0
# HTML Constants and Utilities
1

2
HTML specification constants, enumerations, and utility functions that provide access to standardized HTML element names, namespace URIs, document modes, and other HTML5 specification details.
3

4
## Capabilities
5

6
### HTML Namespace
7

8
Complete HTML constants and utilities namespace providing access to all HTML specification details.
9

10
```typescript { .api }
11
/**
12
 * HTML namespace containing constants and utilities
13
 */
14
namespace html {
15
  // Core namespace and utility functions
16
}
17
```
18

19
### Namespace Constants
20

21
HTML namespace URIs defined by web standards.
22

23
```typescript { .api }
24
/**
25
 * Namespace URI constants
26
 */
27
enum NS {
28
  /** HTML namespace URI */
29
  HTML = 'http://www.w3.org/1999/xhtml',
30
  
31
  /** MathML namespace URI */
32
  MATHML = 'http://www.w3.org/1998/Math/MathML',
33
  
34
  /** SVG namespace URI */
35
  SVG = 'http://www.w3.org/2000/svg',
36
  
37
  /** XLink namespace URI */
38
  XLINK = 'http://www.w3.org/1999/xlink',
39
  
40
  /** XML namespace URI */
41
  XML = 'http://www.w3.org/XML/1998/namespace',
42
  
43
  /** XMLNS namespace URI */
44
  XMLNS = 'http://www.w3.org/2000/xmlns/'
45
}
46
```
47

48
**Usage Examples:**
49

50
```typescript
51
import { html } from "parse5";
52

53
// Check element namespace
54
function isHTMLElement(element: Element): boolean {
55
  return element.namespaceURI === html.NS.HTML;
56
}
57

58
function isSVGElement(element: Element): boolean {
59
  return element.namespaceURI === html.NS.SVG;
60
}
61

62
function isMathMLElement(element: Element): boolean {
63
  return element.namespaceURI === html.NS.MATHML;
64
}
65
```
66

