| 2 |
|
|
| 3 |
=head1 NAME |
=head1 NAME |
| 4 |
|
|
| 5 |
webpac.pl - basic script for all WebPac needs |
all2all.pl - basic script for all WebPAC needs |
| 6 |
|
|
| 7 |
=cut |
=cut |
| 8 |
|
|
| 9 |
use strict; |
use strict; |
|
use OpenIsis; |
|
|
use Text::Iconv; |
|
| 10 |
use Data::Dumper; |
use Data::Dumper; |
| 11 |
|
use Carp; |
| 12 |
|
|
| 13 |
my $cp = Text::Iconv->new("852", "iso-8859-2"); |
use lib './lib'; |
| 14 |
|
use WebPAC; |
| 15 |
|
use WebPAC::jsFind; |
| 16 |
|
|
| 17 |
|
my $webpac = new WebPAC( |
| 18 |
|
code_page => 'ISO-8859-2', |
| 19 |
|
# limit_mfn => 100, |
| 20 |
|
# debug => 1, |
| 21 |
|
) || die; |
| 22 |
|
|
| 23 |
|
my $log = $webpac->_get_logger(); |
| 24 |
|
|
| 25 |
|
my $index = new WebPAC::jsFind( |
| 26 |
|
index_path => './out/index', |
| 27 |
|
keys => 80, |
| 28 |
|
) || die; |
| 29 |
|
|
| 30 |
$|=1; |
$|=1; |
| 31 |
|
|
| 32 |
my $db = OpenIsis::open( shift @ARGV || '/data/hidra/THS-500/THS' ); |
my $maxmfn = $webpac->open_isis( |
| 33 |
my $maxmfn = OpenIsis::maxRowid( $db ) || 1; |
filename => shift @ARGV || '/data/hidra/THS/THS', |
| 34 |
|
lookup => [ |
| 35 |
|
{ 'key' => 'd:v900', 'val' => 'v250^a' }, |
| 36 |
|
# { 'eval' => '"v901^a" eq "Područje"', 'key' => 'pa:v561^4:v562^4:v461^1', 'val' => 'v900' }, |
| 37 |
|
# { 'eval '=> '"v901^a" eq "Mikrotezaurus"', 'key' => 'a:v561^4:v562^4:v461^1', 'val' => 'v900' }, |
| 38 |
|
# { 'eval' => '"v901^a" eq "Deskriptor"', 'key' => 'a:v561^4:v562^4:v461^1', 'val' => 'v900' }, |
| 39 |
|
{ 'key' => 'a:v561^4:v562^4:v461^1', 'val' => 'v900' }, |
| 40 |
|
{ 'key' => '900_mfn:v900', 'val' => 'v000' }, |
| 41 |
|
], |
| 42 |
|
); |
| 43 |
|
|
| 44 |
print "rows: $maxmfn\n\n"; |
$log->info("rows: $maxmfn"); |
| 45 |
|
|
| 46 |
my $data; |
$webpac->open_import_xml(type => 'isis_hidra_ths'); |
| 47 |
|
|
| 48 |
my @lookup = ( |
while (my $rec = $webpac->fetch_rec) { |
|
{ 'key' => 'd:v900', 'val' => 'v250^a' }, |
|
|
{ 'eval' => '"v901^a" eq "Područje"', 'key' => 'pa:v561^4:v562^4:v461^1', 'val' => 'v900' }, |
|
|
{ 'eval '=> '"v901^a" eq "Mikrotezaurus"', 'key' => 'ma:v561^4:v562^4:v461^1', 'val' => 'v900' }, |
|
|
{ 'eval' => '"v901^a" eq "Deskriptor"', 'key' => 'da:v561^4:v562^4:v461^1', 'val' => 'v900' }, |
|
|
); |
|
| 49 |
|
|
| 50 |
sub fill_in { |
my @ds = $webpac->data_structure($rec); |
|
my $tmp = shift || return; |
|
|
my $data = shift || return; |
|
|
my $i = shift || 0; |
|
|
|
|
|
my $found = 0; |
|
|
|
|
|
sub get_sf { |
|
|
my ($found,$data,$f,$sf,$i) = @_; |
|
|
if ($$data->{$f}->[$i]->{$sf}) { |
|
|
$$found++; |
|
|
return $$data->{$f}->[$i]->{$sf}; |
|
|
} else { |
|
|
return ''; |
|
|
} |
|
|
} |
|
| 51 |
|
|
| 52 |
sub get_nosf { |
if ($log->is_debug) { |
| 53 |
my ($found,$data,$f,$i) = @_; |
$log->debug("rec = ",Dumper($rec)); |
| 54 |
if ($$data->{$f}->[$i]) { |
$log->debug("ds = ",Dumper(\@ds)); |
|
$$found++; |
|
|
return $$data->{$f}->[$i]; |
|
|
} else { |
|
|
return ''; |
|
|
} |
|
| 55 |
} |
} |
| 56 |
|
|
| 57 |
