I need to search Magento 2 DB for duplicate SKUs and remove duplicate products using a script, i found a very useful script here: [Remove duplicated products from catalog][1].
but it's not compatible with Magento 2 as Mag 2 is not using Mage class or Mage.php
can someone please convert following code to a Magento 2 version:
<?php
include 'app/Mage.php';
Mage::app();
Mage::register('isSecureArea', 1);
$limit = 100;
$model = Mage::getModel('catalog/product');
$resource = $model->getResource();
$adapter = $resource->getReadConnection();
$name = $resource->getAttribute('sku');
// retrieve a list of all products that have more than 1 occurrence of the same name
$select = $adapter->select()->from($name->getBackendTable(),array($resource->getIdFieldName(),'value','count' => 'COUNT(*)','entity_ids' => new Zend_Db_Expr("GROUP_CONCAT({$resource->getIdFieldName()})")));
$select->where('attribute_id = ?',$name->getAttributeId());
$select->where('entity_type_id = ?',$name->getEntityTypeId());
$select->group('value');
$select->having('count > 1');
$select->limit($limit);
$result = $adapter->fetchAll($select);
// here, we remove the lowest product id from each set of duplicate-named products.
// the theory is that the product which was created first, hence the lowest
// product id, is the one you want to keep
$result = array_map(function($row){
$entityIds = explode(',',$row['entity_ids']);
$min = min($entityIds);
$key = array_search($min, $entityIds);
unset($entityIds[$key]);
$row['entity_ids'] = $entityIds;
return $row;
},$result);
// now that we have narrowed down to the ids of the products we want to delete,
// lets get all product ids to delete into a single array
$entityIds = array();
foreach($result as $row){
$entityIds = array_merge($entityIds,$row['entity_ids']);
}
// lets delete each one individually
$collection = $model->getCollection();
$collection->addFieldToFilter($resource->getIdFieldName(),array('in' => $entityIds));
foreach($collection as $product){
$product->delete();
}
?>