?????????????? PK<»–[~¸##"class-wp-html-text-replacement.phpnu„[µü¤start = $start; $this->end = $end; $this->text = $text; } } PK<»–[ Á È  !class-wp-html-processor-state.phpnu„[µü¤ The frameset-ok flag is set to "ok" when the parser is created. It is set to "not ok" after certain tokens are seen. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#frameset-ok-flag * * @var bool */ public $frameset_ok = true; /** * Constructor - creates a new and empty state value. * * @since 6.4.0 * * @see WP_HTML_Processor */ public function __construct() { $this->stack_of_open_elements = new WP_HTML_Open_Elements(); $this->active_formatting_elements = new WP_HTML_Active_Formatting_Elements(); } } PK<»–[t5â¿ð ð class-wp-html-token.phpnu„[µü¤bookmark_name = $bookmark_name; $this->node_name = $node_name; $this->has_self_closing_flag = $has_self_closing_flag; $this->on_destroy = $on_destroy; } /** * Destructor. * * @since 6.4.0 */ public function __destruct() { if ( is_callable( $this->on_destroy ) ) { call_user_func( $this->on_destroy, $this->bookmark_name ); } } /** * Wakeup magic method. * * @since 6.4.2 */ public function __wakeup() { throw new \LogicException( __CLASS__ . ' should never be unserialized' ); } } PK<»–[å Ôù c cclass-wp-html-doctype-info.phpnu„[µü¤`. * * > DOCTYPEs are required for legacy reasons. When omitted, browsers tend to use a different * > rendering mode that is incompatible with some specifications. Including the DOCTYPE in a * > document ensures that the browser makes a best-effort attempt at following the * > relevant specifications. * * @see https://html.spec.whatwg.org/#the-doctype * * DOCTYPE declarations comprise four properties: a name, public identifier, system identifier, * and an indication of which document compatability mode they would imply if an HTML parser * hadn't already determined it from other information. * * @see https://html.spec.whatwg.org/#the-initial-insertion-mode * * Historically, the DOCTYPE declaration was used in SGML documents to instruct a parser how * to interpret the various tags and entities within a document. Its role in HTML diverged * from how it was used in SGML and no meaning should be back-read into HTML based on how it * is used in SGML, XML, or XHTML documents. * * @see https://www.iso.org/standard/16387.html * * @since 6.7.0 * * @see WP_HTML_Processor */ class WP_HTML_Doctype_Info { /** * Name of the DOCTYPE: should be "html" for HTML documents. * * This value should be considered "read only" and not modified. * * Historically the DOCTYPE name indicates name of the document's root element. * * * ╰──┴── name is "html". * * @see https://html.spec.whatwg.org/#tokenization * * @since 6.7.0 * * @var string|null */ public $name = null; /** * Public identifier of the DOCTYPE. * * This value should be considered "read only" and not modified. * * The public identifier is optional and should not appear in HTML documents. * A `null` value indicates that no public identifier was present in the DOCTYPE. * * Historically the presence of the public identifier indicated that a document * was meant to be shared between computer systems and the value indicated to a * knowledgeable parser how to find the relevant document type definition (DTD). * * * │ │ ╰─── public identifier ─────╯ * ╰──┴── name is "html". * * @see https://html.spec.whatwg.org/#tokenization * * @since 6.7.0 * * @var string|null */ public $public_identifier = null; /** * System identifier of the DOCTYPE. * * This value should be considered "read only" and not modified. * * The system identifier is optional and should not appear in HTML documents. * A `null` value indicates that no system identifier was present in the DOCTYPE. * * Historically the system identifier specified where a relevant document type * declaration for the given document is stored and may be retrieved. * * * │ │ ╰──── system identifier ────╯ * ╰──┴── name is "html". * * If a public identifier were provided it would indicate to a knowledgeable * parser how to interpret the system identifier. * * * │ │ ╰─── public identifier ─────╯ ╰──── system identifier ────╯ * ╰──┴── name is "html". * * @see https://html.spec.whatwg.org/#tokenization * * @since 6.7.0 * * @var string|null */ public $system_identifier = null; /** * Which document compatability mode this DOCTYPE declaration indicates. * * This value should be considered "read only" and not modified. * * When an HTML parser has not already set the document compatability mode, * (e.g. "quirks" or "no-quirks" mode), it will infer if from the properties * of the appropriate DOCTYPE declaration, if one exists. The DOCTYPE can * indicate one of three possible document compatability modes: * * - "no-quirks" and "limited-quirks" modes (also called "standards" mode). * - "quirks" mode (also called `CSS1Compat` mode). * * An appropriate DOCTYPE is one encountered in the "initial" insertion mode, * before the HTML element has been opened and before finding any other * DOCTYPE declaration tokens. * * @see https://html.spec.whatwg.org/#the-initial-insertion-mode * * @since 6.7.0 * * @var string One of "no-quirks", "limited-quirks", or "quirks". */ public $indicated_compatability_mode; /** * Constructor. * * This class should not be instantiated directly. * Use the static {@see self::from_doctype_token} method instead. * * The arguments to this constructor correspond to the "DOCTYPE