DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Header

Mercurial (a3f183201f7f)

VCS Links

Line Code
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482
/* -*- Mode: C++; tab-width: 8; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* vim: set ts=8 sts=2 et sw=2 tw=80: */
/* This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/. */

#include "mozilla/dom/DOMParser.h"

#include "nsIDOMDocument.h"
#include "nsNetUtil.h"
#include "nsIStreamListener.h"
#include "nsStringStream.h"
#include "nsIScriptError.h"
#include "nsIScriptSecurityManager.h"
#include "nsCRT.h"
#include "nsStreamUtils.h"
#include "nsContentUtils.h"
#include "nsDOMJSUtils.h"
#include "nsError.h"
#include "nsPIDOMWindow.h"
#include "NullPrincipal.h"
#include "mozilla/LoadInfo.h"
#include "mozilla/dom/BindingUtils.h"
#include "mozilla/dom/ScriptSettings.h"

using namespace mozilla;
using namespace mozilla::dom;

DOMParser::DOMParser()
  : mAttemptedInit(false)
  , mOriginalPrincipalWasSystem(false)
{
}

DOMParser::~DOMParser()
{
}

// QueryInterface implementation for DOMParser
NS_INTERFACE_MAP_BEGIN_CYCLE_COLLECTION(DOMParser)
  NS_WRAPPERCACHE_INTERFACE_MAP_ENTRY
  NS_INTERFACE_MAP_ENTRY_AMBIGUOUS(nsISupports, nsIDOMParser)
  NS_INTERFACE_MAP_ENTRY(nsIDOMParser)
  NS_INTERFACE_MAP_ENTRY(nsISupportsWeakReference)
NS_INTERFACE_MAP_END

NS_IMPL_CYCLE_COLLECTION_WRAPPERCACHE(DOMParser, mOwner)

NS_IMPL_CYCLE_COLLECTING_ADDREF(DOMParser)
NS_IMPL_CYCLE_COLLECTING_RELEASE(DOMParser)

static const char*
StringFromSupportedType(SupportedType aType)
{
  return SupportedTypeValues::strings[static_cast<int>(aType)].value;
}

already_AddRefed<nsIDocument>
DOMParser::ParseFromString(const nsAString& aStr, SupportedType aType,
                           ErrorResult& rv)
{
  nsCOMPtr<nsIDOMDocument> domDocument;
  rv = ParseFromString(aStr,
                       StringFromSupportedType(aType),
                       getter_AddRefs(domDocument));
  nsCOMPtr<nsIDocument> document(do_QueryInterface(domDocument));
  return document.forget();
}

NS_IMETHODIMP
DOMParser::ParseFromString(const char16_t *str,
                           const char *contentType,
                           nsIDOMDocument **aResult)
{
  NS_ENSURE_ARG(str);
  // Converting a string to an enum value manually is a bit of a pain,
  // so let's just use a helper that takes a content-type string.
  return ParseFromString(nsDependentString(str), contentType, aResult);
}

nsresult
DOMParser::ParseFromString(const nsAString& str,
                           const char *contentType,
                           nsIDOMDocument **aResult)
{
  NS_ENSURE_ARG_POINTER(aResult);

  nsresult rv;

  if (!nsCRT::strcmp(contentType, "text/html")) {
    nsCOMPtr<nsIDOMDocument> domDocument;
    rv = SetUpDocument(DocumentFlavorHTML, getter_AddRefs(domDocument));
    NS_ENSURE_SUCCESS(rv, rv);
    nsCOMPtr<nsIDocument> document = do_QueryInterface(domDocument);

    // Keep the XULXBL state in sync with the XML case.

    if (mOriginalPrincipalWasSystem) {
      document->ForceEnableXULXBL();
    }

    rv = nsContentUtils::ParseDocumentHTML(str, document, false);
    NS_ENSURE_SUCCESS(rv, rv);

    domDocument.forget(aResult);
    return rv;
  }

  nsAutoCString utf8str;
  // Convert from UTF16 to UTF8 using fallible allocations
  if (!AppendUTF16toUTF8(str, utf8str, mozilla::fallible)) {
    return NS_ERROR_OUT_OF_MEMORY;
  }

