third_party/WebKit/Source/core/html/parser/TextDocumentParser.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 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 "core/html/parser/TextDocumentParser.h"
  27
  28 #include "core/HTMLNames.h"
  29 #include "core/html/parser/HTMLTreeBuilder.h"
  30 #include "core/html/parser/ParserSynchronizationPolicy.h"
  31
  32 namespace blink {
  33
  34 using namespace HTMLNames;
  35
  36 TextDocumentParser::TextDocumentParser(HTMLDocument& document, ParserSynchronizationPolicy syncPolicy)
  37     : HTMLDocumentParser(document, false, syncPolicy)
  38     , m_haveInsertedFakePreElement(false)
  39 {
  40 }
  41
  42 TextDocumentParser::~TextDocumentParser()
  43 {
  44 }
  45
  46 void TextDocumentParser::appendBytes(const char* data, size_t length)
  47 {
  48     if (!m_haveInsertedFakePreElement)
  49         insertFakePreElement();
  50     HTMLDocumentParser::appendBytes(data, length);
  51 }
  52
  53 void TextDocumentParser::insertFakePreElement()
  54 {
  55     // In principle, we should create a specialized tree builder for
  56     // TextDocuments, but instead we re-use the existing HTMLTreeBuilder.
  57     // We create a fake token and give it to the tree builder rather than
  58     // sending fake bytes through the front-end of the parser to avoid
  59     // distrubing the line/column number calculations.
  60     Vector<Attribute> attributes;
  61     attributes.append(Attribute(styleAttr, "word-wrap: break-word; white-space: pre-wrap;"));
  62     AtomicHTMLToken fakePre(HTMLToken::StartTag, preTag.localName(), attributes);
  63     treeBuilder()->constructTree(&fakePre);
  64
  65     // Normally we would skip the first \n after a <pre> element, but we don't
  66     // want to skip the first \n for text documents!
  67     treeBuilder()->setShouldSkipLeadingNewline(false);
  68
  69     // Although Text Documents expose a "pre" element in their DOM, they
  70     // act like a <plaintext> tag, so we have to force plaintext mode.
  71     forcePlaintextForTextDocument();
  72
  73     m_haveInsertedFakePreElement = true;
  74 }
  75
  76 }