#!/usr/bin/env sh

# Description: List non-empty duplicate files in the current directory (based on size followed by MD5)
#
# Source: https://www.commandlinefu.com/commands/view/3555/find-duplicate-files-based-on-size-first-then-md5-hash
#
# Dependencies: find md5sum sort uniq xargs
#
# Shell: POSIX compliant
# Authors: syssyphus, KlzXS

find . -size +0 -type f -printf "%s %p\n" | sort -rn | sed -n 'N; /^\([0-9]*\) .*\n\1.*$/p;$d;D' | awk '{printf("%s\0", substr($0, index($0, $2)))}' | xargs -0 md5sum | sort | uniq -w32 --all-repeated=separate

printf "Press any key to exit"
read -r _