From 09ce30ba50dd5b23643bb37a8a6c496a8a9d11ca Mon Sep 17 00:00:00 2001 From: Dennis Snell Date: Fri, 12 Jul 2024 22:29:13 +0000 Subject: [PATCH] HTML API: Add context to Unsupported_Exception class for improved debugging. The HTML Processor internally throws an exception when it reaches HTML that it knows it cannot process, but this exception is not made available to calling code. It can be useful to extract more knowledge about why it gave up, especially for debugging purposes. In this patch, more context is added to the WP_HTML_Unsupported_Exception and the last exception is made available to calling code through a new method, `get_unsupported_exception()`. Developed in https://github.com/WordPress/wordpress-develop/pull/6985 Discussed in https://core.trac.wordpress.org/ticket/61646 Props bernhard-reiter, dmsnell, jonsurrell. See #61646. Built from https://develop.svn.wordpress.org/trunk@58714 git-svn-id: https://core.svn.wordpress.org/trunk@58116 1a063a9b-81f0-0310-95a4-ce76da25c4cd --- .../html-api/class-wp-html-processor.php | 151 +++++++++++------- .../class-wp-html-unsupported-exception.php | 84 ++++++++++ wp-includes/version.php | 2 +- 3 files changed, 180 insertions(+), 57 deletions(-) diff --git a/wp-includes/html-api/class-wp-html-processor.php b/wp-includes/html-api/class-wp-html-processor.php index d7f77f495c..04c387c003 100644 --- a/wp-includes/html-api/class-wp-html-processor.php +++ b/wp-includes/html-api/class-wp-html-processor.php @@ -188,6 +188,17 @@ class WP_HTML_Processor extends WP_HTML_Tag_Processor { */ private $last_error = null; + /** + * Stores context for why the parser bailed on unsupported HTML, if it did. + * + * @see self::get_unsupported_exception + * + * @since 6.7.0 + * + * @var WP_HTML_Unsupported_Exception|null + */ + private $unsupported_exception = null; + /** * Releases a bookmark when PHP garbage-collects its wrapping WP_HTML_Token instance. * @@ -384,6 +395,45 @@ function ( WP_HTML_Token $token ) { }; } + /** + * Stops the parser and terminates its execution when encountering unsupported markup. + * + * @throws WP_HTML_Unsupported_Exception Halts execution of the parser. + * + * @since 6.7.0 + * + * @param string $message Explains support is missing in order to parse the current node. + * + * @return mixed + */ + private function bail( string $message ) { + $here = $this->bookmarks[ $this->state->current_token->bookmark_name ]; + $token = substr( $this->html, $here->start, $here->length ); + + $open_elements = array(); + foreach ( $this->state->stack_of_open_elements->stack as $item ) { + $open_elements[] = $item->node_name; + } + + $active_formats = array(); + foreach ( $this->state->active_formatting_elements->walk_down() as $item ) { + $active_formats[] = $item->node_name; + } + + $this->last_error = self::ERROR_UNSUPPORTED; + + $this->unsupported_exception = new WP_HTML_Unsupported_Exception( + $message, + $this->state->current_token->node_name, + $here->start, + $token, + $open_elements, + $active_formats + ); + + throw $this->unsupported_exception; + } + /** * Returns the last error, if any. * @@ -411,6 +461,21 @@ public function get_last_error() { return $this->last_error; } + /** + * Returns context for why the parser aborted due to unsupported HTML, if it did. + * + * This is meant for debugging purposes, not for production use. + * + * @since 6.7.0 + * + * @see self::$unsupported_exception + * + * @return WP_HTML_Unsupported_Exception|null + */ + public function get_unsupported_exception() { + return $this->unsupported_exception; + } + /** * Finds the next tag matching the $query. * @@ -841,8 +906,7 @@ public function step( $node_to_process = self::PROCESS_NEXT_NODE ) { // This should be unreachable but PHP doesn't have total type checking on switch. default: - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "Found unrecognized insertion mode '{$this->state->insertion_mode}'." ); + $this->bail( "Unaware of the requested parsing mode: '{$this->state->insertion_mode}'." ); } } catch ( WP_HTML_Unsupported_Exception $e ) { /* @@ -922,8 +986,7 @@ public function get_current_depth() { * @return bool Whether an element was found. */ private function step_initial() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -942,8 +1005,7 @@ private function step_initial() { * @return bool Whether an element was found. */ private function step_before_html() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -962,8 +1024,7 @@ private function step_before_html() { * @return bool Whether an element was found. */ private function step_before_head() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -982,8 +1043,7 @@ private function step_before_head() { * @return