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
|
/*
* Copyright (C) 2000 Peter Kelly (pmk@post.com)
* Copyright (C) 2005, 2006, 2008 Apple Inc. All rights reserved.
* Copyright (C) 2006 Alexey Proskuryakov (ap@webkit.org)
* Copyright (C) 2007 Samuel Weinig (sam@webkit.org)
* Copyright (C) 2008 Nokia Corporation and/or its subsidiary(-ies)
* Copyright (C) 2008 Holger Hans Peter Freyther
* Copyright (C) 2008 Torch Mobile Inc. All rights reserved. (http://www.torchmobile.com/)
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Library General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Library General Public License for more details.
*
* You should have received a copy of the GNU Library General Public License
* along with this library; see the file COPYING.LIB. If not, write to
* the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
* Boston, MA 02110-1301, USA.
*/
#include "config.h"
#include "XMLDocumentParser.h"
#include "CDATASection.h"
#include "CachedScript.h"
#include "Comment.h"
#include "CachedResourceLoader.h"
#include "Document.h"
#include "DocumentFragment.h"
#include "DocumentType.h"
#include "Frame.h"
#include "FrameLoader.h"
#include "FrameView.h"
#include "HTMLLinkElement.h"
#include "HTMLNames.h"
#include "HTMLStyleElement.h"
#include "ImageLoader.h"
#include "ProcessingInstruction.h"
#include "ResourceError.h"
#include "ResourceRequest.h"
#include "ResourceResponse.h"
#include "ScriptElement.h"
#include "ScriptSourceCode.h"
#include "ScriptValue.h"
#include "TextResourceDecoder.h"
#include "TreeDepthLimit.h"
#include "XMLErrors.h"
#include <wtf/StringExtras.h>
#include <wtf/Threading.h>
#include <wtf/Vector.h>
#if ENABLE(SVG)
#include "SVGNames.h"
#include "SVGStyleElement.h"
#endif
using namespace std;
namespace WebCore {
using namespace HTMLNames;
void XMLDocumentParser::pushCurrentNode(ContainerNode* n)
{
ASSERT(n);
ASSERT(m_currentNode);
if (n != document())
n->ref();
m_currentNodeStack.append(m_currentNode);
m_currentNode = n;
if (m_currentNodeStack.size() > maxDOMTreeDepth)
handleError(XMLErrors::fatal, "Excessive node nesting.", textPosition());
}
void XMLDocumentParser::popCurrentNode()
{
if (!m_currentNode)
return;
ASSERT(m_currentNodeStack.size());
if (m_currentNode != document())
m_currentNode->deref();
m_currentNode = m_currentNodeStack.last();
m_currentNodeStack.removeLast();
}
void XMLDocumentParser::clearCurrentNodeStack()
{
if (m_currentNode && m_currentNode != document())
m_currentNode->deref();
m_currentNode = 0;
m_leafTextNode = 0;
if (m_currentNodeStack.size()) { // Aborted parsing.
for (size_t i = m_currentNodeStack.size() - 1; i != 0; --i)
m_currentNodeStack[i]->deref();
if (m_currentNodeStack[0] && m_currentNodeStack[0] != document())
m_currentNodeStack[0]->deref();
m_currentNodeStack.clear();
}
}
void XMLDocumentParser::insert(const SegmentedString&)
{
ASSERT_NOT_REACHED();
}
void XMLDocumentParser::append(PassRefPtr<StringImpl> inputSource)
{
SegmentedString source(inputSource);
if (m_sawXSLTransform || !m_sawFirstElement)
m_originalSourceForTransform.append(source);
if (isStopped() || m_sawXSLTransform)
return;
if (m_parserPaused) {
m_pendingSrc.append(source);
return;
}
doWrite(source.toString());
// After parsing, go ahead and dispatch image beforeload events.
