artifacts/dict_mined_xz_AutoZip/decompressor/decompress.py

#!/usr/bin/env python3
import json, subprocess, sys
from pathlib import Path
inp = Path(sys.argv[1]) if len(sys.argv) > 1 else Path('archive.xz')
out = Path(sys.argv[2]) if len(sys.argv) > 2 else Path('enwik8.out')
pp = inp.parent / 'tmp.preprocessed.bin'
subprocess.run(['xz','-d','-c',str(inp)], check=True, stdout=pp.open('wb'))
subs = json.loads((Path(__file__).with_name('subs.json')).read_text())
data = pp.read_bytes()
for code, pat_hex in subs:
    data = data.replace(bytes([code]), bytes.fromhex(pat_hex))
out.write_bytes(data)
pp.unlink(missing_ok=True)