Merge pull request #341 from j0k3r/fix/2.x-update-deps

[2.x] Update deps

Author: j0k3r

.github/workflows/coding-standards.yml

@@ -3,10 +3,12 @@ name: "CS"
 on:
   pull_request:
     branches:
-      - master
+      - "master"
+      - "2.x"
   push:
     branches:
-      - master
+      - "master"
+      - "2.x"
 
 jobs:
   coding-standards:
@@ -16,11 +18,11 @@ jobs:
     strategy:
       matrix:
         php:
-          - "7.3"
+          - "7.4"
 
     steps:
       - name: "Checkout"
-        uses: "actions/checkout@v2"
+        uses: "actions/checkout@v4"
 
       - name: "Install PHP"
         uses: "shivammathur/setup-php@v2"
@@ -33,7 +35,7 @@ jobs:
           COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: "Install dependencies with Composer"
-        uses: "ramsey/composer-install@v1"
+        uses: "ramsey/composer-install@v2"
 
       - name: "Run PHP CS Fixer"
         run: "php vendor/bin/php-cs-fixer fix --verbose --dry-run --format=checkstyle | cs2pr"

.github/workflows/continuous-integration.yml

@@ -4,9 +4,11 @@ on:
   pull_request:
     branches:
       - "master"
+      - "2.x"
   push:
     branches:
       - "master"
+      - "2.x"
 
 env:
   fail-fast: true
@@ -24,10 +26,13 @@ jobs:
           - "7.3"
           - "7.4"
           - "8.0"
+          - "8.1"
+          - "8.2"
+          - "8.3"
 
     steps:
       - name: "Checkout"
-        uses: "actions/checkout@v2"
+        uses: "actions/checkout@v4"
         with:
           fetch-depth: 2
 
@@ -43,7 +48,7 @@ jobs:
           COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: "Install dependencies with Composer"
-        uses: "ramsey/composer-install@v1"
+        uses: "ramsey/composer-install@v2"
 
       - name: "Setup logs"
         run: "mkdir -p build/logs"
@@ -62,7 +67,7 @@ jobs:
 
     steps:
       - name: "Checkout"
-        uses: "actions/checkout@v2"
+        uses: "actions/checkout@v4"
         with:
           fetch-depth: 2
 
@@ -78,7 +83,7 @@ jobs:
           COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: "Install dependencies with Composer"
-        uses: "ramsey/composer-install@v1"
+        uses: "ramsey/composer-install@v2"
 
       - name: "Setup logs"
         run: "mkdir -p build/logs"
@@ -108,7 +113,7 @@ jobs:
 
     steps:
       - name: "Checkout"
-        uses: "actions/checkout@v2"
+        uses: "actions/checkout@v4"
         with:
           fetch-depth: 2
 
@@ -124,7 +129,7 @@ jobs:
           COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: "Install dependencies with Composer"
-        uses: "ramsey/composer-install@v1"
+        uses: "ramsey/composer-install@v2"
         with:
           dependency-versions: "lowest"
 
@@ -145,7 +150,7 @@ jobs:
 
     steps:
       - name: "Checkout"
-        uses: "actions/checkout@v2"
+        uses: "actions/checkout@v4"
         with:
           fetch-depth: 2
 
@@ -161,7 +166,7 @@ jobs:
           COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: "Install dependencies with Composer"
-        uses: "ramsey/composer-install@v1"
+        uses: "ramsey/composer-install@v2"
 
       - name: "Setup adapter: Guzzle 5"
         run: |
@@ -185,7 +190,7 @@ jobs:
 
     steps:
       - name: "Checkout"
-        uses: "actions/checkout@v2"
+        uses: "actions/checkout@v4"
         with:
           fetch-depth: 2
 
@@ -201,7 +206,7 @@ jobs:
           COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: "Install dependencies with Composer"
-        uses: "ramsey/composer-install@v1"
+        uses: "ramsey/composer-install@v2"
 
       - name: "Setup adapter: Guzzle 7"
         run: |
@@ -225,7 +230,7 @@ jobs:
 
     steps:
       - name: "Checkout"
-        uses: "actions/checkout@v2"
+        uses: "actions/checkout@v4"
         with:
           fetch-depth: 2
 
@@ -241,13 +246,12 @@ jobs:
           COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: "Install dependencies with Composer"
-        uses: "ramsey/composer-install@v1"
+        uses: "ramsey/composer-install@v2"
 
       - name: "Setup adapter: cURL"
         run: |
           composer remove php-http/guzzle6-adapter --dev -n
           composer require php-http/curl-client --dev -n
-          composer require zendframework/zend-diactoros --dev -n
 
       - name: "Setup logs"
         run: "mkdir -p build/logs"
@@ -266,7 +270,7 @@ jobs:
 
     steps:
       - name: "Checkout"
-        uses: "actions/checkout@v2"
+        uses: "actions/checkout@v4"
         with:
           fetch-depth: 2
 
@@ -282,7 +286,7 @@ jobs:
           COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: "Install dependencies with Composer"
-        uses: "ramsey/composer-install@v1"
+        uses: "ramsey/composer-install@v2"
 
       - name: "Setup logs"
         run: "mkdir -p build/logs"

composer.json

@@ -19,18 +19,18 @@
         "ext-curl": "*",
         "ext-tidy": "*",
         "fossar/htmlawed": "^1.2.7",
-        "http-interop/http-factory-guzzle": "^1.0",
-        "j0k3r/graby-site-config": "^1.0.110",
+        "http-interop/http-factory-guzzle": "^1.1",
+        "j0k3r/graby-site-config": "^1.0.181",
         "j0k3r/httplug-ssrf-plugin": "^2.0",
-        "j0k3r/php-readability": "^1.2.3",
+        "j0k3r/php-readability": "^1.2.10",
         "monolog/monolog": "^1.18.0|^2.0",
-        "php-http/client-common": "^2.3",
-        "php-http/discovery": "^1.12",
-        "php-http/httplug": "^2.2",
-        "php-http/message": "^1.9",
-        "simplepie/simplepie": "^1.5",
-        "smalot/pdfparser": "^1.0",
-        "symfony/options-resolver": "^3.4|^4.4|^5.3|^6.0",
+        "php-http/client-common": "^2.7",
+        "php-http/discovery": "^1.19",
+        "php-http/httplug": "^2.4",
+        "php-http/message": "^1.14",
+        "simplepie/simplepie": "^1.7",
+        "smalot/pdfparser": "^1.1",
+        "symfony/options-resolver": "^3.4|^4.4|^5.3|^6.0|^7.0",
         "true/punycode": "^2.1",
         "guzzlehttp/psr7": "^1.5.0|^2.0"
     },
@@ -43,7 +43,7 @@
         "phpstan/phpstan": "^0.12",
         "phpstan/phpstan-deprecation-rules": "^0.12",
         "phpstan/phpstan-phpunit": "^0.12",
-        "symfony/phpunit-bridge": "^5.3"
+        "symfony/phpunit-bridge": "^6.4.1"
     },
     "extra": {
         "branch-alias": {
@@ -61,6 +61,10 @@
         }
     },
     "config": {
-        "sort-packages": true
+        "sort-packages": true,
+        "allow-plugins": {
+            "php-http/discovery": true,
+            "phpstan/extension-installer": true
+        }
     }
 }

phpunit.xml

@@ -38,6 +38,10 @@
         </listener>
     </listeners>
 
+    <php>
+        <env name="SYMFONY_DEPRECATIONS_HELPER" value="max[direct]=0" />
+    </php>
+
     <!-- <logging>
         <log type="coverage-html" target="build" lowUpperBound="35" highLowerBound="70"/>
     </logging> -->

src/Extractor/ContentExtractor.php

@@ -21,14 +21,14 @@ class ContentExtractor
     private $xpath;
     private $html;
     private $config;
-    private $siteConfig = null;
-    private $title = null;
-    private $language = null;
+    private $siteConfig;
+    private $title;
+    private $language;
     private $authors = [];
-    private $body = null;
-    private $image = null;
+    private $body;
+    private $image;
     private $nativeAd = false;
-    private $date = null;
+    private $date;
     private $success = false;
     private $nextPageUrl;
     /** @var LoggerInterface */

src/Extractor/HttpClient.php

@@ -13,8 +13,8 @@
 use Http\Client\Common\Plugin\RedirectPlugin;
 use Http\Client\Common\PluginClient;
 use Http\Client\Exception\TransferException;
-use Http\Client\HttpClient as Client;
 use Http\Discovery\Psr17FactoryDiscovery;
+use Psr\Http\Client\ClientInterface;
 use Psr\Http\Message\ResponseInterface;
 use Psr\Log\LoggerInterface;
 use Psr\Log\NullLogger;
@@ -42,11 +42,7 @@ class HttpClient
      */
     private $responseHistory;
 
