Simply script to build a powershell regex to check for homoglyphs of a specific string

create_homoglyph_regex.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright © 2018 seamus tuohy, <code@seamustuohy.com>
#
# This program is free software: you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by the Free
# Software Foundation, either version 3 of the License, or (at your option)
# any later version.
#
# This program is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE. See the included LICENSE file for details.

# YOU WILL NEED THIS
# http://regexhero.net/reference/

# This creates a powershell compatible regular expression that you can use to check for homoglyphs of a specific string.

import argparse
import re

import logging
logging.basicConfig(level=logging.ERROR)
log = logging.getLogger(__name__)


def main():
    args = parse_arguments()
    set_logging(args.verbose, args.debug)

    # homoglyphs = get_homoglyphs()
    # regex = create_regex(args.string, homoglyphs)
    if args.puny_only is True:
        homoglyphs = get_puny_homoglyphs()
    else:
        homoglyphs = get_homoglyphs()
    # print(homoglyphs)
    nm_homoglyphs = make_homoglyph_named_matches(homoglyphs)
    #print(nm_homoglyphs)
    #print("")
    regex = create_nm_regex(args.string, nm_homoglyphs)
    #print("")
    print('"{0}"'.format(regex))

def make_homoglyph_named_matches(homoglyphs):
    nm = {}
    for letter,strings in homoglyphs.items():
        current_hg = set(nm.get(letter.lower(), []))
        for i in strings:
            current_hg.add(i)
        nm[letter.lower()] = current_hg
    nm_define = '(?<{0}>[{1}])'
    nm_regex = {}
    for letter,strings in nm.items():
        nm_regex[letter] = nm_define.format(letter, ''.join(strings))
    return nm_regex

def get_regex_rejecting_name_match(string):
    name_regex = " ".join(["[{0}{1}]{2}".format(i[0].upper(), i[0].lower(), i[1:]) for i in string.split()])
    return "(?!{0})".format(name_regex)

def create_nm_regex(string, nm_homoglyphs):
    homo_regex = ""
    # \p{name} :: Matches any single character in the Unicode general category or named block specified by name.
    # https://www.regular-expressions.info/unicode.html
    # (?<name1-name2>pattern) :: Defines a balancing group definition.
    whitespace_define =  '(?<WC>[\p{M}\p{Z}\p{P}\p{C}]*)'
    # \k<name> :: Named backreference. Matches the value of a named expression.
    whitespace_checks = "\k<WC>"
    nm_hg_checks = "\k<{0}>"
    letter_set = set()
    for i in string:
        # Define the character string upon first use
        if not re.match("[a-zA-Z]", i): # Don't replace non-ascii
            match_set = i
        elif i.lower() in letter_set:
            match_set = nm_hg_checks.format(i.lower())
        else:
            match_set = nm_homoglyphs.get(i.lower(), None)
            letter_set.add(i.lower())
        if match_set is None:
            match_set = i
        homo_regex = "{0}{1}{2}".format(homo_regex, whitespace_checks, match_set)
    regex_not_original_name = get_regex_rejecting_name_match(string)
    homo_regex = regex_not_original_name + whitespace_define + homo_regex
    # Remove multi-space checks for beginning and end of string
    homo_regex = homo_regex.replace('\k<WC> \k<WC>', '\k<WC> ')
    return homo_regex

def create_regex(string, homoglyphs):
    homo_regex = ""
    whitespace_define =  '(?<WC>[\p{M}\p{Z}\p{P}\p{C}]*)'
    whitespace_checks = "\k<WC>"
    for i in string:
        all_letter_variations = list(set(homoglyphs.get(i.lower(), []) + homoglyphs.get(i.upper(), [])))
        match_set = "[{0}]".format(''.join(all_letter_variations))
        if match_set != []:
            homo_regex = "{0}{1}{2}".format(homo_regex, whitespace_checks, match_set)
        else:
            homo_regex = "{0}{1}{2}".format(homo_regex, whitespace_checks, i)
    homo_regex = whitespace_define + homo_regex
    return homo_regex


def get_puny_homoglyphs():
    initial_homoglyphs = get_homoglyphs()
    puny_homoglyphs = {}
    for i,x in initial_homoglyphs.items():
        _ph = set([i.encode('idna').decode('idna') for i in x])
        puny_homoglyphs[i] = ''.join(list(_ph))
    return puny_homoglyphs

def get_homoglyphs():
    homoglyph_strings = {
        " ": "\s",
        "A": "𝗔𝖠𝙰𝘈A𝘼𝜜ꭺᗅ𝒜ꓮ𝔸Ꭺ𝓐𝚨ÅÁ𝔄𝝖𝐴À𝞐𐊠ᴀÂ𝐀ÃА𖽀𝑨𝕬𝛢ＡÄΑ",
        "B": "𝛣𝞑ᗷß𝗕ꞴＢ𝖡𝜝𐊡Β𝑩𝔹𝓑𝔅в𝘉ᛒ𝐵𝙱𝝗ꓐВ𝐁ᏼ𝚩ℬBβ𐌁𐊂𝘽ʙ𝕭Ᏼ",
        "C": "Ⲥ𝑪𑣩🝌Ｃℭ𝙲𝒞ꓚ𝓒Ꮯ𐊢ℂ𝐶C𐔜𝗖𝐂Ⅽ𐌂𑣲С𝘾𝘊𺀠𝖢𝕮Ϲ𐐕𐐠",
        "D": "𝓓𝗗ᗞ𝔻𝘿Đᗪ𝐷𝙳𝖣𝒟ĎꓓDⅅⅮ𝕯𝔇ᴅ𝐃𝑫𝘋ＤᎠꭰ",
        "E": "𝙀ÈĚ𝔈Éᴇ𝘌𝔼Е𑢦𝜠Ēℰ⋿𝝚ĔΕË𝛦𝑬𝚬𝗘𝞔ꭼĖE𝕰ＥĘ𑢮𝖤𝙴𐊆𝓔𝐸ꓰÊ𝐄Ꭼⴹ",
        "F": "𝙁𝔽𝑭F𝙵ꓝ𝐹ᖴ𝟊𐊇𝐅𝈓Ꞙ𝕱𝔉𝓕𝖥ℱ𝗙𑢢Ｆ𑣂𐔥𐊥Ϝ𝘍",
        "G": "𝘎Ｇԍ𝗚ɢ𝐺𝔾𝙂𝑮𝕲Ꮐնꮐ𝒢ᏻꓖԌ𝓖G𝔊𝐆𝙶𝖦Ᏻ",
        "H": "𝞖𝐇𝝜𝗛ℍ𝛨𝘏Ⲏ𝖧𝜢𝙷ꓧһнᎻℋꮋ𝚮Hᕼ𝓗𝐻𝑯ʜ𝙃Η𐋏Ｈ𝕳Нℌ",
        "I": "ι𝝸Ⅰiᛁꭵاӏ𝚤Ι𰰠𝐢𝑖І𝕚𝚒lᎥ˛𐐠⍳𝜄I𝗂ιіꙇⅰ𝛊ɪ𝖎ī𝙞ｉͺ𝒾𝓲ɩℹ𝔦𝗶𑣃𝜾𝞲ⅈı𝘪Ｉ𝒊",
        "J": "𝔍𝓙Ꭻ𝕁ᴊＪ𝒥𝙹𝑱Ϳ𝙅յ𝐽Jꭻ𝗝𝕵Јᒍ𝐉ꓙ𝖩Ʝ𝘑",
        "K": "𝙆𝛫𝑲𝐾𝕂𝒦𝞙𝓚𝖪𝘒К𝝟ᛕꓗ𝙺𐔘KK𝚱𝔎𝐊𝗞Ⲕ𝕶ᏦΚ𝜥Ｋ",
        "L": "ι𐑃ＬⳐ𝕃𝙇𑢣L𝐋𝓛𝔏𝕷𝈪l𐐛𝙻𝐿ⳑʟⅬ𝑳𐔦ꓡ𝘓Ꮮᒪℒ𝖫ꮮ𖼖ⅼ𝗟𑢲",
