[2.x] Fix CI

.github/workflows/coding-standards.yml

@@ -30,7 +30,6 @@ jobs:
           coverage: "none"
           php-version: "${{ matrix.php }}"
           tools: cs2pr, composer:v2
-          ini-values: "date.timezone=Europe/Paris"
         env:
           COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 

.github/workflows/continuous-integration.yml

@@ -43,7 +43,6 @@ jobs:
           coverage: "none"
           tools: composer:v2
           extensions: tidy
-          ini-values: "date.timezone=Europe/Paris"
         env:
           COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
@@ -78,7 +77,6 @@ jobs:
           coverage: "pcov"
           tools: composer:v2
           extensions: tidy
-          ini-values: "date.timezone=Europe/Paris"
         env:
           COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
@@ -124,7 +122,6 @@ jobs:
           coverage: "none"
           tools: composer:v2
           extensions: tidy
-          ini-values: "date.timezone=Europe/Paris"
         env:
           COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
@@ -161,7 +158,6 @@ jobs:
           coverage: "none"
           tools: composer:v2
           extensions: tidy
-          ini-values: "date.timezone=Europe/Paris"
         env:
           COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
@@ -171,7 +167,7 @@ jobs:
       - name: "Setup adapter: Guzzle 5"
         run: |
           composer remove guzzlehttp/guzzle php-http/guzzle6-adapter --dev -n
-          composer require php-http/guzzle5-adapter --dev -n
+          composer require php-http/guzzle5-adapter --dev -n --with-all-dependencies
 
       - name: "Setup logs"
         run: "mkdir -p build/logs"
@@ -241,7 +237,6 @@ jobs:
           coverage: "none"
           tools: composer:v2
           extensions: tidy
-          ini-values: "date.timezone=Europe/Paris"
         env:
           COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
@@ -281,7 +276,6 @@ jobs:
           coverage: "none"
           tools: composer:v1
           extensions: tidy
-          ini-values: "date.timezone=Europe/Paris"
         env:
           COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 

.php-cs-fixer.php

@@ -12,11 +12,15 @@
         '@Symfony:risky' => true,
         'array_syntax' => ['syntax' => 'short'],
         'combine_consecutive_unsets' => true,
+        // Enabled by @Symfony:risky but requires PHP 8.
+        'get_class_to_class_keyword' => false,
         'heredoc_to_nowdoc' => true,
         'no_extra_blank_lines' => ['tokens' => ['break', 'continue', 'extra', 'return', 'throw', 'use', 'parenthesis_brace_block', 'square_brace_block', 'curly_brace_block']],
         'no_unreachable_default_argument_value' => true,
         'no_useless_else' => true,
         'no_useless_return' => true,
+        // Enabled by Symfony and changes properties without type hints but we cannot use those yet because they require PHP 8.
+        'no_null_property_initialization' => false,
         'ordered_class_elements' => true,
         'ordered_imports' => true,
         'php_unit_strict' => true,

composer.json

@@ -60,6 +60,11 @@
             "Tests\\Graby\\": "tests/"
         }
     },
+    "scripts": {
+        "fix": "php-cs-fixer fix --verbose --diff",
+        "phpstan": "phpstan analyse --memory-limit 512M",
+        "test": "simple-phpunit -v"
+    },
     "config": {
         "sort-packages": true,
         "allow-plugins": {

phpunit.xml

@@ -40,6 +40,8 @@
 
     <php>
         <env name="SYMFONY_DEPRECATIONS_HELPER" value="max[direct]=0" />
+
+        <ini name="date.timezone" value="Europe/Paris"/>
     </php>
 
     <!-- <logging>

src/Extractor/ContentExtractor.php

@@ -39,7 +39,7 @@ class ContentExtractor
     /**
      * @param array $config
      */
-    public function __construct($config = [], LoggerInterface $logger = null, ConfigBuilder $configBuilder = null)
+    public function __construct($config = [], ?LoggerInterface $logger = null, ?ConfigBuilder $configBuilder = null)
     {
         $resolver = new OptionsResolver();
         $resolver->setDefaults([
@@ -166,7 +166,7 @@ public function buildSiteConfig($url, $html = '', $addToCache = true)
      *
      * @return bool true on success, false on failure
      */
-    public function process($html, $url, SiteConfig $siteConfig = null, $smartTidy = true)
+    public function process($html, $url, ?SiteConfig $siteConfig = null, $smartTidy = true)
     {
         $this->reset();
 
