[dups.git] / dups.sh

#! /bin/sh

find $@ -type f -print0 \
| xargs -0 -P $(nproc) md5sum \
| awk '
    {
        digest = $1
        sub("^" $1 " +", "")
        path = $0
        paths[digest, ++count[digest]] = path
    }

    END {
        for (digest in count) {
            n = count[digest]
            if (n > 1) {
                print(digest, n)
                for (i=1; i<=n; i++) {
                    printf "    %s\n", paths[digest, i]
                }
            }
        }
    }'
Commit	Line	Data
f41b9cdf SK	1	#! /bin/sh
	2
	3	find $@ -type f -print0 \
	4	\| xargs -0 -P $(nproc) md5sum \
	5	\| awk '
	6	{
	7	digest = $1
	8	sub("^" $1 " +", "")
	9	path = $0
	10	paths[digest, ++count[digest]] = path
	11	}
	12
	13	END {
	14	for (digest in count) {
	15	n = count[digest]
	16	if (n > 1) {
	17	print(digest, n)
	18	for (i=1; i<=n; i++) {
	19	printf " %s\n", paths[digest, i]
	20	}
	21	}
	22	}
	23	}'