Changeset 58836 for trunk/tests/phpunit/tests/html-api/wpHtmlProcessorBreadcrumbs.php

Timestamp:

07/31/2024 04:54:23 PM (2 months ago)

Author:

dmsnell

Message:

HTML API: Introduce full parsing mode in HTML Processor.

The HTML Processor has only supported a specific kind of parsing mode
called _the fragment parsing mode_, where it behaves in the same way
that node.innerHTML = html does in the DOM. This mode assumes a
context node and doesn't support parsing an entire document.

As part of work to add more spec support to the HTML API, this patch
introduces a full parsing mode, which can parse a full HTML document
from start to end, including the doctype declaration and head tags.

Developed in ​https://github.com/wordpress/wordpress-develop/pull/6977
Discussed in https://core.trac.wordpress.org/ticket/61576

Props: dmsnell, jonsurrell.
See #61576.

File:

• trunk/tests/phpunit/tests/html-api/wpHtmlProcessorBreadcrumbs.php (modified) (7 diffs)

trunk/tests/phpunit/tests/html-api/wpHtmlProcessorBreadcrumbs.php

@@ -26 +26 @@
         $processor = WP_HTML_Processor::create_fragment( $html );
 
-        $this->assertTrue( $processor->step(), "Failed to step into supported {$tag_name} element." );
+        $this->assertTrue( $processor->next_token(), "Failed to step into supported {$tag_name} element." );
         $this->assertSame( $tag_name, $processor->get_tag(), "Misread {$tag_name} as a {$processor->get_tag()} element." );
     }
@@ -91 +91 @@
             'INS',
             'LI',
+            'LINK',
             'ISINDEX', // Deprecated.
             'KBD',
@@ -109 +110 @@
             'NEXTID', // Deprecated.
             'NOBR', // Neutralized.
+            'NOEMBED', // Neutralized.
+            'NOFRAMES', // Neutralized.
             'NOSCRIPT',
             'OBJECT',
@@ -123 +126 @@
             'RUBY',
             'SAMP',
+            'SCRIPT',
             'SEARCH',
             'SECTION',
@@ -131 +135 @@
             'STRIKE',
             'STRONG',
+            'STYLE',
             'SUB',
             'SUMMARY',
             'SUP',
             'TABLE',
+            'TEXTAREA',
             'TIME',
+            'TITLE',
             'TT',
             'U',
@@ -141 +148 @@
             'VAR',
             'VIDEO',
+            'XMP', // Deprecated, use PRE instead.
         );
 
         $data = array();
         foreach ( $supported_elements as $tag_name ) {
-            $data[ $tag_name ] = array( "<{$tag_name}>", $tag_name );
+            $closer = in_array( $tag_name, array( 'NOEMBED', 'NOFRAMES', 'SCRIPT', 'STYLE', 'TEXTAREA', 'TITLE', 'XMP' ), true )
+                ? "</{$tag_name}>"
+                : '';
+
+            $data[ $tag_name ] = array( "<{$tag_name}>{$closer}", $tag_name );
         }
 
@@ -183 +195 @@
     public static function data_unsupported_elements() {
         $unsupported_elements = array(
-            'BODY',
-            'FRAME',
-            'FRAMESET',
-            'HEAD',
-            'HTML',
-            'IFRAME',
             'MATH',
-            'NOEMBED', // Neutralized.
-            'NOFRAMES', // Neutralized.
             'PLAINTEXT', // Neutralized.
-            'SCRIPT',
-            'STYLE',
             'SVG',
-            'TEXTAREA',
-            'TITLE',
-            'XMP', // Deprecated, use PRE instead.
         );