Created
February 19, 2016 18:02
-
-
Save Gabriellpweb/cf16c6a46516a88f58dc to your computer and use it in GitHub Desktop.
Copy a list of files to a list of possible files that filename matches with 75% of assert rate.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
from __future__ import print_function | |
import math | |
import difflib | |
import shutil | |
import os.path | |
recovered = 'tofiles.txt' | |
original = 'fromfiles.txt' | |
found = 'found.txt' | |
src_image_path = '/home/usr/src' | |
dest_image_path = '/home/usr/dst' | |
with open(recovered) as rfile: | |
for rline in rfile: | |
try: | |
rlength = int(math.ceil((len(rline) / 2))) | |
rtxt_teste = rline[:rlength] | |
if rtxt_teste <> '': | |
with open(original) as ofile: | |
for line in ofile: | |
try: | |
copy = False | |
if rline in line: | |
#print('(%s) => %s match %s' % (rline, rtxt_teste, line)) | |
copy = True | |
elif difflib.SequenceMatcher(None, rline, line).ratio() > 0.75: | |
#print('(%s) => %s fuzz match %s' % (rline, rtxt_teste, line)) | |
copy = True | |
elif rtxt_teste in line: | |
#print('(%s) => %s match %s' % (rline, rtxt_teste, line)) | |
copy = True | |
if copy: | |
src_image = (src_image_path + rline).replace('\n', '') | |
dst_image = (dest_image_path + line).replace('\n', '') | |
shutil.copy2(src_image, dst_image) | |
print ('[%s] from %s to %s' % (os.path.isfile(src_image), src_image, dst_image)) | |
break | |
except: | |
print('ops2') | |
raise | |
except: | |
print('ops1') | |
raise |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment