HEAD;
return true;
/*
* > An end tag whose tag name is one of: "body", "html", "br"
*
* BR tags are always reported by the Tag Processor as opening tags.
*/
case '-BODY':
case '-HTML':
/*
* > Act as described in the "anything else" entry below.
*/
goto in_head_anything_else;
break;
/*
* > A start tag whose tag name is "template"
*
* @todo Could the adjusted insertion location be anything other than the current location?
*/
case '+TEMPLATE':
$this->state->active_formatting_elements->insert_marker();
$this->state->frameset_ok = false;
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TEMPLATE;
$this->state->stack_of_template_insertion_modes[] = WP_HTML_Processor_State::INSERTION_MODE_IN_TEMPLATE;
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > An end tag whose tag name is "template"
*/
case '-TEMPLATE':
if ( ! $this->state->stack_of_open_elements->contains( 'TEMPLATE' ) ) {
// @todo Indicate a parse error once it's possible.
return $this->step();
}
$this->generate_implied_end_tags_thoroughly();
if ( ! $this->state->stack_of_open_elements->current_node_is( 'TEMPLATE' ) ) {
// @todo Indicate a parse error once it's possible.
}
$this->state->stack_of_open_elements->pop_until( 'TEMPLATE' );
$this->state->active_formatting_elements->clear_up_to_last_marker();
array_pop( $this->state->stack_of_template_insertion_modes );
$this->reset_insertion_mode_appropriately();
return true;
}
/*
* > A start tag whose tag name is "head"
* > Any other end tag
*/
if ( '+HEAD' === $op || $is_closer ) {
// Parse error: ignore the token.
return $this->step();
}
/*
* > Anything else
*/
in_head_anything_else:
$this->state->stack_of_open_elements->pop();
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_AFTER_HEAD;
return $this->step( self::REPROCESS_CURRENT_NODE );
}
/**
* Parses next element in the 'in head noscript' insertion mode.
*
* This internal function performs the 'in head noscript' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0 Stub implementation.
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#parsing-main-inheadnoscript
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_in_head_noscript(): bool {
$token_name = $this->get_token_name();
$token_type = $this->get_token_type();
$is_closer = parent::is_tag_closer();
$op_sigil = '#tag' === $token_type ? ( $is_closer ? '-' : '+' ) : '';
$op = "{$op_sigil}{$token_name}";
switch ( $op ) {
/*
* > A character token that is one of U+0009 CHARACTER TABULATION,
* > U+000A LINE FEED (LF), U+000C FORM FEED (FF),
* > U+000D CARRIAGE RETURN (CR), or U+0020 SPACE
*
* Parse error: ignore the token.
*/
case '#text':
if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
return $this->step_in_head();
}
goto in_head_noscript_anything_else;
break;
/*
* > A DOCTYPE token
*/
case 'html':
// Parse error: ignore the token.
return $this->step();
/*
* > A start tag whose tag name is "html"
*/
case '+HTML':
return $this->step_in_body();
/*
* > An end tag whose tag name is "noscript"
*/
case '-NOSCRIPT':
$this->state->stack_of_open_elements->pop();
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_HEAD;
return true;
/*
* > A comment token
* >
* > A start tag whose tag name is one of: "basefont", "bgsound",
* > "link", "meta", "noframes", "style"
*/
case '#comment':
case '#funky-comment':
case '#presumptuous-tag':
case '+BASEFONT':
case '+BGSOUND':
case '+LINK':
case '+META':
case '+NOFRAMES':
case '+STYLE':
return $this->step_in_head();
/*
* > An end tag whose tag name is "br"
*
* This should never happen, as the Tag Processor prevents showing a BR closing tag.
*/
}
/*
* > A start tag whose tag name is one of: "head", "noscript"
* > Any other end tag
*/
if ( '+HEAD' === $op || '+NOSCRIPT' === $op || $is_closer ) {
// Parse error: ignore the token.
return $this->step();
}
/*
* > Anything else
*
* Anything here is a parse error.
*/
in_head_noscript_anything_else:
$this->state->stack_of_open_elements->pop();
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_HEAD;
return $this->step( self::REPROCESS_CURRENT_NODE );
}
/**
* Parses next element in the 'after head' insertion mode.
*
* This internal function performs the 'after head' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0 Stub implementation.
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#the-after-head-insertion-mode
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_after_head(): bool {
$token_name = $this->get_token_name();
$token_type = $this->get_token_type();
$is_closer = parent::is_tag_closer();
$op_sigil = '#tag' === $token_type ? ( $is_closer ? '-' : '+' ) : '';
$op = "{$op_sigil}{$token_name}";
switch ( $op ) {
/*
* > A character token that is one of U+0009 CHARACTER TABULATION,
* > U+000A LINE FEED (LF), U+000C FORM FEED (FF),
* > U+000D CARRIAGE RETURN (CR), or U+0020 SPACE
*/
case '#text':
if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
// Insert the character.
$this->insert_html_element( $this->state->current_token );
return true;
}
goto after_head_anything_else;
break;
/*
* > A comment token
*/
case '#comment':
case '#funky-comment':
case '#presumptuous-tag':
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A DOCTYPE token
*/
case 'html':
// Parse error: ignore the token.
return $this->step();
/*
* > A start tag whose tag name is "html"
*/
case '+HTML':
return $this->step_in_body();
/*
* > A start tag whose tag name is "body"
*/
case '+BODY':
$this->insert_html_element( $this->state->current_token );
$this->state->frameset_ok = false;
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY;
return true;
/*
* > A start tag whose tag name is "frameset"
*/
case '+FRAMESET':
$this->insert_html_element( $this->state->current_token );
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_FRAMESET;
return true;
/*
* > A start tag whose tag name is one of: "base", "basefont", "bgsound",
* > "link", "meta", "noframes", "script", "style", "template", "title"
*
* Anything here is a parse error.
*/
case '+BASE':
case '+BASEFONT':
case '+BGSOUND':
case '+LINK':
case '+META':
case '+NOFRAMES':
case '+SCRIPT':
case '+STYLE':
case '+TEMPLATE':
case '+TITLE':
/*
* > Push the node pointed to by the head element pointer onto the stack of open elements.
* > Process the token using the rules for the "in head" insertion mode.
* > Remove the node pointed to by the head element pointer from the stack of open elements. (It might not be the current node at this point.)
*/
$this->bail( 'Cannot process elements after HEAD which reopen the HEAD element.' );
/*
* Do not leave this break in when adding support; it's here to prevent
* WPCS from getting confused at the switch structure without a return,
* because it doesn't know that `bail()` always throws.
*/
break;
/*
* > An end tag whose tag name is "template"
*/
case '-TEMPLATE':
return $this->step_in_head();
/*
* > An end tag whose tag name is one of: "body", "html", "br"
*
* Closing BR tags are always reported by the Tag Processor as opening tags.
*/
case '-BODY':
case '-HTML':
/*
* > Act as described in the "anything else" entry below.
*/
goto after_head_anything_else;
break;
}
/*
* > A start tag whose tag name is "head"
* > Any other end tag
*/
if ( '+HEAD' === $op || $is_closer ) {
// Parse error: ignore the token.
return $this->step();
}
/*
* > Anything else
* > Insert an HTML element for a "body" start tag token with no attributes.
*/
after_head_anything_else:
$this->insert_virtual_node( 'BODY' );
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY;
return $this->step( self::REPROCESS_CURRENT_NODE );
}
/**
* Parses next element in the 'in body' insertion mode.
*
* This internal function performs the 'in body' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.4.0
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#parsing-main-inbody
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_in_body(): bool {
$token_name = $this->get_token_name();
$token_type = $this->get_token_type();
$op_sigil = '#tag' === $token_type ? ( parent::is_tag_closer() ? '-' : '+' ) : '';
$op = "{$op_sigil}{$token_name}";
switch ( $op ) {
case '#text':
/*
* > A character token that is U+0000 NULL
*
* Any successive sequence of NULL bytes is ignored and won't
* trigger active format reconstruction. Therefore, if the text
* only comprises NULL bytes then the token should be ignored
* here, but if there are any other characters in the stream
* the active formats should be reconstructed.
*/
if ( parent::TEXT_IS_NULL_SEQUENCE === $this->text_node_classification ) {
// Parse error: ignore the token.
return $this->step();
}
$this->reconstruct_active_formatting_elements();
/*
* Whitespace-only text does not affect the frameset-ok flag.
* It is probably inter-element whitespace, but it may also
* contain character references which decode only to whitespace.
*/
if ( parent::TEXT_IS_GENERIC === $this->text_node_classification ) {
$this->state->frameset_ok = false;
}
$this->insert_html_element( $this->state->current_token );
return true;
case '#comment':
case '#funky-comment':
case '#presumptuous-tag':
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A DOCTYPE token
* > Parse error. Ignore the token.
*/
case 'html':
return $this->step();
/*
* > A start tag whose tag name is "html"
*/
case '+HTML':
if ( ! $this->state->stack_of_open_elements->contains( 'TEMPLATE' ) ) {
/*
* > Otherwise, for each attribute on the token, check to see if the attribute
* > is already present on the top element of the stack of open elements. If
* > it is not, add the attribute and its corresponding value to that element.
*
* This parser does not currently support this behavior: ignore the token.
*/
}
// Ignore the token.
return $this->step();
/*
* > A start tag whose tag name is one of: "base", "basefont", "bgsound", "link",
* > "meta", "noframes", "script", "style", "template", "title"
* >
* > An end tag whose tag name is "template"
*/
case '+BASE':
case '+BASEFONT':
case '+BGSOUND':
case '+LINK':
case '+META':
case '+NOFRAMES':
case '+SCRIPT':
case '+STYLE':
case '+TEMPLATE':
case '+TITLE':
case '-TEMPLATE':
return $this->step_in_head();
/*
* > A start tag whose tag name is "body"
*
* This tag in the IN BODY insertion mode is a parse error.
*/
case '+BODY':
if (
1 === $this->state->stack_of_open_elements->count() ||
'BODY' !== ( $this->state->stack_of_open_elements->at( 2 )->node_name ?? null ) ||
$this->state->stack_of_open_elements->contains( 'TEMPLATE' )
) {
// Ignore the token.
return $this->step();
}
/*
* > Otherwise, set the frameset-ok flag to "not ok"; then, for each attribute
* > on the token, check to see if the attribute is already present on the body
* > element (the second element) on the stack of open elements, and if it is
* > not, add the attribute and its corresponding value to that element.
*
* This parser does not currently support this behavior: ignore the token.
*/
$this->state->frameset_ok = false;
return $this->step();
/*
* > A start tag whose tag name is "frameset"
*
* This tag in the IN BODY insertion mode is a parse error.
*/
case '+FRAMESET':
if (
1 === $this->state->stack_of_open_elements->count() ||
'BODY' !== ( $this->state->stack_of_open_elements->at( 2 )->node_name ?? null ) ||
false === $this->state->frameset_ok
) {
// Ignore the token.
return $this->step();
}
/*
* > Otherwise, run the following steps:
*/
$this->bail( 'Cannot process non-ignored FRAMESET tags.' );
break;
/*
* > An end tag whose tag name is "body"
*/
case '-BODY':
if ( ! $this->state->stack_of_open_elements->has_element_in_scope( 'BODY' ) ) {
// Parse error: ignore the token.
return $this->step();
}
/*
* > Otherwise, if there is a node in the stack of open elements that is not either a
* > dd element, a dt element, an li element, an optgroup element, an option element,
* > a p element, an rb element, an rp element, an rt element, an rtc element, a tbody
* > element, a td element, a tfoot element, a th element, a thread element, a tr
* > element, the body element, or the html element, then this is a parse error.
*
* There is nothing to do for this parse error, so don't check for it.
*/
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_AFTER_BODY;
/*
* The BODY element is not removed from the stack of open elements.
* Only internal state has changed, this does not qualify as a "step"
* in terms of advancing through the document to another token.
* Nothing has been pushed or popped.
* Proceed to parse the next item.
*/
return $this->step();
/*
* > An end tag whose tag name is "html"
*/
case '-HTML':
if ( ! $this->state->stack_of_open_elements->has_element_in_scope( 'BODY' ) ) {
// Parse error: ignore the token.
return $this->step();
}
/*
* > Otherwise, if there is a node in the stack of open elements that is not either a
* > dd element, a dt element, an li element, an optgroup element, an option element,
* > a p element, an rb element, an rp element, an rt element, an rtc element, a tbody
* > element, a td element, a tfoot element, a th element, a thread element, a tr
* > element, the body element, or the html element, then this is a parse error.
*
* There is nothing to do for this parse error, so don't check for it.
*/
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_AFTER_BODY;
return $this->step( self::REPROCESS_CURRENT_NODE );
/*
* > A start tag whose tag name is one of: "address", "article", "aside",
* > "blockquote", "center", "details", "dialog", "dir", "div", "dl",
* > "fieldset", "figcaption", "figure", "footer", "header", "hgroup",
* > "main", "menu", "nav", "ol", "p", "search", "section", "summary", "ul"
*/
case '+ADDRESS':
case '+ARTICLE':
case '+ASIDE':
case '+BLOCKQUOTE':
case '+CENTER':
case '+DETAILS':
case '+DIALOG':
case '+DIR':
case '+DIV':
case '+DL':
case '+FIELDSET':
case '+FIGCAPTION':
case '+FIGURE':
case '+FOOTER':
case '+HEADER':
case '+HGROUP':
case '+MAIN':
case '+MENU':
case '+NAV':
case '+OL':
case '+P':
case '+SEARCH':
case '+SECTION':
case '+SUMMARY':
case '+UL':
if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
$this->close_a_p_element();
}
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A start tag whose tag name is one of: "h1", "h2", "h3", "h4", "h5", "h6"
*/
case '+H1':
case '+H2':
case '+H3':
case '+H4':
case '+H5':
case '+H6':
if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
$this->close_a_p_element();
}
if (
in_array(
$this->state->stack_of_open_elements->current_node()->node_name,
array( 'H1', 'H2', 'H3', 'H4', 'H5', 'H6' ),
true
)
) {
// @todo Indicate a parse error once it's possible.
$this->state->stack_of_open_elements->pop();
}
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A start tag whose tag name is one of: "pre", "listing"
*/
case '+PRE':
case '+LISTING':
if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
$this->close_a_p_element();
}
/*
* > If the next token is a U+000A LINE FEED (LF) character token,
* > then ignore that token and move on to the next one. (Newlines
* > at the start of pre blocks are ignored as an authoring convenience.)
*
* This is handled in `get_modifiable_text()`.
*/
$this->insert_html_element( $this->state->current_token );
$this->state->frameset_ok = false;
return true;
/*
* > A start tag whose tag name is "form"
*/
case '+FORM':
$stack_contains_template = $this->state->stack_of_open_elements->contains( 'TEMPLATE' );
if ( isset( $this->state->form_element ) && ! $stack_contains_template ) {
// Parse error: ignore the token.
return $this->step();
}
if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
$this->close_a_p_element();
}
$this->insert_html_element( $this->state->current_token );
if ( ! $stack_contains_template ) {
$this->state->form_element = $this->state->current_token;
}
return true;
/*
* > A start tag whose tag name is "li"
* > A start tag whose tag name is one of: "dd", "dt"
*/
case '+DD':
case '+DT':
case '+LI':
$this->state->frameset_ok = false;
$node = $this->state->stack_of_open_elements->current_node();
$is_li = 'LI' === $token_name;
in_body_list_loop:
/*
* The logic for LI and DT/DD is the same except for one point: LI elements _only_
* close other LI elements, but a DT or DD element closes _any_ open DT or DD element.
*/
if ( $is_li ? 'LI' === $node->node_name : ( 'DD' === $node->node_name || 'DT' === $node->node_name ) ) {
$node_name = $is_li ? 'LI' : $node->node_name;
$this->generate_implied_end_tags( $node_name );
if ( ! $this->state->stack_of_open_elements->current_node_is( $node_name ) ) {
// @todo Indicate a parse error once it's possible. This error does not impact the logic here.
}
$this->state->stack_of_open_elements->pop_until( $node_name );
goto in_body_list_done;
}
if (
'ADDRESS' !== $node->node_name &&
'DIV' !== $node->node_name &&
'P' !== $node->node_name &&
self::is_special( $node )
) {
/*
* > If node is in the special category, but is not an address, div,
* > or p element, then jump to the step labeled done below.
*/
goto in_body_list_done;
} else {
/*
* > Otherwise, set node to the previous entry in the stack of open elements
* > and return to the step labeled loop.
*/
foreach ( $this->state->stack_of_open_elements->walk_up( $node ) as $item ) {
$node = $item;
break;
}
goto in_body_list_loop;
}
in_body_list_done:
if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
$this->close_a_p_element();
}
$this->insert_html_element( $this->state->current_token );
return true;
case '+PLAINTEXT':
if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
$this->close_a_p_element();
}
/*
* @todo This may need to be handled in the Tag Processor and turn into
* a single self-contained tag like TEXTAREA, whose modifiable text
* is the rest of the input document as plaintext.
*/
$this->bail( 'Cannot process PLAINTEXT elements.' );
break;
/*
* > A start tag whose tag name is "button"
*/
case '+BUTTON':
if ( $this->state->stack_of_open_elements->has_element_in_scope( 'BUTTON' ) ) {
// @todo Indicate a parse error once it's possible. This error does not impact the logic here.
