1 |
#!/usr/bin/perl -w |
#!/usr/bin/perl -w |
2 |
|
|
3 |
use strict; |
use strict; |
4 |
use OpenIsis; |
use Biblio::Isis; |
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; |
11 |
#use GDBM_File; |
#use GDBM_File; |
12 |
use Fcntl; # for O_RDWR |
use Fcntl; # for O_RDWR |
13 |
use TDB_File; |
use TDB_File; |
14 |
|
use Carp; |
15 |
|
|
16 |
$|=1; |
$|=1; |
17 |
|
|
18 |
my $config_file = $0; |
my $config_file = $0; |
19 |
$config_file =~ s/\.pl$/.conf/; |
$config_file =~ s/\.pl$/.conf/; |
20 |
$config_file = $ARGV[0] if (-f $ARGV[0]); |
$config_file = $ARGV[0] if ($ARGV[0] && -f $ARGV[0]); |
21 |
die "FATAL: can't find configuration file '$config_file'" if (! -e $config_file); |
die "FATAL: can't find configuration file '$config_file'" if (! -e $config_file); |
22 |
|
|
23 |
my $config; |
my $config; |
24 |
|
|
25 |
#use index_DBI; # default DBI module for index |
#use index_DBI; # default DBI module for index |
26 |
use index_DBI_cache; # faster DBI module using memory cache |
#use index_DBI_cache; # faster DBI module using memory cache |
27 |
|
use index_DBI_filter; # filter support for indexes |
28 |
my $index; |
my $index; |
29 |
|
|
30 |
my %opts; |
my %opts; |
63 |
'isis' => 'isis', |
'isis' => 'isis', |
64 |
'excel' => 'column', |
'excel' => 'column', |
65 |
'marc' => 'marc', |
'marc' => 'marc', |
66 |
'feed' => 'feed' |
'feed' => 'feed', |
67 |
|
'dbf' => 'isis', # special case, re-use isis import_xml |
68 |
); |
); |
69 |
|
|
70 |
my $cache; # for cacheing |
my $cache; # for cacheing |
114 |
$cache->{tags_by_order} = \@sorted_tags; |
$cache->{tags_by_order} = \@sorted_tags; |
115 |
} |
} |
116 |
|
|
117 |
|
if (! @sorted_tags) { |
118 |
|
print STDERR "WARNING: no tags for this type found in import_xml file!\n"; |
119 |
|
} |
120 |
|
|
121 |
# lookup key |
# lookup key |
122 |
my $lookup_key; |
my $lookup_key; |
123 |
|
|
146 |
} else { |
} else { |
147 |
print STDERR "WARNING: field '$field' doesn't have 'name' attribute!"; |
print STDERR "WARNING: field '$field' doesn't have 'name' attribute!"; |
148 |
} |
} |
149 |
|
|
150 |
if ($field_name) { |
if ($field_name) { |
151 |
|
$field_name = x($field_name); |
152 |
if (! $last_field_name) { |
if (! $last_field_name) { |
153 |
$last_field_name = x($field_name); |
$last_field_name = $field_name; |
154 |
return $last_field_name; |
return $last_field_name; |
155 |
} elsif ($field_name ne $last_field_name) { |
} elsif ($field_name ne $last_field_name) { |
156 |
$last_field_name = x($field_name); |
$last_field_name = $field_name; |
157 |
return $last_field_name; |
return $last_field_name; |
158 |
} |
} |
159 |
} |
} |
177 |
($s,$se,$d,$i) = (0,1,0,0); |
($s,$se,$d,$i) = (0,1,0,0); |
178 |
} elsif (lc($type) =~ /^lookup/) { |
} elsif (lc($type) =~ /^lookup/) { |
179 |
($s,$se,$d,$i,$il) = (0,1,0,0,1); |
($s,$se,$d,$i,$il) = (0,1,0,0,1); |
180 |
|
} elsif ($type) { |
181 |
|
print STDERR "WARNING: unknown type: $type\n"; |
182 |
} |
} |
183 |
return ($s,$se,$d,$i,$il); |
return ($s,$se,$d,$i,$il); |
184 |
} |
} |
264 |
# init vars so that we go into while... |
# init vars so that we go into while... |
265 |
($swish,$display) = (1,1); |
($swish,$display) = (1,1); |
266 |
|
|
|
# placeholder for all repeatable entries for index |
|
|
|
|
267 |
sub mkformat($$) { |
sub mkformat($$) { |
268 |
my $x = shift || die "mkformat needs tag reference"; |
my $x = shift || die "mkformat needs tag reference"; |
269 |
my $data = shift || return; |
my $data = shift || return; |
534 |
$swish_data =~ s/ +/ /g; |
$swish_data =~ s/ +/ /g; |
535 |
$swish_data =~ s/ +$//g; |
$swish_data =~ s/ +$//g; |
536 |
|
|
537 |
$xml .= xmlify($field."_swish", unac_string($codepage,$swish_data)); |
$xml .= xmlify($field."_swish", my_unac_string($codepage,$swish_data)); |
538 |
} |
} |
539 |
|
|
540 |
my $swish_exact_data = $cache->{swish_exact_data}->{$field}->[$page]; |
my $swish_exact_data = $cache->{swish_exact_data}->{$field}->[$page]; |
544 |
|
|
545 |
# add delimiters before and after word. |
# add delimiters before and after word. |
546 |
# That is required to produce exact match |
# That is required to produce exact match |
547 |
$xml .= xmlify($field."_swish_exact", unac_string($codepage,$swish_exact_data)); |
$xml .= xmlify($field."_swish_exact", my_unac_string($codepage,$swish_exact_data)); |
548 |
} |
} |
549 |
|
|
550 |
my $idel = $cache->{index_delimiter}->{$field}; |
my $idel = $cache->{index_delimiter}->{$field}; |
577 |
$swish_data =~ s/ +/ /g; |
$swish_data =~ s/ +/ /g; |
578 |
$swish_data =~ s/ +$//g; |
$swish_data =~ s/ +$//g; |
579 |
|
|
580 |
$xml .= xmlify($field."_swish", unac_string($codepage,$swish_data)); |
$xml .= xmlify($field."_swish", my_unac_string($codepage,$swish_data)); |
581 |
} |
} |
582 |
|
|
583 |
if ($swish_exact_data) { |
if ($swish_exact_data) { |
586 |
|
|
587 |
# add delimiters before and after word. |
# add delimiters before and after word. |
588 |
# That is required to produce exact match |
# That is required to produce exact match |
589 |
$xml .= xmlify($field."_swish_exact", unac_string($codepage,$swish_exact_data)); |
$xml .= xmlify($field."_swish_exact", my_unac_string($codepage,$swish_exact_data)); |
590 |
} |
} |
591 |
} |
} |
592 |
} |
} |
623 |
|
|
624 |
my $show_progress = $cfg_global->val('global', 'show_progress'); |
my $show_progress = $cfg_global->val('global', 'show_progress'); |
625 |
|
|
626 |
my $unac_filter = $cfg_global->val('global', 'unac_filter'); |
my $my_unac_filter = $cfg_global->val('global', 'my_unac_filter'); |
627 |
if ($unac_filter) { |
if ($my_unac_filter) { |
628 |
require $unac_filter; |
print STDERR "using $my_unac_filter to filter characters for search\n"; |
629 |
|
require $my_unac_filter; |
630 |
|
} else { |
631 |
|
print STDERR "### fallback to default my_unac_string!\n"; |
632 |
|
eval q{ |
633 |
|
sub main::my_unac_string($$) { |
