Generation of Slovenian BIP0039 wordlist

bip0039.py

from random import randint
import sys

COMMON = 'common.txt'

MIN_LENGTH = 4
MAX_LENGTH = 8

NUM = 2048

def condition(word):
    # Check length
    # Check if ASCII
    # Check if letter
    # Check if lowercase

    return \
        MIN_LENGTH <= len(word) <= MAX_LENGTH and \
        all(ord(char) < 128 and char.isalpha() and char.islower() for char in word)

def main():
    # Read all files
    words = []
    for input in sys.argv[1:]:
        with open(input) as file:
            words += file.read().splitlines()

    # Check conditions
    words = [word for word in words if condition(word)]

    # Remove duplicates
    words = list(dict.fromkeys(words))

    # Sort alphabetically
    words.sort()

    # Remove some not common words
    with open(COMMON) as file:
        common = file.read().splitlines()

    orig = words[:]
    words = []

    for value in orig:
        if randint(1, 10) <= 5 or value in common:
            words.append(value)

    # Remove similar words
    orig = words[:]
    words = []

    for key, value in enumerate(orig):
        if key > 0:
            if not orig[key - 1][:MIN_LENGTH] == value[:MIN_LENGTH]:
                words.append(value)

    # Remove words
    while len(words) > NUM:
        del words[randint(0, len(words))]

    # Re run if too little words
    if len(words) < NUM:
        main()
        return

    # Write to file
    with open('bip0039.txt', 'w') as file:
        for word in words:
            file.write('%s\n' % word)

main()