[Summary view] [Print] [Text view]

   1  <?php
   2  /**
   3   * HTML API: WP_HTML_Processor_State class
   4   *
   5   * @package WordPress
   6   * @subpackage HTML-API
   7   * @since 6.4.0
   8   */
   9  
  10  /**
  11   * Core class used by the HTML processor during HTML parsing
  12   * for managing the internal parsing state.
  13   *
  14   * This class is designed for internal use by the HTML processor.
  15   *
  16   * @since 6.4.0
  17   *
  18   * @access private
  19   * @ignore
  20   *
  21   * @see WP_HTML_Processor
  22   */
  23  class WP_HTML_Processor_State {
  24      /*
  25       * Insertion mode constants.
  26       *
  27       * These constants exist and are named to make it easier to
  28       * discover and recognize the supported insertion modes in
  29       * the parser.
  30       *
  31       * Out of all the possible insertion modes, only those
  32       * supported by the parser are listed here. As support
  33       * is added to the parser for more modes, add them here
  34       * following the same naming and value pattern.
  35       *
  36       * @see https://html.spec.whatwg.org/#the-insertion-mode
  37       */
  38  
  39      /**
  40       * Initial insertion mode for full HTML parser.
  41       *
  42       * @since 6.4.0
  43       *
  44       * @see https://html.spec.whatwg.org/#the-initial-insertion-mode
  45       * @see WP_HTML_Processor_State::$insertion_mode
  46       *
  47       * @var string
  48       */
  49      const INSERTION_MODE_INITIAL = 'insertion-mode-initial';
  50  
  51      /**
  52       * Before HTML insertion mode for full HTML parser.
  53       *
  54       * @since 6.7.0
  55       *
  56       * @see https://html.spec.whatwg.org/#the-before-html-insertion-mode
  57       * @see WP_HTML_Processor_State::$insertion_mode
  58       *
  59       * @var string
  60       */
  61      const INSERTION_MODE_BEFORE_HTML = 'insertion-mode-before-html';
  62  
  63      /**
  64       * Before head insertion mode for full HTML parser.
  65       *
  66       * @since 6.7.0
  67       *
  68       * @see https://html.spec.whatwg.org/#parsing-main-beforehead
  69       * @see WP_HTML_Processor_State::$insertion_mode
  70       *
  71       * @var string
  72       */
  73      const INSERTION_MODE_BEFORE_HEAD = 'insertion-mode-before-head';
  74  
  75      /**
  76       * In head insertion mode for full HTML parser.
  77       *
  78       * @since 6.7.0
  79       *
  80       * @see https://html.spec.whatwg.org/#parsing-main-inhead
  81       * @see WP_HTML_Processor_State::$insertion_mode
  82       *
  83       * @var string
  84       */
  85      const INSERTION_MODE_IN_HEAD = 'insertion-mode-in-head';
  86  
  87      /**
  88       * In head noscript insertion mode for full HTML parser.
  89       *
  90       * @since 6.7.0
  91       *
  92       * @see https://html.spec.whatwg.org/#parsing-main-inheadnoscript
  93       * @see WP_HTML_Processor_State::$insertion_mode
  94       *
  95       * @var string
  96       */
  97      const INSERTION_MODE_IN_HEAD_NOSCRIPT = 'insertion-mode-in-head-noscript';
  98  
  99      /**
 100       * After head insertion mode for full HTML parser.
 101       *
 102       * @since 6.7.0
 103       *
 104       * @see https://html.spec.whatwg.org/#parsing-main-afterhead
 105       * @see WP_HTML_Processor_State::$insertion_mode
 106       *
 107       * @var string
 108       */
 109      const INSERTION_MODE_AFTER_HEAD = 'insertion-mode-after-head';
 110  
 111      /**
 112       * In body insertion mode for full HTML parser.
