Created
September 2, 2019 18:54
-
-
Save cutaway/3dd7ca7f6a214dd43ea0e37b6462ad91 to your computer and use it in GitHub Desktop.
Conduct frequency analysis on all characters in a binary blob.
This file contains hidden or 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 python3 | |
import os, sys | |
# Debug if you want to stop early in large files | |
DEBUG = False | |
COLUMNS = 4 | |
def main(): | |
# Preload a dictionary with all characters | |
table = {} | |
table = {e:0 for e in range(256)} | |
# Grab data from file | |
data = open(sys.argv[1], 'rb').read() | |
# Loop thru data and count | |
if DEBUG: b = 0 | |
for c in data: | |
table[c] += 1 | |
# Debug large files | |
if DEBUG: | |
b += 1 | |
if b == 2000: break | |
# print results | |
for e in range(0,256,COLUMNS): | |
print() | |
for r in range(COLUMNS): | |
# This formating will help the column output | |
print('{:<3s} {:>4s} {:>4d}'.format(hex(e+r),repr(chr(e+r)),table[e+r]), end = '') | |
# Don't put the colon on the last column | |
if r < (COLUMNS - 1): print(' : ',end = '') | |
print() | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment