Converts class name updates into tag attributes updates (they are accumulated in different data formats for performance).
Description
See also
- WP_HTML_Tag_Processor::$lexical_updates
- WP_HTML_Tag_Processor::$classname_updates
Source
$attribute_end = $end_quote_at + 1;
$this->bytes_already_parsed = $attribute_end;
break;
default:
$value_start = $this->bytes_already_parsed;
$value_length = strcspn( $this->html, "> \t\f\r\n", $value_start );
$attribute_end = $value_start + $value_length;
$this->bytes_already_parsed = $attribute_end;
}
} else {
$value_start = $this->bytes_already_parsed;
$value_length = 0;
$attribute_end = $attribute_start + $name_length;
}
if ( $attribute_end >= $doc_length ) {
$this->parser_state = self::STATE_INCOMPLETE_INPUT;
return false;
}
if ( $this->is_closing_tag ) {
return true;
}
/*
* > 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
*
* @see https://html.spec.whatwg.org/multipage/syntax.html#attributes-2:ascii-case-insensitive
*/
$comparable_name = strtolower( $attribute_name );
// If an attribute is listed many times, only use the first declaration and ignore the rest.
if ( ! isset( $this->attributes[ $comparable_name ] ) ) {
$this->attributes[ $comparable_name ] = new WP_HTML_Attribute_Token(
$attribute_name,
$value_start,
$value_length,
$attribute_start,
$attribute_end - $attribute_start,
! $has_value
);
return true;
}
/*
* Track the duplicate attributes so if we remove it, all disappear together.
*
* While `$this->duplicated_attributes` could always be stored as an `array()`,
* which would simplify the logic here, storing a `null` and only allocating
* an array when encountering duplicates avoids needless allocations in the
* normative case of parsing tags with no duplicate attributes.
*/
$duplicate_span = new WP_HTML_Span( $attribute_start, $attribute_end - $attribute_start );
if ( null === $this->duplicate_attributes ) {
$this->duplicate_attributes = array( $comparable_name => array( $duplicate_span ) );
} elseif ( ! isset( $this->duplicate_attributes[ $comparable_name ] ) ) {
$this->duplicate_attributes[ $comparable_name ] = array( $duplicate_span );
} else {
$this->duplicate_attributes[ $comparable_name ][] = $duplicate_span;
}
return true;
}
/**
* Move the internal cursor past any immediate successive whitespace.
*
* @since 6.2.0
*/
private function skip_whitespace(): void {
$this->bytes_already_parsed += strspn( $this->html, " \t\f\r\n", $this->bytes_already_parsed );
}
/**
* Applies attribute updates and cleans up once a tag is fully parsed.
*
* @since 6.2.0
*/
private function after_tag(): void {
/*
* There could be lexical updates enqueued for an attribute that
* also exists on the next tag. In order to avoid conflating the
* attributes across the two tags, lexical updates with names
* need to be flushed to raw lexical updates.
*/
$this->class_name_updates_to_attributes_updates();
/*
* Purge updates if there are too many. The actual count isn't
* scientific, but a few values from 100 to a few thousand were
* tests to find a practically-useful limit.
*
* If the update queue grows too big, then the Tag Processor
* will spend more time iterating through them and lose the
* efficiency gains of deferring applying them.
*/
if ( 1000 < count( $this->lexical_updates ) ) {
$this->get_updated_html();
}
foreach ( $this->lexical_updates as $name => $update ) {
/*
* Any updates appearing after the cursor should be applied
* before proceeding, otherwise they may be overlooked.
*/
if ( $update->start >= $this->bytes_already_parsed ) {
$this->get_updated_html();
break;
}
if ( is_int( $name ) ) {
continue;
}
$this->lexical_updates[] = $update;
unset( $this->lexical_updates[ $name ] );
}
$this->token_starts_at = null;
$this->token_length = null;
$this->tag_name_starts_at = null;
$this->tag_name_length = null;
$this->text_starts_at = 0;
$this->text_length = 0;
$this->is_closing_tag = null;
$this->attributes = array();
Changelog
Version | Description |
---|---|
6.2.0 | Introduced. |
User Contributed Notes
You must log in before being able to contribute a note or feedback.