m105
1c9fc5d423
Adds Site/SitePage models and the crawlindex:fetch command, which pulls CDX index records from Common Crawl and optionally enriches them with page title/description/keywords/body text extracted from the WARC archive. CDX/WARC access and the site/page upsert logic live in CommonCrawlIndexService and WarcRecordFetcher.
36 lines
873 B
PHP
36 lines
873 B
PHP
<?php
|
|
|
|
use Illuminate\Database\Migrations\Migration;
|
|
use Illuminate\Database\Schema\Blueprint;
|
|
use Illuminate\Support\Facades\Schema;
|
|
|
|
return new class extends Migration
|
|
{
|
|
/**
|
|
* Run the migrations.
|
|
*/
|
|
public function up(): void
|
|
{
|
|
Schema::create('cache', function (Blueprint $table) {
|
|
$table->string('key')->primary();
|
|
$table->mediumText('value');
|
|
$table->bigInteger('expiration')->index();
|
|
});
|
|
|
|
Schema::create('cache_locks', function (Blueprint $table) {
|
|
$table->string('key')->primary();
|
|
$table->string('owner');
|
|
$table->bigInteger('expiration')->index();
|
|
});
|
|
}
|
|
|
|
/**
|
|
* Reverse the migrations.
|
|
*/
|
|
public function down(): void
|
|
{
|
|
Schema::dropIfExists('cache');
|
|
Schema::dropIfExists('cache_locks');
|
|
}
|
|
};
|