634 |
|
my ($charset, $string) = (@_); |
635 |
|
return $string; |
636 |
|
} |
637 |
|
}; |
638 |
} |
} |
639 |
|
|
640 |
foreach my $database ($cfg->Sections) { |
foreach my $database ($cfg->Sections) { |
641 |
|
|
642 |
|
# save database name in global variable path for later |
643 |
|
# (need for index filter creation) |
644 |
|
$path = $database; |
645 |
|
|
646 |
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"; |
647 |
my $add_xml = $cfg -> val($database, 'xml'); # optional |
my $add_xml = $cfg -> val($database, 'xml'); # optional |
648 |
|
|
650 |
my $lookup_file = $cfg -> val($database, 'lookup_newfile'); # optional |
my $lookup_file = $cfg -> val($database, 'lookup_newfile'); # optional |
651 |
if ($lookup_file) { |
if ($lookup_file) { |
652 |
#tie %lhash, 'GDBM_File', $lookup_file, &GDBM_NEWDB, 0644; |
#tie %lhash, 'GDBM_File', $lookup_file, &GDBM_NEWDB, 0644; |
653 |
|
if (! -e $lookup_file) { |
654 |
|
open(LOOKUP, "> $lookup_file") || die "can't create $lookup_file': $!"; |
655 |
|
close(LOOKUP); |
656 |
|
} |
657 |
tie %lhash, 'TDB_File', $lookup_file, TDB_CLEAR_IF_FIRST, O_RDWR, 0644; |
tie %lhash, 'TDB_File', $lookup_file, TDB_CLEAR_IF_FIRST, O_RDWR, 0644; |
658 |
print STDERR "creating lookup file '$lookup_file'\n"; |
print STDERR "creating lookup file '$lookup_file'\n"; |
659 |
# delete memory cache for lookup file |
# delete memory cache for lookup file |
668 |
print STDERR "opening lookup file '$lookup_file'\n"; |
print STDERR "opening lookup file '$lookup_file'\n"; |
669 |
} |
} |
670 |
|
|
671 |
print STDERR "reading ./import_xml/$type.xml\n"; |
my $import_xml_file = "./import_xml/$type.xml"; |
672 |
|
|
673 |
|
if (! -r $import_xml_file) { |
674 |
|
print STDERR "ERROR: file $import_xml_file not readable skipping!\n"; |
675 |
|
next; |
676 |
|
} |
677 |
|
|
678 |
|
print STDERR "reading $import_xml_file\n"; |
679 |
|
|
680 |
# extract just type basic |
# extract just type basic |
681 |
my $type_base = $type; |
my $type_base = $type; |
682 |
$type_base =~ s/_.+$//g; |
$type_base =~ s/_.+$//g; |
683 |
|
|
684 |
$config=XMLin("./import_xml/$type.xml", ForceArray => [ $type2tag{$type_base}, 'config', 'format' ], ForceContent => 1 ); |
$config=XMLin($import_xml_file, ForceArray => [ $type2tag{$type_base}, 'config', 'format' ], ForceContent => 1 ); |
685 |
|
|
686 |
|
# helper for progress bar |
687 |
|
sub fmt_time { |
688 |
|
my $t = shift || 0; |
689 |
|
my $out = ""; |
690 |
|
|
691 |
|
my ($ss,$mm,$hh) = gmtime($t); |
692 |
|
$out .= "${hh}h" if ($hh); |
693 |
|
$out .= sprintf("%02d:%02d", $mm,$ss); |
694 |
|
$out .= " " if ($hh == 0); |
695 |
|
return $out; |
696 |
|
} |
697 |
|
|
698 |
# output current progress indicator |
# output current progress indicator |
699 |
my $last_p = 0; |
my $last_p = 0; |
700 |
|
my $start_t = time(); |
701 |
sub progress { |
sub progress { |
702 |
return if (! $show_progress); |
