Updated to PHP 8 features using Rector <3

src/BaseUriCollection.php

@@ -19,7 +19,7 @@ final class BaseUriCollection implements \IteratorAggregate, \Countable
     /**
      * @var array<UriInterface>
      */
-    private $baseUris = [];
+    private array $baseUris = [];
 
     /**
      * @param array<UriInterface> $baseUris

src/CrawlUri.php

@@ -14,43 +14,23 @@
 
 use Psr\Http\Message\UriInterface;
 
-final class CrawlUri
+final class CrawlUri implements \Stringable
 {
-    /**
-     * @var UriInterface
-     */
-    private $uri;
-
-    /**
-     * @var int
-     */
-    private $level;
-
-    /**
-     * @var bool
-     */
-    private $processed = false;
-
-    /**
-     * @var bool
-     */
-    private $wasMarkedProcessed = false;
-
-    /**
-     * @var UriInterface|null
-     */
-    private $foundOn;
-
-    /**
-     * @var array
-     */
-    private $tags = [];
-
-    public function __construct(UriInterface $uri, int $level, bool $processed = false, UriInterface|null $foundOn = null)
-    {
+    private readonly UriInterface $uri;
+
+    private bool $wasMarkedProcessed = false;
+
+    private UriInterface|null $foundOn = null;
+
+    private array $tags = [];
+
+    public function __construct(
+        UriInterface $uri,
+        private readonly int $level,
+        private bool $processed = false,
+        UriInterface|null $foundOn = null,
+    ) {
         $this->uri = self::normalizeUri($uri);
-        $this->level = $level;
-        $this->processed = $processed;
 
         if (null !== $foundOn) {
             $this->foundOn = self::normalizeUri($foundOn);

src/Escargot.php

@@ -37,118 +37,72 @@ final class Escargot
 {
     private const DEFAULT_USER_AGENT = 'terminal42/escargot';
 
-    /**
-     * @var QueueInterface
-     */
-    private $queue;
-
-    /**
-     * @var ClockInterface
-     */
-    private $clock;
+    private ClockInterface $clock;
 
-    /**
-     * @var string
-     */
-    private $jobId;
+    private HttpClientInterface|null $client = null;
 
-    /**
-     * @var BaseUriCollection
-     */
-    private $baseUris;
-
-    /**
-     * @var HttpClientInterface|null
-     */
-    private $client;
-
-    /**
-     * @var LoggerInterface|null
-     */
-    private $logger;
+    private LoggerInterface|null $logger = null;
 
     /**
      * @var array<SubscriberInterface>
      */
-    private $subscribers = [];
+    private array $subscribers = [];
 
-    /**
-     * @var string
-     */
-    private $userAgent;
+    private string $userAgent;
 
     /**
      * Maximum number of requests
      * Escargot is going to
      * execute.
      * 0 means no limit.
-     *
-     * @var int
      */
-    private $maxRequests = 0;
+    private int $maxRequests = 0;
 
     /**
      * Maximum number of duration in seconds
      * Escargot is going to work on requests.
      *
      * 0 means no limit.
-     *
-     * @var int
      */
-    private $maxDurationInSeconds = 0;
+    private int $maxDurationInSeconds = 0;
 
     /**
      * Request delay in microseconds.
      * 0 means no delay.
-     *
-     * @var int
      */
-    private $requestDelay = 0;
+    private int $requestDelay = 0;
 
     /**
      * Maximum concurrent requests
      * that are being sent.
-     *
-     * @var int
      */
-    private $concurrency = 10;
+    private int $concurrency = 10;
 
     /**
      * Maximum depth Escargot
      * is going to crawl.
      * 0 means no limit.
-     *
-     * @var int
      */
-    private $maxDepth = 0;
+    private int $maxDepth = 0;
 
-    /**
-     * @var int
-     */
-    private $requestsSent = 0;
+    private int $requestsSent = 0;
 
-    /**
-     * @var array
-     */
-    private $runningRequests = [];
+    private array $runningRequests = [];
 
     /**
      * Keeps track of all the decisions
      * for all the subscribers for
      * every CrawlUri instance.
-     *
-     * @var array
      */
-    private $decisionMap = ['shouldRequest' => [], 'needsContent' => []];
+    private array $decisionMap = ['shouldRequest' => [], 'needsContent' => []];
 
     private \DateTimeImmutable $startTime;
 
-    private function __construct(QueueInterface $queue, string $jobId, BaseUriCollection $baseUris)
-    {
-        $this->queue = $queue;
-        $this->jobId = $jobId;
-        $this->baseUris = $baseUris;
-
+    private function __construct(
+        private readonly QueueInterface $queue,
+        private readonly string $jobId,
+        private readonly BaseUriCollection $baseUris,
+    ) {
         $this->clock = new NativeClock();
         $this->userAgent = self::DEFAULT_USER_AGENT;
     }
@@ -567,6 +521,7 @@ private function processResponseChunk(ResponseInterface $response, ChunkInterfac
      */
     private function prepareResponses(): array
     {
+        $response = null;
         $responses = [];
 
         $hasMaxRequestsReached = $this->isMaxRequestsReached();
@@ -622,7 +577,7 @@ private function prepareResponses(): array
 
             // Request delay
             if (0 !== $this->requestDelay) {
-                $this->clock->sleep($this->requestDelay / 1000000);
+                $this->clock->sleep($this->requestDelay / 1_000_000);
             }
 
             try {
@@ -698,16 +653,11 @@ private function handleException(ExceptionInterface $exception, CrawlUri $crawlU
                     continue;
                 }
 
-                switch (true) {
-                    case $exception instanceof TransportExceptionInterface:
-                        $subscriber->onTransportException($crawlUri, $exception, $response);
-                        break;
-                    case $exception instanceof HttpExceptionInterface:
-                        $subscriber->onHttpException($crawlUri, $exception, $response, $chunk);
-                        break;
-                    default:
-                        throw new \RuntimeException('Unknown exception type!');
-                }
+                match (true) {
+                    $exception instanceof TransportExceptionInterface => $subscriber->onTransportException($crawlUri, $exception, $response),
+                    $exception instanceof HttpExceptionInterface => $subscriber->onHttpException($crawlUri, $exception, $response, $chunk),
+                    default => throw new \RuntimeException('Unknown exception type!'),
+                };
             }
         }
 

src/Queue/DoctrineQueue.php

@@ -23,9 +23,9 @@
 final class DoctrineQueue implements QueueInterface
 {
     public function __construct(
-        private Connection $connection,
-        private \Closure $jobIdGenerator,
-        private string $tableName = 'escargot',
+        private readonly Connection $connection,
+        private readonly \Closure $jobIdGenerator,
+        private readonly string $tableName = 'escargot',
     ) {
     }
 

src/Queue/InMemoryQueue.php

@@ -21,12 +21,12 @@ final class InMemoryQueue implements QueueInterface
     /**
      * @var array<string, array<UriInterface>>
      */
-    private $baseUris = [];
+    private array $baseUris = [];
 
     /**
      * @var array<string, array<string, CrawlUri>>
      */
-    private $queue = [];
+    private array $queue = [];
 
     public function createJobId(BaseUriCollection $baseUris): string
     {

src/Queue/LazyQueue.php

@@ -18,30 +18,17 @@
 
 final class LazyQueue implements QueueInterface
 {
-    /**
-     * @var QueueInterface
-     */
-    private $primaryQueue;
-
-    /**
-     * @var QueueInterface
-     */
-    private $secondaryQueue;
-
     /**
      * @var array<string, string>
      */
-    private $jobIdMapper = [];
+    private array $jobIdMapper = [];
 
-    /**
-     * @var int
-     */
-    private $toSkip = 0;
+    private int $toSkip = 0;
 