$this->generate_implied_end_tags();
$this->state->stack_of_open_elements->pop_until( 'BUTTON' );
}
$this->reconstruct_active_formatting_elements();
$this->insert_html_element( $this->state->current_token );
$this->state->frameset_ok = false;
return true;
/*
* > An end tag whose tag name is one of: "address", "article", "aside", "blockquote",
* > "button", "center", "details", "dialog", "dir", "div", "dl", "fieldset",
* > "figcaption", "figure", "footer", "header", "hgroup", "listing", "main",
* > "menu", "nav", "ol", "pre", "search", "section", "summary", "ul"
*/
case '-ADDRESS':
case '-ARTICLE':
case '-ASIDE':
case '-BLOCKQUOTE':
case '-BUTTON':
case '-CENTER':
case '-DETAILS':
case '-DIALOG':
case '-DIR':
case '-DIV':
case '-DL':
case '-FIELDSET':
case '-FIGCAPTION':
case '-FIGURE':
case '-FOOTER':
case '-HEADER':
case '-HGROUP':
case '-LISTING':
case '-MAIN':
case '-MENU':
case '-NAV':
case '-OL':
case '-PRE':
case '-SEARCH':
case '-SECTION':
case '-SUMMARY':
case '-UL':
if ( ! $this->state->stack_of_open_elements->has_element_in_scope( $token_name ) ) {
// @todo Report parse error.
// Ignore the token.
return $this->step();
}
$this->generate_implied_end_tags();
if ( ! $this->state->stack_of_open_elements->current_node_is( $token_name ) ) {
// @todo Record parse error: this error doesn't impact parsing.
}
$this->state->stack_of_open_elements->pop_until( $token_name );
return true;
/*
* > An end tag whose tag name is "form"
*/
case '-FORM':
if ( ! $this->state->stack_of_open_elements->contains( 'TEMPLATE' ) ) {
$node = $this->state->form_element;
$this->state->form_element = null;
/*
* > If node is null or if the stack of open elements does not have node
* > in scope, then this is a parse error; return and ignore the token.
*
* @todo It's necessary to check if the form token itself is in scope, not
* simply whether any FORM is in scope.
*/
if (
null === $node ||
! $this->state->stack_of_open_elements->has_element_in_scope( 'FORM' )
) {
// Parse error: ignore the token.
return $this->step();
}
$this->generate_implied_end_tags();
if ( $node !== $this->state->stack_of_open_elements->current_node() ) {
// @todo Indicate a parse error once it's possible. This error does not impact the logic here.
$this->bail( 'Cannot close a FORM when other elements remain open as this would throw off the breadcrumbs for the following tokens.' );
}
$this->state->stack_of_open_elements->remove_node( $node );
return true;
} else {
/*
* > If the stack of open elements does not have a form element in scope,
* > then this is a parse error; return and ignore the token.
*
* Note that unlike in the clause above, this is checking for any FORM in scope.
*/
if ( ! $this->state->stack_of_open_elements->has_element_in_scope( 'FORM' ) ) {
// Parse error: ignore the token.
return $this->step();
}
$this->generate_implied_end_tags();
if ( ! $this->state->stack_of_open_elements->current_node_is( 'FORM' ) ) {
// @todo Indicate a parse error once it's possible. This error does not impact the logic here.
}
$this->state->stack_of_open_elements->pop_until( 'FORM' );
return true;
}
break;
/*
* > An end tag whose tag name is "p"
*/
case '-P':
if ( ! $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
$this->insert_html_element( $this->state->current_token );
}
$this->close_a_p_element();
return true;
/*
* > An end tag whose tag name is "li"
* > An end tag whose tag name is one of: "dd", "dt"
*/
case '-DD':
case '-DT':
case '-LI':
if (
/*
* An end tag whose tag name is "li":
* If the stack of open elements does not have an li element in list item scope,
* then this is a parse error; ignore the token.
*/
(
'LI' === $token_name &&
! $this->state->stack_of_open_elements->has_element_in_list_item_scope( 'LI' )
) ||
/*
* An end tag whose tag name is one of: "dd", "dt":
* If the stack of open elements does not have an element in scope that is an
* HTML element with the same tag name as that of the token, then this is a
* parse error; ignore the token.
*/
(
'LI' !== $token_name &&
! $this->state->stack_of_open_elements->has_element_in_scope( $token_name )
)
) {
/*
* This is a parse error, ignore the token.
*
* @todo Indicate a parse error once it's possible.
*/
return $this->step();
}
$this->generate_implied_end_tags( $token_name );
if ( ! $this->state->stack_of_open_elements->current_node_is( $token_name ) ) {
// @todo Indicate a parse error once it's possible. This error does not impact the logic here.
}
$this->state->stack_of_open_elements->pop_until( $token_name );
return true;
/*
* > An end tag whose tag name is one of: "h1", "h2", "h3", "h4", "h5", "h6"
*/
case '-H1':
case '-H2':
case '-H3':
case '-H4':
case '-H5':
case '-H6':
if ( ! $this->state->stack_of_open_elements->has_element_in_scope( '(internal: H1 through H6 - do not use)' ) ) {
/*
* This is a parse error; ignore the token.
*
* @todo Indicate a parse error once it's possible.
*/
return $this->step();
}
$this->generate_implied_end_tags();
if ( ! $this->state->stack_of_open_elements->current_node_is( $token_name ) ) {
// @todo Record parse error: this error doesn't impact parsing.
}
$this->state->stack_of_open_elements->pop_until( '(internal: H1 through H6 - do not use)' );
return true;
/*
* > A start tag whose tag name is "a"
*/
case '+A':
foreach ( $this->state->active_formatting_elements->walk_up() as $item ) {
switch ( $item->node_name ) {
case 'marker':
break 2;
case 'A':
$this->run_adoption_agency_algorithm();
$this->state->active_formatting_elements->remove_node( $item );
$this->state->stack_of_open_elements->remove_node( $item );
break 2;
}
}
$this->reconstruct_active_formatting_elements();
$this->insert_html_element( $this->state->current_token );
$this->state->active_formatting_elements->push( $this->state->current_token );
return true;
/*
* > A start tag whose tag name is one of: "b", "big", "code", "em", "font", "i",
* > "s", "small", "strike", "strong", "tt", "u"
*/
case '+B':
case '+BIG':
case '+CODE':
case '+EM':
case '+FONT':
case '+I':
case '+S':
case '+SMALL':
case '+STRIKE':
case '+STRONG':
case '+TT':
case '+U':
$this->reconstruct_active_formatting_elements();
$this->insert_html_element( $this->state->current_token );
$this->state->active_formatting_elements->push( $this->state->current_token );
return true;
/*
* > A start tag whose tag name is "nobr"
*/
case '+NOBR':
$this->reconstruct_active_formatting_elements();
if ( $this->state->stack_of_open_elements->has_element_in_scope( 'NOBR' ) ) {
// Parse error.
$this->run_adoption_agency_algorithm();
$this->reconstruct_active_formatting_elements();
}
$this->insert_html_element( $this->state->current_token );
$this->state->active_formatting_elements->push( $this->state->current_token );
return true;
/*
* > An end tag whose tag name is one of: "a", "b", "big", "code", "em", "font", "i",
* > "nobr", "s", "small", "strike", "strong", "tt", "u"
*/
case '-A':
case '-B':
case '-BIG':
case '-CODE':
case '-EM':
case '-FONT':
case '-I':
case '-NOBR':
case '-S':
case '-SMALL':
case '-STRIKE':
case '-STRONG':
case '-TT':
case '-U':
$this->run_adoption_agency_algorithm();
return true;
/*
* > A start tag whose tag name is one of: "applet", "marquee", "object"
*/
case '+APPLET':
case '+MARQUEE':
case '+OBJECT':
$this->reconstruct_active_formatting_elements();
$this->insert_html_element( $this->state->current_token );
$this->state->active_formatting_elements->insert_marker();
$this->state->frameset_ok = false;
return true;
/*
* > A end tag token whose tag name is one of: "applet", "marquee", "object"
*/
case '-APPLET':
case '-MARQUEE':
case '-OBJECT':
if ( ! $this->state->stack_of_open_elements->has_element_in_scope( $token_name ) ) {
// Parse error: ignore the token.
return $this->step();
}
$this->generate_implied_end_tags();
if ( ! $this->state->stack_of_open_elements->current_node_is( $token_name ) ) {
// This is a parse error.
}
$this->state->stack_of_open_elements->pop_until( $token_name );
$this->state->active_formatting_elements->clear_up_to_last_marker();
return true;
/*
* > A start tag whose tag name is "table"
*/
case '+TABLE':
/*
* > If the Document is not set to quirks mode, and the stack of open elements
* > has a p element in button scope, then close a p element.
*/
if (
WP_HTML_Tag_Processor::QUIRKS_MODE !== $this->compat_mode &&
$this->state->stack_of_open_elements->has_p_in_button_scope()
) {
$this->close_a_p_element();
}
$this->insert_html_element( $this->state->current_token );
$this->state->frameset_ok = false;
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE;
return true;
/*
* > An end tag whose tag name is "br"
*
* This is prevented from happening because the Tag Processor
* reports all closing BR tags as if they were opening tags.
*/
/*
* > A start tag whose tag name is one of: "area", "br", "embed", "img", "keygen", "wbr"
*/
case '+AREA':
case '+BR':
case '+EMBED':
case '+IMG':
case '+KEYGEN':
case '+WBR':
$this->reconstruct_active_formatting_elements();
$this->insert_html_element( $this->state->current_token );
$this->state->frameset_ok = false;
return true;
/*
* > A start tag whose tag name is "input"
*/
case '+INPUT':
$this->reconstruct_active_formatting_elements();
$this->insert_html_element( $this->state->current_token );
/*
* > If the token does not have an attribute with the name "type", or if it does,
* > but that attribute's value is not an ASCII case-insensitive match for the
* > string "hidden", then: set the frameset-ok flag to "not ok".
*/
$type_attribute = $this->get_attribute( 'type' );
if ( ! is_string( $type_attribute ) || 'hidden' !== strtolower( $type_attribute ) ) {
$this->state->frameset_ok = false;
}
return true;
/*
* > A start tag whose tag name is one of: "param", "source", "track"
*/
case '+PARAM':
case '+SOURCE':
case '+TRACK':
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A start tag whose tag name is "hr"
*/
case '+HR':
if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
$this->close_a_p_element();
}
$this->insert_html_element( $this->state->current_token );
$this->state->frameset_ok = false;
return true;
/*
* > A start tag whose tag name is "image"
*/
case '+IMAGE':
/*
* > Parse error. Change the token's tag name to "img" and reprocess it. (Don't ask.)
*
* Note that this is handled elsewhere, so it should not be possible to reach this code.
*/
$this->bail( "Cannot process an IMAGE tag. (Don't ask.)" );
break;
/*
* > A start tag whose tag name is "textarea"
*/
case '+TEXTAREA':
$this->insert_html_element( $this->state->current_token );
/*
* > If the next token is a U+000A LINE FEED (LF) character token, then ignore
* > that token and move on to the next one. (Newlines at the start of
* > textarea elements are ignored as an authoring convenience.)
*
* This is handled in `get_modifiable_text()`.
*/
$this->state->frameset_ok = false;
/*
* > Switch the insertion mode to "text".
*
* As a self-contained node, this behavior is handled in the Tag Processor.
*/
return true;
/*
* > A start tag whose tag name is "xmp"
*/
case '+XMP':
if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
$this->close_a_p_element();
}
$this->reconstruct_active_formatting_elements();
$this->state->frameset_ok = false;
/*
* > Follow the generic raw text element parsing algorithm.
*
* As a self-contained node, this behavior is handled in the Tag Processor.
*/
$this->insert_html_element( $this->state->current_token );
return true;
/*
* A start tag whose tag name is "iframe"
*/
case '+IFRAME':
$this->state->frameset_ok = false;
/*
* > Follow the generic raw text element parsing algorithm.
*
* As a self-contained node, this behavior is handled in the Tag Processor.
*/
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A start tag whose tag name is "noembed"
* > A start tag whose tag name is "noscript", if the scripting flag is enabled
*
* The scripting flag is never enabled in this parser.
*/
case '+NOEMBED':
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A start tag whose tag name is "select"
*/
case '+SELECT':
$this->reconstruct_active_formatting_elements();
$this->insert_html_element( $this->state->current_token );
$this->state->frameset_ok = false;
switch ( $this->state->insertion_mode ) {
/*
* > If the insertion mode is one of "in table", "in caption", "in table body", "in row",
* > or "in cell", then switch the insertion mode to "in select in table".
*/
case WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE:
case WP_HTML_Processor_State::INSERTION_MODE_IN_CAPTION:
case WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY:
case WP_HTML_Processor_State::INSERTION_MODE_IN_ROW:
case WP_HTML_Processor_State::INSERTION_MODE_IN_CELL:
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_SELECT_IN_TABLE;
break;
/*
* > Otherwise, switch the insertion mode to "in select".
*/
default:
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_SELECT;
break;
}
return true;
/*
* > A start tag whose tag name is one of: "optgroup", "option"
*/
case '+OPTGROUP':
case '+OPTION':
if ( $this->state->stack_of_open_elements->current_node_is( 'OPTION' ) ) {
$this->state->stack_of_open_elements->pop();
}
$this->reconstruct_active_formatting_elements();
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A start tag whose tag name is one of: "rb", "rtc"
*/
case '+RB':
case '+RTC':
if ( $this->state->stack_of_open_elements->has_element_in_scope( 'RUBY' ) ) {
$this->generate_implied_end_tags();
if ( $this->state->stack_of_open_elements->current_node_is( 'RUBY' ) ) {
// @todo Indicate a parse error once it's possible.
}
}
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A start tag whose tag name is one of: "rp", "rt"
*/
case '+RP':
case '+RT':
if ( $this->state->stack_of_open_elements->has_element_in_scope( 'RUBY' ) ) {
$this->generate_implied_end_tags( 'RTC' );
$current_node_name = $this->state->stack_of_open_elements->current_node()->node_name;
if ( 'RTC' === $current_node_name || 'RUBY' === $current_node_name ) {
// @todo Indicate a parse error once it's possible.
}
}
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A start tag whose tag name is "math"
*/
case '+MATH':
$this->reconstruct_active_formatting_elements();
/*
* @todo Adjust MathML attributes for the token. (This fixes the case of MathML attributes that are not all lowercase.)
* @todo Adjust foreign attributes for the token. (This fixes the use of namespaced attributes, in particular XLink.)
*
* These ought to be handled in the attribute methods.
*/
$this->state->current_token->namespace = 'math';
$this->insert_html_element( $this->state->current_token );
if ( $this->state->current_token->has_self_closing_flag ) {
$this->state->stack_of_open_elements->pop();
}
return true;
/*
* > A start tag whose tag name is "svg"
*/
case '+SVG':
$this->reconstruct_active_formatting_elements();
/*
* @todo Adjust SVG attributes for the token. (This fixes the case of SVG attributes that are not all lowercase.)
* @todo Adjust foreign attributes for the token. (This fixes the use of namespaced attributes, in particular XLink in SVG.)
*
* These ought to be handled in the attribute methods.
*/
$this->state->current_token->namespace = 'svg';
$this->insert_html_element( $this->state->current_token );
if ( $this->state->current_token->has_self_closing_flag ) {
$this->state->stack_of_open_elements->pop();
}
return true;
/*
* > A start tag whose tag name is one of: "caption", "col", "colgroup",
* > "frame", "head", "tbody", "td", "tfoot", "th", "thead", "tr"
*/
case '+CAPTION':
case '+COL':
case '+COLGROUP':
case '+FRAME':
case '+HEAD':
case '+TBODY':
case '+TD':
case '+TFOOT':
case '+TH':
case '+THEAD':
case '+TR':
// Parse error. Ignore the token.
return $this->step();
}
if ( ! parent::is_tag_closer() ) {
/*
* > Any other start tag
*/
$this->reconstruct_active_formatting_elements();
$this->insert_html_element( $this->state->current_token );
return true;
} else {
/*
* > Any other end tag
*/
/*
* Find the corresponding tag opener in the stack of open elements, if
* it exists before reaching a special element, which provides a kind
* of boundary in the stack. For example, a `` should not
* close anything beyond its containing `P` or `DIV` element.
*/
foreach ( $this->state->stack_of_open_elements->walk_up() as $node ) {
if ( 'html' === $node->namespace && $token_name === $node->node_name ) {
break;
}
if ( self::is_special( $node ) ) {
// This is a parse error, ignore the token.
return $this->step();
}
}
$this->generate_implied_end_tags( $token_name );
if ( $node !== $this->state->stack_of_open_elements->current_node() ) {
// @todo Record parse error: this error doesn't impact parsing.
}
foreach ( $this->state->stack_of_open_elements->walk_up() as $item ) {
$this->state->stack_of_open_elements->pop();
if ( $node === $item ) {
return true;
}
}
}
$this->bail( 'Should not have been able to reach end of IN BODY processing. Check HTML API code.' );
// This unnecessary return prevents tools from inaccurately reporting type errors.
return false;
}
/**
* Parses next element in the 'in table' insertion mode.
*
* This internal function performs the 'in table' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#parsing-main-intable
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_in_table(): bool {
$token_name = $this->get_token_name();
$token_type = $this->get_token_type();
$op_sigil = '#tag' === $token_type ? ( parent::is_tag_closer() ? '-' : '+' ) : '';
$op = "{$op_sigil}{$token_name}";
switch ( $op ) {
/*
* > A character token, if the current node is table,
* > tbody, template, tfoot, thead, or tr element
*/
case '#text':
$current_node = $this->state->stack_of_open_elements->current_node();
$current_node_name = $current_node ? $current_node->node_name : null;
if (
$current_node_name && (
'TABLE' === $current_node_name ||
'TBODY' === $current_node_name ||
'TEMPLATE' === $current_node_name ||
'TFOOT' === $current_node_name ||
'THEAD' === $current_node_name ||
'TR' === $current_node_name
)
) {
/*
* If the text is empty after processing HTML entities and stripping
* U+0000 NULL bytes then ignore the token.
*/
if ( parent::TEXT_IS_NULL_SEQUENCE === $this->text_node_classification ) {
return $this->step();
}
/*
* This follows the rules for "in table text" insertion mode.
*
* Whitespace-only text nodes are inserted in-place. Otherwise
* foster parenting is enabled and the nodes would be
* inserted out-of-place.
*
* > If any of the tokens in the pending table character tokens
* > list are character tokens that are not ASCII whitespace,
* > then this is a parse error: reprocess the character tokens
* > in the pending table character tokens list using the rules
* > given in the "anything else" entry in the "in table"
* > insertion mode.
