Last active
September 30, 2022 18:05
-
-
Save Demindiro/f5358e65d2305c03f2486d445363bc5d to your computer and use it in GitHub Desktop.
Python script implementing decoder for LZ4 block format. License: 0BSD
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
import lz4.block | |
f = open('lz4_Block_format.md', 'rb').read() | |
e = lz4.block.compress(f, compression=12, store_size=False) | |
d = [0] * len(f) | |
i = k = 0 | |
while i < len(e): | |
def get_len(l): | |
# Get a variable length | |
global i | |
if l == 15: | |
while True: | |
n = e[i] | |
i += 1 | |
l += n | |
if n != 255: | |
break | |
return l | |
# Get token | |
t = e[i] | |
i += 1 | |
# Copy literals | |
l = get_len(t >> 4) | |
d[k:k + l] = e[i:i + l] | |
i += l | |
k += l | |
# "The block ends right after the literals (no offset field)" | |
if i == len(e): | |
break | |
# Get offset (16 bit little-endian) | |
offt = (e[i + 1] << 8) | e[i] | |
i += 2 | |
assert offt != 0 # zero offset is invalid | |
# Copy match | |
l = get_len(t & 0xf) + 4 | |
# We have to copy byte by byte because it may overlap and we're copying | |
# from low to high | |
m = k - offt | |
for _ in range(l): | |
d[k] = d[m] | |
k += 1 | |
m += 1 | |
print(bytes(d).decode('utf-8')) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment