#!/usr/bin/perl

# splitExcel

# pulls top line off txt file specified, and will add it onto the beginning of all the files it creates
# out of the remainder of lines.

# all other lines will be judged based on the collection number portion of the item number in the 
# 2nd tab column.  All lines for each collection will be gathered, and the collection name used to create 
# the output file, which will be collnum.txt.

## Copyright (c) 2010, The University of Alabama Libraries. 
## Contributed by Jody DeRidder, 7/30/10.
## All rights reserved.

## Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:

##    * Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
##    * Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in 
##       the documentation and/or other materials provided with the distribution.
##    * Neither the name of The University of Alabama Libraries nor the names of its contributors may be used to endorse or promote products 
##       derived from this software without specific prior written permission.

##THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, 
##THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR 
##CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, 
##PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 
##LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
##EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

$doMe = "/srv/deposits/hold/WadeHallCivilWar_remediated.txt";
#$doMe = "/srv/deposits/hold/u0001_2009001_thru_2009037.txt";

# output files go in ./splits directory
$base = "/srv/scripts/metadata/splits/";

open (IN, $doMe) or die "can't read $doMe\n";
undef $first;
while ($line = <IN>){ 
  if (!$first){ $first = $line;}
  elsif ($line =~ /([a-z]{1}\d{4}\_\d{7}).*/){
#     print "found a match! $1\n";
     $collnum = $1;
     push (@{$collLists{$collnum}}, $line);
     }
  else{  print "no match!  $line\n";}
  }
close(IN);

@colls = keys (%collLists);
foreach $coll (@colls){
  $mine = $base.$coll.".txt";
  open (OUT, ">".$mine) or die "can't write to $mine\n";
  print OUT $first;
  @mylist = @{$collLists{$coll}};
  foreach (@mylist){ print OUT $_;}
  close OUT;
  }