67
### HTML Tag Names
68

69
Standardized HTML tag name constants.
70

71
```typescript { .api }
72
/**
73
 * HTML tag name constants
74
 */
75
enum TAG_NAMES {
76
  A = 'a',
77
  ADDRESS = 'address',
78
  ANNOTATION_XML = 'annotation-xml',
79
  APPLET = 'applet',
80
  AREA = 'area',
81
  ARTICLE = 'article',
82
  ASIDE = 'aside',
83
  B = 'b',
84
  BASE = 'base',
85
  BASEFONT = 'basefont',
86
  BGSOUND = 'bgsound',
87
  BIG = 'big',
88
  BLOCKQUOTE = 'blockquote',
89
  BODY = 'body',
90
  BR = 'br',
91
  BUTTON = 'button',
92
  CAPTION = 'caption',
93
  CENTER = 'center',
94
  CODE = 'code',
95
  COL = 'col',
96
  COLGROUP = 'colgroup',
97
  DD = 'dd',
98
  DESC = 'desc',
99
  DETAILS = 'details',
100
  DIALOG = 'dialog',
101
  DIR = 'dir',
102
  DIV = 'div',
103
  DL = 'dl',
104
  DT = 'dt',
105
  EM = 'em',
106
  EMBED = 'embed',
107
  FIELDSET = 'fieldset',
108
  FIGCAPTION = 'figcaption',
109
  FIGURE = 'figure',
110
  FONT = 'font',
111
  FOOTER = 'footer',
112
  FOREIGN_OBJECT = 'foreignObject',
113
  FORM = 'form',
114
  FRAME = 'frame',
115
  FRAMESET = 'frameset',
116
  H1 = 'h1',
117
  H2 = 'h2',
118
  H3 = 'h3',
119
  H4 = 'h4',
120
  H5 = 'h5',
121
  H6 = 'h6',
122
  HEAD = 'head',
123
  HEADER = 'header',
124
  HGROUP = 'hgroup',
125
  HR = 'hr',
126
  HTML = 'html',
127
  I = 'i',
128
  IMG = 'img',
129
  IMAGE = 'image',
130
  INPUT = 'input',
131
  IFRAME = 'iframe',
132
  KEYGEN = 'keygen',
133
  LABEL = 'label',
134
  LI = 'li',
135
  LINK = 'link',
136
  LISTING = 'listing',
137
  MAIN = 'main',
138
  MALIGNMARK = 'malignmark',
139
  MARQUEE = 'marquee',
140
  MATH = 'math',
141
  MENU = 'menu',
142
  META = 'meta',
143
  MGLYPH = 'mglyph',
144
  MI = 'mi',
145
  MO = 'mo',
146
  MN = 'mn',
147
  MS = 'ms',
148
  MTEXT = 'mtext',
149
  NAV = 'nav',
150
  NOBR = 'nobr',
151
  NOFRAMES = 'noframes',
152
  NOEMBED = 'noembed',
153
  NOSCRIPT = 'noscript',
154
  OBJECT = 'object',
155
  OL = 'ol',
156
  OPTGROUP = 'optgroup',
157
  OPTION = 'option',
158
  P = 'p',
159
  PARAM = 'param',
160
  PICTURE = 'picture',
161
  PLAINTEXT = 'plaintext',
162
  PRE = 'pre',
163
  RB = 'rb',
164
  RP = 'rp',
165
  RT = 'rt',
166
  RTC = 'rtc',
167
  RUBY = 'ruby',
168
  S = 's',
169
  SCRIPT = 'script',
170
  SEARCH = 'search',
171
  SECTION = 'section',
172
  SELECT = 'select',
173
  SOURCE = 'source',
174
  SMALL = 'small',
175
  SPAN = 'span',
176
  STRIKE = 'strike',
177
  STRONG = 'strong',
178
  STYLE = 'style',
179
  SUB = 'sub',
180
  SUMMARY = 'summary',
181
  SUP = 'sup',
182
  TABLE = 'table',
183
  TBODY = 'tbody',
184
  TEMPLATE = 'template',
185
  TEXTAREA = 'textarea',
186
  TFOOT = 'tfoot',
187
  TD = 'td',
188
  TH = 'th',
189
  THEAD = 'thead',
190
  TITLE = 'title',
191
  TR = 'tr',
192
  TRACK = 'track',
193
  TT = 'tt',
194
  U = 'u',
195
  UL = 'ul',
196
  SVG = 'svg',
197
  VAR = 'var',
198
  WBR = 'wbr',
199
  XMP = 'xmp'
200
}
201
```
202

203
### HTML Tag IDs
204

205
Numerical tag identifiers for efficient tag comparison.
206

207
```typescript { .api }
208
/**
209
 * HTML tag ID enumeration for efficient comparison
210
 */
211
enum TAG_ID {
212
  UNKNOWN = 0,
213
  A = 1,
214
  ADDRESS = 2,
215
  ANNOTATION_XML = 3,
216
  APPLET = 4,
217
  AREA = 5,
218
  ARTICLE = 6,
219
  ASIDE = 7,
220
  B = 8,
221
  BASE = 9,
222
  BASEFONT = 10,
223
  BGSOUND = 11,
224
  BIG = 12,
225
  BLOCKQUOTE = 13,
226
  BODY = 14,
227
  BR = 15,
228
  BUTTON = 16,
229
  CAPTION = 17,
230
  CENTER = 18,
231
  CODE = 19,
232
  COL = 20,
233
  COLGROUP = 21,
234
  DD = 22,
235
  DESC = 23,
236
  DETAILS = 24,
237
  DIALOG = 25,
238
  DIR = 26,
239
  DIV = 27,
240
  DL = 28,
241
  DT = 29,
242
  EM = 30,
243
  EMBED = 31,
244
  FIELDSET = 32,
245
  FIGCAPTION = 33,
246
  FIGURE = 34,
247
  FONT = 35,
248
  FOOTER = 36,
249
  FOREIGN_OBJECT = 37,
250
  FORM = 38,
251
  FRAME = 39,
252
  FRAMESET = 40,
253
  H1 = 41,
254
  H2 = 42,
255
  H3 = 43,
256
  H4 = 44,
257
  H5 = 45,
258
  H6 = 46,
259
  HEAD = 47,
260
  HEADER = 48,
261
  HGROUP = 49,
262
  HR = 50,
263
  HTML = 51,
264
  I = 52,
265
  IMG = 53,
266
  IMAGE = 54,
267
  INPUT = 55,
268
  IFRAME = 56,
269
  KEYGEN = 57,
270
  LABEL = 58,
271
  LI = 59,
272
  LINK = 60,
273
  LISTING = 61,
274
  MAIN = 62,
275
  MALIGNMARK = 63,
276
  MARQUEE = 64,
277
  MATH = 65,
278
  MENU = 66,
279
  META = 67,
280
  MGLYPH = 68,
281
  MI = 69,
282
  MO = 70,
283
  MN = 71,
284
  MS = 72,
285
  MTEXT = 73,
286
  NAV = 74,
287
  NOBR = 75,
288
  NOFRAMES = 76,
289
  NOEMBED = 77,
290
  NOSCRIPT = 78,
291
  OBJECT = 79,
292
  OL = 80,
293
  OPTGROUP = 81,
294
  OPTION = 82,
295
  P = 83,
296
  PARAM = 84,
297
  PICTURE = 85,
298
  PLAINTEXT = 86,
299
  PRE = 87,
300
  RB = 88,
301
  RP = 89,
302
  RT = 90,
303
  RTC = 91,
304
  RUBY = 92,
305
  S = 93,
306
  SCRIPT = 94,
307
  SEARCH = 95,
308
  SECTION = 96,
309
  SELECT = 97,
310
  SOURCE = 98,
311
  SMALL = 99,
312
  SPAN = 100,
313
  STRIKE = 101,
314
  STRONG = 102,
315
  STYLE = 103,
316
  SUB = 104,
317
  SUMMARY = 105,
318
  SUP = 106,
319
  TABLE = 107,
320
  TBODY = 108,
321
  TEMPLATE = 109,
322
  TEXTAREA = 110,
323
  TFOOT = 111,
324
  TD = 112,
325
  TH = 113,
326
  THEAD = 114,
327
  TITLE = 115,
328
  TR = 116,
329
  TRACK = 117,
330
  TT = 118,
331
  U = 119,
332
  UL = 120,
333
  SVG = 121,
334
  VAR = 122,
335
  WBR = 123,
336
  XMP = 124
337
}
338
```
339

340
### Document Mode Constants
341

342
HTML document mode enumeration for quirks mode handling.
343

344
```typescript { .api }
345
/**
346
 * Document mode constants for quirks mode handling
347
 */
348
enum DOCUMENT_MODE {
349
  /** Standards mode (no quirks) */
350
  NO_QUIRKS = 'no-quirks',
351
  
352
  /** Quirks mode */
353
  QUIRKS = 'quirks',
354
  
355
  /** Limited quirks mode */
356
  LIMITED_QUIRKS = 'limited-quirks'
357
}
358
```
359