 113       *
 114       * @since 6.4.0
 115       *
 116       * @see https://html.spec.whatwg.org/#parsing-main-inbody
 117       * @see WP_HTML_Processor_State::$insertion_mode
 118       *
 119       * @var string
 120       */
 121      const INSERTION_MODE_IN_BODY = 'insertion-mode-in-body';
 122  
 123      /**
 124       * In table insertion mode for full HTML parser.
 125       *
 126       * @since 6.7.0
 127       *
 128       * @see https://html.spec.whatwg.org/#parsing-main-intable
 129       * @see WP_HTML_Processor_State::$insertion_mode
 130       *
 131       * @var string
 132       */
 133      const INSERTION_MODE_IN_TABLE = 'insertion-mode-in-table';
 134  
 135      /**
 136       * In table text insertion mode for full HTML parser.
 137       *
 138       * @since 6.7.0
 139       *
 140       * @see https://html.spec.whatwg.org/#parsing-main-intabletext
 141       * @see WP_HTML_Processor_State::$insertion_mode
 142       *
 143       * @var string
 144       */
 145      const INSERTION_MODE_IN_TABLE_TEXT = 'insertion-mode-in-table-text';
 146  
 147      /**
 148       * In caption insertion mode for full HTML parser.
 149       *
 150       * @since 6.7.0
 151       *
 152       * @see https://html.spec.whatwg.org/#parsing-main-incaption
 153       * @see WP_HTML_Processor_State::$insertion_mode
 154       *
 155       * @var string
 156       */
 157      const INSERTION_MODE_IN_CAPTION = 'insertion-mode-in-caption';
 158  
 159      /**
 160       * In column group insertion mode for full HTML parser.
 161       *
 162       * @since 6.7.0
 163       *
 164       * @see https://html.spec.whatwg.org/#parsing-main-incolumngroup
 165       * @see WP_HTML_Processor_State::$insertion_mode
 166       *
 167       * @var string
 168       */
 169      const INSERTION_MODE_IN_COLUMN_GROUP = 'insertion-mode-in-column-group';
 170  
 171      /**
 172       * In table body insertion mode for full HTML parser.
 173       *
 174       * @since 6.7.0
 175       *
 176       * @see https://html.spec.whatwg.org/#parsing-main-intablebody
 177       * @see WP_HTML_Processor_State::$insertion_mode
 178       *
 179       * @var string
 180       */
 181      const INSERTION_MODE_IN_TABLE_BODY = 'insertion-mode-in-table-body';
 182  
 183      /**
 184       * In row insertion mode for full HTML parser.
 185       *
 186       * @since 6.7.0
 187       *
 188       * @see https://html.spec.whatwg.org/#parsing-main-inrow
 189       * @see WP_HTML_Processor_State::$insertion_mode
 190       *
 191       * @var string
 192       */
 193      const INSERTION_MODE_IN_ROW = 'insertion-mode-in-row';
 194  
 195      /**
 196       * In cell insertion mode for full HTML parser.
 197       *
 198       * @since 6.7.0
 199       *
 200       * @see https://html.spec.whatwg.org/#parsing-main-incell
 201       * @see WP_HTML_Processor_State::$insertion_mode
 202       *
 203       * @var string
 204       */
 205      const INSERTION_MODE_IN_CELL = 'insertion-mode-in-cell';
 206  
 207      /**
 208       * In select insertion mode for full HTML parser.
 209       *
 210       * @since 6.7.0
 211       *
 212       * @deprecated 7.1.0 The "in select" insertion mode was removed from the standard.
 213       * @ignore
 214       *
 215       * @see WP_HTML_Processor_State::$insertion_mode
 216       *
 217       * @var string
 218       */
 219      const INSERTION_MODE_IN_SELECT = 'insertion-mode-in-select';
 220  
 221      /**
 222       * In select in table insertion mode for full HTML parser.
 223       *
 224       * @since 6.7.0
 225       *
 226       * @deprecated 7.1.0 The "in select in table" insertion mode was removed from the standard.
