Remove support for CDATA sections.

Author: dmsnell

src/wp-includes/html-api/class-wp-html-tag-processor.php

@@ -313,8 +313,7 @@
  *  - Comment nodes and nodes that became comments because of some syntax error. The
  *    text for these nodes is the portion of the comment inside of the syntax. E.g. for
  *    `<!-- comment -->` the text is `" comment "` (note that the spaces are part of it).
- *  - `CDATA` sections, whose text is the content inside of the section itself. E.g. for
- *    `<![CDATA[some content]]>` the text is `"some content"`.
+ *    For `<![CDATA[some content]]>` the text is `"[CDATA[some content]]"`.
  *  - "Funky comments," which are a special case of invalid closing tags whose name is
  *    invalid. The text for these nodes is the text that a browser would transform into
  *    an HTML when parsing. E.g. for `</%post_author>` the text is `%post_author`.
@@ -481,7 +480,6 @@ class WP_HTML_Tag_Processor {
 	 * | *Incomplete*    | The HTML ended in the middle of a token; nothing more can be parsed. |
 	 * | *Matched tag*   | Found an HTML tag; it's possible to modify its attributes.           |
 	 * | *Text node*     | Found a #text node; this is plaintext and modifiable.                |
-	 * | *CDATA node*    | Found a CDATA section; this is modifiable.                           |
 	 * | *Comment*       | Found a comment or bogus comment; this is modifiable.                |
 	 * | *Presumptuous*  | Found an empty tag closer: `</>`.                                    |
 	 * | *Funky comment* | Found a tag closer with an invalid tag name; this is modifiable.     |
@@ -493,7 +491,6 @@ class WP_HTML_Tag_Processor {
 	 * @see WP_HTML_Tag_Processor::STATE_INCOMPLETE
 	 * @see WP_HTML_Tag_Processor::STATE_MATCHED_TAG
 	 * @see WP_HTML_Tag_Processor::STATE_TEXT_NODE
-	 * @see WP_HTML_Tag_Processor::STATE_CDATA_NODE
 	 * @see WP_HTML_Tag_Processor::STATE_COMMENT
 	 * @see WP_HTML_Tag_Processor::STATE_DOCTYPE
 	 * @see WP_HTML_Tag_Processor::STATE_PRESUMPTUOUS_TAG
@@ -1620,36 +1617,6 @@ private function parse_next_tag() {
 					}
 				}
 
-				/*
-				 * <![CDATA[ transitions to CDATA section state – skip to the nearest ]]>
-				 * The CDATA is case-sensitive.
-				 * https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
-				 */
-				if (
-					$doc_length > $at + 8 &&
-					'[' === $html[ $at + 2 ] &&
-					'C' === $html[ $at + 3 ] &&
-					'D' === $html[ $at + 4 ] &&
-					'A' === $html[ $at + 5 ] &&
-					'T' === $html[ $at + 6 ] &&
-					'A' === $html[ $at + 7 ] &&
-					'[' === $html[ $at + 8 ]
-				) {
-					$closer_at = strpos( $html, ']]>', $at + 9 );
-					if ( false === $closer_at ) {
-						$this->parser_state = self::STATE_INCOMPLETE;
-
-						return false;
-					}
-
-					$this->parser_state         = self::STATE_CDATA_NODE;
-					$this->token_length         = $closer_at + 4 - $this->token_starts_at;
-					$this->text_starts_at       = $this->token_starts_at + 9;
-					$this->text_length          = $closer_at - $this->text_starts_at;
-					$this->bytes_already_parsed = $closer_at + 3;
-					return true;
-				}
-
 				/*
 				 * <!DOCTYPE transitions to DOCTYPE state – skip to the nearest >
 				 * These are ASCII-case-insensitive.
@@ -2524,7 +2491,6 @@ public function is_tag_closer() {
 	 * Possible values:
 	 *  - `#tag` when matched on a tag.
 	 *  - `#text` when matched on a text node.
-	 *  - `#cdata-section` when matched on a CDATA node.
 	 *  - `#comment` when matched on a comment.
 	 *  - `#presumptuous-tag` when matched on an empty tag closer.
 	 *  - `#funky-comment` when matched on a funky comment.
@@ -2574,9 +2540,6 @@ public function get_token_name() {
 			case self::STATE_TEXT_NODE:
 				return '#text';
 
-			case self::STATE_CDATA_NODE:
-				return '#cdata-section';
-
 			case self::STATE_COMMENT:
 				return '#comment';
 
