Merge branch 'feature/readability-ignore-more-elements' into 'master'HEADmaster

Have Readability ignore/strip 'template' elements.

See merge request tt-rss/plugins/ttrss-af-readability!1

11 files changed, 129 insertions, 116 deletions

diff --git a/composer.lock b/composer.lock
index f4fc172..1f87b0a 100644
--- a/composer.lock
+++ b/composer.lock
@@ -12,7 +12,7 @@
             "source": {
                 "type": "git",
                 "url": "https://dev.tt-rss.org/fox/readability-php.git",
-                "reference": "8ac5abdd497b37d2be4833bcf18d6819bba4d9c9"
+                "reference": "37c0c2ce76aa90e8adafbd5cb0b0332a54df1523"
             },
             "require": {
                 "ext-dom": "*",
@@ -64,7 +64,7 @@
                 "html",
                 "readability"
             ],
-            "time": "2022-07-31T06:02:47+00:00"
+            "time": "2024-04-03T17:38:00+00:00"
         },
         {
             "name": "league/uri",
@@ -469,5 +469,5 @@
     "prefer-lowest": false,
     "platform": [],
     "platform-dev": [],
-    "plugin-api-version": "2.3.0"
+    "plugin-api-version": "2.6.0"
 }
diff --git a/init.php b/init.php
index 1deb1fc..591be6e 100755
--- a/init.php
+++ b/init.php
@@ -220,8 +220,9 @@ class Af_Readability extends Plugin {
 			try {
 
 				$r = new Readability(new Configuration([
-					'fixRelativeURLs' => true,
-					'originalURL'     => $url,
+					'FixRelativeURLs'      => true,
+					'OriginalURL'          => $url,
+					'ExtraIgnoredElements' => ['template'],
 				]));
 
 				if ($r->parse($tmp)) {
diff --git a/vendor/composer/ClassLoader.php b/vendor/composer/ClassLoader.php
index afef3fa..7824d8f 100644
--- a/vendor/composer/ClassLoader.php
+++ b/vendor/composer/ClassLoader.php
@@ -42,35 +42,37 @@ namespace Composer\Autoload;
  */
 class ClassLoader
 {
-    /** @var ?string */
+    /** @var \Closure(string):void */
+    private static $includeFile;
+
+    /** @var string|null */
     private $vendorDir;
 
     // PSR-4
     /**
-     * @var array[]
-     * @psalm-var array<string, array<string, int>>
+     * @var array<string, array<string, int>>
      */
     private $prefixLengthsPsr4 = array();
     /**
-     * @var array[]
-     * @psalm-var array<string, array<int, string>>
+     * @var array<string, list<string>>
      */
     private $prefixDirsPsr4 = array();
     /**
-     * @var array[]
-     * @psalm-var array<string, string>
+     * @var list<string>
      */
     private $fallbackDirsPsr4 = array();
 
     // PSR-0
     /**
-     * @var array[]
-     * @psalm-var array<string, array<string, string[]>>
+     * List of PSR-0 prefixes
+     *
+     * Structured as array('F (first letter)' => array('Foo\Bar (full prefix)' => array('path', 'path2')))
+     *
+     * @var array<string, array<string, list<string>>>
      */
     private $prefixesPsr0 = array();
     /**
-     * @var array[]
-     * @psalm-var array<string, string>
+     * @var list<string>
      */
     private $fallbackDirsPsr0 = array();
 
@@ -78,8 +80,7 @@ class ClassLoader
     private $useIncludePath = false;
 
     /**
-     * @var string[]
-     * @psalm-var array<string, string>
+     * @var array<string, string>
      */
     private $classMap = array();
 
@@ -87,29 +88,29 @@ class ClassLoader
     private $classMapAuthoritative = false;
 
     /**
-     * @var bool[]
-     * @psalm-var array<string, bool>
+     * @var array<string, bool>
      */
     private $missingClasses = array();
 