-    public function __construct(QueueInterface $primaryQueue, QueueInterface $secondaryQueue)
-    {
-        $this->primaryQueue = $primaryQueue;
-        $this->secondaryQueue = $secondaryQueue;
+    public function __construct(
+        private readonly QueueInterface $primaryQueue,
+        private readonly QueueInterface $secondaryQueue,
+    ) {
     }
 
     public function createJobId(BaseUriCollection $baseUris): string

src/Subscriber/HtmlCrawlerSubscriber.php

@@ -84,7 +84,7 @@ private function addNewUriToQueueFromNode(CrawlUri $crawlUri, string $uri, \DOME
 
         try {
             $uri = HttpUriFactory::create($uri);
-        } catch (\InvalidArgumentException $e) {
+        } catch (\InvalidArgumentException) {
             $this->logWithCrawlUri(
                 $crawlUri,
                 LogLevel::DEBUG,
@@ -119,8 +119,8 @@ private function addNewUriToQueueFromNode(CrawlUri $crawlUri, string $uri, \DOME
         // Add all data attributes as tags for e.g. other subscribers
         if ($node->hasAttributes()) {
             foreach ($node->attributes as $attribute) {
-                if (str_starts_with($attribute->name, 'data-')) {
-                    $newCrawlUri->addTag(substr($attribute->name, 5));
+                if (str_starts_with((string) $attribute->name, 'data-')) {
+                    $newCrawlUri->addTag(substr((string) $attribute->name, 5));
                 }
             }
         }

src/Subscriber/RobotsSubscriber.php

@@ -47,7 +47,7 @@ final class RobotsSubscriber implements SubscriberInterface, EscargotAwareInterf
     /**
      * @var array<string, File>
      */
-    private $robotsTxtCache = [];
+    private array $robotsTxtCache = [];
 
     public function shouldRequest(CrawlUri $crawlUri): string
     {
@@ -176,15 +176,15 @@ private function getRobotsTxtFile(CrawlUri $crawlUri): File|null
 
             try {
                 $robotsTxtContent = $response->getContent();
-            } catch (HttpExceptionInterface $e) {
+            } catch (HttpExceptionInterface) {
                 return $this->robotsTxtCache[(string) $robotsTxtUri] = null;
             }
 
             $parser = new Parser();
             $parser->setSource($robotsTxtContent);
 
             return $this->robotsTxtCache[(string) $robotsTxtUri] = $parser->getFile();
-        } catch (TransportExceptionInterface $exception) {
+        } catch (TransportExceptionInterface) {
             return $this->robotsTxtCache[(string) $robotsTxtUri] = null;
         }
     }
@@ -209,7 +209,7 @@ private function handleSitemap(CrawlUri $crawlUri, File $robotsTxt): void
         foreach ($robotsTxt->getNonGroupDirectives()->getByField('sitemap')->getDirectives() as $directive) {
             try {
                 $sitemapUri = HttpUriFactory::create($directive->getValue()->get());
-            } catch (\InvalidArgumentException $e) {
+            } catch (\InvalidArgumentException) {
                 $this->logWithCrawlUri(
                     $crawlUri,
                     LogLevel::DEBUG,
@@ -239,14 +239,14 @@ private function extractUrisFromSitemap(CrawlUri $sitemapUri, string $content):
         }
 
         set_error_handler(
-            static function ($errno, $errstr): void {
+            static function ($errno, $errstr): never {
                 throw new \Exception($errstr, $errno);
             },
         );
 
         try {
             $urls = new \SimpleXMLElement($content);
-        } catch (\Exception $exception) {
+        } catch (\Exception) {
             return;
         } finally {
             restore_error_handler();
@@ -258,7 +258,7 @@ static function ($errno, $errstr): void {
             // Add it to the queue if not present already
             try {
                 $uri = HttpUriFactory::create((string) $url->loc);
-            } catch (\InvalidArgumentException $e) {
+            } catch (\InvalidArgumentException) {
                 $this->logWithCrawlUri(
                     $sitemapUri,
                     LogLevel::DEBUG,