133 |
"clean" => \$clean, |
"clean" => \$clean, |
134 |
"one=s" => \$only_filter, |
"one=s" => \$only_filter, |
135 |
"only=s" => \$only_filter, |
"only=s" => \$only_filter, |
136 |
"config" => \$config_path, |
"config=s" => \$config_path, |
137 |
"debug+" => \$debug, |
"debug+" => \$debug, |
138 |
"stats" => \$stats, |
"stats" => \$stats, |
139 |
"validate=s" => \$validate_path, |
"validate=s" => \$validate_path, |
191 |
|
|
192 |
# parse normalize files and create source files for lookup and normalization |
# parse normalize files and create source files for lookup and normalization |
193 |
|
|
194 |
my $parser = new WebPAC::Parser( config => $config ); |
my ($only_database,$only_input) = split(m#/#, $only_filter) if $only_filter; |
195 |
|
|
196 |
|
my $parser = new WebPAC::Parser( |
197 |
|
config => $config, |
198 |
|
only_database => $only_database, |
199 |
|
only_input => $only_input, |
200 |
|
); |
201 |
|
|
202 |
my $total_rows = 0; |
my $total_rows = 0; |
203 |
my $start_t = time(); |
my $start_t = time(); |
221 |
foreach my $database ( sort keys %{ $config->databases } ) { |
foreach my $database ( sort keys %{ $config->databases } ) { |
222 |
my $db_config = $config->databases->{$database}; |
my $db_config = $config->databases->{$database}; |
223 |
|
|
|
my ($only_database,$only_input) = split(m#/#, $only_filter) if ($only_filter); |
|
224 |
next if ($only_database && $database !~ m/$only_database/i); |
next if ($only_database && $database !~ m/$only_database/i); |
225 |
|
|
226 |
if ($parallel) { |
if ($parallel) { |
316 |
|
|
317 |
foreach my $output ( @outputs ) { |
foreach my $output ( @outputs ) { |
318 |
|
|
319 |
warn '## output = ',dump( $output ); |
#warn '## output = ',dump( $output ); |
320 |
|
|
321 |
my $module = $output->{module} || $log->logdie("need module in output section of $database"); |
my $module = $output->{module} || $log->logdie("need module in output section of $database"); |
322 |
$module = 'WebPAC::Output::' . $module unless $module =~ m/::/; |
$module = 'WebPAC::Output::' . $module unless $module =~ m/::/; |
323 |
|
|
324 |
$log->debug("loading output module $module"); |
$log->debug("loading output module $module"); |
325 |
eval "require $module"; |
eval "require $module"; |
326 |
|
|
327 |
|
# add database to arugemnts for output filter |
328 |
$output->{database} = $database; |
$output->{database} = $database; |
329 |
|
|
330 |
$log->debug("calling $module->new(",dump( $output ),")"); |
$log->debug("calling $module->new(",dump( $output ),")"); |
352 |
|
|
353 |
my $type = lc($input->{type}); |
my $type = lc($input->{type}); |
354 |
|
|
355 |
die "I know only how to handle input types ", join(",", $config->webpac('inputs') ), " not '$type'!\n" unless (grep(/$type/, $config->webpac('inputs'))); |
# FIXME check if input module exists |
356 |
|
my $input_module = $input->{module}; |
357 |
|
|
358 |
my $input_module = $config->webpac('inputs')->{$type}; |
if ( ! $input_module ) { |
359 |
|
if ( grep(/$type/, $config->webpac('inputs')) ) { |
360 |
|
$input_module = $config->webpac('inputs')->{$type}; |
361 |
|
} else { |
362 |
|
$log->logdie("I know only how to handle input types ", join(",", $config->webpac('inputs') ), " not '$type'!" ); |
363 |
|
} |
364 |
|
} |
365 |
|
|
366 |
my @lookups = $parser->have_lookup_create($database, $input); |
my @lookups = $parser->have_lookup_create($database, $input); |
367 |
|
|
521 |
} |
} |
522 |
|
|
523 |
|
|
524 |
|
# setup input name for all output filters |
525 |
|
foreach my $out ( @output_modules ) { |
526 |
|
if ( $out->can('input') ) { |
527 |
|
$out->input( $input_name ); |
528 |
|
} else { |
529 |
|
$log->warn("output filter ",ref($out)," doesn't support input name"); |
530 |
|
} |
531 |
|
} |
532 |
|
|
533 |
|
|
534 |
foreach my $pos ( 0 ... $input_db->size ) { |
foreach my $pos ( 0 ... $input_db->size ) { |
535 |
|
|
536 |
my $row = $input_db->fetch || next; |
my $row = $input_db->fetch || next; |
563 |
marc_encoding => 'utf-8', |
marc_encoding => 'utf-8', |
564 |
load_row_coderef => sub { |
load_row_coderef => sub { |
565 |
my ($database,$input,$mfn) = @_; |
my ($database,$input,$mfn) = @_; |
566 |
|
warn "### load_row($database,$input,$mfn) from data_structure\n"; |
567 |
return $store->load_row( |
return $store->load_row( |
568 |
database => $database, |
database => $database, |
569 |
input => $input, |
input => $input, |
572 |
}, |
}, |
573 |
); |
); |
574 |
|
|
575 |
$log->debug("ds = ", sub { dump($ds) }) if ($ds); |
$log->debug("ds = ", sub { dump($ds) }); |
576 |
|
|
577 |
|
if ( $ds ) { |
578 |
|
|
579 |
|
$store->save_ds( |
580 |
|
database => $database, |
581 |
|
input => $input_name, |
582 |
|
id => $mfn, |
583 |
|
ds => $ds, |
584 |
|
) if !$stats; |
585 |
|
|
586 |
|
$indexer->add( |
587 |
|
id => "${input_name}/${mfn}", |
588 |
|
ds => $ds, |
589 |
|
type => $config->get($indexer_config)->{type}, |
590 |
|
) if $indexer; |
591 |
|
|
592 |
$store->save_ds( |
foreach my $out ( @output_modules ) { |
593 |
database => $database, |
$out->add( $mfn, $ds ) if $out->can('add'); |
594 |
input => $input_name, |
} |
595 |
id => $mfn, |
|
596 |
ds => $ds, |
} else { |
597 |
) if ($ds && !$stats); |
$log->warn("record $pos didn't produce any output after normalization rules!") unless $marc; |
598 |
|
} |
|
$indexer->add( |
|
|
id => "${input_name}/${mfn}", |
|
|
ds => $ds, |
|
|
type => $config->get($indexer_config)->{type}, |
|
|
) if ($indexer && $ds); |
|
599 |
|
|
600 |
if ($marc) { |
if ($marc) { |
601 |
my $i = 0; |
my $i = 0; |
613 |
$log->info("Created $i instances of MFN $mfn\n") if ($i > 1); |
$log->info("Created $i instances of MFN $mfn\n") if ($i > 1); |
614 |
} |
} |
615 |
|
|
|
foreach my $out ( @output_modules ) { |
|
|
$out->add( $mfn, $ds ) if $out->can('add'); |
|
|
} |
|
|
|
|
616 |
} |
} |
617 |
|
|
618 |
if ($validate) { |
if ($validate) { |