Fixes

Author: fivefilters

.github/workflows/main.yml

@@ -22,7 +22,7 @@ jobs:
 
     strategy:
       matrix:
-        php: ['8.1', '8.2', '8.3']
+        php: ['8.1', '8.2', '8.3', '8.4']
         libxml: ['2.9.14']
 
     # Steps represent a sequence of tasks that will be executed as part of the job

Makefile

@@ -1,6 +1,6 @@
 .PHONY: test-all
 
-test-all: start test-8.1 test-8.2 test-8.3 stop
+test-all: start test-8.1 test-8.2 test-8.3 test-8.4 stop
 
 test-8.1:
 	docker-compose exec php-8.1-libxml-2.9.13 php /app/vendor/phpunit/phpunit/phpunit --configuration /app/phpunit.xml
@@ -11,15 +11,18 @@ test-8.2:
 test-8.3:
 	docker-compose exec php-8.3-libxml-2.9.14 php /app/vendor/phpunit/phpunit/phpunit --configuration /app/phpunit.xml
 
+test-8.4:
+	docker-compose exec php-8.4-libxml-2.9.14 php /app/vendor/phpunit/phpunit/phpunit --configuration /app/phpunit.xml
+
 start:
-	docker-compose up -d php-8.1-libxml-2.9.13 php-8.2-libxml-2.9.14 php-8.3-libxml-2.9.14
+	docker-compose up -d php-8.1-libxml-2.9.13 php-8.2-libxml-2.9.14 php-8.3-libxml-2.9.14 php-8.4-libxml-2.9.14
 
 stop:
 	docker-compose stop
 
 test-all-versions:
-	for php_version in 8.1 8.2 8.3; do \
-	    for libxml_version in 2.9.13 2.9.14; do \
+	for php_version in 8.1 8.2 8.3 8.4; do \
+	    for libxml_version in 2.9.14; do \
 			docker-compose up -d php-$$php_version-libxml-$$libxml_version; \
 			docker-compose exec php-$$php_version-libxml-$$libxml_version php /app/vendor/phpunit/phpunit/phpunit --configuration /app/phpunit.xml; \
 		done \

docker-compose.yml

@@ -1,5 +1,3 @@
-version: '3'
-
 services:
   php-8.1-libxml-2.9.13: &template
     build:
@@ -33,4 +31,12 @@ services:
       context: ./docker/php
       args:
         LIBXML_VERSION: 2.9.14
-        PHP_VERSION: 8.3
+        PHP_VERSION: 8.3
+
+  php-8.4-libxml-2.9.14:
+    <<: *template
+    build:
+      context: ./docker/php
+      args:
+        LIBXML_VERSION: 2.9.14
+        PHP_VERSION: 8.4

docker/php/Dockerfile

@@ -10,6 +10,7 @@
 # Ubuntu 23.04 - php 8.1, libxml2 2.9.14
 # Ubuntu 23.10 - php 8.2, libxml2 2.9.14
 # Ubuntu 24.04 - php 8.3, libxml2 2.9.14
+# Ubuntu 24.10 - php 8.3, libxml2 2.12.7
 
 ARG PHP_VERSION
 ARG LIBXML_VERSION

docker/php/build.Dockerfile

@@ -1,17 +1,17 @@
 # Use this file to build a Docker image using the versions of PHP and Libxml specified.
 #
-# We have pre-built images at https://hub.docker.com/r/fivefilters/php-libxml which are 
+# We have pre-built images at https://hub.docker.com/r/fivefilters/php-libxml which are
 # faster to load than building from this file.
 #
-# To build using this file, type the following command from the root project folder 
+# To build using this file, type the following command from the root project folder
 # (replace version of PHP/Libxml with the ones you want to use):
 #
 # docker build --build-arg PHP_VERSION=7.4 --build-arg LIBXML_VERSION=2.9.12 -t php-libxml -f ./docker/php/build.Dockerfile .
 