  // The new stream holds a reference to the buffer
  nsCOMPtr<nsIInputStream> stream;
  rv = NS_NewByteInputStream(getter_AddRefs(stream),
                             utf8str.get(), utf8str.Length(),
                             NS_ASSIGNMENT_DEPEND);
  if (NS_FAILED(rv))
    return rv;

  return ParseFromStream(stream, "UTF-8", utf8str.Length(), contentType, aResult);
}

already_AddRefed<nsIDocument>
DOMParser::ParseFromBuffer(const Sequence<uint8_t>& aBuf, uint32_t aBufLen,
                           SupportedType aType, ErrorResult& rv)
{
  if (aBufLen > aBuf.Length()) {
    rv.Throw(NS_ERROR_XPC_NOT_ENOUGH_ELEMENTS_IN_ARRAY);
    return nullptr;
  }
  nsCOMPtr<nsIDOMDocument> domDocument;
  rv = DOMParser::ParseFromBuffer(aBuf.Elements(), aBufLen,
                                  StringFromSupportedType(aType),
                                  getter_AddRefs(domDocument));
  nsCOMPtr<nsIDocument> document(do_QueryInterface(domDocument));
  return document.forget();
}

already_AddRefed<nsIDocument>
DOMParser::ParseFromBuffer(const Uint8Array& aBuf, uint32_t aBufLen,
                           SupportedType aType, ErrorResult& rv)
{
  aBuf.ComputeLengthAndData();

  if (aBufLen > aBuf.Length()) {
    rv.Throw(NS_ERROR_XPC_NOT_ENOUGH_ELEMENTS_IN_ARRAY);
    return nullptr;
  }
  nsCOMPtr<nsIDOMDocument> domDocument;
  rv = DOMParser::ParseFromBuffer(aBuf.Data(), aBufLen,
                                    StringFromSupportedType(aType),
                                    getter_AddRefs(domDocument));
  nsCOMPtr<nsIDocument> document(do_QueryInterface(domDocument));
  return document.forget();
}

NS_IMETHODIMP
DOMParser::ParseFromBuffer(const uint8_t *buf,
                           uint32_t bufLen,
                           const char *contentType,
                           nsIDOMDocument **aResult)
{
  NS_ENSURE_ARG_POINTER(buf);
  NS_ENSURE_ARG_POINTER(aResult);

  // The new stream holds a reference to the buffer
  nsCOMPtr<nsIInputStream> stream;
  nsresult rv = NS_NewByteInputStream(getter_AddRefs(stream),
                                      reinterpret_cast<const char *>(buf),
                                      bufLen, NS_ASSIGNMENT_DEPEND);
  if (NS_FAILED(rv))
    return rv;

  return ParseFromStream(stream, nullptr, bufLen, contentType, aResult);
}


already_AddRefed<nsIDocument>
DOMParser::ParseFromStream(nsIInputStream* aStream,
                           const nsAString& aCharset,
                           int32_t aContentLength,
                           SupportedType aType,
                           ErrorResult& rv)
{
  nsCOMPtr<nsIDOMDocument> domDocument;
  rv = DOMParser::ParseFromStream(aStream,
                                  NS_ConvertUTF16toUTF8(aCharset).get(),
                                  aContentLength,
                                  StringFromSupportedType(aType),
                                  getter_AddRefs(domDocument));
  nsCOMPtr<nsIDocument> document(do_QueryInterface(domDocument));
  return document.forget();
}

NS_IMETHODIMP
DOMParser::ParseFromStream(nsIInputStream* aStream,
                           const char* aCharset,
                           int32_t aContentLength,
                           const char* aContentType,
                           nsIDOMDocument** aResult)
{
  NS_ENSURE_ARG(aStream);
  NS_ENSURE_ARG(aContentType);
  NS_ENSURE_ARG_POINTER(aResult);
  *aResult = nullptr;

  bool svg = nsCRT::strcmp(aContentType, "image/svg+xml") == 0;

  // For now, we can only create XML documents.
  //XXXsmaug Should we create an HTMLDocument (in XHTML mode)
  //         for "application/xhtml+xml"?
  if ((nsCRT::strcmp(aContentType, "text/xml") != 0) &&
      (nsCRT::strcmp(aContentType, "application/xml") != 0) &&
      (nsCRT::strcmp(aContentType, "application/xhtml+xml") != 0) &&
      !svg)
    return NS_ERROR_NOT_IMPLEMENTED;

  nsresult rv;

  // Put the nsCOMPtr out here so we hold a ref to the stream as needed
  nsCOMPtr<nsIInputStream> stream = aStream;
  if (!NS_InputStreamIsBuffered(stream)) {
    nsCOMPtr<nsIInputStream> bufferedStream;
    rv = NS_NewBufferedInputStream(getter_AddRefs(bufferedStream),
                                   stream.forget(), 4096);
    NS_ENSURE_SUCCESS(rv, rv);

    stream = bufferedStream;
  }

  nsCOMPtr<nsIDOMDocument> domDocument;
  rv = SetUpDocument(svg ? DocumentFlavorSVG : DocumentFlavorLegacyGuess,
                     getter_AddRefs(domDocument));
  NS_ENSURE_SUCCESS(rv, rv);

  // Create a fake channel
  nsCOMPtr<nsIChannel> parserChannel;
  NS_NewInputStreamChannel(getter_AddRefs(parserChannel),
                           mDocumentURI,
                           nullptr, // aStream
                           mPrincipal,
                           nsILoadInfo::SEC_FORCE_INHERIT_PRINCIPAL,
                           nsIContentPolicy::TYPE_OTHER,
                           nsDependentCString(aContentType));
  NS_ENSURE_STATE(parserChannel);

  if (aCharset) {
    parserChannel->SetContentCharset(nsDependentCString(aCharset));
  }

  // Tell the document to start loading
  nsCOMPtr<nsIStreamListener> listener;

  // Have to pass false for reset here, else the reset will remove
  // our event listener.  Should that listener addition move to later
  // than this call?
  nsCOMPtr<nsIDocument> document(do_QueryInterface(domDocument));
  if (!document) return NS_ERROR_FAILURE;

  // Keep the XULXBL state in sync with the HTML case

  if (mOriginalPrincipalWasSystem) {
    document->ForceEnableXULXBL();
  }

  rv = document->StartDocumentLoad(kLoadAsData, parserChannel,
                                   nullptr, nullptr,
                                   getter_AddRefs(listener),
                                   false);

  if (NS_FAILED(rv) || !listener) {
    return NS_ERROR_FAILURE;
  }

  // Now start pumping data to the listener
  nsresult status;

  rv = listener->OnStartRequest(parserChannel, nullptr);
  if (NS_FAILED(rv))
    parserChannel->Cancel(rv);
  parserChannel->GetStatus(&status);

  if (NS_SUCCEEDED(rv) && NS_SUCCEEDED(status)) {
    rv = listener->OnDataAvailable(parserChannel, nullptr, stream, 0,
                                   aContentLength);
    if (NS_FAILED(rv))
      parserChannel->Cancel(rv);
    parserChannel->GetStatus(&status);
  }

  rv = listener->OnStopRequest(parserChannel, nullptr, status);
  // Failure returned from OnStopRequest does not affect the final status of
  // the channel, so we do not need to call Cancel(rv) as we do above.

  if (NS_FAILED(rv)) {
    return NS_ERROR_FAILURE;
  }

  domDocument.swap(*aResult);

  return NS_OK;
}

NS_IMETHODIMP
DOMParser::Init(nsIPrincipal* principal, nsIURI* documentURI,
                nsIURI* baseURI, nsIGlobalObject* aScriptObject)
{
  NS_ENSURE_STATE(!mAttemptedInit);
  mAttemptedInit = true;
  NS_ENSURE_ARG(principal || documentURI);
  mDocumentURI = documentURI;

  if (!mDocumentURI) {
    principal->GetURI(getter_AddRefs(mDocumentURI));
    // If we have the system principal, then we'll just use the null principals
    // uri.
    if (!mDocumentURI && !nsContentUtils::IsSystemPrincipal(principal)) {
      return NS_ERROR_INVALID_ARG;
    }
  }

  mScriptHandlingObject = do_GetWeakReference(aScriptObject);
  mPrincipal = principal;
  nsresult rv;
  if (!mPrincipal) {
    // BUG 1237080 -- in this case we're getting a chrome privilege scripted
    // DOMParser object creation without an explicit principal set.  This is
    // now deprecated.
    nsContentUtils::ReportToConsole(nsIScriptError::warningFlag,
                                    NS_LITERAL_CSTRING("DOM"),
                                    nullptr,
                                    nsContentUtils::eDOM_PROPERTIES,
                                    "ChromeScriptedDOMParserWithoutPrincipal",
                                    nullptr,
                                    0,
                                    documentURI);

    OriginAttributes attrs;
    mPrincipal = BasePrincipal::CreateCodebasePrincipal(mDocumentURI, attrs);
    NS_ENSURE_TRUE(mPrincipal, NS_ERROR_FAILURE);
  } else {
    if (nsContentUtils::IsSystemPrincipal(mPrincipal)) {
      // Don't give DOMParsers the system principal.  Use a null
      // principal instead.
      mOriginalPrincipalWasSystem = true;
      mPrincipal = NullPrincipal::Create();

      if (!mDocumentURI) {
        rv = mPrincipal->GetURI(getter_AddRefs(mDocumentURI));
        NS_ENSURE_SUCCESS(rv, rv);
      }
    }
  }

  mBaseURI = baseURI;

  MOZ_ASSERT(mPrincipal, "Must have principal");
  MOZ_ASSERT(mDocumentURI, "Must have document URI");
  return NS_OK;
}

