...
+ * 01234
+ * - tag name starts at 1
+ *
+ * @since 6.2.0
+ *
+ * @var int|null
+ */
+ private $tag_name_starts_at;
+
+ /**
+ * Byte length of current tag name.
+ *
+ * Example:
+ *
+ *
...
+ * 01234
+ * --- tag name length is 3
+ *
+ * @since 6.2.0
+ *
+ * @var int|null
+ */
+ private $tag_name_length;
+
+ /**
+ * Whether the current tag is an opening tag, e.g.
, or a closing tag, e.g.
.
+ *
+ * @var bool
+ */
+ private $is_closing_tag;
+
+ /**
+ * Lazily-built index of attributes found within an HTML tag, keyed by the attribute name.
+ *
+ * Example:
+ *
+ * // Supposing the parser is working through this content
+ * // and stops after recognizing the `id` attribute.
+ * //
+ * // ^ parsing will continue from this point.
+ * $this->attributes = array(
+ * 'id' => new WP_HTML_Attribute_Token( 'id', 9, 6, 5, 11, false )
+ * );
+ *
+ * // When picking up parsing again, or when asking to find the
+ * // `class` attribute we will continue and add to this array.
+ * $this->attributes = array(
+ * 'id' => new WP_HTML_Attribute_Token( 'id', 9, 6, 5, 11, false ),
+ * 'class' => new WP_HTML_Attribute_Token( 'class', 23, 7, 17, 13, false )
+ * );
+ *
+ * // Note that only the `class` attribute value is stored in the index.
+ * // That's because it is the only value used by this class at the moment.
+ *
+ * @since 6.2.0
+ * @var WP_HTML_Attribute_Token[]
+ */
+ private $attributes = array();
+
+ /**
+ * Tracks spans of duplicate attributes on a given tag, used for removing
+ * all copies of an attribute when calling `remove_attribute()`.
+ *
+ * @since 6.3.2
+ *
+ * @var (WP_HTML_Span[])[]|null
+ */
+ private $duplicate_attributes = null;
+
+ /**
+ * Which class names to add or remove from a tag.
+ *
+ * These are tracked separately from attribute updates because they are
+ * semantically distinct, whereas this interface exists for the common
+ * case of adding and removing class names while other attributes are
+ * generally modified as with DOM `setAttribute` calls.
+ *
+ * When modifying an HTML document these will eventually be collapsed
+ * into a single `set_attribute( 'class', $changes )` call.
+ *
+ * Example:
+ *
+ * // Add the `wp-block-group` class, remove the `wp-group` class.
+ * $classname_updates = array(
+ * // Indexed by a comparable class name.
+ * 'wp-block-group' => WP_HTML_Tag_Processor::ADD_CLASS,
+ * 'wp-group' => WP_HTML_Tag_Processor::REMOVE_CLASS
+ * );
+ *
+ * @since 6.2.0
+ * @var bool[]
+ */
+ private $classname_updates = array();
+
+ /**
+ * Tracks a semantic location in the original HTML which
+ * shifts with updates as they are applied to the document.
+ *
+ * @since 6.2.0
+ * @var WP_HTML_Span[]
+ */
+ protected $bookmarks = array();
+
+ const ADD_CLASS = true;
+ const REMOVE_CLASS = false;
+ const SKIP_CLASS = null;
+
+ /**
+ * Lexical replacements to apply to input HTML document.
+ *
+ * "Lexical" in this class refers to the part of this class which
+ * operates on pure text _as text_ and not as HTML. There's a line
+ * between the public interface, with HTML-semantic methods like
+ * `set_attribute` and `add_class`, and an internal state that tracks
+ * text offsets in the input document.
+ *
+ * When higher-level HTML methods are called, those have to transform their
+ * operations (such as setting an attribute's value) into text diffing
+ * operations (such as replacing the sub-string from indices A to B with
+ * some given new string). These text-diffing operations are the lexical
+ * updates.
+ *
+ * As new higher-level methods are added they need to collapse their
+ * operations into these lower-level lexical updates since that's the
+ * Tag Processor's internal language of change. Any code which creates
+ * these lexical updates must ensure that they do not cross HTML syntax
+ * boundaries, however, so these should never be exposed outside of this
+ * class or any classes which intentionally expand its functionality.
+ *
+ * These are enqueued while editing the document instead of being immediately
+ * applied to avoid processing overhead, string allocations, and string
+ * copies when applying many updates to a single document.
+ *
+ * Example:
+ *
+ * // Replace an attribute stored with a new value, indices
+ * // sourced from the lazily-parsed HTML recognizer.
+ * $start = $attributes['src']->start;
+ * $length = $attributes['src']->length;
+ * $modifications[] = new WP_HTML_Text_Replacement( $start, $length, $new_value );
+ *
+ * // Correspondingly, something like this will appear in this array.
+ * $lexical_updates = array(
+ * WP_HTML_Text_Replacement( 14, 28, 'https://my-site.my-domain/wp-content/uploads/2014/08/kittens.jpg' )
+ * );
+ *
+ * @since 6.2.0
+ * @var WP_HTML_Text_Replacement[]
+ */
+ protected $lexical_updates = array();
+
+ /**
+ * Tracks and limits `seek()` calls to prevent accidental infinite loops.
+ *
+ * @since 6.2.0
+ * @var int
+ *
+ * @see WP_HTML_Tag_Processor::seek()
+ */
+ protected $seek_count = 0;
+
+ /**
+ * Constructor.
+ *
+ * @since 6.2.0
+ *
+ * @param string $html HTML to process.
+ */
+ public function __construct( $html ) {
+ $this->html = $html;
+ }
+
+ /**
+ * Finds the next tag matching the $query.
+ *
+ * @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 whole class name to match.
+ * @type string|null $tag_closers "visit" or "skip": whether to stop on tag closers, e.g.
.
+ * }
+ * @return bool Whether a tag was matched.
+ */
+ public function next_tag( $query = null ) {
+ $this->parse_query( $query );
+ $already_found = 0;
+
+ do {
+ if ( $this->bytes_already_parsed >= strlen( $this->html ) ) {
+ return false;
+ }
+
+ // Find the next tag if it exists.
+ if ( false === $this->parse_next_tag() ) {
+ $this->bytes_already_parsed = strlen( $this->html );
+
+ return false;
+ }
+
+ // Parse all of its attributes.
+ while ( $this->parse_next_attribute() ) {
+ continue;
+ }
+
+ // Ensure that the tag closes before the end of the document.
+ if ( $this->bytes_already_parsed >= strlen( $this->html ) ) {
+ return false;
+ }
+
+ $tag_ends_at = strpos( $this->html, '>', $this->bytes_already_parsed );
+ if ( false === $tag_ends_at ) {
+ return false;
+ }
+ $this->token_length = $tag_ends_at - $this->token_starts_at;
+ $this->bytes_already_parsed = $tag_ends_at;
+
+ // Finally, check if the parsed tag and its attributes match the search query.
+ if ( $this->matches() ) {
+ ++$already_found;
+ }
+
+ /*
+ * For non-DATA sections which might contain text that looks like HTML tags but
+ * isn't, scan with the appropriate alternative mode. Looking at the first letter
+ * of the tag name as a pre-check avoids a string allocation when it's not needed.
+ */
+ $t = $this->html[ $this->tag_name_starts_at ];
+ if (
+ ! $this->is_closing_tag &&
+ (
+ 'i' === $t || 'I' === $t ||
+ 'n' === $t || 'N' === $t ||
+ 's' === $t || 'S' === $t ||
+ 't' === $t || 'T' === $t
+ ) ) {
+ $tag_name = $this->get_tag();
+
+ if ( 'SCRIPT' === $tag_name && ! $this->skip_script_data() ) {
+ $this->bytes_already_parsed = strlen( $this->html );
+ return false;
+ } elseif (
+ ( 'TEXTAREA' === $tag_name || 'TITLE' === $tag_name ) &&
+ ! $this->skip_rcdata( $tag_name )
+ ) {
+ $this->bytes_already_parsed = strlen( $this->html );
+ return false;
+ } elseif (
+ (
+ 'IFRAME' === $tag_name ||
+ 'NOEMBED' === $tag_name ||
+ 'NOFRAMES' === $tag_name ||
+ 'NOSCRIPT' === $tag_name ||
+ 'STYLE' === $tag_name
+ ) &&
+ ! $this->skip_rawtext( $tag_name )
+ ) {
+ /*
+ * "XMP" should be here too but its rules are more complicated and require the
+ * complexity of the HTML Processor (it needs to close out any open P element,
+ * meaning it can't be skipped here or else the HTML Processor will lose its
+ * place). For now, it can be ignored as it's a rare HTML tag in practice and
+ * any normative HTML should be using PRE instead.
+ */
+ $this->bytes_already_parsed = strlen( $this->html );
+ return false;
+ }
+ }
+ } while ( $already_found < $this->sought_match_offset );
+
+ return true;
+ }
+
+
+ /**
+ * 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 = new WP_HTML_Tag_Processor( "
" );
+ * $p->next_tag();
+ * foreach ( $p->class_list() as $class_name ) {
+ * echo "{$class_name} ";
+ * }
+ * // Outputs: "free
lang-en "
+ *
+ * @since 6.4.0
+ */
+ public function class_list() {
+ /** @var string $class contains the string value of the class attribute, with character references decoded. */
+ $class = $this->get_attribute( 'class' );
+
+ if ( ! is_string( $class ) ) {
+ return;
+ }
+
+ $seen = array();
+
+ $at = 0;
+ while ( $at < strlen( $class ) ) {
+ // Skip past any initial boundary characters.
+ $at += strspn( $class, " \t\f\r\n", $at );
+ if ( $at >= strlen( $class ) ) {
+ return;
+ }
+
+ // Find the byte length until the next boundary.
+ $length = strcspn( $class, " \t\f\r\n", $at );
+ if ( 0 === $length ) {
+ return;
+ }
+
+ /*
+ * CSS class names are case-insensitive in the ASCII range.
+ *
+ * @see https://www.w3.org/TR/CSS2/syndata.html#x1
+ */
+ $name = strtolower( substr( $class, $at, $length ) );
+ $at += $length;
+
+ /*
+ * It's expected that the number of class names for a given tag is relatively small.
+ * Given this, it is probably faster overall to scan an array for a value rather
+ * than to use the class name as a key and check if it's a key of $seen.
+ */
+ if ( in_array( $name, $seen, true ) ) {
+ continue;
+ }
+
+ $seen[] = $name;
+ yield $name;
+ }
+ }
+
+
+ /**
+ * Returns if a matched tag contains the given ASCII case-insensitive class name.