-    /** @var ?string */
+    /** @var string|null */
     private $apcuPrefix;
 
     /**
-     * @var self[]
+     * @var array<string, self>
      */
     private static $registeredLoaders = array();
 
     /**
-     * @param ?string $vendorDir
+     * @param string|null $vendorDir
      */
     public function __construct($vendorDir = null)
     {
         $this->vendorDir = $vendorDir;
+        self::initializeIncludeClosure();
     }
 
     /**
-     * @return string[]
+     * @return array<string, list<string>>
      */
     public function getPrefixes()
     {
@@ -121,8 +122,7 @@ class ClassLoader
     }
 
     /**
-     * @return array[]
-     * @psalm-return array<string, array<int, string>>
+     * @return array<string, list<string>>
      */
     public function getPrefixesPsr4()
     {
@@ -130,8 +130,7 @@ class ClassLoader
     }
 
     /**
-     * @return array[]
-     * @psalm-return array<string, string>
+     * @return list<string>
      */
     public function getFallbackDirs()
     {
@@ -139,8 +138,7 @@ class ClassLoader
     }
 
     /**
-     * @return array[]
-     * @psalm-return array<string, string>
+     * @return list<string>
      */
     public function getFallbackDirsPsr4()
     {
@@ -148,8 +146,7 @@ class ClassLoader
     }
 
     /**
-     * @return string[] Array of classname => path
-     * @psalm-return array<string, string>
+     * @return array<string, string> Array of classname => path
      */
     public function getClassMap()
     {
@@ -157,8 +154,7 @@ class ClassLoader
     }
 
     /**
-     * @param string[] $classMap Class to filename map
-     * @psalm-param array<string, string> $classMap
+     * @param array<string, string> $classMap Class to filename map
      *
      * @return void
      */
@@ -175,24 +171,25 @@ class ClassLoader
      * Registers a set of PSR-0 directories for a given prefix, either
      * appending or prepending to the ones previously set for this prefix.
      *
-     * @param string          $prefix  The prefix
-     * @param string[]|string $paths   The PSR-0 root directories
-     * @param bool            $prepend Whether to prepend the directories
+     * @param string              $prefix  The prefix
+     * @param list<string>|string $paths   The PSR-0 root directories
+     * @param bool                $prepend Whether to prepend the directories
      *
      * @return void
      */
     public function add($prefix, $paths, $prepend = false)
     {
+        $paths = (array) $paths;
         if (!$prefix) {
             if ($prepend) {
                 $this->fallbackDirsPsr0 = array_merge(
-                    (array) $paths,
+                    $paths,
                     $this->fallbackDirsPsr0
                 );
             } else {
                 $this->fallbackDirsPsr0 = array_merge(
                     $this->fallbackDirsPsr0,
-                    (array) $paths
+                    $paths
                 );
             }
 
@@ -201,19 +198,19 @@ class ClassLoader
 
         $first = $prefix[0];
         if (!isset($this->prefixesPsr0[$first][$prefix])) {
-            $this->prefixesPsr0[$first][$prefix] = (array) $paths;
+            $this->prefixesPsr0[$first][$prefix] = $paths;
 
             return;
         }
         if ($prepend) {
             $this->prefixesPsr0[$first][$prefix] = array_merge(
-                (array) $paths,
+                $paths,
                 $this->prefixesPsr0[$first][$prefix]
             );
         } else {
             $this->prefixesPsr0[$first][$prefix] = array_merge(
                 $this->prefixesPsr0[$first][$prefix],
-                (array) $paths
+                $paths
             );
         }
     }
@@ -222,9 +219,9 @@ class ClassLoader
      * Registers a set of PSR-4 directories for a given namespace, either
      * appending or prepending to the ones previously set for this namespace.
      *
-     * @param string          $prefix  The prefix/namespace, with trailing '\\'
-     * @param string[]|string $paths   The PSR-4 base directories
-     * @param bool            $prepend Whether to prepend the directories
+     * @param string              $prefix  The prefix/namespace, with trailing '\\'
+     * @param list<string>|string $paths   The PSR-4 base directories
+     * @param bool                $prepend Whether to prepend the directories
      *
      * @throws \InvalidArgumentException
      *
@@ -232,17 +229,18 @@ class ClassLoader
      */
     public function addPsr4($prefix, $paths, $prepend = false)
     {
+        $paths = (array) $paths;
         if (!$prefix) {
             // Register directories for the root namespace.
             if ($prepend) {
                 $this->fallbackDirsPsr4 = array_merge(
-                    (array) $paths,
+                    $paths,
                     $this->fallbackDirsPsr4
                 );
             } else {
                 $this->fallbackDirsPsr4 = array_merge(
                     $this->fallbackDirsPsr4,
-                    (array) $paths
+                    $paths
                 );
             }
         } elseif (!isset($this->prefixDirsPsr4[$prefix])) {
@@ -252,18 +250,18 @@ class ClassLoader
                 throw new \InvalidArgumentException("A non-empty PSR-4 prefix must end with a namespace separator.");
             }
             $this->prefixLengthsPsr4[$prefix[0]][$prefix] = $length;
-            $this->prefixDirsPsr4[$prefix] = (array) $paths;
+            $this->prefixDirsPsr4[$prefix] = $paths;
         } elseif ($prepend) {
             // Prepend directories for an already registered namespace.
             $this->prefixDirsPsr4[$prefix] = array_merge(
-                (array) $paths,
+                $paths,
                 $this->prefixDirsPsr4[$prefix]
             );
         } else {
             // Append directories for an already registered namespace.
             $this->prefixDirsPsr4[$prefix] = array_merge(
                 $this->prefixDirsPsr4[$prefix],
-                (array) $paths
+                $paths
             );
         }
     }
@@ -272,8 +270,8 @@ class ClassLoader
      * Registers a set of PSR-0 directories for a given prefix,
      * replacing any others previously set for this prefix.
      *
-     * @param string          $prefix The prefix
-     * @param string[]|string $paths  The PSR-0 base directories
+     * @param string              $prefix The prefix
+     * @param list<string>|string $paths  The PSR-0 base directories
      *
      * @return void
      */
@@ -290,8 +288,8 @@ class ClassLoader
      * Registers a set of PSR-4 directories for a given namespace,
      * replacing any others previously set for this namespace.
      *
-     * @param string          $prefix The prefix/namespace, with trailing '\\'
-     * @param string[]|string $paths  The PSR-4 base directories
+     * @param string              $prefix The prefix/namespace, with trailing '\\'
+     * @param list<string>|string $paths  The PSR-4 base directories
      *
      * @throws \InvalidArgumentException
      *
@@ -425,7 +423,8 @@ class ClassLoader
     public function loadClass($class)
     {
         if ($file = $this->findFile($class)) {
-            includeFile($file);
+            $includeFile = self::$includeFile;
+            $includeFile($file);
 
             return true;
         }
@@ -476,9 +475,9 @@ class ClassLoader
     }
 
     /**
-     * Returns the currently registered loaders indexed by their corresponding vendor directories.
+     * Returns the currently registered loaders keyed by their corresponding vendor directories.
      *
-     * @return self[]
+     * @return array<string, self>
      */
     public static function getRegisteredLoaders()
     {
@@ -555,18 +554,26 @@ class ClassLoader
 
