poljakowski/sweeper
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

added rethash parameter to iter_file_dups

Browse source
This commit is contained in:
Darko Poljak 2014-01-28 07:29:23 +01:00
parent 609418975e
commit a60ede31fb
1 changed files with 9 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
sweeper/sweeper.py
View file

@ -103,11 +103,16 @@ def mv_file_dups(topdirs=['./'], hashalg='md5', block_size=4096,
shutil.move(f, dest_dir) shutil.move(f, dest_dir)
def iter_file_dups(topdirs=['./'], hashalg='md5', block_size=4096): def iter_file_dups(topdirs=['./'], rethash=False, hashalg='md5', block_size=4096):
"""Yield list of duplicate files when found in specified directory list. """Yield duplicate files when found in specified directory list.
If rethash is True then tuple hash value and duplicate paths list is
returned, otherwise duplicate paths list is returned.
""" """
dups = file_dups(topdirs, hashalg, block_size) dups = file_dups(topdirs, hashalg, block_size)
for fpaths in dups.itervalues(): for hash, fpaths in _dict_iter_items:
if rethash:
yield (hash, fpaths)
else:
yield fpaths yield fpaths