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.
'#text' === $token_name
)
) ||
(
'math' === $adjusted_current_node->namespace &&
'ANNOTATION-XML' === $adjusted_current_node->node_name &&
$is_start_tag && 'SVG' === $token_name
) ||
(
'html' === $adjusted_current_node->integration_node_type &&
( $is_start_tag || '#text' === $token_name )
)
);
try {
if ( ! $parse_in_current_insertion_mode ) {
return $this->step_in_foreign_content();
}
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}'." );
}
} catch ( WP_HTML_Unsupported_Exception $e ) {
/*
* Exceptions are used in this class to escape deep call stacks that
* otherwise might involve messier calling and return conventions.
*/
return false;
}
}
/**
* Computes the HTML breadcrumbs for the currently-matched node, if matched.
*
* Breadcrumbs start at the outermost parent and descend toward the matched element.
* They always include the entire path from the root HTML node to the matched element.
*
* @todo It could be more efficient to expose a generator-based version of this function
* to avoid creating the array copy on tag iteration. If this is done, it would likely
* be more useful to walk up the stack when yielding instead of starting at the top.
*
* Example
*
* $processor = WP_HTML_Processor::create_fragment( '<p><strong><em><img></em></strong></p>' );
* $processor->next_tag( 'IMG' );
* $processor->get_breadcrumbs() === array( 'HTML', 'BODY', 'P', 'STRONG', 'EM', 'IMG' );
*
* @since 6.4.0
*
* @return string[]|null Array of tag names representing path to matched node, if matched, otherwise NULL.
*/
public function get_breadcrumbs(): ?array {
return $this->breadcrumbs;
}
/**
* Returns the nesting depth of the current location in the document.
*
* Example:
*
* $processor = WP_HTML_Processor::create_fragment( '<div><p></p></div>' );
* // The processor starts in the BODY context, meaning it has depth from the start: HTML > BODY.
* 2 === $processor->get_current_depth();
*
* // Opening the DIV element increases the depth.
* $processor->next_token();
* 3 === $processor->get_current_depth();
*
* // Opening the P element increases the depth.
* $processor->next_token();
* 4 === $processor->get_current_depth();
*
* // The P element is closed during `next_token()` so the depth is decreased to reflect that.
* $processor->next_token();
* 3 === $processor->get_current_depth();
*
* @since 6.6.0
*
* @return int Nesting-depth of current location in the document.
*/
public function get_current_depth(): int {
return count( $this->breadcrumbs );
}
/**
* Normalizes an HTML fragment by serializing it.
*
* This method assumes that the given HTML snippet is found in BODY context.
* For normalizing full documents or fragments found in other contexts, create
* a new processor using WP_HTML_Processor::create_fragment or
* WP_HTML_Processor::create_full_parser and call WP_HTML_Processor::serialize
* on the created instances.
*
* Many aspects of an input HTML fragment may be changed during normalization.
*
* - Attribute values will be double-quoted.
* - Duplicate attributes will be removed.
* - Omitted tags will be added.
* - Tag and attribute name casing will be lower-cased,
* except for specific SVG and MathML tags or attributes.
* - Text will be re-encoded, null bytes handled,
* and invalid UTF-8 replaced with U+FFFD.
* - Any incomplete syntax trailing at the end will be omitted,
* for example, an unclosed comment opener will be removed.
*
* Example:
*
* echo WP_HTML_Processor::normalize( '<a href=#anchor v=5 href="/" enabled>One</a another v=5><!--' );
* // <a href="#anchor" v="5" enabled>One</a>
*
* echo WP_HTML_Processor::normalize( '<div></p>fun<table><td>cell</div>' );
* // <div><p></p>fun<table><tbody><tr><td>cell</td></tr></tbody></table></div>
*
* echo WP_HTML_Processor::normalize( '<![CDATA[invalid comment]]> syntax < <> "oddities"' );
* // <!--[CDATA[invalid comment]]--> syntax < <> "oddities"
*
* @since 6.7.0
*
* @param string $html Input HTML to normalize.
*
* @return string|null Normalized output, or `null` if unable to normalize.
*/
public static function normalize( string $html ): ?string {
return static::create_fragment( $html )->serialize();
}
/**
* Returns normalized HTML for a fragment by serializing it.