* >
* > Otherwise, insert the characters given by the pending table
* > character tokens list.
*
* @see https://html.spec.whatwg.org/#parsing-main-intabletext
*/
if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
$this->insert_html_element( $this->state->current_token );
return true;
}
// Non-whitespace would trigger fostering, unsupported at this time.
$this->bail( 'Foster parenting is not supported.' );
break;
}
break;
/*
* > A comment token
*/
case '#comment':
case '#funky-comment':
case '#presumptuous-tag':
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A DOCTYPE token
*/
case 'html':
// Parse error: ignore the token.
return $this->step();
/*
* > A start tag whose tag name is "caption"
*/
case '+CAPTION':
$this->state->stack_of_open_elements->clear_to_table_context();
$this->state->active_formatting_elements->insert_marker();
$this->insert_html_element( $this->state->current_token );
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_CAPTION;
return true;
/*
* > A start tag whose tag name is "colgroup"
*/
case '+COLGROUP':
$this->state->stack_of_open_elements->clear_to_table_context();
$this->insert_html_element( $this->state->current_token );
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_COLUMN_GROUP;
return true;
/*
* > A start tag whose tag name is "col"
*/
case '+COL':
$this->state->stack_of_open_elements->clear_to_table_context();
/*
* > Insert an HTML element for a "colgroup" start tag token with no attributes,
* > then switch the insertion mode to "in column group".
*/
$this->insert_virtual_node( 'COLGROUP' );
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_COLUMN_GROUP;
return $this->step( self::REPROCESS_CURRENT_NODE );
/*
* > A start tag whose tag name is one of: "tbody", "tfoot", "thead"
*/
case '+TBODY':
case '+TFOOT':
case '+THEAD':
$this->state->stack_of_open_elements->clear_to_table_context();
$this->insert_html_element( $this->state->current_token );
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY;
return true;
/*
* > A start tag whose tag name is one of: "td", "th", "tr"
*/
case '+TD':
case '+TH':
case '+TR':
$this->state->stack_of_open_elements->clear_to_table_context();
/*
* > Insert an HTML element for a "tbody" start tag token with no attributes,
* > then switch the insertion mode to "in table body".
*/
$this->insert_virtual_node( 'TBODY' );
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY;
return $this->step( self::REPROCESS_CURRENT_NODE );
/*
* > A start tag whose tag name is "table"
*
* This tag in the IN TABLE insertion mode is a parse error.
*/
case '+TABLE':
if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( 'TABLE' ) ) {
return $this->step();
}
$this->state->stack_of_open_elements->pop_until( 'TABLE' );
$this->reset_insertion_mode_appropriately();
return $this->step( self::REPROCESS_CURRENT_NODE );
/*
* > An end tag whose tag name is "table"
*/
case '-TABLE':
if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( 'TABLE' ) ) {
// @todo Indicate a parse error once it's possible.
return $this->step();
}
$this->state->stack_of_open_elements->pop_until( 'TABLE' );
$this->reset_insertion_mode_appropriately();
return true;
/*
* > An end tag whose tag name is one of: "body", "caption", "col", "colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr"
*/
case '-BODY':
case '-CAPTION':
case '-COL':
case '-COLGROUP':
case '-HTML':
case '-TBODY':
case '-TD':
case '-TFOOT':
case '-TH':
case '-THEAD':
case '-TR':
// Parse error: ignore the token.
return $this->step();
/*
* > A start tag whose tag name is one of: "style", "script", "template"
* > An end tag whose tag name is "template"
*/
case '+STYLE':
case '+SCRIPT':
case '+TEMPLATE':
case '-TEMPLATE':
/*
* > Process the token using the rules for the "in head" insertion mode.
*/
return $this->step_in_head();
/*
* > A start tag whose tag name is "input"
*
* > If the token does not have an attribute with the name "type", or if it does, but
* > that attribute's value is not an ASCII case-insensitive match for the string
* > "hidden", then: act as described in the "anything else" entry below.
*/
case '+INPUT':
$type_attribute = $this->get_attribute( 'type' );
if ( ! is_string( $type_attribute ) || 'hidden' !== strtolower( $type_attribute ) ) {
goto anything_else;
}
// @todo Indicate a parse error once it's possible.
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A start tag whose tag name is "form"
*
* This tag in the IN TABLE insertion mode is a parse error.
*/
case '+FORM':
if (
$this->state->stack_of_open_elements->has_element_in_scope( 'TEMPLATE' ) ||
isset( $this->state->form_element )
) {
return $this->step();
}
// This FORM is special because it immediately closes and cannot have other children.
$this->insert_html_element( $this->state->current_token );
$this->state->form_element = $this->state->current_token;
$this->state->stack_of_open_elements->pop();
return true;
}
/*
* > Anything else
* > Parse error. Enable foster parenting, process the token using the rules for the
* > "in body" insertion mode, and then disable foster parenting.
*
* @todo Indicate a parse error once it's possible.
*/
anything_else:
$this->bail( 'Foster parenting is not supported.' );
}
/**
* Parses next element in the 'in table text' insertion mode.
*
* This internal function performs the 'in table text' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0 Stub implementation.
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#parsing-main-intabletext
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_in_table_text(): bool {
$this->bail( 'No support for parsing in the ' . WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_TEXT . ' state.' );
}
/**
* Parses next element in the 'in caption' insertion mode.
*
* This internal function performs the 'in caption' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#parsing-main-incaption
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_in_caption(): bool {
$tag_name = $this->get_tag();
$op_sigil = $this->is_tag_closer() ? '-' : '+';
$op = "{$op_sigil}{$tag_name}";
switch ( $op ) {
/*
* > An end tag whose tag name is "caption"
* > A start tag whose tag name is one of: "caption", "col", "colgroup", "tbody", "td", "tfoot", "th", "thead", "tr"
* > An end tag whose tag name is "table"
*
* These tag handling rules are identical except for the final instruction.
* Handle them in a single block.
*/
case '-CAPTION':
case '+CAPTION':
case '+COL':
case '+COLGROUP':
case '+TBODY':
case '+TD':
case '+TFOOT':
case '+TH':
case '+THEAD':
case '+TR':
case '-TABLE':
if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( 'CAPTION' ) ) {
// Parse error: ignore the token.
return $this->step();
}
$this->generate_implied_end_tags();
if ( ! $this->state->stack_of_open_elements->current_node_is( 'CAPTION' ) ) {
// @todo Indicate a parse error once it's possible.
}
$this->state->stack_of_open_elements->pop_until( 'CAPTION' );
$this->state->active_formatting_elements->clear_up_to_last_marker();
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE;
// If this is not a CAPTION end tag, the token should be reprocessed.
if ( '-CAPTION' === $op ) {
return true;
}
return $this->step( self::REPROCESS_CURRENT_NODE );
/**
* > An end tag whose tag name is one of: "body", "col", "colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr"
*/
case '-BODY':
case '-COL':
case '-COLGROUP':
case '-HTML':
case '-TBODY':
case '-TD':
case '-TFOOT':
case '-TH':
case '-THEAD':
case '-TR':
// Parse error: ignore the token.
return $this->step();
}
/**
* > Anything else
* > Process the token using the rules for the "in body" insertion mode.
*/
return $this->step_in_body();
}
/**
* Parses next element in the 'in column group' insertion mode.
*
* This internal function performs the 'in column group' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#parsing-main-incolgroup
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_in_column_group(): bool {
$token_name = $this->get_token_name();
$token_type = $this->get_token_type();
$op_sigil = '#tag' === $token_type ? ( parent::is_tag_closer() ? '-' : '+' ) : '';
$op = "{$op_sigil}{$token_name}";
switch ( $op ) {
/*
* > A character token that is one of U+0009 CHARACTER TABULATION, U+000A LINE FEED (LF),
* > U+000C FORM FEED (FF), U+000D CARRIAGE RETURN (CR), or U+0020 SPACE
*/
case '#text':
if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
// Insert the character.
$this->insert_html_element( $this->state->current_token );
return true;
}
goto in_column_group_anything_else;
break;
/*
* > A comment token
*/
case '#comment':
case '#funky-comment':
case '#presumptuous-tag':
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A DOCTYPE token
*/
case 'html':
// @todo Indicate a parse error once it's possible.
return $this->step();
/*
* > A start tag whose tag name is "html"
*/
case '+HTML':
return $this->step_in_body();
/*
* > A start tag whose tag name is "col"
*/
case '+COL':
$this->insert_html_element( $this->state->current_token );
$this->state->stack_of_open_elements->pop();
return true;
/*
* > An end tag whose tag name is "colgroup"
*/
case '-COLGROUP':
if ( ! $this->state->stack_of_open_elements->current_node_is( 'COLGROUP' ) ) {
// @todo Indicate a parse error once it's possible.
return $this->step();
}
$this->state->stack_of_open_elements->pop();
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE;
return true;
/*
* > An end tag whose tag name is "col"
*/
case '-COL':
// Parse error: ignore the token.
return $this->step();
/*
* > A start tag whose tag name is "template"
* > An end tag whose tag name is "template"
*/
case '+TEMPLATE':
case '-TEMPLATE':
return $this->step_in_head();
}
in_column_group_anything_else:
/*
* > Anything else
*/
if ( ! $this->state->stack_of_open_elements->current_node_is( 'COLGROUP' ) ) {
// @todo Indicate a parse error once it's possible.
return $this->step();
}
$this->state->stack_of_open_elements->pop();
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE;
return $this->step( self::REPROCESS_CURRENT_NODE );
}
/**
* Parses next element in the 'in table body' insertion mode.
*
* This internal function performs the 'in table body' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#parsing-main-intbody
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_in_table_body(): bool {
$tag_name = $this->get_tag();
$op_sigil = $this->is_tag_closer() ? '-' : '+';
$op = "{$op_sigil}{$tag_name}";
switch ( $op ) {
/*
* > A start tag whose tag name is "tr"
*/
case '+TR':
$this->state->stack_of_open_elements->clear_to_table_body_context();
$this->insert_html_element( $this->state->current_token );
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_ROW;
return true;
/*
* > A start tag whose tag name is one of: "th", "td"
*/
case '+TH':
case '+TD':
// @todo Indicate a parse error once it's possible.
$this->state->stack_of_open_elements->clear_to_table_body_context();
$this->insert_virtual_node( 'TR' );
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_ROW;
return $this->step( self::REPROCESS_CURRENT_NODE );
/*
* > An end tag whose tag name is one of: "tbody", "tfoot", "thead"
*/
case '-TBODY':
case '-TFOOT':
case '-THEAD':
if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( $tag_name ) ) {
// Parse error: ignore the token.
return $this->step();
}
$this->state->stack_of_open_elements->clear_to_table_body_context();
$this->state->stack_of_open_elements->pop();
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE;
return true;
/*
* > A start tag whose tag name is one of: "caption", "col", "colgroup", "tbody", "tfoot", "thead"
* > An end tag whose tag name is "table"
*/
case '+CAPTION':
case '+COL':
case '+COLGROUP':
case '+TBODY':
case '+TFOOT':
case '+THEAD':
case '-TABLE':
if (
! $this->state->stack_of_open_elements->has_element_in_table_scope( 'TBODY' ) &&
! $this->state->stack_of_open_elements->has_element_in_table_scope( 'THEAD' ) &&
! $this->state->stack_of_open_elements->has_element_in_table_scope( 'TFOOT' )
) {
// Parse error: ignore the token.
return $this->step();
}
$this->state->stack_of_open_elements->clear_to_table_body_context();
$this->state->stack_of_open_elements->pop();
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE;
return $this->step( self::REPROCESS_CURRENT_NODE );
/*
* > An end tag whose tag name is one of: "body", "caption", "col", "colgroup", "html", "td", "th", "tr"
*/
case '-BODY':
case '-CAPTION':
case '-COL':
case '-COLGROUP':
case '-HTML':
case '-TD':
case '-TH':
case '-TR':
// Parse error: ignore the token.
return $this->step();
}
/*
* > Anything else
* > Process the token using the rules for the "in table" insertion mode.
*/
return $this->step_in_table();
}
/**
* Parses next element in the 'in row' insertion mode.
*
* This internal function performs the 'in row' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#parsing-main-intr
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_in_row(): bool {
$tag_name = $this->get_tag();
$op_sigil = $this->is_tag_closer() ? '-' : '+';
$op = "{$op_sigil}{$tag_name}";
switch ( $op ) {
/*
* > A start tag whose tag name is one of: "th", "td"
*/
case '+TH':
case '+TD':
$this->state->stack_of_open_elements->clear_to_table_row_context();
$this->insert_html_element( $this->state->current_token );
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_CELL;
$this->state->active_formatting_elements->insert_marker();
return true;
/*
* > An end tag whose tag name is "tr"
*/
case '-TR':
if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( 'TR' ) ) {
// Parse error: ignore the token.
return $this->step();
}
$this->state->stack_of_open_elements->clear_to_table_row_context();
$this->state->stack_of_open_elements->pop();
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY;
return true;
/*
* > A start tag whose tag name is one of: "caption", "col", "colgroup", "tbody", "tfoot", "thead", "tr"
* > An end tag whose tag name is "table"
*/
case '+CAPTION':
case '+COL':
case '+COLGROUP':
case '+TBODY':
case '+TFOOT':
case '+THEAD':
case '+TR':
case '-TABLE':
if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( 'TR' ) ) {
// Parse error: ignore the token.
return $this->step();
}
$this->state->stack_of_open_elements->clear_to_table_row_context();
$this->state->stack_of_open_elements->pop();
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY;
return $this->step( self::REPROCESS_CURRENT_NODE );
/*
* > An end tag whose tag name is one of: "tbody", "tfoot", "thead"
*/
case '-TBODY':
case '-TFOOT':
case '-THEAD':
if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( $tag_name ) ) {
// Parse error: ignore the token.
return $this->step();
}
if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( 'TR' ) ) {
// Ignore the token.
return $this->step();
}
$this->state->stack_of_open_elements->clear_to_table_row_context();
$this->state->stack_of_open_elements->pop();
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY;
return $this->step( self::REPROCESS_CURRENT_NODE );
/*
* > An end tag whose tag name is one of: "body", "caption", "col", "colgroup", "html", "td", "th"
*/
case '-BODY':
case '-CAPTION':
case '-COL':
case '-COLGROUP':
case '-HTML':
case '-TD':
case '-TH':
// Parse error: ignore the token.
return $this->step();
}
/*
* > Anything else
* > Process the token using the rules for the "in table" insertion mode.
*/
return $this->step_in_table();
}
/**
* Parses next element in the 'in cell' insertion mode.
*
* This internal function performs the 'in cell' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#parsing-main-intd
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_in_cell(): bool {
$tag_name = $this->get_tag();
$op_sigil = $this->is_tag_closer() ? '-' : '+';
$op = "{$op_sigil}{$tag_name}";
switch ( $op ) {
/*
* > An end tag whose tag name is one of: "td", "th"
*/
case '-TD':
case '-TH':
if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( $tag_name ) ) {
// Parse error: ignore the token.
return $this->step();
}
$this->generate_implied_end_tags();
/*
* @todo This needs to check if the current node is an HTML element, meaning that
* when SVG and MathML support is added, this needs to differentiate between an
* HTML element of the given name, such as `
`, and a foreign element of
* the same given name.
*/
if ( ! $this->state->stack_of_open_elements->current_node_is( $tag_name ) ) {
// @todo Indicate a parse error once it's possible.
}
$this->state->stack_of_open_elements->pop_until( $tag_name );
$this->state->active_formatting_elements->clear_up_to_last_marker();
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_ROW;
return true;
/*
* > A start tag whose tag name is one of: "caption", "col", "colgroup", "tbody", "td",
* > "tfoot", "th", "thead", "tr"
*/
case '+CAPTION':
case '+COL':
case '+COLGROUP':
case '+TBODY':
case '+TD':
case '+TFOOT':
case '+TH':
case '+THEAD':
case '+TR':
/*
* > Assert: The stack of open elements has a td or th element in table scope.
*
* Nothing to do here, except to verify in tests that this never appears.
*/
$this->close_cell();
return $this->step( self::REPROCESS_CURRENT_NODE );
/*
* > An end tag whose tag name is one of: "body", "caption", "col", "colgroup", "html"
*/
case '-BODY':
case '-CAPTION':
case '-COL':
case '-COLGROUP':
case '-HTML':
// Parse error: ignore the token.
return $this->step();
/*
* > An end tag whose tag name is one of: "table", "tbody", "tfoot", "thead", "tr"
*/
case '-TABLE':
case '-TBODY':
case '-TFOOT':
case '-THEAD':
case '-TR':
if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( $tag_name ) ) {
// Parse error: ignore the token.
return $this->step();
}
$this->close_cell();
return $this->step( self::REPROCESS_CURRENT_NODE );
}
/*
* > Anything else
* > Process the token using the rules for the "in body" insertion mode.
*/
return $this->step_in_body();
}
/**
* Parses next element in the 'in select' insertion mode.
*
* This internal function performs the 'in select' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/multipage/parsing.html#parsing-main-inselect
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_in_select(): bool {
$token_name = $this->get_token_name();
$token_type = $this->get_token_type();
$op_sigil = '#tag' === $token_type ? ( parent::is_tag_closer() ? '-' : '+' ) : '';
$op = "{$op_sigil}{$token_name}";
switch ( $op ) {
/*
* > Any other character token
*/
case '#text':
/*
* > A character token that is U+0000 NULL
*
* If a text node only comprises null bytes then it should be
* entirely ignored and should not return to calling code.
*/
if ( parent::TEXT_IS_NULL_SEQUENCE === $this->text_node_classification ) {
// Parse error: ignore the token.
return $this->step();
}
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A comment token
*/
case '#comment':
case '#funky-comment':
case '#presumptuous-tag':
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A DOCTYPE token
*/
case 'html':
// Parse error: ignore the token.
return $this->step();
/*
* > A start tag whose tag name is "html"
*/
case '+HTML':
return $this->step_in_body();
/*
* > A start tag whose tag name is "option"
*/
case '+OPTION':
if ( $this->state->stack_of_open_elements->current_node_is( 'OPTION' ) ) {
$this->state->stack_of_open_elements->pop();
}
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A start tag whose tag name is "optgroup"
* > A start tag whose tag name is "hr"
*
* These rules are identical except for the treatment of the self-closing flag and
* the subsequent pop of the HR void element, all of which is handled elsewhere in the processor.
