xml::twig help

[Ken Foskey]

I am extracting addresses from an XML file to process through other
programs using pipe delimiter the following code works but this is going
to get 130,000 records through it it must be very efficient and I cannot
follow the documentation on the best way to do this.

After this simple one is programmed I have to change a much more complex
version of this program.

#!/usr/bin/perl -w
# vi:set sw=4 ts=4 et cin:
# $Id:$

=head1 SYNOPSIS

Extract addresses from an XML file into pipe delimited file.

   usage: address_extract.pl  xml_file

=cut

use warnings;
use strict;

use XML::Twig qw(:strict);

sub no_pipe
{
    my $value = shift;

    $value =~ s/\|//g;
    return $value;
}

if( ! -f $ARGV[0] ) {
    print "$ARGV[0] is not a filename, requires filename as first
parameter!\n";
}

my $sort;
my $sort_file = $ARGV[0].'.unsorted';
unlink $sort_file; # in case of rerun
open( $sort, '>', $sort_file  ) 
    or die "Unable to open $sort_file for output $!";

my $ref = XML::Twig->new( twig_handlers=>{mem=>\&member} ) 
    or die "Unable to open $ARGV[0] $!";

my $member = 0;

$ref->parsefile( $ARGV[0] );

sub get_value
{
    my ($mem_ref, $key) = @_;
    my @array = $mem_ref->descendants( $key );
    return $array[0]->text();
}

sub member {
    my ($t, $mem_ref) = @_;
    $member++;

    my $mem_no = get_value( $mem_ref, 'member' );
    my $add1   = get_value( $mem_ref, 'add1' );
    my $add2   = get_value( $mem_ref, 'add2' );
    my $add3   = get_value( $mem_ref, 'add3' );
    my $suburb = get_value( $mem_ref, 'suburb' );
    my $state  = get_value( $mem_ref, 'state' );
    my $pcode  = get_value( $mem_ref, 'pcode' );

    print $sort join( '|', $member,
                     $mem_no,
                     no_pipe( $add1 ),
                     no_pipe( $add2 ),
                     no_pipe( $add3 ),
                     no_pipe( $suburb),
                     $state,
                     $pcode,
                    ) ."\n";
    return 1;
}