@@ -888,7 +888,7 @@ private function extractEntityFromQuery($entity, $detectEntity, $xpathExpression
      *
      * @return bool Telling if we have to detect title again or not
      */
-    private function extractTitle($detectTitle, $cssClass, \DOMNode $node = null, $logMessage)
+    private function extractTitle($detectTitle, $cssClass, ?\DOMNode $node, $logMessage)
     {
         if (null === $node) {
             return true;
@@ -913,7 +913,7 @@ private function extractTitle($detectTitle, $cssClass, \DOMNode $node = null, $l
      *
      * @return bool Telling if we have to detect date again or not
      */
-    private function extractDate($detectDate, $cssClass, \DOMNode $node = null, $logMessage)
+    private function extractDate($detectDate, $cssClass, ?\DOMNode $node, $logMessage)
     {
         if (null === $node) {
             return true;
@@ -936,7 +936,7 @@ private function extractDate($detectDate, $cssClass, \DOMNode $node = null, $log
      *
      * @return bool Telling if we have to detect author again or not
      */
-    private function extractAuthor($detectAuthor, \DOMNode $node = null)
+    private function extractAuthor($detectAuthor, ?\DOMNode $node)
     {
         if (false === $detectAuthor) {
             return false;
@@ -983,7 +983,7 @@ private function extractAuthor($detectAuthor, \DOMNode $node = null)
      *
      * @return bool Telling if we have to detect body again or not
      */
-    private function extractBody($detectBody, $xpathExpression, \DOMNode $node = null, $type)
+    private function extractBody($detectBody, $xpathExpression, ?\DOMNode $node, $type)
     {
         if (false === $detectBody) {
             return false;

src/Extractor/HttpClient.php

@@ -42,7 +42,7 @@ class HttpClient
      */
     private $responseHistory;
 
-    public function __construct(ClientInterface $client, $config = [], LoggerInterface $logger = null)
+    public function __construct(ClientInterface $client, $config = [], ?LoggerInterface $logger = null)
     {
         $resolver = new OptionsResolver();
         $resolver->setDefaults([

src/Graby.php

@@ -44,7 +44,7 @@ class Graby
     private $imgNoReferrer = false;
     private $prefetchedContent;
 
-    public function __construct($config = [], ClientInterface $client = null, ConfigBuilder $configBuilder = null)
+    public function __construct($config = [], ?ClientInterface $client = null, ?ConfigBuilder $configBuilder = null)
     {
         $resolver = new OptionsResolver();
         $resolver->setDefaults([
@@ -150,7 +150,7 @@ public function reloadConfigFiles()
     public function getConfig($key)
     {
         if (!isset($this->config[$key])) {
-            throw new \Exception(sprintf('No config found for key: "%s"', $key));
+            throw new \Exception(\sprintf('No config found for key: "%s"', $key));
         }
 
         return $this->config[$key];
@@ -307,7 +307,7 @@ private function doFetchContent($url)
         $effectiveUrl = $response['effective_url'];
         $effectiveUrl = str_replace(' ', '%20', $effectiveUrl);
         if (!$this->isUrlAllowed($effectiveUrl)) {
-            throw new \Exception(sprintf('Url "%s" is not allowed to be parsed.', $effectiveUrl));
+            throw new \Exception(\sprintf('Url "%s" is not allowed to be parsed.', $effectiveUrl));
         }
 
         // check if action defined for returned Content-Type, like image, pdf, audio or video
@@ -511,17 +511,17 @@ private function validateUrl($url)
         $url = (string) $uri;
 
         if (false === filter_var($url, \FILTER_VALIDATE_URL)) {
-            throw new \InvalidArgumentException(sprintf('Url "%s" is not valid.', $url));
+            throw new \InvalidArgumentException(\sprintf('Url "%s" is not valid.', $url));
         }
 
         $url = filter_var($url, \FILTER_SANITIZE_URL);
 
         if (false === $url) {
-            throw new \InvalidArgumentException(sprintf('Sanitizing url "%s" failed.', $url));
+            throw new \InvalidArgumentException(\sprintf('Sanitizing url "%s" failed.', $url));
         }
 
         if (false === $this->isUrlAllowed($url)) {
-            throw new \InvalidArgumentException(sprintf('Url "%s" is not allowed to be parsed.', $url));
+            throw new \InvalidArgumentException(\sprintf('Url "%s" is not allowed to be parsed.', $url));
         }
 
         return $url;
@@ -621,7 +621,7 @@ private function handleMimeAction($mimeInfo, $effectiveUrl, $response = [])
         ];
 
         if ('exclude' === $mimeInfo['action']) {
-            throw new \Exception(sprintf('This is url "%s" is blocked by mime action.', $effectiveUrl));
+            throw new \Exception(\sprintf('This is url "%s" is blocked by mime action.', $effectiveUrl));
         }
 
         $infos['html'] = '<a href="' . $effectiveUrl . '">Download ' . $mimeInfo['name'] . '</a>';

src/HttpClient/Plugin/CookiePlugin.php

@@ -51,7 +51,7 @@ public function handleRequest(RequestInterface $request, callable $next, callabl
                 continue;
             }
 
-            $cookies[] = sprintf('%s=%s', $cookie->getName(), $cookie->getValue());
+            $cookies[] = \sprintf('%s=%s', $cookie->getName(), $cookie->getValue());
         }
 
         if (!empty($cookies)) {
@@ -114,7 +114,7 @@ private function createCookie(RequestInterface $request, string $setCookieHeader
                     try {
                         $expires = CookieUtil::parseDate((string) $value);
                     } catch (UnexpectedValueException $e) {
-                        throw new TransferException(sprintf('Cookie header `%s` expires value `%s` could not be converted to date', $name, $value), 0, $e);
+                        throw new TransferException(\sprintf('Cookie header `%s` expires value `%s` could not be converted to date', $name, $value), 0, $e);
                     }
 
                     break;

src/SiteConfig/ConfigBuilder.php

@@ -33,7 +33,7 @@ class ConfigBuilder
     /**
      * @param array $config
      */
-    public function __construct($config = [], LoggerInterface $logger = null)
+    public function __construct($config = [], ?LoggerInterface $logger = null)
     {
         $resolver = new OptionsResolver();
         $resolver->setDefaults([
@@ -385,23 +385,23 @@ public function parseLines(array $lines)
                 $command = 'strip';
             }
 
-            // check for commands where we accept multiple statements
             if (\in_array($command, ['title', 'body', 'strip', 'strip_id_or_class', 'strip_image_src', 'single_page_link', 'next_page_link', 'test_url', 'find_string', 'replace_string', 'login_extra_fields', 'native_ad_clue', 'date', 'author'], true)) {
+                // check for commands where we accept multiple statements
                 $config->$command[] = $val;
-            // check for single statement commands that evaluate to true or false
             } elseif (\in_array($command, ['tidy', 'prune', 'autodetect_on_failure', 'requires_login', 'skip_json_ld'], true)) {
+                // check for single statement commands that evaluate to true or false
                 $config->$command = ('yes' === $val || 'true' === $val);
-            // check for single statement commands stored as strings
             } elseif (\in_array($command, ['parser', 'login_username_field', 'login_password_field', 'not_logged_in_xpath', 'login_uri', 'src_lazy_load_attr'], true)) {
+                // check for single statement commands stored as strings
                 $config->$command = $val;
-            // check for replace_string(find): replace
             } elseif ((')' === substr($command, -1)) && preg_match('!^([a-z0-9_]+)\((.*?)\)$!i', $command, $match) && 'replace_string' === $match[1]) {
+                // check for replace_string(find): replace
                 $config->find_string[] = $match[2];
                 $config->replace_string[] = $val;
             } elseif ((')' === substr($command, -1)) && preg_match('!^([a-z0-9_]+)\(([a-z0-9_-]+)\)$!i', $command, $match) && 'http_header' === $match[1] && \in_array(strtolower($match[2]), $this->acceptedHeaders, true)) {
                 $config->http_header[strtolower(trim($match[2]))] = $val;
-            // special treatment for if_page_contains
             } elseif (\in_array($command, ['if_page_contains'], true)) {
+                // special treatment for if_page_contains
                 $this->handleIfPageContainsCondition($config, $val);
             } elseif ((')' === substr($command, -1)) && preg_match('!([a-z0-9_]+)\(([a-z]+)\)$!i', $command, $match) && 'wrap_in' === $match[1] && \in_array(strtolower($match[2]), $this->acceptedWrapInTags, true)) {
                 $config->wrap_in[strtolower(trim($match[2]))] = $val;

tests/Extractor/ContentExtractorTest.php

@@ -390,7 +390,7 @@ public function dataForStripIdOrClass(): array
     /**
      * @dataProvider dataForStripIdOrClass
      */
-    public function testApplyStripIdOrClass(string $pattern, string $html, ?string $removedContent, string $matchContent = null): void
+    public function testApplyStripIdOrClass(string $pattern, string $html, ?string $removedContent, ?string $matchContent = null): void
     {
         $contentExtractor = new ContentExtractor(self::$contentExtractorConfig);
 
@@ -482,14 +482,14 @@ public function dataForStripAttr(): array
     {
         return [
             [['//*/@class'], '<html><body><div class="hello world"><i class="class">bar</i>class="foo"' . str_repeat('this is the best part of the show', 10) . ' <a class="hc" href="void">link</a></div></body></html>', [
-                    'removedContent' => ['class="class"', 'class="hello world"', 'class="hc"'],
-                    'keptContent' => ['class="foo"', '<a href="void"', '<em>bar'],
-                ],
+                'removedContent' => ['class="class"', 'class="hello world"', 'class="hc"'],
+                'keptContent' => ['class="foo"', '<a href="void"', '<em>bar'],
+            ],
             ],
             [['//img/@class', '//p/@class'], '<html><body><img class="bar-class" src="void" /><a class="hello" href="void">link</a> <p class="yes">' . str_repeat('this is the best part of the show', 10) . '</p></body></html>', [
-                    'removedContent' => ['class="bar-class"', 'class="yes"'],
-                    'keptContent' => ['class="hello"'],
-                ],
+                'removedContent' => ['class="bar-class"', 'class="yes"'],
+                'keptContent' => ['class="hello"'],
+            ],
             ],
         ];
     }