ImageLoader::dispatchPendingBeforeLoadEvents();
}
void XMLDocumentParser::handleError(XMLErrors::ErrorType type, const char* m, TextPosition position)
{
m_xmlErrors.handleError(type, m, position);
if (type != XMLErrors::warning)
m_sawError = true;
if (type == XMLErrors::fatal)
stopParsing();
}
void XMLDocumentParser::enterText()
{
#if !USE(QXMLSTREAM)
ASSERT(m_bufferedText.size() == 0);
#endif
ASSERT(!m_leafTextNode);
m_leafTextNode = Text::create(m_currentNode->document(), "");
m_currentNode->parserAppendChild(m_leafTextNode.get());
}
#if !USE(QXMLSTREAM)
static inline String toString(const xmlChar* string, size_t size)
{
return String::fromUTF8(reinterpret_cast<const char*>(string), size);
}
#endif
void XMLDocumentParser::exitText()
{
if (isStopped())
return;
if (!m_leafTextNode)
return;
#if !USE(QXMLSTREAM)
m_leafTextNode->appendData(toString(m_bufferedText.data(), m_bufferedText.size()), IGNORE_EXCEPTION);
Vector<xmlChar> empty;
m_bufferedText.swap(empty);
#endif
if (m_view && m_leafTextNode->parentNode() && m_leafTextNode->parentNode()->attached()
&& !m_leafTextNode->attached())
m_leafTextNode->attach();
m_leafTextNode = 0;
}
void XMLDocumentParser::detach()
{
clearCurrentNodeStack();
ScriptableDocumentParser::detach();
}
void XMLDocumentParser::end()
{
// XMLDocumentParserLibxml2 will do bad things to the document if doEnd() is called.
// I don't believe XMLDocumentParserQt needs doEnd called in the fragment case.
ASSERT(!m_parsingFragment);
doEnd();
// doEnd() call above can detach the parser and null out its document.
// In that case, we just bail out.
if (isDetached())
return;
// doEnd() could process a script tag, thus pausing parsing.
if (m_parserPaused)
return;
if (m_sawError)
insertErrorMessageBlock();
else {
exitText();
document()->styleResolverChanged(RecalcStyleImmediately);
}
if (isParsing())
prepareToStopParsing();
document()->setReadyState(Document::Interactive);
clearCurrentNodeStack();
document()->finishedParsing();
}
void XMLDocumentParser::finish()
{
// FIXME: We should ASSERT(!m_parserStopped) here, since it does not
// makes sense to call any methods on DocumentParser once it's been stopped.
// However, FrameLoader::stop calls DocumentParser::finish unconditionally.
if (m_parserPaused)
m_finishCalled = true;
else
end();
}
void XMLDocumentParser::insertErrorMessageBlock()
{
#if USE(QXMLSTREAM)
if (m_parsingFragment)
return;
#endif
m_xmlErrors.insertErrorMessageBlock();
}
void XMLDocumentParser::notifyFinished(CachedResource* unusedResource)
{
ASSERT_UNUSED(unusedResource, unusedResource == m_pendingScript);
ASSERT(m_pendingScript->accessCount() > 0);
ScriptSourceCode sourceCode(m_pendingScript.get());
bool errorOccurred = m_pendingScript->errorOccurred();
bool wasCanceled = m_pendingScript->wasCanceled();
m_pendingScript->removeClient(this);
m_pendingScript = 0;
RefPtr<Element> e = m_scriptElement;
m_scriptElement = 0;
ScriptElement* scriptElement = toScriptElementIfPossible(e.get());
ASSERT(scriptElement);
// JavaScript can detach this parser, make sure it's kept alive even if detached.
RefPtr<XMLDocumentParser> protect(this);
if (errorOccurred)
scriptElement->dispatchErrorEvent();
else if (!wasCanceled) {
scriptElement->executeScript(sourceCode);
scriptElement->dispatchLoadEvent();
}
m_scriptElement = 0;
if (!isDetached() && !m_requestingScript)
resumeParsing();
}
bool XMLDocumentParser::isWaitingForScripts() const
{
return m_pendingScript;
}
void XMLDocumentParser::pauseParsing()
{
if (m_parsingFragment)
return;
m_parserPaused = true;
}
bool XMLDocumentParser::parseDocumentFragment(const String& chunk, DocumentFragment* fragment, Element* contextElement, ParserContentPolicy parserContentPolicy)
{
if (!chunk.length())
return true;
// FIXME: We need to implement the HTML5 XML Fragment parsing algorithm:
// http://www.whatwg.org/specs/web-apps/current-work/multipage/the-xhtml-syntax.html#xml-fragment-parsing-algorithm
// For now we have a hack for script/style innerHTML support:
if (contextElement && (contextElement->hasLocalName(HTMLNames::scriptTag) || contextElement->hasLocalName(HTMLNames::styleTag))) {
fragment->parserAppendChild(fragment->document()->createTextNode(chunk));
return true;
}
RefPtr<XMLDocumentParser> parser = XMLDocumentParser::create(fragment, contextElement, parserContentPolicy);
bool wellFormed = parser->appendFragmentSource(chunk);
// Do not call finish(). Current finish() and doEnd() implementations touch the main Document/loader
// and can cause crashes in the fragment case.
parser->detach(); // Allows ~DocumentParser to assert it was detached before destruction.
return wellFormed; // appendFragmentSource()'s wellFormed is more permissive than wellFormed().
}
} // namespace WebCore
|