chatLZMA

chatLZMA.py

import lzma
import nltk
import random

nltk.download('reuters')
nltk.download('brown')
nltk.download('gutenberg')

my_filters = [
    {"id": lzma.FILTER_LZMA2, "preset": 9 | lzma.PRESET_EXTREME},
]
lzc = lzma.LZMACompressor(lzma.FORMAT_RAW, filters=my_filters)

corp = nltk.corpus.reuters.raw().encode()
out1 = lzc.compress(corp)

corp = ' '.join(nltk.corpus.brown.words()).encode()
out2 = lzc.compress(corp)

corp = nltk.corpus.gutenberg.raw().encode()
out3 = lzc.compress(corp)

out_end = lzc.flush()

lzd = lzma.LZMADecompressor(lzma.FORMAT_RAW, filters=my_filters)

lzd.decompress(out1)
lzd.decompress(out2)
lzd.decompress(out3)
lzd.decompress(out_end[:-50])

i = 0
while True:
  try:
    print(i, '\t', lzd.decompress(random.randbytes(10)).decode(errors="ignore"))
    i += 1
  except Exception as e:
    print(e)
    break