+ *
+ * @since 6.4.0
+ *
+ * @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 ) {
+ if ( ! $this->tag_name_starts_at ) {
+ return null;
+ }
+
+ $wanted_class = strtolower( $wanted_class );
+
+ foreach ( $this->class_list() as $class_name ) {
+ if ( $class_name === $wanted_class ) {
+ return true;
+ }
+ }
+
+ 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:
+ *
+ *
+ * ^^^^
+ * 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.
+ *
+ * @since 6.2.0
+ *
+ * @param string $name Identifies this particular bookmark.
+ * @return bool Whether the bookmark was successfully created.
+ */
+ public function set_bookmark( $name ) {
+ if ( null === $this->tag_name_starts_at ) {
+ return false;
+ }
+
+ if ( ! array_key_exists( $name, $this->bookmarks ) && count( $this->bookmarks ) >= static::MAX_BOOKMARKS ) {
+ _doing_it_wrong(
+ __METHOD__,
+ __( 'Too many bookmarks: cannot create any more.' ),
+ '6.2.0'
+ );
+ return false;
+ }
+
+ $this->bookmarks[ $name ] = new Gutenberg_HTML_Span_6_5( $this->token_starts_at, $this->token_length );
+
+ return true;
+ }
+
+
+ /**
+ * Removes a bookmark that is no longer needed.
+ *
+ * Releasing a bookmark frees up the small
+ * performance overhead it requires.
+ *
+ * @param string $name Name of the bookmark to remove.
+ * @return bool Whether the bookmark already existed before removal.
+ */
+ public function release_bookmark( $name ) {
+ if ( ! array_key_exists( $name, $this->bookmarks ) ) {
+ return false;
+ }
+
+ unset( $this->bookmarks[ $name ] );
+
+ return true;
+ }
+
+ /**
+ * Skips contents of generic rawtext elements.
+ *
+ * @since 6.3.2
+ *
+ * @see https://html.spec.whatwg.org/#generic-raw-text-element-parsing-algorithm
+ *
+ * @param string $tag_name The uppercase tag name which will close the RAWTEXT region.
+ * @return bool Whether an end to the RAWTEXT region was found before the end of the document.
+ */
+ private function skip_rawtext( $tag_name ) {
+ /*
+ * These two functions distinguish themselves on whether character references are
+ * decoded, and since functionality to read the inner markup isn't supported, it's
+ * not necessary to implement these two functions separately.
+ */
+ return $this->skip_rcdata( $tag_name );
+ }
+
+ /**
+ * Skips contents of RCDATA elements, namely title and textarea tags.
+ *
+ * @since 6.2.0
+ *
+ * @see https://html.spec.whatwg.org/multipage/parsing.html#rcdata-state
+ *
+ * @param string $tag_name The uppercase tag name which will close the RCDATA region.
+ * @return bool Whether an end to the RCDATA region was found before the end of the document.
+ */
+ private function skip_rcdata( $tag_name ) {
+ $html = $this->html;
+ $doc_length = strlen( $html );
+ $tag_length = strlen( $tag_name );
+
+ $at = $this->bytes_already_parsed;
+
+ while ( false !== $at && $at < $doc_length ) {
+ $at = strpos( $this->html, '= $doc_length ) {
+ $this->bytes_already_parsed = $doc_length;
+ return false;
+ }
+
+ $closer_potentially_starts_at = $at;
+ $at += 2;
+
+ /*
+ * Find a case-insensitive match to the tag name.
+ *
+ * Because tag names are limited to US-ASCII there is no
+ * need to perform any kind of Unicode normalization when
+ * comparing; any character which could be impacted by such
+ * normalization could not be part of a tag name.
+ */
+ for ( $i = 0; $i < $tag_length; $i++ ) {
+ $tag_char = $tag_name[ $i ];
+ $html_char = $html[ $at + $i ];
+
+ if ( $html_char !== $tag_char && strtoupper( $html_char ) !== $tag_char ) {
+ $at += $i;
+ continue 2;
+ }
+ }
+
+ $at += $tag_length;
+ $this->bytes_already_parsed = $at;
+
+ /*
+ * Ensure that the tag name terminates to avoid matching on
+ * substrings of a longer tag name. For example, the sequence
+ * "' !== $c ) {
+ continue;
+ }
+
+ while ( $this->parse_next_attribute() ) {
+ continue;
+ }
+ $at = $this->bytes_already_parsed;
+ if ( $at >= strlen( $this->html ) ) {
+ return false;
+ }
+
+ if ( '>' === $html[ $at ] || '/' === $html[ $at ] ) {
+ $this->bytes_already_parsed = $closer_potentially_starts_at;
+ return true;
+ }
+ }
+
+ return false;
+ }
+
+ /**
+ * Skips contents of script tags.
+ *
+ * @since 6.2.0
+ *
+ * @return bool Whether the script tag was closed before the end of the document.
+ */
+ private function skip_script_data() {
+ $state = 'unescaped';
+ $html = $this->html;
+ $doc_length = strlen( $html );
+ $at = $this->bytes_already_parsed;
+
+ while ( false !== $at && $at < $doc_length ) {
+ $at += strcspn( $html, '-<', $at );
+
+ /*
+ * For all script states a "-->" transitions
+ * back into the normal unescaped script mode,
+ * even if that's the current state.
+ */
+ if (
+ $at + 2 < $doc_length &&
+ '-' === $html[ $at ] &&
+ '-' === $html[ $at + 1 ] &&
+ '>' === $html[ $at + 2 ]
+ ) {
+ $at += 3;
+ $state = 'unescaped';
+ continue;
+ }
+
+ // Everything of interest past here starts with "<".
