58 |
'isis' => 'isis', |
'isis' => 'isis', |
59 |
'excel' => 'column', |
'excel' => 'column', |
60 |
'marc' => 'marc', |
'marc' => 'marc', |
61 |
|
'feed' => 'feed' |
62 |
); |
); |
63 |
|
|
64 |
sub data2xml { |
sub data2xml { |
124 |
# init vars so that we go into while... |
# init vars so that we go into while... |
125 |
($swish,$display) = (1,1); |
($swish,$display) = (1,1); |
126 |
|
|
127 |
if ($swish || $display) { |
# placeholder for all repeatable entries for index |
128 |
|
my @index_data; |
129 |
|
my $index_filter; |
130 |
|
|
131 |
|
# while because of repeatable fields |
132 |
|
while ($swish || $display) { |
133 |
($swish,$display) = parse_format($type, $format,$row,$repeat_off++,$import2cp); |
($swish,$display) = parse_format($type, $format,$row,$repeat_off++,$import2cp); |
134 |
|
if ($repeat_off > 1000) { |
135 |
|
print STDERR "loop (more than 1000 repeatable fields) deteced in $row, $format\n"; |
136 |
|
last; |
137 |
|
} |
138 |
|
|
139 |
# filter="name" ; filter this field through |
# filter="name" ; filter this field through |
140 |
# filter/[name].pm |
# filter/[name].pm |
141 |
my $filter = $x->{filter}; |
my $filter = $x->{filter}; |
172 |
|
|
173 |
# type="index" ; insert into index |
# type="index" ; insert into index |
174 |
if ($i && $display) { |
if ($i && $display) { |
175 |
my $index_data = $display; |
push @index_data, $display; |
176 |
if ($filter) { |
$index_filter = $filter if ($filter); |
177 |
no strict 'refs'; |
} |
178 |
foreach my $d (&$filter($index_data)) { |
} |
179 |
$index->insert($field, $d, $path); |
|
180 |
} |
# fill data in index |
181 |
} else { |
if (@index_data) { |
182 |
$index->insert($field, $index_data, $path); |
if ($index_filter) { |
183 |
|
no strict 'refs'; |
184 |
|
foreach my $d (&$index_filter(@index_data)) { |
185 |
|
$index->insert($field, $d, $path); |
186 |
|
} |
187 |
|
} else { |
188 |
|
foreach my $d (@index_data) { |
189 |
|
$index->insert($field, $d, $path); |
190 |
} |
} |
191 |
} |
} |
192 |
} |
} |
248 |
|
|
249 |
# dump formatted output in <html> |
# dump formatted output in <html> |
250 |
if ($html) { |
if ($html) { |
251 |
$xml .= xmlify("html",$html); |
#$xml .= xmlify("html",$html); |
252 |
|
$xml .= "<html><![CDATA[ $html ]]></html>"; |
253 |
} |
} |
254 |
|
|
255 |
if ($xml) { |
if ($xml) { |
276 |
$cfg_global->val('global', 'dbi_passwd') || '', |
$cfg_global->val('global', 'dbi_passwd') || '', |
277 |
); |
); |
278 |
|
|
279 |
|
my $show_progress = $cfg_global->val('global', 'show_progress'); |
280 |
|
|
281 |
foreach my $database ($cfg->Sections) { |
foreach my $database ($cfg->Sections) { |
282 |
|
|
283 |
my $type = lc($cfg -> val($database, 'type')) || die "$database doesn't have 'type' defined"; |
my $type = lc($cfg -> val($database, 'type')) || die "$database doesn't have 'type' defined"; |
294 |
# output current progress indicator |
# output current progress indicator |
295 |
my $last_p = 0; |
my $last_p = 0; |
296 |
sub progress { |
sub progress { |
297 |
#return if (! $opts{q}); # FIXME |
# XXX return if ($show_progress ne ""); |
298 |
my $current = shift; |
my $current = shift; |
299 |
my $total = shift || 1; |
my $total = shift || 1; |
300 |
my $p = int($current * 100 / $total); |
my $p = int($current * 100 / $total); |
304 |
} |
} |
305 |
} |
} |
306 |
|
|
307 |
|
my $fake_dir = 1; |
308 |
|
sub fakeprogress { |
309 |
|
my $current = shift @_; |
310 |
|
|
311 |
|
my @ind = ('-','\\','|','/','-','\\','|','/', '-'); |
312 |
|
|
313 |
|
$last_p += $fake_dir; |
314 |
|
$fake_dir = -$fake_dir if ($last_p > 1000 || $last_p < 0); |
315 |
|
if ($last_p % 10 == 0) { |
316 |
|
printf STDERR ("%5d / %5s [%-51s]\r",$current,"?"," " x ($last_p/20).$ind[($last_p/20) % $#ind]); |
317 |
|
} |
318 |
|
} |
319 |
|
|
320 |
# now read database |
# now read database |
321 |
print STDERR "using: $type...\n"; |