@@ -2597,11 +2560,10 @@ public function get_token_name() {
 	 * Modifiable text is text content that may be read and changed without
 	 * changing the HTML structure of the document around it. This includes
 	 * the contents of `#text` nodes in the HTML as well as the inner
-	 * contents of HTML comments, CDATA sections, Processing Instructions,
-	 * and others, even though these nodes aren't part of a parsed DOM tree.
-	 * They also contain the contents of SCRIPT and STYLE tags, of TEXTAREA
-	 * tags, and of any other section in an HTML document which cannot
-	 * contain HTML markup (DATA).
+	 * contents of HTML comments, Processing Instructions, and others, even
+	 * though these nodes aren't part of a parsed DOM tree. They also contain
+	 * the contents of SCRIPT and STYLE tags, of TEXTAREA tags, and of any
+	 * other section in an HTML document which cannot contain HTML markup (DATA).
 	 *
 	 * If a token has no modifiable text then an empty string is returned to
 	 * avoid needless crashing or type errors. An empty string does not mean
@@ -3165,22 +3127,6 @@ private function matches() {
 	 */
 	const STATE_TEXT_NODE = 'STATE_TEXT_NODE';
 
-	/**
-	 * Parser CDATA Node State.
-	 *
-	 * Indicates that the parser has found a CDADA node and it's possible
-	 * to read and modify its modifiable text. Note that in HTML there are
-	 * no CDATA nodes outside foreign elements (SVG and MathML). Outside
-	 * of foreign elements, they are treated as HTML comments. Nonetheless,
-	 * the Tag Processor still recognizes them as they appear in the HTML
-	 * stream and exposes them for inspection and modification.
-	 *
-	 * @since 6.5.0
-	 *
-	 * @access private
-	 */
-	const STATE_CDATA_NODE = 'STATE_CDATA_NODE';
-
 	/**
 	 * Indicates that the parser has found an HTML comment and it's
 	 * possible to read and modify its modifiable text.

tests/phpunit/tests/html-api/wpHtmlTagProcessor-token-scanning.php

@@ -302,42 +302,6 @@ public function data_rawtext_elements() {
 		);
 	}
 
-	/**
-	 * Ensures that normative CDATA sections are properly parsed.
-	 *
-	 * @ticket 60170
-	 *
-	 * @since 6.5.0
-	 *
-	 * @covers WP_HTML_Tag_Processor::next_token
-	 */
-	public function test_basic_assertion_cdata_section() {
-		$processor = WP_HTML_Processor::create_fragment( '<![CDATA[this is <a comment>]]>' );
-		$processor->next_token();
-
-		$this->assertSame(
-			'#cdata-section',
-			$processor->get_token_name(),
-			"Should have found CDATA section name but found {$processor->get_token_name()} instead."
-		);
-
-		$this->assertNull(
-			$processor->get_tag(),
-			'Should not have been able to query tag name on non-element token.'
-		);
-
-		$this->assertNull(
-			$processor->get_attribute( 'type' ),
-			'Should not have been able to query attributes on non-element token.'
-		);
-
-		$this->assertSame(
-			'this is <a comment>',
-			$processor->get_modifiable_text(),
-			'Found incorrect modifiable text.'
-		);
-	}
-
 	/**
 	 * Ensures that common comments are properly parsed.
 	 *

tests/phpunit/tests/html-api/wpHtmlTagProcessor.php

@@ -2363,6 +2363,7 @@ public function data_html_without_tags() {
 			'No tags'                => array( 'this is nothing more than a text node' ),
 			'Text with comments'     => array( 'One <!-- sneaky --> comment.' ),
 			'Empty tag closer'       => array( '</>' ),
+			'CDATA as HTML comment'  => array( '<![CDATA[this closes at the first &gt;]>' ),
 			'Processing instruction' => array( '<?xml version="1.0"?>' ),
 			'Combination XML-like'   => array( '<!DOCTYPE xml><?xml version=""?><!-- this is not a real document. --><![CDATA[it only serves as a test]]>' ),
 		);
@@ -2416,7 +2417,6 @@ public function data_incomplete_syntax_elements() {
 			'Incomplete CDATA'                     => array( '<![CDATA[something inside of here needs to get out' ),
 			'Partial CDATA'                        => array( '<![CDA' ),
 			'Partially closed CDATA]'              => array( '<![CDATA[cannot escape]' ),
-			'Partially closed CDATA]>'             => array( '<![CDATA[cannot escape]>' ),
 			'Unclosed IFRAME'                      => array( '<iframe><div>' ),
 			'Unclosed NOEMBED'                     => array( '<noembed><div>' ),
 			'Unclosed NOFRAMES'                    => array( '<noframes><div>' ),
@@ -2513,7 +2513,7 @@ public function data_updating_attributes() {
 			),
 			'tag inside of CDATA'      => array(
 				'input'    => '<![CDATA[This <is> a <strong id="yes">HTML Tag</strong>]]><span>test</span>',
-				'expected' => '<![CDATA[This <is> a <strong id="yes">HTML Tag</strong>]]><span class="firstTag" foo="bar">test</span>',
+				'expected' => '<![CDATA[This <is> a <strong class="firstTag" foo="bar" id="yes">HTML Tag</strong>]]><span class="secondTag">test</span>',
 			),
 		);
 	}