jonnybarnes.uk/app/Console/Commands/ParseCachedWebMentions.php
Jonny Barnes 1dfa17abca
Some checks failed
PHP Unit / PHPUnit test suite (pull_request) Has been cancelled
Laravel Pint / Laravel Pint (pull_request) Has been cancelled
Update Laravel to v12
2025-04-01 21:10:30 +01:00

67 lines
1.9 KiB
PHP
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<?php
declare(strict_types=1);
namespace App\Console\Commands;
use App\Models\WebMention;
use Illuminate\Console\Command;
use Illuminate\Contracts\Filesystem\FileNotFoundException;
use Illuminate\FileSystem\FileSystem;
/**
* @psalm-suppress UnusedClass
*/
class ParseCachedWebMentions extends Command
{
/**
* The name and signature of the console command.
*
* @var string
*/
protected $signature = 'webmentions:parsecached';
/**
* The console command description.
*
* @var string
*/
protected $description = 'Re-parse the webmentions cached HTML';
/**
* Execute the console command.
*
* @throws FileNotFoundException
*/
public function handle(FileSystem $filesystem): void
{
$htmlFiles = $filesystem->allFiles(storage_path() . '/HTML');
foreach ($htmlFiles as $file) {
if ($file->getExtension() !== 'backup') { // we dont want to parse `.backup` files
$filepath = $file->getPathname();
$this->info('Loading HTML from: ' . $filepath);
$html = $filesystem->get($filepath);
$url = $this->urlFromFilename($filepath);
$webmention = WebMention::where('source', $url)->firstOrFail();
$microformats = \Mf2\parse($html, $url);
$webmention->mf2 = json_encode($microformats);
$webmention->save();
$this->info('Saved the microformats to the database.');
}
}
}
/**
* Determine the source URL from a filename.
*/
private function urlFromFilename(string $filepath): string
{
$dir = mb_substr($filepath, mb_strlen(storage_path() . '/HTML/'));
$url = str_replace(['http/', 'https/'], ['http://', 'https://'], $dir);
if (mb_substr($url, -10) === 'index.html') {
$url = mb_substr($url, 0, -10);
}
return $url;
}
}