-    /**
-     * @param Client $client Http client
-     * @param array  $config
-     */
-    public function __construct(Client $client, $config = [], LoggerInterface $logger = null)
+    public function __construct(ClientInterface $client, $config = [], LoggerInterface $logger = null)
     {
         $resolver = new OptionsResolver();
         $resolver->setDefaults([
@@ -254,7 +250,7 @@ public function fetch($url, $skipTypeVerification = false, $httpHeader = [])
         // check for <meta name='fragment' content='!'/>
         // for AJAX sites, e.g. Blogger with its dynamic views templates.
         // Based on Google's spec: https://developers.google.com/webmasters/ajax-crawling/docs/specification
-        if (false === strpos($effectiveUrl, '_escaped_fragment_')) {
+        if (!str_contains($effectiveUrl, '_escaped_fragment_')) {
             $redirectURL = $this->getMetaRefreshURL($effectiveUrl, $body) ?: $this->getUglyURL($effectiveUrl, $body);
 
             if (false !== $redirectURL) {
@@ -296,7 +292,7 @@ private function cleanupUrl($url)
     {
         // rewrite part of urls to something more readable
         foreach ($this->config['rewrite_url'] as $find => $action) {
-            if (false !== strpos($url, $find) && \is_array($action)) {
+            if (str_contains($url, $find) && \is_array($action)) {
                 $url = strtr($url, $action);
             }
         }

src/Graby.php

@@ -9,11 +9,11 @@
 use GuzzleHttp\Psr7\Uri;
 use GuzzleHttp\Psr7\UriResolver;
 use Http\Client\Common\PluginClient;
-use Http\Client\HttpClient as Client;
-use Http\Discovery\HttpClientDiscovery;
+use Http\Discovery\Psr18ClientDiscovery;
 use Http\Message\CookieJar;
 use Monolog\Handler\StreamHandler;
 use Monolog\Logger;
+use Psr\Http\Client\ClientInterface;
 use Psr\Log\LoggerInterface;
 use Psr\Log\NullLogger;
 use Readability\Readability;
@@ -34,21 +34,17 @@ class Graby
 
     private $config = [];
 
-    private $httpClient = null;
-    private $extractor = null;
+    private $httpClient;
+    private $extractor;
 
     /** @var ConfigBuilder */
     private $configBuilder;
     private $punycode;
 
     private $imgNoReferrer = false;
-    private $prefetchedContent = null;
+    private $prefetchedContent;
 
-    /**
-     * @param array       $config
-     * @param Client|null $client Http client
-     */
-    public function __construct($config = [], Client $client = null, ConfigBuilder $configBuilder = null)
+    public function __construct($config = [], ClientInterface $client = null, ConfigBuilder $configBuilder = null)
     {
         $resolver = new OptionsResolver();
         $resolver->setDefaults([
@@ -118,7 +114,7 @@ public function __construct($config = [], Client $client = null, ConfigBuilder $
         );
 
         $this->httpClient = new HttpClient(
-            $client ?: new PluginClient(HttpClientDiscovery::find(), [new CookiePlugin(new CookieJar())]),
+            $client ?: new PluginClient(Psr18ClientDiscovery::find(), [new CookiePlugin(new CookieJar())]),
             $this->config['http_client'],
             $this->logger
         );
@@ -150,8 +146,6 @@ public function reloadConfigFiles()
      * Return a config.
      *
      * @param string $key
-     *
-     * @return mixed
      */
     public function getConfig($key)
     {
@@ -226,7 +220,7 @@ public function cleanupHtml($contentBlock, $url)
         }
 
         // footnotes
-        if ('footnotes' === $this->config['content_links'] && false === strpos($url, 'wikipedia.org')) {
+        if ('footnotes' === $this->config['content_links'] && !str_contains($url, 'wikipedia.org')) {
             $this->extractor->readability->addFootnotes($contentBlock);
         }
 
@@ -343,13 +337,6 @@ private function doFetchContent($url)
 
         $this->logger->debug('HTML after regex empty nodes stripping', ['html' => $html]);
 
-        // some non utf8 enconding might be breaking after converting to utf8
-        // when it happen the string (usually) starts with this character
-        // in that case, we'll take the default response instead of the utf8 forced one
-        if (0 === strpos(utf8_encode($response['body']), 'ÿþ')) {
-            $html = $response['body'];
-        }
-
         // check site config for single page URL - fetch it if found
         $isSinglePage = false;
         if ($this->config['singlepage'] && null === $this->prefetchedContent && ($singlePageResponse = $this->getSinglePage($html, $effectiveUrl))) {