Generate random UTF-8 string in Python

People may find their way here based mainly on the question title, so here's a way to generate a random string containing a variety of Unicode characters. To include more (or fewer) possible characters, just extend that part of the example with the code point ranges that you want.

import random

def get_random_unicode(length):

    try:
        get_char = unichr
    except NameError:
        get_char = chr

    # Update this to include code point ranges to be sampled
    include_ranges = [
        ( 0x0021, 0x0021 ),
        ( 0x0023, 0x0026 ),
        ( 0x0028, 0x007E ),
        ( 0x00A1, 0x00AC ),
        ( 0x00AE, 0x00FF ),
        ( 0x0100, 0x017F ),
        ( 0x0180, 0x024F ),
        ( 0x2C60, 0x2C7F ),
        ( 0x16A0, 0x16F0 ),
        ( 0x0370, 0x0377 ),
        ( 0x037A, 0x037E ),
        ( 0x0384, 0x038A ),
        ( 0x038C, 0x038C ),
    ]

    alphabet = [
        get_char(code_point) for current_range in include_ranges
            for code_point in range(current_range[0], current_range[1] + 1)
    ]
    return ''.join(random.choice(alphabet) for i in range(length))

if __name__ == '__main__':
    print('A random string: ' + get_random_unicode(10))

Here is an example function that probably creates a random well-formed UTF-8 sequence, as defined in Table 3–7 of Unicode 5.0.0:

#!/usr/bin/env python3.1

# From Table 3–7 of the Unicode Standard 5.0.0

import random

def byte_range(first, last):
    return list(range(first, last+1))

first_values = byte_range(0x00, 0x7F) + byte_range(0xC2, 0xF4)
trailing_values = byte_range(0x80, 0xBF)

def random_utf8_seq():
    first = random.choice(first_values)
    if first <= 0x7F:
        return bytes([first])
    elif first <= 0xDF:
        return bytes([first, random.choice(trailing_values)])
    elif first == 0xE0:
        return bytes([first, random.choice(byte_range(0xA0, 0xBF)), random.choice(trailing_values)])
    elif first == 0xED:
        return bytes([first, random.choice(byte_range(0x80, 0x9F)), random.choice(trailing_values)])
    elif first <= 0xEF:
        return bytes([first, random.choice(trailing_values), random.choice(trailing_values)])
    elif first == 0xF0:
        return bytes([first, random.choice(byte_range(0x90, 0xBF)), random.choice(trailing_values), random.choice(trailing_values)])
    elif first <= 0xF3:
        return bytes([first, random.choice(trailing_values), random.choice(trailing_values), random.choice(trailing_values)])
    elif first == 0xF4:
        return bytes([first, random.choice(byte_range(0x80, 0x8F)), random.choice(trailing_values), random.choice(trailing_values)])

print("".join(str(random_utf8_seq(), "utf8") for i in range(10)))

Because of the vastness of the Unicode standard I cannot test this thoroughly. Also note that the characters are not equally distributed (but each byte in the sequence is).


There is a UTF-8 stress test from Markus Kuhn you could use.

See also Really Good, Bad UTF-8 example test data.