#!/usr/bin/perl -w
use warnings;
use strict;

my $record_element = 'dcterms:available';
my $filename_element = 'dc:identifier';

my ($file, $dir) = @ARGV;
defined($file) && defined($dir) || usage();
chop($dir) if $dir =~ m#/$#;
#$/ = "</$record_element>";
mkdir $dir;

open(INPUT, "<$ARGV[0]") || die "Failed to open $ARGV[0]\n";
  $file = "INPUT";

my $record_count = 0;
my $header1 = '<?xml version="1.0" encoding="UTF-8"?>';
my $header2 = '<qualifieddc xmlns="http://example.org/appqualifieddc/"';  
my $header3 = 'xmlns:dc="http://purl.org/dc/elements/1.1/"';
my $header4 = 'xmlns:dcterms="http://purl.org/dc/terms/"';
my $header5 = 'xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"';
my $header6 = 'xsi:schemaLocation="http://example.org/appqualifieddc/';
my $header7 = 'http://dublincore.org/schemas/xmls/qdc/2003/04/02/appqualifieddc.xsd"';
my $closing = '</qualifieddc>';

$/ ='terms/">';
<INPUT>;

$/ = "</$record_element>";

while(<INPUT>){
  next if m/^\s*$/;    #Disregard 0+ trailing spaces
  s/^\s*//;            #Collapse 0+ leading spaces
  $record_count++;
  if (m#<$filename_element xsi:type="dcterms:URI">(\w+) (\w+) (\w+)_(\w+)</$filename_element>#s)
  	{
	msg("Just matched $1 $2 $3_$4");
	my $outfile = "$dir/$4.xml";
	open (OUTPUT, '>', $outfile) or die "Can't create/open $outfile for writing";
        print OUTPUT $header1, "\n", $header2, "\n", $header3, "\n", $header4, "\n", $header5, "\n", $header6, "\n", $header7, "\n";      
	print OUTPUT $_, "\n";
 	print OUTPUT $closing;

	close (OUTPUT) or die "Couldn't close $outfile after writing record";
      } 
  else {
	warn("Couldn't find filename in record $record_count, skipping...");
       }
      }

close (INPUT) or die "Couldn't close $file";
close (OUTFILE);

$record_count--;
msg("Processed $record_count records from $file");

sub msg {
    print @_, "\n";
}

sub usage {
    msg("Usage: $0 <file> <directory>");
    exit(1);
}