5 |
use Getopt::Std; |
use Getopt::Std; |
6 |
use Data::Dumper; |
use Data::Dumper; |
7 |
use XML::Simple; |
use XML::Simple; |
|
use Text::Unaccent 1.02; # 1.01 won't compile on my platform, |
|
8 |
use Text::Iconv; |
use Text::Iconv; |
9 |
use Config::IniFiles; |
use Config::IniFiles; |
10 |
use Encode; |
use Encode; |
16 |
|
|
17 |
my $config_file = $0; |
my $config_file = $0; |
18 |
$config_file =~ s/\.pl$/.conf/; |
$config_file =~ s/\.pl$/.conf/; |
19 |
|
$config_file = $ARGV[0] if ($ARGV[0] && -f $ARGV[0]); |
20 |
die "FATAL: can't find configuration file '$config_file'" if (! -e $config_file); |
die "FATAL: can't find configuration file '$config_file'" if (! -e $config_file); |
21 |
|
|
22 |
my $config; |
my $config; |
139 |
} else { |
} else { |
140 |
print STDERR "WARNING: field '$field' doesn't have 'name' attribute!"; |
print STDERR "WARNING: field '$field' doesn't have 'name' attribute!"; |
141 |
} |
} |
142 |
|
|
143 |
if ($field_name) { |
if ($field_name) { |
144 |
|
$field_name = x($field_name); |
145 |
if (! $last_field_name) { |
if (! $last_field_name) { |
146 |
$last_field_name = x($field_name); |
$last_field_name = $field_name; |
147 |
return $last_field_name; |
return $last_field_name; |
148 |
} elsif ($field_name ne $last_field_name) { |
} elsif ($field_name ne $last_field_name) { |
149 |
$last_field_name = x($field_name); |
$last_field_name = $field_name; |
150 |
return $last_field_name; |
return $last_field_name; |
151 |
} |
} |
152 |
} |
} |
170 |
($s,$se,$d,$i) = (0,1,0,0); |
($s,$se,$d,$i) = (0,1,0,0); |
171 |
} elsif (lc($type) =~ /^lookup/) { |
} elsif (lc($type) =~ /^lookup/) { |
172 |
($s,$se,$d,$i,$il) = (0,1,0,0,1); |
($s,$se,$d,$i,$il) = (0,1,0,0,1); |
173 |
|
} elsif ($type) { |
174 |
|
print STDERR "WARNING: unknown type: $type\n"; |
175 |
} |
} |
176 |
return ($s,$se,$d,$i,$il); |
return ($s,$se,$d,$i,$il); |
177 |
} |
} |
249 |
|
|
250 |
# what will separate last line from this one? |
# what will separate last line from this one? |
251 |
if ($display_data && $x->{append}) { |
if ($display_data && $x->{append}) { |
252 |
$line_delimiter = ' '; |
$line_delimiter = $delimiter; |
253 |
} elsif ($display_data) { |
} elsif ($display_data) { |
254 |
$line_delimiter = '<br/>'; |
$line_delimiter = '<br/>'; |
255 |
} |
} |
529 |
$swish_data =~ s/ +/ /g; |
$swish_data =~ s/ +/ /g; |
530 |
$swish_data =~ s/ +$//g; |
$swish_data =~ s/ +$//g; |
531 |
|
|
532 |
$xml .= xmlify($field."_swish", unac_string($codepage,$swish_data)); |
$xml .= xmlify($field."_swish", my_unac_string($codepage,$swish_data)); |
533 |
} |
} |
534 |
|
|
535 |
my $swish_exact_data = $cache->{swish_exact_data}->{$field}->[$page]; |
my $swish_exact_data = $cache->{swish_exact_data}->{$field}->[$page]; |
539 |
|
|
540 |
# add delimiters before and after word. |
# add delimiters before and after word. |
541 |
# That is required to produce exact match |
# That is required to produce exact match |
542 |
$xml .= xmlify($field."_swish_exact", unac_string($codepage,$swish_exact_data)); |
$xml .= xmlify($field."_swish_exact", my_unac_string($codepage,$swish_exact_data)); |
543 |
} |
} |
544 |
|
|
545 |
my $idel = $cache->{index_delimiter}->{$field}; |
my $idel = $cache->{index_delimiter}->{$field}; |
