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 || $display) { |
# while because of repeatable fields |
128 |
|
while ($swish || $display) { |
129 |
($swish,$display) = parse_format($type, $format,$row,$repeat_off++,$import2cp); |
($swish,$display) = parse_format($type, $format,$row,$repeat_off++,$import2cp); |
130 |
|
if ($repeat_off > 1000) { |
131 |
|
print STDERR "loop (more than 1000 repeatable fields) deteced in $row, $format\n"; |
132 |
|
last; |
133 |
|
} |
134 |
|
|
135 |
# filter="name" ; filter this field through |
# filter="name" ; filter this field through |
136 |
# filter/[name].pm |
# filter/[name].pm |
137 |
my $filter = $x->{filter}; |
my $filter = $x->{filter}; |
237 |
|
|
238 |
# dump formatted output in <html> |
# dump formatted output in <html> |
239 |
if ($html) { |
if ($html) { |
240 |
$xml .= xmlify("html",$html); |
#$xml .= xmlify("html",$html); |
241 |
|
$xml .= "<html><![CDATA[ $html ]]></html>"; |
242 |
} |
} |
243 |
|
|
244 |
if ($xml) { |
if ($xml) { |
291 |
} |
} |
292 |
} |
} |
293 |
|
|
294 |
|
my $fake_dir = 1; |
295 |
|
sub fakeprogress { |
296 |
|
my $current = shift @_; |
297 |
|
|
298 |
|
my @ind = ('-','\\','|','/','-','\\','|','/', '-'); |
299 |
|
|
300 |
|
$last_p += $fake_dir; |
301 |
|
$fake_dir = -$fake_dir if ($last_p > 1000 || $last_p < 0); |
302 |
|
if ($last_p % 10 == 0) { |
303 |
|
printf STDERR ("%5d / %5s [%-51s]\r",$current,"?"," " x ($last_p/20).$ind[($last_p/20) % $#ind]); |
304 |
|
} |
305 |
|
} |
306 |
|
|
307 |
# now read database |
# now read database |
308 |
print STDERR "using: $type...\n"; |
print STDERR "using: $type...\n"; |
309 |
|
|
394 |
} |
} |
395 |
} |
} |
396 |
} elsif ($type_base eq "marc") { |
} elsif ($type_base eq "marc") { |
397 |
## XXX |
|
398 |
use MARC; |
use MARC; |
399 |
|
|
400 |
$import2cp = Text::Iconv->new($config->{marc_codepage},$codepage); |
$import2cp = Text::Iconv->new($config->{marc_codepage},$codepage); |
403 |
# optional argument is format |
# optional argument is format |
404 |
my $format = x($config->{format}) || 'usmarc'; |
my $format = x($config->{format}) || 'usmarc'; |
405 |
|
|
|
my %id_stored; # to aviod duplicates |
|
|
|
|
406 |
print STDERR "Reading MARC file '$marc_file'\n"; |
print STDERR "Reading MARC file '$marc_file'\n"; |
407 |
|
|
408 |
my $marc = new MARC; |
my $marc = new MARC; |
411 |
}) || die "Can't open MARC file '$marc_file'"; |
}) || die "Can't open MARC file '$marc_file'"; |
412 |
|
|
413 |
my $i=0; # record nr. |
my $i=0; # record nr. |
|
my $inc=1; |
|
|
my $max_i=1000; |
|
414 |
|
|
415 |
my $rec; |
my $rec; |
416 |
|
|
417 |
while ($marc->nextmarc(1)) { |
while ($marc->nextmarc(1)) { |
418 |
|
|
419 |
# XXX |
# XXX |
420 |
progress($i, $max_i); |
fakeprogress($i++); |
|
$i += $inc; |
|
|
$inc = -$inc if ($i > $max_i || $i < 0); |
|
421 |
|
|
422 |
my $swishpath = $database."#".$i; |
my $swishpath = $database."#".$i; |
423 |
|
|
429 |
print "Document-Type: XML\n\n$xml\n"; |
print "Document-Type: XML\n\n$xml\n"; |
430 |
} |
} |
431 |
} |
} |
432 |
|
} elsif ($type_base eq "feed") { |
433 |
|
|
434 |
|
$import2cp = Text::Iconv->new($config->{feed_codepage},$codepage); |
435 |
|
my $prog = x($config->{prog}) || die "$database doesn't have 'prog' defined!"; |
436 |
|
|
437 |
|
print STDERR "Reading feed from program '$prog'\n"; |
438 |
|
|
439 |
|
open(FEED,"feeds/$prog |") || die "can't start $prog: $!"; |
440 |
|
|
441 |
|
my $i=1; # record nr. |
442 |
|
|
443 |
|
my $data; |
444 |
|
my $line=1; |
445 |
|
|
446 |
|
while (<FEED>) { |
447 |
|
chomp; |
448 |
|
|
449 |
|
if (/^$/) { |
450 |
|
my $swishpath = $database."#".$i++; |
451 |
|
|
452 |
|
if (my $xml = data2xml($type_base,$data,$add_xml,$cfg,$database)) { |
453 |
|
$xml = $cp2utf->convert($xml); |
454 |
|
use bytes; # as opposed to chars |
455 |
|
print "Path-Name: $swishpath\n"; |
456 |
|
print "Content-Length: ".(length($xml)+1)."\n"; |
457 |
|
print "Document-Type: XML\n\n$xml\n"; |
458 |
|
} |
459 |
|
$line = 1; |
460 |
|
$data = {}; |
461 |
|
next; |
462 |
|
} |
463 |
|
|
464 |
|
$line = $1 if (s/^(\d+):\s*//); |
465 |
|
$data->{$line++} = $_; |
466 |
|
|
467 |
|
fakeprogress($i); |
468 |
|
|
469 |
|
} |
470 |
} |
} |
471 |
} |
} |
472 |
|
|
479 |
|
|
480 |
=head1 NAME |
=head1 NAME |
481 |
|
|
482 |
isis2xml.pl - read isis file and dump XML |
all2xml.pl - read various file formats and dump XML for SWISH-E |
483 |
|
|
484 |
=head1 DESCRIPTION |
=head1 DESCRIPTION |
485 |
|
|
486 |
This command will read ISIS data file using OpenIsis perl module and |
This command will read ISIS data file using OpenIsis perl module, MARC |
487 |
create XML file for usage with I<SWISH-E> |
records using MARC module and optionally Micro$oft Excel files to |
488 |
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, |
489 |
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 |
490 |
script is tailor-made for SWISH-E. |
has something like that). Output of this script is tailor-made for SWISH-E. |
491 |
|
|
492 |
|
=head1 BUGS |
493 |
|
|
494 |
|
Documentation is really lacking. However, in true Open Source spirit, source |
495 |
|
is best documentation. I even made considerable effort to comment parts |
496 |
|
which are not intuitively clear, so... |
497 |
|
|
498 |
=head1 AUTHOR |
=head1 AUTHOR |
499 |
|
|