 # To upload the image to Docker Hub, the tag (-t) value should be something like org/repo:tag, e.g. for us, fivefilters/php-libxml:php-8-libxml-2.9.12
 # The tag can be applied afterwards too, e.g. docker tag php-libxml org/repo:tag
 
-ARG PHP_VERSION=8.1
+ARG PHP_VERSION=8.4
 FROM php:${PHP_VERSION}-cli
 
 # Install sqlite and libonig-dev (required for building PHP 7.4), libreadline-dev for php 8.1

src/Nodes/DOM/DOMNodeList.php

@@ -42,7 +42,7 @@ public function __get($name)
     /**
      * Add node to the list.
      */
-    public function add(DOMNode|DOMElement|DOMComment $node): DOMNodeList
+    public function add(DOMNode|DOMElement|DOMText|DOMComment $node): DOMNodeList
     {
         $this->items[] = $node;
         $this->length++;
@@ -53,7 +53,7 @@ public function add(DOMNode|DOMElement|DOMComment $node): DOMNodeList
     /**
      * Get node.
      */
-    public function item(int $offset): DOMNode|DOMElement|DOMComment
+    public function item(int $offset): DOMNode|DOMElement|DOMText|DOMComment
     {
         return $this->items[$offset];
     }

src/Nodes/NodeTrait.php

@@ -221,7 +221,7 @@ public function getAllLinks(): array
      * Get the density of links as a percentage of the content
      * This is the amount of text that is inside a link divided by the total text in the node.
      */
-    public function getLinkDensity(): int
+    public function getLinkDensity(): float
     {
         $textLength = mb_strlen($this->getTextContent(true));
         if ($textLength === 0) {

src/Nodes/NodeUtility.php

@@ -5,6 +5,8 @@
 use fivefilters\Readability\Nodes\DOM\DOMDocument;
 use fivefilters\Readability\Nodes\DOM\DOMElement;
 use fivefilters\Readability\Nodes\DOM\DOMNode;
+use fivefilters\Readability\Nodes\DOM\DOMText;
+use fivefilters\Readability\Nodes\DOM\DOMComment;
 use fivefilters\Readability\Nodes\DOM\DOMNodeList;
 
 /**
@@ -50,7 +52,7 @@ class NodeUtility
      *
      * Imported from the Element class on league\html-to-markdown.
      */
-    public static function nextNode(DOMNode $node): DOMNode
+    public static function nextNode(DOMNode|DOMComment|DOMText|DOMElement|null $node): DOMNode|DOMComment|DOMText|DOMElement|null
     {
         $next = $node;
         while ($next
@@ -66,7 +68,7 @@ public static function nextNode(DOMNode $node): DOMNode
      * Changes the node tag name. Since tagName on DOMElement is a read only value, this must be done creating a new
      * element with the new tag name and importing it to the main DOMDocument.
      */
-    public static function setNodeTag(DOMNode|DOMElement $node, string $value, bool $importAttributes = true): DOMNode
+    public static function setNodeTag(DOMNode|DOMElement $node, string $value, bool $importAttributes = true): DOMNode|DOMElement
     {
         $new = new DOMDocument('1.0', 'utf-8');
         $new->appendChild($new->createElement($value));
@@ -95,7 +97,7 @@ public static function setNodeTag(DOMNode|DOMElement $node, string $value, bool
     /**
      * Removes the current node and returns the next node to be parsed (child, sibling or parent).
      */
-    public static function removeAndGetNext(DOMNode|DOMElement $node): DOMNode
+    public static function removeAndGetNext(DOMNode|DOMComment|DOMText|DOMElement $node): DOMNode|DOMComment|DOMText|DOMElement|null
     {
         $nextNode = self::getNextNode($node, true);
         $node->parentNode->removeChild($node);
@@ -106,7 +108,7 @@ public static function removeAndGetNext(DOMNode|DOMElement $node): DOMNode
     /**
      * Remove the selected node.
      */
-    public static function removeNode(DOMElement $node): void
+    public static function removeNode(DOMNode|DOMComment|DOMText|DOMElement $node): void
     {
         $parent = $node->parentNode;
         if ($parent) {
@@ -118,7 +120,7 @@ public static function removeNode(DOMElement $node): void
      * Returns the next node. First checks for children (if the flag allows it), then for siblings, and finally
      * for parents.
      */
-    public static function getNextNode(DOMNode|DOMElement|DOMDocument $originalNode, bool $ignoreSelfAndKids = false): DOMNode
+    public static function getNextNode(DOMNode|DOMComment|DOMText|DOMElement|DOMDocument $originalNode, bool $ignoreSelfAndKids = false): DOMNode|DOMComment|DOMText|DOMElement|DOMDocument|null
     {
         /*
          * Traverse the DOM from node to node, starting at the node passed in.

src/Readability.php

@@ -6,6 +6,7 @@
 use fivefilters\Readability\Nodes\DOM\DOMElement;
 use fivefilters\Readability\Nodes\DOM\DOMNode;
 use fivefilters\Readability\Nodes\DOM\DOMText;
+use fivefilters\Readability\Nodes\DOM\DOMComment;
 use fivefilters\Readability\Nodes\NodeUtility;
 use Psr\Log\LoggerInterface;
 use Masterminds\HTML5;
@@ -794,9 +795,12 @@ public function getPathInfo(string $url): array
     /**
      * Gets nodes from the root element.
      */
-    private function getNodes(DOMNode|DOMText $node): array
+    private function getNodes(DOMNode|DOMComment|DOMText|DOMElement|null $node): array
     {
         $this->logger->info('[Get Nodes] Retrieving nodes...');
+        if ($node === null) {
+            return [];
+        }
 
