HTML-API: Introduce minimal HTML Processor.

Author: dmsnell

src/wp-includes/html-api/class-wp-html-active-formatting-elements.php

@@ -0,0 +1,185 @@
+<?php
+/**
+ * HTML API: WP_HTML_Active_Formatting_Elements class
+ *
+ * @package WordPress
+ * @subpackage HTML-API
+ * @since {WP_VERSION}
+ */
+
+/**
+ * Core class used by the HTML processor during HTML parsing
+ * for managing the stack of active formatting elements.
+ *
+ * This class is designed for internal use by the HTML processor.
+ *
+ * > Initially, the list of active formatting elements is empty.
+ * > It is used to handle mis-nested formatting element tags.
+ * >
+ * > The list contains elements in the formatting category, and markers.
+ * > The markers are inserted when entering applet, object, marquee,
+ * > template, td, th, and caption elements, and are used to prevent
+ * > formatting from "leaking" into applet, object, marquee, template,
+ * > td, th, and caption elements.
+ * >
+ * > In addition, each element in the list of active formatting elements
+ * > is associated with the token for which it was created, so that
+ * > further elements can be created for that token if necessary.
+ *
+ * @since {WP_VERSION}
+ *
+ * @access private
+ *
+ * @see https://html.spec.whatwg.org/#list-of-active-formatting-elements
+ * @see WP_HTML_Processor
+ */
+class WP_HTML_Active_Formatting_Elements {
+	/**
+	 * Holds the stack of active formatting element references.
+	 *
+	 * @since {WP_VERSION}
+	 *
+	 * @var WP_HTML_Token[]
+	 */
+	private $stack = array();
+
+	/**
+	 * Reports if a specific node is in the stack of active formatting elements.
+	 *
+	 * @since {WP_VERSION}
+	 *
+	 * @param WP_HTML_Token $token Look for this node in the stack.
+	 * @return bool Whether the referenced node is in the stack of active formatting elements.
+	 *
+	 */
+	public function contains_node( $token ) {
+		foreach ( $this->walk_up() as $item ) {
+			if ( $token->bookmark_name === $item->bookmark_name ) {
+				return true;
+			}
+		}
+
+		return false;
+	}
+
+	/**
+	 * Returns how many nodes are currently in the stack of active formatting elements.
+	 *
+	 * @since {WP_VERSION}
+	 *
+	 * @return int How many node are in the stack of active formatting elements.
+	 */
+	public function count() {
+		return count( $this->stack );
+	}
+
+	/**
+	 * Returns the node at the end of the stack of active formatting elements,
+	 * if one exists. If the stack is empty, returns null.
+	 *
+	 * @since {WP_VERSION}
+	 *
+	 * @return WP_HTML_Token|null Last node in the stack of active formatting elements, if one exists, otherwise null.
+	 */
+	public function current_node() {
+		$current_node = end( $this->stack );
+
+		return $current_node ? $current_node : null;
+	}
+
+	/**
+	 * Pushes a node onto the stack of active formatting elements.
+	 *
+	 * @since {WP_VERSION}
+	 *
+	 * @see https://html.spec.whatwg.org/#push-onto-the-list-of-active-formatting-elements
+	 *
+	 * @param WP_HTML_Token $token Push this node onto the stack.
+	 */
+	public function push( $token ) {
+		defined( 'DEBUG' ) && printf( "Pushing \e[31m{$token->node_name}\e[m element onto Active stack at \e[35m{$token->bookmark_name}\e[m\n" );
+
+		/*
+		 * > If there are already three elements in the list of active formatting elements after the last marker,
+		 * > if any, or anywhere in the list if there are no markers, that have the same tag name, namespace, and
+		 * > attributes as element, then remove the earliest such element from the list of active formatting
+		 * > elements. For these purposes, the attributes must be compared as they were when the elements were
+		 * > created by the parser; two elements have the same attributes if all their parsed attributes can be
+		 * > paired such that the two attributes in each pair have identical names, namespaces, and values
+		 * > (the order of the attributes does not matter).
+		 *
+		 * @TODO: Implement the "Noah's Ark clause" to only add up to three of any given kind of formatting elements to the stack.
+		 */
+
+		// > Add element to the list of active formatting elements.
+		$this->stack[] = $token;
+	}
+
+	/**
+	 * Removes a node from the stack of active formatting elements.
+	 *
+	 * @since {WP_VERSION}
+	 *
+	 * @param WP_HTML_Token $token Remove this node from the stack, if it's there already.
+	 */
+	public function remove_node( $token ) {
+		foreach ( $this->walk_up() as $position => $item ) {
+			if ( $token->bookmark_name === $item->bookmark_name ) {
+				array_splice( $this->stack, $this->count() - $position - 1, 1 );
+				return;
+			}
+		}
+	}
+
+	/**
+	 * Step through the stack of active formatting elements, starting with the
+	 * top element (added first) and walking downwards to the one added last.
+	 *
+	 * This generator function is designed to be used inside a "foreach" loop.
+	 *
+	 * Example:
+	 *
+	 *     $html = '<em><strong><a>We are here';
+	 *     foreach ( $stack->walk_down() as $node ) {
+	 *         echo "{$node->node_name} -> ";
+	 *     }
+	 *     > EM -> STRONG -> A ->
+	 *
+	 * To start with the most-recently added element and walk towards the top,
+	 * @see WP_HTML_Active_Formatting_Elements::walk_up
+	 *
+	 * @since {WP_VERSION}
+	 */
+	public function walk_down() {
+		$count = count( $this->stack );
+
+		for ( $i = 0; $i < $count; $i++ ) {
+			yield $this->stack[ $i ];
+		}
+	}
+
+	/**
+	 * Step through the stack of active formatting elements, starting with the
+	 * bottom element (added last) and walking upwards to the one added first.
+	 *
+	 * This generator function is designed to be used inside a "foreach" loop.
+	 *
+	 * Example:
+	 *
+	 *     $html = '<em><strong><a>We are here';
+	 *     foreach ( $stack->walk_up() as $node ) {
+	 *         echo "{$node->node_name} -> ";
+	 *     }
+	 *     > A -> STRONG -> EM ->
+	 *
+	 * To start with the first added element and walk towards the bottom,
+	 * @see WP_HTML_Active_Formatting_Elements::walk_down
+	 *
+	 * @since {WP_VERSION}
+	 */
+	public function walk_up() {
+		for ( $i = count( $this->stack ) - 1; $i >= 0; $i-- ) {
+			yield $this->stack[ $i ];
+		}
+	}
+}