print STDERR "using: $type...\n"; |
322 |
|
|
407 |
} |
} |
408 |
} |
} |
409 |
} elsif ($type_base eq "marc") { |
} elsif ($type_base eq "marc") { |
410 |
## XXX |
|
411 |
use MARC; |
use MARC; |
412 |
|
|
413 |
$import2cp = Text::Iconv->new($config->{marc_codepage},$codepage); |
$import2cp = Text::Iconv->new($config->{marc_codepage},$codepage); |
416 |
# optional argument is format |
# optional argument is format |
417 |
my $format = x($config->{format}) || 'usmarc'; |
my $format = x($config->{format}) || 'usmarc'; |
418 |
|
|
|
my %id_stored; # to aviod duplicates |
|
|
|
|
419 |
print STDERR "Reading MARC file '$marc_file'\n"; |
print STDERR "Reading MARC file '$marc_file'\n"; |
420 |
|
|
421 |
my $marc = new MARC; |
my $marc = new MARC; |
424 |
}) || die "Can't open MARC file '$marc_file'"; |
}) || die "Can't open MARC file '$marc_file'"; |
425 |
|
|
426 |
my $i=0; # record nr. |
my $i=0; # record nr. |
|
my $inc=1; |
|
|
my $max_i=1000; |
|
427 |
|
|
428 |
my $rec; |
my $rec; |
429 |
|
|
430 |
while ($marc->nextmarc(1)) { |
while ($marc->nextmarc(1)) { |
431 |
|
|
432 |
# XXX |
# XXX |
433 |
progress($i, $max_i); |
fakeprogress($i++); |
|
$i += $inc; |
|
|
$inc = -$inc if ($i > $max_i || $i < 0); |
|
434 |
|
|
435 |
my $swishpath = $database."#".$i; |
my $swishpath = $database."#".$i; |
436 |
|
|
442 |
print "Document-Type: XML\n\n$xml\n"; |
print "Document-Type: XML\n\n$xml\n"; |
443 |
} |
} |
444 |
} |
} |
445 |
|
} elsif ($type_base eq "feed") { |
446 |
|
|
447 |
|
$import2cp = Text::Iconv->new($config->{feed_codepage},$codepage); |
448 |
|
my $prog = x($config->{prog}) || die "$database doesn't have 'prog' defined!"; |
449 |
|
|
450 |
|
print STDERR "Reading feed from program '$prog'\n"; |
451 |
|
|
452 |
|
open(FEED,"feeds/$prog |") || die "can't start $prog: $!"; |
453 |
|
|
454 |
|
my $i=1; # record nr. |
455 |
|
|
456 |
|
my $data; |
457 |
|
my $line=1; |
458 |
|
|
459 |
|
while (<FEED>) { |
460 |
|
chomp; |
461 |
|
|
462 |
|
if (/^$/) { |
463 |
|
my $swishpath = $database."#".$i++; |
464 |
|
|
465 |
|
if (my $xml = data2xml($type_base,$data,$add_xml,$cfg,$database)) { |
466 |
|
$xml = $cp2utf->convert($xml); |
467 |
|
use bytes; # as opposed to chars |
468 |
|
print "Path-Name: $swishpath\n"; |
469 |
|
print "Content-Length: ".(length($xml)+1)."\n"; |
470 |
|
print "Document-Type: XML\n\n$xml\n"; |
471 |
|
} |
472 |
|
$line = 1; |
473 |
|
$data = {}; |
474 |
|
next; |
475 |
|
} |
476 |
|
|
477 |
|
$line = $1 if (s/^(\d+):\s*//); |
478 |
|
$data->{$line++} = $_; |
479 |
|
|
480 |
|
fakeprogress($i); |
481 |
|
|
482 |
|
} |
483 |
} |
} |
484 |
} |
} |
485 |
|
|
492 |
|
|
493 |
=head1 NAME |
=head1 NAME |
494 |
|
|
495 |
isis2xml.pl - read isis file and dump XML |
all2xml.pl - read various file formats and dump XML for SWISH-E |
496 |
|
|
497 |
=head1 DESCRIPTION |
=head1 DESCRIPTION |
498 |
|
|
499 |
This command will read ISIS data file using OpenIsis perl module and |
This command will read ISIS data file using OpenIsis perl module, MARC |
500 |
create XML file for usage with I<SWISH-E> |
records using MARC module and optionally Micro$oft Excel files to |
501 |
indexer. Dispite it's name, this script B<isn't general xml generator> |
create one XML file for usage with I<SWISH-E> indexer. Dispite it's name, |
502 |
from isis files (isis allready has something like that). Output of this |
this script B<isn't general xml generator> from isis files (isis allready |
503 |
script is tailor-made for SWISH-E. |
has something like that). Output of this script is tailor-made for SWISH-E. |
504 |
|
|
505 |
|
=head1 BUGS |
506 |
|
|
507 |
|
Documentation is really lacking. However, in true Open Source spirit, source |
508 |
|
is best documentation. I even made considerable effort to comment parts |
509 |
|
which are not intuitively clear, so... |
510 |
|
|
511 |
=head1 AUTHOR |
=head1 AUTHOR |
512 |
|
|