token" * as defined in the HTML specification. * * > DOCTYPE tokens have a name, a public identifier, a system identifier, * > and a force-quirks flag. When a DOCTYPE token is created, its name, public identifier, * > and system identifier must be marked as missing (which is a distinct state from the * > empty string), and the force-quirks flag must be set to off (its other state is on). * * @see https://html.spec.whatwg.org/multipage/parsing.html#tokenization * * @since 6.7.0 * * @param string|null $name Name of the DOCTYPE. * @param string|null $public_identifier Public identifier of the DOCTYPE. * @param string|null $system_identifier System identifier of the DOCTYPE. * @param bool $force_quirks_flag Whether the force-quirks flag is set for the token. */ private function __construct( ?string $name, ?string $public_identifier, ?string $system_identifier, bool $force_quirks_flag ) { $this->name = $name; $this->public_identifier = $public_identifier; $this->system_identifier = $system_identifier; /* * > If the DOCTYPE token matches one of the conditions in the following list, * > then set the Document to quirks mode: */ /* * > The force-quirks flag is set to on. */ if ( $force_quirks_flag ) { $this->indicated_compatability_mode = 'quirks'; return; } /* * Normative documents will contain the literal `` with no * public or system identifiers; short-circuit to avoid extra parsing. */ if ( 'html' === $name && null === $public_identifier && null === $system_identifier ) { $this->indicated_compatability_mode = 'no-quirks'; return; } /* * > The name is not "html". * * The tokenizer must report the name in lower case even if provided in * the document in upper case; thus no conversion is required here. */ if ( 'html' !== $name ) { $this->indicated_compatability_mode = 'quirks'; return; } /* * Set up some variables to handle the rest of the conditions. * * > set...the public identifier...to...the empty string if the public identifier was missing. * > set...the system identifier...to...the empty string if the system identifier was missing. * > * > The system identifier and public identifier strings must be compared... * > in an ASCII case-insensitive manner. * > * > A system identifier whose value is the empty string is not considered missing * > for the purposes of the conditions above. */ $system_identifier_is_missing = null === $system_identifier; $public_identifier = null === $public_identifier ? '' : strtolower( $public_identifier ); $system_identifier = null === $system_identifier ? '' : strtolower( $system_identifier ); /* * > The public identifier is set to… */ if ( '-//w3o//dtd w3 html strict 3.0//en//' === $public_identifier || '-/w3c/dtd html 4.0 transitional/en' === $public_identifier || 'html' === $public_identifier ) { $this->indicated_compatability_mode = 'quirks'; return; } /* * > The system identifier is set to… */ if ( 'http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd' === $system_identifier ) { $this->indicated_compatability_mode = 'quirks'; return; } /* * All of the following conditions depend on matching the public identifier. * If the public identifier is empty, none of the following conditions will match. */ if ( '' === $public_identifier ) { $this->indicated_compatability_mode = 'no-quirks'; return; } /* * > The public identifier starts with… * * @todo Optimize this matching. It shouldn't be a large overall performance issue, * however, as only a single DOCTYPE declaration token should ever be parsed, * and normative documents will have exited before reaching this condition. */ if ( str_starts_with( $public_identifier, '+//silmaril//dtd html pro v0r11 19970101//' ) || str_starts_with( $public_identifier, '-//as//dtd html 3.0 aswedit + extensions//' ) || str_starts_with( $public_identifier, '-//advasoft ltd//dtd html 3.0 aswedit + extensions//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html 2.0 level 1//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html 2.0 level 2//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html 2.0 strict level 1//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html 2.0 strict level 2//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html 2.0 strict//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html 2.0//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html 2.1e//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html 3.0//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html 3.2 final//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html 3.2//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html 3//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html level 0//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html level 1//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html level 2//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html level 3//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html strict level 0//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html strict level 1//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html strict level 2//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html strict level 3//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html strict//' ) || str_starts_with( $public_identifier, '-//ietf//dtd html//' ) || str_starts_with( $public_identifier, '-//metrius//dtd metrius presentational//' ) || str_starts_with( $public_identifier, '-//microsoft//dtd internet explorer 2.0 html strict//' ) || str_starts_with( $public_identifier, '-//microsoft//dtd internet explorer 2.0 html//' ) || str_starts_with( $public_identifier, '-//microsoft//dtd internet explorer 2.0 tables//' ) || str_starts_with( $public_identifier, '-//microsoft//dtd internet explorer 3.0 html strict//' ) || str_starts_with( $public_identifier, '-//microsoft//dtd internet explorer 3.0 html//' ) || str_starts_with( $public_identifier, '-//microsoft//dtd internet explorer 3.0 tables//' ) || str_starts_with( $public_identifier, '-//netscape comm. corp.