|
156 |
|
=head2 open |
157 |
|
|
158 |
|
This function will read whole database in memory and produce lookups. |
159 |
|
|
160 |
|
$input->open( |
161 |
|
path => '/path/to/database/file', |
162 |
|
code_page => '852', |
163 |
|
limit => 500, |
164 |
|
offset => 6000, |
165 |
|
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>. |
178 |
|
|
179 |
|
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 |
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> |
193 |
|
parametars, see also C<size>. |
194 |
|
|
195 |
|
=cut |
196 |
|
|
197 |
|
sub open { |
198 |
|
my $self = shift; |
199 |
|
my $arg = {@_}; |
200 |
|
|
201 |
|
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'}); |
208 |
|
my $code_page = $arg->{'code_page'} || '852'; |
209 |
|
|
210 |
|
# store data in object |
211 |
|
$self->{'input_code_page'} = $code_page; |
212 |
|
foreach my $v (qw/path offset limit/) { |
213 |
|
$self->{$v} = $arg->{$v} if ($arg->{$v}); |
214 |
|
} |
215 |
|
|
216 |
|
# create Text::Iconv object |
217 |
|
$self->{iconv} = Text::Iconv->new($code_page,$self->{'encoding'}); ## FIXME remove! |
218 |
|
|
219 |
|
my $filter_ref; |
220 |
|
my $recode_regex; |
221 |
|
my $recode_map; |
222 |
|
|
223 |
|
if ($self->{recode}) { |
224 |
|
my @r = split(/\s/, $self->{recode}); |
225 |
|
if ($#r % 2 != 1) { |
226 |
|
$log->logwarn("recode needs even number of elements (some number of valid pairs)"); |
227 |
|
} else { |
228 |
|
while (@r) { |
229 |
|
my $from = shift @r; |
230 |
|
my $to = shift @r; |
231 |
|
$recode_map->{$from} = $to; |
232 |
|
} |
233 |
|
|
234 |
|
$recode_regex = join '|' => keys %{ $recode_map }; |
235 |
|
|
236 |
|
$log->debug("using recode regex: $recode_regex"); |
237 |
|
} |
238 |
|
|
239 |
|
} |
240 |
|
|
241 |
|
my $rec_regex = $self->modify_record_regexps(%{ $arg->{modify_records} }); |
242 |
|
$log->debug("rec_regex: ", Dumper($rec_regex)); |
243 |
|
|
244 |
|
my ($db, $size) = $self->{open_db}->( $self, |
245 |
|
path => $arg->{path}, |
246 |
|
filter => sub { |
247 |
|
my ($l,$f_nr) = @_; |
248 |
|
return unless defined($l); |
249 |
|
|
250 |
|
## FIXME remove iconv! |
251 |
|
$l = $self->{iconv}->convert($l) if ($self->{iconv}); |
252 |
|
|
253 |
|
$l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map); |
254 |
|
|
255 |
|
return $l unless ($rec_regex); |
256 |
|
|
257 |
|
# apply regexps |
258 |
|
if ($rec_regex && defined($rec_regex->{$f_nr})) { |
259 |
|
$log->logconfess("regexps->{$f_nr} must be ARRAY") if (ref($rec_regex->{$f_nr}) ne 'ARRAY'); |
260 |
|
my $c = 0; |
261 |
|
foreach my $r (@{ $rec_regex->{$f_nr} }) { |
262 |
|
while ( eval '$l =~ ' . $r ) { $c++ }; |
263 |
|
} |
264 |
|
warn "## field $f_nr triggered $c regexpes\n" if ($c && $self->{debug}); |
265 |
|
} |
266 |
|
|
267 |
|
return $l; |
268 |
|
}, |
269 |
|
%{ $arg }, |
270 |
|
); |
271 |