+ if ( $at + 1 >= $doc_length || '<' !== $html[ $at++ ] ) {
+ continue;
+ }
+
+ /*
+ * Unlike with "-->", the "
+ * https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
+ */
+ if (
+ strlen( $html ) > $at + 3 &&
+ '-' === $html[ $at + 2 ] &&
+ '-' === $html[ $at + 3 ]
+ ) {
+ $closer_at = $at + 4;
+ // If it's not possible to close the comment then there is nothing more to scan.
+ if ( strlen( $html ) <= $closer_at ) {
+ return false;
+ }
+
+ // Abruptly-closed empty comments are a sequence of dashes followed by `>`.
+ $span_of_dashes = strspn( $html, '-', $closer_at );
+ if ( '>' === $html[ $closer_at + $span_of_dashes ] ) {
+ $at = $closer_at + $span_of_dashes + 1;
+ continue;
+ }
+
+ /*
+ * Comments may be closed by either a --> or an invalid --!>.
+ * The first occurrence closes the comment.
+ *
+ * See https://html.spec.whatwg.org/#parse-error-incorrectly-closed-comment
+ */
+ --$closer_at; // Pre-increment inside condition below reduces risk of accidental infinite looping.
+ while ( ++$closer_at < strlen( $html ) ) {
+ $closer_at = strpos( $html, '--', $closer_at );
+ if ( false === $closer_at ) {
+ return false;
+ }
+
+ if ( $closer_at + 2 < strlen( $html ) && '>' === $html[ $closer_at + 2 ] ) {
+ $at = $closer_at + 3;
+ continue 2;
+ }
+
+ if ( $closer_at + 3 < strlen( $html ) && '!' === $html[ $closer_at + 2 ] && '>' === $html[ $closer_at + 3 ] ) {
+ $at = $closer_at + 4;
+ continue 2;
+ }
+ }
+ }
+
+ /*
+ *
+ * The CDATA is case-sensitive.
+ * https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
+ */
+ if (
+ strlen( $html ) > $at + 8 &&
+ '[' === $html[ $at + 2 ] &&
+ 'C' === $html[ $at + 3 ] &&
+ 'D' === $html[ $at + 4 ] &&
+ 'A' === $html[ $at + 5 ] &&
+ 'T' === $html[ $at + 6 ] &&
+ 'A' === $html[ $at + 7 ] &&
+ '[' === $html[ $at + 8 ]
+ ) {
+ $closer_at = strpos( $html, ']]>', $at + 9 );
+ if ( false === $closer_at ) {
+ return false;
+ }
+
+ $at = $closer_at + 3;
+ continue;
+ }
+
+ /*
+ *
+ * These are ASCII-case-insensitive.
+ * https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
+ */
+ if (
+ strlen( $html ) > $at + 8 &&
+ ( 'D' === $html[ $at + 2 ] || 'd' === $html[ $at + 2 ] ) &&
+ ( 'O' === $html[ $at + 3 ] || 'o' === $html[ $at + 3 ] ) &&
+ ( 'C' === $html[ $at + 4 ] || 'c' === $html[ $at + 4 ] ) &&
+ ( 'T' === $html[ $at + 5 ] || 't' === $html[ $at + 5 ] ) &&
+ ( 'Y' === $html[ $at + 6 ] || 'y' === $html[ $at + 6 ] ) &&
+ ( 'P' === $html[ $at + 7 ] || 'p' === $html[ $at + 7 ] ) &&
+ ( 'E' === $html[ $at + 8 ] || 'e' === $html[ $at + 8 ] )
+ ) {
+ $closer_at = strpos( $html, '>', $at + 9 );
+ if ( false === $closer_at ) {
+ return false;
+ }
+
+ $at = $closer_at + 1;
+ continue;
+ }
+
+ /*
+ * Anything else here is an incorrectly-opened comment and transitions
+ * to the bogus comment state - skip to the nearest >.
+ */
+ $at = strpos( $html, '>', $at + 1 );
+ continue;
+ }
+
+ /*
+ * is a missing end tag name, which is ignored.
+ *
+ * See https://html.spec.whatwg.org/#parse-error-missing-end-tag-name
+ */
+ if ( '>' === $html[ $at + 1 ] ) {
+ ++$at;
+ continue;
+ }
+
+ /*
+ *
+ * See https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
+ */
+ if ( '?' === $html[ $at + 1 ] ) {
+ $closer_at = strpos( $html, '>', $at + 2 );
+ if ( false === $closer_at ) {
+ return false;
+ }
+
+ $at = $closer_at + 1;
+ continue;
+ }
+
+ /*
+ * If a non-alpha starts the tag name in a tag closer it's a comment.
+ * Find the first `>`, which closes the comment.
+ *
+ * See https://html.spec.whatwg.org/#parse-error-invalid-first-character-of-tag-name
+ */
+ if ( $this->is_closing_tag ) {
+ $closer_at = strpos( $html, '>', $at + 3 );
+ if ( false === $closer_at ) {
+ return false;
+ }
+
+ $at = $closer_at + 1;
+ continue;
+ }
+
+ ++$at;
+ }
+
+ return false;
+ }
+
+ /**
+ * Parses the next attribute.
+ *
+ * @since 6.2.0
+ *
+ * @return bool Whether an attribute was found before the end of the document.
+ */
+ private function parse_next_attribute() {
+ // Skip whitespace and slashes.
