ue of attribute or `null` if not available. Boolean attributes return `true`.
*/
public function get_attribute( $name ) {
if ( null === $this->tag_name_starts_at ) {
return null;
}
$comparable = strtolower( $name );
/*
* For every attribute other than `class` it's possible to perform a quick check if
* there's an enqueued lexical update whose value takes priority over what's found in
* the input document.
*
* The `class` attribute is special though because of the exposed helpers `add_class`
* and `remove_class`. These form a builder for the `class` attribute, so an additional
* check for enqueued class changes is required in addition to the check for any enqueued
* attribute values. If any exist, those enqueued class changes must first be flushed out
* into an attribute value update.
*/
if ( 'class' === $name ) {
$this->class_name_updates_to_attributes_updates();
}
// Return any enqueued attribute value updates if they exist.
$enqueued_value = $this->get_enqueued_attribute_value( $comparable );
if ( false !== $enqueued_value ) {
return $enqueued_value;
}
if ( ! isset( $this->attributes[ $comparable ] ) ) {
return null;
}
$attribute = $this->attributes[ $comparable ];
/*
* This flag distinguishes an attribute with no value
* from an attribute with an empty string value. For
* unquoted attributes this could look very similar.
* It refers to whether an `=` follows the name.
*
* e.g.
* ¹ ²
* 1. Attribute `boolean-attribute` is `true`.
* 2. Attribute `empty-attribute` is `""`.
*/
if ( true === $attribute->is_true ) {
return true;
}
$raw_value = substr( $this->html, $attribute->value_starts_at, $attribute->value_length );
return html_entity_decode( $raw_value );
}
/**
* 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 6.2.0
*
* @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.
*/
function get_attribute_names_with_prefix( $prefix ) {
if ( $this->is_closing_tag || null === $this->tag_name_starts_at ) {
return null;
}
$comparable = strtolower( $prefix );
$matches = array();
foreach ( array_keys( $this->attributes ) as $attr_name ) {
if ( str_starts_with( $attr_name, $comparable ) ) {
$matches[] = $attr_name;
}
}
return $matches;
}
/**
* Returns the uppercase name of the matched tag.
*
* Example:
*
* $p = new WP_HTML_Tag_Processor( 'Test
' );
* $p->next_tag() === true;
* $p->get_tag() === 'DIV';
*
* $p->next_tag() === false;
* $p->get_tag() === null;
*
* @since 6.2.0
*
* @return string|null Name of currently matched tag in input HTML, or `null` if none found.
*/
public function get_tag() {
if ( null === $this->tag_name_starts_at ) {
return null;
}
$tag_name = substr( $this->html, $this->tag_name_starts_at, $this->tag_name_length );
return strtoupper( $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 6.3.0
*
* @return bool Whether the currently matched tag contains the self-closing flag.
*/
public function has_self_closing_flag() {
if ( ! $this->tag_name_starts_at ) {
return false;
}
return '/' === $this->html[ $this->tag_ends_at - 1 ];
}
/**
* Indicates if the current tag token is a tag closer.
*
* Example:
*
* $p = new WP_HTML_Tag_Processor( '' );
* $p->next_tag( array( 'tag_name' => 'div', 'tag_closers' => 'visit' ) );
* $p->is_tag_closer() === false;
*
* $p->next_tag( array( 'tag_name' => 'div', 'tag_closers' => 'visit' ) );
* $p->is_tag_closer() === true;
*
* @since 6.2.0
*
* @return bool Whether the current tag is a tag closer.
*/
public function is_tag_closer() {
return $this->is_closing_tag;
}
/**
* 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 6.2.0
* @since 6.2.1 Fix: Only create a single update for multiple calls with case-variant attribute names.
*
* @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 ) {
if ( $this->is_closing_tag || null === $this->tag_name_starts_at ) {
return false;
}
/*
* WordPress rejects more characters than are strictly forbidden
* in HTML5. This is to prevent additional security risks deeper
* in the WordPress and plugin stack. Specifically the
* less-than (<) greater-than (>) and ampersand (&) aren't allowed.
*
* The use of a PCRE match enables looking for specific Unicode
* code points without writing a UTF-8 decoder. Whereas scanning
* for one-byte characters is trivial (with `strcspn`), scanning
* for the longer byte sequences would be more complicated. Given
* that this shouldn't be in the hot path for execution, it's a
* reasonable compromise in efficiency without introducing a
* noticeable impact on the overall system.
*
* @see https://html.spec.whatwg.org/#attributes-2
*
* @TODO as the only regex pattern maybe we should take it out? are
* Unicode patterns available broadly in Core?
*/
if ( preg_match(
'~[' .
// Syntax-like characters.
'"\'>& =' .
// Control characters.
'\x{00}-\x{1F}' .
// HTML noncharacters.
'\x{FDD0}-\x{FDEF}' .
'\x{FFFE}\x{FFFF}\x{1FFFE}\x{1FFFF}\x{2FFFE}\x{2FFFF}\x{3FFFE}\x{3FFFF}' .
'\x{4FFFE}\x{4FFFF}\x{5FFFE}\x{5FFFF}\x{6FFFE}\x{6FFFF}\x{7FFFE}\x{7FFFF}' .
'\x{8FFFE}\x{8FFFF}\x{9FFFE}\x{9FFFF}\x{AFFFE}\x{AFFFF}\x{BFFFE}\x{BFFFF}' .
'\x{CFFFE}\x{CFFFF}\x{DFFFE}\x{DFFFF}\x{EFFFE}\x{EFFFF}\x{FFFFE}\x{FFFFF}' .
'\x{10FFFE}\x{10FFFF}' .
']~Ssu',
$name
) ) {
_doing_it_wrong(
__METHOD__,
__( 'Invalid attribute name.' ),
'6.2.0'
);
return false;
}
/*
* > The values "true" and "false" are not allowed on boolean attributes.
* > To represent a false value, the attribute has to be omitted altogether.
* - HTML5 spec, https://html.spec.whatwg.org/#boolean-attributes
*/
if ( false === $value ) {
return $this->remove_attribute( $name );
}
if ( true === $value ) {
$updated_attribute = $name;
} else {
$escaped_new_value = esc_attr( $value );
$updated_attribute = "{$name}=\"{$escaped_new_value}\"";
}
/*
* > 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( $name );
if ( isset( $this->attributes[ $comparable_name ] ) ) {
/*
* Update an existing attribute.
*
* Example – set attribute id to "new" in :
*
*
* ^-------------^
* start end
* replacement: `id="new"`
*
* Result:
*/
$existing_attribute = $this->attributes[ $comparable_name ];
$this->lexical_updates[ $comparable_name ] = new WP_HTML_Text_Replacement(
$existing_attribute->start,
$existing_attribute->end,
$updated_attribute
);
} else {
/*
* Create a new attribute at the tag's name end.
*
* Example – add attribute id="new" to :
*
*
* ^
* start and end
* replacement: ` id="new"`
*
* Result:
*/
$this->lexical_updates[ $comparable_name ] = new WP_HTML_Text_Replacement(
$this->tag_name_starts_at + $this->tag_name_length,
$this->tag_name_starts_at + $this->tag_name_length,
' ' . $updated_attribute
);
}
/*
* Any calls to update the `class` attribute directly should wipe out any
* enqueued class changes from `add_class` and `remove_class`.
*/
if ( 'class' === $comparable_name && ! empty( $this->classname_updates ) ) {
$this->classname_updates = array();
}
return true;
}
/**
* Remove an attribute from the currently-matched tag.
*
* @since 6.2.0
*
* @param string $name The attribute name to remove.
* @return bool Whether an attribute was removed.
*/
public function remove_attribute( $name ) {
if ( $this->is_closing_tag ) {
return false;
}
/*
* > 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
*/
$name = strtolower( $name );
/*
* Any calls to update the `class` attribute directly should wipe out any
* enqueued class changes from `add_class` and `remove_class`.
*/
if ( 'class' === $name && count( $this->classname_updates ) !== 0 ) {
$this->classname_updates = array();
}
/*
* If updating an attribute that didn't exist in the input
* document, then remove the enqueued update and move on.
*
* For example, this might occur when calling `remove_attribute()`
* after calling `set_attribute()` for the same attribute
* and when that attribute wasn't originally present.
*/
if ( ! isset( $this->attributes[ $name ] ) ) {
if ( isset( $this->lexical_updates[ $name ] ) ) {
unset( $this->lexical_updates[ $name ] );
}
return false;
}
/*
* Removes an existing tag attribute.
