I am trying to chunk a file and create SHA1 finger prints for those chunks. Following is the code. My file is just having one line "tests" when I generate finger print from python command prompt I get different answer.
>>> m = hashlib.sha1()
>>> m.update("tests")
>>> m.digest()
'\x04\xd1?\xd0\xaao\x01\x97\xcf,\x99\x90\x19\xa6\x07\xc3l\x81\xeb\x9f'
>>>
>>> m.hexdigest()
'04d13fd0aa6f0197cf2c999019a607c36c81eb9f'
-------------------------------------------------------------
import sys, os,hashlib
kilobytes = 1024
megabytes = kilobytes * 1000
chunksize = int(1.4 * megabytes) # default: roughly a floppy
hash = hashlib.sha1()
def split(fromfile, todir, chunksize=chunksize):
if not os.path.exists(todir): # caller handles errors
os.mkdir(todir) # make dir, read/write parts
else:
print " path exists"
##for fname in os.listdir(todir): # delete any existing files
## os.remove(os.path.join(todir, fname))
partnum = 0
input = open(fromfile, 'rb') # use binary mode on Windows
while 1: # eof=empty string from read
chunk = input.read(chunksize) # get next part <= chunksize
print "chunk=",chunk,"\n"
if not chunk: break
partnum = partnum+1
filename = os.path.join(todir, ('hashpart%04d' % partnum))
fileobj = open(filename, 'wb')
print "chunk before hashin is =",chunk, "of type ",type(chunk)
hash.update(chunk)
print "finger print is ",hash.hexdigest()
fileobj.write(hash.digest())
fileobj.close()
input.close( )
assert partnum <= 9999 # join sort fails if 5 digits
return partnum
-----------------------------------------------------------
but with the code written above it gives me
chunk before hashin is = tests
of type <type 'str'>
finger print is 64853233b4bd86fc53565e1383f2b19b6ede2995
Can someone help me?
