#!/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;
use Getopt::Long;
-use Equinox::Migration::MapDrivenMARCXMLProc 1.003;
+use Equinox::Migration::MapDrivenMARCXMLProc 1.005;
use Equinox::Migration::MARCXMLSampler;
my $VERSION = '1.001';
sub extract_holdings {
my ($c) = @_;
- print "Parsing records for extraction... ";
+ print "Parsing records for extraction:\n";
my $m = Equinox::Migration::MapDrivenMARCXMLProc->new( marcfile => $c->{marcfile},
mapfile => $c->{map},
verbose => 1,
);
+
print "Writing holdings to output file(s)...\n";
# open main holdings file
open HOLDINGS, '>', ($c->{prefix} . "-HOLDINGS.pg");
print HOLDINGS "BEGIN;\n\negid, hseq, " unless $j;
my $rec = $m->{data}{recs}[$i];
my $k = 0; # holding-within-record pointer
- # for each holdings tag in the record...
- while ( defined $rec->{tmap}{ $c->{holdings} }[$k] ) {
- my $holdidx = $rec->{tmap}{ $c->{holdings} }[$k];
+
+ for my $holdidx ( @{ $rec->{tmap}{ $c->{holdings} } } ) {
+ # for each holdings tag in the record...
my $tagid = $rec->{tags}[$holdidx]{tag};
$k++;
# now get everything else in the mapping
for my $othertag ( sort keys %{$rec->{tmap}} ) {
next if $othertag eq $c->{holdings}; # ignoring the holdings, o'course
- my $idx = $rec->{tmap}{$othertag}[0]; # get index into tags struct
- for my $sub ( sort keys %{$rec->{tags}[$idx]{uni}} ) {
- push @out, $rec->{tags}[$idx]{uni}{$sub};
- print HOLDINGS "l_", $m->name($rec->{tags}[$idx]{tag}, $sub), ", "
- unless $j;
+ my $test_idx = $rec->{tmap}{$othertag}[0]; # get index into tags struct
+ unless (defined $test_idx) {
+ push @out, '';
+ next;
+ }
+ # handle only first other tag unless it is known to be multi
+ my $limit = 0;
+ if (exists($multis->{$othertag})) {
+ $limit = $#{ $rec->{tmap}{$othertag} };
+ }
+ foreach my $idx (0..$limit) {
+ my $tag_idx = $rec->{tmap}{$othertag}[$idx];
+ for my $sub ( sort keys %{$rec->{tags}[$tag_idx]{uni}} ) {
+ if ($m->first_only($rec->{tags}[$tag_idx]{tag}, $sub)) {
+ push @out, ($k == 1) ? $rec->{tags}[$tag_idx]{uni}{$sub} : '';
+ } else {
+ push @out, $rec->{tags}[$tag_idx]{uni}{$sub};
+ }
+ print HOLDINGS "l_", $m->name($rec->{tags}[$tag_idx]{tag}, $sub), ", " unless $j;
+ }
+ next unless exists($multis->{$othertag});
+ for my $sub ( sort keys %{$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";
+ }
+ }
}
}
# and dump it
print HOLDINGS "\n" unless $j;
- print HOLDINGS join("\t", @out);
+ print HOLDINGS normalize_output(join("\t", @out));
print HOLDINGS "\n";
$j++;
-
- @out = undef;
}
$i++;
- print "\r$i";
+ print "\r$i $j";
}
print "\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} > $sub->{tcnt}) ? "MULTI" : "", " ||\n";
}
print "\n";
}
print "\n";
}
select STDOUT;
+ print "Saved results as ", ($c->{prefix} . "-HOLDINGS-DETAIL.txt"), " and ",
+ ($c->{prefix} . "-HOLDINGS-SUBCOUNTS.txt"), "\n";
}
sub dump_sample_overview {
print " (", sprintf("%03d", int($tags->{ $tagsbycount[$i] } / $count * 100)), "%)\n";
}
select STDOUT;
- print "\n";
+ print "Saved results as ", ($c->{prefix} . "-HOLDINGS-OVERVIEW.txt"), "\n";
close SAMPLE;
}
'holdings|h=i',
'copyid|c=s',
'prefix|p=s',
+ 'disable-pg-normalization',
'version|v',
'help',
);
return $c;
}
+sub normalize_output {
+ my $str = shift;
+ $str =~ s!\\!\\\\!g unless $c->{'disable-pg-normalization'};
+ return $str;
+}
+
sub show_help {
my ($msg) = @_;
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
SAMPLING ARGUMENTS
--sample -s Generate a report of all tags in the MARC data
- --samplemap -sm Specify a E::M::STL map file which will be used to generate
- subfield breakdown reports about specific tags in the MARC
- data
+ --samplemap -sm Specify a Equinox::Migration::SimpleTagList map file which
+ will be used to generate subfield breakdown reports about
+ specific tags in the MARC data
--samplestr -ss As above, but with a one-liner map specified on the command
line as a string (e.g. '-ss "852 999"')
If --samplemap and --samplestr are both specified, --samplemap wins.
HOLDINGS EXTRACTION ARGUMENTS
- --map -m E::M::SM map file which will be used to extract holdings data
- from the input MARC file
+ --map -m Equinox::Migration::SubfieldMapper map file which will be
+ used to extract holdings data from the input MARC file
--holdings -h Specifies actual holdings tag
--copyid -c Specifies subfield of holdings with unique copy identifier
+ --disable-pg-normalization By default, output is normalized so that a Postgres
+ copy or \\copy can import the data without choking on
+ backslashes; use this command-line option if
+ output is not meant to be consumed by psql.
- Both these must be given together.
+ All three of these must be given together.
HELP
exit;
}