*/
case '+OPTGROUP':
case '+HR':
if ( $this->state->stack_of_open_elements->current_node_is( 'OPTION' ) ) {
$this->state->stack_of_open_elements->pop();
}
if ( $this->state->stack_of_open_elements->current_node_is( 'OPTGROUP' ) ) {
$this->state->stack_of_open_elements->pop();
}
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > An end tag whose tag name is "optgroup"
*/
case '-OPTGROUP':
$current_node = $this->state->stack_of_open_elements->current_node();
if ( $current_node && 'OPTION' === $current_node->node_name ) {
foreach ( $this->state->stack_of_open_elements->walk_up( $current_node ) as $parent ) {
break;
}
if ( $parent && 'OPTGROUP' === $parent->node_name ) {
$this->state->stack_of_open_elements->pop();
}
}
if ( $this->state->stack_of_open_elements->current_node_is( 'OPTGROUP' ) ) {
$this->state->stack_of_open_elements->pop();
return true;
}
// Parse error: ignore the token.
return $this->step();
/*
* > An end tag whose tag name is "option"
*/
case '-OPTION':
if ( $this->state->stack_of_open_elements->current_node_is( 'OPTION' ) ) {
$this->state->stack_of_open_elements->pop();
return true;
}
// Parse error: ignore the token.
return $this->step();
/*
* > An end tag whose tag name is "select"
* > A start tag whose tag name is "select"
*
* > It just gets treated like an end tag.
*/
case '-SELECT':
case '+SELECT':
if ( ! $this->state->stack_of_open_elements->has_element_in_select_scope( 'SELECT' ) ) {
// Parse error: ignore the token.
return $this->step();
}
$this->state->stack_of_open_elements->pop_until( 'SELECT' );
$this->reset_insertion_mode_appropriately();
return true;
/*
* > A start tag whose tag name is one of: "input", "keygen", "textarea"
*
* All three of these tags are considered a parse error when found in this insertion mode.
*/
case '+INPUT':
case '+KEYGEN':
case '+TEXTAREA':
if ( ! $this->state->stack_of_open_elements->has_element_in_select_scope( 'SELECT' ) ) {
// Ignore the token.
return $this->step();
}
$this->state->stack_of_open_elements->pop_until( 'SELECT' );
$this->reset_insertion_mode_appropriately();
return $this->step( self::REPROCESS_CURRENT_NODE );
/*
* > A start tag whose tag name is one of: "script", "template"
* > An end tag whose tag name is "template"
*/
case '+SCRIPT':
case '+TEMPLATE':
case '-TEMPLATE':
return $this->step_in_head();
}
/*
* > Anything else
* > Parse error: ignore the token.
*/
return $this->step();
}
/**
* Parses next element in the 'in select in table' insertion mode.
*
* This internal function performs the 'in select in table' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#parsing-main-inselectintable
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_in_select_in_table(): bool {
$token_name = $this->get_token_name();
$token_type = $this->get_token_type();
$op_sigil = '#tag' === $token_type ? ( parent::is_tag_closer() ? '-' : '+' ) : '';
$op = "{$op_sigil}{$token_name}";
switch ( $op ) {
/*
* > A start tag whose tag name is one of: "caption", "table", "tbody", "tfoot", "thead", "tr", "td", "th"
*/
case '+CAPTION':
case '+TABLE':
case '+TBODY':
case '+TFOOT':
case '+THEAD':
case '+TR':
case '+TD':
case '+TH':
// @todo Indicate a parse error once it's possible.
$this->state->stack_of_open_elements->pop_until( 'SELECT' );
$this->reset_insertion_mode_appropriately();
return $this->step( self::REPROCESS_CURRENT_NODE );
/*
* > An end tag whose tag name is one of: "caption", "table", "tbody", "tfoot", "thead", "tr", "td", "th"
*/
case '-CAPTION':
case '-TABLE':
case '-TBODY':
case '-TFOOT':
case '-THEAD':
case '-TR':
case '-TD':
case '-TH':
// @todo Indicate a parse error once it's possible.
if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( $token_name ) ) {
return $this->step();
}
$this->state->stack_of_open_elements->pop_until( 'SELECT' );
$this->reset_insertion_mode_appropriately();
return $this->step( self::REPROCESS_CURRENT_NODE );
}
/*
* > Anything else
*/
return $this->step_in_select();
}
/**
* Parses next element in the 'in template' insertion mode.
*
* This internal function performs the 'in template' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0 Stub implementation.
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#parsing-main-intemplate
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_in_template(): bool {
$token_name = $this->get_token_name();
$token_type = $this->get_token_type();
$is_closer = $this->is_tag_closer();
$op_sigil = '#tag' === $token_type ? ( $is_closer ? '-' : '+' ) : '';
$op = "{$op_sigil}{$token_name}";
switch ( $op ) {
/*
* > A character token
* > A comment token
* > A DOCTYPE token
*/
case '#text':
case '#comment':
case '#funky-comment':
case '#presumptuous-tag':
case 'html':
return $this->step_in_body();
/*
* > A start tag whose tag name is one of: "base", "basefont", "bgsound", "link",
* > "meta", "noframes", "script", "style", "template", "title"
* > An end tag whose tag name is "template"
*/
case '+BASE':
case '+BASEFONT':
case '+BGSOUND':
case '+LINK':
case '+META':
case '+NOFRAMES':
case '+SCRIPT':
case '+STYLE':
case '+TEMPLATE':
case '+TITLE':
case '-TEMPLATE':
return $this->step_in_head();
/*
* > A start tag whose tag name is one of: "caption", "colgroup", "tbody", "tfoot", "thead"
*/
case '+CAPTION':
case '+COLGROUP':
case '+TBODY':
case '+TFOOT':
case '+THEAD':
array_pop( $this->state->stack_of_template_insertion_modes );
$this->state->stack_of_template_insertion_modes[] = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE;
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE;
return $this->step( self::REPROCESS_CURRENT_NODE );
/*
* > A start tag whose tag name is "col"
*/
case '+COL':
array_pop( $this->state->stack_of_template_insertion_modes );
$this->state->stack_of_template_insertion_modes[] = WP_HTML_Processor_State::INSERTION_MODE_IN_COLUMN_GROUP;
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_COLUMN_GROUP;
return $this->step( self::REPROCESS_CURRENT_NODE );
/*
* > A start tag whose tag name is "tr"
*/
case '+TR':
array_pop( $this->state->stack_of_template_insertion_modes );
$this->state->stack_of_template_insertion_modes[] = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY;
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY;
return $this->step( self::REPROCESS_CURRENT_NODE );
/*
* > A start tag whose tag name is one of: "td", "th"
*/
case '+TD':
case '+TH':
array_pop( $this->state->stack_of_template_insertion_modes );
$this->state->stack_of_template_insertion_modes[] = WP_HTML_Processor_State::INSERTION_MODE_IN_ROW;
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_ROW;
return $this->step( self::REPROCESS_CURRENT_NODE );
}
/*
* > Any other start tag
*/
if ( ! $is_closer ) {
array_pop( $this->state->stack_of_template_insertion_modes );
$this->state->stack_of_template_insertion_modes[] = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY;
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY;
return $this->step( self::REPROCESS_CURRENT_NODE );
}
/*
* > Any other end tag
*/
if ( $is_closer ) {
// Parse error: ignore the token.
return $this->step();
}
/*
* > An end-of-file token
*/
if ( ! $this->state->stack_of_open_elements->contains( 'TEMPLATE' ) ) {
// Stop parsing.
return false;
}
// @todo Indicate a parse error once it's possible.
$this->state->stack_of_open_elements->pop_until( 'TEMPLATE' );
$this->state->active_formatting_elements->clear_up_to_last_marker();
array_pop( $this->state->stack_of_template_insertion_modes );
$this->reset_insertion_mode_appropriately();
return $this->step( self::REPROCESS_CURRENT_NODE );
}
/**
* Parses next element in the 'after body' insertion mode.
*
* This internal function performs the 'after body' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0 Stub implementation.
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#parsing-main-afterbody
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_after_body(): bool {
$tag_name = $this->get_token_name();
$token_type = $this->get_token_type();
$op_sigil = '#tag' === $token_type ? ( $this->is_tag_closer() ? '-' : '+' ) : '';
$op = "{$op_sigil}{$tag_name}";
switch ( $op ) {
/*
* > A character token that is one of U+0009 CHARACTER TABULATION, U+000A LINE FEED (LF),
* > U+000C FORM FEED (FF), U+000D CARRIAGE RETURN (CR), or U+0020 SPACE
*
* > Process the token using the rules for the "in body" insertion mode.
*/
case '#text':
if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
return $this->step_in_body();
}
goto after_body_anything_else;
break;
/*
* > A comment token
*/
case '#comment':
case '#funky-comment':
case '#presumptuous-tag':
$this->bail( 'Content outside of BODY is unsupported.' );
break;
/*
* > A DOCTYPE token
*/
case 'html':
// Parse error: ignore the token.
return $this->step();
/*
* > A start tag whose tag name is "html"
*/
case '+HTML':
return $this->step_in_body();
/*
* > An end tag whose tag name is "html"
*
* > If the parser was created as part of the HTML fragment parsing algorithm,
* > this is a parse error; ignore the token. (fragment case)
* >
* > Otherwise, switch the insertion mode to "after after body".
*/
case '-HTML':
if ( isset( $this->context_node ) ) {
return $this->step();
}
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_AFTER_AFTER_BODY;
/*
* The HTML element is not removed from the stack of open elements.
* Only internal state has changed, this does not qualify as a "step"
* in terms of advancing through the document to another token.
* Nothing has been pushed or popped.
* Proceed to parse the next item.
*/
return $this->step();
}
/*
* > Parse error. Switch the insertion mode to "in body" and reprocess the token.
*/
after_body_anything_else:
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY;
return $this->step( self::REPROCESS_CURRENT_NODE );
}
/**
* Parses next element in the 'in frameset' insertion mode.
*
* This internal function performs the 'in frameset' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0 Stub implementation.
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#parsing-main-inframeset
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_in_frameset(): bool {
$tag_name = $this->get_token_name();
$token_type = $this->get_token_type();
$op_sigil = '#tag' === $token_type ? ( $this->is_tag_closer() ? '-' : '+' ) : '';
$op = "{$op_sigil}{$tag_name}";
switch ( $op ) {
/*
* > A character token that is one of U+0009 CHARACTER TABULATION, U+000A LINE FEED (LF),
* > U+000C FORM FEED (FF), U+000D CARRIAGE RETURN (CR), or U+0020 SPACE
* >
* > Insert the character.
*
* This algorithm effectively strips non-whitespace characters from text and inserts
* them under HTML. This is not supported at this time.
*/
case '#text':
if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
return $this->step_in_body();
}
$this->bail( 'Non-whitespace characters cannot be handled in frameset.' );
break;
/*
* > A comment token
*/
case '#comment':
case '#funky-comment':
case '#presumptuous-tag':
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A DOCTYPE token
*/
case 'html':
// Parse error: ignore the token.
return $this->step();
/*
* > A start tag whose tag name is "html"
*/
case '+HTML':
return $this->step_in_body();
/*
* > A start tag whose tag name is "frameset"
*/
case '+FRAMESET':
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > An end tag whose tag name is "frameset"
*/
case '-FRAMESET':
/*
* > If the current node is the root html element, then this is a parse error;
* > ignore the token. (fragment case)
*/
if ( $this->state->stack_of_open_elements->current_node_is( 'HTML' ) ) {
return $this->step();
}
/*
* > Otherwise, pop the current node from the stack of open elements.
*/
$this->state->stack_of_open_elements->pop();
/*
* > If the parser was not created as part of the HTML fragment parsing algorithm
* > (fragment case), and the current node is no longer a frameset element, then
* > switch the insertion mode to "after frameset".
*/
if ( ! isset( $this->context_node ) && ! $this->state->stack_of_open_elements->current_node_is( 'FRAMESET' ) ) {
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_AFTER_FRAMESET;
}
return true;
/*
* > A start tag whose tag name is "frame"
*
* > Insert an HTML element for the token. Immediately pop the
* > current node off the stack of open elements.
* >
* > Acknowledge the token's self-closing flag, if it is set.
*/
case '+FRAME':
$this->insert_html_element( $this->state->current_token );
$this->state->stack_of_open_elements->pop();
return true;
/*
* > A start tag whose tag name is "noframes"
*/
case '+NOFRAMES':
return $this->step_in_head();
}
// Parse error: ignore the token.
return $this->step();
}
/**
* Parses next element in the 'after frameset' insertion mode.
*
* This internal function performs the 'after frameset' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0 Stub implementation.
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#parsing-main-afterframeset
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_after_frameset(): bool {
$tag_name = $this->get_token_name();
$token_type = $this->get_token_type();
$op_sigil = '#tag' === $token_type ? ( $this->is_tag_closer() ? '-' : '+' ) : '';
$op = "{$op_sigil}{$tag_name}";
switch ( $op ) {
/*
* > A character token that is one of U+0009 CHARACTER TABULATION, U+000A LINE FEED (LF),
* > U+000C FORM FEED (FF), U+000D CARRIAGE RETURN (CR), or U+0020 SPACE
* >
* > Insert the character.
*
* This algorithm effectively strips non-whitespace characters from text and inserts
* them under HTML. This is not supported at this time.
*/
case '#text':
if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
return $this->step_in_body();
}
$this->bail( 'Non-whitespace characters cannot be handled in after frameset' );
break;
/*
* > A comment token
*/
case '#comment':
case '#funky-comment':
case '#presumptuous-tag':
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > A DOCTYPE token
*/
case 'html':
// Parse error: ignore the token.
return $this->step();
/*
* > A start tag whose tag name is "html"
*/
case '+HTML':
return $this->step_in_body();
/*
* > An end tag whose tag name is "html"
*/
case '-HTML':
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_AFTER_AFTER_FRAMESET;
/*
* The HTML element is not removed from the stack of open elements.
* Only internal state has changed, this does not qualify as a "step"
* in terms of advancing through the document to another token.
* Nothing has been pushed or popped.
* Proceed to parse the next item.
*/
return $this->step();
/*
* > A start tag whose tag name is "noframes"
*/
case '+NOFRAMES':
return $this->step_in_head();
}
// Parse error: ignore the token.
return $this->step();
}
/**
* Parses next element in the 'after after body' insertion mode.
*
* This internal function performs the 'after after body' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0 Stub implementation.
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#the-after-after-body-insertion-mode
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_after_after_body(): bool {
$tag_name = $this->get_token_name();
$token_type = $this->get_token_type();
$op_sigil = '#tag' === $token_type ? ( $this->is_tag_closer() ? '-' : '+' ) : '';
$op = "{$op_sigil}{$tag_name}";
switch ( $op ) {
/*
* > A comment token
*/
case '#comment':
case '#funky-comment':
case '#presumptuous-tag':
$this->bail( 'Content outside of HTML is unsupported.' );
break;
/*
* > A DOCTYPE token
* > A start tag whose tag name is "html"
*
* > Process the token using the rules for the "in body" insertion mode.
*/
case 'html':
case '+HTML':
return $this->step_in_body();
/*
* > A character token that is one of U+0009 CHARACTER TABULATION, U+000A LINE FEED (LF),
* > U+000C FORM FEED (FF), U+000D CARRIAGE RETURN (CR), or U+0020 SPACE
* >
* > Process the token using the rules for the "in body" insertion mode.
*/
case '#text':
if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
return $this->step_in_body();
}
goto after_after_body_anything_else;
break;
}
/*
* > Parse error. Switch the insertion mode to "in body" and reprocess the token.
*/
after_after_body_anything_else:
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY;
return $this->step( self::REPROCESS_CURRENT_NODE );
}
/**
* Parses next element in the 'after after frameset' insertion mode.
*
* This internal function performs the 'after after frameset' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0 Stub implementation.
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#the-after-after-frameset-insertion-mode
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_after_after_frameset(): bool {
$tag_name = $this->get_token_name();
$token_type = $this->get_token_type();
$op_sigil = '#tag' === $token_type ? ( $this->is_tag_closer() ? '-' : '+' ) : '';
$op = "{$op_sigil}{$tag_name}";
switch ( $op ) {
/*
* > A comment token
*/
case '#comment':
case '#funky-comment':
case '#presumptuous-tag':
$this->bail( 'Content outside of HTML is unsupported.' );
break;
/*
* > A DOCTYPE token
* > A start tag whose tag name is "html"
*
* > Process the token using the rules for the "in body" insertion mode.
*/
case 'html':
case '+HTML':
return $this->step_in_body();
/*
* > A character token that is one of U+0009 CHARACTER TABULATION, U+000A LINE FEED (LF),
* > U+000C FORM FEED (FF), U+000D CARRIAGE RETURN (CR), or U+0020 SPACE
* >
* > Process the token using the rules for the "in body" insertion mode.
*
* This algorithm effectively strips non-whitespace characters from text and inserts
* them under HTML. This is not supported at this time.
*/
case '#text':
if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
return $this->step_in_body();
}
$this->bail( 'Non-whitespace characters cannot be handled in after after frameset.' );
break;
/*
* > A start tag whose tag name is "noframes"
*/
case '+NOFRAMES':
return $this->step_in_head();
}
// Parse error: ignore the token.
return $this->step();
}
/**
* Parses next element in the 'in foreign content' insertion mode.
*
* This internal function performs the 'in foreign content' insertion mode
* logic for the generalized WP_HTML_Processor::step() function.
*
* @since 6.7.0 Stub implementation.
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#parsing-main-inforeign
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_in_foreign_content(): bool {
$tag_name = $this->get_token_name();
$token_type = $this->get_token_type();
$op_sigil = '#tag' === $token_type ? ( $this->is_tag_closer() ? '-' : '+' ) : '';
$op = "{$op_sigil}{$tag_name}";
/*
* > A start tag whose name is "font", if the token has any attributes named "color", "face", or "size"
*
* This section drawn out above the switch to more easily incorporate
* the additional rules based on the presence of the attributes.
*/
if (
'+FONT' === $op &&
(
null !== $this->get_attribute( 'color' ) ||
null !== $this->get_attribute( 'face' ) ||
null !== $this->get_attribute( 'size' )
)
) {
$op = '+FONT with attributes';
}
switch ( $op ) {
case '#text':
/*
* > A character token that is U+0000 NULL
*
* This is handled by `get_modifiable_text()`.
*/
/*
* Whitespace-only text does not affect the frameset-ok flag.
* It is probably inter-element whitespace, but it may also
* contain character references which decode only to whitespace.
*/
if ( parent::TEXT_IS_GENERIC === $this->text_node_classification ) {
$this->state->frameset_ok = false;
}
$this->insert_foreign_element( $this->state->current_token, false );
return true;
/*
* CDATA sections are alternate wrappers for text content and therefore
* ought to follow the same rules as text nodes.
*/
case '#cdata-section':
/*
* NULL bytes and whitespace do not change the frameset-ok flag.
*/
$current_token = $this->bookmarks[ $this->state->current_token->bookmark_name ];
$cdata_content_start = $current_token->start + 9;
$cdata_content_length = $current_token->length - 12;
if ( strspn( $this->html, "\0 \t\n\f\r", $cdata_content_start, $cdata_content_length ) !== $cdata_content_length ) {
$this->state->frameset_ok = false;
}
$this->insert_foreign_element( $this->state->current_token, false );
return true;
/*
* > A comment token
*/
case '#comment':
case '#funky-comment':
case '#presumptuous-tag':
$this->insert_foreign_element( $this->state->current_token, false );
return true;
/*
* > A DOCTYPE token
*/
case 'html':
// Parse error: ignore the token.
return $this->step();
/*
* > A start tag whose tag name is "b", "big", "blockquote", "body", "br", "center",
* > "code", "dd", "div", "dl", "dt", "em", "embed", "h1", "h2", "h3", "h4", "h5",
* > "h6", "head", "hr", "i", "img", "li", "listing", "menu", "meta", "nobr", "ol",
* > "p", "pre", "ruby", "s", "small", "span", "strong", "strike", "sub", "sup",
* > "table", "tt", "u", "ul", "var"
*
* > A start tag whose name is "font", if the token has any attributes named "color", "face", or "size"
*
* > An end tag whose tag name is "br", "p"
*
* Closing BR tags are always reported by the Tag Processor as opening tags.
*/
case '+B':
case '+BIG':
case '+BLOCKQUOTE':
case '+BODY':
case '+BR':
case '+CENTER':
case '+CODE':
case '+DD':
case '+DIV':
case '+DL':
case '+DT':
case '+EM':
case '+EMBED':
case '+H1':
case '+H2':
case '+H3':
case '+H4':
case '+H5':
case '+H6':
case '+HEAD':
case '+HR':
case '+I':
case '+IMG':
case '+LI':
case '+LISTING':
case '+MENU':
case '+META':
case '+NOBR':
case '+OL':
case '+P':
case '+PRE':
case '+RUBY':
case '+S':
case '+SMALL':
case '+SPAN':
case '+STRONG':
case '+STRIKE':
case '+SUB':
case '+SUP':
case '+TABLE':
case '+TT':
case '+U':
case '+UL':
case '+VAR':
case '+FONT with attributes':
case '-BR':
case '-P':
// @todo Indicate a parse error once it's possible.
foreach ( $this->state->stack_of_open_elements->walk_up() as $current_node ) {
if (
'math' === $current_node->integration_node_type ||
'html' === $current_node->integration_node_type ||
'html' === $current_node->namespace
) {
break;
}
$this->state->stack_of_open_elements->pop();
}
goto in_foreign_content_process_in_current_insertion_mode;
}
/*
* > Any other start tag
*/
if ( ! $this->is_tag_closer() ) {
$this->insert_foreign_element( $this->state->current_token, false );
/*
* > If the token has its self-closing flag set, then run
* > the appropriate steps from the following list:
* >
* > ↪ the token's tag name is "script", and the new current node is in the SVG namespace
* > Acknowledge the token's self-closing flag, and then act as
* > described in the steps for a "script" end tag below.
* >
* > ↪ Otherwise
* > Pop the current node off the stack of open elements and
* > acknowledge the token's self-closing flag.
*
* Since the rules for SCRIPT below indicate to pop the element off of the stack of
* open elements, which is the same for the Otherwise condition, there's no need to
* separate these checks. The difference comes when a parser operates with the scripting
* flag enabled, and executes the script, which this parser does not support.
*/
if ( $this->state->current_token->has_self_closing_flag ) {
$this->state->stack_of_open_elements->pop();
}
return true;
}
/*
* > An end tag whose name is "script", if the current node is an SVG script element.
*/
if ( $this->is_tag_closer() && 'SCRIPT' === $this->state->current_token->node_name && 'svg' === $this->state->current_token->namespace ) {
$this->state->stack_of_open_elements->pop();
return true;
}
/*
* > Any other end tag
*/
if ( $this->is_tag_closer() ) {
$node = $this->state->stack_of_open_elements->current_node();
if ( $tag_name !== $node->node_name ) {
// @todo Indicate a parse error once it's possible.
}
in_foreign_content_end_tag_loop:
if ( $node === $this->state->stack_of_open_elements->at( 1 ) ) {
return true;
}
/*
* > If node's tag name, converted to ASCII lowercase, is the same as the tag name
* > of the token, pop elements from the stack of open elements until node has
* > been popped from the stack, and then return.
*/
if ( 0 === strcasecmp( $node->node_name, $tag_name ) ) {
foreach ( $this->state->stack_of_open_elements->walk_up() as $item ) {
$this->state->stack_of_open_elements->pop();
if ( $node === $item ) {
return true;
}
}
}
foreach ( $this->state->stack_of_open_elements->walk_up( $node ) as $item ) {
$node = $item;
break;
}
if ( 'html' !== $node->namespace ) {
goto in_foreign_content_end_tag_loop;
}
in_foreign_content_process_in_current_insertion_mode:
switch ( $this->state->insertion_mode ) {
case WP_HTML_Processor_State::INSERTION_MODE_INITIAL:
return $this->step_initial();
case WP_HTML_Processor_State::INSERTION_MODE_BEFORE_HTML:
return $this->step_before_html();
case WP_HTML_Processor_State::INSERTION_MODE_BEFORE_HEAD:
return $this->step_before_head();
case WP_HTML_Processor_State::INSERTION_MODE_IN_HEAD:
return $this->step_in_head();
case WP_HTML_Processor_State::INSERTION_MODE_IN_HEAD_NOSCRIPT:
return $this->step_in_head_noscript();
case WP_HTML_Processor_State::INSERTION_MODE_AFTER_HEAD:
return $this->step_after_head();
case WP_HTML_Processor_State::INSERTION_MODE_IN_BODY:
return $this->step_in_body();
case WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE:
return $this->step_in_table();
case WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_TEXT:
return $this->step_in_table_text();
case WP_HTML_Processor_State::INSERTION_MODE_IN_CAPTION:
return $this->step_in_caption();
case WP_HTML_Processor_State::INSERTION_MODE_IN_COLUMN_GROUP:
return $this->step_in_column_group();
case WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY:
return $this->step_in_table_body();
case WP_HTML_Processor_State::INSERTION_MODE_IN_ROW:
return $this->step_in_row();
case WP_HTML_Processor_State::INSERTION_MODE_IN_CELL:
return $this->step_in_cell();
case WP_HTML_Processor_State::INSERTION_MODE_IN_SELECT:
return $this->step_in_select();
case WP_HTML_Processor_State::INSERTION_MODE_IN_SELECT_IN_TABLE:
return $this->step_in_select_in_table();
case WP_HTML_Processor_State::INSERTION_MODE_IN_TEMPLATE:
return $this->step_in_template();
case WP_HTML_Processor_State::INSERTION_MODE_AFTER_BODY:
return $this->step_after_body();
case WP_HTML_Processor_State::INSERTION_MODE_IN_FRAMESET:
return $this->step_in_frameset();
case WP_HTML_Processor_State::INSERTION_MODE_AFTER_FRAMESET:
return $this->step_after_frameset();
case WP_HTML_Processor_State::INSERTION_MODE_AFTER_AFTER_BODY:
return $this->step_after_after_body();
case WP_HTML_Processor_State::INSERTION_MODE_AFTER_AFTER_FRAMESET:
return $this->step_after_after_frameset();
// This should be unreachable but PHP doesn't have total type checking on switch.
default:
$this->bail( "Unaware of the requested parsing mode: '{$this->state->insertion_mode}'." );
}
}
$this->bail( 'Should not have been able to reach end of IN FOREIGN CONTENT processing. Check HTML API code.' );
// This unnecessary return prevents tools from inaccurately reporting type errors.
return false;
}
/*
* Internal helpers
*/
/**
* Creates a new bookmark for the currently-matched token and returns the generated name.
*
* @since 6.4.0
* @since 6.5.0 Renamed from bookmark_tag() to bookmark_token().
*
* @throws Exception When unable to allocate requested bookmark.
*
* @return string|false Name of created bookmark, or false if unable to create.
*/
private function bookmark_token() {
if ( ! parent::set_bookmark( ++$this->bookmark_counter ) ) {
$this->last_error = self::ERROR_EXCEEDED_MAX_BOOKMARKS;
throw new Exception( 'could not allocate bookmark' );
}
return "{$this->bookmark_counter}";
}
/*
* HTML semantic overrides for Tag Processor
*/
/**
* Indicates the namespace of the current token, or "html" if there is none.
*
* @return string One of "html", "math", or "svg".
*/
public function get_namespace(): string {
if ( ! isset( $this->current_element ) ) {
return parent::get_namespace();
}
return $this->current_element->token->namespace;
}
/**
* Returns the uppercase name of the matched tag.
*
* The semantic rules for HTML specify that certain tags be reprocessed
* with a different tag name. Because of this, the tag name presented
* by the HTML Processor may differ from the one reported by the HTML
* Tag Processor, which doesn't apply these semantic rules.
*
* Example:
*
* $processor = new WP_HTML_Tag_Processor( '
Test
' );
* $processor->next_tag() === true;
* $processor->get_tag() === 'DIV';
*
* $processor->next_tag() === false;
* $processor->get_tag() === null;
*
* @since 6.4.0
*
* @return string|null Name of currently matched tag in input HTML, or `null` if none found.
*/
public function get_tag(): ?string {
if ( null !== $this->last_error ) {
return null;
}
if ( $this->is_virtual() ) {
return $this->current_element->token->node_name;
}
$tag_name = parent::get_tag();
/*
* > A start tag whose tag name is "image"
* > Change the token's tag name to "img" and reprocess it. (Don't ask.)
*/
return ( 'IMAGE' === $tag_name && 'html' === $this->get_namespace() )
? 'IMG'
: $tag_name;
}
/**
* Indicates if the currently matched tag contains the self-closing flag.
*
* No HTML elements ought to have the self-closing flag and for those, the self-closing
* flag will be ignored. For void elements this is benign because they "self close"
* automatically. For non-void HTML elements though problems will appear if someone
* intends to use a self-closing element in place of that element with an empty body.
* For HTML foreign elements and custom elements the self-closing flag determines if
* they self-close or not.
*
* This function does not determine if a tag is self-closing,
* but only if the self-closing flag is present in the syntax.
*
* @since 6.6.0 Subclassed for the HTML Processor.
*
* @return bool Whether the currently matched tag contains the self-closing flag.
*/
public function has_self_closing_flag(): bool {
return $this->is_virtual() ? false : parent::has_self_closing_flag();
}
/**
* Returns the node name represented by the token.
*
* This matches the DOM API value `nodeName`. Some values
* are static, such as `#text` for a text node, while others
* are dynamically generated from the token itself.
*
* Dynamic names:
* - Uppercase tag name for tag matches.
* - `html` for DOCTYPE declarations.
*
* Note that if the Tag Processor is not matched on a token
* then this function will return `null`, either because it
* hasn't yet found a token or because it reached the end
* of the document without matching a token.
*
* @since 6.6.0 Subclassed for the HTML Processor.
*
* @return string|null Name of the matched token.
*/
public function get_token_name(): ?string {
return $this->is_virtual()
? $this->current_element->token->node_name
: parent::get_token_name();
}
/**
* Indicates the kind of matched token, if any.
*
* This differs from `get_token_name()` in that it always
* returns a static string indicating the type, whereas
* `get_token_name()` may return values derived from the
* token itself, such as a tag name or processing
* instruction tag.
*
* Possible values:
* - `#tag` when matched on a tag.
* - `#text` when matched on a text node.
* - `#cdata-section` when matched on a CDATA node.
* - `#comment` when matched on a comment.
* - `#doctype` when matched on a DOCTYPE declaration.
* - `#presumptuous-tag` when matched on an empty tag closer.
* - `#funky-comment` when matched on a funky comment.
*
* @since 6.6.0 Subclassed for the HTML Processor.
*
* @return string|null What kind of token is matched, or null.
*/
public function get_token_type(): ?string {
if ( $this->is_virtual() ) {
/*
* This logic comes from the Tag Processor.
*
* @todo It would be ideal not to repeat this here, but it's not clearly
* better to allow passing a token name to `get_token_type()`.
*/
$node_name = $this->current_element->token->node_name;
$starting_char = $node_name[0];
if ( 'A' <= $starting_char && 'Z' >= $starting_char ) {
return '#tag';
}
if ( 'html' === $node_name ) {
return '#doctype';
}
return $node_name;
}
return parent::get_token_type();
}
/**
* Returns the value of a requested attribute from a matched tag opener if that attribute exists.
*
* Example:
*
* $p = WP_HTML_Processor::create_fragment( '
Test
' );
* $p->next_token() === true;
* $p->get_attribute( 'data-test-id' ) === '14';
* $p->get_attribute( 'enabled' ) === true;
* $p->get_attribute( 'aria-label' ) === null;
*
* $p->next_tag() === false;
* $p->get_attribute( 'class' ) === null;
*
* @since 6.6.0 Subclassed for HTML Processor.
*
* @param string $name Name of attribute whose value is requested.
* @return string|true|null Value of attribute or `null` if not available. Boolean attributes return `true`.
*/
public function get_attribute( $name ) {
return $this->is_virtual() ? null : parent::get_attribute( $name );
}
/**
* Updates or creates a new attribute on the currently matched tag with the passed value.
*
* For boolean attributes special handling is provided:
* - When `true` is passed as the value, then only the attribute name is added to the tag.
* - When `false` is passed, the attribute gets removed if it existed before.
*
* For string attributes, the value is escaped using the `esc_attr` function.
*
* @since 6.6.0 Subclassed for the HTML Processor.
*
* @param string $name The attribute name to target.
* @param string|bool $value The new attribute value.
* @return bool Whether an attribute value was set.
*/
public function set_attribute( $name, $value ): bool {
return $this->is_virtual() ? false : parent::set_attribute( $name, $value );
}
/**
* Remove an attribute from the currently-matched tag.
*
* @since 6.6.0 Subclassed for HTML Processor.
*
* @param string $name The attribute name to remove.
* @return bool Whether an attribute was removed.
*/
public function remove_attribute( $name ): bool {
return $this->is_virtual() ? false : parent::remove_attribute( $name );
}
/**
* Gets lowercase names of all attributes matching a given prefix in the current tag.
*
* Note that matching is case-insensitive. This is in accordance with the spec:
*
* > There must never be two or more attributes on
* > the same start tag whose names are an ASCII
* > case-insensitive match for each other.
* - HTML 5 spec
*
* Example:
*
* $p = new WP_HTML_Tag_Processor( '
Test
' );
* $p->next_tag( array( 'class_name' => 'test' ) ) === true;
* $p->get_attribute_names_with_prefix( 'data-' ) === array( 'data-enabled', 'data-test-id' );
*
* $p->next_tag() === false;
* $p->get_attribute_names_with_prefix( 'data-' ) === null;
*
* @since 6.6.0 Subclassed for the HTML Processor.
*
* @see https://html.spec.whatwg.org/multipage/syntax.html#attributes-2:ascii-case-insensitive
*
* @param string $prefix Prefix of requested attribute names.
* @return array|null List of attribute names, or `null` when no tag opener is matched.
*/
public function get_attribute_names_with_prefix( $prefix ): ?array {
return $this->is_virtual() ? null : parent::get_attribute_names_with_prefix( $prefix );
}
/**
* Adds a new class name to the currently matched tag.
*
* @since 6.6.0 Subclassed for the HTML Processor.
*
* @param string $class_name The class name to add.
* @return bool Whether the class was set to be added.
*/
public function add_class( $class_name ): bool {
return $this->is_virtual() ? false : parent::add_class( $class_name );
}
/**
* Removes a class name from the currently matched tag.
*
* @since 6.6.0 Subclassed for the HTML Processor.
*
* @param string $class_name The class name to remove.
* @return bool Whether the class was set to be removed.
*/
public function remove_class( $class_name ): bool {
return $this->is_virtual() ? false : parent::remove_class( $class_name );
}
/**
* Returns if a matched tag contains the given ASCII case-insensitive class name.
*
* @since 6.6.0 Subclassed for the HTML Processor.
*
* @todo When reconstructing active formatting elements with attributes, find a way
* to indicate if the virtually-reconstructed formatting elements contain the
* wanted class name.
*
* @param string $wanted_class Look for this CSS class name, ASCII case-insensitive.
* @return bool|null Whether the matched tag contains the given class name, or null if not matched.
*/
public function has_class( $wanted_class ): ?bool {
return $this->is_virtual() ? null : parent::has_class( $wanted_class );
}
/**
* Generator for a foreach loop to step through each class name for the matched tag.