|
|
272 |
|
unless (defined($db)) { |
273 |
|
$log->logwarn("can't open database $arg->{path}, skipping..."); |
274 |
|
return; |
275 |
|
} |
276 |
|
|
277 |
|
unless ($size) { |
278 |
|
$log->logwarn("no records in database $arg->{path}, skipping..."); |
279 |
|
return; |
280 |
|
} |
281 |
|
|
282 |
|
my $from_rec = 1; |
283 |
|
my $to_rec = $size; |
284 |
|
|
285 |
|
if (my $s = $self->{offset}) { |
286 |
|
$log->debug("skipping to MFN $s"); |
287 |
|
$from_rec = $s; |
288 |
|
} else { |
289 |
|
$self->{offset} = $from_rec; |
290 |
|
} |
291 |
|
|
292 |
|
if ($self->{limit}) { |
293 |
|
$log->debug("limiting to ",$self->{limit}," records"); |
294 |
|
$to_rec = $from_rec + $self->{limit} - 1; |
295 |
|
$to_rec = $size if ($to_rec > $size); |
296 |
|
} |
297 |
|
|
298 |
|
# store size for later |
299 |
|
$self->{size} = ($to_rec - $from_rec) ? ($to_rec - $from_rec + 1) : 0; |
300 |
|
|
301 |
|
$log->info("processing $self->{size}/$size records [$from_rec-$to_rec] convert $code_page -> $self->{encoding}", $self->{stats} ? ' [stats]' : ''); |
302 |
|
|
303 |
|
# read database |
304 |
|
for (my $pos = $from_rec; $pos <= $to_rec; $pos++) { |
305 |
|
|
306 |
|
$log->debug("position: $pos\n"); |
307 |
|
|
308 |
|
my $rec = $self->{fetch_rec}->($self, $db, $pos ); |
309 |
|
|
310 |
|
$log->debug(sub { Dumper($rec) }); |
311 |
|
|
312 |
|
if (! $rec) { |
313 |
|
$log->warn("record $pos empty? skipping..."); |
314 |
|
next; |
315 |
|
} |
316 |
|
|
317 |
|
# store |
318 |
|
if ($self->{low_mem}) { |
319 |
|
$self->{db}->put($pos, $rec); |
320 |
|
} else { |
321 |
|
$self->{data}->{$pos} = $rec; |
322 |
|
} |
323 |
|
|
324 |
|
# create lookup |
325 |
|
$arg->{'lookup_coderef'}->( $rec ) if ($rec && $arg->{'lookup_coderef'}); |
326 |
|
|
327 |
|
# update counters for statistics |
328 |
|
if ($self->{stats}) { |
329 |
|
|
330 |
|
foreach my $fld (keys %{ $rec }) { |
331 |
|
$self->{_stats}->{fld}->{ $fld }++; |
332 |
|
|
333 |
|
$log->logdie("invalid record fild $fld, not ARRAY") |
334 |
|
unless (ref($rec->{ $fld }) eq 'ARRAY'); |
335 |
|
|
336 |
|
foreach my $row (@{ $rec->{$fld} }) { |
337 |
|
|
338 |
|
if (ref($row) eq 'HASH') { |
339 |
|
|
340 |
|
foreach my $sf (keys %{ $row }) { |
341 |
|
$self->{_stats}->{sf}->{ $fld }->{ $sf }->{count}++; |
342 |
|
$self->{_stats}->{sf}->{ $fld }->{ $sf }->{repeatable}++ |
343 |
|
if (ref($row->{$sf}) eq 'ARRAY'); |
344 |
|
} |
345 |
|
|
346 |
|
} else { |
347 |
|
$self->{_stats}->{repeatable}->{ $fld }++; |
348 |
|
} |
349 |
|
} |
350 |
|
} |
351 |
|
} |
352 |
|
|
353 |
|
$self->progress_bar($pos,$to_rec) unless ($self->{no_progress_bar}); |
354 |
|
|
355 |
|
} |
356 |
|
|
357 |
|
$self->{pos} = -1; |
358 |
|
$self->{last_pcnt} = 0; |
359 |
|
|
360 |
|
# store max mfn and return it. |
361 |
|
$self->{max_pos} = $to_rec; |
362 |
|
