code.angularjs.org/1.2.8/angular-sanitize.js at master · angular/code.angularjs.org · GitHub

This repository was archived by the owner on Apr 17, 2025. It is now read-only.

History

622 lines (555 loc) · 19.9 KB

Raw

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

396

397

398

399

400

401

402

403

404

405

406

407

408

409

410

411

412

413

414

415

416

417

418

419

420

421

422

423

424

425

426

427

428

429

430

431

432

433

434

435

436

437

438

439

440

441

442

443

444

445

446

447

448

449

450

451

452

453

454

455

456

457

458

459

460

461

462

463

464

465

466

467

468

469

470

471

472

473

474

475

476

477

478

479

480

481

482

483

484

485

486

487

488

489

490

491

492

493

494

495

496

497

498

499

500

501

502

503

504

505

506

507

508

509

510

511

512

513

514

515

516

517

518

519

520

521

522

523

524

525

526

527

528

529

530

531

532

533

534

535

536

537

538

539

540

541

542

543

544

545

546

547

548

549

550

551

552

553

554

555

556

557

558

559

560

561

562

563

564

565

566

567

568

569

570

571

572

573

574

575

576

577

578

579

580

581

582

583

584

585

586

587

588

589

590

591

592

593

594

595

596

597

598

599

600

601

602

603

604

605

606

607

608

609

610

611

612

613

614

615

616

617

618

619

620

621

622

/**

* @license AngularJS v1.2.8

* License: MIT

(function(window, angular, undefined) {'use strict';

var $sanitizeMinErr = angular.$$minErr('$sanitize');

/**

* @ngdoc overview

* @name ngSanitize

* @description

* # ngSanitize

* The `ngSanitize` module provides functionality to sanitize HTML.

* {@installModule sanitize}

* <div doc-module-components="ngSanitize"></div>

* See {@link ngSanitize.$sanitize `$sanitize`} for usage.

* HTML Parser By Misko Hevery (misko@hevery.com)

* based on: HTML Parser By John Resig (ejohn.org)

* Original code by Erik Arvidsson, Mozilla Public License

* http://erik.eae.net/simplehtmlparser/simplehtmlparser.js

* // Use like so:

* htmlParser(htmlString, {

* start: function(tag, attrs, unary) {},

* end: function(tag) {},

* chars: function(text) {},

* comment: function(text) {}

* });

/**

* @ngdoc service

* @name ngSanitize.$sanitize

* @function

* @description

* The input is sanitized by parsing the html into tokens. All safe tokens (from a whitelist) are

* then serialized back to properly escaped html string. This means that no unsafe input can make

* it into the returned string, however, since our parser is more strict than a typical browser

* parser, it's possible that some obscure input, which would be recognized as valid HTML by a

* browser, won't make it through the sanitizer.

* The whitelist is configured using the functions `aHrefSanitizationWhitelist` and

* `imgSrcSanitizationWhitelist` of {@link ng.$compileProvider `$compileProvider`}.

* @param {string} html Html input.

* @returns {string} Sanitized html.

* @example

<doc:example module="ngSanitize">

<doc:source>

function Ctrl($scope, $sce) {

$scope.snippet =

'<p style="color:blue">an html\n' +

'<em onmouseover="this.textContent=\'PWN3D!\'">click here</em>\n' +

'snippet</p>';

$scope.deliberatelyTrustDangerousSnippet = function() {

return $sce.trustAsHtml($scope.snippet);

};

}

</script>

Snippet: <textarea ng-model="snippet" cols="60" rows="3"></textarea>

<table>

<tr>

<td>Directive</td>

<td>Source</td>

<td>Rendered</td>

</tr>

<td>Automatically uses $sanitize</td>

</tr>

<td>Bypass $sanitize by explicitly trusting the dangerous value</td>

<td>

</div></pre>

</td>

</tr>

<td>Automatically escapes</td>

</tr>

</table>

</div>

</doc:source>

<doc:scenario>

it('should sanitize the html snippet by default', function() {

expect(using('#bind-html-with-sanitize').element('div').html()).

toBe('<p>an html\n<em>click here</em>\nsnippet</p>');

});

it('should inline raw snippet if bound to a trusted value', function() {

expect(using('#bind-html-with-trust').element("div").html()).

toBe("<p style=\"color:blue\">an html\n" +

"<em onmouseover=\"this.textContent='PWN3D!'\">click here</em>\n" +

"snippet</p>");

});

it('should escape snippet without any filter', function() {

expect(using('#bind-default').element('div').html()).

toBe("<p style=\"color:blue\">an html\n" +

"<em onmouseover=\"this.textContent='PWN3D!'\">click here</em>\n" +

"snippet</p>");

});

it('should update', function() {

input('snippet').enter('new <b onclick="alert(1)">text</b>');

expect(using('#bind-html-with-sanitize').element('div').html()).toBe('new <b>text</b>');

expect(using('#bind-html-with-trust').element('div').html()).toBe(

'new <b onclick="alert(1)">text</b>');

expect(using('#bind-default').element('div').html()).toBe(

"new <b onclick=\"alert(1)\">text</b>");

});

</doc:scenario>

</doc:example>

function $SanitizeProvider() {

this.$get = ['$$sanitizeUri', function($$sanitizeUri) {

return function(html) {

var buf = [];

htmlParser(html, htmlSanitizeWriter(buf, function(uri, isImage) {

return !/^unsafe/.test($$sanitizeUri(uri, isImage));

}));

return buf.join('');

};

}];

}

function sanitizeText(chars) {

var buf = [];

var writer = htmlSanitizeWriter(buf, angular.noop);

writer.chars(chars);

return buf.join('');

}

// Regular Expressions for parsing tags and attributes

var START_TAG_REGEXP =

/^<\s*([\w:-]+)((?:\s+[\w:-]+(?:\s*=\s*(?:(?:"[^"]*")|(?:'[^']*')|[^>\s]+))?)*)\s*(\/?)\s*>/,

END_TAG_REGEXP = /^<\s*\/\s*([\w:-]+)[^>]*>/,

ATTR_REGEXP = /([\w:-]+)(?:\s*=\s*(?:(?:"((?:[^"])*)")|(?:'((?:[^'])*)')|([^>\s]+)))?/g,

BEGIN_TAG_REGEXP = /^</,

BEGING_END_TAGE_REGEXP = /^<\s*\//,

COMMENT_REGEXP = //g,

DOCTYPE_REGEXP = /<!DOCTYPE([^>]*?)>/i,

CDATA_REGEXP = /<!\[CDATA\[(.*?)]]>/g,

// Match everything outside of normal chars and " (quote character)

NON_ALPHANUMERIC_REGEXP = /([^\#-~| |!])/g;

// Good source of info about elements and attributes

// http://dev.w3.org/html5/spec/Overview.html#semantics

// http://simon.html5.org/html-elements

// Safe Void Elements - HTML5

// http://dev.w3.org/html5/spec/Overview.html#void-elements

var voidElements = makeMap("area,br,col,hr,img,wbr");

// Elements that you can, intentionally, leave open (and which close themselves)

// http://dev.w3.org/html5/spec/Overview.html#optional-tags

var optionalEndTagBlockElements = makeMap("colgroup,dd,dt,li,p,tbody,td,tfoot,th,thead,tr"),

optionalEndTagInlineElements = makeMap("rp,rt"),

optionalEndTagElements = angular.extend({},

optionalEndTagInlineElements,

optionalEndTagBlockElements);

// Safe Block Elements - HTML5

var blockElements = angular.extend({}, optionalEndTagBlockElements, makeMap("address,article," +

"aside,blockquote,caption,center,del,dir,div,dl,figure,figcaption,footer,h1,h2,h3,h4,h5," +

"h6,header,hgroup,hr,ins,map,menu,nav,ol,pre,script,section,table,ul"));

// Inline Elements - HTML5

var inlineElements = angular.extend({}, optionalEndTagInlineElements, makeMap("a,abbr,acronym,b," +