*
* This generator function is designed to be used inside a "foreach" loop.
*
* Example:
*
* $p = WP_HTML_Processor::create_fragment( "
" );
* $p->next_tag();
* foreach ( $p->class_list() as $class_name ) {
* echo "{$class_name} ";
* }
* // Outputs: "free lang-en "
*
* @since 6.6.0 Subclassed for the HTML Processor.
*/
public function class_list() {
return $this->is_virtual() ? null : parent::class_list();
}
/**
* Returns the modifiable text for a matched token, or an empty string.
*
* Modifiable text is text content that may be read and changed without
* changing the HTML structure of the document around it. This includes
* the contents of `#text` nodes in the HTML as well as the inner
* contents of HTML comments, Processing Instructions, and others, even
* though these nodes aren't part of a parsed DOM tree. They also contain
* the contents of SCRIPT and STYLE tags, of TEXTAREA tags, and of any
* other section in an HTML document which cannot contain HTML markup (DATA).
*
* If a token has no modifiable text then an empty string is returned to
* avoid needless crashing or type errors. An empty string does not mean
* that a token has modifiable text, and a token with modifiable text may
* have an empty string (e.g. a comment with no contents).
*
* @since 6.6.0 Subclassed for the HTML Processor.
*
* @return string
*/
public function get_modifiable_text(): string {
return $this->is_virtual() ? '' : parent::get_modifiable_text();
}
/**
* Indicates what kind of comment produced the comment node.
*
* Because there are different kinds of HTML syntax which produce
* comments, the Tag Processor tracks and exposes this as a type
* for the comment. Nominally only regular HTML comments exist as
* they are commonly known, but a number of unrelated syntax errors
* also produce comments.
*
* @see self::COMMENT_AS_ABRUPTLY_CLOSED_COMMENT
* @see self::COMMENT_AS_CDATA_LOOKALIKE
* @see self::COMMENT_AS_INVALID_HTML
* @see self::COMMENT_AS_HTML_COMMENT
* @see self::COMMENT_AS_PI_NODE_LOOKALIKE
*
* @since 6.6.0 Subclassed for the HTML Processor.
*
* @return string|null
*/
public function get_comment_type(): ?string {
return $this->is_virtual() ? null : parent::get_comment_type();
}
/**
* Removes a bookmark that is no longer needed.
*
* Releasing a bookmark frees up the small
* performance overhead it requires.
*
* @since 6.4.0
*
* @param string $bookmark_name Name of the bookmark to remove.
* @return bool Whether the bookmark already existed before removal.
*/
public function release_bookmark( $bookmark_name ): bool {
return parent::release_bookmark( "_{$bookmark_name}" );
}
/**
* Moves the internal cursor in the HTML Processor to a given bookmark's location.
*
* Be careful! Seeking backwards to a previous location resets the parser to the
* start of the document and reparses the entire contents up until it finds the
* sought-after bookmarked location.
*
* In order to prevent accidental infinite loops, there's a
* maximum limit on the number of times seek() can be called.
*
* @throws Exception When unable to allocate a bookmark for the next token in the input HTML document.
*
* @since 6.4.0
*
* @param string $bookmark_name Jump to the place in the document identified by this bookmark name.
* @return bool Whether the internal cursor was successfully moved to the bookmark's location.
*/
public function seek( $bookmark_name ): bool {
// Flush any pending updates to the document before beginning.
$this->get_updated_html();
$actual_bookmark_name = "_{$bookmark_name}";
$processor_started_at = $this->state->current_token
? $this->bookmarks[ $this->state->current_token->bookmark_name ]->start
: 0;
$bookmark_starts_at = $this->bookmarks[ $actual_bookmark_name ]->start;
$direction = $bookmark_starts_at > $processor_started_at ? 'forward' : 'backward';
/*
* If seeking backwards, it's possible that the sought-after bookmark exists within an element
* which has been closed before the current cursor; in other words, it has already been removed
* from the stack of open elements. This means that it's insufficient to simply pop off elements
* from the stack of open elements which appear after the bookmarked location and then jump to
* that location, as the elements which were open before won't be re-opened.
*
* In order to maintain consistency, the HTML Processor rewinds to the start of the document
* and reparses everything until it finds the sought-after bookmark.
*
* There are potentially better ways to do this: cache the parser state for each bookmark and
* restore it when seeking; store an immutable and idempotent register of where elements open
* and close.
*
* If caching the parser state it will be essential to properly maintain the cached stack of
* open elements and active formatting elements when modifying the document. This could be a
* tedious and time-consuming process as well, and so for now will not be performed.
*
* It may be possible to track bookmarks for where elements open and close, and in doing so
* be able to quickly recalculate breadcrumbs for any element in the document. It may even
* be possible to remove the stack of open elements and compute it on the fly this way.
* If doing this, the parser would need to track the opening and closing locations for all
* tokens in the breadcrumb path for any and all bookmarks. By utilizing bookmarks themselves
* this list could be automatically maintained while modifying the document. Finding the
* breadcrumbs would then amount to traversing that list from the start until the token
* being inspected. Once an element closes, if there are no bookmarks pointing to locations
* within that element, then all of these locations may be forgotten to save on memory use
* and computation time.
*/
if ( 'backward' === $direction ) {
/*
* When moving backward, stateful stacks should be cleared.
*/
foreach ( $this->state->stack_of_open_elements->walk_up() as $item ) {
$this->state->stack_of_open_elements->remove_node( $item );
}
foreach ( $this->state->active_formatting_elements->walk_up() as $item ) {
$this->state->active_formatting_elements->remove_node( $item );
}
/*
* **After** clearing stacks, more processor state can be reset.
* This must be done after clearing the stack because those stacks generate events that
* would appear on a subsequent call to `next_token()`.
*/
$this->state->frameset_ok = true;
$this->state->stack_of_template_insertion_modes = array();
$this->state->head_element = null;
$this->state->form_element = null;
$this->state->current_token = null;
$this->current_element = null;
$this->element_queue = array();
/*
* The absence of a context node indicates a full parse.
* The presence of a context node indicates a fragment parser.
*/
if ( null === $this->context_node ) {
$this->change_parsing_namespace( 'html' );
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_INITIAL;
$this->breadcrumbs = array();
$this->bookmarks['initial'] = new WP_HTML_Span( 0, 0 );
parent::seek( 'initial' );
unset( $this->bookmarks['initial'] );
} else {
/*
* Push the root-node (HTML) back onto the stack of open elements.
*
* Fragment parsers require this extra bit of setup.
* It's handled in full parsers by advancing the processor state.
*/
$this->state->stack_of_open_elements->push(
new WP_HTML_Token(
'root-node',
'HTML',
false
)
);
$this->change_parsing_namespace(
$this->context_node->integration_node_type
? 'html'
: $this->context_node->namespace
);
if ( 'TEMPLATE' === $this->context_node->node_name ) {
$this->state->stack_of_template_insertion_modes[] = WP_HTML_Processor_State::INSERTION_MODE_IN_TEMPLATE;
}
$this->reset_insertion_mode_appropriately();
$this->breadcrumbs = array_slice( $this->breadcrumbs, 0, 2 );
parent::seek( $this->context_node->bookmark_name );
}
}
/*
* Here, the processor moves forward through the document until it matches the bookmark.
* do-while is used here because the processor is expected to already be stopped on
* a token than may match the bookmarked location.
*/
do {
/*
* The processor will stop on virtual tokens, but bookmarks may not be set on them.
* They should not be matched when seeking a bookmark, skip them.
*/
if ( $this->is_virtual() ) {
continue;
}
if ( $bookmark_starts_at === $this->bookmarks[ $this->state->current_token->bookmark_name ]->start ) {
return true;
}
} while ( $this->next_token() );
return false;
}
/**
* Sets a bookmark in the HTML document.
*
* Bookmarks represent specific places or tokens in the HTML
* document, such as a tag opener or closer. When applying
* edits to a document, such as setting an attribute, the
* text offsets of that token may shift; the bookmark is
* kept updated with those shifts and remains stable unless
* the entire span of text in which the token sits is removed.
*
* Release bookmarks when they are no longer needed.
*
* Example:
*
*
Surprising fact you may not know!
* ^ ^
* \-|-- this `H2` opener bookmark tracks the token
*
*
Surprising fact you may no…
* ^ ^
* \-|-- it shifts with edits
*
* Bookmarks provide the ability to seek to a previously-scanned
* place in the HTML document. This avoids the need to re-scan
* the entire document.
*
* Example:
*
*
One
Two
Three
* ^^^^
* want to note this last item
*
* $p = new WP_HTML_Tag_Processor( $html );
* $in_list = false;
* while ( $p->next_tag( array( 'tag_closers' => $in_list ? 'visit' : 'skip' ) ) ) {
* if ( 'UL' === $p->get_tag() ) {
* if ( $p->is_tag_closer() ) {
* $in_list = false;
* $p->set_bookmark( 'resume' );
* if ( $p->seek( 'last-li' ) ) {
* $p->add_class( 'last-li' );
* }
* $p->seek( 'resume' );
* $p->release_bookmark( 'last-li' );
* $p->release_bookmark( 'resume' );
* } else {
* $in_list = true;
* }
* }
*
* if ( 'LI' === $p->get_tag() ) {
* $p->set_bookmark( 'last-li' );
* }
* }
*
* Bookmarks intentionally hide the internal string offsets
* to which they refer. They are maintained internally as
* updates are applied to the HTML document and therefore
* retain their "position" - the location to which they
* originally pointed. The inability to use bookmarks with
* functions like `substr` is therefore intentional to guard
* against accidentally breaking the HTML.
*
* Because bookmarks allocate memory and require processing
* for every applied update, they are limited and require
* a name. They should not be created with programmatically-made
* names, such as "li_{$index}" with some loop. As a general
* rule they should only be created with string-literal names
* like "start-of-section" or "last-paragraph".
*
* Bookmarks are a powerful tool to enable complicated behavior.
* Consider double-checking that you need this tool if you are
* reaching for it, as inappropriate use could lead to broken
* HTML structure or unwanted processing overhead.
*
* Bookmarks cannot be set on tokens that do no appear in the original
* HTML text. For example, the HTML `
` stops at tags `TABLE`,
* `TBODY`, `TR`, and `TD`. The `TBODY` and `TR` tags do not appear in
* the original HTML and cannot be used as bookmarks.
*
* @since 6.4.0
*
* @param string $bookmark_name Identifies this particular bookmark.
* @return bool Whether the bookmark was successfully created.
*/
public function set_bookmark( $bookmark_name ): bool {
if ( $this->is_virtual() ) {
_doing_it_wrong(
__METHOD__,
__( 'Cannot set bookmarks on tokens that do no appear in the original HTML text.' ),
'6.8.0'
);
return false;
}
return parent::set_bookmark( "_{$bookmark_name}" );
}
/**
* Checks whether a bookmark with the given name exists.
*
* @since 6.5.0
*
* @param string $bookmark_name Name to identify a bookmark that potentially exists.
* @return bool Whether that bookmark exists.
*/
public function has_bookmark( $bookmark_name ): bool {
return parent::has_bookmark( "_{$bookmark_name}" );
}
/*
* HTML Parsing Algorithms
*/
/**
* Closes a P element.
*
* @since 6.4.0
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#close-a-p-element
*/
private function close_a_p_element(): void {
$this->generate_implied_end_tags( 'P' );
$this->state->stack_of_open_elements->pop_until( 'P' );
}
/**
* Closes elements that have implied end tags.
*
* @since 6.4.0
* @since 6.7.0 Full spec support.
*
* @see https://html.spec.whatwg.org/#generate-implied-end-tags
*
* @param string|null $except_for_this_element Perform as if this element doesn't exist in the stack of open elements.
*/
private function generate_implied_end_tags( ?string $except_for_this_element = null ): void {
$elements_with_implied_end_tags = array(
'DD',
'DT',
'LI',
'OPTGROUP',
'OPTION',
'P',
'RB',
'RP',
'RT',
'RTC',
);
$no_exclusions = ! isset( $except_for_this_element );
while (
( $no_exclusions || ! $this->state->stack_of_open_elements->current_node_is( $except_for_this_element ) ) &&
in_array( $this->state->stack_of_open_elements->current_node()->node_name, $elements_with_implied_end_tags, true )
) {
$this->state->stack_of_open_elements->pop();
}
}
/**
* Closes elements that have implied end tags, thoroughly.
*
* See the HTML specification for an explanation why this is
* different from generating end tags in the normal sense.
*
* @since 6.4.0
* @since 6.7.0 Full spec support.
*
* @see WP_HTML_Processor::generate_implied_end_tags
* @see https://html.spec.whatwg.org/#generate-implied-end-tags
*/
private function generate_implied_end_tags_thoroughly(): void {
$elements_with_implied_end_tags = array(
'CAPTION',
'COLGROUP',
'DD',
'DT',
'LI',
'OPTGROUP',
'OPTION',
'P',
'RB',
'RP',
'RT',
'RTC',
'TBODY',
'TD',
'TFOOT',
'TH',
'THEAD',
'TR',
);
while ( in_array( $this->state->stack_of_open_elements->current_node()->node_name, $elements_with_implied_end_tags, true ) ) {
$this->state->stack_of_open_elements->pop();
}
}
/**
* Returns the adjusted current node.
*
* > The adjusted current node is the context element if the parser was created as
* > part of the HTML fragment parsing algorithm and the stack of open elements
* > has only one element in it (fragment case); otherwise, the adjusted current
* > node is the current node.
*
* @see https://html.spec.whatwg.org/#adjusted-current-node
*
* @since 6.7.0
*
* @return WP_HTML_Token|null The adjusted current node.
*/
private function get_adjusted_current_node(): ?WP_HTML_Token {
if ( isset( $this->context_node ) && 1 === $this->state->stack_of_open_elements->count() ) {
return $this->context_node;
}
return $this->state->stack_of_open_elements->current_node();
}
/**
* Reconstructs the active formatting elements.
*
* > This has the effect of reopening all the formatting elements that were opened
* > in the current body, cell, or caption (whichever is youngest) that haven't
* > been explicitly closed.
*
* @since 6.4.0
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#reconstruct-the-active-formatting-elements
*
* @return bool Whether any formatting elements needed to be reconstructed.
*/
private function reconstruct_active_formatting_elements(): bool {
/*
* > If there are no entries in the list of active formatting elements, then there is nothing
* > to reconstruct; stop this algorithm.
*/
if ( 0 === $this->state->active_formatting_elements->count() ) {
return false;
}
$last_entry = $this->state->active_formatting_elements->current_node();
if (
/*
* > If the last (most recently added) entry in the list of active formatting elements is a marker;
* > stop this algorithm.
*/
'marker' === $last_entry->node_name ||
/*
* > If the last (most recently added) entry in the list of active formatting elements is an
* > element that is in the stack of open elements, then there is nothing to reconstruct;
* > stop this algorithm.
*/
$this->state->stack_of_open_elements->contains_node( $last_entry )
) {
return false;
}
$this->bail( 'Cannot reconstruct active formatting elements when advancing and rewinding is required.' );
}
/**
* Runs the reset the insertion mode appropriately algorithm.
*
* @since 6.7.0
*
* @see https://html.spec.whatwg.org/multipage/parsing.html#reset-the-insertion-mode-appropriately
*/
private function reset_insertion_mode_appropriately(): void {
// Set the first node.
$first_node = null;
foreach ( $this->state->stack_of_open_elements->walk_down() as $first_node ) {
break;
}
/*
* > 1. Let _last_ be false.
*/
$last = false;
foreach ( $this->state->stack_of_open_elements->walk_up() as $node ) {
/*
* > 2. Let _node_ be the last node in the stack of open elements.
* > 3. _Loop_: If _node_ is the first node in the stack of open elements, then set _last_
* > to true, and, if the parser was created as part of the HTML fragment parsing
* > algorithm (fragment case), set node to the context element passed to
* > that algorithm.
* > …
*/
if ( $node === $first_node ) {
$last = true;
if ( isset( $this->context_node ) ) {
$node = $this->context_node;
}
}
// All of the following rules are for matching HTML elements.
if ( 'html' !== $node->namespace ) {
continue;
}
switch ( $node->node_name ) {
/*
* > 4. If node is a `select` element, run these substeps:
* > 1. If _last_ is true, jump to the step below labeled done.
* > 2. Let _ancestor_ be _node_.
* > 3. _Loop_: If _ancestor_ is the first node in the stack of open elements,
* > jump to the step below labeled done.
* > 4. Let ancestor be the node before ancestor in the stack of open elements.
* > …
* > 7. Jump back to the step labeled _loop_.
* > 8. _Done_: Switch the insertion mode to "in select" and return.
*/
case 'SELECT':
if ( ! $last ) {
foreach ( $this->state->stack_of_open_elements->walk_up( $node ) as $ancestor ) {
if ( 'html' !== $ancestor->namespace ) {
continue;
}
switch ( $ancestor->node_name ) {
/*
* > 5. If _ancestor_ is a `template` node, jump to the step below
* > labeled _done_.
*/
case 'TEMPLATE':
break 2;
/*
* > 6. If _ancestor_ is a `table` node, switch the insertion mode to
* > "in select in table" and return.
*/
case 'TABLE':
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_SELECT_IN_TABLE;
return;
}
}
}
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_SELECT;
return;
/*
* > 5. If _node_ is a `td` or `th` element and _last_ is false, then switch the
* > insertion mode to "in cell" and return.
*/
case 'TD':
case 'TH':
if ( ! $last ) {
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_CELL;
return;
}
break;
/*
* > 6. If _node_ is a `tr` element, then switch the insertion mode to "in row"
* > and return.
*/
case 'TR':
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_ROW;
return;
/*
* > 7. If _node_ is a `tbody`, `thead`, or `tfoot` element, then switch the
* > insertion mode to "in table body" and return.
*/
case 'TBODY':
case 'THEAD':
case 'TFOOT':
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY;
return;
/*
* > 8. If _node_ is a `caption` element, then switch the insertion mode to
* > "in caption" and return.