*
* This differs from WP_HTML_Processor::normalize in that it starts with
* a specific HTML Processor, which _must_ not have already started scanning;
* it must be in the initial ready state and will be in the completed state once
* serialization is complete.
*
* Many aspects of an input HTML fragment may be changed during normalization.
*
* - Attribute values will be double-quoted.
* - Duplicate attributes will be removed.
* - Omitted tags will be added.
* - Tag and attribute name casing will be lower-cased,
* except for specific SVG and MathML tags or attributes.
* - Text will be re-encoded, null bytes handled,
* and invalid UTF-8 replaced with U+FFFD.
* - Any incomplete syntax trailing at the end will be omitted,
* for example, an unclosed comment opener will be removed.
*
* Example:
*
* $processor = WP_HTML_Processor::create_fragment( '<a href=#anchor v=5 href="/" enabled>One</a another v=5><!--' );
* echo $processor->serialize();
* // <a href="#anchor" v="5" enabled>One</a>
*
* $processor = WP_HTML_Processor::create_fragment( '<div></p>fun<table><td>cell</div>' );
* echo $processor->serialize();
* // <div><p></p>fun<table><tbody><tr><td>cell</td></tr></tbody></table></div>
*
* $processor = WP_HTML_Processor::create_fragment( '<![CDATA[invalid comment]]> syntax < <> "oddities"' );
* echo $processor->serialize();
* // <!--[CDATA[invalid comment]]--> syntax < <> "oddities"
*
* @since 6.7.0
*
* @return string|null Normalized HTML markup represented by processor,
* or `null` if unable to generate serialization.
*/
public function serialize(): ?string {
if ( WP_HTML_Tag_Processor::STATE_READY !== $this->parser_state ) {
wp_trigger_error(
__METHOD__,
'An HTML Processor which has already started processing cannot serialize its contents. Serialize immediately after creating the instance.',
E_USER_WARNING
);
return null;
}
$html = '';
while ( $this->next_token() ) {
$html .= $this->serialize_token();
}
if ( null !== $this->get_last_error() ) {
wp_trigger_error(
__METHOD__,
"Cannot serialize HTML Processor with parsing error: {$this->get_last_error()}.",
E_USER_WARNING
);
return null;
}
return $html;
}
/**
* Serializes the currently-matched token.
*
* This method produces a fully-normative HTML string for the currently-matched token,
* if able. If not matched at any token or if the token doesn't correspond to any HTML
* it will return an empty string (for example, presumptuous end tags are ignored).
*
* @see static::serialize()
*
* @since 6.7.0
*
* @return string Serialization of token, or empty string if no serialization exists.
*/
protected function serialize_token(): string {
$html = '';
$token_type = $this->get_token_type();
switch ( $token_type ) {
case '#text':
$html .= htmlspecialchars( $this->get_modifiable_text(), ENT_QUOTES | ENT_SUBSTITUTE | ENT_HTML5, 'UTF-8' );
break;
// Unlike the `<>` which is interpreted as plaintext, this is ignored entirely.
case '#presumptuous-tag':
break;
case '#funky-comment':
case '#comment':
$html .= "<!--{$this->get_full_comment_text()}-->";
break;
case '#cdata-section':
$html .= "<![CDATA[{$this->get_modifiable_text()}]]>";
break;
case 'html':
$html .= '<!DOCTYPE html>';
break;
}
if ( '#tag' !== $token_type ) {
return $html;
}
$tag_name = str_replace( "\x00", "\u{FFFD}", $this->get_tag() );
$in_html = 'html' === $this->get_namespace();
$qualified_name = $in_html ? strtolower( $tag_name ) : $this->get_qualified_tag_name();
if ( $this->is_tag_closer() ) {
$html .= "</{$qualified_name}>";
return $html;
}
$attribute_names = $this->get_attribute_names_with_prefix( '' );
if ( ! isset( $attribute_names ) ) {
$html .= "<{$qualified_name}>";
return $html;
}
$html .= "<{$qualified_name}";
foreach ( $attribute_names as $attribute_name ) {
$html .= " {$this->get_qualified_attribute_name( $attribute_name )}";
$value = $this->get_attribute( $attribute_name );
if ( is_string( $value ) ) {
$html .= '="' . htmlspecialchars( $value, ENT_QUOTES | ENT_SUBSTITUTE | ENT_HTML5 ) . '"';
}
$html = str_replace( "\x00", "\u{FFFD}", $html );
}
if ( ! $in_html && $this->has_self_closing_flag() ) {
$html .= ' /';
}
$html .= '>';
// Flush out self-contained elements.