$log->debug("max_pos: $to_rec"); |
363 |
|
|
364 |
|
return $size; |
365 |
|
} |
366 |
|
|
367 |
|
=head2 fetch |
368 |
|
|
369 |
|
Fetch next record from database. It will also displays progress bar. |
370 |
|
|
371 |
|
my $rec = $isis->fetch; |
372 |
|
|
373 |
|
Record from this function should probably go to C<data_structure> for |
374 |
|
normalisation. |
375 |
|
|
376 |
|
=cut |
377 |
|
|
378 |
|
sub fetch { |
379 |
|
my $self = shift; |
380 |
|
|
381 |
|
my $log = $self->_get_logger(); |
382 |
|
|
383 |
|
$log->logconfess("it seems that you didn't load database!") unless ($self->{pos}); |
384 |
|
|
385 |
|
if ($self->{pos} == -1) { |
386 |
|
$self->{pos} = $self->{offset}; |
387 |
|
} else { |
388 |
|
$self->{pos}++; |
389 |
|
} |
390 |
|
|
391 |
|
my $mfn = $self->{pos}; |
392 |
|
|
393 |
|
if ($mfn > $self->{max_pos}) { |
394 |
|
$self->{pos} = $self->{max_pos}; |
395 |
|
$log->debug("at EOF"); |
396 |
|
return; |
397 |
|
} |
398 |
|
|
399 |
|
$self->progress_bar($mfn,$self->{max_pos}) unless ($self->{no_progress_bar}); |
400 |
|
|
401 |
|
my $rec; |
402 |
|
|
403 |
|
if ($self->{low_mem}) { |
404 |
|
$rec = $self->{db}->get($mfn); |
405 |
|
} else { |
406 |
|
$rec = $self->{data}->{$mfn}; |
407 |
|
} |
408 |
|
|
409 |
|
$rec ||= 0E0; |
410 |
|
} |
411 |
|
|
412 |
|
=head2 pos |
413 |
|
|
414 |
|
Returns current record number (MFN). |
415 |
|
|
416 |
|
print $isis->pos; |
417 |
|
|
418 |
|
First record in database has position 1. |
419 |
|
|
420 |
|
=cut |
421 |
|
|
422 |
|
sub pos { |
423 |
|
my $self = shift; |
424 |
|
return $self->{pos}; |
425 |
|
} |
426 |
|
|
427 |
|
|
428 |
|
=head2 size |
429 |
|
|
430 |
|
Returns number of records in database |
431 |
|
|
432 |
|
print $isis->size; |
433 |
|
|
434 |
|
Result from this function can be used to loop through all records |
435 |
|
|
436 |
|
foreach my $mfn ( 1 ... $isis->size ) { ... } |
437 |
|
|
438 |
|
because it takes into account C<offset> and C<limit>. |
439 |
|
|
440 |
|
=cut |
441 |
|
|
442 |
|
sub size { |
443 |
|
my $self = shift; |
444 |
|
return $self->{size}; |
445 |
|
} |
446 |
|
|
447 |
|
=head2 seek |
448 |
|
|
449 |
|
Seek to specified MFN in file. |
450 |
|
|
451 |
|
$isis->seek(42); |
452 |
|
|
453 |
|
First record in database has position 1. |
454 |
|
|
455 |
|
=cut |
456 |
|
|
457 |
|
sub seek { |
458 |
|
my $self = shift; |
459 |
|
my $pos = shift || return; |
460 |
|
|
461 |
|
my $log = $self->_get_logger(); |
462 |
|
|
463 |
|
if ($pos < 1) { |
464 |
|
$log->warn("seek before first record"); |
465 |
|
$pos = 1; |
466 |
|
} elsif ($pos > $self->{max_pos}) { |
467 |
|
$log->warn("seek beyond last record"); |
468 |
|
$pos = $self->{max_pos}; |
469 |
|
} |
470 |
|
|
471 |
|
return $self->{pos} = (($pos - 1) || -1); |
472 |
|
} |
473 |
|
|
474 |
|
=head2 stats |
475 |
|
|
476 |
|
Dump statistics about field and subfield usage |
