HTML API: Fix splitting single text node.

dmsnell · dmsnell · commit 0b800d7e580f · 2024-01-30T22:07:42.000Z
When `next_token()` was introduced, it brought a subtle bug. When encountering a `<` in the HTML stream which did not lead to a tag or comment or other token, it was treating the full text span to that point as one text node, and the following span another text node. The entire span should be one text node. In this patch the Tag Processor properly detects this scenario and combines the spans into one text node. Follow-up to [57348] Props jonsurrell Fixes #60385 git-svn-id: https://develop.svn.wordpress.org/trunk@57489 602fd350-edb4-49c9-b593-d223f7449a82
diff --git a/src/wp-includes/html-api/class-wp-html-tag-processor.php b/src/wp-includes/html-api/class-wp-html-tag-processor.php
@@ -1512,16 +1512,6 @@ private function parse_next_tag() {
 		while ( false !== $at && $at < $doc_length ) {
 			$at = strpos( $html, '<', $at );
 
-			if ( $at > $was_at ) {
-				$this->parser_state         = self::STATE_TEXT_NODE;
-				$this->token_starts_at      = $was_at;
-				$this->token_length         = $at - $was_at;
-				$this->text_starts_at       = $was_at;
-				$this->text_length          = $this->token_length;
-				$this->bytes_already_parsed = $at;
-				return true;
-			}
-
 			/*
 			 * This does not imply an incomplete parse; it indicates that there
 			 * can be nothing left in the document other than a #text node.
@@ -1536,6 +1526,37 @@ private function parse_next_tag() {
 				return true;
 			}
 
+			if ( $at > $was_at ) {
+				/*
+				 * A "<" has been found in the document. That may be the start of another node, or
+				 * it may be an "ivalid-first-character-of-tag-name" error. If this is not the start
+				 * of another node the "<" should be included in this text node and another
+				 * termination point should be found for the text node.
+				 *
+				 * @see https://html.spec.whatwg.org/#tag-open-state
+				 */
+				if ( strlen( $html ) > $at + 1 ) {
+					$next_character  = $html[ $at + 1 ];
+					$at_another_node =
+						'!' === $next_character ||
+						'/' === $next_character ||
+						'?' === $next_character ||
+						( 'A' <= $next_character && $next_character <= 'z' );
+					if ( ! $at_another_node ) {
+						++$at;
+						continue;
+					}
+				}
+
+				$this->parser_state         = self::STATE_TEXT_NODE;
+				$this->token_starts_at      = $was_at;
+				$this->token_length         = $at - $was_at;
+				$this->text_starts_at       = $was_at;
+				$this->text_length          = $this->token_length;
+				$this->bytes_already_parsed = $at;
+				return true;
+			}
+
 			$this->token_starts_at = $at;
 
 			if ( $at + 1 < $doc_length && '/' === $this->html[ $at + 1 ] ) {
diff --git a/tests/phpunit/tests/html-api/wpHtmlTagProcessor.php b/tests/phpunit/tests/html-api/wpHtmlTagProcessor.php
@@ -2715,4 +2715,16 @@ public function test_handles_malformed_taglike_close_short_html() {
 		$result = $p->next_tag();
 		$this->assertFalse( $result, 'Did not handle "</ " html properly.' );
 	}
+
+	/**
+	 * Ensures that non-tag syntax starting with `<` is consumed inside a text node.
+	 *
+	 * @ticket 60385
+	 */
+	public function test_single_text_node_with_taglike_text() {
+		$p = new WP_HTML_Tag_Processor( 'test< /A>' );
+		$p->next_token();
+		$this->assertSame( '#text', $p->get_token_type(), 'Did not find text node.' );
+		$this->assertSame( 'test< /A>', $p->get_modifiable_text(), 'Did not find complete text node.' );
+	}
 }
