Python - some handy functions for generating Unicode data

unicode_data.py

#!/usr/bin/env python
#
# Functions for generating Unicode data


import random
import unicodedata


def get_all_chars():
    """Returns a tuple of all Unicode characters."""
    return tuple(chr(i) for i in range(0x0000, 1 + 0xFFFF, 1))


def get_printable_chars(chars):
    """Returns a tuple of all printable characters from a sequence
    of characters.

    A character is "printable" if it can be represented as a string
    without hex-escaping.
    """
    return tuple(char for char in chars if char.isprintable())


def get_whitespace_chars(chars):
    """Returns a tuple of all whitespace characters from a sequence
    of characters.

    A character is "whitespace" if in the Unicode character database,
    either its general category is Zs ('Separator, space'), or its
    bidirectional class is one of WS, B, or S.
    """
    return tuple(char for char in chars if char.isspace())


def get_string_chars(chars):
    """Returns a tuple of string representations from a sequence
    of characters.
    """
    return tuple(repr(char) for char in chars)


def print_name_table(chars, width=30):
    """Prints a table of Unicode names and string representations
    from a sequence of characters.
    """
    print(f"{'Name':{width}}Character")
    print("-" * 39)
    for char in chars:
        name = unicodedata.name(char, "Undefined").title()
        print(f"{name:{width}}{repr(char)}")


def generate_random_string(chars, length):
    """Generates a random string of given length from a sequence
    of characters.
    """
    return "".join(random.choices(chars, k=length))