         return false;
     }
-}
 
-/**
- * Scope isolated include.
- *
- * Prevents access to $this/self from included files.
- *
- * @param  string $file
- * @return void
- * @private
- */
-function includeFile($file)
-{
-    include $file;
+    /**
+     * @return void
+     */
+    private static function initializeIncludeClosure()
+    {
+        if (self::$includeFile !== null) {
+            return;
+        }
+
+        /**
+         * Scope isolated include.
+         *
+         * Prevents access to $this/self from included files.
+         *
+         * @param  string $file
+         * @return void
+         */
+        self::$includeFile = \Closure::bind(static function($file) {
+            include $file;
+        }, null, null);
+    }
 }
diff --git a/vendor/composer/InstalledVersions.php b/vendor/composer/InstalledVersions.php
index c6b54af..51e734a 100644
--- a/vendor/composer/InstalledVersions.php
+++ b/vendor/composer/InstalledVersions.php
@@ -98,7 +98,7 @@ class InstalledVersions
     {
         foreach (self::getInstalled() as $installed) {
             if (isset($installed['versions'][$packageName])) {
-                return $includeDevRequirements || empty($installed['versions'][$packageName]['dev_requirement']);
+                return $includeDevRequirements || !isset($installed['versions'][$packageName]['dev_requirement']) || $installed['versions'][$packageName]['dev_requirement'] === false;
             }
         }
 
@@ -119,7 +119,7 @@ class InstalledVersions
      */
     public static function satisfies(VersionParser $parser, $packageName, $constraint)
     {
-        $constraint = $parser->parseConstraints($constraint);
+        $constraint = $parser->parseConstraints((string) $constraint);
         $provided = $parser->parseConstraints(self::getVersionRanges($packageName));
 
         return $provided->matches($constraint);
@@ -328,7 +328,9 @@ class InstalledVersions
                 if (isset(self::$installedByVendor[$vendorDir])) {
                     $installed[] = self::$installedByVendor[$vendorDir];
                 } elseif (is_file($vendorDir.'/composer/installed.php')) {
-                    $installed[] = self::$installedByVendor[$vendorDir] = require $vendorDir.'/composer/installed.php';
+                    /** @var array{root: array{name: string, pretty_version: string, version: string, reference: string|null, type: string, install_path: string, aliases: string[], dev: bool}, versions: array<string, array{pretty_version?: string, version?: string, reference?: string|null, type?: string, install_path?: string, aliases?: string[], dev_requirement: bool, replaced?: string[], provided?: string[]}>} $required */
+                    $required = require $vendorDir.'/composer/installed.php';
+                    $installed[] = self::$installedByVendor[$vendorDir] = $required;
                     if (null === self::$installed && strtr($vendorDir.'/composer', '\\', '/') === strtr(__DIR__, '\\', '/')) {
                         self::$installed = $installed[count($installed) - 1];
                     }
@@ -340,12 +342,17 @@ class InstalledVersions
             // only require the installed.php file if this file is loaded from its dumped location,
             // and not from its source location in the composer/composer package, see https://github.com/composer/composer/issues/9937
             if (substr(__DIR__, -8, 1) !== 'C') {
-                self::$installed = require __DIR__ . '/installed.php';
+                /** @var array{root: array{name: string, pretty_version: string, version: string, reference: string|null, type: string, install_path: string, aliases: string[], dev: bool}, versions: array<string, array{pretty_version?: string, version?: string, reference?: string|null, type?: string, install_path?: string, aliases?: string[], dev_requirement: bool, replaced?: string[], provided?: string[]}>} $required */
+                $required = require __DIR__ . '/installed.php';
+                self::$installed = $required;
             } else {
                 self::$installed = array();
             }
         }
-        $installed[] = self::$installed;
+
+        if (self::$installed !== array()) {
+            $installed[] = self::$installed;
+        }
 
         return $installed;
     }
diff --git a/vendor/composer/autoload_real.php b/vendor/composer/autoload_real.php
index 0ab935b..63b0d87 100644
--- a/vendor/composer/autoload_real.php
+++ b/vendor/composer/autoload_real.php
@@ -22,8 +22,6 @@ class ComposerAutoloaderInitb44cc79a0eaef9cd9c2f2ac697cbe9c0
             return self::$loader;
         }
 
