WP_HTML_Tag_Processor::parse_next_attribute(): bool

Source

	/*
	 * </> is a missing end tag name, which is ignored.
	 *
	 * This was also known as the "presumptuous empty tag"
	 * in early discussions as it was proposed to close
	 * the nearest previous opening tag.
	 *
	 * See https://html.spec.whatwg.org/#parse-error-missing-end-tag-name
	 */
	if ( '>' === $html[ $at + 1 ] ) {
		// `<>` is interpreted as plaintext.
		if ( ! $this->is_closing_tag ) {
			++$at;
			continue;
		}

		$this->parser_state         = self::STATE_PRESUMPTUOUS_TAG;
		$this->token_length         = $at + 2 - $this->token_starts_at;
		$this->bytes_already_parsed = $at + 2;
		return true;
	}

	/*
	 * `<?` transitions to a bogus comment state – skip to the nearest >
	 * See https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
	 */
	if ( ! $this->is_closing_tag && '?' === $html[ $at + 1 ] ) {
		$closer_at = strpos( $html, '>', $at + 2 );
		if ( false === $closer_at ) {
			$this->parser_state = self::STATE_INCOMPLETE_INPUT;

			return false;
		}

		$this->parser_state         = self::STATE_COMMENT;
		$this->comment_type         = self::COMMENT_AS_INVALID_HTML;
		$this->token_length         = $closer_at + 1 - $this->token_starts_at;
		$this->text_starts_at       = $this->token_starts_at + 2;
		$this->text_length          = $closer_at - $this->text_starts_at;
		$this->bytes_already_parsed = $closer_at + 1;

		/*
		 * Identify a Processing Instruction node were HTML to have them.
		 *
		 * This section must occur after identifying the bogus comment end
		 * because in an HTML parser it will span to the nearest `>`, even
		 * if there's no `?>` as would be required in an XML document. It
		 * is therefore not possible to parse a Processing Instruction node
		 * containing a `>` in the HTML syntax.
		 *
		 * XML allows for more target names, but this code only identifies
		 * those with ASCII-representable target names. This means that it
		 * may identify some Processing Instruction nodes as bogus comments,
		 * but it will not misinterpret the HTML structure. By limiting the
		 * identification to these target names the Tag Processor can avoid
		 * the need to start parsing UTF-8 sequences.
		 *
		 * > NameStartChar ::= ":" | [A-Z] | "_" | [a-z] | [#xC0-#xD6] | [#xD8-#xF6] | [#xF8-#x2FF] |
		 *                     [#x370-#x37D] | [#x37F-#x1FFF] | [#x200C-#x200D] | [#x2070-#x218F] |
		 *                     [#x2C00-#x2FEF] | [#x3001-#xD7FF] | [#xF900-#xFDCF] | [#xFDF0-#xFFFD] |
		 *                     [#x10000-#xEFFFF]
		 * > NameChar      ::= NameStartChar | "-" | "." | [0-9] | #xB7 | [#x0300-#x036F] | [#x203F-#x2040]
		 *
		 * @todo Processing instruction nodes in SGML may contain any kind of markup. XML defines a
		 *       special case with `<?xml ... ?>` syntax, but the `?` is part of the bogus comment.
		 *
		 * @see https://www.w3.org/TR/2006/REC-xml11-20060816/#NT-PITarget
		 */
		if ( $this->token_length >= 5 && '?' === $html[ $closer_at - 1 ] ) {
			$comment_text     = substr( $html, $this->token_starts_at + 2, $this->token_length - 4 );
			$pi_target_length = strspn( $comment_text, 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ:_' );

			if ( 0 < $pi_target_length ) {
				$pi_target_length += strspn( $comment_text, 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789:_-.', $pi_target_length );

				$this->comment_type       = self::COMMENT_AS_PI_NODE_LOOKALIKE;
				$this->tag_name_starts_at = $this->token_starts_at + 2;
				$this->tag_name_length    = $pi_target_length;
				$this->text_starts_at    += $pi_target_length;
				$this->text_length       -= $pi_target_length + 1;
			}
		}

		return true;
	}

	/*
	 * If a non-alpha starts the tag name in a tag closer it's a comment.
	 * Find the first `>`, which closes the comment.
	 *
	 * This parser classifies these particular comments as special "funky comments"
	 * which are made available for further processing.
	 *
	 * See https://html.spec.whatwg.org/#parse-error-invalid-first-character-of-tag-name
	 */
	if ( $this->is_closing_tag ) {
		// No chance of finding a closer.
		if ( $at + 3 > $doc_length ) {
			$this->parser_state = self::STATE_INCOMPLETE_INPUT;

			return false;
		}

		$closer_at = strpos( $html, '>', $at + 2 );
		if ( false === $closer_at ) {
			$this->parser_state = self::STATE_INCOMPLETE_INPUT;

			return false;
		}

		$this->parser_state         = self::STATE_FUNKY_COMMENT;
		$this->token_length         = $closer_at + 1 - $this->token_starts_at;
		$this->text_starts_at       = $this->token_starts_at + 2;
		$this->text_length          = $closer_at - $this->text_starts_at;
		$this->bytes_already_parsed = $closer_at + 1;
		return true;
	}

	++$at;
}

/*
 * This does not imply an incomplete parse; it indicates that there
 * can be nothing left in the document other than a #text node.
 */

View all references View on Trac View on GitHub