blob: 01d40f9ed636275cb2c3727d79e4a61db67f941d (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
|
#!/usr/bin/env python3
import bitstring
import bidict
special_characters = bidict.bidict(
{
' ': 27,
'.': 28,
',': 29,
"-": 30,
'"': 31,
}
)
def compress(uncompressed: str) -> bytes:
"""
Compress a word sequence into a stream of bytes. The compressed
form will be 5/8th the size of the original. Words can be lower
case letters or special_characters (above).
>>> import binascii
>>> binascii.hexlify(compress('this is a test'))
b'99d12d225a06a6494c'
"""
compressed = bitstring.BitArray()
for (n, letter) in enumerate(uncompressed):
if 'a' <= letter <= 'z':
bits = ord(letter) - ord('a') + 1 # 1..26
else:
if letter not in special_characters:
raise Exception(f'"{uncompressed}" contains uncompressable char="{letter}"')
bits = special_characters[letter]
compressed.append(f"uint:5={bits}")
while len(compressed) % 8 != 0:
compressed.append("uint:1=0")
return compressed.bytes
def decompress(kompressed: bytes) -> str:
"""
Decompress a previously compressed stream of bytes back into
its original form.
>>> import binascii
>>> decompress(binascii.unhexlify(b'99d12d225a06a6494c'))
'this is a test'
"""
decompressed = ''
compressed = bitstring.BitArray(kompressed)
for chunk in compressed.cut(5):
chunk = chunk.uint
if chunk == 0:
break
elif 1 <= chunk <= 26:
letter = chr(chunk - 1 + ord('a'))
else:
letter = special_characters.inverse[chunk][0]
decompressed += letter
return decompressed
if __name__ == '__main__':
import doctest
doctest.testmod()
|