*/
case 'CAPTION':
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_CAPTION;
return;
/*
* > 9. If _node_ is a `colgroup` element, then switch the insertion mode to
* > "in column group" and return.
*/
case 'COLGROUP':
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_COLUMN_GROUP;
return;
/*
* > 10. If _node_ is a `table` element, then switch the insertion mode to
* > "in table" and return.
*/
case 'TABLE':
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE;
return;
/*
* > 11. If _node_ is a `template` element, then switch the insertion mode to the
* > current template insertion mode and return.
*/
case 'TEMPLATE':
$this->state->insertion_mode = end( $this->state->stack_of_template_insertion_modes );
return;
/*
* > 12. If _node_ is a `head` element and _last_ is false, then switch the
* > insertion mode to "in head" and return.
*/
case 'HEAD':
if ( ! $last ) {
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_HEAD;
return;
}
break;
/*
* > 13. If _node_ is a `body` element, then switch the insertion mode to "in body"
* > and return.
*/
case 'BODY':
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY;
return;
/*
* > 14. If _node_ is a `frameset` element, then switch the insertion mode to
* > "in frameset" and return. (fragment case)
*/
case 'FRAMESET':
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_FRAMESET;
return;
/*
* > 15. If _node_ is an `html` element, run these substeps:
* > 1. If the head element pointer is null, switch the insertion mode to
* > "before head" and return. (fragment case)
* > 2. Otherwise, the head element pointer is not null, switch the insertion
* > mode to "after head" and return.
*/
case 'HTML':
$this->state->insertion_mode = isset( $this->state->head_element )
? WP_HTML_Processor_State::INSERTION_MODE_AFTER_HEAD
: WP_HTML_Processor_State::INSERTION_MODE_BEFORE_HEAD;
return;
}
}
/*
* > 16. If _last_ is true, then switch the insertion mode to "in body"
* > and return. (fragment case)
*
* This is only reachable if `$last` is true, as per the fragment parsing case.
*/
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY;
}
/**
* Runs the adoption agency algorithm.
*
* @since 6.4.0
*
* @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
*
* @see https://html.spec.whatwg.org/#adoption-agency-algorithm
*/
private function run_adoption_agency_algorithm(): void {
$budget = 1000;
$subject = $this->get_tag();
$current_node = $this->state->stack_of_open_elements->current_node();
if (
// > If the current node is an HTML element whose tag name is subject
$current_node && $subject === $current_node->node_name &&
// > the current node is not in the list of active formatting elements
! $this->state->active_formatting_elements->contains_node( $current_node )
) {
$this->state->stack_of_open_elements->pop();
return;
}
$outer_loop_counter = 0;
while ( $budget-- > 0 ) {
if ( $outer_loop_counter++ >= 8 ) {
return;
}
/*
* > Let formatting element be the last element in the list of active formatting elements that:
* > - is between the end of the list and the last marker in the list,
* > if any, or the start of the list otherwise,
* > - and has the tag name subject.
*/
$formatting_element = null;
foreach ( $this->state->active_formatting_elements->walk_up() as $item ) {
if ( 'marker' === $item->node_name ) {
break;
}
if ( $subject === $item->node_name ) {
$formatting_element = $item;
break;
}
}
// > 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->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.
if ( ! $this->state->stack_of_open_elements->contains_node( $formatting_element ) ) {
$this->state->active_formatting_elements->remove_node( $formatting_element );
return;
}
// > If formatting element is in the stack of open elements, but the element is not in scope, then this is a parse error; return.
if ( ! $this->state->stack_of_open_elements->has_element_in_scope( $formatting_element->node_name ) ) {
return;
}
/*
* > Let furthest block be the topmost node in the stack of open elements that is lower in the stack
* > than formatting element, and is an element in the special category. There might not be one.
*/
$is_above_formatting_element = true;
$furthest_block = null;
foreach ( $this->state->stack_of_open_elements->walk_down() as $item ) {
if ( $is_above_formatting_element && $formatting_element->bookmark_name !== $item->bookmark_name ) {
continue;
}
if ( $is_above_formatting_element ) {
$is_above_formatting_element = false;
continue;
}
if ( self::is_special( $item ) ) {
$furthest_block = $item;
break;
}
}
/*
* > If there is no furthest block, then the UA must first pop all the nodes from the bottom of the
* > stack of open elements, from the current node up to and including formatting element, then
* > remove formatting element from the list of active formatting elements, and finally return.
*/
if ( null === $furthest_block ) {
foreach ( $this->state->stack_of_open_elements->walk_up() as $item ) {
$this->state->stack_of_open_elements->pop();
if ( $formatting_element->bookmark_name === $item->bookmark_name ) {
$this->state->active_formatting_elements->remove_node( $formatting_element );
return;
}
}
}
$this->bail( 'Cannot extract common ancestor in adoption agency algorithm.' );
}
$this->bail( 'Cannot run adoption agency when looping required.' );
}
/**
* Runs the "close the cell" algorithm.
*
* > Where the steps above say to close the cell, they mean to run the following algorithm:
* > 1. Generate implied end tags.
* > 2. If the current node is not now a td element or a th element, then this is a parse error.
* > 3. Pop elements from the stack of open elements stack until a td element or a th element has been popped from the stack.
* > 4. Clear the list of active formatting elements up to the last marker.
* > 5. Switch the insertion mode to "in row".
*
* @see https://html.spec.whatwg.org/multipage/parsing.html#close-the-cell
*
* @since 6.7.0
*/
private function close_cell(): void {
$this->generate_implied_end_tags();
// @todo Parse error if the current node is a "td" or "th" element.
foreach ( $this->state->stack_of_open_elements->walk_up() as $element ) {
$this->state->stack_of_open_elements->pop();
if ( 'TD' === $element->node_name || 'TH' === $element->node_name ) {
break;
}
}
$this->state->active_formatting_elements->clear_up_to_last_marker();
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_ROW;
}
/**
* Inserts an HTML element on the stack of open elements.
*
* @since 6.4.0
*
* @see https://html.spec.whatwg.org/#insert-a-foreign-element
*
* @param WP_HTML_Token $token Name of bookmark pointing to element in original input HTML.
*/
private function insert_html_element( WP_HTML_Token $token ): void {
$this->state->stack_of_open_elements->push( $token );
}
/**
* Inserts a foreign element on to the stack of open elements.
*
* @since 6.7.0
*
* @see https://html.spec.whatwg.org/#insert-a-foreign-element
*
* @param WP_HTML_Token $token Insert this token. The token's namespace and
* insertion point will be updated correctly.
* @param bool $only_add_to_element_stack Whether to skip the "insert an element at the adjusted
* insertion location" algorithm when adding this element.
*/
private function insert_foreign_element( WP_HTML_Token $token, bool $only_add_to_element_stack ): void {
$adjusted_current_node = $this->get_adjusted_current_node();
$token->namespace = $adjusted_current_node ? $adjusted_current_node->namespace : 'html';
if ( $this->is_mathml_integration_point() ) {
$token->integration_node_type = 'math';
} elseif ( $this->is_html_integration_point() ) {
$token->integration_node_type = 'html';
}
if ( false === $only_add_to_element_stack ) {
/*
* @todo Implement the "appropriate place for inserting a node" and the
* "insert an element at the adjusted insertion location" algorithms.
*
* These algorithms mostly impacts DOM tree construction and not the HTML API.
* Here, there's no DOM node onto which the element will be appended, so the
* parser will skip this step.
*
* @see https://html.spec.whatwg.org/#insert-an-element-at-the-adjusted-insertion-location
*/
}
$this->insert_html_element( $token );
}
/**
* Inserts a virtual element on the stack of open elements.
*
* @since 6.7.0
*
* @param string $token_name Name of token to create and insert into the stack of open elements.
* @param string|null $bookmark_name Optional. Name to give bookmark for created virtual node.
* Defaults to auto-creating a bookmark name.
* @return WP_HTML_Token Newly-created virtual token.
*/
private function insert_virtual_node( $token_name, $bookmark_name = null ): WP_HTML_Token {
$here = $this->bookmarks[ $this->state->current_token->bookmark_name ];
$name = $bookmark_name ?? $this->bookmark_token();
$this->bookmarks[ $name ] = new WP_HTML_Span( $here->start, 0 );
$token = new WP_HTML_Token( $name, $token_name, false );
$this->insert_html_element( $token );
return $token;
}
/*
* HTML Specification Helpers
*/
/**
* Indicates if the current token is a MathML integration point.
*
* @since 6.7.0
*
* @see https://html.spec.whatwg.org/#mathml-text-integration-point
*
* @return bool Whether the current token is a MathML integration point.
*/
private function is_mathml_integration_point(): bool {
$current_token = $this->state->current_token;
if ( ! isset( $current_token ) ) {
return false;
}
if ( 'math' !== $current_token->namespace || 'M' !== $current_token->node_name[0] ) {
return false;
}
$tag_name = $current_token->node_name;
return (
'MI' === $tag_name ||
'MO' === $tag_name ||
'MN' === $tag_name ||
'MS' === $tag_name ||
'MTEXT' === $tag_name
);
}
/**
* Indicates if the current token is an HTML integration point.
*
* Note that this method must be an instance method with access
* to the current token, since it needs to examine the attributes
* of the currently-matched tag, if it's in the MathML namespace.
* Otherwise it would be required to scan the HTML and ensure that
* no other accounting is overlooked.
*
* @since 6.7.0
*
* @see https://html.spec.whatwg.org/#html-integration-point
*
* @return bool Whether the current token is an HTML integration point.
*/
private function is_html_integration_point(): bool {
$current_token = $this->state->current_token;
if ( ! isset( $current_token ) ) {
return false;
}
if ( 'html' === $current_token->namespace ) {
return false;
}
$tag_name = $current_token->node_name;
if ( 'svg' === $current_token->namespace ) {
return (
'DESC' === $tag_name ||
'FOREIGNOBJECT' === $tag_name ||
'TITLE' === $tag_name
);
}
if ( 'math' === $current_token->namespace ) {
if ( 'ANNOTATION-XML' !== $tag_name ) {
return false;
}
$encoding = $this->get_attribute( 'encoding' );
return (
is_string( $encoding ) &&
(
0 === strcasecmp( $encoding, 'application/xhtml+xml' ) ||
0 === strcasecmp( $encoding, 'text/html' )
)
);
}
$this->bail( 'Should not have reached end of HTML Integration Point detection: check HTML API code.' );
// This unnecessary return prevents tools from inaccurately reporting type errors.
return false;
}
/**
* Returns whether an element of a given name is in the HTML special category.
*
* @since 6.4.0
*
* @see https://html.spec.whatwg.org/#special
*
* @param WP_HTML_Token|string $tag_name Node to check, or only its name if in the HTML namespace.
* @return bool Whether the element of the given name is in the special category.
*/
public static function is_special( $tag_name ): bool {
if ( is_string( $tag_name ) ) {
$tag_name = strtoupper( $tag_name );
} else {
$tag_name = 'html' === $tag_name->namespace
? strtoupper( $tag_name->node_name )
: "{$tag_name->namespace} {$tag_name->node_name}";
}
return (
'ADDRESS' === $tag_name ||
'APPLET' === $tag_name ||
'AREA' === $tag_name ||
'ARTICLE' === $tag_name ||
'ASIDE' === $tag_name ||
'BASE' === $tag_name ||
'BASEFONT' === $tag_name ||
'BGSOUND' === $tag_name ||
'BLOCKQUOTE' === $tag_name ||
'BODY' === $tag_name ||
'BR' === $tag_name ||
'BUTTON' === $tag_name ||
'CAPTION' === $tag_name ||
'CENTER' === $tag_name ||
'COL' === $tag_name ||
'COLGROUP' === $tag_name ||
'DD' === $tag_name ||
'DETAILS' === $tag_name ||
'DIR' === $tag_name ||
'DIV' === $tag_name ||
'DL' === $tag_name ||
'DT' === $tag_name ||
'EMBED' === $tag_name ||
'FIELDSET' === $tag_name ||
'FIGCAPTION' === $tag_name ||
'FIGURE' === $tag_name ||
'FOOTER' === $tag_name ||
'FORM' === $tag_name ||
'FRAME' === $tag_name ||
'FRAMESET' === $tag_name ||
'H1' === $tag_name ||
'H2' === $tag_name ||
'H3' === $tag_name ||
'H4' === $tag_name ||
'H5' === $tag_name ||
'H6' === $tag_name ||
'HEAD' === $tag_name ||
'HEADER' === $tag_name ||
'HGROUP' === $tag_name ||
'HR' === $tag_name ||
'HTML' === $tag_name ||
'IFRAME' === $tag_name ||
'IMG' === $tag_name ||
'INPUT' === $tag_name ||
'KEYGEN' === $tag_name ||
'LI' === $tag_name ||
'LINK' === $tag_name ||
'LISTING' === $tag_name ||
'MAIN' === $tag_name ||
'MARQUEE' === $tag_name ||
'MENU' === $tag_name ||
'META' === $tag_name ||
'NAV' === $tag_name ||
'NOEMBED' === $tag_name ||
'NOFRAMES' === $tag_name ||
'NOSCRIPT' === $tag_name ||
'OBJECT' === $tag_name ||
'OL' === $tag_name ||
'P' === $tag_name ||
'PARAM' === $tag_name ||
'PLAINTEXT' === $tag_name ||
'PRE' === $tag_name ||
'SCRIPT' === $tag_name ||
'SEARCH' === $tag_name ||
'SECTION' === $tag_name ||
'SELECT' === $tag_name ||
'SOURCE' === $tag_name ||
'STYLE' === $tag_name ||
'SUMMARY' === $tag_name ||
'TABLE' === $tag_name ||
'TBODY' === $tag_name ||
'TD' === $tag_name ||
'TEMPLATE' === $tag_name ||
'TEXTAREA' === $tag_name ||
'TFOOT' === $tag_name ||
'TH' === $tag_name ||
'THEAD' === $tag_name ||
'TITLE' === $tag_name ||
'TR' === $tag_name ||
'TRACK' === $tag_name ||
'UL' === $tag_name ||
'WBR' === $tag_name ||
'XMP' === $tag_name ||
// MathML.
'math MI' === $tag_name ||
'math MO' === $tag_name ||
'math MN' === $tag_name ||
'math MS' === $tag_name ||
'math MTEXT' === $tag_name ||
'math ANNOTATION-XML' === $tag_name ||
// SVG.
'svg DESC' === $tag_name ||
'svg FOREIGNOBJECT' === $tag_name ||
'svg TITLE' === $tag_name
);
}
/**
* Returns whether a given element is an HTML Void Element
*
* > area, base, br, col, embed, hr, img, input, link, meta, source, track, wbr
*
* @since 6.4.0
*
* @see https://html.spec.whatwg.org/#void-elements
*
* @param string $tag_name Name of HTML tag to check.
* @return bool Whether the given tag is an HTML Void Element.
*/
public static function is_void( $tag_name ): bool {
$tag_name = strtoupper( $tag_name );
return (
'AREA' === $tag_name ||
'BASE' === $tag_name ||
'BASEFONT' === $tag_name || // Obsolete but still treated as void.
'BGSOUND' === $tag_name || // Obsolete but still treated as void.
'BR' === $tag_name ||
'COL' === $tag_name ||
'EMBED' === $tag_name ||
'FRAME' === $tag_name ||
'HR' === $tag_name ||
'IMG' === $tag_name ||
'INPUT' === $tag_name ||
'KEYGEN' === $tag_name || // Obsolete but still treated as void.
'LINK' === $tag_name ||
'META' === $tag_name ||
'PARAM' === $tag_name || // Obsolete but still treated as void.
'SOURCE' === $tag_name ||
'TRACK' === $tag_name ||
'WBR' === $tag_name
);
}
/**
* Gets an encoding from a given string.
*
* This is an algorithm defined in the WHAT-WG specification.
*
* Example:
*
* 'UTF-8' === self::get_encoding( 'utf8' );
* 'UTF-8' === self::get_encoding( " \tUTF-8 " );
* null === self::get_encoding( 'UTF-7' );
* null === self::get_encoding( 'utf8; charset=' );
*
* @see https://encoding.spec.whatwg.org/#concept-encoding-get
*
* @todo As this parser only supports UTF-8, only the UTF-8
* encodings are detected. Add more as desired, but the
* parser will bail on non-UTF-8 encodings.
*
* @since 6.7.0
*
* @param string $label A string which may specify a known encoding.
* @return string|null Known encoding if matched, otherwise null.
*/
protected static function get_encoding( string $label ): ?string {
/*
* > Remove any leading and trailing ASCII whitespace from label.
*/
$label = trim( $label, " \t\f\r\n" );
/*
* > If label is an ASCII case-insensitive match for any of the labels listed in the
* > table below, then return the corresponding encoding; otherwise return failure.
*/
switch ( strtolower( $label ) ) {
case 'unicode-1-1-utf-8':
case 'unicode11utf8':
case 'unicode20utf8':
case 'utf-8':
case 'utf8':
case 'x-unicode20utf8':
return 'UTF-8';
default:
return null;
}
}
/*
* Constants that would pollute the top of the class if they were found there.
*/
/**
* Indicates that the next HTML token should be parsed and processed.
*
* @since 6.4.0
*
* @var string
*/
const PROCESS_NEXT_NODE = 'process-next-node';
/**
* Indicates that the current HTML token should be reprocessed in the newly-selected insertion mode.
*
* @since 6.4.0
*
* @var string
*/
const REPROCESS_CURRENT_NODE = 'reprocess-current-node';
/**
* Indicates that the current HTML token should be processed without advancing the parser.
*
* @since 6.5.0
*
* @var string
*/
const PROCESS_CURRENT_NODE = 'process-current-node';
/**
* Indicates that the parser encountered unsupported markup and has bailed.
*
* @since 6.4.0
*
* @var string
*/
const ERROR_UNSUPPORTED = 'unsupported';
/**
* Indicates that the parser encountered more HTML tokens than it
* was able to process and has bailed.
