1 |
#!/usr/bin/perl -w |
#!/usr/bin/perl -w |
2 |
|
|
3 |
use strict; |
use strict; |
4 |
use IsisDB; |
use Biblio::Isis; |
5 |
use Getopt::Std; |
use Getopt::Std; |
6 |
use Data::Dumper; |
use Data::Dumper; |
7 |
use XML::Simple; |
use XML::Simple; |
22 |
my $config; |
my $config; |
23 |
|
|
24 |
#use index_DBI; # default DBI module for index |
#use index_DBI; # default DBI module for index |
25 |
use index_DBI_cache; # faster DBI module using memory cache |
#use index_DBI_cache; # faster DBI module using memory cache |
26 |
|
use index_DBI_filter; # filter support for indexes |
27 |
my $index; |
my $index; |
28 |
|
|
29 |
my %opts; |
my %opts; |
258 |
# init vars so that we go into while... |
# init vars so that we go into while... |
259 |
($swish,$display) = (1,1); |
($swish,$display) = (1,1); |
260 |
|
|
|
# placeholder for all repeatable entries for index |
|
|
|
|
261 |
sub mkformat($$) { |
sub mkformat($$) { |
262 |
my $x = shift || die "mkformat needs tag reference"; |
my $x = shift || die "mkformat needs tag reference"; |
263 |
my $data = shift || return; |
my $data = shift || return; |
686 |
my $current = shift; |
my $current = shift; |
687 |
my $total = shift || 1; |
my $total = shift || 1; |
688 |
my $p = int($current * 100 / $total); |
my $p = int($current * 100 / $total); |
689 |
if ($p < $last_p) { |
if ($p < $last_p || $current == 1) { |
690 |
$start_t = time(); |
$start_t = time(); |
691 |
|
$last_p = 0; |
692 |
} elsif ($p != $last_p) { |
} elsif ($p != $last_p) { |
693 |
my $rate = ($current / (time() - $start_t || 1)); |
my $rate = ($current / (time() - $start_t || 1)); |
694 |
my $eta = ($total-$current) / ($rate || 1); |
my $eta = ($total-$current) / ($rate || 1); |
698 |
} |
} |
699 |
|
|
700 |
my $fake_dir = 1; |
my $fake_dir = 1; |
701 |
|
my $fake_pos = 0; |
702 |
|
my $last_fake_t = time(); |
703 |
sub fakeprogress { |
sub fakeprogress { |
704 |
return if (! $show_progress); |
return if (! $show_progress); |
705 |
my $current = shift @_; |
my $current = shift @_; |
706 |
|
|
707 |
my @ind = ('-','\\','|','/','-','\\','|','/', '-'); |
my @ind = ('-','\\','|','/','-','\\','|','/'); |
708 |
|
|
709 |
|
if ($current < $fake_pos) { |
710 |
|
$start_t = time(); |
711 |
|
$last_fake_t = 0; |
712 |
|
$fake_dir = 1; |
713 |
|
$fake_pos = 0; |
714 |
|
} |
715 |
|
|
716 |
|
if (time()-$last_fake_t >= 1) { |
717 |
|
$last_fake_t = time(); |
718 |
|
$fake_pos += $fake_dir; |
719 |
|
$fake_dir = -$fake_dir if ($fake_pos > 38); |
720 |
|
} |
721 |
|
|
722 |
$last_p += $fake_dir; |
if ($current % 10 == 0) { |
723 |
$fake_dir = -$fake_dir if ($last_p > 1000 || $last_p < 0); |
my $rate = ($current / (time() - $start_t || 1)); |
724 |
if ($last_p % 10 == 0) { |
printf STDERR ("%5d [%-38s] %0.1f/s\r",$current, " " x $fake_pos .$ind[($current / 10) % 8], $rate); |
|
printf STDERR ("%5d / %5s [%-51s]\r",$current,"?"," " x ($last_p/20).$ind[($last_p/20) % $#ind]); |
|
725 |
} |
} |
726 |
} |
} |
727 |
|
|
736 |
my $isis_db = $cfg -> val($database, 'isis_db') || die "$database doesn't have 'isis_db' defined!"; |
my $isis_db = $cfg -> val($database, 'isis_db') || die "$database doesn't have 'isis_db' defined!"; |
737 |
|
|
738 |
$import2cp = Text::Iconv->new($config->{isis_codepage},$codepage); |
$import2cp = Text::Iconv->new($config->{isis_codepage},$codepage); |
739 |
my $db = new IsisDB( isisdb => $isis_db ); |