"bdi,bdo,big,br,cite,code,del,dfn,em,font,i,img,ins,kbd,label,map,mark,q,ruby,rp,rt,s," +

"samp,small,span,strike,strong,sub,sup,time,tt,u,var"));

// Special Elements (can contain anything)

var specialElements = makeMap("script,style");

var validElements = angular.extend({},

voidElements,

blockElements,

inlineElements,

optionalEndTagElements);

//Attributes that have href and hence need to be sanitized

var uriAttrs = makeMap("background,cite,href,longdesc,src,usemap");

var validAttrs = angular.extend({}, uriAttrs, makeMap(

'abbr,align,alt,axis,bgcolor,border,cellpadding,cellspacing,class,clear,'+

'color,cols,colspan,compact,coords,dir,face,headers,height,hreflang,hspace,'+

'ismap,lang,language,nohref,nowrap,rel,rev,rows,rowspan,rules,'+

'scope,scrolling,shape,size,span,start,summary,target,title,type,'+

'valign,value,vspace,width'));

function makeMap(str) {

var obj = {}, items = str.split(','), i;

for (i = 0; i < items.length; i++) obj[items[i]] = true;

return obj;

}

/**

* @example

* htmlParser(htmlString, {

* start: function(tag, attrs, unary) {},

* end: function(tag) {},

* chars: function(text) {},

* comment: function(text) {}

* });

* @param {string} html string

* @param {object} handler

function htmlParser( html, handler ) {

var index, chars, match, stack = [], last = html;

stack.last = function() { return stack[ stack.length - 1 ]; };

while ( html ) {

chars = true;

// Make sure we're not in a script or style element

if ( !stack.last() || !specialElements[ stack.last() ] ) {

// Comment

if ( html.indexOf("<!--") === 0 ) {

// comments containing -- are not allowed unless they terminate the comment

index = html.indexOf("--", 4);

if ( index >= 0 && html.lastIndexOf("-->", index) === index) {

if (handler.comment) handler.comment( html.substring( 4, index ) );

html = html.substring( index + 3 );

chars = false;

}

// DOCTYPE

} else if ( DOCTYPE_REGEXP.test(html) ) {

match = html.match( DOCTYPE_REGEXP );

if ( match ) {

html = html.replace( match[0] , '');

chars = false;

}

// end tag

} else if ( BEGING_END_TAGE_REGEXP.test(html) ) {

match = html.match( END_TAG_REGEXP );

if ( match ) {

html = html.substring( match[0].length );

match[0].replace( END_TAG_REGEXP, parseEndTag );

chars = false;

}

// start tag

} else if ( BEGIN_TAG_REGEXP.test(html) ) {

match = html.match( START_TAG_REGEXP );

if ( match ) {

html = html.substring( match[0].length );

match[0].replace( START_TAG_REGEXP, parseStartTag );

chars = false;

}

if ( chars ) {

index = html.indexOf("<");

var text = index < 0 ? html : html.substring( 0, index );

html = index < 0 ? "" : html.substring( index );

if (handler.chars) handler.chars( decodeEntities(text) );

}

} else {

html = html.replace(new RegExp("(.*)<\\s*\\/\\s*" + stack.last() + "[^>]*>", 'i'),

function(all, text){

text = text.replace(COMMENT_REGEXP, "$1").replace(CDATA_REGEXP, "$1");

if (handler.chars) handler.chars( decodeEntities(text) );

return "";

});

parseEndTag( "", stack.last() );

}

if ( html == last ) {

throw $sanitizeMinErr('badparse', "The sanitizer was unable to parse the following block " +

"of html: {0}", html);

}

last = html;

}

// Clean up any remaining tags

parseEndTag();

function parseStartTag( tag, tagName, rest, unary ) {

tagName = angular.lowercase(tagName);

if ( blockElements[ tagName ] ) {

while ( stack.last() && inlineElements[ stack.last() ] ) {

parseEndTag( "", stack.last() );

}

if ( optionalEndTagElements[ tagName ] && stack.last() == tagName ) {

parseEndTag( "", tagName );

