#!/usr/bin/env python3

# 33, 35-38, 40, 42-43, 49-57, 64-90, 92, 94, 97-122, 124
# 149-156, 158, 161-166, 168-204, 206-255

character_octets = {33, 35, 36, 37, 38, 40, 42, 43, 49, 50, 51, 52, 53, 54, 55,
56, 57, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81,
82, 83, 84, 85, 86, 87, 88, 89, 90, 92, 94, 97, 98, 99, 100, 101, 102, 103, 104,
105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120,
121, 122, 124, 149, 150, 151, 152, 153, 154, 155, 156, 158, 161, 162, 163, 164,
165, 166, 168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181,
182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197,
198, 199, 200, 201, 202, 203, 204, 206, 207, 208, 209, 210, 211, 212, 213, 214,
215, 216, 217, 218, 219, 220, 221, 222, 223, 224, 225, 226, 227, 228, 229, 230,
231, 232, 233, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246,
247, 248, 249, 250, 251, 252, 253, 254, 255}

character_chars = {bytes([o]) for o in character_octets}
def split(word):
    for i in range(len(word)):
        yield word[:i], word[i], word[i + 1:]

def voynich_words():
    with open("voyn_101.txt", "rb") as f:
        octets = f.read()
        word = b""
        ignore = False

        for octet in octets:
            octet = bytes([octet])
            if octet == b",":
                continue

            if octet == b"<":
                ignore = True

            if ignore is False:
                if octet in character_chars:
                    word += octet

                elif word:
                    yield word
                    word = b""

            if octet == b">":
                ignore = False

        if word:
            yield word

import sys

for word in voynich_words():
    sys.stdout.buffer.write(word + b"\n")