Initial version using PHP 8.4's HTML5 parser

Author: fivefilters

composer.json

@@ -32,7 +32,6 @@
         "ext-xml": "*",
         "ext-mbstring": "*",
         "psr/log": "^1.0 || ^2.0 || ^3.0",
-        "masterminds/html5": "^2.0",
         "league/uri": "^7.0"
     },
     "require-dev": {

src/Configuration.php

@@ -20,7 +20,6 @@ class Configuration
     protected bool $cleanConditionally = true;
     protected bool $weightClasses = true;
     protected bool $fixRelativeURLs = false;
-    protected bool $substituteEntities = false;
     protected bool $normalizeEntities = false;
     protected bool $summonCthulhu = false;
     protected string $originalURL = 'http://fakehost';
@@ -206,24 +205,6 @@ public function setFixRelativeURLs(bool $fixRelativeURLs): Configuration
         return $this;
     }
 
-    /**
-     * Get substitute entities.
-     */
-    public function getSubstituteEntities(): bool
-    {
-        return $this->substituteEntities;
-    }
-
-    /**
-     * Set substitute entities.
-     */
-    public function setSubstituteEntities(bool $substituteEntities): Configuration
-    {
-        $this->substituteEntities = $substituteEntities;
-
-        return $this;
-    }
-
     /**
      * Get normalize entities.
      */
@@ -273,7 +254,11 @@ public function getParser(): string
      */
     public function setParser(string $parser): Configuration
     {
-        $this->parser = $parser;
+        if ($parser !== 'html5') {
+            throw new \InvalidArgumentException('This version of Readability.php only supports the HTML5 parser introduced in PHP 8.4');
+        } else {
+            $this->parser = $parser;
+        }
 
         return $this;
     }

src/Nodes/DOM/DOMAttr.php src/Nodes/DOM/Attr.phpsrc/Nodes/DOM/DOMAttr.php renamed to src/Nodes/DOM/Attr.php

@@ -4,7 +4,7 @@
 
 use fivefilters\Readability\Nodes\NodeTrait;
 
-class DOMAttr extends \DOMAttr
+class Attr extends \DOM\Attr
 {
     use NodeTrait;
 }

src/Nodes/DOM/DOMNotation.php src/Nodes/DOM/CdataSection.phpsrc/Nodes/DOM/DOMNotation.php renamed to src/Nodes/DOM/CdataSection.php

@@ -4,7 +4,7 @@
 
 use fivefilters\Readability\Nodes\NodeTrait;
 
-class DOMNotation extends \DOMNotation
+class CdataSection extends \DOM\CdataSection
 {
     use NodeTrait;
 }

src/Nodes/DOM/DOMCdataSection.php src/Nodes/DOM/CharacterData.phpsrc/Nodes/DOM/DOMCdataSection.php renamed to src/Nodes/DOM/CharacterData.php

@@ -4,7 +4,7 @@
 
 use fivefilters\Readability\Nodes\NodeTrait;
 
-class DOMCdataSection extends \DOMCdataSection
+class CharacterData extends \DOM\CharacterData
 {
     use NodeTrait;
 }

src/Nodes/DOM/DOMEntity.php src/Nodes/DOM/Comment.phpsrc/Nodes/DOM/DOMEntity.php renamed to src/Nodes/DOM/Comment.php

@@ -4,7 +4,7 @@
 
 use fivefilters\Readability\Nodes\NodeTrait;
 
-class DOMEntity extends \DOMEntity
+class Comment extends \DOM\Comment
 {
     use NodeTrait;
 }