PHP 7.3 advanced bad word filter

CensorEngine.php

<?php
/**
 * The Scunthorpe problem
 *
 * PHP version 7.3
 *
 * @category LolPHP
 * @package  LolPHP
 * @author   Elliott Landsborough <elliott.landsborough@gmail.com>
 * @license  MIT https://opensource.org/licenses/MIT
 * @link     https://github.com/ElliottLandsborough
 */
namespace App;

/**
 * CensorEngine Class
 *
 * So I used to work for an agency maintaining a website
 * with a target audience of high average age.
 *
 * Certain pages had comment forms for user discussions etc.
 *
 * Before realising that every comment would have to be moderated
 * before being published, this solution was implemented.
 *
 * More info about the Scunthorpe problem:
 * https://en.wikipedia.org/wiki/Scunthorpe_problem
 *
 * According to the commit logs, the first iteration of this was
 * committed on Mon May 19 14:19:32 2014.
 *
 * It is still in the codebase as of now (2019-08-29)
 *
 * @category LolPHP
 * @package  LolPHP
 * @author   Elliott Landsborough <elliott.landsborough@gmail.com>
 * @license  MIT https://opensource.org/licenses/MIT
 * @link     https://github.com/ElliottLandsborough
 */
class CensorEngine
{
    /**
     * An array of all the bad words we are looking for
     *
     * @var array
     */
    protected $badwords = [];

    /**
     * Constructor
     */
    public function __construct()
    {
        $this->addWords();
    }

    /**
     * RandCensor Function
     *
     * @param string $chars I don't know
     * @param int    $len   I don't know
     *
     * @return string
     */
    protected function randCensor($chars, $len): ?string
    {
        mt_srand(); // useful for < PHP4.2
        $lastChar = strlen($chars) - 1;
        $randOld = -1;
        $out = '';

        // create $len chars
        for ($i = $len; $i > 0; $i--) {
            // generate random char - it must be different from previously generated
            while (($randNew = mt_rand(0, $lastChar)) === $randOld) {
            }
            $randOld = $randNew;
            $out .= $chars[$randNew];
        }

        return $out;
    }

    /**
     * CensorString replaces bad words in a string with a specified character
     *
     * @param string $string     The string to be censored
     * @param string $censorChar The character to censor with
     *
     * @return array
     */
    public function censorString($string, $censorChar = '*'): ?array
    {
        $badwords = $this->badwords;

        $leet_replace = [];

        $leet_replace['a'] = '(a|a\.|a\-|4|@|Á|á|À|Â|à|Â|â|Ä|ä|Ã|ã|Å|å|α|Δ|Λ|λ)';
        $leet_replace['b'] = '(b|b\.|b\-|8|\|3|ß|Β|β)';
        $leet_replace['c'] = '(c|c\.|c\-|Ç|ç|¢|€|<|\(|{|©)';
        $leet_replace['d'] = '(d|d\.|d\-|&part;|\|\)|Þ|þ|Ð|ð)';
        $leet_replace['e'] = '(e|e\.|e\-|3|€|È|è|É|é|Ê|ê|∑)';
        $leet_replace['f'] = '(f|f\.|f\-|ƒ)';
        $leet_replace['g'] = '(g|g\.|g\-|6|9)';
        $leet_replace['h'] = '(h|h\.|h\-|Η)';
        $leet_replace['i'] = '(i|i\.|i\-|!|\||\]\[|]|1|∫|Ì|Í|Î|Ï|ì|í|î|ï)';
        $leet_replace['j'] = '(j|j\.|j\-)';
        $leet_replace['k'] = '(k|k\.|k\-|Κ|κ)';
        $leet_replace['l'] = '(l|1\.|l\-|!|\||\]\[|]|£|∫|Ì|Í|Î|Ï)';
        $leet_replace['m'] = '(m|m\.|m\-)';
        $leet_replace['n'] = '(n|n\.|n\-|η|Ν|Π)';
        $leet_replace['o'] = '(o|o\.|o\-|0|Ο|ο|Φ|¤|°|ø)';
        $leet_replace['p'] = '(p|p\.|p\-|ρ|Ρ|¶|þ)';
        $leet_replace['q'] = '(q|q\.|q\-)';
        $leet_replace['r'] = '(r|r\.|r\-|®)';
        $leet_replace['s'] = '(s|s\.|s\-|5|\$|§)';
        $leet_replace['t'] = '(t|t\.|t\-|Τ|τ)';
        $leet_replace['u'] = '(u|u\.|u\-|υ|µ)';
        $leet_replace['v'] = '(v|v\.|v\-|υ|ν)';
        $leet_replace['w'] = '(w|w\.|w\-|ω|ψ|Ψ)';
        $leet_replace['x'] = '(x|x\.|x\-|Χ|χ)';
        $leet_replace['y'] = '(y|y\.|y\-|¥|γ|ÿ|ý|Ÿ|Ý)';
        $leet_replace['z'] = '(z|z\.|z\-|Ζ)';

        $words = explode(" ", $string);

        // is $censorChar a single char?
        $isOneChar = (strlen($censorChar) === 1);

        for ($x = 0; $x < count($badwords); $x++) {
            $replacement[$x] = $isOneChar
            ? str_repeat($censorChar, strlen($badwords[$x]))
            : $this->randCensor($censorChar, strlen($badwords[$x]));

            $badwords[$x] = '/' . str_ireplace(
                array_keys($leet_replace),
                array_values($leet_replace),
                $badwords[$x]
            ) . '/i';
        }

