WP_HTML_Decoder

12class WP_HTML_Decoder {13	/**14	 * Indicates if an attribute value starts with a given raw string value.15	 *16	 * Use this method to determine if an attribute value starts with a given string, regardless17	 * of how it might be encoded in HTML. For instance, `http:` could be represented as `http:`18	 * or as `http&colon;` or as `&#x68;ttp:` or as `h&#116;tp&colon;`, or in many other ways.19	 *20	 * Example:21	 *22	 *     $value = 'http&colon;//wordpress.org/';23	 *     true   === WP_HTML_Decoder::attribute_starts_with( $value, 'http:', 'ascii-case-insensitive' );24	 *     false  === WP_HTML_Decoder::attribute_starts_with( $value, 'https:', 'ascii-case-insensitive' );25	 *26	 * @since 6.6.027	 *28	 * @param string $haystack         String containing the raw non-decoded attribute value.29	 * @param string $search_text      Does the attribute value start with this plain string.30	 * @param string $case_sensitivity Optional. Pass 'ascii-case-insensitive' to ignore ASCII case when matching.31	 *                                 Default 'case-sensitive'.32	 * @return bool Whether the attribute value starts with the given string.33	 */34	public static function attribute_starts_with( $haystack, $search_text, $case_sensitivity = 'case-sensitive' ): bool {35		$search_length = strlen( $search_text );36		$loose_case    = 'ascii-case-insensitive' === $case_sensitivity;37		$haystack_end  = strlen( $haystack );38		$search_at     = 0;39		$haystack_at   = 0;40 41		while ( $search_at < $search_length && $haystack_at < $haystack_end ) {42			$chars_match = $loose_case43				? strtolower( $haystack[ $haystack_at ] ) === strtolower( $search_text[ $search_at ] )44				: $haystack[ $haystack_at ] === $search_text[ $search_at ];45 46			$is_introducer = '&' === $haystack[ $haystack_at ];47			$next_chunk    = $is_introducer48				? self::read_character_reference( 'attribute', $haystack, $haystack_at, $token_length )49				: null;50 51			// If there's no character reference and the characters don't match, the match fails.52			if ( null === $next_chunk && ! $chars_match ) {53				return false;54			}55 56			// If there's no character reference but the character do match, then it could still match.57			if ( null === $next_chunk && $chars_match ) {58				++$haystack_at;59				++$search_at;60				continue;61			}62 63			// If there is a character reference, then the decoded value must exactly match what follows in the search string.64			if ( 0 !== substr_compare( $search_text, $next_chunk, $search_at, strlen( $next_chunk ), $loose_case ) ) {65				return false;66			}67 68			// The character reference matched, so continue checking.69			$haystack_at += $token_length;70			$search_at   += strlen( $next_chunk );71		}72 73		return true;74	}75 76	/**77	 * Returns a string containing the decoded value of a given HTML text node.78	 *79	 * Text nodes appear in HTML DATA sections, which are the text segments inside80	 * and around tags, excepting SCRIPT and STYLE elements (and some others),81	 * whose inner text is not decoded. Use this function to read the decoded82	 * value of such a text span in an HTML document.83	 *84	 * Example:85	 *86	 *     '“😄”' === WP_HTML_Decode::decode_text_node( '&#x93;&#x1f604;&#x94' );87	 *88	 * @since 6.6.089	 *90	 * @param string $text Text containing raw and non-decoded text node to decode.91	 * @return string Decoded UTF-8 value of given text node.