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

   1 /*
   2  * Copyright (C) 2010 Adam Barth. 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/HTMLSourceTracker.h"
  28
  29 #include "core/html/parser/HTMLTokenizer.h"
  30 #include "wtf/text/StringBuilder.h"
  31
  32 namespace blink {
  33
  34 HTMLSourceTracker::HTMLSourceTracker()
  35     : m_isStarted(false)
  36 {
  37 }
  38
  39 void HTMLSourceTracker::start(SegmentedString& currentInput, HTMLTokenizer* tokenizer, HTMLToken& token)
  40 {
  41     if (token.type() == HTMLToken::Uninitialized && !m_isStarted) {
  42         m_previousSource.clear();
  43         if (tokenizer->numberOfBufferedCharacters())
  44             m_previousSource = tokenizer->bufferedCharacters();
  45     } else
  46         m_previousSource.append(m_currentSource);
  47
  48     m_isStarted = true;
  49     m_currentSource = currentInput;
  50     token.setBaseOffset(m_currentSource.numberOfCharactersConsumed() - m_previousSource.length());
  51 }
  52
  53 void HTMLSourceTracker::end(SegmentedString& currentInput, HTMLTokenizer* tokenizer, HTMLToken& token)
  54 {
  55     m_isStarted = false;
  56
  57     m_cachedSourceForToken = String();
  58
  59     // FIXME: This work should really be done by the HTMLTokenizer.
  60     token.end(currentInput.numberOfCharactersConsumed() - tokenizer->numberOfBufferedCharacters());
  61 }
  62
  63 String HTMLSourceTracker::sourceForToken(const HTMLToken& token)
  64 {
  65     if (!m_cachedSourceForToken.isEmpty())
  66         return m_cachedSourceForToken;
  67
  68     size_t length;
  69     if (token.type() == HTMLToken::EndOfFile) {
  70         // Consume the remainder of the input, omitting the null character we use to mark the end of the file.
  71         length = m_previousSource.length() + m_currentSource.length() - 1;
  72     } else {
  73         ASSERT(!token.startIndex());
  74         length = static_cast<size_t>(token.endIndex() - token.startIndex());
  75     }
  76
  77     StringBuilder source;
  78     source.reserveCapacity(length);
  79
  80     size_t i = 0;
  81     for ( ; i < length && !m_previousSource.isEmpty(); ++i) {
  82         source.append(m_previousSource.currentChar());
  83         m_previousSource.advance();
  84     }
  85     for ( ; i < length; ++i) {
  86         ASSERT(!m_currentSource.isEmpty());
  87         source.append(m_currentSource.currentChar());
  88         m_currentSource.advance();
  89     }
  90
  91     m_cachedSourceForToken = source.toString();
  92     return m_cachedSourceForToken;
  93 }
  94
  95 }