/*static */already_AddRefed<DOMParser>
DOMParser::Constructor(const GlobalObject& aOwner,
                       nsIPrincipal* aPrincipal, nsIURI* aDocumentURI,
                       nsIURI* aBaseURI, ErrorResult& rv)
{
  if (aOwner.CallerType() != CallerType::System) {
    rv.Throw(NS_ERROR_DOM_SECURITY_ERR);
    return nullptr;
  }
  RefPtr<DOMParser> domParser = new DOMParser(aOwner.GetAsSupports());
  rv = domParser->InitInternal(aOwner.GetAsSupports(), aPrincipal, aDocumentURI,
                               aBaseURI);
  if (rv.Failed()) {
    return nullptr;
  }
  return domParser.forget();
}

/*static */already_AddRefed<DOMParser>
DOMParser::Constructor(const GlobalObject& aOwner,
                       ErrorResult& rv)
{
  RefPtr<DOMParser> domParser = new DOMParser(aOwner.GetAsSupports());
  rv = domParser->InitInternal(aOwner.GetAsSupports(),
                               nsContentUtils::SubjectPrincipal(),
                               nullptr, nullptr);
  if (rv.Failed()) {
    return nullptr;
  }
  return domParser.forget();
}

nsresult
DOMParser::InitInternal(nsISupports* aOwner, nsIPrincipal* prin,
                        nsIURI* documentURI, nsIURI* baseURI)
{
  AttemptedInitMarker marker(&mAttemptedInit);
  if (!documentURI) {
    // No explicit documentURI; grab document and base URIs off the window our
    // constructor was called on. Error out if anything untoward happens.

    // Note that this is a behavior change as far as I can tell -- we're now
    // using the base URI and document URI of the window off of which the
    // DOMParser is created, not the window in which parse*() is called.
    // Does that matter?

    // Also note that |cx| matches what GetDocumentFromContext() would return,
    // while GetDocumentFromCaller() gives us the window that the DOMParser()
    // call was made on.

    nsCOMPtr<nsPIDOMWindowInner> window = do_QueryInterface(aOwner);
    if (!window) {
      return NS_ERROR_UNEXPECTED;
    }

    baseURI = window->GetDocBaseURI();
    documentURI = window->GetDocumentURI();
    if (!documentURI) {
      return NS_ERROR_UNEXPECTED;
    }
  }

  nsCOMPtr<nsIGlobalObject> scriptglobal = do_QueryInterface(aOwner);
  return Init(prin, documentURI, baseURI, scriptglobal);
}

void
DOMParser::Init(nsIPrincipal* aPrincipal, nsIURI* aDocumentURI,
                nsIURI* aBaseURI, mozilla::ErrorResult& rv)
{
  AttemptedInitMarker marker(&mAttemptedInit);

  nsCOMPtr<nsIPrincipal> principal = aPrincipal;
  if (!principal && !aDocumentURI) {
    principal = nsContentUtils::SubjectPrincipal();
  }

  rv = Init(principal, aDocumentURI, aBaseURI, GetEntryGlobal());
}

nsresult
DOMParser::SetUpDocument(DocumentFlavor aFlavor, nsIDOMDocument** aResult)
{
  // We should really QI to nsIGlobalObject here, but nsDocument gets confused
  // if we pass it a scriptHandlingObject that doesn't QI to
  // nsIScriptGlobalObject, and test_isequalnode.js (an xpcshell test without
  // a window global) breaks. The correct solution is just to wean nsDocument
  // off of nsIScriptGlobalObject, but that's a yak to shave another day.
  nsCOMPtr<nsIScriptGlobalObject> scriptHandlingObject =
    do_QueryReferent(mScriptHandlingObject);
  nsresult rv;
  if (!mPrincipal) {
    NS_ENSURE_TRUE(!mAttemptedInit, NS_ERROR_NOT_INITIALIZED);
    AttemptedInitMarker marker(&mAttemptedInit);

    nsCOMPtr<nsIPrincipal> prin = NullPrincipal::Create();
    rv = Init(prin, nullptr, nullptr, scriptHandlingObject);
    NS_ENSURE_SUCCESS(rv, rv);
  }

  // Try to inherit a style backend.
  auto styleBackend = StyleBackendType::None;
  nsCOMPtr<nsPIDOMWindowInner> window = do_QueryInterface(scriptHandlingObject);
  if (window && window->GetExtantDoc()) {
    styleBackend = window->GetExtantDoc()->GetStyleBackendType();
  }

  NS_ASSERTION(mPrincipal, "Must have principal by now");
  NS_ASSERTION(mDocumentURI, "Must have document URI by now");

  return NS_NewDOMDocument(aResult, EmptyString(), EmptyString(), nullptr,
                           mDocumentURI, mBaseURI,
                           mPrincipal,
                           true,
                           scriptHandlingObject,
                           aFlavor,
                           styleBackend);
}