-twill-quill-fix.md

This is an untested draft, I'll come back to this, but it may already be helpful!

Dependencies:

"ezyang/htmlpurifier": "^4.12",

BlockRepository.php

<?php

namespace App\Repositories;

use A17\Twill\Models\Block;
use App\Services\Purifier;

class BlockRepository
{
    private $purifierService;

    public function __construct()
    {
        $this->purifierService = app(Purifier::class);
    }

    private function fixAllHtmlItems($content)
    {
        if (is_string($content)) {
            return $this->fixHtmlString($content);
        }

        if (is_array($content)) {
            foreach ($content as $key => $value) {
                $content[$key] = $this->fixAllHtmlItems($value);
            }
        }

        return $content;
    }

    /**
     * @param \A17\Twill\Models\Block $block
     */
    public function fixBlockHtmls(Block $block): void
    {
        $block['content'] = $this->fixAllHtmlItems($block['content']);

        $block->save();
    }

    public function fixHtml()
    {
        foreach (Block::all() as $block) {
            $this->fixBlockHtmls($block);
        }
    }

    private function fixHtmlString(string $content)
    {
        if (is_html($content)) {
            return $this->purifierService->purify(
                $this->removeNonPrintableChars($content),
            );
        }

        return $content;
    }

    private function removeNonPrintableChars(string $string)
    {
        $string = str_replace(
            ['<br>', '<br />', '<br/>', "\n", "\r", '\n', '\r'],
            '',
            $string,
        );

        return preg_replace('/[\x00-\x1F\x7F]/u', '', $string);
    }
}

PostRepository.php

<?php

namespace App\Repositories;

use App\Models\Post;
use A17\Twill\Repositories\Behaviors\HandleFiles;
use A17\Twill\Repositories\Behaviors\HandleSlugs;
use A17\Twill\Repositories\Behaviors\HandleMedias;
use A17\Twill\Repositories\Behaviors\HandleBlocks;
use A17\Twill\Repositories\Behaviors\HandleRevisions;
use A17\Twill\Repositories\Behaviors\HandleTranslations;

class PostRepository extends Repository
{
    use HandleBlocks,
        HandleTranslations,
        HandleSlugs,
        HandleMedias,
        HandleFiles,
        HandleRevisions;


    public function __construct(Post $model)
    {
        $this->model = $model;
    }

    private function fixHtmls($id)
    {
        if (request()->get('fix_html_on_update')) {
            $this->model
                ->findOrFail($id)
                ->blocks->each(
                    fn($block) => app(BlockRepository::class)->fixBlockHtmls(
                        $block,
                    ),
                );
        }
    }

    /**
     * @param mixed $id
     * @param array $fields
     * @return void
     */
    public function update($id, $fields)
    {
        parent::update($id, $fields);

        $this->fixHtmls($id);
    }
}

Purifier.php

<?php

namespace App\Services;

use HTMLPurifier;
use HTMLPurifier_Config;

class Purifier
{
    private function listWrongTags($html)
    {
        preg_match_all('#(<\s?\\\/.{1,5}>)#', $html, $matches);

        $tags = [];

        foreach ($matches[0] as $tag) {
            $newTag = str_replace('<\/', '</', $tag);

            $newTag = str_replace('< \/', '</', $newTag);

            $tags[$tag] = $newTag;
        }

        return $tags;
    }

    private function removeBrokenHtmlTags($html)
    {
        foreach ($this->listWrongTags($html) as $tag => $newTag) {
            $html = str_replace($tag, $newTag, $html);
        }

        return str_replace(['\n\r', '\r\n'], ['', ''], $html);
    }

    public function purify($html)
    { 
        if (blank($html)) {
            return false;
        }

        if (strip_tags_and_entities($html) == $html) {
            return false;
        }

        $pure = $this->removeBrokenHtmlTags($html);

        $config = HTMLPurifier_Config::createDefault();

        $config->set('HTML.Doctype', 'XHTML 1.0 Transitional');
        $config->set('HTML.SafeIframe', true);
        $config->set('HTML.Trusted', true);
        $config->set(
            'URI.SafeIframeRegexp',
            '%^(http://|https://|//)(www.youtube.com/embed/|player.vimeo.com/video/|vernissage.fondationlouisvuitton.eventmaker.io/|player.freecaster.com/|api.soundcloud.com/tracks/|w.soundcloud.com/player/)%',
        );

        $pure = (new HTMLPurifier($config))->purify($pure);

        return $this->removeHtmlentitiedTags($html, $pure);
    }

    private function removeHtmlentitiedTags($html, string $newHtml)
    {
        foreach ($this->listWrongTags($html) as $tag => $newTag) {
            $newHtml = str_replace(
                [htmlentities($tag), htmlentities($newTag)],
                ['', ''],
                $newHtml,
            );
        }

        return $newHtml;
    }
}