//dtd html//' ) || str_starts_with( $public_identifier, '-//netscape comm. corp.//dtd strict html//' ) || str_starts_with( $public_identifier, "-//o'reilly and associates//dtd html 2.0//" ) || str_starts_with( $public_identifier, "-//o'reilly and associates//dtd html extended 1.0//" ) || str_starts_with( $public_identifier, "-//o'reilly and associates//dtd html extended relaxed 1.0//" ) || str_starts_with( $public_identifier, '-//sq//dtd html 2.0 hotmetal + extensions//' ) || str_starts_with( $public_identifier, '-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//' ) || str_starts_with( $public_identifier, '-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//' ) || str_starts_with( $public_identifier, '-//spyglass//dtd html 2.0 extended//' ) || str_starts_with( $public_identifier, '-//sun microsystems corp.//dtd hotjava html//' ) || str_starts_with( $public_identifier, '-//sun microsystems corp.//dtd hotjava strict html//' ) || str_starts_with( $public_identifier, '-//w3c//dtd html 3 1995-03-24//' ) || str_starts_with( $public_identifier, '-//w3c//dtd html 3.2 draft//' ) || str_starts_with( $public_identifier, '-//w3c//dtd html 3.2 final//' ) || str_starts_with( $public_identifier, '-//w3c//dtd html 3.2//' ) || str_starts_with( $public_identifier, '-//w3c//dtd html 3.2s draft//' ) || str_starts_with( $public_identifier, '-//w3c//dtd html 4.0 frameset//' ) || str_starts_with( $public_identifier, '-//w3c//dtd html 4.0 transitional//' ) || str_starts_with( $public_identifier, '-//w3c//dtd html experimental 19960712//' ) || str_starts_with( $public_identifier, '-//w3c//dtd html experimental 970421//' ) || str_starts_with( $public_identifier, '-//w3c//dtd w3 html//' ) || str_starts_with( $public_identifier, '-//w3o//dtd w3 html 3.0//' ) || str_starts_with( $public_identifier, '-//webtechs//dtd mozilla html 2.0//' ) || str_starts_with( $public_identifier, '-//webtechs//dtd mozilla html//' ) ) { $this->indicated_compatability_mode = 'quirks'; return; } /* * > The system identifier is missing and the public identifier starts with… */ if ( $system_identifier_is_missing && ( str_starts_with( $public_identifier, '-//w3c//dtd html 4.01 frameset//' ) || str_starts_with( $public_identifier, '-//w3c//dtd html 4.01 transitional//' ) ) ) { $this->indicated_compatability_mode = 'quirks'; return; } /* * > Otherwise, if the DOCTYPE token matches one of the conditions in * > the following list, then set the Document to limited-quirks mode. */ /* * > The public identifier starts with… */ if ( str_starts_with( $public_identifier, '-//w3c//dtd xhtml 1.0 frameset//' ) || str_starts_with( $public_identifier, '-//w3c//dtd xhtml 1.0 transitional//' ) ) { $this->indicated_compatability_mode = 'limited-quirks'; return; } /* * > The system identifier is not missing and the public identifier starts with… */ if ( ! $system_identifier_is_missing && ( str_starts_with( $public_identifier, '-//w3c//dtd html 4.01 frameset//' ) || str_starts_with( $public_identifier, '-//w3c//dtd html 4.01 transitional//' ) ) ) { $this->indicated_compatability_mode = 'limited-quirks'; return; } $this->indicated_compatability_mode = 'no-quirks'; } /** * Creates a WP_HTML_Doctype_Info instance by parsing a raw DOCTYPE declaration token. * * Use this method to parse a DOCTYPE declaration token and get access to its properties * via the returned WP_HTML_Doctype_Info class instance. The provided input must parse * properly as a DOCTYPE declaration, though it must not represent a valid DOCTYPE. * * Example: * * // Normative HTML DOCTYPE declaration. * $doctype = WP_HTML_Doctype_Info::from_doctype_token( '' ); * 'no-quirks' === $doctype->indicated_compatability_mode; * * // A nonsensical DOCTYPE is still valid, and will indicate "quirks" mode. * $doctype = WP_HTML_Doctype_Info::from_doctype_token( '' ); * 'quirks' === $doctype->indicated_compatability_mode; * * // Textual quirks present in raw HTML are handled appropriately. * $doctype = WP_HTML_Doctype_Info::from_doctype_token( "" ); * 'no-quirks' === $doctype->indicated_compatability_mode; * * // Anything other than a proper DOCTYPE declaration token fails to parse. * null === WP_HTML_Doctype_Info::from_doctype_token( ' ' ); * null === WP_HTML_Doctype_Info::from_doctype_token( '

