Created
January 10, 2019 17:40
-
-
Save neumond/81415723ab9fe2a7cbcb8ac684b0d432 to your computer and use it in GitHub Desktop.
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 unicodedata | |
from random import randint, choice | |
def getcharset(): | |
hira = [chr(i) for i in range(ord('ぁ'), ord('ゟ') + 1)] | |
rs = [] | |
for ch in hira: | |
try: | |
n = unicodedata.name(ch) | |
except ValueError: | |
continue | |
if 'HIRAGANA LETTER' not in n: | |
continue | |
if 'SMALL' in n: | |
continue | |
rs.append(ch) | |
return ''.join(rs) | |
def transcribe(s): | |
rs = [] | |
for ch in s: | |
rs.append(unicodedata.name(ch).rsplit(' ', 1)[1]) | |
return ''.join(rs) | |
def to_base(n, base): | |
rs = [] | |
while n > 0: | |
rs.append(n % base) | |
n //= base | |
rs.reverse() | |
return rs | |
# n = 123545454 | |
# cs = getcharset() | |
# name = ''.join(cs[v] for v in to_base(n, len(cs))) | |
# print(name) | |
# print(transcribe(name)) | |
def mumble(chars, words=50): | |
wlens = (1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 5, 5, 6) | |
rs = [] | |
for _ in range(words): | |
n = randint(1, len(chars) ** choice(wlens)) | |
word = ''.join(chars[v] for v in to_base(n, len(chars))) | |
rs.append(transcribe(word)) | |
return ' '.join(rs) | |
print(mumble(getcharset())) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment