Version 1.6.0 (#34)

* Updated to supported Symfony and Doctrine versions only

* Implemented maxDurationInSeconds()

* Updated Coding Style implementation

* Updated to PHP 8 features using Rector <3

* Fixed missing docs

* Update CI

* Update CI to include PHP 8.3

.github/workflows/ci.yaml

@@ -18,23 +18,26 @@ jobs:
             - name: Setup PHP
               uses: shivammathur/setup-php@v2
               with:
-                  php-version: 7.4
+                  php-version: 8.2
                   coverage: none
                   tools: php-cs-fixer
 
-            -   name: Checkout
-                uses: actions/checkout@v2
-
+            - name: Checkout
+              uses: actions/checkout@v2
+
+            - name: Install the dependencies
+              run: composer install --no-interaction --no-suggest
+
             - name: Run the CS fixer
-              run: php-cs-fixer fix
+              run: composer cs
 
     tests:
         name: PHP ${{ matrix.php }}
         runs-on: ubuntu-latest
         strategy:
             fail-fast: false
             matrix:
-                php: [7.4, 8.0, 8.1, 8.2]
+                php: [8.1, 8.2, 8.3]
         steps:
             - name: Setup PHP
               uses: shivammathur/setup-php@v2
@@ -58,7 +61,7 @@ jobs:
         strategy:
             fail-fast: false
             matrix:
-                php: [7.4, 8.0, 8.1, 8.2]
+                php: [8.1, 8.2, 8.3]
         steps:
             - name: Setup PHP
               uses: shivammathur/setup-php@v2

README.md

@@ -211,7 +211,7 @@ There are `2` other interfaces which you might want to integrate but you don't h
 #### Tags
 
 Sometimes you may want to add meta information to any `CrawlUri`  instance so you can let other subscribers decide
-what they want to do with this information or it may be relevant during another request.
+what they want to do with this information, or it may be relevant during another request.
 The `RobotsSubscriber` for instance, tags `CrawlUri` instances when they contained a `<meta name="robots" content="nofollow">`
 in the body or the corresponding `X-Robots-Tag` header was set. All the links found on this URI are then not followed
 which happens during the next `shouldRequest()` call.
@@ -438,6 +438,12 @@ There are different configurations you can apply to the `Escargot` instance:
 
    Returns a clone of the `Escargot` instance with a maximum total requests that are going to be executed. It can be
    useful if you have limited resources and only want to execute e.g. `100` requests in this run and continue later on.
+
+* `Escargot::withMaxDurationInSeconds(int $maxDurationInSeconds): Escargot`
+
+   Returns a clone of the `Escargot` instance with a maximum total seconds Escargot is going to be running. It can be
+   useful if you have limited resources and only want to execute the crawl process for e.g. `30` seconds in this run 
+   and continue later on.
 
 * `Escargot::withUserAgent(string $userAgent): Escargot`
 

composer.json

@@ -16,27 +16,32 @@
         "source": "https://github.com/terminal42/escargot"
     },
     "require": {
-        "php": "^7.4 || ^8.0",
+        "php": "^8.1",
         "ext-simplexml": "*",
         "nyholm/psr7": "^1.1",
         "psr/http-message": "^1.0 || ^2.0",
         "psr/log": "^1.1 || ^2.0 || ^3.0",
-        "symfony/dom-crawler": "^4.4 || ^5.0 || ^6.0",
-        "symfony/event-dispatcher": "^4.4 || ^5.0 || ^6.0",
-        "symfony/http-client": "^4.4 || ^5.0 || ^6.0",
+        "symfony/clock": "^6.2",
+        "symfony/dom-crawler": "^5.4 || ^6.0",
+        "symfony/event-dispatcher": "^5.4 || ^6.0",
+        "symfony/http-client": "^5.4 || ^6.0",
+        "terminal42/contao-build-tools": "@dev",
         "webignition/robots-txt-file": "^3.0"
     },
     "require-dev": {
-        "doctrine/dbal": "^2.13 || ^3.0",
-        "symfony/finder": "^4.4 || ^5.0 || ^6.0",
-        "symfony/phpunit-bridge": "^5.1.8 || ^6.0",
+        "doctrine/dbal": "^3.6",
+        "symfony/finder": "^5.4|| ^6.0",
+        "symfony/phpunit-bridge": "^5.4 || ^6.0",
         "fig/log-test": "^1.0"
     },
     "config": {
         "preferred-install": {
             "*": "dist"
         },
-        "sort-packages": true
+        "sort-packages": true,
+        "allow-plugins": {
+            "terminal42/contao-build-tools": true
+        }
     },
     "autoload": {
         "psr-4": {

src/BaseUriCollection.php

@@ -19,7 +19,7 @@ final class BaseUriCollection implements \IteratorAggregate, \Countable
     /**
      * @var array<UriInterface>
      */
-    private $baseUris = [];
+    private array $baseUris = [];
 
     /**
      * @param array<UriInterface> $baseUris
@@ -80,17 +80,11 @@ public function all(): array
         return array_values($this->baseUris);
     }
 
-    /**
-     * {@inheritdoc}
-     */
     public function getIterator(): \Traversable
     {
         return new \ArrayIterator($this->all());
     }
 
-    /**
-     * {@inheritdoc}
-     */
     public function count(): int
     {
         return \count($this->all());

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 = null;
-
-    /**
-     * @var array
-     */
-    private $tags = [];
-
-    public function __construct(UriInterface $uri, int $level, bool $processed = false, ?UriInterface $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);
@@ -64,7 +44,7 @@ public function __toString(): string
             $this->getLevel(),
             $this->isProcessed() ? 'yes' : 'no',
             (string) ($this->getFoundOn() ?: 'root'),
-            $this->getTags() ? implode(', ', $this->getTags()) : 'none'
+            $this->getTags() ? implode(', ', $this->getTags()) : 'none',
         );
     }
 
@@ -96,7 +76,7 @@ public function wasMarkedProcessed(): bool
         return $this->wasMarkedProcessed;
     }
 
-    public function getFoundOn(): ?UriInterface
+    public function getFoundOn(): UriInterface|null
     {
         return $this->foundOn;
     }
@@ -108,7 +88,7 @@ public function getTags(): array
 
     public function addTag(string $tag): self
     {
-        if (false !== strpos($tag, ',')) {
+        if (str_contains($tag, ',')) {
             throw new \InvalidArgumentException('Cannot use commas in tags.');
         }
 
@@ -139,8 +119,6 @@ public static function normalizeUri(UriInterface $uri): UriInterface
             $uri = $uri->withPath('/');
         }
 
-        $uri = $uri->withFragment('');
-
-        return $uri;
+        return $uri->withFragment('');
     }
 }