HTML API: Preserve raw text contents in serialization.

The contents of `iframe`, `noembed`, and `noframes` elements are parsed as raw text and must be appended literally when serializing rather than escaped or omitted. Setting the modifiable text of these elements, as well as `xmp`, is now supported.

Developed in WordPress#12289.

Follow-up to [62542].

Props jonsurrell, dmsnell.
See #65372.


git-svn-id: https://develop.svn.wordpress.org/trunk@62715 602fd350-edb4-49c9-b593-d223f7449a82

Author: sirreal

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

@@ -1511,9 +1511,6 @@ public function serialize_token(): string {
 				case 'IFRAME':
 				case 'NOEMBED':
 				case 'NOFRAMES':
-					$text = '';
-					break;
-
 				case 'SCRIPT':
 				case 'STYLE':
 				case 'XMP':

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

@@ -298,7 +298,7 @@
  *    closing the SCRIPT from inside a JavaScript string. E.g. `console.log( '</script>' )`.
  *  - `TITLE` and `TEXTAREA` whose contents are treated as plaintext and then any
  *    character references are decoded. E.g. `1 &lt; 2 < 3` becomes `1 < 2 < 3`.
- *  - `IFRAME`, `NOEMBED`, `NOFRAMES`, `STYLE` whose contents are treated as
+ *  - `IFRAME`, `NOEMBED`, `NOFRAMES`, `STYLE`, `XMP` whose contents are treated as
  *    raw plaintext and left as-is. E.g. `1 &lt; 2 < 3` remains `1 &lt; 2 < 3`.
  *
  * #### Other tokens with modifiable text.
@@ -4075,6 +4075,32 @@ public function set_modifiable_text( string $plaintext_content ): bool {
 				);
 				return true;
 
+			case 'IFRAME':
+			case 'NOEMBED':
+			case 'NOFRAMES':
+			case 'XMP':
+				$tag_name = $this->get_tag();
+				if ( false !== stripos( $plaintext_content, "</{$tag_name}" ) ) {
+					_doing_it_wrong(
+						__METHOD__,
+						sprintf(
+							/* translators: %s: HTML tag name. */
+							__( '%s text cannot contain its own closing tag.' ),
+							$tag_name
+						),
+						'7.1.0'
+					);
+					return false;
+				}
+
+				$this->lexical_updates['modifiable text'] = new WP_HTML_Text_Replacement(
+					$this->text_starts_at,
+					$this->text_length,
+					$plaintext_content
+				);
+
+				return true;
+
 			case 'STYLE':
 				$plaintext_content = preg_replace_callback(
 					'~</(?P<TAG_NAME>style)~i',
@@ -4132,7 +4158,7 @@ static function ( $tag_match ) {
 
 		_doing_it_wrong(
 			__METHOD__,
-			__( 'Only the SCRIPT, STYLE, TEXTAREA, and TITLE tags support setting modifiable text.' ),
+			__( 'This tag does not support setting modifiable text.' ),
 			'7.1.0'
 		);
 		return false;

tests/phpunit/tests/html-api/wpHtmlProcessor-serialize.php

@@ -270,22 +270,6 @@ public function test_style_contents_are_not_escaped() {
 		);
 	}
 
-	/**
-	 * XMP contents are parsed using the generic raw text element parsing algorithm.
-	 * Their contents should not be escaped with HTML character references on normalization.
-	 *
-	 * @ticket 65372
-	 */
-	public function test_xmp_contents_are_not_escaped() {
-		$normalized = WP_HTML_Processor::normalize( "<xmp> < > & \" ' \x00 </xmp>" );
-
-		$this->assertSame(
-			"<xmp> < > & \" ' \u{FFFD} </xmp>",
-			$normalized,
-			'Should have preserved text inside an XMP element, except for replacing NULL bytes.'
-		);
-	}
-
 	public function test_unexpected_closing_tags_are_removed() {
 		$this->assertSame(
 			WP_HTML_Processor::normalize( 'one</div>two</span>three' ),
@@ -481,9 +465,9 @@ public function test_replaces_null_bytes_appropriately( string $html_with_nulls,
 	/**
 	 * Data provider.
 	 *
-	 * @return array[]
+	 * @return array<string, array{string, string}>
 	 */
-	public static function data_tokens_with_null_bytes() {
+	public static function data_tokens_with_null_bytes(): array {
 		return array(
 			'Tag name'             => array( "<img\x00id=5>", "<img\u{FFFD}id=5></img\u{FFFD}id=5>" ),
 			'Attribute name'       => array( "<img/\x00id=5>", "<img \u{FFFD}id=\"5\">" ),
@@ -492,11 +476,45 @@ public static function data_tokens_with_null_bytes() {
 			'Foreign content text' => array( "<svg>one\x00two</svg>", "<svg>one\u{FFFD}two</svg>" ),
 			'SCRIPT content'       => array( "<script>alert(\x00)</script>", "<script>alert(\u{FFFD})</script>" ),
 			'STYLE content'        => array( "<style>\x00 {}</style>", "<style>\u{FFFD} {}</style>" ),
+			'IFRAME content'       => array( "<iframe>a\x00b</iframe>", "<iframe>a\u{FFFD}b</iframe>" ),
+			'NOEMBED content'      => array( "<noembed>a\x00b</noembed>", "<noembed>a\u{FFFD}b</noembed>" ),
+			'NOFRAMES content'     => array( "<noframes>a\x00b</noframes>", "<noframes>a\u{FFFD}b</noframes>" ),
 			'XMP content'          => array( "<xmp>a\x00b</xmp>", "<xmp>a\u{FFFD}b</xmp>" ),
 			'Comment text'         => array( "<!-- \x00 -->", "<!-- \u{FFFD} -->" ),
 		);
 	}
 