572 |
$swish_data =~ s/ +/ /g; |
$swish_data =~ s/ +/ /g; |
573 |
$swish_data =~ s/ +$//g; |
$swish_data =~ s/ +$//g; |
574 |
|
|
575 |
$xml .= xmlify($field."_swish", unac_string($codepage,$swish_data)); |
$xml .= xmlify($field."_swish", my_unac_string($codepage,$swish_data)); |
576 |
} |
} |
577 |
|
|
578 |
if ($swish_exact_data) { |
if ($swish_exact_data) { |
581 |
|
|
582 |
# add delimiters before and after word. |
# add delimiters before and after word. |
583 |
# That is required to produce exact match |
# That is required to produce exact match |
584 |
$xml .= xmlify($field."_swish_exact", unac_string($codepage,$swish_exact_data)); |
$xml .= xmlify($field."_swish_exact", my_unac_string($codepage,$swish_exact_data)); |
585 |
} |
} |
586 |
} |
} |
587 |
} |
} |
618 |
|
|
619 |
my $show_progress = $cfg_global->val('global', 'show_progress'); |
my $show_progress = $cfg_global->val('global', 'show_progress'); |
620 |
|
|
621 |
my $unac_filter = $cfg_global->val('global', 'unac_filter'); |
my $my_unac_filter = $cfg_global->val('global', 'my_unac_filter'); |
622 |
if ($unac_filter) { |
if ($my_unac_filter) { |
623 |
require $unac_filter; |
print STDERR "using $my_unac_filter to filter characters for search\n"; |
624 |
|
require $my_unac_filter; |
625 |
|
} else { |
626 |
|
print STDERR "### fallback to default my_unac_string!\n"; |
627 |
|
eval q{ |
628 |
|
sub main::my_unac_string($$) { |
629 |
|
my ($charset, $string) = (@_); |
630 |
|
return $string; |
631 |
|
} |
632 |
|
}; |
633 |
} |
} |
634 |
|
|
635 |
foreach my $database ($cfg->Sections) { |
foreach my $database ($cfg->Sections) { |
641 |
my $lookup_file = $cfg -> val($database, 'lookup_newfile'); # optional |
my $lookup_file = $cfg -> val($database, 'lookup_newfile'); # optional |
642 |
if ($lookup_file) { |
if ($lookup_file) { |
643 |
#tie %lhash, 'GDBM_File', $lookup_file, &GDBM_NEWDB, 0644; |
#tie %lhash, 'GDBM_File', $lookup_file, &GDBM_NEWDB, 0644; |
644 |
|
if (! -e $lookup_file) { |
645 |
|
open(LOOKUP, "> $lookup_file") || die "can't create $lookup_file': $!"; |
646 |
|
close(LOOKUP); |
647 |
|
} |
648 |
tie %lhash, 'TDB_File', $lookup_file, TDB_CLEAR_IF_FIRST, O_RDWR, 0644; |
tie %lhash, 'TDB_File', $lookup_file, TDB_CLEAR_IF_FIRST, O_RDWR, 0644; |
649 |
print STDERR "creating lookup file '$lookup_file'\n"; |
print STDERR "creating lookup file '$lookup_file'\n"; |
650 |
# delete memory cache for lookup file |
# delete memory cache for lookup file |
815 |
for(my $iC = $oWorksheet->{MinCol} ; defined $oWorksheet->{MaxCol} && $iC <= $oWorksheet->{MaxCol} ; $iC++) { |
for(my $iC = $oWorksheet->{MinCol} ; defined $oWorksheet->{MaxCol} && $iC <= $oWorksheet->{MaxCol} ; $iC++) { |
816 |
my $cell = $oWorksheet->{Cells}[$iR][$iC]; |
my $cell = $oWorksheet->{Cells}[$iR][$iC]; |
817 |
if ($cell) { |
if ($cell) { |
818 |
$row->{int2col($iC)} = $cell->Value; |
# this conversion is a cludge. |
819 |
|
# Files from Excell could have |
820 |
|
# characters which don't fit into |
821 |
|
# destination encoding. |
822 |
|
$row->{int2col($iC)} = $utf2cp->convert($cell->Value) || $cell->Value; |
823 |
} |
} |
824 |
} |
} |
825 |
|
|
845 |
} |
} |
846 |
} elsif ($type_base eq "marc") { |