return if (! $show_progress); |
703 |
my $current = shift; |
my $current = shift; |
704 |
my $total = shift || 1; |
my $total = shift || 1; |
705 |
my $p = int($current * 100 / $total); |
my $p = int($current * 100 / $total); |
706 |
if ($p != $last_p) { |
if ($p < $last_p || $current == 1) { |
707 |
printf STDERR ("%5d / %5d [%-51s] %-2d %% \r",$current,$total,"=" x ($p/2).">", $p ); |
$start_t = time(); |
708 |
|
$last_p = 0; |
709 |
|
} elsif ($p != $last_p) { |
710 |
|
my $rate = ($current / (time() - $start_t || 1)); |
711 |
|
my $eta = ($total-$current) / ($rate || 1); |
712 |
|
printf STDERR ("%5d [%-38s] %-5d %0.1f/s %s\r",$current,"=" x ($p/3)."$p%>", $total, $rate, fmt_time($eta)); |
713 |
$last_p = $p; |
$last_p = $p; |
714 |
} |
} |
715 |
} |
} |
716 |
|
|
717 |
my $fake_dir = 1; |
my $fake_dir = 1; |
718 |
|
my $fake_pos = 0; |
719 |
|
my $last_fake_t = time(); |
720 |
sub fakeprogress { |
sub fakeprogress { |
721 |
return if (! $show_progress); |
return if (! $show_progress); |
722 |
my $current = shift @_; |
my $current = shift @_; |
723 |
|
|
724 |
my @ind = ('-','\\','|','/','-','\\','|','/', '-'); |
my @ind = ('-','\\','|','/','-','\\','|','/'); |
725 |
|
|
726 |
|
if ($current < $fake_pos) { |
727 |
|
$start_t = time(); |
728 |
|
$last_fake_t = 0; |
729 |
|
$fake_dir = 1; |
730 |
|
$fake_pos = 0; |
731 |
|
} |
732 |
|
|
733 |
|
if (time()-$last_fake_t >= 1) { |
734 |
|
$last_fake_t = time(); |
735 |
|
$fake_pos += $fake_dir; |
736 |
|
$fake_dir = -$fake_dir if ($fake_pos > 38); |
737 |
|
} |
738 |
|
|
739 |
$last_p += $fake_dir; |
if ($current % 10 == 0) { |
740 |
$fake_dir = -$fake_dir if ($last_p > 1000 || $last_p < 0); |
my $rate = ($current / (time() - $start_t || 1)); |
741 |
if ($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]); |
|
742 |
} |
} |
743 |
} |
} |
744 |
|
|
753 |
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!"; |
754 |
|
|
755 |
$import2cp = Text::Iconv->new($config->{isis_codepage},$codepage); |
$import2cp = Text::Iconv->new($config->{isis_codepage},$codepage); |
756 |
my $db = OpenIsis::open( $isis_db ); |
my $db = new Biblio::Isis( isisdb => $isis_db ); |
757 |
|
|
758 |
# check if .txt database for OpenIsis is zero length, |
if (! $db) { |
759 |
# if so, erase it and re-open database |
print STDERR "FATAL: can't read ISIS database: $isis_db, skipping...\n"; |
|
sub check_txt_db { |
|
|
my $isis_db = shift || die "need isis database name"; |
|
|
my $reopen = 0; |
|
|
|
|
|
if (-e $isis_db.".TXT") { |
|
|
print STDERR "WARNING: removing $isis_db.TXT OpenIsis database...\n"; |
|
|
unlink $isis_db.".TXT" || warn "FATAL: unlink error on '$isis_db.TXT': $!"; |
|
|
$reopen++; |
|
|
} |
|
|
if (-e $isis_db.".PTR") { |
|
|
print STDERR "WARNING: removing $isis_db.PTR OpenIsis database...\n"; |
|
|
unlink $isis_db.".PTR" || warn "FATAL: unlink error on '$isis_db.PTR': $!"; |
|
|
$reopen++; |
|
|
} |
|
|
return OpenIsis::open( $isis_db ) if ($reopen); |
|
|
} |
|
|
|
|
|
# EOF error |
|
|
if ($db == -1) { |
|
|
$db = check_txt_db($isis_db); |
|
|
if ($db == -1) { |
|
|
print STDERR "FATAL: OpenIsis can't open zero size file $isis_db\n"; |
|
|
next; |
|
|
} |
|
|
} |
|
|
|
|
|
# OpenIsis::ERR_BADF |
|
|
if ($db == -4) { |
|
|
print STDERR "FATAL: OpenIsis can't find file $isis_db\n"; |
|
|
next; |
|
|
# OpenIsis::ERR_IO |
|
|
} elsif ($db == -5) { |
|
|
print STDERR "FATAL: OpenIsis can't access file $isis_db\n"; |
|
|
next; |
|
|
} elsif ($db < 0) { |
|
|
print STDERR "FATAL: OpenIsis unknown error $db with file $isis_db\n"; |
|
760 |
next; |
next; |
761 |
} |
} |
762 |
|
|
763 |
my $max_rowid = OpenIsis::maxRowid( $db ); |
my $max_rowid = $db->count if ($db); |
|
|
|
|
# if 0 records, try to rease isis .txt database |
|
|
if ($max_rowid == 0) { |
|
|
# force removal of database |
|
|
$db = check_txt_db($isis_db); |
|
|
$max_rowid = OpenIsis::maxRowid( $db ); |
|
|
} |
|
764 |
|
|
765 |
print STDERR "Reading database: $isis_db [$max_rowid rows]\n"; |
print STDERR "Reading database: $isis_db [$max_rowid rows]\n"; |
766 |
|
|
|
my $path = $database; |
|
|
|
|
767 |
for (my $row_id = 1; $row_id <= $max_rowid; $row_id++ ) { |
for (my $row_id = 1; $row_id <= $max_rowid; $row_id++ ) { |
768 |
my $row = OpenIsis::read( $db, $row_id ); |
my $row = $db->to_hash( $row_id ); |
769 |
if ($row && $row->{mfn}) { |
if ($row) { |
770 |
|
|
771 |
|
$row->{mfn} = $row_id; |
772 |
|
$row->{record} = $db->{record}; |
773 |
|
|
774 |
progress($row->{mfn}, $max_rowid); |
progress($row->{mfn}, $max_rowid); |
775 |
|
|
776 |
my $swishpath = $path."#".int($row->{mfn}); |
my $swishpath = $path."#".int($row->{mfn}); |
784 |
} |
} |
785 |
} |
} |
786 |
} |
} |
|
# for this to work with current version of OpenIsis (0.9.0) |
|
|
# you might need my patch from |
|
|
# http://www.rot13.org/~dpavlin/projects/openisis-0.9.0-perl_close.diff |
|
|
OpenIsis::close($db); |
|
787 |
print STDERR "\n"; |
print STDERR "\n"; |
788 |
|
|
789 |
} elsif ($type_base eq "excel") { |
} elsif ($type_base eq "excel") { |
817 |
for(my $iC = $oWorksheet->{MinCol} ; defined $oWorksheet->{MaxCol} && $iC <= $oWorksheet->{MaxCol} ; $iC++) { |
for(my $iC = $oWorksheet->{MinCol} ; defined $oWorksheet->{MaxCol} && $iC <= $oWorksheet->{MaxCol} ; $iC++) { |
818 |
my $cell = $oWorksheet->{Cells}[$iR][$iC]; |
my $cell = $oWorksheet->{Cells}[$iR][$iC]; |
819 |
if ($cell) { |
if ($cell) { |
820 |
$row->{int2col($iC)} = $cell->Value; |
# this conversion is a cludge. |
821 |
|
# Files from Excell could have |
822 |
|
# characters which don't fit into |
823 |
|
# destination encoding. |
824 |
|
$row->{int2col($iC)} = $utf2cp->convert($cell->Value) || $cell->Value; |
825 |
} |
} |
826 |
} |
} |
827 |
|
|
845 |
print "Document-Type: XML\n\n$xml\n"; |
print "Document-Type: XML\n\n$xml\n"; |
846 |
} |
} |
847 |
} |
} |
848 |
|
|
849 |
|
print STDERR "\n"; |
850 |