}

unary = voidElements[ tagName ] || !!unary;

if ( !unary )

stack.push( tagName );

var attrs = {};

rest.replace(ATTR_REGEXP,

function(match, name, doubleQuotedValue, singleQuotedValue, unquotedValue) {

var value = doubleQuotedValue

|| singleQuotedValue

|| unquotedValue

|| '';

attrs[name] = decodeEntities(value);

});

if (handler.start) handler.start( tagName, attrs, unary );

}

function parseEndTag( tag, tagName ) {

var pos = 0, i;

tagName = angular.lowercase(tagName);

if ( tagName )

// Find the closest opened tag of the same type

for ( pos = stack.length - 1; pos >= 0; pos-- )

if ( stack[ pos ] == tagName )

break;

if ( pos >= 0 ) {

// Close all the open elements, up the stack

for ( i = stack.length - 1; i >= pos; i-- )

if (handler.end) handler.end( stack[ i ] );

// Remove the open elements from the stack

stack.length = pos;

}

var hiddenPre=document.createElement("pre");

var spaceRe = /^(\s*)([\s\S]*?)(\s*)$/;

/**

* decodes all entities into regular string

* @param value

* @returns {string} A string with decoded entities.

function decodeEntities(value) {

if (!value) { return ''; }

// Note: IE8 does not preserve spaces at the start/end of innerHTML

// so we must capture them and reattach them afterward

var parts = spaceRe.exec(value);

var spaceBefore = parts[1];

var spaceAfter = parts[3];

var content = parts[2];

if (content) {

hiddenPre.innerHTML=content.replace(/</g,"<");

// innerText depends on styling as it doesn't display hidden elements.

// Therefore, it's better to use textContent not to cause unnecessary

// reflows. However, IE<9 don't support textContent so the innerText

// fallback is necessary.

content = 'textContent' in hiddenPre ?

hiddenPre.textContent : hiddenPre.innerText;

}

return spaceBefore + content + spaceAfter;

}

/**

* Escapes all potentially dangerous characters, so that the

* resulting string can be safely inserted into attribute or

* element text.

* @param value

* @returns escaped text

function encodeEntities(value) {

return value.

replace(/&/g, '&').

replace(NON_ALPHANUMERIC_REGEXP, function(value){

return '&#' + value.charCodeAt(0) + ';';

}).

replace(/</g, '<').

replace(/>/g, '>');

}

/**

* create an HTML/XML writer which writes to buffer

* @param {Array} buf use buf.jain('') to get out sanitized html string

* @returns {object} in the form of {

* start: function(tag, attrs, unary) {},

* end: function(tag) {},

* chars: function(text) {},

* comment: function(text) {}

* }

function htmlSanitizeWriter(buf, uriValidator){

var ignore = false;

var out = angular.bind(buf, buf.push);

return {

start: function(tag, attrs, unary){

tag = angular.lowercase(tag);

if (!ignore && specialElements[tag]) {

ignore = tag;

}

if (!ignore && validElements[tag] === true) {

out('<');

out(tag);

angular.forEach(attrs, function(value, key){

var lkey=angular.lowercase(key);

var isImage = (tag === 'img' && lkey === 'src') || (lkey === 'background');

if (validAttrs[lkey] === true &&

(uriAttrs[lkey] !== true || uriValidator(value, isImage))) {

out(' ');

out(key);

out('="');

out(encodeEntities(value));

out('"');

}

});

out(unary ? '/>' : '>');

}

end: function(tag){

tag = angular.lowercase(tag);

if (!ignore && validElements[tag] === true) {

out('</');

out(tag);

out('>');

}

if (tag == ignore) {

ignore = false;

}

chars: function(chars){

if (!ignore) {

out(encodeEntities(chars));

}

};

}

// define ngSanitize module and register $sanitize service

angular.module('ngSanitize', []).provider('$sanitize', $SanitizeProvider);

/* global sanitizeText: false */

/**

* @ngdoc filter

* @name ngSanitize.filter:linky

* @function

* @description

* Finds links in text input and turns them into html links. Supports http/https/ftp/mailto and

* plain email address links.