360
### HTML Attributes
361

362
Common HTML attribute name constants.
363

364
```typescript { .api }
365
/**
366
 * Common HTML attribute name constants
367
 */
368
enum ATTRS {
369
  TYPE = 'type',
370
  ACTION = 'action',
371
  ENCODING = 'encoding',
372
  PROMPT = 'prompt',
373
  NAME = 'name',
374
  COLOR = 'color',
375
  FACE = 'face',
376
  SIZE = 'size',
377
  CLASS = 'class',
378
  ID = 'id',
379
  STYLE = 'style',
380
  LANG = 'lang',
381
  DIR = 'dir',
382
  TITLE = 'title',
383
  ALT = 'alt',
384
  SRC = 'src',
385
  HREF = 'href',
386
  REL = 'rel',
387
  MEDIA = 'media',
388
  CHARSET = 'charset',
389
  CONTENT = 'content',
390
  HTTP_EQUIV = 'http-equiv',
391
  VALUE = 'value',
392
  CHECKED = 'checked',
393
  SELECTED = 'selected',
394
  DISABLED = 'disabled',
395
  READONLY = 'readonly',
396
  MULTIPLE = 'multiple',
397
  HIDDEN = 'hidden',
398
  REQUIRED = 'required',
399
  AUTOFOCUS = 'autofocus',
400
  PLACEHOLDER = 'placeholder',
401
  PATTERN = 'pattern',
402
  MIN = 'min',
403
  MAX = 'max',
404
  STEP = 'step',
405
  MAXLENGTH = 'maxlength',
406
  MINLENGTH = 'minlength',
407
  COLS = 'cols',
408
  ROWS = 'rows',
409
  WRAP = 'wrap',
410
  ACCEPT = 'accept',
411
  ACCEPT_CHARSET = 'accept-charset',
412
  ACCESSKEY = 'accesskey',
413
  CONTENTEDITABLE = 'contenteditable',
414
  CONTEXTMENU = 'contextmenu',
415
  CONTROLS = 'controls',
416
  COORDS = 'coords',
417
  CROSSORIGIN = 'crossorigin',
418
  DATA = 'data',
419
  DATETIME = 'datetime',
420
  DEFAULT = 'default',
421
  DEFER = 'defer',
422
  DRAGGABLE = 'draggable',
423
  DROPZONE = 'dropzone',
424
  ENCTYPE = 'enctype',
425
  FOR = 'for',
426
  FORM = 'form',
427
  FORMACTION = 'formaction',
428
  FORMENCTYPE = 'formenctype',
429
  FORMMETHOD = 'formmethod',
430
  FORMNOVALIDATE = 'formnovalidate',
431
  FORMTARGET = 'formtarget',
432
  FRAMEBORDER = 'frameborder',
433
  HEADERS = 'headers',
434
  HEIGHT = 'height',
435
  HIGH = 'high',
436
  HREFLANG = 'hreflang',
437
  ICON = 'icon',
438
  ISMAP = 'ismap',
439
  ITEMID = 'itemid',
440
  ITEMPROP = 'itemprop',
441
  ITEMREF = 'itemref',
442
  ITEMSCOPE = 'itemscope',
443
  ITEMTYPE = 'itemtype',
444
  KIND = 'kind',
445
  LABEL = 'label',
446
  LIST = 'list',
447
  LOOP = 'loop',
448
  LOW = 'low',
449
  MANIFEST = 'manifest',
450
  MARGINHEIGHT = 'marginheight',
451
  MARGINWIDTH = 'marginwidth',
452
  METHOD = 'method',
453
  MUTED = 'muted',
454
  NOVALIDATE = 'novalidate',
455
  OPEN = 'open',
456
  OPTIMUM = 'optimum',
457
  PING = 'ping',
458
  POSTER = 'poster',
459
  PRELOAD = 'preload',
460
  RADIOGROUP = 'radiogroup',
461
  REVERSED = 'reversed',
462
  ROLE = 'role',
463
  SANDBOX = 'sandbox',
464
  SCOPE = 'scope',
465
  SCOPED = 'scoped',
466
  SEAMLESS = 'seamless',
467
  SHAPE = 'shape',
468
  SIZES = 'sizes',
469
  SPAN = 'span',
470
  SPELLCHECK = 'spellcheck',
471
  SRCDOC = 'srcdoc',
472
  SRCLANG = 'srclang',
473
  SRCSET = 'srcset',
474
  START = 'start',
475
  TABINDEX = 'tabindex',
476
  TARGET = 'target',
477
  TRANSLATE = 'translate',
478
  USEMAP = 'usemap',
479
  WIDTH = 'width'
480
}
481
```
482

483
### HTML Utility Functions
484

485
Utility functions for HTML processing and tag identification.
486

487
```typescript { .api }
488
/**
489
 * Get numeric tag ID from tag name string
490
 * @param tagName - HTML tag name
491
 * @returns Corresponding TAG_ID or TAG_ID.UNKNOWN
492
 */
493
function getTagID(tagName: string): TAG_ID;
494

495
/**
496
 * Check if a tag contains unescaped text content
497
 * @param tagName - HTML tag name
498
 * @param scriptingEnabled - Whether scripting is enabled
499
 * @returns True if tag contains unescaped text
500
 */
501
function hasUnescapedText(tagName: string, scriptingEnabled: boolean): boolean;
502
```
503

