Created
January 19, 2011 19:57
-
-
Save mcgrew/786739 to your computer and use it in GitHub Desktop.
Removes duplicate files in a directory, replacing them with hard links.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/sh | |
dir=$1 | |
if [ -z $dir ]; then | |
dir="." | |
fi; | |
# create a temporary file name | |
TMPFILE="/tmp/$(echo -n "$dir" | md5sum | awk '{print $1}' | tr -d '\n')_$(date +%Y.%m.%d.%H.%M)_dupes.txt" | |
#find the duplicates and output the list to the temporary file | |
echo "Looking for duplicates..." | |
nice fdupes -qr1 $dir | egrep -i "\.(mzxml|mzdata|mzml|csv|cdf|dlt|sig|txt)\s*\$" | tee $TMPFILE | |
# overwrite duplicate files with hard links. | |
cat $TMPFILE | while read dupe; do | |
firstfile="" | |
nextdupe="" | |
for i in $dupe; do | |
if [ -z "$firstfile" ]; then | |
firstfile="$i"; | |
elif [ ! -f "$firstfile" ]; then | |
firstfile="$firstfile $i" | |
elif [ -z "$nextdupe" ]; then | |
nextdupe="$i"; | |
elif [ ! -f "$nextdupe" ]; then | |
nextdupe="$nextdupe $i"; | |
fi; | |
if [ -f "$firstfile" -a -f "$nextdupe" ]; then | |
echo -e "\033[01;32mLinking $nextdupe to $firstfile\033[0m" | |
ln -f "$firstfile" "$nextdupe" | |
nextdupe="" | |
fi; | |
done; | |
done; | |
#rm $TMPFILE | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment