Home | History | Annotate | Download | only in parser 
      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 COMPUTER, 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 COMPUTER, INC. OR
     17  * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
     18  * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
     19  * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
     20  * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
     21  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
     22  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
     23  */
     24 
     25 #include "config.h"
     26 #include "TextDocumentParser.h"
     27 
     28 #include "HTMLDocument.h"
     29 #include "HTMLNames.h"
     30 #include "HTMLTokenizer.h"
     31 #include "HTMLTreeBuilder.h"
     32 
     33 namespace WebCore {
     34 
     35 using namespace HTMLNames;
     36 
     37 TextDocumentParser::TextDocumentParser(HTMLDocument* document)
     38     : HTMLDocumentParser(document, false)
     39     , m_haveInsertedFakePreElement(false)
     40 {
     41     tokenizer()->setState(HTMLTokenizer::PLAINTEXTState);
     42 }
     43 
     44 TextDocumentParser::~TextDocumentParser()
     45 {
     46 }
     47 
     48 void TextDocumentParser::append(const SegmentedString& text)
     49 {
     50     if (!m_haveInsertedFakePreElement)
     51         insertFakePreElement();
     52     HTMLDocumentParser::append(text);
     53 }
     54 
     55 void TextDocumentParser::insertFakePreElement()
     56 {
     57     // In principle, we should create a specialized tree builder for
     58     // TextDocuments, but instead we re-use the existing HTMLTreeBuilder.
     59     // We create a fake token and give it to the tree builder rather than
     60     // sending fake bytes through the front-end of the parser to avoid
     61     // distrubing the line/column number calculations.
     62 
     63     RefPtr<Attribute> styleAttribute = Attribute::createMapped("style", "word-wrap: break-word; white-space: pre-wrap;");
     64     RefPtr<NamedNodeMap> attributes = NamedNodeMap::create();
     65     attributes->insertAttribute(styleAttribute.release(), false);
     66     AtomicHTMLToken fakePre(HTMLToken::StartTag, preTag.localName(), attributes.release());
     67 
     68     treeBuilder()->constructTreeFromAtomicToken(fakePre);
     69     m_haveInsertedFakePreElement = true;
     70 }
     71 
     72 }
     73