        "M": "𝜧Ꮇℳ𝛭𝝡Μ𝞛𝑀𝗠𝙼𝔐Ϻ𝚳𐊰𝐌𝙈Ⅿ𝘔ᗰМ𝖬𐌑𝓜MꓟᛖⲘ𝑴𝕸Ｍ𝕄",
        "N": "𐔓𝑵𝝢𝙽Ｎ𝚴𝒩𝞜𝙉𝕹ℕ𝐍Ⲛ𝛮𝘕𝔑𝖭𝜨Nɴ𝗡ꓠ𝑁𝓝Ν",
        "O": "οΟｏՕО0𱠠ＯoOо𐐠",
        "P": "𝙋𝑷𝜬Ꮲ𝞠ꮲ𝚸ℙ𝘗𝙿РᑭΡꓑ𝐏𝝦ᴩ𝓟𐊕𝖯𝛲ⲢᴘPＰ𝔓𝑃𝒫𝗣𝕻",
        "Q": "Qℚ𝖰𝙌𝚀𝗤𝘘𝐐ႳႭ𝑄ⵕ𝕼𝑸𝒬𝔔𝓠Ｑ",
        "R": "ꭱ𐒴𝘙Ｒ𝑅ℝꮢᖇℛᚱℜ𝚁𝐑ƦR𝈖ꓣ𝕽𝙍𖼵Ꭱ𝖱𝗥𝑹Ꮢʀ𝓡",
        "S": "Ꮥ𵠠𝚂𝗦𝖲ႽЅ𝐒𝑺𝕊Ｓ𝕾𝑆𖼺𐊖S𝙎𝒮𝓢ꓢsｓ𝘚ᏚՏѕ𝔖𐐠",
        "T": "⟙𝞣𑢼Ꭲ𐊗𝞽Τтᴛ𝐓𝒯𝙏𝖳𝜏Ⲧτ𝕋ꭲ𝑻𝗧𝑇Ｔ𐊱𐌕𖼊T𝛕𝚻𝝉⊤Т𝔗ꓔ𝜯𝝩𝘛𝛵🝨𝞃𝕿𝓣𝚃",
        "U": "𖽂𝔘𝓤𐓎𝚄ՍUＵ𝗨𝑼Ա𝙐⋃u𑢸𝑈μ𝖀υ𝐔ሀ∪𝕌𝖴ꓴᑌ𝒰𝘜",
        "V": "𝙑𝑽ꓦᏙ𝚅ѴⅤ𝐕𝔙𖼈Ｖ𝕍ꛟ𝖁𝗩𝘝𝈍V۷٧𑢠𐔝ⴸ𝖵𝑉𝓥𝒱ᐯ",
        "W": "𝘞𝗪𝖂𝐖𑣦Ԝ𝖶Ｗ𝓦𝕎ｗꓪW𝙒wᏔ𝚆𝑊𝔚𑣯𝒲𝑾Ꮃ",
        "X": "ｘ𝕏𐌗𐊴Ꭓ𝒳𝛸Ｘ𝖃𝜲𝔛ꓫ𑣬𝘟𝓧Ⅹ𝐗𝞦Χ𝚇𐔧𝑋╳𐊐𝚾𝗫ᚷ𝙓XⲬⵝ𝝬𝑿χ𐌢Х𝖷᙭",
        "Y": "Ꭹ𝝪𝒀ʏｙ𝖄Ү𝐘ϒ𝒴γ𖽃𝙔𝚼𝔜𑢤Ꮍ𝚈𝞤ꓬy𝓨у𝘠𝛶ＹY𝑌УⲨ𝗬𐊲𝜰Υ𝖸𝕐",
        "Z": "𝚉𝐙𝒵𝙕ℨℤ𝘡𝞕𝒁𝖹Ꮓ𝛧𝓩𑢩Ζ𝜡𐋵𝖅ꓜＺ𝝛𝗭𝑍𑣥𝚭Z",
        "a": "𝒶ã⍺α𝜶𝛼ǎɑâ𝖆𝖺𝑎а𝐚𝛂𝗮ａáạä𝓪àăåȧa𝒂𝞪𝕒𝔞𝚊𝝰ą𝙖𝘢",
        "b": "𝗯𝖇ЬḇƅᏏᖯḅ𝓫𝕓d𝑏ḃlɓ𝘣𝙗Ƅ𝐛ｂ𝒃𝒷𝖻𝔟b𝚋ʙ",
        "c": "𐐽ᴄⲥ𝖼𝘤𝒸𝙘𝒄𝓬ꮯᏟϲ𝐜с𝕔𝗰Ⅽ𝔠𺀠c𝚌𝑐𝖈ⅽｃ𐐠",
        "d": "𝗱ꓒ𝙙𝕕ԁᏧ𝒹ɗ𝖽𝘥ḏďｄ𝒅dɖl𝚍ᑯⅾ𝓭𝐝ḓ𝑑ժḑḋ𝔡đcḍb𝖉ⅆ",
        "e": "ꬲ𝖊𝕖𝚎℮êė𝔢ⅇȩҽ𝖾ē𝒆ḛĕ𝑒ɇ𝓮ẹℯ𝙚ę𝘦ée𝐞ëèеěcｅ𝗲",
        "f": "𝔣𝙛ꞙ𝒻𝚏ƒｆ𝑓𝗳ẝf𝕗𝒇𝟋𝓯ք𝘧ꬵſ𝖿𝐟𝖋ϝḟ",
        "g": "ɡᶃ𝗴𝔤ɢǧ𝐠g𝘨qģ𝕘ｇնցġℊ𝗀ĝ𝒈ǥ𝚐ƍ𝓰𝙜𝑔𝖌ğǵ",
        "h": "ħȟհᏂⱨ𝚑ẖһ𝔥𝒽lḥḩ𝖍ℎ𝕙𝘩𝗁𝐡ɦ𝒉𝗵ｈhĥḧ𝓱𝙝ḣḫ",
        "i": "ι𝝸Ⅰiᛁɨꭵاӏ𝚤𰰠𝐢𝑖𝕚𝚒1lȋᎥ˛𐐠⍳𝜄𝗂ιіꙇⅰ𝛊ɪ𝖎ỉīĭ𝙞ｉͺ𝒾𝓲íɩℹ𝔦𝗶𑣃𝜾𝞲ịǐïⅈı𝘪Ｉì𝒊",
        "j": "𝔧𝚓jϳ𝗷𝐣𝙟𝒋𝗃յ𝒿𝑗𝖏ɉ𝘫ʝјⅉ𝕛ｊ𝓳",
        "k": "𝐤𝑘𝗄𝗸𝚔ḳḵ𝓴𝓀ｋκⱪ𝕜k𝔨𝖐𝒌ķ𝙠𝘬",
        "m": "ᴍｍmṁⅿḿṃɱrn",
        "n": "𝓃ｎ𝚗ñr𝐧𝒏ռ𝙣mꞑ𝗇𝘯ṅńņ𝓷𝗻ǹɴnṇň𝑛ṉո𝕟𝖓𝔫",
        "p": "ƥ𝗉ṗᏢ𝝆ṕ𝒑𝛒𝕡𝔭ｐ𝚙ρ𝝔⍴𝜌𝞀𝓹ƿϱⲣ𝑝Ｐ𝖕𝞺p𝓅𝐩р𝙥𝞎𝘱𝛠𝗽𝟈𝜚",
        "q": "𝐪𝖖g𝑞գｑʠq𝘲Ⴍ𝚚ԛ𝕢𝓆𝔮𝗾𝒒𝗊Ⴓ𝙦զ𝓺",
        "r": "𝓇𝐫ṛrᴦꭈ𝑟ɼṙṟ𝘳ꭇ𝗿ȑ𝗋Իгɾŕɍȓ𝔯ⲅŗｒ𝒓ř𝙧ʀɽ𝚛ꮁ𝖗𝕣𝓻",
        "s": "𵠠ꜱ𑣁𝘀ႽЅṣƽ𝓼ŝṡ𐑈Ｓʂ𝑠𐐠ś𝙨𝓈S𝖘sｓ𝕤Ꮪ𝐬𝔰𝗌𝚜ѕ𝒔ꮪ𝘴șšՏ",
        "t": "𝐭𝒕𝑡ṫᎢ𝖙ț𝘁𝓽ƫτ𝔱ţ𝙩ｔ𝓉𝗍𝘵𝚝ṭt𝕥ŧ",
        "u": "𝕦𑣘ůūǔùUꭎｕՍＵųűư𝗎ꞟʉսûԱ𝖚𝐮𝞄𝘂𝘶𝛖𐓶𝜐ú⋃uũȗụ𝒖𝓊𝔲üυμ𝝊ʋ𝑢ŭȕ𝞾𝓾𝙪𝚞ᴜꭒ",
        "v": "𝒗⋁𝚟𑣀𝗏ѵѴ𝜈𝞶𝑣𝓋𝐯𝔳𝘃ｖ𝝼vⱱνטⱴ𝖛ᴠ𝘷∨ⅴ𝙫𝕧ṽꮩ𝓿ṿᶌ𑜆𝛎𝝂",
        "w": "𑜊ẅ𝑤𑜎𝘄ẘ𝖜ɯ𝒘𝔀Ｗ𝗐𝘸vｗ𝚠ẇẁ𝐰ẉWwẃ𝔴ԝꮃ𝕨աⱳ𑜏𝙬Ꮃŵᴡ𝓌ѡ",
        "x": "ｘ𝐱⤬𝘅𝙭𝓍𝔁ᕽⅩᕁ𝗑𝖝𝑥᙮х𝚡𝔵×⤫ⅹχ𝒙𝘹x⨯𝕩",
        "y": "𝛄𝕪𝓎ʏɣ𝗒ｙ𝒚Үŷγƴ𝚢ỿ𝛾𑣜ℽ𝞬ɏꭚẏ𝔂𝔶ყ𝝲ỵ𝘆ү𝖞ȳyýÿу𝘺𝙮𝑦ＹYᶌΥ𝐲𝜸",
        "z": "𝖟𝕫𝙯ꮓź𝘻ｚᏃ𝗓𝔃𝘇ʐƶż𝐳ⱬẕ𝓏𝒛ᴢẓ𝑧𝚣𑣄𝔷z"
    }
    homoglyph_set = {}

    for name, glyphs in homoglyph_strings.items():
        homoglyph_set[name] = list(set(glyphs))
    return homoglyph_set


# Command Line Functions below this point

def set_logging(verbose=False, debug=False):
    if debug == True:
        log.setLevel("DEBUG")
    elif verbose == True:
        log.setLevel("INFO")

def parse_arguments():
    parser = argparse.ArgumentParser("Get a summary of some text")
    parser.add_argument("--verbose", "-v",
                        help="Turn verbosity on",
                        action='store_true')
    parser.add_argument("--debug", "-d",
                        help="Turn debugging on",
                        action='store_true')
    parser.add_argument("--string", "-s",
                        help="string to transform into regex",
                        required=True)
    parser.add_argument("--puny_only", "-p",
                        help="use only puny compliant chars",
                        action='store_true')
    args = parser.parse_args()
    return args

if __name__ == '__main__':
    main()