def retrieve_table(dest_file: io) -> dict:
"""
Read the binary file, and return the translation table as a reversed
dictionary.
"""
offset, *_ = unpack("i", dest_file.read(_sizeof("i")))
chars = dest_file.read(offset * _sizeof("c"))
codes = dest_file.read(offset * _sizeof("L"))
chars = unpack("{}c".format(offset), chars)
codes = unpack("{}L".format(offset), codes)
return {
"b{0}".format(tobinary(code)): str(char, encoding=ENC)
for char, code in zip(chars, codes)
}
def _decode_block(
binary_content: bytes, table: dict, block_length: int
) -> str:
"""Transform the compressed content of a block into the original text."""
newchars = []
cont = binascii.hexlify(binary_content)
bitarray = tobinary(cont)
# Ignore first bit, sentinel
bitarray = bitarray[1:]
window_start, window_end = 0, 1
part = bitarray[window_start:window_end]
restored = 0 # bytes
while part:
char = table.get(bitarray[window_start:window_end], False)
while not char and bitarray[window_start:window_end]:
window_end += 1
char = table.get(bitarray[window_start:window_end], False)
newchars.append(char)
restored += 1
if restored == block_length:
break
window_start, window_end = window_end, window_end + 1
part = bitarray[window_start:window_end]
return "".join(newchars)[:block_length]
def test_tobinary_string():
assert tobinary('ff') == '11111111'
assert tobinary('F') == tobinary(15)
def test_tobinary_bytes():
assert tobinary(b'ff') == tobinary(255)
assert tobinary(b'A') == '1010'
def test_tobinary_int():
assert tobinary(0xff) == '11111111'
assert tobinary(42) == '101010'