Unicode special character converter

readme.md

This Python script converts a plain text into a 𝐑𝐢𝐜𝐡 and 𝓖𝓸𝓻𝓰𝓮𝓸𝓾𝓼 text. Python 3.7+ is required.

Usage: /Users/takumi/dev/rcs/scripts/fontify STYLE [TEXT]
TEXT is ignored if stdin is piped.
Available styles:
 - serif-b
    𝐓𝐇𝐄 𝐐𝐔𝐈𝐂𝐊 𝐁𝐑𝐎𝐖𝐍 𝐅𝐎𝐗 𝐉𝐔𝐌𝐏𝐒 𝐎𝐕𝐄𝐑 𝐓𝐇𝐄 𝐋𝐀𝐙𝐘 𝐃𝐎𝐆. 𝟎𝟏𝟐𝟑𝟒
    𝐭𝐡𝐞 𝐪𝐮𝐢𝐜𝐤 𝐛𝐫𝐨𝐰𝐧 𝐟𝐨𝐱 𝐣𝐮𝐦𝐩𝐬 𝐨𝐯𝐞𝐫 𝐭𝐡𝐞 𝐥𝐚𝐳𝐲 𝐝𝐨𝐠. 𝟎𝟏𝟐𝟑𝟒
 - serif-i
    𝑇𝐻𝐸 𝑄𝑈𝐼𝐶𝐾 𝐵𝑅𝑂𝑊𝑁 𝐹𝑂𝑋 𝐽𝑈𝑀𝑃𝑆 𝑂𝑉𝐸𝑅 𝑇𝐻𝐸 𝐿𝐴𝑍𝑌 𝐷𝑂𝐺. 01234
    𝑡ℎ𝑒 𝑞𝑢𝑖𝑐𝑘 𝑏𝑟𝑜𝑤𝑛 𝑓𝑜𝑥 𝑗𝑢𝑚𝑝𝑠 𝑜𝑣𝑒𝑟 𝑡ℎ𝑒 𝑙𝑎𝑧𝑦 𝑑𝑜𝑔. 01234
 - serif-bi
    𝑻𝑯𝑬 𝑸𝑼𝑰𝑪𝑲 𝑩𝑹𝑶𝑾𝑵 𝑭𝑶𝑿 𝑱𝑼𝑴𝑷𝑺 𝑶𝑽𝑬𝑹 𝑻𝑯𝑬 𝑳𝑨𝒁𝒀 𝑫𝑶𝑮. 01234
    𝒕𝒉𝒆 𝒒𝒖𝒊𝒄𝒌 𝒃𝒓𝒐𝒘𝒏 𝒇𝒐𝒙 𝒋𝒖𝒎𝒑𝒔 𝒐𝒗𝒆𝒓 𝒕𝒉𝒆 𝒍𝒂𝒛𝒚 𝒅𝒐𝒈. 01234
 - sans-serif-n
    𝖳𝖧𝖤 𝖰𝖴𝖨𝖢𝖪 𝖡𝖱𝖮𝖶𝖭 𝖥𝖮𝖷 𝖩𝖴𝖬𝖯𝖲 𝖮𝖵𝖤𝖱 𝖳𝖧𝖤 𝖫𝖠𝖹𝖸 𝖣𝖮𝖦. 𝟢𝟣𝟤𝟥𝟦
    𝗍𝗁𝖾 𝗊𝗎𝗂𝖼𝗄 𝖻𝗋𝗈𝗐𝗇 𝖿𝗈𝗑 𝗃𝗎𝗆𝗉𝗌 𝗈𝗏𝖾𝗋 𝗍𝗁𝖾 𝗅𝖺𝗓𝗒 𝖽𝗈𝗀. 𝟢𝟣𝟤𝟥𝟦
 - sans-serif-b
    𝗧𝗛𝗘 𝗤𝗨𝗜𝗖𝗞 𝗕𝗥𝗢𝗪𝗡 𝗙𝗢𝗫 𝗝𝗨𝗠𝗣𝗦 𝗢𝗩𝗘𝗥 𝗧𝗛𝗘 𝗟𝗔𝗭𝗬 𝗗𝗢𝗚. 𝟬𝟭𝟮𝟯𝟰
    𝘁𝗵𝗲 𝗾𝘂𝗶𝗰𝗸 𝗯𝗿𝗼𝘄𝗻 𝗳𝗼𝘅 𝗷𝘂𝗺𝗽𝘀 𝗼𝘃𝗲𝗿 𝘁𝗵𝗲 𝗹𝗮𝘇𝘆 𝗱𝗼𝗴. 𝟬𝟭𝟮𝟯𝟰
 - sans-serif-i
    𝘛𝘏𝘌 𝘘𝘜𝘐𝘊𝘒 𝘉𝘙𝘖𝘞𝘕 𝘍𝘖𝘟 𝘑𝘜𝘔𝘗𝘚 𝘖𝘝𝘌𝘙 𝘛𝘏𝘌 𝘓𝘈𝘡𝘠 𝘋𝘖𝘎. 01234
