rdupes

recursively search for duplicate files
git clone https://a3nm.net/git/rdupes/
Log | Files | Refs

commit c610ec8516c279a2b9271fa2e330745250429762
parent 10025a7fc483089af9bb9c38484b57009e8786e1
Author: Antoine Amarilli <a3nm@a3nm.net>
Date:   Sat,  7 Jan 2012 12:37:47 +0100

just output the data

Diffstat:
rdupes.py | 15+--------------
1 file changed, 1 insertion(+), 14 deletions(-)

diff --git a/rdupes.py b/rdupes.py @@ -4,17 +4,8 @@ import os import sys import hashlib -hashes = {} -sizes = {} - def register(f, h, s): - print >> sys.stderr, f - if h in hashes.keys(): - hashes[h].append(f) - assert(sizes[h] == s) - else: - hashes[h] = [f] - sizes[h] = s + print "%s\t%s\t%s" % (h, s, f) def hashfile(f): sha1 = hashlib.sha1() @@ -54,7 +45,3 @@ def explore(d): for d in sys.argv[1:]: explore(d) -hashes2 = [(sizes[x], hashes[x]) for x in hashes.keys() if len(hashes[x]) > 1] -hashes2.sort(reverse=True) -print '\n'.join([str(s) + ": " + ' '.join(f) for (s, f) in hashes2]) -