my $db = new Biblio::Isis( isisdb => $isis_db ); |
740 |
|
|
741 |
|
my $max_rowid = $db->count; |
742 |
|
|
743 |
my $max_rowid = $db->{'maxmfn'} || die "can't find maxmfn"; |
if (! $max_rowid) { |
744 |
|
print STDERR "FATAL: can't read ISIS database: $isis_db, skipping...\n"; |
745 |
|
next; |
746 |
|
} |
747 |
|
|
748 |
print STDERR "Reading database: $isis_db [$max_rowid rows]\n"; |
print STDERR "Reading database: $isis_db [$max_rowid rows]\n"; |
749 |
|
|
750 |
my $path = $database; |
$path = $database; |
751 |
|
|
752 |
for (my $row_id = 1; $row_id <= $max_rowid; $row_id++ ) { |
for (my $row_id = 1; $row_id <= $max_rowid; $row_id++ ) { |
753 |
my $row = $db->to_hash( $row_id ); |
my $row = $db->to_hash( $row_id ); |
841 |
warn "marc_format is no longer used!" if ($config->{marc_format}); |
warn "marc_format is no longer used!" if ($config->{marc_format}); |
842 |
print STDERR "Reading MARC file '$marc_file'\n"; |
print STDERR "Reading MARC file '$marc_file'\n"; |
843 |
|
|
844 |
my $marc = MARC::File::USMARC->in( $marc_file ) |
my $marc = MARC::File::USMARC->in( $marc_file ); |
845 |
|| die "Can't open MARC file '$marc_file': ".$MARC::File::ERROR; |
|
846 |
|
if (! $marc) { |
847 |
|
print STDERR "FATAL: can't read MARC file: $marc_file, skipping...\n"; |
848 |
|
next; |
849 |
|
} |
850 |
|
|
851 |
# count records in MARC file |
# count records in MARC file |
852 |
sub marc_count { |
sub marc_count { |
853 |
my $filename = shift || die; |
my $filename = shift || die; |
854 |
my $file = MARC::File::USMARC->in($filename) || die $MARC::File::ERROR; |
my $file = MARC::File::USMARC->in($filename) || return; |
855 |
my $count = 0; |
my $count = 0; |
856 |
while ($file->skip()) { |
while ($file->skip()) { |
857 |
$count++; |
$count++; |
861 |
|
|
862 |
my $count = marc_count($marc_file) || warn "no records in '$marc_file'?"; |
my $count = marc_count($marc_file) || warn "no records in '$marc_file'?"; |
863 |
|
|
864 |
my $i = 0; |
my $i = 1; |
865 |
|
|
866 |
while( my $rec = $marc->next() ) { |
while( my $rec = $marc->next() ) { |
867 |
|
|
868 |
progress($i++,$count); |
progress($i,$count); |
869 |
|
|
870 |
my $swishpath = $database."#".$i; |
my $swishpath = $database."#".$i; |
871 |
|
|
876 |
print "Content-Length: ".(length($xml)+1)."\n"; |
print "Content-Length: ".(length($xml)+1)."\n"; |
877 |
print "Document-Type: XML\n\n$xml\n"; |
print "Document-Type: XML\n\n$xml\n"; |
878 |
} |
} |
879 |
|
|
880 |
|
$i++; |
881 |
} |
} |
882 |
|
|
883 |
print STDERR "\n"; |
print STDERR "\n"; |
942 |
|
|
943 |
=head1 DESCRIPTION |
=head1 DESCRIPTION |
944 |
|
|
945 |
This command will read ISIS data file using IsisDB perl module, MARC |
This command will read ISIS data file using Biblio::Isis perl module, MARC |
946 |
records using MARC module and optionally Micro$oft Excel files to |
records using MARC::File module and optionally Micro$oft Excel files to |
947 |
create one XML file for usage with I<SWISH-E> indexer. Dispite it's name, |
create one XML file for usage with I<SWISH-E> indexer. Dispite it's name, |
948 |
this script B<isn't general xml generator> from isis files (isis allready |
this script B<isn't general xml generator> from isis files (isis allready |
949 |
has something like that). Output of this script is tailor-made for SWISH-E. |
has something like that). Output of this script is tailor-made for SWISH-E. |