477 |
|
|
478 |
|
print $input->stats; |
479 |
|
|
480 |
|
=cut |
481 |
|
|
482 |
|
sub stats { |
483 |
|
my $self = shift; |
484 |
|
|
485 |
|
my $log = $self->_get_logger(); |
486 |
|
|
487 |
|
my $s = $self->{_stats}; |
488 |
|
if (! $s) { |
489 |
|
$log->warn("called stats, but there is no statistics collected"); |
490 |
|
return; |
491 |
|
} |
492 |
|
|
493 |
|
my $max_fld = 0; |
494 |
|
|
495 |
|
my $out = join("\n", |
496 |
|
map { |
497 |
|
my $f = $_ || die "no field"; |
498 |
|
my $v = $s->{fld}->{$f} || die "no s->{fld}->{$f}"; |
499 |
|
$max_fld = $v if ($v > $max_fld); |
500 |
|
|
501 |
|
my $o = sprintf("%4s %d ~", $f, $v); |
502 |
|
|
503 |
|
if (defined($s->{sf}->{$f})) { |
504 |
|
map { |
505 |
|
$o .= sprintf(" %s:%d%s", $_, |
506 |
|
$s->{sf}->{$f}->{$_}->{count}, |
507 |
|
$s->{sf}->{$f}->{$_}->{repeatable} ? '*' : '', |
508 |
|
); |
509 |
|
} sort keys %{ $s->{sf}->{$f} }; |
510 |
|
} |
511 |
|
|
512 |
|
if (my $v_r = $s->{repeatable}->{$f}) { |
513 |
|
$o .= " ($v_r)" if ($v_r != $v); |
514 |
|
} |
515 |
|
|
516 |
|
$o; |
517 |
|
} sort { $a cmp $b } keys %{ $s->{fld} } |
518 |
|
); |
519 |
|
|
520 |
|
$log->debug( sub { Dumper($s) } ); |
521 |
|
|
522 |
|
return $out; |
523 |
|
} |
524 |
|
|
525 |
|
=head1 modify_record_regexps |
526 |
|
|
527 |
|
Generate hash with regexpes to be applied using L<filter>. |
528 |
|
|
529 |
|
my $regexpes = $input->modify_record_regexps( |
530 |
|
900 => { '^a' => { ' : ' => '^b' } }, |
531 |
|
901 => { '*' => { '^b' => ' ; ' } }, |
532 |
|
); |
533 |
|
|
534 |
|
=cut |
535 |
|
|
536 |
|
sub modify_record_regexps { |
537 |
|
my $self = shift; |
538 |
|
my $modify_record = {@_}; |
539 |
|
|
540 |
|
my $regexpes; |
541 |
|
|
542 |
|
foreach my $f (keys %$modify_record) { |
543 |
|
warn "--- f: $f\n"; |
544 |
|
foreach my $sf (keys %{ $modify_record->{$f} }) { |
545 |
|
warn "---- sf: $sf\n"; |
546 |
|
foreach my $from (keys %{ $modify_record->{$f}->{$sf} }) { |
547 |
|
my $to = $modify_record->{$f}->{$sf}->{$from}; |
548 |
|
#die "no field?" unless defined($to); |
549 |
|
warn "----- transform: |$from| -> |$to|\n"; |
550 |
|
|
551 |
|
if ($sf =~ /^\^/) { |
552 |
|
my $regex = |
553 |
|
's/\Q'. $sf .'\E([^\^]+)\Q'. $from .'\E([^\^]+)/'. $sf .'$1'. $to .'$2/g'; |
554 |
|
push @{ $regexpes->{$f} }, $regex; |
555 |
|
warn ">>>>> $regex [sf]\n"; |
556 |
|
} else { |
557 |
|
my $regex = |
558 |
|
's/\Q'. $from .'\E/'. $to .'/g'; |
559 |
|
push @{ $regexpes->{$f} }, $regex; |
560 |
|
warn ">>>>> $regex [global]\n"; |
561 |
|
} |
562 |
|
|
563 |
|
} |
564 |
|
} |
565 |
|
} |
566 |
|
|
567 |
|
return $regexpes; |
568 |
|
} |
569 |
|
|
570 |
=head1 MEMORY USAGE |
=head1 MEMORY USAGE |
571 |
|
|
572 |
C<low_mem> options is double-edged sword. If enabled, WebPAC |
C<low_mem> options is double-edged sword. If enabled, WebPAC |