bool Whether an element was found. */ private function step_in_head() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -1002,8 +1062,7 @@ private function step_in_head() { * @return bool Whether an element was found. */ private function step_in_head_noscript() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -1022,8 +1081,7 @@ private function step_in_head_noscript() { * @return bool Whether an element was found. */ private function step_after_head() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -1445,8 +1503,9 @@ private function step_in_body() { * > than the end tag token that it actually is. */ case '-BR': - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( 'Closing BR tags require unimplemented special handling.' ); + $this->bail( 'Closing BR tags require unimplemented special handling.' ); + // This return required because PHPCS can't determine that the call to bail() throws. + return false; /* * > A start tag whose tag name is one of: "area", "br", "embed", "img", "keygen", "wbr" @@ -1602,8 +1661,7 @@ private function step_in_body() { case 'TITLE': case 'TR': case 'XMP': - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "Cannot process {$token_name} element." ); + $this->bail( "Cannot process {$token_name} element." ); } if ( ! parent::is_tag_closer() ) { @@ -1665,8 +1723,7 @@ private function step_in_body() { * @return bool Whether an element was found. */ private function step_in_table() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -1685,8 +1742,7 @@ private function step_in_table() { * @return bool Whether an element was found. */ private function step_in_table_text() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -1705,8 +1761,7 @@ private function step_in_table_text() { * @return bool Whether an element was found. */ private function step_in_caption() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -1725,8 +1780,7 @@ private function step_in_caption() { * @return bool Whether an element was found. */ private function step_in_column_group() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -1745,8 +1799,7 @@ private function step_in_column_group() { * @return bool Whether an element was found. */ private function step_in_table_body() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -1765,8 +1818,7 @@ private function step_in_table_body() { * @return bool Whether an element was found. */ private function step_in_row() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -1785,8 +1837,7 @@ private function step_in_row() { * @return bool Whether an element was found. */ private function step_in_cell() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -1986,8 +2037,7 @@ private function step_in_select() { * @return bool Whether an element was found. */ private function step_in_select_in_table() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -2006,8 +2056,7 @@ private function step_in_select_in_table() { * @return bool Whether an element was found. */ private function step_in_template() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -2026,8 +2075,7 @@ private function step_in_template() { * @return bool Whether an element was found. */ private function step_after_body() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -2046,8 +2094,7 @@ private function step_after_body() { * @return bool Whether an element was found. */ private function step_in_frameset() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -2066,8 +2113,7 @@ private function step_in_frameset() { * @return bool Whether an element was found. */ private function step_after_frameset() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -2086,8 +2132,7 @@ private function step_after_frameset() { * @return bool Whether an element was found. */ private function step_after_after_body() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -2106,8 +2151,7 @@ private function step_after_after_body() { * @return bool Whether an element was found. */ private function step_after_after_frameset() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /** @@ -2126,8 +2170,7 @@ private function step_after_after_frameset() { * @return bool Whether an element was found. */ private function step_in_foreign_content() { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." ); + $this->bail( "No support for parsing in the '{$this->state->insertion_mode}' state." ); } /* @@ -2835,8 +2878,7 @@ private function reconstruct_active_formatting_elements() { return false; } - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( 'Cannot reconstruct active formatting elements when advancing and rewinding is required.' ); + $this->bail( 'Cannot reconstruct active formatting elements when advancing and rewinding is