        $newstring = [];
        $newstring['orig'] = html_entity_decode($string);
        $newstring['clean'] = preg_replace(
            $badwords,
            $replacement,
            $newstring['orig']
        );

        return $newstring;
    }

    /**
     * Adds bad words to class variable
     *
     * @return void
     */
    protected function addWords(): void
    {
        array_push(
            $this->badwords,
            'assfuck',
            'assfucker',
            'asshat',
            'asshole',
            'assholes',
            'asshore',
            'assjockey',
            'asskiss',
            'asskisser',
            'assklown',
            'asslick',
            'asslicker',
            'asslover',
            'assmonkey',
            'assmunch',
            'assmuncher',
            'asspacker',
            'asspirate',
            'asspuppies',
            'assranger',
            'asswhore',
            'asswipe',
            'arsehole',
            'ballsack',
            'bastard ',
            'bitch',
            'blowjob',
            'bollock',
            'bugger',
            'bullshit',
            'clitoris',
            'cockhead',
            'cockknob',
            'cocklicker',
            'cocklover',
            'cocknob',
            'cockqueen',
            'cockrider',
            'cocksman',
            'cocksmith',
            'cocksmoker',
            'cocksucer',
            'cocksuck',
            'cocksucked',
            'cocksucker',
            'cocksucking',
            'crackwhore',
            'crack-whore',
            'cunt',
            'dickbrain',
            'dickforbrains',
            'dickhead',
            'dickless',
            'dicklick',
            'dicklicker',
            'ejaculate',
            'ejaculated',
            'ejaculating ',
            'ejaculation',
            'fagging',
            'faggot',
            'fagot',
            'felcher',
            'felching',
            'fellatio',
            'fetish',
            'fuck',
            'fucck',
            'fudgepacker',
            'genital',
            'gypo',
            'gypp',
            'handjob',
            'hymen',
            'limpdick',
            'mastabate',
            'masterbate',
            'molest',
            'mothafuck',
            'mothafucka',
            'mothafuckaz',
            'mothafucked',
            'mothafucker',
            'mothafuckin',
            'mothafucking',
            'mothafuckings',
            'motherfuck',
            'motherfucked',
            'motherfucker',
            'motherfuckin',
            'motherfucking',
            'motherfuckings',
            'motherlovebone',
            'muffdive',
            'muffdiver',
            'muffindiver',
            'mufflikcer',
            'nigga',
            'orgasm',
            'penis',
            'pornography',
            'pussie',
            'pussyeater',
            'pussyfucker',
            'pussylicker',
            'pussylips',
            'pussylover',
            'pussypounder',
            'raghead',
            'retard',
            'retarded',
            'shagging',
            'shit',
            'skank',
            'slut',
            'slutty',
            'slutwear',
            'slutwhore',
            'testicle',
            'vulva'
        );
    }
}

$censorEngine = new CensorEngine();

print_r($censorEngine->censorString('You are a whoreish asspirate.'));

/**
 * Expected output:
 *
 * Array
 * (
 *     [orig] => You are a whoreish asspirate.
 *     [clean] => You are a whoreish *********.
 *  )
 *
 * The original wordlist from 19/05/2014:
 *
 * 'analplug', 'analsex', 'arse', 'assassin','balls', 'bimbo', 'bloody',
 * 'bloodyhell', 'blowjob', 'bollocks', 'boner', 'boobies', 'boobs',
 * 'bugger', 'bukkake', 'bullshit', 'chink', 'clit', 'clitoris',
 * 'cocksucker', 'condom', 'coon', 'crap', 'cumshot', 'damm', 'dammit',
 * 'damn', 'dickhead', 'doggystyle', 'f0ck', 'fags', 'fanny', 'fck',
 * 'fcker', 'fckr', 'fcku', 'fcuk', 'fucker', 'fuckface', 'fuckr',
 * 'fuct', 'genital', 'genitalia', 'genitals', 'glory hole', 'gloryhole',
 * 'gobshite', 'godammet', 'godammit', 'goddammet', 'goddammit',
 * 'goddamn', 'gypo', 'hitler', 'hooker', 'hore', 'horny', 'jesussucks',
 * 'jizzum', 'kaffir', 'kill', 'killer', 'killin', 'killing', 'lesbo',
 * 'masturbate', 'milf', 'molest', 'moron', 'motherfuck', 'mthrfckr',
 * 'murder', 'murderer', 'nazi', 'negro', 'nigga', 'niggah', 'nonce',
 * 'paedo', 'paedophile', 'paki', 'pecker', 'pedo', 'pedofile',
 * 'pedophile', 'phuk', 'pig', 'pimp', 'poof', 'porn', 'prick', 'pron',
 * 'prostitute', 'raped', 'rapes', 'rapist', 'schlong', 'screw',
 * 'scrotum', 'shag', 'shemale', 'shite', 'shiz', 'slag', 'spastic',
 * 'spaz', 'sperm', 'spunk', 'stripper', 'tart', 'terrorist', 'tits',
 * 'tittyfuck', 'tosser', 'turd', 'vaginal', 'vibrator', 'wanker',
 * 'weed', 'wetback', 'whor', 'whore', 'wog', 'wtf', 'xxx' 'anal',
 * 'anus', 'ass', 'bastard', 'bitch', 'boob', 'cock', 'cum', 'cunt',
 * 'dick', 'dildo', 'dyke', 'fag', 'faggot', 'fuck', 'fuk', 'handjob',
 * 'homo', 'jizz', 'kike', 'kunt', 'muff', 'nigger', 'penis', 'piss',
 * 'poop', 'pussy', 'queer', 'rape', 'semen', 'sex', 'shit', 'slut',
 * 'titties', 'twat', 'vagina', 'vulva', 'wank'
 */