ampproject · schlessera · Apr 9, 2021 · Mar 31, 2021 · Mar 31, 2021 · Mar 31, 2021
diff --git a/README.md b/README.md
@@ -144,6 +144,7 @@ Note that this only lets you check whether an error "category" popped up. It can
 | [`AmpRuntimeCss`](https://github.com/ampproject/amp-toolbox-php/blob/main/src/Optimizer/Transformer/AmpRuntimeCss.php) | Transformer adding `https://cdn.ampproject.org/v0.css` if server-side-rendering is applied (known by the presence of the `<style amp-runtime>` tag). AMP runtime css (`v0.css`) will always be inlined as it'll get automatically updated to the latest version once the AMP runtime has loaded. |
 | [`PreloadHeroImage`](https://github.com/ampproject/amp-toolbox-php/blob/main/src/Optimizer/Transformer/PreloadHeroImage.php) | Transformer that optimizes image rendering times for hero images by adding preload and serverside-rendered `<img>` tags when possible. Viable hero images are `<amp-img>` tags, `<amp-video>` tags with a `poster` attribute as well as `<amp-iframe>` and `<amnp-video-iframe>` tags with a `placeholder` attribute. The first viable image that is encountered is used by default, but this behavior can be overridden by adding the `data-hero` attribute to a maximum of two images. The preloads only work work images that don't use `srcset`, as that is not supported as a preload in most browsers. The serverside-rendered image will not be created for `<amp-video>` tags. |
 | [`ReorderHead`](https://github.com/ampproject/amp-toolbox-php/blob/main/src/Optimizer/Transformer/ReorderHead.php) | Transformer applying the head reordering transformations to the HTML input. `ReorderHead` reorders the children of `<head>`. Specifically, it orders the `<head>` like so:<br>(0) `<meta charset>` tag<br>(1) `<style amp-runtime>` (inserted by `AmpRuntimeCss`)<br>(2) remaining `<meta>` tags (those other than `<meta charset>`)<br>(3) AMP runtime `.js` `<script>` tag<br>(4) AMP viewer runtime `.js` `<script>`<br>(5) `<script>` tags that are render delaying<br>(6) `<script>` tags for remaining extensions<br>(7) `<link>` tag for favicons<br>(8) `<link>` tag for resource hints<br>(9) `<link rel=stylesheet>` tags before `<style amp-custom>`<br>(10) `<style amp-custom>`<br>(11) any other tags allowed in `<head>`<br>(12) AMP boilerplate (first `<style>` boilerplate, then `<noscript>`) |
+| [`RewriteAmpUrls`](https://github.com/ampproject/amp-toolbox-php/blob/main/src/Optimizer/Transformer/RewriteAmpUrls.php) | Transformer that rewrites AMP runtime URLs to decide what version of the runtime to use. This allows you to do such things as switching to the LTS version or disabling ES modules.|
 | [`ServerSideRendering`](https://github.com/ampproject/amp-toolbox-php/blob/main/src/Optimizer/Transformer/ServerSideRendering.php) | Transformer applying the server-side rendering transformations to the HTML input. This does immediately on the server what would normally be done on the client _after_ the runtime was downloaded and executed to process the DOM. As such, it allows for the removal of the boilerplate CSS that _hides_ the page while it has not yet been processed on the client, drastically improving time it takes for the First Contentful Paint (FCP).|
 | [`TransformedIdentifier`](https://github.com/ampproject/amp-toolbox-php/blob/main/src/Optimizer/Transformer/TransformedIdentifier.php) | Transformer applying the transformed identifier transformations to the HTML input. This is what marks an AMP document as "already optimized", so that the AMP runtime does not need to process it anymore. |
 

diff --git a/bin/sync-amp-toolbox-test-suite.php b/bin/sync-amp-toolbox-test-suite.php
@@ -70,7 +70,7 @@ function ensureDirExists($directory)
 for ($index = 0; $index < $zip->numFiles; $index++) {
     $archivedPath = $zip->statIndex($index)['name'];
 
-    if (substr($archivedPath, -5) !== '.html') {
+    if (substr($archivedPath, -5) !== '.html' && substr($archivedPath, -11) !== 'config.json') {
         continue;
     }
 

diff --git a/composer.json b/composer.json
@@ -6,6 +6,7 @@
   "require": {
     "php": "^5.6 || ^7.0 || ^8.0",
     "ext-dom": "*",
+    "ext-filter": "*",
     "ext-iconv": "*",
     "ext-json": "*",
     "ext-libxml": "*"

diff --git a/src/Amp.php b/src/Amp.php
@@ -150,8 +150,11 @@ public static function isRuntimeScript(DOMNode $node)
         }
 
         if (
+            // @TODO Compare performance against single regex.
             substr($src, -6) !== '/v0.js'
+            && substr($src, -7) !== '/v0.mjs'
             && substr($src, -14) !== '/amp4ads-v0.js'
+            && substr($src, -15) !== '/amp4ads-v0.mjs'
         ) {
             return false;
         }

diff --git a/src/Attribute.php b/src/Attribute.php
@@ -35,6 +35,7 @@ interface Attribute
     const CHARSET               = 'charset';
     const CLASS_                = 'class'; // Underscore needed because 'class' is a PHP keyword.
     const CONTENT               = 'content';
+    const CROSSORIGIN           = 'crossorigin';
     const CUSTOM_ELEMENT        = 'custom-element';
     const CUSTOM_TEMPLATE       = 'custom-template';
     const DECODING              = 'decoding';
@@ -59,6 +60,7 @@ interface Attribute
     const MEDIA                 = 'media';
     const NAME                  = 'name';
     const NOLOADING             = 'noloading';
+    const NOMODULE              = 'nomodule';
     const OBJECT_FIT            = 'object-fit';
     const OBJECT_POSITION       = 'object-position';
     const ON                    = 'on';
@@ -89,21 +91,25 @@ interface Attribute
     const TYPE_HTML       = 'text/html';
     const TYPE_JSON       = 'application/json';
     const TYPE_LD_JSON    = 'application/ld+json';
+    const TYPE_MODULE     = 'module';
     const TYPE_TEXT_PLAIN = 'text/plain';
 
-    const REL_AMPHTML      = 'amphtml';
-    const REL_CANONICAL    = 'canonical';
-    const REL_DNS_PREFETCH = 'dns-prefetch';
-    const REL_ICON         = 'icon';
-    const REL_NOAMPHTML    = 'noamphtml';
-    const REL_NOFOLLOW     = 'nofollow';
-    const REL_PRECONNECT   = 'preconnect';
-    const REL_PREFETCH     = 'prefetch';
-    const REL_PRELOAD      = 'preload';
-    const REL_PRERENDER    = 'prerender';
-    const REL_STYLESHEET   = 'stylesheet';
+    const REL_AMPHTML       = 'amphtml';
+    const REL_CANONICAL     = 'canonical';
+    const REL_DNS_PREFETCH  = 'dns-prefetch';
+    const REL_ICON          = 'icon';
+    const REL_MODULEPRELOAD = 'modulepreload';
+    const REL_NOAMPHTML     = 'noamphtml';
+    const REL_NOFOLLOW      = 'nofollow';
+    const REL_PRECONNECT    = 'preconnect';
+    const REL_PREFETCH      = 'prefetch';
+    const REL_PRELOAD       = 'preload';
+    const REL_PRERENDER     = 'prerender';
+    const REL_STYLESHEET    = 'stylesheet';
 
     const DATA_AMP_STORY_PLAYER_POSTER_IMG = 'data-amp-story-player-poster-img';
     const DATA_HERO                        = 'data-hero';
     const DATA_HERO_CANDIDATE              = 'data-hero-candidate';
+
+    const CROSSORIGIN_ANONYMOUS = 'anonymous';
 }
diff --git a/src/Dom/Document.php b/src/Dom/Document.php
@@ -346,6 +346,7 @@ public function __construct($version = '', $encoding = null)
         $this->originalEncoding = (string)$encoding ?: Encoding::UNKNOWN;
         parent::__construct($version ?: '1.0', Encoding::AMP);
         $this->registerNodeClass(DOMElement::class, Element::class);
+        $this->options = Option::DEFAULTS;
     }
 
     /**
@@ -500,7 +501,7 @@ public function loadHTMLFragment($source, $options = [])
             $options = [Option::LIBXML_FLAGS => $options];
         }
 
-        $this->options = array_merge(Option::DEFAULTS, $options);
+        $this->options = array_merge($this->options, $options);
 
         $this->reset();
 
@@ -2022,7 +2023,7 @@ public function __get($name)
         }
 
         // Mimic regular PHP behavior for missing notices.
-        trigger_error(self::PROPERTY_GETTER_ERROR_MESSAGE . $name, E_USER_NOTICE); // phpcs:ignore WordPress.PHP.DevelopmentFunctions,WordPress.Security.EscapeOutput,Generic.Files.LineLength.TooLong
+        trigger_error(self::PROPERTY_GETTER_ERROR_MESSAGE . $name, E_USER_NOTICE);
         return null;
     }
 
@@ -2059,6 +2060,32 @@ public function createElement($name, $value = null)
         return $element;
     }
 
+    /**
+     * Create new element node.
+     *
+     * @link https://php.net/manual/domdocument.createelement.php
+     *
+     * This override only serves to provide the correct object type-hint for our extended Dom/Element class.
+     *
+     * @param string $name       The tag name of the element.
+     * @param array  $attributes Attributes to add to the newly created element.
+     * @param string $value      Optional. The value of the element. By default, an empty element will be created.
+     *                           You can also set the value later with Element->nodeValue.
+     * @return Element|false A new instance of class Element or false if an error occurred.
+     */
+    public function createElementWithAttributes($name, $attributes, $value = null)
+    {
+        $element = parent::createElement($name, $value);
+
+        if (!$element instanceof Element) {
+            return false;
+        }
+
+        $element->addAttributes($attributes);
+
+        return $element;
+    }
+
     /**
      * Check whether the CSS maximum byte count is enforced.
      *
@@ -2074,7 +2101,7 @@ public function isCssMaxByteCountEnforced()
      *
      * @param int $maxByteCount Maximum number of bytes to limit the CSS to. A negative number disables the limit.
      */
-    public function enforceCssMaxByteCount($maxByteCount = AMP::MAX_CSS_BYTE_COUNT)
+    public function enforceCssMaxByteCount($maxByteCount = Amp::MAX_CSS_BYTE_COUNT)
     {
         $this->cssMaxByteCountEnforced = $maxByteCount;
     }

diff --git a/src/Dom/Element.php b/src/Dom/Element.php
@@ -7,6 +7,7 @@
 use AmpProject\Optimizer\CssRule;
 use DOMAttr;
 use DOMElement;
+use DOMException;
 
 /**
  * Class AmpProject\Dom\Element.
@@ -19,6 +20,20 @@
 final class Element extends DOMElement
 {
 
+    /**
+     * Regular expression pattern to match events and actions within an 'on' attribute.
+     *
+     * @var string
+     */
+    const AMP_EVENT_ACTIONS_REGEX_PATTERN = '/((?<event>[^:;]+):(?<actions>(?:[^;,\(]+(?:\([^\)]+\))?,?)+))+?/';
+
+    /**
+     * Regular expression pattern to match individual actions within an event.
+     *
+     * @var string
+     */
+    const AMP_ACTION_REGEX_PATTERN = '/(?<action>[^(),\s]+(?:\([^\)]+\))?)+/';
+
     /**
      * Error message to use when the __get() is triggered for an unknown property.
      *
@@ -77,6 +92,170 @@ public function setAttribute($name, $value)
         return parent::setAttribute($name, $value);
     }
 