* Requires the {@link ngSanitize `ngSanitize`} module to be installed.

* @param {string} text Input text.

* @param {string} target Window (_blank|_self|_parent|_top) or named frame to open links in.

* @returns {string} Html-linkified text.

* @usage

* @example

<doc:example module="ngSanitize">

<doc:source>

function Ctrl($scope) {

$scope.snippet =

'Pretty text with some links:\n'+

'http://angularjs.org/,\n'+

'mailto:us@somewhere.org,\n'+

'another@somewhere.org,\n'+

'and one more: ftp://127.0.0.1/.';

$scope.snippetWithTarget = 'http://angularjs.org/';

}

</script>

Snippet: <textarea ng-model="snippet" cols="60" rows="3"></textarea>

<table>

<tr>

<td>Filter</td>

<td>Source</td>

<td>Rendered</td>

</tr>

<td>linky filter</td>

<td>

</td>

<td>

</td>

</tr>

<td>linky target</td>

<td>

</td>

<td>

</td>

</tr>

<td>no filter</td>

</tr>

</table>

</doc:source>

<doc:scenario>

it('should linkify the snippet with urls', function() {

expect(using('#linky-filter').binding('snippet | linky')).

toBe('Pretty text with some links:
' +

'<a href="http://angularjs.org/">http://angularjs.org/</a>,
' +

'<a href="mailto:us@somewhere.org">us@somewhere.org</a>,
' +

'<a href="mailto:another@somewhere.org">another@somewhere.org</a>,
' +

'and one more: <a href="ftp://127.0.0.1/">ftp://127.0.0.1/</a>.');

});

it ('should not linkify snippet without the linky filter', function() {

expect(using('#escaped-html').binding('snippet')).

toBe("Pretty text with some links:\n" +

"http://angularjs.org/,\n" +

"mailto:us@somewhere.org,\n" +

"another@somewhere.org,\n" +

"and one more: ftp://127.0.0.1/.");

});

it('should update', function() {

input('snippet').enter('new http://link.');

expect(using('#linky-filter').binding('snippet | linky')).

toBe('new <a href="http://link">http://link</a>.');

expect(using('#escaped-html').binding('snippet')).toBe('new http://link.');

});

it('should work with the target property', function() {

expect(using('#linky-target').binding("snippetWithTarget | linky:'_blank'")).

toBe('<a target="_blank" href="http://angularjs.org/">http://angularjs.org/</a>');

});

</doc:scenario>

</doc:example>

angular.module('ngSanitize').filter('linky', ['$sanitize', function($sanitize) {

var LINKY_URL_REGEXP =

/((ftp|https?):\/\/|(mailto:)?[A-Za-z0-9._%+-]+@)\S*[^\s.;,(){}<>]/,

MAILTO_REGEXP = /^mailto:/;

return function(text, target) {

if (!text) return text;

var match;

var raw = text;

var html = [];

var url;

var i;

while ((match = raw.match(LINKY_URL_REGEXP))) {

// We can not end in these as they are sometimes found at the end of the sentence

url = match[0];

// if we did not match ftp/http/mailto then assume mailto

if (match[2] == match[3]) url = 'mailto:' + url;

i = match.index;

addText(raw.substr(0, i));

addLink(url, match[0].replace(MAILTO_REGEXP, ''));

raw = raw.substring(i + match[0].length);

}

addText(raw);

return $sanitize(html.join(''));

function addText(text) {

if (!text) {

return;

}

html.push(sanitizeText(text));

}

function addLink(url, text) {

html.push('<a ');

if (angular.isDefined(target)) {

html.push('target="');

html.push(target);

html.push('" ');

}

html.push('href="');

html.push(url);

html.push('">');

addText(text);

html.push('</a>');

}

};

}]);

})(window, window.angular);

code.angularjs.org/1.2.8/angular-sanitize.js at master · angular/code.angularjs.org · GitHub

Uh oh!

Expand file tree

Breadcrumbs

angular-sanitize.js

Latest commit

History

Breadcrumbs

angular-sanitize.js

File metadata and controls