Introduce HTML API with HTML Tag Processor

This commit pulls in the HTML Tag Processor from the Gutenbeg repository.

The Tag Processor attempts to be an HTML5-spec-compliant parser that provides the ability in PHP to find specific HTML tags and then add, remove, or update attributes on that tag. It provides a safe and reliable way to modify the attribute on HTML tags.

More information: WordPress/wordpress-develop#3920.

Props: antonvlasenko, bernhard-reiter, costdev, dmsnell, felixarntz, gziolo, hellofromtonya, zieladam, flixos90, ntsekouras, peterwilsoncc, swissspidy, andrewserong, onemaggie, get_dave, aristath, scruffian, justlevine, andraganescu, noisysocks, dlh, soean, cbirdsong, revgeorge, azaozz.
Fixes #57575.
Built from https://develop.svn.wordpress.org/trunk@55203


git-svn-id: http://core.svn.wordpress.org/trunk@54736 1a063a9b-81f0-0310-95a4-ce76da25c4cd

wp-includes/html-api/class-wp-html-attribute-token.php

@@ -0,0 +1,89 @@
+<?php
+/**
+ * HTML Tag Processor: Attribute token structure class.
+ *
+ * @package WordPress
+ * @subpackage HTML-API
+ * @since 6.2.0
+ */
+
+/**
+ * Data structure for the attribute token that allows to drastically improve performance.
+ *
+ * This class is for internal usage of the WP_HTML_Tag_Processor class.
+ *
+ * @access private
+ * @since 6.2.0
+ *
+ * @see WP_HTML_Tag_Processor
+ */
+class WP_HTML_Attribute_Token {
+	/**
+	 * Attribute name.
+	 *
+	 * @since 6.2.0
+	 * @var string
+	 */
+	public $name;
+
+	/**
+	 * Attribute value.
+	 *
+	 * @since 6.2.0
+	 * @var int
+	 */
+	public $value_starts_at;
+
+	/**
+	 * How many bytes the value occupies in the input HTML.
+	 *
+	 * @since 6.2.0
+	 * @var int
+	 */
+	public $value_length;
+
+	/**
+	 * The string offset where the attribute name starts.
+	 *
+	 * @since 6.2.0
+	 * @var int
+	 */
+	public $start;
+
+	/**
+	 * The string offset after the attribute value or its name.
+	 *
+	 * @since 6.2.0
+	 * @var int
+	 */
+	public $end;
+
+	/**
+	 * Whether the attribute is a boolean attribute with value `true`.
+	 *
+	 * @since 6.2.0
+	 * @var bool
+	 */
+	public $is_true;
+
+	/**
+	 * Constructor.
+	 *
+	 * @since 6.2.0
+	 *
+	 * @param string $name         Attribute name.
+	 * @param int    $value_start  Attribute value.
+	 * @param int    $value_length Number of bytes attribute value spans.
+	 * @param int    $start        The string offset where the attribute name starts.
+	 * @param int    $end          The string offset after the attribute value or its name.
+	 * @param bool   $is_true      Whether the attribute is a boolean attribute with true value.
+	 */
+	public function __construct( $name, $value_start, $value_length, $start, $end, $is_true ) {
+		$this->name            = $name;
+		$this->value_starts_at = $value_start;
+		$this->value_length    = $value_length;
+		$this->start           = $start;
+		$this->end             = $end;
+		$this->is_true         = $is_true;
+	}
+}

wp-includes/html-api/class-wp-html-span.php

@@ -0,0 +1,52 @@
+<?php
+/**
+ * HTML Span: Represents a textual span inside an HTML document.
+ *
+ * @package WordPress
+ * @subpackage HTML-API
+ * @since 6.2.0
+ */
+
+/**
+ * Represents a textual span inside an HTML document.
+ *
+ * This is a two-tuple in disguise, used to avoid the memory
+ * overhead involved in using an array for the same purpose.
+ *
+ * This class is for internal usage of the WP_HTML_Tag_Processor class.
+ *
+ * @access private
+ * @since 6.2.0
+ *
+ * @see WP_HTML_Tag_Processor
+ */
+class WP_HTML_Span {
+	/**
+	 * Byte offset into document where span begins.
+	 *
+	 * @since 6.2.0
+	 * @var int
+	 */
+	public $start;
+
+	/**
+	 * Byte offset into document where span ends.
+	 *
+	 * @since 6.2.0
+	 * @var int
+	 */
+	public $end;
+
+	/**
+	 * Constructor.
+	 *
+	 * @since 6.2.0
+	 *
+	 * @param int $start Byte offset into document where replacement span begins.
+	 * @param int $end   Byte offset into document where replacement span ends.
+	 */
+	public function __construct( $start, $end ) {
+		$this->start = $start;
+		$this->end   = $end;
+	}
+}