+    /**
+     * Adds a boolean attribute without value.
+     *
+     * @param string $name  The name of the attribute.
+     * @return DOMAttr|false The new or modified DOMAttr or false if an error occurred.
+     * @throws MaxCssByteCountExceeded If the allowed max byte count is exceeded.
+     */
+    public function addBooleanAttribute($name)
+    {
+        $attribute = new DOMAttr($name);
+        $result    = $this->setAttributeNode($attribute);
+
+        if (!$result instanceof DOMAttr) {
+            return false;
+        }
+
+        return $result;
+    }
+
+    /**
+     * Copy one or more attributes from this element to another element.
+     *
+     * @param array|string $attributes       Attribute name or array of attribute names to copy.
+     * @param Element      $target           Target Dom\Element to copy the attributes to.
+     * @param string       $defaultSeparator Default separator to use for multiple values if the attribute is not known.
+     */
+    public function copyAttributes($attributes, Element $target, $defaultSeparator = ',')
+    {
+        foreach ((array) $attributes as $attribute) {
+            if ($this->hasAttribute($attribute)) {
+                $values = $this->getAttribute($attribute);
+                if ($target->hasAttribute($attribute)) {
+                    switch ($attribute) {
+                        case Attribute::ON:
+                            $values = self::mergeAmpActions($target->getAttribute($attribute), $values);
+                            break;
+                        case Attribute::CLASS_:
+                            $values = $target->getAttribute($attribute) . ' ' . $values;
+                            break;
+                        default:
+                            $values = $target->getAttribute($attribute) . $defaultSeparator . $values;
+                    }
+                }
+                $target->setAttribute($attribute, $values);
+            }
+        }
+    }
+
+    /**
+     * Register an AMP action to an event.
+     *
+     * If the element already contains one or more events or actions, the method
+     * will assemble them in a smart way.
+     *
+     * @param string $event  Event to trigger the action on.
+     * @param string $action Action to add.
+     */
+    public function addAmpAction($event, $action)
+    {
+        $eventActionString = "{$event}:{$action}";
+
+        if (! $this->hasAttribute(Attribute::ON)) {
+            // There's no "on" attribute yet, so just add it and be done.
+            $this->setAttribute(Attribute::ON, $eventActionString);
+            return;
+        }
+
+        $this->setAttribute(
+            Attribute::ON,
+            self::mergeAmpActions(
+                $this->getAttribute(Attribute::ON),
+                $eventActionString
+            )
+        );
+    }
+
+    /**
+     * Merge two sets of AMP events & actions.
+     *
+     * @param string $first  First event/action string.
+     * @param string $second First event/action string.
+     * @return string Merged event/action string.
+     */
+    public static function mergeAmpActions($first, $second)
+    {
+        $events = [];
+        foreach ([$first, $second] as $eventActionString) {
+            $matches = [];
+            $results = preg_match_all(self::AMP_EVENT_ACTIONS_REGEX_PATTERN, $eventActionString, $matches);
+
+            if (! $results || ! isset($matches['event'])) {
+                continue;
+            }
+
+            foreach ($matches['event'] as $index => $event) {
+                $events[$event][] = $matches['actions'][ $index ];
+            }
+        }
+
+        $valueStrings = [];
+        foreach ($events as $event => $actionStringsArray) {
+            $actionsArray = [];
+            array_walk(
+                $actionStringsArray,
+                static function ($actions) use (&$actionsArray) {
+                    $matches = [];
+                    $results = preg_match_all(self::AMP_ACTION_REGEX_PATTERN, $actions, $matches);
+
+                    if (! $results || ! isset($matches['action'])) {
+                        $actionsArray[] = $actions;
+                        return;
+                    }
+
+                    $actionsArray = array_merge($actionsArray, $matches['action']);
+                }
+            );
+
+            $actions         = implode(',', array_unique(array_filter($actionsArray)));
+            $valueStrings[] = "{$event}:{$actions}";
+        }
+
+        return implode(';', $valueStrings);
+    }
+
+    /**
+     * Extract this element's HTML attributes and return as an associative array.
+     *
+     * @return string[] The attributes for the passed node, or an empty array if it has no attributes.
+     */
+    public function getAttributesAsAssocArray()
+    {
+        $attributes = [];
+        if (! $this->hasAttributes()) {
+            return $attributes;
+        }
+
+        foreach ($this->attributes as $attribute) {
+            $attributes[ $attribute->nodeName ] = $attribute->nodeValue;
+        }
+
+        return $attributes;
+    }
+
+    /**
+     * Add one or more HTML element attributes to this element.
+     *
+     * @param string[] $attributes One or more attributes for the node's HTML element.
+     */
+    public function addAttributes($attributes)
+    {
+        foreach ($attributes as $name => $value) {
+            try {
+                $this->setAttribute($name, $value);
+            } catch (DOMException $e) {
+                /*
+                 * Catch a "Invalid Character Error" when libxml is able to parse attributes with invalid characters,
+                 * but it throws error when attempting to set them via DOM methods. For example, '...this' can be parsed
+                 * as an attribute but it will throw an exception when attempting to setAttribute().
+                 */
+                continue;
+            }
+        }
+    }
+
     /**
      * Magic getter to implement lazily-created, cached properties for the element.
      *
@@ -95,10 +274,7 @@ public function __get($name)
         }
 
         // Mimic regular PHP behavior for missing notices.
-        trigger_error(
-            self::PROPERTY_GETTER_ERROR_MESSAGE . $name,
-            E_USER_NOTICE
-        ); // phpcs:ignore WordPress.PHP.DevelopmentFunctions,WordPress.Security.EscapeOutput,Generic.Files.LineLength.TooLong
+        trigger_error(self::PROPERTY_GETTER_ERROR_MESSAGE . $name, E_USER_NOTICE);
 
         return null;
     }

diff --git a/src/Exception/FailedToGetCachedResponse.php b/src/Exception/FailedToGetCachedResponse.php
@@ -13,7 +13,7 @@ final class FailedToGetCachedResponse extends RuntimeException implements Failed
 {
 
     /**
-     * Instantiate a FailedToGetCachedResponseData exception for a URL if the cached response data could not be
+     * Instantiate a FailedToGetCachedResponse exception for a URL if the cached response data could not be
      * retrieved.
      *
      * @param string $url URL that failed to be fetched.