 227       * @ignore
 228       *
 229       * @see WP_HTML_Processor_State::$insertion_mode
 230       *
 231       * @var string
 232       */
 233      const INSERTION_MODE_IN_SELECT_IN_TABLE = 'insertion-mode-in-select-in-table';
 234  
 235      /**
 236       * In template insertion mode for full HTML parser.
 237       *
 238       * @since 6.7.0
 239       *
 240       * @see https://html.spec.whatwg.org/#parsing-main-intemplate
 241       * @see WP_HTML_Processor_State::$insertion_mode
 242       *
 243       * @var string
 244       */
 245      const INSERTION_MODE_IN_TEMPLATE = 'insertion-mode-in-template';
 246  
 247      /**
 248       * After body insertion mode for full HTML parser.
 249       *
 250       * @since 6.7.0
 251       *
 252       * @see https://html.spec.whatwg.org/#parsing-main-afterbody
 253       * @see WP_HTML_Processor_State::$insertion_mode
 254       *
 255       * @var string
 256       */
 257      const INSERTION_MODE_AFTER_BODY = 'insertion-mode-after-body';
 258  
 259      /**
 260       * In frameset insertion mode for full HTML parser.
 261       *
 262       * @since 6.7.0
 263       *
 264       * @see https://html.spec.whatwg.org/#parsing-main-inframeset
 265       * @see WP_HTML_Processor_State::$insertion_mode
 266       *
 267       * @var string
 268       */
 269      const INSERTION_MODE_IN_FRAMESET = 'insertion-mode-in-frameset';
 270  
 271      /**
 272       * After frameset insertion mode for full HTML parser.
 273       *
 274       * @since 6.7.0
 275       *
 276       * @see https://html.spec.whatwg.org/#parsing-main-afterframeset
 277       * @see WP_HTML_Processor_State::$insertion_mode
 278       *
 279       * @var string
 280       */
 281      const INSERTION_MODE_AFTER_FRAMESET = 'insertion-mode-after-frameset';
 282  
 283      /**
 284       * After after body insertion mode for full HTML parser.
 285       *
 286       * @since 6.7.0
 287       *
 288       * @see https://html.spec.whatwg.org/#the-after-after-body-insertion-mode
 289       * @see WP_HTML_Processor_State::$insertion_mode
 290       *
 291       * @var string
 292       */
 293      const INSERTION_MODE_AFTER_AFTER_BODY = 'insertion-mode-after-after-body';
 294  
 295      /**
 296       * After after frameset insertion mode for full HTML parser.
 297       *
 298       * @since 6.7.0
 299       *
 300       * @see https://html.spec.whatwg.org/#the-after-after-frameset-insertion-mode
 301       * @see WP_HTML_Processor_State::$insertion_mode
 302       *
 303       * @var string
 304       */
 305      const INSERTION_MODE_AFTER_AFTER_FRAMESET = 'insertion-mode-after-after-frameset';
 306  
 307      /**
 308       * The stack of template insertion modes.
 309       *
 310       * @since 6.7.0
 311       *
 312       * @see https://html.spec.whatwg.org/#the-insertion-mode:stack-of-template-insertion-modes
 313       *
 314       * @var array<string>
 315       */
 316      public $stack_of_template_insertion_modes = array();
 317  
 318      /**
 319       * Tracks open elements while scanning HTML.
 320       *
 321       * This property is initialized in the constructor and never null.
 322       *
 323       * @since 6.4.0
 324       *
 325       * @see https://html.spec.whatwg.org/#stack-of-open-elements
 326       *
 327       * @var WP_HTML_Open_Elements
 328       */
 329      public $stack_of_open_elements;
 330  
 331      /**
 332       * Tracks open formatting elements, used to handle mis-nested formatting element tags.
 333       *
 334       * This property is initialized in the constructor and never null.
 335       *
 336       * @since 6.4.0
 337       *
 338       * @see https://html.spec.whatwg.org/#list-of-active-formatting-elements
 339       *
 340       * @var WP_HTML_Active_Formatting_Elements
 341       */
 342      public $active_formatting_elements;
 343  
 344      /**
 345       * Refers to the currently-matched tag, if any.
