Internal method which finds the next token in the HTML document.
This method is a protected internal function which implements the logic for finding the next token in a document. It exists so that the parser can update its state without affecting the location of the cursor in the document and without triggering subclass methods for things like next_token(), e.g. when applying patches before searching for the next token.
private function base_class_next_token(): bool {
$was_at = $this->bytes_already_parsed;
$this->after_tag();
// Don't proceed if there's nothing more to scan.
if (
self::STATE_COMPLETE === $this->parser_state ||
self::STATE_INCOMPLETE_INPUT === $this->parser_state
) {
return false;
}
/*
* The next step in the parsing loop determines the parsing state;
* clear it so that state doesn't linger from the previous step.
*/
$this->parser_state = self::STATE_READY;
if ( $this->bytes_already_parsed >= strlen( $this->html ) ) {
$this->parser_state = self::STATE_COMPLETE;
return false;
}
// Find the next tag if it exists.
if ( false === $this->parse_next_tag() ) {
if ( self::STATE_INCOMPLETE_INPUT === $this->parser_state ) {
$this->bytes_already_parsed = $was_at;
}
return false;
}
/*
* For legacy reasons the rest of this function handles tags and their
* attributes. If the processor has reached the end of the document
* or if it matched any other token then it should return here to avoid
* attempting to process tag-specific syntax.
*/
if (
self::STATE_INCOMPLETE_INPUT !== $this->parser_state &&
self::STATE_COMPLETE !== $this->parser_state &&
self::STATE_MATCHED_TAG !== $this->parser_state
) {
return true;
}
// Parse all of its attributes.
while ( $this->parse_next_attribute() ) {
continue;
}
// Ensure that the tag closes before the end of the document.
if (
self::STATE_INCOMPLETE_INPUT === $this->parser_state ||
$this->bytes_already_parsed >= strlen( $this->html )
) {
// Does this appropriately clear state (parsed attributes)?
$this->parser_state = self::STATE_INCOMPLETE_INPUT;
$this->bytes_already_parsed = $was_at;
return false;
}
$tag_ends_at = strpos( $this->html, '>', $this->bytes_already_parsed );
if ( false === $tag_ends_at ) {
$this->parser_state = self::STATE_INCOMPLETE_INPUT;
$this->bytes_already_parsed = $was_at;
return false;
}
$this->parser_state = self::STATE_MATCHED_TAG;
$this->bytes_already_parsed = $tag_ends_at + 1;
$this->token_length = $this->bytes_already_parsed - $this->token_starts_at;
/*
* Certain tags require additional processing. The first-letter pre-check
* avoids unnecessary string allocation when comparing the tag names.
*
* - IFRAME
* - LISTING (deprecated)
* - NOEMBED (deprecated)
* - NOFRAMES (deprecated)
* - PRE
* - SCRIPT
* - STYLE
* - TEXTAREA
* - TITLE
* - XMP (deprecated)
*/
if (
$this->is_closing_tag ||
'html' !== $this->parsing_namespace ||
1 !== strspn( $this->html, 'iIlLnNpPsStTxX', $this->tag_name_starts_at, 1 )
) {
return true;
}
$tag_name = $this->get_tag();
/*
* For LISTING, PRE, and TEXTAREA, the first linefeed of an immediately-following
* text node is ignored as an authoring convenience.
*
* @see static::skip_newline_at
*/
if ( 'LISTING' === $tag_name || 'PRE' === $tag_name ) {
$this->skip_newline_at = $this->bytes_already_parsed;
return true;
}
/*
* There are certain elements whose children are not DATA but are instead
* RCDATA or RAWTEXT. These cannot contain other elements, and the contents
* are parsed as plaintext, with character references decoded in RCDATA but
* not in RAWTEXT.
*
* These elements are described here as "self-contained" or special atomic
* elements whose end tag is consumed with the opening tag, and they will
* contain modifiable text inside of them.
*
* Preserve the opening tag pointers, as these will be overwritten
* when finding the closing tag. They will be reset after finding
* the closing to tag to point to the opening of the special atomic
* tag sequence.
*/
$tag_name_starts_at = $this->tag_name_starts_at;
$tag_name_length = $this->tag_name_length;
$tag_ends_at = $this->token_starts_at + $this->token_length;
$attributes = $this->attributes;
$duplicate_attributes = $this->duplicate_attributes;
// Find the closing tag if necessary.
switch ( $tag_name ) {
case 'SCRIPT':
$found_closer = $this->skip_script_data();
break;
case 'TEXTAREA':
case 'TITLE':
$found_closer = $this->skip_rcdata( $tag_name );
break;
/*
* In the browser this list would include the NOSCRIPT element,
* but the Tag Processor is an environment with the scripting
* flag disabled, meaning that it needs to descend into the
* NOSCRIPT element to be able to properly process what will be
* sent to a browser.
*
* Note that this rule makes HTML5 syntax incompatible with XML,
* because the parsing of this token depends on client application.
* The NOSCRIPT element cannot be represented in the XHTML syntax.
*/
case 'IFRAME':
case 'NOEMBED':
case 'NOFRAMES':
case 'STYLE':
case 'XMP':
$found_closer = $this->skip_rawtext( $tag_name );
break;
// No other tags should be treated in their entirety here.
default:
return true;
}
if ( ! $found_closer ) {
$this->parser_state = self::STATE_INCOMPLETE_INPUT;
$this->bytes_already_parsed = $was_at;
return false;
}
/*
* The values here look like they reference the opening tag but they reference
* the closing tag instead. This is why the opening tag values were stored
* above in a variable. It reads confusingly here, but that's because the
* functions that skip the contents have moved all the internal cursors past
* the inner content of the tag.
*/
$this->token_starts_at = $was_at;
$this->token_length = $this->bytes_already_parsed - $this->token_starts_at;
$this->text_starts_at = $tag_ends_at;
$this->text_length = $this->tag_name_starts_at - $this->text_starts_at;
$this->tag_name_starts_at = $tag_name_starts_at;
$this->tag_name_length = $tag_name_length;
$this->attributes = $attributes;
$this->duplicate_attributes = $duplicate_attributes;
return true;
}
