From 78ef4f749e7be502828c647f22a29fdfc91df879 Mon Sep 17 00:00:00 2001
From: Dennis Snell <dmsnell@git.wordpress.org>
Date: Wed, 24 Jan 2024 03:28:27 +0000
Subject: [PATCH] HTML API: Support INPUT tags.

Adds support for the following HTML elements to the HTML Processor:

 - INPUT

Previously this element was not supported and the HTML Processor would bail when encountering one. Now, with this patch applied, it will proceed to parse the HTML document.

Developed in https://github.com/WordPress/wordpress-develop/pull/5907
Discussed in https://core.trac.wordpress.org/ticket/60283

Props jonsurrell
See #60283



git-svn-id: https://develop.svn.wordpress.org/trunk@57343 602fd350-edb4-49c9-b593-d223f7449a82
---
 .../html-api/class-wp-html-processor.php      | 28 +++++++++++++++----
 .../tests/html-api/wpHtmlProcessor.php        |  1 -
 .../html-api/wpHtmlProcessorBreadcrumbs.php   |  1 -
 3 files changed, 22 insertions(+), 8 deletions(-)

diff --git a/src/wp-includes/html-api/class-wp-html-processor.php b/src/wp-includes/html-api/class-wp-html-processor.php
index f0c3b27b28..8a3f981ae6 100644
--- a/src/wp-includes/html-api/class-wp-html-processor.php
+++ b/src/wp-includes/html-api/class-wp-html-processor.php
@@ -101,18 +101,18 @@
  *
  *  - Containers: ADDRESS, BLOCKQUOTE, DETAILS, DIALOG, DIV, FOOTER, HEADER, MAIN, MENU, SPAN, SUMMARY.
  *  - Custom elements: All custom elements are supported. :)
- *  - Form elements: BUTTON, DATALIST, FIELDSET, LABEL, LEGEND, METER, PROGRESS, SEARCH.
+ *  - Form elements: BUTTON, DATALIST, FIELDSET, INPUT, LABEL, LEGEND, METER, PROGRESS, SEARCH.
  *  - Formatting elements: B, BIG, CODE, EM, FONT, I, PRE, SMALL, STRIKE, STRONG, TT, U, WBR.
  *  - Heading elements: H1, H2, H3, H4, H5, H6, HGROUP.
  *  - Links: A.
- *  - Lists: DD, DL, DT, LI, OL, LI.
- *  - Media elements: AUDIO, CANVAS, EMBED, FIGCAPTION, FIGURE, IMG, MAP, PARAM, PICTURE, SOURCE, VIDEO, TRACK.
+ *  - Lists: DD, DL, DT, LI, OL, UL.
+ *  - Media elements: AUDIO, CANVAS, EMBED, FIGCAPTION, FIGURE, IMG, MAP, PICTURE, SOURCE, TRACK, VIDEO.
  *  - Paragraph: BR, P.
- *  - Phrasing elements: AREA, ABBR, BDI, BDO, CITE, DATA, DEL, DFN, INS, MARK, OUTPUT, Q, SAMP, SUB, SUP, TIME, VAR.
+ *  - Phrasing elements: ABBR, AREA, BDI, BDO, CITE, DATA, DEL, DFN, INS, MARK, OUTPUT, Q, SAMP, SUB, SUP, TIME, VAR.
  *  - Sectioning elements: ARTICLE, ASIDE, HR, NAV, SECTION.
  *  - Templating elements: SLOT.
  *  - Text decoration: RUBY.
- *  - Deprecated elements: ACRONYM, BLINK, CENTER, DIR, ISINDEX, KEYGEN, LISTING, MULTICOL, NEXTID, SPACER.
+ *  - Deprecated elements: ACRONYM, BLINK, CENTER, DIR, ISINDEX, KEYGEN, LISTING, MULTICOL, NEXTID, PARAM, SPACER.
  *
  * ### Supported markup
  *
@@ -972,6 +972,23 @@ class WP_HTML_Processor extends WP_HTML_Tag_Processor {
 				$this->state->frameset_ok = false;
 				return true;
 
+			/*
+			 * > A start tag whose tag name is "input"
+			 */
+			case '+INPUT':
+				$this->reconstruct_active_formatting_elements();
+				$this->insert_html_element( $this->state->current_token );
+				$type_attribute = $this->get_attribute( 'type' );
+				/*
+				 * > If the token does not have an attribute with the name "type", or if it does,
+				 * > but that attribute's value is not an ASCII case-insensitive match for the
+				 * > string "hidden", then: set the frameset-ok flag to "not ok".
+				 */
+				if ( ! is_string( $type_attribute ) || 'hidden' !== strtolower( $type_attribute ) ) {
+					$this->state->frameset_ok = false;
+				}
+				return true;
+
 			/*
 			 * > A start tag whose tag name is "hr"
 			 */
@@ -1024,7 +1041,6 @@ class WP_HTML_Processor extends WP_HTML_Tag_Processor {
 			case 'HEAD':
 			case 'HTML':
 			case 'IFRAME':
-			case 'INPUT':
 			case 'LINK':
 			case 'MARQUEE':
 			case 'MATH':
diff --git a/tests/phpunit/tests/html-api/wpHtmlProcessor.php b/tests/phpunit/tests/html-api/wpHtmlProcessor.php
index 232fecebf8..109f384e25 100644
--- a/tests/phpunit/tests/html-api/wpHtmlProcessor.php
+++ b/tests/phpunit/tests/html-api/wpHtmlProcessor.php
@@ -253,7 +253,6 @@ class Tests_HtmlApi_WpHtmlProcessor extends WP_UnitTestCase {
 			'HEAD'      => array( 'HEAD' ),
 			'HTML'      => array( 'HTML' ),
 			'IFRAME'    => array( 'IFRAME' ),
-			'INPUT'     => array( 'INPUT' ),
 			'LINK'      => array( 'LINK' ),
 			'MARQUEE'   => array( 'MARQUEE' ),
 			'MATH'      => array( 'MATH' ),
diff --git a/tests/phpunit/tests/html-api/wpHtmlProcessorBreadcrumbs.php b/tests/phpunit/tests/html-api/wpHtmlProcessorBreadcrumbs.php
index b9d567fbeb..af3df4a3e6 100644
--- a/tests/phpunit/tests/html-api/wpHtmlProcessorBreadcrumbs.php
+++ b/tests/phpunit/tests/html-api/wpHtmlProcessorBreadcrumbs.php
@@ -180,7 +180,6 @@ class Tests_HtmlApi_WpHtmlProcessorBreadcrumbs extends WP_UnitTestCase {
 			'HEAD',
 			'HTML',
 			'IFRAME',
-			'INPUT',
 			'LINK',
 			'MARQUEE', // Deprecated.
 			'MATH',