Include ON DELETE CASCADE associations in the delete order computation

lib/Doctrine/ORM/Internal/StronglyConnectedComponents.php

@@ -0,0 +1,166 @@
+<?php
+
+declare(strict_types=1);
+
+namespace Doctrine\ORM\Internal;
+
+use InvalidArgumentException;
+
+use function array_keys;
+use function array_pop;
+use function array_push;
+use function min;
+use function spl_object_id;
+
+/**
+ * StronglyConnectedComponents implements Tarjan's algorithm to find strongly connected
+ * components (SCC) in a directed graph. This algorithm has a linear running time based on
+ * nodes (V) and edges between the nodes (E), resulting in a computational complexity
+ * of O(V + E).
+ *
+ * See https://en.wikipedia.org/wiki/Tarjan%27s_strongly_connected_components_algorithm
+ * for an explanation and the meaning of the DFS and lowlink numbers.
+ *
+ * @internal
+ */
+final class StronglyConnectedComponents
+{
+    private const NOT_VISITED = 1;
+    private const IN_PROGRESS = 2;
+    private const VISITED     = 3;
+
+    /**
+     * Array of all nodes, indexed by object ids.
+     *
+     * @var array<int, object>
+     */
+    private $nodes = [];
+
+    /**
+     * DFS state for the different nodes, indexed by node object id and using one of
+     * this class' constants as value.
+     *
+     * @var array<int, self::*>
+     */
+    private $states = [];
+
+    /**
+     * Edges between the nodes. The first-level key is the object id of the outgoing
+     * node; the second array maps the destination node by object id as key.
+     *
+     * @var array<int, array<int, bool>>
+     */
+    private $edges = [];
+
+    /**
+     * DFS numbers, by object ID
+     *
+     * @var array<int, int>
+     */
+    private $dfs = [];
+
+    /**
+     * lowlink numbers, by object ID
+     *
+     * @var array<int, int>
+     */
+    private $lowlink = [];
+
+    /** @var int */
+    private $maxdfs = 0;
+
+    /**
+     * Nodes representing the SCC another node is in, indexed by lookup-node object ID
+     *
+     * @var array<int, object>
+     */
+    private $representingNodes = [];
+
+    /** @var array<int> */
+    private $stack = [];
+
+    /** @param object $node */
+    public function addNode($node): void
+    {
+        $id                = spl_object_id($node);
+        $this->nodes[$id]  = $node;
+        $this->states[$id] = self::NOT_VISITED;
+        $this->edges[$id]  = [];
+    }
+
+    /** @param object $node */
+    public function hasNode($node): bool
+    {
+        return isset($this->nodes[spl_object_id($node)]);
+    }
+
+    /**
+     * Adds a new edge between two nodes to the graph
+     *
+     * @param object $from
+     * @param object $to
+     */
+    public function addEdge($from, $to): void
+    {
+        $fromId = spl_object_id($from);
+        $toId   = spl_object_id($to);
+
+        $this->edges[$fromId][$toId] = true;
+    }
+
+    public function findStronglyConnectedComponents(): void
+    {
+        foreach (array_keys($this->nodes) as $oid) {
+            if ($this->states[$oid] === self::NOT_VISITED) {
+                $this->tarjan($oid);
+            }
+        }
+    }
+
+    private function tarjan(int $oid): void
+    {
+        $this->dfs[$oid]    = $this->lowlink[$oid] = $this->maxdfs++;
+        $this->states[$oid] = self::IN_PROGRESS;
+        array_push($this->stack, $oid);
+
+        foreach ($this->edges[$oid] as $adjacentId => $ignored) {
+            if ($this->states[$adjacentId] === self::NOT_VISITED) {
+                $this->tarjan($adjacentId);
+                $this->lowlink[$oid] = min($this->lowlink[$oid], $this->lowlink[$adjacentId]);
+            } elseif ($this->states[$adjacentId] === self::IN_PROGRESS) {
+                $this->lowlink[$oid] = min($this->lowlink[$oid], $this->dfs[$adjacentId]);
+            }
+        }
+
+        $lowlink = $this->lowlink[$oid];
+        if ($lowlink === $this->dfs[$oid]) {
+            $representingNode = null;
+            do {
+                $unwindOid = array_pop($this->stack);
+
+                if (! $representingNode) {
+                    $representingNode = $this->nodes[$unwindOid];
+                }
+
+                $this->representingNodes[$unwindOid] = $representingNode;
+                $this->states[$unwindOid]            = self::VISITED;
+            } while ($unwindOid !== $oid);
+        }
+    }
+
+    /**
+     * @param object $node
+     *
+     * @return object
+     */
+    public function getNodeRepresentingStronglyConnectedComponent($node)
+    {
+        $oid = spl_object_id($node);
+
+        if (! isset($this->representingNodes[$oid])) {
+            throw new InvalidArgumentException('unknown node');
+        }
+
+        return $this->representingNodes[$oid];
+    }
+}

lib/Doctrine/ORM/UnitOfWork.php

@@ -28,6 +28,7 @@
 use Doctrine\ORM\Exception\UnexpectedAssociationValue;
 use Doctrine\ORM\Id\AssignedGenerator;
 use Doctrine\ORM\Internal\HydrationCompleteHandler;
+use Doctrine\ORM\Internal\StronglyConnectedComponents;
 use Doctrine\ORM\Internal\TopologicalSort;
 use Doctrine\ORM\Mapping\ClassMetadata;
 use Doctrine\ORM\Mapping\MappingException;
@@ -1391,14 +1392,19 @@ private function computeInsertExecutionOrder(): array
     /** @return list<object> */
     private function computeDeleteExecutionOrder(): array
     {
-        $sort = new TopologicalSort();
+        $stronglyConnectedComponents = new StronglyConnectedComponents();
+        $sort                        = new TopologicalSort();
 