' ); * null === WP_HTML_Doctype_Info::from_doctype_token( '' ); * null === WP_HTML_Doctype_Info::from_doctype_token( 'html' ); * null === WP_HTML_Doctype_Info::from_doctype_token( '' ); * * @since 6.7.0 * * @param string $doctype_html The complete raw DOCTYPE HTML string, e.g. ``. * * @return WP_HTML_Doctype_Info|null A WP_HTML_Doctype_Info instance will be returned if the * provided DOCTYPE HTML is a valid DOCTYPE. Otherwise, null. */ public static function from_doctype_token( string $doctype_html ): ?self { $doctype_name = null; $doctype_public_id = null; $doctype_system_id = null; $end = strlen( $doctype_html ) - 1; /* * This parser combines the rules for parsing DOCTYPE tokens found in the HTML * specification for the DOCTYPE related tokenizer states. * * @see https://html.spec.whatwg.org/#doctype-state */ /* * - Valid DOCTYPE HTML token must be at least `` assuming a complete token not * ending in end-of-file. * - It must start with an ASCII case-insensitive match for `` must be the final byte in the HTML string. */ if ( $end < 9 || 0 !== substr_compare( $doctype_html, '`? if ( '>' !== $doctype_html[ $end ] || ( strcspn( $doctype_html, '>', $at ) + $at ) < $end ) { return null; } /* * Perform newline normalization and ensure the $end value is correct after normalization. * * @see https://html.spec.whatwg.org/#preprocessing-the-input-stream * @see https://infra.spec.whatwg.org/#normalize-newlines */ $doctype_html = str_replace( "\r\n", "\n", $doctype_html ); $doctype_html = str_replace( "\r", "\n", $doctype_html ); $end = strlen( $doctype_html ) - 1; /* * In this state, the doctype token has been found and its "content" optionally including the * name, public identifier, and system identifier is between the current position and the end. * * "" * ╰─ $at ╰─ $end * * It's also possible that the declaration part is empty. * * ╭─ $at * "" * ╰─ $end * * Rules for parsing ">" which terminates the DOCTYPE do not need to be considered as they * have been handled above in the condition that the provided DOCTYPE HTML must contain * exactly one ">" character in the final position. */ /* * * Parsing effectively begins in "Before DOCTYPE name state". Ignore whitespace and * proceed to the next state. * * @see https://html.spec.whatwg.org/#before-doctype-name-state */ $at += strspn( $doctype_html, " \t\n\f\r", $at ); if ( $at >= $end ) { return new self( $doctype_name, $doctype_public_id, $doctype_system_id, true ); } $name_length = strcspn( $doctype_html, " \t\n\f\r", $at, $end - $at ); $doctype_name = str_replace( "\0", "\u{FFFD}", strtolower( substr( $doctype_html, $at, $name_length ) ) ); $at += $name_length; $at += strspn( $doctype_html, " \t\n\f\r", $at, $end - $at ); if ( $at >= $end ) { return new self( $doctype_name, $doctype_public_id, $doctype_system_id, false ); } /* * "After DOCTYPE name state" * * Find a case-insensitive match for "PUBLIC" or "SYSTEM" at this point. * Otherwise, set force-quirks and enter bogus DOCTYPE state (skip the rest of the doctype). * * @see https://html.spec.whatwg.org/#after-doctype-name-state */ if ( $at + 6 >= $end ) { return new self( $doctype_name, $doctype_public_id, $doctype_system_id, true ); } /* * > If the six characters starting from the current input character are an ASCII * > case-insensitive match for the word "PUBLIC", then consume those characters * > and switch to the after DOCTYPE public keyword state. */ if ( 0 === substr_compare( $doctype_html, 'PUBLIC', $at, 6, true ) ) { $at += 6; $at += strspn( $doctype_html, " \t\n\f\r", $at, $end - $at ); if ( $at >= $end ) { return new self( $doctype_name, $doctype_public_id, $doctype_system_id, true ); } goto parse_doctype_public_identifier; } /* * > Otherwise, if the six characters starting from the current input character are an ASCII * > case-insensitive match for the word "SYSTEM", then consume those characters and switch * > to the after DOCTYPE system keyword state. */ if ( 0 === substr_compare( $doctype_html, 'SYSTEM', $at, 6, true ) ) { $at += 6; $at += strspn( $doctype_html, " \t\n\f\r", $at, $end - $at ); if ( $at >= $end ) { return new self( $doctype_name, $doctype_public_id, $doctype_system_id, true ); } goto parse_doctype_system_identifier; } /* * > Otherwise, this is an invalid-character-sequence-after-doctype-name parse error. * > Set the current DOCTYPE token's force-quirks flag to on. Reconsume in the bogus * > DOCTYPE state. */ return new self( $doctype_name, $doctype_public_id, $doctype_system_id, true ); parse_doctype_public_identifier: /* * The parser should enter "DOCTYPE public identifier (double-quoted) state" or * "DOCTYPE public identifier (single-quoted) state" by finding one of the valid quotes. * Anything else forces quirks mode and ignores the rest of the contents. * * @see https://html.spec.whatwg.org/#doctype-public-identifier-(double-quoted)-state * @see https://html.spec.whatwg.org/#doctype-public-identifier-(single-quoted)-state */ $closer_quote = $doctype_html[ $at ]; /* * > This is a missing-quote-before-doctype-public-identifier parse error. Set the * > current DOCTYPE token's force-quirks flag to on. Reconsume in the bogus DOCTYPE state. */ if ( '"' !== $closer_quote && "'" !== $closer_quote ) { return new self( $doctype_name, $doctype_public_id, $doctype_system_id, true ); } ++$at; $identifier_length = strcspn( $doctype_html, $closer_quote, $at, $end - $at ); $doctype_public_id = str_replace( "\0", "\u{FFFD}", substr( $doctype_html, $at, $identifier_length ) ); $at += $identifier_length; if ( $at >= $end || $closer_quote !