if ( $in_html && in_array( $tag_name, array( 'IFRAME', 'NOEMBED', 'NOFRAMES', 'SCRIPT', 'STYLE', 'TEXTAREA', 'TITLE', 'XMP' ), true ) ) {
$text = $this->get_modifiable_text();
switch ( $tag_name ) {
case 'IFRAME':
case 'NOEMBED':
case 'NOFRAMES':
$text = '';
break;
case 'SCRIPT':
case 'STYLE':
break;
default:
$text = htmlspecialchars( $text, ENT_QUOTES | ENT_SUBSTITUTE | ENT_HTML5, 'UTF-8' );
}
$html .= "{$text}</{$qualified_name}>";
}
return $html;
}
/**
* Parses next element in the 'initial' insertion mode.
*
* This internal function performs the 'initial' 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/#the-initial-insertion-mode
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_initial(): 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
*
* Parse error: ignore the token.
*/
case '#text':
if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
return $this->step();
}
goto initial_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':
$doctype = $this->get_doctype_info();
if ( null !== $doctype && 'quirks' === $doctype->indicated_compatability_mode ) {
$this->compat_mode = WP_HTML_Tag_Processor::QUIRKS_MODE;
}
/*
* > Then, switch the insertion mode to "before html".
*/
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_BEFORE_HTML;
$this->insert_html_element( $this->state->current_token );
return true;
}
/*
* > Anything else
*/
initial_anything_else:
$this->compat_mode = WP_HTML_Tag_Processor::QUIRKS_MODE;
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_BEFORE_HTML;
return $this->step( self::REPROCESS_CURRENT_NODE );
}
/**
* Parses next element in the 'before html' insertion mode.
*
* This internal function performs the 'before html' 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/#the-before-html-insertion-mode
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_before_html(): 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 DOCTYPE token
*/
case 'html':
// Parse error: ignore the token.
return $this->step();
/*
* > A comment token
*/
case '#comment':
case '#funky-comment':
case '#presumptuous-tag':
$this->insert_html_element( $this->state->current_token );
return true;
/*
* > 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();
}
goto before_html_anything_else;
break;
/*
* > A start tag whose tag name is "html"
*/
case '+HTML':
$this->insert_html_element( $this->state->current_token );
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_BEFORE_HEAD;
return true;
/*
* > An end tag whose tag name is one of: "head", "body", "html", "br"
*
* Closing BR tags are always reported by the Tag Processor as opening tags.
*/
case '-HEAD':
case '-BODY':
case '-HTML':
/*
* > Act as described in the "anything else" entry below.
*/
goto before_html_anything_else;
break;
}
/*
* > Any other end tag
*/
if ( $is_closer ) {
// Parse error: ignore the token.
return $this->step();
}
/*
* > Anything else.
*
* > Create an html element whose node document is the Document object.
* > Append it to the Document object. Put this element in the stack of open elements.
* > Switch the insertion mode to "before head", then reprocess the token.
*/
before_html_anything_else:
$this->insert_virtual_node( 'HTML' );
$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_BEFORE_HEAD;
return $this->step( self::REPROCESS_CURRENT_NODE );
}
/**
* Parses next element in the 'before head' insertion mode.
*
* This internal function performs the 'before 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-before-head-insertion-mode
* @see WP_HTML_Processor::step
*
* @return bool Whether an element was found.
*/
private function step_before_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
*
* Parse error: ignore the token.
*/
case '#text':
if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
return $this->step();
}
goto before_head_anything_else;
break;
/*
| Version | Description |
|---|---|
| 6.4.0 | Introduced. |
© 2003–2024 WordPress Foundation
Licensed under the GNU GPLv2+ License.
https://developer.wordpress.org/reference/classes/wp_html_processor/step_in_body