504
**Usage Examples:**
505

506
```typescript
507
import { html } from "parse5";
508

509
// Get tag ID for efficient comparison
510
const divTagId = html.getTagID('div');
511
const spanTagId = html.getTagID('span');
512

513
if (divTagId === html.TAG_ID.DIV) {
514
  console.log('Found div tag');
515
}
516

517
// Check if tag has unescaped text content
518
const hasUnescaped = html.hasUnescapedText('script', true);
519
console.log('Script has unescaped text:', hasUnescaped); // true
520

521
// Use tag name constants
522
function isHeadingTag(tagName: string): boolean {
523
  return [
524
    html.TAG_NAMES.H1,
525
    html.TAG_NAMES.H2,
526
    html.TAG_NAMES.H3,
527
    html.TAG_NAMES.H4,
528
    html.TAG_NAMES.H5,
529
    html.TAG_NAMES.H6
530
  ].includes(tagName as any);
531
}
532

533
// Use attribute constants
534
function hasRequiredClass(element: Element): boolean {
535
  const className = element.getAttribute(html.ATTRS.CLASS);
536
  return className?.includes('required') ?? false;
537
}
538

539
// Use namespace constants
540
function createElement(tagName: string, namespace = html.NS.HTML): Element {
541
  return document.createElementNS(namespace, tagName);
542
}
543
```
544

545
## HTML Specification Compliance Patterns
546

547
### Tag Validation
548

549
```typescript
550
import { html } from "parse5";
551

552
class HTMLValidator {
553
  private voidElements = new Set([
554
    html.TAG_ID.AREA, html.TAG_ID.BASE, html.TAG_ID.BR,
555
    html.TAG_ID.COL, html.TAG_ID.EMBED, html.TAG_ID.HR,
556
    html.TAG_ID.IMG, html.TAG_ID.INPUT, html.TAG_ID.LINK,
557
    html.TAG_ID.META, html.TAG_ID.PARAM, html.TAG_ID.SOURCE,
558
    html.TAG_ID.TRACK, html.TAG_ID.WBR
559
  ]);
560

561
  isVoidElement(tagName: string): boolean {
562
    const tagId = html.getTagID(tagName);
563
    return this.voidElements.has(tagId);
564
  }
565

566
  isBlockElement(tagName: string): boolean {
567
    const tagId = html.getTagID(tagName);
568
    const blockElements = new Set([
569
      html.TAG_ID.DIV, html.TAG_ID.P, html.TAG_ID.H1,
570
      html.TAG_ID.H2, html.TAG_ID.H3, html.TAG_ID.H4,
571
      html.TAG_ID.H5, html.TAG_ID.H6, html.TAG_ID.HEADER,
572
      html.TAG_ID.FOOTER, html.TAG_ID.SECTION, html.TAG_ID.ARTICLE,
573
      html.TAG_ID.ASIDE, html.TAG_ID.NAV, html.TAG_ID.MAIN
574
    ]);
575
    return blockElements.has(tagId);
576
  }
577

578
  isInlineElement(tagName: string): boolean {
579
    const tagId = html.getTagID(tagName);
580
    const inlineElements = new Set([
581
      html.TAG_ID.SPAN, html.TAG_ID.A, html.TAG_ID.STRONG,
582
      html.TAG_ID.EM, html.TAG_ID.CODE, html.TAG_ID.B,
583
      html.TAG_ID.I, html.TAG_ID.U, html.TAG_ID.S
584
    ]);
585
    return inlineElements.has(tagId);
586
  }
587
}
588
```
589

590
### Namespace-Aware Element Creation
591

592
```typescript
593
import { html } from "parse5";
594

595
class NamespaceAwareBuilder {
596
  createElement(tagName: string, namespace?: string): Element {
597
    // Determine namespace based on tag name if not provided
598
    if (!namespace) {
599
      if (tagName === html.TAG_NAMES.SVG) {
600
        namespace = html.NS.SVG;
601
      } else if (tagName === html.TAG_NAMES.MATH) {
602
        namespace = html.NS.MATHML;
603
      } else {
604
        namespace = html.NS.HTML;
605
      }
606
    }
607

608
    return document.createElementNS(namespace, tagName);
609
  }
610

611
  createSVGElement(tagName: string): Element {
612
    return this.createElement(tagName, html.NS.SVG);
613
  }
614

615
  createMathMLElement(tagName: string): Element {
616
    return this.createElement(tagName, html.NS.MATHML);
617
  }
618

619
  isForeignElement(element: Element): boolean {
620
    return element.namespaceURI !== html.NS.HTML;
621
  }
622
}
623
```
624