required.' ); } /** @@ -3072,8 +3114,7 @@ private function run_adoption_agency_algorithm() { // > If there is no such element, then return and instead act as described in the "any other end tag" entry above. if ( null === $formatting_element ) { - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( 'Cannot run adoption agency when "any other end tag" is required.' ); + $this->bail( 'Cannot run adoption agency when "any other end tag" is required.' ); } // > If formatting element is not in the stack of open elements, then this is a parse error; remove the element from the list, and return. @@ -3125,12 +3166,10 @@ private function run_adoption_agency_algorithm() { } } - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( 'Cannot extract common ancestor in adoption agency algorithm.' ); + $this->bail( 'Cannot extract common ancestor in adoption agency algorithm.' ); } - $this->last_error = self::ERROR_UNSUPPORTED; - throw new WP_HTML_Unsupported_Exception( 'Cannot run adoption agency when looping required.' ); + $this->bail( 'Cannot run adoption agency when looping required.' ); } /** diff --git a/wp-includes/html-api/class-wp-html-unsupported-exception.php b/wp-includes/html-api/class-wp-html-unsupported-exception.php index 6e7228670b..7b244a5e8a 100644 --- a/wp-includes/html-api/class-wp-html-unsupported-exception.php +++ b/wp-includes/html-api/class-wp-html-unsupported-exception.php @@ -21,11 +21,95 @@ * operation and signify that the given HTML cannot be processed. * * @since 6.4.0 + * @since 6.7.0 Gained contextual information for use in debugging parse failures. * * @access private * * @see WP_HTML_Processor */ class WP_HTML_Unsupported_Exception extends Exception { + /** + * Name of the matched token when the exception was raised, + * if matched on a token. + * + * This does not imply that the token itself was unsupported, but it + * may have been the case that the token triggered part of the HTML + * parsing that isn't supported, such as the adoption agency algorithm. + * + * @since 6.7.0 + * + * @var string + */ + public $token_name; + /** + * Number of bytes into the input HTML document where the parser was + * parsing when the exception was raised. + * + * Use this to reconstruct context for the failure. + * + * @since 6.7.0 + * + * @var int + */ + public $token_at; + + /** + * Full raw text of the matched token when the exception was raised, + * if matched on a token. + * + * Whereas the `$token_name` will be normalized, this contains the full + * raw text of the token, including original casing, duplicated attributes, + * and other syntactic variations that are normally abstracted in the HTML API. + * + * @since 6.7.0 + * + * @var string + */ + public $token; + + /** + * Stack of open elements when the exception was raised. + * + * Use this to trace the parsing circumstances which led to the exception. + * + * @since 6.7.0 + * + * @var string[] + */ + public $stack_of_open_elements = array(); + + /** + * List of active formatting elements when the exception was raised. + * + * Use this to trace the parsing circumstances which led to the exception. + * + * @since 6.7.0 + * + * @var string[] + */ + public $active_formatting_elements = array(); + + /** + * Constructor function. + * + * @since 6.7.0 + * + * @param string $message Brief message explaining what is unsupported, the reason this exception was raised. + * @param string $token_name Normalized name of matched token when this exception was raised. + * @param int $token_at Number of bytes into source HTML document where matched token starts. + * @param string $token Full raw text of matched token when this exception was raised. + * @param string[] $stack_of_open_elements Stack of open elements when this exception was raised. + * @param string[] $active_formatting_elements List of active formatting elements when this exception was raised. + */ + public function __construct( string $message, string $token_name, int $token_at, string $token, array $stack_of_open_elements, array $active_formatting_elements ) { + parent::__construct( $message ); + + $this->token_name = $token_name; + $this->token_at = $token_at; + $this->token = $token; + + $this->stack_of_open_elements = $stack_of_open_elements; + $this->active_formatting_elements = $active_formatting_elements; + } } diff --git a/wp-includes/version.php b/wp-includes/version.php index 453cc90702..5448ace375 100644 --- a/wp-includes/version.php +++ b/wp-includes/version.php @@ -16,7 +16,7 @@ * * @global string $wp_version */ -$wp_version = '6.7-alpha-58713'; +$wp_version = '6.7-alpha-58714'; /** * Holds the WordPress DB revision, increments when changes are made to the WordPress DB schema.