    𝘵𝘩𝘦 𝘲𝘶𝘪𝘤𝘬 𝘣𝘳𝘰𝘸𝘯 𝘧𝘰𝘹 𝘫𝘶𝘮𝘱𝘴 𝘰𝘷𝘦𝘳 𝘵𝘩𝘦 𝘭𝘢𝘻𝘺 𝘥𝘰𝘨. 01234
 - sans-serif-bi
    𝙏𝙃𝙀 𝙌𝙐𝙄𝘾𝙆 𝘽𝙍𝙊𝙒𝙉 𝙁𝙊𝙓 𝙅𝙐𝙈𝙋𝙎 𝙊𝙑𝙀𝙍 𝙏𝙃𝙀 𝙇𝘼𝙕𝙔 𝘿𝙊𝙂. 01234
    𝙩𝙝𝙚 𝙦𝙪𝙞𝙘𝙠 𝙗𝙧𝙤𝙬𝙣 𝙛𝙤𝙭 𝙟𝙪𝙢𝙥𝙨 𝙤𝙫𝙚𝙧 𝙩𝙝𝙚 𝙡𝙖𝙯𝙮 𝙙𝙤𝙜. 01234
 - script-n
    𝒯ℋℰ 𝒬𝒰ℐ𝒞𝒦 ℬℛ𝒪𝒲𝒩 ℱ𝒪𝒳 𝒥𝒰ℳ𝒫𝒮 𝒪𝒱ℰℛ 𝒯ℋℰ ℒ𝒜𝒵𝒴 𝒟𝒪𝒢. 01234
    𝓉𝒽ℯ 𝓆𝓊𝒾𝒸𝓀 𝒷𝓇ℴ𝓌𝓃 𝒻ℴ𝓍 𝒿𝓊𝓂𝓅𝓈 ℴ𝓋ℯ𝓇 𝓉𝒽ℯ 𝓁𝒶𝓏𝓎 𝒹ℴℊ. 01234
 - script-b
    𝓣𝓗𝓔 𝓠𝓤𝓘𝓒𝓚 𝓑𝓡𝓞𝓦𝓝 𝓕𝓞𝓧 𝓙𝓤𝓜𝓟𝓢 𝓞𝓥𝓔𝓡 𝓣𝓗𝓔 𝓛𝓐𝓩𝓨 𝓓𝓞𝓖. 01234
    𝓽𝓱𝓮 𝓺𝓾𝓲𝓬𝓴 𝓫𝓻𝓸𝔀𝓷 𝓯𝓸𝔁 𝓳𝓾𝓶𝓹𝓼 𝓸𝓿𝓮𝓻 𝓽𝓱𝓮 𝓵𝓪𝔃𝔂 𝓭𝓸𝓰. 01234
 - fraktur-n
    𝔗ℌ𝔈 𝔔𝔘ℑ ℭ𝔎 𝔅ℜ𝔒𝔚𝔑 𝔉𝔒𝔛 𝔍𝔘𝔐𝔓𝔖 𝔒𝔙𝔈ℜ 𝔗ℌ𝔈 𝔏𝔄ℨ𝔜 𝔇𝔒𝔊. 01234
    𝔱𝔥𝔢 𝔮𝔲𝔦𝔠𝔨 𝔟𝔯𝔬𝔴𝔫 𝔣𝔬𝔵 𝔧𝔲𝔪𝔭𝔰 𝔬𝔳𝔢𝔯 𝔱𝔥𝔢 𝔩𝔞𝔷𝔶 𝔡𝔬𝔤. 01234
 - fraktur-b
    𝕿𝕳𝕰 𝕼𝖀𝕴𝕮𝕶 𝕭𝕽𝕺𝖂𝕹 𝕱𝕺𝖃 𝕵𝖀𝕸𝕻𝕾 𝕺𝖁𝕰𝕽 𝕿𝕳𝕰 𝕷𝕬𝖅𝖄 𝕯𝕺𝕲. 01234
    𝖙𝖍𝖊 𝖖𝖚𝖎𝖈𝖐 𝖇𝖗𝖔𝖜𝖓 𝖋𝖔𝖝 𝖏𝖚𝖒𝖕𝖘 𝖔𝖛𝖊𝖗 𝖙𝖍𝖊 𝖑𝖆𝖟𝖞 𝖉𝖔𝖌. 01234
 - monospace
    𝚃𝙷𝙴 𝚀𝚄𝙸𝙲𝙺 𝙱𝚁𝙾𝚆𝙽 𝙵𝙾𝚇 𝙹𝚄𝙼𝙿𝚂 𝙾𝚅𝙴𝚁 𝚃𝙷𝙴 𝙻𝙰𝚉𝚈 𝙳𝙾𝙶. 𝟶𝟷𝟸𝟹𝟺
    𝚝𝚑𝚎 𝚚𝚞𝚒𝚌𝚔 𝚋𝚛𝚘𝚠𝚗 𝚏𝚘𝚡 𝚓𝚞𝚖𝚙𝚜 𝚘𝚟𝚎𝚛 𝚝𝚑𝚎 𝚕𝚊𝚣𝚢 𝚍𝚘𝚐. 𝟶𝟷𝟸𝟹𝟺
 - double-struck
    𝕋ℍ𝔼 ℚ𝕌𝕀ℂ𝕂 𝔹ℝ𝕆𝕎ℕ 𝔽𝕆𝕏 𝕁𝕌𝕄ℙ𝕊 𝕆𝕍𝔼ℝ 𝕋ℍ𝔼 𝕃𝔸ℤ𝕐 𝔻𝕆𝔾. 𝟘𝟙𝟚𝟛𝟜
    𝕥𝕙𝕖 𝕢𝕦𝕚𝕔𝕜 𝕓𝕣𝕠𝕨𝕟 𝕗𝕠𝕩 𝕛𝕦𝕞𝕡𝕤 𝕠𝕧𝕖𝕣 𝕥𝕙𝕖 𝕝𝕒𝕫𝕪 𝕕𝕠𝕘. 𝟘𝟙𝟚𝟛𝟜

