嘗試還原遺失ASCII高位元的Big5字串。

big5recover.py

import codecs, itertools

decode = codecs.getdecoder('big5')
f = open('input.txt', 'r')
l = 8		# 8-byte decode block
L = 2 ** l	# Use bit-flag to do permutations
d = f.read()

for pointer in range(0, len(d), l):
  s = d[pointer:pointer+l]
	occured = []
	for iter in range(L + 1):
		str = ''
		for i in range(l):
			if ((2 ** i) & iter) == 0:
				str += s[i]
			else:
				str += chr(ord(s[i]) | 0x80)
		S = decode(str, 'ignore')[0]
		if S in occured: continue
		print S
		occured.append(S)