|
|
851 |
} elsif ($type_base eq "marc") { |
} elsif ($type_base eq "marc") { |
852 |
|
|
853 |
require MARC; |
require MARC::File::USMARC; |
854 |
|
|
855 |
$import2cp = Text::Iconv->new($config->{marc_codepage},$codepage); |
$import2cp = Text::Iconv->new($config->{marc_codepage},$codepage); |
856 |
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!"; |
857 |
|
|
858 |
# optional argument is format |
# optional argument is format |
859 |
my $format = x($config->{marc_format}) || 'usmarc'; |
warn "marc_format is no longer used!" if ($config->{marc_format}); |
|
|
|
860 |
print STDERR "Reading MARC file '$marc_file'\n"; |
print STDERR "Reading MARC file '$marc_file'\n"; |
861 |
|
|
862 |
my $marc = new MARC; |
my $marc = MARC::File::USMARC->in( $marc_file ); |
863 |
my $nr = $marc->openmarc({ |
|
864 |
file=>$marc_file, format=>$format |
if (! $marc) { |
865 |
}) || die "Can't open MARC file '$marc_file' with format '$format'"; |
print STDERR "FATAL: can't read MARC file: $marc_file, skipping...\n"; |
866 |
|
next; |
867 |
|
} |
868 |
|
|
869 |
# read MARC file in memory |
# count records in MARC file |
870 |
$marc->nextmarc(-1); |
sub marc_count { |
871 |
|
my $filename = shift || die; |
872 |
|
my $file = MARC::File::USMARC->in($filename) || return; |
873 |
|
my $count = 0; |
874 |
|
while ($file->skip()) { |
875 |
|
$count++; |
876 |
|
} |
877 |
|
return $count; |
878 |
|
} |
879 |
|
|
880 |
my $max_rec = $marc->marc_count(); |
my $count = marc_count($marc_file) || warn "no records in '$marc_file'?"; |
881 |
|
|
882 |
for(my $i=1; $i<=$max_rec; $i++) { |
my $i = 1; |
883 |
|
|
884 |
progress($i,$max_rec); |
while( my $rec = $marc->next() ) { |
885 |
|
|
886 |
# store value for marc_sf.pm |
progress($i,$count); |
|
$main::cache->{marc_record} = $i; |
|
887 |
|
|
888 |
my $swishpath = $database."#".$i; |
my $swishpath = $database."#".$i; |
889 |
|
|
890 |
if (my $xml = data2xml($type_base,$marc,$add_xml,$cfg,$database)) { |
if (my $xml = data2xml($type_base,$rec,$add_xml,$cfg,$database)) { |
891 |
$xml = $cp2utf->convert($xml); |
$xml = $cp2utf->convert($xml); |
892 |
use bytes; # as opposed to chars |
use bytes; # as opposed to chars |
893 |
print "Path-Name: $swishpath\n"; |
print "Path-Name: $swishpath\n"; |
894 |
print "Content-Length: ".(length($xml)+1)."\n"; |
print "Content-Length: ".(length($xml)+1)."\n"; |
895 |
print "Document-Type: XML\n\n$xml\n"; |
print "Document-Type: XML\n\n$xml\n"; |
896 |
} |
} |
897 |
|
|
898 |
|
$i++; |
899 |
} |
} |
900 |
|
|
901 |
print STDERR "\n"; |
print STDERR "\n"; |
940 |
} |
} |
941 |
# close lookup |
# close lookup |
942 |
untie %lhash if (%lhash); |
untie %lhash if (%lhash); |
943 |
|
|
944 |
|
} elsif ($type_base eq "dbf") { |
945 |
|
|
946 |
|
my $dbf_file = $cfg -> val($database, 'dbf_file') || die "$database doesn't have 'dbf_file' defined!"; |
947 |
|
my $dbf_codepage = $cfg -> val($database, 'dbf_codepage') || die "$database doesn't have 'dbf_codepage' defined!"; |