*
* @since 6.4.0
*
* @var string
*/
const ERROR_EXCEEDED_MAX_BOOKMARKS = 'exceeded-max-bookmarks';
/**
* Unlock code that must be passed into the constructor to create this class.
*
* This class extends the WP_HTML_Tag_Processor, which has a public class
* constructor. Therefore, it's not possible to have a private constructor here.
*
* This unlock code is used to ensure that anyone calling the constructor is
* doing so with a full understanding that it's intended to be a private API.
*
* @access private
*/
const CONSTRUCTOR_UNLOCK_CODE = 'Use WP_HTML_Processor::create_fragment() instead of calling the class constructor directly.';
}
Scruffy Wants You On Your Hands And Knees – UK Muppets
Don’t worry, it’s not the disgusting thought some of you are thinking. No, we are talking another one Scruffy’s fetishes, banning!
I’m seriously starting to worry about the kind of life the Vaughns have led so far. The way they need to feel the power to make you beneath them, is a typical reaction to being bullied in the past.
We’ve heard time and time again how Mark was pulled out of School because it was allegedly rife with rape and drugs. But it does make you think, is that really why he was pulled out?
People are highly critical of so called power obsessed Mods in channels, such as AngelStormee. But as much as i’ve seen her ban people for silly reasons, i don’t recall her ever doing this:
A guest say’s something she doesn’t like, so she tells them to shut up (very professional), but then, somewhat bizarrely, tells them to beg her for their IP address back. WTF?
At first, i thought she was just trolling. Then she gives the email to contact her, to beg for their ‘IP’ address back (how do you beg for your ip back?)
Still stunned, i’m thinking, nah, she’s just taking the piss out of herself, she’s not being serious, surely?
Hmm. I’m sure FoxmanShawn is pulling in more viewers on Blab than he used to on Vaughn? Joe Walsh, is he begging to come back?
No, thought not!
The delusion doesn’t end there though. This was her reply to Jackielee mentioning blogtv.ca launching soon.
Arrogant, or simply deluded? Either way, if this Blogtv does launch, i’m going to love seeing the cocky smirk being wiped off the Vaughns faces.
I wonder how many people will be getting down on their knees and begging for forgiveness to Scruffy then?
lmao, She banned me, I have never and don’t intend to beg to be unbanned. She just can’t help but keep on shooting herself in the foot. hahahahahaha That’s the most funniest thing I have read yet, the headline should read “The daftness of Miss Scruffy”
Lol Ben have to agree the only thing I have done is ask why I was IP banned then had my channel closed for merely having a difference of opinion with Scruffy but of course no reply has ever been received.
I was in GG’s sorry Scratches room and asked Mark straight out but his reply was I dont know of anyone being IP banned or having their channel closed, if it has been then my mother must of had just reason for doing so she doesnt just ban for disagreeing with her. YES MARK SHE DOES and you know it.
She is delusional if Mark was any sort of a man he would pull his mother into line but she is still breast feeding him it seems and he hasnt got the balls to stand up to her.
Vaughn is all but dead and tbh a lot of the staff and techs are getting the same if you say one word they dont like wham your gone from the channel.
I now can’t even be bothered to make up another name and log into vaughn oh and Mark I’m still waiting for you to reply to my FB message about why but I have a feeling hell may freeze over before that happens
Pity during that conversation I had with her in trying to get it through her head that I had no part to play in what she was throwing at me, surely with me Being in the UK and hadn’t even bothered to ask me where I was from as anybody can read with that conversation I have published in various places, should have looked up the location of the IP which again, was not my IP she had banned but still, stuck to her story non the less in accusing me of streaming porn and in posting the links to porn site. How stupid is that? Surely with her classing herself as the director of Vaughnlive, she would have at least made some effort and apologising that she was and still is in the wrong.
The site’s rules says no disrespect of staff, meaning don’t say that the community manager’s personal illnesses are all on her head – that is very disrespectful. There is a difference between ‘difference of opinion’ and attacking someone, I guess not everyone is capable of understanding that. If she believes the earth is flat for example, and you don’t – that’s fine. But you’re not allowed to try to publicly shame someone for what you think their illnesses are. I do not understand in the least bit why any of you think this is out of line.
Youknowwho in no way was i disrespectful to scruffy on the contrary she was extremely rude to me. There was a discussion about whether VIP casters received preferential treatment over other casters and I am not talking access etc but in general. I stated that from what I could see there was clearly one set of rules for the VIP casters and another for those choosing not to take it up.
Scruffy said prove it so I gave her a recent example and i was met with the words well if you dont like it fuck off then and I was IP banned.
About 2 weeks later I tried to sign in under my name and my channel had been closed due to violation of TOS guidelines. I have asked for an explanation but received none (again very politely). I can fully understand people saying that scruffy is ruining the site and she is indeed using to settle personal grudges and it doesnt surprise me in the least that she is demanding people beg her to get their IP or channel back. She is a nasty woman full of her own self importance when in fact if it wasnt for the casters and guests vaughn would not exist and the rate she is alienating everyone it will soon disappear and Mark will only have himself because he does nothing to stop her running wild and his mother to blame for their demise.
I saw you being disrespectful to her as a guest in the screenshots in this blog post mr. anonymous – you might not think so but it was way out of line. Respect of staff means do not question their dealings with others also….
these are words on a screen, doesn’t matter what or who the source is or where they come from. It’s just logical debating. You can plainly see Guest 752 saying in the screenshots that they believe all of Miss Scruffy’s illnesses are in her head, and she has mental illness issues. That’s a blatant accusation and completely disrespectful, isn’t it? Or do you not agree?
Ryan you saw fuck all now get out of the vaughns asses. Respect of staff does not mean they can run riot and treat people like shit.
Tell me exactly what was being disrespectful or way out of line in the post you comment on being told to fuck off because of an observation doesnt warrant any respect of any sort kinda like i have for you absolutely none.
I saw come into a cast on Ivlog troll then run back to vaughn shouting I stuck up for you Mark can I suck your cock now.
Okay Katie – this “Guest_75232401754: Yes bc it’s a mental ILLNESS — you needed help you never got bc of PC”
For those of you who cannot read between the lines, what this guest has essentially said is that “miss scruffy, stop being so politically correct, you are mentally ill and all your health problems are in your head”
Now that is VERY disrespectful, and that’s why the person was warned to get a new IP – it means an IP ban is imminent and coming at any moment for what that guest just said.
This is absolutely insane – you cannot logically debate. Anything turns into personal attacks against the one who has an opposite point of view.
This isn’t about me, or you, this is a logical debate about whether or not Miss Scruffy is out of line, and she isn’t. Where on earth do any of you get the idea that it’s perfectly alright to voice an opinion that puts any of the site’s staff in a negative light? You can do it here on your blogs, but if you do it on vaughnlive you’ll get dealt with. And then suddenly in your eyes the problem is with them, when you have been the one who behaved badly. This is akin to a 5 year old flipping out because daddy won’t buy the sugary cereal the child wants when visiting the supermarket – then you go and tell your daddy to fuck off when he says no. Positions of AUTHORITY mean that authority should be respected, not mocked. If this 100% logical argument flies above your heads there is nothing more to say.
sorry, your juvenile taunting and bullying tactics (trying to shame me into changing my opinion because you cannot understand why someone would see something another way) won’t work on me.
Ryan I was not in anyway disrespectful to Miss Scruffy I had a different opinion on a subject that they wanted open debate on but because I did not share the same view as Miss Scruffy she was the one who became abusive and childish. If she didnt want to hear other people’s opinion why the hell ask for it in the first place. Just because you are the site owners mother does not give her the right to bully other people. Yes Ryan bully a word you love to bandy around. With her current attitude she should not be in any position of authority as she is using VaughnLive to hold and settle petty grudges with people.
I feel sorry for you Ryan because you need to take off you rose coloured glasses and see what is really happening on VL.
I understand that you cannot see further than you undying devotion to the Vaughns but I doubt they appreciate it and would kick you out as soon as see your name appear on screen if they had a mind to and it would probably be for no reason at all other than Miss Scruffy felt like it.
see, you’re typing to me in an unfriendly and insulting manner. Don’t you see if this was VL and i was Miss Scruffy, suggesting I or someone else belong in an institution is grounds for a ban…
It’s not ‘telling it like it is’ or ‘exercising your right to free speech’
I didnt type that Ryan now please answer my question about Scruffys rude and arrogant behaviour and her decision to ban someone because she doesnt like the answer to a question she has asked.
You totally ignore that because it would mean that Miss Scruffy was wrong and I dont feel you could possibly type anything that was against the Vaughns.
How about you get your head out of your ass hole Ryan and start reading stuff of what Miss Scruffy is sending out. This is the reason why people are so pissed off about, stop listening to bullshit son and listen to the other side of the story before jumping into sticking up for the likes of Scruffy.
Yes, Scruffy is actually a cunt I have you know, I never stepped out of line myself against her or as she has claimed, broken any TOS on Vaughn.
Yes, you did Ben – you just were too damn drunk to remember. I have seen you on their site many times being abusive to staff and making fun of them. As for ‘Anonymous’ – I have explained that Miss Scruffy was justified in banning the IP of Guest752XXX.
This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish.AcceptRejectRead More
Privacy & Cookies Policy
Privacy Overview
This website uses cookies to improve your experience while you navigate through the website. Out of these, the cookies that are categorized as necessary are stored on your browser as they are essential for the working of basic functionalities of the website. We also use third-party cookies that help us analyze and understand how you use this website. These cookies will be stored in your browser only with your consent. You also have the option to opt-out of these cookies. But opting out of some of these cookies may affect your browsing experience.
Necessary cookies are absolutely essential for the website to function properly. This category only includes cookies that ensures basic functionalities and security features of the website. These cookies do not store any personal information.
Any cookies that may not be particularly necessary for the website to function and is used specifically to collect user personal data via analytics, ads, other embedded contents are termed as non-necessary cookies. It is mandatory to procure user consent prior to running these cookies on your website.
lmao, She banned me, I have never and don’t intend to beg to be unbanned. She just can’t help but keep on shooting herself in the foot. hahahahahaha That’s the most funniest thing I have read yet, the headline should read “The daftness of Miss Scruffy”
Lol Ben have to agree the only thing I have done is ask why I was IP banned then had my channel closed for merely having a difference of opinion with Scruffy but of course no reply has ever been received.
I was in GG’s sorry Scratches room and asked Mark straight out but his reply was I dont know of anyone being IP banned or having their channel closed, if it has been then my mother must of had just reason for doing so she doesnt just ban for disagreeing with her. YES MARK SHE DOES and you know it.
She is delusional if Mark was any sort of a man he would pull his mother into line but she is still breast feeding him it seems and he hasnt got the balls to stand up to her.
Vaughn is all but dead and tbh a lot of the staff and techs are getting the same if you say one word they dont like wham your gone from the channel.
I now can’t even be bothered to make up another name and log into vaughn oh and Mark I’m still waiting for you to reply to my FB message about why but I have a feeling hell may freeze over before that happens
Deluded, crazy, nasty, condescending, arrogant, old fucking ratbag is what she is.
Scruffy, please, please, please just fucking die soon and rest in piss.
im going to beg them for my channel back and see if they say i begged them to everyone on vaughn or fb lol
I called Scruffy a banning NAZI cunt and she ip banned me.
I emailed her saying it wasn’t me, She said yes it was and has my house addy to prove it was me.
Well thats weird/funny, I live about 20 miles from where my ip addy says I live…..LOL. What a STUPID asswipe liar she is.
So you insulted her, then lied about it to try to get out of a ban and SHE’s the one with a problem?
Pity during that conversation I had with her in trying to get it through her head that I had no part to play in what she was throwing at me, surely with me Being in the UK and hadn’t even bothered to ask me where I was from as anybody can read with that conversation I have published in various places, should have looked up the location of the IP which again, was not my IP she had banned but still, stuck to her story non the less in accusing me of streaming porn and in posting the links to porn site. How stupid is that? Surely with her classing herself as the director of Vaughnlive, she would have at least made some effort and apologising that she was and still is in the wrong.
The site’s rules says no disrespect of staff, meaning don’t say that the community manager’s personal illnesses are all on her head – that is very disrespectful. There is a difference between ‘difference of opinion’ and attacking someone, I guess not everyone is capable of understanding that. If she believes the earth is flat for example, and you don’t – that’s fine. But you’re not allowed to try to publicly shame someone for what you think their illnesses are. I do not understand in the least bit why any of you think this is out of line.
Youknowwho in no way was i disrespectful to scruffy on the contrary she was extremely rude to me. There was a discussion about whether VIP casters received preferential treatment over other casters and I am not talking access etc but in general. I stated that from what I could see there was clearly one set of rules for the VIP casters and another for those choosing not to take it up.
Scruffy said prove it so I gave her a recent example and i was met with the words well if you dont like it fuck off then and I was IP banned.
About 2 weeks later I tried to sign in under my name and my channel had been closed due to violation of TOS guidelines. I have asked for an explanation but received none (again very politely). I can fully understand people saying that scruffy is ruining the site and she is indeed using to settle personal grudges and it doesnt surprise me in the least that she is demanding people beg her to get their IP or channel back. She is a nasty woman full of her own self importance when in fact if it wasnt for the casters and guests vaughn would not exist and the rate she is alienating everyone it will soon disappear and Mark will only have himself because he does nothing to stop her running wild and his mother to blame for their demise.
I saw you being disrespectful to her as a guest in the screenshots in this blog post mr. anonymous – you might not think so but it was way out of line. Respect of staff means do not question their dealings with others also….
Man, you was actually doing pretty well with being anonymous the first couple of posts, but you really are giving yourself away AGAIN lol, js 😉
these are words on a screen, doesn’t matter what or who the source is or where they come from. It’s just logical debating. You can plainly see Guest 752 saying in the screenshots that they believe all of Miss Scruffy’s illnesses are in her head, and she has mental illness issues. That’s a blatant accusation and completely disrespectful, isn’t it? Or do you not agree?
Ryan you saw fuck all now get out of the vaughns asses. Respect of staff does not mean they can run riot and treat people like shit.
Tell me exactly what was being disrespectful or way out of line in the post you comment on being told to fuck off because of an observation doesnt warrant any respect of any sort kinda like i have for you absolutely none.
I saw come into a cast on Ivlog troll then run back to vaughn shouting I stuck up for you Mark can I suck your cock now.
Okay Katie – this “Guest_75232401754: Yes bc it’s a mental ILLNESS — you needed help you never got bc of PC”
For those of you who cannot read between the lines, what this guest has essentially said is that “miss scruffy, stop being so politically correct, you are mentally ill and all your health problems are in your head”
Now that is VERY disrespectful, and that’s why the person was warned to get a new IP – it means an IP ban is imminent and coming at any moment for what that guest just said.
Ryan,you really are a sad prick.
I’m starting to think you will be by Scruffy’s bedside, holding her hand when she passes away.
This is absolutely insane – you cannot logically debate. Anything turns into personal attacks against the one who has an opposite point of view.
This isn’t about me, or you, this is a logical debate about whether or not Miss Scruffy is out of line, and she isn’t. Where on earth do any of you get the idea that it’s perfectly alright to voice an opinion that puts any of the site’s staff in a negative light? You can do it here on your blogs, but if you do it on vaughnlive you’ll get dealt with. And then suddenly in your eyes the problem is with them, when you have been the one who behaved badly. This is akin to a 5 year old flipping out because daddy won’t buy the sugary cereal the child wants when visiting the supermarket – then you go and tell your daddy to fuck off when he says no. Positions of AUTHORITY mean that authority should be respected, not mocked. If this 100% logical argument flies above your heads there is nothing more to say.
hi ryan
lol, he just can’t change his style at all can he?
Ryans after a Free VIP GOLD. Kissy Kissy Miss Scruffy and Mark.
sorry, your juvenile taunting and bullying tactics (trying to shame me into changing my opinion because you cannot understand why someone would see something another way) won’t work on me.
Ryan I was not in anyway disrespectful to Miss Scruffy I had a different opinion on a subject that they wanted open debate on but because I did not share the same view as Miss Scruffy she was the one who became abusive and childish. If she didnt want to hear other people’s opinion why the hell ask for it in the first place. Just because you are the site owners mother does not give her the right to bully other people. Yes Ryan bully a word you love to bandy around. With her current attitude she should not be in any position of authority as she is using VaughnLive to hold and settle petty grudges with people.
I feel sorry for you Ryan because you need to take off you rose coloured glasses and see what is really happening on VL.
I understand that you cannot see further than you undying devotion to the Vaughns but I doubt they appreciate it and would kick you out as soon as see your name appear on screen if they had a mind to and it would probably be for no reason at all other than Miss Scruffy felt like it.
Ryan you belong in a mental institution.
see, you’re typing to me in an unfriendly and insulting manner. Don’t you see if this was VL and i was Miss Scruffy, suggesting I or someone else belong in an institution is grounds for a ban…
It’s not ‘telling it like it is’ or ‘exercising your right to free speech’
I didnt type that Ryan now please answer my question about Scruffys rude and arrogant behaviour and her decision to ban someone because she doesnt like the answer to a question she has asked.
You totally ignore that because it would mean that Miss Scruffy was wrong and I dont feel you could possibly type anything that was against the Vaughns.
We’re not on VL, I’ll say whatever I want to you, fat fuck. Grow a pair of balls and man the fuck up.
How about you get your head out of your ass hole Ryan and start reading stuff of what Miss Scruffy is sending out. This is the reason why people are so pissed off about, stop listening to bullshit son and listen to the other side of the story before jumping into sticking up for the likes of Scruffy.
Yes, Scruffy is actually a cunt I have you know, I never stepped out of line myself against her or as she has claimed, broken any TOS on Vaughn.
Yes, you did Ben – you just were too damn drunk to remember. I have seen you on their site many times being abusive to staff and making fun of them. As for ‘Anonymous’ – I have explained that Miss Scruffy was justified in banning the IP of Guest752XXX.