625
### Document Mode Detection
626

627
```typescript
628
import { html } from "parse5";
629

630
class DocumentModeDetector {
631
  detectMode(doctype: string | null): html.DOCUMENT_MODE {
632
    if (!doctype) {
633
      return html.DOCUMENT_MODE.QUIRKS;
634
    }
635

636
    const doctypeLower = doctype.toLowerCase();
637
    
638
    // HTML5 doctype
639
    if (doctypeLower === '<!doctype html>') {
640
      return html.DOCUMENT_MODE.NO_QUIRKS;
641
    }
642

643
    // Legacy doctypes that trigger quirks mode
644
    const quirksPatterns = [
645
      'html 4.01 transitional',
646
      'html 4.01 frameset',
647
      'xhtml 1.0 transitional',
648
      'xhtml 1.0 frameset'
649
    ];
650

651
    if (quirksPatterns.some(pattern => doctypeLower.includes(pattern))) {
652
      return html.DOCUMENT_MODE.LIMITED_QUIRKS;
653
    }
654

655
    // Default to no-quirks for unrecognized doctypes
656
    return html.DOCUMENT_MODE.NO_QUIRKS;
657
  }
658

659
  applyQuirksMode(mode: html.DOCUMENT_MODE): void {
660
    switch (mode) {
661
      case html.DOCUMENT_MODE.QUIRKS:
662
        console.log('Applying full quirks mode');
663
        break;
664
      case html.DOCUMENT_MODE.LIMITED_QUIRKS:
665
        console.log('Applying limited quirks mode');
666
        break;
667
      case html.DOCUMENT_MODE.NO_QUIRKS:
668
        console.log('Applying standards mode');
669
        break;
670
    }
671
  }
672
}
673
```
674

675
### Attribute Processing
676

677
```typescript
678
import { html } from "parse5";
679

680
class AttributeProcessor {
681
  private booleanAttributes = new Set([
682
    html.ATTRS.CHECKED, html.ATTRS.SELECTED, html.ATTRS.DISABLED,
683
    html.ATTRS.READONLY, html.ATTRS.MULTIPLE, html.ATTRS.HIDDEN,
684
    html.ATTRS.REQUIRED, html.ATTRS.AUTOFOCUS, html.ATTRS.DEFER,
685
    html.ATTRS.ASYNC, html.ATTRS.CONTROLS, html.ATTRS.LOOP,
686
    html.ATTRS.MUTED, html.ATTRS.OPEN, html.ATTRS.REVERSED
687
  ]);
688

689
  isBooleanAttribute(name: string): boolean {
690
    return this.booleanAttributes.has(name as any);
691
  }
692

693
  normalizeAttributeValue(name: string, value: string): string | boolean {
694
    if (this.isBooleanAttribute(name)) {
695
      // Boolean attributes: presence = true, absence = false
696
      return value !== null;
697
    }
698

699
    // Standard attributes
700
    return value;
701
  }
702

703
  validateAttribute(tagName: string, attrName: string, attrValue: string): boolean {
704
    const tagId = html.getTagID(tagName);
705

706
    // Example validation rules
707
    switch (tagId) {
708
      case html.TAG_ID.IMG:
709
        if (attrName === html.ATTRS.SRC) {
710
          return attrValue.length > 0;
711
        }
712
        if (attrName === html.ATTRS.ALT) {
713
          return true; // Alt can be empty
714
        }
715
        break;
716

717
      case html.TAG_ID.A:
718
        if (attrName === html.ATTRS.HREF) {
719
          return attrValue.length > 0;
720
        }
721
        break;
722

723
      case html.TAG_ID.INPUT:
724
        if (attrName === html.ATTRS.TYPE) {
725
          const validTypes = ['text', 'password', 'email', 'number', 'checkbox', 'radio', 'submit', 'button'];
726
          return validTypes.includes(attrValue);
727
        }
728
        break;
729
    }
730

731
    return true; // Default to valid
732
  }
733
}
734
```