HTML API: Add get full comment text method

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

@@ -3385,6 +3385,58 @@ public function get_comment_type(): ?string {
 		return $this->comment_type;
 	}
 
+	/**
+	 * Returns the text of a matched comment or null if not on a comment type node.
+	 *
+	 * This method returns the entire text content of a comment node as it
+	 * would appear in the browser.
+	 *
+	 * This differs from {@see ::get_modifiable_text()} in that certain comment
+	 * types in the HTML API cannot allow their entire comment text content to
+	 * be modified. Namely, "bogus comments" of the form `<?not allowed in html>`
+	 * will create a comment whose text content starts with `?`. Note that if
+	 * that character were modified, it would be possible to change the node
+	 * type.
+	 *
+	 * @since 6.7.0
+	 *
+	 * @return string|null The comment text as it would appear in the browser or null
+	 *                     if not on a comment type node.
+	 */
+	public function get_full_comment_text(): ?string {
+		if ( self::STATE_FUNKY_COMMENT === $this->parser_state ) {
+			return $this->get_modifiable_text();
+		}
+
+		if ( self::STATE_COMMENT !== $this->parser_state ) {
+			return null;
+		}
+
+		switch ( $this->get_comment_type() ) {
+			case self::COMMENT_AS_HTML_COMMENT:
+			case self::COMMENT_AS_ABRUPTLY_CLOSED_COMMENT:
+				return $this->get_modifiable_text();
+
+			case self::COMMENT_AS_CDATA_LOOKALIKE:
+				return "[CDATA[{$this->get_modifiable_text()}]]";
+
+			case self::COMMENT_AS_PI_NODE_LOOKALIKE:
+				return "?{$this->get_tag()}{$this->get_modifiable_text()}?";
+
+			/*
+			 * This represents "bogus comments state" from HTML tokenization.
+			 * This can be entered by `<?` or `<!`, where `?` is included in
+			 * the comment text but `!` is not.
+			 */
+			case self::COMMENT_AS_INVALID_HTML:
+				$preceding_character = $this->html[ $this->text_starts_at - 1 ];
+				$comment_start       = '?' === $preceding_character ? '?' : '';
+				return "{$comment_start}{$this->get_modifiable_text()}";
+		}
+
+		return null;
+	}
+
 	/**
 	 * Subdivides a matched text node, splitting NULL byte sequences and decoded whitespace as
 	 * distinct nodes prefixes.

tests/phpunit/tests/html-api/wpHtmlProcessorHtml5lib.php

@@ -27,20 +27,17 @@ class Tests_HtmlApi_Html5lib extends WP_UnitTestCase {
 	 * Skip specific tests that may not be supported or have known issues.
 	 */
 	const SKIP_TESTS = array(
-		'comments01/line0155'    => 'Unimplemented: Need to access raw comment text on non-normative comments.',
-		'comments01/line0169'    => 'Unimplemented: Need to access raw comment text on non-normative comments.',
-		'html5test-com/line0129' => 'Unimplemented: Need to access raw comment text on non-normative comments.',
-		'noscript01/line0014'    => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
-		'tests14/line0022'       => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
-		'tests14/line0055'       => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
-		'tests19/line0488'       => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
-		'tests19/line0500'       => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
-		'tests19/line1079'       => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
-		'tests2/line0207'        => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
-		'tests2/line0686'        => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
-		'tests2/line0697'        => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
-		'tests2/line0709'        => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
-		'webkit01/line0231'      => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
+		'noscript01/line0014' => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
+		'tests14/line0022'    => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
+		'tests14/line0055'    => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
+		'tests19/line0488'    => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
+		'tests19/line0500'    => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
+		'tests19/line1079'    => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
+		'tests2/line0207'     => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
+		'tests2/line0686'     => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
+		'tests2/line0697'     => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
+		'tests2/line0709'     => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
+		'webkit01/line0231'   => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
 	);
 
 	/**
@@ -315,26 +312,8 @@ static function ( $a, $b ) {
 					break;
 
 				case '#comment':
-					switch ( $processor->get_comment_type() ) {
-						case WP_HTML_Processor::COMMENT_AS_ABRUPTLY_CLOSED_COMMENT:
-						case WP_HTML_Processor::COMMENT_AS_HTML_COMMENT:
-						case WP_HTML_Processor::COMMENT_AS_INVALID_HTML:
-							$comment_text_content = $processor->get_modifiable_text();
-							break;
-
-						case WP_HTML_Processor::COMMENT_AS_CDATA_LOOKALIKE:
-							$comment_text_content = "[CDATA[{$processor->get_modifiable_text()}]]";
-							break;
-
-						case WP_HTML_Processor::COMMENT_AS_PI_NODE_LOOKALIKE:
-							$comment_text_content = "?{$processor->get_tag()}{$processor->get_modifiable_text()}?";
-							break;
-
-						default:
-							throw new Error( "Unhandled comment type for tree construction: {$processor->get_comment_type()}" );
-					}
 					// Comments must be "<" then "!-- " then the data then " -->".
-					$output .= str_repeat( self::TREE_INDENT, $indent_level ) . "<!-- {$comment_text_content} -->\n";
+					$output .= str_repeat( self::TREE_INDENT, $indent_level ) . "<!-- {$processor->get_full_comment_text()} -->\n";
 					break;
 
 				default: