Sanitize WYSIWYG input

sanitize-wysiwyg-input.php

<?php
    /**
     * Removes empty paragraphs, ordered and unordered lists
     * Reconciles spacing
     * Replaces curly quotes with straight equivalent
     *
     * @param  $html
     * @return string
     */
    public static function sanitizeWysiwygInput($html)
    {
        // Replace `&nbsp;` with a space character throughout (it prevents run-on sentences breaking out of layout)
        $html = str_replace('&nbsp;', ' ', $html);

        // Remove leading and trailing spaces from within an HTML string
        $html = preg_replace('/(?<=>)\s+|\s+(?=<\/)/', '', $html);
        
        // Replace multiple spaces with a single space
        $html = preg_replace('!\s+!', ' ', $html);        

        // Convert curly quotes to straight equivalent
        $replacements = [
            "\xE2\x80\x98" => "'",   // ‘
            "\xE2\x80\x99" => "'",   // ’
            "\xE2\x80\x9A" => "'",   // ‚
            "\xE2\x80\x9B" => "'",   // ‛
            "\xE2\x80\x9C" => '"',   // “
            "\xE2\x80\x9D" => '"',   // ”
            "\xE2\x80\x9E" => '"',   // „
            "\xE2\x80\x9F" => '"',   // ‟
            "\xE2\x80\x93" => '-',
            "\xE2\x80\x94" => '--',
            "\xE2\x80\xa6" => '...',
        ];
        $html = strtr($html, $replacements);

        // Fastest way of removing unwanted tags
        $html = strip_tags($html, '<p><ol><ul><li>');

        // Ignore malformed HTML
        libxml_use_internal_errors(true) && libxml_clear_errors();
        $dom = new DOMDocument();
        $dom->loadHTML($html);
        $html  = ''; // Clear var for returning output
        $xpath = new DOMXPath($dom);

        // Remove empty tags
        foreach ($xpath->query('//*[not(node())]') as $node) {
            $node->parentNode->removeChild($node);
        }

        // Remove all attributes
        foreach ($xpath->query('//*') as $node) {
            for ($i = $node->attributes->length -1; $i >= 0; $i--) {
                $attribute = $node->attributes->item($i);
                $node->removeAttributeNode($attribute);
            }
        }

        // We are only interested in saving the `body` content
        $body     = $xpath->query('//body');
        $children = $body->item(0)->childNodes;
        foreach ($children as $child) {
            $html .= $child->ownerDocument->saveHtml($child);
        }

        return $html;
    }