*
* Example – remove the attribute id from :
*
* ^-------------^
* start end
* replacement: ``
*
* Result:
*/
$this->lexical_updates[ $name ] = new WP_HTML_Text_Replacement(
$this->attributes[ $name ]->start,
$this->attributes[ $name ]->end,
''
);
// Removes any duplicated attributes if they were also present.
if ( null !== $this->duplicate_attributes && array_key_exists( $name, $this->duplicate_attributes ) ) {
foreach ( $this->duplicate_attributes[ $name ] as $attribute_token ) {
$this->lexical_updates[] = new WP_HTML_Text_Replacement(
$attribute_token->start,
$attribute_token->end,
''
);
}
}
return true;
}
/**
* Adds a new class name to the currently matched tag.
*
* @since 6.2.0
*
* @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 ) {
if ( $this->is_closing_tag ) {
return false;
}
if ( null !== $this->tag_name_starts_at ) {
$this->classname_updates[ $class_name ] = self::ADD_CLASS;
}
return true;
}
/**
* Removes a class name from the currently matched tag.
*
* @since 6.2.0
*
* @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 ) {
if ( $this->is_closing_tag ) {
return false;
}
if ( null !== $this->tag_name_starts_at ) {
$this->classname_updates[ $class_name ] = self::REMOVE_CLASS;
}
return true;
}
/**
* Returns the string representation of the HTML Tag Processor.
*
* @since 6.2.0
*
* @see WP_HTML_Tag_Processor::get_updated_html()
*
* @return string The processed HTML.
*/
public function __toString() {
return $this->get_updated_html();
}
/**
* Returns the string representation of the HTML Tag Processor.
*
* @since 6.2.0
* @since 6.2.1 Shifts the internal cursor corresponding to the applied updates.
*
* @return string The processed HTML.
*/
public function get_updated_html() {
$requires_no_updating = 0 === count( $this->classname_updates ) && 0 === count( $this->lexical_updates );
/*
* When there is nothing more to update and nothing has already been
* updated, return the original document and avoid a string copy.
*/
if ( $requires_no_updating ) {
return $this->html;
}
/*
* Keep track of the position right before the current tag. This will
* be necessary for reparsing the current tag after updating the HTML.
*/
$before_current_tag = $this->tag_name_starts_at - 1;
/*
* 1. Apply the enqueued edits and update all the pointers to reflect those changes.
*/
$this->class_name_updates_to_attributes_updates();
$before_current_tag += $this->apply_attributes_updates( $before_current_tag );
/*
* 2. Rewind to before the current tag and reparse to get updated attributes.
*
* At this point the internal cursor points to the end of the tag name.
* Rewind before the tag name starts so that it's as if the cursor didn't
* move; a call to `next_tag()` will reparse the recently-updated attributes
* and additional calls to modify the attributes will apply at this same
* location.
*
* Previous HTMLMore HTML
* ^ | back up by the length of the tag name plus the opening <
* \<-/ back up by strlen("em") + 1 ==> 3
*/
// Store existing state so it can be restored after reparsing.
$previous_parsed_byte_count = $this->bytes_already_parsed;
$previous_query = $this->last_query;
// Reparse attributes.
$this->bytes_already_parsed = $before_current_tag;
$this->next_tag();
// Restore previous state.
$this->bytes_already_parsed = $previous_parsed_byte_count;
$this->parse_query( $previous_query );
return $this->html;
}
/**
* Parses tag query input into internal search criteria.
*
* @since 6.2.0
*
* @param array|string|null $query {
* Optional. Which tag name to find, having which class, etc. Default is to find any tag.
*
* @type string|null $tag_name Which tag to find, or `null` for "any tag."
* @type int|null $match_offset Find the Nth tag matching all search criteria.
* 1 for "first" tag, 3 for "third," etc.
* Defaults to first tag.
* @type string|null $class_name Tag must contain this class name to match.
* @type string $tag_closers "visit" or "skip": whether to stop on tag closers, e.g. .
* }
*/
private function parse_query( $query ) {
if ( null !== $query && $query === $this->last_query ) {
return;
}
$this->last_query = $query;
$this->sought_tag_name = null;
$this->sought_class_name = null;
$this->sought_match_offset = 1;
$this->stop_on_tag_closers = false;
// A single string value means "find the tag of this name".
if ( is_string( $query ) ) {
$this->sought_tag_name = $query;
return;
}
// An empty query parameter applies no restrictions on the search.
if ( null === $query ) {
return;
}
// If not using the string interface, an associative array is required.
if ( ! is_array( $query ) ) {
_doing_it_wrong(
__METHOD__,
__( 'The query argument must be an array or a tag name.' ),
'6.2.0'
);
return;
}
if ( isset( $query['tag_name'] ) && is_string( $query['tag_name'] ) ) {
$this->sought_tag_name = $query['tag_name'];
}
if ( isset( $query['class_name'] ) && is_string( $query['class_name'] ) ) {
$this->sought_class_name = $query['class_name'];
}
if ( isset( $query['match_offset'] ) && is_int( $query['match_offset'] ) && 0 < $query['match_offset'] ) {
$this->sought_match_offset = $query['match_offset'];
}
if ( isset( $query['tag_closers'] ) ) {
$this->stop_on_tag_closers = 'visit' === $query['tag_closers'];
}
}
/**
* Checks whether a given tag and its attributes match the search criteria.
*
* @since 6.2.0
*
* @return boolean Whether the given tag and its attribute match the search criteria.
*/
private function matches() {
if ( $this->is_closing_tag && ! $this->stop_on_tag_closers ) {
return false;
}
// Does the tag name match the requested tag name in a case-insensitive manner?
if ( null !== $this->sought_tag_name ) {
/*
* String (byte) length lookup is fast. If they aren't the
* same length then they can't be the same string values.
*/
if ( strlen( $this->sought_tag_name ) !== $this->tag_name_length ) {
return false;
}
/*
* Check each character to determine if they are the same.
* Defer calls to `strtoupper()` to avoid them when possible.
* Calling `strcasecmp()` here tested slowed than comparing each
* character, so unless benchmarks show otherwise, it should
* not be used.
*
* It's expected that most of the time that this runs, a
* lower-case tag name will be supplied and the input will
* contain lower-case tag names, thus normally bypassing
* the case comparison code.
*/
for ( $i = 0; $i < $this->tag_name_length; $i++ ) {
$html_char = $this->html[ $this->tag_name_starts_at + $i ];
$tag_char = $this->sought_tag_name[ $i ];
if ( $html_char !== $tag_char && strtoupper( $html_char ) !== $tag_char ) {
return false;
}
}
}
$needs_class_name = null !== $this->sought_class_name;
if ( $needs_class_name && ! isset( $this->attributes['class'] ) ) {
return false;
}
/*
* Match byte-for-byte (case-sensitive and encoding-form-sensitive) on the class name.
*
* This will overlook certain classes that exist in other lexical variations
* than was supplied to the search query, but requires more complicated searching.
*/
if ( $needs_class_name ) {
$class_start = $this->attributes['class']->value_starts_at;
$class_end = $class_start + $this->attributes['class']->value_length;
$class_at = $class_start;
/*
* Ensure that boundaries surround the class name to avoid matching on
* substrings of a longer name. For example, the sequence "not-odd"
* should not match for the class "odd" even though "odd" is found
* within the class attribute text.
*
* See https://html.spec.whatwg.org/#attributes-3
* See https://html.spec.whatwg.org/#space-separated-tokens
*/
while (
// phpcs:ignore WordPress.CodeAnalysis.AssignmentInCondition.FoundInWhileCondition
false !== ( $class_at = strpos( $this->html, $this->sought_class_name, $class_at ) ) &&
$class_at < $class_end
) {
/*
* Verify this class starts at a boundary.
*/
if ( $class_at > $class_start ) {
$character = $this->html[ $class_at - 1 ];
if ( ' ' !== $character && "\t" !== $character && "\f" !== $character && "\r" !== $character && "\n" !== $character ) {
$class_at += strlen( $this->sought_class_name );
continue;
}
}
/*
* Verify this class ends at a boundary as well.
*/
if ( $class_at + strlen( $this->sought_class_name ) < $class_end ) {
$character = $this->html[ $class_at + strlen( $this->sought_class_name ) ];
if ( ' ' !== $character && "\t" !== $character && "\f" !== $character && "\r" !== $character && "\n" !== $character ) {
$class_at += strlen( $this->sought_class_name );
continue;
}
}
return true;
}
return false;
}
return true;
}
}