 346       *
 347       * @since 6.4.0
 348       *
 349       * @var WP_HTML_Token|null
 350       */
 351      public $current_token = null;
 352  
 353      /**
 354       * Tree construction insertion mode.
 355       *
 356       * @since 6.4.0
 357       *
 358       * @see https://html.spec.whatwg.org/#insertion-mode
 359       *
 360       * @var string
 361       */
 362      public $insertion_mode = self::INSERTION_MODE_INITIAL;
 363  
 364      /**
 365       * Context node initializing fragment parser, if created as a fragment parser.
 366       *
 367       * @since 6.4.0
 368       * @deprecated 6.8.0 WP_HTML_Processor tracks the context_node internally.
 369       *
 370       * @var null
 371       */
 372      public $context_node = null;
 373  
 374      /**
 375       * The recognized encoding of the input byte stream.
 376       *
 377       * > The stream of code points that comprises the input to the tokenization
 378       * > stage will be initially seen by the user agent as a stream of bytes
 379       * > (typically coming over the network or from the local file system).
 380       * > The bytes encode the actual characters according to a particular character
 381       * > encoding, which the user agent uses to decode the bytes into characters.
 382       *
 383       * @since 6.7.0
 384       *
 385       * @var string|null
 386       */
 387      public $encoding = null;
 388  
 389      /**
 390       * The parser's confidence in the input encoding.
 391       *
 392       * > When the HTML parser is decoding an input byte stream, it uses a character
 393       * > encoding and a confidence. The confidence is either tentative, certain, or
 394       * > irrelevant. The encoding used, and whether the confidence in that encoding
 395       * > is tentative or certain, is used during the parsing to determine whether to
 396       * > change the encoding. If no encoding is necessary, e.g. because the parser is
 397       * > operating on a Unicode stream and doesn't have to use a character encoding
 398       * > at all, then the confidence is irrelevant.
 399       *
 400       * @since 6.7.0
 401       *
 402       * @var string
 403       */
 404      public $encoding_confidence = 'tentative';
 405  
 406      /**
 407       * HEAD element pointer.
 408       *
 409       * @since 6.7.0
 410       *
 411       * @see https://html.spec.whatwg.org/multipage/parsing.html#head-element-pointer
 412       *
 413       * @var WP_HTML_Token|null
 414       */
 415      public $head_element = null;
 416  
 417      /**
 418       * FORM element pointer.
 419       *
 420       * > points to the last form element that was opened and whose end tag has
 421       * > not yet been seen. It is used to make form controls associate with
 422       * > forms in the face of dramatically bad markup, for historical reasons.
 423       * > It is ignored inside template elements.
 424       *
 425       * @todo This may be invalidated by a seek operation.
 426       *
 427       * @see https://html.spec.whatwg.org/#form-element-pointer
 428       *
 429       * @since 6.7.0
 430       *
 431       * @var WP_HTML_Token|null
 432       */
 433      public $form_element = null;
 434  
 435      /**
 436       * The frameset-ok flag indicates if a `FRAMESET` element is allowed in the current state.
 437       *
 438       * > The frameset-ok flag is set to "ok" when the parser is created. It is set to "not ok" after certain tokens are seen.
 439       *
 440       * @since 6.4.0
 441       *
 442       * @see https://html.spec.whatwg.org/#frameset-ok-flag
 443       *
 444       * @var bool
 445       */
 446      public $frameset_ok = true;
 447  
 448      /**
 449       * Constructor - creates a new and empty state value.
 450       *
 451       * @since 6.4.0
 452       *
 453       * @see WP_HTML_Processor
 454       */
 455  	public function __construct() {
 456          $this->stack_of_open_elements     = new WP_HTML_Open_Elements();
 457          $this->active_formatting_elements = new WP_HTML_Active_Formatting_Elements();
 458      }
 459  }