948 |
|
my $dbf_mapping = $cfg -> val($database, 'dbf_mapping') || die "$database doesn't have 'dbf_mapping' defined!"; |
949 |
|
|
950 |
|
$import2cp = Text::Iconv->new($dbf_codepage,$codepage); |
951 |
|
require XBase; |
952 |
|
my $db = new XBase $dbf_file; |
953 |
|
|
954 |
|
if (! $db) { |
955 |
|
print STDERR "ERROR: can't read DBF database: $dbf_file, skipping...\n"; |
956 |
|
next; |
957 |
|
} |
958 |
|
|
959 |
|
my $max_rowid = $db->last_record; |
960 |
|
|
961 |
|
print STDERR "Reading database: $dbf_file [$max_rowid rows]\n"; |
962 |
|
|
963 |
|
my %dbf2iso; |
964 |
|
foreach my $m (split(/[\n\r]+/,$dbf_mapping)) { |
965 |
|
my ($col,$fld) = split(/\s+/,$m,2); |
966 |
|
$dbf2iso{$col} = $fld; |
967 |
|
} |
968 |
|
|
969 |
|
#print STDERR "## dbf2iso: ",Dumper(\%dbf2iso),"\n## /dbf2iso\n"; |
970 |
|
|
971 |
|
# bad, bad... |
972 |
|
require "to_hash.pm"; |
973 |
|
|
974 |
|
foreach my $row_id (0 .. $max_rowid) { |
975 |
|
my $dbf_row = $db->get_record_as_hash($row_id); |
976 |
|
if ($dbf_row) { |
977 |
|
|
978 |
|
#print STDERR "## dbf_row: ",Dumper($dbf_row),"\n## /dbf_row\n"; |
979 |
|
# apply mapping from config file |
980 |
|
# all unspecified records will get _ in |
981 |
|
# front of them - _DELETE will be __DELETE |
982 |
|
my $rec; |
983 |
|
map { |
984 |
|
my $new_fld = $dbf2iso{$_} || '_'.$_; |
985 |
|
my $data = $dbf_row->{$_}; |
986 |
|
push @{ $rec->{$new_fld} }, $data if ($data && $data !~ /^(?:\s+|\$a\.|)$/); |
987 |
|
} keys %{$dbf_row}; |
988 |
|
#print STDERR "## rec: ",Dumper($rec),"\n## /rec\n"; |
989 |
|
my $row = to_hash($row_id+1, $rec); |
990 |
|
|
991 |
|
$row->{mfn} = $row_id+1; |
992 |
|
$row->{record} = $rec; |
993 |
|
|
994 |
|
#print STDERR "## row: ",Dumper($row),"\n## /row\n"; |
995 |
|
progress($row->{mfn}, $max_rowid); |
996 |
|
|
997 |
|
my $swishpath = $path."#".int($row->{mfn}); |
998 |
|
|
999 |
|
if (my $xml = data2xml($type_base,$row,$add_xml,$cfg,$database)) { |
1000 |
|
$xml = $cp2utf->convert($xml); |
1001 |
|
use bytes; # as opposed to chars |
1002 |
|
print "Path-Name: $swishpath\n"; |
1003 |
|
print "Content-Length: ".(length($xml)+1)."\n"; |
1004 |
|
print "Document-Type: XML\n\n$xml\n"; |
1005 |
|
} |
1006 |
|
} |
1007 |
|
} |
1008 |
|
print STDERR "\n"; |
1009 |
} |
} |
1010 |
} |
} |
1011 |
|
|
1026 |
|
|
1027 |
=head1 DESCRIPTION |
=head1 DESCRIPTION |
1028 |
|
|
1029 |
This command will read ISIS data file using OpenIsis perl module, MARC |
This command will read ISIS data file using Biblio::Isis perl module, MARC |
1030 |
records using MARC module and optionally Micro$oft Excel files to |
records using MARC::File module and optionally Micro$oft Excel files to |
1031 |
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, |
1032 |
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 |
1033 |
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. |