+ $this->bytes_already_parsed += strspn( $this->html, " \t\f\r\n/", $this->bytes_already_parsed );
+ if ( $this->bytes_already_parsed >= strlen( $this->html ) ) {
+ return false;
+ }
+
+ /*
+ * Treat the equal sign as a part of the attribute
+ * name if it is the first encountered byte.
+ *
+ * @see https://html.spec.whatwg.org/multipage/parsing.html#before-attribute-name-state
+ */
+ $name_length = '=' === $this->html[ $this->bytes_already_parsed ]
+ ? 1 + strcspn( $this->html, "=/> \t\f\r\n", $this->bytes_already_parsed + 1 )
+ : strcspn( $this->html, "=/> \t\f\r\n", $this->bytes_already_parsed );
+
+ // No attribute, just tag closer.
+ if ( 0 === $name_length || $this->bytes_already_parsed + $name_length >= strlen( $this->html ) ) {
+ return false;
+ }
+
+ $attribute_start = $this->bytes_already_parsed;
+ $attribute_name = substr( $this->html, $attribute_start, $name_length );
+ $this->bytes_already_parsed += $name_length;
+ if ( $this->bytes_already_parsed >= strlen( $this->html ) ) {
+ return false;
+ }
+
+ $this->skip_whitespace();
+ if ( $this->bytes_already_parsed >= strlen( $this->html ) ) {
+ return false;
+ }
+
+ $has_value = '=' === $this->html[ $this->bytes_already_parsed ];
+ if ( $has_value ) {
+ ++$this->bytes_already_parsed;
+ $this->skip_whitespace();
+ if ( $this->bytes_already_parsed >= strlen( $this->html ) ) {
+ return false;
+ }
+
+ switch ( $this->html[ $this->bytes_already_parsed ] ) {
+ case "'":
+ case '"':
+ $quote = $this->html[ $this->bytes_already_parsed ];
+ $value_start = $this->bytes_already_parsed + 1;
+ $value_length = strcspn( $this->html, $quote, $value_start );
+ $attribute_end = $value_start + $value_length + 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 >= strlen( $this->html ) ) {
+ 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 ( ! array_key_exists( $comparable_name, $this->attributes ) ) {
+ $this->attributes[ $comparable_name ] = new Gutenberg_HTML_Attribute_Token_6_5(
+ $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 Gutenberg_HTML_Span_6_5( $attribute_start, $attribute_end - $attribute_start );
+ if ( null === $this->duplicate_attributes ) {
+ $this->duplicate_attributes = array( $comparable_name => array( $duplicate_span ) );
+ } elseif ( ! array_key_exists( $comparable_name, $this->duplicate_attributes ) ) {
+ $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() {
+ $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() {
+ $this->get_updated_html();
+ $this->token_starts_at = null;
+ $this->token_length = null;
+ $this->tag_name_starts_at = null;
+ $this->tag_name_length = null;
+ $this->is_closing_tag = null;
+ $this->attributes = array();
+ $this->duplicate_attributes = null;
+ }
+
+ /**
+ * Converts class name updates into tag attributes updates
+ * (they are accumulated in different data formats for performance).
+ *
+ * @since 6.2.0
+ *
+ * @see WP_HTML_Tag_Processor::$lexical_updates
+ * @see WP_HTML_Tag_Processor::$classname_updates
+ */
+ private function class_name_updates_to_attributes_updates() {
+ if ( count( $this->classname_updates ) === 0 ) {
+ return;
+ }
+
+ $existing_class = $this->get_enqueued_attribute_value( 'class' );
+ if ( null === $existing_class || true === $existing_class ) {
+ $existing_class = '';
+ }
+
+ if ( false === $existing_class && isset( $this->attributes['class'] ) ) {
+ $existing_class = substr(
+ $this->html,
+ $this->attributes['class']->value_starts_at,
+ $this->attributes['class']->value_length
+ );
+ }
+
+ if ( false === $existing_class ) {
+ $existing_class = '';
+ }
+
+ /**
+ * Updated "class" attribute value.
+ *
+ * This is incrementally built while scanning through the existing class
+ * attribute, skipping removed classes on the way, and then appending
+ * added classes at the end. Only when finished processing will the
+ * value contain the final new value.
+
+ * @var string $class
+ */
+ $class = '';
+
+ /**
+ * Tracks the cursor position in the existing
+ * class attribute value while parsing.
+ *
+ * @var int $at
+ */
+ $at = 0;
+
+ /**
+ * Indicates if there's any need to modify the existing class attribute.
+ *
+ * If a call to `add_class()` and `remove_class()` wouldn't impact
+ * the `class` attribute value then there's no need to rebuild it.
+ * For example, when adding a class that's already present or
+ * removing one that isn't.
+ *
+ * This flag enables a performance optimization when none of the enqueued
+ * class updates would impact the `class` attribute; namely, that the
+ * processor can continue without modifying the input document, as if
+ * none of the `add_class()` or `remove_class()` calls had been made.
+ *
+ * This flag is set upon the first change that requires a string update.
+ *
+ * @var bool $modified
+ */
+ $modified = false;
+
+ // Remove unwanted classes by only copying the new ones.
+ $existing_class_length = strlen( $existing_class );
+ while ( $at < $existing_class_length ) {
+ // Skip to the first non-whitespace character.
+ $ws_at = $at;
+ $ws_length = strspn( $existing_class, " \t\f\r\n", $ws_at );
+ $at += $ws_length;
+
+ // Capture the class name – it's everything until the next whitespace.
+ $name_length = strcspn( $existing_class, " \t\f\r\n", $at );
+ if ( 0 === $name_length ) {
+ // If no more class names are found then that's the end.
+ break;
+ }
+
+ $name = substr( $existing_class, $at, $name_length );
+ $at += $name_length;
+
+ // If this class is marked for removal, start processing the next one.
+ $remove_class = (
+ isset( $this->classname_updates[ $name ] ) &&
+ self::REMOVE_CLASS === $this->classname_updates[ $name ]
+ );
+
+ // If a class has already been seen then skip it; it should not be added twice.
+ if ( ! $remove_class ) {
+ $this->classname_updates[ $name ] = self::SKIP_CLASS;
+ }
+
+ if ( $remove_class ) {
+ $modified = true;
+ continue;
+ }
+
+ /*
+ * Otherwise, append it to the new "class" attribute value.
+ *
+ * There are options for handling whitespace between tags.
+ * Preserving the existing whitespace produces fewer changes
+ * to the HTML content and should clarify the before/after
+ * content when debugging the modified output.
+ *
+ * This approach contrasts normalizing the inter-class
+ * whitespace to a single space, which might appear cleaner
+ * in the output HTML but produce a noisier change.
+ */
+ $class .= substr( $existing_class, $ws_at, $ws_length );
+ $class .= $name;
+ }
+
+ // Add new classes by appending those which haven't already been seen.
+ foreach ( $this->classname_updates as $name => $operation ) {
+ if ( self::ADD_CLASS === $operation ) {
+ $modified = true;
+
+ $class .= strlen( $class ) > 0 ? ' ' : '';
+ $class .= $name;
+ }
+ }
+
+ $this->classname_updates = array();
+ if ( ! $modified ) {
+ return;
+ }
+
+ if ( strlen( $class ) > 0 ) {
+ $this->set_attribute( 'class', $class );
+ } else {
+ $this->remove_attribute( 'class' );
+ }
+ }
+
+ /**
+ * Applies attribute updates to HTML document.
+ *
+ * @since 6.2.0
+ * @since 6.2.1 Accumulates shift for internal cursor and passed pointer.
+ * @since 6.3.0 Invalidate any bookmarks whose targets are overwritten.
+ *
+ * @param int $shift_this_point Accumulate and return shift for this position.
+ * @return int How many bytes the given pointer moved in response to the updates.
+ */
+ private function apply_attributes_updates( $shift_this_point = 0 ) {
+ if ( ! count( $this->lexical_updates ) ) {
+ return 0;
+ }
+
+ $accumulated_shift_for_given_point = 0;
+
+ /*
+ * Attribute updates can be enqueued in any order but updates
+ * to the document must occur in lexical order; that is, each
+ * replacement must be made before all others which follow it
+ * at later string indices in the input document.
+ *
+ * Sorting avoid making out-of-order replacements which
+ * can lead to mangled output, partially-duplicated
+ * attributes, and overwritten attributes.
+ */
+ usort( $this->lexical_updates, array( self::class, 'sort_start_ascending' ) );
+
+ $bytes_already_copied = 0;
+ $output_buffer = '';
+ foreach ( $this->lexical_updates as $diff ) {
+ $shift = strlen( $diff->text ) - $diff->length;
+
+ // Adjust the cursor position by however much an update affects it.
+ if ( $diff->start <= $this->bytes_already_parsed ) {
+ $this->bytes_already_parsed += $shift;
+ }
+
+ // Accumulate shift of the given pointer within this function call.
+ if ( $diff->start <= $shift_this_point ) {
+ $accumulated_shift_for_given_point += $shift;
+ }
+
+ $output_buffer .= substr( $this->html, $bytes_already_copied, $diff->start - $bytes_already_copied );
+ $output_buffer .= $diff->text;
+ $bytes_already_copied = $diff->start + $diff->length;
+ }
+
+ $this->html = $output_buffer . substr( $this->html, $bytes_already_copied );
+
+ /*
+ * Adjust bookmark locations to account for how the text
+ * replacements adjust offsets in the input document.
+ */
+ foreach ( $this->bookmarks as $bookmark_name => $bookmark ) {
+ $bookmark_end = $bookmark->start + $bookmark->length;
+
+ /*
+ * Each lexical update which appears before the bookmark's endpoints
+ * might shift the offsets for those endpoints. Loop through each change
+ * and accumulate the total shift for each bookmark, then apply that
+ * shift after tallying the full delta.
+ */
+ $head_delta = 0;
+ $tail_delta = 0;
+
+ foreach ( $this->lexical_updates as $diff ) {
+ $diff_end = $diff->start + $diff->length;
+
+ if ( $bookmark->start < $diff->start && $bookmark_end < $diff->start ) {
+ break;
+ }
+
+ if ( $bookmark->start >= $diff->start && $bookmark_end < $diff_end ) {
+ $this->release_bookmark( $bookmark_name );
+ continue 2;
+ }
+
+ $delta = strlen( $diff->text ) - $diff->length;
+
+ if ( $bookmark->start >= $diff->start ) {
+ $head_delta += $delta;
+ }
+
+ if ( $bookmark_end >= $diff_end ) {
+ $tail_delta += $delta;
+ }
+ }
+
+ $bookmark->start += $head_delta;
+ $bookmark->length += $tail_delta - $head_delta;
+ }
+
+ $this->lexical_updates = array();
+
+ return $accumulated_shift_for_given_point;
+ }
+
+ /**
+ * Checks whether a bookmark with the given name exists.
