third_party/WebKit/Source/core/html/parser/HTMLViewSourceParser.cpp

   1 /*
   2  * Copyright (C) 2010 Google, Inc. All Rights Reserved.
   3  *
   4  * Redistribution and use in source and binary forms, with or without
   5  * modification, are permitted provided that the following conditions
   6  * are met:
   7  * 1. Redistributions of source code must retain the above copyright
   8  *    notice, this list of conditions and the following disclaimer.
   9  * 2. Redistributions in binary form must reproduce the above copyright
  10  *    notice, this list of conditions and the following disclaimer in the
  11  *    documentation and/or other materials provided with the distribution.
  12  *
  13  * THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY
  14  * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  15  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
  16  * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL APPLE INC. OR
  17  * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
  18  * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
  19  * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
  20  * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
  21  * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  22  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  23  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  24  */
  25
  26 #include "config.h"
  27 #include "core/html/parser/HTMLViewSourceParser.h"
  28
  29 #include "core/dom/DOMImplementation.h"
  30 #include "core/html/parser/HTMLParserIdioms.h"
  31 #include "core/html/parser/HTMLParserOptions.h"
  32 #include "core/html/parser/HTMLToken.h"
  33 #include "core/html/parser/XSSAuditorDelegate.h"
  34
  35 namespace blink {
  36
  37 HTMLViewSourceParser::HTMLViewSourceParser(HTMLViewSourceDocument& document, const String& mimeType)
  38     : DecodedDataDocumentParser(document)
  39     , m_tokenizer(HTMLTokenizer::create(HTMLParserOptions(&document)))
  40 {
  41     if (mimeType != "text/html" && !DOMImplementation::isXMLMIMEType(mimeType))
  42         m_tokenizer->setState(HTMLTokenizer::PLAINTEXTState);
  43 }
  44
  45 void HTMLViewSourceParser::pumpTokenizer()
  46 {
  47     m_xssAuditor.init(document(), 0);
  48
  49     while (true) {
  50         m_sourceTracker.start(m_input.current(), m_tokenizer.get(), m_token);
  51         if (!m_tokenizer->nextToken(m_input.current(), m_token))
  52             return;
  53         m_sourceTracker.end(m_input.current(), m_tokenizer.get(), m_token);
  54
  55         OwnPtr<XSSInfo> xssInfo = m_xssAuditor.filterToken(FilterTokenRequest(m_token, m_sourceTracker, m_tokenizer->shouldAllowCDATA()));
  56         HTMLViewSourceDocument::SourceAnnotation annotation = xssInfo ? HTMLViewSourceDocument::AnnotateSourceAsXSS : HTMLViewSourceDocument::AnnotateSourceAsSafe;
  57         document()->addSource(m_sourceTracker.sourceForToken(m_token), m_token, annotation);
  58
  59         // FIXME: The tokenizer should do this work for us.
  60         if (m_token.type() == HTMLToken::StartTag)
  61             m_tokenizer->updateStateFor(attemptStaticStringCreation(m_token.name(), Likely8Bit));
  62         m_token.clear();
  63     }
  64 }
  65
  66 void HTMLViewSourceParser::append(const String& input)
  67 {
  68     m_input.appendToEnd(input);
  69     pumpTokenizer();
  70 }
  71
  72 void HTMLViewSourceParser::finish()
  73 {
  74     if (!m_input.haveSeenEndOfFile())
  75         m_input.markEndOfFile();
  76     pumpTokenizer();
  77     document()->finishedParsing();
  78 }
  79
  80 }