+	/**
+	 * Ensures that contents of rawtext elements are preserved when serializing.
+	 *
+	 * @ticket 65372
+	 *
+	 * @dataProvider data_rawtext_elements_with_html_syntax_character_contents
+	 *
+	 * @param string $html Normalized HTML containing a rawtext element with contents.
+	 */
+	public function test_rawtext_element_contents_are_preserved_when_normalizing( string $html ): void {
+		$this->assertSame(
+			$html,
+			WP_HTML_Processor::normalize( $html ),
+			'Should have preserved the rawtext element contents.'
+		);
+	}
+
+	/**
+	 * Data provider.
+	 *
+	 * @return array<string, array{string}>
+	 */
+	public static function data_rawtext_elements_with_html_syntax_character_contents(): array {
+		return array(
+			'IFRAME'   => array( 'before<iframe> < > &amp; " \' </iframe>after' ),
+			'NOEMBED'  => array( 'before<noembed> < > &amp; " \' </noembed>after' ),
+			'NOFRAMES' => array( 'before<noframes> < > &amp; " \' </noframes>after' ),
+			'XMP'      => array( 'before<xmp> < > &amp; " \' </xmp>after' ),
+		);
+	}
+
 	/**
 	 * @ticket 62396
 	 *

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

@@ -434,6 +434,10 @@ public static function data_tokens_with_basic_modifiable_text_updates() {
 			'PI node (no separator)'  => array( '<?wp-bit?>', 1, '{"just": "kidding"}', '<?wp-bit {"just": "kidding"}?>' ),
 			'Text node (end)'         => array( '<img>of a dog', 2, 'of a cat', '<img>of a cat' ),
 			'Encoded text node'       => array( '<figcaption>birds and dogs</figcaption>', 2, '<birds> & <dogs>', '<figcaption>&lt;birds&gt; &amp; &lt;dogs&gt;</figcaption>' ),
+			'IFRAME tag'              => array( 'before<iframe>old content</iframe>after', 2, '<p>raw & text</p>', 'before<iframe><p>raw & text</p></iframe>after' ),
+			'NOEMBED tag'             => array( 'before<noembed>old content</noembed>after', 2, '<p>raw & text</p>', 'before<noembed><p>raw & text</p></noembed>after' ),
+			'NOFRAMES tag'            => array( 'before<noframes>old content</noframes>after', 2, '<p>raw & text</p>', 'before<noframes><p>raw & text</p></noframes>after' ),
+			'XMP tag'                 => array( 'before<xmp>old content</xmp>after', 2, '<p>raw & text</p>', 'before<xmp><p>raw & text</p></xmp>after' ),
 			'SCRIPT tag'              => array( 'before<script></script>after', 2, 'const img = "<img> & <br>";', 'before<script>const img = "<img> & <br>";</script>after' ),
 			'STYLE tag'               => array( '<style></style>', 1, 'p::before { content: "<img> & </style>"; }', '<style>p::before { content: "<img> & \3c\2fstyle>"; }</style>' ),
 			'TEXTAREA tag'            => array( 'a<textarea>has no need to escape</textarea>b', 2, "so it <doesn't>", "a<textarea>so it <doesn't></textarea>b" ),
@@ -624,6 +628,10 @@ public static function data_unallowed_modifiable_text_updates() {
 		return array(
 			'Comment with -->'                        => array( '<!-- this is a comment -->', 'Comments end in -->' ),
 			'Comment with --!>'                       => array( '<!-- this is a comment -->', 'Invalid but legitimate comments end in --!>' ),
+			'IFRAME with </iframe>'                   => array( '<iframe>Replace me</iframe>', 'Just a </iframe>' ),
+			'NOEMBED with </NOEMBED>'                 => array( '<noembed>Replace me</noembed>', 'Just a </NOEMBED>' ),
+			'NOFRAMES with </noframes attributes>'    => array( '<noframes>Replace me</noframes>', 'before</noframes sneaky>after' ),
+			'XMP with </xmp>'                         => array( '<xmp>Replace me</xmp>', 'Just a </xmp>' ),
 			'PI with >'                               => array( '<?wp-bit some data?>', 'Processing instructions end at the first >' ),
 			'PI with leading space'                   => array( '<?wp-bit some data?>', ' leading whitespace is skipped after the target' ),
 			'PI with leading tab'                     => array( '<?wp-bit some data?>', "\tleading whitespace is skipped after the target" ),