+ *
+ * @since 6.3.0
+ *
+ * @param string $bookmark_name Name to identify a bookmark that potentially exists.
+ * @return bool Whether that bookmark exists.
+ */
+ public function has_bookmark( $bookmark_name ) {
+ return array_key_exists( $bookmark_name, $this->bookmarks );
+ }
+
+ /**
+ * Move the internal cursor in the Tag Processor to a given bookmark's location.
+ *
+ * In order to prevent accidental infinite loops, there's a
+ * maximum limit on the number of times seek() can be called.
+ *
+ * @since 6.2.0
+ *
+ * @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 ) {
+ if ( ! array_key_exists( $bookmark_name, $this->bookmarks ) ) {
+ _doing_it_wrong(
+ __METHOD__,
+ __( 'Unknown bookmark name.' ),
+ '6.2.0'
+ );
+ return false;
+ }
+
+ if ( ++$this->seek_count > static::MAX_SEEK_OPS ) {
+ _doing_it_wrong(
+ __METHOD__,
+ __( 'Too many calls to seek() - this can lead to performance issues.' ),
+ '6.2.0'
+ );
+ return false;
+ }
+
+ // Flush out any pending updates to the document.
+ $this->get_updated_html();
+
+ // Point this tag processor before the sought tag opener and consume it.
+ $this->bytes_already_parsed = $this->bookmarks[ $bookmark_name ]->start;
+ return $this->next_tag( array( 'tag_closers' => 'visit' ) );
+ }
+
+ /**
+ * Compare two WP_HTML_Text_Replacement objects.
+ *
+ * @since 6.2.0
+ *
+ * @param WP_HTML_Text_Replacement $a First attribute update.
+ * @param WP_HTML_Text_Replacement $b Second attribute update.
+ * @return int Comparison value for string order.
+ */
+ private static function sort_start_ascending( $a, $b ) {
+ $by_start = $a->start - $b->start;
+ if ( 0 !== $by_start ) {
+ return $by_start;
+ }
+
+ $by_text = isset( $a->text, $b->text ) ? strcmp( $a->text, $b->text ) : 0;
+ if ( 0 !== $by_text ) {
+ return $by_text;
+ }
+
+ /*
+ * This code should be unreachable, because it implies the two replacements
+ * start at the same location and contain the same text.
+ */
+ return $a->length - $b->length;
+ }
+
+ /**
+ * Return the enqueued value for a given attribute, if one exists.
+ *
+ * Enqueued updates can take different data types:
+ * - If an update is enqueued and is boolean, the return will be `true`
+ * - If an update is otherwise enqueued, the return will be the string value of that update.
+ * - If an attribute is enqueued to be removed, the return will be `null` to indicate that.
+ * - If no updates are enqueued, the return will be `false` to differentiate from "removed."
+ *
+ * @since 6.2.0
+ *
+ * @param string $comparable_name The attribute name in its comparable form.
+ * @return string|boolean|null Value of enqueued update if present, otherwise false.
+ */
+ private function get_enqueued_attribute_value( $comparable_name ) {
+ if ( ! isset( $this->lexical_updates[ $comparable_name ] ) ) {
+ return false;
+ }
+
+ $enqueued_text = $this->lexical_updates[ $comparable_name ]->text;
+
+ // Removed attributes erase the entire span.
+ if ( '' === $enqueued_text ) {
+ return null;
+ }
+
+ /*
+ * Boolean attribute updates are just the attribute name without a corresponding value.
+ *
+ * This value might differ from the given comparable name in that there could be leading
+ * or trailing whitespace, and that the casing follows the name given in `set_attribute`.
+ *
+ * Example:
+ *
+ * $p->set_attribute( 'data-TEST-id', 'update' );
+ * 'update' === $p->get_enqueued_attribute_value( 'data-test-id' );
+ *
+ * Detect this difference based on the absence of the `=`, which _must_ exist in any
+ * attribute containing a value, e.g. ``.
+ * ¹ ²
+ * 1. Attribute with a string value.
+ * 2. Boolean attribute whose value is `true`.
+ */
+ $equals_at = strpos( $enqueued_text, '=' );
+ if ( false === $equals_at ) {
+ return true;
+ }
+
+ /*
+ * Finally, a normal update's value will appear after the `=` and
+ * be double-quoted, as performed incidentally by `set_attribute`.
+ *
+ * e.g. `type="text"`
+ * ¹² ³
+ * 1. Equals is here.
+ * 2. Double-quoting starts one after the equals sign.
+ * 3. Double-quoting ends at the last character in the update.
+ */
+ $enqueued_value = substr( $enqueued_text, $equals_at + 2, -1 );
+ return html_entity_decode( $enqueued_value );
+ }
+
+ /**
+ * Returns the value of a requested attribute from a matched tag opener if that attribute exists.
+ *
+ * Example:
+ *
+ * $p = new WP_HTML_Tag_Processor( '
Test
' );
+ * $p->next_tag( array( 'class_name' => 'test' ) ) === 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 6.2.0
+ *
+ * @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 ) {
+ 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.
+ */
+ public 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;
+ }
+
+ /*
+ * The self-closing flag is the solidus at the _end_ of the tag, not the beginning.
+ *
+ * Example:
+ *
+ *
+ * ^ this appears one character before the end of the closing ">".
+ */
+ return '/' === $this->html[ $this->token_starts_at + $this->token_length - 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.
+ '"\'>& 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 Gutenberg_HTML_Text_Replacement_6_5(
+ $existing_attribute->start,
+ $existing_attribute->length,
+ $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 Gutenberg_HTML_Text_Replacement_6_5(
+ $this->tag_name_starts_at + $this->tag_name_length,
+ 0,
+ ' ' . $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 Gutenberg_HTML_Text_Replacement_6_5(
+ $this->attributes[ $name ]->start,
+ $this->attributes[ $name ]->length,
+ ''
+ );
+
+ // 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 Gutenberg_HTML_Text_Replacement_6_5(
+ $attribute_token->start,
+ $attribute_token->length,
+ ''
+ );
+ }
+ }
+
+ 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.
+ * @since 6.4.0 No longer calls subclass method `next_tag()` after updating HTML.
+ *
+ * @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->token_starts_at;
+
+ /*
+ * 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, but in order to avoid issues with subclasses that might add
+ * behaviors to `next_tag()`, the internal methods should be called here
+ * instead.
+ *
+ * It's important to note that in this specific place there will be no change
+ * because the processor was already at a tag when this was called and it's
+ * rewinding only to the beginning of this very tag before reprocessing it
+ * and its attributes.
+ *
+ * Previous HTMLMore HTML
+ * ↑ │ back up by the length of the tag name plus the opening <
+ * └←─┘ back up by strlen("em") + 1 ==> 3
+ */
+ $this->bytes_already_parsed = $before_current_tag;
+ $this->parse_next_tag();
+ // Reparse the attributes.
+ while ( $this->parse_next_attribute() ) {
+ continue;
+ }
+
+ $tag_ends_at = strpos( $this->html, '>', $this->bytes_already_parsed );
+ $this->token_length = $tag_ends_at - $this->token_starts_at;
+ $this->bytes_already_parsed = $tag_ends_at;
+
+ 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 bool 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;
+ }
+ }
+ }
+
+ if ( null !== $this->sought_class_name && ! $this->has_class( $this->sought_class_name ) ) {
+ return false;
+ }
+
+ return true;
+ }
+}
diff --git a/lib/compat/wordpress-6.5/html-api/class-gutenberg-html-text-replacement-6-5.php b/lib/compat/wordpress-6.5/html-api/class-gutenberg-html-text-replacement-6-5.php
new file mode 100644
index 0000000000000..6409255833c81
--- /dev/null
+++ b/lib/compat/wordpress-6.5/html-api/class-gutenberg-html-text-replacement-6-5.php
@@ -0,0 +1,64 @@
+start = $start;
+ $this->length = $length;
+ $this->text = $text;
+ }
+}
diff --git a/lib/experimental/interactivity-api/class-wp-directive-processor.php b/lib/experimental/interactivity-api/class-wp-directive-processor.php
index e717b2e553943..cf55a048bb9fa 100644
--- a/lib/experimental/interactivity-api/class-wp-directive-processor.php
+++ b/lib/experimental/interactivity-api/class-wp-directive-processor.php
@@ -20,7 +20,7 @@
* available. Please restrain from investing unnecessary time and effort trying
* to improve this code.
*/
-class WP_Directive_Processor extends Gutenberg_HTML_Tag_Processor_6_4 {
+class WP_Directive_Processor extends Gutenberg_HTML_Tag_Processor_6_5 {
/**
* An array of root blocks.
@@ -195,7 +195,7 @@ public function get_inner_html() {
}
list( $start_name, $end_name ) = $bookmarks;
- $start = $this->bookmarks[ $start_name ]->end + 1;
+ $start = $this->bookmarks[ $start_name ]->start + $this->bookmarks[ $start_name ]->length + 1;
$end = $this->bookmarks[ $end_name ]->start;
$this->seek( $start_name ); // Return to original position.
@@ -225,14 +225,14 @@ public function set_inner_html( $new_html ) {
}
list( $start_name, $end_name ) = $bookmarks;
- $start = $this->bookmarks[ $start_name ]->end + 1;
+ $start = $this->bookmarks[ $start_name ]->start + $this->bookmarks[ $start_name ]->length + 1;
$end = $this->bookmarks[ $end_name ]->start;
$this->seek( $start_name ); // Return to original position.
$this->release_bookmark( $start_name );
$this->release_bookmark( $end_name );
- $this->lexical_updates[] = new WP_HTML_Text_Replacement( $start, $end, $new_html );
+ $this->lexical_updates[] = new Gutenberg_HTML_Text_Replacement_6_5( $start, $end - $start, $new_html );
return true;
}
diff --git a/lib/load.php b/lib/load.php
index 9c7618dbfc678..59fb75541ac41 100644
--- a/lib/load.php
+++ b/lib/load.php
@@ -76,6 +76,10 @@ function gutenberg_is_experiment_enabled( $name ) {
* always be loaded so that Gutenberg code can run the newest version of the Tag Processor.
*/
require __DIR__ . '/compat/wordpress-6.4/html-api/class-gutenberg-html-tag-processor-6-4.php';
+require __DIR__ . '/compat/wordpress-6.5/html-api/class-gutenberg-html-attribute-token-6-5.php';
+require __DIR__ . '/compat/wordpress-6.5/html-api/class-gutenberg-html-span-6-5.php';
+require __DIR__ . '/compat/wordpress-6.5/html-api/class-gutenberg-html-text-replacement-6-5.php';
+require __DIR__ . '/compat/wordpress-6.5/html-api/class-gutenberg-html-tag-processor-6-5.php';
/*
* The HTML Processor appeared after WordPress 6.3. If Gutenberg is running on a version of