-        require __DIR__ . '/platform_check.php';
-
         spl_autoload_register(array('ComposerAutoloaderInitb44cc79a0eaef9cd9c2f2ac697cbe9c0', 'loadClassLoader'), true, true);
         self::$loader = $loader = new \Composer\Autoload\ClassLoader(\dirname(__DIR__));
         spl_autoload_unregister(array('ComposerAutoloaderInitb44cc79a0eaef9cd9c2f2ac697cbe9c0', 'loadClassLoader'));
diff --git a/vendor/composer/installed.json b/vendor/composer/installed.json
index 9e3c8f6..df421eb 100644
--- a/vendor/composer/installed.json
+++ b/vendor/composer/installed.json
@@ -7,7 +7,7 @@
             "source": {
                 "type": "git",
                 "url": "https://dev.tt-rss.org/fox/readability-php.git",
-                "reference": "8ac5abdd497b37d2be4833bcf18d6819bba4d9c9"
+                "reference": "37c0c2ce76aa90e8adafbd5cb0b0332a54df1523"
             },
             "require": {
                 "ext-dom": "*",
@@ -25,7 +25,7 @@
             "suggest": {
                 "monolog/monolog": "Allow logging debug information"
             },
-            "time": "2022-07-31T06:02:47+00:00",
+            "time": "2024-04-03T17:38:00+00:00",
             "default-branch": true,
             "type": "library",
             "installation-source": "source",
diff --git a/vendor/composer/installed.php b/vendor/composer/installed.php
index 165891d..f929588 100644
--- a/vendor/composer/installed.php
+++ b/vendor/composer/installed.php
@@ -1,9 +1,9 @@
 <?php return array(
     'root' => array(
         'name' => '__root__',
-        'pretty_version' => '1.0.0+no-version-set',
-        'version' => '1.0.0.0',
-        'reference' => NULL,
+        'pretty_version' => 'dev-master',
+        'version' => 'dev-master',
+        'reference' => '684721a181377915e42c7a04c1a099be12eb4a38',
         'type' => 'library',
         'install_path' => __DIR__ . '/../../',
         'aliases' => array(),
@@ -11,9 +11,9 @@
     ),
     'versions' => array(
         '__root__' => array(
-            'pretty_version' => '1.0.0+no-version-set',
-            'version' => '1.0.0.0',
-            'reference' => NULL,
+            'pretty_version' => 'dev-master',
+            'version' => 'dev-master',
+            'reference' => '684721a181377915e42c7a04c1a099be12eb4a38',
             'type' => 'library',
             'install_path' => __DIR__ . '/../../',
             'aliases' => array(),
@@ -22,7 +22,7 @@
         'fivefilters/readability.php' => array(
             'pretty_version' => 'dev-master',
             'version' => 'dev-master',
-            'reference' => '8ac5abdd497b37d2be4833bcf18d6819bba4d9c9',
+            'reference' => '37c0c2ce76aa90e8adafbd5cb0b0332a54df1523',
             'type' => 'library',
             'install_path' => __DIR__ . '/../fivefilters/readability.php',
             'aliases' => array(
diff --git a/vendor/composer/platform_check.php b/vendor/composer/platform_check.php
deleted file mode 100644
index 580fa96..0000000
--- a/vendor/composer/platform_check.php
+++ /dev/null
@@ -1,26 +0,0 @@
-<?php
-
-// platform_check.php @generated by Composer
-
-$issues = array();
-
-if (!(PHP_VERSION_ID >= 70400)) {
-    $issues[] = 'Your Composer dependencies require a PHP version ">= 7.4.0". You are running ' . PHP_VERSION . '.';
-}
-
-if ($issues) {
-    if (!headers_sent()) {
-        header('HTTP/1.1 500 Internal Server Error');
-    }
-    if (!ini_get('display_errors')) {
-        if (PHP_SAPI === 'cli' || PHP_SAPI === 'phpdbg') {
-            fwrite(STDERR, 'Composer detected issues in your platform:' . PHP_EOL.PHP_EOL . implode(PHP_EOL, $issues) . PHP_EOL.PHP_EOL);
-        } elseif (!headers_sent()) {
-            echo 'Composer detected issues in your platform:' . PHP_EOL.PHP_EOL . str_replace('You are running '.PHP_VERSION.'.', '', implode(PHP_EOL, $issues)) . PHP_EOL.PHP_EOL;
-        }
-    }
-    trigger_error(
-        'Composer detected issues in your platform: ' . implode(' ', $issues),
-        E_USER_ERROR
-    );
-}
diff --git a/vendor/fivefilters/readability.php/README.md b/vendor/fivefilters/readability.php/README.md
index c910714..547178c 100644
--- a/vendor/fivefilters/readability.php/README.md
+++ b/vendor/fivefilters/readability.php/README.md
@@ -117,6 +117,7 @@ Then you pass this Configuration object to Readability. The following options ar
 - **KeepClasses**: default value `false`, which removes all `class="..."` attribute values from HTML elements.
 - **Parser**: default value `html5`, which uses HTML5-PHP for parsing. Set to `libxml` to use that instead (not recommended for modern HTML documents).
 - **SummonCthulhu**: default value `false`, remove all `<script>` nodes via regex. This is not ideal as it might break things, but if you've set the parser to libxml (see above), it might be the only solution to [libxml problems with unescaped javascript](https://github.com/fivefilters/readability.php#known-libxml-parsing-issues).
+- **ExtraIgnoredElements**: default value `[]`, additional DOM elements that should be ignored.  `noscript` and `script` are always ignored.
 