fontify.py

#!/usr/bin/env python3

import fileinput, sys
from dataclasses import dataclass


@dataclass
class Style:
    start: int
    patch: dict
    have_digits: bool
    digits_start: int


styles = {
    'serif-b': Style(
        0x1D400,
        dict(),
        True,
        0x1D7CE,
    ),
    'serif-i': Style(
        0x1D434,
        {'h': 'ℎ'},
        False,
        0,
    ),
    'serif-bi': Style(
        0x1D468,
        dict(),
        False,
        0,
    ),
    'sans-serif-n': Style(
        0x1D5A0,
        dict(),
        True,
        0x1D7E2,
    ),
    'sans-serif-b': Style(
        0x1D5D4,
        dict(),
        True,
        0x1D7EC,
    ),
    'sans-serif-i': Style(
        0x1D608,
        dict(),
        False,
        0,
    ),
    'sans-serif-bi': Style(
        0x1D63C,
        dict(),
        False,
        0,
    ),
    'script-n': Style(
        0x1D49C,
        {
            'B': 'ℬ',
            'E': 'ℰ',
            'F': 'ℱ',
            'H': 'ℋ',
            'I': 'ℐ',
            'L': 'ℒ',
            'M': 'ℳ',
            'R': 'ℛ',
            'e': 'ℯ',
            'g': 'ℊ',
            'o': 'ℴ',
        },
        False,
        0,
    ),
    'script-b': Style(
        0x1D4D0,
        dict(),
        False,
        0,
    ),
    'fraktur-n': Style(
        0x1D504,
        {
            'C': 'ℭ',
            'H': 'ℌ',
            'I': 'ℑ ',
            'R': 'ℜ',
            'Z': 'ℨ',
        },
        False,
        0,
    ),
    'fraktur-b': Style(
        0x1D56C,
        dict(),
        False,
        0,
    ),
    'monospace': Style(
        0x1D670,
        dict(),
        True,
        0x1D7F6,
    ),
    'double-struck': Style(
        0x1D538,
        {
            'C': 'ℂ',
            'H': 'ℍ',
            'N': 'ℕ',
            'P': 'ℙ',
            'Q': 'ℚ',
            'R': 'ℝ',
            'Z': 'ℤ',
        },
        True,
        0x1D7D8,
    ),
}


def convert(style, text):
    out = []
    for c in text:
        if c in style.patch:
            out.append(style.patch[c])
            continue

        if ord(c) in range(ord('A'), ord('Z') + 1):
            start = style.start
            offset = ord('A')
        elif ord(c) in range(ord('a'), ord('z') + 1):
            start = style.start
            offset = ord('a') - 26
        elif ord(c) in range(ord('0'), ord('9') + 1):
            if not style.have_digits:
                out.append(c)
                continue
            start = style.digits_start
            offset = ord('0')
        else:
            out.append(c)
            continue

        c = start + ord(c) - offset
        out.append(eval(f'"\\U{c:08x}"'))

    return ''.join(out)


def main():
    tty = sys.stdin.isatty()
    argv = sys.argv
    sufficient_args = (tty and len(argv) >= 3) or (not tty and len(argv) >= 2)

    if '-h' in argv or '--help' in argv or not sufficient_args:
        usage()

    if argv[1] not in styles:
        print(f'Style "{argv[1]}" was not found', file=sys.stderr)
        sys.exit(1)

    style = styles[argv[1]]

    if tty:
        print(convert(style, argv[-1]), end='')
    else:
        print(convert(style, sys.stdin.read()), end='')


def usage():
    print(f'Usage: {sys.argv[0]} STYLE [TEXT]')
    print(f'TEXT is ignored if stdin is piped.')
    print(f'Available styles:')
    for name, style in styles.items():
        sample1 = convert(
            style, 'THE QUICK BROWN FOX JUMPS OVER THE LAZY DOG. 01234'
        )
        sample2 = convert(
            style, 'the quick brown fox jumps over the lazy dog. 01234'
        )
        print(f' - {name}')
        print(f'    {sample1}')
        print(f'    {sample2}')
    print()

    if '-h' in sys.argv or '--help' in sys.argv:
        sys.exit(0)
    else:
        sys.exit(1)


main()