         $stripUnlikelyCandidates = $this->configuration->getStripUnlikelyCandidates();
 
@@ -939,7 +943,7 @@ private function getNodes(DOMNode|DOMText $node): array
      *
      * @return int 1 = same text, 0 = completely different text
      */
-    private function textSimilarity(string $textA, string $textB): int
+    private function textSimilarity(string $textA, string $textB): float
     {
         $tokensA = array_filter(preg_split(NodeUtility::$regexps['tokenize'], mb_strtolower($textA)));
         $tokensB = array_filter(preg_split(NodeUtility::$regexps['tokenize'], mb_strtolower($textB)));
@@ -956,7 +960,7 @@ private function textSimilarity(string $textA, string $textB): int
     /**
      * Checks if the node is a byline.
      */
-    private function checkByline(DOMNode $node, string $matchString): bool
+    private function checkByline(DOMNode|DOMText|DOMElement $node, string $matchString): bool
     {
         if (!$this->configuration->getArticleByLine()) {
             return false;
@@ -999,7 +1003,7 @@ private function isValidByline(string $text): bool
     /**
      * Converts some of the common HTML entities in string to their corresponding characters.
      */
-    private function unescapeHtmlEntities(string $str): string
+    private function unescapeHtmlEntities(?string $str): ?string
     {
         if (!$str) {
             return $str;
@@ -1026,7 +1030,7 @@ private function unescapeHtmlEntities(string $str): string
      * Check if node is image, or if node contains exactly only one image
      * whether as a direct child or as its descendants.
      */
-    private function isSingleImage(DOMElement $node): bool
+    private function isSingleImage(DOMElement|DOMNode|DOMText $node): bool
     {
         if ($node->tagName === 'img') {
             return true;
@@ -1749,7 +1753,7 @@ public function _fixLazyImages(DOMDocument $article): void
     /**
      * Remove the style attribute on every e and under.
      **/
-    public function _cleanStyles(DOMDocument|DOMNode $node): void
+    public function _cleanStyles(DOMDocument|DOMNode|DOMElement|DOMText $node): void
     {
         if (property_exists($node, 'tagName') && $node->tagName === 'svg') {
             return;
@@ -2038,7 +2042,7 @@ public function _cleanHeaders(DOMDocument $article): void
      * @param DOMNode the node to check.
      * @return boolean indicating whether this is a title-like header.
      */
-    private function headerDuplicatesTitle(DOMNode $node): bool
+    private function headerDuplicatesTitle(DOMNode|DOMText|DOMElement $node): bool
     {
         if ($node->nodeName !== 'h1' && $node->nodeName !== 'h2') {
             return false;
@@ -2058,7 +2062,7 @@ private function headerDuplicatesTitle(DOMNode $node): bool
      * Readability.js has a special filter to avoid cleaning the classes that the algorithm adds. We don't add classes
      * here so no need to filter those.
      **/
-    public function _cleanClasses(DOMDocument|DOMNode|DOMElement $node): void
+    public function _cleanClasses(DOMDocument|DOMText|DOMNode|DOMElement $node): void
     {
         if ($node->getAttribute('class') !== '') {
             $node->removeAttribute('class');
@@ -2176,9 +2180,8 @@ public function postProcessContent(DOMDocument $article): DOMDocument
      *
      * @param  array nodeList The NodeList.
      * @param  callable fn    The test function.
-     * @return DOMNode|null
      */
-    private function findNode(array $nodeList, callable $fn): ?DOMNode
+    private function findNode(array $nodeList, callable $fn): DOMNode|DOMText|DOMElement|null
     {
         foreach ($nodeList as $node) {
             if ($fn($node)) {
@@ -2207,7 +2210,7 @@ public function getTitle(): ?string
     /**
      * Set title.
      */
-    protected function setTitle(string $title): void
+    protected function setTitle(?string $title): void
     {
         $this->title = $title;
     }
@@ -2258,7 +2261,7 @@ public function getExcerpt(): ?string
     /**
      * Set excerpt.
      */
-    public function setExcerpt(string $excerpt): void
+    public function setExcerpt(?string $excerpt): void
     {
         $this->excerpt = $excerpt;
     }