Quick & dirty PHP script to find hard-coded Dutch words in a PHP / PHTML codebase (such as Magento)

checkDutchWords.php

<?php

if (!file_exists('dutch.txt')) {
    shell_exec('wget -O dutch.txt https://github.com/OpenTaal/opentaal-wordlist/blob/master/wordlist.txt?raw=true');
}
$dict = explode("\n", file_get_contents('dutch.txt'));

$blacklisted = ['echo', 'var', 'reviews', 'rating', 'all', 'item', 'int', 'details', 'helper', 'label', 'configurator', 'display', 'var', 'id', 'show', 'a', 'br', 'preview', 'as', 'index', 'content', 'import', 'h', 'am', 'the', 'filter', 'type', 'Google', 'source', 'file', 'x', 'y', 'field', 'html'];

$dict = array_diff($dict, $blacklisted);

function rsearch($folder, $pattern) {
    $iti = new RecursiveDirectoryIterator($folder);
    $results = [];
    foreach(new RecursiveIteratorIterator($iti) as $file){
        if(strpos($file , $pattern) !== false){
            $results[] = $file;
        }
    }
    return $results;
}

$phtmls = rsearch('app', '.phtml');
$phps = rsearch('app', '.php');

$files = array_merge($phtmls, $phps);

foreach ($files as $phtml) {
    $tokens = token_get_all(file_get_contents($phtml));
    $tokens = array_filter($tokens);
    foreach ($tokens as $token) {
        if (isset($token[1])) {
            $words = strip_tags($token[1]);
            $words = explode(" ", $words);
            $words = array_map(function ($word) {
                return preg_replace("/[^a-zA-Z]/", "", $word);
            }, array_filter($words));
            $words = array_filter($words);
            $dutchWords = array_intersect($words, $dict);
            if (count($dutchWords) > 0) {
                echo $phtml . PHP_EOL;
                print_r($dutchWords);
                echo PHP_EOL;
            }
        }
    }
}