#!/bin/sh
#
# Local version: 0.5
# Copyright (c) 2008 Peter Kuyarov, All rights reserved [some of it]
#  Thu Feb 21 08:20:55 MST 2008 - basics, more "options" coming soon
#
# script to recursively check for duplicate files in current directory
#
# scripts@pknet.net
# http://peterk.org/scripts/
#

PATH=/sbin:/bin:/usr/sbin:/usr/bin:/usr/games:/usr/local/sbin:/usr/local/bin:/usr/X11R6/bin:/usr/local/vpopmail/bin:/root/bin
export PATH

# user configurable variables
# files
cksumraw=/tmp/cksumraw
echo -n > $cksumraw

cksumsorted=/tmp/cksumsorted
echo -n > $cksumsorted

cksumresults=/tmp/cksumresults
echo -n > $cksumresults

#init start of list
startlist=0

#start cksumming directory for all files
#sort list, then check if cksum is a duplicate in list
#cksum $(find ./ -type f -print)|sort -k 1,1n |

find ./ | while read file ; do cksum "$file" >> $cksumraw;done
sort $cksumraw > $cksumsorted
# now go through sorted list to check for dups
cat $cksumsorted | \
while read c1 c2 n3
do
   # if first file, make it same as previous
   if [ $startlist -eq 0 ]
   then
      startlist=1
      prevchksum=$c1
      prevfile=$n3
      continue
   fi
   # if current checksum equals saved checksum,
   # the file is a duplicate
   if [ $prevchksum -eq $c1 ]
   then
      printf "file $prevfile \n    has duplicate $n3 \n" >> $cksumresults
      printf "file $prevfile \n    has duplicate $n3 \n"
   else
      prevchksum=$c1
      prevfile=$n3
   fi
done
rm $cksumraw
rm $cksumsorted
echo Output list of duplicates saved in $cksumresults