 ### Debug log
 
diff --git a/vendor/fivefilters/readability.php/src/Configuration.php b/vendor/fivefilters/readability.php/src/Configuration.php
index 6d1f03f..0659a82 100644
--- a/vendor/fivefilters/readability.php/src/Configuration.php
+++ b/vendor/fivefilters/readability.php/src/Configuration.php
@@ -84,6 +84,11 @@ class Configuration
     protected $disableJSONLD = false;
 
     /**
+     * @var array<string>
+     */
+    protected $extraIgnoredElements = [];
+
+    /**
      * Configuration constructor.
      *
      * @param array $params
@@ -420,4 +425,24 @@ class Configuration
 
         return $this;
     }
+
+    /**
+     * @return array<string>
+     */
+    public function getExtraIgnoredElements()
+    {
+        return $this->extraIgnoredElements;
+    }
+
+    /**
+     * @param array<string>
+     *
+     * @return $this
+     */
+    public function setExtraIgnoredElements($extraIgnoredElements)
+    {
+        $this->extraIgnoredElements = $extraIgnoredElements;
+
+        return $this;
+    }
 }
diff --git a/vendor/fivefilters/readability.php/src/Readability.php b/vendor/fivefilters/readability.php/src/Readability.php
index 6407a92..c5318a4 100644
--- a/vendor/fivefilters/readability.php/src/Readability.php
+++ b/vendor/fivefilters/readability.php/src/Readability.php
@@ -342,7 +342,7 @@ class Readability
         // Extract JSON-LD metadata before removing scripts
         $this->jsonld = $this->configuration->getDisableJSONLD() ? [] : $this->getJSONLD($dom);
 
-        $this->removeScripts($dom);
+        $this->removeIgnoredElements($dom);
 
         $this->prepDocument($dom);
 
@@ -1188,13 +1188,13 @@ class Readability
     }
 
     /**
-     * Removes all the scripts of the html.
+     * Removes elements that should be ignored.
      *
      * @param DOMDocument $dom
      */
-    private function removeScripts(DOMDocument $dom)
+    private function removeIgnoredElements(DOMDocument $dom)
     {
-        foreach (['script', 'noscript'] as $tag) {
+        foreach (['noscript', 'script', ...$this->configuration->getExtraIgnoredElements()] as $tag) {
             $nodes = $dom->getElementsByTagName($tag);
             foreach (iterator_to_array($nodes) as $node) {
                 NodeUtility::removeNode($node);