== $doctype_html[ $at ] ) { return new self( $doctype_name, $doctype_public_id, $doctype_system_id, true ); } ++$at; /* * "Between DOCTYPE public and system identifiers state" * * Advance through whitespace between public and system identifiers. * * @see https://html.spec.whatwg.org/#between-doctype-public-and-system-identifiers-state */ $at += strspn( $doctype_html, " \t\n\f\r", $at, $end - $at ); if ( $at >= $end ) { return new self( $doctype_name, $doctype_public_id, $doctype_system_id, false ); } parse_doctype_system_identifier: /* * The parser should enter "DOCTYPE system identifier (double-quoted) state" or * "DOCTYPE system identifier (single-quoted) state" by finding one of the valid quotes. * Anything else forces quirks mode and ignores the rest of the contents. * * @see https://html.spec.whatwg.org/#doctype-system-identifier-(double-quoted)-state * @see https://html.spec.whatwg.org/#doctype-system-identifier-(single-quoted)-state */ $closer_quote = $doctype_html[ $at ]; /* * > This is a missing-quote-before-doctype-system-identifier parse error. Set the * > current DOCTYPE token's force-quirks flag to on. Reconsume in the bogus DOCTYPE state. */ if ( '"' !== $closer_quote && "'" !== $closer_quote ) { return new self( $doctype_name, $doctype_public_id, $doctype_system_id, true ); } ++$at; $identifier_length = strcspn( $doctype_html, $closer_quote, $at, $end - $at ); $doctype_system_id = str_replace( "\0", "\u{FFFD}", substr( $doctype_html, $at, $identifier_length ) ); $at += $identifier_length; if ( $at >= $end || $closer_quote !== $doctype_html[ $at ] ) { return new self( $doctype_name, $doctype_public_id, $doctype_system_id, true ); } return new self( $doctype_name, $doctype_public_id, $doctype_system_id, false ); } } PK<»–[±FœM!class-wp-html-attribute-token.phpnu„[µü¤name = $name; $this->value_starts_at = $value_start; $this->value_length = $value_length; $this->start = $start; $this->end = $end; $this->is_true = $is_true; } } PK<»–[,M÷  class-wp-html-span.phpnu„[µü¤start = $start; $this->end = $end; } } PK<»–[P°&DD'class-wp-html-unsupported-exception.phpnu„[µü¤ Initially, the stack of open elements is empty. The stack grows * > downwards; the topmost node on the stack is the first one added * > to the stack, and the bottommost node of the stack is the most * > recently added node in the stack (notwithstanding when the stack * > is manipulated in a random access fashion as part of the handling * > for misnested tags). * * @since 6.4.0 * * @access private * * @see https://html.spec.whatwg.org/#stack-of-open-elements * @see WP_HTML_Processor */ class WP_HTML_Open_Elements { /** * Holds the stack of open element references. * * @since 6.4.0 * * @var WP_HTML_Token[] */ public $stack = array(); /** * Whether a P element is in button scope currently. * * This class optimizes scope lookup by pre-calculating * this value when elements are added and removed to the * stack of open elements which might change its value. * This avoids frequent iteration over the stack. * * @since 6.4.0 * * @var bool */ private $has_p_in_button_scope = false; /** * Reports if a specific node is in the stack of open elements. * * @since 6.4.0 * * @param WP_HTML_Token $token Look for this node in the stack. * @return bool Whether the referenced node is in the stack of open elements. */ public function contains_node( $token ) { foreach ( $this->walk_up() as $item ) { if ( $token->bookmark_name === $item->bookmark_name ) { return true; } } return false; } /** * Returns how many nodes are currently in the stack of open elements. * * @since 6.4.0 * * @return int How many node are in the stack of open elements. */ public function count() { return count( $this->stack ); } /** * Returns the node at the end of the stack of open elements, * if one exists. If the stack is empty, returns null. * * @since 6.4.0 * * @return WP_HTML_Token|null Last node in the stack of open elements, if one exists, otherwise null. */ public function current_node() { $current_node = end( $this->stack ); return $current_node ? $current_node : null; } /** * Returns whether an element is in a specific scope. * * ## HTML Support * * This function skips checking for the termination list because there * are no supported elements which appear in the termination list. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#has-an-element-in-the-specific-scope * * @param string $tag_name Name of tag check. * @param string[] $termination_list List of elements that terminate the search. * @return bool Whether the element was found in a specific scope. */ public function has_element_in_specific_scope( $tag_name, $termination_list ) { foreach ( $this->walk_up() as $node ) { if ( $node->node_name === $tag_name ) { return true; } switch ( $node->node_name ) { case 'HTML': return false; } if ( in_array( $node->node_name, $termination_list, true ) ) { return true; } } return false; } /** * Returns whether a particular element is in scope. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#has-an-element-in-scope * * @param string $tag_name Name of tag to check. * @return bool Whether given element is in scope. */ public function has_element_in_scope( $tag_name ) { return $this->has_element_in_specific_scope( $tag_name, array( /* * Because it's not currently possible to encounter * one of the termination elements, they don't need * to be listed here. If they were, they would be * unreachable and only waste CPU cycles while * scanning through HTML. */ ) ); } /** * Returns whether a particular element is in list item scope. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#has-an-element-in-list-item-scope * * @throws WP_HTML_Unsupported_Exception Always until this function is implemented. * * @param string $tag_name Name of tag to check. * @return bool Whether given element is in scope. */ public function has_element_in_list_item_scope( $tag_name ) { throw new WP_HTML_Unsupported_Exception( 'Cannot process elements depending on list item scope.' ); return false; // The linter requires this unreachable code until the function is implemented and can return. } /** * Returns whether a particular element is in button scope. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#has-an-element-in-button-scope * * @param string $tag_name Name of tag to check. * @return bool Whether given element is in scope. */ public function has_element_in_button_scope( $tag_name ) { return $this->has_element_in_specific_scope( $tag_name, array( 'BUTTON' ) ); } /** * Returns whether a particular element is in table scope. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#has-an-element-in-table-scope * * @throws WP_HTML_Unsupported_Exception Always until this function is implemented. * * @param string $tag_name Name of tag to check. * @return bool Whether given element is in scope. */ public function has_element_in_table_scope( $tag_name ) { throw new WP_HTML_Unsupported_Exception( 'Cannot process elements depending on table scope.' ); return false; // The linter requires this unreachable code until the function is implemented and can return. } /** * Returns whether a particular element is in select scope. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#has-an-element-in-select-scope * * @throws WP_HTML_Unsupported_Exception Always until this function is implemented. * * @param string $tag_name Name of tag to check. * @return bool Whether given element is in scope. */ public function has_element_in_select_scope( $tag_name ) { throw new WP_HTML_Unsupported_Exception( 'Cannot process elements depending on select scope.' ); return false; // The linter requires this unreachable code until the function is implemented and can return. } /** * Returns whether a P is in BUTTON scope. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#has-an-element-in-button-scope * * @return bool Whether a P is in BUTTON scope. */ public function has_p_in_button_scope() { return $this->has_p_in_button_scope; } /** * Pops a node off of the stack of open elements. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#stack-of-open-elements * * @return bool Whether a node was popped off of the stack. */ public function pop() { $item = array_pop( $this->stack ); if ( null === $item ) { return false; } $this->after_element_pop( $item ); return true; } /** * Pops nodes off of the stack of open elements until one with the given tag name has been popped. * * @since 6.4.0 * * @see WP_HTML_Open_Elements::pop * * @param string $tag_name Name of tag that needs to be popped off of the stack of open elements. * @return bool Whether a tag of the given name was found and popped off of the stack of open elements. */ public function pop_until( $tag_name ) { foreach ( $this->walk_up() as $item ) { $this->pop(); if ( $tag_name === $item->node_name ) { return true; } } return false; } /** * Pushes a node onto the stack of open elements. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#stack-of-open-elements * * @param WP_HTML_Token $stack_item Item to add onto stack. */ public function push( $stack_item ) { $this->stack[] = $stack_item; $this->after_element_push( $stack_item ); } /** * Removes a specific node from the stack of open elements. * * @since 6.4.0 * * @param WP_HTML_Token $token The node to remove from the stack of open elements. * @return bool Whether the node was found and removed from the stack of open elements. */ public function remove_node( $token ) { foreach ( $this->walk_up() as $position_from_end => $item ) { if ( $token->bookmark_name !== $item->bookmark_name ) { continue; } $position_from_start = $this->count() - $position_from_end - 1; array_splice( $this->stack, $position_from_start, 1 ); $this->after_element_pop( $item ); return true; } return false; } /** * Steps through the stack of open elements, starting with the top element * (added first) and walking downwards to the one added last. * * This generator function is designed to be used inside a "foreach" loop. * * Example: * * $html = 'We are here'; * foreach ( $stack->walk_down() as $node ) { * echo "{$node->node_name} -> "; * } * > EM -> STRONG -> A -> * * To start with the most-recently added element and walk towards the top, * see WP_HTML_Open_Elements::walk_up(). * * @since 6.4.0 */ public function walk_down() { $count = count( $this->stack ); for ( $i = 0; $i < $count; $i++ ) { yield $this->stack[ $i ]; } } /** * Steps through the stack of open elements, starting with the bottom element * (added last) and walking upwards to the one added first. * * This generator function is designed to be used inside a "foreach" loop. * * Example: * * $html = 'We are here'; * foreach ( $stack->walk_up() as $node ) { * echo "{$node->node_name} -> "; * } * > A -> STRONG -> EM -> * * To start with the first added element and walk towards the bottom, * see WP_HTML_Open_Elements::walk_down(). * * @since 6.4.0 */ public function walk_up() { for ( $i = count( $this->stack ) - 1; $i >= 0; $i-- ) { yield $this->stack[ $i ]; } } /* * Internal helpers. */ /** * Updates internal flags after adding an element. * * Certain conditions (such as "has_p_in_button_scope") are maintained here as * flags that are only modified