Python script to get data from unicode character (from lib unicodedata)

unicodedata

#!/usr/bin/env python3

import re
import sys
import argparse
import unicodedata

if len(sys.argv) == 1:
    sys.argv.append('-h')

# Usage:
#   unicodedata <CHAR>
#   unicodedata U+<HEX>

argparser = argparse.ArgumentParser(description='Print unicode data for a character')
argparser.add_argument('char', metavar='CHAR', type=str, nargs='?',
                          help='character or codepoint (U+XXXX)')

options = argparser.parse_args()

if re.match('^[Uu]\+[0-9A-Fa-f]+$', options.char):
    options.char = chr(int(options.char[2:], 16))

char = options.char

def format_codepoint(code):
    if code < 0x10000:
        return 'U+{:04X}'.format(code)
    else:
        return 'U+{:06X}'.format(code)

print(f'Character:       {char}')
print(f'Codepoint:       {format_codepoint(ord(char))}')
try:
    print(f'Name:            {unicodedata.name(char)}')
except ValueError:
    print('Name:            <not found>')
print(f'Category:        {unicodedata.category(char)}')
if unicodedata.bidirectional(char).strip():
    print(f'Bidirectional:   {unicodedata.bidirectional(char)}')
print(f'Combining class: {unicodedata.combining(char)}')
if unicodedata.decomposition(char).strip():
    print(f'Decomposition:   {unicodedata.decomposition(char)}')
try:
    print(f'Decimal digit:   {unicodedata.decimal(char)}')
except:
    pass
try:
    print(f'Digit:           {unicodedata.digit(char)}')
except:
    pass
print(f'UTF-8:           {" ".join([f"{c:02X}" for c in char.encode("utf-8")])}')
print(f'UTF-16 LE:       {" ".join([f"{c:02X}" for c in char.encode("utf-16-le")])}')
print(f'UTF-16 BE:       {" ".join([f"{c:02X}" for c in char.encode("utf-16-be")])}')