Generates a random length string of non-control Unicode characters

unicode_fuzz.py

#!/usr/bin/python
import random
import unicodedata


def unicode_fuzz(lower_limit=0, upper_limit=60):
    unicode_glyphs = ''.join(
        unichr(char)
        for char in xrange(65533)
        # use the unicode categories that don't include control codes
        if unicodedata.category(unichr(char))[0] in ('LMNPSZ')
        )

    rand_length = random.randint(lower_limit, upper_limit)

    # generate it
    utf_string = ''.join([random.choice(unicode_glyphs).encode('utf-8')
        for i in xrange(rand_length)])

    return utf_string

# call it with some upper and lower string lengths, or use the defaults
# print unicode_fuzz(0, 250)

what is xrange?

This doesn't work! I tried fixing it but it didn't output anything. Here is my fixed version:

from random import randint, choice
from unicodedata import category

import pyparsing
from cffi.backend_ctypes import xrange


def gen_unicode(lower_limit, upper_limit):
    unicode_glyphs = ''.join(
        pyparsing.unichr(char) for char in xrange(65533) if category(pyparsing.unichr(char))[0] in 'LMNPSZ')

    rand_length = randint(lower_limit, upper_limit)
    utf_string = ''.join([choice(unicode_glyphs).encode('utf-8') for _ in xrange(rand_length)])

    return utf_string


print(gen_unicode(0, 30))

This doesn't work! I tried fixing it but it didn't output anything. Here is my fixed version:

from random import randint, choice
from unicodedata import category

import pyparsing
from cffi.backend_ctypes import xrange


def gen_unicode(lower_limit, upper_limit):
    unicode_glyphs = ''.join(
        pyparsing.unichr(char) for char in xrange(65533) if category(pyparsing.unichr(char))[0] in 'LMNPSZ')

    rand_length = randint(lower_limit, upper_limit)
    utf_string = ''.join([choice(unicode_glyphs).encode('utf-8') for _ in xrange(rand_length)])

    return utf_string


print(gen_unicode(0, 30))

Error: TypeError: sequence item 0: expected str instance, bytes found

Congratulations, guys. I don't even remember that I wrote it. Welcome to orphaned code. Hope you are well.

…

On Thu, Apr 7, 2022 at 11:05 PM VB PROGER ***@***.***> wrote: ***@***.**** commented on this gist. ------------------------------ This doesn't work! I tried fixing it but it didn't output anything. Here is my fixed version: from random import randint, choicefrom unicodedata import category import pyparsingfrom cffi.backend_ctypes import xrange def gen_unicode(lower_limit, upper_limit): unicode_glyphs = ''.join( pyparsing.unichr(char) for char in xrange(65533) if category(pyparsing.unichr(char))[0] in 'LMNPSZ') rand_length = randint(lower_limit, upper_limit) utf_string = ''.join([choice(unicode_glyphs).encode('utf-8') for _ in xrange(rand_length)]) return utf_string print(gen_unicode(0, 30)) Error: TypeError: sequence item 0: expected str instance, bytes found — Reply to this email directly, view it on GitHub <https://gist.github.com/3173004#gistcomment-4125292>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAF27B2Y7PEJLIKRR5QJEMDVD5EXBANCNFSM43D4PRGQ> . You are receiving this because you authored the thread.Message ID: ***@***.***>