#!/bin/bash
#
#    This little script finds duplicate files parsing current directory
#    and recursively all the others inside. It can accept more than one
#    dir to parse as args: eg:
#    ./duplicate_finder.sh .
#    ./duplicate_finder.sh ~/my_photos ~/las_vegas_marriage /some/where/else/folder
#
#    For duplicate i mean file with same or different names located in
#    same or different dirs.  The parsing is first done on sizes and
#    then, only on matching files, on their md5 checksum. I hope that
#    this can speed up the parsing and definitely eliminate false
#    positives.
#    
#    The script does wide use of find and inodes this is to avoid
#    problems with strange filenames.
#
#    Known bugs: a little problem with md5sum, it prepends a \
#    (backslash) to the sum if the filename contains one or mode \, this
#    problem affects only the output not the functionality of the script
#    Workarounds for this problem are welcome.
#
#    This script is a deep rewrite of one i've found online, written by
#    Jarno Elonen (thanks)
#    Lately I found fdupes, a C program that does the same (and more) of
#    this script.
#
#    Do anything you like with this but DO NOT call me for ANY problem
#    :-)
#
#    pit at asashi a dot net site
#
#
#    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., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.



if [ -e ".duplic" ] ;
then
	echo "Sorry, you should delete an old .duplic file"
	exit 0
else
echo "#!/bin/bash" > .duplic
find $@ -type f -printf "%s\n" |\
sort | uniq -d |\
while read x ; do
	find $@ -size "$x"c -printf "%i\t" -exec md5sum {} \; ;
	done |\
awk '{print $2,$1}' | sed -e s/^[\\]// |\
sort --key=1,32 | uniq -w 32 -D | awk '{print $2}' |\
while read y ; do
	find $@ -inum $y -printf "#find " -exec echo -n "$@" \; -printf " -inum %i -exec rm -i \"{}\" \";\" # size: %s\n#" -exec md5sum {} \; -printf "\n"; done >> .duplic

chmod u+x .duplic
ls -l .duplic
fi
exit 0

#    Let me explain...
#
#    1- fast check for an existing .duplic file
#    2- echo script header
#    3- find regular files - feed sort & uniq to find those of equal size
#    4- exec md5sum on this files
#    5- sort by sum
#    6- write instance for remove in the .duplic files
#
# vim:tabstop=3:expandtab:shiftwidth=3:autoindent
#