Delete duplicate files (ie. same hash) within a directory.

deldup.sh

#!/bin/bash

MDF="/tmp/deldup.md5"
DUP="/tmp/deldup.list"
if [ $MDF -nt . ]; then
	echo found cached hash list in $MDF
else 
	echo -n "hashing files... "
	find -O3 . -type f -print0 $@ | xargs -L 1 -P 2 -0 md5sum > $MDF
	echo finished
fi

cut -f1 -d" " < $MDF | sort | uniq -d > $DUP

echo Found $(cat $DUP | wc -l) duplicate files
for dh in $(cat $DUP); do
	echo
	echo All files with hash $dh:
	grep -a $dh $MDF | cut -f2- -d" " | { 
		readarray -t -O 1 FILES

		C=1 # counter
		for line in $(seq ${#FILES[@]}); do
			printf "%4d\t%s\n" $C "${FILES[$C]}"
			C=$((C+1))
		done

		echo -n 'Select to delete (eg. "1", "2,3,4", "1,3-5"): '
		IFS=',' read -ra RANGE <&1; 
		for i in "${RANGE[@]}"; do
			if [[ $i =~ ^([0-9]+)-([0-9]+)$ ]]; then
				START=${BASH_REMATCH[1]}
				END=${BASH_REMATCH[2]}
				for x in $(seq $START $END); do
					rm -v "$(echo ${FILES[$x]} | xargs -0 echo)"
				done
			elif [[ $i =~ ^[0-9]+$ ]]; then
                    		rm -v "$(echo ${FILES[$i]} | xargs -0 echo)"
			else
				echo Invalid range or number \"$i\"
			fi
		done
	}
done

echo
read -p "delete cache [y/N]? " DC
[[ $DC =~ ^[yY] ]] && rm -v $MDF && rm -v $DUP