} elsif ($type_base eq "marc") { |
847 |
|
|
848 |
require MARC; |
require MARC::File::USMARC; |
849 |
|
|
850 |
$import2cp = Text::Iconv->new($config->{marc_codepage},$codepage); |
$import2cp = Text::Iconv->new($config->{marc_codepage},$codepage); |
851 |
my $marc_file = $cfg -> val($database, 'marc_file') || die "$database doesn't have 'marc_file' defined!"; |
my $marc_file = $cfg -> val($database, 'marc_file') || die "$database doesn't have 'marc_file' defined!"; |
852 |
|
|
853 |
# optional argument is format |
# optional argument is format |
854 |
my $format = x($config->{marc_format}) || 'usmarc'; |
warn "marc_format is no longer used!" if ($config->{marc_format}); |
|
|
|
855 |
print STDERR "Reading MARC file '$marc_file'\n"; |
print STDERR "Reading MARC file '$marc_file'\n"; |
856 |
|
|
857 |
my $marc = new MARC; |
my $marc = MARC::File::USMARC->in( $marc_file ) |
858 |
my $nr = $marc->openmarc({ |
|| die "Can't open MARC file '$marc_file': ".$MARC::File::ERROR; |
|
file=>$marc_file, format=>$format |
|
|
}) || die "Can't open MARC file '$marc_file' with format '$format'"; |
|
859 |
|
|
860 |
# read MARC file in memory |
# count records in MARC file |
861 |
$marc->nextmarc(-1); |
sub marc_count { |
862 |
|
my $filename = shift || die; |
863 |
|
my $file = MARC::File::USMARC->in($filename) || die $MARC::File::ERROR; |
864 |
|
my $count = 0; |
865 |
|
while ($file->skip()) { |
866 |
|
$count++; |
867 |
|
} |
868 |
|
return $count; |
869 |
|
} |
870 |
|
|
871 |
my $max_rec = $marc->marc_count(); |
my $count = marc_count($marc_file) || warn "no records in '$marc_file'?"; |
872 |
|
|
873 |
for(my $i=1; $i<=$max_rec; $i++) { |
my $i = 0; |
874 |
|
|
875 |
progress($i,$max_rec); |
while( my $rec = $marc->next() ) { |
876 |
|
|
877 |
# store value for marc_sf.pm |
progress($i++,$count); |
|
$main::cache->{marc_record} = $i; |
|
878 |
|
|
879 |
my $swishpath = $database."#".$i; |
my $swishpath = $database."#".$i; |
880 |
|
|
881 |
if (my $xml = data2xml($type_base,$marc,$add_xml,$cfg,$database)) { |
if (my $xml = data2xml($type_base,$rec,$add_xml,$cfg,$database)) { |
882 |
$xml = $cp2utf->convert($xml); |
$xml = $cp2utf->convert($xml); |
883 |
use bytes; # as opposed to chars |
use bytes; # as opposed to chars |
884 |
print "Path-Name: $swishpath\n"; |
print "Path-Name: $swishpath\n"; |
943 |
|
|
944 |
all2xml.pl - read various file formats and dump XML for SWISH-E |
all2xml.pl - read various file formats and dump XML for SWISH-E |
945 |
|
|
946 |
|
=head1 SYNOPSYS |
947 |
|
|
948 |
|
$ all2xml.pl [test.conf] |
949 |
|
|
950 |
=head1 DESCRIPTION |
=head1 DESCRIPTION |
951 |
|
|
952 |
This command will read ISIS data file using OpenIsis perl module, MARC |
This command will read ISIS data file using OpenIsis perl module, MARC |
955 |
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 |
956 |
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. |
957 |
|
|
958 |
|
If no configuration file is specified, it will use default one called |
959 |
|
C<all2xml.conf>. |
960 |
|
|
961 |
=head1 BUGS |
=head1 BUGS |
962 |
|
|
963 |
Documentation is really lacking. However, in true Open Source spirit, source |
Documentation is really lacking. However, in true Open Source spirit, source |