$tmp =~ s/v(\d+)\^(\w)/get_sf(\$found,\$data,$1,$2,$i)/ges; |
next if (! @ds); |
|
$tmp =~ s/v(\d+)/get_nosf(\$found,\$data,$1,$i)/ges; |
|
| 58 |
|
|
| 59 |
if ($found) { |
my $filename = $webpac->{'current_filename'}; |
| 60 |
return $tmp; |
|
| 61 |
|
if ($filename) { |
| 62 |
|
open(OUT,"> $filename") || $log->logdie("can't open output '$filename': $!"); |
| 63 |
|
print OUT $webpac->output( |
| 64 |
|
template => 'html.tt', |
| 65 |
|
data => \@ds, |
| 66 |
|
headline => $webpac->{'headline'}, |
| 67 |
|
); |
| 68 |
|
close(OUT); |
| 69 |
} else { |
} else { |
| 70 |
return; |
print $webpac->output( |
| 71 |
|
template => 'text.tt', |
| 72 |
|
data => \@ds, |
| 73 |
|
headline => $webpac->{'headline'}, |
| 74 |
|
); |
| 75 |
} |
} |
|
} |
|
|
|
|
|
print "reading database...\n"; |
|
| 76 |
|
|
| 77 |
for (my $mfn = 1; $mfn <= $maxmfn; $mfn++) { |
my $headline = $webpac->{'headline'}; |
| 78 |
|
|
| 79 |
my $row = OpenIsis::read( $db, $mfn ); |
my $f = $filename; |
| 80 |
print Dumper($row); |
$f =~ s!out/!!; |
|
foreach my $k (keys %{$row}) { |
|
|
if ($k ne "mfn") { |
|
|
foreach my $l (@{$row->{$k}}) { |
|
|
next if (! $l); |
|
|
$l = $cp->convert($l); |
|
|
# has subfields? |
|
|
my $val; |
|
|
if ($l =~ m/\^/) { |
|
|
foreach my $t (split(/\^/,$l)) { |
|
|
next if (! $t); |
|
|
$val->{substr($t,0,1)} = substr($t,1); |
|
|
} |
|
|
} else { |
|
|
$val = $l; |
|
|
} |
|
|
|
|
|
push @{$data->{$mfn}->{$k}}, $val if ($val && $val ne ""); |
|
|
} |
|
|
} |
|
| 81 |
|
|
| 82 |
|
# save into index |
| 83 |
|
foreach my $ds (@ds) { |
| 84 |
|
next if (! $ds->{'swish'}); |
| 85 |
|
|
| 86 |
|
$index->insert( |
| 87 |
|
index_name => $ds->{'tag'}, |
| 88 |
|
path => $f, |
| 89 |
|
headline => $headline, |
| 90 |
|
words => join(" ",@{$ds->{'swish'}}) |
| 91 |
|
); |
| 92 |
} |
} |
| 93 |
|
|
| 94 |
foreach my $i (@lookup) { |
# print Dumper(\@ds); |
|
if ($i->{'eval'}) { |
|
|
my $eval = fill_in($i->{'eval'},$data->{$mfn}); |
|
|
my $key = fill_in($i->{'key'}, $data->{$mfn}); |
|
|
my $val = fill_in($i->{'val'}, $data->{$mfn}); |
|
|
if ($key && $val && eval $eval) { |
|
|
push @{$data->{lookup}->{$key}}, $val; |
|
|
} |
|
|
} else { |
|
|
my $key = fill_in($i->{'key'}, $data->{$mfn}); |
|
|
my $val = fill_in($i->{'val'}, $data->{$mfn}); |
|
|
if ($key && $val) { |
|
|
push @{$data->{lookup}->{$key}}, $val; |
|
|
} |
|
|
} |
|
|
} |
|
| 95 |
|
|
| 96 |
} |
} |
|
print "\n"; |
|
| 97 |
|
|
| 98 |
for (my $mfn = 1; $mfn <= $maxmfn; $mfn++) { |
if ($log->is_debug) { |
| 99 |
my $d = $data->{$mfn}; |
$log->debug("lookup hash: ",Dumper($webpac->{'lookup'})); |
| 100 |
print $d->{'250'}->[0]->{'a'},"\n"; |
$log->debug("data hash: ",Dumper($webpac->{'data'})); |
|
my $t = fill_in('v553^1;;v553^a', $d); |
|
|
print " Uži pojam: $t\n" if ($t); |
|
|
$t = fill_in('[a:v251];;[d:[a:v251]]', $d); |
|
|
print " Uži pojam: $t\n" if ($t); |
|
| 101 |
} |
} |
| 102 |
|
|
| 103 |
print Dumper($data); |
$index->close; |
| 104 |
|
|
Parent Directory
| 
Revision Log
| 
Patch