#!/usr/bin/perl
+
+# Copyright 2009-2012, Equinox Software, Inc.
+#
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License
+# as published by the Free Software Foundation; either version 2
+# of the License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+
use strict;
use warnings;
print "Writing holdings to output file(s)...\n";
# open main holdings file
- open HOLDINGS, '>', ($c->{prefix} . "-HOLDINGS.pg");
+ open HOLDINGS, '>', ($c->{prefix} . "-" . $c->{suffix} . ".pg");
# create multi files
my $multis = $m->get_multis;
my %MULTIFILE = ();
for my $t ( keys %{$multis} ) {
for my $s ( keys %{$multis->{$t}})
- { open my $fh, ">", ($c->{prefix} . "-HOLDINGS-MULT-$t$s.pg"); $MULTIFILE{"$t$s"} = $fh }
+ { open my $fh, ">", ($c->{prefix} . "-" . $c->{suffix} . "-MULT-$t$s.pg"); $MULTIFILE{"$t$s"} = $fh }
}
+ my $parallel_fields = $m->get_parallel_fields;
+
my $i = 0; # record counter
my $j = 0; # holdings counter
for my $sub ( sort keys %{$multis->{$tagid}} ) {
for my $value ( @{$rec->{tags}[$holdidx]{multi}{$sub}} ) {
my $fh = $MULTIFILE{"$tagid$sub"};
- print $fh join("\t", $rec->{egid}, $j, $value), "\n";
+ my $clean_value = $value;
+ $clean_value =~ s/[\r\n\t]//g;
+ print $fh join("\t", $rec->{egid}, $j, $clean_value), "\n";
}
}
push @out, '';
next;
}
+
+ # handle parallel fields
+ if (exists($parallel_fields->{$othertag})) {
+ my $num_fields = $#{ $rec->{tmap}{$othertag} };
+ my $tag_idx;
+ if ($holdidx > $num_fields) {
+ $tag_idx = -1;
+ } else {
+ $tag_idx = $rec->{tmap}{$othertag}[$holdidx];
+ }
+ for my $sub ( sort keys %{ $parallel_fields->{$othertag } } ) {
+ push @out, $tag_idx > -1 ? $rec->{tags}[$tag_idx]{parallel}{$sub}->[0] : '';
+ print HOLDINGS "l_", $m->name($rec->{tags}[$tag_idx]{tag}, $sub), ", " unless $j;
+ }
+ }
+
# handle only first other tag unless it is known to be multi
my $limit = 0;
if (exists($multis->{$othertag})) {
next if $m->first_only($rec->{tags}[$tag_idx]{tag}, $sub) and ($k > 1);
for my $value ( @{$rec->{tags}[$tag_idx]{multi}{$sub}} ) {
my $fh = $MULTIFILE{"$othertag$sub"};
- print $fh normalize_output(join("\t", $rec->{egid}, $j, $value)), "\n";
+ my $clean_value = $value;
+ $clean_value =~ s/[\r\n\t]//g;
+ print $fh normalize_output(join("\t", $rec->{egid}, $j, $clean_value)), "\n";
}
}
}
my $count = $s->{data}{rcnt};
my $scnt = $s->{data}{scnt};
- open DETAIL, '>', ($c->{prefix} . "-HOLDINGS-DETAIL.txt");
+ open DETAIL, '>', ($c->{prefix} . "-" . $c->{suffix} . "-DETAIL.txt");
select DETAIL;
for my $tag (sort keys %{ $tags }) {
print ">>>>> TAG $tag\n\n";
for my $subkey (sort keys %{ $tags->{$tag} }) {
my $sub = $tags->{$tag}{$subkey};
print "|| $subkey | ", $sub->{value}, " | ",
- $sub->{count}, "/", $sub->{tcnt}, " | ||\n";
+ $sub->{count}, "/", $sub->{tcnt}, " | ", ($sub->{count} > $sub->{tcnt}) ? "MULTI" : "", " ||\n";
}
print "\n";
}
close DETAIL;
- open SCOUNT, '>', ($c->{prefix} . "-HOLDINGS-SUBCOUNTS.txt");
+ open SCOUNT, '>', ($c->{prefix} . "-" . $c->{suffix} . "-SUBCOUNTS.txt");
select SCOUNT;
for my $tag (sort keys %{ $scnt }) {
print ">>>>> TAG $tag\n\n";
print "\n";
}
select STDOUT;
+ print "Saved results as ", ($c->{prefix} . "-" . $c->{suffix} . "-DETAIL.txt"), " and ",
+ ($c->{prefix} . "-" . $c->{suffix} . "-SUBCOUNTS.txt"), "\n";
}
sub dump_sample_overview {
my @tagsbyname = sort keys %{$tags};
my @tagsbycount = reverse sort { $tags->{$a} <=> $tags->{$b} } keys %{$tags};
- open SAMPLE, '>', ($c->{prefix} . "-HOLDINGS-OVERVIEW.txt");
+ open SAMPLE, '>', ($c->{prefix} . "-" . $c->{suffix} . "-OVERVIEW.txt");
select SAMPLE;
print "SAMPLE REPORT FOR ", $c->{prefix},": $count records\n\n";
print "FOUND TAGS (BY TAG) FOUND TAGS (BY COUNT)\n";
print " (", sprintf("%03d", int($tags->{ $tagsbycount[$i] } / $count * 100)), "%)\n";
}
select STDOUT;
- print "\n";
+ print "Saved results as ", ($c->{prefix} . "-" . $c->{suffix} . "-OVERVIEW.txt"), "\n";
close SAMPLE;
}
'holdings|h=i',
'copyid|c=s',
'prefix|p=s',
+ 'suffix|o=s',
'disable-pg-normalization',
'version|v',
'help',
if ($c->{map} and !($c->{holdings} and $c->{copyid}));
show_version() if $c->{version};
+ if (! $c->{suffix}) {
+ $c->{suffix} = 'HOLDINGS';
+ }
if ($c->{prefix} and !$c->{marcfile}) {
$c->{marcfile} = $c->{prefix} . ".clean.marc.xml";
}
print "\nERROR - $msg\n" if $msg;
print <<HELP;
-Usage is: extract_holdings -p PREFIX -m MARCFILE [ARGUMENTS]
+Usage is: extract_holdings --prefix PREFIX --marcfile MARCFILE [ARGUMENTS]
REQUIRED ARGUMENTS
--prefix -p Prefix string for output filenames
+ --suffix -o Suffix string for output filenames (defaults to HOLDINGS)
--marcfile MARCXML to use as source data
Defaults to 'PREFIX.clean.marc.xml'