when adding and removing elements. This allows * the HTML Processor to quickly check for these conditions instead of iterating * over the open stack elements upon each new tag it encounters. These flags, * however, need to be maintained as items are added and removed from the stack. * * @since 6.4.0 * * @param WP_HTML_Token $item Element that was added to the stack of open elements. */ public function after_element_push( $item ) { /* * When adding support for new elements, expand this switch to trap * cases where the precalculated value needs to change. */ switch ( $item->node_name ) { case 'BUTTON': $this->has_p_in_button_scope = false; break; case 'P': $this->has_p_in_button_scope = true; break; } } /** * Updates internal flags after removing an element. * * Certain conditions (such as "has_p_in_button_scope") are maintained here as * flags that are only modified when adding and removing elements. This allows * the HTML Processor to quickly check for these conditions instead of iterating * over the open stack elements upon each new tag it encounters. These flags, * however, need to be maintained as items are added and removed from the stack. * * @since 6.4.0 * * @param WP_HTML_Token $item Element that was removed from the stack of open elements. */ public function after_element_pop( $item ) { /* * When adding support for new elements, expand this switch to trap * cases where the precalculated value needs to change. */ switch ( $item->node_name ) { case 'BUTTON': $this->has_p_in_button_scope = $this->has_element_in_button_scope( 'P' ); break; case 'P': $this->has_p_in_button_scope = $this->has_element_in_button_scope( 'P' ); break; } } } PK<»–[MzW8b¶b¶class-wp-html-processor.phpnu„[µü¤next_tag( array( 'breadcrumbs' => array( 'DIV', 'FIGURE', 'IMG' ) ) ) ) { * $processor->add_class( 'responsive-image' ); * } * * #### Breadcrumbs * * Breadcrumbs represent the stack of open elements from the root * of the document or fragment down to the currently-matched node, * if one is currently selected. Call WP_HTML_Processor::get_breadcrumbs() * to inspect the breadcrumbs for a matched tag. * * Breadcrumbs can specify nested HTML structure and are equivalent * to a CSS selector comprising tag names separated by the child * combinator, such as "DIV > FIGURE > IMG". * * Since all elements find themselves inside a full HTML document * when parsed, the return value from `get_breadcrumbs()` will always * contain any implicit outermost elements. For example, when parsing * with `create_fragment()` in the `BODY` context (the default), any * tag in the given HTML document will contain `array( 'HTML', 'BODY', … )` * in its breadcrumbs. * * Despite containing the implied outermost elements in their breadcrumbs, * tags may be found with the shortest-matching breadcrumb query. That is, * `array( 'IMG' )` matches all IMG elements and `array( 'P', 'IMG' )` * matches all IMG elements directly inside a P element. To ensure that no * partial matches erroneously match it's possible to specify in a query * the full breadcrumb match all the way down from the root HTML element. * * Example: * * $html = '

A lovely day outside
'; * // ----- Matches here. * $processor->next_tag( array( 'breadcrumbs' => array( 'FIGURE', 'IMG' ) ) ); * * $html = '
A lovely day outside
'; * // ---- Matches here. * $processor->next_tag( array( 'breadcrumbs' => array( 'FIGURE', 'FIGCAPTION', 'EM' ) ) ); * * $html = '
'; * // ----- Matches here, because IMG must be a direct child of the implicit BODY. * $processor->next_tag( array( 'breadcrumbs' => array( 'BODY', 'IMG' ) ) ); * * ## HTML Support * * This class implements a small part of the HTML5 specification. * It's designed to operate within its support and abort early whenever * encountering circumstances it can't properly handle. This is * the principle way in which this class remains as simple as possible * without cutting corners and breaking compliance. * * ### Supported elements * * If any unsupported element appears in the HTML input the HTML Processor * will abort early and stop all processing. This draconian measure ensures * that the HTML Processor won't break any HTML it doesn't fully understand. * * The following list specifies the HTML tags that _are_ supported: * * - Links: A. * - The formatting elements: B, BIG, CODE, EM, FONT, I, SMALL, STRIKE, STRONG, TT, U. * - Containers: DIV, FIGCAPTION, FIGURE, SPAN. * - Form elements: BUTTON. * - Paragraph: P. * - Void elements: IMG. * * ### Supported markup * * Some kinds of non-normative HTML involve reconstruction of formatting elements and * re-parenting of mis-nested elements. For example, a DIV tag found inside a TABLE * may in fact belong _before_ the table in the DOM. If the HTML Processor encounters * such a case it will stop processing. * * The following list specifies HTML markup that _is_ supported: * * - Markup involving only those tags listed above. * - Fully-balanced and non-overlapping tags. * - HTML with unexpected tag closers. * - Some unbalanced or overlapping tags. * - P tags after unclosed P tags. * - BUTTON tags after unclosed BUTTON tags. * - A tags after unclosed A tags that don't involve any active formatting elements. * * @since 6.4.0 * * @see WP_HTML_Tag_Processor * @see https://html.spec.whatwg.org/ */ class WP_HTML_Processor extends WP_HTML_Tag_Processor { /** * The maximum number of bookmarks allowed to exist