from rabin import Rabin, get_file_fingerprints, set_min_block_size, set_max_block_size, set_average_block_size
TARGET = 'test.bin'
os.system("dd if=/dev/urandom of=%s bs=1024 count=100" % TARGET)
random.seed(open(TARGET, 'rb').read(1024))
set_min_block_size(1024)
set_max_block_size(2048)
set_average_block_size(1024)
reached = []
def block_reached(start, length, fingerprint):
# print('(%s, %s, %s)' % (start, length, fingerprint))
reached.append((start, length, fingerprint))
r = Rabin()
r.register(block_reached)
with open(TARGET, 'rb') as f:
while True:
size = random.randint(1,os.path.getsize(TARGET))
data = f.read(size)
if len(data) == 0:
break
r.update(data)
partial = r.fingerprints()
gold = get_file_fingerprints(TARGET)
assert len(gold) == len(partial) == len(reached)
from rabin import Rabin, get_file_fingerprints, set_min_block_size, set_max_block_size, set_average_block_size
TARGET = 'test.bin'
filesizeM = 10
Mb = 1024 * 1024
os.system("dd if=/dev/urandom of=%s bs=%d count=%d" % (TARGET, Mb, filesizeM))
random.seed(open(TARGET, 'rb').read(1024))
set_min_block_size(1024)
set_max_block_size(2048)
set_average_block_size(1024)
r = Rabin()
before = get_file_fingerprints(TARGET)
f = open(TARGET, 'rb+')
data = f.read(int(filesizeM / 2 * Mb))
r.update(data)
r.update(b'x')
data = f.read()
r.update(data)
after = r.fingerprints()
assert len(before) <= len(after)
diffcount = 0
for i in range(len(before)):
try:
#!/usr/bin/env python
import os
import random
from rabin import Rabin, get_file_fingerprints, set_min_block_size, set_max_block_size, set_average_block_size
TARGET = 'test.bin'
os.system("dd if=/dev/urandom of=%s bs=1024k count=10" % TARGET)
random.seed(open(TARGET, 'r').read(1024))
set_min_block_size(1024)
set_max_block_size(2048)
set_average_block_size(1024)
r = Rabin()
before = get_file_fingerprints(TARGET)
fh = open(TARGET, 'r+')
fh.seek(1024*1024*5)
fh.write('x')
fh.close()
after = get_file_fingerprints(TARGET)
assert len(before) == len(after)
diffcount = 0
for i in range(len(before)):
try:
bs,bl,bp = before[i]
As,al,ap = after[i]
from rabin import Rabin, set_min_block_size, set_max_block_size, set_average_block_size, set_prime
#This method generate the fingerprint of document
reached = []
def block_reached(start, length, fingerprint):
# print '(%s, %s, %s)' % (start, length, fingerprint)
reached.append(( fingerprint))
r = Rabin()
r.register(block_reached)
def rabinFinger(emailBody):
for i in range(0,emailBody.__len__()):
chunk = str((emailBody[i])[0])
set_min_block_size(chunk.__len__())
set_max_block_size(chunk.__len__())
set_average_block_size(chunk.__len__())
r.update(emailBody[i][0])
return reached
# input is the list of email body, and the output is the list of fingerprint
def rabinFingerprint(emailBody):
fingerPrint = []
for i in range(0, len(emailBody)):
# print rabinFingerprint(test[i])
from rabin import Rabin, get_file_fingerprints, set_min_block_size, set_max_block_size, set_average_block_size
TARGET = 'test.bin'
filesizeM = 10
Mb = 1024*1024
os.system("dd if=/dev/urandom of=%s bs=%d count=%d" % (
TARGET, Mb, filesizeM))
random.seed(open(TARGET, 'r').read(1024))
set_min_block_size(1024)
set_max_block_size(2048)
set_average_block_size(1024)
r = Rabin()
before = get_file_fingerprints(TARGET)
f = open(TARGET, 'r+')
data = f.read(filesizeM/2 * Mb)
r.update(data)
r.update('x')
data = f.read()
r.update(data)
after = r.fingerprints()
assert len(before) <= len(after)
diffcount = 0
for i in range(len(before)):
try:
os.system("dd if=/dev/urandom of=%s bs=1024 count=100" % TARGET)
random.seed(open(TARGET, 'rb').read(1024))
set_min_block_size(1024)
set_max_block_size(2048)
set_average_block_size(1024)
reached = []
def block_reached(start, length, fingerprint):
# print('(%s, %s, %s)' % (start, length, fingerprint))
reached.append((start, length, fingerprint))
r = Rabin()
r.register(block_reached)
with open(TARGET, 'rb') as f:
while True:
size = random.randint(1, os.path.getsize(TARGET))
data = f.read(size)
if len(data) == 0:
break
r.update(data)
partial = r.fingerprints()
gold = get_file_fingerprints(TARGET)
assert len(gold) == len(partial) == len(reached)
from rabin import Rabin
from common import get_args, sys
## sample file
import os
SAMPLE_FILE = os.path.join((os.path.abspath(os.path.dirname(__file__))), '..',
'sample.txt')
if __name__ == '__main__':
text, to_find = get_args(sys.argv[1:])
r = Rabin(to_find, text)
r.search(use_rabin_fingerprint=True)
if r.result:
print("Pattern '{}' found at positions {}".format(to_find, r.result))
else:
print("No match found for pattern '{}'".format(to_find))