-        // First make sure we have all the nodes
         foreach ($this->entityDeletions as $entity) {
+            $stronglyConnectedComponents->addNode($entity);
             $sort->addNode($entity);
         }
 
-        // Now add edges
+        // First, consider only "on delete cascade" associations between entities
+        // and find strongly connected groups. Once we delete any one of the entities
+        // in such a group, _all_ of the other entities will be removed as well. So,
+        // we need to treat those groups like a single entity when performing delete
+        // order topological sorting.
         foreach ($this->entityDeletions as $entity) {
             $class = $this->em->getClassMetadata(get_class($entity));
 
@@ -1410,16 +1416,65 @@ private function computeDeleteExecutionOrder(): array
                     continue;
                 }
 
-                // For associations that implement a database-level cascade/set null operation,
+                assert(isset($assoc['joinColumns']));
+                $joinColumns = reset($assoc['joinColumns']);
+                if (! isset($joinColumns['onDelete'])) {
+                    continue;
+                }
+
+                $onDeleteOption = strtolower($joinColumns['onDelete']);
+                if ($onDeleteOption !== 'cascade') {
+                    continue;
+                }
+
+                $targetEntity = $class->getFieldValue($entity, $assoc['fieldName']);
+
+                // If the association does not refer to another entity or that entity
+                // is not to be deleted, there is no ordering problem and we can
+                // skip this particular association.
+                if ($targetEntity === null || ! $stronglyConnectedComponents->hasNode($targetEntity)) {
+                    continue;
+                }
+
+                $stronglyConnectedComponents->addEdge($entity, $targetEntity);
+            }
+        }
+
+        $stronglyConnectedComponents->findStronglyConnectedComponents();
+
+        // Now do the actual topological sorting to find the delete order.
+        foreach ($this->entityDeletions as $entity) {
+            $class = $this->em->getClassMetadata(get_class($entity));
+
+            // Get the entities representing the SCC
+            $entityComponent = $stronglyConnectedComponents->getNodeRepresentingStronglyConnectedComponent($entity);
+
+            // When $entity is part of a non-trivial strongly connected component group
+            // (a group containing not only those entities alone), make sure we process it _after_ the
+            // entity representing the group.
+            // The dependency direction implies that "$entity depends on $entityComponent
+            // being deleted first". The topological sort will output the depended-upon nodes first.
+            if ($entityComponent !== $entity) {
+                $sort->addEdge($entity, $entityComponent, false);
+            }
+
+            foreach ($class->associationMappings as $assoc) {
+                // We only need to consider the owning sides of to-one associations,
+                // since many-to-many associations can always be (and have already been)
+                // deleted in a preceding step.
+                if (! ($assoc['isOwningSide'] && $assoc['type'] & ClassMetadata::TO_ONE)) {
+                    continue;
+                }
+
+                // For associations that implement a database-level set null operation,
                 // we do not have to follow a particular order: If the referred-to entity is
-                // deleted first, the DBMS will either delete the current $entity right away
-                // (CASCADE) or temporarily set the foreign key to NULL (SET NULL).
-                // Either way, we can skip it in the computation.
+                // deleted first, the DBMS will temporarily set the foreign key to NULL (SET NULL).
+                // So, we can skip it in the computation.
                 assert(isset($assoc['joinColumns']));
                 $joinColumns = reset($assoc['joinColumns']);
                 if (isset($joinColumns['onDelete'])) {
                     $onDeleteOption = strtolower($joinColumns['onDelete']);
-                    if ($onDeleteOption === 'cascade' || $onDeleteOption === 'set null') {
+                    if ($onDeleteOption === 'set null') {
                         continue;
                     }
                 }
@@ -1433,10 +1488,17 @@ private function computeDeleteExecutionOrder(): array
                     continue;
                 }
 
-                // Add dependency. The dependency direction implies that "$targetEntity depends on $entity
+                // Get the entities representing the SCC
+                $targetEntityComponent = $stronglyConnectedComponents->getNodeRepresentingStronglyConnectedComponent($targetEntity);
+
+                // When we have a dependency between two different groups of strongly connected nodes,
+                // add it to the computation.
+                // The dependency direction implies that "$targetEntityComponent depends on $entityComponent
                 // being deleted first". The topological sort will output the depended-upon nodes first,
                 // so we can work through the result in the returned order.
-                $sort->addEdge($targetEntity, $entity, false);
+                if ($targetEntityComponent !== $entityComponent) {
+                    $sort->addEdge($targetEntityComponent, $entityComponent, false);
+                }
             }
         }