at any given time. * * HTML processing requires more bookmarks than basic tag processing, * so this class constant from the Tag Processor is overwritten. * * @since 6.4.0 * * @var int */ const MAX_BOOKMARKS = 100; /** * Static query for instructing the Tag Processor to visit every token. * * @access private * * @since 6.4.0 * * @var array */ const VISIT_EVERYTHING = array( 'tag_closers' => 'visit' ); /** * Holds the working state of the parser, including the stack of * open elements and the stack of active formatting elements. * * Initialized in the constructor. * * @since 6.4.0 * * @var WP_HTML_Processor_State */ private $state = null; /** * Used to create unique bookmark names. * * This class sets a bookmark for every tag in the HTML document that it encounters. * The bookmark name is auto-generated and increments, starting with `1`. These are * internal bookmarks and are automatically released when the referring WP_HTML_Token * goes out of scope and is garbage-collected. * * @since 6.4.0 * * @see WP_HTML_Processor::$release_internal_bookmark_on_destruct * * @var int */ private $bookmark_counter = 0; /** * Stores an explanation for why something failed, if it did. * * @see self::get_last_error * * @since 6.4.0 * * @var string|null */ private $last_error = null; /** * Releases a bookmark when PHP garbage-collects its wrapping WP_HTML_Token instance. * * This function is created inside the class constructor so that it can be passed to * the stack of open elements and the stack of active formatting elements without * exposing it as a public method on the class. * * @since 6.4.0 * * @var closure */ private $release_internal_bookmark_on_destruct = null; /* * Public Interface Functions */ /** * Creates an HTML processor in the fragment parsing mode. * * Use this for cases where you are processing chunks of HTML that * will be found within a bigger HTML document, such as rendered * block output that exists within a post, `the_content` inside a * rendered site layout. * * Fragment parsing occurs within a context, which is an HTML element * that the document will eventually be placed in. It becomes important * when special elements have different rules than others, such as inside * a TEXTAREA or a TITLE tag where things that look like tags are text, * or inside a SCRIPT tag where things that look like HTML syntax are JS. * * The context value should be a representation of the tag into which the * HTML is found. For most cases this will be the body element. The HTML * form is provided because a context element may have attributes that * impact the parse, such as with a SCRIPT tag and its `type` attribute. * * ## Current HTML Support * * - The only supported context is ``, which is the default value. * - The only supported document encoding is `UTF-8`, which is the default value. * * @since 6.4.0 * * @param string $html Input HTML fragment to process. * @param string $context Context element for the fragment, must be default of ``. * @param string $encoding Text encoding of the document; must be default of 'UTF-8'. * @return WP_HTML_Processor|null The created processor if successful, otherwise null. */ public static function create_fragment( $html, $context = '', $encoding = 'UTF-8' ) { if ( '' !== $context || 'UTF-8' !== $encoding ) { return null; } $p = new self( $html, self::CONSTRUCTOR_UNLOCK_CODE ); $p->state->context_node = array( 'BODY', array() ); $p->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY; // @TODO: Create "fake" bookmarks for non-existent but implied nodes. $p->bookmarks['root-node'] = new WP_HTML_Span( 0, 0 ); $p->bookmarks['context-node'] = new WP_HTML_Span( 0, 0 ); $p->state->stack_of_open_elements->push( new WP_HTML_Token( 'root-node', 'HTML', false ) ); $p->state->stack_of_open_elements->push( new WP_HTML_Token( 'context-node', $p->state->context_node[0], false ) ); return $p; } /** * Constructor. * * Do not use this method. Use the static creator methods instead. * * @access private * * @since 6.4.0 * * @see WP_HTML_Processor::create_fragment() * * @param string $html HTML to process. * @param string|null $use_the_static_create_methods_instead This constructor should not be called manually. */ public function __construct( $html, $use_the_static_create_methods_instead = null ) { parent::__construct( $html ); if ( self::CONSTRUCTOR_UNLOCK_CODE !== $use_the_static_create_methods_instead ) { _doing_it_wrong( __METHOD__, sprintf( /* translators: %s: WP_HTML_Processor::create_fragment(). */ __( 'Call %s to create an HTML Processor instead of calling the constructor directly.' ), 'WP_HTML_Processor::create_fragment()' ), '6.4.0' ); } $this->state = new WP_HTML_Processor_State(); /* * Create this wrapper so that it's possible to pass * a private method into WP_HTML_Token classes without * exposing it to any public API. */ $this->release_internal_bookmark_on_destruct = function ( $name ) { parent::release_bookmark( $name ); }; } /** * Returns the last error, if any. * * Various situations lead to parsing failure but this class will * return `false` in all those cases. To determine why something * failed it's possible to request the last error. This can be * helpful to know to distinguish whether a given tag couldn't * be found or if content in the document caused the processor * to give up and abort processing. * * Example * * $processor = WP_HTML_Processor::create_fragment( '