Format scatterhash.py
This commit is contained in:
@@ -17,30 +17,27 @@ def even_select(N, M):
|
|||||||
q, r = divmod(N, M)
|
q, r = divmod(N, M)
|
||||||
indices = [q*i + min(i, r) for i in range(M)]
|
indices = [q*i + min(i, r) for i in range(M)]
|
||||||
cut[indices] = False
|
cut[indices] = False
|
||||||
|
|
||||||
return cut
|
return cut
|
||||||
|
|
||||||
def get_offsets(blocksize, blockcount,blocks_to_hash):
|
def get_offsets(blocksize, blockcount,blocks_to_hash):
|
||||||
selection=even_select(blockcount,blocks_to_hash)
|
selection = even_select(blockcount,blocks_to_hash)
|
||||||
for i in range(0,blockcount):
|
for i in range(0,blockcount):
|
||||||
if selection[i]==0:
|
if selection[i] == 0:
|
||||||
offset=int(blocksize*i)
|
offset = int(blocksize*i)
|
||||||
yield offset
|
yield offset
|
||||||
|
|
||||||
|
|
||||||
def get_hash(file,hashalgo,spread):
|
def get_hash(file,hashalgo,spread):
|
||||||
h=hashlib.new(hashalgo)
|
h=hashlib.new(hashalgo)
|
||||||
filesize=os.path.getsize(file.name)
|
filesize = os.path.getsize(file.name)
|
||||||
blocksize=h.block_size*65535
|
blocksize = h.block_size*65535
|
||||||
blockcount=math.ceil(filesize/blocksize)
|
blockcount = math.ceil(filesize/blocksize)
|
||||||
blocks_to_hash=math.ceil(blockcount*spread/100)
|
blocks_to_hash = math.ceil(blockcount*spread/100)
|
||||||
if filesize>blocksize:
|
if filesize>blocksize:
|
||||||
for of in get_offsets(blocksize,blockcount,blocks_to_hash):
|
for of in get_offsets(blocksize,blockcount,blocks_to_hash):
|
||||||
infile.seek(of)
|
infile.seek(of)
|
||||||
h.update(file.read(blocksize))
|
h.update(file.read(blocksize))
|
||||||
else:
|
else:
|
||||||
h.update(file.read(blocksize))
|
h.update(file.read(blocksize))
|
||||||
|
|
||||||
result="{};{};{};{};{}".format(h.hexdigest(),spread,filesize,hashalgo,file.name)
|
result="{};{};{};{};{}".format(h.hexdigest(),spread,filesize,hashalgo,file.name)
|
||||||
return result
|
return result
|
||||||
|
|
||||||
@@ -48,10 +45,10 @@ parser = argparse.ArgumentParser(description='Sparsly hash large files. Only a g
|
|||||||
parser.add_argument('-p',metavar='N', action="store",dest="spread",type=int, nargs='?',default=10,help='percentage of file to hash. 0 < N < 100 (default=10)')
|
parser.add_argument('-p',metavar='N', action="store",dest="spread",type=int, nargs='?',default=10,help='percentage of file to hash. 0 < N < 100 (default=10)')
|
||||||
parser.add_argument('-c', action="store",dest="hashalgo",nargs='?',default="md5",help='select an hashalgorithm (default=md5)')
|
parser.add_argument('-c', action="store",dest="hashalgo",nargs='?',default="md5",help='select an hashalgorithm (default=md5)')
|
||||||
parser.add_argument('file', type=argparse.FileType('rb'), nargs='+')
|
parser.add_argument('file', type=argparse.FileType('rb'), nargs='+')
|
||||||
args=parser.parse_args()
|
args = parser.parse_args()
|
||||||
|
|
||||||
hashalgo=args.hashalgo
|
hashalgo = args.hashalgo
|
||||||
spread=args.spread
|
spread = args.spread
|
||||||
for infile in args.file:
|
for infile in args.file:
|
||||||
hashvalue=get_hash(infile,hashalgo,spread)
|
hashvalue = get_hash(infile,hashalgo,spread)
|
||||||
print(hashvalue)
|
print(hashvalue)
|
||||||
|
|||||||
Reference in New Issue
Block a user